{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 32740, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.0543677458766035e-05, "grad_norm": 0.9461981058120728, "learning_rate": 4.999999988490608e-05, "loss": 4.8674, "step": 1 }, { "epoch": 6.108735491753207e-05, "grad_norm": 3.3696038722991943, "learning_rate": 4.99999995396243e-05, "loss": 4.933, "step": 2 }, { "epoch": 9.163103237629811e-05, "grad_norm": 1.1703721284866333, "learning_rate": 4.999999896415467e-05, "loss": 4.8403, "step": 3 }, { "epoch": 0.00012217470983506414, "grad_norm": 1.0180854797363281, "learning_rate": 4.9999998158497195e-05, "loss": 4.7839, "step": 4 }, { "epoch": 0.00015271838729383018, "grad_norm": 0.815761923789978, "learning_rate": 4.999999712265189e-05, "loss": 4.7976, "step": 5 }, { "epoch": 0.00018326206475259622, "grad_norm": 0.8171932101249695, "learning_rate": 4.999999585661875e-05, "loss": 4.6755, "step": 6 }, { "epoch": 0.00021380574221136224, "grad_norm": 0.7552642226219177, "learning_rate": 4.9999994360397794e-05, "loss": 4.7509, "step": 7 }, { "epoch": 0.0002443494196701283, "grad_norm": 0.7287338376045227, "learning_rate": 4.999999263398904e-05, "loss": 4.7487, "step": 8 }, { "epoch": 0.0002748930971288943, "grad_norm": 0.7503976821899414, "learning_rate": 4.99999906773925e-05, "loss": 4.7602, "step": 9 }, { "epoch": 0.00030543677458766036, "grad_norm": 0.7616397738456726, "learning_rate": 4.999998849060819e-05, "loss": 4.7485, "step": 10 }, { "epoch": 0.0003359804520464264, "grad_norm": 0.6994743347167969, "learning_rate": 4.9999986073636136e-05, "loss": 4.7551, "step": 11 }, { "epoch": 0.00036652412950519245, "grad_norm": 0.8037027716636658, "learning_rate": 4.999998342647635e-05, "loss": 4.7481, "step": 12 }, { "epoch": 0.00039706780696395846, "grad_norm": 0.707435131072998, "learning_rate": 4.9999980549128865e-05, "loss": 4.713, "step": 13 }, { "epoch": 0.0004276114844227245, "grad_norm": 0.7030737996101379, "learning_rate": 4.9999977441593715e-05, "loss": 4.7668, "step": 14 }, { "epoch": 0.00045815516188149055, "grad_norm": 0.6589767932891846, "learning_rate": 4.99999741038709e-05, "loss": 4.7301, "step": 15 }, { "epoch": 0.0004886988393402566, "grad_norm": 0.6508762836456299, "learning_rate": 4.99999705359605e-05, "loss": 4.5374, "step": 16 }, { "epoch": 0.0005192425167990226, "grad_norm": 0.6662896871566772, "learning_rate": 4.999996673786249e-05, "loss": 4.6837, "step": 17 }, { "epoch": 0.0005497861942577886, "grad_norm": 0.7037979960441589, "learning_rate": 4.999996270957694e-05, "loss": 4.7555, "step": 18 }, { "epoch": 0.0005803298717165547, "grad_norm": 0.6596120595932007, "learning_rate": 4.999995845110388e-05, "loss": 4.7312, "step": 19 }, { "epoch": 0.0006108735491753207, "grad_norm": 0.6499984264373779, "learning_rate": 4.9999953962443355e-05, "loss": 4.6493, "step": 20 }, { "epoch": 0.0006414172266340867, "grad_norm": 0.6645963191986084, "learning_rate": 4.999994924359539e-05, "loss": 4.7041, "step": 21 }, { "epoch": 0.0006719609040928528, "grad_norm": 0.6550754904747009, "learning_rate": 4.999994429456004e-05, "loss": 4.6143, "step": 22 }, { "epoch": 0.0007025045815516188, "grad_norm": 0.6950271725654602, "learning_rate": 4.9999939115337355e-05, "loss": 4.5953, "step": 23 }, { "epoch": 0.0007330482590103849, "grad_norm": 0.6537031531333923, "learning_rate": 4.9999933705927374e-05, "loss": 4.6179, "step": 24 }, { "epoch": 0.0007635919364691509, "grad_norm": 0.6444075107574463, "learning_rate": 4.999992806633015e-05, "loss": 4.709, "step": 25 }, { "epoch": 0.0007941356139279169, "grad_norm": 0.6400203704833984, "learning_rate": 4.999992219654574e-05, "loss": 4.6807, "step": 26 }, { "epoch": 0.0008246792913866829, "grad_norm": 0.6349486708641052, "learning_rate": 4.999991609657418e-05, "loss": 4.6982, "step": 27 }, { "epoch": 0.000855222968845449, "grad_norm": 0.6281805634498596, "learning_rate": 4.9999909766415557e-05, "loss": 4.6147, "step": 28 }, { "epoch": 0.0008857666463042151, "grad_norm": 0.6181201338768005, "learning_rate": 4.99999032060699e-05, "loss": 4.6941, "step": 29 }, { "epoch": 0.0009163103237629811, "grad_norm": 0.6233382821083069, "learning_rate": 4.999989641553728e-05, "loss": 4.6405, "step": 30 }, { "epoch": 0.0009468540012217471, "grad_norm": 0.6272516846656799, "learning_rate": 4.9999889394817756e-05, "loss": 4.6667, "step": 31 }, { "epoch": 0.0009773976786805131, "grad_norm": 0.6065088510513306, "learning_rate": 4.9999882143911406e-05, "loss": 4.5624, "step": 32 }, { "epoch": 0.0010079413561392791, "grad_norm": 0.6170499920845032, "learning_rate": 4.999987466281828e-05, "loss": 4.6595, "step": 33 }, { "epoch": 0.0010384850335980452, "grad_norm": 0.6528582572937012, "learning_rate": 4.999986695153846e-05, "loss": 4.6848, "step": 34 }, { "epoch": 0.0010690287110568112, "grad_norm": 0.6029648184776306, "learning_rate": 4.999985901007201e-05, "loss": 4.6531, "step": 35 }, { "epoch": 0.0010995723885155772, "grad_norm": 0.6160905361175537, "learning_rate": 4.999985083841901e-05, "loss": 4.6414, "step": 36 }, { "epoch": 0.0011301160659743434, "grad_norm": 0.6008835434913635, "learning_rate": 4.9999842436579514e-05, "loss": 4.6107, "step": 37 }, { "epoch": 0.0011606597434331094, "grad_norm": 0.5997536778450012, "learning_rate": 4.999983380455362e-05, "loss": 4.6488, "step": 38 }, { "epoch": 0.0011912034208918754, "grad_norm": 0.6018967628479004, "learning_rate": 4.9999824942341414e-05, "loss": 4.5413, "step": 39 }, { "epoch": 0.0012217470983506415, "grad_norm": 0.5919588208198547, "learning_rate": 4.9999815849942956e-05, "loss": 4.6662, "step": 40 }, { "epoch": 0.0012522907758094075, "grad_norm": 0.5930258631706238, "learning_rate": 4.999980652735834e-05, "loss": 4.6578, "step": 41 }, { "epoch": 0.0012828344532681735, "grad_norm": 0.6040099859237671, "learning_rate": 4.999979697458766e-05, "loss": 4.64, "step": 42 }, { "epoch": 0.0013133781307269395, "grad_norm": 0.6035155057907104, "learning_rate": 4.9999787191630985e-05, "loss": 4.5989, "step": 43 }, { "epoch": 0.0013439218081857055, "grad_norm": 0.577336847782135, "learning_rate": 4.999977717848842e-05, "loss": 4.5611, "step": 44 }, { "epoch": 0.0013744654856444715, "grad_norm": 0.6061881184577942, "learning_rate": 4.999976693516005e-05, "loss": 4.6585, "step": 45 }, { "epoch": 0.0014050091631032375, "grad_norm": 0.6010106205940247, "learning_rate": 4.999975646164598e-05, "loss": 4.5919, "step": 46 }, { "epoch": 0.0014355528405620036, "grad_norm": 0.6097066402435303, "learning_rate": 4.9999745757946296e-05, "loss": 4.5347, "step": 47 }, { "epoch": 0.0014660965180207698, "grad_norm": 0.5868769288063049, "learning_rate": 4.99997348240611e-05, "loss": 4.6608, "step": 48 }, { "epoch": 0.0014966401954795358, "grad_norm": 0.5834839344024658, "learning_rate": 4.9999723659990486e-05, "loss": 4.6258, "step": 49 }, { "epoch": 0.0015271838729383018, "grad_norm": 0.6195083856582642, "learning_rate": 4.9999712265734566e-05, "loss": 4.6565, "step": 50 }, { "epoch": 0.0015577275503970678, "grad_norm": 0.5833982825279236, "learning_rate": 4.999970064129344e-05, "loss": 4.6316, "step": 51 }, { "epoch": 0.0015882712278558339, "grad_norm": 0.5935212969779968, "learning_rate": 4.999968878666722e-05, "loss": 4.6391, "step": 52 }, { "epoch": 0.0016188149053145999, "grad_norm": 0.5792343616485596, "learning_rate": 4.999967670185601e-05, "loss": 4.7158, "step": 53 }, { "epoch": 0.0016493585827733659, "grad_norm": 0.5948423743247986, "learning_rate": 4.999966438685993e-05, "loss": 4.6322, "step": 54 }, { "epoch": 0.001679902260232132, "grad_norm": 0.577419638633728, "learning_rate": 4.999965184167908e-05, "loss": 4.6484, "step": 55 }, { "epoch": 0.001710445937690898, "grad_norm": 0.6049875020980835, "learning_rate": 4.9999639066313574e-05, "loss": 4.641, "step": 56 }, { "epoch": 0.001740989615149664, "grad_norm": 0.5822872519493103, "learning_rate": 4.999962606076354e-05, "loss": 4.6543, "step": 57 }, { "epoch": 0.0017715332926084302, "grad_norm": 0.5509516596794128, "learning_rate": 4.9999612825029106e-05, "loss": 4.6157, "step": 58 }, { "epoch": 0.0018020769700671962, "grad_norm": 0.5641384124755859, "learning_rate": 4.999959935911037e-05, "loss": 4.5662, "step": 59 }, { "epoch": 0.0018326206475259622, "grad_norm": 0.5743777751922607, "learning_rate": 4.9999585663007484e-05, "loss": 4.7023, "step": 60 }, { "epoch": 0.0018631643249847282, "grad_norm": 0.571131706237793, "learning_rate": 4.999957173672055e-05, "loss": 4.6273, "step": 61 }, { "epoch": 0.0018937080024434942, "grad_norm": 0.5682878494262695, "learning_rate": 4.9999557580249706e-05, "loss": 4.6493, "step": 62 }, { "epoch": 0.0019242516799022602, "grad_norm": 0.5771433711051941, "learning_rate": 4.9999543193595085e-05, "loss": 4.6068, "step": 63 }, { "epoch": 0.0019547953573610262, "grad_norm": 0.5868772268295288, "learning_rate": 4.9999528576756814e-05, "loss": 4.6111, "step": 64 }, { "epoch": 0.0019853390348197925, "grad_norm": 0.5565571188926697, "learning_rate": 4.999951372973503e-05, "loss": 4.5797, "step": 65 }, { "epoch": 0.0020158827122785583, "grad_norm": 0.544167697429657, "learning_rate": 4.999949865252987e-05, "loss": 4.6403, "step": 66 }, { "epoch": 0.0020464263897373245, "grad_norm": 0.555985152721405, "learning_rate": 4.999948334514147e-05, "loss": 4.5244, "step": 67 }, { "epoch": 0.0020769700671960903, "grad_norm": 0.5627229809761047, "learning_rate": 4.999946780756998e-05, "loss": 4.5974, "step": 68 }, { "epoch": 0.0021075137446548565, "grad_norm": 0.5412760376930237, "learning_rate": 4.999945203981553e-05, "loss": 4.5361, "step": 69 }, { "epoch": 0.0021380574221136223, "grad_norm": 0.5498285889625549, "learning_rate": 4.999943604187828e-05, "loss": 4.608, "step": 70 }, { "epoch": 0.0021686010995723886, "grad_norm": 0.5510600209236145, "learning_rate": 4.9999419813758355e-05, "loss": 4.5849, "step": 71 }, { "epoch": 0.0021991447770311544, "grad_norm": 0.5492358803749084, "learning_rate": 4.999940335545593e-05, "loss": 4.5413, "step": 72 }, { "epoch": 0.0022296884544899206, "grad_norm": 0.551906943321228, "learning_rate": 4.999938666697114e-05, "loss": 4.5973, "step": 73 }, { "epoch": 0.002260232131948687, "grad_norm": 0.5714211463928223, "learning_rate": 4.9999369748304145e-05, "loss": 4.5753, "step": 74 }, { "epoch": 0.0022907758094074526, "grad_norm": 0.5656085014343262, "learning_rate": 4.99993525994551e-05, "loss": 4.6195, "step": 75 }, { "epoch": 0.002321319486866219, "grad_norm": 0.554760217666626, "learning_rate": 4.999933522042416e-05, "loss": 4.5891, "step": 76 }, { "epoch": 0.0023518631643249847, "grad_norm": 0.5710964798927307, "learning_rate": 4.9999317611211494e-05, "loss": 4.6632, "step": 77 }, { "epoch": 0.002382406841783751, "grad_norm": 0.5595614314079285, "learning_rate": 4.9999299771817246e-05, "loss": 4.6723, "step": 78 }, { "epoch": 0.0024129505192425167, "grad_norm": 0.5441321134567261, "learning_rate": 4.99992817022416e-05, "loss": 4.5596, "step": 79 }, { "epoch": 0.002443494196701283, "grad_norm": 0.5443785190582275, "learning_rate": 4.9999263402484706e-05, "loss": 4.5579, "step": 80 }, { "epoch": 0.0024740378741600487, "grad_norm": 0.5617441534996033, "learning_rate": 4.999924487254675e-05, "loss": 4.6552, "step": 81 }, { "epoch": 0.002504581551618815, "grad_norm": 0.5523468852043152, "learning_rate": 4.999922611242789e-05, "loss": 4.6831, "step": 82 }, { "epoch": 0.0025351252290775807, "grad_norm": 0.560664176940918, "learning_rate": 4.99992071221283e-05, "loss": 4.6121, "step": 83 }, { "epoch": 0.002565668906536347, "grad_norm": 0.5626385807991028, "learning_rate": 4.999918790164816e-05, "loss": 4.5173, "step": 84 }, { "epoch": 0.002596212583995113, "grad_norm": 0.5412537455558777, "learning_rate": 4.999916845098764e-05, "loss": 4.5533, "step": 85 }, { "epoch": 0.002626756261453879, "grad_norm": 0.5477762222290039, "learning_rate": 4.9999148770146925e-05, "loss": 4.5871, "step": 86 }, { "epoch": 0.0026572999389126452, "grad_norm": 0.5422031879425049, "learning_rate": 4.9999128859126196e-05, "loss": 4.6327, "step": 87 }, { "epoch": 0.002687843616371411, "grad_norm": 0.5437096953392029, "learning_rate": 4.9999108717925626e-05, "loss": 4.5954, "step": 88 }, { "epoch": 0.0027183872938301773, "grad_norm": 0.5415818095207214, "learning_rate": 4.999908834654542e-05, "loss": 4.587, "step": 89 }, { "epoch": 0.002748930971288943, "grad_norm": 0.5352805852890015, "learning_rate": 4.999906774498574e-05, "loss": 4.5531, "step": 90 }, { "epoch": 0.0027794746487477093, "grad_norm": 0.5415881872177124, "learning_rate": 4.9999046913246806e-05, "loss": 4.6621, "step": 91 }, { "epoch": 0.002810018326206475, "grad_norm": 0.5469527244567871, "learning_rate": 4.999902585132878e-05, "loss": 4.6813, "step": 92 }, { "epoch": 0.0028405620036652413, "grad_norm": 0.5460872650146484, "learning_rate": 4.999900455923188e-05, "loss": 4.6337, "step": 93 }, { "epoch": 0.002871105681124007, "grad_norm": 0.5301305055618286, "learning_rate": 4.999898303695629e-05, "loss": 4.5248, "step": 94 }, { "epoch": 0.0029016493585827734, "grad_norm": 0.535185694694519, "learning_rate": 4.999896128450221e-05, "loss": 4.532, "step": 95 }, { "epoch": 0.0029321930360415396, "grad_norm": 0.5482925772666931, "learning_rate": 4.999893930186984e-05, "loss": 4.5795, "step": 96 }, { "epoch": 0.0029627367135003054, "grad_norm": 0.5475911498069763, "learning_rate": 4.9998917089059375e-05, "loss": 4.5619, "step": 97 }, { "epoch": 0.0029932803909590716, "grad_norm": 0.5219764709472656, "learning_rate": 4.999889464607104e-05, "loss": 4.5508, "step": 98 }, { "epoch": 0.0030238240684178374, "grad_norm": 0.5227431058883667, "learning_rate": 4.999887197290501e-05, "loss": 4.5274, "step": 99 }, { "epoch": 0.0030543677458766036, "grad_norm": 0.545891523361206, "learning_rate": 4.999884906956153e-05, "loss": 4.6169, "step": 100 }, { "epoch": 0.0030849114233353694, "grad_norm": 0.5355101823806763, "learning_rate": 4.999882593604079e-05, "loss": 4.5946, "step": 101 }, { "epoch": 0.0031154551007941357, "grad_norm": 0.537729024887085, "learning_rate": 4.999880257234301e-05, "loss": 4.6747, "step": 102 }, { "epoch": 0.0031459987782529015, "grad_norm": 0.5367782711982727, "learning_rate": 4.9998778978468384e-05, "loss": 4.5835, "step": 103 }, { "epoch": 0.0031765424557116677, "grad_norm": 0.5285100936889648, "learning_rate": 4.9998755154417166e-05, "loss": 4.5793, "step": 104 }, { "epoch": 0.003207086133170434, "grad_norm": 0.5392974615097046, "learning_rate": 4.999873110018954e-05, "loss": 4.6651, "step": 105 }, { "epoch": 0.0032376298106291997, "grad_norm": 0.5398030281066895, "learning_rate": 4.9998706815785755e-05, "loss": 4.5978, "step": 106 }, { "epoch": 0.003268173488087966, "grad_norm": 0.5427578687667847, "learning_rate": 4.9998682301206024e-05, "loss": 4.562, "step": 107 }, { "epoch": 0.0032987171655467318, "grad_norm": 0.5269204378128052, "learning_rate": 4.9998657556450565e-05, "loss": 4.6058, "step": 108 }, { "epoch": 0.003329260843005498, "grad_norm": 0.5378360748291016, "learning_rate": 4.999863258151962e-05, "loss": 4.6192, "step": 109 }, { "epoch": 0.003359804520464264, "grad_norm": 0.5296205878257751, "learning_rate": 4.999860737641341e-05, "loss": 4.5856, "step": 110 }, { "epoch": 0.00339034819792303, "grad_norm": 0.5339716076850891, "learning_rate": 4.999858194113217e-05, "loss": 4.556, "step": 111 }, { "epoch": 0.003420891875381796, "grad_norm": 0.5361059904098511, "learning_rate": 4.9998556275676135e-05, "loss": 4.5437, "step": 112 }, { "epoch": 0.003451435552840562, "grad_norm": 0.5306206941604614, "learning_rate": 4.9998530380045524e-05, "loss": 4.5456, "step": 113 }, { "epoch": 0.003481979230299328, "grad_norm": 0.5180391073226929, "learning_rate": 4.999850425424061e-05, "loss": 4.4641, "step": 114 }, { "epoch": 0.003512522907758094, "grad_norm": 0.533701479434967, "learning_rate": 4.999847789826161e-05, "loss": 4.6165, "step": 115 }, { "epoch": 0.0035430665852168603, "grad_norm": 0.5234943628311157, "learning_rate": 4.999845131210876e-05, "loss": 4.4857, "step": 116 }, { "epoch": 0.003573610262675626, "grad_norm": 0.5222747325897217, "learning_rate": 4.999842449578233e-05, "loss": 4.6231, "step": 117 }, { "epoch": 0.0036041539401343923, "grad_norm": 0.5405493974685669, "learning_rate": 4.999839744928254e-05, "loss": 4.5637, "step": 118 }, { "epoch": 0.003634697617593158, "grad_norm": 0.5329803228378296, "learning_rate": 4.999837017260966e-05, "loss": 4.5843, "step": 119 }, { "epoch": 0.0036652412950519244, "grad_norm": 0.5203055739402771, "learning_rate": 4.999834266576393e-05, "loss": 4.6566, "step": 120 }, { "epoch": 0.00369578497251069, "grad_norm": 0.5306685566902161, "learning_rate": 4.99983149287456e-05, "loss": 4.6261, "step": 121 }, { "epoch": 0.0037263286499694564, "grad_norm": 0.5247727632522583, "learning_rate": 4.9998286961554946e-05, "loss": 4.5794, "step": 122 }, { "epoch": 0.003756872327428222, "grad_norm": 0.5016365051269531, "learning_rate": 4.99982587641922e-05, "loss": 4.5733, "step": 123 }, { "epoch": 0.0037874160048869884, "grad_norm": 0.5171604752540588, "learning_rate": 4.9998230336657636e-05, "loss": 4.5668, "step": 124 }, { "epoch": 0.0038179596823457542, "grad_norm": 0.5265522599220276, "learning_rate": 4.999820167895152e-05, "loss": 4.481, "step": 125 }, { "epoch": 0.0038485033598045205, "grad_norm": 0.5187985301017761, "learning_rate": 4.99981727910741e-05, "loss": 4.5746, "step": 126 }, { "epoch": 0.0038790470372632867, "grad_norm": 0.5120770335197449, "learning_rate": 4.999814367302565e-05, "loss": 4.5882, "step": 127 }, { "epoch": 0.0039095907147220525, "grad_norm": 0.5481209754943848, "learning_rate": 4.999811432480644e-05, "loss": 4.6488, "step": 128 }, { "epoch": 0.003940134392180819, "grad_norm": 0.5157997012138367, "learning_rate": 4.999808474641674e-05, "loss": 4.5728, "step": 129 }, { "epoch": 0.003970678069639585, "grad_norm": 0.5177810788154602, "learning_rate": 4.999805493785682e-05, "loss": 4.5661, "step": 130 }, { "epoch": 0.00400122174709835, "grad_norm": 0.5171740055084229, "learning_rate": 4.999802489912695e-05, "loss": 4.6449, "step": 131 }, { "epoch": 0.0040317654245571165, "grad_norm": 0.5271416902542114, "learning_rate": 4.999799463022742e-05, "loss": 4.5944, "step": 132 }, { "epoch": 0.004062309102015883, "grad_norm": 0.5314010381698608, "learning_rate": 4.999796413115849e-05, "loss": 4.4947, "step": 133 }, { "epoch": 0.004092852779474649, "grad_norm": 0.5351556539535522, "learning_rate": 4.999793340192047e-05, "loss": 4.5579, "step": 134 }, { "epoch": 0.004123396456933414, "grad_norm": 0.521051824092865, "learning_rate": 4.999790244251361e-05, "loss": 4.5806, "step": 135 }, { "epoch": 0.004153940134392181, "grad_norm": 0.5300737619400024, "learning_rate": 4.999787125293821e-05, "loss": 4.5407, "step": 136 }, { "epoch": 0.004184483811850947, "grad_norm": 0.5197071433067322, "learning_rate": 4.999783983319456e-05, "loss": 4.5814, "step": 137 }, { "epoch": 0.004215027489309713, "grad_norm": 0.5224230885505676, "learning_rate": 4.999780818328295e-05, "loss": 4.545, "step": 138 }, { "epoch": 0.004245571166768479, "grad_norm": 0.558630108833313, "learning_rate": 4.999777630320366e-05, "loss": 4.6005, "step": 139 }, { "epoch": 0.004276114844227245, "grad_norm": 0.5158746242523193, "learning_rate": 4.9997744192956997e-05, "loss": 4.603, "step": 140 }, { "epoch": 0.004306658521686011, "grad_norm": 0.5282468199729919, "learning_rate": 4.999771185254325e-05, "loss": 4.6019, "step": 141 }, { "epoch": 0.004337202199144777, "grad_norm": 0.5188183188438416, "learning_rate": 4.999767928196272e-05, "loss": 4.6757, "step": 142 }, { "epoch": 0.004367745876603543, "grad_norm": 0.5195818543434143, "learning_rate": 4.999764648121569e-05, "loss": 4.5616, "step": 143 }, { "epoch": 0.004398289554062309, "grad_norm": 0.5057955384254456, "learning_rate": 4.9997613450302494e-05, "loss": 4.6022, "step": 144 }, { "epoch": 0.004428833231521075, "grad_norm": 0.5131983160972595, "learning_rate": 4.99975801892234e-05, "loss": 4.4429, "step": 145 }, { "epoch": 0.004459376908979841, "grad_norm": 0.5238367915153503, "learning_rate": 4.9997546697978746e-05, "loss": 4.5847, "step": 146 }, { "epoch": 0.004489920586438607, "grad_norm": 0.5072973966598511, "learning_rate": 4.9997512976568825e-05, "loss": 4.5623, "step": 147 }, { "epoch": 0.004520464263897374, "grad_norm": 0.5049300193786621, "learning_rate": 4.9997479024993956e-05, "loss": 4.4809, "step": 148 }, { "epoch": 0.004551007941356139, "grad_norm": 0.5325057506561279, "learning_rate": 4.999744484325444e-05, "loss": 4.5634, "step": 149 }, { "epoch": 0.004581551618814905, "grad_norm": 0.5207141637802124, "learning_rate": 4.999741043135059e-05, "loss": 4.5631, "step": 150 }, { "epoch": 0.0046120952962736715, "grad_norm": 0.521955668926239, "learning_rate": 4.999737578928274e-05, "loss": 4.5699, "step": 151 }, { "epoch": 0.004642638973732438, "grad_norm": 0.5085853338241577, "learning_rate": 4.999734091705119e-05, "loss": 4.5094, "step": 152 }, { "epoch": 0.004673182651191203, "grad_norm": 0.5326888561248779, "learning_rate": 4.999730581465627e-05, "loss": 4.562, "step": 153 }, { "epoch": 0.004703726328649969, "grad_norm": 0.5132759213447571, "learning_rate": 4.999727048209831e-05, "loss": 4.5361, "step": 154 }, { "epoch": 0.0047342700061087355, "grad_norm": 0.5114791989326477, "learning_rate": 4.999723491937762e-05, "loss": 4.5325, "step": 155 }, { "epoch": 0.004764813683567502, "grad_norm": 0.521934449672699, "learning_rate": 4.9997199126494545e-05, "loss": 4.5708, "step": 156 }, { "epoch": 0.004795357361026267, "grad_norm": 0.5079047083854675, "learning_rate": 4.99971631034494e-05, "loss": 4.5317, "step": 157 }, { "epoch": 0.004825901038485033, "grad_norm": 0.5306348204612732, "learning_rate": 4.9997126850242525e-05, "loss": 4.6132, "step": 158 }, { "epoch": 0.0048564447159438, "grad_norm": 0.5128415822982788, "learning_rate": 4.999709036687425e-05, "loss": 4.6217, "step": 159 }, { "epoch": 0.004886988393402566, "grad_norm": 0.4988538324832916, "learning_rate": 4.9997053653344906e-05, "loss": 4.6048, "step": 160 }, { "epoch": 0.004917532070861332, "grad_norm": 0.4999312460422516, "learning_rate": 4.999701670965484e-05, "loss": 4.5705, "step": 161 }, { "epoch": 0.004948075748320097, "grad_norm": 0.5049161314964294, "learning_rate": 4.99969795358044e-05, "loss": 4.554, "step": 162 }, { "epoch": 0.004978619425778864, "grad_norm": 0.5122001767158508, "learning_rate": 4.99969421317939e-05, "loss": 4.5409, "step": 163 }, { "epoch": 0.00500916310323763, "grad_norm": 0.5090537667274475, "learning_rate": 4.999690449762371e-05, "loss": 4.612, "step": 164 }, { "epoch": 0.005039706780696396, "grad_norm": 0.5141797065734863, "learning_rate": 4.999686663329417e-05, "loss": 4.5542, "step": 165 }, { "epoch": 0.0050702504581551615, "grad_norm": 0.5111452341079712, "learning_rate": 4.9996828538805625e-05, "loss": 4.5922, "step": 166 }, { "epoch": 0.005100794135613928, "grad_norm": 0.5160804390907288, "learning_rate": 4.999679021415843e-05, "loss": 4.631, "step": 167 }, { "epoch": 0.005131337813072694, "grad_norm": 0.5116831064224243, "learning_rate": 4.9996751659352924e-05, "loss": 4.6072, "step": 168 }, { "epoch": 0.00516188149053146, "grad_norm": 0.5347469449043274, "learning_rate": 4.9996712874389484e-05, "loss": 4.6042, "step": 169 }, { "epoch": 0.005192425167990226, "grad_norm": 0.5111247301101685, "learning_rate": 4.9996673859268455e-05, "loss": 4.5136, "step": 170 }, { "epoch": 0.005222968845448992, "grad_norm": 0.5083816647529602, "learning_rate": 4.9996634613990204e-05, "loss": 4.5873, "step": 171 }, { "epoch": 0.005253512522907758, "grad_norm": 0.5301270484924316, "learning_rate": 4.9996595138555076e-05, "loss": 4.6601, "step": 172 }, { "epoch": 0.005284056200366524, "grad_norm": 0.496581494808197, "learning_rate": 4.9996555432963444e-05, "loss": 4.5237, "step": 173 }, { "epoch": 0.0053145998778252905, "grad_norm": 0.5270989537239075, "learning_rate": 4.999651549721568e-05, "loss": 4.5843, "step": 174 }, { "epoch": 0.005345143555284056, "grad_norm": 0.5217635631561279, "learning_rate": 4.999647533131214e-05, "loss": 4.5775, "step": 175 }, { "epoch": 0.005375687232742822, "grad_norm": 0.5310185551643372, "learning_rate": 4.9996434935253205e-05, "loss": 4.5476, "step": 176 }, { "epoch": 0.005406230910201588, "grad_norm": 0.5135783553123474, "learning_rate": 4.9996394309039244e-05, "loss": 4.5994, "step": 177 }, { "epoch": 0.0054367745876603545, "grad_norm": 0.5140482187271118, "learning_rate": 4.999635345267062e-05, "loss": 4.5965, "step": 178 }, { "epoch": 0.005467318265119121, "grad_norm": 0.50392746925354, "learning_rate": 4.9996312366147725e-05, "loss": 4.6323, "step": 179 }, { "epoch": 0.005497861942577886, "grad_norm": 0.5232574939727783, "learning_rate": 4.999627104947093e-05, "loss": 4.5849, "step": 180 }, { "epoch": 0.005528405620036652, "grad_norm": 0.5076006650924683, "learning_rate": 4.999622950264061e-05, "loss": 4.4503, "step": 181 }, { "epoch": 0.005558949297495419, "grad_norm": 0.5260009169578552, "learning_rate": 4.999618772565716e-05, "loss": 4.5704, "step": 182 }, { "epoch": 0.005589492974954185, "grad_norm": 0.5075931549072266, "learning_rate": 4.9996145718520956e-05, "loss": 4.5754, "step": 183 }, { "epoch": 0.00562003665241295, "grad_norm": 0.5137465000152588, "learning_rate": 4.999610348123238e-05, "loss": 4.6262, "step": 184 }, { "epoch": 0.005650580329871716, "grad_norm": 0.5120919942855835, "learning_rate": 4.999606101379183e-05, "loss": 4.5513, "step": 185 }, { "epoch": 0.005681124007330483, "grad_norm": 0.5034908652305603, "learning_rate": 4.99960183161997e-05, "loss": 4.6291, "step": 186 }, { "epoch": 0.005711667684789249, "grad_norm": 0.5200950503349304, "learning_rate": 4.9995975388456376e-05, "loss": 4.5955, "step": 187 }, { "epoch": 0.005742211362248014, "grad_norm": 0.5070845484733582, "learning_rate": 4.9995932230562254e-05, "loss": 4.5798, "step": 188 }, { "epoch": 0.0057727550397067805, "grad_norm": 0.516202986240387, "learning_rate": 4.9995888842517734e-05, "loss": 4.611, "step": 189 }, { "epoch": 0.005803298717165547, "grad_norm": 0.49991732835769653, "learning_rate": 4.9995845224323215e-05, "loss": 4.5459, "step": 190 }, { "epoch": 0.005833842394624313, "grad_norm": 0.5028305649757385, "learning_rate": 4.999580137597909e-05, "loss": 4.5409, "step": 191 }, { "epoch": 0.005864386072083079, "grad_norm": 0.5249139666557312, "learning_rate": 4.999575729748578e-05, "loss": 4.6773, "step": 192 }, { "epoch": 0.0058949297495418445, "grad_norm": 0.5065988302230835, "learning_rate": 4.999571298884367e-05, "loss": 4.6286, "step": 193 }, { "epoch": 0.005925473427000611, "grad_norm": 0.5460578799247742, "learning_rate": 4.999566845005319e-05, "loss": 4.5718, "step": 194 }, { "epoch": 0.005956017104459377, "grad_norm": 0.49160170555114746, "learning_rate": 4.9995623681114727e-05, "loss": 4.5056, "step": 195 }, { "epoch": 0.005986560781918143, "grad_norm": 0.5003544092178345, "learning_rate": 4.999557868202871e-05, "loss": 4.5786, "step": 196 }, { "epoch": 0.006017104459376909, "grad_norm": 0.5671514272689819, "learning_rate": 4.999553345279555e-05, "loss": 4.5787, "step": 197 }, { "epoch": 0.006047648136835675, "grad_norm": 0.503929078578949, "learning_rate": 4.999548799341567e-05, "loss": 4.565, "step": 198 }, { "epoch": 0.006078191814294441, "grad_norm": 0.5221534371376038, "learning_rate": 4.9995442303889476e-05, "loss": 4.5175, "step": 199 }, { "epoch": 0.006108735491753207, "grad_norm": 0.5125637650489807, "learning_rate": 4.9995396384217385e-05, "loss": 4.5872, "step": 200 }, { "epoch": 0.0061392791692119735, "grad_norm": 0.4980536103248596, "learning_rate": 4.9995350234399836e-05, "loss": 4.5727, "step": 201 }, { "epoch": 0.006169822846670739, "grad_norm": 0.5147995352745056, "learning_rate": 4.999530385443724e-05, "loss": 4.5028, "step": 202 }, { "epoch": 0.006200366524129505, "grad_norm": 0.4936220049858093, "learning_rate": 4.9995257244330036e-05, "loss": 4.589, "step": 203 }, { "epoch": 0.006230910201588271, "grad_norm": 0.4954053461551666, "learning_rate": 4.9995210404078646e-05, "loss": 4.6386, "step": 204 }, { "epoch": 0.006261453879047038, "grad_norm": 0.5011706948280334, "learning_rate": 4.9995163333683504e-05, "loss": 4.4898, "step": 205 }, { "epoch": 0.006291997556505803, "grad_norm": 0.4939839839935303, "learning_rate": 4.999511603314504e-05, "loss": 4.5289, "step": 206 }, { "epoch": 0.006322541233964569, "grad_norm": 0.5141433477401733, "learning_rate": 4.999506850246369e-05, "loss": 4.6154, "step": 207 }, { "epoch": 0.006353084911423335, "grad_norm": 0.5041474103927612, "learning_rate": 4.999502074163989e-05, "loss": 4.5355, "step": 208 }, { "epoch": 0.006383628588882102, "grad_norm": 0.4971977770328522, "learning_rate": 4.999497275067409e-05, "loss": 4.6115, "step": 209 }, { "epoch": 0.006414172266340868, "grad_norm": 0.495219349861145, "learning_rate": 4.9994924529566724e-05, "loss": 4.5719, "step": 210 }, { "epoch": 0.006444715943799633, "grad_norm": 0.4971889555454254, "learning_rate": 4.999487607831823e-05, "loss": 4.5889, "step": 211 }, { "epoch": 0.0064752596212583995, "grad_norm": 0.49934518337249756, "learning_rate": 4.999482739692907e-05, "loss": 4.5368, "step": 212 }, { "epoch": 0.006505803298717166, "grad_norm": 0.5157909989356995, "learning_rate": 4.9994778485399675e-05, "loss": 4.5479, "step": 213 }, { "epoch": 0.006536346976175932, "grad_norm": 0.5042538046836853, "learning_rate": 4.999472934373051e-05, "loss": 4.5064, "step": 214 }, { "epoch": 0.006566890653634697, "grad_norm": 0.49223512411117554, "learning_rate": 4.999467997192201e-05, "loss": 4.6044, "step": 215 }, { "epoch": 0.0065974343310934635, "grad_norm": 0.5243251919746399, "learning_rate": 4.999463036997465e-05, "loss": 4.5998, "step": 216 }, { "epoch": 0.00662797800855223, "grad_norm": 0.49291786551475525, "learning_rate": 4.999458053788888e-05, "loss": 4.5811, "step": 217 }, { "epoch": 0.006658521686010996, "grad_norm": 0.5091967582702637, "learning_rate": 4.9994530475665154e-05, "loss": 4.5016, "step": 218 }, { "epoch": 0.006689065363469761, "grad_norm": 0.48437973856925964, "learning_rate": 4.999448018330393e-05, "loss": 4.4577, "step": 219 }, { "epoch": 0.006719609040928528, "grad_norm": 0.5224564075469971, "learning_rate": 4.9994429660805676e-05, "loss": 4.5605, "step": 220 }, { "epoch": 0.006750152718387294, "grad_norm": 0.49197474122047424, "learning_rate": 4.999437890817086e-05, "loss": 4.4804, "step": 221 }, { "epoch": 0.00678069639584606, "grad_norm": 0.4973504841327667, "learning_rate": 4.999432792539995e-05, "loss": 4.532, "step": 222 }, { "epoch": 0.006811240073304826, "grad_norm": 0.5091337561607361, "learning_rate": 4.99942767124934e-05, "loss": 4.5542, "step": 223 }, { "epoch": 0.006841783750763592, "grad_norm": 0.4932248890399933, "learning_rate": 4.999422526945171e-05, "loss": 4.6714, "step": 224 }, { "epoch": 0.006872327428222358, "grad_norm": 0.5094410181045532, "learning_rate": 4.999417359627533e-05, "loss": 4.596, "step": 225 }, { "epoch": 0.006902871105681124, "grad_norm": 0.5097929239273071, "learning_rate": 4.999412169296474e-05, "loss": 4.5797, "step": 226 }, { "epoch": 0.00693341478313989, "grad_norm": 0.5039474964141846, "learning_rate": 4.999406955952043e-05, "loss": 4.5627, "step": 227 }, { "epoch": 0.006963958460598656, "grad_norm": 0.5140076279640198, "learning_rate": 4.9994017195942854e-05, "loss": 4.4385, "step": 228 }, { "epoch": 0.006994502138057422, "grad_norm": 0.51008141040802, "learning_rate": 4.999396460223252e-05, "loss": 4.5099, "step": 229 }, { "epoch": 0.007025045815516188, "grad_norm": 0.5066068768501282, "learning_rate": 4.999391177838991e-05, "loss": 4.5952, "step": 230 }, { "epoch": 0.007055589492974954, "grad_norm": 0.49843883514404297, "learning_rate": 4.9993858724415497e-05, "loss": 4.4983, "step": 231 }, { "epoch": 0.007086133170433721, "grad_norm": 0.5025901198387146, "learning_rate": 4.9993805440309785e-05, "loss": 4.4278, "step": 232 }, { "epoch": 0.007116676847892486, "grad_norm": 0.5133771300315857, "learning_rate": 4.999375192607324e-05, "loss": 4.5429, "step": 233 }, { "epoch": 0.007147220525351252, "grad_norm": 0.4938851594924927, "learning_rate": 4.9993698181706385e-05, "loss": 4.5575, "step": 234 }, { "epoch": 0.0071777642028100185, "grad_norm": 0.5207307934761047, "learning_rate": 4.9993644207209686e-05, "loss": 4.608, "step": 235 }, { "epoch": 0.007208307880268785, "grad_norm": 0.4868352711200714, "learning_rate": 4.999359000258367e-05, "loss": 4.5078, "step": 236 }, { "epoch": 0.00723885155772755, "grad_norm": 0.5056172013282776, "learning_rate": 4.999353556782881e-05, "loss": 4.4958, "step": 237 }, { "epoch": 0.007269395235186316, "grad_norm": 0.4922236204147339, "learning_rate": 4.999348090294562e-05, "loss": 4.5663, "step": 238 }, { "epoch": 0.0072999389126450825, "grad_norm": 0.5193564295768738, "learning_rate": 4.99934260079346e-05, "loss": 4.5237, "step": 239 }, { "epoch": 0.007330482590103849, "grad_norm": 0.4955739974975586, "learning_rate": 4.9993370882796257e-05, "loss": 4.5605, "step": 240 }, { "epoch": 0.007361026267562614, "grad_norm": 0.5038309097290039, "learning_rate": 4.999331552753109e-05, "loss": 4.4985, "step": 241 }, { "epoch": 0.00739156994502138, "grad_norm": 0.5001890063285828, "learning_rate": 4.999325994213963e-05, "loss": 4.5941, "step": 242 }, { "epoch": 0.007422113622480147, "grad_norm": 0.48461365699768066, "learning_rate": 4.999320412662237e-05, "loss": 4.5656, "step": 243 }, { "epoch": 0.007452657299938913, "grad_norm": 0.4956376552581787, "learning_rate": 4.999314808097983e-05, "loss": 4.6099, "step": 244 }, { "epoch": 0.007483200977397679, "grad_norm": 0.5081021785736084, "learning_rate": 4.999309180521253e-05, "loss": 4.5413, "step": 245 }, { "epoch": 0.007513744654856444, "grad_norm": 0.49761897325515747, "learning_rate": 4.9993035299320976e-05, "loss": 4.5787, "step": 246 }, { "epoch": 0.007544288332315211, "grad_norm": 0.49359872937202454, "learning_rate": 4.9992978563305696e-05, "loss": 4.5762, "step": 247 }, { "epoch": 0.007574832009773977, "grad_norm": 0.4981115162372589, "learning_rate": 4.999292159716722e-05, "loss": 4.5511, "step": 248 }, { "epoch": 0.007605375687232743, "grad_norm": 0.49026161432266235, "learning_rate": 4.9992864400906056e-05, "loss": 4.5197, "step": 249 }, { "epoch": 0.0076359193646915085, "grad_norm": 0.4899888336658478, "learning_rate": 4.9992806974522746e-05, "loss": 4.536, "step": 250 }, { "epoch": 0.007666463042150275, "grad_norm": 0.4991248846054077, "learning_rate": 4.999274931801781e-05, "loss": 4.5962, "step": 251 }, { "epoch": 0.007697006719609041, "grad_norm": 0.48248642683029175, "learning_rate": 4.999269143139178e-05, "loss": 4.4576, "step": 252 }, { "epoch": 0.007727550397067807, "grad_norm": 0.48837393522262573, "learning_rate": 4.9992633314645184e-05, "loss": 4.5305, "step": 253 }, { "epoch": 0.007758094074526573, "grad_norm": 0.5074008107185364, "learning_rate": 4.999257496777857e-05, "loss": 4.6193, "step": 254 }, { "epoch": 0.007788637751985339, "grad_norm": 0.5081068277359009, "learning_rate": 4.999251639079247e-05, "loss": 4.5926, "step": 255 }, { "epoch": 0.007819181429444105, "grad_norm": 0.5005317330360413, "learning_rate": 4.9992457583687424e-05, "loss": 4.5654, "step": 256 }, { "epoch": 0.00784972510690287, "grad_norm": 0.5162996053695679, "learning_rate": 4.9992398546463964e-05, "loss": 4.6076, "step": 257 }, { "epoch": 0.007880268784361637, "grad_norm": 0.5035264492034912, "learning_rate": 4.9992339279122644e-05, "loss": 4.5967, "step": 258 }, { "epoch": 0.007910812461820403, "grad_norm": 0.4812132716178894, "learning_rate": 4.999227978166401e-05, "loss": 4.5021, "step": 259 }, { "epoch": 0.00794135613927917, "grad_norm": 0.4929453134536743, "learning_rate": 4.9992220054088604e-05, "loss": 4.5923, "step": 260 }, { "epoch": 0.007971899816737935, "grad_norm": 0.4788275361061096, "learning_rate": 4.999216009639697e-05, "loss": 4.4814, "step": 261 }, { "epoch": 0.0080024434941967, "grad_norm": 0.5100696086883545, "learning_rate": 4.9992099908589673e-05, "loss": 4.5035, "step": 262 }, { "epoch": 0.008032987171655468, "grad_norm": 0.48487284779548645, "learning_rate": 4.9992039490667265e-05, "loss": 4.6013, "step": 263 }, { "epoch": 0.008063530849114233, "grad_norm": 0.4904158115386963, "learning_rate": 4.99919788426303e-05, "loss": 4.5948, "step": 264 }, { "epoch": 0.008094074526573, "grad_norm": 0.48148107528686523, "learning_rate": 4.9991917964479335e-05, "loss": 4.5169, "step": 265 }, { "epoch": 0.008124618204031766, "grad_norm": 0.4842403829097748, "learning_rate": 4.999185685621494e-05, "loss": 4.6107, "step": 266 }, { "epoch": 0.008155161881490531, "grad_norm": 0.4907386004924774, "learning_rate": 4.9991795517837656e-05, "loss": 4.4987, "step": 267 }, { "epoch": 0.008185705558949298, "grad_norm": 0.4864923059940338, "learning_rate": 4.9991733949348064e-05, "loss": 4.5642, "step": 268 }, { "epoch": 0.008216249236408063, "grad_norm": 0.49220046401023865, "learning_rate": 4.9991672150746726e-05, "loss": 4.5076, "step": 269 }, { "epoch": 0.008246792913866829, "grad_norm": 0.4927719235420227, "learning_rate": 4.9991610122034224e-05, "loss": 4.5753, "step": 270 }, { "epoch": 0.008277336591325596, "grad_norm": 0.4810394048690796, "learning_rate": 4.9991547863211106e-05, "loss": 4.5154, "step": 271 }, { "epoch": 0.008307880268784361, "grad_norm": 0.48268669843673706, "learning_rate": 4.999148537427797e-05, "loss": 4.4545, "step": 272 }, { "epoch": 0.008338423946243128, "grad_norm": 0.49330490827560425, "learning_rate": 4.999142265523537e-05, "loss": 4.534, "step": 273 }, { "epoch": 0.008368967623701894, "grad_norm": 0.5250360369682312, "learning_rate": 4.99913597060839e-05, "loss": 4.5336, "step": 274 }, { "epoch": 0.008399511301160659, "grad_norm": 0.48182544112205505, "learning_rate": 4.9991296526824115e-05, "loss": 4.5296, "step": 275 }, { "epoch": 0.008430054978619426, "grad_norm": 0.47800105810165405, "learning_rate": 4.999123311745663e-05, "loss": 4.5613, "step": 276 }, { "epoch": 0.008460598656078192, "grad_norm": 0.49840009212493896, "learning_rate": 4.9991169477982005e-05, "loss": 4.5389, "step": 277 }, { "epoch": 0.008491142333536959, "grad_norm": 0.48606106638908386, "learning_rate": 4.999110560840083e-05, "loss": 4.4866, "step": 278 }, { "epoch": 0.008521686010995724, "grad_norm": 0.47551119327545166, "learning_rate": 4.999104150871371e-05, "loss": 4.403, "step": 279 }, { "epoch": 0.00855222968845449, "grad_norm": 0.49408262968063354, "learning_rate": 4.9990977178921216e-05, "loss": 4.564, "step": 280 }, { "epoch": 0.008582773365913256, "grad_norm": 0.4886331260204315, "learning_rate": 4.9990912619023945e-05, "loss": 4.5808, "step": 281 }, { "epoch": 0.008613317043372022, "grad_norm": 0.4755284786224365, "learning_rate": 4.999084782902249e-05, "loss": 4.5249, "step": 282 }, { "epoch": 0.008643860720830789, "grad_norm": 0.4737836420536041, "learning_rate": 4.999078280891745e-05, "loss": 4.5414, "step": 283 }, { "epoch": 0.008674404398289554, "grad_norm": 0.5099769830703735, "learning_rate": 4.999071755870942e-05, "loss": 4.5039, "step": 284 }, { "epoch": 0.00870494807574832, "grad_norm": 0.4812254309654236, "learning_rate": 4.9990652078399016e-05, "loss": 4.5489, "step": 285 }, { "epoch": 0.008735491753207087, "grad_norm": 0.4948258697986603, "learning_rate": 4.999058636798683e-05, "loss": 4.5851, "step": 286 }, { "epoch": 0.008766035430665852, "grad_norm": 0.47962337732315063, "learning_rate": 4.9990520427473456e-05, "loss": 4.5725, "step": 287 }, { "epoch": 0.008796579108124617, "grad_norm": 0.4933229982852936, "learning_rate": 4.999045425685951e-05, "loss": 4.5673, "step": 288 }, { "epoch": 0.008827122785583385, "grad_norm": 0.4885675311088562, "learning_rate": 4.999038785614561e-05, "loss": 4.5915, "step": 289 }, { "epoch": 0.00885766646304215, "grad_norm": 0.4728856682777405, "learning_rate": 4.999032122533236e-05, "loss": 4.4459, "step": 290 }, { "epoch": 0.008888210140500917, "grad_norm": 0.4837527871131897, "learning_rate": 4.999025436442037e-05, "loss": 4.4935, "step": 291 }, { "epoch": 0.008918753817959682, "grad_norm": 0.4682120382785797, "learning_rate": 4.999018727341026e-05, "loss": 4.4813, "step": 292 }, { "epoch": 0.008949297495418448, "grad_norm": 0.47346532344818115, "learning_rate": 4.999011995230265e-05, "loss": 4.5359, "step": 293 }, { "epoch": 0.008979841172877215, "grad_norm": 0.4823390543460846, "learning_rate": 4.999005240109815e-05, "loss": 4.5079, "step": 294 }, { "epoch": 0.00901038485033598, "grad_norm": 0.4769464433193207, "learning_rate": 4.9989984619797396e-05, "loss": 4.5634, "step": 295 }, { "epoch": 0.009040928527794747, "grad_norm": 0.492043137550354, "learning_rate": 4.9989916608401e-05, "loss": 4.481, "step": 296 }, { "epoch": 0.009071472205253513, "grad_norm": 0.4785471260547638, "learning_rate": 4.99898483669096e-05, "loss": 4.5224, "step": 297 }, { "epoch": 0.009102015882712278, "grad_norm": 0.49262651801109314, "learning_rate": 4.9989779895323816e-05, "loss": 4.5754, "step": 298 }, { "epoch": 0.009132559560171045, "grad_norm": 0.4891035854816437, "learning_rate": 4.998971119364427e-05, "loss": 4.5308, "step": 299 }, { "epoch": 0.00916310323762981, "grad_norm": 0.48848292231559753, "learning_rate": 4.9989642261871614e-05, "loss": 4.5155, "step": 300 }, { "epoch": 0.009193646915088576, "grad_norm": 0.4871023893356323, "learning_rate": 4.9989573100006476e-05, "loss": 4.4953, "step": 301 }, { "epoch": 0.009224190592547343, "grad_norm": 0.4775359332561493, "learning_rate": 4.998950370804949e-05, "loss": 4.5766, "step": 302 }, { "epoch": 0.009254734270006108, "grad_norm": 0.5111933946609497, "learning_rate": 4.998943408600129e-05, "loss": 4.548, "step": 303 }, { "epoch": 0.009285277947464875, "grad_norm": 0.48263052105903625, "learning_rate": 4.9989364233862525e-05, "loss": 4.5265, "step": 304 }, { "epoch": 0.00931582162492364, "grad_norm": 0.4953759014606476, "learning_rate": 4.998929415163383e-05, "loss": 4.6073, "step": 305 }, { "epoch": 0.009346365302382406, "grad_norm": 0.48311135172843933, "learning_rate": 4.9989223839315856e-05, "loss": 4.5291, "step": 306 }, { "epoch": 0.009376908979841173, "grad_norm": 0.525779128074646, "learning_rate": 4.998915329690925e-05, "loss": 4.6544, "step": 307 }, { "epoch": 0.009407452657299939, "grad_norm": 0.4839927852153778, "learning_rate": 4.998908252441467e-05, "loss": 4.5063, "step": 308 }, { "epoch": 0.009437996334758706, "grad_norm": 0.4749681055545807, "learning_rate": 4.998901152183275e-05, "loss": 4.595, "step": 309 }, { "epoch": 0.009468540012217471, "grad_norm": 0.48141831159591675, "learning_rate": 4.998894028916416e-05, "loss": 4.5432, "step": 310 }, { "epoch": 0.009499083689676236, "grad_norm": 0.511533260345459, "learning_rate": 4.998886882640954e-05, "loss": 4.581, "step": 311 }, { "epoch": 0.009529627367135004, "grad_norm": 0.4769567847251892, "learning_rate": 4.9988797133569564e-05, "loss": 4.5506, "step": 312 }, { "epoch": 0.009560171044593769, "grad_norm": 0.47453227639198303, "learning_rate": 4.998872521064488e-05, "loss": 4.5941, "step": 313 }, { "epoch": 0.009590714722052534, "grad_norm": 0.49107879400253296, "learning_rate": 4.9988653057636156e-05, "loss": 4.5924, "step": 314 }, { "epoch": 0.009621258399511301, "grad_norm": 0.4751940071582794, "learning_rate": 4.998858067454406e-05, "loss": 4.5565, "step": 315 }, { "epoch": 0.009651802076970067, "grad_norm": 0.482023686170578, "learning_rate": 4.998850806136926e-05, "loss": 4.6393, "step": 316 }, { "epoch": 0.009682345754428834, "grad_norm": 0.4743650555610657, "learning_rate": 4.998843521811241e-05, "loss": 4.5118, "step": 317 }, { "epoch": 0.0097128894318876, "grad_norm": 0.49330568313598633, "learning_rate": 4.998836214477418e-05, "loss": 4.5702, "step": 318 }, { "epoch": 0.009743433109346365, "grad_norm": 0.48030340671539307, "learning_rate": 4.998828884135526e-05, "loss": 4.5313, "step": 319 }, { "epoch": 0.009773976786805132, "grad_norm": 0.4957825243473053, "learning_rate": 4.9988215307856325e-05, "loss": 4.4591, "step": 320 }, { "epoch": 0.009804520464263897, "grad_norm": 0.46306711435317993, "learning_rate": 4.998814154427803e-05, "loss": 4.4556, "step": 321 }, { "epoch": 0.009835064141722664, "grad_norm": 0.4873681962490082, "learning_rate": 4.998806755062108e-05, "loss": 4.5626, "step": 322 }, { "epoch": 0.00986560781918143, "grad_norm": 0.5521280169487, "learning_rate": 4.998799332688613e-05, "loss": 4.6106, "step": 323 }, { "epoch": 0.009896151496640195, "grad_norm": 0.47573167085647583, "learning_rate": 4.998791887307389e-05, "loss": 4.4677, "step": 324 }, { "epoch": 0.009926695174098962, "grad_norm": 0.4962542653083801, "learning_rate": 4.998784418918503e-05, "loss": 4.5358, "step": 325 }, { "epoch": 0.009957238851557727, "grad_norm": 0.4675671458244324, "learning_rate": 4.998776927522024e-05, "loss": 4.4059, "step": 326 }, { "epoch": 0.009987782529016494, "grad_norm": 0.49965983629226685, "learning_rate": 4.9987694131180216e-05, "loss": 4.5299, "step": 327 }, { "epoch": 0.01001832620647526, "grad_norm": 0.5066965818405151, "learning_rate": 4.998761875706564e-05, "loss": 4.5731, "step": 328 }, { "epoch": 0.010048869883934025, "grad_norm": 0.49405401945114136, "learning_rate": 4.9987543152877216e-05, "loss": 4.5985, "step": 329 }, { "epoch": 0.010079413561392792, "grad_norm": 0.47717007994651794, "learning_rate": 4.998746731861562e-05, "loss": 4.5071, "step": 330 }, { "epoch": 0.010109957238851558, "grad_norm": 0.4934486448764801, "learning_rate": 4.998739125428158e-05, "loss": 4.5891, "step": 331 }, { "epoch": 0.010140500916310323, "grad_norm": 0.48619505763053894, "learning_rate": 4.9987314959875774e-05, "loss": 4.5395, "step": 332 }, { "epoch": 0.01017104459376909, "grad_norm": 0.48591578006744385, "learning_rate": 4.998723843539892e-05, "loss": 4.5842, "step": 333 }, { "epoch": 0.010201588271227855, "grad_norm": 0.4817206561565399, "learning_rate": 4.998716168085171e-05, "loss": 4.5175, "step": 334 }, { "epoch": 0.010232131948686623, "grad_norm": 0.478702187538147, "learning_rate": 4.9987084696234856e-05, "loss": 4.5318, "step": 335 }, { "epoch": 0.010262675626145388, "grad_norm": 0.47930699586868286, "learning_rate": 4.9987007481549066e-05, "loss": 4.5217, "step": 336 }, { "epoch": 0.010293219303604153, "grad_norm": 0.4903324246406555, "learning_rate": 4.9986930036795046e-05, "loss": 4.5377, "step": 337 }, { "epoch": 0.01032376298106292, "grad_norm": 0.4870699644088745, "learning_rate": 4.9986852361973516e-05, "loss": 4.5698, "step": 338 }, { "epoch": 0.010354306658521686, "grad_norm": 0.5205526351928711, "learning_rate": 4.998677445708519e-05, "loss": 4.4923, "step": 339 }, { "epoch": 0.010384850335980453, "grad_norm": 0.4832594692707062, "learning_rate": 4.9986696322130786e-05, "loss": 4.6265, "step": 340 }, { "epoch": 0.010415394013439218, "grad_norm": 0.4955943822860718, "learning_rate": 4.9986617957111025e-05, "loss": 4.4158, "step": 341 }, { "epoch": 0.010445937690897984, "grad_norm": 0.512687087059021, "learning_rate": 4.9986539362026625e-05, "loss": 4.4026, "step": 342 }, { "epoch": 0.01047648136835675, "grad_norm": 0.489568829536438, "learning_rate": 4.998646053687831e-05, "loss": 4.5494, "step": 343 }, { "epoch": 0.010507025045815516, "grad_norm": 0.4797149896621704, "learning_rate": 4.99863814816668e-05, "loss": 4.5227, "step": 344 }, { "epoch": 0.010537568723274281, "grad_norm": 0.48131313920021057, "learning_rate": 4.9986302196392834e-05, "loss": 4.5661, "step": 345 }, { "epoch": 0.010568112400733048, "grad_norm": 0.5050808191299438, "learning_rate": 4.998622268105714e-05, "loss": 4.5235, "step": 346 }, { "epoch": 0.010598656078191814, "grad_norm": 0.4701762795448303, "learning_rate": 4.998614293566044e-05, "loss": 4.6329, "step": 347 }, { "epoch": 0.010629199755650581, "grad_norm": 0.48152467608451843, "learning_rate": 4.998606296020348e-05, "loss": 4.3946, "step": 348 }, { "epoch": 0.010659743433109346, "grad_norm": 0.48972320556640625, "learning_rate": 4.9985982754686986e-05, "loss": 4.558, "step": 349 }, { "epoch": 0.010690287110568112, "grad_norm": 0.46491917967796326, "learning_rate": 4.998590231911171e-05, "loss": 4.4683, "step": 350 }, { "epoch": 0.010720830788026879, "grad_norm": 0.499918669462204, "learning_rate": 4.998582165347838e-05, "loss": 4.5385, "step": 351 }, { "epoch": 0.010751374465485644, "grad_norm": 0.4896565079689026, "learning_rate": 4.998574075778775e-05, "loss": 4.5748, "step": 352 }, { "epoch": 0.010781918142944411, "grad_norm": 0.4813145697116852, "learning_rate": 4.998565963204055e-05, "loss": 4.5344, "step": 353 }, { "epoch": 0.010812461820403177, "grad_norm": 0.5144221186637878, "learning_rate": 4.998557827623754e-05, "loss": 4.4746, "step": 354 }, { "epoch": 0.010843005497861942, "grad_norm": 0.47660398483276367, "learning_rate": 4.998549669037946e-05, "loss": 4.5036, "step": 355 }, { "epoch": 0.010873549175320709, "grad_norm": 0.5107724666595459, "learning_rate": 4.998541487446707e-05, "loss": 4.4895, "step": 356 }, { "epoch": 0.010904092852779474, "grad_norm": 0.5097813010215759, "learning_rate": 4.998533282850112e-05, "loss": 4.516, "step": 357 }, { "epoch": 0.010934636530238242, "grad_norm": 0.4728618562221527, "learning_rate": 4.998525055248236e-05, "loss": 4.4597, "step": 358 }, { "epoch": 0.010965180207697007, "grad_norm": 0.49367016553878784, "learning_rate": 4.9985168046411554e-05, "loss": 4.5196, "step": 359 }, { "epoch": 0.010995723885155772, "grad_norm": 0.4881974458694458, "learning_rate": 4.998508531028947e-05, "loss": 4.559, "step": 360 }, { "epoch": 0.01102626756261454, "grad_norm": 0.49036064743995667, "learning_rate": 4.998500234411685e-05, "loss": 4.547, "step": 361 }, { "epoch": 0.011056811240073305, "grad_norm": 0.46378380060195923, "learning_rate": 4.998491914789447e-05, "loss": 4.5516, "step": 362 }, { "epoch": 0.01108735491753207, "grad_norm": 0.4786543548107147, "learning_rate": 4.9984835721623084e-05, "loss": 4.5504, "step": 363 }, { "epoch": 0.011117898594990837, "grad_norm": 0.47745880484580994, "learning_rate": 4.9984752065303474e-05, "loss": 4.4964, "step": 364 }, { "epoch": 0.011148442272449603, "grad_norm": 0.4710202217102051, "learning_rate": 4.998466817893641e-05, "loss": 4.5105, "step": 365 }, { "epoch": 0.01117898594990837, "grad_norm": 0.48642560839653015, "learning_rate": 4.998458406252266e-05, "loss": 4.5417, "step": 366 }, { "epoch": 0.011209529627367135, "grad_norm": 0.4662715792655945, "learning_rate": 4.9984499716063e-05, "loss": 4.4748, "step": 367 }, { "epoch": 0.0112400733048259, "grad_norm": 0.47302934527397156, "learning_rate": 4.99844151395582e-05, "loss": 4.4586, "step": 368 }, { "epoch": 0.011270616982284667, "grad_norm": 0.49067434668540955, "learning_rate": 4.998433033300904e-05, "loss": 4.5036, "step": 369 }, { "epoch": 0.011301160659743433, "grad_norm": 0.4623538851737976, "learning_rate": 4.998424529641632e-05, "loss": 4.5194, "step": 370 }, { "epoch": 0.0113317043372022, "grad_norm": 0.4742567241191864, "learning_rate": 4.99841600297808e-05, "loss": 4.4965, "step": 371 }, { "epoch": 0.011362248014660965, "grad_norm": 0.5077010989189148, "learning_rate": 4.998407453310327e-05, "loss": 4.5386, "step": 372 }, { "epoch": 0.01139279169211973, "grad_norm": 0.502530574798584, "learning_rate": 4.998398880638452e-05, "loss": 4.5424, "step": 373 }, { "epoch": 0.011423335369578498, "grad_norm": 0.45707380771636963, "learning_rate": 4.998390284962535e-05, "loss": 4.482, "step": 374 }, { "epoch": 0.011453879047037263, "grad_norm": 0.4902297258377075, "learning_rate": 4.9983816662826535e-05, "loss": 4.5533, "step": 375 }, { "epoch": 0.011484422724496028, "grad_norm": 0.48150306940078735, "learning_rate": 4.998373024598887e-05, "loss": 4.5336, "step": 376 }, { "epoch": 0.011514966401954796, "grad_norm": 0.4818294644355774, "learning_rate": 4.998364359911316e-05, "loss": 4.5589, "step": 377 }, { "epoch": 0.011545510079413561, "grad_norm": 0.5259777903556824, "learning_rate": 4.998355672220019e-05, "loss": 4.4699, "step": 378 }, { "epoch": 0.011576053756872328, "grad_norm": 0.4820966422557831, "learning_rate": 4.998346961525078e-05, "loss": 4.5076, "step": 379 }, { "epoch": 0.011606597434331093, "grad_norm": 0.49018651247024536, "learning_rate": 4.998338227826571e-05, "loss": 4.5137, "step": 380 }, { "epoch": 0.011637141111789859, "grad_norm": 0.4680514931678772, "learning_rate": 4.99832947112458e-05, "loss": 4.5228, "step": 381 }, { "epoch": 0.011667684789248626, "grad_norm": 0.4713480472564697, "learning_rate": 4.998320691419185e-05, "loss": 4.4492, "step": 382 }, { "epoch": 0.011698228466707391, "grad_norm": 0.46755218505859375, "learning_rate": 4.998311888710466e-05, "loss": 4.5782, "step": 383 }, { "epoch": 0.011728772144166158, "grad_norm": 0.475494921207428, "learning_rate": 4.998303062998506e-05, "loss": 4.6104, "step": 384 }, { "epoch": 0.011759315821624924, "grad_norm": 0.48888128995895386, "learning_rate": 4.998294214283386e-05, "loss": 4.5276, "step": 385 }, { "epoch": 0.011789859499083689, "grad_norm": 0.46920984983444214, "learning_rate": 4.998285342565185e-05, "loss": 4.4619, "step": 386 }, { "epoch": 0.011820403176542456, "grad_norm": 0.47397348284721375, "learning_rate": 4.998276447843987e-05, "loss": 4.6051, "step": 387 }, { "epoch": 0.011850946854001222, "grad_norm": 0.4709441363811493, "learning_rate": 4.998267530119873e-05, "loss": 4.605, "step": 388 }, { "epoch": 0.011881490531459989, "grad_norm": 0.4668095111846924, "learning_rate": 4.9982585893929255e-05, "loss": 4.5081, "step": 389 }, { "epoch": 0.011912034208918754, "grad_norm": 0.4852149486541748, "learning_rate": 4.9982496256632274e-05, "loss": 4.5987, "step": 390 }, { "epoch": 0.01194257788637752, "grad_norm": 0.4858957827091217, "learning_rate": 4.998240638930859e-05, "loss": 4.5322, "step": 391 }, { "epoch": 0.011973121563836286, "grad_norm": 0.47049811482429504, "learning_rate": 4.998231629195906e-05, "loss": 4.5458, "step": 392 }, { "epoch": 0.012003665241295052, "grad_norm": 0.47932228446006775, "learning_rate": 4.99822259645845e-05, "loss": 4.513, "step": 393 }, { "epoch": 0.012034208918753817, "grad_norm": 0.4807007610797882, "learning_rate": 4.9982135407185725e-05, "loss": 4.6063, "step": 394 }, { "epoch": 0.012064752596212584, "grad_norm": 0.49310532212257385, "learning_rate": 4.9982044619763596e-05, "loss": 4.5612, "step": 395 }, { "epoch": 0.01209529627367135, "grad_norm": 0.5088486671447754, "learning_rate": 4.998195360231894e-05, "loss": 4.5062, "step": 396 }, { "epoch": 0.012125839951130117, "grad_norm": 0.4596993327140808, "learning_rate": 4.998186235485258e-05, "loss": 4.541, "step": 397 }, { "epoch": 0.012156383628588882, "grad_norm": 0.45588719844818115, "learning_rate": 4.998177087736539e-05, "loss": 4.4999, "step": 398 }, { "epoch": 0.012186927306047647, "grad_norm": 0.47369951009750366, "learning_rate": 4.998167916985818e-05, "loss": 4.5678, "step": 399 }, { "epoch": 0.012217470983506415, "grad_norm": 0.4699941873550415, "learning_rate": 4.9981587232331793e-05, "loss": 4.3834, "step": 400 }, { "epoch": 0.01224801466096518, "grad_norm": 0.47851085662841797, "learning_rate": 4.9981495064787106e-05, "loss": 4.4984, "step": 401 }, { "epoch": 0.012278558338423947, "grad_norm": 0.4853276014328003, "learning_rate": 4.998140266722494e-05, "loss": 4.5643, "step": 402 }, { "epoch": 0.012309102015882712, "grad_norm": 0.48934775590896606, "learning_rate": 4.998131003964616e-05, "loss": 4.562, "step": 403 }, { "epoch": 0.012339645693341478, "grad_norm": 0.4730273187160492, "learning_rate": 4.998121718205161e-05, "loss": 4.5285, "step": 404 }, { "epoch": 0.012370189370800245, "grad_norm": 0.48575496673583984, "learning_rate": 4.9981124094442155e-05, "loss": 4.5364, "step": 405 }, { "epoch": 0.01240073304825901, "grad_norm": 0.47966042160987854, "learning_rate": 4.998103077681864e-05, "loss": 4.4742, "step": 406 }, { "epoch": 0.012431276725717776, "grad_norm": 0.48183873295783997, "learning_rate": 4.998093722918194e-05, "loss": 4.4695, "step": 407 }, { "epoch": 0.012461820403176543, "grad_norm": 0.49603402614593506, "learning_rate": 4.99808434515329e-05, "loss": 4.6161, "step": 408 }, { "epoch": 0.012492364080635308, "grad_norm": 0.4759756326675415, "learning_rate": 4.998074944387239e-05, "loss": 4.4669, "step": 409 }, { "epoch": 0.012522907758094075, "grad_norm": 0.47528719902038574, "learning_rate": 4.9980655206201285e-05, "loss": 4.6187, "step": 410 }, { "epoch": 0.01255345143555284, "grad_norm": 0.4813397228717804, "learning_rate": 4.9980560738520435e-05, "loss": 4.5024, "step": 411 }, { "epoch": 0.012583995113011606, "grad_norm": 0.4654485285282135, "learning_rate": 4.998046604083072e-05, "loss": 4.4501, "step": 412 }, { "epoch": 0.012614538790470373, "grad_norm": 0.4948764145374298, "learning_rate": 4.998037111313301e-05, "loss": 4.5933, "step": 413 }, { "epoch": 0.012645082467929138, "grad_norm": 0.48054370284080505, "learning_rate": 4.998027595542818e-05, "loss": 4.5478, "step": 414 }, { "epoch": 0.012675626145387905, "grad_norm": 0.4772642254829407, "learning_rate": 4.99801805677171e-05, "loss": 4.5574, "step": 415 }, { "epoch": 0.01270616982284667, "grad_norm": 0.4788022041320801, "learning_rate": 4.998008495000067e-05, "loss": 4.4767, "step": 416 }, { "epoch": 0.012736713500305436, "grad_norm": 0.47291460633277893, "learning_rate": 4.9979989102279746e-05, "loss": 4.4958, "step": 417 }, { "epoch": 0.012767257177764203, "grad_norm": 0.4668591320514679, "learning_rate": 4.9979893024555214e-05, "loss": 4.5331, "step": 418 }, { "epoch": 0.012797800855222969, "grad_norm": 0.5064446330070496, "learning_rate": 4.9979796716827965e-05, "loss": 4.5414, "step": 419 }, { "epoch": 0.012828344532681736, "grad_norm": 0.4673791825771332, "learning_rate": 4.997970017909889e-05, "loss": 4.5762, "step": 420 }, { "epoch": 0.012858888210140501, "grad_norm": 0.45934975147247314, "learning_rate": 4.997960341136887e-05, "loss": 4.525, "step": 421 }, { "epoch": 0.012889431887599266, "grad_norm": 0.48354610800743103, "learning_rate": 4.99795064136388e-05, "loss": 4.5552, "step": 422 }, { "epoch": 0.012919975565058034, "grad_norm": 0.4830506443977356, "learning_rate": 4.997940918590956e-05, "loss": 4.5351, "step": 423 }, { "epoch": 0.012950519242516799, "grad_norm": 0.4646760821342468, "learning_rate": 4.997931172818206e-05, "loss": 4.4967, "step": 424 }, { "epoch": 0.012981062919975564, "grad_norm": 0.46591800451278687, "learning_rate": 4.99792140404572e-05, "loss": 4.4843, "step": 425 }, { "epoch": 0.013011606597434331, "grad_norm": 0.4794045090675354, "learning_rate": 4.9979116122735875e-05, "loss": 4.5319, "step": 426 }, { "epoch": 0.013042150274893097, "grad_norm": 0.49249494075775146, "learning_rate": 4.9979017975018985e-05, "loss": 4.526, "step": 427 }, { "epoch": 0.013072693952351864, "grad_norm": 0.4684283137321472, "learning_rate": 4.997891959730743e-05, "loss": 4.5146, "step": 428 }, { "epoch": 0.01310323762981063, "grad_norm": 0.45434150099754333, "learning_rate": 4.9978820989602116e-05, "loss": 4.4693, "step": 429 }, { "epoch": 0.013133781307269395, "grad_norm": 0.46570727229118347, "learning_rate": 4.997872215190396e-05, "loss": 4.4933, "step": 430 }, { "epoch": 0.013164324984728162, "grad_norm": 0.45464393496513367, "learning_rate": 4.997862308421386e-05, "loss": 4.4391, "step": 431 }, { "epoch": 0.013194868662186927, "grad_norm": 0.47210437059402466, "learning_rate": 4.997852378653274e-05, "loss": 4.5701, "step": 432 }, { "epoch": 0.013225412339645694, "grad_norm": 0.46096405386924744, "learning_rate": 4.99784242588615e-05, "loss": 4.5483, "step": 433 }, { "epoch": 0.01325595601710446, "grad_norm": 0.4605373442173004, "learning_rate": 4.997832450120108e-05, "loss": 4.5504, "step": 434 }, { "epoch": 0.013286499694563225, "grad_norm": 0.47743985056877136, "learning_rate": 4.997822451355238e-05, "loss": 4.5182, "step": 435 }, { "epoch": 0.013317043372021992, "grad_norm": 0.46149787306785583, "learning_rate": 4.997812429591632e-05, "loss": 4.579, "step": 436 }, { "epoch": 0.013347587049480757, "grad_norm": 0.47727516293525696, "learning_rate": 4.997802384829382e-05, "loss": 4.6002, "step": 437 }, { "epoch": 0.013378130726939523, "grad_norm": 0.4836481809616089, "learning_rate": 4.9977923170685824e-05, "loss": 4.5214, "step": 438 }, { "epoch": 0.01340867440439829, "grad_norm": 0.4763633608818054, "learning_rate": 4.9977822263093246e-05, "loss": 4.5296, "step": 439 }, { "epoch": 0.013439218081857055, "grad_norm": 0.4857737720012665, "learning_rate": 4.9977721125517006e-05, "loss": 4.6267, "step": 440 }, { "epoch": 0.013469761759315822, "grad_norm": 0.4620451033115387, "learning_rate": 4.9977619757958054e-05, "loss": 4.4206, "step": 441 }, { "epoch": 0.013500305436774588, "grad_norm": 0.46296942234039307, "learning_rate": 4.9977518160417316e-05, "loss": 4.4655, "step": 442 }, { "epoch": 0.013530849114233353, "grad_norm": 0.46762731671333313, "learning_rate": 4.997741633289572e-05, "loss": 4.5826, "step": 443 }, { "epoch": 0.01356139279169212, "grad_norm": 0.46769243478775024, "learning_rate": 4.9977314275394214e-05, "loss": 4.4801, "step": 444 }, { "epoch": 0.013591936469150885, "grad_norm": 0.465159147977829, "learning_rate": 4.997721198791373e-05, "loss": 4.551, "step": 445 }, { "epoch": 0.013622480146609653, "grad_norm": 0.4604896306991577, "learning_rate": 4.997710947045522e-05, "loss": 4.5647, "step": 446 }, { "epoch": 0.013653023824068418, "grad_norm": 0.45501387119293213, "learning_rate": 4.9977006723019615e-05, "loss": 4.4993, "step": 447 }, { "epoch": 0.013683567501527183, "grad_norm": 0.45952731370925903, "learning_rate": 4.997690374560787e-05, "loss": 4.4988, "step": 448 }, { "epoch": 0.01371411117898595, "grad_norm": 0.4745103418827057, "learning_rate": 4.997680053822092e-05, "loss": 4.4755, "step": 449 }, { "epoch": 0.013744654856444716, "grad_norm": 0.46304988861083984, "learning_rate": 4.997669710085974e-05, "loss": 4.3797, "step": 450 }, { "epoch": 0.013775198533903483, "grad_norm": 0.4585976302623749, "learning_rate": 4.9976593433525265e-05, "loss": 4.4939, "step": 451 }, { "epoch": 0.013805742211362248, "grad_norm": 0.45562705397605896, "learning_rate": 4.997648953621845e-05, "loss": 4.5416, "step": 452 }, { "epoch": 0.013836285888821014, "grad_norm": 0.4582900404930115, "learning_rate": 4.997638540894025e-05, "loss": 4.5753, "step": 453 }, { "epoch": 0.01386682956627978, "grad_norm": 0.48375651240348816, "learning_rate": 4.997628105169163e-05, "loss": 4.5542, "step": 454 }, { "epoch": 0.013897373243738546, "grad_norm": 0.9484280347824097, "learning_rate": 4.997617646447356e-05, "loss": 4.507, "step": 455 }, { "epoch": 0.013927916921197311, "grad_norm": 0.4748675227165222, "learning_rate": 4.9976071647286984e-05, "loss": 4.4959, "step": 456 }, { "epoch": 0.013958460598656078, "grad_norm": 0.8874634504318237, "learning_rate": 4.997596660013287e-05, "loss": 4.5349, "step": 457 }, { "epoch": 0.013989004276114844, "grad_norm": 0.46590542793273926, "learning_rate": 4.9975861323012196e-05, "loss": 4.5171, "step": 458 }, { "epoch": 0.014019547953573611, "grad_norm": 0.4768444299697876, "learning_rate": 4.997575581592592e-05, "loss": 4.4887, "step": 459 }, { "epoch": 0.014050091631032376, "grad_norm": 0.46567386388778687, "learning_rate": 4.9975650078875023e-05, "loss": 4.5334, "step": 460 }, { "epoch": 0.014080635308491142, "grad_norm": 0.4825081527233124, "learning_rate": 4.9975544111860475e-05, "loss": 4.5127, "step": 461 }, { "epoch": 0.014111178985949909, "grad_norm": 0.4781312346458435, "learning_rate": 4.997543791488325e-05, "loss": 4.5528, "step": 462 }, { "epoch": 0.014141722663408674, "grad_norm": 0.47084948420524597, "learning_rate": 4.997533148794433e-05, "loss": 4.3786, "step": 463 }, { "epoch": 0.014172266340867441, "grad_norm": 0.4605811536312103, "learning_rate": 4.9975224831044687e-05, "loss": 4.5008, "step": 464 }, { "epoch": 0.014202810018326207, "grad_norm": 0.48108628392219543, "learning_rate": 4.997511794418531e-05, "loss": 4.4916, "step": 465 }, { "epoch": 0.014233353695784972, "grad_norm": 0.48143091797828674, "learning_rate": 4.997501082736718e-05, "loss": 4.5125, "step": 466 }, { "epoch": 0.014263897373243739, "grad_norm": 0.47660908102989197, "learning_rate": 4.9974903480591285e-05, "loss": 4.5442, "step": 467 }, { "epoch": 0.014294441050702504, "grad_norm": 0.47169584035873413, "learning_rate": 4.997479590385862e-05, "loss": 4.5652, "step": 468 }, { "epoch": 0.01432498472816127, "grad_norm": 0.4754911959171295, "learning_rate": 4.997468809717015e-05, "loss": 4.5263, "step": 469 }, { "epoch": 0.014355528405620037, "grad_norm": 0.46527886390686035, "learning_rate": 4.997458006052691e-05, "loss": 4.526, "step": 470 }, { "epoch": 0.014386072083078802, "grad_norm": 0.49387234449386597, "learning_rate": 4.997447179392986e-05, "loss": 4.5553, "step": 471 }, { "epoch": 0.01441661576053757, "grad_norm": 0.45955124497413635, "learning_rate": 4.997436329738e-05, "loss": 4.5216, "step": 472 }, { "epoch": 0.014447159437996335, "grad_norm": 0.4676190912723541, "learning_rate": 4.997425457087834e-05, "loss": 4.4897, "step": 473 }, { "epoch": 0.0144777031154551, "grad_norm": 0.47655412554740906, "learning_rate": 4.9974145614425885e-05, "loss": 4.5431, "step": 474 }, { "epoch": 0.014508246792913867, "grad_norm": 0.49385035037994385, "learning_rate": 4.997403642802362e-05, "loss": 4.5869, "step": 475 }, { "epoch": 0.014538790470372633, "grad_norm": 0.4906599819660187, "learning_rate": 4.9973927011672575e-05, "loss": 4.5268, "step": 476 }, { "epoch": 0.0145693341478314, "grad_norm": 0.47176307439804077, "learning_rate": 4.997381736537373e-05, "loss": 4.4921, "step": 477 }, { "epoch": 0.014599877825290165, "grad_norm": 0.4577195346355438, "learning_rate": 4.997370748912812e-05, "loss": 4.5296, "step": 478 }, { "epoch": 0.01463042150274893, "grad_norm": 0.6579554080963135, "learning_rate": 4.9973597382936735e-05, "loss": 4.5052, "step": 479 }, { "epoch": 0.014660965180207697, "grad_norm": 0.4635465741157532, "learning_rate": 4.9973487046800606e-05, "loss": 4.4732, "step": 480 }, { "epoch": 0.014691508857666463, "grad_norm": 0.47596389055252075, "learning_rate": 4.9973376480720735e-05, "loss": 4.5113, "step": 481 }, { "epoch": 0.014722052535125228, "grad_norm": 0.4679240882396698, "learning_rate": 4.997326568469816e-05, "loss": 4.4844, "step": 482 }, { "epoch": 0.014752596212583995, "grad_norm": 0.4633959233760834, "learning_rate": 4.9973154658733876e-05, "loss": 4.4772, "step": 483 }, { "epoch": 0.01478313989004276, "grad_norm": 0.47225144505500793, "learning_rate": 4.997304340282891e-05, "loss": 4.5319, "step": 484 }, { "epoch": 0.014813683567501528, "grad_norm": 0.5124285221099854, "learning_rate": 4.997293191698431e-05, "loss": 4.5373, "step": 485 }, { "epoch": 0.014844227244960293, "grad_norm": 0.4882796108722687, "learning_rate": 4.9972820201201074e-05, "loss": 4.431, "step": 486 }, { "epoch": 0.014874770922419059, "grad_norm": 0.4557977318763733, "learning_rate": 4.997270825548025e-05, "loss": 4.4614, "step": 487 }, { "epoch": 0.014905314599877826, "grad_norm": 0.46813926100730896, "learning_rate": 4.9972596079822866e-05, "loss": 4.5275, "step": 488 }, { "epoch": 0.014935858277336591, "grad_norm": 0.5082011818885803, "learning_rate": 4.997248367422994e-05, "loss": 4.6176, "step": 489 }, { "epoch": 0.014966401954795358, "grad_norm": 0.4854367971420288, "learning_rate": 4.997237103870252e-05, "loss": 4.511, "step": 490 }, { "epoch": 0.014996945632254123, "grad_norm": 0.4741274118423462, "learning_rate": 4.997225817324164e-05, "loss": 4.4974, "step": 491 }, { "epoch": 0.015027489309712889, "grad_norm": 0.47860461473464966, "learning_rate": 4.9972145077848344e-05, "loss": 4.4453, "step": 492 }, { "epoch": 0.015058032987171656, "grad_norm": 0.489597350358963, "learning_rate": 4.997203175252366e-05, "loss": 4.5322, "step": 493 }, { "epoch": 0.015088576664630421, "grad_norm": 0.4883572459220886, "learning_rate": 4.9971918197268645e-05, "loss": 4.5067, "step": 494 }, { "epoch": 0.015119120342089188, "grad_norm": 0.4665326476097107, "learning_rate": 4.997180441208435e-05, "loss": 4.5705, "step": 495 }, { "epoch": 0.015149664019547954, "grad_norm": 0.48192280530929565, "learning_rate": 4.997169039697179e-05, "loss": 4.5455, "step": 496 }, { "epoch": 0.015180207697006719, "grad_norm": 0.48297324776649475, "learning_rate": 4.997157615193205e-05, "loss": 4.4688, "step": 497 }, { "epoch": 0.015210751374465486, "grad_norm": 0.4559938311576843, "learning_rate": 4.997146167696618e-05, "loss": 4.4535, "step": 498 }, { "epoch": 0.015241295051924252, "grad_norm": 0.4700694978237152, "learning_rate": 4.99713469720752e-05, "loss": 4.5635, "step": 499 }, { "epoch": 0.015271838729383017, "grad_norm": 0.4661923348903656, "learning_rate": 4.9971232037260215e-05, "loss": 4.5296, "step": 500 }, { "epoch": 0.015302382406841784, "grad_norm": 0.49784937500953674, "learning_rate": 4.997111687252224e-05, "loss": 4.4907, "step": 501 }, { "epoch": 0.01533292608430055, "grad_norm": 0.4514216482639313, "learning_rate": 4.997100147786236e-05, "loss": 4.5579, "step": 502 }, { "epoch": 0.015363469761759316, "grad_norm": 0.48073410987854004, "learning_rate": 4.997088585328163e-05, "loss": 4.5328, "step": 503 }, { "epoch": 0.015394013439218082, "grad_norm": 0.4705450236797333, "learning_rate": 4.997076999878112e-05, "loss": 4.5784, "step": 504 }, { "epoch": 0.015424557116676847, "grad_norm": 0.45168033242225647, "learning_rate": 4.997065391436188e-05, "loss": 4.5381, "step": 505 }, { "epoch": 0.015455100794135614, "grad_norm": 0.47547367215156555, "learning_rate": 4.9970537600024994e-05, "loss": 4.4702, "step": 506 }, { "epoch": 0.01548564447159438, "grad_norm": 0.4662361145019531, "learning_rate": 4.997042105577153e-05, "loss": 4.5942, "step": 507 }, { "epoch": 0.015516188149053147, "grad_norm": 0.46509432792663574, "learning_rate": 4.9970304281602564e-05, "loss": 4.4164, "step": 508 }, { "epoch": 0.015546731826511912, "grad_norm": 0.44448259472846985, "learning_rate": 4.9970187277519174e-05, "loss": 4.6015, "step": 509 }, { "epoch": 0.015577275503970677, "grad_norm": 0.4526440501213074, "learning_rate": 4.997007004352242e-05, "loss": 4.5606, "step": 510 }, { "epoch": 0.015607819181429445, "grad_norm": 0.45678240060806274, "learning_rate": 4.99699525796134e-05, "loss": 4.462, "step": 511 }, { "epoch": 0.01563836285888821, "grad_norm": 0.45028093457221985, "learning_rate": 4.9969834885793185e-05, "loss": 4.3837, "step": 512 }, { "epoch": 0.015668906536346977, "grad_norm": 0.46091118454933167, "learning_rate": 4.996971696206286e-05, "loss": 4.4628, "step": 513 }, { "epoch": 0.01569945021380574, "grad_norm": 0.46230682730674744, "learning_rate": 4.9969598808423516e-05, "loss": 4.5282, "step": 514 }, { "epoch": 0.015729993891264508, "grad_norm": 0.46371009945869446, "learning_rate": 4.9969480424876234e-05, "loss": 4.5457, "step": 515 }, { "epoch": 0.015760537568723275, "grad_norm": 0.4726001024246216, "learning_rate": 4.996936181142211e-05, "loss": 4.5126, "step": 516 }, { "epoch": 0.015791081246182042, "grad_norm": 0.46941453218460083, "learning_rate": 4.9969242968062243e-05, "loss": 4.5247, "step": 517 }, { "epoch": 0.015821624923640806, "grad_norm": 0.46772611141204834, "learning_rate": 4.996912389479771e-05, "loss": 4.5226, "step": 518 }, { "epoch": 0.015852168601099573, "grad_norm": 0.4760301411151886, "learning_rate": 4.996900459162961e-05, "loss": 4.5799, "step": 519 }, { "epoch": 0.01588271227855834, "grad_norm": 0.474025160074234, "learning_rate": 4.9968885058559055e-05, "loss": 4.5544, "step": 520 }, { "epoch": 0.015913255956017103, "grad_norm": 0.47160661220550537, "learning_rate": 4.9968765295587135e-05, "loss": 4.5009, "step": 521 }, { "epoch": 0.01594379963347587, "grad_norm": 0.4682590663433075, "learning_rate": 4.996864530271496e-05, "loss": 4.5211, "step": 522 }, { "epoch": 0.015974343310934638, "grad_norm": 0.5003926157951355, "learning_rate": 4.9968525079943616e-05, "loss": 4.5347, "step": 523 }, { "epoch": 0.0160048869883934, "grad_norm": 0.4805755615234375, "learning_rate": 4.996840462727423e-05, "loss": 4.5303, "step": 524 }, { "epoch": 0.01603543066585217, "grad_norm": 0.46491190791130066, "learning_rate": 4.9968283944707915e-05, "loss": 4.5521, "step": 525 }, { "epoch": 0.016065974343310935, "grad_norm": 0.4521999657154083, "learning_rate": 4.9968163032245764e-05, "loss": 4.4818, "step": 526 }, { "epoch": 0.0160965180207697, "grad_norm": 0.45224249362945557, "learning_rate": 4.99680418898889e-05, "loss": 4.497, "step": 527 }, { "epoch": 0.016127061698228466, "grad_norm": 0.4579017460346222, "learning_rate": 4.996792051763843e-05, "loss": 4.4804, "step": 528 }, { "epoch": 0.016157605375687233, "grad_norm": 0.47500887513160706, "learning_rate": 4.996779891549549e-05, "loss": 4.492, "step": 529 }, { "epoch": 0.016188149053146, "grad_norm": 0.46403807401657104, "learning_rate": 4.996767708346118e-05, "loss": 4.5268, "step": 530 }, { "epoch": 0.016218692730604764, "grad_norm": 0.4625454246997833, "learning_rate": 4.9967555021536635e-05, "loss": 4.4498, "step": 531 }, { "epoch": 0.01624923640806353, "grad_norm": 0.4742032289505005, "learning_rate": 4.9967432729722976e-05, "loss": 4.5313, "step": 532 }, { "epoch": 0.016279780085522298, "grad_norm": 0.4693801999092102, "learning_rate": 4.996731020802132e-05, "loss": 4.5585, "step": 533 }, { "epoch": 0.016310323762981062, "grad_norm": 0.4466424882411957, "learning_rate": 4.9967187456432814e-05, "loss": 4.5217, "step": 534 }, { "epoch": 0.01634086744043983, "grad_norm": 0.47670042514801025, "learning_rate": 4.9967064474958566e-05, "loss": 4.5311, "step": 535 }, { "epoch": 0.016371411117898596, "grad_norm": 0.4705662727355957, "learning_rate": 4.996694126359972e-05, "loss": 4.5141, "step": 536 }, { "epoch": 0.01640195479535736, "grad_norm": 0.4662919342517853, "learning_rate": 4.996681782235741e-05, "loss": 4.5598, "step": 537 }, { "epoch": 0.016432498472816127, "grad_norm": 0.4682966470718384, "learning_rate": 4.996669415123277e-05, "loss": 4.4671, "step": 538 }, { "epoch": 0.016463042150274894, "grad_norm": 0.4674915075302124, "learning_rate": 4.996657025022694e-05, "loss": 4.5318, "step": 539 }, { "epoch": 0.016493585827733658, "grad_norm": 0.46091794967651367, "learning_rate": 4.996644611934106e-05, "loss": 4.5488, "step": 540 }, { "epoch": 0.016524129505192425, "grad_norm": 0.4647943675518036, "learning_rate": 4.996632175857629e-05, "loss": 4.5724, "step": 541 }, { "epoch": 0.01655467318265119, "grad_norm": 0.4535447359085083, "learning_rate": 4.9966197167933736e-05, "loss": 4.5108, "step": 542 }, { "epoch": 0.01658521686010996, "grad_norm": 0.45533400774002075, "learning_rate": 4.996607234741458e-05, "loss": 4.4822, "step": 543 }, { "epoch": 0.016615760537568722, "grad_norm": 0.46834418177604675, "learning_rate": 4.9965947297019954e-05, "loss": 4.6133, "step": 544 }, { "epoch": 0.01664630421502749, "grad_norm": 0.4598640501499176, "learning_rate": 4.996582201675102e-05, "loss": 4.5614, "step": 545 }, { "epoch": 0.016676847892486257, "grad_norm": 0.46588921546936035, "learning_rate": 4.9965696506608926e-05, "loss": 4.4726, "step": 546 }, { "epoch": 0.01670739156994502, "grad_norm": 0.48871371150016785, "learning_rate": 4.996557076659483e-05, "loss": 4.5546, "step": 547 }, { "epoch": 0.016737935247403787, "grad_norm": 0.4606657326221466, "learning_rate": 4.996544479670988e-05, "loss": 4.5176, "step": 548 }, { "epoch": 0.016768478924862554, "grad_norm": 0.46695101261138916, "learning_rate": 4.9965318596955255e-05, "loss": 4.5234, "step": 549 }, { "epoch": 0.016799022602321318, "grad_norm": 0.464518278837204, "learning_rate": 4.9965192167332096e-05, "loss": 4.4727, "step": 550 }, { "epoch": 0.016829566279780085, "grad_norm": 0.5034158825874329, "learning_rate": 4.996506550784158e-05, "loss": 4.526, "step": 551 }, { "epoch": 0.016860109957238852, "grad_norm": 0.45259153842926025, "learning_rate": 4.9964938618484875e-05, "loss": 4.5163, "step": 552 }, { "epoch": 0.016890653634697616, "grad_norm": 0.47014254331588745, "learning_rate": 4.9964811499263144e-05, "loss": 4.5468, "step": 553 }, { "epoch": 0.016921197312156383, "grad_norm": 0.45631155371665955, "learning_rate": 4.996468415017755e-05, "loss": 4.4378, "step": 554 }, { "epoch": 0.01695174098961515, "grad_norm": 0.45052528381347656, "learning_rate": 4.996455657122928e-05, "loss": 4.5659, "step": 555 }, { "epoch": 0.016982284667073917, "grad_norm": 0.45571354031562805, "learning_rate": 4.99644287624195e-05, "loss": 4.6095, "step": 556 }, { "epoch": 0.01701282834453268, "grad_norm": 0.47980156540870667, "learning_rate": 4.996430072374939e-05, "loss": 4.5457, "step": 557 }, { "epoch": 0.017043372021991448, "grad_norm": 0.45273005962371826, "learning_rate": 4.9964172455220126e-05, "loss": 4.5298, "step": 558 }, { "epoch": 0.017073915699450215, "grad_norm": 0.4753735065460205, "learning_rate": 4.996404395683289e-05, "loss": 4.5384, "step": 559 }, { "epoch": 0.01710445937690898, "grad_norm": 0.47534772753715515, "learning_rate": 4.996391522858886e-05, "loss": 4.5201, "step": 560 }, { "epoch": 0.017135003054367746, "grad_norm": 0.4610385000705719, "learning_rate": 4.9963786270489244e-05, "loss": 4.5894, "step": 561 }, { "epoch": 0.017165546731826513, "grad_norm": 0.4537050127983093, "learning_rate": 4.9963657082535195e-05, "loss": 4.5746, "step": 562 }, { "epoch": 0.017196090409285276, "grad_norm": 0.46166297793388367, "learning_rate": 4.996352766472794e-05, "loss": 4.5131, "step": 563 }, { "epoch": 0.017226634086744044, "grad_norm": 0.4533979892730713, "learning_rate": 4.996339801706863e-05, "loss": 4.496, "step": 564 }, { "epoch": 0.01725717776420281, "grad_norm": 0.4568382501602173, "learning_rate": 4.996326813955849e-05, "loss": 4.4, "step": 565 }, { "epoch": 0.017287721441661578, "grad_norm": 0.4595445692539215, "learning_rate": 4.996313803219871e-05, "loss": 4.5328, "step": 566 }, { "epoch": 0.01731826511912034, "grad_norm": 0.4382367432117462, "learning_rate": 4.9963007694990474e-05, "loss": 4.4856, "step": 567 }, { "epoch": 0.01734880879657911, "grad_norm": 0.45088765025138855, "learning_rate": 4.9962877127934995e-05, "loss": 4.5262, "step": 568 }, { "epoch": 0.017379352474037876, "grad_norm": 0.45491552352905273, "learning_rate": 4.9962746331033474e-05, "loss": 4.4877, "step": 569 }, { "epoch": 0.01740989615149664, "grad_norm": 0.4657602906227112, "learning_rate": 4.9962615304287116e-05, "loss": 4.5434, "step": 570 }, { "epoch": 0.017440439828955406, "grad_norm": 0.4504329264163971, "learning_rate": 4.9962484047697114e-05, "loss": 4.4938, "step": 571 }, { "epoch": 0.017470983506414173, "grad_norm": 0.45039141178131104, "learning_rate": 4.996235256126469e-05, "loss": 4.4896, "step": 572 }, { "epoch": 0.017501527183872937, "grad_norm": 0.4827897548675537, "learning_rate": 4.996222084499106e-05, "loss": 4.5329, "step": 573 }, { "epoch": 0.017532070861331704, "grad_norm": 0.46392354369163513, "learning_rate": 4.996208889887742e-05, "loss": 4.4584, "step": 574 }, { "epoch": 0.01756261453879047, "grad_norm": 0.44818583130836487, "learning_rate": 4.9961956722924995e-05, "loss": 4.5619, "step": 575 }, { "epoch": 0.017593158216249235, "grad_norm": 0.4487197697162628, "learning_rate": 4.9961824317135e-05, "loss": 4.4591, "step": 576 }, { "epoch": 0.017623701893708002, "grad_norm": 0.4796917140483856, "learning_rate": 4.996169168150866e-05, "loss": 4.417, "step": 577 }, { "epoch": 0.01765424557116677, "grad_norm": 0.452671080827713, "learning_rate": 4.9961558816047186e-05, "loss": 4.4519, "step": 578 }, { "epoch": 0.017684789248625536, "grad_norm": 0.4543212950229645, "learning_rate": 4.99614257207518e-05, "loss": 4.5401, "step": 579 }, { "epoch": 0.0177153329260843, "grad_norm": 0.4528760015964508, "learning_rate": 4.996129239562374e-05, "loss": 4.5211, "step": 580 }, { "epoch": 0.017745876603543067, "grad_norm": 0.4618910253047943, "learning_rate": 4.996115884066423e-05, "loss": 4.5271, "step": 581 }, { "epoch": 0.017776420281001834, "grad_norm": 0.459536612033844, "learning_rate": 4.9961025055874494e-05, "loss": 4.5186, "step": 582 }, { "epoch": 0.017806963958460598, "grad_norm": 0.4664803743362427, "learning_rate": 4.996089104125576e-05, "loss": 4.5058, "step": 583 }, { "epoch": 0.017837507635919365, "grad_norm": 0.46022844314575195, "learning_rate": 4.9960756796809285e-05, "loss": 4.5192, "step": 584 }, { "epoch": 0.017868051313378132, "grad_norm": 0.46366849541664124, "learning_rate": 4.996062232253628e-05, "loss": 4.5189, "step": 585 }, { "epoch": 0.017898594990836895, "grad_norm": 0.4738246202468872, "learning_rate": 4.996048761843799e-05, "loss": 4.5367, "step": 586 }, { "epoch": 0.017929138668295663, "grad_norm": 0.45728814601898193, "learning_rate": 4.9960352684515655e-05, "loss": 4.398, "step": 587 }, { "epoch": 0.01795968234575443, "grad_norm": 0.45516976714134216, "learning_rate": 4.9960217520770516e-05, "loss": 4.4889, "step": 588 }, { "epoch": 0.017990226023213193, "grad_norm": 0.45304691791534424, "learning_rate": 4.996008212720383e-05, "loss": 4.4458, "step": 589 }, { "epoch": 0.01802076970067196, "grad_norm": 0.4505080282688141, "learning_rate": 4.995994650381683e-05, "loss": 4.5352, "step": 590 }, { "epoch": 0.018051313378130728, "grad_norm": 0.4613843560218811, "learning_rate": 4.9959810650610774e-05, "loss": 4.4866, "step": 591 }, { "epoch": 0.018081857055589495, "grad_norm": 0.448640912771225, "learning_rate": 4.99596745675869e-05, "loss": 4.4239, "step": 592 }, { "epoch": 0.018112400733048258, "grad_norm": 0.4470510482788086, "learning_rate": 4.995953825474647e-05, "loss": 4.5156, "step": 593 }, { "epoch": 0.018142944410507025, "grad_norm": 0.45849013328552246, "learning_rate": 4.995940171209075e-05, "loss": 4.5004, "step": 594 }, { "epoch": 0.018173488087965792, "grad_norm": 0.44809919595718384, "learning_rate": 4.9959264939620976e-05, "loss": 4.5024, "step": 595 }, { "epoch": 0.018204031765424556, "grad_norm": 0.449961394071579, "learning_rate": 4.995912793733842e-05, "loss": 4.5258, "step": 596 }, { "epoch": 0.018234575442883323, "grad_norm": 0.44155076146125793, "learning_rate": 4.9958990705244334e-05, "loss": 4.5271, "step": 597 }, { "epoch": 0.01826511912034209, "grad_norm": 0.44106554985046387, "learning_rate": 4.995885324334e-05, "loss": 4.488, "step": 598 }, { "epoch": 0.018295662797800854, "grad_norm": 0.45234063267707825, "learning_rate": 4.9958715551626664e-05, "loss": 4.4656, "step": 599 }, { "epoch": 0.01832620647525962, "grad_norm": 0.459531307220459, "learning_rate": 4.9958577630105604e-05, "loss": 4.5798, "step": 600 }, { "epoch": 0.018356750152718388, "grad_norm": 0.46010151505470276, "learning_rate": 4.995843947877809e-05, "loss": 4.4911, "step": 601 }, { "epoch": 0.01838729383017715, "grad_norm": 0.4512796401977539, "learning_rate": 4.995830109764538e-05, "loss": 4.5361, "step": 602 }, { "epoch": 0.01841783750763592, "grad_norm": 0.4458327293395996, "learning_rate": 4.995816248670877e-05, "loss": 4.5074, "step": 603 }, { "epoch": 0.018448381185094686, "grad_norm": 0.4639643132686615, "learning_rate": 4.995802364596952e-05, "loss": 4.5109, "step": 604 }, { "epoch": 0.018478924862553453, "grad_norm": 0.44587138295173645, "learning_rate": 4.995788457542891e-05, "loss": 4.4281, "step": 605 }, { "epoch": 0.018509468540012217, "grad_norm": 0.46558406949043274, "learning_rate": 4.9957745275088235e-05, "loss": 4.4867, "step": 606 }, { "epoch": 0.018540012217470984, "grad_norm": 0.45090147852897644, "learning_rate": 4.9957605744948765e-05, "loss": 4.5048, "step": 607 }, { "epoch": 0.01857055589492975, "grad_norm": 0.44190967082977295, "learning_rate": 4.9957465985011784e-05, "loss": 4.5058, "step": 608 }, { "epoch": 0.018601099572388514, "grad_norm": 0.46193888783454895, "learning_rate": 4.995732599527858e-05, "loss": 4.4682, "step": 609 }, { "epoch": 0.01863164324984728, "grad_norm": 0.45434409379959106, "learning_rate": 4.9957185775750445e-05, "loss": 4.5101, "step": 610 }, { "epoch": 0.01866218692730605, "grad_norm": 0.44933149218559265, "learning_rate": 4.9957045326428676e-05, "loss": 4.5088, "step": 611 }, { "epoch": 0.018692730604764812, "grad_norm": 0.4409005343914032, "learning_rate": 4.995690464731456e-05, "loss": 4.4326, "step": 612 }, { "epoch": 0.01872327428222358, "grad_norm": 0.47147440910339355, "learning_rate": 4.995676373840938e-05, "loss": 4.4984, "step": 613 }, { "epoch": 0.018753817959682346, "grad_norm": 0.4668456017971039, "learning_rate": 4.9956622599714454e-05, "loss": 4.5815, "step": 614 }, { "epoch": 0.01878436163714111, "grad_norm": 0.4670104384422302, "learning_rate": 4.995648123123107e-05, "loss": 4.4684, "step": 615 }, { "epoch": 0.018814905314599877, "grad_norm": 0.45611193776130676, "learning_rate": 4.995633963296052e-05, "loss": 4.5037, "step": 616 }, { "epoch": 0.018845448992058644, "grad_norm": 0.4557349383831024, "learning_rate": 4.995619780490414e-05, "loss": 4.5544, "step": 617 }, { "epoch": 0.01887599266951741, "grad_norm": 0.4590979814529419, "learning_rate": 4.99560557470632e-05, "loss": 4.5364, "step": 618 }, { "epoch": 0.018906536346976175, "grad_norm": 0.4612823724746704, "learning_rate": 4.995591345943903e-05, "loss": 4.537, "step": 619 }, { "epoch": 0.018937080024434942, "grad_norm": 0.4501083493232727, "learning_rate": 4.995577094203293e-05, "loss": 4.568, "step": 620 }, { "epoch": 0.01896762370189371, "grad_norm": 0.4443254768848419, "learning_rate": 4.9955628194846224e-05, "loss": 4.4824, "step": 621 }, { "epoch": 0.018998167379352473, "grad_norm": 0.4539344608783722, "learning_rate": 4.995548521788021e-05, "loss": 4.3939, "step": 622 }, { "epoch": 0.01902871105681124, "grad_norm": 0.48574015498161316, "learning_rate": 4.995534201113622e-05, "loss": 4.4804, "step": 623 }, { "epoch": 0.019059254734270007, "grad_norm": 0.4440174996852875, "learning_rate": 4.995519857461556e-05, "loss": 4.4591, "step": 624 }, { "epoch": 0.01908979841172877, "grad_norm": 0.4522970914840698, "learning_rate": 4.9955054908319555e-05, "loss": 4.5246, "step": 625 }, { "epoch": 0.019120342089187538, "grad_norm": 0.4400783181190491, "learning_rate": 4.995491101224953e-05, "loss": 4.506, "step": 626 }, { "epoch": 0.019150885766646305, "grad_norm": 0.4564816653728485, "learning_rate": 4.995476688640681e-05, "loss": 4.5814, "step": 627 }, { "epoch": 0.01918142944410507, "grad_norm": 0.4446890652179718, "learning_rate": 4.995462253079272e-05, "loss": 4.4695, "step": 628 }, { "epoch": 0.019211973121563836, "grad_norm": 0.46327051520347595, "learning_rate": 4.9954477945408595e-05, "loss": 4.5556, "step": 629 }, { "epoch": 0.019242516799022603, "grad_norm": 0.4713856875896454, "learning_rate": 4.995433313025575e-05, "loss": 4.5723, "step": 630 }, { "epoch": 0.01927306047648137, "grad_norm": 0.4823109805583954, "learning_rate": 4.995418808533554e-05, "loss": 4.5204, "step": 631 }, { "epoch": 0.019303604153940133, "grad_norm": 0.45977020263671875, "learning_rate": 4.995404281064929e-05, "loss": 4.5237, "step": 632 }, { "epoch": 0.0193341478313989, "grad_norm": 0.45673686265945435, "learning_rate": 4.9953897306198326e-05, "loss": 4.4933, "step": 633 }, { "epoch": 0.019364691508857668, "grad_norm": 0.4518212378025055, "learning_rate": 4.995375157198402e-05, "loss": 4.4499, "step": 634 }, { "epoch": 0.01939523518631643, "grad_norm": 0.4574190676212311, "learning_rate": 4.995360560800767e-05, "loss": 4.5375, "step": 635 }, { "epoch": 0.0194257788637752, "grad_norm": 0.4580807089805603, "learning_rate": 4.995345941427066e-05, "loss": 4.4671, "step": 636 }, { "epoch": 0.019456322541233965, "grad_norm": 0.45550358295440674, "learning_rate": 4.995331299077432e-05, "loss": 4.4497, "step": 637 }, { "epoch": 0.01948686621869273, "grad_norm": 0.471762090921402, "learning_rate": 4.9953166337519985e-05, "loss": 4.5087, "step": 638 }, { "epoch": 0.019517409896151496, "grad_norm": 0.4701639413833618, "learning_rate": 4.995301945450902e-05, "loss": 4.4758, "step": 639 }, { "epoch": 0.019547953573610263, "grad_norm": 0.493457168340683, "learning_rate": 4.9952872341742785e-05, "loss": 4.4947, "step": 640 }, { "epoch": 0.01957849725106903, "grad_norm": 0.46456179022789, "learning_rate": 4.9952724999222616e-05, "loss": 4.4547, "step": 641 }, { "epoch": 0.019609040928527794, "grad_norm": 0.4468267560005188, "learning_rate": 4.995257742694989e-05, "loss": 4.5154, "step": 642 }, { "epoch": 0.01963958460598656, "grad_norm": 0.47805309295654297, "learning_rate": 4.995242962492594e-05, "loss": 4.4356, "step": 643 }, { "epoch": 0.019670128283445328, "grad_norm": 0.4771351218223572, "learning_rate": 4.995228159315215e-05, "loss": 4.4638, "step": 644 }, { "epoch": 0.019700671960904092, "grad_norm": 0.4487154185771942, "learning_rate": 4.995213333162987e-05, "loss": 4.4932, "step": 645 }, { "epoch": 0.01973121563836286, "grad_norm": 0.46226656436920166, "learning_rate": 4.9951984840360464e-05, "loss": 4.5883, "step": 646 }, { "epoch": 0.019761759315821626, "grad_norm": 0.47253984212875366, "learning_rate": 4.995183611934532e-05, "loss": 4.5114, "step": 647 }, { "epoch": 0.01979230299328039, "grad_norm": 0.4602360725402832, "learning_rate": 4.995168716858578e-05, "loss": 4.4941, "step": 648 }, { "epoch": 0.019822846670739157, "grad_norm": 0.45173484086990356, "learning_rate": 4.995153798808323e-05, "loss": 4.5526, "step": 649 }, { "epoch": 0.019853390348197924, "grad_norm": 0.4553060531616211, "learning_rate": 4.9951388577839044e-05, "loss": 4.5182, "step": 650 }, { "epoch": 0.019883934025656688, "grad_norm": 0.47702139616012573, "learning_rate": 4.995123893785459e-05, "loss": 4.4933, "step": 651 }, { "epoch": 0.019914477703115455, "grad_norm": 0.4556225538253784, "learning_rate": 4.995108906813125e-05, "loss": 4.4528, "step": 652 }, { "epoch": 0.01994502138057422, "grad_norm": 0.4365609288215637, "learning_rate": 4.9950938968670416e-05, "loss": 4.5508, "step": 653 }, { "epoch": 0.01997556505803299, "grad_norm": 0.46144869923591614, "learning_rate": 4.995078863947344e-05, "loss": 4.4977, "step": 654 }, { "epoch": 0.020006108735491752, "grad_norm": 0.48121586441993713, "learning_rate": 4.9950638080541733e-05, "loss": 4.5225, "step": 655 }, { "epoch": 0.02003665241295052, "grad_norm": 0.45144274830818176, "learning_rate": 4.995048729187668e-05, "loss": 4.467, "step": 656 }, { "epoch": 0.020067196090409287, "grad_norm": 0.445926308631897, "learning_rate": 4.995033627347965e-05, "loss": 4.3556, "step": 657 }, { "epoch": 0.02009773976786805, "grad_norm": 0.46426627039909363, "learning_rate": 4.9950185025352056e-05, "loss": 4.4963, "step": 658 }, { "epoch": 0.020128283445326817, "grad_norm": 0.4734305441379547, "learning_rate": 4.995003354749528e-05, "loss": 4.5252, "step": 659 }, { "epoch": 0.020158827122785584, "grad_norm": 0.44871091842651367, "learning_rate": 4.9949881839910704e-05, "loss": 4.4842, "step": 660 }, { "epoch": 0.020189370800244348, "grad_norm": 0.4665108919143677, "learning_rate": 4.994972990259975e-05, "loss": 4.4716, "step": 661 }, { "epoch": 0.020219914477703115, "grad_norm": 0.45041853189468384, "learning_rate": 4.99495777355638e-05, "loss": 4.4932, "step": 662 }, { "epoch": 0.020250458155161882, "grad_norm": 0.4504912495613098, "learning_rate": 4.994942533880427e-05, "loss": 4.5374, "step": 663 }, { "epoch": 0.020281001832620646, "grad_norm": 0.44862863421440125, "learning_rate": 4.9949272712322545e-05, "loss": 4.5464, "step": 664 }, { "epoch": 0.020311545510079413, "grad_norm": 0.46906349062919617, "learning_rate": 4.9949119856120037e-05, "loss": 4.528, "step": 665 }, { "epoch": 0.02034208918753818, "grad_norm": 0.4710213541984558, "learning_rate": 4.994896677019816e-05, "loss": 4.5391, "step": 666 }, { "epoch": 0.020372632864996947, "grad_norm": 0.45288267731666565, "learning_rate": 4.994881345455831e-05, "loss": 4.52, "step": 667 }, { "epoch": 0.02040317654245571, "grad_norm": 0.4533650577068329, "learning_rate": 4.994865990920191e-05, "loss": 4.5581, "step": 668 }, { "epoch": 0.020433720219914478, "grad_norm": 0.4465511441230774, "learning_rate": 4.994850613413038e-05, "loss": 4.5316, "step": 669 }, { "epoch": 0.020464263897373245, "grad_norm": 0.4432264566421509, "learning_rate": 4.9948352129345116e-05, "loss": 4.4723, "step": 670 }, { "epoch": 0.02049480757483201, "grad_norm": 0.4472845196723938, "learning_rate": 4.9948197894847546e-05, "loss": 4.5209, "step": 671 }, { "epoch": 0.020525351252290776, "grad_norm": 0.44247952103614807, "learning_rate": 4.99480434306391e-05, "loss": 4.4091, "step": 672 }, { "epoch": 0.020555894929749543, "grad_norm": 0.451898455619812, "learning_rate": 4.994788873672119e-05, "loss": 4.4881, "step": 673 }, { "epoch": 0.020586438607208307, "grad_norm": 0.44659343361854553, "learning_rate": 4.994773381309523e-05, "loss": 4.4444, "step": 674 }, { "epoch": 0.020616982284667074, "grad_norm": 0.44923242926597595, "learning_rate": 4.994757865976267e-05, "loss": 4.4676, "step": 675 }, { "epoch": 0.02064752596212584, "grad_norm": 0.4577009379863739, "learning_rate": 4.9947423276724924e-05, "loss": 4.4451, "step": 676 }, { "epoch": 0.020678069639584604, "grad_norm": 0.455472856760025, "learning_rate": 4.994726766398342e-05, "loss": 4.5211, "step": 677 }, { "epoch": 0.02070861331704337, "grad_norm": 0.4598701596260071, "learning_rate": 4.9947111821539605e-05, "loss": 4.5397, "step": 678 }, { "epoch": 0.02073915699450214, "grad_norm": 0.45120251178741455, "learning_rate": 4.9946955749394895e-05, "loss": 4.4961, "step": 679 }, { "epoch": 0.020769700671960906, "grad_norm": 0.4574894309043884, "learning_rate": 4.994679944755075e-05, "loss": 4.554, "step": 680 }, { "epoch": 0.02080024434941967, "grad_norm": 0.44177180528640747, "learning_rate": 4.9946642916008584e-05, "loss": 4.5514, "step": 681 }, { "epoch": 0.020830788026878436, "grad_norm": 0.45650357007980347, "learning_rate": 4.9946486154769855e-05, "loss": 4.3921, "step": 682 }, { "epoch": 0.020861331704337203, "grad_norm": 0.4510774314403534, "learning_rate": 4.9946329163836005e-05, "loss": 4.4846, "step": 683 }, { "epoch": 0.020891875381795967, "grad_norm": 0.4541640877723694, "learning_rate": 4.994617194320846e-05, "loss": 4.6125, "step": 684 }, { "epoch": 0.020922419059254734, "grad_norm": 0.44344162940979004, "learning_rate": 4.994601449288871e-05, "loss": 4.5708, "step": 685 }, { "epoch": 0.0209529627367135, "grad_norm": 0.43588224053382874, "learning_rate": 4.994585681287816e-05, "loss": 4.4999, "step": 686 }, { "epoch": 0.020983506414172265, "grad_norm": 0.44707342982292175, "learning_rate": 4.994569890317828e-05, "loss": 4.5108, "step": 687 }, { "epoch": 0.021014050091631032, "grad_norm": 0.45676368474960327, "learning_rate": 4.9945540763790535e-05, "loss": 4.4569, "step": 688 }, { "epoch": 0.0210445937690898, "grad_norm": 0.44143378734588623, "learning_rate": 4.994538239471636e-05, "loss": 4.5097, "step": 689 }, { "epoch": 0.021075137446548563, "grad_norm": 0.4566059112548828, "learning_rate": 4.994522379595723e-05, "loss": 4.5758, "step": 690 }, { "epoch": 0.02110568112400733, "grad_norm": 0.4373421370983124, "learning_rate": 4.99450649675146e-05, "loss": 4.5072, "step": 691 }, { "epoch": 0.021136224801466097, "grad_norm": 0.4592226445674896, "learning_rate": 4.9944905909389924e-05, "loss": 4.4962, "step": 692 }, { "epoch": 0.021166768478924864, "grad_norm": 0.45226162672042847, "learning_rate": 4.994474662158468e-05, "loss": 4.5196, "step": 693 }, { "epoch": 0.021197312156383628, "grad_norm": 0.45795151591300964, "learning_rate": 4.994458710410033e-05, "loss": 4.5059, "step": 694 }, { "epoch": 0.021227855833842395, "grad_norm": 0.45573630928993225, "learning_rate": 4.994442735693834e-05, "loss": 4.5028, "step": 695 }, { "epoch": 0.021258399511301162, "grad_norm": 0.45250943303108215, "learning_rate": 4.994426738010018e-05, "loss": 4.4724, "step": 696 }, { "epoch": 0.021288943188759926, "grad_norm": 0.4472526013851166, "learning_rate": 4.994410717358732e-05, "loss": 4.5295, "step": 697 }, { "epoch": 0.021319486866218693, "grad_norm": 0.45732253789901733, "learning_rate": 4.994394673740125e-05, "loss": 4.4608, "step": 698 }, { "epoch": 0.02135003054367746, "grad_norm": 0.4543858468532562, "learning_rate": 4.994378607154343e-05, "loss": 4.518, "step": 699 }, { "epoch": 0.021380574221136223, "grad_norm": 0.4623492360115051, "learning_rate": 4.994362517601535e-05, "loss": 4.5139, "step": 700 }, { "epoch": 0.02141111789859499, "grad_norm": 0.4623468518257141, "learning_rate": 4.9943464050818496e-05, "loss": 4.4712, "step": 701 }, { "epoch": 0.021441661576053758, "grad_norm": 0.4627689719200134, "learning_rate": 4.9943302695954334e-05, "loss": 4.5094, "step": 702 }, { "epoch": 0.021472205253512525, "grad_norm": 0.4441133439540863, "learning_rate": 4.9943141111424364e-05, "loss": 4.4271, "step": 703 }, { "epoch": 0.021502748930971288, "grad_norm": 0.4600456655025482, "learning_rate": 4.9942979297230063e-05, "loss": 4.494, "step": 704 }, { "epoch": 0.021533292608430055, "grad_norm": 0.46562978625297546, "learning_rate": 4.994281725337293e-05, "loss": 4.5272, "step": 705 }, { "epoch": 0.021563836285888822, "grad_norm": 0.44879257678985596, "learning_rate": 4.994265497985446e-05, "loss": 4.4472, "step": 706 }, { "epoch": 0.021594379963347586, "grad_norm": 0.45676347613334656, "learning_rate": 4.994249247667614e-05, "loss": 4.5287, "step": 707 }, { "epoch": 0.021624923640806353, "grad_norm": 0.4560583233833313, "learning_rate": 4.994232974383946e-05, "loss": 4.4692, "step": 708 }, { "epoch": 0.02165546731826512, "grad_norm": 0.4480816125869751, "learning_rate": 4.994216678134593e-05, "loss": 4.5268, "step": 709 }, { "epoch": 0.021686010995723884, "grad_norm": 0.4444595277309418, "learning_rate": 4.994200358919705e-05, "loss": 4.5097, "step": 710 }, { "epoch": 0.02171655467318265, "grad_norm": 0.4572552740573883, "learning_rate": 4.9941840167394317e-05, "loss": 4.5001, "step": 711 }, { "epoch": 0.021747098350641418, "grad_norm": 0.4394039511680603, "learning_rate": 4.994167651593924e-05, "loss": 4.4473, "step": 712 }, { "epoch": 0.021777642028100182, "grad_norm": 0.46040263772010803, "learning_rate": 4.994151263483332e-05, "loss": 4.4972, "step": 713 }, { "epoch": 0.02180818570555895, "grad_norm": 0.4838213622570038, "learning_rate": 4.994134852407807e-05, "loss": 4.5616, "step": 714 }, { "epoch": 0.021838729383017716, "grad_norm": 0.469569593667984, "learning_rate": 4.994118418367499e-05, "loss": 4.5707, "step": 715 }, { "epoch": 0.021869273060476483, "grad_norm": 0.4522424638271332, "learning_rate": 4.994101961362562e-05, "loss": 4.393, "step": 716 }, { "epoch": 0.021899816737935247, "grad_norm": 0.4424279034137726, "learning_rate": 4.994085481393146e-05, "loss": 4.5046, "step": 717 }, { "epoch": 0.021930360415394014, "grad_norm": 0.45109260082244873, "learning_rate": 4.994068978459402e-05, "loss": 4.5733, "step": 718 }, { "epoch": 0.02196090409285278, "grad_norm": 0.467130571603775, "learning_rate": 4.9940524525614816e-05, "loss": 4.5593, "step": 719 }, { "epoch": 0.021991447770311544, "grad_norm": 0.4374151825904846, "learning_rate": 4.994035903699539e-05, "loss": 4.4598, "step": 720 }, { "epoch": 0.02202199144777031, "grad_norm": 0.4659610688686371, "learning_rate": 4.994019331873726e-05, "loss": 4.4736, "step": 721 }, { "epoch": 0.02205253512522908, "grad_norm": 0.45110759139060974, "learning_rate": 4.994002737084194e-05, "loss": 4.4609, "step": 722 }, { "epoch": 0.022083078802687842, "grad_norm": 0.4614379107952118, "learning_rate": 4.993986119331096e-05, "loss": 4.4704, "step": 723 }, { "epoch": 0.02211362248014661, "grad_norm": 0.4590345323085785, "learning_rate": 4.993969478614587e-05, "loss": 4.5187, "step": 724 }, { "epoch": 0.022144166157605377, "grad_norm": 0.45520660281181335, "learning_rate": 4.993952814934818e-05, "loss": 4.5266, "step": 725 }, { "epoch": 0.02217470983506414, "grad_norm": 0.45546719431877136, "learning_rate": 4.993936128291943e-05, "loss": 4.4643, "step": 726 }, { "epoch": 0.022205253512522907, "grad_norm": 0.4665417969226837, "learning_rate": 4.993919418686116e-05, "loss": 4.4867, "step": 727 }, { "epoch": 0.022235797189981674, "grad_norm": 0.4822233319282532, "learning_rate": 4.993902686117491e-05, "loss": 4.5499, "step": 728 }, { "epoch": 0.02226634086744044, "grad_norm": 0.47178107500076294, "learning_rate": 4.9938859305862206e-05, "loss": 4.4991, "step": 729 }, { "epoch": 0.022296884544899205, "grad_norm": 0.48529815673828125, "learning_rate": 4.993869152092461e-05, "loss": 4.3821, "step": 730 }, { "epoch": 0.022327428222357972, "grad_norm": 0.47320929169654846, "learning_rate": 4.993852350636366e-05, "loss": 4.5548, "step": 731 }, { "epoch": 0.02235797189981674, "grad_norm": 0.4617864489555359, "learning_rate": 4.99383552621809e-05, "loss": 4.4888, "step": 732 }, { "epoch": 0.022388515577275503, "grad_norm": 0.4548394978046417, "learning_rate": 4.9938186788377885e-05, "loss": 4.499, "step": 733 }, { "epoch": 0.02241905925473427, "grad_norm": 0.4537191092967987, "learning_rate": 4.993801808495615e-05, "loss": 4.4659, "step": 734 }, { "epoch": 0.022449602932193037, "grad_norm": 0.47669973969459534, "learning_rate": 4.993784915191727e-05, "loss": 4.501, "step": 735 }, { "epoch": 0.0224801466096518, "grad_norm": 0.4550668001174927, "learning_rate": 4.99376799892628e-05, "loss": 4.4793, "step": 736 }, { "epoch": 0.022510690287110568, "grad_norm": 0.46915173530578613, "learning_rate": 4.993751059699428e-05, "loss": 4.5883, "step": 737 }, { "epoch": 0.022541233964569335, "grad_norm": 0.45221200585365295, "learning_rate": 4.993734097511327e-05, "loss": 4.465, "step": 738 }, { "epoch": 0.0225717776420281, "grad_norm": 0.46373969316482544, "learning_rate": 4.993717112362135e-05, "loss": 4.5454, "step": 739 }, { "epoch": 0.022602321319486866, "grad_norm": 0.4546022415161133, "learning_rate": 4.9937001042520074e-05, "loss": 4.4617, "step": 740 }, { "epoch": 0.022632864996945633, "grad_norm": 0.453151136636734, "learning_rate": 4.9936830731811e-05, "loss": 4.5515, "step": 741 }, { "epoch": 0.0226634086744044, "grad_norm": 0.46986520290374756, "learning_rate": 4.993666019149571e-05, "loss": 4.4672, "step": 742 }, { "epoch": 0.022693952351863163, "grad_norm": 0.4647936224937439, "learning_rate": 4.9936489421575774e-05, "loss": 4.5135, "step": 743 }, { "epoch": 0.02272449602932193, "grad_norm": 0.46450912952423096, "learning_rate": 4.993631842205275e-05, "loss": 4.4817, "step": 744 }, { "epoch": 0.022755039706780698, "grad_norm": 0.4475068747997284, "learning_rate": 4.993614719292822e-05, "loss": 4.5115, "step": 745 }, { "epoch": 0.02278558338423946, "grad_norm": 0.4440170228481293, "learning_rate": 4.9935975734203764e-05, "loss": 4.4722, "step": 746 }, { "epoch": 0.02281612706169823, "grad_norm": 0.4490155577659607, "learning_rate": 4.9935804045880964e-05, "loss": 4.4452, "step": 747 }, { "epoch": 0.022846670739156996, "grad_norm": 0.44843029975891113, "learning_rate": 4.9935632127961394e-05, "loss": 4.6098, "step": 748 }, { "epoch": 0.02287721441661576, "grad_norm": 0.45605048537254333, "learning_rate": 4.993545998044664e-05, "loss": 4.4885, "step": 749 }, { "epoch": 0.022907758094074526, "grad_norm": 0.43447253108024597, "learning_rate": 4.9935287603338276e-05, "loss": 4.4477, "step": 750 }, { "epoch": 0.022938301771533293, "grad_norm": 0.4530479311943054, "learning_rate": 4.9935114996637906e-05, "loss": 4.586, "step": 751 }, { "epoch": 0.022968845448992057, "grad_norm": 0.4377773106098175, "learning_rate": 4.993494216034711e-05, "loss": 4.5148, "step": 752 }, { "epoch": 0.022999389126450824, "grad_norm": 0.4563885033130646, "learning_rate": 4.993476909446748e-05, "loss": 4.4729, "step": 753 }, { "epoch": 0.02302993280390959, "grad_norm": 0.4430772364139557, "learning_rate": 4.993459579900062e-05, "loss": 4.5169, "step": 754 }, { "epoch": 0.023060476481368358, "grad_norm": 0.4443345069885254, "learning_rate": 4.99344222739481e-05, "loss": 4.4811, "step": 755 }, { "epoch": 0.023091020158827122, "grad_norm": 0.4522332549095154, "learning_rate": 4.993424851931154e-05, "loss": 4.5142, "step": 756 }, { "epoch": 0.02312156383628589, "grad_norm": 0.4367412328720093, "learning_rate": 4.993407453509255e-05, "loss": 4.4769, "step": 757 }, { "epoch": 0.023152107513744656, "grad_norm": 0.45920461416244507, "learning_rate": 4.9933900321292695e-05, "loss": 4.5415, "step": 758 }, { "epoch": 0.02318265119120342, "grad_norm": 0.44298094511032104, "learning_rate": 4.993372587791361e-05, "loss": 4.3485, "step": 759 }, { "epoch": 0.023213194868662187, "grad_norm": 0.4489091634750366, "learning_rate": 4.9933551204956886e-05, "loss": 4.5078, "step": 760 }, { "epoch": 0.023243738546120954, "grad_norm": 0.4549529552459717, "learning_rate": 4.993337630242414e-05, "loss": 4.5531, "step": 761 }, { "epoch": 0.023274282223579718, "grad_norm": 0.45155590772628784, "learning_rate": 4.993320117031698e-05, "loss": 4.4628, "step": 762 }, { "epoch": 0.023304825901038485, "grad_norm": 0.4607466757297516, "learning_rate": 4.993302580863701e-05, "loss": 4.4352, "step": 763 }, { "epoch": 0.023335369578497252, "grad_norm": 0.44011980295181274, "learning_rate": 4.9932850217385864e-05, "loss": 4.5466, "step": 764 }, { "epoch": 0.023365913255956015, "grad_norm": 0.44751212000846863, "learning_rate": 4.993267439656514e-05, "loss": 4.5592, "step": 765 }, { "epoch": 0.023396456933414782, "grad_norm": 0.46046462655067444, "learning_rate": 4.993249834617647e-05, "loss": 4.4666, "step": 766 }, { "epoch": 0.02342700061087355, "grad_norm": 0.4483202397823334, "learning_rate": 4.993232206622146e-05, "loss": 4.4634, "step": 767 }, { "epoch": 0.023457544288332317, "grad_norm": 0.43498143553733826, "learning_rate": 4.9932145556701744e-05, "loss": 4.5389, "step": 768 }, { "epoch": 0.02348808796579108, "grad_norm": 0.4436050057411194, "learning_rate": 4.9931968817618944e-05, "loss": 4.4166, "step": 769 }, { "epoch": 0.023518631643249847, "grad_norm": 0.4453854560852051, "learning_rate": 4.993179184897469e-05, "loss": 4.4304, "step": 770 }, { "epoch": 0.023549175320708614, "grad_norm": 0.44462698698043823, "learning_rate": 4.993161465077061e-05, "loss": 4.4471, "step": 771 }, { "epoch": 0.023579718998167378, "grad_norm": 0.4383271038532257, "learning_rate": 4.9931437223008334e-05, "loss": 4.5004, "step": 772 }, { "epoch": 0.023610262675626145, "grad_norm": 0.4599258005619049, "learning_rate": 4.9931259565689506e-05, "loss": 4.532, "step": 773 }, { "epoch": 0.023640806353084912, "grad_norm": 0.45905986428260803, "learning_rate": 4.9931081678815736e-05, "loss": 4.5053, "step": 774 }, { "epoch": 0.023671350030543676, "grad_norm": 0.4407168924808502, "learning_rate": 4.993090356238869e-05, "loss": 4.4741, "step": 775 }, { "epoch": 0.023701893708002443, "grad_norm": 0.4461548626422882, "learning_rate": 4.9930725216409994e-05, "loss": 4.4999, "step": 776 }, { "epoch": 0.02373243738546121, "grad_norm": 0.4494370222091675, "learning_rate": 4.9930546640881294e-05, "loss": 4.541, "step": 777 }, { "epoch": 0.023762981062919977, "grad_norm": 0.4555304944515228, "learning_rate": 4.993036783580424e-05, "loss": 4.513, "step": 778 }, { "epoch": 0.02379352474037874, "grad_norm": 0.45405393838882446, "learning_rate": 4.993018880118046e-05, "loss": 4.5544, "step": 779 }, { "epoch": 0.023824068417837508, "grad_norm": 0.4425373673439026, "learning_rate": 4.9930009537011614e-05, "loss": 4.4654, "step": 780 }, { "epoch": 0.023854612095296275, "grad_norm": 0.4414350688457489, "learning_rate": 4.9929830043299355e-05, "loss": 4.5069, "step": 781 }, { "epoch": 0.02388515577275504, "grad_norm": 0.44578254222869873, "learning_rate": 4.992965032004534e-05, "loss": 4.5422, "step": 782 }, { "epoch": 0.023915699450213806, "grad_norm": 0.45843806862831116, "learning_rate": 4.992947036725121e-05, "loss": 4.3993, "step": 783 }, { "epoch": 0.023946243127672573, "grad_norm": 0.45093265175819397, "learning_rate": 4.992929018491863e-05, "loss": 4.397, "step": 784 }, { "epoch": 0.023976786805131337, "grad_norm": 0.4451911747455597, "learning_rate": 4.9929109773049255e-05, "loss": 4.457, "step": 785 }, { "epoch": 0.024007330482590104, "grad_norm": 0.4503037929534912, "learning_rate": 4.992892913164475e-05, "loss": 4.5535, "step": 786 }, { "epoch": 0.02403787416004887, "grad_norm": 0.47567111253738403, "learning_rate": 4.992874826070678e-05, "loss": 4.4983, "step": 787 }, { "epoch": 0.024068417837507634, "grad_norm": 0.4570143222808838, "learning_rate": 4.992856716023701e-05, "loss": 4.4558, "step": 788 }, { "epoch": 0.0240989615149664, "grad_norm": 0.45248305797576904, "learning_rate": 4.9928385830237104e-05, "loss": 4.523, "step": 789 }, { "epoch": 0.02412950519242517, "grad_norm": 0.4600813090801239, "learning_rate": 4.992820427070873e-05, "loss": 4.516, "step": 790 }, { "epoch": 0.024160048869883936, "grad_norm": 0.46030673384666443, "learning_rate": 4.992802248165356e-05, "loss": 4.4465, "step": 791 }, { "epoch": 0.0241905925473427, "grad_norm": 0.43555551767349243, "learning_rate": 4.992784046307328e-05, "loss": 4.5107, "step": 792 }, { "epoch": 0.024221136224801466, "grad_norm": 0.4449869394302368, "learning_rate": 4.9927658214969554e-05, "loss": 4.4243, "step": 793 }, { "epoch": 0.024251679902260233, "grad_norm": 0.43943798542022705, "learning_rate": 4.9927475737344055e-05, "loss": 4.4882, "step": 794 }, { "epoch": 0.024282223579718997, "grad_norm": 0.45256415009498596, "learning_rate": 4.992729303019847e-05, "loss": 4.5048, "step": 795 }, { "epoch": 0.024312767257177764, "grad_norm": 0.4551859498023987, "learning_rate": 4.992711009353449e-05, "loss": 4.4996, "step": 796 }, { "epoch": 0.02434331093463653, "grad_norm": 0.44811370968818665, "learning_rate": 4.9926926927353784e-05, "loss": 4.5431, "step": 797 }, { "epoch": 0.024373854612095295, "grad_norm": 0.4370417892932892, "learning_rate": 4.9926743531658046e-05, "loss": 4.4266, "step": 798 }, { "epoch": 0.024404398289554062, "grad_norm": 0.4770367741584778, "learning_rate": 4.9926559906448966e-05, "loss": 4.4832, "step": 799 }, { "epoch": 0.02443494196701283, "grad_norm": 0.43943309783935547, "learning_rate": 4.992637605172823e-05, "loss": 4.5322, "step": 800 }, { "epoch": 0.024465485644471593, "grad_norm": 0.44749948382377625, "learning_rate": 4.9926191967497545e-05, "loss": 4.4861, "step": 801 }, { "epoch": 0.02449602932193036, "grad_norm": 0.4591645896434784, "learning_rate": 4.992600765375859e-05, "loss": 4.4731, "step": 802 }, { "epoch": 0.024526572999389127, "grad_norm": 0.4364190697669983, "learning_rate": 4.992582311051306e-05, "loss": 4.4969, "step": 803 }, { "epoch": 0.024557116676847894, "grad_norm": 0.4369507133960724, "learning_rate": 4.992563833776267e-05, "loss": 4.5354, "step": 804 }, { "epoch": 0.024587660354306658, "grad_norm": 0.44160327315330505, "learning_rate": 4.99254533355091e-05, "loss": 4.4522, "step": 805 }, { "epoch": 0.024618204031765425, "grad_norm": 0.4479551315307617, "learning_rate": 4.9925268103754076e-05, "loss": 4.479, "step": 806 }, { "epoch": 0.024648747709224192, "grad_norm": 0.4445747435092926, "learning_rate": 4.992508264249929e-05, "loss": 4.4314, "step": 807 }, { "epoch": 0.024679291386682956, "grad_norm": 0.4472757577896118, "learning_rate": 4.992489695174645e-05, "loss": 4.4775, "step": 808 }, { "epoch": 0.024709835064141723, "grad_norm": 0.46131840348243713, "learning_rate": 4.9924711031497276e-05, "loss": 4.5326, "step": 809 }, { "epoch": 0.02474037874160049, "grad_norm": 0.4496995508670807, "learning_rate": 4.992452488175346e-05, "loss": 4.5268, "step": 810 }, { "epoch": 0.024770922419059253, "grad_norm": 0.44877296686172485, "learning_rate": 4.9924338502516746e-05, "loss": 4.4875, "step": 811 }, { "epoch": 0.02480146609651802, "grad_norm": 0.46303868293762207, "learning_rate": 4.992415189378882e-05, "loss": 4.4078, "step": 812 }, { "epoch": 0.024832009773976788, "grad_norm": 0.45203346014022827, "learning_rate": 4.992396505557142e-05, "loss": 4.4635, "step": 813 }, { "epoch": 0.02486255345143555, "grad_norm": 0.44917210936546326, "learning_rate": 4.992377798786625e-05, "loss": 4.4592, "step": 814 }, { "epoch": 0.02489309712889432, "grad_norm": 0.4530032277107239, "learning_rate": 4.9923590690675046e-05, "loss": 4.4724, "step": 815 }, { "epoch": 0.024923640806353085, "grad_norm": 0.4470662772655487, "learning_rate": 4.992340316399953e-05, "loss": 4.4749, "step": 816 }, { "epoch": 0.024954184483811852, "grad_norm": 0.4510047435760498, "learning_rate": 4.992321540784143e-05, "loss": 4.4317, "step": 817 }, { "epoch": 0.024984728161270616, "grad_norm": 0.4549791216850281, "learning_rate": 4.9923027422202465e-05, "loss": 4.5114, "step": 818 }, { "epoch": 0.025015271838729383, "grad_norm": 0.4495481848716736, "learning_rate": 4.992283920708437e-05, "loss": 4.4899, "step": 819 }, { "epoch": 0.02504581551618815, "grad_norm": 0.44863760471343994, "learning_rate": 4.992265076248889e-05, "loss": 4.5014, "step": 820 }, { "epoch": 0.025076359193646914, "grad_norm": 0.4624579846858978, "learning_rate": 4.992246208841774e-05, "loss": 4.532, "step": 821 }, { "epoch": 0.02510690287110568, "grad_norm": 0.44618335366249084, "learning_rate": 4.992227318487268e-05, "loss": 4.443, "step": 822 }, { "epoch": 0.025137446548564448, "grad_norm": 0.443025141954422, "learning_rate": 4.992208405185543e-05, "loss": 4.4814, "step": 823 }, { "epoch": 0.025167990226023212, "grad_norm": 0.4438301920890808, "learning_rate": 4.992189468936773e-05, "loss": 4.5637, "step": 824 }, { "epoch": 0.02519853390348198, "grad_norm": 0.4546510577201843, "learning_rate": 4.9921705097411344e-05, "loss": 4.5728, "step": 825 }, { "epoch": 0.025229077580940746, "grad_norm": 0.46709492802619934, "learning_rate": 4.992151527598801e-05, "loss": 4.4912, "step": 826 }, { "epoch": 0.02525962125839951, "grad_norm": 0.4583122432231903, "learning_rate": 4.992132522509946e-05, "loss": 4.5423, "step": 827 }, { "epoch": 0.025290164935858277, "grad_norm": 0.42949178814888, "learning_rate": 4.992113494474746e-05, "loss": 4.4674, "step": 828 }, { "epoch": 0.025320708613317044, "grad_norm": 0.4487088918685913, "learning_rate": 4.992094443493375e-05, "loss": 4.5117, "step": 829 }, { "epoch": 0.02535125229077581, "grad_norm": 0.43920305371284485, "learning_rate": 4.9920753695660106e-05, "loss": 4.496, "step": 830 }, { "epoch": 0.025381795968234575, "grad_norm": 0.46549543738365173, "learning_rate": 4.9920562726928257e-05, "loss": 4.5302, "step": 831 }, { "epoch": 0.02541233964569334, "grad_norm": 0.4388175308704376, "learning_rate": 4.992037152873998e-05, "loss": 4.5281, "step": 832 }, { "epoch": 0.02544288332315211, "grad_norm": 0.42893606424331665, "learning_rate": 4.992018010109702e-05, "loss": 4.3792, "step": 833 }, { "epoch": 0.025473427000610872, "grad_norm": 0.44954994320869446, "learning_rate": 4.991998844400116e-05, "loss": 4.4317, "step": 834 }, { "epoch": 0.02550397067806964, "grad_norm": 0.44790852069854736, "learning_rate": 4.991979655745416e-05, "loss": 4.5455, "step": 835 }, { "epoch": 0.025534514355528407, "grad_norm": 0.4366735816001892, "learning_rate": 4.991960444145777e-05, "loss": 4.4756, "step": 836 }, { "epoch": 0.02556505803298717, "grad_norm": 0.45247432589530945, "learning_rate": 4.9919412096013774e-05, "loss": 4.4955, "step": 837 }, { "epoch": 0.025595601710445937, "grad_norm": 0.4588436186313629, "learning_rate": 4.991921952112393e-05, "loss": 4.4456, "step": 838 }, { "epoch": 0.025626145387904704, "grad_norm": 0.4633377492427826, "learning_rate": 4.991902671679003e-05, "loss": 4.5191, "step": 839 }, { "epoch": 0.02565668906536347, "grad_norm": 0.43855178356170654, "learning_rate": 4.991883368301383e-05, "loss": 4.4515, "step": 840 }, { "epoch": 0.025687232742822235, "grad_norm": 0.47110608220100403, "learning_rate": 4.991864041979713e-05, "loss": 4.5482, "step": 841 }, { "epoch": 0.025717776420281002, "grad_norm": 0.4434681534767151, "learning_rate": 4.991844692714168e-05, "loss": 4.4394, "step": 842 }, { "epoch": 0.02574832009773977, "grad_norm": 0.4719473123550415, "learning_rate": 4.991825320504928e-05, "loss": 4.4947, "step": 843 }, { "epoch": 0.025778863775198533, "grad_norm": 0.4549747407436371, "learning_rate": 4.991805925352172e-05, "loss": 4.4795, "step": 844 }, { "epoch": 0.0258094074526573, "grad_norm": 0.47142335772514343, "learning_rate": 4.991786507256077e-05, "loss": 4.5095, "step": 845 }, { "epoch": 0.025839951130116067, "grad_norm": 0.45140206813812256, "learning_rate": 4.9917670662168226e-05, "loss": 4.4489, "step": 846 }, { "epoch": 0.02587049480757483, "grad_norm": 0.4488404393196106, "learning_rate": 4.991747602234588e-05, "loss": 4.5412, "step": 847 }, { "epoch": 0.025901038485033598, "grad_norm": 0.4655189514160156, "learning_rate": 4.991728115309552e-05, "loss": 4.5604, "step": 848 }, { "epoch": 0.025931582162492365, "grad_norm": 0.46070778369903564, "learning_rate": 4.991708605441894e-05, "loss": 4.5321, "step": 849 }, { "epoch": 0.02596212583995113, "grad_norm": 0.45440158247947693, "learning_rate": 4.9916890726317934e-05, "loss": 4.5075, "step": 850 }, { "epoch": 0.025992669517409896, "grad_norm": 0.44805026054382324, "learning_rate": 4.99166951687943e-05, "loss": 4.4458, "step": 851 }, { "epoch": 0.026023213194868663, "grad_norm": 0.47372880578041077, "learning_rate": 4.991649938184986e-05, "loss": 4.5115, "step": 852 }, { "epoch": 0.02605375687232743, "grad_norm": 0.4483877718448639, "learning_rate": 4.9916303365486385e-05, "loss": 4.4802, "step": 853 }, { "epoch": 0.026084300549786194, "grad_norm": 0.47234296798706055, "learning_rate": 4.99161071197057e-05, "loss": 4.4885, "step": 854 }, { "epoch": 0.02611484422724496, "grad_norm": 0.48938238620758057, "learning_rate": 4.99159106445096e-05, "loss": 4.4249, "step": 855 }, { "epoch": 0.026145387904703728, "grad_norm": 0.4452947676181793, "learning_rate": 4.991571393989991e-05, "loss": 4.5704, "step": 856 }, { "epoch": 0.02617593158216249, "grad_norm": 0.44705578684806824, "learning_rate": 4.991551700587843e-05, "loss": 4.4631, "step": 857 }, { "epoch": 0.02620647525962126, "grad_norm": 0.4299383759498596, "learning_rate": 4.991531984244697e-05, "loss": 4.4992, "step": 858 }, { "epoch": 0.026237018937080026, "grad_norm": 0.44560644030570984, "learning_rate": 4.9915122449607344e-05, "loss": 4.4961, "step": 859 }, { "epoch": 0.02626756261453879, "grad_norm": 0.4478975236415863, "learning_rate": 4.9914924827361384e-05, "loss": 4.5239, "step": 860 }, { "epoch": 0.026298106291997556, "grad_norm": 0.4363820552825928, "learning_rate": 4.99147269757109e-05, "loss": 4.4203, "step": 861 }, { "epoch": 0.026328649969456323, "grad_norm": 0.45527487993240356, "learning_rate": 4.991452889465772e-05, "loss": 4.4804, "step": 862 }, { "epoch": 0.026359193646915087, "grad_norm": 0.45201200246810913, "learning_rate": 4.991433058420365e-05, "loss": 4.4414, "step": 863 }, { "epoch": 0.026389737324373854, "grad_norm": 0.45578035712242126, "learning_rate": 4.9914132044350535e-05, "loss": 4.4849, "step": 864 }, { "epoch": 0.02642028100183262, "grad_norm": 0.4686707556247711, "learning_rate": 4.99139332751002e-05, "loss": 4.5166, "step": 865 }, { "epoch": 0.02645082467929139, "grad_norm": 0.44499167799949646, "learning_rate": 4.9913734276454474e-05, "loss": 4.4937, "step": 866 }, { "epoch": 0.026481368356750152, "grad_norm": 0.4586716294288635, "learning_rate": 4.991353504841518e-05, "loss": 4.391, "step": 867 }, { "epoch": 0.02651191203420892, "grad_norm": 0.4483417868614197, "learning_rate": 4.991333559098416e-05, "loss": 4.5109, "step": 868 }, { "epoch": 0.026542455711667686, "grad_norm": 0.4438731074333191, "learning_rate": 4.991313590416326e-05, "loss": 4.4856, "step": 869 }, { "epoch": 0.02657299938912645, "grad_norm": 0.4532318115234375, "learning_rate": 4.991293598795429e-05, "loss": 4.5266, "step": 870 }, { "epoch": 0.026603543066585217, "grad_norm": 0.4540451765060425, "learning_rate": 4.9912735842359124e-05, "loss": 4.5483, "step": 871 }, { "epoch": 0.026634086744043984, "grad_norm": 0.45949268341064453, "learning_rate": 4.991253546737958e-05, "loss": 4.5352, "step": 872 }, { "epoch": 0.026664630421502748, "grad_norm": 0.45715034008026123, "learning_rate": 4.991233486301753e-05, "loss": 4.4346, "step": 873 }, { "epoch": 0.026695174098961515, "grad_norm": 0.4404446482658386, "learning_rate": 4.991213402927479e-05, "loss": 4.4773, "step": 874 }, { "epoch": 0.026725717776420282, "grad_norm": 0.43055084347724915, "learning_rate": 4.991193296615323e-05, "loss": 4.4586, "step": 875 }, { "epoch": 0.026756261453879045, "grad_norm": 0.4533333480358124, "learning_rate": 4.9911731673654685e-05, "loss": 4.523, "step": 876 }, { "epoch": 0.026786805131337812, "grad_norm": 0.45854562520980835, "learning_rate": 4.991153015178103e-05, "loss": 4.4732, "step": 877 }, { "epoch": 0.02681734880879658, "grad_norm": 0.43645337224006653, "learning_rate": 4.99113284005341e-05, "loss": 4.4738, "step": 878 }, { "epoch": 0.026847892486255347, "grad_norm": 0.43650713562965393, "learning_rate": 4.9911126419915765e-05, "loss": 4.5232, "step": 879 }, { "epoch": 0.02687843616371411, "grad_norm": 0.4638458490371704, "learning_rate": 4.991092420992788e-05, "loss": 4.4153, "step": 880 }, { "epoch": 0.026908979841172877, "grad_norm": 0.4335958659648895, "learning_rate": 4.9910721770572314e-05, "loss": 4.4799, "step": 881 }, { "epoch": 0.026939523518631645, "grad_norm": 0.42915990948677063, "learning_rate": 4.9910519101850916e-05, "loss": 4.5054, "step": 882 }, { "epoch": 0.026970067196090408, "grad_norm": 0.45802929997444153, "learning_rate": 4.9910316203765565e-05, "loss": 4.5243, "step": 883 }, { "epoch": 0.027000610873549175, "grad_norm": 0.4501248002052307, "learning_rate": 4.9910113076318127e-05, "loss": 4.524, "step": 884 }, { "epoch": 0.027031154551007942, "grad_norm": 0.4673011302947998, "learning_rate": 4.990990971951047e-05, "loss": 4.491, "step": 885 }, { "epoch": 0.027061698228466706, "grad_norm": 0.4424498677253723, "learning_rate": 4.9909706133344464e-05, "loss": 4.565, "step": 886 }, { "epoch": 0.027092241905925473, "grad_norm": 0.4427497386932373, "learning_rate": 4.990950231782199e-05, "loss": 4.5088, "step": 887 }, { "epoch": 0.02712278558338424, "grad_norm": 0.4303722083568573, "learning_rate": 4.9909298272944917e-05, "loss": 4.4743, "step": 888 }, { "epoch": 0.027153329260843004, "grad_norm": 0.43069034814834595, "learning_rate": 4.990909399871513e-05, "loss": 4.4964, "step": 889 }, { "epoch": 0.02718387293830177, "grad_norm": 0.4486393928527832, "learning_rate": 4.99088894951345e-05, "loss": 4.4202, "step": 890 }, { "epoch": 0.027214416615760538, "grad_norm": 0.4501226842403412, "learning_rate": 4.990868476220493e-05, "loss": 4.5038, "step": 891 }, { "epoch": 0.027244960293219305, "grad_norm": 0.43906325101852417, "learning_rate": 4.990847979992829e-05, "loss": 4.4602, "step": 892 }, { "epoch": 0.02727550397067807, "grad_norm": 0.43298399448394775, "learning_rate": 4.990827460830646e-05, "loss": 4.4507, "step": 893 }, { "epoch": 0.027306047648136836, "grad_norm": 0.4600071310997009, "learning_rate": 4.9908069187341346e-05, "loss": 4.4909, "step": 894 }, { "epoch": 0.027336591325595603, "grad_norm": 0.4513777196407318, "learning_rate": 4.9907863537034836e-05, "loss": 4.4846, "step": 895 }, { "epoch": 0.027367135003054367, "grad_norm": 0.44201046228408813, "learning_rate": 4.9907657657388815e-05, "loss": 4.4359, "step": 896 }, { "epoch": 0.027397678680513134, "grad_norm": 0.460163414478302, "learning_rate": 4.990745154840518e-05, "loss": 4.476, "step": 897 }, { "epoch": 0.0274282223579719, "grad_norm": 0.45481082797050476, "learning_rate": 4.990724521008584e-05, "loss": 4.4827, "step": 898 }, { "epoch": 0.027458766035430664, "grad_norm": 0.4389089047908783, "learning_rate": 4.990703864243269e-05, "loss": 4.5367, "step": 899 }, { "epoch": 0.02748930971288943, "grad_norm": 0.42823538184165955, "learning_rate": 4.990683184544762e-05, "loss": 4.4388, "step": 900 }, { "epoch": 0.0275198533903482, "grad_norm": 0.43648451566696167, "learning_rate": 4.990662481913255e-05, "loss": 4.437, "step": 901 }, { "epoch": 0.027550397067806966, "grad_norm": 0.4601791501045227, "learning_rate": 4.990641756348937e-05, "loss": 4.515, "step": 902 }, { "epoch": 0.02758094074526573, "grad_norm": 0.4394223093986511, "learning_rate": 4.990621007852001e-05, "loss": 4.4006, "step": 903 }, { "epoch": 0.027611484422724496, "grad_norm": 0.4351063072681427, "learning_rate": 4.990600236422636e-05, "loss": 4.5424, "step": 904 }, { "epoch": 0.027642028100183264, "grad_norm": 0.4439597725868225, "learning_rate": 4.990579442061034e-05, "loss": 4.4873, "step": 905 }, { "epoch": 0.027672571777642027, "grad_norm": 0.4472661316394806, "learning_rate": 4.990558624767388e-05, "loss": 4.5117, "step": 906 }, { "epoch": 0.027703115455100794, "grad_norm": 0.44165951013565063, "learning_rate": 4.9905377845418864e-05, "loss": 4.4526, "step": 907 }, { "epoch": 0.02773365913255956, "grad_norm": 0.4430685043334961, "learning_rate": 4.990516921384724e-05, "loss": 4.4288, "step": 908 }, { "epoch": 0.027764202810018325, "grad_norm": 0.4256487786769867, "learning_rate": 4.9904960352960914e-05, "loss": 4.4552, "step": 909 }, { "epoch": 0.027794746487477092, "grad_norm": 0.4431725740432739, "learning_rate": 4.990475126276182e-05, "loss": 4.5132, "step": 910 }, { "epoch": 0.02782529016493586, "grad_norm": 0.4472985863685608, "learning_rate": 4.990454194325187e-05, "loss": 4.4752, "step": 911 }, { "epoch": 0.027855833842394623, "grad_norm": 0.44639453291893005, "learning_rate": 4.9904332394433e-05, "loss": 4.5911, "step": 912 }, { "epoch": 0.02788637751985339, "grad_norm": 0.44002386927604675, "learning_rate": 4.9904122616307124e-05, "loss": 4.5325, "step": 913 }, { "epoch": 0.027916921197312157, "grad_norm": 0.4460946321487427, "learning_rate": 4.9903912608876205e-05, "loss": 4.523, "step": 914 }, { "epoch": 0.027947464874770924, "grad_norm": 0.43251460790634155, "learning_rate": 4.990370237214215e-05, "loss": 4.4225, "step": 915 }, { "epoch": 0.027978008552229688, "grad_norm": 0.43621358275413513, "learning_rate": 4.9903491906106905e-05, "loss": 4.4722, "step": 916 }, { "epoch": 0.028008552229688455, "grad_norm": 0.4438236653804779, "learning_rate": 4.99032812107724e-05, "loss": 4.5143, "step": 917 }, { "epoch": 0.028039095907147222, "grad_norm": 0.4421790540218353, "learning_rate": 4.990307028614058e-05, "loss": 4.4469, "step": 918 }, { "epoch": 0.028069639584605986, "grad_norm": 0.44144344329833984, "learning_rate": 4.99028591322134e-05, "loss": 4.5142, "step": 919 }, { "epoch": 0.028100183262064753, "grad_norm": 0.4250102937221527, "learning_rate": 4.990264774899279e-05, "loss": 4.4768, "step": 920 }, { "epoch": 0.02813072693952352, "grad_norm": 0.44221219420433044, "learning_rate": 4.990243613648069e-05, "loss": 4.4828, "step": 921 }, { "epoch": 0.028161270616982283, "grad_norm": 0.46344122290611267, "learning_rate": 4.9902224294679066e-05, "loss": 4.4833, "step": 922 }, { "epoch": 0.02819181429444105, "grad_norm": 0.4275769591331482, "learning_rate": 4.9902012223589854e-05, "loss": 4.5277, "step": 923 }, { "epoch": 0.028222357971899818, "grad_norm": 0.4334767162799835, "learning_rate": 4.990179992321501e-05, "loss": 4.5165, "step": 924 }, { "epoch": 0.02825290164935858, "grad_norm": 0.44374269247055054, "learning_rate": 4.990158739355649e-05, "loss": 4.458, "step": 925 }, { "epoch": 0.02828344532681735, "grad_norm": 0.45753100514411926, "learning_rate": 4.990137463461626e-05, "loss": 4.4204, "step": 926 }, { "epoch": 0.028313989004276115, "grad_norm": 0.43707776069641113, "learning_rate": 4.990116164639627e-05, "loss": 4.4132, "step": 927 }, { "epoch": 0.028344532681734882, "grad_norm": 0.4488135576248169, "learning_rate": 4.9900948428898473e-05, "loss": 4.4601, "step": 928 }, { "epoch": 0.028375076359193646, "grad_norm": 0.4625096023082733, "learning_rate": 4.990073498212485e-05, "loss": 4.5438, "step": 929 }, { "epoch": 0.028405620036652413, "grad_norm": 0.4385423958301544, "learning_rate": 4.990052130607735e-05, "loss": 4.4559, "step": 930 }, { "epoch": 0.02843616371411118, "grad_norm": 0.4664844870567322, "learning_rate": 4.990030740075795e-05, "loss": 4.5497, "step": 931 }, { "epoch": 0.028466707391569944, "grad_norm": 0.4611520767211914, "learning_rate": 4.9900093266168626e-05, "loss": 4.5242, "step": 932 }, { "epoch": 0.02849725106902871, "grad_norm": 0.42483583092689514, "learning_rate": 4.9899878902311333e-05, "loss": 4.4621, "step": 933 }, { "epoch": 0.028527794746487478, "grad_norm": 0.4661921560764313, "learning_rate": 4.989966430918805e-05, "loss": 4.495, "step": 934 }, { "epoch": 0.028558338423946242, "grad_norm": 0.45135068893432617, "learning_rate": 4.989944948680076e-05, "loss": 4.4862, "step": 935 }, { "epoch": 0.02858888210140501, "grad_norm": 0.4263477325439453, "learning_rate": 4.989923443515143e-05, "loss": 4.4797, "step": 936 }, { "epoch": 0.028619425778863776, "grad_norm": 0.44398707151412964, "learning_rate": 4.989901915424205e-05, "loss": 4.5252, "step": 937 }, { "epoch": 0.02864996945632254, "grad_norm": 0.4533078968524933, "learning_rate": 4.989880364407461e-05, "loss": 4.4761, "step": 938 }, { "epoch": 0.028680513133781307, "grad_norm": 0.4437996745109558, "learning_rate": 4.989858790465107e-05, "loss": 4.48, "step": 939 }, { "epoch": 0.028711056811240074, "grad_norm": 0.44864869117736816, "learning_rate": 4.989837193597343e-05, "loss": 4.4732, "step": 940 }, { "epoch": 0.02874160048869884, "grad_norm": 0.4438769519329071, "learning_rate": 4.9898155738043686e-05, "loss": 4.5024, "step": 941 }, { "epoch": 0.028772144166157605, "grad_norm": 0.45125681161880493, "learning_rate": 4.989793931086382e-05, "loss": 4.4991, "step": 942 }, { "epoch": 0.02880268784361637, "grad_norm": 0.4486524164676666, "learning_rate": 4.989772265443582e-05, "loss": 4.4641, "step": 943 }, { "epoch": 0.02883323152107514, "grad_norm": 0.4605449438095093, "learning_rate": 4.989750576876169e-05, "loss": 4.5308, "step": 944 }, { "epoch": 0.028863775198533902, "grad_norm": 0.45007559657096863, "learning_rate": 4.989728865384342e-05, "loss": 4.4787, "step": 945 }, { "epoch": 0.02889431887599267, "grad_norm": 0.43901318311691284, "learning_rate": 4.989707130968301e-05, "loss": 4.4983, "step": 946 }, { "epoch": 0.028924862553451437, "grad_norm": 0.4403001666069031, "learning_rate": 4.9896853736282466e-05, "loss": 4.4408, "step": 947 }, { "epoch": 0.0289554062309102, "grad_norm": 0.4439829885959625, "learning_rate": 4.9896635933643796e-05, "loss": 4.4471, "step": 948 }, { "epoch": 0.028985949908368967, "grad_norm": 0.449659526348114, "learning_rate": 4.9896417901768994e-05, "loss": 4.5542, "step": 949 }, { "epoch": 0.029016493585827734, "grad_norm": 0.4431803524494171, "learning_rate": 4.989619964066007e-05, "loss": 4.4517, "step": 950 }, { "epoch": 0.029047037263286498, "grad_norm": 0.43450668454170227, "learning_rate": 4.989598115031904e-05, "loss": 4.4569, "step": 951 }, { "epoch": 0.029077580940745265, "grad_norm": 0.4198727011680603, "learning_rate": 4.9895762430747906e-05, "loss": 4.435, "step": 952 }, { "epoch": 0.029108124618204032, "grad_norm": 0.44360917806625366, "learning_rate": 4.9895543481948684e-05, "loss": 4.5089, "step": 953 }, { "epoch": 0.0291386682956628, "grad_norm": 0.44827699661254883, "learning_rate": 4.98953243039234e-05, "loss": 4.5145, "step": 954 }, { "epoch": 0.029169211973121563, "grad_norm": 0.43623048067092896, "learning_rate": 4.989510489667406e-05, "loss": 4.5096, "step": 955 }, { "epoch": 0.02919975565058033, "grad_norm": 0.44635602831840515, "learning_rate": 4.9894885260202695e-05, "loss": 4.4688, "step": 956 }, { "epoch": 0.029230299328039097, "grad_norm": 0.44131025671958923, "learning_rate": 4.989466539451132e-05, "loss": 4.3722, "step": 957 }, { "epoch": 0.02926084300549786, "grad_norm": 0.42790067195892334, "learning_rate": 4.989444529960197e-05, "loss": 4.4801, "step": 958 }, { "epoch": 0.029291386682956628, "grad_norm": 0.43767306208610535, "learning_rate": 4.9894224975476644e-05, "loss": 4.5463, "step": 959 }, { "epoch": 0.029321930360415395, "grad_norm": 0.4419073164463043, "learning_rate": 4.98940044221374e-05, "loss": 4.5494, "step": 960 }, { "epoch": 0.02935247403787416, "grad_norm": 0.448506236076355, "learning_rate": 4.989378363958626e-05, "loss": 4.5539, "step": 961 }, { "epoch": 0.029383017715332926, "grad_norm": 0.43518486618995667, "learning_rate": 4.9893562627825254e-05, "loss": 4.5114, "step": 962 }, { "epoch": 0.029413561392791693, "grad_norm": 0.43481189012527466, "learning_rate": 4.9893341386856404e-05, "loss": 4.5521, "step": 963 }, { "epoch": 0.029444105070250456, "grad_norm": 0.45261842012405396, "learning_rate": 4.989311991668178e-05, "loss": 4.5049, "step": 964 }, { "epoch": 0.029474648747709224, "grad_norm": 0.4322468638420105, "learning_rate": 4.9892898217303395e-05, "loss": 4.4149, "step": 965 }, { "epoch": 0.02950519242516799, "grad_norm": 0.4342586100101471, "learning_rate": 4.9892676288723295e-05, "loss": 4.4582, "step": 966 }, { "epoch": 0.029535736102626758, "grad_norm": 0.45657581090927124, "learning_rate": 4.9892454130943526e-05, "loss": 4.3862, "step": 967 }, { "epoch": 0.02956627978008552, "grad_norm": 0.44048482179641724, "learning_rate": 4.989223174396614e-05, "loss": 4.5352, "step": 968 }, { "epoch": 0.02959682345754429, "grad_norm": 0.4405576288700104, "learning_rate": 4.989200912779317e-05, "loss": 4.5207, "step": 969 }, { "epoch": 0.029627367135003056, "grad_norm": 0.44488590955734253, "learning_rate": 4.989178628242668e-05, "loss": 4.5231, "step": 970 }, { "epoch": 0.02965791081246182, "grad_norm": 0.4466779828071594, "learning_rate": 4.989156320786871e-05, "loss": 4.4408, "step": 971 }, { "epoch": 0.029688454489920586, "grad_norm": 0.4393039047718048, "learning_rate": 4.989133990412132e-05, "loss": 4.4963, "step": 972 }, { "epoch": 0.029718998167379353, "grad_norm": 0.45638981461524963, "learning_rate": 4.989111637118657e-05, "loss": 4.514, "step": 973 }, { "epoch": 0.029749541844838117, "grad_norm": 0.4377239942550659, "learning_rate": 4.989089260906651e-05, "loss": 4.5094, "step": 974 }, { "epoch": 0.029780085522296884, "grad_norm": 0.43605247139930725, "learning_rate": 4.989066861776321e-05, "loss": 4.4704, "step": 975 }, { "epoch": 0.02981062919975565, "grad_norm": 0.4398247003555298, "learning_rate": 4.9890444397278726e-05, "loss": 4.4642, "step": 976 }, { "epoch": 0.02984117287721442, "grad_norm": 0.4309748709201813, "learning_rate": 4.989021994761511e-05, "loss": 4.4961, "step": 977 }, { "epoch": 0.029871716554673182, "grad_norm": 0.45134371519088745, "learning_rate": 4.988999526877446e-05, "loss": 4.5553, "step": 978 }, { "epoch": 0.02990226023213195, "grad_norm": 0.44860127568244934, "learning_rate": 4.9889770360758816e-05, "loss": 4.5289, "step": 979 }, { "epoch": 0.029932803909590716, "grad_norm": 0.4454253017902374, "learning_rate": 4.9889545223570254e-05, "loss": 4.5315, "step": 980 }, { "epoch": 0.02996334758704948, "grad_norm": 0.44910404086112976, "learning_rate": 4.9889319857210863e-05, "loss": 4.4879, "step": 981 }, { "epoch": 0.029993891264508247, "grad_norm": 0.4297874867916107, "learning_rate": 4.98890942616827e-05, "loss": 4.4649, "step": 982 }, { "epoch": 0.030024434941967014, "grad_norm": 0.43446511030197144, "learning_rate": 4.988886843698786e-05, "loss": 4.4731, "step": 983 }, { "epoch": 0.030054978619425778, "grad_norm": 0.44638320803642273, "learning_rate": 4.98886423831284e-05, "loss": 4.5078, "step": 984 }, { "epoch": 0.030085522296884545, "grad_norm": 0.4461064636707306, "learning_rate": 4.988841610010642e-05, "loss": 4.4709, "step": 985 }, { "epoch": 0.030116065974343312, "grad_norm": 0.43939051032066345, "learning_rate": 4.9888189587923994e-05, "loss": 4.3918, "step": 986 }, { "epoch": 0.030146609651802075, "grad_norm": 0.4478667080402374, "learning_rate": 4.988796284658321e-05, "loss": 4.4332, "step": 987 }, { "epoch": 0.030177153329260843, "grad_norm": 0.4354453384876251, "learning_rate": 4.988773587608615e-05, "loss": 4.4013, "step": 988 }, { "epoch": 0.03020769700671961, "grad_norm": 0.4322938621044159, "learning_rate": 4.988750867643492e-05, "loss": 4.4649, "step": 989 }, { "epoch": 0.030238240684178377, "grad_norm": 0.4386839270591736, "learning_rate": 4.98872812476316e-05, "loss": 4.4417, "step": 990 }, { "epoch": 0.03026878436163714, "grad_norm": 0.44718876481056213, "learning_rate": 4.988705358967828e-05, "loss": 4.4875, "step": 991 }, { "epoch": 0.030299328039095907, "grad_norm": 0.43737027049064636, "learning_rate": 4.988682570257707e-05, "loss": 4.5174, "step": 992 }, { "epoch": 0.030329871716554675, "grad_norm": 0.4462781846523285, "learning_rate": 4.988659758633005e-05, "loss": 4.5351, "step": 993 }, { "epoch": 0.030360415394013438, "grad_norm": 0.45453593134880066, "learning_rate": 4.988636924093934e-05, "loss": 4.5761, "step": 994 }, { "epoch": 0.030390959071472205, "grad_norm": 0.4331234395503998, "learning_rate": 4.9886140666407026e-05, "loss": 4.4582, "step": 995 }, { "epoch": 0.030421502748930972, "grad_norm": 0.4405016601085663, "learning_rate": 4.988591186273522e-05, "loss": 4.5205, "step": 996 }, { "epoch": 0.030452046426389736, "grad_norm": 0.4474893808364868, "learning_rate": 4.988568282992604e-05, "loss": 4.513, "step": 997 }, { "epoch": 0.030482590103848503, "grad_norm": 0.44827109575271606, "learning_rate": 4.988545356798157e-05, "loss": 4.4736, "step": 998 }, { "epoch": 0.03051313378130727, "grad_norm": 0.4306630790233612, "learning_rate": 4.9885224076903944e-05, "loss": 4.4232, "step": 999 }, { "epoch": 0.030543677458766034, "grad_norm": 0.4223962724208832, "learning_rate": 4.9884994356695255e-05, "loss": 4.4366, "step": 1000 }, { "epoch": 0.0305742211362248, "grad_norm": 0.43155720829963684, "learning_rate": 4.988476440735763e-05, "loss": 4.4468, "step": 1001 }, { "epoch": 0.030604764813683568, "grad_norm": 0.4385729432106018, "learning_rate": 4.988453422889319e-05, "loss": 4.4608, "step": 1002 }, { "epoch": 0.030635308491142335, "grad_norm": 0.422100305557251, "learning_rate": 4.9884303821304045e-05, "loss": 4.4169, "step": 1003 }, { "epoch": 0.0306658521686011, "grad_norm": 0.4506666660308838, "learning_rate": 4.988407318459233e-05, "loss": 4.5185, "step": 1004 }, { "epoch": 0.030696395846059866, "grad_norm": 0.4387304186820984, "learning_rate": 4.988384231876015e-05, "loss": 4.4796, "step": 1005 }, { "epoch": 0.030726939523518633, "grad_norm": 0.42804044485092163, "learning_rate": 4.988361122380964e-05, "loss": 4.4835, "step": 1006 }, { "epoch": 0.030757483200977397, "grad_norm": 0.43766307830810547, "learning_rate": 4.9883379899742933e-05, "loss": 4.4244, "step": 1007 }, { "epoch": 0.030788026878436164, "grad_norm": 0.43353259563446045, "learning_rate": 4.988314834656215e-05, "loss": 4.4382, "step": 1008 }, { "epoch": 0.03081857055589493, "grad_norm": 0.4486056864261627, "learning_rate": 4.988291656426942e-05, "loss": 4.421, "step": 1009 }, { "epoch": 0.030849114233353694, "grad_norm": 0.43108564615249634, "learning_rate": 4.988268455286689e-05, "loss": 4.408, "step": 1010 }, { "epoch": 0.03087965791081246, "grad_norm": 0.44685420393943787, "learning_rate": 4.9882452312356685e-05, "loss": 4.4939, "step": 1011 }, { "epoch": 0.03091020158827123, "grad_norm": 0.4503936767578125, "learning_rate": 4.988221984274096e-05, "loss": 4.5096, "step": 1012 }, { "epoch": 0.030940745265729992, "grad_norm": 0.4362449049949646, "learning_rate": 4.988198714402184e-05, "loss": 4.4853, "step": 1013 }, { "epoch": 0.03097128894318876, "grad_norm": 0.4359174072742462, "learning_rate": 4.988175421620146e-05, "loss": 4.456, "step": 1014 }, { "epoch": 0.031001832620647526, "grad_norm": 0.4288271367549896, "learning_rate": 4.988152105928199e-05, "loss": 4.4667, "step": 1015 }, { "epoch": 0.031032376298106294, "grad_norm": 0.4369167387485504, "learning_rate": 4.988128767326555e-05, "loss": 4.5674, "step": 1016 }, { "epoch": 0.031062919975565057, "grad_norm": 0.4501354694366455, "learning_rate": 4.988105405815431e-05, "loss": 4.521, "step": 1017 }, { "epoch": 0.031093463653023824, "grad_norm": 0.43229225277900696, "learning_rate": 4.988082021395041e-05, "loss": 4.5049, "step": 1018 }, { "epoch": 0.03112400733048259, "grad_norm": 0.46074578166007996, "learning_rate": 4.988058614065601e-05, "loss": 4.4825, "step": 1019 }, { "epoch": 0.031154551007941355, "grad_norm": 0.44106388092041016, "learning_rate": 4.9880351838273255e-05, "loss": 4.4515, "step": 1020 }, { "epoch": 0.031185094685400122, "grad_norm": 0.44535937905311584, "learning_rate": 4.9880117306804316e-05, "loss": 4.4484, "step": 1021 }, { "epoch": 0.03121563836285889, "grad_norm": 0.43883493542671204, "learning_rate": 4.987988254625134e-05, "loss": 4.5158, "step": 1022 }, { "epoch": 0.031246182040317653, "grad_norm": 0.43619510531425476, "learning_rate": 4.987964755661649e-05, "loss": 4.4983, "step": 1023 }, { "epoch": 0.03127672571777642, "grad_norm": 0.44368505477905273, "learning_rate": 4.9879412337901936e-05, "loss": 4.5007, "step": 1024 }, { "epoch": 0.031307269395235184, "grad_norm": 0.4346553087234497, "learning_rate": 4.987917689010985e-05, "loss": 4.5412, "step": 1025 }, { "epoch": 0.031337813072693954, "grad_norm": 0.43500036001205444, "learning_rate": 4.987894121324238e-05, "loss": 4.4963, "step": 1026 }, { "epoch": 0.03136835675015272, "grad_norm": 0.4333658814430237, "learning_rate": 4.987870530730171e-05, "loss": 4.4877, "step": 1027 }, { "epoch": 0.03139890042761148, "grad_norm": 0.42751461267471313, "learning_rate": 4.987846917229001e-05, "loss": 4.4787, "step": 1028 }, { "epoch": 0.03142944410507025, "grad_norm": 0.43537667393684387, "learning_rate": 4.987823280820944e-05, "loss": 4.4838, "step": 1029 }, { "epoch": 0.031459987782529016, "grad_norm": 0.43305477499961853, "learning_rate": 4.987799621506221e-05, "loss": 4.4191, "step": 1030 }, { "epoch": 0.03149053145998778, "grad_norm": 0.44517454504966736, "learning_rate": 4.9877759392850466e-05, "loss": 4.5202, "step": 1031 }, { "epoch": 0.03152107513744655, "grad_norm": 0.4508369266986847, "learning_rate": 4.98775223415764e-05, "loss": 4.4828, "step": 1032 }, { "epoch": 0.03155161881490531, "grad_norm": 0.4399476647377014, "learning_rate": 4.987728506124219e-05, "loss": 4.4455, "step": 1033 }, { "epoch": 0.031582162492364084, "grad_norm": 0.4486696720123291, "learning_rate": 4.987704755185004e-05, "loss": 4.4914, "step": 1034 }, { "epoch": 0.03161270616982285, "grad_norm": 0.4341636300086975, "learning_rate": 4.9876809813402115e-05, "loss": 4.4696, "step": 1035 }, { "epoch": 0.03164324984728161, "grad_norm": 0.42273035645484924, "learning_rate": 4.987657184590062e-05, "loss": 4.4734, "step": 1036 }, { "epoch": 0.03167379352474038, "grad_norm": 0.4455605149269104, "learning_rate": 4.987633364934773e-05, "loss": 4.5014, "step": 1037 }, { "epoch": 0.031704337202199145, "grad_norm": 0.43395915627479553, "learning_rate": 4.9876095223745645e-05, "loss": 4.5076, "step": 1038 }, { "epoch": 0.03173488087965791, "grad_norm": 0.44518375396728516, "learning_rate": 4.987585656909656e-05, "loss": 4.5103, "step": 1039 }, { "epoch": 0.03176542455711668, "grad_norm": 0.45865195989608765, "learning_rate": 4.9875617685402676e-05, "loss": 4.5103, "step": 1040 }, { "epoch": 0.03179596823457544, "grad_norm": 0.4541948735713959, "learning_rate": 4.9875378572666196e-05, "loss": 4.4699, "step": 1041 }, { "epoch": 0.03182651191203421, "grad_norm": 0.43269190192222595, "learning_rate": 4.987513923088931e-05, "loss": 4.4735, "step": 1042 }, { "epoch": 0.03185705558949298, "grad_norm": 0.4422370195388794, "learning_rate": 4.9874899660074226e-05, "loss": 4.4146, "step": 1043 }, { "epoch": 0.03188759926695174, "grad_norm": 0.4446101188659668, "learning_rate": 4.987465986022315e-05, "loss": 4.4509, "step": 1044 }, { "epoch": 0.031918142944410505, "grad_norm": 0.44200223684310913, "learning_rate": 4.98744198313383e-05, "loss": 4.5183, "step": 1045 }, { "epoch": 0.031948686621869275, "grad_norm": 0.4319263994693756, "learning_rate": 4.987417957342187e-05, "loss": 4.5062, "step": 1046 }, { "epoch": 0.03197923029932804, "grad_norm": 0.4285332262516022, "learning_rate": 4.9873939086476084e-05, "loss": 4.4821, "step": 1047 }, { "epoch": 0.0320097739767868, "grad_norm": 0.4417552947998047, "learning_rate": 4.987369837050315e-05, "loss": 4.549, "step": 1048 }, { "epoch": 0.03204031765424557, "grad_norm": 0.43378424644470215, "learning_rate": 4.9873457425505285e-05, "loss": 4.4445, "step": 1049 }, { "epoch": 0.03207086133170434, "grad_norm": 0.42372241616249084, "learning_rate": 4.987321625148471e-05, "loss": 4.4196, "step": 1050 }, { "epoch": 0.0321014050091631, "grad_norm": 0.42715883255004883, "learning_rate": 4.987297484844364e-05, "loss": 4.4993, "step": 1051 }, { "epoch": 0.03213194868662187, "grad_norm": 0.4436572790145874, "learning_rate": 4.9872733216384315e-05, "loss": 4.4102, "step": 1052 }, { "epoch": 0.032162492364080635, "grad_norm": 0.4292815327644348, "learning_rate": 4.987249135530894e-05, "loss": 4.5309, "step": 1053 }, { "epoch": 0.0321930360415394, "grad_norm": 0.4210621416568756, "learning_rate": 4.987224926521974e-05, "loss": 4.4839, "step": 1054 }, { "epoch": 0.03222357971899817, "grad_norm": 0.4472120404243469, "learning_rate": 4.9872006946118966e-05, "loss": 4.4734, "step": 1055 }, { "epoch": 0.03225412339645693, "grad_norm": 0.429620623588562, "learning_rate": 4.987176439800882e-05, "loss": 4.4373, "step": 1056 }, { "epoch": 0.032284667073915696, "grad_norm": 0.42835015058517456, "learning_rate": 4.987152162089157e-05, "loss": 4.409, "step": 1057 }, { "epoch": 0.03231521075137447, "grad_norm": 0.44243454933166504, "learning_rate": 4.987127861476942e-05, "loss": 4.447, "step": 1058 }, { "epoch": 0.03234575442883323, "grad_norm": 0.43776360154151917, "learning_rate": 4.987103537964463e-05, "loss": 4.4573, "step": 1059 }, { "epoch": 0.032376298106292, "grad_norm": 0.4254832863807678, "learning_rate": 4.987079191551942e-05, "loss": 4.5033, "step": 1060 }, { "epoch": 0.032406841783750764, "grad_norm": 0.4428327679634094, "learning_rate": 4.987054822239605e-05, "loss": 4.4766, "step": 1061 }, { "epoch": 0.03243738546120953, "grad_norm": 0.46177881956100464, "learning_rate": 4.987030430027676e-05, "loss": 4.5173, "step": 1062 }, { "epoch": 0.0324679291386683, "grad_norm": 0.42781829833984375, "learning_rate": 4.9870060149163775e-05, "loss": 4.4607, "step": 1063 }, { "epoch": 0.03249847281612706, "grad_norm": 0.43060359358787537, "learning_rate": 4.986981576905937e-05, "loss": 4.5018, "step": 1064 }, { "epoch": 0.032529016493585826, "grad_norm": 0.4498033821582794, "learning_rate": 4.986957115996578e-05, "loss": 4.5014, "step": 1065 }, { "epoch": 0.032559560171044596, "grad_norm": 0.43605247139930725, "learning_rate": 4.986932632188527e-05, "loss": 4.4986, "step": 1066 }, { "epoch": 0.03259010384850336, "grad_norm": 0.4325885772705078, "learning_rate": 4.986908125482007e-05, "loss": 4.5237, "step": 1067 }, { "epoch": 0.032620647525962124, "grad_norm": 0.43682464957237244, "learning_rate": 4.9868835958772465e-05, "loss": 4.5105, "step": 1068 }, { "epoch": 0.032651191203420894, "grad_norm": 0.4248811602592468, "learning_rate": 4.98685904337447e-05, "loss": 4.4601, "step": 1069 }, { "epoch": 0.03268173488087966, "grad_norm": 0.4434506297111511, "learning_rate": 4.986834467973903e-05, "loss": 4.538, "step": 1070 }, { "epoch": 0.03271227855833842, "grad_norm": 0.43159741163253784, "learning_rate": 4.9868098696757734e-05, "loss": 4.4411, "step": 1071 }, { "epoch": 0.03274282223579719, "grad_norm": 0.443983793258667, "learning_rate": 4.986785248480306e-05, "loss": 4.4615, "step": 1072 }, { "epoch": 0.032773365913255956, "grad_norm": 0.43862029910087585, "learning_rate": 4.986760604387728e-05, "loss": 4.5168, "step": 1073 }, { "epoch": 0.03280390959071472, "grad_norm": 0.4303744435310364, "learning_rate": 4.986735937398268e-05, "loss": 4.4696, "step": 1074 }, { "epoch": 0.03283445326817349, "grad_norm": 0.4387555420398712, "learning_rate": 4.9867112475121504e-05, "loss": 4.4592, "step": 1075 }, { "epoch": 0.032864996945632254, "grad_norm": 0.4662041664123535, "learning_rate": 4.9866865347296044e-05, "loss": 4.4909, "step": 1076 }, { "epoch": 0.03289554062309102, "grad_norm": 0.4423297941684723, "learning_rate": 4.9866617990508566e-05, "loss": 4.5183, "step": 1077 }, { "epoch": 0.03292608430054979, "grad_norm": 0.43558868765830994, "learning_rate": 4.9866370404761354e-05, "loss": 4.468, "step": 1078 }, { "epoch": 0.03295662797800855, "grad_norm": 0.43419474363327026, "learning_rate": 4.986612259005668e-05, "loss": 4.498, "step": 1079 }, { "epoch": 0.032987171655467315, "grad_norm": 0.43076011538505554, "learning_rate": 4.9865874546396826e-05, "loss": 4.4287, "step": 1080 }, { "epoch": 0.033017715332926086, "grad_norm": 0.44016513228416443, "learning_rate": 4.986562627378409e-05, "loss": 4.4964, "step": 1081 }, { "epoch": 0.03304825901038485, "grad_norm": 0.45621171593666077, "learning_rate": 4.986537777222074e-05, "loss": 4.4579, "step": 1082 }, { "epoch": 0.03307880268784362, "grad_norm": 0.4468437731266022, "learning_rate": 4.9865129041709085e-05, "loss": 4.6057, "step": 1083 }, { "epoch": 0.03310934636530238, "grad_norm": 0.43346405029296875, "learning_rate": 4.9864880082251395e-05, "loss": 4.3745, "step": 1084 }, { "epoch": 0.03313989004276115, "grad_norm": 0.4402841329574585, "learning_rate": 4.9864630893849975e-05, "loss": 4.4996, "step": 1085 }, { "epoch": 0.03317043372021992, "grad_norm": 0.4605574607849121, "learning_rate": 4.98643814765071e-05, "loss": 4.5022, "step": 1086 }, { "epoch": 0.03320097739767868, "grad_norm": 0.4305304288864136, "learning_rate": 4.986413183022509e-05, "loss": 4.4675, "step": 1087 }, { "epoch": 0.033231521075137445, "grad_norm": 0.4292060136795044, "learning_rate": 4.986388195500624e-05, "loss": 4.4583, "step": 1088 }, { "epoch": 0.033262064752596215, "grad_norm": 0.4279692471027374, "learning_rate": 4.9863631850852835e-05, "loss": 4.5477, "step": 1089 }, { "epoch": 0.03329260843005498, "grad_norm": 0.42044252157211304, "learning_rate": 4.9863381517767194e-05, "loss": 4.424, "step": 1090 }, { "epoch": 0.03332315210751374, "grad_norm": 0.43720144033432007, "learning_rate": 4.9863130955751614e-05, "loss": 4.4426, "step": 1091 }, { "epoch": 0.03335369578497251, "grad_norm": 0.45280301570892334, "learning_rate": 4.9862880164808405e-05, "loss": 4.4856, "step": 1092 }, { "epoch": 0.03338423946243128, "grad_norm": 0.4337567389011383, "learning_rate": 4.986262914493988e-05, "loss": 4.495, "step": 1093 }, { "epoch": 0.03341478313989004, "grad_norm": 0.43958523869514465, "learning_rate": 4.986237789614834e-05, "loss": 4.4235, "step": 1094 }, { "epoch": 0.03344532681734881, "grad_norm": 0.4327262043952942, "learning_rate": 4.98621264184361e-05, "loss": 4.443, "step": 1095 }, { "epoch": 0.033475870494807575, "grad_norm": 0.4301166832447052, "learning_rate": 4.986187471180548e-05, "loss": 4.4519, "step": 1096 }, { "epoch": 0.03350641417226634, "grad_norm": 0.43165647983551025, "learning_rate": 4.98616227762588e-05, "loss": 4.447, "step": 1097 }, { "epoch": 0.03353695784972511, "grad_norm": 0.4367760121822357, "learning_rate": 4.9861370611798374e-05, "loss": 4.4346, "step": 1098 }, { "epoch": 0.03356750152718387, "grad_norm": 0.46036332845687866, "learning_rate": 4.9861118218426526e-05, "loss": 4.4829, "step": 1099 }, { "epoch": 0.033598045204642636, "grad_norm": 0.44425132870674133, "learning_rate": 4.986086559614559e-05, "loss": 4.504, "step": 1100 }, { "epoch": 0.03362858888210141, "grad_norm": 0.41933777928352356, "learning_rate": 4.9860612744957875e-05, "loss": 4.3575, "step": 1101 }, { "epoch": 0.03365913255956017, "grad_norm": 0.43945175409317017, "learning_rate": 4.9860359664865714e-05, "loss": 4.4937, "step": 1102 }, { "epoch": 0.033689676237018934, "grad_norm": 0.44876259565353394, "learning_rate": 4.986010635587144e-05, "loss": 4.4395, "step": 1103 }, { "epoch": 0.033720219914477705, "grad_norm": 0.43600842356681824, "learning_rate": 4.9859852817977395e-05, "loss": 4.5365, "step": 1104 }, { "epoch": 0.03375076359193647, "grad_norm": 0.4337829351425171, "learning_rate": 4.985959905118589e-05, "loss": 4.4693, "step": 1105 }, { "epoch": 0.03378130726939523, "grad_norm": 0.44273343682289124, "learning_rate": 4.985934505549928e-05, "loss": 4.4384, "step": 1106 }, { "epoch": 0.033811850946854, "grad_norm": 0.4442185163497925, "learning_rate": 4.98590908309199e-05, "loss": 4.4718, "step": 1107 }, { "epoch": 0.033842394624312766, "grad_norm": 0.4473362863063812, "learning_rate": 4.985883637745009e-05, "loss": 4.5074, "step": 1108 }, { "epoch": 0.03387293830177154, "grad_norm": 0.4468764662742615, "learning_rate": 4.985858169509219e-05, "loss": 4.4841, "step": 1109 }, { "epoch": 0.0339034819792303, "grad_norm": 0.42711302638053894, "learning_rate": 4.9858326783848546e-05, "loss": 4.5177, "step": 1110 }, { "epoch": 0.033934025656689064, "grad_norm": 0.4364064931869507, "learning_rate": 4.98580716437215e-05, "loss": 4.5481, "step": 1111 }, { "epoch": 0.033964569334147834, "grad_norm": 0.4542803168296814, "learning_rate": 4.985781627471342e-05, "loss": 4.5316, "step": 1112 }, { "epoch": 0.0339951130116066, "grad_norm": 0.439724862575531, "learning_rate": 4.985756067682664e-05, "loss": 4.5134, "step": 1113 }, { "epoch": 0.03402565668906536, "grad_norm": 0.43712863326072693, "learning_rate": 4.985730485006352e-05, "loss": 4.578, "step": 1114 }, { "epoch": 0.03405620036652413, "grad_norm": 0.4458712935447693, "learning_rate": 4.985704879442642e-05, "loss": 4.3777, "step": 1115 }, { "epoch": 0.034086744043982896, "grad_norm": 0.450823038816452, "learning_rate": 4.985679250991768e-05, "loss": 4.5162, "step": 1116 }, { "epoch": 0.03411728772144166, "grad_norm": 0.42946791648864746, "learning_rate": 4.985653599653968e-05, "loss": 4.4961, "step": 1117 }, { "epoch": 0.03414783139890043, "grad_norm": 0.4404873251914978, "learning_rate": 4.985627925429477e-05, "loss": 4.4626, "step": 1118 }, { "epoch": 0.034178375076359194, "grad_norm": 0.4353826642036438, "learning_rate": 4.985602228318531e-05, "loss": 4.4091, "step": 1119 }, { "epoch": 0.03420891875381796, "grad_norm": 0.43861129879951477, "learning_rate": 4.985576508321368e-05, "loss": 4.5357, "step": 1120 }, { "epoch": 0.03423946243127673, "grad_norm": 0.45822951197624207, "learning_rate": 4.9855507654382245e-05, "loss": 4.4963, "step": 1121 }, { "epoch": 0.03427000610873549, "grad_norm": 0.448813259601593, "learning_rate": 4.9855249996693366e-05, "loss": 4.5255, "step": 1122 }, { "epoch": 0.034300549786194255, "grad_norm": 0.43762990832328796, "learning_rate": 4.9854992110149426e-05, "loss": 4.3683, "step": 1123 }, { "epoch": 0.034331093463653026, "grad_norm": 0.44096678495407104, "learning_rate": 4.985473399475279e-05, "loss": 4.4542, "step": 1124 }, { "epoch": 0.03436163714111179, "grad_norm": 0.43811219930648804, "learning_rate": 4.985447565050584e-05, "loss": 4.436, "step": 1125 }, { "epoch": 0.03439218081857055, "grad_norm": 0.43330538272857666, "learning_rate": 4.9854217077410945e-05, "loss": 4.4173, "step": 1126 }, { "epoch": 0.034422724496029324, "grad_norm": 0.4506336450576782, "learning_rate": 4.985395827547051e-05, "loss": 4.5121, "step": 1127 }, { "epoch": 0.03445326817348809, "grad_norm": 0.44121015071868896, "learning_rate": 4.985369924468689e-05, "loss": 4.5182, "step": 1128 }, { "epoch": 0.03448381185094685, "grad_norm": 0.4426872134208679, "learning_rate": 4.985343998506249e-05, "loss": 4.5338, "step": 1129 }, { "epoch": 0.03451435552840562, "grad_norm": 0.4378417730331421, "learning_rate": 4.9853180496599694e-05, "loss": 4.4861, "step": 1130 }, { "epoch": 0.034544899205864385, "grad_norm": 0.43118369579315186, "learning_rate": 4.985292077930088e-05, "loss": 4.468, "step": 1131 }, { "epoch": 0.034575442883323156, "grad_norm": 0.4334087669849396, "learning_rate": 4.985266083316844e-05, "loss": 4.435, "step": 1132 }, { "epoch": 0.03460598656078192, "grad_norm": 0.4299747943878174, "learning_rate": 4.9852400658204784e-05, "loss": 4.3916, "step": 1133 }, { "epoch": 0.03463653023824068, "grad_norm": 0.42701882123947144, "learning_rate": 4.9852140254412295e-05, "loss": 4.4635, "step": 1134 }, { "epoch": 0.03466707391569945, "grad_norm": 0.4342126250267029, "learning_rate": 4.9851879621793373e-05, "loss": 4.4628, "step": 1135 }, { "epoch": 0.03469761759315822, "grad_norm": 0.43497344851493835, "learning_rate": 4.985161876035042e-05, "loss": 4.4579, "step": 1136 }, { "epoch": 0.03472816127061698, "grad_norm": 0.4326953589916229, "learning_rate": 4.985135767008583e-05, "loss": 4.4565, "step": 1137 }, { "epoch": 0.03475870494807575, "grad_norm": 0.45080652832984924, "learning_rate": 4.9851096351002014e-05, "loss": 4.4686, "step": 1138 }, { "epoch": 0.034789248625534515, "grad_norm": 0.42367488145828247, "learning_rate": 4.9850834803101374e-05, "loss": 4.4623, "step": 1139 }, { "epoch": 0.03481979230299328, "grad_norm": 0.43067672848701477, "learning_rate": 4.985057302638633e-05, "loss": 4.519, "step": 1140 }, { "epoch": 0.03485033598045205, "grad_norm": 0.4321616590023041, "learning_rate": 4.9850311020859273e-05, "loss": 4.4691, "step": 1141 }, { "epoch": 0.03488087965791081, "grad_norm": 0.43026959896087646, "learning_rate": 4.985004878652264e-05, "loss": 4.4803, "step": 1142 }, { "epoch": 0.034911423335369576, "grad_norm": 0.4343564808368683, "learning_rate": 4.9849786323378816e-05, "loss": 4.4528, "step": 1143 }, { "epoch": 0.03494196701282835, "grad_norm": 0.4423926770687103, "learning_rate": 4.984952363143024e-05, "loss": 4.4138, "step": 1144 }, { "epoch": 0.03497251069028711, "grad_norm": 0.4379522204399109, "learning_rate": 4.9849260710679326e-05, "loss": 4.4493, "step": 1145 }, { "epoch": 0.035003054367745874, "grad_norm": 0.42649638652801514, "learning_rate": 4.9848997561128484e-05, "loss": 4.4616, "step": 1146 }, { "epoch": 0.035033598045204645, "grad_norm": 0.43985220789909363, "learning_rate": 4.984873418278015e-05, "loss": 4.4585, "step": 1147 }, { "epoch": 0.03506414172266341, "grad_norm": 0.4598795175552368, "learning_rate": 4.984847057563674e-05, "loss": 4.5575, "step": 1148 }, { "epoch": 0.03509468540012217, "grad_norm": 0.43268752098083496, "learning_rate": 4.98482067397007e-05, "loss": 4.5097, "step": 1149 }, { "epoch": 0.03512522907758094, "grad_norm": 0.4416188597679138, "learning_rate": 4.984794267497443e-05, "loss": 4.4748, "step": 1150 }, { "epoch": 0.035155772755039706, "grad_norm": 0.4675302505493164, "learning_rate": 4.984767838146038e-05, "loss": 4.4865, "step": 1151 }, { "epoch": 0.03518631643249847, "grad_norm": 0.43643444776535034, "learning_rate": 4.9847413859160984e-05, "loss": 4.4599, "step": 1152 }, { "epoch": 0.03521686010995724, "grad_norm": 0.46044862270355225, "learning_rate": 4.9847149108078666e-05, "loss": 4.4309, "step": 1153 }, { "epoch": 0.035247403787416004, "grad_norm": 0.45665016770362854, "learning_rate": 4.9846884128215874e-05, "loss": 4.4889, "step": 1154 }, { "epoch": 0.03527794746487477, "grad_norm": 0.4454558193683624, "learning_rate": 4.984661891957505e-05, "loss": 4.501, "step": 1155 }, { "epoch": 0.03530849114233354, "grad_norm": 0.4348011910915375, "learning_rate": 4.984635348215863e-05, "loss": 4.4586, "step": 1156 }, { "epoch": 0.0353390348197923, "grad_norm": 0.4610336720943451, "learning_rate": 4.984608781596905e-05, "loss": 4.5651, "step": 1157 }, { "epoch": 0.03536957849725107, "grad_norm": 0.43759623169898987, "learning_rate": 4.9845821921008773e-05, "loss": 4.4791, "step": 1158 }, { "epoch": 0.035400122174709836, "grad_norm": 0.44950631260871887, "learning_rate": 4.984555579728024e-05, "loss": 4.4591, "step": 1159 }, { "epoch": 0.0354306658521686, "grad_norm": 0.4602692425251007, "learning_rate": 4.984528944478589e-05, "loss": 4.5095, "step": 1160 }, { "epoch": 0.03546120952962737, "grad_norm": 0.43360406160354614, "learning_rate": 4.98450228635282e-05, "loss": 4.4153, "step": 1161 }, { "epoch": 0.035491753207086134, "grad_norm": 0.43495339155197144, "learning_rate": 4.98447560535096e-05, "loss": 4.4649, "step": 1162 }, { "epoch": 0.0355222968845449, "grad_norm": 0.43823152780532837, "learning_rate": 4.9844489014732556e-05, "loss": 4.4552, "step": 1163 }, { "epoch": 0.03555284056200367, "grad_norm": 0.4301774203777313, "learning_rate": 4.984422174719954e-05, "loss": 4.5209, "step": 1164 }, { "epoch": 0.03558338423946243, "grad_norm": 0.43023261427879333, "learning_rate": 4.9843954250912985e-05, "loss": 4.5168, "step": 1165 }, { "epoch": 0.035613927916921195, "grad_norm": 0.4193190038204193, "learning_rate": 4.9843686525875384e-05, "loss": 4.4624, "step": 1166 }, { "epoch": 0.035644471594379966, "grad_norm": 0.43464651703834534, "learning_rate": 4.984341857208918e-05, "loss": 4.3882, "step": 1167 }, { "epoch": 0.03567501527183873, "grad_norm": 0.43792659044265747, "learning_rate": 4.984315038955685e-05, "loss": 4.4907, "step": 1168 }, { "epoch": 0.03570555894929749, "grad_norm": 0.43226343393325806, "learning_rate": 4.9842881978280856e-05, "loss": 4.5062, "step": 1169 }, { "epoch": 0.035736102626756264, "grad_norm": 0.4462173581123352, "learning_rate": 4.984261333826368e-05, "loss": 4.526, "step": 1170 }, { "epoch": 0.03576664630421503, "grad_norm": 0.4367814064025879, "learning_rate": 4.98423444695078e-05, "loss": 4.5197, "step": 1171 }, { "epoch": 0.03579718998167379, "grad_norm": 0.4318976402282715, "learning_rate": 4.9842075372015664e-05, "loss": 4.4505, "step": 1172 }, { "epoch": 0.03582773365913256, "grad_norm": 0.45005494356155396, "learning_rate": 4.984180604578977e-05, "loss": 4.5579, "step": 1173 }, { "epoch": 0.035858277336591325, "grad_norm": 0.45874378085136414, "learning_rate": 4.984153649083261e-05, "loss": 4.4527, "step": 1174 }, { "epoch": 0.03588882101405009, "grad_norm": 0.43518802523612976, "learning_rate": 4.984126670714664e-05, "loss": 4.5398, "step": 1175 }, { "epoch": 0.03591936469150886, "grad_norm": 0.4595767855644226, "learning_rate": 4.984099669473435e-05, "loss": 4.4806, "step": 1176 }, { "epoch": 0.03594990836896762, "grad_norm": 0.4606952667236328, "learning_rate": 4.984072645359824e-05, "loss": 4.4995, "step": 1177 }, { "epoch": 0.03598045204642639, "grad_norm": 0.4416442811489105, "learning_rate": 4.9840455983740794e-05, "loss": 4.4467, "step": 1178 }, { "epoch": 0.03601099572388516, "grad_norm": 0.4453841745853424, "learning_rate": 4.984018528516449e-05, "loss": 4.4669, "step": 1179 }, { "epoch": 0.03604153940134392, "grad_norm": 0.44378867745399475, "learning_rate": 4.983991435787183e-05, "loss": 4.534, "step": 1180 }, { "epoch": 0.036072083078802684, "grad_norm": 0.41994720697402954, "learning_rate": 4.9839643201865306e-05, "loss": 4.5236, "step": 1181 }, { "epoch": 0.036102626756261455, "grad_norm": 0.43042200803756714, "learning_rate": 4.983937181714742e-05, "loss": 4.4683, "step": 1182 }, { "epoch": 0.03613317043372022, "grad_norm": 0.4262160360813141, "learning_rate": 4.983910020372067e-05, "loss": 4.3899, "step": 1183 }, { "epoch": 0.03616371411117899, "grad_norm": 0.42623040080070496, "learning_rate": 4.983882836158754e-05, "loss": 4.4079, "step": 1184 }, { "epoch": 0.03619425778863775, "grad_norm": 0.42370226979255676, "learning_rate": 4.983855629075055e-05, "loss": 4.4726, "step": 1185 }, { "epoch": 0.036224801466096516, "grad_norm": 0.44347792863845825, "learning_rate": 4.9838283991212206e-05, "loss": 4.507, "step": 1186 }, { "epoch": 0.03625534514355529, "grad_norm": 0.44023630023002625, "learning_rate": 4.983801146297501e-05, "loss": 4.5005, "step": 1187 }, { "epoch": 0.03628588882101405, "grad_norm": 0.45449092984199524, "learning_rate": 4.983773870604148e-05, "loss": 4.4715, "step": 1188 }, { "epoch": 0.036316432498472814, "grad_norm": 0.430242657661438, "learning_rate": 4.9837465720414115e-05, "loss": 4.4558, "step": 1189 }, { "epoch": 0.036346976175931585, "grad_norm": 0.43173086643218994, "learning_rate": 4.983719250609542e-05, "loss": 4.4442, "step": 1190 }, { "epoch": 0.03637751985339035, "grad_norm": 0.44661852717399597, "learning_rate": 4.983691906308794e-05, "loss": 4.5042, "step": 1191 }, { "epoch": 0.03640806353084911, "grad_norm": 0.4272581934928894, "learning_rate": 4.9836645391394165e-05, "loss": 4.4768, "step": 1192 }, { "epoch": 0.03643860720830788, "grad_norm": 0.42819273471832275, "learning_rate": 4.9836371491016634e-05, "loss": 4.3772, "step": 1193 }, { "epoch": 0.036469150885766646, "grad_norm": 0.433056116104126, "learning_rate": 4.983609736195785e-05, "loss": 4.5226, "step": 1194 }, { "epoch": 0.03649969456322541, "grad_norm": 0.4289737045764923, "learning_rate": 4.983582300422036e-05, "loss": 4.4327, "step": 1195 }, { "epoch": 0.03653023824068418, "grad_norm": 0.42828169465065, "learning_rate": 4.983554841780668e-05, "loss": 4.4837, "step": 1196 }, { "epoch": 0.036560781918142944, "grad_norm": 0.4228408634662628, "learning_rate": 4.9835273602719324e-05, "loss": 4.5376, "step": 1197 }, { "epoch": 0.03659132559560171, "grad_norm": 0.4362833499908447, "learning_rate": 4.9834998558960844e-05, "loss": 4.4541, "step": 1198 }, { "epoch": 0.03662186927306048, "grad_norm": 0.4244055151939392, "learning_rate": 4.983472328653376e-05, "loss": 4.5013, "step": 1199 }, { "epoch": 0.03665241295051924, "grad_norm": 0.4297665059566498, "learning_rate": 4.983444778544061e-05, "loss": 4.4914, "step": 1200 }, { "epoch": 0.036682956627978006, "grad_norm": 0.43337881565093994, "learning_rate": 4.9834172055683934e-05, "loss": 4.4581, "step": 1201 }, { "epoch": 0.036713500305436776, "grad_norm": 0.4368029534816742, "learning_rate": 4.9833896097266264e-05, "loss": 4.4025, "step": 1202 }, { "epoch": 0.03674404398289554, "grad_norm": 0.4394289255142212, "learning_rate": 4.9833619910190145e-05, "loss": 4.5233, "step": 1203 }, { "epoch": 0.0367745876603543, "grad_norm": 0.424144983291626, "learning_rate": 4.983334349445812e-05, "loss": 4.4805, "step": 1204 }, { "epoch": 0.036805131337813074, "grad_norm": 0.4201831519603729, "learning_rate": 4.983306685007273e-05, "loss": 4.5006, "step": 1205 }, { "epoch": 0.03683567501527184, "grad_norm": 0.4299711585044861, "learning_rate": 4.983278997703653e-05, "loss": 4.4767, "step": 1206 }, { "epoch": 0.03686621869273061, "grad_norm": 0.42736679315567017, "learning_rate": 4.9832512875352065e-05, "loss": 4.4135, "step": 1207 }, { "epoch": 0.03689676237018937, "grad_norm": 0.4491906464099884, "learning_rate": 4.983223554502189e-05, "loss": 4.4721, "step": 1208 }, { "epoch": 0.036927306047648135, "grad_norm": 0.43775004148483276, "learning_rate": 4.9831957986048546e-05, "loss": 4.4666, "step": 1209 }, { "epoch": 0.036957849725106906, "grad_norm": 0.4346114695072174, "learning_rate": 4.9831680198434596e-05, "loss": 4.53, "step": 1210 }, { "epoch": 0.03698839340256567, "grad_norm": 0.44274914264678955, "learning_rate": 4.983140218218261e-05, "loss": 4.4561, "step": 1211 }, { "epoch": 0.03701893708002443, "grad_norm": 0.43384620547294617, "learning_rate": 4.983112393729513e-05, "loss": 4.4569, "step": 1212 }, { "epoch": 0.037049480757483204, "grad_norm": 0.42039912939071655, "learning_rate": 4.9830845463774724e-05, "loss": 4.4844, "step": 1213 }, { "epoch": 0.03708002443494197, "grad_norm": 0.42584022879600525, "learning_rate": 4.983056676162396e-05, "loss": 4.4229, "step": 1214 }, { "epoch": 0.03711056811240073, "grad_norm": 0.44918277859687805, "learning_rate": 4.98302878308454e-05, "loss": 4.41, "step": 1215 }, { "epoch": 0.0371411117898595, "grad_norm": 0.4274400472640991, "learning_rate": 4.983000867144162e-05, "loss": 4.4775, "step": 1216 }, { "epoch": 0.037171655467318265, "grad_norm": 0.4316425621509552, "learning_rate": 4.982972928341517e-05, "loss": 4.5423, "step": 1217 }, { "epoch": 0.03720219914477703, "grad_norm": 0.42477038502693176, "learning_rate": 4.9829449666768644e-05, "loss": 4.4727, "step": 1218 }, { "epoch": 0.0372327428222358, "grad_norm": 0.4198659360408783, "learning_rate": 4.982916982150462e-05, "loss": 4.476, "step": 1219 }, { "epoch": 0.03726328649969456, "grad_norm": 0.41879668831825256, "learning_rate": 4.982888974762565e-05, "loss": 4.426, "step": 1220 }, { "epoch": 0.03729383017715333, "grad_norm": 0.4336703419685364, "learning_rate": 4.9828609445134324e-05, "loss": 4.515, "step": 1221 }, { "epoch": 0.0373243738546121, "grad_norm": 0.43889063596725464, "learning_rate": 4.982832891403323e-05, "loss": 4.4591, "step": 1222 }, { "epoch": 0.03735491753207086, "grad_norm": 0.41877084970474243, "learning_rate": 4.982804815432495e-05, "loss": 4.5447, "step": 1223 }, { "epoch": 0.037385461209529625, "grad_norm": 0.4272119700908661, "learning_rate": 4.982776716601206e-05, "loss": 4.3911, "step": 1224 }, { "epoch": 0.037416004886988395, "grad_norm": 0.4249156415462494, "learning_rate": 4.9827485949097154e-05, "loss": 4.4696, "step": 1225 }, { "epoch": 0.03744654856444716, "grad_norm": 0.41837945580482483, "learning_rate": 4.9827204503582826e-05, "loss": 4.5672, "step": 1226 }, { "epoch": 0.03747709224190592, "grad_norm": 0.4367252290248871, "learning_rate": 4.982692282947165e-05, "loss": 4.4684, "step": 1227 }, { "epoch": 0.03750763591936469, "grad_norm": 0.4279501438140869, "learning_rate": 4.9826640926766237e-05, "loss": 4.4209, "step": 1228 }, { "epoch": 0.03753817959682346, "grad_norm": 0.4386809766292572, "learning_rate": 4.982635879546917e-05, "loss": 4.5115, "step": 1229 }, { "epoch": 0.03756872327428222, "grad_norm": 0.4277787506580353, "learning_rate": 4.982607643558307e-05, "loss": 4.3622, "step": 1230 }, { "epoch": 0.03759926695174099, "grad_norm": 0.45654767751693726, "learning_rate": 4.98257938471105e-05, "loss": 4.5345, "step": 1231 }, { "epoch": 0.037629810629199754, "grad_norm": 0.4459189176559448, "learning_rate": 4.9825511030054094e-05, "loss": 4.5284, "step": 1232 }, { "epoch": 0.037660354306658525, "grad_norm": 0.4362432062625885, "learning_rate": 4.9825227984416446e-05, "loss": 4.5151, "step": 1233 }, { "epoch": 0.03769089798411729, "grad_norm": 0.42307713627815247, "learning_rate": 4.9824944710200146e-05, "loss": 4.4692, "step": 1234 }, { "epoch": 0.03772144166157605, "grad_norm": 0.43038660287857056, "learning_rate": 4.982466120740783e-05, "loss": 4.5222, "step": 1235 }, { "epoch": 0.03775198533903482, "grad_norm": 0.436323344707489, "learning_rate": 4.982437747604209e-05, "loss": 4.4385, "step": 1236 }, { "epoch": 0.037782529016493586, "grad_norm": 0.42931392788887024, "learning_rate": 4.982409351610554e-05, "loss": 4.4546, "step": 1237 }, { "epoch": 0.03781307269395235, "grad_norm": 0.4325854778289795, "learning_rate": 4.98238093276008e-05, "loss": 4.4223, "step": 1238 }, { "epoch": 0.03784361637141112, "grad_norm": 0.4349120557308197, "learning_rate": 4.982352491053048e-05, "loss": 4.4783, "step": 1239 }, { "epoch": 0.037874160048869884, "grad_norm": 0.43097659945487976, "learning_rate": 4.982324026489722e-05, "loss": 4.5328, "step": 1240 }, { "epoch": 0.03790470372632865, "grad_norm": 0.43240121006965637, "learning_rate": 4.982295539070361e-05, "loss": 4.4592, "step": 1241 }, { "epoch": 0.03793524740378742, "grad_norm": 0.4288118779659271, "learning_rate": 4.982267028795229e-05, "loss": 4.3868, "step": 1242 }, { "epoch": 0.03796579108124618, "grad_norm": 0.4342803955078125, "learning_rate": 4.982238495664588e-05, "loss": 4.5267, "step": 1243 }, { "epoch": 0.037996334758704946, "grad_norm": 0.4295060932636261, "learning_rate": 4.982209939678701e-05, "loss": 4.5327, "step": 1244 }, { "epoch": 0.038026878436163716, "grad_norm": 0.4215022325515747, "learning_rate": 4.982181360837831e-05, "loss": 4.4777, "step": 1245 }, { "epoch": 0.03805742211362248, "grad_norm": 0.4495910704135895, "learning_rate": 4.982152759142241e-05, "loss": 4.4984, "step": 1246 }, { "epoch": 0.038087965791081244, "grad_norm": 0.43988174200057983, "learning_rate": 4.982124134592194e-05, "loss": 4.4515, "step": 1247 }, { "epoch": 0.038118509468540014, "grad_norm": 0.42749860882759094, "learning_rate": 4.9820954871879544e-05, "loss": 4.4063, "step": 1248 }, { "epoch": 0.03814905314599878, "grad_norm": 0.4256836175918579, "learning_rate": 4.982066816929785e-05, "loss": 4.4017, "step": 1249 }, { "epoch": 0.03817959682345754, "grad_norm": 0.44026514887809753, "learning_rate": 4.98203812381795e-05, "loss": 4.5146, "step": 1250 }, { "epoch": 0.03821014050091631, "grad_norm": 0.47141021490097046, "learning_rate": 4.982009407852715e-05, "loss": 4.5141, "step": 1251 }, { "epoch": 0.038240684178375076, "grad_norm": 0.4294418692588806, "learning_rate": 4.981980669034343e-05, "loss": 4.4734, "step": 1252 }, { "epoch": 0.03827122785583384, "grad_norm": 0.43947333097457886, "learning_rate": 4.981951907363098e-05, "loss": 4.4921, "step": 1253 }, { "epoch": 0.03830177153329261, "grad_norm": 0.4296603500843048, "learning_rate": 4.9819231228392463e-05, "loss": 4.4358, "step": 1254 }, { "epoch": 0.03833231521075137, "grad_norm": 0.4356744885444641, "learning_rate": 4.981894315463053e-05, "loss": 4.4406, "step": 1255 }, { "epoch": 0.03836285888821014, "grad_norm": 0.4495771825313568, "learning_rate": 4.9818654852347813e-05, "loss": 4.4928, "step": 1256 }, { "epoch": 0.03839340256566891, "grad_norm": 0.43896713852882385, "learning_rate": 4.9818366321546986e-05, "loss": 4.5139, "step": 1257 }, { "epoch": 0.03842394624312767, "grad_norm": 0.43626898527145386, "learning_rate": 4.98180775622307e-05, "loss": 4.4632, "step": 1258 }, { "epoch": 0.03845448992058644, "grad_norm": 0.43087896704673767, "learning_rate": 4.9817788574401613e-05, "loss": 4.5465, "step": 1259 }, { "epoch": 0.038485033598045205, "grad_norm": 0.4331875443458557, "learning_rate": 4.9817499358062395e-05, "loss": 4.4484, "step": 1260 }, { "epoch": 0.03851557727550397, "grad_norm": 0.4327346980571747, "learning_rate": 4.981720991321568e-05, "loss": 4.5244, "step": 1261 }, { "epoch": 0.03854612095296274, "grad_norm": 0.43072420358657837, "learning_rate": 4.9816920239864174e-05, "loss": 4.4326, "step": 1262 }, { "epoch": 0.0385766646304215, "grad_norm": 0.42721259593963623, "learning_rate": 4.981663033801052e-05, "loss": 4.3227, "step": 1263 }, { "epoch": 0.03860720830788027, "grad_norm": 0.41899558901786804, "learning_rate": 4.9816340207657387e-05, "loss": 4.4589, "step": 1264 }, { "epoch": 0.03863775198533904, "grad_norm": 0.42097437381744385, "learning_rate": 4.981604984880745e-05, "loss": 4.4119, "step": 1265 }, { "epoch": 0.0386682956627978, "grad_norm": 0.43626463413238525, "learning_rate": 4.9815759261463376e-05, "loss": 4.4984, "step": 1266 }, { "epoch": 0.038698839340256565, "grad_norm": 0.44170641899108887, "learning_rate": 4.981546844562785e-05, "loss": 4.5376, "step": 1267 }, { "epoch": 0.038729383017715335, "grad_norm": 0.4219547212123871, "learning_rate": 4.981517740130356e-05, "loss": 4.5269, "step": 1268 }, { "epoch": 0.0387599266951741, "grad_norm": 0.45047059655189514, "learning_rate": 4.981488612849317e-05, "loss": 4.5002, "step": 1269 }, { "epoch": 0.03879047037263286, "grad_norm": 0.4429052472114563, "learning_rate": 4.9814594627199355e-05, "loss": 4.5032, "step": 1270 }, { "epoch": 0.03882101405009163, "grad_norm": 0.4382612407207489, "learning_rate": 4.9814302897424815e-05, "loss": 4.4611, "step": 1271 }, { "epoch": 0.0388515577275504, "grad_norm": 0.4330303966999054, "learning_rate": 4.981401093917223e-05, "loss": 4.4564, "step": 1272 }, { "epoch": 0.03888210140500916, "grad_norm": 0.44408974051475525, "learning_rate": 4.9813718752444286e-05, "loss": 4.5375, "step": 1273 }, { "epoch": 0.03891264508246793, "grad_norm": 0.4430452883243561, "learning_rate": 4.981342633724368e-05, "loss": 4.4079, "step": 1274 }, { "epoch": 0.038943188759926695, "grad_norm": 0.44406959414482117, "learning_rate": 4.981313369357309e-05, "loss": 4.4402, "step": 1275 }, { "epoch": 0.03897373243738546, "grad_norm": 0.44824352860450745, "learning_rate": 4.9812840821435233e-05, "loss": 4.5766, "step": 1276 }, { "epoch": 0.03900427611484423, "grad_norm": 0.4281243681907654, "learning_rate": 4.981254772083278e-05, "loss": 4.5279, "step": 1277 }, { "epoch": 0.03903481979230299, "grad_norm": 0.4369008243083954, "learning_rate": 4.981225439176845e-05, "loss": 4.4642, "step": 1278 }, { "epoch": 0.039065363469761756, "grad_norm": 0.4645702838897705, "learning_rate": 4.981196083424494e-05, "loss": 4.5455, "step": 1279 }, { "epoch": 0.03909590714722053, "grad_norm": 0.4392424523830414, "learning_rate": 4.9811667048264946e-05, "loss": 4.5047, "step": 1280 }, { "epoch": 0.03912645082467929, "grad_norm": 0.4518178403377533, "learning_rate": 4.9811373033831175e-05, "loss": 4.4694, "step": 1281 }, { "epoch": 0.03915699450213806, "grad_norm": 0.45175525546073914, "learning_rate": 4.9811078790946344e-05, "loss": 4.52, "step": 1282 }, { "epoch": 0.039187538179596824, "grad_norm": 0.4598143696784973, "learning_rate": 4.981078431961315e-05, "loss": 4.4371, "step": 1283 }, { "epoch": 0.03921808185705559, "grad_norm": 0.4332829415798187, "learning_rate": 4.98104896198343e-05, "loss": 4.4147, "step": 1284 }, { "epoch": 0.03924862553451436, "grad_norm": 0.4311375617980957, "learning_rate": 4.981019469161252e-05, "loss": 4.4344, "step": 1285 }, { "epoch": 0.03927916921197312, "grad_norm": 0.4320319890975952, "learning_rate": 4.980989953495052e-05, "loss": 4.4602, "step": 1286 }, { "epoch": 0.039309712889431886, "grad_norm": 0.4544300138950348, "learning_rate": 4.980960414985103e-05, "loss": 4.4632, "step": 1287 }, { "epoch": 0.039340256566890656, "grad_norm": 0.43135714530944824, "learning_rate": 4.9809308536316745e-05, "loss": 4.4238, "step": 1288 }, { "epoch": 0.03937080024434942, "grad_norm": 0.42065566778182983, "learning_rate": 4.980901269435041e-05, "loss": 4.466, "step": 1289 }, { "epoch": 0.039401343921808184, "grad_norm": 0.43470484018325806, "learning_rate": 4.980871662395473e-05, "loss": 4.4836, "step": 1290 }, { "epoch": 0.039431887599266954, "grad_norm": 0.426692396402359, "learning_rate": 4.9808420325132455e-05, "loss": 4.4182, "step": 1291 }, { "epoch": 0.03946243127672572, "grad_norm": 0.44513458013534546, "learning_rate": 4.9808123797886284e-05, "loss": 4.4689, "step": 1292 }, { "epoch": 0.03949297495418448, "grad_norm": 0.4191712737083435, "learning_rate": 4.980782704221897e-05, "loss": 4.4663, "step": 1293 }, { "epoch": 0.03952351863164325, "grad_norm": 0.4329189360141754, "learning_rate": 4.9807530058133236e-05, "loss": 4.4714, "step": 1294 }, { "epoch": 0.039554062309102016, "grad_norm": 0.42188072204589844, "learning_rate": 4.980723284563182e-05, "loss": 4.5041, "step": 1295 }, { "epoch": 0.03958460598656078, "grad_norm": 0.43049517273902893, "learning_rate": 4.980693540471745e-05, "loss": 4.4429, "step": 1296 }, { "epoch": 0.03961514966401955, "grad_norm": 0.4219736158847809, "learning_rate": 4.980663773539288e-05, "loss": 4.4494, "step": 1297 }, { "epoch": 0.039645693341478314, "grad_norm": 0.44677576422691345, "learning_rate": 4.980633983766084e-05, "loss": 4.4129, "step": 1298 }, { "epoch": 0.03967623701893708, "grad_norm": 0.42908212542533875, "learning_rate": 4.980604171152407e-05, "loss": 4.442, "step": 1299 }, { "epoch": 0.03970678069639585, "grad_norm": 0.44729387760162354, "learning_rate": 4.980574335698532e-05, "loss": 4.5054, "step": 1300 }, { "epoch": 0.03973732437385461, "grad_norm": 0.4136873781681061, "learning_rate": 4.980544477404734e-05, "loss": 4.3942, "step": 1301 }, { "epoch": 0.039767868051313375, "grad_norm": 0.45581960678100586, "learning_rate": 4.980514596271288e-05, "loss": 4.4563, "step": 1302 }, { "epoch": 0.039798411728772146, "grad_norm": 0.4331686794757843, "learning_rate": 4.9804846922984684e-05, "loss": 4.4625, "step": 1303 }, { "epoch": 0.03982895540623091, "grad_norm": 0.43477243185043335, "learning_rate": 4.980454765486551e-05, "loss": 4.49, "step": 1304 }, { "epoch": 0.03985949908368967, "grad_norm": 0.4294906258583069, "learning_rate": 4.9804248158358106e-05, "loss": 4.4863, "step": 1305 }, { "epoch": 0.03989004276114844, "grad_norm": 0.4312804043292999, "learning_rate": 4.980394843346524e-05, "loss": 4.5204, "step": 1306 }, { "epoch": 0.03992058643860721, "grad_norm": 0.43250778317451477, "learning_rate": 4.980364848018967e-05, "loss": 4.4604, "step": 1307 }, { "epoch": 0.03995113011606598, "grad_norm": 0.4414885938167572, "learning_rate": 4.9803348298534156e-05, "loss": 4.506, "step": 1308 }, { "epoch": 0.03998167379352474, "grad_norm": 0.42682239413261414, "learning_rate": 4.9803047888501464e-05, "loss": 4.4411, "step": 1309 }, { "epoch": 0.040012217470983505, "grad_norm": 0.42635488510131836, "learning_rate": 4.980274725009435e-05, "loss": 4.4877, "step": 1310 }, { "epoch": 0.040042761148442275, "grad_norm": 0.42135557532310486, "learning_rate": 4.9802446383315594e-05, "loss": 4.4579, "step": 1311 }, { "epoch": 0.04007330482590104, "grad_norm": 0.4305514693260193, "learning_rate": 4.980214528816796e-05, "loss": 4.4463, "step": 1312 }, { "epoch": 0.0401038485033598, "grad_norm": 0.4285798668861389, "learning_rate": 4.9801843964654225e-05, "loss": 4.5089, "step": 1313 }, { "epoch": 0.04013439218081857, "grad_norm": 0.4329708218574524, "learning_rate": 4.9801542412777155e-05, "loss": 4.5756, "step": 1314 }, { "epoch": 0.04016493585827734, "grad_norm": 0.4319542944431305, "learning_rate": 4.980124063253955e-05, "loss": 4.4499, "step": 1315 }, { "epoch": 0.0401954795357361, "grad_norm": 0.44449472427368164, "learning_rate": 4.980093862394415e-05, "loss": 4.5154, "step": 1316 }, { "epoch": 0.04022602321319487, "grad_norm": 0.43124598264694214, "learning_rate": 4.980063638699377e-05, "loss": 4.451, "step": 1317 }, { "epoch": 0.040256566890653635, "grad_norm": 0.43049636483192444, "learning_rate": 4.980033392169117e-05, "loss": 4.4988, "step": 1318 }, { "epoch": 0.0402871105681124, "grad_norm": 0.44063669443130493, "learning_rate": 4.9800031228039154e-05, "loss": 4.4877, "step": 1319 }, { "epoch": 0.04031765424557117, "grad_norm": 0.4106568396091461, "learning_rate": 4.979972830604049e-05, "loss": 4.4376, "step": 1320 }, { "epoch": 0.04034819792302993, "grad_norm": 0.4263697564601898, "learning_rate": 4.979942515569798e-05, "loss": 4.5058, "step": 1321 }, { "epoch": 0.040378741600488696, "grad_norm": 0.4327084422111511, "learning_rate": 4.979912177701441e-05, "loss": 4.4274, "step": 1322 }, { "epoch": 0.04040928527794747, "grad_norm": 0.44387510418891907, "learning_rate": 4.9798818169992585e-05, "loss": 4.5274, "step": 1323 }, { "epoch": 0.04043982895540623, "grad_norm": 0.43175598978996277, "learning_rate": 4.979851433463528e-05, "loss": 4.474, "step": 1324 }, { "epoch": 0.040470372632864994, "grad_norm": 0.4172610938549042, "learning_rate": 4.979821027094531e-05, "loss": 4.4824, "step": 1325 }, { "epoch": 0.040500916310323765, "grad_norm": 0.4263928532600403, "learning_rate": 4.9797905978925464e-05, "loss": 4.3952, "step": 1326 }, { "epoch": 0.04053145998778253, "grad_norm": 0.4528030455112457, "learning_rate": 4.979760145857855e-05, "loss": 4.5135, "step": 1327 }, { "epoch": 0.04056200366524129, "grad_norm": 0.4356888234615326, "learning_rate": 4.9797296709907374e-05, "loss": 4.4651, "step": 1328 }, { "epoch": 0.04059254734270006, "grad_norm": 0.4260261356830597, "learning_rate": 4.979699173291473e-05, "loss": 4.4212, "step": 1329 }, { "epoch": 0.040623091020158826, "grad_norm": 0.4471377730369568, "learning_rate": 4.979668652760344e-05, "loss": 4.4843, "step": 1330 }, { "epoch": 0.0406536346976176, "grad_norm": 0.44659867882728577, "learning_rate": 4.9796381093976304e-05, "loss": 4.5203, "step": 1331 }, { "epoch": 0.04068417837507636, "grad_norm": 0.43786412477493286, "learning_rate": 4.9796075432036135e-05, "loss": 4.4545, "step": 1332 }, { "epoch": 0.040714722052535124, "grad_norm": 0.42211729288101196, "learning_rate": 4.9795769541785757e-05, "loss": 4.4111, "step": 1333 }, { "epoch": 0.040745265729993894, "grad_norm": 0.42555707693099976, "learning_rate": 4.979546342322798e-05, "loss": 4.4906, "step": 1334 }, { "epoch": 0.04077580940745266, "grad_norm": 0.41672253608703613, "learning_rate": 4.979515707636562e-05, "loss": 4.4659, "step": 1335 }, { "epoch": 0.04080635308491142, "grad_norm": 0.45060431957244873, "learning_rate": 4.9794850501201494e-05, "loss": 4.4239, "step": 1336 }, { "epoch": 0.04083689676237019, "grad_norm": 0.44305115938186646, "learning_rate": 4.979454369773845e-05, "loss": 4.5081, "step": 1337 }, { "epoch": 0.040867440439828956, "grad_norm": 0.4362044036388397, "learning_rate": 4.979423666597928e-05, "loss": 4.4708, "step": 1338 }, { "epoch": 0.04089798411728772, "grad_norm": 0.43121883273124695, "learning_rate": 4.979392940592682e-05, "loss": 4.4751, "step": 1339 }, { "epoch": 0.04092852779474649, "grad_norm": 0.4373183846473694, "learning_rate": 4.979362191758391e-05, "loss": 4.5085, "step": 1340 }, { "epoch": 0.040959071472205254, "grad_norm": 0.44077861309051514, "learning_rate": 4.979331420095338e-05, "loss": 4.5424, "step": 1341 }, { "epoch": 0.04098961514966402, "grad_norm": 0.4415019750595093, "learning_rate": 4.9793006256038055e-05, "loss": 4.4512, "step": 1342 }, { "epoch": 0.04102015882712279, "grad_norm": 0.42088136076927185, "learning_rate": 4.9792698082840774e-05, "loss": 4.4326, "step": 1343 }, { "epoch": 0.04105070250458155, "grad_norm": 0.4213380515575409, "learning_rate": 4.979238968136438e-05, "loss": 4.4098, "step": 1344 }, { "epoch": 0.041081246182040315, "grad_norm": 0.4362452030181885, "learning_rate": 4.97920810516117e-05, "loss": 4.4865, "step": 1345 }, { "epoch": 0.041111789859499086, "grad_norm": 0.4251163899898529, "learning_rate": 4.979177219358558e-05, "loss": 4.4547, "step": 1346 }, { "epoch": 0.04114233353695785, "grad_norm": 0.4361472725868225, "learning_rate": 4.979146310728888e-05, "loss": 4.4584, "step": 1347 }, { "epoch": 0.04117287721441661, "grad_norm": 0.4259623885154724, "learning_rate": 4.9791153792724424e-05, "loss": 4.4159, "step": 1348 }, { "epoch": 0.041203420891875384, "grad_norm": 0.424018532037735, "learning_rate": 4.979084424989507e-05, "loss": 4.4784, "step": 1349 }, { "epoch": 0.04123396456933415, "grad_norm": 0.4327428936958313, "learning_rate": 4.9790534478803666e-05, "loss": 4.5255, "step": 1350 }, { "epoch": 0.04126450824679291, "grad_norm": 0.4475521147251129, "learning_rate": 4.979022447945306e-05, "loss": 4.473, "step": 1351 }, { "epoch": 0.04129505192425168, "grad_norm": 0.42733076214790344, "learning_rate": 4.978991425184611e-05, "loss": 4.4604, "step": 1352 }, { "epoch": 0.041325595601710445, "grad_norm": 0.43195682764053345, "learning_rate": 4.978960379598569e-05, "loss": 4.4887, "step": 1353 }, { "epoch": 0.04135613927916921, "grad_norm": 0.4308215379714966, "learning_rate": 4.9789293111874636e-05, "loss": 4.4892, "step": 1354 }, { "epoch": 0.04138668295662798, "grad_norm": 0.4330419898033142, "learning_rate": 4.978898219951581e-05, "loss": 4.4761, "step": 1355 }, { "epoch": 0.04141722663408674, "grad_norm": 0.43421852588653564, "learning_rate": 4.978867105891208e-05, "loss": 4.5241, "step": 1356 }, { "epoch": 0.04144777031154551, "grad_norm": 0.42901626229286194, "learning_rate": 4.978835969006631e-05, "loss": 4.4557, "step": 1357 }, { "epoch": 0.04147831398900428, "grad_norm": 0.4268363118171692, "learning_rate": 4.9788048092981364e-05, "loss": 4.4951, "step": 1358 }, { "epoch": 0.04150885766646304, "grad_norm": 0.4319549798965454, "learning_rate": 4.9787736267660124e-05, "loss": 4.4702, "step": 1359 }, { "epoch": 0.04153940134392181, "grad_norm": 0.4281691908836365, "learning_rate": 4.978742421410545e-05, "loss": 4.4941, "step": 1360 }, { "epoch": 0.041569945021380575, "grad_norm": 0.4197748899459839, "learning_rate": 4.978711193232021e-05, "loss": 4.4456, "step": 1361 }, { "epoch": 0.04160048869883934, "grad_norm": 0.41866421699523926, "learning_rate": 4.9786799422307297e-05, "loss": 4.5382, "step": 1362 }, { "epoch": 0.04163103237629811, "grad_norm": 0.4136416018009186, "learning_rate": 4.9786486684069565e-05, "loss": 4.4313, "step": 1363 }, { "epoch": 0.04166157605375687, "grad_norm": 0.4386947453022003, "learning_rate": 4.978617371760991e-05, "loss": 4.465, "step": 1364 }, { "epoch": 0.041692119731215636, "grad_norm": 0.42825746536254883, "learning_rate": 4.978586052293122e-05, "loss": 4.5283, "step": 1365 }, { "epoch": 0.04172266340867441, "grad_norm": 0.4262630045413971, "learning_rate": 4.9785547100036354e-05, "loss": 4.491, "step": 1366 }, { "epoch": 0.04175320708613317, "grad_norm": 0.42729702591896057, "learning_rate": 4.978523344892822e-05, "loss": 4.4316, "step": 1367 }, { "epoch": 0.041783750763591934, "grad_norm": 0.42674586176872253, "learning_rate": 4.97849195696097e-05, "loss": 4.5588, "step": 1368 }, { "epoch": 0.041814294441050705, "grad_norm": 0.42693766951560974, "learning_rate": 4.978460546208368e-05, "loss": 4.4852, "step": 1369 }, { "epoch": 0.04184483811850947, "grad_norm": 0.42388325929641724, "learning_rate": 4.978429112635305e-05, "loss": 4.429, "step": 1370 }, { "epoch": 0.04187538179596823, "grad_norm": 0.44971978664398193, "learning_rate": 4.9783976562420706e-05, "loss": 4.5116, "step": 1371 }, { "epoch": 0.041905925473427, "grad_norm": 0.43425890803337097, "learning_rate": 4.9783661770289556e-05, "loss": 4.5896, "step": 1372 }, { "epoch": 0.041936469150885766, "grad_norm": 0.43778127431869507, "learning_rate": 4.978334674996249e-05, "loss": 4.5128, "step": 1373 }, { "epoch": 0.04196701282834453, "grad_norm": 0.42984434962272644, "learning_rate": 4.9783031501442406e-05, "loss": 4.5271, "step": 1374 }, { "epoch": 0.0419975565058033, "grad_norm": 0.45334264636039734, "learning_rate": 4.9782716024732214e-05, "loss": 4.4877, "step": 1375 }, { "epoch": 0.042028100183262064, "grad_norm": 0.4359396696090698, "learning_rate": 4.9782400319834795e-05, "loss": 4.4955, "step": 1376 }, { "epoch": 0.04205864386072083, "grad_norm": 0.41660574078559875, "learning_rate": 4.978208438675309e-05, "loss": 4.4211, "step": 1377 }, { "epoch": 0.0420891875381796, "grad_norm": 0.4244540333747864, "learning_rate": 4.9781768225489994e-05, "loss": 4.4318, "step": 1378 }, { "epoch": 0.04211973121563836, "grad_norm": 0.4175567626953125, "learning_rate": 4.978145183604841e-05, "loss": 4.5125, "step": 1379 }, { "epoch": 0.042150274893097125, "grad_norm": 0.42198285460472107, "learning_rate": 4.978113521843126e-05, "loss": 4.3635, "step": 1380 }, { "epoch": 0.042180818570555896, "grad_norm": 0.4389648735523224, "learning_rate": 4.978081837264146e-05, "loss": 4.4078, "step": 1381 }, { "epoch": 0.04221136224801466, "grad_norm": 0.45750412344932556, "learning_rate": 4.978050129868192e-05, "loss": 4.4334, "step": 1382 }, { "epoch": 0.04224190592547343, "grad_norm": 0.4083096981048584, "learning_rate": 4.978018399655556e-05, "loss": 4.4091, "step": 1383 }, { "epoch": 0.042272449602932194, "grad_norm": 0.4272179901599884, "learning_rate": 4.977986646626531e-05, "loss": 4.4017, "step": 1384 }, { "epoch": 0.04230299328039096, "grad_norm": 0.42709460854530334, "learning_rate": 4.9779548707814095e-05, "loss": 4.467, "step": 1385 }, { "epoch": 0.04233353695784973, "grad_norm": 0.43027523159980774, "learning_rate": 4.977923072120483e-05, "loss": 4.5164, "step": 1386 }, { "epoch": 0.04236408063530849, "grad_norm": 0.4380227029323578, "learning_rate": 4.977891250644044e-05, "loss": 4.445, "step": 1387 }, { "epoch": 0.042394624312767255, "grad_norm": 0.4279484152793884, "learning_rate": 4.977859406352387e-05, "loss": 4.4531, "step": 1388 }, { "epoch": 0.042425167990226026, "grad_norm": 0.42523515224456787, "learning_rate": 4.977827539245804e-05, "loss": 4.5088, "step": 1389 }, { "epoch": 0.04245571166768479, "grad_norm": 0.4174189865589142, "learning_rate": 4.977795649324589e-05, "loss": 4.3957, "step": 1390 }, { "epoch": 0.04248625534514355, "grad_norm": 0.4240768551826477, "learning_rate": 4.977763736589036e-05, "loss": 4.462, "step": 1391 }, { "epoch": 0.042516799022602324, "grad_norm": 0.4301595985889435, "learning_rate": 4.977731801039438e-05, "loss": 4.459, "step": 1392 }, { "epoch": 0.04254734270006109, "grad_norm": 0.4287280738353729, "learning_rate": 4.977699842676089e-05, "loss": 4.517, "step": 1393 }, { "epoch": 0.04257788637751985, "grad_norm": 0.4386129379272461, "learning_rate": 4.9776678614992846e-05, "loss": 4.5332, "step": 1394 }, { "epoch": 0.04260843005497862, "grad_norm": 0.4403684735298157, "learning_rate": 4.9776358575093174e-05, "loss": 4.4502, "step": 1395 }, { "epoch": 0.042638973732437385, "grad_norm": 0.4220081865787506, "learning_rate": 4.977603830706483e-05, "loss": 4.4082, "step": 1396 }, { "epoch": 0.04266951740989615, "grad_norm": 0.4660375416278839, "learning_rate": 4.977571781091077e-05, "loss": 4.4933, "step": 1397 }, { "epoch": 0.04270006108735492, "grad_norm": 0.4321023225784302, "learning_rate": 4.9775397086633937e-05, "loss": 4.4804, "step": 1398 }, { "epoch": 0.04273060476481368, "grad_norm": 0.42573976516723633, "learning_rate": 4.977507613423728e-05, "loss": 4.4117, "step": 1399 }, { "epoch": 0.04276114844227245, "grad_norm": 0.4289371073246002, "learning_rate": 4.977475495372376e-05, "loss": 4.4373, "step": 1400 }, { "epoch": 0.04279169211973122, "grad_norm": 0.4294872283935547, "learning_rate": 4.977443354509633e-05, "loss": 4.348, "step": 1401 }, { "epoch": 0.04282223579718998, "grad_norm": 0.4287579357624054, "learning_rate": 4.9774111908357955e-05, "loss": 4.496, "step": 1402 }, { "epoch": 0.042852779474648744, "grad_norm": 0.4249367415904999, "learning_rate": 4.9773790043511595e-05, "loss": 4.3899, "step": 1403 }, { "epoch": 0.042883323152107515, "grad_norm": 0.43048223853111267, "learning_rate": 4.977346795056022e-05, "loss": 4.4568, "step": 1404 }, { "epoch": 0.04291386682956628, "grad_norm": 0.43979430198669434, "learning_rate": 4.977314562950677e-05, "loss": 4.4644, "step": 1405 }, { "epoch": 0.04294441050702505, "grad_norm": 0.42741861939430237, "learning_rate": 4.977282308035425e-05, "loss": 4.5128, "step": 1406 }, { "epoch": 0.04297495418448381, "grad_norm": 0.4269108772277832, "learning_rate": 4.9772500303105595e-05, "loss": 4.3813, "step": 1407 }, { "epoch": 0.043005497861942577, "grad_norm": 0.4315357506275177, "learning_rate": 4.977217729776381e-05, "loss": 4.4588, "step": 1408 }, { "epoch": 0.04303604153940135, "grad_norm": 0.4136689007282257, "learning_rate": 4.977185406433184e-05, "loss": 4.4901, "step": 1409 }, { "epoch": 0.04306658521686011, "grad_norm": 0.4294436573982239, "learning_rate": 4.977153060281268e-05, "loss": 4.4695, "step": 1410 }, { "epoch": 0.043097128894318874, "grad_norm": 0.4317609667778015, "learning_rate": 4.977120691320929e-05, "loss": 4.5301, "step": 1411 }, { "epoch": 0.043127672571777645, "grad_norm": 0.42581072449684143, "learning_rate": 4.977088299552467e-05, "loss": 4.4289, "step": 1412 }, { "epoch": 0.04315821624923641, "grad_norm": 0.4167250692844391, "learning_rate": 4.9770558849761795e-05, "loss": 4.5058, "step": 1413 }, { "epoch": 0.04318875992669517, "grad_norm": 0.42585283517837524, "learning_rate": 4.977023447592365e-05, "loss": 4.5236, "step": 1414 }, { "epoch": 0.04321930360415394, "grad_norm": 0.4276866316795349, "learning_rate": 4.976990987401322e-05, "loss": 4.5082, "step": 1415 }, { "epoch": 0.043249847281612706, "grad_norm": 0.42160236835479736, "learning_rate": 4.976958504403349e-05, "loss": 4.5445, "step": 1416 }, { "epoch": 0.04328039095907147, "grad_norm": 0.42081835865974426, "learning_rate": 4.976925998598746e-05, "loss": 4.4651, "step": 1417 }, { "epoch": 0.04331093463653024, "grad_norm": 0.4347904920578003, "learning_rate": 4.976893469987811e-05, "loss": 4.4361, "step": 1418 }, { "epoch": 0.043341478313989004, "grad_norm": 0.42379042506217957, "learning_rate": 4.976860918570845e-05, "loss": 4.5011, "step": 1419 }, { "epoch": 0.04337202199144777, "grad_norm": 0.4236457645893097, "learning_rate": 4.9768283443481477e-05, "loss": 4.405, "step": 1420 }, { "epoch": 0.04340256566890654, "grad_norm": 0.42634057998657227, "learning_rate": 4.976795747320018e-05, "loss": 4.4949, "step": 1421 }, { "epoch": 0.0434331093463653, "grad_norm": 0.43245455622673035, "learning_rate": 4.976763127486756e-05, "loss": 4.4981, "step": 1422 }, { "epoch": 0.043463653023824066, "grad_norm": 0.433727890253067, "learning_rate": 4.9767304848486616e-05, "loss": 4.4558, "step": 1423 }, { "epoch": 0.043494196701282836, "grad_norm": 0.43212246894836426, "learning_rate": 4.976697819406038e-05, "loss": 4.4717, "step": 1424 }, { "epoch": 0.0435247403787416, "grad_norm": 0.45063862204551697, "learning_rate": 4.976665131159183e-05, "loss": 4.3613, "step": 1425 }, { "epoch": 0.043555284056200363, "grad_norm": 0.42698562145233154, "learning_rate": 4.976632420108399e-05, "loss": 4.5137, "step": 1426 }, { "epoch": 0.043585827733659134, "grad_norm": 0.4211123287677765, "learning_rate": 4.976599686253987e-05, "loss": 4.4365, "step": 1427 }, { "epoch": 0.0436163714111179, "grad_norm": 0.44610917568206787, "learning_rate": 4.9765669295962486e-05, "loss": 4.4385, "step": 1428 }, { "epoch": 0.04364691508857666, "grad_norm": 0.42322659492492676, "learning_rate": 4.976534150135485e-05, "loss": 4.4843, "step": 1429 }, { "epoch": 0.04367745876603543, "grad_norm": 0.41679227352142334, "learning_rate": 4.976501347871998e-05, "loss": 4.393, "step": 1430 }, { "epoch": 0.043708002443494195, "grad_norm": 0.41829654574394226, "learning_rate": 4.9764685228060904e-05, "loss": 4.3589, "step": 1431 }, { "epoch": 0.043738546120952966, "grad_norm": 0.44328761100769043, "learning_rate": 4.976435674938063e-05, "loss": 4.5954, "step": 1432 }, { "epoch": 0.04376908979841173, "grad_norm": 0.4222569763660431, "learning_rate": 4.97640280426822e-05, "loss": 4.4141, "step": 1433 }, { "epoch": 0.04379963347587049, "grad_norm": 0.4231128990650177, "learning_rate": 4.976369910796862e-05, "loss": 4.4747, "step": 1434 }, { "epoch": 0.043830177153329264, "grad_norm": 0.4348537027835846, "learning_rate": 4.9763369945242935e-05, "loss": 4.5202, "step": 1435 }, { "epoch": 0.04386072083078803, "grad_norm": 0.4406977593898773, "learning_rate": 4.9763040554508175e-05, "loss": 4.6047, "step": 1436 }, { "epoch": 0.04389126450824679, "grad_norm": 0.4262091815471649, "learning_rate": 4.9762710935767364e-05, "loss": 4.4418, "step": 1437 }, { "epoch": 0.04392180818570556, "grad_norm": 0.41806983947753906, "learning_rate": 4.976238108902355e-05, "loss": 4.4351, "step": 1438 }, { "epoch": 0.043952351863164325, "grad_norm": 0.411943256855011, "learning_rate": 4.976205101427975e-05, "loss": 4.4247, "step": 1439 }, { "epoch": 0.04398289554062309, "grad_norm": 0.4363647699356079, "learning_rate": 4.976172071153902e-05, "loss": 4.4738, "step": 1440 }, { "epoch": 0.04401343921808186, "grad_norm": 0.4272732734680176, "learning_rate": 4.9761390180804394e-05, "loss": 4.3903, "step": 1441 }, { "epoch": 0.04404398289554062, "grad_norm": 0.4318220615386963, "learning_rate": 4.976105942207892e-05, "loss": 4.3724, "step": 1442 }, { "epoch": 0.04407452657299939, "grad_norm": 0.42104217410087585, "learning_rate": 4.976072843536565e-05, "loss": 4.412, "step": 1443 }, { "epoch": 0.04410507025045816, "grad_norm": 0.43223148584365845, "learning_rate": 4.976039722066761e-05, "loss": 4.4246, "step": 1444 }, { "epoch": 0.04413561392791692, "grad_norm": 0.4201071560382843, "learning_rate": 4.9760065777987865e-05, "loss": 4.4804, "step": 1445 }, { "epoch": 0.044166157605375685, "grad_norm": 0.4402651786804199, "learning_rate": 4.975973410732946e-05, "loss": 4.51, "step": 1446 }, { "epoch": 0.044196701282834455, "grad_norm": 0.42723792791366577, "learning_rate": 4.975940220869546e-05, "loss": 4.4963, "step": 1447 }, { "epoch": 0.04422724496029322, "grad_norm": 0.4494529962539673, "learning_rate": 4.975907008208891e-05, "loss": 4.4794, "step": 1448 }, { "epoch": 0.04425778863775198, "grad_norm": 0.447825163602829, "learning_rate": 4.9758737727512875e-05, "loss": 4.3621, "step": 1449 }, { "epoch": 0.04428833231521075, "grad_norm": 0.4220925271511078, "learning_rate": 4.975840514497041e-05, "loss": 4.3869, "step": 1450 }, { "epoch": 0.04431887599266952, "grad_norm": 0.4259473383426666, "learning_rate": 4.975807233446458e-05, "loss": 4.4306, "step": 1451 }, { "epoch": 0.04434941967012828, "grad_norm": 0.41890963912010193, "learning_rate": 4.975773929599845e-05, "loss": 4.4426, "step": 1452 }, { "epoch": 0.04437996334758705, "grad_norm": 0.4436529278755188, "learning_rate": 4.975740602957508e-05, "loss": 4.4334, "step": 1453 }, { "epoch": 0.044410507025045814, "grad_norm": 0.41458866000175476, "learning_rate": 4.9757072535197546e-05, "loss": 4.4563, "step": 1454 }, { "epoch": 0.04444105070250458, "grad_norm": 0.4380228817462921, "learning_rate": 4.975673881286892e-05, "loss": 4.5228, "step": 1455 }, { "epoch": 0.04447159437996335, "grad_norm": 0.4202967584133148, "learning_rate": 4.9756404862592266e-05, "loss": 4.4045, "step": 1456 }, { "epoch": 0.04450213805742211, "grad_norm": 0.42022189497947693, "learning_rate": 4.975607068437067e-05, "loss": 4.4487, "step": 1457 }, { "epoch": 0.04453268173488088, "grad_norm": 0.41675445437431335, "learning_rate": 4.97557362782072e-05, "loss": 4.3979, "step": 1458 }, { "epoch": 0.044563225412339647, "grad_norm": 0.4196869730949402, "learning_rate": 4.975540164410494e-05, "loss": 4.5396, "step": 1459 }, { "epoch": 0.04459376908979841, "grad_norm": 0.42956623435020447, "learning_rate": 4.9755066782066965e-05, "loss": 4.4627, "step": 1460 }, { "epoch": 0.04462431276725718, "grad_norm": 0.43254268169403076, "learning_rate": 4.9754731692096355e-05, "loss": 4.4129, "step": 1461 }, { "epoch": 0.044654856444715944, "grad_norm": 0.41740143299102783, "learning_rate": 4.975439637419621e-05, "loss": 4.4792, "step": 1462 }, { "epoch": 0.04468540012217471, "grad_norm": 0.4200443625450134, "learning_rate": 4.975406082836962e-05, "loss": 4.5148, "step": 1463 }, { "epoch": 0.04471594379963348, "grad_norm": 0.42078110575675964, "learning_rate": 4.975372505461965e-05, "loss": 4.4684, "step": 1464 }, { "epoch": 0.04474648747709224, "grad_norm": 0.4311658442020416, "learning_rate": 4.975338905294942e-05, "loss": 4.4841, "step": 1465 }, { "epoch": 0.044777031154551006, "grad_norm": 0.4245566725730896, "learning_rate": 4.9753052823362e-05, "loss": 4.5144, "step": 1466 }, { "epoch": 0.044807574832009776, "grad_norm": 0.4244740605354309, "learning_rate": 4.97527163658605e-05, "loss": 4.3982, "step": 1467 }, { "epoch": 0.04483811850946854, "grad_norm": 0.427941232919693, "learning_rate": 4.975237968044801e-05, "loss": 4.4451, "step": 1468 }, { "epoch": 0.044868662186927304, "grad_norm": 0.4136554002761841, "learning_rate": 4.9752042767127636e-05, "loss": 4.4592, "step": 1469 }, { "epoch": 0.044899205864386074, "grad_norm": 0.4198348820209503, "learning_rate": 4.975170562590248e-05, "loss": 4.4153, "step": 1470 }, { "epoch": 0.04492974954184484, "grad_norm": 0.43046510219573975, "learning_rate": 4.9751368256775644e-05, "loss": 4.486, "step": 1471 }, { "epoch": 0.0449602932193036, "grad_norm": 0.42815741896629333, "learning_rate": 4.975103065975023e-05, "loss": 4.5045, "step": 1472 }, { "epoch": 0.04499083689676237, "grad_norm": 0.41928839683532715, "learning_rate": 4.975069283482935e-05, "loss": 4.4611, "step": 1473 }, { "epoch": 0.045021380574221136, "grad_norm": 0.4088485538959503, "learning_rate": 4.9750354782016126e-05, "loss": 4.4503, "step": 1474 }, { "epoch": 0.0450519242516799, "grad_norm": 0.43175268173217773, "learning_rate": 4.975001650131366e-05, "loss": 4.5182, "step": 1475 }, { "epoch": 0.04508246792913867, "grad_norm": 0.4352647066116333, "learning_rate": 4.974967799272505e-05, "loss": 4.4912, "step": 1476 }, { "epoch": 0.045113011606597433, "grad_norm": 0.42723479866981506, "learning_rate": 4.974933925625345e-05, "loss": 4.5614, "step": 1477 }, { "epoch": 0.0451435552840562, "grad_norm": 0.4194130599498749, "learning_rate": 4.974900029190194e-05, "loss": 4.4681, "step": 1478 }, { "epoch": 0.04517409896151497, "grad_norm": 0.425796777009964, "learning_rate": 4.9748661099673674e-05, "loss": 4.4458, "step": 1479 }, { "epoch": 0.04520464263897373, "grad_norm": 0.4350992441177368, "learning_rate": 4.974832167957175e-05, "loss": 4.4934, "step": 1480 }, { "epoch": 0.0452351863164325, "grad_norm": 0.44197264313697815, "learning_rate": 4.974798203159931e-05, "loss": 4.4427, "step": 1481 }, { "epoch": 0.045265729993891266, "grad_norm": 0.4226035475730896, "learning_rate": 4.974764215575948e-05, "loss": 4.4357, "step": 1482 }, { "epoch": 0.04529627367135003, "grad_norm": 0.4585952162742615, "learning_rate": 4.9747302052055375e-05, "loss": 4.5254, "step": 1483 }, { "epoch": 0.0453268173488088, "grad_norm": 0.42630505561828613, "learning_rate": 4.974696172049014e-05, "loss": 4.5574, "step": 1484 }, { "epoch": 0.04535736102626756, "grad_norm": 0.4345228672027588, "learning_rate": 4.9746621161066906e-05, "loss": 4.4519, "step": 1485 }, { "epoch": 0.04538790470372633, "grad_norm": 0.4444091320037842, "learning_rate": 4.974628037378881e-05, "loss": 4.4869, "step": 1486 }, { "epoch": 0.0454184483811851, "grad_norm": 0.42581918835639954, "learning_rate": 4.974593935865898e-05, "loss": 4.4639, "step": 1487 }, { "epoch": 0.04544899205864386, "grad_norm": 0.4229923486709595, "learning_rate": 4.974559811568057e-05, "loss": 4.452, "step": 1488 }, { "epoch": 0.045479535736102625, "grad_norm": 0.4139668643474579, "learning_rate": 4.9745256644856705e-05, "loss": 4.4331, "step": 1489 }, { "epoch": 0.045510079413561395, "grad_norm": 0.43170809745788574, "learning_rate": 4.974491494619056e-05, "loss": 4.4004, "step": 1490 }, { "epoch": 0.04554062309102016, "grad_norm": 0.4384748041629791, "learning_rate": 4.974457301968524e-05, "loss": 4.4432, "step": 1491 }, { "epoch": 0.04557116676847892, "grad_norm": 0.4225018620491028, "learning_rate": 4.974423086534392e-05, "loss": 4.4423, "step": 1492 }, { "epoch": 0.04560171044593769, "grad_norm": 0.4201083779335022, "learning_rate": 4.974388848316975e-05, "loss": 4.4359, "step": 1493 }, { "epoch": 0.04563225412339646, "grad_norm": 0.42741429805755615, "learning_rate": 4.974354587316587e-05, "loss": 4.4454, "step": 1494 }, { "epoch": 0.04566279780085522, "grad_norm": 0.43670108914375305, "learning_rate": 4.974320303533544e-05, "loss": 4.4695, "step": 1495 }, { "epoch": 0.04569334147831399, "grad_norm": 0.4239257872104645, "learning_rate": 4.974285996968162e-05, "loss": 4.4286, "step": 1496 }, { "epoch": 0.045723885155772755, "grad_norm": 0.45146283507347107, "learning_rate": 4.9742516676207575e-05, "loss": 4.5115, "step": 1497 }, { "epoch": 0.04575442883323152, "grad_norm": 0.4306902587413788, "learning_rate": 4.974217315491645e-05, "loss": 4.5354, "step": 1498 }, { "epoch": 0.04578497251069029, "grad_norm": 0.43374601006507874, "learning_rate": 4.9741829405811416e-05, "loss": 4.5082, "step": 1499 }, { "epoch": 0.04581551618814905, "grad_norm": 0.429240345954895, "learning_rate": 4.974148542889564e-05, "loss": 4.4598, "step": 1500 }, { "epoch": 0.045846059865607816, "grad_norm": 0.4529660940170288, "learning_rate": 4.974114122417228e-05, "loss": 4.4099, "step": 1501 }, { "epoch": 0.04587660354306659, "grad_norm": 0.4430246353149414, "learning_rate": 4.974079679164452e-05, "loss": 4.4809, "step": 1502 }, { "epoch": 0.04590714722052535, "grad_norm": 0.43301311135292053, "learning_rate": 4.9740452131315516e-05, "loss": 4.4819, "step": 1503 }, { "epoch": 0.045937690897984114, "grad_norm": 0.4264627695083618, "learning_rate": 4.974010724318845e-05, "loss": 4.4869, "step": 1504 }, { "epoch": 0.045968234575442884, "grad_norm": 0.4330560266971588, "learning_rate": 4.973976212726651e-05, "loss": 4.5398, "step": 1505 }, { "epoch": 0.04599877825290165, "grad_norm": 0.43494755029678345, "learning_rate": 4.9739416783552846e-05, "loss": 4.538, "step": 1506 }, { "epoch": 0.04602932193036042, "grad_norm": 0.437141478061676, "learning_rate": 4.973907121205066e-05, "loss": 4.492, "step": 1507 }, { "epoch": 0.04605986560781918, "grad_norm": 0.42867860198020935, "learning_rate": 4.973872541276312e-05, "loss": 4.4265, "step": 1508 }, { "epoch": 0.046090409285277946, "grad_norm": 0.459139347076416, "learning_rate": 4.973837938569341e-05, "loss": 4.4739, "step": 1509 }, { "epoch": 0.046120952962736717, "grad_norm": 0.4304356873035431, "learning_rate": 4.973803313084473e-05, "loss": 4.4536, "step": 1510 }, { "epoch": 0.04615149664019548, "grad_norm": 0.430705726146698, "learning_rate": 4.973768664822026e-05, "loss": 4.4416, "step": 1511 }, { "epoch": 0.046182040317654244, "grad_norm": 0.4208402633666992, "learning_rate": 4.973733993782319e-05, "loss": 4.522, "step": 1512 }, { "epoch": 0.046212583995113014, "grad_norm": 0.41436508297920227, "learning_rate": 4.973699299965672e-05, "loss": 4.4076, "step": 1513 }, { "epoch": 0.04624312767257178, "grad_norm": 0.4221092462539673, "learning_rate": 4.9736645833724024e-05, "loss": 4.4139, "step": 1514 }, { "epoch": 0.04627367135003054, "grad_norm": 0.42930909991264343, "learning_rate": 4.973629844002832e-05, "loss": 4.5054, "step": 1515 }, { "epoch": 0.04630421502748931, "grad_norm": 0.41621533036231995, "learning_rate": 4.973595081857279e-05, "loss": 4.4638, "step": 1516 }, { "epoch": 0.046334758704948076, "grad_norm": 0.4524540603160858, "learning_rate": 4.973560296936065e-05, "loss": 4.4784, "step": 1517 }, { "epoch": 0.04636530238240684, "grad_norm": 0.4222273528575897, "learning_rate": 4.973525489239509e-05, "loss": 4.5465, "step": 1518 }, { "epoch": 0.04639584605986561, "grad_norm": 0.43885502219200134, "learning_rate": 4.9734906587679326e-05, "loss": 4.4367, "step": 1519 }, { "epoch": 0.046426389737324374, "grad_norm": 0.4315822124481201, "learning_rate": 4.973455805521655e-05, "loss": 4.4723, "step": 1520 }, { "epoch": 0.04645693341478314, "grad_norm": 0.41301268339157104, "learning_rate": 4.9734209295009995e-05, "loss": 4.3823, "step": 1521 }, { "epoch": 0.04648747709224191, "grad_norm": 0.42491692304611206, "learning_rate": 4.973386030706285e-05, "loss": 4.4131, "step": 1522 }, { "epoch": 0.04651802076970067, "grad_norm": 0.4228004217147827, "learning_rate": 4.973351109137834e-05, "loss": 4.5328, "step": 1523 }, { "epoch": 0.046548564447159435, "grad_norm": 0.42498230934143066, "learning_rate": 4.973316164795967e-05, "loss": 4.489, "step": 1524 }, { "epoch": 0.046579108124618206, "grad_norm": 0.43343794345855713, "learning_rate": 4.9732811976810066e-05, "loss": 4.4305, "step": 1525 }, { "epoch": 0.04660965180207697, "grad_norm": 0.4298953413963318, "learning_rate": 4.973246207793275e-05, "loss": 4.453, "step": 1526 }, { "epoch": 0.04664019547953573, "grad_norm": 0.4158632159233093, "learning_rate": 4.973211195133094e-05, "loss": 4.4821, "step": 1527 }, { "epoch": 0.046670739156994503, "grad_norm": 0.4324990212917328, "learning_rate": 4.973176159700785e-05, "loss": 4.3885, "step": 1528 }, { "epoch": 0.04670128283445327, "grad_norm": 0.4310811161994934, "learning_rate": 4.973141101496672e-05, "loss": 4.492, "step": 1529 }, { "epoch": 0.04673182651191203, "grad_norm": 0.43916869163513184, "learning_rate": 4.973106020521078e-05, "loss": 4.4827, "step": 1530 }, { "epoch": 0.0467623701893708, "grad_norm": 0.42640554904937744, "learning_rate": 4.973070916774325e-05, "loss": 4.5044, "step": 1531 }, { "epoch": 0.046792913866829565, "grad_norm": 0.4300033450126648, "learning_rate": 4.973035790256736e-05, "loss": 4.4804, "step": 1532 }, { "epoch": 0.046823457544288336, "grad_norm": 0.44642001390457153, "learning_rate": 4.973000640968635e-05, "loss": 4.3875, "step": 1533 }, { "epoch": 0.0468540012217471, "grad_norm": 0.43594688177108765, "learning_rate": 4.9729654689103465e-05, "loss": 4.5928, "step": 1534 }, { "epoch": 0.04688454489920586, "grad_norm": 0.43553924560546875, "learning_rate": 4.9729302740821925e-05, "loss": 4.3785, "step": 1535 }, { "epoch": 0.04691508857666463, "grad_norm": 0.43935534358024597, "learning_rate": 4.972895056484499e-05, "loss": 4.5381, "step": 1536 }, { "epoch": 0.0469456322541234, "grad_norm": 0.4199060797691345, "learning_rate": 4.972859816117588e-05, "loss": 4.4088, "step": 1537 }, { "epoch": 0.04697617593158216, "grad_norm": 0.42682746052742004, "learning_rate": 4.972824552981786e-05, "loss": 4.4143, "step": 1538 }, { "epoch": 0.04700671960904093, "grad_norm": 0.41368094086647034, "learning_rate": 4.9727892670774166e-05, "loss": 4.4367, "step": 1539 }, { "epoch": 0.047037263286499695, "grad_norm": 0.4210017919540405, "learning_rate": 4.9727539584048056e-05, "loss": 4.5102, "step": 1540 }, { "epoch": 0.04706780696395846, "grad_norm": 0.4230133295059204, "learning_rate": 4.972718626964277e-05, "loss": 4.5244, "step": 1541 }, { "epoch": 0.04709835064141723, "grad_norm": 0.423881858587265, "learning_rate": 4.972683272756157e-05, "loss": 4.5042, "step": 1542 }, { "epoch": 0.04712889431887599, "grad_norm": 0.4244433641433716, "learning_rate": 4.972647895780771e-05, "loss": 4.4558, "step": 1543 }, { "epoch": 0.047159437996334756, "grad_norm": 0.4357309639453888, "learning_rate": 4.972612496038444e-05, "loss": 4.5091, "step": 1544 }, { "epoch": 0.04718998167379353, "grad_norm": 0.43308398127555847, "learning_rate": 4.972577073529503e-05, "loss": 4.4656, "step": 1545 }, { "epoch": 0.04722052535125229, "grad_norm": 0.41055747866630554, "learning_rate": 4.972541628254273e-05, "loss": 4.4283, "step": 1546 }, { "epoch": 0.047251069028711054, "grad_norm": 0.4131997227668762, "learning_rate": 4.9725061602130815e-05, "loss": 4.4642, "step": 1547 }, { "epoch": 0.047281612706169825, "grad_norm": 0.41948482394218445, "learning_rate": 4.972470669406254e-05, "loss": 4.2956, "step": 1548 }, { "epoch": 0.04731215638362859, "grad_norm": 0.4474071264266968, "learning_rate": 4.972435155834118e-05, "loss": 4.5244, "step": 1549 }, { "epoch": 0.04734270006108735, "grad_norm": 0.4221652150154114, "learning_rate": 4.972399619497e-05, "loss": 4.4891, "step": 1550 }, { "epoch": 0.04737324373854612, "grad_norm": 0.4599990248680115, "learning_rate": 4.972364060395228e-05, "loss": 4.4379, "step": 1551 }, { "epoch": 0.047403787416004886, "grad_norm": 0.41411516070365906, "learning_rate": 4.972328478529129e-05, "loss": 4.407, "step": 1552 }, { "epoch": 0.04743433109346365, "grad_norm": 0.4216192364692688, "learning_rate": 4.9722928738990305e-05, "loss": 4.5018, "step": 1553 }, { "epoch": 0.04746487477092242, "grad_norm": 0.4180082082748413, "learning_rate": 4.9722572465052605e-05, "loss": 4.4542, "step": 1554 }, { "epoch": 0.047495418448381184, "grad_norm": 0.4262545108795166, "learning_rate": 4.972221596348147e-05, "loss": 4.4586, "step": 1555 }, { "epoch": 0.047525962125839954, "grad_norm": 0.4118442237377167, "learning_rate": 4.9721859234280176e-05, "loss": 4.5057, "step": 1556 }, { "epoch": 0.04755650580329872, "grad_norm": 0.42878833413124084, "learning_rate": 4.972150227745201e-05, "loss": 4.4201, "step": 1557 }, { "epoch": 0.04758704948075748, "grad_norm": 0.41153770685195923, "learning_rate": 4.972114509300028e-05, "loss": 4.4802, "step": 1558 }, { "epoch": 0.04761759315821625, "grad_norm": 0.4174201488494873, "learning_rate": 4.972078768092824e-05, "loss": 4.4522, "step": 1559 }, { "epoch": 0.047648136835675016, "grad_norm": 0.4113972783088684, "learning_rate": 4.972043004123921e-05, "loss": 4.4702, "step": 1560 }, { "epoch": 0.04767868051313378, "grad_norm": 0.41774359345436096, "learning_rate": 4.972007217393646e-05, "loss": 4.5163, "step": 1561 }, { "epoch": 0.04770922419059255, "grad_norm": 0.41541874408721924, "learning_rate": 4.971971407902329e-05, "loss": 4.4813, "step": 1562 }, { "epoch": 0.047739767868051314, "grad_norm": 0.4256347715854645, "learning_rate": 4.9719355756503015e-05, "loss": 4.4686, "step": 1563 }, { "epoch": 0.04777031154551008, "grad_norm": 0.4263465404510498, "learning_rate": 4.971899720637893e-05, "loss": 4.4938, "step": 1564 }, { "epoch": 0.04780085522296885, "grad_norm": 0.429614394903183, "learning_rate": 4.971863842865431e-05, "loss": 4.4381, "step": 1565 }, { "epoch": 0.04783139890042761, "grad_norm": 0.4262996315956116, "learning_rate": 4.971827942333248e-05, "loss": 4.4675, "step": 1566 }, { "epoch": 0.047861942577886375, "grad_norm": 0.429612398147583, "learning_rate": 4.9717920190416756e-05, "loss": 4.501, "step": 1567 }, { "epoch": 0.047892486255345146, "grad_norm": 0.42476341128349304, "learning_rate": 4.971756072991042e-05, "loss": 4.5185, "step": 1568 }, { "epoch": 0.04792302993280391, "grad_norm": 0.45157313346862793, "learning_rate": 4.97172010418168e-05, "loss": 4.4685, "step": 1569 }, { "epoch": 0.04795357361026267, "grad_norm": 0.43426674604415894, "learning_rate": 4.971684112613919e-05, "loss": 4.4557, "step": 1570 }, { "epoch": 0.047984117287721444, "grad_norm": 0.4248296022415161, "learning_rate": 4.971648098288093e-05, "loss": 4.5518, "step": 1571 }, { "epoch": 0.04801466096518021, "grad_norm": 0.42508813738822937, "learning_rate": 4.971612061204531e-05, "loss": 4.5129, "step": 1572 }, { "epoch": 0.04804520464263897, "grad_norm": 0.4383309483528137, "learning_rate": 4.971576001363567e-05, "loss": 4.5038, "step": 1573 }, { "epoch": 0.04807574832009774, "grad_norm": 0.42814943194389343, "learning_rate": 4.971539918765532e-05, "loss": 4.4779, "step": 1574 }, { "epoch": 0.048106291997556505, "grad_norm": 0.4246964156627655, "learning_rate": 4.9715038134107574e-05, "loss": 4.4553, "step": 1575 }, { "epoch": 0.04813683567501527, "grad_norm": 0.42760637402534485, "learning_rate": 4.971467685299577e-05, "loss": 4.2871, "step": 1576 }, { "epoch": 0.04816737935247404, "grad_norm": 0.4243183732032776, "learning_rate": 4.9714315344323223e-05, "loss": 4.4527, "step": 1577 }, { "epoch": 0.0481979230299328, "grad_norm": 0.43434420228004456, "learning_rate": 4.971395360809328e-05, "loss": 4.3389, "step": 1578 }, { "epoch": 0.04822846670739157, "grad_norm": 0.4445837438106537, "learning_rate": 4.9713591644309245e-05, "loss": 4.4389, "step": 1579 }, { "epoch": 0.04825901038485034, "grad_norm": 0.4296148419380188, "learning_rate": 4.971322945297447e-05, "loss": 4.4662, "step": 1580 }, { "epoch": 0.0482895540623091, "grad_norm": 0.4151635766029358, "learning_rate": 4.971286703409229e-05, "loss": 4.4418, "step": 1581 }, { "epoch": 0.04832009773976787, "grad_norm": 0.42739683389663696, "learning_rate": 4.9712504387666034e-05, "loss": 4.4382, "step": 1582 }, { "epoch": 0.048350641417226635, "grad_norm": 0.418802946805954, "learning_rate": 4.971214151369905e-05, "loss": 4.4251, "step": 1583 }, { "epoch": 0.0483811850946854, "grad_norm": 0.4326557517051697, "learning_rate": 4.9711778412194666e-05, "loss": 4.4492, "step": 1584 }, { "epoch": 0.04841172877214417, "grad_norm": 0.4097955524921417, "learning_rate": 4.9711415083156234e-05, "loss": 4.4609, "step": 1585 }, { "epoch": 0.04844227244960293, "grad_norm": 0.429903507232666, "learning_rate": 4.97110515265871e-05, "loss": 4.4311, "step": 1586 }, { "epoch": 0.048472816127061696, "grad_norm": 0.42046043276786804, "learning_rate": 4.9710687742490605e-05, "loss": 4.4653, "step": 1587 }, { "epoch": 0.04850335980452047, "grad_norm": 0.4293437898159027, "learning_rate": 4.9710323730870104e-05, "loss": 4.4334, "step": 1588 }, { "epoch": 0.04853390348197923, "grad_norm": 0.4271472692489624, "learning_rate": 4.970995949172895e-05, "loss": 4.3991, "step": 1589 }, { "epoch": 0.048564447159437994, "grad_norm": 0.4184289574623108, "learning_rate": 4.97095950250705e-05, "loss": 4.54, "step": 1590 }, { "epoch": 0.048594990836896765, "grad_norm": 0.4258788228034973, "learning_rate": 4.9709230330898094e-05, "loss": 4.512, "step": 1591 }, { "epoch": 0.04862553451435553, "grad_norm": 0.43064820766448975, "learning_rate": 4.970886540921511e-05, "loss": 4.421, "step": 1592 }, { "epoch": 0.04865607819181429, "grad_norm": 0.41959813237190247, "learning_rate": 4.9708500260024885e-05, "loss": 4.4897, "step": 1593 }, { "epoch": 0.04868662186927306, "grad_norm": 0.4209898114204407, "learning_rate": 4.97081348833308e-05, "loss": 4.4432, "step": 1594 }, { "epoch": 0.048717165546731826, "grad_norm": 0.4272014796733856, "learning_rate": 4.970776927913622e-05, "loss": 4.484, "step": 1595 }, { "epoch": 0.04874770922419059, "grad_norm": 0.42247894406318665, "learning_rate": 4.97074034474445e-05, "loss": 4.4235, "step": 1596 }, { "epoch": 0.04877825290164936, "grad_norm": 0.42848116159439087, "learning_rate": 4.970703738825902e-05, "loss": 4.402, "step": 1597 }, { "epoch": 0.048808796579108124, "grad_norm": 0.4298878014087677, "learning_rate": 4.970667110158313e-05, "loss": 4.4912, "step": 1598 }, { "epoch": 0.04883934025656689, "grad_norm": 0.43062058091163635, "learning_rate": 4.970630458742022e-05, "loss": 4.4626, "step": 1599 }, { "epoch": 0.04886988393402566, "grad_norm": 0.4372946619987488, "learning_rate": 4.970593784577366e-05, "loss": 4.3914, "step": 1600 }, { "epoch": 0.04890042761148442, "grad_norm": 0.43281978368759155, "learning_rate": 4.970557087664684e-05, "loss": 4.4995, "step": 1601 }, { "epoch": 0.048930971288943186, "grad_norm": 0.41656020283699036, "learning_rate": 4.9705203680043114e-05, "loss": 4.4628, "step": 1602 }, { "epoch": 0.048961514966401956, "grad_norm": 0.43081048130989075, "learning_rate": 4.970483625596588e-05, "loss": 4.5201, "step": 1603 }, { "epoch": 0.04899205864386072, "grad_norm": 0.42619481682777405, "learning_rate": 4.970446860441852e-05, "loss": 4.453, "step": 1604 }, { "epoch": 0.04902260232131949, "grad_norm": 0.4178897738456726, "learning_rate": 4.9704100725404414e-05, "loss": 4.5204, "step": 1605 }, { "epoch": 0.049053145998778254, "grad_norm": 0.420391708612442, "learning_rate": 4.9703732618926945e-05, "loss": 4.4643, "step": 1606 }, { "epoch": 0.04908368967623702, "grad_norm": 0.43446436524391174, "learning_rate": 4.970336428498952e-05, "loss": 4.4686, "step": 1607 }, { "epoch": 0.04911423335369579, "grad_norm": 0.4334181845188141, "learning_rate": 4.97029957235955e-05, "loss": 4.4634, "step": 1608 }, { "epoch": 0.04914477703115455, "grad_norm": 0.4325396418571472, "learning_rate": 4.970262693474832e-05, "loss": 4.4841, "step": 1609 }, { "epoch": 0.049175320708613315, "grad_norm": 0.41894862055778503, "learning_rate": 4.970225791845133e-05, "loss": 4.5144, "step": 1610 }, { "epoch": 0.049205864386072086, "grad_norm": 0.42123013734817505, "learning_rate": 4.970188867470797e-05, "loss": 4.4474, "step": 1611 }, { "epoch": 0.04923640806353085, "grad_norm": 0.4307807981967926, "learning_rate": 4.970151920352161e-05, "loss": 4.3846, "step": 1612 }, { "epoch": 0.04926695174098961, "grad_norm": 5.684503555297852, "learning_rate": 4.9701149504895664e-05, "loss": 4.5198, "step": 1613 }, { "epoch": 0.049297495418448384, "grad_norm": 0.454233318567276, "learning_rate": 4.970077957883354e-05, "loss": 4.4528, "step": 1614 }, { "epoch": 0.04932803909590715, "grad_norm": 0.42869842052459717, "learning_rate": 4.970040942533863e-05, "loss": 4.4318, "step": 1615 }, { "epoch": 0.04935858277336591, "grad_norm": 0.4269618093967438, "learning_rate": 4.970003904441436e-05, "loss": 4.4661, "step": 1616 }, { "epoch": 0.04938912645082468, "grad_norm": 0.4297157824039459, "learning_rate": 4.969966843606413e-05, "loss": 4.4764, "step": 1617 }, { "epoch": 0.049419670128283445, "grad_norm": 0.42939093708992004, "learning_rate": 4.969929760029135e-05, "loss": 4.4881, "step": 1618 }, { "epoch": 0.04945021380574221, "grad_norm": 0.4197126030921936, "learning_rate": 4.9698926537099435e-05, "loss": 4.4572, "step": 1619 }, { "epoch": 0.04948075748320098, "grad_norm": 0.4377574026584625, "learning_rate": 4.969855524649181e-05, "loss": 4.392, "step": 1620 }, { "epoch": 0.04951130116065974, "grad_norm": 0.47400394082069397, "learning_rate": 4.969818372847188e-05, "loss": 4.5331, "step": 1621 }, { "epoch": 0.04954184483811851, "grad_norm": 0.42266178131103516, "learning_rate": 4.9697811983043075e-05, "loss": 4.4779, "step": 1622 }, { "epoch": 0.04957238851557728, "grad_norm": 0.4212955832481384, "learning_rate": 4.9697440010208826e-05, "loss": 4.5309, "step": 1623 }, { "epoch": 0.04960293219303604, "grad_norm": 0.42005032300949097, "learning_rate": 4.9697067809972544e-05, "loss": 4.5174, "step": 1624 }, { "epoch": 0.049633475870494805, "grad_norm": 0.44197896122932434, "learning_rate": 4.9696695382337656e-05, "loss": 4.5239, "step": 1625 }, { "epoch": 0.049664019547953575, "grad_norm": 0.4260278642177582, "learning_rate": 4.96963227273076e-05, "loss": 4.4595, "step": 1626 }, { "epoch": 0.04969456322541234, "grad_norm": 0.41937321424484253, "learning_rate": 4.96959498448858e-05, "loss": 4.4422, "step": 1627 }, { "epoch": 0.0497251069028711, "grad_norm": 0.4185517430305481, "learning_rate": 4.96955767350757e-05, "loss": 4.4322, "step": 1628 }, { "epoch": 0.04975565058032987, "grad_norm": 0.43618044257164, "learning_rate": 4.9695203397880716e-05, "loss": 4.441, "step": 1629 }, { "epoch": 0.04978619425778864, "grad_norm": 0.4275550842285156, "learning_rate": 4.9694829833304315e-05, "loss": 4.5087, "step": 1630 }, { "epoch": 0.04981673793524741, "grad_norm": 0.422965407371521, "learning_rate": 4.96944560413499e-05, "loss": 4.3862, "step": 1631 }, { "epoch": 0.04984728161270617, "grad_norm": 0.41211724281311035, "learning_rate": 4.969408202202094e-05, "loss": 4.4106, "step": 1632 }, { "epoch": 0.049877825290164934, "grad_norm": 0.4064997434616089, "learning_rate": 4.9693707775320875e-05, "loss": 4.4369, "step": 1633 }, { "epoch": 0.049908368967623705, "grad_norm": 0.42480796575546265, "learning_rate": 4.969333330125314e-05, "loss": 4.5168, "step": 1634 }, { "epoch": 0.04993891264508247, "grad_norm": 0.42615294456481934, "learning_rate": 4.9692958599821196e-05, "loss": 4.4324, "step": 1635 }, { "epoch": 0.04996945632254123, "grad_norm": 0.4216930866241455, "learning_rate": 4.969258367102847e-05, "loss": 4.4691, "step": 1636 }, { "epoch": 0.05, "grad_norm": 0.4318346083164215, "learning_rate": 4.9692208514878444e-05, "loss": 4.4127, "step": 1637 }, { "epoch": 0.050030543677458766, "grad_norm": 0.42112401127815247, "learning_rate": 4.9691833131374554e-05, "loss": 4.4959, "step": 1638 }, { "epoch": 0.05006108735491753, "grad_norm": 0.4199839234352112, "learning_rate": 4.9691457520520265e-05, "loss": 4.3836, "step": 1639 }, { "epoch": 0.0500916310323763, "grad_norm": 0.4455925524234772, "learning_rate": 4.969108168231903e-05, "loss": 4.3667, "step": 1640 }, { "epoch": 0.050122174709835064, "grad_norm": 0.42925846576690674, "learning_rate": 4.9690705616774314e-05, "loss": 4.4729, "step": 1641 }, { "epoch": 0.05015271838729383, "grad_norm": 0.43974414467811584, "learning_rate": 4.969032932388957e-05, "loss": 4.4517, "step": 1642 }, { "epoch": 0.0501832620647526, "grad_norm": 0.42132681608200073, "learning_rate": 4.968995280366827e-05, "loss": 4.4172, "step": 1643 }, { "epoch": 0.05021380574221136, "grad_norm": 0.43696174025535583, "learning_rate": 4.968957605611389e-05, "loss": 4.536, "step": 1644 }, { "epoch": 0.050244349419670126, "grad_norm": 0.4349776804447174, "learning_rate": 4.968919908122988e-05, "loss": 4.4013, "step": 1645 }, { "epoch": 0.050274893097128896, "grad_norm": 0.42612358927726746, "learning_rate": 4.968882187901972e-05, "loss": 4.4783, "step": 1646 }, { "epoch": 0.05030543677458766, "grad_norm": 0.4169961214065552, "learning_rate": 4.968844444948689e-05, "loss": 4.4871, "step": 1647 }, { "epoch": 0.050335980452046424, "grad_norm": 0.41781580448150635, "learning_rate": 4.9688066792634855e-05, "loss": 4.413, "step": 1648 }, { "epoch": 0.050366524129505194, "grad_norm": 0.4215141534805298, "learning_rate": 4.968768890846709e-05, "loss": 4.4899, "step": 1649 }, { "epoch": 0.05039706780696396, "grad_norm": 0.43063685297966003, "learning_rate": 4.9687310796987085e-05, "loss": 4.504, "step": 1650 }, { "epoch": 0.05042761148442272, "grad_norm": 0.4192904531955719, "learning_rate": 4.968693245819832e-05, "loss": 4.355, "step": 1651 }, { "epoch": 0.05045815516188149, "grad_norm": 0.4122423529624939, "learning_rate": 4.968655389210427e-05, "loss": 4.4698, "step": 1652 }, { "epoch": 0.050488698839340256, "grad_norm": 0.42161646485328674, "learning_rate": 4.9686175098708426e-05, "loss": 4.5185, "step": 1653 }, { "epoch": 0.05051924251679902, "grad_norm": 0.4303356409072876, "learning_rate": 4.968579607801428e-05, "loss": 4.5129, "step": 1654 }, { "epoch": 0.05054978619425779, "grad_norm": 0.42364591360092163, "learning_rate": 4.968541683002531e-05, "loss": 4.5075, "step": 1655 }, { "epoch": 0.05058032987171655, "grad_norm": 0.4377082884311676, "learning_rate": 4.9685037354745026e-05, "loss": 4.5486, "step": 1656 }, { "epoch": 0.050610873549175324, "grad_norm": 0.42021816968917847, "learning_rate": 4.9684657652176905e-05, "loss": 4.4453, "step": 1657 }, { "epoch": 0.05064141722663409, "grad_norm": 0.4324728548526764, "learning_rate": 4.968427772232445e-05, "loss": 4.4298, "step": 1658 }, { "epoch": 0.05067196090409285, "grad_norm": 0.4343882203102112, "learning_rate": 4.968389756519115e-05, "loss": 4.5172, "step": 1659 }, { "epoch": 0.05070250458155162, "grad_norm": 0.42626625299453735, "learning_rate": 4.968351718078053e-05, "loss": 4.5004, "step": 1660 }, { "epoch": 0.050733048259010385, "grad_norm": 0.42623069882392883, "learning_rate": 4.968313656909606e-05, "loss": 4.522, "step": 1661 }, { "epoch": 0.05076359193646915, "grad_norm": 0.44052624702453613, "learning_rate": 4.9682755730141264e-05, "loss": 4.4957, "step": 1662 }, { "epoch": 0.05079413561392792, "grad_norm": 0.43962979316711426, "learning_rate": 4.968237466391965e-05, "loss": 4.4265, "step": 1663 }, { "epoch": 0.05082467929138668, "grad_norm": 0.42564380168914795, "learning_rate": 4.9681993370434725e-05, "loss": 4.5176, "step": 1664 }, { "epoch": 0.05085522296884545, "grad_norm": 0.4086362421512604, "learning_rate": 4.9681611849689994e-05, "loss": 4.3255, "step": 1665 }, { "epoch": 0.05088576664630422, "grad_norm": 0.41831040382385254, "learning_rate": 4.968123010168897e-05, "loss": 4.4545, "step": 1666 }, { "epoch": 0.05091631032376298, "grad_norm": 0.4126277267932892, "learning_rate": 4.968084812643518e-05, "loss": 4.4651, "step": 1667 }, { "epoch": 0.050946854001221745, "grad_norm": 0.44216424226760864, "learning_rate": 4.968046592393212e-05, "loss": 4.4271, "step": 1668 }, { "epoch": 0.050977397678680515, "grad_norm": 0.42161664366722107, "learning_rate": 4.968008349418333e-05, "loss": 4.5713, "step": 1669 }, { "epoch": 0.05100794135613928, "grad_norm": 0.4224699139595032, "learning_rate": 4.967970083719231e-05, "loss": 4.5313, "step": 1670 }, { "epoch": 0.05103848503359804, "grad_norm": 0.42529115080833435, "learning_rate": 4.967931795296261e-05, "loss": 4.4957, "step": 1671 }, { "epoch": 0.05106902871105681, "grad_norm": 0.41639837622642517, "learning_rate": 4.967893484149773e-05, "loss": 4.5082, "step": 1672 }, { "epoch": 0.05109957238851558, "grad_norm": 0.4082757234573364, "learning_rate": 4.967855150280121e-05, "loss": 4.4696, "step": 1673 }, { "epoch": 0.05113011606597434, "grad_norm": 0.43165111541748047, "learning_rate": 4.9678167936876585e-05, "loss": 4.4676, "step": 1674 }, { "epoch": 0.05116065974343311, "grad_norm": 0.43207430839538574, "learning_rate": 4.9677784143727366e-05, "loss": 4.4587, "step": 1675 }, { "epoch": 0.051191203420891875, "grad_norm": 0.41794589161872864, "learning_rate": 4.9677400123357114e-05, "loss": 4.4805, "step": 1676 }, { "epoch": 0.05122174709835064, "grad_norm": 0.4516582190990448, "learning_rate": 4.967701587576935e-05, "loss": 4.4608, "step": 1677 }, { "epoch": 0.05125229077580941, "grad_norm": 0.4063143730163574, "learning_rate": 4.9676631400967606e-05, "loss": 4.4048, "step": 1678 }, { "epoch": 0.05128283445326817, "grad_norm": 0.428566575050354, "learning_rate": 4.967624669895543e-05, "loss": 4.528, "step": 1679 }, { "epoch": 0.05131337813072694, "grad_norm": 0.40947842597961426, "learning_rate": 4.967586176973636e-05, "loss": 4.4394, "step": 1680 }, { "epoch": 0.05134392180818571, "grad_norm": 0.42314666509628296, "learning_rate": 4.9675476613313955e-05, "loss": 4.4726, "step": 1681 }, { "epoch": 0.05137446548564447, "grad_norm": 0.440019816160202, "learning_rate": 4.9675091229691744e-05, "loss": 4.471, "step": 1682 }, { "epoch": 0.05140500916310324, "grad_norm": 0.41162678599357605, "learning_rate": 4.967470561887329e-05, "loss": 4.5378, "step": 1683 }, { "epoch": 0.051435552840562004, "grad_norm": 0.41986119747161865, "learning_rate": 4.967431978086212e-05, "loss": 4.4365, "step": 1684 }, { "epoch": 0.05146609651802077, "grad_norm": 0.41278859972953796, "learning_rate": 4.9673933715661806e-05, "loss": 4.3652, "step": 1685 }, { "epoch": 0.05149664019547954, "grad_norm": 0.41443535685539246, "learning_rate": 4.96735474232759e-05, "loss": 4.4538, "step": 1686 }, { "epoch": 0.0515271838729383, "grad_norm": 0.4182356297969818, "learning_rate": 4.9673160903707964e-05, "loss": 4.4862, "step": 1687 }, { "epoch": 0.051557727550397066, "grad_norm": 0.4218771159648895, "learning_rate": 4.967277415696154e-05, "loss": 4.5138, "step": 1688 }, { "epoch": 0.051588271227855836, "grad_norm": 0.4153624176979065, "learning_rate": 4.96723871830402e-05, "loss": 4.4366, "step": 1689 }, { "epoch": 0.0516188149053146, "grad_norm": 0.41975584626197815, "learning_rate": 4.967199998194751e-05, "loss": 4.3484, "step": 1690 }, { "epoch": 0.051649358582773364, "grad_norm": 0.420699805021286, "learning_rate": 4.967161255368703e-05, "loss": 4.3889, "step": 1691 }, { "epoch": 0.051679902260232134, "grad_norm": 0.4291766583919525, "learning_rate": 4.9671224898262325e-05, "loss": 4.5029, "step": 1692 }, { "epoch": 0.0517104459376909, "grad_norm": 0.42461445927619934, "learning_rate": 4.967083701567697e-05, "loss": 4.4488, "step": 1693 }, { "epoch": 0.05174098961514966, "grad_norm": 0.4414498209953308, "learning_rate": 4.967044890593453e-05, "loss": 4.3824, "step": 1694 }, { "epoch": 0.05177153329260843, "grad_norm": 0.42509397864341736, "learning_rate": 4.967006056903859e-05, "loss": 4.4729, "step": 1695 }, { "epoch": 0.051802076970067196, "grad_norm": 0.4073006212711334, "learning_rate": 4.966967200499272e-05, "loss": 4.4441, "step": 1696 }, { "epoch": 0.05183262064752596, "grad_norm": 0.43127089738845825, "learning_rate": 4.966928321380049e-05, "loss": 4.4815, "step": 1697 }, { "epoch": 0.05186316432498473, "grad_norm": 0.43090686202049255, "learning_rate": 4.966889419546548e-05, "loss": 4.4649, "step": 1698 }, { "epoch": 0.051893708002443494, "grad_norm": 0.4225195646286011, "learning_rate": 4.9668504949991284e-05, "loss": 4.4894, "step": 1699 }, { "epoch": 0.05192425167990226, "grad_norm": 0.4194287955760956, "learning_rate": 4.966811547738148e-05, "loss": 4.4893, "step": 1700 }, { "epoch": 0.05195479535736103, "grad_norm": 0.4055797755718231, "learning_rate": 4.966772577763966e-05, "loss": 4.441, "step": 1701 }, { "epoch": 0.05198533903481979, "grad_norm": 0.42644205689430237, "learning_rate": 4.966733585076939e-05, "loss": 4.4469, "step": 1702 }, { "epoch": 0.052015882712278555, "grad_norm": 0.4290865361690521, "learning_rate": 4.966694569677429e-05, "loss": 4.3943, "step": 1703 }, { "epoch": 0.052046426389737326, "grad_norm": 0.4221682846546173, "learning_rate": 4.9666555315657934e-05, "loss": 4.4423, "step": 1704 }, { "epoch": 0.05207697006719609, "grad_norm": 0.4234026074409485, "learning_rate": 4.9666164707423924e-05, "loss": 4.4925, "step": 1705 }, { "epoch": 0.05210751374465486, "grad_norm": 0.44897332787513733, "learning_rate": 4.966577387207585e-05, "loss": 4.4763, "step": 1706 }, { "epoch": 0.05213805742211362, "grad_norm": 0.4166105389595032, "learning_rate": 4.966538280961731e-05, "loss": 4.4328, "step": 1707 }, { "epoch": 0.05216860109957239, "grad_norm": 0.421772301197052, "learning_rate": 4.966499152005192e-05, "loss": 4.4773, "step": 1708 }, { "epoch": 0.05219914477703116, "grad_norm": 0.4228907525539398, "learning_rate": 4.966460000338326e-05, "loss": 4.5062, "step": 1709 }, { "epoch": 0.05222968845448992, "grad_norm": 0.4194931387901306, "learning_rate": 4.9664208259614954e-05, "loss": 4.3577, "step": 1710 }, { "epoch": 0.052260232131948685, "grad_norm": 0.41444137692451477, "learning_rate": 4.96638162887506e-05, "loss": 4.538, "step": 1711 }, { "epoch": 0.052290775809407455, "grad_norm": 0.423409640789032, "learning_rate": 4.96634240907938e-05, "loss": 4.4499, "step": 1712 }, { "epoch": 0.05232131948686622, "grad_norm": 0.42645055055618286, "learning_rate": 4.9663031665748185e-05, "loss": 4.4413, "step": 1713 }, { "epoch": 0.05235186316432498, "grad_norm": 0.4133751690387726, "learning_rate": 4.966263901361735e-05, "loss": 4.3885, "step": 1714 }, { "epoch": 0.05238240684178375, "grad_norm": 0.42119720578193665, "learning_rate": 4.9662246134404924e-05, "loss": 4.4696, "step": 1715 }, { "epoch": 0.05241295051924252, "grad_norm": 0.4226873815059662, "learning_rate": 4.966185302811451e-05, "loss": 4.4502, "step": 1716 }, { "epoch": 0.05244349419670128, "grad_norm": 0.4423399865627289, "learning_rate": 4.9661459694749745e-05, "loss": 4.489, "step": 1717 }, { "epoch": 0.05247403787416005, "grad_norm": 0.423618882894516, "learning_rate": 4.9661066134314236e-05, "loss": 4.4812, "step": 1718 }, { "epoch": 0.052504581551618815, "grad_norm": 0.4269375503063202, "learning_rate": 4.966067234681161e-05, "loss": 4.4246, "step": 1719 }, { "epoch": 0.05253512522907758, "grad_norm": 0.43420150876045227, "learning_rate": 4.966027833224549e-05, "loss": 4.4386, "step": 1720 }, { "epoch": 0.05256566890653635, "grad_norm": 0.4277670979499817, "learning_rate": 4.965988409061952e-05, "loss": 4.4102, "step": 1721 }, { "epoch": 0.05259621258399511, "grad_norm": 0.4142540395259857, "learning_rate": 4.9659489621937314e-05, "loss": 4.4137, "step": 1722 }, { "epoch": 0.052626756261453876, "grad_norm": 0.41409382224082947, "learning_rate": 4.9659094926202505e-05, "loss": 4.4515, "step": 1723 }, { "epoch": 0.05265729993891265, "grad_norm": 0.4104526937007904, "learning_rate": 4.965870000341873e-05, "loss": 4.5015, "step": 1724 }, { "epoch": 0.05268784361637141, "grad_norm": 0.4324127435684204, "learning_rate": 4.965830485358963e-05, "loss": 4.4632, "step": 1725 }, { "epoch": 0.052718387293830174, "grad_norm": 0.41638556122779846, "learning_rate": 4.965790947671883e-05, "loss": 4.4873, "step": 1726 }, { "epoch": 0.052748930971288945, "grad_norm": 0.4002689719200134, "learning_rate": 4.965751387280999e-05, "loss": 4.4017, "step": 1727 }, { "epoch": 0.05277947464874771, "grad_norm": 0.41908711194992065, "learning_rate": 4.965711804186674e-05, "loss": 4.471, "step": 1728 }, { "epoch": 0.05281001832620647, "grad_norm": 0.41485264897346497, "learning_rate": 4.965672198389273e-05, "loss": 4.4796, "step": 1729 }, { "epoch": 0.05284056200366524, "grad_norm": 0.4234860837459564, "learning_rate": 4.965632569889159e-05, "loss": 4.405, "step": 1730 }, { "epoch": 0.052871105681124006, "grad_norm": 0.4185733497142792, "learning_rate": 4.9655929186867e-05, "loss": 4.4675, "step": 1731 }, { "epoch": 0.05290164935858278, "grad_norm": 0.4226457476615906, "learning_rate": 4.9655532447822586e-05, "loss": 4.4468, "step": 1732 }, { "epoch": 0.05293219303604154, "grad_norm": 0.41166040301322937, "learning_rate": 4.9655135481762004e-05, "loss": 4.4374, "step": 1733 }, { "epoch": 0.052962736713500304, "grad_norm": 0.4162254333496094, "learning_rate": 4.9654738288688915e-05, "loss": 4.4466, "step": 1734 }, { "epoch": 0.052993280390959074, "grad_norm": 0.4194771349430084, "learning_rate": 4.965434086860698e-05, "loss": 4.4272, "step": 1735 }, { "epoch": 0.05302382406841784, "grad_norm": 0.4178805351257324, "learning_rate": 4.965394322151984e-05, "loss": 4.4695, "step": 1736 }, { "epoch": 0.0530543677458766, "grad_norm": 0.41933390498161316, "learning_rate": 4.965354534743118e-05, "loss": 4.4099, "step": 1737 }, { "epoch": 0.05308491142333537, "grad_norm": 0.41649213433265686, "learning_rate": 4.965314724634465e-05, "loss": 4.4898, "step": 1738 }, { "epoch": 0.053115455100794136, "grad_norm": 0.4307872951030731, "learning_rate": 4.9652748918263916e-05, "loss": 4.5242, "step": 1739 }, { "epoch": 0.0531459987782529, "grad_norm": 0.41266173124313354, "learning_rate": 4.9652350363192646e-05, "loss": 4.487, "step": 1740 }, { "epoch": 0.05317654245571167, "grad_norm": 0.4263797700405121, "learning_rate": 4.965195158113452e-05, "loss": 4.42, "step": 1741 }, { "epoch": 0.053207086133170434, "grad_norm": 0.4266386032104492, "learning_rate": 4.965155257209319e-05, "loss": 4.4738, "step": 1742 }, { "epoch": 0.0532376298106292, "grad_norm": 0.4247896075248718, "learning_rate": 4.965115333607235e-05, "loss": 4.4728, "step": 1743 }, { "epoch": 0.05326817348808797, "grad_norm": 0.4158194363117218, "learning_rate": 4.965075387307566e-05, "loss": 4.2921, "step": 1744 }, { "epoch": 0.05329871716554673, "grad_norm": 0.42858830094337463, "learning_rate": 4.965035418310681e-05, "loss": 4.4705, "step": 1745 }, { "epoch": 0.053329260843005495, "grad_norm": 0.42725780606269836, "learning_rate": 4.9649954266169466e-05, "loss": 4.427, "step": 1746 }, { "epoch": 0.053359804520464266, "grad_norm": 0.4127044081687927, "learning_rate": 4.964955412226733e-05, "loss": 4.4232, "step": 1747 }, { "epoch": 0.05339034819792303, "grad_norm": 0.40451517701148987, "learning_rate": 4.964915375140407e-05, "loss": 4.3009, "step": 1748 }, { "epoch": 0.05342089187538179, "grad_norm": 0.4210917055606842, "learning_rate": 4.964875315358338e-05, "loss": 4.3967, "step": 1749 }, { "epoch": 0.053451435552840564, "grad_norm": 0.4390374422073364, "learning_rate": 4.9648352328808947e-05, "loss": 4.4948, "step": 1750 }, { "epoch": 0.05348197923029933, "grad_norm": 0.41631266474723816, "learning_rate": 4.9647951277084456e-05, "loss": 4.4647, "step": 1751 }, { "epoch": 0.05351252290775809, "grad_norm": 0.43099039793014526, "learning_rate": 4.9647549998413614e-05, "loss": 4.425, "step": 1752 }, { "epoch": 0.05354306658521686, "grad_norm": 0.44063055515289307, "learning_rate": 4.96471484928001e-05, "loss": 4.5531, "step": 1753 }, { "epoch": 0.053573610262675625, "grad_norm": 0.4425213038921356, "learning_rate": 4.964674676024762e-05, "loss": 4.4524, "step": 1754 }, { "epoch": 0.053604153940134396, "grad_norm": 0.41631126403808594, "learning_rate": 4.964634480075987e-05, "loss": 4.3406, "step": 1755 }, { "epoch": 0.05363469761759316, "grad_norm": 0.4256959855556488, "learning_rate": 4.964594261434055e-05, "loss": 4.507, "step": 1756 }, { "epoch": 0.05366524129505192, "grad_norm": 0.4345991015434265, "learning_rate": 4.964554020099337e-05, "loss": 4.4671, "step": 1757 }, { "epoch": 0.05369578497251069, "grad_norm": 0.42455923557281494, "learning_rate": 4.964513756072202e-05, "loss": 4.4121, "step": 1758 }, { "epoch": 0.05372632864996946, "grad_norm": 0.44499072432518005, "learning_rate": 4.9644734693530224e-05, "loss": 4.46, "step": 1759 }, { "epoch": 0.05375687232742822, "grad_norm": 0.42552974820137024, "learning_rate": 4.964433159942169e-05, "loss": 4.4842, "step": 1760 }, { "epoch": 0.05378741600488699, "grad_norm": 0.42224186658859253, "learning_rate": 4.964392827840012e-05, "loss": 4.4665, "step": 1761 }, { "epoch": 0.053817959682345755, "grad_norm": 0.42373695969581604, "learning_rate": 4.9643524730469225e-05, "loss": 4.4504, "step": 1762 }, { "epoch": 0.05384850335980452, "grad_norm": 0.4129830002784729, "learning_rate": 4.964312095563273e-05, "loss": 4.4341, "step": 1763 }, { "epoch": 0.05387904703726329, "grad_norm": 0.42043766379356384, "learning_rate": 4.9642716953894355e-05, "loss": 4.4633, "step": 1764 }, { "epoch": 0.05390959071472205, "grad_norm": 0.4307229220867157, "learning_rate": 4.964231272525781e-05, "loss": 4.4896, "step": 1765 }, { "epoch": 0.053940134392180816, "grad_norm": 0.4294053018093109, "learning_rate": 4.9641908269726826e-05, "loss": 4.4299, "step": 1766 }, { "epoch": 0.05397067806963959, "grad_norm": 0.4203529953956604, "learning_rate": 4.964150358730512e-05, "loss": 4.4049, "step": 1767 }, { "epoch": 0.05400122174709835, "grad_norm": 0.42285510897636414, "learning_rate": 4.9641098677996426e-05, "loss": 4.3695, "step": 1768 }, { "epoch": 0.054031765424557114, "grad_norm": 0.4281501770019531, "learning_rate": 4.9640693541804464e-05, "loss": 4.4033, "step": 1769 }, { "epoch": 0.054062309102015885, "grad_norm": 0.4220729470252991, "learning_rate": 4.9640288178732965e-05, "loss": 4.4139, "step": 1770 }, { "epoch": 0.05409285277947465, "grad_norm": 0.42160114645957947, "learning_rate": 4.963988258878566e-05, "loss": 4.4715, "step": 1771 }, { "epoch": 0.05412339645693341, "grad_norm": 0.42365461587905884, "learning_rate": 4.96394767719663e-05, "loss": 4.4822, "step": 1772 }, { "epoch": 0.05415394013439218, "grad_norm": 0.41206398606300354, "learning_rate": 4.96390707282786e-05, "loss": 4.4642, "step": 1773 }, { "epoch": 0.054184483811850946, "grad_norm": 0.425219863653183, "learning_rate": 4.963866445772631e-05, "loss": 4.4364, "step": 1774 }, { "epoch": 0.05421502748930971, "grad_norm": 0.43849673867225647, "learning_rate": 4.9638257960313166e-05, "loss": 4.4732, "step": 1775 }, { "epoch": 0.05424557116676848, "grad_norm": 0.4237378239631653, "learning_rate": 4.9637851236042916e-05, "loss": 4.4727, "step": 1776 }, { "epoch": 0.054276114844227244, "grad_norm": 0.4274462163448334, "learning_rate": 4.96374442849193e-05, "loss": 4.4813, "step": 1777 }, { "epoch": 0.05430665852168601, "grad_norm": 0.4219074547290802, "learning_rate": 4.963703710694607e-05, "loss": 4.3744, "step": 1778 }, { "epoch": 0.05433720219914478, "grad_norm": 0.418683797121048, "learning_rate": 4.9636629702126966e-05, "loss": 4.3885, "step": 1779 }, { "epoch": 0.05436774587660354, "grad_norm": 0.4258024990558624, "learning_rate": 4.963622207046575e-05, "loss": 4.3807, "step": 1780 }, { "epoch": 0.05439828955406231, "grad_norm": 0.41407012939453125, "learning_rate": 4.963581421196618e-05, "loss": 4.359, "step": 1781 }, { "epoch": 0.054428833231521076, "grad_norm": 0.42234164476394653, "learning_rate": 4.963540612663199e-05, "loss": 4.4467, "step": 1782 }, { "epoch": 0.05445937690897984, "grad_norm": 0.42754900455474854, "learning_rate": 4.9634997814466956e-05, "loss": 4.4625, "step": 1783 }, { "epoch": 0.05448992058643861, "grad_norm": 0.4351663291454315, "learning_rate": 4.9634589275474824e-05, "loss": 4.5216, "step": 1784 }, { "epoch": 0.054520464263897374, "grad_norm": 0.4347614645957947, "learning_rate": 4.9634180509659364e-05, "loss": 4.4332, "step": 1785 }, { "epoch": 0.05455100794135614, "grad_norm": 0.40738773345947266, "learning_rate": 4.9633771517024344e-05, "loss": 4.3588, "step": 1786 }, { "epoch": 0.05458155161881491, "grad_norm": 0.4454953968524933, "learning_rate": 4.9633362297573524e-05, "loss": 4.5006, "step": 1787 }, { "epoch": 0.05461209529627367, "grad_norm": 0.4246457517147064, "learning_rate": 4.9632952851310666e-05, "loss": 4.4714, "step": 1788 }, { "epoch": 0.054642638973732435, "grad_norm": 0.4221711754798889, "learning_rate": 4.963254317823955e-05, "loss": 4.4415, "step": 1789 }, { "epoch": 0.054673182651191206, "grad_norm": 0.41455215215682983, "learning_rate": 4.9632133278363947e-05, "loss": 4.405, "step": 1790 }, { "epoch": 0.05470372632864997, "grad_norm": 0.43079277873039246, "learning_rate": 4.963172315168762e-05, "loss": 4.5229, "step": 1791 }, { "epoch": 0.05473427000610873, "grad_norm": 0.425081342458725, "learning_rate": 4.963131279821436e-05, "loss": 4.5207, "step": 1792 }, { "epoch": 0.054764813683567504, "grad_norm": 0.43016698956489563, "learning_rate": 4.963090221794794e-05, "loss": 4.5377, "step": 1793 }, { "epoch": 0.05479535736102627, "grad_norm": 0.4105452597141266, "learning_rate": 4.963049141089213e-05, "loss": 4.4494, "step": 1794 }, { "epoch": 0.05482590103848503, "grad_norm": 0.4092511534690857, "learning_rate": 4.963008037705073e-05, "loss": 4.4119, "step": 1795 }, { "epoch": 0.0548564447159438, "grad_norm": 0.4246903359889984, "learning_rate": 4.962966911642751e-05, "loss": 4.4292, "step": 1796 }, { "epoch": 0.054886988393402565, "grad_norm": 0.40891319513320923, "learning_rate": 4.962925762902627e-05, "loss": 4.3762, "step": 1797 }, { "epoch": 0.05491753207086133, "grad_norm": 0.4176236689090729, "learning_rate": 4.9628845914850794e-05, "loss": 4.4726, "step": 1798 }, { "epoch": 0.0549480757483201, "grad_norm": 0.42146036028862, "learning_rate": 4.962843397390487e-05, "loss": 4.5795, "step": 1799 }, { "epoch": 0.05497861942577886, "grad_norm": 0.41204527020454407, "learning_rate": 4.962802180619228e-05, "loss": 4.4321, "step": 1800 }, { "epoch": 0.05500916310323763, "grad_norm": 0.4281948208808899, "learning_rate": 4.962760941171685e-05, "loss": 4.4416, "step": 1801 }, { "epoch": 0.0550397067806964, "grad_norm": 0.41604962944984436, "learning_rate": 4.9627196790482345e-05, "loss": 4.3969, "step": 1802 }, { "epoch": 0.05507025045815516, "grad_norm": 0.42504361271858215, "learning_rate": 4.962678394249257e-05, "loss": 4.4999, "step": 1803 }, { "epoch": 0.05510079413561393, "grad_norm": 0.4164290428161621, "learning_rate": 4.962637086775135e-05, "loss": 4.4381, "step": 1804 }, { "epoch": 0.055131337813072695, "grad_norm": 0.40276777744293213, "learning_rate": 4.962595756626246e-05, "loss": 4.4344, "step": 1805 }, { "epoch": 0.05516188149053146, "grad_norm": 0.43611958622932434, "learning_rate": 4.962554403802973e-05, "loss": 4.3848, "step": 1806 }, { "epoch": 0.05519242516799023, "grad_norm": 0.43211817741394043, "learning_rate": 4.962513028305694e-05, "loss": 4.509, "step": 1807 }, { "epoch": 0.05522296884544899, "grad_norm": 0.42073073983192444, "learning_rate": 4.962471630134792e-05, "loss": 4.5149, "step": 1808 }, { "epoch": 0.055253512522907756, "grad_norm": 0.416453093290329, "learning_rate": 4.9624302092906474e-05, "loss": 4.445, "step": 1809 }, { "epoch": 0.05528405620036653, "grad_norm": 0.4301612079143524, "learning_rate": 4.962388765773642e-05, "loss": 4.4563, "step": 1810 }, { "epoch": 0.05531459987782529, "grad_norm": 0.4298001527786255, "learning_rate": 4.962347299584158e-05, "loss": 4.499, "step": 1811 }, { "epoch": 0.055345143555284054, "grad_norm": 0.40858250856399536, "learning_rate": 4.962305810722575e-05, "loss": 4.4627, "step": 1812 }, { "epoch": 0.055375687232742825, "grad_norm": 0.41326913237571716, "learning_rate": 4.9622642991892776e-05, "loss": 4.4369, "step": 1813 }, { "epoch": 0.05540623091020159, "grad_norm": 0.4170013964176178, "learning_rate": 4.9622227649846463e-05, "loss": 4.457, "step": 1814 }, { "epoch": 0.05543677458766035, "grad_norm": 0.4165545701980591, "learning_rate": 4.962181208109064e-05, "loss": 4.406, "step": 1815 }, { "epoch": 0.05546731826511912, "grad_norm": 0.42270368337631226, "learning_rate": 4.962139628562914e-05, "loss": 4.4809, "step": 1816 }, { "epoch": 0.055497861942577886, "grad_norm": 0.41891777515411377, "learning_rate": 4.962098026346578e-05, "loss": 4.3284, "step": 1817 }, { "epoch": 0.05552840562003665, "grad_norm": 0.4292317032814026, "learning_rate": 4.962056401460439e-05, "loss": 4.4444, "step": 1818 }, { "epoch": 0.05555894929749542, "grad_norm": 0.42447277903556824, "learning_rate": 4.962014753904882e-05, "loss": 4.4308, "step": 1819 }, { "epoch": 0.055589492974954184, "grad_norm": 0.41514161229133606, "learning_rate": 4.961973083680289e-05, "loss": 4.4792, "step": 1820 }, { "epoch": 0.05562003665241295, "grad_norm": 0.4236904978752136, "learning_rate": 4.9619313907870435e-05, "loss": 4.4579, "step": 1821 }, { "epoch": 0.05565058032987172, "grad_norm": 0.4283989667892456, "learning_rate": 4.96188967522553e-05, "loss": 4.4172, "step": 1822 }, { "epoch": 0.05568112400733048, "grad_norm": 0.4034225344657898, "learning_rate": 4.961847936996133e-05, "loss": 4.4194, "step": 1823 }, { "epoch": 0.055711667684789246, "grad_norm": 0.4085237681865692, "learning_rate": 4.961806176099235e-05, "loss": 4.4681, "step": 1824 }, { "epoch": 0.055742211362248016, "grad_norm": 0.4152710735797882, "learning_rate": 4.961764392535223e-05, "loss": 4.5217, "step": 1825 }, { "epoch": 0.05577275503970678, "grad_norm": 0.40188145637512207, "learning_rate": 4.96172258630448e-05, "loss": 4.4092, "step": 1826 }, { "epoch": 0.05580329871716554, "grad_norm": 0.4187221825122833, "learning_rate": 4.961680757407392e-05, "loss": 4.4651, "step": 1827 }, { "epoch": 0.055833842394624314, "grad_norm": 0.41766685247421265, "learning_rate": 4.9616389058443435e-05, "loss": 4.4536, "step": 1828 }, { "epoch": 0.05586438607208308, "grad_norm": 0.40988999605178833, "learning_rate": 4.96159703161572e-05, "loss": 4.3947, "step": 1829 }, { "epoch": 0.05589492974954185, "grad_norm": 0.42328163981437683, "learning_rate": 4.961555134721907e-05, "loss": 4.4655, "step": 1830 }, { "epoch": 0.05592547342700061, "grad_norm": 0.41021642088890076, "learning_rate": 4.961513215163289e-05, "loss": 4.5103, "step": 1831 }, { "epoch": 0.055956017104459375, "grad_norm": 0.40816420316696167, "learning_rate": 4.9614712729402545e-05, "loss": 4.5115, "step": 1832 }, { "epoch": 0.055986560781918146, "grad_norm": 0.4151955842971802, "learning_rate": 4.961429308053188e-05, "loss": 4.4408, "step": 1833 }, { "epoch": 0.05601710445937691, "grad_norm": 0.42784059047698975, "learning_rate": 4.961387320502477e-05, "loss": 4.4392, "step": 1834 }, { "epoch": 0.05604764813683567, "grad_norm": 0.4212954342365265, "learning_rate": 4.961345310288507e-05, "loss": 4.5022, "step": 1835 }, { "epoch": 0.056078191814294444, "grad_norm": 0.41122981905937195, "learning_rate": 4.961303277411665e-05, "loss": 4.476, "step": 1836 }, { "epoch": 0.05610873549175321, "grad_norm": 0.41912150382995605, "learning_rate": 4.961261221872339e-05, "loss": 4.379, "step": 1837 }, { "epoch": 0.05613927916921197, "grad_norm": 0.41621777415275574, "learning_rate": 4.961219143670914e-05, "loss": 4.3945, "step": 1838 }, { "epoch": 0.05616982284667074, "grad_norm": 0.4130394458770752, "learning_rate": 4.96117704280778e-05, "loss": 4.428, "step": 1839 }, { "epoch": 0.056200366524129505, "grad_norm": 0.42197445034980774, "learning_rate": 4.9611349192833235e-05, "loss": 4.5132, "step": 1840 }, { "epoch": 0.05623091020158827, "grad_norm": 0.4226660430431366, "learning_rate": 4.961092773097932e-05, "loss": 4.5031, "step": 1841 }, { "epoch": 0.05626145387904704, "grad_norm": 0.42927086353302, "learning_rate": 4.961050604251994e-05, "loss": 4.4468, "step": 1842 }, { "epoch": 0.0562919975565058, "grad_norm": 0.41281116008758545, "learning_rate": 4.961008412745899e-05, "loss": 4.3901, "step": 1843 }, { "epoch": 0.05632254123396457, "grad_norm": 0.4146377146244049, "learning_rate": 4.960966198580033e-05, "loss": 4.53, "step": 1844 }, { "epoch": 0.05635308491142334, "grad_norm": 0.41515496373176575, "learning_rate": 4.9609239617547855e-05, "loss": 4.4856, "step": 1845 }, { "epoch": 0.0563836285888821, "grad_norm": 0.4070688784122467, "learning_rate": 4.960881702270547e-05, "loss": 4.39, "step": 1846 }, { "epoch": 0.056414172266340865, "grad_norm": 0.4356880784034729, "learning_rate": 4.960839420127704e-05, "loss": 4.4493, "step": 1847 }, { "epoch": 0.056444715943799635, "grad_norm": 0.41910484433174133, "learning_rate": 4.960797115326649e-05, "loss": 4.5321, "step": 1848 }, { "epoch": 0.0564752596212584, "grad_norm": 0.42036381363868713, "learning_rate": 4.960754787867768e-05, "loss": 4.3691, "step": 1849 }, { "epoch": 0.05650580329871716, "grad_norm": 0.41796547174453735, "learning_rate": 4.9607124377514535e-05, "loss": 4.4597, "step": 1850 }, { "epoch": 0.05653634697617593, "grad_norm": 0.40484634041786194, "learning_rate": 4.960670064978094e-05, "loss": 4.34, "step": 1851 }, { "epoch": 0.0565668906536347, "grad_norm": 0.42214667797088623, "learning_rate": 4.9606276695480803e-05, "loss": 4.4364, "step": 1852 }, { "epoch": 0.05659743433109346, "grad_norm": 0.42831951379776, "learning_rate": 4.9605852514618026e-05, "loss": 4.4725, "step": 1853 }, { "epoch": 0.05662797800855223, "grad_norm": 0.41134577989578247, "learning_rate": 4.960542810719651e-05, "loss": 4.3874, "step": 1854 }, { "epoch": 0.056658521686010994, "grad_norm": 0.41185295581817627, "learning_rate": 4.960500347322017e-05, "loss": 4.4835, "step": 1855 }, { "epoch": 0.056689065363469765, "grad_norm": 0.4121701121330261, "learning_rate": 4.960457861269291e-05, "loss": 4.413, "step": 1856 }, { "epoch": 0.05671960904092853, "grad_norm": 0.4126023054122925, "learning_rate": 4.9604153525618645e-05, "loss": 4.457, "step": 1857 }, { "epoch": 0.05675015271838729, "grad_norm": 0.4054149389266968, "learning_rate": 4.9603728212001285e-05, "loss": 4.4539, "step": 1858 }, { "epoch": 0.05678069639584606, "grad_norm": 0.4314635097980499, "learning_rate": 4.9603302671844754e-05, "loss": 4.4291, "step": 1859 }, { "epoch": 0.056811240073304826, "grad_norm": 0.41300928592681885, "learning_rate": 4.960287690515297e-05, "loss": 4.3054, "step": 1860 }, { "epoch": 0.05684178375076359, "grad_norm": 0.4247496426105499, "learning_rate": 4.960245091192984e-05, "loss": 4.4296, "step": 1861 }, { "epoch": 0.05687232742822236, "grad_norm": 0.4190668761730194, "learning_rate": 4.96020246921793e-05, "loss": 4.4652, "step": 1862 }, { "epoch": 0.056902871105681124, "grad_norm": 0.4190422296524048, "learning_rate": 4.960159824590527e-05, "loss": 4.4783, "step": 1863 }, { "epoch": 0.05693341478313989, "grad_norm": 0.4139538109302521, "learning_rate": 4.960117157311167e-05, "loss": 4.4593, "step": 1864 }, { "epoch": 0.05696395846059866, "grad_norm": 0.415129154920578, "learning_rate": 4.960074467380244e-05, "loss": 4.4091, "step": 1865 }, { "epoch": 0.05699450213805742, "grad_norm": 0.41631993651390076, "learning_rate": 4.96003175479815e-05, "loss": 4.4339, "step": 1866 }, { "epoch": 0.057025045815516186, "grad_norm": 0.424610435962677, "learning_rate": 4.95998901956528e-05, "loss": 4.4259, "step": 1867 }, { "epoch": 0.057055589492974956, "grad_norm": 0.4104938805103302, "learning_rate": 4.9599462616820256e-05, "loss": 4.445, "step": 1868 }, { "epoch": 0.05708613317043372, "grad_norm": 0.41840213537216187, "learning_rate": 4.959903481148781e-05, "loss": 4.4567, "step": 1869 }, { "epoch": 0.057116676847892484, "grad_norm": 0.42481178045272827, "learning_rate": 4.9598606779659404e-05, "loss": 4.3833, "step": 1870 }, { "epoch": 0.057147220525351254, "grad_norm": 0.4206811189651489, "learning_rate": 4.9598178521338976e-05, "loss": 4.3536, "step": 1871 }, { "epoch": 0.05717776420281002, "grad_norm": 0.4238629937171936, "learning_rate": 4.959775003653047e-05, "loss": 4.5514, "step": 1872 }, { "epoch": 0.05720830788026878, "grad_norm": 0.42929285764694214, "learning_rate": 4.9597321325237834e-05, "loss": 4.4925, "step": 1873 }, { "epoch": 0.05723885155772755, "grad_norm": 0.426444411277771, "learning_rate": 4.959689238746502e-05, "loss": 4.4445, "step": 1874 }, { "epoch": 0.057269395235186316, "grad_norm": 0.4014277160167694, "learning_rate": 4.959646322321597e-05, "loss": 4.4211, "step": 1875 }, { "epoch": 0.05729993891264508, "grad_norm": 0.42686179280281067, "learning_rate": 4.9596033832494624e-05, "loss": 4.4327, "step": 1876 }, { "epoch": 0.05733048259010385, "grad_norm": 0.4052599370479584, "learning_rate": 4.959560421530496e-05, "loss": 4.3986, "step": 1877 }, { "epoch": 0.05736102626756261, "grad_norm": 0.4179946482181549, "learning_rate": 4.959517437165092e-05, "loss": 4.489, "step": 1878 }, { "epoch": 0.057391569945021384, "grad_norm": 0.4178179204463959, "learning_rate": 4.959474430153647e-05, "loss": 4.5227, "step": 1879 }, { "epoch": 0.05742211362248015, "grad_norm": 0.41635680198669434, "learning_rate": 4.959431400496556e-05, "loss": 4.4824, "step": 1880 }, { "epoch": 0.05745265729993891, "grad_norm": 0.4210611581802368, "learning_rate": 4.959388348194215e-05, "loss": 4.4095, "step": 1881 }, { "epoch": 0.05748320097739768, "grad_norm": 0.41873928904533386, "learning_rate": 4.959345273247021e-05, "loss": 4.4837, "step": 1882 }, { "epoch": 0.057513744654856445, "grad_norm": 0.41214409470558167, "learning_rate": 4.9593021756553716e-05, "loss": 4.4676, "step": 1883 }, { "epoch": 0.05754428833231521, "grad_norm": 0.40716245770454407, "learning_rate": 4.959259055419662e-05, "loss": 4.5248, "step": 1884 }, { "epoch": 0.05757483200977398, "grad_norm": 0.41852253675460815, "learning_rate": 4.959215912540289e-05, "loss": 4.4649, "step": 1885 }, { "epoch": 0.05760537568723274, "grad_norm": 0.4084785580635071, "learning_rate": 4.959172747017652e-05, "loss": 4.4638, "step": 1886 }, { "epoch": 0.05763591936469151, "grad_norm": 0.419728547334671, "learning_rate": 4.959129558852147e-05, "loss": 4.39, "step": 1887 }, { "epoch": 0.05766646304215028, "grad_norm": 0.4210933744907379, "learning_rate": 4.9590863480441714e-05, "loss": 4.4303, "step": 1888 }, { "epoch": 0.05769700671960904, "grad_norm": 0.41995880007743835, "learning_rate": 4.959043114594123e-05, "loss": 4.4652, "step": 1889 }, { "epoch": 0.057727550397067805, "grad_norm": 0.42697030305862427, "learning_rate": 4.958999858502401e-05, "loss": 4.473, "step": 1890 }, { "epoch": 0.057758094074526575, "grad_norm": 0.41350144147872925, "learning_rate": 4.958956579769403e-05, "loss": 4.3823, "step": 1891 }, { "epoch": 0.05778863775198534, "grad_norm": 0.41960734128952026, "learning_rate": 4.9589132783955275e-05, "loss": 4.5012, "step": 1892 }, { "epoch": 0.0578191814294441, "grad_norm": 0.41267916560173035, "learning_rate": 4.958869954381173e-05, "loss": 4.4207, "step": 1893 }, { "epoch": 0.05784972510690287, "grad_norm": 0.42182156443595886, "learning_rate": 4.9588266077267383e-05, "loss": 4.4056, "step": 1894 }, { "epoch": 0.05788026878436164, "grad_norm": 0.4223248362541199, "learning_rate": 4.958783238432624e-05, "loss": 4.4545, "step": 1895 }, { "epoch": 0.0579108124618204, "grad_norm": 0.4183523952960968, "learning_rate": 4.9587398464992276e-05, "loss": 4.3947, "step": 1896 }, { "epoch": 0.05794135613927917, "grad_norm": 0.4153251051902771, "learning_rate": 4.9586964319269486e-05, "loss": 4.4792, "step": 1897 }, { "epoch": 0.057971899816737935, "grad_norm": 0.41799524426460266, "learning_rate": 4.958652994716188e-05, "loss": 4.3445, "step": 1898 }, { "epoch": 0.0580024434941967, "grad_norm": 0.42105817794799805, "learning_rate": 4.958609534867345e-05, "loss": 4.4268, "step": 1899 }, { "epoch": 0.05803298717165547, "grad_norm": 0.4423670470714569, "learning_rate": 4.9585660523808196e-05, "loss": 4.4216, "step": 1900 }, { "epoch": 0.05806353084911423, "grad_norm": 0.41067028045654297, "learning_rate": 4.9585225472570126e-05, "loss": 4.4463, "step": 1901 }, { "epoch": 0.058094074526572996, "grad_norm": 0.42443838715553284, "learning_rate": 4.958479019496325e-05, "loss": 4.3725, "step": 1902 }, { "epoch": 0.05812461820403177, "grad_norm": 0.4116731584072113, "learning_rate": 4.9584354690991575e-05, "loss": 4.5386, "step": 1903 }, { "epoch": 0.05815516188149053, "grad_norm": 0.4185870289802551, "learning_rate": 4.95839189606591e-05, "loss": 4.3651, "step": 1904 }, { "epoch": 0.0581857055589493, "grad_norm": 0.4256425201892853, "learning_rate": 4.958348300396984e-05, "loss": 4.519, "step": 1905 }, { "epoch": 0.058216249236408064, "grad_norm": 0.41345521807670593, "learning_rate": 4.9583046820927814e-05, "loss": 4.4195, "step": 1906 }, { "epoch": 0.05824679291386683, "grad_norm": 0.42299559712409973, "learning_rate": 4.958261041153704e-05, "loss": 4.414, "step": 1907 }, { "epoch": 0.0582773365913256, "grad_norm": 0.4083499014377594, "learning_rate": 4.9582173775801536e-05, "loss": 4.4111, "step": 1908 }, { "epoch": 0.05830788026878436, "grad_norm": 0.4136027991771698, "learning_rate": 4.9581736913725305e-05, "loss": 4.4535, "step": 1909 }, { "epoch": 0.058338423946243126, "grad_norm": 0.4220796227455139, "learning_rate": 4.9581299825312396e-05, "loss": 4.5053, "step": 1910 }, { "epoch": 0.058368967623701896, "grad_norm": 0.40727102756500244, "learning_rate": 4.9580862510566816e-05, "loss": 4.4853, "step": 1911 }, { "epoch": 0.05839951130116066, "grad_norm": 0.4091317653656006, "learning_rate": 4.95804249694926e-05, "loss": 4.4115, "step": 1912 }, { "epoch": 0.058430054978619424, "grad_norm": 0.4072117507457733, "learning_rate": 4.957998720209377e-05, "loss": 4.4952, "step": 1913 }, { "epoch": 0.058460598656078194, "grad_norm": 0.39927583932876587, "learning_rate": 4.9579549208374356e-05, "loss": 4.3844, "step": 1914 }, { "epoch": 0.05849114233353696, "grad_norm": 0.42244645953178406, "learning_rate": 4.957911098833841e-05, "loss": 4.5424, "step": 1915 }, { "epoch": 0.05852168601099572, "grad_norm": 0.4230502247810364, "learning_rate": 4.957867254198993e-05, "loss": 4.4153, "step": 1916 }, { "epoch": 0.05855222968845449, "grad_norm": 0.4123765826225281, "learning_rate": 4.957823386933299e-05, "loss": 4.4598, "step": 1917 }, { "epoch": 0.058582773365913256, "grad_norm": 0.40362483263015747, "learning_rate": 4.957779497037161e-05, "loss": 4.4396, "step": 1918 }, { "epoch": 0.05861331704337202, "grad_norm": 0.4147886037826538, "learning_rate": 4.957735584510984e-05, "loss": 4.4496, "step": 1919 }, { "epoch": 0.05864386072083079, "grad_norm": 0.40753668546676636, "learning_rate": 4.957691649355171e-05, "loss": 4.4222, "step": 1920 }, { "epoch": 0.058674404398289554, "grad_norm": 0.4212847650051117, "learning_rate": 4.9576476915701274e-05, "loss": 4.3946, "step": 1921 }, { "epoch": 0.05870494807574832, "grad_norm": 0.4309561848640442, "learning_rate": 4.957603711156259e-05, "loss": 4.4904, "step": 1922 }, { "epoch": 0.05873549175320709, "grad_norm": 0.41013774275779724, "learning_rate": 4.9575597081139683e-05, "loss": 4.4313, "step": 1923 }, { "epoch": 0.05876603543066585, "grad_norm": 0.42076799273490906, "learning_rate": 4.957515682443663e-05, "loss": 4.3795, "step": 1924 }, { "epoch": 0.058796579108124615, "grad_norm": 0.4259682595729828, "learning_rate": 4.957471634145746e-05, "loss": 4.5326, "step": 1925 }, { "epoch": 0.058827122785583386, "grad_norm": 0.42230838537216187, "learning_rate": 4.957427563220626e-05, "loss": 4.4605, "step": 1926 }, { "epoch": 0.05885766646304215, "grad_norm": 0.41977232694625854, "learning_rate": 4.957383469668705e-05, "loss": 4.4851, "step": 1927 }, { "epoch": 0.05888821014050091, "grad_norm": 0.4144451320171356, "learning_rate": 4.9573393534903925e-05, "loss": 4.4098, "step": 1928 }, { "epoch": 0.05891875381795968, "grad_norm": 0.40930885076522827, "learning_rate": 4.957295214686092e-05, "loss": 4.4375, "step": 1929 }, { "epoch": 0.05894929749541845, "grad_norm": 0.41080203652381897, "learning_rate": 4.9572510532562114e-05, "loss": 4.4656, "step": 1930 }, { "epoch": 0.05897984117287722, "grad_norm": 0.4118286073207855, "learning_rate": 4.9572068692011564e-05, "loss": 4.3719, "step": 1931 }, { "epoch": 0.05901038485033598, "grad_norm": 0.4174047112464905, "learning_rate": 4.957162662521335e-05, "loss": 4.4241, "step": 1932 }, { "epoch": 0.059040928527794745, "grad_norm": 0.41771695017814636, "learning_rate": 4.957118433217154e-05, "loss": 4.4824, "step": 1933 }, { "epoch": 0.059071472205253515, "grad_norm": 0.41012853384017944, "learning_rate": 4.9570741812890196e-05, "loss": 4.4115, "step": 1934 }, { "epoch": 0.05910201588271228, "grad_norm": 0.41158539056777954, "learning_rate": 4.9570299067373407e-05, "loss": 4.4433, "step": 1935 }, { "epoch": 0.05913255956017104, "grad_norm": 0.4141600430011749, "learning_rate": 4.9569856095625237e-05, "loss": 4.4097, "step": 1936 }, { "epoch": 0.05916310323762981, "grad_norm": 0.4117234945297241, "learning_rate": 4.9569412897649766e-05, "loss": 4.4647, "step": 1937 }, { "epoch": 0.05919364691508858, "grad_norm": 0.41370800137519836, "learning_rate": 4.956896947345108e-05, "loss": 4.353, "step": 1938 }, { "epoch": 0.05922419059254734, "grad_norm": 0.4155665636062622, "learning_rate": 4.9568525823033265e-05, "loss": 4.3816, "step": 1939 }, { "epoch": 0.05925473427000611, "grad_norm": 0.4186650514602661, "learning_rate": 4.9568081946400393e-05, "loss": 4.4703, "step": 1940 }, { "epoch": 0.059285277947464875, "grad_norm": 0.4084295928478241, "learning_rate": 4.956763784355656e-05, "loss": 4.4244, "step": 1941 }, { "epoch": 0.05931582162492364, "grad_norm": 0.4150434732437134, "learning_rate": 4.956719351450586e-05, "loss": 4.4176, "step": 1942 }, { "epoch": 0.05934636530238241, "grad_norm": 0.4169052541255951, "learning_rate": 4.956674895925237e-05, "loss": 4.4385, "step": 1943 }, { "epoch": 0.05937690897984117, "grad_norm": 0.42757540941238403, "learning_rate": 4.9566304177800196e-05, "loss": 4.5276, "step": 1944 }, { "epoch": 0.059407452657299936, "grad_norm": 0.40892383456230164, "learning_rate": 4.956585917015343e-05, "loss": 4.3596, "step": 1945 }, { "epoch": 0.05943799633475871, "grad_norm": 0.4116773009300232, "learning_rate": 4.956541393631616e-05, "loss": 4.4311, "step": 1946 }, { "epoch": 0.05946854001221747, "grad_norm": 0.4039560556411743, "learning_rate": 4.9564968476292504e-05, "loss": 4.5054, "step": 1947 }, { "epoch": 0.059499083689676234, "grad_norm": 0.41535431146621704, "learning_rate": 4.956452279008655e-05, "loss": 4.4728, "step": 1948 }, { "epoch": 0.059529627367135005, "grad_norm": 0.4140225648880005, "learning_rate": 4.95640768777024e-05, "loss": 4.4404, "step": 1949 }, { "epoch": 0.05956017104459377, "grad_norm": 0.42522042989730835, "learning_rate": 4.9563630739144175e-05, "loss": 4.4564, "step": 1950 }, { "epoch": 0.05959071472205253, "grad_norm": 0.41613632440567017, "learning_rate": 4.956318437441597e-05, "loss": 4.4966, "step": 1951 }, { "epoch": 0.0596212583995113, "grad_norm": 0.4180488586425781, "learning_rate": 4.956273778352189e-05, "loss": 4.3956, "step": 1952 }, { "epoch": 0.059651802076970066, "grad_norm": 0.40761974453926086, "learning_rate": 4.956229096646606e-05, "loss": 4.4829, "step": 1953 }, { "epoch": 0.05968234575442884, "grad_norm": 0.4117845296859741, "learning_rate": 4.9561843923252585e-05, "loss": 4.461, "step": 1954 }, { "epoch": 0.0597128894318876, "grad_norm": 0.41637617349624634, "learning_rate": 4.956139665388558e-05, "loss": 4.5228, "step": 1955 }, { "epoch": 0.059743433109346364, "grad_norm": 0.4283355176448822, "learning_rate": 4.956094915836918e-05, "loss": 4.4479, "step": 1956 }, { "epoch": 0.059773976786805134, "grad_norm": 0.4069743752479553, "learning_rate": 4.9560501436707484e-05, "loss": 4.5108, "step": 1957 }, { "epoch": 0.0598045204642639, "grad_norm": 0.43355825543403625, "learning_rate": 4.956005348890463e-05, "loss": 4.371, "step": 1958 }, { "epoch": 0.05983506414172266, "grad_norm": 0.4214645028114319, "learning_rate": 4.955960531496473e-05, "loss": 4.3642, "step": 1959 }, { "epoch": 0.05986560781918143, "grad_norm": 0.4169953763484955, "learning_rate": 4.955915691489192e-05, "loss": 4.4267, "step": 1960 }, { "epoch": 0.059896151496640196, "grad_norm": 0.41505223512649536, "learning_rate": 4.955870828869033e-05, "loss": 4.4407, "step": 1961 }, { "epoch": 0.05992669517409896, "grad_norm": 0.4077603220939636, "learning_rate": 4.955825943636408e-05, "loss": 4.4069, "step": 1962 }, { "epoch": 0.05995723885155773, "grad_norm": 0.4128997325897217, "learning_rate": 4.95578103579173e-05, "loss": 4.441, "step": 1963 }, { "epoch": 0.059987782529016494, "grad_norm": 0.4242171049118042, "learning_rate": 4.9557361053354145e-05, "loss": 4.4318, "step": 1964 }, { "epoch": 0.06001832620647526, "grad_norm": 0.433275043964386, "learning_rate": 4.955691152267874e-05, "loss": 4.408, "step": 1965 }, { "epoch": 0.06004886988393403, "grad_norm": 0.43296411633491516, "learning_rate": 4.9556461765895226e-05, "loss": 4.5005, "step": 1966 }, { "epoch": 0.06007941356139279, "grad_norm": 0.4064117670059204, "learning_rate": 4.9556011783007734e-05, "loss": 4.4762, "step": 1967 }, { "epoch": 0.060109957238851555, "grad_norm": 0.40360745787620544, "learning_rate": 4.955556157402042e-05, "loss": 4.4296, "step": 1968 }, { "epoch": 0.060140500916310326, "grad_norm": 0.427791029214859, "learning_rate": 4.9555111138937425e-05, "loss": 4.5156, "step": 1969 }, { "epoch": 0.06017104459376909, "grad_norm": 0.41703522205352783, "learning_rate": 4.95546604777629e-05, "loss": 4.4098, "step": 1970 }, { "epoch": 0.06020158827122785, "grad_norm": 0.402496874332428, "learning_rate": 4.955420959050099e-05, "loss": 4.4832, "step": 1971 }, { "epoch": 0.060232131948686624, "grad_norm": 0.4183426797389984, "learning_rate": 4.955375847715585e-05, "loss": 4.2213, "step": 1972 }, { "epoch": 0.06026267562614539, "grad_norm": 0.41651493310928345, "learning_rate": 4.955330713773163e-05, "loss": 4.504, "step": 1973 }, { "epoch": 0.06029321930360415, "grad_norm": 0.40984445810317993, "learning_rate": 4.955285557223248e-05, "loss": 4.4453, "step": 1974 }, { "epoch": 0.06032376298106292, "grad_norm": 0.418621689081192, "learning_rate": 4.9552403780662574e-05, "loss": 4.4697, "step": 1975 }, { "epoch": 0.060354306658521685, "grad_norm": 0.4089677333831787, "learning_rate": 4.955195176302606e-05, "loss": 4.3278, "step": 1976 }, { "epoch": 0.06038485033598045, "grad_norm": 0.40854522585868835, "learning_rate": 4.955149951932711e-05, "loss": 4.4599, "step": 1977 }, { "epoch": 0.06041539401343922, "grad_norm": 0.4108300507068634, "learning_rate": 4.955104704956987e-05, "loss": 4.4025, "step": 1978 }, { "epoch": 0.06044593769089798, "grad_norm": 0.40115246176719666, "learning_rate": 4.9550594353758516e-05, "loss": 4.4195, "step": 1979 }, { "epoch": 0.06047648136835675, "grad_norm": 0.4094507396221161, "learning_rate": 4.9550141431897225e-05, "loss": 4.4457, "step": 1980 }, { "epoch": 0.06050702504581552, "grad_norm": 0.4139654338359833, "learning_rate": 4.954968828399016e-05, "loss": 4.4638, "step": 1981 }, { "epoch": 0.06053756872327428, "grad_norm": 0.4107531011104584, "learning_rate": 4.954923491004149e-05, "loss": 4.4753, "step": 1982 }, { "epoch": 0.06056811240073305, "grad_norm": 0.42227354645729065, "learning_rate": 4.9548781310055384e-05, "loss": 4.3959, "step": 1983 }, { "epoch": 0.060598656078191815, "grad_norm": 0.4142867922782898, "learning_rate": 4.954832748403604e-05, "loss": 4.4495, "step": 1984 }, { "epoch": 0.06062919975565058, "grad_norm": 0.4298505485057831, "learning_rate": 4.954787343198761e-05, "loss": 4.3866, "step": 1985 }, { "epoch": 0.06065974343310935, "grad_norm": 0.4043416976928711, "learning_rate": 4.95474191539143e-05, "loss": 4.4537, "step": 1986 }, { "epoch": 0.06069028711056811, "grad_norm": 0.4175834357738495, "learning_rate": 4.954696464982027e-05, "loss": 4.4368, "step": 1987 }, { "epoch": 0.060720830788026876, "grad_norm": 0.43155720829963684, "learning_rate": 4.9546509919709725e-05, "loss": 4.5268, "step": 1988 }, { "epoch": 0.06075137446548565, "grad_norm": 0.40985581278800964, "learning_rate": 4.954605496358684e-05, "loss": 4.4457, "step": 1989 }, { "epoch": 0.06078191814294441, "grad_norm": 0.4023636281490326, "learning_rate": 4.9545599781455805e-05, "loss": 4.4113, "step": 1990 }, { "epoch": 0.060812461820403174, "grad_norm": 0.4148274064064026, "learning_rate": 4.9545144373320815e-05, "loss": 4.5333, "step": 1991 }, { "epoch": 0.060843005497861945, "grad_norm": 0.42866167426109314, "learning_rate": 4.954468873918606e-05, "loss": 4.4009, "step": 1992 }, { "epoch": 0.06087354917532071, "grad_norm": 0.4210703670978546, "learning_rate": 4.954423287905573e-05, "loss": 4.4235, "step": 1993 }, { "epoch": 0.06090409285277947, "grad_norm": 0.42055848240852356, "learning_rate": 4.9543776792934036e-05, "loss": 4.4125, "step": 1994 }, { "epoch": 0.06093463653023824, "grad_norm": 0.41099420189857483, "learning_rate": 4.954332048082517e-05, "loss": 4.4435, "step": 1995 }, { "epoch": 0.060965180207697006, "grad_norm": 0.42233598232269287, "learning_rate": 4.9542863942733333e-05, "loss": 4.3991, "step": 1996 }, { "epoch": 0.06099572388515577, "grad_norm": 0.41228052973747253, "learning_rate": 4.954240717866272e-05, "loss": 4.3786, "step": 1997 }, { "epoch": 0.06102626756261454, "grad_norm": 0.39982688426971436, "learning_rate": 4.954195018861756e-05, "loss": 4.3677, "step": 1998 }, { "epoch": 0.061056811240073304, "grad_norm": 0.4267286956310272, "learning_rate": 4.9541492972602036e-05, "loss": 4.4736, "step": 1999 }, { "epoch": 0.06108735491753207, "grad_norm": 0.4353203773498535, "learning_rate": 4.954103553062037e-05, "loss": 4.4921, "step": 2000 }, { "epoch": 0.06111789859499084, "grad_norm": 0.4187358319759369, "learning_rate": 4.9540577862676773e-05, "loss": 4.6546, "step": 2001 }, { "epoch": 0.0611484422724496, "grad_norm": 0.416778564453125, "learning_rate": 4.9540119968775464e-05, "loss": 4.4609, "step": 2002 }, { "epoch": 0.06117898594990837, "grad_norm": 0.4113112688064575, "learning_rate": 4.953966184892065e-05, "loss": 4.4154, "step": 2003 }, { "epoch": 0.061209529627367136, "grad_norm": 0.41703855991363525, "learning_rate": 4.953920350311655e-05, "loss": 4.4371, "step": 2004 }, { "epoch": 0.0612400733048259, "grad_norm": 0.4101654887199402, "learning_rate": 4.9538744931367384e-05, "loss": 4.4395, "step": 2005 }, { "epoch": 0.06127061698228467, "grad_norm": 0.41293811798095703, "learning_rate": 4.953828613367738e-05, "loss": 4.3899, "step": 2006 }, { "epoch": 0.061301160659743434, "grad_norm": 0.4100814759731293, "learning_rate": 4.953782711005076e-05, "loss": 4.5405, "step": 2007 }, { "epoch": 0.0613317043372022, "grad_norm": 0.42231059074401855, "learning_rate": 4.9537367860491746e-05, "loss": 4.4265, "step": 2008 }, { "epoch": 0.06136224801466097, "grad_norm": 0.403268426656723, "learning_rate": 4.9536908385004574e-05, "loss": 4.4756, "step": 2009 }, { "epoch": 0.06139279169211973, "grad_norm": 0.41189566254615784, "learning_rate": 4.9536448683593475e-05, "loss": 4.4329, "step": 2010 }, { "epoch": 0.061423335369578495, "grad_norm": 0.41524893045425415, "learning_rate": 4.953598875626266e-05, "loss": 4.4577, "step": 2011 }, { "epoch": 0.061453879047037266, "grad_norm": 0.4051072895526886, "learning_rate": 4.95355286030164e-05, "loss": 4.4393, "step": 2012 }, { "epoch": 0.06148442272449603, "grad_norm": 0.41702696681022644, "learning_rate": 4.953506822385891e-05, "loss": 4.4149, "step": 2013 }, { "epoch": 0.06151496640195479, "grad_norm": 0.4258810579776764, "learning_rate": 4.953460761879443e-05, "loss": 4.5215, "step": 2014 }, { "epoch": 0.061545510079413564, "grad_norm": 0.4143289029598236, "learning_rate": 4.95341467878272e-05, "loss": 4.4753, "step": 2015 }, { "epoch": 0.06157605375687233, "grad_norm": 0.42389872670173645, "learning_rate": 4.953368573096146e-05, "loss": 4.3713, "step": 2016 }, { "epoch": 0.06160659743433109, "grad_norm": 0.43480178713798523, "learning_rate": 4.9533224448201475e-05, "loss": 4.5341, "step": 2017 }, { "epoch": 0.06163714111178986, "grad_norm": 0.41675978899002075, "learning_rate": 4.953276293955148e-05, "loss": 4.3985, "step": 2018 }, { "epoch": 0.061667684789248625, "grad_norm": 0.4213145077228546, "learning_rate": 4.9532301205015715e-05, "loss": 4.4691, "step": 2019 }, { "epoch": 0.06169822846670739, "grad_norm": 0.40587133169174194, "learning_rate": 4.953183924459844e-05, "loss": 4.3616, "step": 2020 }, { "epoch": 0.06172877214416616, "grad_norm": 0.4250531494617462, "learning_rate": 4.953137705830391e-05, "loss": 4.4559, "step": 2021 }, { "epoch": 0.06175931582162492, "grad_norm": 0.40622156858444214, "learning_rate": 4.953091464613638e-05, "loss": 4.3899, "step": 2022 }, { "epoch": 0.06178985949908369, "grad_norm": 0.4095541536808014, "learning_rate": 4.9530452008100107e-05, "loss": 4.4366, "step": 2023 }, { "epoch": 0.06182040317654246, "grad_norm": 0.41419175267219543, "learning_rate": 4.952998914419934e-05, "loss": 4.3986, "step": 2024 }, { "epoch": 0.06185094685400122, "grad_norm": 0.42871537804603577, "learning_rate": 4.952952605443836e-05, "loss": 4.4416, "step": 2025 }, { "epoch": 0.061881490531459984, "grad_norm": 0.42323431372642517, "learning_rate": 4.952906273882142e-05, "loss": 4.4604, "step": 2026 }, { "epoch": 0.061912034208918755, "grad_norm": 0.4155062437057495, "learning_rate": 4.9528599197352784e-05, "loss": 4.4161, "step": 2027 }, { "epoch": 0.06194257788637752, "grad_norm": 0.4169531464576721, "learning_rate": 4.952813543003674e-05, "loss": 4.4032, "step": 2028 }, { "epoch": 0.06197312156383629, "grad_norm": 0.40291428565979004, "learning_rate": 4.952767143687752e-05, "loss": 4.3843, "step": 2029 }, { "epoch": 0.06200366524129505, "grad_norm": 0.4101433753967285, "learning_rate": 4.9527207217879434e-05, "loss": 4.4143, "step": 2030 }, { "epoch": 0.062034208918753816, "grad_norm": 0.4202878177165985, "learning_rate": 4.952674277304673e-05, "loss": 4.442, "step": 2031 }, { "epoch": 0.06206475259621259, "grad_norm": 0.41292521357536316, "learning_rate": 4.9526278102383705e-05, "loss": 4.48, "step": 2032 }, { "epoch": 0.06209529627367135, "grad_norm": 0.4055149257183075, "learning_rate": 4.952581320589462e-05, "loss": 4.4106, "step": 2033 }, { "epoch": 0.062125839951130114, "grad_norm": 0.41001269221305847, "learning_rate": 4.9525348083583764e-05, "loss": 4.4192, "step": 2034 }, { "epoch": 0.062156383628588885, "grad_norm": 0.414328932762146, "learning_rate": 4.952488273545542e-05, "loss": 4.4853, "step": 2035 }, { "epoch": 0.06218692730604765, "grad_norm": 0.41420555114746094, "learning_rate": 4.952441716151387e-05, "loss": 4.4989, "step": 2036 }, { "epoch": 0.06221747098350641, "grad_norm": 0.41283339262008667, "learning_rate": 4.9523951361763396e-05, "loss": 4.4671, "step": 2037 }, { "epoch": 0.06224801466096518, "grad_norm": 0.41386279463768005, "learning_rate": 4.952348533620831e-05, "loss": 4.3839, "step": 2038 }, { "epoch": 0.062278558338423946, "grad_norm": 0.42375892400741577, "learning_rate": 4.952301908485287e-05, "loss": 4.4668, "step": 2039 }, { "epoch": 0.06230910201588271, "grad_norm": 0.4205210506916046, "learning_rate": 4.952255260770139e-05, "loss": 4.4432, "step": 2040 }, { "epoch": 0.06233964569334148, "grad_norm": 0.4197731018066406, "learning_rate": 4.952208590475816e-05, "loss": 4.4615, "step": 2041 }, { "epoch": 0.062370189370800244, "grad_norm": 0.4279046356678009, "learning_rate": 4.952161897602747e-05, "loss": 4.4142, "step": 2042 }, { "epoch": 0.06240073304825901, "grad_norm": 0.4190242886543274, "learning_rate": 4.952115182151364e-05, "loss": 4.5013, "step": 2043 }, { "epoch": 0.06243127672571778, "grad_norm": 0.412716269493103, "learning_rate": 4.952068444122095e-05, "loss": 4.5287, "step": 2044 }, { "epoch": 0.06246182040317654, "grad_norm": 0.4162868857383728, "learning_rate": 4.952021683515371e-05, "loss": 4.4223, "step": 2045 }, { "epoch": 0.062492364080635306, "grad_norm": 0.4418197572231293, "learning_rate": 4.951974900331623e-05, "loss": 4.4323, "step": 2046 }, { "epoch": 0.06252290775809408, "grad_norm": 0.4106200039386749, "learning_rate": 4.951928094571281e-05, "loss": 4.3702, "step": 2047 }, { "epoch": 0.06255345143555284, "grad_norm": 0.4026845395565033, "learning_rate": 4.951881266234777e-05, "loss": 4.4411, "step": 2048 }, { "epoch": 0.0625839951130116, "grad_norm": 0.40904802083969116, "learning_rate": 4.951834415322541e-05, "loss": 4.3105, "step": 2049 }, { "epoch": 0.06261453879047037, "grad_norm": 0.42639094591140747, "learning_rate": 4.9517875418350054e-05, "loss": 4.4559, "step": 2050 }, { "epoch": 0.06264508246792914, "grad_norm": 0.4223572611808777, "learning_rate": 4.9517406457726004e-05, "loss": 4.3486, "step": 2051 }, { "epoch": 0.06267562614538791, "grad_norm": 0.41509974002838135, "learning_rate": 4.95169372713576e-05, "loss": 4.519, "step": 2052 }, { "epoch": 0.06270616982284667, "grad_norm": 0.41040074825286865, "learning_rate": 4.951646785924914e-05, "loss": 4.4728, "step": 2053 }, { "epoch": 0.06273671350030544, "grad_norm": 0.4386955201625824, "learning_rate": 4.951599822140496e-05, "loss": 4.5154, "step": 2054 }, { "epoch": 0.0627672571777642, "grad_norm": 0.44848477840423584, "learning_rate": 4.9515528357829374e-05, "loss": 4.4622, "step": 2055 }, { "epoch": 0.06279780085522296, "grad_norm": 0.42378994822502136, "learning_rate": 4.951505826852672e-05, "loss": 4.4856, "step": 2056 }, { "epoch": 0.06282834453268174, "grad_norm": 0.42093613743782043, "learning_rate": 4.9514587953501316e-05, "loss": 4.4731, "step": 2057 }, { "epoch": 0.0628588882101405, "grad_norm": 0.41706719994544983, "learning_rate": 4.95141174127575e-05, "loss": 4.4369, "step": 2058 }, { "epoch": 0.06288943188759927, "grad_norm": 0.41666755080223083, "learning_rate": 4.9513646646299595e-05, "loss": 4.4159, "step": 2059 }, { "epoch": 0.06291997556505803, "grad_norm": 0.4175820052623749, "learning_rate": 4.951317565413195e-05, "loss": 4.4678, "step": 2060 }, { "epoch": 0.0629505192425168, "grad_norm": 0.43366748094558716, "learning_rate": 4.951270443625888e-05, "loss": 4.533, "step": 2061 }, { "epoch": 0.06298106291997556, "grad_norm": 0.41365185379981995, "learning_rate": 4.9512232992684746e-05, "loss": 4.473, "step": 2062 }, { "epoch": 0.06301160659743434, "grad_norm": 0.41494208574295044, "learning_rate": 4.9511761323413885e-05, "loss": 4.4472, "step": 2063 }, { "epoch": 0.0630421502748931, "grad_norm": 0.43085935711860657, "learning_rate": 4.951128942845063e-05, "loss": 4.3534, "step": 2064 }, { "epoch": 0.06307269395235186, "grad_norm": 0.405318021774292, "learning_rate": 4.951081730779933e-05, "loss": 4.4567, "step": 2065 }, { "epoch": 0.06310323762981063, "grad_norm": 0.43889495730400085, "learning_rate": 4.951034496146433e-05, "loss": 4.4184, "step": 2066 }, { "epoch": 0.06313378130726939, "grad_norm": 0.4401618242263794, "learning_rate": 4.950987238944998e-05, "loss": 4.4267, "step": 2067 }, { "epoch": 0.06316432498472817, "grad_norm": 0.41045135259628296, "learning_rate": 4.9509399591760644e-05, "loss": 4.5099, "step": 2068 }, { "epoch": 0.06319486866218693, "grad_norm": 0.41912513971328735, "learning_rate": 4.950892656840066e-05, "loss": 4.5116, "step": 2069 }, { "epoch": 0.0632254123396457, "grad_norm": 0.40930578112602234, "learning_rate": 4.950845331937439e-05, "loss": 4.4658, "step": 2070 }, { "epoch": 0.06325595601710446, "grad_norm": 0.43562719225883484, "learning_rate": 4.950797984468618e-05, "loss": 4.3839, "step": 2071 }, { "epoch": 0.06328649969456322, "grad_norm": 0.427117258310318, "learning_rate": 4.950750614434041e-05, "loss": 4.4813, "step": 2072 }, { "epoch": 0.06331704337202199, "grad_norm": 0.41994595527648926, "learning_rate": 4.950703221834142e-05, "loss": 4.4932, "step": 2073 }, { "epoch": 0.06334758704948076, "grad_norm": 0.42132237553596497, "learning_rate": 4.9506558066693595e-05, "loss": 4.4267, "step": 2074 }, { "epoch": 0.06337813072693953, "grad_norm": 0.41703519225120544, "learning_rate": 4.9506083689401285e-05, "loss": 4.3638, "step": 2075 }, { "epoch": 0.06340867440439829, "grad_norm": 0.4103826582431793, "learning_rate": 4.9505609086468864e-05, "loss": 4.4464, "step": 2076 }, { "epoch": 0.06343921808185705, "grad_norm": 0.4153715968132019, "learning_rate": 4.950513425790069e-05, "loss": 4.336, "step": 2077 }, { "epoch": 0.06346976175931582, "grad_norm": 0.43885698914527893, "learning_rate": 4.950465920370115e-05, "loss": 4.4927, "step": 2078 }, { "epoch": 0.06350030543677458, "grad_norm": 0.41975125670433044, "learning_rate": 4.9504183923874624e-05, "loss": 4.4145, "step": 2079 }, { "epoch": 0.06353084911423336, "grad_norm": 0.42122864723205566, "learning_rate": 4.9503708418425474e-05, "loss": 4.4146, "step": 2080 }, { "epoch": 0.06356139279169212, "grad_norm": 0.4091666638851166, "learning_rate": 4.950323268735808e-05, "loss": 4.4014, "step": 2081 }, { "epoch": 0.06359193646915089, "grad_norm": 0.4177514612674713, "learning_rate": 4.950275673067683e-05, "loss": 4.4058, "step": 2082 }, { "epoch": 0.06362248014660965, "grad_norm": 0.4097045660018921, "learning_rate": 4.9502280548386085e-05, "loss": 4.4447, "step": 2083 }, { "epoch": 0.06365302382406841, "grad_norm": 0.41823285818099976, "learning_rate": 4.950180414049026e-05, "loss": 4.4403, "step": 2084 }, { "epoch": 0.06368356750152718, "grad_norm": 0.4185314178466797, "learning_rate": 4.950132750699372e-05, "loss": 4.4698, "step": 2085 }, { "epoch": 0.06371411117898595, "grad_norm": 0.41595548391342163, "learning_rate": 4.950085064790086e-05, "loss": 4.4748, "step": 2086 }, { "epoch": 0.06374465485644472, "grad_norm": 0.42209887504577637, "learning_rate": 4.950037356321608e-05, "loss": 4.4623, "step": 2087 }, { "epoch": 0.06377519853390348, "grad_norm": 0.43421077728271484, "learning_rate": 4.949989625294374e-05, "loss": 4.5392, "step": 2088 }, { "epoch": 0.06380574221136225, "grad_norm": 0.4047274589538574, "learning_rate": 4.9499418717088286e-05, "loss": 4.4721, "step": 2089 }, { "epoch": 0.06383628588882101, "grad_norm": 0.41520780324935913, "learning_rate": 4.949894095565407e-05, "loss": 4.4104, "step": 2090 }, { "epoch": 0.06386682956627979, "grad_norm": 0.4321168065071106, "learning_rate": 4.949846296864552e-05, "loss": 4.4219, "step": 2091 }, { "epoch": 0.06389737324373855, "grad_norm": 0.42274874448776245, "learning_rate": 4.949798475606702e-05, "loss": 4.4085, "step": 2092 }, { "epoch": 0.06392791692119731, "grad_norm": 0.41055238246917725, "learning_rate": 4.949750631792298e-05, "loss": 4.3964, "step": 2093 }, { "epoch": 0.06395846059865608, "grad_norm": 0.4283234775066376, "learning_rate": 4.94970276542178e-05, "loss": 4.4165, "step": 2094 }, { "epoch": 0.06398900427611484, "grad_norm": 0.4127075672149658, "learning_rate": 4.9496548764955896e-05, "loss": 4.3804, "step": 2095 }, { "epoch": 0.0640195479535736, "grad_norm": 0.41579708456993103, "learning_rate": 4.9496069650141674e-05, "loss": 4.4231, "step": 2096 }, { "epoch": 0.06405009163103238, "grad_norm": 0.4205564856529236, "learning_rate": 4.949559030977954e-05, "loss": 4.4864, "step": 2097 }, { "epoch": 0.06408063530849115, "grad_norm": 0.4160216152667999, "learning_rate": 4.949511074387391e-05, "loss": 4.4428, "step": 2098 }, { "epoch": 0.06411117898594991, "grad_norm": 0.4128498136997223, "learning_rate": 4.949463095242921e-05, "loss": 4.4493, "step": 2099 }, { "epoch": 0.06414172266340867, "grad_norm": 0.40321260690689087, "learning_rate": 4.9494150935449846e-05, "loss": 4.4749, "step": 2100 }, { "epoch": 0.06417226634086744, "grad_norm": 0.40863850712776184, "learning_rate": 4.9493670692940234e-05, "loss": 4.3245, "step": 2101 }, { "epoch": 0.0642028100183262, "grad_norm": 0.41996270418167114, "learning_rate": 4.9493190224904807e-05, "loss": 4.4045, "step": 2102 }, { "epoch": 0.06423335369578498, "grad_norm": 0.4072003662586212, "learning_rate": 4.949270953134798e-05, "loss": 4.4568, "step": 2103 }, { "epoch": 0.06426389737324374, "grad_norm": 0.4067898690700531, "learning_rate": 4.949222861227419e-05, "loss": 4.467, "step": 2104 }, { "epoch": 0.0642944410507025, "grad_norm": 0.4290608763694763, "learning_rate": 4.9491747467687854e-05, "loss": 4.4204, "step": 2105 }, { "epoch": 0.06432498472816127, "grad_norm": 0.4117540717124939, "learning_rate": 4.9491266097593414e-05, "loss": 4.388, "step": 2106 }, { "epoch": 0.06435552840562003, "grad_norm": 0.4127131998538971, "learning_rate": 4.949078450199528e-05, "loss": 4.3993, "step": 2107 }, { "epoch": 0.0643860720830788, "grad_norm": 0.4451899230480194, "learning_rate": 4.949030268089791e-05, "loss": 4.4957, "step": 2108 }, { "epoch": 0.06441661576053757, "grad_norm": 0.41802844405174255, "learning_rate": 4.948982063430574e-05, "loss": 4.4548, "step": 2109 }, { "epoch": 0.06444715943799634, "grad_norm": 0.4071800708770752, "learning_rate": 4.948933836222319e-05, "loss": 4.4902, "step": 2110 }, { "epoch": 0.0644777031154551, "grad_norm": 0.4356223940849304, "learning_rate": 4.948885586465471e-05, "loss": 4.3911, "step": 2111 }, { "epoch": 0.06450824679291386, "grad_norm": 0.4417966306209564, "learning_rate": 4.948837314160475e-05, "loss": 4.4745, "step": 2112 }, { "epoch": 0.06453879047037263, "grad_norm": 0.4225013852119446, "learning_rate": 4.948789019307775e-05, "loss": 4.4237, "step": 2113 }, { "epoch": 0.06456933414783139, "grad_norm": 0.44826775789260864, "learning_rate": 4.948740701907814e-05, "loss": 4.3045, "step": 2114 }, { "epoch": 0.06459987782529017, "grad_norm": 0.41924363374710083, "learning_rate": 4.948692361961039e-05, "loss": 4.5409, "step": 2115 }, { "epoch": 0.06463042150274893, "grad_norm": 0.4147401452064514, "learning_rate": 4.948643999467894e-05, "loss": 4.4445, "step": 2116 }, { "epoch": 0.0646609651802077, "grad_norm": 0.4184533953666687, "learning_rate": 4.948595614428826e-05, "loss": 4.4077, "step": 2117 }, { "epoch": 0.06469150885766646, "grad_norm": 0.42804837226867676, "learning_rate": 4.9485472068442785e-05, "loss": 4.519, "step": 2118 }, { "epoch": 0.06472205253512522, "grad_norm": 0.41622665524482727, "learning_rate": 4.948498776714698e-05, "loss": 4.3673, "step": 2119 }, { "epoch": 0.064752596212584, "grad_norm": 0.40889647603034973, "learning_rate": 4.94845032404053e-05, "loss": 4.461, "step": 2120 }, { "epoch": 0.06478313989004277, "grad_norm": 0.40960150957107544, "learning_rate": 4.948401848822222e-05, "loss": 4.4624, "step": 2121 }, { "epoch": 0.06481368356750153, "grad_norm": 0.4071058928966522, "learning_rate": 4.9483533510602186e-05, "loss": 4.5359, "step": 2122 }, { "epoch": 0.06484422724496029, "grad_norm": 0.41419583559036255, "learning_rate": 4.948304830754967e-05, "loss": 4.3899, "step": 2123 }, { "epoch": 0.06487477092241906, "grad_norm": 0.414141982793808, "learning_rate": 4.9482562879069145e-05, "loss": 4.4764, "step": 2124 }, { "epoch": 0.06490531459987782, "grad_norm": 0.4048827290534973, "learning_rate": 4.948207722516507e-05, "loss": 4.4643, "step": 2125 }, { "epoch": 0.0649358582773366, "grad_norm": 0.41952401399612427, "learning_rate": 4.9481591345841925e-05, "loss": 4.42, "step": 2126 }, { "epoch": 0.06496640195479536, "grad_norm": 0.4327563941478729, "learning_rate": 4.9481105241104185e-05, "loss": 4.4067, "step": 2127 }, { "epoch": 0.06499694563225412, "grad_norm": 0.4092366099357605, "learning_rate": 4.948061891095632e-05, "loss": 4.5097, "step": 2128 }, { "epoch": 0.06502748930971289, "grad_norm": 0.4080316126346588, "learning_rate": 4.948013235540281e-05, "loss": 4.4597, "step": 2129 }, { "epoch": 0.06505803298717165, "grad_norm": 0.4090469181537628, "learning_rate": 4.947964557444813e-05, "loss": 4.4467, "step": 2130 }, { "epoch": 0.06508857666463042, "grad_norm": 0.4175790250301361, "learning_rate": 4.9479158568096775e-05, "loss": 4.382, "step": 2131 }, { "epoch": 0.06511912034208919, "grad_norm": 0.4073866903781891, "learning_rate": 4.947867133635321e-05, "loss": 4.4719, "step": 2132 }, { "epoch": 0.06514966401954796, "grad_norm": 0.41378119587898254, "learning_rate": 4.947818387922194e-05, "loss": 4.4796, "step": 2133 }, { "epoch": 0.06518020769700672, "grad_norm": 0.40867888927459717, "learning_rate": 4.947769619670745e-05, "loss": 4.4147, "step": 2134 }, { "epoch": 0.06521075137446548, "grad_norm": 0.4303741753101349, "learning_rate": 4.9477208288814216e-05, "loss": 4.4388, "step": 2135 }, { "epoch": 0.06524129505192425, "grad_norm": 0.4078911542892456, "learning_rate": 4.9476720155546754e-05, "loss": 4.5079, "step": 2136 }, { "epoch": 0.06527183872938301, "grad_norm": 0.4152074456214905, "learning_rate": 4.947623179690953e-05, "loss": 4.4687, "step": 2137 }, { "epoch": 0.06530238240684179, "grad_norm": 0.4225131869316101, "learning_rate": 4.947574321290706e-05, "loss": 4.4621, "step": 2138 }, { "epoch": 0.06533292608430055, "grad_norm": 0.4084863066673279, "learning_rate": 4.947525440354384e-05, "loss": 4.4205, "step": 2139 }, { "epoch": 0.06536346976175932, "grad_norm": 0.42406144738197327, "learning_rate": 4.947476536882437e-05, "loss": 4.4336, "step": 2140 }, { "epoch": 0.06539401343921808, "grad_norm": 0.4096646308898926, "learning_rate": 4.947427610875315e-05, "loss": 4.4594, "step": 2141 }, { "epoch": 0.06542455711667684, "grad_norm": 0.4034583568572998, "learning_rate": 4.9473786623334686e-05, "loss": 4.4341, "step": 2142 }, { "epoch": 0.06545510079413562, "grad_norm": 0.4033152461051941, "learning_rate": 4.9473296912573485e-05, "loss": 4.4387, "step": 2143 }, { "epoch": 0.06548564447159438, "grad_norm": 0.41499853134155273, "learning_rate": 4.947280697647406e-05, "loss": 4.4423, "step": 2144 }, { "epoch": 0.06551618814905315, "grad_norm": 0.4110106825828552, "learning_rate": 4.947231681504091e-05, "loss": 4.4409, "step": 2145 }, { "epoch": 0.06554673182651191, "grad_norm": 0.39909231662750244, "learning_rate": 4.947182642827857e-05, "loss": 4.4755, "step": 2146 }, { "epoch": 0.06557727550397068, "grad_norm": 0.40923070907592773, "learning_rate": 4.947133581619153e-05, "loss": 4.504, "step": 2147 }, { "epoch": 0.06560781918142944, "grad_norm": 0.41513001918792725, "learning_rate": 4.947084497878432e-05, "loss": 4.4304, "step": 2148 }, { "epoch": 0.06563836285888822, "grad_norm": 0.4117802083492279, "learning_rate": 4.947035391606146e-05, "loss": 4.4063, "step": 2149 }, { "epoch": 0.06566890653634698, "grad_norm": 0.42294710874557495, "learning_rate": 4.946986262802748e-05, "loss": 4.4815, "step": 2150 }, { "epoch": 0.06569945021380574, "grad_norm": 0.42190003395080566, "learning_rate": 4.946937111468688e-05, "loss": 4.3222, "step": 2151 }, { "epoch": 0.06572999389126451, "grad_norm": 0.40086349844932556, "learning_rate": 4.9468879376044206e-05, "loss": 4.4675, "step": 2152 }, { "epoch": 0.06576053756872327, "grad_norm": 0.4077390134334564, "learning_rate": 4.946838741210398e-05, "loss": 4.3925, "step": 2153 }, { "epoch": 0.06579108124618203, "grad_norm": 0.41250887513160706, "learning_rate": 4.946789522287073e-05, "loss": 4.4986, "step": 2154 }, { "epoch": 0.06582162492364081, "grad_norm": 0.409906804561615, "learning_rate": 4.9467402808348985e-05, "loss": 4.448, "step": 2155 }, { "epoch": 0.06585216860109958, "grad_norm": 0.4082791209220886, "learning_rate": 4.9466910168543286e-05, "loss": 4.3813, "step": 2156 }, { "epoch": 0.06588271227855834, "grad_norm": 0.41707843542099, "learning_rate": 4.9466417303458164e-05, "loss": 4.4568, "step": 2157 }, { "epoch": 0.0659132559560171, "grad_norm": 0.40896761417388916, "learning_rate": 4.946592421309816e-05, "loss": 4.5292, "step": 2158 }, { "epoch": 0.06594379963347587, "grad_norm": 0.41928836703300476, "learning_rate": 4.946543089746781e-05, "loss": 4.4309, "step": 2159 }, { "epoch": 0.06597434331093463, "grad_norm": 0.41085946559906006, "learning_rate": 4.946493735657166e-05, "loss": 4.5005, "step": 2160 }, { "epoch": 0.06600488698839341, "grad_norm": 0.41144493222236633, "learning_rate": 4.946444359041425e-05, "loss": 4.5096, "step": 2161 }, { "epoch": 0.06603543066585217, "grad_norm": 0.41206929087638855, "learning_rate": 4.946394959900014e-05, "loss": 4.5136, "step": 2162 }, { "epoch": 0.06606597434331093, "grad_norm": 0.41956448554992676, "learning_rate": 4.9463455382333856e-05, "loss": 4.4141, "step": 2163 }, { "epoch": 0.0660965180207697, "grad_norm": 0.4192856550216675, "learning_rate": 4.9462960940419964e-05, "loss": 4.4278, "step": 2164 }, { "epoch": 0.06612706169822846, "grad_norm": 0.40377604961395264, "learning_rate": 4.946246627326302e-05, "loss": 4.4422, "step": 2165 }, { "epoch": 0.06615760537568724, "grad_norm": 0.395431786775589, "learning_rate": 4.9461971380867554e-05, "loss": 4.3457, "step": 2166 }, { "epoch": 0.066188149053146, "grad_norm": 0.4162684679031372, "learning_rate": 4.9461476263238163e-05, "loss": 4.4309, "step": 2167 }, { "epoch": 0.06621869273060477, "grad_norm": 0.4023705720901489, "learning_rate": 4.9460980920379365e-05, "loss": 4.3758, "step": 2168 }, { "epoch": 0.06624923640806353, "grad_norm": 0.4004048705101013, "learning_rate": 4.946048535229575e-05, "loss": 4.4315, "step": 2169 }, { "epoch": 0.0662797800855223, "grad_norm": 0.3998977839946747, "learning_rate": 4.945998955899186e-05, "loss": 4.4811, "step": 2170 }, { "epoch": 0.06631032376298106, "grad_norm": 0.4048939645290375, "learning_rate": 4.945949354047228e-05, "loss": 4.4748, "step": 2171 }, { "epoch": 0.06634086744043984, "grad_norm": 0.4098106324672699, "learning_rate": 4.945899729674156e-05, "loss": 4.4017, "step": 2172 }, { "epoch": 0.0663714111178986, "grad_norm": 0.39909812808036804, "learning_rate": 4.9458500827804284e-05, "loss": 4.3799, "step": 2173 }, { "epoch": 0.06640195479535736, "grad_norm": 0.4231869578361511, "learning_rate": 4.9458004133665015e-05, "loss": 4.3909, "step": 2174 }, { "epoch": 0.06643249847281613, "grad_norm": 0.4172084331512451, "learning_rate": 4.945750721432832e-05, "loss": 4.5039, "step": 2175 }, { "epoch": 0.06646304215027489, "grad_norm": 0.4034794867038727, "learning_rate": 4.945701006979878e-05, "loss": 4.3976, "step": 2176 }, { "epoch": 0.06649358582773365, "grad_norm": 0.4182693362236023, "learning_rate": 4.945651270008098e-05, "loss": 4.3659, "step": 2177 }, { "epoch": 0.06652412950519243, "grad_norm": 0.4029407799243927, "learning_rate": 4.945601510517949e-05, "loss": 4.4736, "step": 2178 }, { "epoch": 0.0665546731826512, "grad_norm": 0.4118330478668213, "learning_rate": 4.94555172850989e-05, "loss": 4.4081, "step": 2179 }, { "epoch": 0.06658521686010996, "grad_norm": 0.4095119833946228, "learning_rate": 4.945501923984379e-05, "loss": 4.4797, "step": 2180 }, { "epoch": 0.06661576053756872, "grad_norm": 0.41506427526474, "learning_rate": 4.945452096941874e-05, "loss": 4.5199, "step": 2181 }, { "epoch": 0.06664630421502749, "grad_norm": 0.42277097702026367, "learning_rate": 4.945402247382833e-05, "loss": 4.4105, "step": 2182 }, { "epoch": 0.06667684789248625, "grad_norm": 0.41327524185180664, "learning_rate": 4.945352375307718e-05, "loss": 4.4013, "step": 2183 }, { "epoch": 0.06670739156994503, "grad_norm": 0.4292905330657959, "learning_rate": 4.945302480716986e-05, "loss": 4.5243, "step": 2184 }, { "epoch": 0.06673793524740379, "grad_norm": 0.4176824986934662, "learning_rate": 4.9452525636110965e-05, "loss": 4.408, "step": 2185 }, { "epoch": 0.06676847892486255, "grad_norm": 0.4288008511066437, "learning_rate": 4.945202623990509e-05, "loss": 4.4782, "step": 2186 }, { "epoch": 0.06679902260232132, "grad_norm": 0.4253174364566803, "learning_rate": 4.9451526618556845e-05, "loss": 4.4235, "step": 2187 }, { "epoch": 0.06682956627978008, "grad_norm": 0.40951278805732727, "learning_rate": 4.945102677207082e-05, "loss": 4.4351, "step": 2188 }, { "epoch": 0.06686010995723884, "grad_norm": 0.41704338788986206, "learning_rate": 4.945052670045162e-05, "loss": 4.4258, "step": 2189 }, { "epoch": 0.06689065363469762, "grad_norm": 0.44027310609817505, "learning_rate": 4.945002640370385e-05, "loss": 4.4661, "step": 2190 }, { "epoch": 0.06692119731215639, "grad_norm": 0.41933637857437134, "learning_rate": 4.944952588183211e-05, "loss": 4.3858, "step": 2191 }, { "epoch": 0.06695174098961515, "grad_norm": 0.42112430930137634, "learning_rate": 4.944902513484103e-05, "loss": 4.4662, "step": 2192 }, { "epoch": 0.06698228466707391, "grad_norm": 0.42459636926651, "learning_rate": 4.944852416273519e-05, "loss": 4.417, "step": 2193 }, { "epoch": 0.06701282834453268, "grad_norm": 0.41406819224357605, "learning_rate": 4.944802296551923e-05, "loss": 4.3725, "step": 2194 }, { "epoch": 0.06704337202199145, "grad_norm": 0.4207044839859009, "learning_rate": 4.944752154319774e-05, "loss": 4.5069, "step": 2195 }, { "epoch": 0.06707391569945022, "grad_norm": 0.4155278205871582, "learning_rate": 4.944701989577535e-05, "loss": 4.4819, "step": 2196 }, { "epoch": 0.06710445937690898, "grad_norm": 0.4076477587223053, "learning_rate": 4.944651802325669e-05, "loss": 4.3441, "step": 2197 }, { "epoch": 0.06713500305436775, "grad_norm": 0.421983003616333, "learning_rate": 4.944601592564636e-05, "loss": 4.4581, "step": 2198 }, { "epoch": 0.06716554673182651, "grad_norm": 0.4189545512199402, "learning_rate": 4.9445513602948994e-05, "loss": 4.4226, "step": 2199 }, { "epoch": 0.06719609040928527, "grad_norm": 0.42191198468208313, "learning_rate": 4.944501105516922e-05, "loss": 4.4807, "step": 2200 }, { "epoch": 0.06722663408674405, "grad_norm": 0.3990602195262909, "learning_rate": 4.9444508282311656e-05, "loss": 4.4683, "step": 2201 }, { "epoch": 0.06725717776420281, "grad_norm": 0.40880879759788513, "learning_rate": 4.944400528438094e-05, "loss": 4.4345, "step": 2202 }, { "epoch": 0.06728772144166158, "grad_norm": 0.41852641105651855, "learning_rate": 4.94435020613817e-05, "loss": 4.4349, "step": 2203 }, { "epoch": 0.06731826511912034, "grad_norm": 0.41195613145828247, "learning_rate": 4.944299861331856e-05, "loss": 4.4361, "step": 2204 }, { "epoch": 0.0673488087965791, "grad_norm": 0.4106094539165497, "learning_rate": 4.944249494019617e-05, "loss": 4.3856, "step": 2205 }, { "epoch": 0.06737935247403787, "grad_norm": 0.41588613390922546, "learning_rate": 4.9441991042019164e-05, "loss": 4.4891, "step": 2206 }, { "epoch": 0.06740989615149665, "grad_norm": 0.4125690758228302, "learning_rate": 4.944148691879218e-05, "loss": 4.5268, "step": 2207 }, { "epoch": 0.06744043982895541, "grad_norm": 0.4179782569408417, "learning_rate": 4.9440982570519855e-05, "loss": 4.4508, "step": 2208 }, { "epoch": 0.06747098350641417, "grad_norm": 0.39884430170059204, "learning_rate": 4.9440477997206846e-05, "loss": 4.537, "step": 2209 }, { "epoch": 0.06750152718387294, "grad_norm": 0.41558194160461426, "learning_rate": 4.943997319885778e-05, "loss": 4.4651, "step": 2210 }, { "epoch": 0.0675320708613317, "grad_norm": 0.39650511741638184, "learning_rate": 4.943946817547732e-05, "loss": 4.3749, "step": 2211 }, { "epoch": 0.06756261453879046, "grad_norm": 0.4025038182735443, "learning_rate": 4.943896292707011e-05, "loss": 4.4111, "step": 2212 }, { "epoch": 0.06759315821624924, "grad_norm": 0.4204712212085724, "learning_rate": 4.943845745364081e-05, "loss": 4.3107, "step": 2213 }, { "epoch": 0.067623701893708, "grad_norm": 0.4078240394592285, "learning_rate": 4.943795175519405e-05, "loss": 4.4985, "step": 2214 }, { "epoch": 0.06765424557116677, "grad_norm": 0.4178171157836914, "learning_rate": 4.943744583173452e-05, "loss": 4.5148, "step": 2215 }, { "epoch": 0.06768478924862553, "grad_norm": 0.4165521264076233, "learning_rate": 4.943693968326685e-05, "loss": 4.4712, "step": 2216 }, { "epoch": 0.0677153329260843, "grad_norm": 0.4184548258781433, "learning_rate": 4.9436433309795724e-05, "loss": 4.5178, "step": 2217 }, { "epoch": 0.06774587660354307, "grad_norm": 0.40475979447364807, "learning_rate": 4.9435926711325784e-05, "loss": 4.3706, "step": 2218 }, { "epoch": 0.06777642028100184, "grad_norm": 0.424190878868103, "learning_rate": 4.94354198878617e-05, "loss": 4.4474, "step": 2219 }, { "epoch": 0.0678069639584606, "grad_norm": 0.41620245575904846, "learning_rate": 4.9434912839408156e-05, "loss": 4.4391, "step": 2220 }, { "epoch": 0.06783750763591936, "grad_norm": 0.4034965932369232, "learning_rate": 4.9434405565969786e-05, "loss": 4.3842, "step": 2221 }, { "epoch": 0.06786805131337813, "grad_norm": 0.40793895721435547, "learning_rate": 4.94338980675513e-05, "loss": 4.5281, "step": 2222 }, { "epoch": 0.06789859499083689, "grad_norm": 0.4021962583065033, "learning_rate": 4.9433390344157346e-05, "loss": 4.4159, "step": 2223 }, { "epoch": 0.06792913866829567, "grad_norm": 0.40744665265083313, "learning_rate": 4.94328823957926e-05, "loss": 4.4815, "step": 2224 }, { "epoch": 0.06795968234575443, "grad_norm": 0.41245195269584656, "learning_rate": 4.943237422246174e-05, "loss": 4.4898, "step": 2225 }, { "epoch": 0.0679902260232132, "grad_norm": 0.4145760238170624, "learning_rate": 4.943186582416946e-05, "loss": 4.4987, "step": 2226 }, { "epoch": 0.06802076970067196, "grad_norm": 0.4070971608161926, "learning_rate": 4.943135720092043e-05, "loss": 4.4278, "step": 2227 }, { "epoch": 0.06805131337813072, "grad_norm": 0.40836581587791443, "learning_rate": 4.9430848352719324e-05, "loss": 4.4009, "step": 2228 }, { "epoch": 0.06808185705558949, "grad_norm": 0.4161604642868042, "learning_rate": 4.9430339279570834e-05, "loss": 4.4504, "step": 2229 }, { "epoch": 0.06811240073304826, "grad_norm": 0.41853198409080505, "learning_rate": 4.942982998147966e-05, "loss": 4.4915, "step": 2230 }, { "epoch": 0.06814294441050703, "grad_norm": 0.4174474775791168, "learning_rate": 4.9429320458450477e-05, "loss": 4.4297, "step": 2231 }, { "epoch": 0.06817348808796579, "grad_norm": 0.4023926556110382, "learning_rate": 4.9428810710487974e-05, "loss": 4.4395, "step": 2232 }, { "epoch": 0.06820403176542456, "grad_norm": 0.4099077880382538, "learning_rate": 4.9428300737596855e-05, "loss": 4.4475, "step": 2233 }, { "epoch": 0.06823457544288332, "grad_norm": 0.41808491945266724, "learning_rate": 4.9427790539781816e-05, "loss": 4.5155, "step": 2234 }, { "epoch": 0.06826511912034208, "grad_norm": 0.4086846113204956, "learning_rate": 4.9427280117047545e-05, "loss": 4.3977, "step": 2235 }, { "epoch": 0.06829566279780086, "grad_norm": 0.39261507987976074, "learning_rate": 4.9426769469398745e-05, "loss": 4.4624, "step": 2236 }, { "epoch": 0.06832620647525962, "grad_norm": 0.40377557277679443, "learning_rate": 4.9426258596840126e-05, "loss": 4.4654, "step": 2237 }, { "epoch": 0.06835675015271839, "grad_norm": 0.43229469656944275, "learning_rate": 4.9425747499376384e-05, "loss": 4.3995, "step": 2238 }, { "epoch": 0.06838729383017715, "grad_norm": 0.4110877215862274, "learning_rate": 4.942523617701222e-05, "loss": 4.488, "step": 2239 }, { "epoch": 0.06841783750763591, "grad_norm": 0.41451478004455566, "learning_rate": 4.942472462975235e-05, "loss": 4.5414, "step": 2240 }, { "epoch": 0.06844838118509469, "grad_norm": 0.4136226177215576, "learning_rate": 4.9424212857601485e-05, "loss": 4.411, "step": 2241 }, { "epoch": 0.06847892486255346, "grad_norm": 0.39722153544425964, "learning_rate": 4.942370086056434e-05, "loss": 4.4061, "step": 2242 }, { "epoch": 0.06850946854001222, "grad_norm": 0.4235999286174774, "learning_rate": 4.9423188638645616e-05, "loss": 4.4205, "step": 2243 }, { "epoch": 0.06854001221747098, "grad_norm": 0.4221334755420685, "learning_rate": 4.942267619185004e-05, "loss": 4.4847, "step": 2244 }, { "epoch": 0.06857055589492975, "grad_norm": 0.3960389494895935, "learning_rate": 4.942216352018232e-05, "loss": 4.4061, "step": 2245 }, { "epoch": 0.06860109957238851, "grad_norm": 0.4129825830459595, "learning_rate": 4.9421650623647196e-05, "loss": 4.4881, "step": 2246 }, { "epoch": 0.06863164324984729, "grad_norm": 0.43517357110977173, "learning_rate": 4.942113750224937e-05, "loss": 4.5067, "step": 2247 }, { "epoch": 0.06866218692730605, "grad_norm": 0.413751482963562, "learning_rate": 4.942062415599358e-05, "loss": 4.3561, "step": 2248 }, { "epoch": 0.06869273060476482, "grad_norm": 0.40592262148857117, "learning_rate": 4.942011058488454e-05, "loss": 4.432, "step": 2249 }, { "epoch": 0.06872327428222358, "grad_norm": 0.409025102853775, "learning_rate": 4.9419596788926995e-05, "loss": 4.4391, "step": 2250 }, { "epoch": 0.06875381795968234, "grad_norm": 0.41096827387809753, "learning_rate": 4.941908276812566e-05, "loss": 4.5049, "step": 2251 }, { "epoch": 0.0687843616371411, "grad_norm": 0.41173237562179565, "learning_rate": 4.941856852248528e-05, "loss": 4.4323, "step": 2252 }, { "epoch": 0.06881490531459988, "grad_norm": 0.4202759265899658, "learning_rate": 4.941805405201059e-05, "loss": 4.4974, "step": 2253 }, { "epoch": 0.06884544899205865, "grad_norm": 0.41140520572662354, "learning_rate": 4.941753935670631e-05, "loss": 4.3369, "step": 2254 }, { "epoch": 0.06887599266951741, "grad_norm": 0.4218631982803345, "learning_rate": 4.94170244365772e-05, "loss": 4.4648, "step": 2255 }, { "epoch": 0.06890653634697617, "grad_norm": 0.4067656695842743, "learning_rate": 4.9416509291627984e-05, "loss": 4.4532, "step": 2256 }, { "epoch": 0.06893708002443494, "grad_norm": 0.41336530447006226, "learning_rate": 4.941599392186342e-05, "loss": 4.4487, "step": 2257 }, { "epoch": 0.0689676237018937, "grad_norm": 0.405641108751297, "learning_rate": 4.941547832728824e-05, "loss": 4.5513, "step": 2258 }, { "epoch": 0.06899816737935248, "grad_norm": 0.40160971879959106, "learning_rate": 4.94149625079072e-05, "loss": 4.4005, "step": 2259 }, { "epoch": 0.06902871105681124, "grad_norm": 0.4111149311065674, "learning_rate": 4.941444646372505e-05, "loss": 4.4977, "step": 2260 }, { "epoch": 0.06905925473427, "grad_norm": 0.406473308801651, "learning_rate": 4.9413930194746536e-05, "loss": 4.4952, "step": 2261 }, { "epoch": 0.06908979841172877, "grad_norm": 0.41531068086624146, "learning_rate": 4.941341370097642e-05, "loss": 4.4199, "step": 2262 }, { "epoch": 0.06912034208918753, "grad_norm": 0.4091484546661377, "learning_rate": 4.9412896982419446e-05, "loss": 4.4095, "step": 2263 }, { "epoch": 0.06915088576664631, "grad_norm": 0.3969113230705261, "learning_rate": 4.941238003908037e-05, "loss": 4.3798, "step": 2264 }, { "epoch": 0.06918142944410507, "grad_norm": 0.4110895097255707, "learning_rate": 4.9411862870963976e-05, "loss": 4.4713, "step": 2265 }, { "epoch": 0.06921197312156384, "grad_norm": 0.4031120538711548, "learning_rate": 4.9411345478075e-05, "loss": 4.3763, "step": 2266 }, { "epoch": 0.0692425167990226, "grad_norm": 0.41364413499832153, "learning_rate": 4.941082786041822e-05, "loss": 4.3977, "step": 2267 }, { "epoch": 0.06927306047648137, "grad_norm": 0.41394221782684326, "learning_rate": 4.94103100179984e-05, "loss": 4.5533, "step": 2268 }, { "epoch": 0.06930360415394013, "grad_norm": 0.4193447530269623, "learning_rate": 4.940979195082029e-05, "loss": 4.5553, "step": 2269 }, { "epoch": 0.0693341478313989, "grad_norm": 0.40476924180984497, "learning_rate": 4.940927365888869e-05, "loss": 4.3375, "step": 2270 }, { "epoch": 0.06936469150885767, "grad_norm": 0.40809133648872375, "learning_rate": 4.940875514220835e-05, "loss": 4.5033, "step": 2271 }, { "epoch": 0.06939523518631643, "grad_norm": 0.3940771520137787, "learning_rate": 4.940823640078405e-05, "loss": 4.4763, "step": 2272 }, { "epoch": 0.0694257788637752, "grad_norm": 0.41333770751953125, "learning_rate": 4.940771743462057e-05, "loss": 4.492, "step": 2273 }, { "epoch": 0.06945632254123396, "grad_norm": 0.4126693606376648, "learning_rate": 4.940719824372269e-05, "loss": 4.4012, "step": 2274 }, { "epoch": 0.06948686621869272, "grad_norm": 0.41069620847702026, "learning_rate": 4.940667882809519e-05, "loss": 4.3728, "step": 2275 }, { "epoch": 0.0695174098961515, "grad_norm": 0.4089561402797699, "learning_rate": 4.940615918774284e-05, "loss": 4.5, "step": 2276 }, { "epoch": 0.06954795357361027, "grad_norm": 0.41328129172325134, "learning_rate": 4.940563932267044e-05, "loss": 4.4845, "step": 2277 }, { "epoch": 0.06957849725106903, "grad_norm": 0.40974026918411255, "learning_rate": 4.940511923288277e-05, "loss": 4.4422, "step": 2278 }, { "epoch": 0.0696090409285278, "grad_norm": 0.3996257185935974, "learning_rate": 4.9404598918384617e-05, "loss": 4.507, "step": 2279 }, { "epoch": 0.06963958460598656, "grad_norm": 0.3999396860599518, "learning_rate": 4.9404078379180774e-05, "loss": 4.4157, "step": 2280 }, { "epoch": 0.06967012828344532, "grad_norm": 0.41262054443359375, "learning_rate": 4.940355761527603e-05, "loss": 4.4505, "step": 2281 }, { "epoch": 0.0697006719609041, "grad_norm": 0.4076370894908905, "learning_rate": 4.940303662667519e-05, "loss": 4.4691, "step": 2282 }, { "epoch": 0.06973121563836286, "grad_norm": 0.4154304265975952, "learning_rate": 4.940251541338305e-05, "loss": 4.4595, "step": 2283 }, { "epoch": 0.06976175931582163, "grad_norm": 0.4148658514022827, "learning_rate": 4.9401993975404395e-05, "loss": 4.4594, "step": 2284 }, { "epoch": 0.06979230299328039, "grad_norm": 0.413016676902771, "learning_rate": 4.9401472312744034e-05, "loss": 4.478, "step": 2285 }, { "epoch": 0.06982284667073915, "grad_norm": 0.4302217662334442, "learning_rate": 4.940095042540678e-05, "loss": 4.3835, "step": 2286 }, { "epoch": 0.06985339034819792, "grad_norm": 0.40815305709838867, "learning_rate": 4.9400428313397426e-05, "loss": 4.4556, "step": 2287 }, { "epoch": 0.0698839340256567, "grad_norm": 0.4210585653781891, "learning_rate": 4.939990597672078e-05, "loss": 4.4229, "step": 2288 }, { "epoch": 0.06991447770311546, "grad_norm": 0.3954309821128845, "learning_rate": 4.9399383415381664e-05, "loss": 4.4361, "step": 2289 }, { "epoch": 0.06994502138057422, "grad_norm": 0.41536036133766174, "learning_rate": 4.9398860629384866e-05, "loss": 4.3614, "step": 2290 }, { "epoch": 0.06997556505803298, "grad_norm": 0.4139772951602936, "learning_rate": 4.9398337618735225e-05, "loss": 4.4714, "step": 2291 }, { "epoch": 0.07000610873549175, "grad_norm": 0.4199586808681488, "learning_rate": 4.939781438343753e-05, "loss": 4.3435, "step": 2292 }, { "epoch": 0.07003665241295053, "grad_norm": 0.4124809801578522, "learning_rate": 4.939729092349663e-05, "loss": 4.3824, "step": 2293 }, { "epoch": 0.07006719609040929, "grad_norm": 0.3933543264865875, "learning_rate": 4.939676723891733e-05, "loss": 4.3437, "step": 2294 }, { "epoch": 0.07009773976786805, "grad_norm": 0.4170548915863037, "learning_rate": 4.939624332970444e-05, "loss": 4.4427, "step": 2295 }, { "epoch": 0.07012828344532682, "grad_norm": 0.41238483786582947, "learning_rate": 4.93957191958628e-05, "loss": 4.3339, "step": 2296 }, { "epoch": 0.07015882712278558, "grad_norm": 0.40275296568870544, "learning_rate": 4.939519483739723e-05, "loss": 4.4558, "step": 2297 }, { "epoch": 0.07018937080024434, "grad_norm": 0.40965721011161804, "learning_rate": 4.939467025431255e-05, "loss": 4.4815, "step": 2298 }, { "epoch": 0.07021991447770312, "grad_norm": 0.4072987735271454, "learning_rate": 4.9394145446613604e-05, "loss": 4.369, "step": 2299 }, { "epoch": 0.07025045815516189, "grad_norm": 0.40808019042015076, "learning_rate": 4.939362041430522e-05, "loss": 4.3373, "step": 2300 }, { "epoch": 0.07028100183262065, "grad_norm": 0.4153602123260498, "learning_rate": 4.939309515739223e-05, "loss": 4.4863, "step": 2301 }, { "epoch": 0.07031154551007941, "grad_norm": 0.399604856967926, "learning_rate": 4.939256967587947e-05, "loss": 4.4391, "step": 2302 }, { "epoch": 0.07034208918753818, "grad_norm": 0.40803930163383484, "learning_rate": 4.9392043969771784e-05, "loss": 4.4177, "step": 2303 }, { "epoch": 0.07037263286499694, "grad_norm": 0.4078657329082489, "learning_rate": 4.939151803907401e-05, "loss": 4.4782, "step": 2304 }, { "epoch": 0.07040317654245572, "grad_norm": 0.4240778684616089, "learning_rate": 4.939099188379098e-05, "loss": 4.4714, "step": 2305 }, { "epoch": 0.07043372021991448, "grad_norm": 0.4006946086883545, "learning_rate": 4.939046550392755e-05, "loss": 4.4264, "step": 2306 }, { "epoch": 0.07046426389737324, "grad_norm": 0.43422794342041016, "learning_rate": 4.938993889948857e-05, "loss": 4.4035, "step": 2307 }, { "epoch": 0.07049480757483201, "grad_norm": 0.415679931640625, "learning_rate": 4.938941207047888e-05, "loss": 4.4269, "step": 2308 }, { "epoch": 0.07052535125229077, "grad_norm": 0.40179455280303955, "learning_rate": 4.938888501690333e-05, "loss": 4.4006, "step": 2309 }, { "epoch": 0.07055589492974954, "grad_norm": 0.4115680456161499, "learning_rate": 4.938835773876678e-05, "loss": 4.4106, "step": 2310 }, { "epoch": 0.07058643860720831, "grad_norm": 0.4113300144672394, "learning_rate": 4.938783023607407e-05, "loss": 4.3894, "step": 2311 }, { "epoch": 0.07061698228466708, "grad_norm": 0.419704794883728, "learning_rate": 4.938730250883008e-05, "loss": 4.4906, "step": 2312 }, { "epoch": 0.07064752596212584, "grad_norm": 0.40976935625076294, "learning_rate": 4.938677455703965e-05, "loss": 4.4675, "step": 2313 }, { "epoch": 0.0706780696395846, "grad_norm": 0.4044290781021118, "learning_rate": 4.938624638070765e-05, "loss": 4.4844, "step": 2314 }, { "epoch": 0.07070861331704337, "grad_norm": 0.4195289611816406, "learning_rate": 4.938571797983894e-05, "loss": 4.4883, "step": 2315 }, { "epoch": 0.07073915699450214, "grad_norm": 0.4126370847225189, "learning_rate": 4.9385189354438395e-05, "loss": 4.4781, "step": 2316 }, { "epoch": 0.07076970067196091, "grad_norm": 0.4158046841621399, "learning_rate": 4.938466050451087e-05, "loss": 4.5192, "step": 2317 }, { "epoch": 0.07080024434941967, "grad_norm": 0.42054691910743713, "learning_rate": 4.938413143006123e-05, "loss": 4.5409, "step": 2318 }, { "epoch": 0.07083078802687844, "grad_norm": 0.4079258441925049, "learning_rate": 4.9383602131094366e-05, "loss": 4.5034, "step": 2319 }, { "epoch": 0.0708613317043372, "grad_norm": 0.4009108245372772, "learning_rate": 4.9383072607615136e-05, "loss": 4.4562, "step": 2320 }, { "epoch": 0.07089187538179596, "grad_norm": 0.4248134195804596, "learning_rate": 4.938254285962842e-05, "loss": 4.3847, "step": 2321 }, { "epoch": 0.07092241905925474, "grad_norm": 0.4323190450668335, "learning_rate": 4.938201288713909e-05, "loss": 4.5066, "step": 2322 }, { "epoch": 0.0709529627367135, "grad_norm": 0.4167052209377289, "learning_rate": 4.9381482690152036e-05, "loss": 4.3799, "step": 2323 }, { "epoch": 0.07098350641417227, "grad_norm": 0.4060290455818176, "learning_rate": 4.9380952268672145e-05, "loss": 4.4387, "step": 2324 }, { "epoch": 0.07101405009163103, "grad_norm": 0.4075753092765808, "learning_rate": 4.938042162270428e-05, "loss": 4.3942, "step": 2325 }, { "epoch": 0.0710445937690898, "grad_norm": 0.42431309819221497, "learning_rate": 4.937989075225334e-05, "loss": 4.37, "step": 2326 }, { "epoch": 0.07107513744654856, "grad_norm": 0.4203122556209564, "learning_rate": 4.937935965732421e-05, "loss": 4.3588, "step": 2327 }, { "epoch": 0.07110568112400734, "grad_norm": 0.40573039650917053, "learning_rate": 4.937882833792178e-05, "loss": 4.3985, "step": 2328 }, { "epoch": 0.0711362248014661, "grad_norm": 0.4202752113342285, "learning_rate": 4.937829679405095e-05, "loss": 4.4323, "step": 2329 }, { "epoch": 0.07116676847892486, "grad_norm": 0.42453548312187195, "learning_rate": 4.9377765025716596e-05, "loss": 4.438, "step": 2330 }, { "epoch": 0.07119731215638363, "grad_norm": 0.42143669724464417, "learning_rate": 4.937723303292363e-05, "loss": 4.4172, "step": 2331 }, { "epoch": 0.07122785583384239, "grad_norm": 0.4199756681919098, "learning_rate": 4.937670081567695e-05, "loss": 4.4536, "step": 2332 }, { "epoch": 0.07125839951130115, "grad_norm": 0.40171733498573303, "learning_rate": 4.9376168373981454e-05, "loss": 4.4797, "step": 2333 }, { "epoch": 0.07128894318875993, "grad_norm": 0.41558507084846497, "learning_rate": 4.937563570784204e-05, "loss": 4.4769, "step": 2334 }, { "epoch": 0.0713194868662187, "grad_norm": 0.4195444583892822, "learning_rate": 4.937510281726361e-05, "loss": 4.4565, "step": 2335 }, { "epoch": 0.07135003054367746, "grad_norm": 0.4063006639480591, "learning_rate": 4.9374569702251085e-05, "loss": 4.394, "step": 2336 }, { "epoch": 0.07138057422113622, "grad_norm": 0.43032506108283997, "learning_rate": 4.9374036362809355e-05, "loss": 4.4279, "step": 2337 }, { "epoch": 0.07141111789859499, "grad_norm": 0.4019707143306732, "learning_rate": 4.937350279894335e-05, "loss": 4.3901, "step": 2338 }, { "epoch": 0.07144166157605376, "grad_norm": 0.4026373326778412, "learning_rate": 4.937296901065796e-05, "loss": 4.4615, "step": 2339 }, { "epoch": 0.07147220525351253, "grad_norm": 0.4207073748111725, "learning_rate": 4.9372434997958126e-05, "loss": 4.4942, "step": 2340 }, { "epoch": 0.07150274893097129, "grad_norm": 0.41142070293426514, "learning_rate": 4.937190076084874e-05, "loss": 4.3813, "step": 2341 }, { "epoch": 0.07153329260843005, "grad_norm": 0.4173298478126526, "learning_rate": 4.937136629933474e-05, "loss": 4.4886, "step": 2342 }, { "epoch": 0.07156383628588882, "grad_norm": 0.4103105068206787, "learning_rate": 4.937083161342104e-05, "loss": 4.3233, "step": 2343 }, { "epoch": 0.07159437996334758, "grad_norm": 0.4104990065097809, "learning_rate": 4.9370296703112576e-05, "loss": 4.4366, "step": 2344 }, { "epoch": 0.07162492364080636, "grad_norm": 0.4230630099773407, "learning_rate": 4.936976156841424e-05, "loss": 4.4735, "step": 2345 }, { "epoch": 0.07165546731826512, "grad_norm": 0.43112632632255554, "learning_rate": 4.9369226209330985e-05, "loss": 4.4916, "step": 2346 }, { "epoch": 0.07168601099572389, "grad_norm": 0.4189693331718445, "learning_rate": 4.936869062586774e-05, "loss": 4.4251, "step": 2347 }, { "epoch": 0.07171655467318265, "grad_norm": 0.41853204369544983, "learning_rate": 4.936815481802943e-05, "loss": 4.4734, "step": 2348 }, { "epoch": 0.07174709835064141, "grad_norm": 0.41162577271461487, "learning_rate": 4.936761878582099e-05, "loss": 4.3907, "step": 2349 }, { "epoch": 0.07177764202810018, "grad_norm": 0.420280396938324, "learning_rate": 4.936708252924735e-05, "loss": 4.4733, "step": 2350 }, { "epoch": 0.07180818570555896, "grad_norm": 0.39862874150276184, "learning_rate": 4.936654604831345e-05, "loss": 4.4455, "step": 2351 }, { "epoch": 0.07183872938301772, "grad_norm": 0.4116351902484894, "learning_rate": 4.9366009343024247e-05, "loss": 4.4794, "step": 2352 }, { "epoch": 0.07186927306047648, "grad_norm": 0.42049649357795715, "learning_rate": 4.9365472413384655e-05, "loss": 4.5237, "step": 2353 }, { "epoch": 0.07189981673793525, "grad_norm": 0.43992555141448975, "learning_rate": 4.9364935259399633e-05, "loss": 4.4715, "step": 2354 }, { "epoch": 0.07193036041539401, "grad_norm": 0.4065140187740326, "learning_rate": 4.9364397881074134e-05, "loss": 4.4153, "step": 2355 }, { "epoch": 0.07196090409285277, "grad_norm": 0.4037289619445801, "learning_rate": 4.936386027841309e-05, "loss": 4.4308, "step": 2356 }, { "epoch": 0.07199144777031155, "grad_norm": 0.3985872268676758, "learning_rate": 4.9363322451421455e-05, "loss": 4.3498, "step": 2357 }, { "epoch": 0.07202199144777031, "grad_norm": 0.4210902154445648, "learning_rate": 4.936278440010419e-05, "loss": 4.5145, "step": 2358 }, { "epoch": 0.07205253512522908, "grad_norm": 0.40072503685951233, "learning_rate": 4.936224612446624e-05, "loss": 4.4932, "step": 2359 }, { "epoch": 0.07208307880268784, "grad_norm": 0.40698137879371643, "learning_rate": 4.936170762451256e-05, "loss": 4.4743, "step": 2360 }, { "epoch": 0.0721136224801466, "grad_norm": 0.4129365384578705, "learning_rate": 4.9361168900248114e-05, "loss": 4.4617, "step": 2361 }, { "epoch": 0.07214416615760537, "grad_norm": 0.4215279221534729, "learning_rate": 4.9360629951677866e-05, "loss": 4.3179, "step": 2362 }, { "epoch": 0.07217470983506415, "grad_norm": 0.4052811861038208, "learning_rate": 4.936009077880677e-05, "loss": 4.4008, "step": 2363 }, { "epoch": 0.07220525351252291, "grad_norm": 0.4102719724178314, "learning_rate": 4.935955138163979e-05, "loss": 4.5123, "step": 2364 }, { "epoch": 0.07223579718998167, "grad_norm": 0.41446030139923096, "learning_rate": 4.9359011760181905e-05, "loss": 4.4285, "step": 2365 }, { "epoch": 0.07226634086744044, "grad_norm": 0.42273515462875366, "learning_rate": 4.9358471914438067e-05, "loss": 4.4088, "step": 2366 }, { "epoch": 0.0722968845448992, "grad_norm": 0.4154093265533447, "learning_rate": 4.935793184441325e-05, "loss": 4.4257, "step": 2367 }, { "epoch": 0.07232742822235798, "grad_norm": 0.41466039419174194, "learning_rate": 4.9357391550112444e-05, "loss": 4.4533, "step": 2368 }, { "epoch": 0.07235797189981674, "grad_norm": 0.4089548885822296, "learning_rate": 4.93568510315406e-05, "loss": 4.4491, "step": 2369 }, { "epoch": 0.0723885155772755, "grad_norm": 0.4278721213340759, "learning_rate": 4.935631028870271e-05, "loss": 4.3232, "step": 2370 }, { "epoch": 0.07241905925473427, "grad_norm": 0.4059169292449951, "learning_rate": 4.9355769321603754e-05, "loss": 4.4418, "step": 2371 }, { "epoch": 0.07244960293219303, "grad_norm": 0.4191809892654419, "learning_rate": 4.93552281302487e-05, "loss": 4.3431, "step": 2372 }, { "epoch": 0.0724801466096518, "grad_norm": 0.41605880856513977, "learning_rate": 4.9354686714642536e-05, "loss": 4.482, "step": 2373 }, { "epoch": 0.07251069028711057, "grad_norm": 0.4099518656730652, "learning_rate": 4.935414507479025e-05, "loss": 4.4081, "step": 2374 }, { "epoch": 0.07254123396456934, "grad_norm": 0.4161764085292816, "learning_rate": 4.935360321069683e-05, "loss": 4.4267, "step": 2375 }, { "epoch": 0.0725717776420281, "grad_norm": 0.4146297872066498, "learning_rate": 4.935306112236727e-05, "loss": 4.4014, "step": 2376 }, { "epoch": 0.07260232131948686, "grad_norm": 0.40238574147224426, "learning_rate": 4.935251880980655e-05, "loss": 4.4228, "step": 2377 }, { "epoch": 0.07263286499694563, "grad_norm": 0.4073331654071808, "learning_rate": 4.935197627301967e-05, "loss": 4.4454, "step": 2378 }, { "epoch": 0.07266340867440439, "grad_norm": 0.419045090675354, "learning_rate": 4.935143351201162e-05, "loss": 4.4491, "step": 2379 }, { "epoch": 0.07269395235186317, "grad_norm": 0.4043416678905487, "learning_rate": 4.935089052678741e-05, "loss": 4.3718, "step": 2380 }, { "epoch": 0.07272449602932193, "grad_norm": 0.4089053273200989, "learning_rate": 4.9350347317352016e-05, "loss": 4.5042, "step": 2381 }, { "epoch": 0.0727550397067807, "grad_norm": 0.4133273661136627, "learning_rate": 4.9349803883710464e-05, "loss": 4.422, "step": 2382 }, { "epoch": 0.07278558338423946, "grad_norm": 0.3973572552204132, "learning_rate": 4.9349260225867755e-05, "loss": 4.4289, "step": 2383 }, { "epoch": 0.07281612706169822, "grad_norm": 0.42167577147483826, "learning_rate": 4.934871634382888e-05, "loss": 4.4238, "step": 2384 }, { "epoch": 0.07284667073915699, "grad_norm": 0.4252791702747345, "learning_rate": 4.9348172237598854e-05, "loss": 4.3787, "step": 2385 }, { "epoch": 0.07287721441661577, "grad_norm": 0.4101259708404541, "learning_rate": 4.934762790718269e-05, "loss": 4.3934, "step": 2386 }, { "epoch": 0.07290775809407453, "grad_norm": 0.4208475649356842, "learning_rate": 4.93470833525854e-05, "loss": 4.4882, "step": 2387 }, { "epoch": 0.07293830177153329, "grad_norm": 0.396595299243927, "learning_rate": 4.9346538573811984e-05, "loss": 4.4104, "step": 2388 }, { "epoch": 0.07296884544899206, "grad_norm": 0.4195277988910675, "learning_rate": 4.934599357086748e-05, "loss": 4.4654, "step": 2389 }, { "epoch": 0.07299938912645082, "grad_norm": 0.4041915535926819, "learning_rate": 4.934544834375689e-05, "loss": 4.4586, "step": 2390 }, { "epoch": 0.0730299328039096, "grad_norm": 0.4106425940990448, "learning_rate": 4.934490289248525e-05, "loss": 4.4787, "step": 2391 }, { "epoch": 0.07306047648136836, "grad_norm": 0.39930790662765503, "learning_rate": 4.934435721705757e-05, "loss": 4.4141, "step": 2392 }, { "epoch": 0.07309102015882712, "grad_norm": 0.407382071018219, "learning_rate": 4.934381131747887e-05, "loss": 4.3394, "step": 2393 }, { "epoch": 0.07312156383628589, "grad_norm": 0.4080624580383301, "learning_rate": 4.934326519375418e-05, "loss": 4.4062, "step": 2394 }, { "epoch": 0.07315210751374465, "grad_norm": 0.40385791659355164, "learning_rate": 4.934271884588854e-05, "loss": 4.4213, "step": 2395 }, { "epoch": 0.07318265119120342, "grad_norm": 0.40999966859817505, "learning_rate": 4.9342172273886965e-05, "loss": 4.484, "step": 2396 }, { "epoch": 0.07321319486866219, "grad_norm": 0.4294677972793579, "learning_rate": 4.93416254777545e-05, "loss": 4.4028, "step": 2397 }, { "epoch": 0.07324373854612096, "grad_norm": 0.4295858144760132, "learning_rate": 4.934107845749617e-05, "loss": 4.4692, "step": 2398 }, { "epoch": 0.07327428222357972, "grad_norm": 0.4021710455417633, "learning_rate": 4.934053121311702e-05, "loss": 4.4582, "step": 2399 }, { "epoch": 0.07330482590103848, "grad_norm": 0.4116922914981842, "learning_rate": 4.933998374462208e-05, "loss": 4.3987, "step": 2400 }, { "epoch": 0.07333536957849725, "grad_norm": 0.41163745522499084, "learning_rate": 4.93394360520164e-05, "loss": 4.3736, "step": 2401 }, { "epoch": 0.07336591325595601, "grad_norm": 0.42307183146476746, "learning_rate": 4.933888813530501e-05, "loss": 4.4586, "step": 2402 }, { "epoch": 0.07339645693341479, "grad_norm": 0.4010006785392761, "learning_rate": 4.933833999449297e-05, "loss": 4.4245, "step": 2403 }, { "epoch": 0.07342700061087355, "grad_norm": 0.42526480555534363, "learning_rate": 4.9337791629585315e-05, "loss": 4.3748, "step": 2404 }, { "epoch": 0.07345754428833232, "grad_norm": 0.40639838576316833, "learning_rate": 4.9337243040587105e-05, "loss": 4.3843, "step": 2405 }, { "epoch": 0.07348808796579108, "grad_norm": 0.41746169328689575, "learning_rate": 4.933669422750339e-05, "loss": 4.4834, "step": 2406 }, { "epoch": 0.07351863164324984, "grad_norm": 0.4038412272930145, "learning_rate": 4.9336145190339206e-05, "loss": 4.3628, "step": 2407 }, { "epoch": 0.0735491753207086, "grad_norm": 0.39772501587867737, "learning_rate": 4.933559592909963e-05, "loss": 4.434, "step": 2408 }, { "epoch": 0.07357971899816738, "grad_norm": 0.41546908020973206, "learning_rate": 4.93350464437897e-05, "loss": 4.4388, "step": 2409 }, { "epoch": 0.07361026267562615, "grad_norm": 0.39224937558174133, "learning_rate": 4.933449673441449e-05, "loss": 4.4359, "step": 2410 }, { "epoch": 0.07364080635308491, "grad_norm": 0.41000398993492126, "learning_rate": 4.9333946800979066e-05, "loss": 4.4693, "step": 2411 }, { "epoch": 0.07367135003054368, "grad_norm": 0.39279088377952576, "learning_rate": 4.933339664348847e-05, "loss": 4.4474, "step": 2412 }, { "epoch": 0.07370189370800244, "grad_norm": 0.3989960253238678, "learning_rate": 4.933284626194779e-05, "loss": 4.3763, "step": 2413 }, { "epoch": 0.07373243738546122, "grad_norm": 0.4058275520801544, "learning_rate": 4.9332295656362085e-05, "loss": 4.4225, "step": 2414 }, { "epoch": 0.07376298106291998, "grad_norm": 0.4053497314453125, "learning_rate": 4.933174482673641e-05, "loss": 4.2951, "step": 2415 }, { "epoch": 0.07379352474037874, "grad_norm": 0.4059452712535858, "learning_rate": 4.933119377307586e-05, "loss": 4.4167, "step": 2416 }, { "epoch": 0.07382406841783751, "grad_norm": 0.408789724111557, "learning_rate": 4.933064249538549e-05, "loss": 4.4933, "step": 2417 }, { "epoch": 0.07385461209529627, "grad_norm": 0.40647175908088684, "learning_rate": 4.93300909936704e-05, "loss": 4.4623, "step": 2418 }, { "epoch": 0.07388515577275503, "grad_norm": 0.40814200043678284, "learning_rate": 4.932953926793564e-05, "loss": 4.5051, "step": 2419 }, { "epoch": 0.07391569945021381, "grad_norm": 0.40188080072402954, "learning_rate": 4.932898731818631e-05, "loss": 4.4466, "step": 2420 }, { "epoch": 0.07394624312767258, "grad_norm": 0.42025288939476013, "learning_rate": 4.932843514442749e-05, "loss": 4.5073, "step": 2421 }, { "epoch": 0.07397678680513134, "grad_norm": 0.4130689203739166, "learning_rate": 4.932788274666424e-05, "loss": 4.3318, "step": 2422 }, { "epoch": 0.0740073304825901, "grad_norm": 0.4250946640968323, "learning_rate": 4.932733012490168e-05, "loss": 4.4341, "step": 2423 }, { "epoch": 0.07403787416004887, "grad_norm": 0.42314761877059937, "learning_rate": 4.9326777279144885e-05, "loss": 4.3833, "step": 2424 }, { "epoch": 0.07406841783750763, "grad_norm": 0.4020572006702423, "learning_rate": 4.932622420939894e-05, "loss": 4.4127, "step": 2425 }, { "epoch": 0.07409896151496641, "grad_norm": 0.4105934500694275, "learning_rate": 4.932567091566894e-05, "loss": 4.3187, "step": 2426 }, { "epoch": 0.07412950519242517, "grad_norm": 0.42503073811531067, "learning_rate": 4.9325117397959985e-05, "loss": 4.4849, "step": 2427 }, { "epoch": 0.07416004886988393, "grad_norm": 0.4072922468185425, "learning_rate": 4.932456365627717e-05, "loss": 4.4546, "step": 2428 }, { "epoch": 0.0741905925473427, "grad_norm": 0.4049052298069, "learning_rate": 4.9324009690625585e-05, "loss": 4.4271, "step": 2429 }, { "epoch": 0.07422113622480146, "grad_norm": 0.4219745099544525, "learning_rate": 4.932345550101033e-05, "loss": 4.5111, "step": 2430 }, { "epoch": 0.07425167990226023, "grad_norm": 0.4142187833786011, "learning_rate": 4.9322901087436525e-05, "loss": 4.4808, "step": 2431 }, { "epoch": 0.074282223579719, "grad_norm": 0.4192129969596863, "learning_rate": 4.932234644990926e-05, "loss": 4.4683, "step": 2432 }, { "epoch": 0.07431276725717777, "grad_norm": 0.41923245787620544, "learning_rate": 4.9321791588433654e-05, "loss": 4.4461, "step": 2433 }, { "epoch": 0.07434331093463653, "grad_norm": 0.43503671884536743, "learning_rate": 4.9321236503014795e-05, "loss": 4.5469, "step": 2434 }, { "epoch": 0.0743738546120953, "grad_norm": 0.42089352011680603, "learning_rate": 4.932068119365781e-05, "loss": 4.4663, "step": 2435 }, { "epoch": 0.07440439828955406, "grad_norm": 0.420005738735199, "learning_rate": 4.9320125660367815e-05, "loss": 4.445, "step": 2436 }, { "epoch": 0.07443494196701282, "grad_norm": 0.4089008867740631, "learning_rate": 4.931956990314991e-05, "loss": 4.3884, "step": 2437 }, { "epoch": 0.0744654856444716, "grad_norm": 0.420121431350708, "learning_rate": 4.931901392200923e-05, "loss": 4.374, "step": 2438 }, { "epoch": 0.07449602932193036, "grad_norm": 0.4213723838329315, "learning_rate": 4.931845771695088e-05, "loss": 4.3926, "step": 2439 }, { "epoch": 0.07452657299938913, "grad_norm": 0.4072766900062561, "learning_rate": 4.931790128797999e-05, "loss": 4.3751, "step": 2440 }, { "epoch": 0.07455711667684789, "grad_norm": 0.40558990836143494, "learning_rate": 4.931734463510168e-05, "loss": 4.3817, "step": 2441 }, { "epoch": 0.07458766035430665, "grad_norm": 0.40676990151405334, "learning_rate": 4.931678775832107e-05, "loss": 4.3064, "step": 2442 }, { "epoch": 0.07461820403176543, "grad_norm": 0.41081270575523376, "learning_rate": 4.9316230657643295e-05, "loss": 4.3913, "step": 2443 }, { "epoch": 0.0746487477092242, "grad_norm": 0.40986528992652893, "learning_rate": 4.9315673333073486e-05, "loss": 4.452, "step": 2444 }, { "epoch": 0.07467929138668296, "grad_norm": 0.40671849250793457, "learning_rate": 4.931511578461677e-05, "loss": 4.4333, "step": 2445 }, { "epoch": 0.07470983506414172, "grad_norm": 0.4108060598373413, "learning_rate": 4.931455801227828e-05, "loss": 4.4105, "step": 2446 }, { "epoch": 0.07474037874160049, "grad_norm": 0.40134620666503906, "learning_rate": 4.931400001606314e-05, "loss": 4.4392, "step": 2447 }, { "epoch": 0.07477092241905925, "grad_norm": 0.4071528911590576, "learning_rate": 4.9313441795976525e-05, "loss": 4.4832, "step": 2448 }, { "epoch": 0.07480146609651803, "grad_norm": 0.4117608368396759, "learning_rate": 4.931288335202353e-05, "loss": 4.4722, "step": 2449 }, { "epoch": 0.07483200977397679, "grad_norm": 0.413804292678833, "learning_rate": 4.931232468420933e-05, "loss": 4.3817, "step": 2450 }, { "epoch": 0.07486255345143555, "grad_norm": 0.41102057695388794, "learning_rate": 4.931176579253905e-05, "loss": 4.4532, "step": 2451 }, { "epoch": 0.07489309712889432, "grad_norm": 0.4024387001991272, "learning_rate": 4.931120667701785e-05, "loss": 4.3925, "step": 2452 }, { "epoch": 0.07492364080635308, "grad_norm": 0.4185151159763336, "learning_rate": 4.9310647337650864e-05, "loss": 4.4488, "step": 2453 }, { "epoch": 0.07495418448381184, "grad_norm": 0.4116700291633606, "learning_rate": 4.9310087774443245e-05, "loss": 4.367, "step": 2454 }, { "epoch": 0.07498472816127062, "grad_norm": 0.3947449326515198, "learning_rate": 4.930952798740016e-05, "loss": 4.3319, "step": 2455 }, { "epoch": 0.07501527183872939, "grad_norm": 0.4204408526420593, "learning_rate": 4.930896797652674e-05, "loss": 4.507, "step": 2456 }, { "epoch": 0.07504581551618815, "grad_norm": 0.4091596007347107, "learning_rate": 4.930840774182816e-05, "loss": 4.4456, "step": 2457 }, { "epoch": 0.07507635919364691, "grad_norm": 0.4063577651977539, "learning_rate": 4.9307847283309574e-05, "loss": 4.3927, "step": 2458 }, { "epoch": 0.07510690287110568, "grad_norm": 0.39701250195503235, "learning_rate": 4.9307286600976134e-05, "loss": 4.4459, "step": 2459 }, { "epoch": 0.07513744654856444, "grad_norm": 0.4170685410499573, "learning_rate": 4.9306725694833014e-05, "loss": 4.4619, "step": 2460 }, { "epoch": 0.07516799022602322, "grad_norm": 0.4010050594806671, "learning_rate": 4.930616456488537e-05, "loss": 4.4218, "step": 2461 }, { "epoch": 0.07519853390348198, "grad_norm": 0.41173264384269714, "learning_rate": 4.930560321113837e-05, "loss": 4.3895, "step": 2462 }, { "epoch": 0.07522907758094075, "grad_norm": 0.41904187202453613, "learning_rate": 4.9305041633597194e-05, "loss": 4.5333, "step": 2463 }, { "epoch": 0.07525962125839951, "grad_norm": 0.4075686037540436, "learning_rate": 4.930447983226699e-05, "loss": 4.3701, "step": 2464 }, { "epoch": 0.07529016493585827, "grad_norm": 0.431727796792984, "learning_rate": 4.9303917807152956e-05, "loss": 4.4092, "step": 2465 }, { "epoch": 0.07532070861331705, "grad_norm": 0.41026976704597473, "learning_rate": 4.930335555826025e-05, "loss": 4.3863, "step": 2466 }, { "epoch": 0.07535125229077581, "grad_norm": 0.4124406576156616, "learning_rate": 4.9302793085594054e-05, "loss": 4.4577, "step": 2467 }, { "epoch": 0.07538179596823458, "grad_norm": 0.40668782591819763, "learning_rate": 4.930223038915955e-05, "loss": 4.368, "step": 2468 }, { "epoch": 0.07541233964569334, "grad_norm": 0.41422343254089355, "learning_rate": 4.930166746896191e-05, "loss": 4.4112, "step": 2469 }, { "epoch": 0.0754428833231521, "grad_norm": 0.41618233919143677, "learning_rate": 4.9301104325006324e-05, "loss": 4.4027, "step": 2470 }, { "epoch": 0.07547342700061087, "grad_norm": 0.42209434509277344, "learning_rate": 4.930054095729798e-05, "loss": 4.3641, "step": 2471 }, { "epoch": 0.07550397067806965, "grad_norm": 0.4119701683521271, "learning_rate": 4.929997736584206e-05, "loss": 4.386, "step": 2472 }, { "epoch": 0.07553451435552841, "grad_norm": 0.41618669033050537, "learning_rate": 4.9299413550643745e-05, "loss": 4.4554, "step": 2473 }, { "epoch": 0.07556505803298717, "grad_norm": 0.43840083479881287, "learning_rate": 4.9298849511708254e-05, "loss": 4.3771, "step": 2474 }, { "epoch": 0.07559560171044594, "grad_norm": 0.3971463441848755, "learning_rate": 4.929828524904075e-05, "loss": 4.4039, "step": 2475 }, { "epoch": 0.0756261453879047, "grad_norm": 0.3912225067615509, "learning_rate": 4.9297720762646445e-05, "loss": 4.4559, "step": 2476 }, { "epoch": 0.07565668906536346, "grad_norm": 0.4085349440574646, "learning_rate": 4.929715605253052e-05, "loss": 4.418, "step": 2477 }, { "epoch": 0.07568723274282224, "grad_norm": 0.403414249420166, "learning_rate": 4.9296591118698203e-05, "loss": 4.3473, "step": 2478 }, { "epoch": 0.075717776420281, "grad_norm": 0.4107297360897064, "learning_rate": 4.929602596115468e-05, "loss": 4.3744, "step": 2479 }, { "epoch": 0.07574832009773977, "grad_norm": 0.4191109538078308, "learning_rate": 4.929546057990514e-05, "loss": 4.4247, "step": 2480 }, { "epoch": 0.07577886377519853, "grad_norm": 0.4124848246574402, "learning_rate": 4.929489497495482e-05, "loss": 4.4399, "step": 2481 }, { "epoch": 0.0758094074526573, "grad_norm": 0.4011933207511902, "learning_rate": 4.92943291463089e-05, "loss": 4.3967, "step": 2482 }, { "epoch": 0.07583995113011606, "grad_norm": 0.41922318935394287, "learning_rate": 4.92937630939726e-05, "loss": 4.366, "step": 2483 }, { "epoch": 0.07587049480757484, "grad_norm": 0.4143977463245392, "learning_rate": 4.9293196817951135e-05, "loss": 4.3945, "step": 2484 }, { "epoch": 0.0759010384850336, "grad_norm": 0.4188496470451355, "learning_rate": 4.929263031824972e-05, "loss": 4.474, "step": 2485 }, { "epoch": 0.07593158216249236, "grad_norm": 0.41684597730636597, "learning_rate": 4.9292063594873564e-05, "loss": 4.3167, "step": 2486 }, { "epoch": 0.07596212583995113, "grad_norm": 0.4127344787120819, "learning_rate": 4.9291496647827884e-05, "loss": 4.367, "step": 2487 }, { "epoch": 0.07599266951740989, "grad_norm": 0.42349889874458313, "learning_rate": 4.929092947711791e-05, "loss": 4.4114, "step": 2488 }, { "epoch": 0.07602321319486867, "grad_norm": 0.3992343544960022, "learning_rate": 4.9290362082748865e-05, "loss": 4.4147, "step": 2489 }, { "epoch": 0.07605375687232743, "grad_norm": 0.42340728640556335, "learning_rate": 4.9289794464725955e-05, "loss": 4.4272, "step": 2490 }, { "epoch": 0.0760843005497862, "grad_norm": 0.41604653000831604, "learning_rate": 4.928922662305443e-05, "loss": 4.458, "step": 2491 }, { "epoch": 0.07611484422724496, "grad_norm": 0.41680896282196045, "learning_rate": 4.9288658557739496e-05, "loss": 4.3925, "step": 2492 }, { "epoch": 0.07614538790470372, "grad_norm": 0.41478174924850464, "learning_rate": 4.92880902687864e-05, "loss": 4.3791, "step": 2493 }, { "epoch": 0.07617593158216249, "grad_norm": 0.40648218989372253, "learning_rate": 4.9287521756200376e-05, "loss": 4.4993, "step": 2494 }, { "epoch": 0.07620647525962126, "grad_norm": 0.41562676429748535, "learning_rate": 4.9286953019986646e-05, "loss": 4.4327, "step": 2495 }, { "epoch": 0.07623701893708003, "grad_norm": 0.41625675559043884, "learning_rate": 4.928638406015045e-05, "loss": 4.4595, "step": 2496 }, { "epoch": 0.07626756261453879, "grad_norm": 0.405590683221817, "learning_rate": 4.928581487669704e-05, "loss": 4.4241, "step": 2497 }, { "epoch": 0.07629810629199756, "grad_norm": 0.4010188579559326, "learning_rate": 4.9285245469631634e-05, "loss": 4.4275, "step": 2498 }, { "epoch": 0.07632864996945632, "grad_norm": 0.4161880314350128, "learning_rate": 4.9284675838959494e-05, "loss": 4.4393, "step": 2499 }, { "epoch": 0.07635919364691508, "grad_norm": 0.4239867031574249, "learning_rate": 4.928410598468585e-05, "loss": 4.4254, "step": 2500 }, { "epoch": 0.07638973732437386, "grad_norm": 0.41247501969337463, "learning_rate": 4.9283535906815956e-05, "loss": 4.3461, "step": 2501 }, { "epoch": 0.07642028100183262, "grad_norm": 0.43415209650993347, "learning_rate": 4.928296560535507e-05, "loss": 4.4817, "step": 2502 }, { "epoch": 0.07645082467929139, "grad_norm": 0.40785524249076843, "learning_rate": 4.928239508030843e-05, "loss": 4.4588, "step": 2503 }, { "epoch": 0.07648136835675015, "grad_norm": 0.4097374677658081, "learning_rate": 4.928182433168129e-05, "loss": 4.4643, "step": 2504 }, { "epoch": 0.07651191203420891, "grad_norm": 0.4102279543876648, "learning_rate": 4.9281253359478916e-05, "loss": 4.4005, "step": 2505 }, { "epoch": 0.07654245571166768, "grad_norm": 0.40285220742225647, "learning_rate": 4.928068216370656e-05, "loss": 4.441, "step": 2506 }, { "epoch": 0.07657299938912646, "grad_norm": 0.40958496928215027, "learning_rate": 4.9280110744369474e-05, "loss": 4.3702, "step": 2507 }, { "epoch": 0.07660354306658522, "grad_norm": 0.41731327772140503, "learning_rate": 4.927953910147293e-05, "loss": 4.513, "step": 2508 }, { "epoch": 0.07663408674404398, "grad_norm": 0.4152686297893524, "learning_rate": 4.9278967235022176e-05, "loss": 4.4373, "step": 2509 }, { "epoch": 0.07666463042150275, "grad_norm": 0.4038211703300476, "learning_rate": 4.9278395145022495e-05, "loss": 4.4303, "step": 2510 }, { "epoch": 0.07669517409896151, "grad_norm": 0.39766061305999756, "learning_rate": 4.927782283147915e-05, "loss": 4.4111, "step": 2511 }, { "epoch": 0.07672571777642027, "grad_norm": 0.4205915033817291, "learning_rate": 4.92772502943974e-05, "loss": 4.4749, "step": 2512 }, { "epoch": 0.07675626145387905, "grad_norm": 0.4133768677711487, "learning_rate": 4.9276677533782524e-05, "loss": 4.4626, "step": 2513 }, { "epoch": 0.07678680513133782, "grad_norm": 0.3987984359264374, "learning_rate": 4.92761045496398e-05, "loss": 4.4329, "step": 2514 }, { "epoch": 0.07681734880879658, "grad_norm": 0.40234172344207764, "learning_rate": 4.92755313419745e-05, "loss": 4.3445, "step": 2515 }, { "epoch": 0.07684789248625534, "grad_norm": 0.3975798785686493, "learning_rate": 4.92749579107919e-05, "loss": 4.3383, "step": 2516 }, { "epoch": 0.0768784361637141, "grad_norm": 0.4207402169704437, "learning_rate": 4.927438425609728e-05, "loss": 4.4166, "step": 2517 }, { "epoch": 0.07690897984117288, "grad_norm": 0.40510571002960205, "learning_rate": 4.927381037789593e-05, "loss": 4.4902, "step": 2518 }, { "epoch": 0.07693952351863165, "grad_norm": 0.41800060868263245, "learning_rate": 4.9273236276193124e-05, "loss": 4.5387, "step": 2519 }, { "epoch": 0.07697006719609041, "grad_norm": 0.40905389189720154, "learning_rate": 4.927266195099415e-05, "loss": 4.4348, "step": 2520 }, { "epoch": 0.07700061087354917, "grad_norm": 0.4087457060813904, "learning_rate": 4.92720874023043e-05, "loss": 4.5038, "step": 2521 }, { "epoch": 0.07703115455100794, "grad_norm": 0.4104590117931366, "learning_rate": 4.927151263012887e-05, "loss": 4.4157, "step": 2522 }, { "epoch": 0.0770616982284667, "grad_norm": 0.4057864248752594, "learning_rate": 4.927093763447313e-05, "loss": 4.3466, "step": 2523 }, { "epoch": 0.07709224190592548, "grad_norm": 0.4922901690006256, "learning_rate": 4.92703624153424e-05, "loss": 4.4662, "step": 2524 }, { "epoch": 0.07712278558338424, "grad_norm": 0.4032481610774994, "learning_rate": 4.926978697274195e-05, "loss": 4.5289, "step": 2525 }, { "epoch": 0.077153329260843, "grad_norm": 0.41446205973625183, "learning_rate": 4.9269211306677104e-05, "loss": 4.502, "step": 2526 }, { "epoch": 0.07718387293830177, "grad_norm": 0.43360480666160583, "learning_rate": 4.926863541715315e-05, "loss": 4.4962, "step": 2527 }, { "epoch": 0.07721441661576053, "grad_norm": 0.42431360483169556, "learning_rate": 4.9268059304175384e-05, "loss": 4.4563, "step": 2528 }, { "epoch": 0.0772449602932193, "grad_norm": 0.40573257207870483, "learning_rate": 4.926748296774913e-05, "loss": 4.3988, "step": 2529 }, { "epoch": 0.07727550397067807, "grad_norm": 0.4000362157821655, "learning_rate": 4.9266906407879673e-05, "loss": 4.366, "step": 2530 }, { "epoch": 0.07730604764813684, "grad_norm": 0.41401001811027527, "learning_rate": 4.9266329624572346e-05, "loss": 4.4061, "step": 2531 }, { "epoch": 0.0773365913255956, "grad_norm": 0.42017149925231934, "learning_rate": 4.926575261783243e-05, "loss": 4.4555, "step": 2532 }, { "epoch": 0.07736713500305437, "grad_norm": 0.40147167444229126, "learning_rate": 4.9265175387665264e-05, "loss": 4.4924, "step": 2533 }, { "epoch": 0.07739767868051313, "grad_norm": 0.41312524676322937, "learning_rate": 4.926459793407615e-05, "loss": 4.418, "step": 2534 }, { "epoch": 0.0774282223579719, "grad_norm": 0.41843560338020325, "learning_rate": 4.926402025707041e-05, "loss": 4.4533, "step": 2535 }, { "epoch": 0.07745876603543067, "grad_norm": 0.4194926917552948, "learning_rate": 4.9263442356653355e-05, "loss": 4.4308, "step": 2536 }, { "epoch": 0.07748930971288943, "grad_norm": 0.40139421820640564, "learning_rate": 4.926286423283031e-05, "loss": 4.4584, "step": 2537 }, { "epoch": 0.0775198533903482, "grad_norm": 0.41375598311424255, "learning_rate": 4.92622858856066e-05, "loss": 4.4188, "step": 2538 }, { "epoch": 0.07755039706780696, "grad_norm": 0.429871529340744, "learning_rate": 4.926170731498755e-05, "loss": 4.4483, "step": 2539 }, { "epoch": 0.07758094074526573, "grad_norm": 0.4100894629955292, "learning_rate": 4.926112852097849e-05, "loss": 4.3507, "step": 2540 }, { "epoch": 0.0776114844227245, "grad_norm": 0.42171987891197205, "learning_rate": 4.9260549503584744e-05, "loss": 4.3802, "step": 2541 }, { "epoch": 0.07764202810018327, "grad_norm": 0.41923975944519043, "learning_rate": 4.925997026281165e-05, "loss": 4.4047, "step": 2542 }, { "epoch": 0.07767257177764203, "grad_norm": 0.40923166275024414, "learning_rate": 4.925939079866453e-05, "loss": 4.4101, "step": 2543 }, { "epoch": 0.0777031154551008, "grad_norm": 0.40760329365730286, "learning_rate": 4.925881111114872e-05, "loss": 4.4499, "step": 2544 }, { "epoch": 0.07773365913255956, "grad_norm": 0.4090975821018219, "learning_rate": 4.925823120026957e-05, "loss": 4.4528, "step": 2545 }, { "epoch": 0.07776420281001832, "grad_norm": 0.41907912492752075, "learning_rate": 4.925765106603242e-05, "loss": 4.4386, "step": 2546 }, { "epoch": 0.0777947464874771, "grad_norm": 0.394863486289978, "learning_rate": 4.925707070844259e-05, "loss": 4.4548, "step": 2547 }, { "epoch": 0.07782529016493586, "grad_norm": 0.3991689383983612, "learning_rate": 4.925649012750545e-05, "loss": 4.4755, "step": 2548 }, { "epoch": 0.07785583384239463, "grad_norm": 0.40509942173957825, "learning_rate": 4.925590932322634e-05, "loss": 4.4701, "step": 2549 }, { "epoch": 0.07788637751985339, "grad_norm": 0.4194912612438202, "learning_rate": 4.925532829561058e-05, "loss": 4.3412, "step": 2550 }, { "epoch": 0.07791692119731215, "grad_norm": 0.415279746055603, "learning_rate": 4.9254747044663556e-05, "loss": 4.4813, "step": 2551 }, { "epoch": 0.07794746487477092, "grad_norm": 0.3962651193141937, "learning_rate": 4.92541655703906e-05, "loss": 4.3836, "step": 2552 }, { "epoch": 0.0779780085522297, "grad_norm": 0.39790529012680054, "learning_rate": 4.925358387279708e-05, "loss": 4.3806, "step": 2553 }, { "epoch": 0.07800855222968846, "grad_norm": 0.4083968698978424, "learning_rate": 4.9253001951888335e-05, "loss": 4.3808, "step": 2554 }, { "epoch": 0.07803909590714722, "grad_norm": 0.4086031913757324, "learning_rate": 4.9252419807669735e-05, "loss": 4.5209, "step": 2555 }, { "epoch": 0.07806963958460598, "grad_norm": 0.3973412811756134, "learning_rate": 4.9251837440146634e-05, "loss": 4.4493, "step": 2556 }, { "epoch": 0.07810018326206475, "grad_norm": 0.41191554069519043, "learning_rate": 4.92512548493244e-05, "loss": 4.4782, "step": 2557 }, { "epoch": 0.07813072693952351, "grad_norm": 0.41358721256256104, "learning_rate": 4.925067203520839e-05, "loss": 4.4805, "step": 2558 }, { "epoch": 0.07816127061698229, "grad_norm": 0.4269641935825348, "learning_rate": 4.925008899780398e-05, "loss": 4.388, "step": 2559 }, { "epoch": 0.07819181429444105, "grad_norm": 0.40132567286491394, "learning_rate": 4.924950573711653e-05, "loss": 4.4621, "step": 2560 }, { "epoch": 0.07822235797189982, "grad_norm": 0.41253164410591125, "learning_rate": 4.924892225315141e-05, "loss": 4.4446, "step": 2561 }, { "epoch": 0.07825290164935858, "grad_norm": 0.4144911766052246, "learning_rate": 4.9248338545914e-05, "loss": 4.4448, "step": 2562 }, { "epoch": 0.07828344532681734, "grad_norm": 0.42653223872184753, "learning_rate": 4.924775461540966e-05, "loss": 4.4546, "step": 2563 }, { "epoch": 0.07831398900427612, "grad_norm": 0.4081707298755646, "learning_rate": 4.924717046164379e-05, "loss": 4.4743, "step": 2564 }, { "epoch": 0.07834453268173489, "grad_norm": 0.40442541241645813, "learning_rate": 4.924658608462174e-05, "loss": 4.5054, "step": 2565 }, { "epoch": 0.07837507635919365, "grad_norm": 0.4018000066280365, "learning_rate": 4.9246001484348915e-05, "loss": 4.4167, "step": 2566 }, { "epoch": 0.07840562003665241, "grad_norm": 0.39599621295928955, "learning_rate": 4.924541666083069e-05, "loss": 4.4321, "step": 2567 }, { "epoch": 0.07843616371411118, "grad_norm": 0.4101335406303406, "learning_rate": 4.924483161407244e-05, "loss": 4.3634, "step": 2568 }, { "epoch": 0.07846670739156994, "grad_norm": 0.4114779829978943, "learning_rate": 4.924424634407957e-05, "loss": 4.5122, "step": 2569 }, { "epoch": 0.07849725106902872, "grad_norm": 0.41891661286354065, "learning_rate": 4.924366085085745e-05, "loss": 4.3869, "step": 2570 }, { "epoch": 0.07852779474648748, "grad_norm": 0.40300410985946655, "learning_rate": 4.924307513441148e-05, "loss": 4.3806, "step": 2571 }, { "epoch": 0.07855833842394624, "grad_norm": 0.4128546714782715, "learning_rate": 4.9242489194747055e-05, "loss": 4.4136, "step": 2572 }, { "epoch": 0.07858888210140501, "grad_norm": 0.5056350231170654, "learning_rate": 4.9241903031869576e-05, "loss": 4.4545, "step": 2573 }, { "epoch": 0.07861942577886377, "grad_norm": 0.4039989709854126, "learning_rate": 4.924131664578442e-05, "loss": 4.5066, "step": 2574 }, { "epoch": 0.07864996945632254, "grad_norm": 0.42492422461509705, "learning_rate": 4.9240730036497e-05, "loss": 4.4357, "step": 2575 }, { "epoch": 0.07868051313378131, "grad_norm": 0.4085298776626587, "learning_rate": 4.924014320401272e-05, "loss": 4.3898, "step": 2576 }, { "epoch": 0.07871105681124008, "grad_norm": 0.40356332063674927, "learning_rate": 4.923955614833697e-05, "loss": 4.4339, "step": 2577 }, { "epoch": 0.07874160048869884, "grad_norm": 0.40157538652420044, "learning_rate": 4.923896886947517e-05, "loss": 4.3608, "step": 2578 }, { "epoch": 0.0787721441661576, "grad_norm": 0.4127812683582306, "learning_rate": 4.923838136743272e-05, "loss": 4.4037, "step": 2579 }, { "epoch": 0.07880268784361637, "grad_norm": 0.4169604480266571, "learning_rate": 4.923779364221503e-05, "loss": 4.377, "step": 2580 }, { "epoch": 0.07883323152107513, "grad_norm": 0.43088093400001526, "learning_rate": 4.9237205693827513e-05, "loss": 4.4836, "step": 2581 }, { "epoch": 0.07886377519853391, "grad_norm": 0.4079956114292145, "learning_rate": 4.9236617522275584e-05, "loss": 4.4126, "step": 2582 }, { "epoch": 0.07889431887599267, "grad_norm": 0.42048966884613037, "learning_rate": 4.923602912756465e-05, "loss": 4.4781, "step": 2583 }, { "epoch": 0.07892486255345144, "grad_norm": 0.4093579351902008, "learning_rate": 4.923544050970015e-05, "loss": 4.4302, "step": 2584 }, { "epoch": 0.0789554062309102, "grad_norm": 0.4345453381538391, "learning_rate": 4.9234851668687475e-05, "loss": 4.5466, "step": 2585 }, { "epoch": 0.07898594990836896, "grad_norm": 0.4142061471939087, "learning_rate": 4.923426260453207e-05, "loss": 4.443, "step": 2586 }, { "epoch": 0.07901649358582773, "grad_norm": 0.4102575182914734, "learning_rate": 4.923367331723934e-05, "loss": 4.4375, "step": 2587 }, { "epoch": 0.0790470372632865, "grad_norm": 0.41988077759742737, "learning_rate": 4.923308380681472e-05, "loss": 4.4783, "step": 2588 }, { "epoch": 0.07907758094074527, "grad_norm": 0.4067745804786682, "learning_rate": 4.923249407326364e-05, "loss": 4.3361, "step": 2589 }, { "epoch": 0.07910812461820403, "grad_norm": 0.4103008508682251, "learning_rate": 4.923190411659153e-05, "loss": 4.4124, "step": 2590 }, { "epoch": 0.0791386682956628, "grad_norm": 0.40906184911727905, "learning_rate": 4.9231313936803816e-05, "loss": 4.3989, "step": 2591 }, { "epoch": 0.07916921197312156, "grad_norm": 0.41377323865890503, "learning_rate": 4.923072353390594e-05, "loss": 4.4023, "step": 2592 }, { "epoch": 0.07919975565058034, "grad_norm": 0.40010732412338257, "learning_rate": 4.9230132907903326e-05, "loss": 4.4524, "step": 2593 }, { "epoch": 0.0792302993280391, "grad_norm": 0.414719820022583, "learning_rate": 4.922954205880143e-05, "loss": 4.4277, "step": 2594 }, { "epoch": 0.07926084300549786, "grad_norm": 0.421983927488327, "learning_rate": 4.9228950986605683e-05, "loss": 4.454, "step": 2595 }, { "epoch": 0.07929138668295663, "grad_norm": 0.4130995273590088, "learning_rate": 4.9228359691321524e-05, "loss": 4.4154, "step": 2596 }, { "epoch": 0.07932193036041539, "grad_norm": 0.4217400550842285, "learning_rate": 4.92277681729544e-05, "loss": 4.4615, "step": 2597 }, { "epoch": 0.07935247403787415, "grad_norm": 0.4176298677921295, "learning_rate": 4.922717643150975e-05, "loss": 4.4512, "step": 2598 }, { "epoch": 0.07938301771533293, "grad_norm": 0.4049248695373535, "learning_rate": 4.9226584466993045e-05, "loss": 4.5167, "step": 2599 }, { "epoch": 0.0794135613927917, "grad_norm": 0.4120014011859894, "learning_rate": 4.922599227940971e-05, "loss": 4.4565, "step": 2600 }, { "epoch": 0.07944410507025046, "grad_norm": 0.40295666456222534, "learning_rate": 4.922539986876521e-05, "loss": 4.42, "step": 2601 }, { "epoch": 0.07947464874770922, "grad_norm": 0.4153028726577759, "learning_rate": 4.9224807235065e-05, "loss": 4.3595, "step": 2602 }, { "epoch": 0.07950519242516799, "grad_norm": 0.4066520929336548, "learning_rate": 4.922421437831454e-05, "loss": 4.4283, "step": 2603 }, { "epoch": 0.07953573610262675, "grad_norm": 0.41690805554389954, "learning_rate": 4.922362129851927e-05, "loss": 4.4472, "step": 2604 }, { "epoch": 0.07956627978008553, "grad_norm": 0.42449092864990234, "learning_rate": 4.922302799568468e-05, "loss": 4.519, "step": 2605 }, { "epoch": 0.07959682345754429, "grad_norm": 0.40186983346939087, "learning_rate": 4.92224344698162e-05, "loss": 4.4925, "step": 2606 }, { "epoch": 0.07962736713500305, "grad_norm": 0.42536571621894836, "learning_rate": 4.922184072091933e-05, "loss": 4.4781, "step": 2607 }, { "epoch": 0.07965791081246182, "grad_norm": 0.41154953837394714, "learning_rate": 4.9221246748999503e-05, "loss": 4.4277, "step": 2608 }, { "epoch": 0.07968845448992058, "grad_norm": 0.40755409002304077, "learning_rate": 4.922065255406221e-05, "loss": 4.4415, "step": 2609 }, { "epoch": 0.07971899816737935, "grad_norm": 0.4035646617412567, "learning_rate": 4.922005813611292e-05, "loss": 4.3823, "step": 2610 }, { "epoch": 0.07974954184483812, "grad_norm": 0.41514602303504944, "learning_rate": 4.9219463495157095e-05, "loss": 4.3676, "step": 2611 }, { "epoch": 0.07978008552229689, "grad_norm": 0.42025572061538696, "learning_rate": 4.921886863120022e-05, "loss": 4.4335, "step": 2612 }, { "epoch": 0.07981062919975565, "grad_norm": 0.41302090883255005, "learning_rate": 4.9218273544247775e-05, "loss": 4.4677, "step": 2613 }, { "epoch": 0.07984117287721441, "grad_norm": 0.4182737171649933, "learning_rate": 4.921767823430523e-05, "loss": 4.4979, "step": 2614 }, { "epoch": 0.07987171655467318, "grad_norm": 0.4266285002231598, "learning_rate": 4.921708270137807e-05, "loss": 4.4908, "step": 2615 }, { "epoch": 0.07990226023213196, "grad_norm": 0.407293438911438, "learning_rate": 4.9216486945471776e-05, "loss": 4.4603, "step": 2616 }, { "epoch": 0.07993280390959072, "grad_norm": 0.40783098340034485, "learning_rate": 4.921589096659184e-05, "loss": 4.3399, "step": 2617 }, { "epoch": 0.07996334758704948, "grad_norm": 0.41281208395957947, "learning_rate": 4.921529476474374e-05, "loss": 4.4352, "step": 2618 }, { "epoch": 0.07999389126450825, "grad_norm": 0.4114416539669037, "learning_rate": 4.921469833993297e-05, "loss": 4.4014, "step": 2619 }, { "epoch": 0.08002443494196701, "grad_norm": 0.4140917956829071, "learning_rate": 4.9214101692165024e-05, "loss": 4.482, "step": 2620 }, { "epoch": 0.08005497861942577, "grad_norm": 0.4072772264480591, "learning_rate": 4.92135048214454e-05, "loss": 4.48, "step": 2621 }, { "epoch": 0.08008552229688455, "grad_norm": 0.40439048409461975, "learning_rate": 4.9212907727779575e-05, "loss": 4.4166, "step": 2622 }, { "epoch": 0.08011606597434331, "grad_norm": 0.4229537844657898, "learning_rate": 4.921231041117307e-05, "loss": 4.3883, "step": 2623 }, { "epoch": 0.08014660965180208, "grad_norm": 0.4026046097278595, "learning_rate": 4.9211712871631375e-05, "loss": 4.487, "step": 2624 }, { "epoch": 0.08017715332926084, "grad_norm": 0.4019193649291992, "learning_rate": 4.921111510915999e-05, "loss": 4.307, "step": 2625 }, { "epoch": 0.0802076970067196, "grad_norm": 0.410543829202652, "learning_rate": 4.921051712376442e-05, "loss": 4.4925, "step": 2626 }, { "epoch": 0.08023824068417837, "grad_norm": 0.4123913049697876, "learning_rate": 4.920991891545017e-05, "loss": 4.4922, "step": 2627 }, { "epoch": 0.08026878436163715, "grad_norm": 0.41906726360321045, "learning_rate": 4.920932048422274e-05, "loss": 4.3871, "step": 2628 }, { "epoch": 0.08029932803909591, "grad_norm": 0.41708076000213623, "learning_rate": 4.9208721830087666e-05, "loss": 4.4505, "step": 2629 }, { "epoch": 0.08032987171655467, "grad_norm": 0.401714026927948, "learning_rate": 4.920812295305043e-05, "loss": 4.4642, "step": 2630 }, { "epoch": 0.08036041539401344, "grad_norm": 0.4050694704055786, "learning_rate": 4.9207523853116564e-05, "loss": 4.4523, "step": 2631 }, { "epoch": 0.0803909590714722, "grad_norm": 0.4161245822906494, "learning_rate": 4.920692453029158e-05, "loss": 4.4741, "step": 2632 }, { "epoch": 0.08042150274893096, "grad_norm": 0.4179038405418396, "learning_rate": 4.9206324984581e-05, "loss": 4.4891, "step": 2633 }, { "epoch": 0.08045204642638974, "grad_norm": 0.3990548253059387, "learning_rate": 4.9205725215990336e-05, "loss": 4.4333, "step": 2634 }, { "epoch": 0.0804825901038485, "grad_norm": 0.40344300866127014, "learning_rate": 4.920512522452511e-05, "loss": 4.4263, "step": 2635 }, { "epoch": 0.08051313378130727, "grad_norm": 0.4191400110721588, "learning_rate": 4.920452501019086e-05, "loss": 4.4089, "step": 2636 }, { "epoch": 0.08054367745876603, "grad_norm": 0.39641430974006653, "learning_rate": 4.92039245729931e-05, "loss": 4.3827, "step": 2637 }, { "epoch": 0.0805742211362248, "grad_norm": 0.41356563568115234, "learning_rate": 4.920332391293736e-05, "loss": 4.4591, "step": 2638 }, { "epoch": 0.08060476481368357, "grad_norm": 0.41789212822914124, "learning_rate": 4.920272303002917e-05, "loss": 4.4459, "step": 2639 }, { "epoch": 0.08063530849114234, "grad_norm": 0.4128623902797699, "learning_rate": 4.920212192427407e-05, "loss": 4.4516, "step": 2640 }, { "epoch": 0.0806658521686011, "grad_norm": 0.402825266122818, "learning_rate": 4.920152059567759e-05, "loss": 4.3091, "step": 2641 }, { "epoch": 0.08069639584605987, "grad_norm": 0.39615684747695923, "learning_rate": 4.9200919044245265e-05, "loss": 4.4419, "step": 2642 }, { "epoch": 0.08072693952351863, "grad_norm": 0.4012303054332733, "learning_rate": 4.9200317269982635e-05, "loss": 4.3507, "step": 2643 }, { "epoch": 0.08075748320097739, "grad_norm": 0.40119317173957825, "learning_rate": 4.919971527289524e-05, "loss": 4.3911, "step": 2644 }, { "epoch": 0.08078802687843617, "grad_norm": 0.4050392806529999, "learning_rate": 4.919911305298863e-05, "loss": 4.3659, "step": 2645 }, { "epoch": 0.08081857055589493, "grad_norm": 0.4019640386104584, "learning_rate": 4.919851061026834e-05, "loss": 4.4631, "step": 2646 }, { "epoch": 0.0808491142333537, "grad_norm": 0.41045892238616943, "learning_rate": 4.919790794473992e-05, "loss": 4.4222, "step": 2647 }, { "epoch": 0.08087965791081246, "grad_norm": 0.41789719462394714, "learning_rate": 4.919730505640893e-05, "loss": 4.3827, "step": 2648 }, { "epoch": 0.08091020158827122, "grad_norm": 0.41103121638298035, "learning_rate": 4.91967019452809e-05, "loss": 4.4693, "step": 2649 }, { "epoch": 0.08094074526572999, "grad_norm": 0.4143518805503845, "learning_rate": 4.9196098611361394e-05, "loss": 4.4856, "step": 2650 }, { "epoch": 0.08097128894318877, "grad_norm": 0.3952718675136566, "learning_rate": 4.919549505465597e-05, "loss": 4.3739, "step": 2651 }, { "epoch": 0.08100183262064753, "grad_norm": 0.41871029138565063, "learning_rate": 4.919489127517019e-05, "loss": 4.4926, "step": 2652 }, { "epoch": 0.08103237629810629, "grad_norm": 0.40441662073135376, "learning_rate": 4.91942872729096e-05, "loss": 4.4623, "step": 2653 }, { "epoch": 0.08106291997556506, "grad_norm": 0.4208622872829437, "learning_rate": 4.919368304787977e-05, "loss": 4.4669, "step": 2654 }, { "epoch": 0.08109346365302382, "grad_norm": 0.4130890369415283, "learning_rate": 4.919307860008626e-05, "loss": 4.5063, "step": 2655 }, { "epoch": 0.08112400733048258, "grad_norm": 0.4005504250526428, "learning_rate": 4.9192473929534634e-05, "loss": 4.4589, "step": 2656 }, { "epoch": 0.08115455100794136, "grad_norm": 0.4080527722835541, "learning_rate": 4.9191869036230466e-05, "loss": 4.4327, "step": 2657 }, { "epoch": 0.08118509468540012, "grad_norm": 0.4004117250442505, "learning_rate": 4.9191263920179314e-05, "loss": 4.3917, "step": 2658 }, { "epoch": 0.08121563836285889, "grad_norm": 0.39824631810188293, "learning_rate": 4.919065858138676e-05, "loss": 4.4426, "step": 2659 }, { "epoch": 0.08124618204031765, "grad_norm": 0.40911680459976196, "learning_rate": 4.919005301985838e-05, "loss": 4.4459, "step": 2660 }, { "epoch": 0.08127672571777642, "grad_norm": 0.4149481952190399, "learning_rate": 4.9189447235599736e-05, "loss": 4.3905, "step": 2661 }, { "epoch": 0.0813072693952352, "grad_norm": 0.4013349115848541, "learning_rate": 4.9188841228616426e-05, "loss": 4.4692, "step": 2662 }, { "epoch": 0.08133781307269396, "grad_norm": 0.4052201807498932, "learning_rate": 4.918823499891401e-05, "loss": 4.4174, "step": 2663 }, { "epoch": 0.08136835675015272, "grad_norm": 0.4026022255420685, "learning_rate": 4.918762854649808e-05, "loss": 4.451, "step": 2664 }, { "epoch": 0.08139890042761148, "grad_norm": 0.4053642153739929, "learning_rate": 4.918702187137422e-05, "loss": 4.4515, "step": 2665 }, { "epoch": 0.08142944410507025, "grad_norm": 0.3955034613609314, "learning_rate": 4.918641497354801e-05, "loss": 4.4458, "step": 2666 }, { "epoch": 0.08145998778252901, "grad_norm": 0.42288628220558167, "learning_rate": 4.9185807853025046e-05, "loss": 4.4129, "step": 2667 }, { "epoch": 0.08149053145998779, "grad_norm": 0.39351263642311096, "learning_rate": 4.9185200509810914e-05, "loss": 4.3919, "step": 2668 }, { "epoch": 0.08152107513744655, "grad_norm": 0.40731167793273926, "learning_rate": 4.9184592943911204e-05, "loss": 4.4529, "step": 2669 }, { "epoch": 0.08155161881490532, "grad_norm": 0.40157926082611084, "learning_rate": 4.918398515533151e-05, "loss": 4.4406, "step": 2670 }, { "epoch": 0.08158216249236408, "grad_norm": 0.40785276889801025, "learning_rate": 4.9183377144077436e-05, "loss": 4.4428, "step": 2671 }, { "epoch": 0.08161270616982284, "grad_norm": 0.405042439699173, "learning_rate": 4.918276891015457e-05, "loss": 4.5004, "step": 2672 }, { "epoch": 0.08164324984728161, "grad_norm": 0.3994094133377075, "learning_rate": 4.918216045356852e-05, "loss": 4.454, "step": 2673 }, { "epoch": 0.08167379352474038, "grad_norm": 0.3940945863723755, "learning_rate": 4.918155177432489e-05, "loss": 4.4126, "step": 2674 }, { "epoch": 0.08170433720219915, "grad_norm": 0.40477779507637024, "learning_rate": 4.918094287242927e-05, "loss": 4.3839, "step": 2675 }, { "epoch": 0.08173488087965791, "grad_norm": 0.41742420196533203, "learning_rate": 4.918033374788728e-05, "loss": 4.411, "step": 2676 }, { "epoch": 0.08176542455711668, "grad_norm": 0.4113258123397827, "learning_rate": 4.9179724400704526e-05, "loss": 4.4397, "step": 2677 }, { "epoch": 0.08179596823457544, "grad_norm": 0.40778717398643494, "learning_rate": 4.917911483088662e-05, "loss": 4.5388, "step": 2678 }, { "epoch": 0.0818265119120342, "grad_norm": 0.3970275819301605, "learning_rate": 4.9178505038439165e-05, "loss": 4.4319, "step": 2679 }, { "epoch": 0.08185705558949298, "grad_norm": 0.406187504529953, "learning_rate": 4.9177895023367784e-05, "loss": 4.4188, "step": 2680 }, { "epoch": 0.08188759926695174, "grad_norm": 0.39202404022216797, "learning_rate": 4.91772847856781e-05, "loss": 4.4885, "step": 2681 }, { "epoch": 0.08191814294441051, "grad_norm": 0.40417125821113586, "learning_rate": 4.9176674325375715e-05, "loss": 4.3752, "step": 2682 }, { "epoch": 0.08194868662186927, "grad_norm": 0.4072033762931824, "learning_rate": 4.917606364246626e-05, "loss": 4.4936, "step": 2683 }, { "epoch": 0.08197923029932803, "grad_norm": 0.4065265953540802, "learning_rate": 4.917545273695537e-05, "loss": 4.4598, "step": 2684 }, { "epoch": 0.0820097739767868, "grad_norm": 0.4068296253681183, "learning_rate": 4.9174841608848646e-05, "loss": 4.5115, "step": 2685 }, { "epoch": 0.08204031765424558, "grad_norm": 0.3954630196094513, "learning_rate": 4.9174230258151725e-05, "loss": 4.4558, "step": 2686 }, { "epoch": 0.08207086133170434, "grad_norm": 0.4125508666038513, "learning_rate": 4.917361868487024e-05, "loss": 4.438, "step": 2687 }, { "epoch": 0.0821014050091631, "grad_norm": 0.42019787430763245, "learning_rate": 4.917300688900982e-05, "loss": 4.4319, "step": 2688 }, { "epoch": 0.08213194868662187, "grad_norm": 0.39640721678733826, "learning_rate": 4.917239487057609e-05, "loss": 4.4569, "step": 2689 }, { "epoch": 0.08216249236408063, "grad_norm": 0.4106099009513855, "learning_rate": 4.91717826295747e-05, "loss": 4.3659, "step": 2690 }, { "epoch": 0.08219303604153941, "grad_norm": 0.400908499956131, "learning_rate": 4.9171170166011274e-05, "loss": 4.415, "step": 2691 }, { "epoch": 0.08222357971899817, "grad_norm": 0.4033311605453491, "learning_rate": 4.9170557479891465e-05, "loss": 4.3741, "step": 2692 }, { "epoch": 0.08225412339645694, "grad_norm": 0.40805041790008545, "learning_rate": 4.916994457122089e-05, "loss": 4.463, "step": 2693 }, { "epoch": 0.0822846670739157, "grad_norm": 0.4043688178062439, "learning_rate": 4.9169331440005225e-05, "loss": 4.4337, "step": 2694 }, { "epoch": 0.08231521075137446, "grad_norm": 0.40002840757369995, "learning_rate": 4.91687180862501e-05, "loss": 4.4587, "step": 2695 }, { "epoch": 0.08234575442883323, "grad_norm": 0.4035409390926361, "learning_rate": 4.916810450996115e-05, "loss": 4.3443, "step": 2696 }, { "epoch": 0.082376298106292, "grad_norm": 0.4036233127117157, "learning_rate": 4.916749071114404e-05, "loss": 4.4155, "step": 2697 }, { "epoch": 0.08240684178375077, "grad_norm": 0.41658735275268555, "learning_rate": 4.9166876689804414e-05, "loss": 4.4192, "step": 2698 }, { "epoch": 0.08243738546120953, "grad_norm": 0.4148896038532257, "learning_rate": 4.916626244594793e-05, "loss": 4.5, "step": 2699 }, { "epoch": 0.0824679291386683, "grad_norm": 0.41055354475975037, "learning_rate": 4.9165647979580245e-05, "loss": 4.4591, "step": 2700 }, { "epoch": 0.08249847281612706, "grad_norm": 0.4190107583999634, "learning_rate": 4.916503329070702e-05, "loss": 4.4796, "step": 2701 }, { "epoch": 0.08252901649358582, "grad_norm": 0.40367385745048523, "learning_rate": 4.9164418379333896e-05, "loss": 4.4365, "step": 2702 }, { "epoch": 0.0825595601710446, "grad_norm": 0.4081443250179291, "learning_rate": 4.916380324546656e-05, "loss": 4.3907, "step": 2703 }, { "epoch": 0.08259010384850336, "grad_norm": 0.40106624364852905, "learning_rate": 4.916318788911066e-05, "loss": 4.3974, "step": 2704 }, { "epoch": 0.08262064752596213, "grad_norm": 0.3941554129123688, "learning_rate": 4.916257231027186e-05, "loss": 4.3933, "step": 2705 }, { "epoch": 0.08265119120342089, "grad_norm": 0.41363421082496643, "learning_rate": 4.9161956508955834e-05, "loss": 4.4799, "step": 2706 }, { "epoch": 0.08268173488087965, "grad_norm": 0.43041062355041504, "learning_rate": 4.9161340485168264e-05, "loss": 4.4637, "step": 2707 }, { "epoch": 0.08271227855833842, "grad_norm": 0.4099506735801697, "learning_rate": 4.9160724238914795e-05, "loss": 4.4536, "step": 2708 }, { "epoch": 0.0827428222357972, "grad_norm": 0.4129907190799713, "learning_rate": 4.9160107770201126e-05, "loss": 4.3733, "step": 2709 }, { "epoch": 0.08277336591325596, "grad_norm": 0.42270901799201965, "learning_rate": 4.9159491079032915e-05, "loss": 4.4646, "step": 2710 }, { "epoch": 0.08280390959071472, "grad_norm": 0.40894705057144165, "learning_rate": 4.915887416541585e-05, "loss": 4.4041, "step": 2711 }, { "epoch": 0.08283445326817349, "grad_norm": 0.42511001229286194, "learning_rate": 4.9158257029355616e-05, "loss": 4.4344, "step": 2712 }, { "epoch": 0.08286499694563225, "grad_norm": 0.40796470642089844, "learning_rate": 4.915763967085788e-05, "loss": 4.4436, "step": 2713 }, { "epoch": 0.08289554062309103, "grad_norm": 0.4081709384918213, "learning_rate": 4.915702208992834e-05, "loss": 4.4565, "step": 2714 }, { "epoch": 0.08292608430054979, "grad_norm": 0.38983678817749023, "learning_rate": 4.915640428657267e-05, "loss": 4.4733, "step": 2715 }, { "epoch": 0.08295662797800855, "grad_norm": 0.4021712839603424, "learning_rate": 4.9155786260796575e-05, "loss": 4.4285, "step": 2716 }, { "epoch": 0.08298717165546732, "grad_norm": 0.3938550055027008, "learning_rate": 4.915516801260573e-05, "loss": 4.3861, "step": 2717 }, { "epoch": 0.08301771533292608, "grad_norm": 0.40984922647476196, "learning_rate": 4.915454954200583e-05, "loss": 4.4196, "step": 2718 }, { "epoch": 0.08304825901038485, "grad_norm": 0.405264288187027, "learning_rate": 4.915393084900259e-05, "loss": 4.4895, "step": 2719 }, { "epoch": 0.08307880268784362, "grad_norm": 0.4015558660030365, "learning_rate": 4.915331193360168e-05, "loss": 4.3857, "step": 2720 }, { "epoch": 0.08310934636530239, "grad_norm": 0.4021953046321869, "learning_rate": 4.9152692795808805e-05, "loss": 4.465, "step": 2721 }, { "epoch": 0.08313989004276115, "grad_norm": 0.40429913997650146, "learning_rate": 4.9152073435629674e-05, "loss": 4.4712, "step": 2722 }, { "epoch": 0.08317043372021991, "grad_norm": 0.40219846367836, "learning_rate": 4.9151453853069985e-05, "loss": 4.4312, "step": 2723 }, { "epoch": 0.08320097739767868, "grad_norm": 0.4096568524837494, "learning_rate": 4.915083404813544e-05, "loss": 4.488, "step": 2724 }, { "epoch": 0.08323152107513744, "grad_norm": 0.4026678800582886, "learning_rate": 4.915021402083175e-05, "loss": 4.3263, "step": 2725 }, { "epoch": 0.08326206475259622, "grad_norm": 0.42120465636253357, "learning_rate": 4.914959377116463e-05, "loss": 4.4672, "step": 2726 }, { "epoch": 0.08329260843005498, "grad_norm": 0.41178804636001587, "learning_rate": 4.914897329913977e-05, "loss": 4.5148, "step": 2727 }, { "epoch": 0.08332315210751375, "grad_norm": 0.39924344420433044, "learning_rate": 4.9148352604762904e-05, "loss": 4.4202, "step": 2728 }, { "epoch": 0.08335369578497251, "grad_norm": 0.4139311909675598, "learning_rate": 4.9147731688039735e-05, "loss": 4.4143, "step": 2729 }, { "epoch": 0.08338423946243127, "grad_norm": 0.4081503450870514, "learning_rate": 4.9147110548975995e-05, "loss": 4.4423, "step": 2730 }, { "epoch": 0.08341478313989004, "grad_norm": 0.4146951138973236, "learning_rate": 4.914648918757738e-05, "loss": 4.4953, "step": 2731 }, { "epoch": 0.08344532681734881, "grad_norm": 0.40617331862449646, "learning_rate": 4.9145867603849635e-05, "loss": 4.366, "step": 2732 }, { "epoch": 0.08347587049480758, "grad_norm": 0.414436399936676, "learning_rate": 4.914524579779847e-05, "loss": 4.4206, "step": 2733 }, { "epoch": 0.08350641417226634, "grad_norm": 0.4129142761230469, "learning_rate": 4.914462376942961e-05, "loss": 4.4039, "step": 2734 }, { "epoch": 0.0835369578497251, "grad_norm": 0.40055444836616516, "learning_rate": 4.9144001518748786e-05, "loss": 4.3585, "step": 2735 }, { "epoch": 0.08356750152718387, "grad_norm": 0.42470070719718933, "learning_rate": 4.914337904576173e-05, "loss": 4.3384, "step": 2736 }, { "epoch": 0.08359804520464265, "grad_norm": 0.40684396028518677, "learning_rate": 4.914275635047416e-05, "loss": 4.3936, "step": 2737 }, { "epoch": 0.08362858888210141, "grad_norm": 0.39569488167762756, "learning_rate": 4.914213343289182e-05, "loss": 4.3594, "step": 2738 }, { "epoch": 0.08365913255956017, "grad_norm": 0.3989909291267395, "learning_rate": 4.9141510293020454e-05, "loss": 4.4521, "step": 2739 }, { "epoch": 0.08368967623701894, "grad_norm": 0.40404897928237915, "learning_rate": 4.9140886930865794e-05, "loss": 4.3979, "step": 2740 }, { "epoch": 0.0837202199144777, "grad_norm": 0.40013352036476135, "learning_rate": 4.914026334643357e-05, "loss": 4.5084, "step": 2741 }, { "epoch": 0.08375076359193646, "grad_norm": 0.42034247517585754, "learning_rate": 4.913963953972952e-05, "loss": 4.4525, "step": 2742 }, { "epoch": 0.08378130726939524, "grad_norm": 0.9109196066856384, "learning_rate": 4.913901551075941e-05, "loss": 4.4579, "step": 2743 }, { "epoch": 0.083811850946854, "grad_norm": 0.38809698820114136, "learning_rate": 4.913839125952897e-05, "loss": 4.3515, "step": 2744 }, { "epoch": 0.08384239462431277, "grad_norm": 0.40398141741752625, "learning_rate": 4.913776678604395e-05, "loss": 4.4067, "step": 2745 }, { "epoch": 0.08387293830177153, "grad_norm": 0.4281899929046631, "learning_rate": 4.91371420903101e-05, "loss": 4.5012, "step": 2746 }, { "epoch": 0.0839034819792303, "grad_norm": 0.3930248022079468, "learning_rate": 4.9136517172333176e-05, "loss": 4.3927, "step": 2747 }, { "epoch": 0.08393402565668906, "grad_norm": 0.3941539227962494, "learning_rate": 4.913589203211892e-05, "loss": 4.4294, "step": 2748 }, { "epoch": 0.08396456933414784, "grad_norm": 0.4157954454421997, "learning_rate": 4.913526666967311e-05, "loss": 4.466, "step": 2749 }, { "epoch": 0.0839951130116066, "grad_norm": 0.4001386761665344, "learning_rate": 4.913464108500148e-05, "loss": 4.3752, "step": 2750 }, { "epoch": 0.08402565668906536, "grad_norm": 0.39332014322280884, "learning_rate": 4.91340152781098e-05, "loss": 4.3806, "step": 2751 }, { "epoch": 0.08405620036652413, "grad_norm": 0.4094865322113037, "learning_rate": 4.9133389249003844e-05, "loss": 4.4534, "step": 2752 }, { "epoch": 0.08408674404398289, "grad_norm": 0.38655632734298706, "learning_rate": 4.913276299768935e-05, "loss": 4.4004, "step": 2753 }, { "epoch": 0.08411728772144166, "grad_norm": 0.39551931619644165, "learning_rate": 4.913213652417211e-05, "loss": 4.3884, "step": 2754 }, { "epoch": 0.08414783139890043, "grad_norm": 0.40035170316696167, "learning_rate": 4.913150982845788e-05, "loss": 4.4256, "step": 2755 }, { "epoch": 0.0841783750763592, "grad_norm": 0.4091048240661621, "learning_rate": 4.9130882910552434e-05, "loss": 4.4671, "step": 2756 }, { "epoch": 0.08420891875381796, "grad_norm": 0.40384387969970703, "learning_rate": 4.913025577046154e-05, "loss": 4.4268, "step": 2757 }, { "epoch": 0.08423946243127672, "grad_norm": 0.3946152627468109, "learning_rate": 4.912962840819097e-05, "loss": 4.4011, "step": 2758 }, { "epoch": 0.08427000610873549, "grad_norm": 0.3935520052909851, "learning_rate": 4.9129000823746504e-05, "loss": 4.3837, "step": 2759 }, { "epoch": 0.08430054978619425, "grad_norm": 0.4153023362159729, "learning_rate": 4.912837301713393e-05, "loss": 4.394, "step": 2760 }, { "epoch": 0.08433109346365303, "grad_norm": 0.4115281105041504, "learning_rate": 4.912774498835901e-05, "loss": 4.4207, "step": 2761 }, { "epoch": 0.08436163714111179, "grad_norm": 0.40466243028640747, "learning_rate": 4.9127116737427544e-05, "loss": 4.5094, "step": 2762 }, { "epoch": 0.08439218081857056, "grad_norm": 0.39938852190971375, "learning_rate": 4.9126488264345314e-05, "loss": 4.4253, "step": 2763 }, { "epoch": 0.08442272449602932, "grad_norm": 0.401082843542099, "learning_rate": 4.9125859569118094e-05, "loss": 4.4159, "step": 2764 }, { "epoch": 0.08445326817348808, "grad_norm": 0.40070411562919617, "learning_rate": 4.912523065175169e-05, "loss": 4.4037, "step": 2765 }, { "epoch": 0.08448381185094686, "grad_norm": 0.4221881628036499, "learning_rate": 4.9124601512251865e-05, "loss": 4.4031, "step": 2766 }, { "epoch": 0.08451435552840562, "grad_norm": 0.3933405876159668, "learning_rate": 4.912397215062444e-05, "loss": 4.4645, "step": 2767 }, { "epoch": 0.08454489920586439, "grad_norm": 0.4096081852912903, "learning_rate": 4.912334256687521e-05, "loss": 4.4415, "step": 2768 }, { "epoch": 0.08457544288332315, "grad_norm": 0.39068281650543213, "learning_rate": 4.912271276100995e-05, "loss": 4.3248, "step": 2769 }, { "epoch": 0.08460598656078192, "grad_norm": 0.4112078547477722, "learning_rate": 4.912208273303447e-05, "loss": 4.4446, "step": 2770 }, { "epoch": 0.08463653023824068, "grad_norm": 0.419338196516037, "learning_rate": 4.912145248295458e-05, "loss": 4.4511, "step": 2771 }, { "epoch": 0.08466707391569946, "grad_norm": 0.41782352328300476, "learning_rate": 4.912082201077607e-05, "loss": 4.5018, "step": 2772 }, { "epoch": 0.08469761759315822, "grad_norm": 0.39575454592704773, "learning_rate": 4.912019131650475e-05, "loss": 4.4299, "step": 2773 }, { "epoch": 0.08472816127061698, "grad_norm": 0.4046315550804138, "learning_rate": 4.911956040014642e-05, "loss": 4.3692, "step": 2774 }, { "epoch": 0.08475870494807575, "grad_norm": 0.41077062487602234, "learning_rate": 4.911892926170692e-05, "loss": 4.4613, "step": 2775 }, { "epoch": 0.08478924862553451, "grad_norm": 0.4016912281513214, "learning_rate": 4.911829790119201e-05, "loss": 4.3443, "step": 2776 }, { "epoch": 0.08481979230299327, "grad_norm": 0.4127584397792816, "learning_rate": 4.9117666318607546e-05, "loss": 4.4446, "step": 2777 }, { "epoch": 0.08485033598045205, "grad_norm": 0.41027846932411194, "learning_rate": 4.911703451395933e-05, "loss": 4.4091, "step": 2778 }, { "epoch": 0.08488087965791082, "grad_norm": 0.4123569130897522, "learning_rate": 4.9116402487253164e-05, "loss": 4.3751, "step": 2779 }, { "epoch": 0.08491142333536958, "grad_norm": 0.4131680727005005, "learning_rate": 4.91157702384949e-05, "loss": 4.4729, "step": 2780 }, { "epoch": 0.08494196701282834, "grad_norm": 0.40098413825035095, "learning_rate": 4.911513776769032e-05, "loss": 4.4161, "step": 2781 }, { "epoch": 0.0849725106902871, "grad_norm": 0.40249761939048767, "learning_rate": 4.911450507484529e-05, "loss": 4.4418, "step": 2782 }, { "epoch": 0.08500305436774587, "grad_norm": 0.40744099020957947, "learning_rate": 4.911387215996559e-05, "loss": 4.4443, "step": 2783 }, { "epoch": 0.08503359804520465, "grad_norm": 0.42786040902137756, "learning_rate": 4.9113239023057087e-05, "loss": 4.4175, "step": 2784 }, { "epoch": 0.08506414172266341, "grad_norm": 0.4076559543609619, "learning_rate": 4.911260566412559e-05, "loss": 4.3705, "step": 2785 }, { "epoch": 0.08509468540012217, "grad_norm": 0.404721736907959, "learning_rate": 4.9111972083176925e-05, "loss": 4.4345, "step": 2786 }, { "epoch": 0.08512522907758094, "grad_norm": 0.4117205739021301, "learning_rate": 4.911133828021695e-05, "loss": 4.4621, "step": 2787 }, { "epoch": 0.0851557727550397, "grad_norm": 0.41077494621276855, "learning_rate": 4.911070425525148e-05, "loss": 4.4583, "step": 2788 }, { "epoch": 0.08518631643249848, "grad_norm": 0.41602882742881775, "learning_rate": 4.911007000828637e-05, "loss": 4.4838, "step": 2789 }, { "epoch": 0.08521686010995724, "grad_norm": 0.41642582416534424, "learning_rate": 4.9109435539327436e-05, "loss": 4.445, "step": 2790 }, { "epoch": 0.085247403787416, "grad_norm": 0.41621237993240356, "learning_rate": 4.9108800848380536e-05, "loss": 4.43, "step": 2791 }, { "epoch": 0.08527794746487477, "grad_norm": 0.4086666703224182, "learning_rate": 4.9108165935451514e-05, "loss": 4.4031, "step": 2792 }, { "epoch": 0.08530849114233353, "grad_norm": 0.39866241812705994, "learning_rate": 4.9107530800546206e-05, "loss": 4.4544, "step": 2793 }, { "epoch": 0.0853390348197923, "grad_norm": 0.4023692309856415, "learning_rate": 4.910689544367047e-05, "loss": 4.4731, "step": 2794 }, { "epoch": 0.08536957849725108, "grad_norm": 0.40270736813545227, "learning_rate": 4.910625986483016e-05, "loss": 4.4738, "step": 2795 }, { "epoch": 0.08540012217470984, "grad_norm": 0.4063119888305664, "learning_rate": 4.910562406403112e-05, "loss": 4.4192, "step": 2796 }, { "epoch": 0.0854306658521686, "grad_norm": 0.4163685142993927, "learning_rate": 4.91049880412792e-05, "loss": 4.469, "step": 2797 }, { "epoch": 0.08546120952962737, "grad_norm": 0.4104331433773041, "learning_rate": 4.910435179658027e-05, "loss": 4.4072, "step": 2798 }, { "epoch": 0.08549175320708613, "grad_norm": 0.40204906463623047, "learning_rate": 4.9103715329940166e-05, "loss": 4.486, "step": 2799 }, { "epoch": 0.0855222968845449, "grad_norm": 0.4119405448436737, "learning_rate": 4.9103078641364776e-05, "loss": 4.4589, "step": 2800 }, { "epoch": 0.08555284056200367, "grad_norm": 0.412751168012619, "learning_rate": 4.9102441730859944e-05, "loss": 4.4271, "step": 2801 }, { "epoch": 0.08558338423946243, "grad_norm": 0.401032030582428, "learning_rate": 4.910180459843153e-05, "loss": 4.4617, "step": 2802 }, { "epoch": 0.0856139279169212, "grad_norm": 0.40527692437171936, "learning_rate": 4.9101167244085425e-05, "loss": 4.3009, "step": 2803 }, { "epoch": 0.08564447159437996, "grad_norm": 0.4273693561553955, "learning_rate": 4.910052966782747e-05, "loss": 4.4906, "step": 2804 }, { "epoch": 0.08567501527183873, "grad_norm": 0.4040946364402771, "learning_rate": 4.909989186966355e-05, "loss": 4.3833, "step": 2805 }, { "epoch": 0.08570555894929749, "grad_norm": 0.4148387312889099, "learning_rate": 4.9099253849599536e-05, "loss": 4.445, "step": 2806 }, { "epoch": 0.08573610262675627, "grad_norm": 0.4192046821117401, "learning_rate": 4.9098615607641296e-05, "loss": 4.3582, "step": 2807 }, { "epoch": 0.08576664630421503, "grad_norm": 0.4121721386909485, "learning_rate": 4.909797714379471e-05, "loss": 4.4868, "step": 2808 }, { "epoch": 0.0857971899816738, "grad_norm": 0.4061965048313141, "learning_rate": 4.909733845806567e-05, "loss": 4.3903, "step": 2809 }, { "epoch": 0.08582773365913256, "grad_norm": 0.4283701777458191, "learning_rate": 4.909669955046004e-05, "loss": 4.3799, "step": 2810 }, { "epoch": 0.08585827733659132, "grad_norm": 0.4007856845855713, "learning_rate": 4.9096060420983706e-05, "loss": 4.4009, "step": 2811 }, { "epoch": 0.0858888210140501, "grad_norm": 0.4271771013736725, "learning_rate": 4.9095421069642556e-05, "loss": 4.4363, "step": 2812 }, { "epoch": 0.08591936469150886, "grad_norm": 0.42170846462249756, "learning_rate": 4.909478149644248e-05, "loss": 4.5119, "step": 2813 }, { "epoch": 0.08594990836896763, "grad_norm": 0.41613247990608215, "learning_rate": 4.909414170138935e-05, "loss": 4.3647, "step": 2814 }, { "epoch": 0.08598045204642639, "grad_norm": 0.4072566628456116, "learning_rate": 4.909350168448908e-05, "loss": 4.3996, "step": 2815 }, { "epoch": 0.08601099572388515, "grad_norm": 0.42066481709480286, "learning_rate": 4.909286144574755e-05, "loss": 4.4859, "step": 2816 }, { "epoch": 0.08604153940134392, "grad_norm": 0.40701907873153687, "learning_rate": 4.909222098517066e-05, "loss": 4.4207, "step": 2817 }, { "epoch": 0.0860720830788027, "grad_norm": 0.4023703336715698, "learning_rate": 4.90915803027643e-05, "loss": 4.4532, "step": 2818 }, { "epoch": 0.08610262675626146, "grad_norm": 0.39996641874313354, "learning_rate": 4.9090939398534377e-05, "loss": 4.3558, "step": 2819 }, { "epoch": 0.08613317043372022, "grad_norm": 0.4156898558139801, "learning_rate": 4.909029827248679e-05, "loss": 4.337, "step": 2820 }, { "epoch": 0.08616371411117899, "grad_norm": 0.4122028946876526, "learning_rate": 4.908965692462744e-05, "loss": 4.4957, "step": 2821 }, { "epoch": 0.08619425778863775, "grad_norm": 0.4198831617832184, "learning_rate": 4.908901535496222e-05, "loss": 4.3471, "step": 2822 }, { "epoch": 0.08622480146609651, "grad_norm": 0.41601046919822693, "learning_rate": 4.9088373563497066e-05, "loss": 4.4839, "step": 2823 }, { "epoch": 0.08625534514355529, "grad_norm": 0.4086710214614868, "learning_rate": 4.908773155023787e-05, "loss": 4.3966, "step": 2824 }, { "epoch": 0.08628588882101405, "grad_norm": 0.41050246357917786, "learning_rate": 4.908708931519054e-05, "loss": 4.4505, "step": 2825 }, { "epoch": 0.08631643249847282, "grad_norm": 0.40862080454826355, "learning_rate": 4.9086446858360994e-05, "loss": 4.4262, "step": 2826 }, { "epoch": 0.08634697617593158, "grad_norm": 0.41373780369758606, "learning_rate": 4.9085804179755144e-05, "loss": 4.3975, "step": 2827 }, { "epoch": 0.08637751985339034, "grad_norm": 0.41257789731025696, "learning_rate": 4.908516127937892e-05, "loss": 4.3391, "step": 2828 }, { "epoch": 0.08640806353084911, "grad_norm": 0.39160364866256714, "learning_rate": 4.9084518157238226e-05, "loss": 4.4679, "step": 2829 }, { "epoch": 0.08643860720830789, "grad_norm": 0.4104714095592499, "learning_rate": 4.9083874813338995e-05, "loss": 4.4636, "step": 2830 }, { "epoch": 0.08646915088576665, "grad_norm": 0.39895713329315186, "learning_rate": 4.908323124768715e-05, "loss": 4.3945, "step": 2831 }, { "epoch": 0.08649969456322541, "grad_norm": 0.40412476658821106, "learning_rate": 4.90825874602886e-05, "loss": 4.391, "step": 2832 }, { "epoch": 0.08653023824068418, "grad_norm": 0.4229419529438019, "learning_rate": 4.908194345114929e-05, "loss": 4.4611, "step": 2833 }, { "epoch": 0.08656078191814294, "grad_norm": 0.40735122561454773, "learning_rate": 4.908129922027515e-05, "loss": 4.4309, "step": 2834 }, { "epoch": 0.0865913255956017, "grad_norm": 0.40765121579170227, "learning_rate": 4.9080654767672106e-05, "loss": 4.4238, "step": 2835 }, { "epoch": 0.08662186927306048, "grad_norm": 0.4086636006832123, "learning_rate": 4.9080010093346085e-05, "loss": 4.4319, "step": 2836 }, { "epoch": 0.08665241295051924, "grad_norm": 0.4055427014827728, "learning_rate": 4.907936519730304e-05, "loss": 4.4216, "step": 2837 }, { "epoch": 0.08668295662797801, "grad_norm": 0.39381352066993713, "learning_rate": 4.907872007954889e-05, "loss": 4.2726, "step": 2838 }, { "epoch": 0.08671350030543677, "grad_norm": 0.4019734561443329, "learning_rate": 4.907807474008959e-05, "loss": 4.3463, "step": 2839 }, { "epoch": 0.08674404398289554, "grad_norm": 0.398861289024353, "learning_rate": 4.907742917893108e-05, "loss": 4.3608, "step": 2840 }, { "epoch": 0.08677458766035431, "grad_norm": 0.3924410045146942, "learning_rate": 4.90767833960793e-05, "loss": 4.4173, "step": 2841 }, { "epoch": 0.08680513133781308, "grad_norm": 0.4022071659564972, "learning_rate": 4.9076137391540184e-05, "loss": 4.3839, "step": 2842 }, { "epoch": 0.08683567501527184, "grad_norm": 0.40076160430908203, "learning_rate": 4.90754911653197e-05, "loss": 4.322, "step": 2843 }, { "epoch": 0.0868662186927306, "grad_norm": 0.4233126640319824, "learning_rate": 4.907484471742379e-05, "loss": 4.4847, "step": 2844 }, { "epoch": 0.08689676237018937, "grad_norm": 0.4151476323604584, "learning_rate": 4.907419804785841e-05, "loss": 4.4207, "step": 2845 }, { "epoch": 0.08692730604764813, "grad_norm": 0.4109843373298645, "learning_rate": 4.907355115662951e-05, "loss": 4.4477, "step": 2846 }, { "epoch": 0.08695784972510691, "grad_norm": 0.4196605384349823, "learning_rate": 4.907290404374304e-05, "loss": 4.484, "step": 2847 }, { "epoch": 0.08698839340256567, "grad_norm": 0.4029078781604767, "learning_rate": 4.9072256709204967e-05, "loss": 4.4254, "step": 2848 }, { "epoch": 0.08701893708002444, "grad_norm": 0.41186901926994324, "learning_rate": 4.9071609153021256e-05, "loss": 4.4498, "step": 2849 }, { "epoch": 0.0870494807574832, "grad_norm": 0.41753530502319336, "learning_rate": 4.9070961375197864e-05, "loss": 4.4419, "step": 2850 }, { "epoch": 0.08708002443494196, "grad_norm": 0.40425100922584534, "learning_rate": 4.9070313375740745e-05, "loss": 4.4423, "step": 2851 }, { "epoch": 0.08711056811240073, "grad_norm": 0.40724867582321167, "learning_rate": 4.906966515465588e-05, "loss": 4.5092, "step": 2852 }, { "epoch": 0.0871411117898595, "grad_norm": 0.41424980759620667, "learning_rate": 4.9069016711949235e-05, "loss": 4.3551, "step": 2853 }, { "epoch": 0.08717165546731827, "grad_norm": 0.4079125225543976, "learning_rate": 4.906836804762678e-05, "loss": 4.3452, "step": 2854 }, { "epoch": 0.08720219914477703, "grad_norm": 0.4082481265068054, "learning_rate": 4.906771916169448e-05, "loss": 4.4495, "step": 2855 }, { "epoch": 0.0872327428222358, "grad_norm": 0.4148153066635132, "learning_rate": 4.906707005415831e-05, "loss": 4.4082, "step": 2856 }, { "epoch": 0.08726328649969456, "grad_norm": 0.4135620892047882, "learning_rate": 4.9066420725024265e-05, "loss": 4.3905, "step": 2857 }, { "epoch": 0.08729383017715332, "grad_norm": 0.3965367376804352, "learning_rate": 4.90657711742983e-05, "loss": 4.3984, "step": 2858 }, { "epoch": 0.0873243738546121, "grad_norm": 0.3982029855251312, "learning_rate": 4.906512140198641e-05, "loss": 4.4973, "step": 2859 }, { "epoch": 0.08735491753207086, "grad_norm": 0.405798077583313, "learning_rate": 4.9064471408094584e-05, "loss": 4.4146, "step": 2860 }, { "epoch": 0.08738546120952963, "grad_norm": 0.44612058997154236, "learning_rate": 4.906382119262879e-05, "loss": 4.4946, "step": 2861 }, { "epoch": 0.08741600488698839, "grad_norm": 0.41937583684921265, "learning_rate": 4.9063170755595015e-05, "loss": 4.4206, "step": 2862 }, { "epoch": 0.08744654856444715, "grad_norm": 0.4003184139728546, "learning_rate": 4.906252009699927e-05, "loss": 4.3269, "step": 2863 }, { "epoch": 0.08747709224190593, "grad_norm": 0.4063473641872406, "learning_rate": 4.906186921684751e-05, "loss": 4.4016, "step": 2864 }, { "epoch": 0.0875076359193647, "grad_norm": 0.41046807169914246, "learning_rate": 4.906121811514576e-05, "loss": 4.4487, "step": 2865 }, { "epoch": 0.08753817959682346, "grad_norm": 0.40817537903785706, "learning_rate": 4.906056679190001e-05, "loss": 4.3487, "step": 2866 }, { "epoch": 0.08756872327428222, "grad_norm": 0.4085542857646942, "learning_rate": 4.905991524711624e-05, "loss": 4.3775, "step": 2867 }, { "epoch": 0.08759926695174099, "grad_norm": 0.39974841475486755, "learning_rate": 4.905926348080046e-05, "loss": 4.4719, "step": 2868 }, { "epoch": 0.08762981062919975, "grad_norm": 0.41806119680404663, "learning_rate": 4.9058611492958676e-05, "loss": 4.4882, "step": 2869 }, { "epoch": 0.08766035430665853, "grad_norm": 0.4233667254447937, "learning_rate": 4.905795928359689e-05, "loss": 4.3054, "step": 2870 }, { "epoch": 0.08769089798411729, "grad_norm": 0.40066632628440857, "learning_rate": 4.90573068527211e-05, "loss": 4.3497, "step": 2871 }, { "epoch": 0.08772144166157606, "grad_norm": 0.4068450331687927, "learning_rate": 4.9056654200337314e-05, "loss": 4.4811, "step": 2872 }, { "epoch": 0.08775198533903482, "grad_norm": 0.4100181460380554, "learning_rate": 4.905600132645155e-05, "loss": 4.3657, "step": 2873 }, { "epoch": 0.08778252901649358, "grad_norm": 0.4157313108444214, "learning_rate": 4.905534823106981e-05, "loss": 4.4984, "step": 2874 }, { "epoch": 0.08781307269395235, "grad_norm": 0.4026559293270111, "learning_rate": 4.9054694914198106e-05, "loss": 4.4484, "step": 2875 }, { "epoch": 0.08784361637141112, "grad_norm": 0.42019498348236084, "learning_rate": 4.9054041375842465e-05, "loss": 4.4817, "step": 2876 }, { "epoch": 0.08787416004886989, "grad_norm": 0.400012344121933, "learning_rate": 4.90533876160089e-05, "loss": 4.3249, "step": 2877 }, { "epoch": 0.08790470372632865, "grad_norm": 0.4157779812812805, "learning_rate": 4.905273363470341e-05, "loss": 4.466, "step": 2878 }, { "epoch": 0.08793524740378741, "grad_norm": 0.40932604670524597, "learning_rate": 4.905207943193205e-05, "loss": 4.4718, "step": 2879 }, { "epoch": 0.08796579108124618, "grad_norm": 0.40922150015830994, "learning_rate": 4.905142500770082e-05, "loss": 4.4464, "step": 2880 }, { "epoch": 0.08799633475870494, "grad_norm": 0.41614460945129395, "learning_rate": 4.905077036201577e-05, "loss": 4.4243, "step": 2881 }, { "epoch": 0.08802687843616372, "grad_norm": 0.4041587710380554, "learning_rate": 4.90501154948829e-05, "loss": 4.4081, "step": 2882 }, { "epoch": 0.08805742211362248, "grad_norm": 0.40967151522636414, "learning_rate": 4.9049460406308256e-05, "loss": 4.4119, "step": 2883 }, { "epoch": 0.08808796579108125, "grad_norm": 0.4084016978740692, "learning_rate": 4.904880509629786e-05, "loss": 4.4443, "step": 2884 }, { "epoch": 0.08811850946854001, "grad_norm": 0.42879873514175415, "learning_rate": 4.904814956485775e-05, "loss": 4.4123, "step": 2885 }, { "epoch": 0.08814905314599877, "grad_norm": 0.41321882605552673, "learning_rate": 4.904749381199397e-05, "loss": 4.4756, "step": 2886 }, { "epoch": 0.08817959682345755, "grad_norm": 0.40831971168518066, "learning_rate": 4.904683783771254e-05, "loss": 4.405, "step": 2887 }, { "epoch": 0.08821014050091631, "grad_norm": 0.403434693813324, "learning_rate": 4.904618164201952e-05, "loss": 4.5172, "step": 2888 }, { "epoch": 0.08824068417837508, "grad_norm": 0.404968798160553, "learning_rate": 4.904552522492094e-05, "loss": 4.4067, "step": 2889 }, { "epoch": 0.08827122785583384, "grad_norm": 0.4138660430908203, "learning_rate": 4.9044868586422845e-05, "loss": 4.4477, "step": 2890 }, { "epoch": 0.0883017715332926, "grad_norm": 0.4069168269634247, "learning_rate": 4.904421172653128e-05, "loss": 4.5027, "step": 2891 }, { "epoch": 0.08833231521075137, "grad_norm": 0.39612647891044617, "learning_rate": 4.90435546452523e-05, "loss": 4.501, "step": 2892 }, { "epoch": 0.08836285888821015, "grad_norm": 0.4078986346721649, "learning_rate": 4.9042897342591945e-05, "loss": 4.4213, "step": 2893 }, { "epoch": 0.08839340256566891, "grad_norm": 0.4198762774467468, "learning_rate": 4.904223981855628e-05, "loss": 4.4098, "step": 2894 }, { "epoch": 0.08842394624312767, "grad_norm": 0.41962698101997375, "learning_rate": 4.904158207315134e-05, "loss": 4.5459, "step": 2895 }, { "epoch": 0.08845448992058644, "grad_norm": 0.40176764130592346, "learning_rate": 4.9040924106383204e-05, "loss": 4.4775, "step": 2896 }, { "epoch": 0.0884850335980452, "grad_norm": 0.42588406801223755, "learning_rate": 4.904026591825792e-05, "loss": 4.422, "step": 2897 }, { "epoch": 0.08851557727550396, "grad_norm": 0.4195308983325958, "learning_rate": 4.903960750878154e-05, "loss": 4.3544, "step": 2898 }, { "epoch": 0.08854612095296274, "grad_norm": 0.42113903164863586, "learning_rate": 4.903894887796013e-05, "loss": 4.4413, "step": 2899 }, { "epoch": 0.0885766646304215, "grad_norm": 0.4155084788799286, "learning_rate": 4.903829002579977e-05, "loss": 4.4549, "step": 2900 }, { "epoch": 0.08860720830788027, "grad_norm": 0.4101812243461609, "learning_rate": 4.9037630952306507e-05, "loss": 4.4716, "step": 2901 }, { "epoch": 0.08863775198533903, "grad_norm": 0.42207202315330505, "learning_rate": 4.903697165748642e-05, "loss": 4.4605, "step": 2902 }, { "epoch": 0.0886682956627978, "grad_norm": 0.41750338673591614, "learning_rate": 4.903631214134558e-05, "loss": 4.4345, "step": 2903 }, { "epoch": 0.08869883934025656, "grad_norm": 0.40839216113090515, "learning_rate": 4.903565240389004e-05, "loss": 4.4737, "step": 2904 }, { "epoch": 0.08872938301771534, "grad_norm": 0.4017690420150757, "learning_rate": 4.90349924451259e-05, "loss": 4.3504, "step": 2905 }, { "epoch": 0.0887599266951741, "grad_norm": 0.4223642647266388, "learning_rate": 4.9034332265059235e-05, "loss": 4.4481, "step": 2906 }, { "epoch": 0.08879047037263287, "grad_norm": 0.3998022973537445, "learning_rate": 4.903367186369611e-05, "loss": 4.487, "step": 2907 }, { "epoch": 0.08882101405009163, "grad_norm": 0.4177427589893341, "learning_rate": 4.903301124104261e-05, "loss": 4.4604, "step": 2908 }, { "epoch": 0.08885155772755039, "grad_norm": 0.4130134582519531, "learning_rate": 4.903235039710482e-05, "loss": 4.4058, "step": 2909 }, { "epoch": 0.08888210140500916, "grad_norm": 0.39583301544189453, "learning_rate": 4.903168933188882e-05, "loss": 4.3662, "step": 2910 }, { "epoch": 0.08891264508246793, "grad_norm": 0.4047951400279999, "learning_rate": 4.9031028045400704e-05, "loss": 4.463, "step": 2911 }, { "epoch": 0.0889431887599267, "grad_norm": 0.41240084171295166, "learning_rate": 4.903036653764656e-05, "loss": 4.4036, "step": 2912 }, { "epoch": 0.08897373243738546, "grad_norm": 0.42272138595581055, "learning_rate": 4.902970480863247e-05, "loss": 4.4489, "step": 2913 }, { "epoch": 0.08900427611484422, "grad_norm": 0.4045035243034363, "learning_rate": 4.9029042858364536e-05, "loss": 4.4886, "step": 2914 }, { "epoch": 0.08903481979230299, "grad_norm": 0.4151114225387573, "learning_rate": 4.902838068684885e-05, "loss": 4.3871, "step": 2915 }, { "epoch": 0.08906536346976177, "grad_norm": 0.41186296939849854, "learning_rate": 4.902771829409151e-05, "loss": 4.4672, "step": 2916 }, { "epoch": 0.08909590714722053, "grad_norm": 0.4057426452636719, "learning_rate": 4.902705568009861e-05, "loss": 4.4671, "step": 2917 }, { "epoch": 0.08912645082467929, "grad_norm": 0.4104883372783661, "learning_rate": 4.902639284487626e-05, "loss": 4.3578, "step": 2918 }, { "epoch": 0.08915699450213806, "grad_norm": 0.4108065962791443, "learning_rate": 4.902572978843055e-05, "loss": 4.4142, "step": 2919 }, { "epoch": 0.08918753817959682, "grad_norm": 0.39478495717048645, "learning_rate": 4.90250665107676e-05, "loss": 4.3028, "step": 2920 }, { "epoch": 0.08921808185705558, "grad_norm": 0.41311925649642944, "learning_rate": 4.902440301189351e-05, "loss": 4.4858, "step": 2921 }, { "epoch": 0.08924862553451436, "grad_norm": 0.40949052572250366, "learning_rate": 4.9023739291814386e-05, "loss": 4.5039, "step": 2922 }, { "epoch": 0.08927916921197313, "grad_norm": 0.4080256521701813, "learning_rate": 4.902307535053634e-05, "loss": 4.4012, "step": 2923 }, { "epoch": 0.08930971288943189, "grad_norm": 0.40619492530822754, "learning_rate": 4.9022411188065496e-05, "loss": 4.4065, "step": 2924 }, { "epoch": 0.08934025656689065, "grad_norm": 0.4041218161582947, "learning_rate": 4.902174680440795e-05, "loss": 4.3798, "step": 2925 }, { "epoch": 0.08937080024434942, "grad_norm": 0.41301262378692627, "learning_rate": 4.902108219956985e-05, "loss": 4.3987, "step": 2926 }, { "epoch": 0.08940134392180818, "grad_norm": 0.4131426215171814, "learning_rate": 4.902041737355728e-05, "loss": 4.4339, "step": 2927 }, { "epoch": 0.08943188759926696, "grad_norm": 0.3882763683795929, "learning_rate": 4.901975232637638e-05, "loss": 4.4533, "step": 2928 }, { "epoch": 0.08946243127672572, "grad_norm": 0.4011121988296509, "learning_rate": 4.901908705803327e-05, "loss": 4.4215, "step": 2929 }, { "epoch": 0.08949297495418448, "grad_norm": 0.40291741490364075, "learning_rate": 4.901842156853408e-05, "loss": 4.4388, "step": 2930 }, { "epoch": 0.08952351863164325, "grad_norm": 0.39865726232528687, "learning_rate": 4.901775585788493e-05, "loss": 4.4228, "step": 2931 }, { "epoch": 0.08955406230910201, "grad_norm": 0.39895525574684143, "learning_rate": 4.901708992609195e-05, "loss": 4.2769, "step": 2932 }, { "epoch": 0.08958460598656078, "grad_norm": 0.41666683554649353, "learning_rate": 4.901642377316128e-05, "loss": 4.3947, "step": 2933 }, { "epoch": 0.08961514966401955, "grad_norm": 0.4097975492477417, "learning_rate": 4.901575739909905e-05, "loss": 4.4373, "step": 2934 }, { "epoch": 0.08964569334147832, "grad_norm": 0.4057697653770447, "learning_rate": 4.901509080391139e-05, "loss": 4.4814, "step": 2935 }, { "epoch": 0.08967623701893708, "grad_norm": 0.39582812786102295, "learning_rate": 4.901442398760444e-05, "loss": 4.3402, "step": 2936 }, { "epoch": 0.08970678069639584, "grad_norm": 0.4137944281101227, "learning_rate": 4.901375695018434e-05, "loss": 4.4326, "step": 2937 }, { "epoch": 0.08973732437385461, "grad_norm": 0.39424949884414673, "learning_rate": 4.901308969165724e-05, "loss": 4.3813, "step": 2938 }, { "epoch": 0.08976786805131338, "grad_norm": 0.39666399359703064, "learning_rate": 4.901242221202927e-05, "loss": 4.4176, "step": 2939 }, { "epoch": 0.08979841172877215, "grad_norm": 0.41031545400619507, "learning_rate": 4.9011754511306585e-05, "loss": 4.4467, "step": 2940 }, { "epoch": 0.08982895540623091, "grad_norm": 0.40486472845077515, "learning_rate": 4.9011086589495335e-05, "loss": 4.406, "step": 2941 }, { "epoch": 0.08985949908368968, "grad_norm": 0.39375054836273193, "learning_rate": 4.901041844660166e-05, "loss": 4.3467, "step": 2942 }, { "epoch": 0.08989004276114844, "grad_norm": 0.3900916576385498, "learning_rate": 4.900975008263172e-05, "loss": 4.3838, "step": 2943 }, { "epoch": 0.0899205864386072, "grad_norm": 0.3957284390926361, "learning_rate": 4.9009081497591666e-05, "loss": 4.3738, "step": 2944 }, { "epoch": 0.08995113011606598, "grad_norm": 0.40791618824005127, "learning_rate": 4.900841269148766e-05, "loss": 4.4847, "step": 2945 }, { "epoch": 0.08998167379352474, "grad_norm": 0.4219895005226135, "learning_rate": 4.9007743664325846e-05, "loss": 4.3932, "step": 2946 }, { "epoch": 0.09001221747098351, "grad_norm": 0.4125772714614868, "learning_rate": 4.90070744161124e-05, "loss": 4.437, "step": 2947 }, { "epoch": 0.09004276114844227, "grad_norm": 0.40304818749427795, "learning_rate": 4.9006404946853466e-05, "loss": 4.523, "step": 2948 }, { "epoch": 0.09007330482590103, "grad_norm": 0.3988664746284485, "learning_rate": 4.900573525655523e-05, "loss": 4.4838, "step": 2949 }, { "epoch": 0.0901038485033598, "grad_norm": 0.41595083475112915, "learning_rate": 4.900506534522384e-05, "loss": 4.4873, "step": 2950 }, { "epoch": 0.09013439218081858, "grad_norm": 0.3955949544906616, "learning_rate": 4.900439521286547e-05, "loss": 4.3399, "step": 2951 }, { "epoch": 0.09016493585827734, "grad_norm": 0.4083910286426544, "learning_rate": 4.90037248594863e-05, "loss": 4.4821, "step": 2952 }, { "epoch": 0.0901954795357361, "grad_norm": 0.4048469364643097, "learning_rate": 4.9003054285092485e-05, "loss": 4.4241, "step": 2953 }, { "epoch": 0.09022602321319487, "grad_norm": 0.4220561981201172, "learning_rate": 4.9002383489690215e-05, "loss": 4.4786, "step": 2954 }, { "epoch": 0.09025656689065363, "grad_norm": 0.40516898036003113, "learning_rate": 4.900171247328566e-05, "loss": 4.4151, "step": 2955 }, { "epoch": 0.0902871105681124, "grad_norm": 0.41232728958129883, "learning_rate": 4.900104123588499e-05, "loss": 4.3344, "step": 2956 }, { "epoch": 0.09031765424557117, "grad_norm": 0.4031190574169159, "learning_rate": 4.900036977749439e-05, "loss": 4.3931, "step": 2957 }, { "epoch": 0.09034819792302994, "grad_norm": 0.4070000648498535, "learning_rate": 4.899969809812006e-05, "loss": 4.4733, "step": 2958 }, { "epoch": 0.0903787416004887, "grad_norm": 0.395289808511734, "learning_rate": 4.899902619776816e-05, "loss": 4.4445, "step": 2959 }, { "epoch": 0.09040928527794746, "grad_norm": 0.41279277205467224, "learning_rate": 4.899835407644489e-05, "loss": 4.4523, "step": 2960 }, { "epoch": 0.09043982895540623, "grad_norm": 0.40902426838874817, "learning_rate": 4.899768173415643e-05, "loss": 4.5159, "step": 2961 }, { "epoch": 0.090470372632865, "grad_norm": 0.40309199690818787, "learning_rate": 4.899700917090898e-05, "loss": 4.4823, "step": 2962 }, { "epoch": 0.09050091631032377, "grad_norm": 0.39721423387527466, "learning_rate": 4.899633638670873e-05, "loss": 4.4471, "step": 2963 }, { "epoch": 0.09053145998778253, "grad_norm": 0.41435644030570984, "learning_rate": 4.8995663381561876e-05, "loss": 4.4052, "step": 2964 }, { "epoch": 0.0905620036652413, "grad_norm": 0.39415934681892395, "learning_rate": 4.8994990155474605e-05, "loss": 4.413, "step": 2965 }, { "epoch": 0.09059254734270006, "grad_norm": 0.39604321122169495, "learning_rate": 4.899431670845312e-05, "loss": 4.3742, "step": 2966 }, { "epoch": 0.09062309102015882, "grad_norm": 0.40716448426246643, "learning_rate": 4.899364304050364e-05, "loss": 4.3642, "step": 2967 }, { "epoch": 0.0906536346976176, "grad_norm": 0.40374428033828735, "learning_rate": 4.899296915163234e-05, "loss": 4.5014, "step": 2968 }, { "epoch": 0.09068417837507636, "grad_norm": 0.4010154902935028, "learning_rate": 4.8992295041845435e-05, "loss": 4.415, "step": 2969 }, { "epoch": 0.09071472205253513, "grad_norm": 0.41216394305229187, "learning_rate": 4.8991620711149145e-05, "loss": 4.4319, "step": 2970 }, { "epoch": 0.09074526572999389, "grad_norm": 0.4035063683986664, "learning_rate": 4.899094615954966e-05, "loss": 4.342, "step": 2971 }, { "epoch": 0.09077580940745265, "grad_norm": 0.4347401559352875, "learning_rate": 4.89902713870532e-05, "loss": 4.4057, "step": 2972 }, { "epoch": 0.09080635308491142, "grad_norm": 0.42719560861587524, "learning_rate": 4.898959639366598e-05, "loss": 4.4614, "step": 2973 }, { "epoch": 0.0908368967623702, "grad_norm": 0.40642035007476807, "learning_rate": 4.898892117939421e-05, "loss": 4.4625, "step": 2974 }, { "epoch": 0.09086744043982896, "grad_norm": 0.4166548550128937, "learning_rate": 4.8988245744244106e-05, "loss": 4.4354, "step": 2975 }, { "epoch": 0.09089798411728772, "grad_norm": 0.4288259446620941, "learning_rate": 4.898757008822189e-05, "loss": 4.4386, "step": 2976 }, { "epoch": 0.09092852779474649, "grad_norm": 0.42446452379226685, "learning_rate": 4.8986894211333786e-05, "loss": 4.3977, "step": 2977 }, { "epoch": 0.09095907147220525, "grad_norm": 0.39215603470802307, "learning_rate": 4.898621811358601e-05, "loss": 4.4241, "step": 2978 }, { "epoch": 0.09098961514966401, "grad_norm": 0.40283849835395813, "learning_rate": 4.89855417949848e-05, "loss": 4.3236, "step": 2979 }, { "epoch": 0.09102015882712279, "grad_norm": 0.41904470324516296, "learning_rate": 4.898486525553636e-05, "loss": 4.4816, "step": 2980 }, { "epoch": 0.09105070250458155, "grad_norm": 0.39687031507492065, "learning_rate": 4.898418849524695e-05, "loss": 4.3258, "step": 2981 }, { "epoch": 0.09108124618204032, "grad_norm": 0.4119867980480194, "learning_rate": 4.898351151412277e-05, "loss": 4.46, "step": 2982 }, { "epoch": 0.09111178985949908, "grad_norm": 0.4040447771549225, "learning_rate": 4.898283431217008e-05, "loss": 4.319, "step": 2983 }, { "epoch": 0.09114233353695785, "grad_norm": 0.40842172503471375, "learning_rate": 4.89821568893951e-05, "loss": 4.446, "step": 2984 }, { "epoch": 0.09117287721441661, "grad_norm": 0.4027288258075714, "learning_rate": 4.898147924580407e-05, "loss": 4.4847, "step": 2985 }, { "epoch": 0.09120342089187539, "grad_norm": 0.4185378849506378, "learning_rate": 4.898080138140323e-05, "loss": 4.4097, "step": 2986 }, { "epoch": 0.09123396456933415, "grad_norm": 0.40303900837898254, "learning_rate": 4.898012329619882e-05, "loss": 4.4259, "step": 2987 }, { "epoch": 0.09126450824679291, "grad_norm": 0.4013930857181549, "learning_rate": 4.897944499019709e-05, "loss": 4.4276, "step": 2988 }, { "epoch": 0.09129505192425168, "grad_norm": 0.408066987991333, "learning_rate": 4.897876646340428e-05, "loss": 4.5239, "step": 2989 }, { "epoch": 0.09132559560171044, "grad_norm": 0.4042193293571472, "learning_rate": 4.897808771582664e-05, "loss": 4.4792, "step": 2990 }, { "epoch": 0.09135613927916922, "grad_norm": 0.40603870153427124, "learning_rate": 4.8977408747470416e-05, "loss": 4.4483, "step": 2991 }, { "epoch": 0.09138668295662798, "grad_norm": 0.41455820202827454, "learning_rate": 4.897672955834186e-05, "loss": 4.4737, "step": 2992 }, { "epoch": 0.09141722663408675, "grad_norm": 0.40953704714775085, "learning_rate": 4.897605014844723e-05, "loss": 4.478, "step": 2993 }, { "epoch": 0.09144777031154551, "grad_norm": 0.4092279076576233, "learning_rate": 4.8975370517792775e-05, "loss": 4.3344, "step": 2994 }, { "epoch": 0.09147831398900427, "grad_norm": 0.4208076596260071, "learning_rate": 4.8974690666384757e-05, "loss": 4.4368, "step": 2995 }, { "epoch": 0.09150885766646304, "grad_norm": 0.419132262468338, "learning_rate": 4.897401059422945e-05, "loss": 4.4891, "step": 2996 }, { "epoch": 0.09153940134392181, "grad_norm": 0.4957329034805298, "learning_rate": 4.8973330301333085e-05, "loss": 4.4054, "step": 2997 }, { "epoch": 0.09156994502138058, "grad_norm": 0.40170788764953613, "learning_rate": 4.897264978770195e-05, "loss": 4.4532, "step": 2998 }, { "epoch": 0.09160048869883934, "grad_norm": 0.40579086542129517, "learning_rate": 4.897196905334229e-05, "loss": 4.3056, "step": 2999 }, { "epoch": 0.0916310323762981, "grad_norm": 0.4239312708377838, "learning_rate": 4.8971288098260406e-05, "loss": 4.3258, "step": 3000 }, { "epoch": 0.09166157605375687, "grad_norm": 0.4110688865184784, "learning_rate": 4.897060692246253e-05, "loss": 4.5191, "step": 3001 }, { "epoch": 0.09169211973121563, "grad_norm": 0.41533514857292175, "learning_rate": 4.896992552595496e-05, "loss": 4.4579, "step": 3002 }, { "epoch": 0.09172266340867441, "grad_norm": 0.4073970317840576, "learning_rate": 4.8969243908743956e-05, "loss": 4.4263, "step": 3003 }, { "epoch": 0.09175320708613317, "grad_norm": 0.4230509102344513, "learning_rate": 4.8968562070835814e-05, "loss": 4.4925, "step": 3004 }, { "epoch": 0.09178375076359194, "grad_norm": 0.41344118118286133, "learning_rate": 4.8967880012236774e-05, "loss": 4.2955, "step": 3005 }, { "epoch": 0.0918142944410507, "grad_norm": 0.4206427335739136, "learning_rate": 4.896719773295316e-05, "loss": 4.331, "step": 3006 }, { "epoch": 0.09184483811850946, "grad_norm": 0.42661529779434204, "learning_rate": 4.8966515232991226e-05, "loss": 4.4822, "step": 3007 }, { "epoch": 0.09187538179596823, "grad_norm": 0.4122799038887024, "learning_rate": 4.8965832512357266e-05, "loss": 4.3236, "step": 3008 }, { "epoch": 0.091905925473427, "grad_norm": 0.4185548722743988, "learning_rate": 4.896514957105756e-05, "loss": 4.4695, "step": 3009 }, { "epoch": 0.09193646915088577, "grad_norm": 0.41199079155921936, "learning_rate": 4.89644664090984e-05, "loss": 4.3444, "step": 3010 }, { "epoch": 0.09196701282834453, "grad_norm": 0.423309862613678, "learning_rate": 4.8963783026486084e-05, "loss": 4.4977, "step": 3011 }, { "epoch": 0.0919975565058033, "grad_norm": 0.42862093448638916, "learning_rate": 4.8963099423226886e-05, "loss": 4.4975, "step": 3012 }, { "epoch": 0.09202810018326206, "grad_norm": 0.4071626663208008, "learning_rate": 4.896241559932712e-05, "loss": 4.4301, "step": 3013 }, { "epoch": 0.09205864386072084, "grad_norm": 0.409252792596817, "learning_rate": 4.896173155479307e-05, "loss": 4.3675, "step": 3014 }, { "epoch": 0.0920891875381796, "grad_norm": 0.41181397438049316, "learning_rate": 4.896104728963104e-05, "loss": 4.4854, "step": 3015 }, { "epoch": 0.09211973121563836, "grad_norm": 0.39835256338119507, "learning_rate": 4.896036280384733e-05, "loss": 4.422, "step": 3016 }, { "epoch": 0.09215027489309713, "grad_norm": 0.4073967933654785, "learning_rate": 4.895967809744824e-05, "loss": 4.5089, "step": 3017 }, { "epoch": 0.09218081857055589, "grad_norm": 0.411308616399765, "learning_rate": 4.895899317044006e-05, "loss": 4.3829, "step": 3018 }, { "epoch": 0.09221136224801466, "grad_norm": 0.4018020033836365, "learning_rate": 4.895830802282913e-05, "loss": 4.4474, "step": 3019 }, { "epoch": 0.09224190592547343, "grad_norm": 0.40589892864227295, "learning_rate": 4.895762265462173e-05, "loss": 4.3888, "step": 3020 }, { "epoch": 0.0922724496029322, "grad_norm": 0.4095047414302826, "learning_rate": 4.8956937065824184e-05, "loss": 4.5149, "step": 3021 }, { "epoch": 0.09230299328039096, "grad_norm": 0.4151572287082672, "learning_rate": 4.89562512564428e-05, "loss": 4.3107, "step": 3022 }, { "epoch": 0.09233353695784972, "grad_norm": 0.40896204113960266, "learning_rate": 4.895556522648389e-05, "loss": 4.3962, "step": 3023 }, { "epoch": 0.09236408063530849, "grad_norm": 0.40781497955322266, "learning_rate": 4.895487897595378e-05, "loss": 4.4861, "step": 3024 }, { "epoch": 0.09239462431276725, "grad_norm": 0.41091683506965637, "learning_rate": 4.895419250485878e-05, "loss": 4.4266, "step": 3025 }, { "epoch": 0.09242516799022603, "grad_norm": 0.4181409478187561, "learning_rate": 4.8953505813205215e-05, "loss": 4.3883, "step": 3026 }, { "epoch": 0.09245571166768479, "grad_norm": 0.40610700845718384, "learning_rate": 4.895281890099941e-05, "loss": 4.4488, "step": 3027 }, { "epoch": 0.09248625534514356, "grad_norm": 0.39875900745391846, "learning_rate": 4.8952131768247675e-05, "loss": 4.4052, "step": 3028 }, { "epoch": 0.09251679902260232, "grad_norm": 0.3989047110080719, "learning_rate": 4.895144441495636e-05, "loss": 4.4948, "step": 3029 }, { "epoch": 0.09254734270006108, "grad_norm": 0.40649959444999695, "learning_rate": 4.8950756841131776e-05, "loss": 4.3524, "step": 3030 }, { "epoch": 0.09257788637751985, "grad_norm": 0.4022350609302521, "learning_rate": 4.8950069046780253e-05, "loss": 4.4294, "step": 3031 }, { "epoch": 0.09260843005497862, "grad_norm": 0.41024619340896606, "learning_rate": 4.894938103190814e-05, "loss": 4.4375, "step": 3032 }, { "epoch": 0.09263897373243739, "grad_norm": 0.39173048734664917, "learning_rate": 4.894869279652177e-05, "loss": 4.4552, "step": 3033 }, { "epoch": 0.09266951740989615, "grad_norm": 0.41070353984832764, "learning_rate": 4.894800434062745e-05, "loss": 4.3998, "step": 3034 }, { "epoch": 0.09270006108735492, "grad_norm": 0.3949914574623108, "learning_rate": 4.894731566423156e-05, "loss": 4.4689, "step": 3035 }, { "epoch": 0.09273060476481368, "grad_norm": 0.413769394159317, "learning_rate": 4.8946626767340416e-05, "loss": 4.5227, "step": 3036 }, { "epoch": 0.09276114844227246, "grad_norm": 0.39338475465774536, "learning_rate": 4.894593764996036e-05, "loss": 4.3812, "step": 3037 }, { "epoch": 0.09279169211973122, "grad_norm": 0.40053603053092957, "learning_rate": 4.894524831209776e-05, "loss": 4.4274, "step": 3038 }, { "epoch": 0.09282223579718998, "grad_norm": 0.39601197838783264, "learning_rate": 4.894455875375893e-05, "loss": 4.4503, "step": 3039 }, { "epoch": 0.09285277947464875, "grad_norm": 0.4056762158870697, "learning_rate": 4.894386897495025e-05, "loss": 4.4383, "step": 3040 }, { "epoch": 0.09288332315210751, "grad_norm": 0.41107410192489624, "learning_rate": 4.894317897567805e-05, "loss": 4.5422, "step": 3041 }, { "epoch": 0.09291386682956627, "grad_norm": 0.3951038122177124, "learning_rate": 4.894248875594869e-05, "loss": 4.4247, "step": 3042 }, { "epoch": 0.09294441050702505, "grad_norm": 0.40681177377700806, "learning_rate": 4.894179831576853e-05, "loss": 4.4798, "step": 3043 }, { "epoch": 0.09297495418448382, "grad_norm": 0.4057008922100067, "learning_rate": 4.8941107655143925e-05, "loss": 4.5154, "step": 3044 }, { "epoch": 0.09300549786194258, "grad_norm": 0.4069632589817047, "learning_rate": 4.8940416774081225e-05, "loss": 4.3657, "step": 3045 }, { "epoch": 0.09303604153940134, "grad_norm": 0.40413394570350647, "learning_rate": 4.893972567258681e-05, "loss": 4.4234, "step": 3046 }, { "epoch": 0.0930665852168601, "grad_norm": 0.4057827293872833, "learning_rate": 4.8939034350667025e-05, "loss": 4.4258, "step": 3047 }, { "epoch": 0.09309712889431887, "grad_norm": 0.40070274472236633, "learning_rate": 4.8938342808328245e-05, "loss": 4.3754, "step": 3048 }, { "epoch": 0.09312767257177765, "grad_norm": 0.41095003485679626, "learning_rate": 4.893765104557683e-05, "loss": 4.4307, "step": 3049 }, { "epoch": 0.09315821624923641, "grad_norm": 0.41539648175239563, "learning_rate": 4.893695906241915e-05, "loss": 4.562, "step": 3050 }, { "epoch": 0.09318875992669517, "grad_norm": 0.38865599036216736, "learning_rate": 4.893626685886159e-05, "loss": 4.3739, "step": 3051 }, { "epoch": 0.09321930360415394, "grad_norm": 0.39118215441703796, "learning_rate": 4.893557443491051e-05, "loss": 4.3808, "step": 3052 }, { "epoch": 0.0932498472816127, "grad_norm": 0.3987773358821869, "learning_rate": 4.89348817905723e-05, "loss": 4.4824, "step": 3053 }, { "epoch": 0.09328039095907147, "grad_norm": 0.4177164137363434, "learning_rate": 4.893418892585332e-05, "loss": 4.413, "step": 3054 }, { "epoch": 0.09331093463653024, "grad_norm": 0.4058838188648224, "learning_rate": 4.893349584075995e-05, "loss": 4.424, "step": 3055 }, { "epoch": 0.09334147831398901, "grad_norm": 0.3884773254394531, "learning_rate": 4.8932802535298584e-05, "loss": 4.4382, "step": 3056 }, { "epoch": 0.09337202199144777, "grad_norm": 0.3982289433479309, "learning_rate": 4.8932109009475605e-05, "loss": 4.4074, "step": 3057 }, { "epoch": 0.09340256566890653, "grad_norm": 0.4234131872653961, "learning_rate": 4.8931415263297384e-05, "loss": 4.3651, "step": 3058 }, { "epoch": 0.0934331093463653, "grad_norm": 0.4058957099914551, "learning_rate": 4.8930721296770326e-05, "loss": 4.4938, "step": 3059 }, { "epoch": 0.09346365302382406, "grad_norm": 0.39384540915489197, "learning_rate": 4.893002710990081e-05, "loss": 4.442, "step": 3060 }, { "epoch": 0.09349419670128284, "grad_norm": 0.40976622700691223, "learning_rate": 4.8929332702695226e-05, "loss": 4.3493, "step": 3061 }, { "epoch": 0.0935247403787416, "grad_norm": 0.40744638442993164, "learning_rate": 4.892863807515998e-05, "loss": 4.4155, "step": 3062 }, { "epoch": 0.09355528405620037, "grad_norm": 0.3891647756099701, "learning_rate": 4.892794322730147e-05, "loss": 4.4431, "step": 3063 }, { "epoch": 0.09358582773365913, "grad_norm": 0.3959744870662689, "learning_rate": 4.892724815912607e-05, "loss": 4.4438, "step": 3064 }, { "epoch": 0.0936163714111179, "grad_norm": 0.40602564811706543, "learning_rate": 4.89265528706402e-05, "loss": 4.4449, "step": 3065 }, { "epoch": 0.09364691508857667, "grad_norm": 0.40728193521499634, "learning_rate": 4.892585736185025e-05, "loss": 4.4394, "step": 3066 }, { "epoch": 0.09367745876603543, "grad_norm": 0.40793493390083313, "learning_rate": 4.892516163276263e-05, "loss": 4.4788, "step": 3067 }, { "epoch": 0.0937080024434942, "grad_norm": 0.399489164352417, "learning_rate": 4.892446568338375e-05, "loss": 4.3966, "step": 3068 }, { "epoch": 0.09373854612095296, "grad_norm": 0.4187966585159302, "learning_rate": 4.892376951372001e-05, "loss": 4.4126, "step": 3069 }, { "epoch": 0.09376908979841173, "grad_norm": 0.4004174768924713, "learning_rate": 4.8923073123777824e-05, "loss": 4.4875, "step": 3070 }, { "epoch": 0.09379963347587049, "grad_norm": 0.3996448218822479, "learning_rate": 4.89223765135636e-05, "loss": 4.4466, "step": 3071 }, { "epoch": 0.09383017715332927, "grad_norm": 0.4049835205078125, "learning_rate": 4.892167968308376e-05, "loss": 4.4638, "step": 3072 }, { "epoch": 0.09386072083078803, "grad_norm": 0.4105885624885559, "learning_rate": 4.892098263234473e-05, "loss": 4.4106, "step": 3073 }, { "epoch": 0.0938912645082468, "grad_norm": 0.3965442478656769, "learning_rate": 4.8920285361352894e-05, "loss": 4.4875, "step": 3074 }, { "epoch": 0.09392180818570556, "grad_norm": 0.40948623418807983, "learning_rate": 4.89195878701147e-05, "loss": 4.4544, "step": 3075 }, { "epoch": 0.09395235186316432, "grad_norm": 0.407272070646286, "learning_rate": 4.8918890158636555e-05, "loss": 4.4381, "step": 3076 }, { "epoch": 0.09398289554062308, "grad_norm": 0.392619788646698, "learning_rate": 4.89181922269249e-05, "loss": 4.4741, "step": 3077 }, { "epoch": 0.09401343921808186, "grad_norm": 0.3994641900062561, "learning_rate": 4.891749407498615e-05, "loss": 4.4598, "step": 3078 }, { "epoch": 0.09404398289554063, "grad_norm": 0.3923986852169037, "learning_rate": 4.891679570282673e-05, "loss": 4.4507, "step": 3079 }, { "epoch": 0.09407452657299939, "grad_norm": 0.4057566225528717, "learning_rate": 4.891609711045308e-05, "loss": 4.3652, "step": 3080 }, { "epoch": 0.09410507025045815, "grad_norm": 0.39330899715423584, "learning_rate": 4.891539829787163e-05, "loss": 4.4542, "step": 3081 }, { "epoch": 0.09413561392791692, "grad_norm": 0.38463228940963745, "learning_rate": 4.8914699265088805e-05, "loss": 4.3849, "step": 3082 }, { "epoch": 0.09416615760537568, "grad_norm": 0.40386146306991577, "learning_rate": 4.891400001211105e-05, "loss": 4.4362, "step": 3083 }, { "epoch": 0.09419670128283446, "grad_norm": 0.39099130034446716, "learning_rate": 4.89133005389448e-05, "loss": 4.3625, "step": 3084 }, { "epoch": 0.09422724496029322, "grad_norm": 0.4129779636859894, "learning_rate": 4.89126008455965e-05, "loss": 4.4322, "step": 3085 }, { "epoch": 0.09425778863775199, "grad_norm": 0.4078871011734009, "learning_rate": 4.8911900932072584e-05, "loss": 4.4633, "step": 3086 }, { "epoch": 0.09428833231521075, "grad_norm": 0.42132771015167236, "learning_rate": 4.891120079837951e-05, "loss": 4.5109, "step": 3087 }, { "epoch": 0.09431887599266951, "grad_norm": 0.4198024570941925, "learning_rate": 4.891050044452371e-05, "loss": 4.3539, "step": 3088 }, { "epoch": 0.09434941967012829, "grad_norm": 0.3967971205711365, "learning_rate": 4.890979987051164e-05, "loss": 4.4242, "step": 3089 }, { "epoch": 0.09437996334758705, "grad_norm": 0.4010731279850006, "learning_rate": 4.8909099076349754e-05, "loss": 4.4669, "step": 3090 }, { "epoch": 0.09441050702504582, "grad_norm": 0.40819796919822693, "learning_rate": 4.8908398062044495e-05, "loss": 4.3196, "step": 3091 }, { "epoch": 0.09444105070250458, "grad_norm": 0.4054500460624695, "learning_rate": 4.8907696827602325e-05, "loss": 4.3753, "step": 3092 }, { "epoch": 0.09447159437996334, "grad_norm": 0.3994203805923462, "learning_rate": 4.8906995373029696e-05, "loss": 4.4077, "step": 3093 }, { "epoch": 0.09450213805742211, "grad_norm": 0.4159437417984009, "learning_rate": 4.890629369833307e-05, "loss": 4.3955, "step": 3094 }, { "epoch": 0.09453268173488089, "grad_norm": 0.41176581382751465, "learning_rate": 4.890559180351891e-05, "loss": 4.5062, "step": 3095 }, { "epoch": 0.09456322541233965, "grad_norm": 0.41452842950820923, "learning_rate": 4.890488968859367e-05, "loss": 4.4568, "step": 3096 }, { "epoch": 0.09459376908979841, "grad_norm": 0.3972187936306, "learning_rate": 4.890418735356383e-05, "loss": 4.4407, "step": 3097 }, { "epoch": 0.09462431276725718, "grad_norm": 0.4057820737361908, "learning_rate": 4.8903484798435834e-05, "loss": 4.4878, "step": 3098 }, { "epoch": 0.09465485644471594, "grad_norm": 0.41360771656036377, "learning_rate": 4.890278202321616e-05, "loss": 4.4861, "step": 3099 }, { "epoch": 0.0946854001221747, "grad_norm": 0.4148619771003723, "learning_rate": 4.89020790279113e-05, "loss": 4.4665, "step": 3100 }, { "epoch": 0.09471594379963348, "grad_norm": 0.4265071451663971, "learning_rate": 4.8901375812527695e-05, "loss": 4.46, "step": 3101 }, { "epoch": 0.09474648747709224, "grad_norm": 0.41700634360313416, "learning_rate": 4.890067237707184e-05, "loss": 4.4667, "step": 3102 }, { "epoch": 0.09477703115455101, "grad_norm": 0.4055590331554413, "learning_rate": 4.88999687215502e-05, "loss": 4.4902, "step": 3103 }, { "epoch": 0.09480757483200977, "grad_norm": 0.4244272708892822, "learning_rate": 4.889926484596927e-05, "loss": 4.5234, "step": 3104 }, { "epoch": 0.09483811850946854, "grad_norm": 0.40001142024993896, "learning_rate": 4.889856075033552e-05, "loss": 4.4416, "step": 3105 }, { "epoch": 0.0948686621869273, "grad_norm": 0.41711971163749695, "learning_rate": 4.889785643465543e-05, "loss": 4.4431, "step": 3106 }, { "epoch": 0.09489920586438608, "grad_norm": 0.4013659954071045, "learning_rate": 4.889715189893548e-05, "loss": 4.4827, "step": 3107 }, { "epoch": 0.09492974954184484, "grad_norm": 0.41210222244262695, "learning_rate": 4.8896447143182175e-05, "loss": 4.3741, "step": 3108 }, { "epoch": 0.0949602932193036, "grad_norm": 0.42466089129447937, "learning_rate": 4.889574216740199e-05, "loss": 4.3964, "step": 3109 }, { "epoch": 0.09499083689676237, "grad_norm": 0.40570980310440063, "learning_rate": 4.8895036971601425e-05, "loss": 4.4149, "step": 3110 }, { "epoch": 0.09502138057422113, "grad_norm": 0.39267927408218384, "learning_rate": 4.889433155578698e-05, "loss": 4.4524, "step": 3111 }, { "epoch": 0.09505192425167991, "grad_norm": 0.4249282479286194, "learning_rate": 4.889362591996512e-05, "loss": 4.4553, "step": 3112 }, { "epoch": 0.09508246792913867, "grad_norm": 0.41660434007644653, "learning_rate": 4.8892920064142365e-05, "loss": 4.4066, "step": 3113 }, { "epoch": 0.09511301160659744, "grad_norm": 0.3971531093120575, "learning_rate": 4.889221398832522e-05, "loss": 4.4797, "step": 3114 }, { "epoch": 0.0951435552840562, "grad_norm": 0.40179121494293213, "learning_rate": 4.889150769252017e-05, "loss": 4.4004, "step": 3115 }, { "epoch": 0.09517409896151496, "grad_norm": 0.4240697920322418, "learning_rate": 4.889080117673372e-05, "loss": 4.4809, "step": 3116 }, { "epoch": 0.09520464263897373, "grad_norm": 0.4131762981414795, "learning_rate": 4.889009444097239e-05, "loss": 4.4082, "step": 3117 }, { "epoch": 0.0952351863164325, "grad_norm": 0.38641276955604553, "learning_rate": 4.8889387485242676e-05, "loss": 4.3769, "step": 3118 }, { "epoch": 0.09526572999389127, "grad_norm": 0.4224994480609894, "learning_rate": 4.888868030955108e-05, "loss": 4.358, "step": 3119 }, { "epoch": 0.09529627367135003, "grad_norm": 0.41291648149490356, "learning_rate": 4.888797291390413e-05, "loss": 4.4576, "step": 3120 }, { "epoch": 0.0953268173488088, "grad_norm": 0.38617533445358276, "learning_rate": 4.888726529830833e-05, "loss": 4.3766, "step": 3121 }, { "epoch": 0.09535736102626756, "grad_norm": 0.4121551215648651, "learning_rate": 4.88865574627702e-05, "loss": 4.5685, "step": 3122 }, { "epoch": 0.09538790470372632, "grad_norm": 0.4160560667514801, "learning_rate": 4.8885849407296246e-05, "loss": 4.3917, "step": 3123 }, { "epoch": 0.0954184483811851, "grad_norm": 0.4005657434463501, "learning_rate": 4.8885141131893e-05, "loss": 4.4384, "step": 3124 }, { "epoch": 0.09544899205864386, "grad_norm": 0.39043301343917847, "learning_rate": 4.888443263656698e-05, "loss": 4.4135, "step": 3125 }, { "epoch": 0.09547953573610263, "grad_norm": 0.39447733759880066, "learning_rate": 4.8883723921324707e-05, "loss": 4.4531, "step": 3126 }, { "epoch": 0.09551007941356139, "grad_norm": 0.39741939306259155, "learning_rate": 4.888301498617271e-05, "loss": 4.3946, "step": 3127 }, { "epoch": 0.09554062309102015, "grad_norm": 0.40215209126472473, "learning_rate": 4.8882305831117515e-05, "loss": 4.4185, "step": 3128 }, { "epoch": 0.09557116676847892, "grad_norm": 0.40581414103507996, "learning_rate": 4.888159645616565e-05, "loss": 4.3434, "step": 3129 }, { "epoch": 0.0956017104459377, "grad_norm": 0.38969820737838745, "learning_rate": 4.888088686132364e-05, "loss": 4.4365, "step": 3130 }, { "epoch": 0.09563225412339646, "grad_norm": 0.42249250411987305, "learning_rate": 4.8880177046598044e-05, "loss": 4.4604, "step": 3131 }, { "epoch": 0.09566279780085522, "grad_norm": 0.4032074809074402, "learning_rate": 4.8879467011995364e-05, "loss": 4.4158, "step": 3132 }, { "epoch": 0.09569334147831399, "grad_norm": 0.3997724652290344, "learning_rate": 4.887875675752216e-05, "loss": 4.4502, "step": 3133 }, { "epoch": 0.09572388515577275, "grad_norm": 0.3978964686393738, "learning_rate": 4.887804628318496e-05, "loss": 4.3496, "step": 3134 }, { "epoch": 0.09575442883323153, "grad_norm": 0.3949587345123291, "learning_rate": 4.887733558899031e-05, "loss": 4.4277, "step": 3135 }, { "epoch": 0.09578497251069029, "grad_norm": 0.39401453733444214, "learning_rate": 4.887662467494477e-05, "loss": 4.3615, "step": 3136 }, { "epoch": 0.09581551618814906, "grad_norm": 0.4071785807609558, "learning_rate": 4.887591354105486e-05, "loss": 4.4319, "step": 3137 }, { "epoch": 0.09584605986560782, "grad_norm": 0.4119778871536255, "learning_rate": 4.887520218732714e-05, "loss": 4.4098, "step": 3138 }, { "epoch": 0.09587660354306658, "grad_norm": 0.3995721936225891, "learning_rate": 4.887449061376815e-05, "loss": 4.4365, "step": 3139 }, { "epoch": 0.09590714722052535, "grad_norm": 0.3925634026527405, "learning_rate": 4.887377882038446e-05, "loss": 4.4002, "step": 3140 }, { "epoch": 0.09593769089798412, "grad_norm": 0.40386754274368286, "learning_rate": 4.8873066807182614e-05, "loss": 4.4772, "step": 3141 }, { "epoch": 0.09596823457544289, "grad_norm": 0.40107089281082153, "learning_rate": 4.887235457416916e-05, "loss": 4.4111, "step": 3142 }, { "epoch": 0.09599877825290165, "grad_norm": 0.4016569256782532, "learning_rate": 4.8871642121350666e-05, "loss": 4.3734, "step": 3143 }, { "epoch": 0.09602932193036041, "grad_norm": 0.40003103017807007, "learning_rate": 4.8870929448733694e-05, "loss": 4.3895, "step": 3144 }, { "epoch": 0.09605986560781918, "grad_norm": 0.39396002888679504, "learning_rate": 4.88702165563248e-05, "loss": 4.3885, "step": 3145 }, { "epoch": 0.09609040928527794, "grad_norm": 0.40295395255088806, "learning_rate": 4.886950344413055e-05, "loss": 4.4077, "step": 3146 }, { "epoch": 0.09612095296273672, "grad_norm": 0.3838302493095398, "learning_rate": 4.8868790112157504e-05, "loss": 4.4756, "step": 3147 }, { "epoch": 0.09615149664019548, "grad_norm": 0.4034798741340637, "learning_rate": 4.886807656041223e-05, "loss": 4.3472, "step": 3148 }, { "epoch": 0.09618204031765425, "grad_norm": 0.40346670150756836, "learning_rate": 4.8867362788901315e-05, "loss": 4.3973, "step": 3149 }, { "epoch": 0.09621258399511301, "grad_norm": 0.39784103631973267, "learning_rate": 4.886664879763132e-05, "loss": 4.3615, "step": 3150 }, { "epoch": 0.09624312767257177, "grad_norm": 0.38466018438339233, "learning_rate": 4.8865934586608814e-05, "loss": 4.3903, "step": 3151 }, { "epoch": 0.09627367135003054, "grad_norm": 0.3986336886882782, "learning_rate": 4.886522015584038e-05, "loss": 4.3239, "step": 3152 }, { "epoch": 0.09630421502748931, "grad_norm": 0.38761988282203674, "learning_rate": 4.886450550533259e-05, "loss": 4.4156, "step": 3153 }, { "epoch": 0.09633475870494808, "grad_norm": 0.3952091336250305, "learning_rate": 4.8863790635092026e-05, "loss": 4.4219, "step": 3154 }, { "epoch": 0.09636530238240684, "grad_norm": 0.38705548644065857, "learning_rate": 4.886307554512528e-05, "loss": 4.4213, "step": 3155 }, { "epoch": 0.0963958460598656, "grad_norm": 0.41504210233688354, "learning_rate": 4.886236023543892e-05, "loss": 4.377, "step": 3156 }, { "epoch": 0.09642638973732437, "grad_norm": 0.4039168059825897, "learning_rate": 4.886164470603954e-05, "loss": 4.4583, "step": 3157 }, { "epoch": 0.09645693341478313, "grad_norm": 0.4004952013492584, "learning_rate": 4.886092895693374e-05, "loss": 4.4791, "step": 3158 }, { "epoch": 0.09648747709224191, "grad_norm": 0.4044911563396454, "learning_rate": 4.8860212988128094e-05, "loss": 4.4253, "step": 3159 }, { "epoch": 0.09651802076970067, "grad_norm": 0.3975781500339508, "learning_rate": 4.885949679962919e-05, "loss": 4.4837, "step": 3160 }, { "epoch": 0.09654856444715944, "grad_norm": 0.4028034508228302, "learning_rate": 4.885878039144365e-05, "loss": 4.3188, "step": 3161 }, { "epoch": 0.0965791081246182, "grad_norm": 0.4058477282524109, "learning_rate": 4.8858063763578035e-05, "loss": 4.4406, "step": 3162 }, { "epoch": 0.09660965180207697, "grad_norm": 0.39813169836997986, "learning_rate": 4.885734691603897e-05, "loss": 4.3943, "step": 3163 }, { "epoch": 0.09664019547953574, "grad_norm": 0.39434391260147095, "learning_rate": 4.885662984883304e-05, "loss": 4.4151, "step": 3164 }, { "epoch": 0.0966707391569945, "grad_norm": 0.4030879735946655, "learning_rate": 4.8855912561966855e-05, "loss": 4.4343, "step": 3165 }, { "epoch": 0.09670128283445327, "grad_norm": 0.3930765986442566, "learning_rate": 4.885519505544702e-05, "loss": 4.4682, "step": 3166 }, { "epoch": 0.09673182651191203, "grad_norm": 0.39937224984169006, "learning_rate": 4.8854477329280136e-05, "loss": 4.3372, "step": 3167 }, { "epoch": 0.0967623701893708, "grad_norm": 0.40051889419555664, "learning_rate": 4.885375938347281e-05, "loss": 4.394, "step": 3168 }, { "epoch": 0.09679291386682956, "grad_norm": 0.4126546084880829, "learning_rate": 4.885304121803167e-05, "loss": 4.4153, "step": 3169 }, { "epoch": 0.09682345754428834, "grad_norm": 0.3928168714046478, "learning_rate": 4.88523228329633e-05, "loss": 4.4522, "step": 3170 }, { "epoch": 0.0968540012217471, "grad_norm": 0.40770772099494934, "learning_rate": 4.885160422827434e-05, "loss": 4.4058, "step": 3171 }, { "epoch": 0.09688454489920587, "grad_norm": 0.4177204370498657, "learning_rate": 4.8850885403971394e-05, "loss": 4.4742, "step": 3172 }, { "epoch": 0.09691508857666463, "grad_norm": 0.3974073827266693, "learning_rate": 4.885016636006109e-05, "loss": 4.4597, "step": 3173 }, { "epoch": 0.09694563225412339, "grad_norm": 0.399763286113739, "learning_rate": 4.8849447096550035e-05, "loss": 4.4517, "step": 3174 }, { "epoch": 0.09697617593158216, "grad_norm": 0.40867310762405396, "learning_rate": 4.8848727613444855e-05, "loss": 4.5333, "step": 3175 }, { "epoch": 0.09700671960904093, "grad_norm": 0.4174284338951111, "learning_rate": 4.884800791075218e-05, "loss": 4.3518, "step": 3176 }, { "epoch": 0.0970372632864997, "grad_norm": 0.4017390310764313, "learning_rate": 4.884728798847864e-05, "loss": 4.4195, "step": 3177 }, { "epoch": 0.09706780696395846, "grad_norm": 0.43014076352119446, "learning_rate": 4.8846567846630855e-05, "loss": 4.3957, "step": 3178 }, { "epoch": 0.09709835064141722, "grad_norm": 0.4168955981731415, "learning_rate": 4.884584748521546e-05, "loss": 4.4809, "step": 3179 }, { "epoch": 0.09712889431887599, "grad_norm": 0.4177359342575073, "learning_rate": 4.884512690423909e-05, "loss": 4.4874, "step": 3180 }, { "epoch": 0.09715943799633475, "grad_norm": 0.41554149985313416, "learning_rate": 4.884440610370837e-05, "loss": 4.4104, "step": 3181 }, { "epoch": 0.09718998167379353, "grad_norm": 0.41027387976646423, "learning_rate": 4.884368508362994e-05, "loss": 4.4056, "step": 3182 }, { "epoch": 0.0972205253512523, "grad_norm": 0.4063595235347748, "learning_rate": 4.8842963844010454e-05, "loss": 4.4079, "step": 3183 }, { "epoch": 0.09725106902871106, "grad_norm": 0.4029373824596405, "learning_rate": 4.8842242384856534e-05, "loss": 4.4689, "step": 3184 }, { "epoch": 0.09728161270616982, "grad_norm": 0.40412813425064087, "learning_rate": 4.884152070617483e-05, "loss": 4.2998, "step": 3185 }, { "epoch": 0.09731215638362858, "grad_norm": 0.4173893928527832, "learning_rate": 4.8840798807971985e-05, "loss": 4.4168, "step": 3186 }, { "epoch": 0.09734270006108736, "grad_norm": 0.415117084980011, "learning_rate": 4.884007669025466e-05, "loss": 4.4141, "step": 3187 }, { "epoch": 0.09737324373854613, "grad_norm": 0.4012244939804077, "learning_rate": 4.8839354353029474e-05, "loss": 4.3568, "step": 3188 }, { "epoch": 0.09740378741600489, "grad_norm": 0.4108572006225586, "learning_rate": 4.883863179630311e-05, "loss": 4.4948, "step": 3189 }, { "epoch": 0.09743433109346365, "grad_norm": 0.39515426754951477, "learning_rate": 4.8837909020082196e-05, "loss": 4.411, "step": 3190 }, { "epoch": 0.09746487477092242, "grad_norm": 0.4013720452785492, "learning_rate": 4.88371860243734e-05, "loss": 4.2266, "step": 3191 }, { "epoch": 0.09749541844838118, "grad_norm": 0.4152351915836334, "learning_rate": 4.8836462809183383e-05, "loss": 4.4422, "step": 3192 }, { "epoch": 0.09752596212583996, "grad_norm": 0.40893885493278503, "learning_rate": 4.883573937451879e-05, "loss": 4.4382, "step": 3193 }, { "epoch": 0.09755650580329872, "grad_norm": 0.39488470554351807, "learning_rate": 4.883501572038629e-05, "loss": 4.4337, "step": 3194 }, { "epoch": 0.09758704948075748, "grad_norm": 0.4061598479747772, "learning_rate": 4.883429184679255e-05, "loss": 4.5047, "step": 3195 }, { "epoch": 0.09761759315821625, "grad_norm": 0.3982124328613281, "learning_rate": 4.8833567753744224e-05, "loss": 4.4241, "step": 3196 }, { "epoch": 0.09764813683567501, "grad_norm": 0.3959367573261261, "learning_rate": 4.883284344124799e-05, "loss": 4.4104, "step": 3197 }, { "epoch": 0.09767868051313378, "grad_norm": 0.4132155776023865, "learning_rate": 4.883211890931052e-05, "loss": 4.4626, "step": 3198 }, { "epoch": 0.09770922419059255, "grad_norm": 0.4033188819885254, "learning_rate": 4.883139415793847e-05, "loss": 4.4464, "step": 3199 }, { "epoch": 0.09773976786805132, "grad_norm": 0.4053443670272827, "learning_rate": 4.8830669187138514e-05, "loss": 4.3613, "step": 3200 }, { "epoch": 0.09777031154551008, "grad_norm": 0.4013921618461609, "learning_rate": 4.882994399691735e-05, "loss": 4.4357, "step": 3201 }, { "epoch": 0.09780085522296884, "grad_norm": 0.4054050147533417, "learning_rate": 4.8829218587281626e-05, "loss": 4.4319, "step": 3202 }, { "epoch": 0.09783139890042761, "grad_norm": 0.4053761661052704, "learning_rate": 4.882849295823804e-05, "loss": 4.4184, "step": 3203 }, { "epoch": 0.09786194257788637, "grad_norm": 0.40440282225608826, "learning_rate": 4.882776710979327e-05, "loss": 4.4705, "step": 3204 }, { "epoch": 0.09789248625534515, "grad_norm": 0.39468058943748474, "learning_rate": 4.882704104195399e-05, "loss": 4.2486, "step": 3205 }, { "epoch": 0.09792302993280391, "grad_norm": 0.38615933060646057, "learning_rate": 4.88263147547269e-05, "loss": 4.4101, "step": 3206 }, { "epoch": 0.09795357361026268, "grad_norm": 0.3992026448249817, "learning_rate": 4.882558824811868e-05, "loss": 4.3502, "step": 3207 }, { "epoch": 0.09798411728772144, "grad_norm": 0.41182941198349, "learning_rate": 4.882486152213601e-05, "loss": 4.4633, "step": 3208 }, { "epoch": 0.0980146609651802, "grad_norm": 0.38762181997299194, "learning_rate": 4.88241345767856e-05, "loss": 4.4153, "step": 3209 }, { "epoch": 0.09804520464263898, "grad_norm": 0.3951145112514496, "learning_rate": 4.882340741207413e-05, "loss": 4.4782, "step": 3210 }, { "epoch": 0.09807574832009774, "grad_norm": 0.4145667552947998, "learning_rate": 4.8822680028008304e-05, "loss": 4.4185, "step": 3211 }, { "epoch": 0.09810629199755651, "grad_norm": 0.3944949805736542, "learning_rate": 4.882195242459481e-05, "loss": 4.2964, "step": 3212 }, { "epoch": 0.09813683567501527, "grad_norm": 0.41509348154067993, "learning_rate": 4.882122460184035e-05, "loss": 4.4131, "step": 3213 }, { "epoch": 0.09816737935247404, "grad_norm": 0.41219064593315125, "learning_rate": 4.8820496559751634e-05, "loss": 4.473, "step": 3214 }, { "epoch": 0.0981979230299328, "grad_norm": 0.4037996530532837, "learning_rate": 4.8819768298335354e-05, "loss": 4.4114, "step": 3215 }, { "epoch": 0.09822846670739158, "grad_norm": 0.4055526554584503, "learning_rate": 4.881903981759822e-05, "loss": 4.3711, "step": 3216 }, { "epoch": 0.09825901038485034, "grad_norm": 0.4005044400691986, "learning_rate": 4.8818311117546946e-05, "loss": 4.4293, "step": 3217 }, { "epoch": 0.0982895540623091, "grad_norm": 0.39731499552726746, "learning_rate": 4.881758219818823e-05, "loss": 4.3296, "step": 3218 }, { "epoch": 0.09832009773976787, "grad_norm": 0.3998105823993683, "learning_rate": 4.8816853059528786e-05, "loss": 4.424, "step": 3219 }, { "epoch": 0.09835064141722663, "grad_norm": 0.40851080417633057, "learning_rate": 4.881612370157533e-05, "loss": 4.452, "step": 3220 }, { "epoch": 0.0983811850946854, "grad_norm": 0.4132811725139618, "learning_rate": 4.881539412433459e-05, "loss": 4.4333, "step": 3221 }, { "epoch": 0.09841172877214417, "grad_norm": 0.39473164081573486, "learning_rate": 4.881466432781325e-05, "loss": 4.4146, "step": 3222 }, { "epoch": 0.09844227244960294, "grad_norm": 0.40458014607429504, "learning_rate": 4.8813934312018074e-05, "loss": 4.5147, "step": 3223 }, { "epoch": 0.0984728161270617, "grad_norm": 0.4011004865169525, "learning_rate": 4.881320407695575e-05, "loss": 4.393, "step": 3224 }, { "epoch": 0.09850335980452046, "grad_norm": 0.38988441228866577, "learning_rate": 4.8812473622633015e-05, "loss": 4.3678, "step": 3225 }, { "epoch": 0.09853390348197923, "grad_norm": 0.4092157185077667, "learning_rate": 4.8811742949056596e-05, "loss": 4.399, "step": 3226 }, { "epoch": 0.09856444715943799, "grad_norm": 0.40503373742103577, "learning_rate": 4.8811012056233206e-05, "loss": 4.4308, "step": 3227 }, { "epoch": 0.09859499083689677, "grad_norm": 0.4231993854045868, "learning_rate": 4.8810280944169596e-05, "loss": 4.4821, "step": 3228 }, { "epoch": 0.09862553451435553, "grad_norm": 0.4038620591163635, "learning_rate": 4.880954961287248e-05, "loss": 4.4287, "step": 3229 }, { "epoch": 0.0986560781918143, "grad_norm": 0.39304319024086, "learning_rate": 4.8808818062348606e-05, "loss": 4.394, "step": 3230 }, { "epoch": 0.09868662186927306, "grad_norm": 0.4076698124408722, "learning_rate": 4.880808629260469e-05, "loss": 4.4022, "step": 3231 }, { "epoch": 0.09871716554673182, "grad_norm": 0.4010239243507385, "learning_rate": 4.88073543036475e-05, "loss": 4.4348, "step": 3232 }, { "epoch": 0.09874770922419059, "grad_norm": 0.39107561111450195, "learning_rate": 4.880662209548374e-05, "loss": 4.4173, "step": 3233 }, { "epoch": 0.09877825290164936, "grad_norm": 0.40600621700286865, "learning_rate": 4.8805889668120185e-05, "loss": 4.4691, "step": 3234 }, { "epoch": 0.09880879657910813, "grad_norm": 0.4094204306602478, "learning_rate": 4.880515702156356e-05, "loss": 4.3676, "step": 3235 }, { "epoch": 0.09883934025656689, "grad_norm": 0.3922732472419739, "learning_rate": 4.880442415582062e-05, "loss": 4.3753, "step": 3236 }, { "epoch": 0.09886988393402565, "grad_norm": 0.3908861577510834, "learning_rate": 4.880369107089809e-05, "loss": 4.4161, "step": 3237 }, { "epoch": 0.09890042761148442, "grad_norm": 0.39404553174972534, "learning_rate": 4.8802957766802755e-05, "loss": 4.4327, "step": 3238 }, { "epoch": 0.0989309712889432, "grad_norm": 0.39633288979530334, "learning_rate": 4.880222424354134e-05, "loss": 4.4137, "step": 3239 }, { "epoch": 0.09896151496640196, "grad_norm": 0.3967893719673157, "learning_rate": 4.880149050112062e-05, "loss": 4.4625, "step": 3240 }, { "epoch": 0.09899205864386072, "grad_norm": 0.398221880197525, "learning_rate": 4.880075653954733e-05, "loss": 4.4716, "step": 3241 }, { "epoch": 0.09902260232131949, "grad_norm": 0.39973050355911255, "learning_rate": 4.8800022358828236e-05, "loss": 4.4571, "step": 3242 }, { "epoch": 0.09905314599877825, "grad_norm": 0.39797496795654297, "learning_rate": 4.879928795897011e-05, "loss": 4.334, "step": 3243 }, { "epoch": 0.09908368967623701, "grad_norm": 0.39861297607421875, "learning_rate": 4.8798553339979694e-05, "loss": 4.4166, "step": 3244 }, { "epoch": 0.09911423335369579, "grad_norm": 0.4143504500389099, "learning_rate": 4.879781850186376e-05, "loss": 4.4297, "step": 3245 }, { "epoch": 0.09914477703115455, "grad_norm": 0.41618797183036804, "learning_rate": 4.8797083444629076e-05, "loss": 4.3625, "step": 3246 }, { "epoch": 0.09917532070861332, "grad_norm": 0.40444955229759216, "learning_rate": 4.879634816828241e-05, "loss": 4.4063, "step": 3247 }, { "epoch": 0.09920586438607208, "grad_norm": 0.4006291627883911, "learning_rate": 4.8795612672830536e-05, "loss": 4.369, "step": 3248 }, { "epoch": 0.09923640806353085, "grad_norm": 0.42785924673080444, "learning_rate": 4.8794876958280225e-05, "loss": 4.3955, "step": 3249 }, { "epoch": 0.09926695174098961, "grad_norm": 0.4127701222896576, "learning_rate": 4.8794141024638243e-05, "loss": 4.4136, "step": 3250 }, { "epoch": 0.09929749541844839, "grad_norm": 0.39935174584388733, "learning_rate": 4.8793404871911366e-05, "loss": 4.3598, "step": 3251 }, { "epoch": 0.09932803909590715, "grad_norm": 0.4153183102607727, "learning_rate": 4.879266850010639e-05, "loss": 4.4783, "step": 3252 }, { "epoch": 0.09935858277336591, "grad_norm": 0.4279473125934601, "learning_rate": 4.879193190923007e-05, "loss": 4.3991, "step": 3253 }, { "epoch": 0.09938912645082468, "grad_norm": 0.40693801641464233, "learning_rate": 4.87911950992892e-05, "loss": 4.4562, "step": 3254 }, { "epoch": 0.09941967012828344, "grad_norm": 0.39970433712005615, "learning_rate": 4.8790458070290567e-05, "loss": 4.4639, "step": 3255 }, { "epoch": 0.0994502138057422, "grad_norm": 0.40599116683006287, "learning_rate": 4.8789720822240956e-05, "loss": 4.464, "step": 3256 }, { "epoch": 0.09948075748320098, "grad_norm": 0.40500548481941223, "learning_rate": 4.8788983355147156e-05, "loss": 4.4676, "step": 3257 }, { "epoch": 0.09951130116065975, "grad_norm": 0.4188423156738281, "learning_rate": 4.8788245669015954e-05, "loss": 4.4215, "step": 3258 }, { "epoch": 0.09954184483811851, "grad_norm": 0.41479864716529846, "learning_rate": 4.878750776385414e-05, "loss": 4.3881, "step": 3259 }, { "epoch": 0.09957238851557727, "grad_norm": 0.4129873216152191, "learning_rate": 4.8786769639668515e-05, "loss": 4.4194, "step": 3260 }, { "epoch": 0.09960293219303604, "grad_norm": 0.4028873145580292, "learning_rate": 4.878603129646587e-05, "loss": 4.4977, "step": 3261 }, { "epoch": 0.09963347587049481, "grad_norm": 0.4074740707874298, "learning_rate": 4.878529273425301e-05, "loss": 4.4091, "step": 3262 }, { "epoch": 0.09966401954795358, "grad_norm": 0.40634411573410034, "learning_rate": 4.878455395303673e-05, "loss": 4.4102, "step": 3263 }, { "epoch": 0.09969456322541234, "grad_norm": 0.40241149067878723, "learning_rate": 4.878381495282382e-05, "loss": 4.3433, "step": 3264 }, { "epoch": 0.0997251069028711, "grad_norm": 0.41190677881240845, "learning_rate": 4.8783075733621106e-05, "loss": 4.4382, "step": 3265 }, { "epoch": 0.09975565058032987, "grad_norm": 0.3860864043235779, "learning_rate": 4.8782336295435396e-05, "loss": 4.3484, "step": 3266 }, { "epoch": 0.09978619425778863, "grad_norm": 0.4159984290599823, "learning_rate": 4.8781596638273474e-05, "loss": 4.4294, "step": 3267 }, { "epoch": 0.09981673793524741, "grad_norm": 0.4151616096496582, "learning_rate": 4.8780856762142166e-05, "loss": 4.418, "step": 3268 }, { "epoch": 0.09984728161270617, "grad_norm": 0.4029606878757477, "learning_rate": 4.878011666704829e-05, "loss": 4.4112, "step": 3269 }, { "epoch": 0.09987782529016494, "grad_norm": 0.4056871235370636, "learning_rate": 4.877937635299865e-05, "loss": 4.4368, "step": 3270 }, { "epoch": 0.0999083689676237, "grad_norm": 0.3899921178817749, "learning_rate": 4.8778635820000063e-05, "loss": 4.4237, "step": 3271 }, { "epoch": 0.09993891264508246, "grad_norm": 0.40063241124153137, "learning_rate": 4.8777895068059354e-05, "loss": 4.4595, "step": 3272 }, { "epoch": 0.09996945632254123, "grad_norm": 0.4136790335178375, "learning_rate": 4.877715409718334e-05, "loss": 4.4278, "step": 3273 }, { "epoch": 0.1, "grad_norm": 0.425114244222641, "learning_rate": 4.877641290737884e-05, "loss": 4.4313, "step": 3274 }, { "epoch": 0.10003054367745877, "grad_norm": 0.41481849551200867, "learning_rate": 4.877567149865269e-05, "loss": 4.4429, "step": 3275 }, { "epoch": 0.10006108735491753, "grad_norm": 0.41055354475975037, "learning_rate": 4.87749298710117e-05, "loss": 4.4177, "step": 3276 }, { "epoch": 0.1000916310323763, "grad_norm": 0.41872236132621765, "learning_rate": 4.877418802446271e-05, "loss": 4.4586, "step": 3277 }, { "epoch": 0.10012217470983506, "grad_norm": 0.4233131408691406, "learning_rate": 4.8773445959012545e-05, "loss": 4.4445, "step": 3278 }, { "epoch": 0.10015271838729382, "grad_norm": 0.40729087591171265, "learning_rate": 4.8772703674668034e-05, "loss": 4.414, "step": 3279 }, { "epoch": 0.1001832620647526, "grad_norm": 0.4103028476238251, "learning_rate": 4.8771961171436026e-05, "loss": 4.4397, "step": 3280 }, { "epoch": 0.10021380574221136, "grad_norm": 0.411732017993927, "learning_rate": 4.8771218449323346e-05, "loss": 4.4704, "step": 3281 }, { "epoch": 0.10024434941967013, "grad_norm": 0.4060571789741516, "learning_rate": 4.8770475508336844e-05, "loss": 4.4273, "step": 3282 }, { "epoch": 0.10027489309712889, "grad_norm": 0.3993336260318756, "learning_rate": 4.876973234848334e-05, "loss": 4.375, "step": 3283 }, { "epoch": 0.10030543677458766, "grad_norm": 0.3964661955833435, "learning_rate": 4.8768988969769696e-05, "loss": 4.4401, "step": 3284 }, { "epoch": 0.10033598045204643, "grad_norm": 0.4062183201313019, "learning_rate": 4.8768245372202745e-05, "loss": 4.3805, "step": 3285 }, { "epoch": 0.1003665241295052, "grad_norm": 0.403463751077652, "learning_rate": 4.876750155578935e-05, "loss": 4.4345, "step": 3286 }, { "epoch": 0.10039706780696396, "grad_norm": 0.3925471603870392, "learning_rate": 4.876675752053633e-05, "loss": 4.4352, "step": 3287 }, { "epoch": 0.10042761148442272, "grad_norm": 0.39204221963882446, "learning_rate": 4.8766013266450574e-05, "loss": 4.4965, "step": 3288 }, { "epoch": 0.10045815516188149, "grad_norm": 0.3920549750328064, "learning_rate": 4.87652687935389e-05, "loss": 4.4175, "step": 3289 }, { "epoch": 0.10048869883934025, "grad_norm": 0.4136514663696289, "learning_rate": 4.8764524101808186e-05, "loss": 4.4517, "step": 3290 }, { "epoch": 0.10051924251679903, "grad_norm": 0.39141806960105896, "learning_rate": 4.876377919126527e-05, "loss": 4.4492, "step": 3291 }, { "epoch": 0.10054978619425779, "grad_norm": 0.3967383801937103, "learning_rate": 4.876303406191703e-05, "loss": 4.4369, "step": 3292 }, { "epoch": 0.10058032987171656, "grad_norm": 0.4001462161540985, "learning_rate": 4.876228871377031e-05, "loss": 4.4349, "step": 3293 }, { "epoch": 0.10061087354917532, "grad_norm": 0.4008621871471405, "learning_rate": 4.876154314683199e-05, "loss": 4.354, "step": 3294 }, { "epoch": 0.10064141722663408, "grad_norm": 0.4249272644519806, "learning_rate": 4.8760797361108917e-05, "loss": 4.428, "step": 3295 }, { "epoch": 0.10067196090409285, "grad_norm": 0.39592069387435913, "learning_rate": 4.876005135660797e-05, "loss": 4.4443, "step": 3296 }, { "epoch": 0.10070250458155162, "grad_norm": 0.39285969734191895, "learning_rate": 4.8759305133336016e-05, "loss": 4.4405, "step": 3297 }, { "epoch": 0.10073304825901039, "grad_norm": 0.4051755964756012, "learning_rate": 4.875855869129992e-05, "loss": 4.3708, "step": 3298 }, { "epoch": 0.10076359193646915, "grad_norm": 0.40946438908576965, "learning_rate": 4.875781203050656e-05, "loss": 4.3875, "step": 3299 }, { "epoch": 0.10079413561392792, "grad_norm": 0.39219775795936584, "learning_rate": 4.875706515096281e-05, "loss": 4.4102, "step": 3300 }, { "epoch": 0.10082467929138668, "grad_norm": 0.4042494595050812, "learning_rate": 4.8756318052675544e-05, "loss": 4.4383, "step": 3301 }, { "epoch": 0.10085522296884544, "grad_norm": 0.398874968290329, "learning_rate": 4.875557073565165e-05, "loss": 4.3843, "step": 3302 }, { "epoch": 0.10088576664630422, "grad_norm": 0.38941723108291626, "learning_rate": 4.875482319989799e-05, "loss": 4.399, "step": 3303 }, { "epoch": 0.10091631032376298, "grad_norm": 0.38751021027565, "learning_rate": 4.8754075445421464e-05, "loss": 4.3909, "step": 3304 }, { "epoch": 0.10094685400122175, "grad_norm": 0.39418092370033264, "learning_rate": 4.875332747222896e-05, "loss": 4.3568, "step": 3305 }, { "epoch": 0.10097739767868051, "grad_norm": 0.4044690430164337, "learning_rate": 4.875257928032736e-05, "loss": 4.4093, "step": 3306 }, { "epoch": 0.10100794135613927, "grad_norm": 0.42270028591156006, "learning_rate": 4.8751830869723535e-05, "loss": 4.5013, "step": 3307 }, { "epoch": 0.10103848503359804, "grad_norm": 0.39817437529563904, "learning_rate": 4.875108224042439e-05, "loss": 4.4353, "step": 3308 }, { "epoch": 0.10106902871105682, "grad_norm": 0.38571658730506897, "learning_rate": 4.875033339243684e-05, "loss": 4.4456, "step": 3309 }, { "epoch": 0.10109957238851558, "grad_norm": 0.41721925139427185, "learning_rate": 4.874958432576774e-05, "loss": 4.447, "step": 3310 }, { "epoch": 0.10113011606597434, "grad_norm": 0.39924970269203186, "learning_rate": 4.8748835040424016e-05, "loss": 4.4716, "step": 3311 }, { "epoch": 0.1011606597434331, "grad_norm": 0.4062357246875763, "learning_rate": 4.8748085536412556e-05, "loss": 4.4433, "step": 3312 }, { "epoch": 0.10119120342089187, "grad_norm": 0.40912386775016785, "learning_rate": 4.874733581374026e-05, "loss": 4.4283, "step": 3313 }, { "epoch": 0.10122174709835065, "grad_norm": 0.39377108216285706, "learning_rate": 4.8746585872414036e-05, "loss": 4.4742, "step": 3314 }, { "epoch": 0.10125229077580941, "grad_norm": 0.41096368432044983, "learning_rate": 4.874583571244079e-05, "loss": 4.4049, "step": 3315 }, { "epoch": 0.10128283445326818, "grad_norm": 0.41849544644355774, "learning_rate": 4.874508533382741e-05, "loss": 4.4856, "step": 3316 }, { "epoch": 0.10131337813072694, "grad_norm": 0.4030824303627014, "learning_rate": 4.874433473658084e-05, "loss": 4.4925, "step": 3317 }, { "epoch": 0.1013439218081857, "grad_norm": 0.3995719254016876, "learning_rate": 4.874358392070796e-05, "loss": 4.3006, "step": 3318 }, { "epoch": 0.10137446548564447, "grad_norm": 0.417148619890213, "learning_rate": 4.87428328862157e-05, "loss": 4.3963, "step": 3319 }, { "epoch": 0.10140500916310324, "grad_norm": 0.4133656919002533, "learning_rate": 4.874208163311097e-05, "loss": 4.3694, "step": 3320 }, { "epoch": 0.10143555284056201, "grad_norm": 0.39783599972724915, "learning_rate": 4.874133016140069e-05, "loss": 4.4068, "step": 3321 }, { "epoch": 0.10146609651802077, "grad_norm": 0.40349459648132324, "learning_rate": 4.874057847109177e-05, "loss": 4.4254, "step": 3322 }, { "epoch": 0.10149664019547953, "grad_norm": 0.4022940397262573, "learning_rate": 4.873982656219114e-05, "loss": 4.3787, "step": 3323 }, { "epoch": 0.1015271838729383, "grad_norm": 0.4043528735637665, "learning_rate": 4.873907443470572e-05, "loss": 4.393, "step": 3324 }, { "epoch": 0.10155772755039706, "grad_norm": 0.40771353244781494, "learning_rate": 4.873832208864244e-05, "loss": 4.4406, "step": 3325 }, { "epoch": 0.10158827122785584, "grad_norm": 0.40254446864128113, "learning_rate": 4.873756952400822e-05, "loss": 4.3784, "step": 3326 }, { "epoch": 0.1016188149053146, "grad_norm": 0.416727215051651, "learning_rate": 4.8736816740809996e-05, "loss": 4.3582, "step": 3327 }, { "epoch": 0.10164935858277337, "grad_norm": 0.401071697473526, "learning_rate": 4.873606373905469e-05, "loss": 4.3918, "step": 3328 }, { "epoch": 0.10167990226023213, "grad_norm": 0.3918854296207428, "learning_rate": 4.873531051874925e-05, "loss": 4.3975, "step": 3329 }, { "epoch": 0.1017104459376909, "grad_norm": 0.40629783272743225, "learning_rate": 4.87345570799006e-05, "loss": 4.4486, "step": 3330 }, { "epoch": 0.10174098961514966, "grad_norm": 0.40044161677360535, "learning_rate": 4.873380342251568e-05, "loss": 4.3784, "step": 3331 }, { "epoch": 0.10177153329260843, "grad_norm": 0.40297725796699524, "learning_rate": 4.873304954660142e-05, "loss": 4.428, "step": 3332 }, { "epoch": 0.1018020769700672, "grad_norm": 0.41064563393592834, "learning_rate": 4.8732295452164775e-05, "loss": 4.4206, "step": 3333 }, { "epoch": 0.10183262064752596, "grad_norm": 0.39726337790489197, "learning_rate": 4.8731541139212695e-05, "loss": 4.3612, "step": 3334 }, { "epoch": 0.10186316432498473, "grad_norm": 0.3941470980644226, "learning_rate": 4.87307866077521e-05, "loss": 4.4986, "step": 3335 }, { "epoch": 0.10189370800244349, "grad_norm": 0.39826640486717224, "learning_rate": 4.873003185778996e-05, "loss": 4.4229, "step": 3336 }, { "epoch": 0.10192425167990227, "grad_norm": 0.401734322309494, "learning_rate": 4.872927688933321e-05, "loss": 4.3701, "step": 3337 }, { "epoch": 0.10195479535736103, "grad_norm": 0.41553786396980286, "learning_rate": 4.872852170238882e-05, "loss": 4.4474, "step": 3338 }, { "epoch": 0.1019853390348198, "grad_norm": 0.3882528841495514, "learning_rate": 4.872776629696372e-05, "loss": 4.3979, "step": 3339 }, { "epoch": 0.10201588271227856, "grad_norm": 0.3984779119491577, "learning_rate": 4.872701067306488e-05, "loss": 4.3491, "step": 3340 }, { "epoch": 0.10204642638973732, "grad_norm": 0.4131994843482971, "learning_rate": 4.872625483069925e-05, "loss": 4.4462, "step": 3341 }, { "epoch": 0.10207697006719609, "grad_norm": 0.42780280113220215, "learning_rate": 4.872549876987379e-05, "loss": 4.3994, "step": 3342 }, { "epoch": 0.10210751374465486, "grad_norm": 0.411694198846817, "learning_rate": 4.8724742490595465e-05, "loss": 4.394, "step": 3343 }, { "epoch": 0.10213805742211363, "grad_norm": 0.41738516092300415, "learning_rate": 4.872398599287125e-05, "loss": 4.4904, "step": 3344 }, { "epoch": 0.10216860109957239, "grad_norm": 0.42547255754470825, "learning_rate": 4.872322927670808e-05, "loss": 4.491, "step": 3345 }, { "epoch": 0.10219914477703115, "grad_norm": 0.407569944858551, "learning_rate": 4.872247234211295e-05, "loss": 4.4906, "step": 3346 }, { "epoch": 0.10222968845448992, "grad_norm": 0.40515992045402527, "learning_rate": 4.872171518909282e-05, "loss": 4.4076, "step": 3347 }, { "epoch": 0.10226023213194868, "grad_norm": 0.40678197145462036, "learning_rate": 4.8720957817654666e-05, "loss": 4.4896, "step": 3348 }, { "epoch": 0.10229077580940746, "grad_norm": 0.3964155614376068, "learning_rate": 4.8720200227805454e-05, "loss": 4.4314, "step": 3349 }, { "epoch": 0.10232131948686622, "grad_norm": 0.425082266330719, "learning_rate": 4.8719442419552164e-05, "loss": 4.3449, "step": 3350 }, { "epoch": 0.10235186316432499, "grad_norm": 0.4312756061553955, "learning_rate": 4.871868439290177e-05, "loss": 4.4052, "step": 3351 }, { "epoch": 0.10238240684178375, "grad_norm": 0.39977070689201355, "learning_rate": 4.871792614786125e-05, "loss": 4.4226, "step": 3352 }, { "epoch": 0.10241295051924251, "grad_norm": 0.40476328134536743, "learning_rate": 4.871716768443759e-05, "loss": 4.4488, "step": 3353 }, { "epoch": 0.10244349419670128, "grad_norm": 0.4120510220527649, "learning_rate": 4.871640900263778e-05, "loss": 4.4441, "step": 3354 }, { "epoch": 0.10247403787416005, "grad_norm": 0.40113160014152527, "learning_rate": 4.8715650102468796e-05, "loss": 4.4504, "step": 3355 }, { "epoch": 0.10250458155161882, "grad_norm": 0.4168161451816559, "learning_rate": 4.8714890983937625e-05, "loss": 4.4582, "step": 3356 }, { "epoch": 0.10253512522907758, "grad_norm": 0.42128029465675354, "learning_rate": 4.871413164705127e-05, "loss": 4.4344, "step": 3357 }, { "epoch": 0.10256566890653634, "grad_norm": 0.3925253748893738, "learning_rate": 4.87133720918167e-05, "loss": 4.3698, "step": 3358 }, { "epoch": 0.10259621258399511, "grad_norm": 0.40148013830184937, "learning_rate": 4.871261231824092e-05, "loss": 4.4243, "step": 3359 }, { "epoch": 0.10262675626145389, "grad_norm": 0.3962223529815674, "learning_rate": 4.8711852326330934e-05, "loss": 4.402, "step": 3360 }, { "epoch": 0.10265729993891265, "grad_norm": 0.4012763798236847, "learning_rate": 4.871109211609374e-05, "loss": 4.453, "step": 3361 }, { "epoch": 0.10268784361637141, "grad_norm": 0.40612947940826416, "learning_rate": 4.8710331687536316e-05, "loss": 4.3468, "step": 3362 }, { "epoch": 0.10271838729383018, "grad_norm": 0.4097200036048889, "learning_rate": 4.870957104066568e-05, "loss": 4.3674, "step": 3363 }, { "epoch": 0.10274893097128894, "grad_norm": 0.4007739722728729, "learning_rate": 4.870881017548883e-05, "loss": 4.4501, "step": 3364 }, { "epoch": 0.1027794746487477, "grad_norm": 0.39396464824676514, "learning_rate": 4.8708049092012785e-05, "loss": 4.4331, "step": 3365 }, { "epoch": 0.10281001832620648, "grad_norm": 0.40180572867393494, "learning_rate": 4.8707287790244536e-05, "loss": 4.4331, "step": 3366 }, { "epoch": 0.10284056200366525, "grad_norm": 0.39371928572654724, "learning_rate": 4.87065262701911e-05, "loss": 4.411, "step": 3367 }, { "epoch": 0.10287110568112401, "grad_norm": 0.3938819468021393, "learning_rate": 4.870576453185949e-05, "loss": 4.435, "step": 3368 }, { "epoch": 0.10290164935858277, "grad_norm": 0.3965904116630554, "learning_rate": 4.8705002575256715e-05, "loss": 4.4132, "step": 3369 }, { "epoch": 0.10293219303604154, "grad_norm": 0.38594910502433777, "learning_rate": 4.8704240400389794e-05, "loss": 4.3947, "step": 3370 }, { "epoch": 0.1029627367135003, "grad_norm": 0.38021332025527954, "learning_rate": 4.8703478007265746e-05, "loss": 4.3675, "step": 3371 }, { "epoch": 0.10299328039095908, "grad_norm": 0.4127308428287506, "learning_rate": 4.870271539589158e-05, "loss": 4.2912, "step": 3372 }, { "epoch": 0.10302382406841784, "grad_norm": 0.40197262167930603, "learning_rate": 4.870195256627434e-05, "loss": 4.3695, "step": 3373 }, { "epoch": 0.1030543677458766, "grad_norm": 0.39110222458839417, "learning_rate": 4.870118951842103e-05, "loss": 4.2464, "step": 3374 }, { "epoch": 0.10308491142333537, "grad_norm": 0.40679875016212463, "learning_rate": 4.870042625233868e-05, "loss": 4.3836, "step": 3375 }, { "epoch": 0.10311545510079413, "grad_norm": 0.3980865180492401, "learning_rate": 4.8699662768034325e-05, "loss": 4.3659, "step": 3376 }, { "epoch": 0.1031459987782529, "grad_norm": 0.39796385169029236, "learning_rate": 4.869889906551498e-05, "loss": 4.3466, "step": 3377 }, { "epoch": 0.10317654245571167, "grad_norm": 0.4076217710971832, "learning_rate": 4.86981351447877e-05, "loss": 4.4619, "step": 3378 }, { "epoch": 0.10320708613317044, "grad_norm": 0.3979220390319824, "learning_rate": 4.8697371005859496e-05, "loss": 4.4216, "step": 3379 }, { "epoch": 0.1032376298106292, "grad_norm": 0.40407663583755493, "learning_rate": 4.869660664873742e-05, "loss": 4.4158, "step": 3380 }, { "epoch": 0.10326817348808796, "grad_norm": 0.4004320502281189, "learning_rate": 4.86958420734285e-05, "loss": 4.3506, "step": 3381 }, { "epoch": 0.10329871716554673, "grad_norm": 0.4055318534374237, "learning_rate": 4.869507727993978e-05, "loss": 4.4182, "step": 3382 }, { "epoch": 0.10332926084300549, "grad_norm": 0.40730708837509155, "learning_rate": 4.86943122682783e-05, "loss": 4.4598, "step": 3383 }, { "epoch": 0.10335980452046427, "grad_norm": 0.4030701518058777, "learning_rate": 4.86935470384511e-05, "loss": 4.3791, "step": 3384 }, { "epoch": 0.10339034819792303, "grad_norm": 0.39946913719177246, "learning_rate": 4.869278159046523e-05, "loss": 4.3703, "step": 3385 }, { "epoch": 0.1034208918753818, "grad_norm": 0.41174888610839844, "learning_rate": 4.869201592432774e-05, "loss": 4.4126, "step": 3386 }, { "epoch": 0.10345143555284056, "grad_norm": 0.4007677137851715, "learning_rate": 4.869125004004568e-05, "loss": 4.3803, "step": 3387 }, { "epoch": 0.10348197923029932, "grad_norm": 0.4010480046272278, "learning_rate": 4.86904839376261e-05, "loss": 4.4214, "step": 3388 }, { "epoch": 0.1035125229077581, "grad_norm": 0.40816569328308105, "learning_rate": 4.868971761707606e-05, "loss": 4.2905, "step": 3389 }, { "epoch": 0.10354306658521686, "grad_norm": 0.41183122992515564, "learning_rate": 4.86889510784026e-05, "loss": 4.4481, "step": 3390 }, { "epoch": 0.10357361026267563, "grad_norm": 0.405130535364151, "learning_rate": 4.8688184321612795e-05, "loss": 4.3578, "step": 3391 }, { "epoch": 0.10360415394013439, "grad_norm": 0.41023731231689453, "learning_rate": 4.868741734671369e-05, "loss": 4.3695, "step": 3392 }, { "epoch": 0.10363469761759316, "grad_norm": 0.407513827085495, "learning_rate": 4.868665015371236e-05, "loss": 4.4214, "step": 3393 }, { "epoch": 0.10366524129505192, "grad_norm": 0.40675270557403564, "learning_rate": 4.868588274261586e-05, "loss": 4.442, "step": 3394 }, { "epoch": 0.1036957849725107, "grad_norm": 0.3898625075817108, "learning_rate": 4.868511511343127e-05, "loss": 4.2819, "step": 3395 }, { "epoch": 0.10372632864996946, "grad_norm": 0.3947095274925232, "learning_rate": 4.8684347266165636e-05, "loss": 4.4153, "step": 3396 }, { "epoch": 0.10375687232742822, "grad_norm": 0.40996217727661133, "learning_rate": 4.868357920082605e-05, "loss": 4.4015, "step": 3397 }, { "epoch": 0.10378741600488699, "grad_norm": 0.4099217653274536, "learning_rate": 4.868281091741956e-05, "loss": 4.3841, "step": 3398 }, { "epoch": 0.10381795968234575, "grad_norm": 0.3946872055530548, "learning_rate": 4.8682042415953256e-05, "loss": 4.3999, "step": 3399 }, { "epoch": 0.10384850335980451, "grad_norm": 0.40408313274383545, "learning_rate": 4.868127369643421e-05, "loss": 4.3653, "step": 3400 }, { "epoch": 0.10387904703726329, "grad_norm": 0.4178633391857147, "learning_rate": 4.8680504758869516e-05, "loss": 4.4235, "step": 3401 }, { "epoch": 0.10390959071472206, "grad_norm": 0.40536466240882874, "learning_rate": 4.867973560326623e-05, "loss": 4.376, "step": 3402 }, { "epoch": 0.10394013439218082, "grad_norm": 0.4181455075740814, "learning_rate": 4.867896622963144e-05, "loss": 4.3426, "step": 3403 }, { "epoch": 0.10397067806963958, "grad_norm": 0.3968583345413208, "learning_rate": 4.867819663797224e-05, "loss": 4.3765, "step": 3404 }, { "epoch": 0.10400122174709835, "grad_norm": 0.4049570858478546, "learning_rate": 4.8677426828295705e-05, "loss": 4.4019, "step": 3405 }, { "epoch": 0.10403176542455711, "grad_norm": 0.4050014317035675, "learning_rate": 4.867665680060893e-05, "loss": 4.4313, "step": 3406 }, { "epoch": 0.10406230910201589, "grad_norm": 0.3929878771305084, "learning_rate": 4.8675886554919e-05, "loss": 4.4043, "step": 3407 }, { "epoch": 0.10409285277947465, "grad_norm": 0.3952869772911072, "learning_rate": 4.8675116091233005e-05, "loss": 4.4373, "step": 3408 }, { "epoch": 0.10412339645693341, "grad_norm": 0.40952813625335693, "learning_rate": 4.8674345409558054e-05, "loss": 4.3547, "step": 3409 }, { "epoch": 0.10415394013439218, "grad_norm": 0.39474767446517944, "learning_rate": 4.8673574509901234e-05, "loss": 4.4041, "step": 3410 }, { "epoch": 0.10418448381185094, "grad_norm": 0.39655545353889465, "learning_rate": 4.8672803392269626e-05, "loss": 4.4505, "step": 3411 }, { "epoch": 0.10421502748930972, "grad_norm": 0.414853036403656, "learning_rate": 4.867203205667036e-05, "loss": 4.4906, "step": 3412 }, { "epoch": 0.10424557116676848, "grad_norm": 0.409990519285202, "learning_rate": 4.867126050311051e-05, "loss": 4.4562, "step": 3413 }, { "epoch": 0.10427611484422725, "grad_norm": 0.39132067561149597, "learning_rate": 4.8670488731597205e-05, "loss": 4.3949, "step": 3414 }, { "epoch": 0.10430665852168601, "grad_norm": 0.3986087441444397, "learning_rate": 4.866971674213754e-05, "loss": 4.4117, "step": 3415 }, { "epoch": 0.10433720219914477, "grad_norm": 0.4171684980392456, "learning_rate": 4.8668944534738626e-05, "loss": 4.5098, "step": 3416 }, { "epoch": 0.10436774587660354, "grad_norm": 0.40293312072753906, "learning_rate": 4.8668172109407566e-05, "loss": 4.4786, "step": 3417 }, { "epoch": 0.10439828955406232, "grad_norm": 0.39256373047828674, "learning_rate": 4.8667399466151475e-05, "loss": 4.4013, "step": 3418 }, { "epoch": 0.10442883323152108, "grad_norm": 0.39474380016326904, "learning_rate": 4.866662660497747e-05, "loss": 4.4632, "step": 3419 }, { "epoch": 0.10445937690897984, "grad_norm": 0.40216559171676636, "learning_rate": 4.8665853525892666e-05, "loss": 4.3849, "step": 3420 }, { "epoch": 0.1044899205864386, "grad_norm": 0.39610573649406433, "learning_rate": 4.8665080228904184e-05, "loss": 4.3994, "step": 3421 }, { "epoch": 0.10452046426389737, "grad_norm": 0.4221336543560028, "learning_rate": 4.866430671401914e-05, "loss": 4.4125, "step": 3422 }, { "epoch": 0.10455100794135613, "grad_norm": 0.4072960913181305, "learning_rate": 4.8663532981244654e-05, "loss": 4.4566, "step": 3423 }, { "epoch": 0.10458155161881491, "grad_norm": 0.4027442932128906, "learning_rate": 4.866275903058784e-05, "loss": 4.3559, "step": 3424 }, { "epoch": 0.10461209529627367, "grad_norm": 0.3922978639602661, "learning_rate": 4.866198486205586e-05, "loss": 4.4516, "step": 3425 }, { "epoch": 0.10464263897373244, "grad_norm": 0.41238895058631897, "learning_rate": 4.866121047565581e-05, "loss": 4.4349, "step": 3426 }, { "epoch": 0.1046731826511912, "grad_norm": 0.40000784397125244, "learning_rate": 4.866043587139483e-05, "loss": 4.4576, "step": 3427 }, { "epoch": 0.10470372632864997, "grad_norm": 0.4084357023239136, "learning_rate": 4.8659661049280056e-05, "loss": 4.5084, "step": 3428 }, { "epoch": 0.10473427000610873, "grad_norm": 0.40939074754714966, "learning_rate": 4.8658886009318614e-05, "loss": 4.5028, "step": 3429 }, { "epoch": 0.1047648136835675, "grad_norm": 0.41148218512535095, "learning_rate": 4.8658110751517644e-05, "loss": 4.3854, "step": 3430 }, { "epoch": 0.10479535736102627, "grad_norm": 0.3892272412776947, "learning_rate": 4.8657335275884284e-05, "loss": 4.3531, "step": 3431 }, { "epoch": 0.10482590103848503, "grad_norm": 0.3930671513080597, "learning_rate": 4.8656559582425674e-05, "loss": 4.3951, "step": 3432 }, { "epoch": 0.1048564447159438, "grad_norm": 0.413738876581192, "learning_rate": 4.865578367114896e-05, "loss": 4.3674, "step": 3433 }, { "epoch": 0.10488698839340256, "grad_norm": 0.4070027768611908, "learning_rate": 4.865500754206128e-05, "loss": 4.3986, "step": 3434 }, { "epoch": 0.10491753207086134, "grad_norm": 0.40221065282821655, "learning_rate": 4.8654231195169785e-05, "loss": 4.448, "step": 3435 }, { "epoch": 0.1049480757483201, "grad_norm": 0.4036170542240143, "learning_rate": 4.865345463048163e-05, "loss": 4.4515, "step": 3436 }, { "epoch": 0.10497861942577887, "grad_norm": 0.40874531865119934, "learning_rate": 4.8652677848003945e-05, "loss": 4.4275, "step": 3437 }, { "epoch": 0.10500916310323763, "grad_norm": 0.40532559156417847, "learning_rate": 4.86519008477439e-05, "loss": 4.4213, "step": 3438 }, { "epoch": 0.10503970678069639, "grad_norm": 0.3814595639705658, "learning_rate": 4.865112362970864e-05, "loss": 4.4317, "step": 3439 }, { "epoch": 0.10507025045815516, "grad_norm": 0.40217912197113037, "learning_rate": 4.865034619390533e-05, "loss": 4.349, "step": 3440 }, { "epoch": 0.10510079413561393, "grad_norm": 0.4098658859729767, "learning_rate": 4.8649568540341116e-05, "loss": 4.4546, "step": 3441 }, { "epoch": 0.1051313378130727, "grad_norm": 0.39451539516448975, "learning_rate": 4.864879066902317e-05, "loss": 4.4279, "step": 3442 }, { "epoch": 0.10516188149053146, "grad_norm": 0.41833046078681946, "learning_rate": 4.8648012579958646e-05, "loss": 4.43, "step": 3443 }, { "epoch": 0.10519242516799023, "grad_norm": 0.40217888355255127, "learning_rate": 4.8647234273154705e-05, "loss": 4.4086, "step": 3444 }, { "epoch": 0.10522296884544899, "grad_norm": 0.4068833291530609, "learning_rate": 4.864645574861853e-05, "loss": 4.3294, "step": 3445 }, { "epoch": 0.10525351252290775, "grad_norm": 0.3992142975330353, "learning_rate": 4.8645677006357285e-05, "loss": 4.4808, "step": 3446 }, { "epoch": 0.10528405620036653, "grad_norm": 0.4122178852558136, "learning_rate": 4.864489804637812e-05, "loss": 4.4697, "step": 3447 }, { "epoch": 0.1053145998778253, "grad_norm": 0.4131196141242981, "learning_rate": 4.8644118868688225e-05, "loss": 4.3682, "step": 3448 }, { "epoch": 0.10534514355528406, "grad_norm": 0.3967343270778656, "learning_rate": 4.864333947329477e-05, "loss": 4.3887, "step": 3449 }, { "epoch": 0.10537568723274282, "grad_norm": 0.38600674271583557, "learning_rate": 4.864255986020494e-05, "loss": 4.3482, "step": 3450 }, { "epoch": 0.10540623091020158, "grad_norm": 0.397812157869339, "learning_rate": 4.86417800294259e-05, "loss": 4.4844, "step": 3451 }, { "epoch": 0.10543677458766035, "grad_norm": 0.42699766159057617, "learning_rate": 4.864099998096484e-05, "loss": 4.5267, "step": 3452 }, { "epoch": 0.10546731826511913, "grad_norm": 0.39130258560180664, "learning_rate": 4.864021971482894e-05, "loss": 4.3276, "step": 3453 }, { "epoch": 0.10549786194257789, "grad_norm": 0.3951404094696045, "learning_rate": 4.863943923102538e-05, "loss": 4.4775, "step": 3454 }, { "epoch": 0.10552840562003665, "grad_norm": 0.4027854800224304, "learning_rate": 4.8638658529561344e-05, "loss": 4.3806, "step": 3455 }, { "epoch": 0.10555894929749542, "grad_norm": 0.4012998640537262, "learning_rate": 4.863787761044403e-05, "loss": 4.4489, "step": 3456 }, { "epoch": 0.10558949297495418, "grad_norm": 0.41275230050086975, "learning_rate": 4.8637096473680616e-05, "loss": 4.4806, "step": 3457 }, { "epoch": 0.10562003665241294, "grad_norm": 0.394881010055542, "learning_rate": 4.863631511927831e-05, "loss": 4.344, "step": 3458 }, { "epoch": 0.10565058032987172, "grad_norm": 0.40866315364837646, "learning_rate": 4.863553354724429e-05, "loss": 4.4089, "step": 3459 }, { "epoch": 0.10568112400733048, "grad_norm": 0.39361879229545593, "learning_rate": 4.863475175758577e-05, "loss": 4.4295, "step": 3460 }, { "epoch": 0.10571166768478925, "grad_norm": 0.3928965628147125, "learning_rate": 4.863396975030993e-05, "loss": 4.3593, "step": 3461 }, { "epoch": 0.10574221136224801, "grad_norm": 0.39697015285491943, "learning_rate": 4.863318752542398e-05, "loss": 4.3928, "step": 3462 }, { "epoch": 0.10577275503970678, "grad_norm": 0.39388662576675415, "learning_rate": 4.863240508293513e-05, "loss": 4.4326, "step": 3463 }, { "epoch": 0.10580329871716555, "grad_norm": 0.4117012023925781, "learning_rate": 4.863162242285057e-05, "loss": 4.3829, "step": 3464 }, { "epoch": 0.10583384239462432, "grad_norm": 0.40141984820365906, "learning_rate": 4.863083954517751e-05, "loss": 4.4472, "step": 3465 }, { "epoch": 0.10586438607208308, "grad_norm": 0.418765664100647, "learning_rate": 4.8630056449923166e-05, "loss": 4.4337, "step": 3466 }, { "epoch": 0.10589492974954184, "grad_norm": 0.4036598801612854, "learning_rate": 4.862927313709475e-05, "loss": 4.3627, "step": 3467 }, { "epoch": 0.10592547342700061, "grad_norm": 0.3958536684513092, "learning_rate": 4.8628489606699444e-05, "loss": 4.4299, "step": 3468 }, { "epoch": 0.10595601710445937, "grad_norm": 0.409550279378891, "learning_rate": 4.86277058587445e-05, "loss": 4.3941, "step": 3469 }, { "epoch": 0.10598656078191815, "grad_norm": 0.41254428029060364, "learning_rate": 4.862692189323712e-05, "loss": 4.3792, "step": 3470 }, { "epoch": 0.10601710445937691, "grad_norm": 0.41431301832199097, "learning_rate": 4.862613771018453e-05, "loss": 4.4143, "step": 3471 }, { "epoch": 0.10604764813683568, "grad_norm": 0.4200925827026367, "learning_rate": 4.862535330959393e-05, "loss": 4.3594, "step": 3472 }, { "epoch": 0.10607819181429444, "grad_norm": 0.41380414366722107, "learning_rate": 4.862456869147256e-05, "loss": 4.335, "step": 3473 }, { "epoch": 0.1061087354917532, "grad_norm": 0.38878870010375977, "learning_rate": 4.8623783855827637e-05, "loss": 4.3245, "step": 3474 }, { "epoch": 0.10613927916921197, "grad_norm": 0.41191086173057556, "learning_rate": 4.862299880266639e-05, "loss": 4.4689, "step": 3475 }, { "epoch": 0.10616982284667074, "grad_norm": 0.4231735169887543, "learning_rate": 4.862221353199605e-05, "loss": 4.4356, "step": 3476 }, { "epoch": 0.10620036652412951, "grad_norm": 0.39217400550842285, "learning_rate": 4.862142804382385e-05, "loss": 4.3598, "step": 3477 }, { "epoch": 0.10623091020158827, "grad_norm": 0.3981366753578186, "learning_rate": 4.862064233815701e-05, "loss": 4.3668, "step": 3478 }, { "epoch": 0.10626145387904704, "grad_norm": 0.4054492115974426, "learning_rate": 4.861985641500277e-05, "loss": 4.4041, "step": 3479 }, { "epoch": 0.1062919975565058, "grad_norm": 0.39943990111351013, "learning_rate": 4.861907027436837e-05, "loss": 4.3528, "step": 3480 }, { "epoch": 0.10632254123396456, "grad_norm": 0.4058052599430084, "learning_rate": 4.861828391626104e-05, "loss": 4.353, "step": 3481 }, { "epoch": 0.10635308491142334, "grad_norm": 0.41080060601234436, "learning_rate": 4.861749734068804e-05, "loss": 4.4119, "step": 3482 }, { "epoch": 0.1063836285888821, "grad_norm": 0.39857321977615356, "learning_rate": 4.861671054765659e-05, "loss": 4.4212, "step": 3483 }, { "epoch": 0.10641417226634087, "grad_norm": 0.41371604800224304, "learning_rate": 4.861592353717395e-05, "loss": 4.3435, "step": 3484 }, { "epoch": 0.10644471594379963, "grad_norm": 0.40466275811195374, "learning_rate": 4.861513630924736e-05, "loss": 4.4258, "step": 3485 }, { "epoch": 0.1064752596212584, "grad_norm": 0.39832067489624023, "learning_rate": 4.8614348863884056e-05, "loss": 4.3754, "step": 3486 }, { "epoch": 0.10650580329871717, "grad_norm": 0.4043061137199402, "learning_rate": 4.8613561201091305e-05, "loss": 4.3601, "step": 3487 }, { "epoch": 0.10653634697617594, "grad_norm": 0.41354888677597046, "learning_rate": 4.861277332087636e-05, "loss": 4.4301, "step": 3488 }, { "epoch": 0.1065668906536347, "grad_norm": 0.3894142508506775, "learning_rate": 4.861198522324647e-05, "loss": 4.4346, "step": 3489 }, { "epoch": 0.10659743433109346, "grad_norm": 0.39023634791374207, "learning_rate": 4.861119690820889e-05, "loss": 4.3108, "step": 3490 }, { "epoch": 0.10662797800855223, "grad_norm": 0.39964115619659424, "learning_rate": 4.8610408375770886e-05, "loss": 4.4014, "step": 3491 }, { "epoch": 0.10665852168601099, "grad_norm": 0.39258652925491333, "learning_rate": 4.8609619625939704e-05, "loss": 4.3737, "step": 3492 }, { "epoch": 0.10668906536346977, "grad_norm": 0.40479540824890137, "learning_rate": 4.8608830658722625e-05, "loss": 4.3681, "step": 3493 }, { "epoch": 0.10671960904092853, "grad_norm": 0.41083717346191406, "learning_rate": 4.86080414741269e-05, "loss": 4.5283, "step": 3494 }, { "epoch": 0.1067501527183873, "grad_norm": 0.41649022698402405, "learning_rate": 4.8607252072159794e-05, "loss": 4.4109, "step": 3495 }, { "epoch": 0.10678069639584606, "grad_norm": 0.4095604717731476, "learning_rate": 4.860646245282858e-05, "loss": 4.4865, "step": 3496 }, { "epoch": 0.10681124007330482, "grad_norm": 0.38430339097976685, "learning_rate": 4.860567261614054e-05, "loss": 4.3536, "step": 3497 }, { "epoch": 0.10684178375076359, "grad_norm": 0.40196317434310913, "learning_rate": 4.8604882562102926e-05, "loss": 4.4509, "step": 3498 }, { "epoch": 0.10687232742822236, "grad_norm": 0.4096452295780182, "learning_rate": 4.860409229072302e-05, "loss": 4.4222, "step": 3499 }, { "epoch": 0.10690287110568113, "grad_norm": 0.40479156374931335, "learning_rate": 4.86033018020081e-05, "loss": 4.4022, "step": 3500 }, { "epoch": 0.10693341478313989, "grad_norm": 0.40381768345832825, "learning_rate": 4.8602511095965456e-05, "loss": 4.3651, "step": 3501 }, { "epoch": 0.10696395846059865, "grad_norm": 0.40386343002319336, "learning_rate": 4.860172017260235e-05, "loss": 4.367, "step": 3502 }, { "epoch": 0.10699450213805742, "grad_norm": 0.3939872980117798, "learning_rate": 4.860092903192607e-05, "loss": 4.4786, "step": 3503 }, { "epoch": 0.10702504581551618, "grad_norm": 0.3911398649215698, "learning_rate": 4.860013767394391e-05, "loss": 4.4765, "step": 3504 }, { "epoch": 0.10705558949297496, "grad_norm": 0.40428486466407776, "learning_rate": 4.859934609866314e-05, "loss": 4.3976, "step": 3505 }, { "epoch": 0.10708613317043372, "grad_norm": 0.38835403323173523, "learning_rate": 4.859855430609106e-05, "loss": 4.408, "step": 3506 }, { "epoch": 0.10711667684789249, "grad_norm": 0.40683332085609436, "learning_rate": 4.8597762296234954e-05, "loss": 4.3296, "step": 3507 }, { "epoch": 0.10714722052535125, "grad_norm": 0.39766791462898254, "learning_rate": 4.859697006910212e-05, "loss": 4.5133, "step": 3508 }, { "epoch": 0.10717776420281001, "grad_norm": 0.4084357023239136, "learning_rate": 4.8596177624699854e-05, "loss": 4.403, "step": 3509 }, { "epoch": 0.10720830788026879, "grad_norm": 0.39057692885398865, "learning_rate": 4.859538496303544e-05, "loss": 4.3065, "step": 3510 }, { "epoch": 0.10723885155772755, "grad_norm": 0.41337424516677856, "learning_rate": 4.8594592084116195e-05, "loss": 4.4209, "step": 3511 }, { "epoch": 0.10726939523518632, "grad_norm": 0.4021071195602417, "learning_rate": 4.8593798987949404e-05, "loss": 4.4113, "step": 3512 }, { "epoch": 0.10729993891264508, "grad_norm": 0.3975255489349365, "learning_rate": 4.859300567454237e-05, "loss": 4.3365, "step": 3513 }, { "epoch": 0.10733048259010385, "grad_norm": 0.3916986584663391, "learning_rate": 4.859221214390242e-05, "loss": 4.3805, "step": 3514 }, { "epoch": 0.10736102626756261, "grad_norm": 0.40836018323898315, "learning_rate": 4.859141839603683e-05, "loss": 4.4314, "step": 3515 }, { "epoch": 0.10739156994502139, "grad_norm": 0.3918825387954712, "learning_rate": 4.8590624430952916e-05, "loss": 4.3811, "step": 3516 }, { "epoch": 0.10742211362248015, "grad_norm": 0.4156215786933899, "learning_rate": 4.8589830248657996e-05, "loss": 4.4719, "step": 3517 }, { "epoch": 0.10745265729993891, "grad_norm": 0.44062328338623047, "learning_rate": 4.858903584915939e-05, "loss": 4.4387, "step": 3518 }, { "epoch": 0.10748320097739768, "grad_norm": 0.4020231068134308, "learning_rate": 4.858824123246439e-05, "loss": 4.3393, "step": 3519 }, { "epoch": 0.10751374465485644, "grad_norm": 0.40741103887557983, "learning_rate": 4.858744639858034e-05, "loss": 4.3963, "step": 3520 }, { "epoch": 0.1075442883323152, "grad_norm": 0.4099840223789215, "learning_rate": 4.858665134751453e-05, "loss": 4.3735, "step": 3521 }, { "epoch": 0.10757483200977398, "grad_norm": 0.3855580985546112, "learning_rate": 4.8585856079274306e-05, "loss": 4.4176, "step": 3522 }, { "epoch": 0.10760537568723275, "grad_norm": 0.3929513990879059, "learning_rate": 4.858506059386697e-05, "loss": 4.3721, "step": 3523 }, { "epoch": 0.10763591936469151, "grad_norm": 0.40057557821273804, "learning_rate": 4.8584264891299855e-05, "loss": 4.3846, "step": 3524 }, { "epoch": 0.10766646304215027, "grad_norm": 0.4127552807331085, "learning_rate": 4.858346897158029e-05, "loss": 4.3536, "step": 3525 }, { "epoch": 0.10769700671960904, "grad_norm": 0.39231637120246887, "learning_rate": 4.8582672834715606e-05, "loss": 4.3231, "step": 3526 }, { "epoch": 0.1077275503970678, "grad_norm": 0.4211205840110779, "learning_rate": 4.8581876480713116e-05, "loss": 4.3916, "step": 3527 }, { "epoch": 0.10775809407452658, "grad_norm": 0.3977634906768799, "learning_rate": 4.8581079909580175e-05, "loss": 4.416, "step": 3528 }, { "epoch": 0.10778863775198534, "grad_norm": 0.39830660820007324, "learning_rate": 4.85802831213241e-05, "loss": 4.4413, "step": 3529 }, { "epoch": 0.1078191814294441, "grad_norm": 0.3879716992378235, "learning_rate": 4.857948611595223e-05, "loss": 4.2896, "step": 3530 }, { "epoch": 0.10784972510690287, "grad_norm": 0.4121384024620056, "learning_rate": 4.8578688893471925e-05, "loss": 4.3967, "step": 3531 }, { "epoch": 0.10788026878436163, "grad_norm": 0.41079121828079224, "learning_rate": 4.8577891453890496e-05, "loss": 4.4293, "step": 3532 }, { "epoch": 0.10791081246182041, "grad_norm": 0.4022669494152069, "learning_rate": 4.85770937972153e-05, "loss": 4.3949, "step": 3533 }, { "epoch": 0.10794135613927917, "grad_norm": 0.38920632004737854, "learning_rate": 4.857629592345368e-05, "loss": 4.3718, "step": 3534 }, { "epoch": 0.10797189981673794, "grad_norm": 0.41231462359428406, "learning_rate": 4.8575497832612985e-05, "loss": 4.3803, "step": 3535 }, { "epoch": 0.1080024434941967, "grad_norm": 0.4087011516094208, "learning_rate": 4.857469952470055e-05, "loss": 4.349, "step": 3536 }, { "epoch": 0.10803298717165546, "grad_norm": 0.3915582597255707, "learning_rate": 4.857390099972374e-05, "loss": 4.3663, "step": 3537 }, { "epoch": 0.10806353084911423, "grad_norm": 0.40569907426834106, "learning_rate": 4.857310225768991e-05, "loss": 4.4254, "step": 3538 }, { "epoch": 0.108094074526573, "grad_norm": 0.39919382333755493, "learning_rate": 4.8572303298606406e-05, "loss": 4.2963, "step": 3539 }, { "epoch": 0.10812461820403177, "grad_norm": 0.4073209762573242, "learning_rate": 4.857150412248058e-05, "loss": 4.5693, "step": 3540 }, { "epoch": 0.10815516188149053, "grad_norm": 0.4213823974132538, "learning_rate": 4.85707047293198e-05, "loss": 4.4411, "step": 3541 }, { "epoch": 0.1081857055589493, "grad_norm": 0.4000970423221588, "learning_rate": 4.856990511913142e-05, "loss": 4.4417, "step": 3542 }, { "epoch": 0.10821624923640806, "grad_norm": 0.3950268030166626, "learning_rate": 4.8569105291922806e-05, "loss": 4.3898, "step": 3543 }, { "epoch": 0.10824679291386682, "grad_norm": 0.4075872600078583, "learning_rate": 4.856830524770132e-05, "loss": 4.4536, "step": 3544 }, { "epoch": 0.1082773365913256, "grad_norm": 0.4032295346260071, "learning_rate": 4.856750498647433e-05, "loss": 4.419, "step": 3545 }, { "epoch": 0.10830788026878437, "grad_norm": 0.394184410572052, "learning_rate": 4.856670450824922e-05, "loss": 4.4274, "step": 3546 }, { "epoch": 0.10833842394624313, "grad_norm": 0.3931080996990204, "learning_rate": 4.856590381303332e-05, "loss": 4.3748, "step": 3547 }, { "epoch": 0.10836896762370189, "grad_norm": 0.4080425798892975, "learning_rate": 4.856510290083404e-05, "loss": 4.3776, "step": 3548 }, { "epoch": 0.10839951130116066, "grad_norm": 0.39924678206443787, "learning_rate": 4.8564301771658746e-05, "loss": 4.413, "step": 3549 }, { "epoch": 0.10843005497861942, "grad_norm": 0.390654593706131, "learning_rate": 4.8563500425514804e-05, "loss": 4.4685, "step": 3550 }, { "epoch": 0.1084605986560782, "grad_norm": 0.3928931653499603, "learning_rate": 4.856269886240959e-05, "loss": 4.3921, "step": 3551 }, { "epoch": 0.10849114233353696, "grad_norm": 0.3866654336452484, "learning_rate": 4.856189708235051e-05, "loss": 4.3766, "step": 3552 }, { "epoch": 0.10852168601099572, "grad_norm": 0.3902047574520111, "learning_rate": 4.8561095085344923e-05, "loss": 4.3964, "step": 3553 }, { "epoch": 0.10855222968845449, "grad_norm": 0.40199756622314453, "learning_rate": 4.8560292871400216e-05, "loss": 4.3846, "step": 3554 }, { "epoch": 0.10858277336591325, "grad_norm": 0.38719287514686584, "learning_rate": 4.855949044052378e-05, "loss": 4.4107, "step": 3555 }, { "epoch": 0.10861331704337202, "grad_norm": 0.40621164441108704, "learning_rate": 4.8558687792723e-05, "loss": 4.4341, "step": 3556 }, { "epoch": 0.10864386072083079, "grad_norm": 0.39932435750961304, "learning_rate": 4.855788492800527e-05, "loss": 4.4241, "step": 3557 }, { "epoch": 0.10867440439828956, "grad_norm": 0.40585389733314514, "learning_rate": 4.8557081846377985e-05, "loss": 4.4316, "step": 3558 }, { "epoch": 0.10870494807574832, "grad_norm": 0.39117297530174255, "learning_rate": 4.855627854784853e-05, "loss": 4.3493, "step": 3559 }, { "epoch": 0.10873549175320708, "grad_norm": 0.38724392652511597, "learning_rate": 4.855547503242431e-05, "loss": 4.3877, "step": 3560 }, { "epoch": 0.10876603543066585, "grad_norm": 0.41270312666893005, "learning_rate": 4.8554671300112716e-05, "loss": 4.4651, "step": 3561 }, { "epoch": 0.10879657910812462, "grad_norm": 0.39067596197128296, "learning_rate": 4.855386735092117e-05, "loss": 4.3066, "step": 3562 }, { "epoch": 0.10882712278558339, "grad_norm": 0.3965253531932831, "learning_rate": 4.855306318485704e-05, "loss": 4.3705, "step": 3563 }, { "epoch": 0.10885766646304215, "grad_norm": 0.3935110569000244, "learning_rate": 4.855225880192775e-05, "loss": 4.4572, "step": 3564 }, { "epoch": 0.10888821014050092, "grad_norm": 0.38893070816993713, "learning_rate": 4.8551454202140705e-05, "loss": 4.5169, "step": 3565 }, { "epoch": 0.10891875381795968, "grad_norm": 0.39879733324050903, "learning_rate": 4.855064938550332e-05, "loss": 4.474, "step": 3566 }, { "epoch": 0.10894929749541844, "grad_norm": 0.3901619017124176, "learning_rate": 4.854984435202299e-05, "loss": 4.4366, "step": 3567 }, { "epoch": 0.10897984117287722, "grad_norm": 0.40101855993270874, "learning_rate": 4.854903910170713e-05, "loss": 4.3756, "step": 3568 }, { "epoch": 0.10901038485033598, "grad_norm": 0.3924363851547241, "learning_rate": 4.854823363456317e-05, "loss": 4.3329, "step": 3569 }, { "epoch": 0.10904092852779475, "grad_norm": 0.402299702167511, "learning_rate": 4.854742795059851e-05, "loss": 4.3145, "step": 3570 }, { "epoch": 0.10907147220525351, "grad_norm": 0.3919810950756073, "learning_rate": 4.854662204982057e-05, "loss": 4.3605, "step": 3571 }, { "epoch": 0.10910201588271227, "grad_norm": 0.39019474387168884, "learning_rate": 4.8545815932236784e-05, "loss": 4.3713, "step": 3572 }, { "epoch": 0.10913255956017104, "grad_norm": 0.3958297669887543, "learning_rate": 4.854500959785455e-05, "loss": 4.4562, "step": 3573 }, { "epoch": 0.10916310323762982, "grad_norm": 0.3895338773727417, "learning_rate": 4.8544203046681324e-05, "loss": 4.4533, "step": 3574 }, { "epoch": 0.10919364691508858, "grad_norm": 0.3950974643230438, "learning_rate": 4.854339627872451e-05, "loss": 4.363, "step": 3575 }, { "epoch": 0.10922419059254734, "grad_norm": 0.4117966592311859, "learning_rate": 4.854258929399154e-05, "loss": 4.4362, "step": 3576 }, { "epoch": 0.1092547342700061, "grad_norm": 0.39198896288871765, "learning_rate": 4.854178209248984e-05, "loss": 4.4634, "step": 3577 }, { "epoch": 0.10928527794746487, "grad_norm": 0.40051254630088806, "learning_rate": 4.854097467422686e-05, "loss": 4.4289, "step": 3578 }, { "epoch": 0.10931582162492363, "grad_norm": 0.40241703391075134, "learning_rate": 4.854016703921001e-05, "loss": 4.4292, "step": 3579 }, { "epoch": 0.10934636530238241, "grad_norm": 0.39264169335365295, "learning_rate": 4.8539359187446744e-05, "loss": 4.4891, "step": 3580 }, { "epoch": 0.10937690897984118, "grad_norm": 0.40387579798698425, "learning_rate": 4.8538551118944496e-05, "loss": 4.4786, "step": 3581 }, { "epoch": 0.10940745265729994, "grad_norm": 0.41506603360176086, "learning_rate": 4.853774283371071e-05, "loss": 4.4653, "step": 3582 }, { "epoch": 0.1094379963347587, "grad_norm": 0.41041457653045654, "learning_rate": 4.853693433175281e-05, "loss": 4.4546, "step": 3583 }, { "epoch": 0.10946854001221747, "grad_norm": 0.40514159202575684, "learning_rate": 4.853612561307827e-05, "loss": 4.4169, "step": 3584 }, { "epoch": 0.10949908368967624, "grad_norm": 0.40639325976371765, "learning_rate": 4.853531667769451e-05, "loss": 4.458, "step": 3585 }, { "epoch": 0.10952962736713501, "grad_norm": 0.40514233708381653, "learning_rate": 4.8534507525608996e-05, "loss": 4.3612, "step": 3586 }, { "epoch": 0.10956017104459377, "grad_norm": 0.40499940514564514, "learning_rate": 4.853369815682917e-05, "loss": 4.381, "step": 3587 }, { "epoch": 0.10959071472205253, "grad_norm": 0.4051241874694824, "learning_rate": 4.853288857136248e-05, "loss": 4.3277, "step": 3588 }, { "epoch": 0.1096212583995113, "grad_norm": 0.4011959731578827, "learning_rate": 4.853207876921639e-05, "loss": 4.3849, "step": 3589 }, { "epoch": 0.10965180207697006, "grad_norm": 0.3870021402835846, "learning_rate": 4.853126875039835e-05, "loss": 4.419, "step": 3590 }, { "epoch": 0.10968234575442884, "grad_norm": 0.4069814682006836, "learning_rate": 4.853045851491582e-05, "loss": 4.4502, "step": 3591 }, { "epoch": 0.1097128894318876, "grad_norm": 0.4098028242588043, "learning_rate": 4.852964806277626e-05, "loss": 4.3689, "step": 3592 }, { "epoch": 0.10974343310934637, "grad_norm": 0.40051189064979553, "learning_rate": 4.852883739398714e-05, "loss": 4.3764, "step": 3593 }, { "epoch": 0.10977397678680513, "grad_norm": 0.4011390507221222, "learning_rate": 4.852802650855591e-05, "loss": 4.4471, "step": 3594 }, { "epoch": 0.1098045204642639, "grad_norm": 0.3851960599422455, "learning_rate": 4.852721540649004e-05, "loss": 4.4409, "step": 3595 }, { "epoch": 0.10983506414172266, "grad_norm": 0.3895151913166046, "learning_rate": 4.8526404087797006e-05, "loss": 4.4316, "step": 3596 }, { "epoch": 0.10986560781918144, "grad_norm": 0.39695605635643005, "learning_rate": 4.852559255248427e-05, "loss": 4.4288, "step": 3597 }, { "epoch": 0.1098961514966402, "grad_norm": 0.3933029770851135, "learning_rate": 4.852478080055931e-05, "loss": 4.3484, "step": 3598 }, { "epoch": 0.10992669517409896, "grad_norm": 0.40665823221206665, "learning_rate": 4.85239688320296e-05, "loss": 4.3928, "step": 3599 }, { "epoch": 0.10995723885155773, "grad_norm": 0.399136483669281, "learning_rate": 4.8523156646902605e-05, "loss": 4.3878, "step": 3600 }, { "epoch": 0.10998778252901649, "grad_norm": 0.39820560812950134, "learning_rate": 4.8522344245185825e-05, "loss": 4.4293, "step": 3601 }, { "epoch": 0.11001832620647525, "grad_norm": 0.40195342898368835, "learning_rate": 4.852153162688672e-05, "loss": 4.4723, "step": 3602 }, { "epoch": 0.11004886988393403, "grad_norm": 0.39062899351119995, "learning_rate": 4.852071879201278e-05, "loss": 4.4279, "step": 3603 }, { "epoch": 0.1100794135613928, "grad_norm": 0.40568968653678894, "learning_rate": 4.8519905740571493e-05, "loss": 4.4117, "step": 3604 }, { "epoch": 0.11010995723885156, "grad_norm": 0.39593398571014404, "learning_rate": 4.851909247257034e-05, "loss": 4.4079, "step": 3605 }, { "epoch": 0.11014050091631032, "grad_norm": 0.4356672465801239, "learning_rate": 4.85182789880168e-05, "loss": 4.4405, "step": 3606 }, { "epoch": 0.11017104459376909, "grad_norm": 0.38059180974960327, "learning_rate": 4.8517465286918386e-05, "loss": 4.4423, "step": 3607 }, { "epoch": 0.11020158827122786, "grad_norm": 0.3925783038139343, "learning_rate": 4.8516651369282575e-05, "loss": 4.4348, "step": 3608 }, { "epoch": 0.11023213194868663, "grad_norm": 0.3863900601863861, "learning_rate": 4.851583723511686e-05, "loss": 4.472, "step": 3609 }, { "epoch": 0.11026267562614539, "grad_norm": 0.38363295793533325, "learning_rate": 4.851502288442874e-05, "loss": 4.3267, "step": 3610 }, { "epoch": 0.11029321930360415, "grad_norm": 0.40107330679893494, "learning_rate": 4.8514208317225717e-05, "loss": 4.4257, "step": 3611 }, { "epoch": 0.11032376298106292, "grad_norm": 0.40671977400779724, "learning_rate": 4.851339353351529e-05, "loss": 4.3769, "step": 3612 }, { "epoch": 0.11035430665852168, "grad_norm": 0.39326149225234985, "learning_rate": 4.851257853330496e-05, "loss": 4.3715, "step": 3613 }, { "epoch": 0.11038485033598046, "grad_norm": 0.3982362747192383, "learning_rate": 4.8511763316602224e-05, "loss": 4.4116, "step": 3614 }, { "epoch": 0.11041539401343922, "grad_norm": 0.3870921730995178, "learning_rate": 4.85109478834146e-05, "loss": 4.4417, "step": 3615 }, { "epoch": 0.11044593769089799, "grad_norm": 0.38566920161247253, "learning_rate": 4.851013223374959e-05, "loss": 4.4364, "step": 3616 }, { "epoch": 0.11047648136835675, "grad_norm": 0.3921654522418976, "learning_rate": 4.850931636761471e-05, "loss": 4.3936, "step": 3617 }, { "epoch": 0.11050702504581551, "grad_norm": 0.4086211323738098, "learning_rate": 4.850850028501746e-05, "loss": 4.409, "step": 3618 }, { "epoch": 0.11053756872327428, "grad_norm": 0.38649821281433105, "learning_rate": 4.8507683985965355e-05, "loss": 4.3281, "step": 3619 }, { "epoch": 0.11056811240073305, "grad_norm": 0.37248241901397705, "learning_rate": 4.8506867470465936e-05, "loss": 4.3623, "step": 3620 }, { "epoch": 0.11059865607819182, "grad_norm": 0.3949643671512604, "learning_rate": 4.850605073852669e-05, "loss": 4.4384, "step": 3621 }, { "epoch": 0.11062919975565058, "grad_norm": 0.39274802803993225, "learning_rate": 4.850523379015515e-05, "loss": 4.4744, "step": 3622 }, { "epoch": 0.11065974343310934, "grad_norm": 0.38036373257637024, "learning_rate": 4.8504416625358834e-05, "loss": 4.3214, "step": 3623 }, { "epoch": 0.11069028711056811, "grad_norm": 0.39162877202033997, "learning_rate": 4.850359924414527e-05, "loss": 4.4046, "step": 3624 }, { "epoch": 0.11072083078802687, "grad_norm": 0.4004744589328766, "learning_rate": 4.850278164652199e-05, "loss": 4.4638, "step": 3625 }, { "epoch": 0.11075137446548565, "grad_norm": 0.3942982256412506, "learning_rate": 4.850196383249651e-05, "loss": 4.4181, "step": 3626 }, { "epoch": 0.11078191814294441, "grad_norm": 0.4020996689796448, "learning_rate": 4.850114580207637e-05, "loss": 4.4685, "step": 3627 }, { "epoch": 0.11081246182040318, "grad_norm": 0.39652326703071594, "learning_rate": 4.850032755526909e-05, "loss": 4.4098, "step": 3628 }, { "epoch": 0.11084300549786194, "grad_norm": 0.39604270458221436, "learning_rate": 4.8499509092082215e-05, "loss": 4.3977, "step": 3629 }, { "epoch": 0.1108735491753207, "grad_norm": 0.40343809127807617, "learning_rate": 4.8498690412523277e-05, "loss": 4.359, "step": 3630 }, { "epoch": 0.11090409285277947, "grad_norm": 0.4130164682865143, "learning_rate": 4.849787151659982e-05, "loss": 4.3679, "step": 3631 }, { "epoch": 0.11093463653023825, "grad_norm": 0.40037772059440613, "learning_rate": 4.8497052404319375e-05, "loss": 4.431, "step": 3632 }, { "epoch": 0.11096518020769701, "grad_norm": 0.38938015699386597, "learning_rate": 4.8496233075689484e-05, "loss": 4.47, "step": 3633 }, { "epoch": 0.11099572388515577, "grad_norm": 0.3862147331237793, "learning_rate": 4.84954135307177e-05, "loss": 4.4227, "step": 3634 }, { "epoch": 0.11102626756261454, "grad_norm": 0.40695303678512573, "learning_rate": 4.8494593769411555e-05, "loss": 4.4583, "step": 3635 }, { "epoch": 0.1110568112400733, "grad_norm": 0.38319623470306396, "learning_rate": 4.8493773791778616e-05, "loss": 4.3387, "step": 3636 }, { "epoch": 0.11108735491753208, "grad_norm": 0.4086441099643707, "learning_rate": 4.849295359782642e-05, "loss": 4.4326, "step": 3637 }, { "epoch": 0.11111789859499084, "grad_norm": 0.39173102378845215, "learning_rate": 4.849213318756252e-05, "loss": 4.366, "step": 3638 }, { "epoch": 0.1111484422724496, "grad_norm": 0.38957464694976807, "learning_rate": 4.849131256099447e-05, "loss": 4.4023, "step": 3639 }, { "epoch": 0.11117898594990837, "grad_norm": 0.39337679743766785, "learning_rate": 4.849049171812983e-05, "loss": 4.4436, "step": 3640 }, { "epoch": 0.11120952962736713, "grad_norm": 0.40827810764312744, "learning_rate": 4.848967065897615e-05, "loss": 4.4298, "step": 3641 }, { "epoch": 0.1112400733048259, "grad_norm": 0.3949773609638214, "learning_rate": 4.8488849383540994e-05, "loss": 4.3998, "step": 3642 }, { "epoch": 0.11127061698228467, "grad_norm": 0.38360899686813354, "learning_rate": 4.848802789183193e-05, "loss": 4.429, "step": 3643 }, { "epoch": 0.11130116065974344, "grad_norm": 0.4101516306400299, "learning_rate": 4.848720618385651e-05, "loss": 4.4339, "step": 3644 }, { "epoch": 0.1113317043372022, "grad_norm": 0.39398741722106934, "learning_rate": 4.848638425962232e-05, "loss": 4.3998, "step": 3645 }, { "epoch": 0.11136224801466096, "grad_norm": 0.41404929757118225, "learning_rate": 4.848556211913691e-05, "loss": 4.422, "step": 3646 }, { "epoch": 0.11139279169211973, "grad_norm": 0.39807024598121643, "learning_rate": 4.848473976240785e-05, "loss": 4.4275, "step": 3647 }, { "epoch": 0.11142333536957849, "grad_norm": 0.39852175116539, "learning_rate": 4.848391718944272e-05, "loss": 4.3184, "step": 3648 }, { "epoch": 0.11145387904703727, "grad_norm": 0.3964295983314514, "learning_rate": 4.848309440024908e-05, "loss": 4.3772, "step": 3649 }, { "epoch": 0.11148442272449603, "grad_norm": 0.38974666595458984, "learning_rate": 4.8482271394834524e-05, "loss": 4.4238, "step": 3650 }, { "epoch": 0.1115149664019548, "grad_norm": 0.38932013511657715, "learning_rate": 4.848144817320662e-05, "loss": 4.4973, "step": 3651 }, { "epoch": 0.11154551007941356, "grad_norm": 0.4063071608543396, "learning_rate": 4.848062473537296e-05, "loss": 4.4248, "step": 3652 }, { "epoch": 0.11157605375687232, "grad_norm": 0.38933300971984863, "learning_rate": 4.84798010813411e-05, "loss": 4.3285, "step": 3653 }, { "epoch": 0.11160659743433109, "grad_norm": 0.3974185883998871, "learning_rate": 4.847897721111865e-05, "loss": 4.41, "step": 3654 }, { "epoch": 0.11163714111178986, "grad_norm": 0.39590680599212646, "learning_rate": 4.8478153124713185e-05, "loss": 4.4554, "step": 3655 }, { "epoch": 0.11166768478924863, "grad_norm": 0.39521557092666626, "learning_rate": 4.847732882213229e-05, "loss": 4.2936, "step": 3656 }, { "epoch": 0.11169822846670739, "grad_norm": 0.3996489346027374, "learning_rate": 4.847650430338355e-05, "loss": 4.4625, "step": 3657 }, { "epoch": 0.11172877214416616, "grad_norm": 0.4065234065055847, "learning_rate": 4.847567956847457e-05, "loss": 4.2515, "step": 3658 }, { "epoch": 0.11175931582162492, "grad_norm": 0.3890705108642578, "learning_rate": 4.847485461741295e-05, "loss": 4.3942, "step": 3659 }, { "epoch": 0.1117898594990837, "grad_norm": 0.3909320533275604, "learning_rate": 4.847402945020626e-05, "loss": 4.3085, "step": 3660 }, { "epoch": 0.11182040317654246, "grad_norm": 0.39009377360343933, "learning_rate": 4.847320406686212e-05, "loss": 4.4281, "step": 3661 }, { "epoch": 0.11185094685400122, "grad_norm": 0.3847140073776245, "learning_rate": 4.847237846738811e-05, "loss": 4.3625, "step": 3662 }, { "epoch": 0.11188149053145999, "grad_norm": 0.40279579162597656, "learning_rate": 4.8471552651791854e-05, "loss": 4.3734, "step": 3663 }, { "epoch": 0.11191203420891875, "grad_norm": 0.3761403560638428, "learning_rate": 4.847072662008094e-05, "loss": 4.4441, "step": 3664 }, { "epoch": 0.11194257788637751, "grad_norm": 0.3822491765022278, "learning_rate": 4.846990037226298e-05, "loss": 4.5011, "step": 3665 }, { "epoch": 0.11197312156383629, "grad_norm": 0.39848756790161133, "learning_rate": 4.846907390834558e-05, "loss": 4.4126, "step": 3666 }, { "epoch": 0.11200366524129506, "grad_norm": 0.39610961079597473, "learning_rate": 4.846824722833635e-05, "loss": 4.3827, "step": 3667 }, { "epoch": 0.11203420891875382, "grad_norm": 0.386778324842453, "learning_rate": 4.8467420332242904e-05, "loss": 4.2813, "step": 3668 }, { "epoch": 0.11206475259621258, "grad_norm": 0.3922331929206848, "learning_rate": 4.846659322007285e-05, "loss": 4.4258, "step": 3669 }, { "epoch": 0.11209529627367135, "grad_norm": 0.4176851809024811, "learning_rate": 4.8465765891833804e-05, "loss": 4.4396, "step": 3670 }, { "epoch": 0.11212583995113011, "grad_norm": 0.39263007044792175, "learning_rate": 4.84649383475334e-05, "loss": 4.3545, "step": 3671 }, { "epoch": 0.11215638362858889, "grad_norm": 0.3892439305782318, "learning_rate": 4.846411058717922e-05, "loss": 4.4728, "step": 3672 }, { "epoch": 0.11218692730604765, "grad_norm": 0.4083977937698364, "learning_rate": 4.846328261077893e-05, "loss": 4.4744, "step": 3673 }, { "epoch": 0.11221747098350641, "grad_norm": 0.3972109258174896, "learning_rate": 4.846245441834013e-05, "loss": 4.4241, "step": 3674 }, { "epoch": 0.11224801466096518, "grad_norm": 0.44679486751556396, "learning_rate": 4.846162600987044e-05, "loss": 4.4391, "step": 3675 }, { "epoch": 0.11227855833842394, "grad_norm": 0.40122440457344055, "learning_rate": 4.846079738537751e-05, "loss": 4.3901, "step": 3676 }, { "epoch": 0.1123091020158827, "grad_norm": 0.45748624205589294, "learning_rate": 4.845996854486895e-05, "loss": 4.4402, "step": 3677 }, { "epoch": 0.11233964569334148, "grad_norm": 0.39031341671943665, "learning_rate": 4.845913948835239e-05, "loss": 4.4471, "step": 3678 }, { "epoch": 0.11237018937080025, "grad_norm": 0.39494484663009644, "learning_rate": 4.845831021583548e-05, "loss": 4.4131, "step": 3679 }, { "epoch": 0.11240073304825901, "grad_norm": 0.3980567157268524, "learning_rate": 4.845748072732585e-05, "loss": 4.3779, "step": 3680 }, { "epoch": 0.11243127672571777, "grad_norm": 0.3970853388309479, "learning_rate": 4.845665102283112e-05, "loss": 4.3983, "step": 3681 }, { "epoch": 0.11246182040317654, "grad_norm": 0.4035974144935608, "learning_rate": 4.845582110235895e-05, "loss": 4.4904, "step": 3682 }, { "epoch": 0.11249236408063532, "grad_norm": 0.38288575410842896, "learning_rate": 4.8454990965916985e-05, "loss": 4.445, "step": 3683 }, { "epoch": 0.11252290775809408, "grad_norm": 0.38155901432037354, "learning_rate": 4.8454160613512853e-05, "loss": 4.4194, "step": 3684 }, { "epoch": 0.11255345143555284, "grad_norm": 0.3824337422847748, "learning_rate": 4.84533300451542e-05, "loss": 4.4016, "step": 3685 }, { "epoch": 0.1125839951130116, "grad_norm": 0.39109382033348083, "learning_rate": 4.845249926084868e-05, "loss": 4.404, "step": 3686 }, { "epoch": 0.11261453879047037, "grad_norm": 0.3954412639141083, "learning_rate": 4.845166826060395e-05, "loss": 4.3863, "step": 3687 }, { "epoch": 0.11264508246792913, "grad_norm": 0.4000152349472046, "learning_rate": 4.8450837044427645e-05, "loss": 4.4496, "step": 3688 }, { "epoch": 0.11267562614538791, "grad_norm": 0.4000042676925659, "learning_rate": 4.8450005612327435e-05, "loss": 4.4461, "step": 3689 }, { "epoch": 0.11270616982284667, "grad_norm": 0.3903994858264923, "learning_rate": 4.844917396431096e-05, "loss": 4.387, "step": 3690 }, { "epoch": 0.11273671350030544, "grad_norm": 0.4058490991592407, "learning_rate": 4.844834210038588e-05, "loss": 4.455, "step": 3691 }, { "epoch": 0.1127672571777642, "grad_norm": 0.3937252163887024, "learning_rate": 4.844751002055986e-05, "loss": 4.3999, "step": 3692 }, { "epoch": 0.11279780085522297, "grad_norm": 0.3826594948768616, "learning_rate": 4.844667772484056e-05, "loss": 4.4461, "step": 3693 }, { "epoch": 0.11282834453268173, "grad_norm": 0.3950396180152893, "learning_rate": 4.8445845213235645e-05, "loss": 4.374, "step": 3694 }, { "epoch": 0.1128588882101405, "grad_norm": 0.4002324938774109, "learning_rate": 4.844501248575278e-05, "loss": 4.4311, "step": 3695 }, { "epoch": 0.11288943188759927, "grad_norm": 0.38833197951316833, "learning_rate": 4.844417954239962e-05, "loss": 4.4203, "step": 3696 }, { "epoch": 0.11291997556505803, "grad_norm": 0.3977566361427307, "learning_rate": 4.8443346383183865e-05, "loss": 4.432, "step": 3697 }, { "epoch": 0.1129505192425168, "grad_norm": 0.38412967324256897, "learning_rate": 4.844251300811316e-05, "loss": 4.4635, "step": 3698 }, { "epoch": 0.11298106291997556, "grad_norm": 0.3875446617603302, "learning_rate": 4.844167941719517e-05, "loss": 4.4735, "step": 3699 }, { "epoch": 0.11301160659743432, "grad_norm": 0.4150639474391937, "learning_rate": 4.84408456104376e-05, "loss": 4.3892, "step": 3700 }, { "epoch": 0.1130421502748931, "grad_norm": 0.39047569036483765, "learning_rate": 4.844001158784811e-05, "loss": 4.4277, "step": 3701 }, { "epoch": 0.11307269395235187, "grad_norm": 0.3835880160331726, "learning_rate": 4.8439177349434375e-05, "loss": 4.4165, "step": 3702 }, { "epoch": 0.11310323762981063, "grad_norm": 0.398176372051239, "learning_rate": 4.843834289520409e-05, "loss": 4.385, "step": 3703 }, { "epoch": 0.1131337813072694, "grad_norm": 0.394965261220932, "learning_rate": 4.843750822516493e-05, "loss": 4.4091, "step": 3704 }, { "epoch": 0.11316432498472816, "grad_norm": 0.40011921525001526, "learning_rate": 4.843667333932458e-05, "loss": 4.4193, "step": 3705 }, { "epoch": 0.11319486866218692, "grad_norm": 0.410347044467926, "learning_rate": 4.8435838237690725e-05, "loss": 4.4742, "step": 3706 }, { "epoch": 0.1132254123396457, "grad_norm": 0.39400386810302734, "learning_rate": 4.843500292027106e-05, "loss": 4.3677, "step": 3707 }, { "epoch": 0.11325595601710446, "grad_norm": 0.3874931037425995, "learning_rate": 4.843416738707328e-05, "loss": 4.4979, "step": 3708 }, { "epoch": 0.11328649969456323, "grad_norm": 0.4038889706134796, "learning_rate": 4.843333163810506e-05, "loss": 4.4607, "step": 3709 }, { "epoch": 0.11331704337202199, "grad_norm": 0.3799731433391571, "learning_rate": 4.8432495673374124e-05, "loss": 4.3817, "step": 3710 }, { "epoch": 0.11334758704948075, "grad_norm": 0.3903711140155792, "learning_rate": 4.843165949288814e-05, "loss": 4.3902, "step": 3711 }, { "epoch": 0.11337813072693953, "grad_norm": 0.39655956625938416, "learning_rate": 4.843082309665482e-05, "loss": 4.4022, "step": 3712 }, { "epoch": 0.1134086744043983, "grad_norm": 0.38312920928001404, "learning_rate": 4.842998648468187e-05, "loss": 4.3987, "step": 3713 }, { "epoch": 0.11343921808185706, "grad_norm": 0.40434879064559937, "learning_rate": 4.842914965697699e-05, "loss": 4.4351, "step": 3714 }, { "epoch": 0.11346976175931582, "grad_norm": 0.39675480127334595, "learning_rate": 4.842831261354788e-05, "loss": 4.5058, "step": 3715 }, { "epoch": 0.11350030543677458, "grad_norm": 0.3981572389602661, "learning_rate": 4.8427475354402246e-05, "loss": 4.4176, "step": 3716 }, { "epoch": 0.11353084911423335, "grad_norm": 0.3900893032550812, "learning_rate": 4.84266378795478e-05, "loss": 4.4531, "step": 3717 }, { "epoch": 0.11356139279169213, "grad_norm": 0.3976571261882782, "learning_rate": 4.842580018899227e-05, "loss": 4.4215, "step": 3718 }, { "epoch": 0.11359193646915089, "grad_norm": 0.41575896739959717, "learning_rate": 4.842496228274334e-05, "loss": 4.5146, "step": 3719 }, { "epoch": 0.11362248014660965, "grad_norm": 0.40062475204467773, "learning_rate": 4.842412416080874e-05, "loss": 4.4414, "step": 3720 }, { "epoch": 0.11365302382406842, "grad_norm": 0.39163658022880554, "learning_rate": 4.842328582319618e-05, "loss": 4.4318, "step": 3721 }, { "epoch": 0.11368356750152718, "grad_norm": 0.38861823081970215, "learning_rate": 4.842244726991339e-05, "loss": 4.4007, "step": 3722 }, { "epoch": 0.11371411117898594, "grad_norm": 0.4152379035949707, "learning_rate": 4.842160850096809e-05, "loss": 4.4577, "step": 3723 }, { "epoch": 0.11374465485644472, "grad_norm": 0.39500147104263306, "learning_rate": 4.842076951636799e-05, "loss": 4.352, "step": 3724 }, { "epoch": 0.11377519853390348, "grad_norm": 0.3927060067653656, "learning_rate": 4.841993031612082e-05, "loss": 4.4176, "step": 3725 }, { "epoch": 0.11380574221136225, "grad_norm": 0.40744808316230774, "learning_rate": 4.841909090023432e-05, "loss": 4.4192, "step": 3726 }, { "epoch": 0.11383628588882101, "grad_norm": 0.39586079120635986, "learning_rate": 4.841825126871621e-05, "loss": 4.4856, "step": 3727 }, { "epoch": 0.11386682956627978, "grad_norm": 0.3965229094028473, "learning_rate": 4.841741142157422e-05, "loss": 4.5042, "step": 3728 }, { "epoch": 0.11389737324373854, "grad_norm": 0.3920157253742218, "learning_rate": 4.841657135881608e-05, "loss": 4.2258, "step": 3729 }, { "epoch": 0.11392791692119732, "grad_norm": 0.4028887450695038, "learning_rate": 4.8415731080449525e-05, "loss": 4.3917, "step": 3730 }, { "epoch": 0.11395846059865608, "grad_norm": 0.39592838287353516, "learning_rate": 4.8414890586482295e-05, "loss": 4.3419, "step": 3731 }, { "epoch": 0.11398900427611484, "grad_norm": 0.3805276155471802, "learning_rate": 4.841404987692213e-05, "loss": 4.3397, "step": 3732 }, { "epoch": 0.11401954795357361, "grad_norm": 0.3873235881328583, "learning_rate": 4.8413208951776765e-05, "loss": 4.4577, "step": 3733 }, { "epoch": 0.11405009163103237, "grad_norm": 0.3797157108783722, "learning_rate": 4.841236781105396e-05, "loss": 4.4163, "step": 3734 }, { "epoch": 0.11408063530849115, "grad_norm": 0.3892649710178375, "learning_rate": 4.841152645476144e-05, "loss": 4.4584, "step": 3735 }, { "epoch": 0.11411117898594991, "grad_norm": 0.407901406288147, "learning_rate": 4.841068488290695e-05, "loss": 4.3951, "step": 3736 }, { "epoch": 0.11414172266340868, "grad_norm": 0.3997655212879181, "learning_rate": 4.8409843095498265e-05, "loss": 4.4082, "step": 3737 }, { "epoch": 0.11417226634086744, "grad_norm": 0.399803102016449, "learning_rate": 4.8409001092543106e-05, "loss": 4.4466, "step": 3738 }, { "epoch": 0.1142028100183262, "grad_norm": 0.40043532848358154, "learning_rate": 4.840815887404924e-05, "loss": 4.4179, "step": 3739 }, { "epoch": 0.11423335369578497, "grad_norm": 0.387754887342453, "learning_rate": 4.8407316440024424e-05, "loss": 4.5066, "step": 3740 }, { "epoch": 0.11426389737324374, "grad_norm": 0.3880404531955719, "learning_rate": 4.8406473790476406e-05, "loss": 4.3631, "step": 3741 }, { "epoch": 0.11429444105070251, "grad_norm": 0.39266902208328247, "learning_rate": 4.8405630925412956e-05, "loss": 4.3453, "step": 3742 }, { "epoch": 0.11432498472816127, "grad_norm": 0.4107303321361542, "learning_rate": 4.840478784484183e-05, "loss": 4.3533, "step": 3743 }, { "epoch": 0.11435552840562004, "grad_norm": 0.3989696800708771, "learning_rate": 4.840394454877077e-05, "loss": 4.4275, "step": 3744 }, { "epoch": 0.1143860720830788, "grad_norm": 0.3906075656414032, "learning_rate": 4.8403101037207576e-05, "loss": 4.5228, "step": 3745 }, { "epoch": 0.11441661576053756, "grad_norm": 0.3900071978569031, "learning_rate": 4.840225731016e-05, "loss": 4.3964, "step": 3746 }, { "epoch": 0.11444715943799634, "grad_norm": 0.39820703864097595, "learning_rate": 4.84014133676358e-05, "loss": 4.4155, "step": 3747 }, { "epoch": 0.1144777031154551, "grad_norm": 0.39850783348083496, "learning_rate": 4.8400569209642756e-05, "loss": 4.4313, "step": 3748 }, { "epoch": 0.11450824679291387, "grad_norm": 0.39118465781211853, "learning_rate": 4.8399724836188644e-05, "loss": 4.401, "step": 3749 }, { "epoch": 0.11453879047037263, "grad_norm": 0.39858558773994446, "learning_rate": 4.8398880247281234e-05, "loss": 4.387, "step": 3750 }, { "epoch": 0.1145693341478314, "grad_norm": 0.4041728973388672, "learning_rate": 4.83980354429283e-05, "loss": 4.4457, "step": 3751 }, { "epoch": 0.11459987782529016, "grad_norm": 0.3860584497451782, "learning_rate": 4.839719042313763e-05, "loss": 4.3966, "step": 3752 }, { "epoch": 0.11463042150274894, "grad_norm": 0.38509222865104675, "learning_rate": 4.839634518791699e-05, "loss": 4.389, "step": 3753 }, { "epoch": 0.1146609651802077, "grad_norm": 0.39534953236579895, "learning_rate": 4.839549973727417e-05, "loss": 4.3701, "step": 3754 }, { "epoch": 0.11469150885766646, "grad_norm": 0.3882072865962982, "learning_rate": 4.839465407121696e-05, "loss": 4.3944, "step": 3755 }, { "epoch": 0.11472205253512523, "grad_norm": 0.3929956555366516, "learning_rate": 4.839380818975314e-05, "loss": 4.4218, "step": 3756 }, { "epoch": 0.11475259621258399, "grad_norm": 0.39046236872673035, "learning_rate": 4.8392962092890503e-05, "loss": 4.4123, "step": 3757 }, { "epoch": 0.11478313989004277, "grad_norm": 0.3993533253669739, "learning_rate": 4.8392115780636835e-05, "loss": 4.4142, "step": 3758 }, { "epoch": 0.11481368356750153, "grad_norm": 0.38876524567604065, "learning_rate": 4.839126925299993e-05, "loss": 4.4351, "step": 3759 }, { "epoch": 0.1148442272449603, "grad_norm": 0.39121848344802856, "learning_rate": 4.8390422509987584e-05, "loss": 4.2833, "step": 3760 }, { "epoch": 0.11487477092241906, "grad_norm": 0.39967161417007446, "learning_rate": 4.838957555160759e-05, "loss": 4.3838, "step": 3761 }, { "epoch": 0.11490531459987782, "grad_norm": 0.40847405791282654, "learning_rate": 4.838872837786775e-05, "loss": 4.489, "step": 3762 }, { "epoch": 0.11493585827733659, "grad_norm": 0.3815258741378784, "learning_rate": 4.838788098877586e-05, "loss": 4.3775, "step": 3763 }, { "epoch": 0.11496640195479536, "grad_norm": 0.40015992522239685, "learning_rate": 4.838703338433972e-05, "loss": 4.5083, "step": 3764 }, { "epoch": 0.11499694563225413, "grad_norm": 0.39309942722320557, "learning_rate": 4.8386185564567144e-05, "loss": 4.3954, "step": 3765 }, { "epoch": 0.11502748930971289, "grad_norm": 0.3869042694568634, "learning_rate": 4.838533752946594e-05, "loss": 4.3937, "step": 3766 }, { "epoch": 0.11505803298717165, "grad_norm": 0.40129005908966064, "learning_rate": 4.83844892790439e-05, "loss": 4.321, "step": 3767 }, { "epoch": 0.11508857666463042, "grad_norm": 0.3948879837989807, "learning_rate": 4.838364081330885e-05, "loss": 4.4363, "step": 3768 }, { "epoch": 0.11511912034208918, "grad_norm": 0.39736583828926086, "learning_rate": 4.83827921322686e-05, "loss": 4.4573, "step": 3769 }, { "epoch": 0.11514966401954796, "grad_norm": 0.39194467663764954, "learning_rate": 4.838194323593095e-05, "loss": 4.3495, "step": 3770 }, { "epoch": 0.11518020769700672, "grad_norm": 0.4177926480770111, "learning_rate": 4.8381094124303725e-05, "loss": 4.4383, "step": 3771 }, { "epoch": 0.11521075137446549, "grad_norm": 0.38692042231559753, "learning_rate": 4.838024479739476e-05, "loss": 4.4061, "step": 3772 }, { "epoch": 0.11524129505192425, "grad_norm": 0.3924277424812317, "learning_rate": 4.8379395255211846e-05, "loss": 4.3751, "step": 3773 }, { "epoch": 0.11527183872938301, "grad_norm": 0.3990093171596527, "learning_rate": 4.837854549776283e-05, "loss": 4.4111, "step": 3774 }, { "epoch": 0.11530238240684178, "grad_norm": 0.3813508152961731, "learning_rate": 4.837769552505552e-05, "loss": 4.3131, "step": 3775 }, { "epoch": 0.11533292608430055, "grad_norm": 0.3976842164993286, "learning_rate": 4.8376845337097745e-05, "loss": 4.4421, "step": 3776 }, { "epoch": 0.11536346976175932, "grad_norm": 0.39685842394828796, "learning_rate": 4.837599493389734e-05, "loss": 4.3963, "step": 3777 }, { "epoch": 0.11539401343921808, "grad_norm": 0.40311774611473083, "learning_rate": 4.837514431546213e-05, "loss": 4.446, "step": 3778 }, { "epoch": 0.11542455711667685, "grad_norm": 0.38574346899986267, "learning_rate": 4.8374293481799946e-05, "loss": 4.4611, "step": 3779 }, { "epoch": 0.11545510079413561, "grad_norm": 0.402269572019577, "learning_rate": 4.837344243291863e-05, "loss": 4.3392, "step": 3780 }, { "epoch": 0.11548564447159437, "grad_norm": 0.3981761038303375, "learning_rate": 4.8372591168826006e-05, "loss": 4.4554, "step": 3781 }, { "epoch": 0.11551618814905315, "grad_norm": 0.39807310700416565, "learning_rate": 4.837173968952992e-05, "loss": 4.4611, "step": 3782 }, { "epoch": 0.11554673182651191, "grad_norm": 0.38890859484672546, "learning_rate": 4.837088799503822e-05, "loss": 4.3281, "step": 3783 }, { "epoch": 0.11557727550397068, "grad_norm": 0.39184263348579407, "learning_rate": 4.837003608535872e-05, "loss": 4.3614, "step": 3784 }, { "epoch": 0.11560781918142944, "grad_norm": 0.3937892019748688, "learning_rate": 4.836918396049929e-05, "loss": 4.3192, "step": 3785 }, { "epoch": 0.1156383628588882, "grad_norm": 0.4150174856185913, "learning_rate": 4.836833162046777e-05, "loss": 4.4594, "step": 3786 }, { "epoch": 0.11566890653634698, "grad_norm": 0.37612292170524597, "learning_rate": 4.8367479065272e-05, "loss": 4.4193, "step": 3787 }, { "epoch": 0.11569945021380575, "grad_norm": 0.3873891234397888, "learning_rate": 4.836662629491985e-05, "loss": 4.3534, "step": 3788 }, { "epoch": 0.11572999389126451, "grad_norm": 0.40625128149986267, "learning_rate": 4.8365773309419147e-05, "loss": 4.4574, "step": 3789 }, { "epoch": 0.11576053756872327, "grad_norm": 0.3991027772426605, "learning_rate": 4.8364920108777756e-05, "loss": 4.4855, "step": 3790 }, { "epoch": 0.11579108124618204, "grad_norm": 0.39984115958213806, "learning_rate": 4.836406669300353e-05, "loss": 4.4205, "step": 3791 }, { "epoch": 0.1158216249236408, "grad_norm": 0.3925839364528656, "learning_rate": 4.8363213062104334e-05, "loss": 4.4224, "step": 3792 }, { "epoch": 0.11585216860109958, "grad_norm": 0.40090832114219666, "learning_rate": 4.836235921608803e-05, "loss": 4.4513, "step": 3793 }, { "epoch": 0.11588271227855834, "grad_norm": 0.39367321133613586, "learning_rate": 4.836150515496246e-05, "loss": 4.45, "step": 3794 }, { "epoch": 0.1159132559560171, "grad_norm": 0.3861657381057739, "learning_rate": 4.83606508787355e-05, "loss": 4.3811, "step": 3795 }, { "epoch": 0.11594379963347587, "grad_norm": 0.4114375710487366, "learning_rate": 4.835979638741502e-05, "loss": 4.4514, "step": 3796 }, { "epoch": 0.11597434331093463, "grad_norm": 0.39305025339126587, "learning_rate": 4.835894168100889e-05, "loss": 4.3316, "step": 3797 }, { "epoch": 0.1160048869883934, "grad_norm": 0.40298953652381897, "learning_rate": 4.835808675952497e-05, "loss": 4.3129, "step": 3798 }, { "epoch": 0.11603543066585217, "grad_norm": 0.3879895508289337, "learning_rate": 4.835723162297114e-05, "loss": 4.4449, "step": 3799 }, { "epoch": 0.11606597434331094, "grad_norm": 0.3944065272808075, "learning_rate": 4.835637627135526e-05, "loss": 4.3655, "step": 3800 }, { "epoch": 0.1160965180207697, "grad_norm": 0.38658407330513, "learning_rate": 4.835552070468523e-05, "loss": 4.4573, "step": 3801 }, { "epoch": 0.11612706169822846, "grad_norm": 0.3944157361984253, "learning_rate": 4.8354664922968897e-05, "loss": 4.4029, "step": 3802 }, { "epoch": 0.11615760537568723, "grad_norm": 0.38809141516685486, "learning_rate": 4.835380892621416e-05, "loss": 4.4025, "step": 3803 }, { "epoch": 0.11618814905314599, "grad_norm": 0.388788640499115, "learning_rate": 4.83529527144289e-05, "loss": 4.4961, "step": 3804 }, { "epoch": 0.11621869273060477, "grad_norm": 0.3859092891216278, "learning_rate": 4.8352096287621004e-05, "loss": 4.4172, "step": 3805 }, { "epoch": 0.11624923640806353, "grad_norm": 0.3906055688858032, "learning_rate": 4.835123964579834e-05, "loss": 4.4024, "step": 3806 }, { "epoch": 0.1162797800855223, "grad_norm": 0.4035678803920746, "learning_rate": 4.8350382788968806e-05, "loss": 4.3803, "step": 3807 }, { "epoch": 0.11631032376298106, "grad_norm": 0.4033508598804474, "learning_rate": 4.83495257171403e-05, "loss": 4.4627, "step": 3808 }, { "epoch": 0.11634086744043982, "grad_norm": 0.3990328907966614, "learning_rate": 4.83486684303207e-05, "loss": 4.3391, "step": 3809 }, { "epoch": 0.1163714111178986, "grad_norm": 0.3956555128097534, "learning_rate": 4.834781092851791e-05, "loss": 4.3568, "step": 3810 }, { "epoch": 0.11640195479535737, "grad_norm": 0.4048220217227936, "learning_rate": 4.834695321173982e-05, "loss": 4.4576, "step": 3811 }, { "epoch": 0.11643249847281613, "grad_norm": 0.4087863862514496, "learning_rate": 4.8346095279994324e-05, "loss": 4.4976, "step": 3812 }, { "epoch": 0.11646304215027489, "grad_norm": 0.3983544707298279, "learning_rate": 4.834523713328932e-05, "loss": 4.4621, "step": 3813 }, { "epoch": 0.11649358582773366, "grad_norm": 0.39992329478263855, "learning_rate": 4.834437877163273e-05, "loss": 4.4027, "step": 3814 }, { "epoch": 0.11652412950519242, "grad_norm": 0.3938056230545044, "learning_rate": 4.834352019503243e-05, "loss": 4.4089, "step": 3815 }, { "epoch": 0.1165546731826512, "grad_norm": 0.393558144569397, "learning_rate": 4.834266140349634e-05, "loss": 4.4454, "step": 3816 }, { "epoch": 0.11658521686010996, "grad_norm": 0.3999091386795044, "learning_rate": 4.834180239703237e-05, "loss": 4.4806, "step": 3817 }, { "epoch": 0.11661576053756872, "grad_norm": 0.3921867609024048, "learning_rate": 4.8340943175648424e-05, "loss": 4.3455, "step": 3818 }, { "epoch": 0.11664630421502749, "grad_norm": 0.38523876667022705, "learning_rate": 4.83400837393524e-05, "loss": 4.3954, "step": 3819 }, { "epoch": 0.11667684789248625, "grad_norm": 0.3904593586921692, "learning_rate": 4.833922408815224e-05, "loss": 4.4222, "step": 3820 }, { "epoch": 0.11670739156994502, "grad_norm": 0.38912564516067505, "learning_rate": 4.8338364222055846e-05, "loss": 4.4323, "step": 3821 }, { "epoch": 0.11673793524740379, "grad_norm": 0.38428670167922974, "learning_rate": 4.833750414107112e-05, "loss": 4.423, "step": 3822 }, { "epoch": 0.11676847892486256, "grad_norm": 0.39066311717033386, "learning_rate": 4.8336643845206e-05, "loss": 4.4534, "step": 3823 }, { "epoch": 0.11679902260232132, "grad_norm": 0.3980608284473419, "learning_rate": 4.83357833344684e-05, "loss": 4.4325, "step": 3824 }, { "epoch": 0.11682956627978008, "grad_norm": 0.3811494708061218, "learning_rate": 4.833492260886625e-05, "loss": 4.4487, "step": 3825 }, { "epoch": 0.11686010995723885, "grad_norm": 0.39547979831695557, "learning_rate": 4.833406166840746e-05, "loss": 4.4582, "step": 3826 }, { "epoch": 0.11689065363469761, "grad_norm": 0.3945917785167694, "learning_rate": 4.833320051309997e-05, "loss": 4.4548, "step": 3827 }, { "epoch": 0.11692119731215639, "grad_norm": 0.38627690076828003, "learning_rate": 4.8332339142951716e-05, "loss": 4.459, "step": 3828 }, { "epoch": 0.11695174098961515, "grad_norm": 0.40756163001060486, "learning_rate": 4.8331477557970615e-05, "loss": 4.3953, "step": 3829 }, { "epoch": 0.11698228466707392, "grad_norm": 0.38327401876449585, "learning_rate": 4.83306157581646e-05, "loss": 4.2923, "step": 3830 }, { "epoch": 0.11701282834453268, "grad_norm": 0.396647572517395, "learning_rate": 4.832975374354162e-05, "loss": 4.4218, "step": 3831 }, { "epoch": 0.11704337202199144, "grad_norm": 0.39930638670921326, "learning_rate": 4.832889151410959e-05, "loss": 4.3913, "step": 3832 }, { "epoch": 0.11707391569945022, "grad_norm": 0.3918902575969696, "learning_rate": 4.8328029069876466e-05, "loss": 4.3166, "step": 3833 }, { "epoch": 0.11710445937690898, "grad_norm": 0.40157002210617065, "learning_rate": 4.832716641085018e-05, "loss": 4.3152, "step": 3834 }, { "epoch": 0.11713500305436775, "grad_norm": 0.3851794898509979, "learning_rate": 4.832630353703869e-05, "loss": 4.3624, "step": 3835 }, { "epoch": 0.11716554673182651, "grad_norm": 0.3950308859348297, "learning_rate": 4.8325440448449924e-05, "loss": 4.37, "step": 3836 }, { "epoch": 0.11719609040928528, "grad_norm": 0.40975093841552734, "learning_rate": 4.832457714509183e-05, "loss": 4.3761, "step": 3837 }, { "epoch": 0.11722663408674404, "grad_norm": 0.38654184341430664, "learning_rate": 4.8323713626972366e-05, "loss": 4.3451, "step": 3838 }, { "epoch": 0.11725717776420282, "grad_norm": 0.3945449888706207, "learning_rate": 4.832284989409948e-05, "loss": 4.4414, "step": 3839 }, { "epoch": 0.11728772144166158, "grad_norm": 0.39032721519470215, "learning_rate": 4.832198594648112e-05, "loss": 4.3774, "step": 3840 }, { "epoch": 0.11731826511912034, "grad_norm": 0.3929752707481384, "learning_rate": 4.832112178412525e-05, "loss": 4.4241, "step": 3841 }, { "epoch": 0.11734880879657911, "grad_norm": 0.4039456844329834, "learning_rate": 4.832025740703982e-05, "loss": 4.4349, "step": 3842 }, { "epoch": 0.11737935247403787, "grad_norm": 0.4001246690750122, "learning_rate": 4.831939281523279e-05, "loss": 4.3812, "step": 3843 }, { "epoch": 0.11740989615149663, "grad_norm": 0.404941588640213, "learning_rate": 4.831852800871212e-05, "loss": 4.427, "step": 3844 }, { "epoch": 0.11744043982895541, "grad_norm": 0.405588299036026, "learning_rate": 4.8317662987485764e-05, "loss": 4.4286, "step": 3845 }, { "epoch": 0.11747098350641418, "grad_norm": 0.39753344655036926, "learning_rate": 4.831679775156171e-05, "loss": 4.4721, "step": 3846 }, { "epoch": 0.11750152718387294, "grad_norm": 0.3987054228782654, "learning_rate": 4.831593230094791e-05, "loss": 4.3422, "step": 3847 }, { "epoch": 0.1175320708613317, "grad_norm": 0.4050379991531372, "learning_rate": 4.8315066635652326e-05, "loss": 4.4255, "step": 3848 }, { "epoch": 0.11756261453879047, "grad_norm": 0.3881913423538208, "learning_rate": 4.8314200755682937e-05, "loss": 4.3585, "step": 3849 }, { "epoch": 0.11759315821624923, "grad_norm": 0.39817801117897034, "learning_rate": 4.831333466104772e-05, "loss": 4.3207, "step": 3850 }, { "epoch": 0.11762370189370801, "grad_norm": 0.3932611644268036, "learning_rate": 4.831246835175464e-05, "loss": 4.396, "step": 3851 }, { "epoch": 0.11765424557116677, "grad_norm": 0.40304747223854065, "learning_rate": 4.831160182781168e-05, "loss": 4.3817, "step": 3852 }, { "epoch": 0.11768478924862553, "grad_norm": 0.39545881748199463, "learning_rate": 4.831073508922681e-05, "loss": 4.4313, "step": 3853 }, { "epoch": 0.1177153329260843, "grad_norm": 0.38448813557624817, "learning_rate": 4.830986813600803e-05, "loss": 4.344, "step": 3854 }, { "epoch": 0.11774587660354306, "grad_norm": 0.3820534348487854, "learning_rate": 4.83090009681633e-05, "loss": 4.4016, "step": 3855 }, { "epoch": 0.11777642028100183, "grad_norm": 0.398913711309433, "learning_rate": 4.830813358570061e-05, "loss": 4.4455, "step": 3856 }, { "epoch": 0.1178069639584606, "grad_norm": 0.4121708869934082, "learning_rate": 4.830726598862796e-05, "loss": 4.4419, "step": 3857 }, { "epoch": 0.11783750763591937, "grad_norm": 0.39386656880378723, "learning_rate": 4.8306398176953324e-05, "loss": 4.3034, "step": 3858 }, { "epoch": 0.11786805131337813, "grad_norm": 0.39149653911590576, "learning_rate": 4.83055301506847e-05, "loss": 4.4516, "step": 3859 }, { "epoch": 0.1178985949908369, "grad_norm": 0.39238640666007996, "learning_rate": 4.830466190983007e-05, "loss": 4.3616, "step": 3860 }, { "epoch": 0.11792913866829566, "grad_norm": 0.3841627538204193, "learning_rate": 4.830379345439744e-05, "loss": 4.4543, "step": 3861 }, { "epoch": 0.11795968234575444, "grad_norm": 0.3811470568180084, "learning_rate": 4.83029247843948e-05, "loss": 4.3703, "step": 3862 }, { "epoch": 0.1179902260232132, "grad_norm": 0.39645105600357056, "learning_rate": 4.8302055899830154e-05, "loss": 4.3727, "step": 3863 }, { "epoch": 0.11802076970067196, "grad_norm": 0.38455867767333984, "learning_rate": 4.830118680071149e-05, "loss": 4.4089, "step": 3864 }, { "epoch": 0.11805131337813073, "grad_norm": 0.40369099378585815, "learning_rate": 4.8300317487046834e-05, "loss": 4.3739, "step": 3865 }, { "epoch": 0.11808185705558949, "grad_norm": 0.4073420763015747, "learning_rate": 4.829944795884417e-05, "loss": 4.5079, "step": 3866 }, { "epoch": 0.11811240073304825, "grad_norm": 0.39658018946647644, "learning_rate": 4.8298578216111504e-05, "loss": 4.3643, "step": 3867 }, { "epoch": 0.11814294441050703, "grad_norm": 0.3841981589794159, "learning_rate": 4.829770825885685e-05, "loss": 4.3318, "step": 3868 }, { "epoch": 0.1181734880879658, "grad_norm": 0.38116803765296936, "learning_rate": 4.829683808708822e-05, "loss": 4.3403, "step": 3869 }, { "epoch": 0.11820403176542456, "grad_norm": 0.3870619833469391, "learning_rate": 4.829596770081362e-05, "loss": 4.3929, "step": 3870 }, { "epoch": 0.11823457544288332, "grad_norm": 0.404019832611084, "learning_rate": 4.829509710004108e-05, "loss": 4.3311, "step": 3871 }, { "epoch": 0.11826511912034209, "grad_norm": 0.40024110674858093, "learning_rate": 4.829422628477859e-05, "loss": 4.4478, "step": 3872 }, { "epoch": 0.11829566279780085, "grad_norm": 0.38538867235183716, "learning_rate": 4.8293355255034185e-05, "loss": 4.4428, "step": 3873 }, { "epoch": 0.11832620647525963, "grad_norm": 0.395176500082016, "learning_rate": 4.829248401081588e-05, "loss": 4.4273, "step": 3874 }, { "epoch": 0.11835675015271839, "grad_norm": 0.38807621598243713, "learning_rate": 4.82916125521317e-05, "loss": 4.3937, "step": 3875 }, { "epoch": 0.11838729383017715, "grad_norm": 0.3779449760913849, "learning_rate": 4.829074087898967e-05, "loss": 4.4776, "step": 3876 }, { "epoch": 0.11841783750763592, "grad_norm": 0.4003903269767761, "learning_rate": 4.828986899139782e-05, "loss": 4.4807, "step": 3877 }, { "epoch": 0.11844838118509468, "grad_norm": 0.4271443486213684, "learning_rate": 4.8288996889364165e-05, "loss": 4.338, "step": 3878 }, { "epoch": 0.11847892486255344, "grad_norm": 0.38931989669799805, "learning_rate": 4.828812457289674e-05, "loss": 4.4058, "step": 3879 }, { "epoch": 0.11850946854001222, "grad_norm": 0.3929561674594879, "learning_rate": 4.828725204200358e-05, "loss": 4.3677, "step": 3880 }, { "epoch": 0.11854001221747099, "grad_norm": 0.39230668544769287, "learning_rate": 4.828637929669272e-05, "loss": 4.3863, "step": 3881 }, { "epoch": 0.11857055589492975, "grad_norm": 0.39553743600845337, "learning_rate": 4.828550633697219e-05, "loss": 4.4206, "step": 3882 }, { "epoch": 0.11860109957238851, "grad_norm": 0.39244621992111206, "learning_rate": 4.828463316285004e-05, "loss": 4.3672, "step": 3883 }, { "epoch": 0.11863164324984728, "grad_norm": 0.398079514503479, "learning_rate": 4.8283759774334286e-05, "loss": 4.4147, "step": 3884 }, { "epoch": 0.11866218692730605, "grad_norm": 0.3967515230178833, "learning_rate": 4.828288617143299e-05, "loss": 4.4201, "step": 3885 }, { "epoch": 0.11869273060476482, "grad_norm": 0.40586569905281067, "learning_rate": 4.8282012354154195e-05, "loss": 4.3895, "step": 3886 }, { "epoch": 0.11872327428222358, "grad_norm": 0.3874095380306244, "learning_rate": 4.8281138322505936e-05, "loss": 4.4528, "step": 3887 }, { "epoch": 0.11875381795968235, "grad_norm": 0.3930962085723877, "learning_rate": 4.8280264076496264e-05, "loss": 4.4349, "step": 3888 }, { "epoch": 0.11878436163714111, "grad_norm": 0.3962920606136322, "learning_rate": 4.8279389616133244e-05, "loss": 4.4373, "step": 3889 }, { "epoch": 0.11881490531459987, "grad_norm": 0.38837936520576477, "learning_rate": 4.82785149414249e-05, "loss": 4.435, "step": 3890 }, { "epoch": 0.11884544899205865, "grad_norm": 0.3929521143436432, "learning_rate": 4.8277640052379314e-05, "loss": 4.3349, "step": 3891 }, { "epoch": 0.11887599266951741, "grad_norm": 0.4032321274280548, "learning_rate": 4.827676494900451e-05, "loss": 4.4577, "step": 3892 }, { "epoch": 0.11890653634697618, "grad_norm": 0.40812942385673523, "learning_rate": 4.8275889631308577e-05, "loss": 4.4556, "step": 3893 }, { "epoch": 0.11893708002443494, "grad_norm": 0.4053998291492462, "learning_rate": 4.827501409929956e-05, "loss": 4.2703, "step": 3894 }, { "epoch": 0.1189676237018937, "grad_norm": 0.3950139284133911, "learning_rate": 4.827413835298552e-05, "loss": 4.4107, "step": 3895 }, { "epoch": 0.11899816737935247, "grad_norm": 0.3806816041469574, "learning_rate": 4.827326239237452e-05, "loss": 4.3927, "step": 3896 }, { "epoch": 0.11902871105681125, "grad_norm": 0.4067184329032898, "learning_rate": 4.827238621747463e-05, "loss": 4.4385, "step": 3897 }, { "epoch": 0.11905925473427001, "grad_norm": 0.4038633704185486, "learning_rate": 4.8271509828293914e-05, "loss": 4.471, "step": 3898 }, { "epoch": 0.11908979841172877, "grad_norm": 0.39037632942199707, "learning_rate": 4.8270633224840446e-05, "loss": 4.3742, "step": 3899 }, { "epoch": 0.11912034208918754, "grad_norm": 0.39524519443511963, "learning_rate": 4.826975640712228e-05, "loss": 4.4626, "step": 3900 }, { "epoch": 0.1191508857666463, "grad_norm": 0.3928167223930359, "learning_rate": 4.8268879375147515e-05, "loss": 4.3428, "step": 3901 }, { "epoch": 0.11918142944410506, "grad_norm": 0.39478999376296997, "learning_rate": 4.8268002128924206e-05, "loss": 4.3608, "step": 3902 }, { "epoch": 0.11921197312156384, "grad_norm": 0.40534892678260803, "learning_rate": 4.826712466846045e-05, "loss": 4.3707, "step": 3903 }, { "epoch": 0.1192425167990226, "grad_norm": 0.3914828896522522, "learning_rate": 4.82662469937643e-05, "loss": 4.3313, "step": 3904 }, { "epoch": 0.11927306047648137, "grad_norm": 0.39626047015190125, "learning_rate": 4.8265369104843863e-05, "loss": 4.3555, "step": 3905 }, { "epoch": 0.11930360415394013, "grad_norm": 0.4083074629306793, "learning_rate": 4.82644910017072e-05, "loss": 4.4008, "step": 3906 }, { "epoch": 0.1193341478313989, "grad_norm": 0.4065626263618469, "learning_rate": 4.8263612684362414e-05, "loss": 4.3679, "step": 3907 }, { "epoch": 0.11936469150885767, "grad_norm": 0.4018379747867584, "learning_rate": 4.8262734152817586e-05, "loss": 4.5063, "step": 3908 }, { "epoch": 0.11939523518631644, "grad_norm": 0.3970339894294739, "learning_rate": 4.8261855407080805e-05, "loss": 4.4654, "step": 3909 }, { "epoch": 0.1194257788637752, "grad_norm": 0.3931751847267151, "learning_rate": 4.826097644716016e-05, "loss": 4.4021, "step": 3910 }, { "epoch": 0.11945632254123396, "grad_norm": 0.4077828824520111, "learning_rate": 4.8260097273063745e-05, "loss": 4.3055, "step": 3911 }, { "epoch": 0.11948686621869273, "grad_norm": 0.39225682616233826, "learning_rate": 4.8259217884799646e-05, "loss": 4.2987, "step": 3912 }, { "epoch": 0.11951740989615149, "grad_norm": 0.39569345116615295, "learning_rate": 4.825833828237598e-05, "loss": 4.3575, "step": 3913 }, { "epoch": 0.11954795357361027, "grad_norm": 0.3974512219429016, "learning_rate": 4.825745846580083e-05, "loss": 4.4449, "step": 3914 }, { "epoch": 0.11957849725106903, "grad_norm": 0.3911745846271515, "learning_rate": 4.82565784350823e-05, "loss": 4.2851, "step": 3915 }, { "epoch": 0.1196090409285278, "grad_norm": 0.3976689875125885, "learning_rate": 4.82556981902285e-05, "loss": 4.3692, "step": 3916 }, { "epoch": 0.11963958460598656, "grad_norm": 0.40396133065223694, "learning_rate": 4.825481773124753e-05, "loss": 4.4632, "step": 3917 }, { "epoch": 0.11967012828344532, "grad_norm": 0.3900049328804016, "learning_rate": 4.82539370581475e-05, "loss": 4.377, "step": 3918 }, { "epoch": 0.11970067196090409, "grad_norm": 0.5349506735801697, "learning_rate": 4.825305617093651e-05, "loss": 4.5263, "step": 3919 }, { "epoch": 0.11973121563836286, "grad_norm": 0.3951496183872223, "learning_rate": 4.8252175069622676e-05, "loss": 4.4635, "step": 3920 }, { "epoch": 0.11976175931582163, "grad_norm": 0.3979254961013794, "learning_rate": 4.825129375421411e-05, "loss": 4.4557, "step": 3921 }, { "epoch": 0.11979230299328039, "grad_norm": 0.3952697515487671, "learning_rate": 4.825041222471893e-05, "loss": 4.4535, "step": 3922 }, { "epoch": 0.11982284667073916, "grad_norm": 0.39377066493034363, "learning_rate": 4.8249530481145256e-05, "loss": 4.3949, "step": 3923 }, { "epoch": 0.11985339034819792, "grad_norm": 0.40224602818489075, "learning_rate": 4.8248648523501194e-05, "loss": 4.4067, "step": 3924 }, { "epoch": 0.11988393402565668, "grad_norm": 0.41150954365730286, "learning_rate": 4.8247766351794876e-05, "loss": 4.2889, "step": 3925 }, { "epoch": 0.11991447770311546, "grad_norm": 0.41554608941078186, "learning_rate": 4.8246883966034416e-05, "loss": 4.4439, "step": 3926 }, { "epoch": 0.11994502138057422, "grad_norm": 0.3907557427883148, "learning_rate": 4.8246001366227944e-05, "loss": 4.406, "step": 3927 }, { "epoch": 0.11997556505803299, "grad_norm": 0.4005690813064575, "learning_rate": 4.824511855238359e-05, "loss": 4.3128, "step": 3928 }, { "epoch": 0.12000610873549175, "grad_norm": 0.39275169372558594, "learning_rate": 4.8244235524509476e-05, "loss": 4.3513, "step": 3929 }, { "epoch": 0.12003665241295051, "grad_norm": 0.38961443305015564, "learning_rate": 4.824335228261373e-05, "loss": 4.3527, "step": 3930 }, { "epoch": 0.12006719609040929, "grad_norm": 0.38818296790122986, "learning_rate": 4.824246882670449e-05, "loss": 4.3823, "step": 3931 }, { "epoch": 0.12009773976786806, "grad_norm": 0.40346115827560425, "learning_rate": 4.824158515678989e-05, "loss": 4.3358, "step": 3932 }, { "epoch": 0.12012828344532682, "grad_norm": 0.39165833592414856, "learning_rate": 4.824070127287808e-05, "loss": 4.445, "step": 3933 }, { "epoch": 0.12015882712278558, "grad_norm": 0.3934876024723053, "learning_rate": 4.8239817174977164e-05, "loss": 4.4312, "step": 3934 }, { "epoch": 0.12018937080024435, "grad_norm": 0.3920111060142517, "learning_rate": 4.823893286309531e-05, "loss": 4.3609, "step": 3935 }, { "epoch": 0.12021991447770311, "grad_norm": 0.393821656703949, "learning_rate": 4.823804833724065e-05, "loss": 4.4447, "step": 3936 }, { "epoch": 0.12025045815516189, "grad_norm": 0.39569753408432007, "learning_rate": 4.8237163597421335e-05, "loss": 4.4565, "step": 3937 }, { "epoch": 0.12028100183262065, "grad_norm": 0.3922397196292877, "learning_rate": 4.823627864364551e-05, "loss": 4.4548, "step": 3938 }, { "epoch": 0.12031154551007942, "grad_norm": 0.39698201417922974, "learning_rate": 4.823539347592132e-05, "loss": 4.4287, "step": 3939 }, { "epoch": 0.12034208918753818, "grad_norm": 0.3993930518627167, "learning_rate": 4.823450809425691e-05, "loss": 4.441, "step": 3940 }, { "epoch": 0.12037263286499694, "grad_norm": 0.3889644145965576, "learning_rate": 4.8233622498660445e-05, "loss": 4.3646, "step": 3941 }, { "epoch": 0.1204031765424557, "grad_norm": 0.4039531946182251, "learning_rate": 4.8232736689140065e-05, "loss": 4.4137, "step": 3942 }, { "epoch": 0.12043372021991448, "grad_norm": 0.39380645751953125, "learning_rate": 4.823185066570394e-05, "loss": 4.3983, "step": 3943 }, { "epoch": 0.12046426389737325, "grad_norm": 0.38547423481941223, "learning_rate": 4.8230964428360216e-05, "loss": 4.4053, "step": 3944 }, { "epoch": 0.12049480757483201, "grad_norm": 0.39059701561927795, "learning_rate": 4.823007797711706e-05, "loss": 4.4719, "step": 3945 }, { "epoch": 0.12052535125229077, "grad_norm": 0.4028998017311096, "learning_rate": 4.822919131198262e-05, "loss": 4.4166, "step": 3946 }, { "epoch": 0.12055589492974954, "grad_norm": 0.38846084475517273, "learning_rate": 4.822830443296509e-05, "loss": 4.4571, "step": 3947 }, { "epoch": 0.1205864386072083, "grad_norm": 0.38481494784355164, "learning_rate": 4.822741734007262e-05, "loss": 4.4228, "step": 3948 }, { "epoch": 0.12061698228466708, "grad_norm": 0.39091312885284424, "learning_rate": 4.8226530033313364e-05, "loss": 4.4035, "step": 3949 }, { "epoch": 0.12064752596212584, "grad_norm": 0.39142632484436035, "learning_rate": 4.8225642512695514e-05, "loss": 4.379, "step": 3950 }, { "epoch": 0.1206780696395846, "grad_norm": 0.4125194847583771, "learning_rate": 4.822475477822722e-05, "loss": 4.4537, "step": 3951 }, { "epoch": 0.12070861331704337, "grad_norm": 0.3950054347515106, "learning_rate": 4.822386682991667e-05, "loss": 4.3427, "step": 3952 }, { "epoch": 0.12073915699450213, "grad_norm": 0.3830608129501343, "learning_rate": 4.822297866777205e-05, "loss": 4.4565, "step": 3953 }, { "epoch": 0.1207697006719609, "grad_norm": 0.39411669969558716, "learning_rate": 4.822209029180152e-05, "loss": 4.4386, "step": 3954 }, { "epoch": 0.12080024434941967, "grad_norm": 0.39930459856987, "learning_rate": 4.8221201702013264e-05, "loss": 4.3329, "step": 3955 }, { "epoch": 0.12083078802687844, "grad_norm": 0.3978331983089447, "learning_rate": 4.822031289841546e-05, "loss": 4.4151, "step": 3956 }, { "epoch": 0.1208613317043372, "grad_norm": 0.3971725404262543, "learning_rate": 4.82194238810163e-05, "loss": 4.3608, "step": 3957 }, { "epoch": 0.12089187538179597, "grad_norm": 0.395370751619339, "learning_rate": 4.8218534649823964e-05, "loss": 4.401, "step": 3958 }, { "epoch": 0.12092241905925473, "grad_norm": 0.40224936604499817, "learning_rate": 4.8217645204846645e-05, "loss": 4.4153, "step": 3959 }, { "epoch": 0.1209529627367135, "grad_norm": 0.4000976085662842, "learning_rate": 4.821675554609253e-05, "loss": 4.3986, "step": 3960 }, { "epoch": 0.12098350641417227, "grad_norm": 0.39381682872772217, "learning_rate": 4.8215865673569806e-05, "loss": 4.4583, "step": 3961 }, { "epoch": 0.12101405009163103, "grad_norm": 0.407606303691864, "learning_rate": 4.821497558728667e-05, "loss": 4.4272, "step": 3962 }, { "epoch": 0.1210445937690898, "grad_norm": 0.40316933393478394, "learning_rate": 4.821408528725132e-05, "loss": 4.4404, "step": 3963 }, { "epoch": 0.12107513744654856, "grad_norm": 0.405531644821167, "learning_rate": 4.8213194773471956e-05, "loss": 4.429, "step": 3964 }, { "epoch": 0.12110568112400732, "grad_norm": 0.39862844347953796, "learning_rate": 4.8212304045956765e-05, "loss": 4.4385, "step": 3965 }, { "epoch": 0.1211362248014661, "grad_norm": 0.395982950925827, "learning_rate": 4.821141310471396e-05, "loss": 4.3984, "step": 3966 }, { "epoch": 0.12116676847892487, "grad_norm": 0.396390438079834, "learning_rate": 4.8210521949751744e-05, "loss": 4.3984, "step": 3967 }, { "epoch": 0.12119731215638363, "grad_norm": 0.4093673825263977, "learning_rate": 4.820963058107831e-05, "loss": 4.4454, "step": 3968 }, { "epoch": 0.1212278558338424, "grad_norm": 0.3960757553577423, "learning_rate": 4.8208738998701876e-05, "loss": 4.3954, "step": 3969 }, { "epoch": 0.12125839951130116, "grad_norm": 0.39945048093795776, "learning_rate": 4.820784720263065e-05, "loss": 4.441, "step": 3970 }, { "epoch": 0.12128894318875992, "grad_norm": 0.38964712619781494, "learning_rate": 4.820695519287285e-05, "loss": 4.4326, "step": 3971 }, { "epoch": 0.1213194868662187, "grad_norm": 0.4032757580280304, "learning_rate": 4.820606296943667e-05, "loss": 4.345, "step": 3972 }, { "epoch": 0.12135003054367746, "grad_norm": 0.38843464851379395, "learning_rate": 4.8205170532330346e-05, "loss": 4.4575, "step": 3973 }, { "epoch": 0.12138057422113623, "grad_norm": 0.37726539373397827, "learning_rate": 4.820427788156208e-05, "loss": 4.4766, "step": 3974 }, { "epoch": 0.12141111789859499, "grad_norm": 0.3884504735469818, "learning_rate": 4.8203385017140104e-05, "loss": 4.3551, "step": 3975 }, { "epoch": 0.12144166157605375, "grad_norm": 0.3965306878089905, "learning_rate": 4.8202491939072625e-05, "loss": 4.3002, "step": 3976 }, { "epoch": 0.12147220525351252, "grad_norm": 0.39478105306625366, "learning_rate": 4.820159864736787e-05, "loss": 4.4174, "step": 3977 }, { "epoch": 0.1215027489309713, "grad_norm": 0.37921014428138733, "learning_rate": 4.820070514203408e-05, "loss": 4.4964, "step": 3978 }, { "epoch": 0.12153329260843006, "grad_norm": 0.41312485933303833, "learning_rate": 4.819981142307947e-05, "loss": 4.4051, "step": 3979 }, { "epoch": 0.12156383628588882, "grad_norm": 0.3980081081390381, "learning_rate": 4.819891749051225e-05, "loss": 4.3903, "step": 3980 }, { "epoch": 0.12159437996334758, "grad_norm": 0.38518959283828735, "learning_rate": 4.8198023344340683e-05, "loss": 4.4331, "step": 3981 }, { "epoch": 0.12162492364080635, "grad_norm": 0.39669620990753174, "learning_rate": 4.819712898457298e-05, "loss": 4.3827, "step": 3982 }, { "epoch": 0.12165546731826513, "grad_norm": 0.3964984714984894, "learning_rate": 4.819623441121739e-05, "loss": 4.4252, "step": 3983 }, { "epoch": 0.12168601099572389, "grad_norm": 0.4066581428050995, "learning_rate": 4.819533962428214e-05, "loss": 4.4515, "step": 3984 }, { "epoch": 0.12171655467318265, "grad_norm": 0.4039974808692932, "learning_rate": 4.8194444623775473e-05, "loss": 4.3996, "step": 3985 }, { "epoch": 0.12174709835064142, "grad_norm": 0.40854042768478394, "learning_rate": 4.819354940970563e-05, "loss": 4.4164, "step": 3986 }, { "epoch": 0.12177764202810018, "grad_norm": 0.3947582244873047, "learning_rate": 4.819265398208085e-05, "loss": 4.3867, "step": 3987 }, { "epoch": 0.12180818570555894, "grad_norm": 0.41333290934562683, "learning_rate": 4.819175834090939e-05, "loss": 4.4246, "step": 3988 }, { "epoch": 0.12183872938301772, "grad_norm": 0.4113290011882782, "learning_rate": 4.8190862486199476e-05, "loss": 4.4592, "step": 3989 }, { "epoch": 0.12186927306047649, "grad_norm": 0.39388522505760193, "learning_rate": 4.818996641795937e-05, "loss": 4.3303, "step": 3990 }, { "epoch": 0.12189981673793525, "grad_norm": 0.4202585220336914, "learning_rate": 4.818907013619732e-05, "loss": 4.406, "step": 3991 }, { "epoch": 0.12193036041539401, "grad_norm": 0.40036681294441223, "learning_rate": 4.818817364092158e-05, "loss": 4.3706, "step": 3992 }, { "epoch": 0.12196090409285278, "grad_norm": 0.40775951743125916, "learning_rate": 4.81872769321404e-05, "loss": 4.3495, "step": 3993 }, { "epoch": 0.12199144777031154, "grad_norm": 0.3947179317474365, "learning_rate": 4.818638000986204e-05, "loss": 4.4312, "step": 3994 }, { "epoch": 0.12202199144777032, "grad_norm": 0.39027824997901917, "learning_rate": 4.818548287409477e-05, "loss": 4.3812, "step": 3995 }, { "epoch": 0.12205253512522908, "grad_norm": 0.392106294631958, "learning_rate": 4.818458552484683e-05, "loss": 4.4058, "step": 3996 }, { "epoch": 0.12208307880268784, "grad_norm": 0.39735814929008484, "learning_rate": 4.8183687962126485e-05, "loss": 4.4302, "step": 3997 }, { "epoch": 0.12211362248014661, "grad_norm": 0.39169198274612427, "learning_rate": 4.818279018594201e-05, "loss": 4.3897, "step": 3998 }, { "epoch": 0.12214416615760537, "grad_norm": 0.3977758586406708, "learning_rate": 4.8181892196301666e-05, "loss": 4.3771, "step": 3999 }, { "epoch": 0.12217470983506414, "grad_norm": 0.3970271050930023, "learning_rate": 4.8180993993213716e-05, "loss": 4.4606, "step": 4000 }, { "epoch": 0.12220525351252291, "grad_norm": 0.3904798924922943, "learning_rate": 4.818009557668645e-05, "loss": 4.4784, "step": 4001 }, { "epoch": 0.12223579718998168, "grad_norm": 0.3886832296848297, "learning_rate": 4.817919694672811e-05, "loss": 4.3831, "step": 4002 }, { "epoch": 0.12226634086744044, "grad_norm": 0.3943300247192383, "learning_rate": 4.8178298103347e-05, "loss": 4.4029, "step": 4003 }, { "epoch": 0.1222968845448992, "grad_norm": 0.40557143092155457, "learning_rate": 4.817739904655137e-05, "loss": 4.355, "step": 4004 }, { "epoch": 0.12232742822235797, "grad_norm": 0.39612630009651184, "learning_rate": 4.817649977634952e-05, "loss": 4.4264, "step": 4005 }, { "epoch": 0.12235797189981674, "grad_norm": 0.38952356576919556, "learning_rate": 4.817560029274971e-05, "loss": 4.4196, "step": 4006 }, { "epoch": 0.12238851557727551, "grad_norm": 0.3994886577129364, "learning_rate": 4.817470059576024e-05, "loss": 4.4792, "step": 4007 }, { "epoch": 0.12241905925473427, "grad_norm": 0.3951044976711273, "learning_rate": 4.8173800685389384e-05, "loss": 4.4577, "step": 4008 }, { "epoch": 0.12244960293219304, "grad_norm": 0.39190229773521423, "learning_rate": 4.817290056164544e-05, "loss": 4.4637, "step": 4009 }, { "epoch": 0.1224801466096518, "grad_norm": 0.399641215801239, "learning_rate": 4.8172000224536676e-05, "loss": 4.3921, "step": 4010 }, { "epoch": 0.12251069028711056, "grad_norm": 0.4026036262512207, "learning_rate": 4.817109967407138e-05, "loss": 4.3954, "step": 4011 }, { "epoch": 0.12254123396456934, "grad_norm": 0.38947272300720215, "learning_rate": 4.817019891025788e-05, "loss": 4.4202, "step": 4012 }, { "epoch": 0.1225717776420281, "grad_norm": 0.39594587683677673, "learning_rate": 4.816929793310443e-05, "loss": 4.4125, "step": 4013 }, { "epoch": 0.12260232131948687, "grad_norm": 0.3766440749168396, "learning_rate": 4.8168396742619345e-05, "loss": 4.3967, "step": 4014 }, { "epoch": 0.12263286499694563, "grad_norm": 0.4093557596206665, "learning_rate": 4.8167495338810925e-05, "loss": 4.4772, "step": 4015 }, { "epoch": 0.1226634086744044, "grad_norm": 0.38801059126853943, "learning_rate": 4.816659372168746e-05, "loss": 4.3509, "step": 4016 }, { "epoch": 0.12269395235186316, "grad_norm": 0.39147329330444336, "learning_rate": 4.8165691891257256e-05, "loss": 4.3509, "step": 4017 }, { "epoch": 0.12272449602932194, "grad_norm": 0.3950570523738861, "learning_rate": 4.816478984752861e-05, "loss": 4.4744, "step": 4018 }, { "epoch": 0.1227550397067807, "grad_norm": 0.39504194259643555, "learning_rate": 4.8163887590509845e-05, "loss": 4.4434, "step": 4019 }, { "epoch": 0.12278558338423946, "grad_norm": 0.3910941481590271, "learning_rate": 4.816298512020925e-05, "loss": 4.4288, "step": 4020 }, { "epoch": 0.12281612706169823, "grad_norm": 0.397720605134964, "learning_rate": 4.816208243663514e-05, "loss": 4.3797, "step": 4021 }, { "epoch": 0.12284667073915699, "grad_norm": 0.3893435299396515, "learning_rate": 4.8161179539795833e-05, "loss": 4.4242, "step": 4022 }, { "epoch": 0.12287721441661575, "grad_norm": 0.39696478843688965, "learning_rate": 4.816027642969963e-05, "loss": 4.344, "step": 4023 }, { "epoch": 0.12290775809407453, "grad_norm": 0.413661390542984, "learning_rate": 4.8159373106354864e-05, "loss": 4.3594, "step": 4024 }, { "epoch": 0.1229383017715333, "grad_norm": 0.40335604548454285, "learning_rate": 4.815846956976984e-05, "loss": 4.3806, "step": 4025 }, { "epoch": 0.12296884544899206, "grad_norm": 0.40375715494155884, "learning_rate": 4.8157565819952876e-05, "loss": 4.4709, "step": 4026 }, { "epoch": 0.12299938912645082, "grad_norm": 0.4136049449443817, "learning_rate": 4.8156661856912305e-05, "loss": 4.3113, "step": 4027 }, { "epoch": 0.12302993280390959, "grad_norm": 0.39989525079727173, "learning_rate": 4.815575768065643e-05, "loss": 4.386, "step": 4028 }, { "epoch": 0.12306047648136835, "grad_norm": 0.401790589094162, "learning_rate": 4.81548532911936e-05, "loss": 4.4128, "step": 4029 }, { "epoch": 0.12309102015882713, "grad_norm": 0.40737053751945496, "learning_rate": 4.815394868853212e-05, "loss": 4.4851, "step": 4030 }, { "epoch": 0.12312156383628589, "grad_norm": 0.4013577401638031, "learning_rate": 4.815304387268034e-05, "loss": 4.4338, "step": 4031 }, { "epoch": 0.12315210751374465, "grad_norm": 0.39486169815063477, "learning_rate": 4.815213884364658e-05, "loss": 4.3746, "step": 4032 }, { "epoch": 0.12318265119120342, "grad_norm": 0.41376498341560364, "learning_rate": 4.815123360143917e-05, "loss": 4.4649, "step": 4033 }, { "epoch": 0.12321319486866218, "grad_norm": 0.38813847303390503, "learning_rate": 4.815032814606645e-05, "loss": 4.3881, "step": 4034 }, { "epoch": 0.12324373854612096, "grad_norm": 0.40821579098701477, "learning_rate": 4.8149422477536756e-05, "loss": 4.4395, "step": 4035 }, { "epoch": 0.12327428222357972, "grad_norm": 0.41851893067359924, "learning_rate": 4.814851659585843e-05, "loss": 4.4799, "step": 4036 }, { "epoch": 0.12330482590103849, "grad_norm": 0.3984676003456116, "learning_rate": 4.81476105010398e-05, "loss": 4.465, "step": 4037 }, { "epoch": 0.12333536957849725, "grad_norm": 0.3982699513435364, "learning_rate": 4.814670419308923e-05, "loss": 4.3836, "step": 4038 }, { "epoch": 0.12336591325595601, "grad_norm": 0.4012869596481323, "learning_rate": 4.814579767201505e-05, "loss": 4.4684, "step": 4039 }, { "epoch": 0.12339645693341478, "grad_norm": 0.4045875370502472, "learning_rate": 4.81448909378256e-05, "loss": 4.4248, "step": 4040 }, { "epoch": 0.12342700061087356, "grad_norm": 0.3879126310348511, "learning_rate": 4.814398399052926e-05, "loss": 4.3505, "step": 4041 }, { "epoch": 0.12345754428833232, "grad_norm": 0.40004104375839233, "learning_rate": 4.8143076830134346e-05, "loss": 4.3793, "step": 4042 }, { "epoch": 0.12348808796579108, "grad_norm": 0.41002827882766724, "learning_rate": 4.814216945664922e-05, "loss": 4.2942, "step": 4043 }, { "epoch": 0.12351863164324985, "grad_norm": 0.4000740051269531, "learning_rate": 4.814126187008226e-05, "loss": 4.3906, "step": 4044 }, { "epoch": 0.12354917532070861, "grad_norm": 0.3984847366809845, "learning_rate": 4.8140354070441786e-05, "loss": 4.3305, "step": 4045 }, { "epoch": 0.12357971899816737, "grad_norm": 0.40581566095352173, "learning_rate": 4.813944605773618e-05, "loss": 4.3719, "step": 4046 }, { "epoch": 0.12361026267562615, "grad_norm": 0.401259183883667, "learning_rate": 4.81385378319738e-05, "loss": 4.4227, "step": 4047 }, { "epoch": 0.12364080635308491, "grad_norm": 0.40722379088401794, "learning_rate": 4.8137629393163005e-05, "loss": 4.3621, "step": 4048 }, { "epoch": 0.12367135003054368, "grad_norm": 0.4021589756011963, "learning_rate": 4.813672074131216e-05, "loss": 4.3881, "step": 4049 }, { "epoch": 0.12370189370800244, "grad_norm": 0.4171379506587982, "learning_rate": 4.813581187642962e-05, "loss": 4.3932, "step": 4050 }, { "epoch": 0.1237324373854612, "grad_norm": 0.38940608501434326, "learning_rate": 4.813490279852378e-05, "loss": 4.3091, "step": 4051 }, { "epoch": 0.12376298106291997, "grad_norm": 0.39171990752220154, "learning_rate": 4.813399350760299e-05, "loss": 4.3878, "step": 4052 }, { "epoch": 0.12379352474037875, "grad_norm": 0.40053924918174744, "learning_rate": 4.813308400367563e-05, "loss": 4.3919, "step": 4053 }, { "epoch": 0.12382406841783751, "grad_norm": 0.39329227805137634, "learning_rate": 4.8132174286750064e-05, "loss": 4.3348, "step": 4054 }, { "epoch": 0.12385461209529627, "grad_norm": 0.401075154542923, "learning_rate": 4.8131264356834685e-05, "loss": 4.2923, "step": 4055 }, { "epoch": 0.12388515577275504, "grad_norm": 0.38938432931900024, "learning_rate": 4.813035421393786e-05, "loss": 4.3479, "step": 4056 }, { "epoch": 0.1239156994502138, "grad_norm": 0.4062279462814331, "learning_rate": 4.812944385806797e-05, "loss": 4.3197, "step": 4057 }, { "epoch": 0.12394624312767258, "grad_norm": 0.4089401364326477, "learning_rate": 4.8128533289233395e-05, "loss": 4.3922, "step": 4058 }, { "epoch": 0.12397678680513134, "grad_norm": 0.39534562826156616, "learning_rate": 4.812762250744253e-05, "loss": 4.4366, "step": 4059 }, { "epoch": 0.1240073304825901, "grad_norm": 0.4036855697631836, "learning_rate": 4.812671151270375e-05, "loss": 4.4072, "step": 4060 }, { "epoch": 0.12403787416004887, "grad_norm": 0.41018107533454895, "learning_rate": 4.8125800305025434e-05, "loss": 4.3748, "step": 4061 }, { "epoch": 0.12406841783750763, "grad_norm": 0.3861103355884552, "learning_rate": 4.8124888884416006e-05, "loss": 4.3912, "step": 4062 }, { "epoch": 0.1240989615149664, "grad_norm": 0.381850928068161, "learning_rate": 4.812397725088382e-05, "loss": 4.3275, "step": 4063 }, { "epoch": 0.12412950519242517, "grad_norm": 0.3864074945449829, "learning_rate": 4.81230654044373e-05, "loss": 4.3925, "step": 4064 }, { "epoch": 0.12416004886988394, "grad_norm": 0.39495766162872314, "learning_rate": 4.812215334508482e-05, "loss": 4.4677, "step": 4065 }, { "epoch": 0.1241905925473427, "grad_norm": 0.40251362323760986, "learning_rate": 4.8121241072834786e-05, "loss": 4.4239, "step": 4066 }, { "epoch": 0.12422113622480146, "grad_norm": 0.39473697543144226, "learning_rate": 4.812032858769559e-05, "loss": 4.3531, "step": 4067 }, { "epoch": 0.12425167990226023, "grad_norm": 0.3942398726940155, "learning_rate": 4.8119415889675655e-05, "loss": 4.3724, "step": 4068 }, { "epoch": 0.12428222357971899, "grad_norm": 0.3884449303150177, "learning_rate": 4.811850297878336e-05, "loss": 4.4207, "step": 4069 }, { "epoch": 0.12431276725717777, "grad_norm": 0.38930708169937134, "learning_rate": 4.8117589855027134e-05, "loss": 4.3466, "step": 4070 }, { "epoch": 0.12434331093463653, "grad_norm": 0.38959500193595886, "learning_rate": 4.811667651841536e-05, "loss": 4.4417, "step": 4071 }, { "epoch": 0.1243738546120953, "grad_norm": 0.4013192057609558, "learning_rate": 4.811576296895647e-05, "loss": 4.4641, "step": 4072 }, { "epoch": 0.12440439828955406, "grad_norm": 0.3863299787044525, "learning_rate": 4.8114849206658864e-05, "loss": 4.481, "step": 4073 }, { "epoch": 0.12443494196701282, "grad_norm": 0.401628315448761, "learning_rate": 4.811393523153095e-05, "loss": 4.4961, "step": 4074 }, { "epoch": 0.12446548564447159, "grad_norm": 0.3839525580406189, "learning_rate": 4.8113021043581155e-05, "loss": 4.4083, "step": 4075 }, { "epoch": 0.12449602932193037, "grad_norm": 0.4028129577636719, "learning_rate": 4.811210664281789e-05, "loss": 4.4022, "step": 4076 }, { "epoch": 0.12452657299938913, "grad_norm": 0.3871093690395355, "learning_rate": 4.811119202924958e-05, "loss": 4.3493, "step": 4077 }, { "epoch": 0.12455711667684789, "grad_norm": 0.3818206489086151, "learning_rate": 4.811027720288464e-05, "loss": 4.3836, "step": 4078 }, { "epoch": 0.12458766035430666, "grad_norm": 0.3935013711452484, "learning_rate": 4.8109362163731496e-05, "loss": 4.4273, "step": 4079 }, { "epoch": 0.12461820403176542, "grad_norm": 0.3839249610900879, "learning_rate": 4.810844691179857e-05, "loss": 4.4057, "step": 4080 }, { "epoch": 0.1246487477092242, "grad_norm": 0.41393664479255676, "learning_rate": 4.81075314470943e-05, "loss": 4.293, "step": 4081 }, { "epoch": 0.12467929138668296, "grad_norm": 0.390005499124527, "learning_rate": 4.81066157696271e-05, "loss": 4.4298, "step": 4082 }, { "epoch": 0.12470983506414172, "grad_norm": 0.3831738531589508, "learning_rate": 4.810569987940541e-05, "loss": 4.3452, "step": 4083 }, { "epoch": 0.12474037874160049, "grad_norm": 0.3848540484905243, "learning_rate": 4.810478377643766e-05, "loss": 4.4662, "step": 4084 }, { "epoch": 0.12477092241905925, "grad_norm": 0.3924897015094757, "learning_rate": 4.810386746073229e-05, "loss": 4.4299, "step": 4085 }, { "epoch": 0.12480146609651802, "grad_norm": 0.40180328488349915, "learning_rate": 4.810295093229772e-05, "loss": 4.4366, "step": 4086 }, { "epoch": 0.1248320097739768, "grad_norm": 0.39290374517440796, "learning_rate": 4.810203419114242e-05, "loss": 4.3507, "step": 4087 }, { "epoch": 0.12486255345143556, "grad_norm": 0.38710182905197144, "learning_rate": 4.8101117237274805e-05, "loss": 4.3385, "step": 4088 }, { "epoch": 0.12489309712889432, "grad_norm": 0.38835030794143677, "learning_rate": 4.810020007070333e-05, "loss": 4.3077, "step": 4089 }, { "epoch": 0.12492364080635308, "grad_norm": 0.39399635791778564, "learning_rate": 4.809928269143643e-05, "loss": 4.414, "step": 4090 }, { "epoch": 0.12495418448381185, "grad_norm": 0.40322038531303406, "learning_rate": 4.809836509948257e-05, "loss": 4.3945, "step": 4091 }, { "epoch": 0.12498472816127061, "grad_norm": 0.39091965556144714, "learning_rate": 4.809744729485017e-05, "loss": 4.4207, "step": 4092 }, { "epoch": 0.12501527183872937, "grad_norm": 0.38874152302742004, "learning_rate": 4.809652927754771e-05, "loss": 4.335, "step": 4093 }, { "epoch": 0.12504581551618815, "grad_norm": 0.39254966378211975, "learning_rate": 4.8095611047583625e-05, "loss": 4.3685, "step": 4094 }, { "epoch": 0.1250763591936469, "grad_norm": 0.4091627895832062, "learning_rate": 4.809469260496637e-05, "loss": 4.4468, "step": 4095 }, { "epoch": 0.12510690287110568, "grad_norm": 0.39327844977378845, "learning_rate": 4.8093773949704416e-05, "loss": 4.4645, "step": 4096 }, { "epoch": 0.12513744654856446, "grad_norm": 0.38901403546333313, "learning_rate": 4.80928550818062e-05, "loss": 4.3191, "step": 4097 }, { "epoch": 0.1251679902260232, "grad_norm": 0.3944195806980133, "learning_rate": 4.8091936001280203e-05, "loss": 4.4312, "step": 4098 }, { "epoch": 0.12519853390348198, "grad_norm": 0.3982577919960022, "learning_rate": 4.809101670813488e-05, "loss": 4.4192, "step": 4099 }, { "epoch": 0.12522907758094073, "grad_norm": 0.39145055413246155, "learning_rate": 4.809009720237869e-05, "loss": 4.4171, "step": 4100 }, { "epoch": 0.1252596212583995, "grad_norm": 0.40892019867897034, "learning_rate": 4.80891774840201e-05, "loss": 4.4874, "step": 4101 }, { "epoch": 0.1252901649358583, "grad_norm": 0.39611971378326416, "learning_rate": 4.808825755306758e-05, "loss": 4.4557, "step": 4102 }, { "epoch": 0.12532070861331704, "grad_norm": 0.39557331800460815, "learning_rate": 4.808733740952961e-05, "loss": 4.3888, "step": 4103 }, { "epoch": 0.12535125229077582, "grad_norm": 0.3926865756511688, "learning_rate": 4.808641705341466e-05, "loss": 4.3537, "step": 4104 }, { "epoch": 0.12538179596823457, "grad_norm": 0.40034595131874084, "learning_rate": 4.808549648473119e-05, "loss": 4.5301, "step": 4105 }, { "epoch": 0.12541233964569334, "grad_norm": 0.40484294295310974, "learning_rate": 4.808457570348768e-05, "loss": 4.4107, "step": 4106 }, { "epoch": 0.12544288332315212, "grad_norm": 0.39756345748901367, "learning_rate": 4.8083654709692615e-05, "loss": 4.3801, "step": 4107 }, { "epoch": 0.12547342700061087, "grad_norm": 0.40370240807533264, "learning_rate": 4.808273350335447e-05, "loss": 4.4098, "step": 4108 }, { "epoch": 0.12550397067806965, "grad_norm": 0.38828280568122864, "learning_rate": 4.8081812084481735e-05, "loss": 4.4006, "step": 4109 }, { "epoch": 0.1255345143555284, "grad_norm": 0.3952183425426483, "learning_rate": 4.808089045308289e-05, "loss": 4.4592, "step": 4110 }, { "epoch": 0.12556505803298718, "grad_norm": 0.39418014883995056, "learning_rate": 4.807996860916642e-05, "loss": 4.3966, "step": 4111 }, { "epoch": 0.12559560171044593, "grad_norm": 0.4206104874610901, "learning_rate": 4.807904655274081e-05, "loss": 4.3932, "step": 4112 }, { "epoch": 0.1256261453879047, "grad_norm": 0.37522464990615845, "learning_rate": 4.807812428381455e-05, "loss": 4.3122, "step": 4113 }, { "epoch": 0.12565668906536348, "grad_norm": 0.4057284891605377, "learning_rate": 4.807720180239613e-05, "loss": 4.4068, "step": 4114 }, { "epoch": 0.12568723274282223, "grad_norm": 0.37988731265068054, "learning_rate": 4.807627910849406e-05, "loss": 4.2886, "step": 4115 }, { "epoch": 0.125717776420281, "grad_norm": 0.4002785384654999, "learning_rate": 4.807535620211682e-05, "loss": 4.4525, "step": 4116 }, { "epoch": 0.12574832009773976, "grad_norm": 0.3921937346458435, "learning_rate": 4.8074433083272905e-05, "loss": 4.4275, "step": 4117 }, { "epoch": 0.12577886377519854, "grad_norm": 0.38791683316230774, "learning_rate": 4.8073509751970824e-05, "loss": 4.3065, "step": 4118 }, { "epoch": 0.1258094074526573, "grad_norm": 0.3925250470638275, "learning_rate": 4.8072586208219075e-05, "loss": 4.3738, "step": 4119 }, { "epoch": 0.12583995113011606, "grad_norm": 0.39512550830841064, "learning_rate": 4.8071662452026165e-05, "loss": 4.4047, "step": 4120 }, { "epoch": 0.12587049480757484, "grad_norm": 0.3895668387413025, "learning_rate": 4.8070738483400596e-05, "loss": 4.3789, "step": 4121 }, { "epoch": 0.1259010384850336, "grad_norm": 0.40238431096076965, "learning_rate": 4.8069814302350874e-05, "loss": 4.391, "step": 4122 }, { "epoch": 0.12593158216249237, "grad_norm": 0.3987976312637329, "learning_rate": 4.806888990888551e-05, "loss": 4.3964, "step": 4123 }, { "epoch": 0.12596212583995112, "grad_norm": 0.38723024725914, "learning_rate": 4.806796530301302e-05, "loss": 4.4185, "step": 4124 }, { "epoch": 0.1259926695174099, "grad_norm": 0.39178502559661865, "learning_rate": 4.806704048474191e-05, "loss": 4.3923, "step": 4125 }, { "epoch": 0.12602321319486867, "grad_norm": 0.3918638825416565, "learning_rate": 4.8066115454080693e-05, "loss": 4.4027, "step": 4126 }, { "epoch": 0.12605375687232742, "grad_norm": 0.394438773393631, "learning_rate": 4.80651902110379e-05, "loss": 4.4648, "step": 4127 }, { "epoch": 0.1260843005497862, "grad_norm": 0.38385826349258423, "learning_rate": 4.8064264755622034e-05, "loss": 4.4186, "step": 4128 }, { "epoch": 0.12611484422724495, "grad_norm": 0.3934765160083771, "learning_rate": 4.806333908784163e-05, "loss": 4.3357, "step": 4129 }, { "epoch": 0.12614538790470373, "grad_norm": 0.3965517282485962, "learning_rate": 4.80624132077052e-05, "loss": 4.435, "step": 4130 }, { "epoch": 0.1261759315821625, "grad_norm": 0.38228923082351685, "learning_rate": 4.806148711522128e-05, "loss": 4.3777, "step": 4131 }, { "epoch": 0.12620647525962125, "grad_norm": 0.3810705840587616, "learning_rate": 4.806056081039839e-05, "loss": 4.3488, "step": 4132 }, { "epoch": 0.12623701893708003, "grad_norm": 0.40468499064445496, "learning_rate": 4.805963429324506e-05, "loss": 4.3978, "step": 4133 }, { "epoch": 0.12626756261453878, "grad_norm": 0.39093321561813354, "learning_rate": 4.805870756376982e-05, "loss": 4.3744, "step": 4134 }, { "epoch": 0.12629810629199756, "grad_norm": 0.3800414800643921, "learning_rate": 4.805778062198121e-05, "loss": 4.3457, "step": 4135 }, { "epoch": 0.12632864996945634, "grad_norm": 0.4012557566165924, "learning_rate": 4.805685346788775e-05, "loss": 4.38, "step": 4136 }, { "epoch": 0.12635919364691509, "grad_norm": 0.41471749544143677, "learning_rate": 4.8055926101497986e-05, "loss": 4.4876, "step": 4137 }, { "epoch": 0.12638973732437386, "grad_norm": 0.38046377897262573, "learning_rate": 4.805499852282046e-05, "loss": 4.2948, "step": 4138 }, { "epoch": 0.1264202810018326, "grad_norm": 0.3972652554512024, "learning_rate": 4.80540707318637e-05, "loss": 4.3694, "step": 4139 }, { "epoch": 0.1264508246792914, "grad_norm": 0.40478166937828064, "learning_rate": 4.805314272863627e-05, "loss": 4.4527, "step": 4140 }, { "epoch": 0.12648136835675014, "grad_norm": 0.40660959482192993, "learning_rate": 4.80522145131467e-05, "loss": 4.3769, "step": 4141 }, { "epoch": 0.12651191203420892, "grad_norm": 0.3885708749294281, "learning_rate": 4.805128608540353e-05, "loss": 4.4165, "step": 4142 }, { "epoch": 0.1265424557116677, "grad_norm": 0.3927946090698242, "learning_rate": 4.8050357445415324e-05, "loss": 4.4371, "step": 4143 }, { "epoch": 0.12657299938912644, "grad_norm": 0.40845754742622375, "learning_rate": 4.804942859319063e-05, "loss": 4.425, "step": 4144 }, { "epoch": 0.12660354306658522, "grad_norm": 0.3940344452857971, "learning_rate": 4.8048499528737986e-05, "loss": 4.3963, "step": 4145 }, { "epoch": 0.12663408674404397, "grad_norm": 0.3874707520008087, "learning_rate": 4.8047570252065955e-05, "loss": 4.3958, "step": 4146 }, { "epoch": 0.12666463042150275, "grad_norm": 0.3959208130836487, "learning_rate": 4.804664076318311e-05, "loss": 4.346, "step": 4147 }, { "epoch": 0.12669517409896153, "grad_norm": 0.3997211754322052, "learning_rate": 4.8045711062097974e-05, "loss": 4.3797, "step": 4148 }, { "epoch": 0.12672571777642028, "grad_norm": 0.3804621696472168, "learning_rate": 4.804478114881914e-05, "loss": 4.3346, "step": 4149 }, { "epoch": 0.12675626145387905, "grad_norm": 0.3930547535419464, "learning_rate": 4.804385102335516e-05, "loss": 4.3859, "step": 4150 }, { "epoch": 0.1267868051313378, "grad_norm": 0.3965001702308655, "learning_rate": 4.804292068571459e-05, "loss": 4.4341, "step": 4151 }, { "epoch": 0.12681734880879658, "grad_norm": 0.3927677273750305, "learning_rate": 4.8041990135906e-05, "loss": 4.3844, "step": 4152 }, { "epoch": 0.12684789248625533, "grad_norm": 0.38852885365486145, "learning_rate": 4.8041059373937966e-05, "loss": 4.3872, "step": 4153 }, { "epoch": 0.1268784361637141, "grad_norm": 0.3967856168746948, "learning_rate": 4.8040128399819044e-05, "loss": 4.4754, "step": 4154 }, { "epoch": 0.1269089798411729, "grad_norm": 0.410704642534256, "learning_rate": 4.803919721355782e-05, "loss": 4.4576, "step": 4155 }, { "epoch": 0.12693952351863164, "grad_norm": 0.3977137804031372, "learning_rate": 4.8038265815162866e-05, "loss": 4.3631, "step": 4156 }, { "epoch": 0.1269700671960904, "grad_norm": 0.38755249977111816, "learning_rate": 4.803733420464274e-05, "loss": 4.3749, "step": 4157 }, { "epoch": 0.12700061087354916, "grad_norm": 0.41259679198265076, "learning_rate": 4.8036402382006044e-05, "loss": 4.4055, "step": 4158 }, { "epoch": 0.12703115455100794, "grad_norm": 0.3859642744064331, "learning_rate": 4.8035470347261346e-05, "loss": 4.3879, "step": 4159 }, { "epoch": 0.12706169822846672, "grad_norm": 0.3944852352142334, "learning_rate": 4.8034538100417226e-05, "loss": 4.2875, "step": 4160 }, { "epoch": 0.12709224190592547, "grad_norm": 0.39418646693229675, "learning_rate": 4.803360564148227e-05, "loss": 4.4798, "step": 4161 }, { "epoch": 0.12712278558338425, "grad_norm": 0.39708471298217773, "learning_rate": 4.8032672970465064e-05, "loss": 4.369, "step": 4162 }, { "epoch": 0.127153329260843, "grad_norm": 0.3979601562023163, "learning_rate": 4.80317400873742e-05, "loss": 4.367, "step": 4163 }, { "epoch": 0.12718387293830177, "grad_norm": 0.3835207223892212, "learning_rate": 4.803080699221826e-05, "loss": 4.3858, "step": 4164 }, { "epoch": 0.12721441661576055, "grad_norm": 0.4027149975299835, "learning_rate": 4.8029873685005836e-05, "loss": 4.4022, "step": 4165 }, { "epoch": 0.1272449602932193, "grad_norm": 0.40205058455467224, "learning_rate": 4.802894016574553e-05, "loss": 4.3479, "step": 4166 }, { "epoch": 0.12727550397067808, "grad_norm": 0.3974112868309021, "learning_rate": 4.802800643444593e-05, "loss": 4.4023, "step": 4167 }, { "epoch": 0.12730604764813683, "grad_norm": 0.39559486508369446, "learning_rate": 4.8027072491115635e-05, "loss": 4.4016, "step": 4168 }, { "epoch": 0.1273365913255956, "grad_norm": 0.41275495290756226, "learning_rate": 4.802613833576324e-05, "loss": 4.399, "step": 4169 }, { "epoch": 0.12736713500305435, "grad_norm": 0.409081369638443, "learning_rate": 4.8025203968397356e-05, "loss": 4.3862, "step": 4170 }, { "epoch": 0.12739767868051313, "grad_norm": 0.39290112257003784, "learning_rate": 4.8024269389026575e-05, "loss": 4.3718, "step": 4171 }, { "epoch": 0.1274282223579719, "grad_norm": 0.39562126994132996, "learning_rate": 4.8023334597659506e-05, "loss": 4.3504, "step": 4172 }, { "epoch": 0.12745876603543066, "grad_norm": 0.3940858840942383, "learning_rate": 4.802239959430477e-05, "loss": 4.4429, "step": 4173 }, { "epoch": 0.12748930971288944, "grad_norm": 0.3992544710636139, "learning_rate": 4.802146437897095e-05, "loss": 4.361, "step": 4174 }, { "epoch": 0.1275198533903482, "grad_norm": 0.4083586633205414, "learning_rate": 4.8020528951666685e-05, "loss": 4.3008, "step": 4175 }, { "epoch": 0.12755039706780696, "grad_norm": 0.3900088667869568, "learning_rate": 4.801959331240057e-05, "loss": 4.3396, "step": 4176 }, { "epoch": 0.12758094074526574, "grad_norm": 0.3999406397342682, "learning_rate": 4.8018657461181214e-05, "loss": 4.3288, "step": 4177 }, { "epoch": 0.1276114844227245, "grad_norm": 0.4127475917339325, "learning_rate": 4.801772139801725e-05, "loss": 4.3748, "step": 4178 }, { "epoch": 0.12764202810018327, "grad_norm": 0.39736515283584595, "learning_rate": 4.80167851229173e-05, "loss": 4.2615, "step": 4179 }, { "epoch": 0.12767257177764202, "grad_norm": 0.39829444885253906, "learning_rate": 4.801584863588996e-05, "loss": 4.4961, "step": 4180 }, { "epoch": 0.1277031154551008, "grad_norm": 0.4040132462978363, "learning_rate": 4.801491193694387e-05, "loss": 4.4552, "step": 4181 }, { "epoch": 0.12773365913255957, "grad_norm": 0.3902493119239807, "learning_rate": 4.801397502608766e-05, "loss": 4.3717, "step": 4182 }, { "epoch": 0.12776420281001832, "grad_norm": 0.3894939720630646, "learning_rate": 4.801303790332995e-05, "loss": 4.4901, "step": 4183 }, { "epoch": 0.1277947464874771, "grad_norm": 0.41084930300712585, "learning_rate": 4.801210056867936e-05, "loss": 4.4056, "step": 4184 }, { "epoch": 0.12782529016493585, "grad_norm": 0.39688169956207275, "learning_rate": 4.8011163022144535e-05, "loss": 4.3661, "step": 4185 }, { "epoch": 0.12785583384239463, "grad_norm": 0.40948039293289185, "learning_rate": 4.80102252637341e-05, "loss": 4.4786, "step": 4186 }, { "epoch": 0.12788637751985338, "grad_norm": 0.4004736542701721, "learning_rate": 4.8009287293456685e-05, "loss": 4.436, "step": 4187 }, { "epoch": 0.12791692119731216, "grad_norm": 0.39700815081596375, "learning_rate": 4.800834911132094e-05, "loss": 4.3113, "step": 4188 }, { "epoch": 0.12794746487477093, "grad_norm": 0.38389459252357483, "learning_rate": 4.800741071733549e-05, "loss": 4.3985, "step": 4189 }, { "epoch": 0.12797800855222968, "grad_norm": 0.399261474609375, "learning_rate": 4.800647211150898e-05, "loss": 4.4712, "step": 4190 }, { "epoch": 0.12800855222968846, "grad_norm": 0.39557066559791565, "learning_rate": 4.800553329385005e-05, "loss": 4.3329, "step": 4191 }, { "epoch": 0.1280390959071472, "grad_norm": 0.39928877353668213, "learning_rate": 4.800459426436735e-05, "loss": 4.3833, "step": 4192 }, { "epoch": 0.128069639584606, "grad_norm": 0.3992801010608673, "learning_rate": 4.8003655023069524e-05, "loss": 4.4952, "step": 4193 }, { "epoch": 0.12810018326206477, "grad_norm": 0.3880499005317688, "learning_rate": 4.800271556996522e-05, "loss": 4.4552, "step": 4194 }, { "epoch": 0.12813072693952351, "grad_norm": 0.38575249910354614, "learning_rate": 4.800177590506308e-05, "loss": 4.3226, "step": 4195 }, { "epoch": 0.1281612706169823, "grad_norm": 0.3918849229812622, "learning_rate": 4.8000836028371777e-05, "loss": 4.4527, "step": 4196 }, { "epoch": 0.12819181429444104, "grad_norm": 0.38205575942993164, "learning_rate": 4.799989593989994e-05, "loss": 4.3756, "step": 4197 }, { "epoch": 0.12822235797189982, "grad_norm": 0.38486534357070923, "learning_rate": 4.799895563965623e-05, "loss": 4.4371, "step": 4198 }, { "epoch": 0.12825290164935857, "grad_norm": 0.39116495847702026, "learning_rate": 4.799801512764932e-05, "loss": 4.5275, "step": 4199 }, { "epoch": 0.12828344532681735, "grad_norm": 0.39974409341812134, "learning_rate": 4.799707440388786e-05, "loss": 4.4134, "step": 4200 }, { "epoch": 0.12831398900427612, "grad_norm": 0.39815810322761536, "learning_rate": 4.799613346838051e-05, "loss": 4.3924, "step": 4201 }, { "epoch": 0.12834453268173487, "grad_norm": 0.3934197723865509, "learning_rate": 4.799519232113594e-05, "loss": 4.4424, "step": 4202 }, { "epoch": 0.12837507635919365, "grad_norm": 0.39766669273376465, "learning_rate": 4.79942509621628e-05, "loss": 4.4302, "step": 4203 }, { "epoch": 0.1284056200366524, "grad_norm": 0.40869608521461487, "learning_rate": 4.799330939146977e-05, "loss": 4.3052, "step": 4204 }, { "epoch": 0.12843616371411118, "grad_norm": 0.3946899175643921, "learning_rate": 4.7992367609065534e-05, "loss": 4.4568, "step": 4205 }, { "epoch": 0.12846670739156996, "grad_norm": 0.39906972646713257, "learning_rate": 4.799142561495874e-05, "loss": 4.4879, "step": 4206 }, { "epoch": 0.1284972510690287, "grad_norm": 0.39394503831863403, "learning_rate": 4.799048340915807e-05, "loss": 4.3879, "step": 4207 }, { "epoch": 0.12852779474648748, "grad_norm": 0.41498133540153503, "learning_rate": 4.798954099167219e-05, "loss": 4.3943, "step": 4208 }, { "epoch": 0.12855833842394623, "grad_norm": 0.3874449133872986, "learning_rate": 4.79885983625098e-05, "loss": 4.4131, "step": 4209 }, { "epoch": 0.128588882101405, "grad_norm": 0.39751213788986206, "learning_rate": 4.7987655521679554e-05, "loss": 4.3827, "step": 4210 }, { "epoch": 0.1286194257788638, "grad_norm": 0.3916889429092407, "learning_rate": 4.798671246919015e-05, "loss": 4.4396, "step": 4211 }, { "epoch": 0.12864996945632254, "grad_norm": 0.3941115736961365, "learning_rate": 4.7985769205050264e-05, "loss": 4.392, "step": 4212 }, { "epoch": 0.12868051313378132, "grad_norm": 0.3929364085197449, "learning_rate": 4.798482572926858e-05, "loss": 4.3989, "step": 4213 }, { "epoch": 0.12871105681124007, "grad_norm": 0.4119430184364319, "learning_rate": 4.798388204185379e-05, "loss": 4.4561, "step": 4214 }, { "epoch": 0.12874160048869884, "grad_norm": 0.39827391505241394, "learning_rate": 4.798293814281458e-05, "loss": 4.4241, "step": 4215 }, { "epoch": 0.1287721441661576, "grad_norm": 0.3836576044559479, "learning_rate": 4.798199403215965e-05, "loss": 4.4329, "step": 4216 }, { "epoch": 0.12880268784361637, "grad_norm": 0.3886201083660126, "learning_rate": 4.798104970989768e-05, "loss": 4.3686, "step": 4217 }, { "epoch": 0.12883323152107515, "grad_norm": 0.3939023017883301, "learning_rate": 4.798010517603736e-05, "loss": 4.4348, "step": 4218 }, { "epoch": 0.1288637751985339, "grad_norm": 0.4003939926624298, "learning_rate": 4.797916043058741e-05, "loss": 4.3825, "step": 4219 }, { "epoch": 0.12889431887599268, "grad_norm": 0.39109164476394653, "learning_rate": 4.797821547355651e-05, "loss": 4.5241, "step": 4220 }, { "epoch": 0.12892486255345142, "grad_norm": 0.3894606828689575, "learning_rate": 4.797727030495336e-05, "loss": 4.414, "step": 4221 }, { "epoch": 0.1289554062309102, "grad_norm": 0.4101135730743408, "learning_rate": 4.797632492478668e-05, "loss": 4.4391, "step": 4222 }, { "epoch": 0.12898594990836898, "grad_norm": 0.4048219919204712, "learning_rate": 4.797537933306515e-05, "loss": 4.365, "step": 4223 }, { "epoch": 0.12901649358582773, "grad_norm": 0.39232704043388367, "learning_rate": 4.79744335297975e-05, "loss": 4.3854, "step": 4224 }, { "epoch": 0.1290470372632865, "grad_norm": 0.4296853840351105, "learning_rate": 4.797348751499243e-05, "loss": 4.34, "step": 4225 }, { "epoch": 0.12907758094074526, "grad_norm": 0.3912959396839142, "learning_rate": 4.797254128865864e-05, "loss": 4.4228, "step": 4226 }, { "epoch": 0.12910812461820403, "grad_norm": 0.40741753578186035, "learning_rate": 4.7971594850804856e-05, "loss": 4.4837, "step": 4227 }, { "epoch": 0.12913866829566278, "grad_norm": 0.39768552780151367, "learning_rate": 4.7970648201439786e-05, "loss": 4.4373, "step": 4228 }, { "epoch": 0.12916921197312156, "grad_norm": 0.3925035893917084, "learning_rate": 4.7969701340572146e-05, "loss": 4.428, "step": 4229 }, { "epoch": 0.12919975565058034, "grad_norm": 0.3983475863933563, "learning_rate": 4.796875426821066e-05, "loss": 4.4229, "step": 4230 }, { "epoch": 0.1292302993280391, "grad_norm": 0.3856567442417145, "learning_rate": 4.796780698436404e-05, "loss": 4.4422, "step": 4231 }, { "epoch": 0.12926084300549787, "grad_norm": 0.3920132517814636, "learning_rate": 4.7966859489041016e-05, "loss": 4.3606, "step": 4232 }, { "epoch": 0.12929138668295662, "grad_norm": 0.3983233571052551, "learning_rate": 4.7965911782250307e-05, "loss": 4.4555, "step": 4233 }, { "epoch": 0.1293219303604154, "grad_norm": 0.39760398864746094, "learning_rate": 4.7964963864000634e-05, "loss": 4.5595, "step": 4234 }, { "epoch": 0.12935247403787417, "grad_norm": 0.42933347821235657, "learning_rate": 4.796401573430074e-05, "loss": 4.3621, "step": 4235 }, { "epoch": 0.12938301771533292, "grad_norm": 0.39162036776542664, "learning_rate": 4.7963067393159346e-05, "loss": 4.4239, "step": 4236 }, { "epoch": 0.1294135613927917, "grad_norm": 0.3979049324989319, "learning_rate": 4.796211884058518e-05, "loss": 4.2858, "step": 4237 }, { "epoch": 0.12944410507025045, "grad_norm": 0.38956964015960693, "learning_rate": 4.796117007658698e-05, "loss": 4.4031, "step": 4238 }, { "epoch": 0.12947464874770923, "grad_norm": 0.38630780577659607, "learning_rate": 4.7960221101173484e-05, "loss": 4.4324, "step": 4239 }, { "epoch": 0.129505192425168, "grad_norm": 0.39065396785736084, "learning_rate": 4.795927191435342e-05, "loss": 4.3744, "step": 4240 }, { "epoch": 0.12953573610262675, "grad_norm": 0.39237359166145325, "learning_rate": 4.795832251613555e-05, "loss": 4.4522, "step": 4241 }, { "epoch": 0.12956627978008553, "grad_norm": 0.40329477190971375, "learning_rate": 4.795737290652859e-05, "loss": 4.4007, "step": 4242 }, { "epoch": 0.12959682345754428, "grad_norm": 0.38693681359291077, "learning_rate": 4.795642308554129e-05, "loss": 4.2887, "step": 4243 }, { "epoch": 0.12962736713500306, "grad_norm": 0.3709688186645508, "learning_rate": 4.795547305318241e-05, "loss": 4.3893, "step": 4244 }, { "epoch": 0.1296579108124618, "grad_norm": 0.4058088958263397, "learning_rate": 4.795452280946068e-05, "loss": 4.4276, "step": 4245 }, { "epoch": 0.12968845448992058, "grad_norm": 0.38559913635253906, "learning_rate": 4.7953572354384854e-05, "loss": 4.3891, "step": 4246 }, { "epoch": 0.12971899816737936, "grad_norm": 0.3793109953403473, "learning_rate": 4.795262168796369e-05, "loss": 4.3914, "step": 4247 }, { "epoch": 0.1297495418448381, "grad_norm": 0.3856565058231354, "learning_rate": 4.795167081020595e-05, "loss": 4.3702, "step": 4248 }, { "epoch": 0.1297800855222969, "grad_norm": 0.39248889684677124, "learning_rate": 4.795071972112036e-05, "loss": 4.381, "step": 4249 }, { "epoch": 0.12981062919975564, "grad_norm": 0.37815210223197937, "learning_rate": 4.7949768420715693e-05, "loss": 4.3268, "step": 4250 }, { "epoch": 0.12984117287721442, "grad_norm": 0.3952866494655609, "learning_rate": 4.794881690900071e-05, "loss": 4.4007, "step": 4251 }, { "epoch": 0.1298717165546732, "grad_norm": 0.3884982466697693, "learning_rate": 4.794786518598418e-05, "loss": 4.3972, "step": 4252 }, { "epoch": 0.12990226023213194, "grad_norm": 0.40473178029060364, "learning_rate": 4.794691325167485e-05, "loss": 4.3014, "step": 4253 }, { "epoch": 0.12993280390959072, "grad_norm": 0.4026556611061096, "learning_rate": 4.7945961106081496e-05, "loss": 4.4718, "step": 4254 }, { "epoch": 0.12996334758704947, "grad_norm": 0.3905491828918457, "learning_rate": 4.794500874921287e-05, "loss": 4.4457, "step": 4255 }, { "epoch": 0.12999389126450825, "grad_norm": 0.40285661816596985, "learning_rate": 4.794405618107776e-05, "loss": 4.4262, "step": 4256 }, { "epoch": 0.13002443494196703, "grad_norm": 0.39280471205711365, "learning_rate": 4.7943103401684924e-05, "loss": 4.4517, "step": 4257 }, { "epoch": 0.13005497861942578, "grad_norm": 0.38711443543434143, "learning_rate": 4.794215041104314e-05, "loss": 4.3845, "step": 4258 }, { "epoch": 0.13008552229688455, "grad_norm": 0.3900642693042755, "learning_rate": 4.794119720916118e-05, "loss": 4.4019, "step": 4259 }, { "epoch": 0.1301160659743433, "grad_norm": 0.3858259916305542, "learning_rate": 4.794024379604783e-05, "loss": 4.4182, "step": 4260 }, { "epoch": 0.13014660965180208, "grad_norm": 0.38149333000183105, "learning_rate": 4.793929017171186e-05, "loss": 4.4083, "step": 4261 }, { "epoch": 0.13017715332926083, "grad_norm": 0.38215136528015137, "learning_rate": 4.793833633616204e-05, "loss": 4.394, "step": 4262 }, { "epoch": 0.1302076970067196, "grad_norm": 0.402582585811615, "learning_rate": 4.793738228940717e-05, "loss": 4.4416, "step": 4263 }, { "epoch": 0.13023824068417839, "grad_norm": 0.3860693871974945, "learning_rate": 4.7936428031456026e-05, "loss": 4.4703, "step": 4264 }, { "epoch": 0.13026878436163714, "grad_norm": 0.387622207403183, "learning_rate": 4.79354735623174e-05, "loss": 4.4155, "step": 4265 }, { "epoch": 0.1302993280390959, "grad_norm": 0.38928791880607605, "learning_rate": 4.7934518882000076e-05, "loss": 4.4579, "step": 4266 }, { "epoch": 0.13032987171655466, "grad_norm": 0.409189909696579, "learning_rate": 4.7933563990512844e-05, "loss": 4.4305, "step": 4267 }, { "epoch": 0.13036041539401344, "grad_norm": 0.3899134397506714, "learning_rate": 4.793260888786449e-05, "loss": 4.4338, "step": 4268 }, { "epoch": 0.13039095907147222, "grad_norm": 0.36506161093711853, "learning_rate": 4.7931653574063826e-05, "loss": 4.4329, "step": 4269 }, { "epoch": 0.13042150274893097, "grad_norm": 0.40512508153915405, "learning_rate": 4.793069804911963e-05, "loss": 4.3937, "step": 4270 }, { "epoch": 0.13045204642638975, "grad_norm": 0.3992270529270172, "learning_rate": 4.7929742313040715e-05, "loss": 4.3904, "step": 4271 }, { "epoch": 0.1304825901038485, "grad_norm": 0.395384281873703, "learning_rate": 4.7928786365835864e-05, "loss": 4.3897, "step": 4272 }, { "epoch": 0.13051313378130727, "grad_norm": 0.39547571539878845, "learning_rate": 4.792783020751389e-05, "loss": 4.3905, "step": 4273 }, { "epoch": 0.13054367745876602, "grad_norm": 0.3939003348350525, "learning_rate": 4.79268738380836e-05, "loss": 4.4242, "step": 4274 }, { "epoch": 0.1305742211362248, "grad_norm": 0.3830110430717468, "learning_rate": 4.792591725755379e-05, "loss": 4.3648, "step": 4275 }, { "epoch": 0.13060476481368358, "grad_norm": 0.38387376070022583, "learning_rate": 4.792496046593328e-05, "loss": 4.4195, "step": 4276 }, { "epoch": 0.13063530849114233, "grad_norm": 0.3846586346626282, "learning_rate": 4.7924003463230866e-05, "loss": 4.3243, "step": 4277 }, { "epoch": 0.1306658521686011, "grad_norm": 0.40117982029914856, "learning_rate": 4.7923046249455365e-05, "loss": 4.3688, "step": 4278 }, { "epoch": 0.13069639584605985, "grad_norm": 0.38909921050071716, "learning_rate": 4.79220888246156e-05, "loss": 4.3701, "step": 4279 }, { "epoch": 0.13072693952351863, "grad_norm": 0.3986440896987915, "learning_rate": 4.7921131188720366e-05, "loss": 4.4509, "step": 4280 }, { "epoch": 0.1307574832009774, "grad_norm": 0.3916711211204529, "learning_rate": 4.7920173341778494e-05, "loss": 4.3922, "step": 4281 }, { "epoch": 0.13078802687843616, "grad_norm": 0.3922314941883087, "learning_rate": 4.791921528379881e-05, "loss": 4.4296, "step": 4282 }, { "epoch": 0.13081857055589494, "grad_norm": 0.3802199959754944, "learning_rate": 4.791825701479012e-05, "loss": 4.3411, "step": 4283 }, { "epoch": 0.13084911423335369, "grad_norm": 0.39764565229415894, "learning_rate": 4.791729853476126e-05, "loss": 4.3907, "step": 4284 }, { "epoch": 0.13087965791081246, "grad_norm": 0.3861972987651825, "learning_rate": 4.7916339843721036e-05, "loss": 4.4462, "step": 4285 }, { "epoch": 0.13091020158827124, "grad_norm": 0.3951597809791565, "learning_rate": 4.79153809416783e-05, "loss": 4.4224, "step": 4286 }, { "epoch": 0.13094074526573, "grad_norm": 0.4013647437095642, "learning_rate": 4.791442182864187e-05, "loss": 4.4726, "step": 4287 }, { "epoch": 0.13097128894318877, "grad_norm": 0.39291641116142273, "learning_rate": 4.7913462504620574e-05, "loss": 4.4402, "step": 4288 }, { "epoch": 0.13100183262064752, "grad_norm": 0.3883773386478424, "learning_rate": 4.791250296962325e-05, "loss": 4.4139, "step": 4289 }, { "epoch": 0.1310323762981063, "grad_norm": 0.40286263823509216, "learning_rate": 4.7911543223658726e-05, "loss": 4.2851, "step": 4290 }, { "epoch": 0.13106291997556505, "grad_norm": 0.39242589473724365, "learning_rate": 4.791058326673585e-05, "loss": 4.357, "step": 4291 }, { "epoch": 0.13109346365302382, "grad_norm": 0.39207327365875244, "learning_rate": 4.790962309886345e-05, "loss": 4.4539, "step": 4292 }, { "epoch": 0.1311240073304826, "grad_norm": 0.375204473733902, "learning_rate": 4.7908662720050376e-05, "loss": 4.4064, "step": 4293 }, { "epoch": 0.13115455100794135, "grad_norm": 0.39012134075164795, "learning_rate": 4.790770213030546e-05, "loss": 4.4153, "step": 4294 }, { "epoch": 0.13118509468540013, "grad_norm": 0.4018087387084961, "learning_rate": 4.790674132963755e-05, "loss": 4.41, "step": 4295 }, { "epoch": 0.13121563836285888, "grad_norm": 0.3814443349838257, "learning_rate": 4.79057803180555e-05, "loss": 4.4071, "step": 4296 }, { "epoch": 0.13124618204031765, "grad_norm": 0.38027116656303406, "learning_rate": 4.7904819095568154e-05, "loss": 4.4425, "step": 4297 }, { "epoch": 0.13127672571777643, "grad_norm": 0.383089542388916, "learning_rate": 4.790385766218436e-05, "loss": 4.4376, "step": 4298 }, { "epoch": 0.13130726939523518, "grad_norm": 0.3896554112434387, "learning_rate": 4.790289601791298e-05, "loss": 4.3539, "step": 4299 }, { "epoch": 0.13133781307269396, "grad_norm": 0.3995117247104645, "learning_rate": 4.790193416276285e-05, "loss": 4.3579, "step": 4300 }, { "epoch": 0.1313683567501527, "grad_norm": 0.3872140645980835, "learning_rate": 4.790097209674285e-05, "loss": 4.4271, "step": 4301 }, { "epoch": 0.1313989004276115, "grad_norm": 0.40110066533088684, "learning_rate": 4.7900009819861814e-05, "loss": 4.5027, "step": 4302 }, { "epoch": 0.13142944410507024, "grad_norm": 0.3888181149959564, "learning_rate": 4.789904733212862e-05, "loss": 4.436, "step": 4303 }, { "epoch": 0.13145998778252901, "grad_norm": 0.4020240902900696, "learning_rate": 4.7898084633552114e-05, "loss": 4.3706, "step": 4304 }, { "epoch": 0.1314905314599878, "grad_norm": 0.39191851019859314, "learning_rate": 4.789712172414118e-05, "loss": 4.365, "step": 4305 }, { "epoch": 0.13152107513744654, "grad_norm": 0.4084716737270355, "learning_rate": 4.789615860390467e-05, "loss": 4.4047, "step": 4306 }, { "epoch": 0.13155161881490532, "grad_norm": 0.3789575397968292, "learning_rate": 4.789519527285146e-05, "loss": 4.3864, "step": 4307 }, { "epoch": 0.13158216249236407, "grad_norm": 0.386673241853714, "learning_rate": 4.78942317309904e-05, "loss": 4.3765, "step": 4308 }, { "epoch": 0.13161270616982285, "grad_norm": 0.41173577308654785, "learning_rate": 4.7893267978330394e-05, "loss": 4.4648, "step": 4309 }, { "epoch": 0.13164324984728162, "grad_norm": 0.39717045426368713, "learning_rate": 4.7892304014880295e-05, "loss": 4.3675, "step": 4310 }, { "epoch": 0.13167379352474037, "grad_norm": 0.39349931478500366, "learning_rate": 4.789133984064899e-05, "loss": 4.3462, "step": 4311 }, { "epoch": 0.13170433720219915, "grad_norm": 0.39035099744796753, "learning_rate": 4.789037545564533e-05, "loss": 4.3488, "step": 4312 }, { "epoch": 0.1317348808796579, "grad_norm": 0.4047548174858093, "learning_rate": 4.7889410859878226e-05, "loss": 4.3909, "step": 4313 }, { "epoch": 0.13176542455711668, "grad_norm": 0.39453792572021484, "learning_rate": 4.788844605335655e-05, "loss": 4.3932, "step": 4314 }, { "epoch": 0.13179596823457546, "grad_norm": 0.3938715159893036, "learning_rate": 4.7887481036089174e-05, "loss": 4.3769, "step": 4315 }, { "epoch": 0.1318265119120342, "grad_norm": 0.39128226041793823, "learning_rate": 4.788651580808501e-05, "loss": 4.4222, "step": 4316 }, { "epoch": 0.13185705558949298, "grad_norm": 0.3968285918235779, "learning_rate": 4.788555036935291e-05, "loss": 4.4249, "step": 4317 }, { "epoch": 0.13188759926695173, "grad_norm": 0.39440402388572693, "learning_rate": 4.7884584719901794e-05, "loss": 4.4296, "step": 4318 }, { "epoch": 0.1319181429444105, "grad_norm": 0.39483219385147095, "learning_rate": 4.788361885974053e-05, "loss": 4.4437, "step": 4319 }, { "epoch": 0.13194868662186926, "grad_norm": 0.3858671486377716, "learning_rate": 4.788265278887803e-05, "loss": 4.3179, "step": 4320 }, { "epoch": 0.13197923029932804, "grad_norm": 0.3895260691642761, "learning_rate": 4.7881686507323175e-05, "loss": 4.4091, "step": 4321 }, { "epoch": 0.13200977397678682, "grad_norm": 0.40261387825012207, "learning_rate": 4.788072001508487e-05, "loss": 4.3286, "step": 4322 }, { "epoch": 0.13204031765424556, "grad_norm": 0.3900909721851349, "learning_rate": 4.787975331217201e-05, "loss": 4.3849, "step": 4323 }, { "epoch": 0.13207086133170434, "grad_norm": 0.38082563877105713, "learning_rate": 4.787878639859349e-05, "loss": 4.3959, "step": 4324 }, { "epoch": 0.1321014050091631, "grad_norm": 0.38531601428985596, "learning_rate": 4.787781927435824e-05, "loss": 4.4483, "step": 4325 }, { "epoch": 0.13213194868662187, "grad_norm": 0.3953334093093872, "learning_rate": 4.787685193947513e-05, "loss": 4.3744, "step": 4326 }, { "epoch": 0.13216249236408065, "grad_norm": 0.38356173038482666, "learning_rate": 4.787588439395308e-05, "loss": 4.4265, "step": 4327 }, { "epoch": 0.1321930360415394, "grad_norm": 0.3991902768611908, "learning_rate": 4.787491663780101e-05, "loss": 4.515, "step": 4328 }, { "epoch": 0.13222357971899817, "grad_norm": 0.3959284722805023, "learning_rate": 4.787394867102782e-05, "loss": 4.4548, "step": 4329 }, { "epoch": 0.13225412339645692, "grad_norm": 0.37914609909057617, "learning_rate": 4.7872980493642425e-05, "loss": 4.2828, "step": 4330 }, { "epoch": 0.1322846670739157, "grad_norm": 0.3884296417236328, "learning_rate": 4.787201210565374e-05, "loss": 4.3697, "step": 4331 }, { "epoch": 0.13231521075137448, "grad_norm": 0.3997547924518585, "learning_rate": 4.787104350707067e-05, "loss": 4.4014, "step": 4332 }, { "epoch": 0.13234575442883323, "grad_norm": 0.4005641043186188, "learning_rate": 4.787007469790215e-05, "loss": 4.3842, "step": 4333 }, { "epoch": 0.132376298106292, "grad_norm": 0.38496339321136475, "learning_rate": 4.7869105678157094e-05, "loss": 4.3955, "step": 4334 }, { "epoch": 0.13240684178375076, "grad_norm": 0.38848593831062317, "learning_rate": 4.786813644784443e-05, "loss": 4.3962, "step": 4335 }, { "epoch": 0.13243738546120953, "grad_norm": 0.40062305331230164, "learning_rate": 4.7867167006973064e-05, "loss": 4.4147, "step": 4336 }, { "epoch": 0.13246792913866828, "grad_norm": 0.3970062732696533, "learning_rate": 4.786619735555194e-05, "loss": 4.4523, "step": 4337 }, { "epoch": 0.13249847281612706, "grad_norm": 0.3954664468765259, "learning_rate": 4.7865227493589975e-05, "loss": 4.3333, "step": 4338 }, { "epoch": 0.13252901649358584, "grad_norm": 0.39783763885498047, "learning_rate": 4.786425742109611e-05, "loss": 4.372, "step": 4339 }, { "epoch": 0.1325595601710446, "grad_norm": 0.40295881032943726, "learning_rate": 4.786328713807927e-05, "loss": 4.3991, "step": 4340 }, { "epoch": 0.13259010384850337, "grad_norm": 0.3935903310775757, "learning_rate": 4.786231664454839e-05, "loss": 4.5236, "step": 4341 }, { "epoch": 0.13262064752596212, "grad_norm": 0.3789663314819336, "learning_rate": 4.786134594051241e-05, "loss": 4.4025, "step": 4342 }, { "epoch": 0.1326511912034209, "grad_norm": 0.4018377661705017, "learning_rate": 4.786037502598026e-05, "loss": 4.362, "step": 4343 }, { "epoch": 0.13268173488087967, "grad_norm": 0.39861154556274414, "learning_rate": 4.785940390096088e-05, "loss": 4.4573, "step": 4344 }, { "epoch": 0.13271227855833842, "grad_norm": 0.396056592464447, "learning_rate": 4.785843256546322e-05, "loss": 4.406, "step": 4345 }, { "epoch": 0.1327428222357972, "grad_norm": 0.4000599980354309, "learning_rate": 4.785746101949622e-05, "loss": 4.395, "step": 4346 }, { "epoch": 0.13277336591325595, "grad_norm": 0.39028987288475037, "learning_rate": 4.785648926306882e-05, "loss": 4.3387, "step": 4347 }, { "epoch": 0.13280390959071472, "grad_norm": 0.3990640938282013, "learning_rate": 4.7855517296189975e-05, "loss": 4.4375, "step": 4348 }, { "epoch": 0.13283445326817347, "grad_norm": 0.393686443567276, "learning_rate": 4.785454511886863e-05, "loss": 4.4126, "step": 4349 }, { "epoch": 0.13286499694563225, "grad_norm": 0.39123469591140747, "learning_rate": 4.785357273111374e-05, "loss": 4.368, "step": 4350 }, { "epoch": 0.13289554062309103, "grad_norm": 0.3822322189807892, "learning_rate": 4.785260013293424e-05, "loss": 4.4024, "step": 4351 }, { "epoch": 0.13292608430054978, "grad_norm": 0.40327489376068115, "learning_rate": 4.785162732433912e-05, "loss": 4.438, "step": 4352 }, { "epoch": 0.13295662797800856, "grad_norm": 0.3943142294883728, "learning_rate": 4.785065430533731e-05, "loss": 4.3514, "step": 4353 }, { "epoch": 0.1329871716554673, "grad_norm": 0.4025326073169708, "learning_rate": 4.784968107593778e-05, "loss": 4.4076, "step": 4354 }, { "epoch": 0.13301771533292608, "grad_norm": 0.37442997097969055, "learning_rate": 4.7848707636149486e-05, "loss": 4.3733, "step": 4355 }, { "epoch": 0.13304825901038486, "grad_norm": 0.38617995381355286, "learning_rate": 4.7847733985981394e-05, "loss": 4.3778, "step": 4356 }, { "epoch": 0.1330788026878436, "grad_norm": 0.40143024921417236, "learning_rate": 4.784676012544247e-05, "loss": 4.4121, "step": 4357 }, { "epoch": 0.1331093463653024, "grad_norm": 0.4157804846763611, "learning_rate": 4.7845786054541675e-05, "loss": 4.3761, "step": 4358 }, { "epoch": 0.13313989004276114, "grad_norm": 0.3819216787815094, "learning_rate": 4.784481177328799e-05, "loss": 4.4633, "step": 4359 }, { "epoch": 0.13317043372021992, "grad_norm": 0.3913758099079132, "learning_rate": 4.784383728169037e-05, "loss": 4.3441, "step": 4360 }, { "epoch": 0.1332009773976787, "grad_norm": 0.4041129946708679, "learning_rate": 4.78428625797578e-05, "loss": 4.4099, "step": 4361 }, { "epoch": 0.13323152107513744, "grad_norm": 0.3923889100551605, "learning_rate": 4.784188766749924e-05, "loss": 4.4188, "step": 4362 }, { "epoch": 0.13326206475259622, "grad_norm": 0.40037307143211365, "learning_rate": 4.7840912544923675e-05, "loss": 4.2953, "step": 4363 }, { "epoch": 0.13329260843005497, "grad_norm": 0.3977792263031006, "learning_rate": 4.78399372120401e-05, "loss": 4.4252, "step": 4364 }, { "epoch": 0.13332315210751375, "grad_norm": 0.3919796645641327, "learning_rate": 4.783896166885747e-05, "loss": 4.374, "step": 4365 }, { "epoch": 0.1333536957849725, "grad_norm": 0.38975217938423157, "learning_rate": 4.7837985915384776e-05, "loss": 4.4302, "step": 4366 }, { "epoch": 0.13338423946243128, "grad_norm": 0.40845200419425964, "learning_rate": 4.783700995163101e-05, "loss": 4.414, "step": 4367 }, { "epoch": 0.13341478313989005, "grad_norm": 0.3842988610267639, "learning_rate": 4.783603377760515e-05, "loss": 4.3328, "step": 4368 }, { "epoch": 0.1334453268173488, "grad_norm": 0.4005535840988159, "learning_rate": 4.783505739331618e-05, "loss": 4.4077, "step": 4369 }, { "epoch": 0.13347587049480758, "grad_norm": 0.4030493497848511, "learning_rate": 4.78340807987731e-05, "loss": 4.4185, "step": 4370 }, { "epoch": 0.13350641417226633, "grad_norm": 0.3907780647277832, "learning_rate": 4.783310399398489e-05, "loss": 4.4175, "step": 4371 }, { "epoch": 0.1335369578497251, "grad_norm": 0.39608293771743774, "learning_rate": 4.783212697896057e-05, "loss": 4.3067, "step": 4372 }, { "epoch": 0.13356750152718389, "grad_norm": 0.39615434408187866, "learning_rate": 4.7831149753709104e-05, "loss": 4.4054, "step": 4373 }, { "epoch": 0.13359804520464263, "grad_norm": 0.40541088581085205, "learning_rate": 4.7830172318239506e-05, "loss": 4.3698, "step": 4374 }, { "epoch": 0.1336285888821014, "grad_norm": 0.39351531863212585, "learning_rate": 4.782919467256077e-05, "loss": 4.3908, "step": 4375 }, { "epoch": 0.13365913255956016, "grad_norm": 0.3879176080226898, "learning_rate": 4.7828216816681915e-05, "loss": 4.334, "step": 4376 }, { "epoch": 0.13368967623701894, "grad_norm": 0.3986053764820099, "learning_rate": 4.782723875061192e-05, "loss": 4.446, "step": 4377 }, { "epoch": 0.1337202199144777, "grad_norm": 0.3941362798213959, "learning_rate": 4.78262604743598e-05, "loss": 4.3951, "step": 4378 }, { "epoch": 0.13375076359193647, "grad_norm": 0.38912898302078247, "learning_rate": 4.7825281987934566e-05, "loss": 4.3526, "step": 4379 }, { "epoch": 0.13378130726939524, "grad_norm": 0.38870498538017273, "learning_rate": 4.782430329134523e-05, "loss": 4.3682, "step": 4380 }, { "epoch": 0.133811850946854, "grad_norm": 0.3941443860530853, "learning_rate": 4.7823324384600784e-05, "loss": 4.3588, "step": 4381 }, { "epoch": 0.13384239462431277, "grad_norm": 0.38255444169044495, "learning_rate": 4.782234526771027e-05, "loss": 4.2883, "step": 4382 }, { "epoch": 0.13387293830177152, "grad_norm": 0.3845776915550232, "learning_rate": 4.7821365940682685e-05, "loss": 4.3561, "step": 4383 }, { "epoch": 0.1339034819792303, "grad_norm": 0.38711851835250854, "learning_rate": 4.7820386403527054e-05, "loss": 4.3917, "step": 4384 }, { "epoch": 0.13393402565668908, "grad_norm": 0.38269346952438354, "learning_rate": 4.7819406656252384e-05, "loss": 4.454, "step": 4385 }, { "epoch": 0.13396456933414783, "grad_norm": 0.40406814217567444, "learning_rate": 4.7818426698867715e-05, "loss": 4.3771, "step": 4386 }, { "epoch": 0.1339951130116066, "grad_norm": 0.39957624673843384, "learning_rate": 4.781744653138205e-05, "loss": 4.4139, "step": 4387 }, { "epoch": 0.13402565668906535, "grad_norm": 0.3904498815536499, "learning_rate": 4.7816466153804425e-05, "loss": 4.4262, "step": 4388 }, { "epoch": 0.13405620036652413, "grad_norm": 0.38115277886390686, "learning_rate": 4.781548556614386e-05, "loss": 4.3542, "step": 4389 }, { "epoch": 0.1340867440439829, "grad_norm": 0.3838099539279938, "learning_rate": 4.7814504768409396e-05, "loss": 4.3394, "step": 4390 }, { "epoch": 0.13411728772144166, "grad_norm": 0.3912336528301239, "learning_rate": 4.7813523760610055e-05, "loss": 4.4096, "step": 4391 }, { "epoch": 0.13414783139890044, "grad_norm": 0.3961077630519867, "learning_rate": 4.781254254275487e-05, "loss": 4.4147, "step": 4392 }, { "epoch": 0.13417837507635919, "grad_norm": 0.4084978699684143, "learning_rate": 4.7811561114852885e-05, "loss": 4.3912, "step": 4393 }, { "epoch": 0.13420891875381796, "grad_norm": 0.38336989283561707, "learning_rate": 4.781057947691312e-05, "loss": 4.3909, "step": 4394 }, { "epoch": 0.1342394624312767, "grad_norm": 0.38086894154548645, "learning_rate": 4.7809597628944625e-05, "loss": 4.3563, "step": 4395 }, { "epoch": 0.1342700061087355, "grad_norm": 0.39455997943878174, "learning_rate": 4.780861557095643e-05, "loss": 4.4061, "step": 4396 }, { "epoch": 0.13430054978619427, "grad_norm": 0.3954651653766632, "learning_rate": 4.780763330295759e-05, "loss": 4.4174, "step": 4397 }, { "epoch": 0.13433109346365302, "grad_norm": 0.39154064655303955, "learning_rate": 4.780665082495714e-05, "loss": 4.403, "step": 4398 }, { "epoch": 0.1343616371411118, "grad_norm": 0.3853631317615509, "learning_rate": 4.7805668136964145e-05, "loss": 4.4213, "step": 4399 }, { "epoch": 0.13439218081857054, "grad_norm": 0.3906896114349365, "learning_rate": 4.780468523898762e-05, "loss": 4.4002, "step": 4400 }, { "epoch": 0.13442272449602932, "grad_norm": 0.3846364915370941, "learning_rate": 4.7803702131036644e-05, "loss": 4.4736, "step": 4401 }, { "epoch": 0.1344532681734881, "grad_norm": 0.37783917784690857, "learning_rate": 4.780271881312025e-05, "loss": 4.3071, "step": 4402 }, { "epoch": 0.13448381185094685, "grad_norm": 0.3932502865791321, "learning_rate": 4.780173528524751e-05, "loss": 4.3992, "step": 4403 }, { "epoch": 0.13451435552840563, "grad_norm": 0.3812691867351532, "learning_rate": 4.780075154742746e-05, "loss": 4.416, "step": 4404 }, { "epoch": 0.13454489920586438, "grad_norm": 0.39535024762153625, "learning_rate": 4.7799767599669165e-05, "loss": 4.2676, "step": 4405 }, { "epoch": 0.13457544288332315, "grad_norm": 0.39901483058929443, "learning_rate": 4.779878344198169e-05, "loss": 4.4418, "step": 4406 }, { "epoch": 0.13460598656078193, "grad_norm": 0.38841262459754944, "learning_rate": 4.77977990743741e-05, "loss": 4.4473, "step": 4407 }, { "epoch": 0.13463653023824068, "grad_norm": 0.39807483553886414, "learning_rate": 4.779681449685545e-05, "loss": 4.4217, "step": 4408 }, { "epoch": 0.13466707391569946, "grad_norm": 0.4031272828578949, "learning_rate": 4.77958297094348e-05, "loss": 4.365, "step": 4409 }, { "epoch": 0.1346976175931582, "grad_norm": 0.3870851397514343, "learning_rate": 4.779484471212124e-05, "loss": 4.392, "step": 4410 }, { "epoch": 0.134728161270617, "grad_norm": 0.3936595320701599, "learning_rate": 4.779385950492382e-05, "loss": 4.4087, "step": 4411 }, { "epoch": 0.13475870494807574, "grad_norm": 0.3995029628276825, "learning_rate": 4.779287408785161e-05, "loss": 4.4048, "step": 4412 }, { "epoch": 0.1347892486255345, "grad_norm": 0.4009629189968109, "learning_rate": 4.779188846091369e-05, "loss": 4.4026, "step": 4413 }, { "epoch": 0.1348197923029933, "grad_norm": 0.38877594470977783, "learning_rate": 4.779090262411914e-05, "loss": 4.3219, "step": 4414 }, { "epoch": 0.13485033598045204, "grad_norm": 0.409449964761734, "learning_rate": 4.778991657747702e-05, "loss": 4.3153, "step": 4415 }, { "epoch": 0.13488087965791082, "grad_norm": 0.39451801776885986, "learning_rate": 4.778893032099644e-05, "loss": 4.3518, "step": 4416 }, { "epoch": 0.13491142333536957, "grad_norm": 0.3794185519218445, "learning_rate": 4.778794385468645e-05, "loss": 4.3317, "step": 4417 }, { "epoch": 0.13494196701282835, "grad_norm": 0.4164871573448181, "learning_rate": 4.778695717855614e-05, "loss": 4.4733, "step": 4418 }, { "epoch": 0.13497251069028712, "grad_norm": 0.39689940214157104, "learning_rate": 4.778597029261461e-05, "loss": 4.4825, "step": 4419 }, { "epoch": 0.13500305436774587, "grad_norm": 0.3925870954990387, "learning_rate": 4.7784983196870926e-05, "loss": 4.4142, "step": 4420 }, { "epoch": 0.13503359804520465, "grad_norm": 0.4029066264629364, "learning_rate": 4.7783995891334195e-05, "loss": 4.4469, "step": 4421 }, { "epoch": 0.1350641417226634, "grad_norm": 0.41426417231559753, "learning_rate": 4.778300837601349e-05, "loss": 4.361, "step": 4422 }, { "epoch": 0.13509468540012218, "grad_norm": 0.398754358291626, "learning_rate": 4.7782020650917924e-05, "loss": 4.3932, "step": 4423 }, { "epoch": 0.13512522907758093, "grad_norm": 0.4133014380931854, "learning_rate": 4.778103271605657e-05, "loss": 4.4473, "step": 4424 }, { "epoch": 0.1351557727550397, "grad_norm": 0.402443528175354, "learning_rate": 4.778004457143855e-05, "loss": 4.4202, "step": 4425 }, { "epoch": 0.13518631643249848, "grad_norm": 0.39156290888786316, "learning_rate": 4.777905621707294e-05, "loss": 4.4475, "step": 4426 }, { "epoch": 0.13521686010995723, "grad_norm": 0.3861156702041626, "learning_rate": 4.777806765296884e-05, "loss": 4.3498, "step": 4427 }, { "epoch": 0.135247403787416, "grad_norm": 0.40875986218452454, "learning_rate": 4.777707887913537e-05, "loss": 4.4886, "step": 4428 }, { "epoch": 0.13527794746487476, "grad_norm": 0.39456483721733093, "learning_rate": 4.777608989558162e-05, "loss": 4.3867, "step": 4429 }, { "epoch": 0.13530849114233354, "grad_norm": 0.40548545122146606, "learning_rate": 4.777510070231669e-05, "loss": 4.4701, "step": 4430 }, { "epoch": 0.13533903481979231, "grad_norm": 0.41638413071632385, "learning_rate": 4.777411129934971e-05, "loss": 4.4886, "step": 4431 }, { "epoch": 0.13536957849725106, "grad_norm": 0.4167528748512268, "learning_rate": 4.777312168668978e-05, "loss": 4.4825, "step": 4432 }, { "epoch": 0.13540012217470984, "grad_norm": 0.39208292961120605, "learning_rate": 4.7772131864346004e-05, "loss": 4.4046, "step": 4433 }, { "epoch": 0.1354306658521686, "grad_norm": 0.4223238229751587, "learning_rate": 4.7771141832327506e-05, "loss": 4.3184, "step": 4434 }, { "epoch": 0.13546120952962737, "grad_norm": 0.39094775915145874, "learning_rate": 4.7770151590643384e-05, "loss": 4.4074, "step": 4435 }, { "epoch": 0.13549175320708615, "grad_norm": 0.39277634024620056, "learning_rate": 4.7769161139302784e-05, "loss": 4.4159, "step": 4436 }, { "epoch": 0.1355222968845449, "grad_norm": 0.396670937538147, "learning_rate": 4.776817047831481e-05, "loss": 4.4736, "step": 4437 }, { "epoch": 0.13555284056200367, "grad_norm": 0.3811646103858948, "learning_rate": 4.776717960768858e-05, "loss": 4.3449, "step": 4438 }, { "epoch": 0.13558338423946242, "grad_norm": 0.3865649104118347, "learning_rate": 4.776618852743322e-05, "loss": 4.4667, "step": 4439 }, { "epoch": 0.1356139279169212, "grad_norm": 0.41304534673690796, "learning_rate": 4.776519723755786e-05, "loss": 4.4012, "step": 4440 }, { "epoch": 0.13564447159437995, "grad_norm": 0.3959059715270996, "learning_rate": 4.7764205738071625e-05, "loss": 4.3771, "step": 4441 }, { "epoch": 0.13567501527183873, "grad_norm": 0.3879881799221039, "learning_rate": 4.776321402898364e-05, "loss": 4.4073, "step": 4442 }, { "epoch": 0.1357055589492975, "grad_norm": 0.39104607701301575, "learning_rate": 4.776222211030303e-05, "loss": 4.3875, "step": 4443 }, { "epoch": 0.13573610262675626, "grad_norm": 0.3806493580341339, "learning_rate": 4.776122998203896e-05, "loss": 4.3212, "step": 4444 }, { "epoch": 0.13576664630421503, "grad_norm": 0.39310625195503235, "learning_rate": 4.776023764420053e-05, "loss": 4.4266, "step": 4445 }, { "epoch": 0.13579718998167378, "grad_norm": 0.3872242569923401, "learning_rate": 4.775924509679689e-05, "loss": 4.2766, "step": 4446 }, { "epoch": 0.13582773365913256, "grad_norm": 0.390995055437088, "learning_rate": 4.775825233983718e-05, "loss": 4.3762, "step": 4447 }, { "epoch": 0.13585827733659134, "grad_norm": 0.3887644410133362, "learning_rate": 4.775725937333054e-05, "loss": 4.4439, "step": 4448 }, { "epoch": 0.1358888210140501, "grad_norm": 0.3866826295852661, "learning_rate": 4.775626619728611e-05, "loss": 4.3469, "step": 4449 }, { "epoch": 0.13591936469150886, "grad_norm": 0.3772350251674652, "learning_rate": 4.7755272811713046e-05, "loss": 4.4513, "step": 4450 }, { "epoch": 0.13594990836896761, "grad_norm": 0.3912487030029297, "learning_rate": 4.775427921662048e-05, "loss": 4.3909, "step": 4451 }, { "epoch": 0.1359804520464264, "grad_norm": 0.3837847411632538, "learning_rate": 4.775328541201757e-05, "loss": 4.3925, "step": 4452 }, { "epoch": 0.13601099572388514, "grad_norm": 0.39506447315216064, "learning_rate": 4.775229139791345e-05, "loss": 4.3975, "step": 4453 }, { "epoch": 0.13604153940134392, "grad_norm": 0.39203158020973206, "learning_rate": 4.77512971743173e-05, "loss": 4.2922, "step": 4454 }, { "epoch": 0.1360720830788027, "grad_norm": 0.4005008935928345, "learning_rate": 4.775030274123825e-05, "loss": 4.3117, "step": 4455 }, { "epoch": 0.13610262675626145, "grad_norm": 0.4095291197299957, "learning_rate": 4.7749308098685466e-05, "loss": 4.4797, "step": 4456 }, { "epoch": 0.13613317043372022, "grad_norm": 0.3794209063053131, "learning_rate": 4.774831324666811e-05, "loss": 4.3906, "step": 4457 }, { "epoch": 0.13616371411117897, "grad_norm": 0.3920299708843231, "learning_rate": 4.7747318185195336e-05, "loss": 4.4096, "step": 4458 }, { "epoch": 0.13619425778863775, "grad_norm": 0.40088674426078796, "learning_rate": 4.774632291427631e-05, "loss": 4.4036, "step": 4459 }, { "epoch": 0.13622480146609653, "grad_norm": 0.39521723985671997, "learning_rate": 4.7745327433920185e-05, "loss": 4.426, "step": 4460 }, { "epoch": 0.13625534514355528, "grad_norm": 0.3915633261203766, "learning_rate": 4.7744331744136145e-05, "loss": 4.4249, "step": 4461 }, { "epoch": 0.13628588882101406, "grad_norm": 0.3910757005214691, "learning_rate": 4.7743335844933346e-05, "loss": 4.3374, "step": 4462 }, { "epoch": 0.1363164324984728, "grad_norm": 0.4090193808078766, "learning_rate": 4.774233973632096e-05, "loss": 4.3686, "step": 4463 }, { "epoch": 0.13634697617593158, "grad_norm": 0.39604610204696655, "learning_rate": 4.774134341830816e-05, "loss": 4.3518, "step": 4464 }, { "epoch": 0.13637751985339036, "grad_norm": 0.3833807706832886, "learning_rate": 4.774034689090412e-05, "loss": 4.452, "step": 4465 }, { "epoch": 0.1364080635308491, "grad_norm": 0.39926257729530334, "learning_rate": 4.773935015411801e-05, "loss": 4.4161, "step": 4466 }, { "epoch": 0.1364386072083079, "grad_norm": 0.3723514676094055, "learning_rate": 4.773835320795902e-05, "loss": 4.3366, "step": 4467 }, { "epoch": 0.13646915088576664, "grad_norm": 0.37815356254577637, "learning_rate": 4.773735605243631e-05, "loss": 4.3765, "step": 4468 }, { "epoch": 0.13649969456322542, "grad_norm": 0.40337106585502625, "learning_rate": 4.773635868755908e-05, "loss": 4.3936, "step": 4469 }, { "epoch": 0.13653023824068417, "grad_norm": 0.4135206937789917, "learning_rate": 4.77353611133365e-05, "loss": 4.3474, "step": 4470 }, { "epoch": 0.13656078191814294, "grad_norm": 0.3858663737773895, "learning_rate": 4.7734363329777764e-05, "loss": 4.351, "step": 4471 }, { "epoch": 0.13659132559560172, "grad_norm": 0.38095933198928833, "learning_rate": 4.773336533689206e-05, "loss": 4.4294, "step": 4472 }, { "epoch": 0.13662186927306047, "grad_norm": 0.38878533244132996, "learning_rate": 4.773236713468857e-05, "loss": 4.4092, "step": 4473 }, { "epoch": 0.13665241295051925, "grad_norm": 0.38884180784225464, "learning_rate": 4.7731368723176484e-05, "loss": 4.3559, "step": 4474 }, { "epoch": 0.136682956627978, "grad_norm": 0.3890630900859833, "learning_rate": 4.7730370102365007e-05, "loss": 4.4245, "step": 4475 }, { "epoch": 0.13671350030543677, "grad_norm": 0.3953840136528015, "learning_rate": 4.7729371272263316e-05, "loss": 4.3411, "step": 4476 }, { "epoch": 0.13674404398289555, "grad_norm": 0.40108057856559753, "learning_rate": 4.772837223288062e-05, "loss": 4.4801, "step": 4477 }, { "epoch": 0.1367745876603543, "grad_norm": 0.405934602022171, "learning_rate": 4.772737298422612e-05, "loss": 4.4765, "step": 4478 }, { "epoch": 0.13680513133781308, "grad_norm": 0.3959044814109802, "learning_rate": 4.772637352630901e-05, "loss": 4.3798, "step": 4479 }, { "epoch": 0.13683567501527183, "grad_norm": 0.4152238070964813, "learning_rate": 4.772537385913849e-05, "loss": 4.3892, "step": 4480 }, { "epoch": 0.1368662186927306, "grad_norm": 0.3980310559272766, "learning_rate": 4.772437398272378e-05, "loss": 4.3269, "step": 4481 }, { "epoch": 0.13689676237018938, "grad_norm": 0.3886687755584717, "learning_rate": 4.7723373897074065e-05, "loss": 4.3917, "step": 4482 }, { "epoch": 0.13692730604764813, "grad_norm": 0.3847730755805969, "learning_rate": 4.7722373602198564e-05, "loss": 4.4866, "step": 4483 }, { "epoch": 0.1369578497251069, "grad_norm": 0.39946943521499634, "learning_rate": 4.7721373098106486e-05, "loss": 4.4505, "step": 4484 }, { "epoch": 0.13698839340256566, "grad_norm": 0.3937529921531677, "learning_rate": 4.772037238480704e-05, "loss": 4.4021, "step": 4485 }, { "epoch": 0.13701893708002444, "grad_norm": 0.38632863759994507, "learning_rate": 4.771937146230946e-05, "loss": 4.3475, "step": 4486 }, { "epoch": 0.1370494807574832, "grad_norm": 0.3871079087257385, "learning_rate": 4.771837033062293e-05, "loss": 4.4264, "step": 4487 }, { "epoch": 0.13708002443494197, "grad_norm": 0.38580313324928284, "learning_rate": 4.771736898975669e-05, "loss": 4.348, "step": 4488 }, { "epoch": 0.13711056811240074, "grad_norm": 0.40065422654151917, "learning_rate": 4.7716367439719956e-05, "loss": 4.417, "step": 4489 }, { "epoch": 0.1371411117898595, "grad_norm": 0.38751253485679626, "learning_rate": 4.771536568052194e-05, "loss": 4.4953, "step": 4490 }, { "epoch": 0.13717165546731827, "grad_norm": 0.37778571248054504, "learning_rate": 4.7714363712171875e-05, "loss": 4.437, "step": 4491 }, { "epoch": 0.13720219914477702, "grad_norm": 0.3892535865306854, "learning_rate": 4.7713361534678993e-05, "loss": 4.4078, "step": 4492 }, { "epoch": 0.1372327428222358, "grad_norm": 0.37931060791015625, "learning_rate": 4.77123591480525e-05, "loss": 4.3186, "step": 4493 }, { "epoch": 0.13726328649969458, "grad_norm": 0.39326292276382446, "learning_rate": 4.7711356552301645e-05, "loss": 4.3674, "step": 4494 }, { "epoch": 0.13729383017715333, "grad_norm": 0.3811175227165222, "learning_rate": 4.771035374743566e-05, "loss": 4.4252, "step": 4495 }, { "epoch": 0.1373243738546121, "grad_norm": 0.3882116675376892, "learning_rate": 4.770935073346376e-05, "loss": 4.3917, "step": 4496 }, { "epoch": 0.13735491753207085, "grad_norm": 0.39492493867874146, "learning_rate": 4.77083475103952e-05, "loss": 4.4395, "step": 4497 }, { "epoch": 0.13738546120952963, "grad_norm": 0.37970325350761414, "learning_rate": 4.7707344078239204e-05, "loss": 4.3925, "step": 4498 }, { "epoch": 0.13741600488698838, "grad_norm": 0.4011629521846771, "learning_rate": 4.770634043700502e-05, "loss": 4.4288, "step": 4499 }, { "epoch": 0.13744654856444716, "grad_norm": 0.381049245595932, "learning_rate": 4.770533658670189e-05, "loss": 4.3744, "step": 4500 }, { "epoch": 0.13747709224190593, "grad_norm": 0.39041760563850403, "learning_rate": 4.770433252733904e-05, "loss": 4.4011, "step": 4501 }, { "epoch": 0.13750763591936468, "grad_norm": 0.3921353816986084, "learning_rate": 4.770332825892573e-05, "loss": 4.4254, "step": 4502 }, { "epoch": 0.13753817959682346, "grad_norm": 0.39577558636665344, "learning_rate": 4.770232378147121e-05, "loss": 4.3683, "step": 4503 }, { "epoch": 0.1375687232742822, "grad_norm": 0.37959733605384827, "learning_rate": 4.770131909498472e-05, "loss": 4.3561, "step": 4504 }, { "epoch": 0.137599266951741, "grad_norm": 0.3859700560569763, "learning_rate": 4.7700314199475507e-05, "loss": 4.3624, "step": 4505 }, { "epoch": 0.13762981062919977, "grad_norm": 0.40289750695228577, "learning_rate": 4.769930909495284e-05, "loss": 4.4169, "step": 4506 }, { "epoch": 0.13766035430665852, "grad_norm": 0.379634827375412, "learning_rate": 4.7698303781425955e-05, "loss": 4.4478, "step": 4507 }, { "epoch": 0.1376908979841173, "grad_norm": 0.390931099653244, "learning_rate": 4.769729825890412e-05, "loss": 4.3741, "step": 4508 }, { "epoch": 0.13772144166157604, "grad_norm": 0.38269859552383423, "learning_rate": 4.769629252739659e-05, "loss": 4.387, "step": 4509 }, { "epoch": 0.13775198533903482, "grad_norm": 0.37771275639533997, "learning_rate": 4.7695286586912625e-05, "loss": 4.3195, "step": 4510 }, { "epoch": 0.1377825290164936, "grad_norm": 0.3911532759666443, "learning_rate": 4.769428043746149e-05, "loss": 4.3588, "step": 4511 }, { "epoch": 0.13781307269395235, "grad_norm": 0.3856517970561981, "learning_rate": 4.769327407905245e-05, "loss": 4.5005, "step": 4512 }, { "epoch": 0.13784361637141113, "grad_norm": 0.3929549753665924, "learning_rate": 4.769226751169476e-05, "loss": 4.4396, "step": 4513 }, { "epoch": 0.13787416004886988, "grad_norm": 0.38259249925613403, "learning_rate": 4.7691260735397704e-05, "loss": 4.3958, "step": 4514 }, { "epoch": 0.13790470372632865, "grad_norm": 0.4132608473300934, "learning_rate": 4.769025375017053e-05, "loss": 4.4437, "step": 4515 }, { "epoch": 0.1379352474037874, "grad_norm": 0.383659303188324, "learning_rate": 4.768924655602254e-05, "loss": 4.3536, "step": 4516 }, { "epoch": 0.13796579108124618, "grad_norm": 0.38591521978378296, "learning_rate": 4.768823915296298e-05, "loss": 4.2679, "step": 4517 }, { "epoch": 0.13799633475870496, "grad_norm": 0.38356107473373413, "learning_rate": 4.768723154100114e-05, "loss": 4.3036, "step": 4518 }, { "epoch": 0.1380268784361637, "grad_norm": 0.39139702916145325, "learning_rate": 4.7686223720146294e-05, "loss": 4.4417, "step": 4519 }, { "epoch": 0.13805742211362249, "grad_norm": 0.392788827419281, "learning_rate": 4.768521569040772e-05, "loss": 4.4251, "step": 4520 }, { "epoch": 0.13808796579108124, "grad_norm": 0.3839782774448395, "learning_rate": 4.76842074517947e-05, "loss": 4.3682, "step": 4521 }, { "epoch": 0.13811850946854, "grad_norm": 0.3882072865962982, "learning_rate": 4.768319900431653e-05, "loss": 4.3386, "step": 4522 }, { "epoch": 0.1381490531459988, "grad_norm": 0.3925648629665375, "learning_rate": 4.768219034798248e-05, "loss": 4.3689, "step": 4523 }, { "epoch": 0.13817959682345754, "grad_norm": 0.4042864739894867, "learning_rate": 4.768118148280184e-05, "loss": 4.3558, "step": 4524 }, { "epoch": 0.13821014050091632, "grad_norm": 0.3860606253147125, "learning_rate": 4.7680172408783895e-05, "loss": 4.3318, "step": 4525 }, { "epoch": 0.13824068417837507, "grad_norm": 0.3979145884513855, "learning_rate": 4.767916312593795e-05, "loss": 4.3533, "step": 4526 }, { "epoch": 0.13827122785583384, "grad_norm": 0.3716588318347931, "learning_rate": 4.7678153634273286e-05, "loss": 4.3346, "step": 4527 }, { "epoch": 0.13830177153329262, "grad_norm": 0.3737616240978241, "learning_rate": 4.76771439337992e-05, "loss": 4.3825, "step": 4528 }, { "epoch": 0.13833231521075137, "grad_norm": 0.40622156858444214, "learning_rate": 4.7676134024524994e-05, "loss": 4.4822, "step": 4529 }, { "epoch": 0.13836285888821015, "grad_norm": 0.4017913043498993, "learning_rate": 4.767512390645996e-05, "loss": 4.3303, "step": 4530 }, { "epoch": 0.1383934025656689, "grad_norm": 0.392783522605896, "learning_rate": 4.76741135796134e-05, "loss": 4.4312, "step": 4531 }, { "epoch": 0.13842394624312768, "grad_norm": 0.38420742750167847, "learning_rate": 4.7673103043994624e-05, "loss": 4.321, "step": 4532 }, { "epoch": 0.13845448992058643, "grad_norm": 0.39180076122283936, "learning_rate": 4.767209229961293e-05, "loss": 4.4317, "step": 4533 }, { "epoch": 0.1384850335980452, "grad_norm": 0.39349937438964844, "learning_rate": 4.767108134647762e-05, "loss": 4.3389, "step": 4534 }, { "epoch": 0.13851557727550398, "grad_norm": 0.39084550738334656, "learning_rate": 4.767007018459802e-05, "loss": 4.3383, "step": 4535 }, { "epoch": 0.13854612095296273, "grad_norm": 0.39288896322250366, "learning_rate": 4.7669058813983415e-05, "loss": 4.3349, "step": 4536 }, { "epoch": 0.1385766646304215, "grad_norm": 0.38787776231765747, "learning_rate": 4.766804723464313e-05, "loss": 4.3277, "step": 4537 }, { "epoch": 0.13860720830788026, "grad_norm": 0.40548089146614075, "learning_rate": 4.7667035446586485e-05, "loss": 4.3884, "step": 4538 }, { "epoch": 0.13863775198533904, "grad_norm": 0.39954277873039246, "learning_rate": 4.766602344982279e-05, "loss": 4.4361, "step": 4539 }, { "epoch": 0.1386682956627978, "grad_norm": 0.4041508138179779, "learning_rate": 4.7665011244361364e-05, "loss": 4.4077, "step": 4540 }, { "epoch": 0.13869883934025656, "grad_norm": 0.3845408856868744, "learning_rate": 4.766399883021152e-05, "loss": 4.4662, "step": 4541 }, { "epoch": 0.13872938301771534, "grad_norm": 0.40145042538642883, "learning_rate": 4.7662986207382596e-05, "loss": 4.4455, "step": 4542 }, { "epoch": 0.1387599266951741, "grad_norm": 0.39243483543395996, "learning_rate": 4.76619733758839e-05, "loss": 4.3143, "step": 4543 }, { "epoch": 0.13879047037263287, "grad_norm": 0.3866580128669739, "learning_rate": 4.766096033572476e-05, "loss": 4.3634, "step": 4544 }, { "epoch": 0.13882101405009162, "grad_norm": 0.3875117003917694, "learning_rate": 4.7659947086914514e-05, "loss": 4.4587, "step": 4545 }, { "epoch": 0.1388515577275504, "grad_norm": 0.4024050533771515, "learning_rate": 4.765893362946249e-05, "loss": 4.4492, "step": 4546 }, { "epoch": 0.13888210140500917, "grad_norm": 0.40336114168167114, "learning_rate": 4.7657919963378e-05, "loss": 4.4248, "step": 4547 }, { "epoch": 0.13891264508246792, "grad_norm": 0.39760875701904297, "learning_rate": 4.7656906088670395e-05, "loss": 4.4068, "step": 4548 }, { "epoch": 0.1389431887599267, "grad_norm": 0.39761197566986084, "learning_rate": 4.765589200534901e-05, "loss": 4.3618, "step": 4549 }, { "epoch": 0.13897373243738545, "grad_norm": 0.3987199366092682, "learning_rate": 4.765487771342318e-05, "loss": 4.3063, "step": 4550 }, { "epoch": 0.13900427611484423, "grad_norm": 0.3953193724155426, "learning_rate": 4.765386321290224e-05, "loss": 4.4367, "step": 4551 }, { "epoch": 0.139034819792303, "grad_norm": 0.41374194622039795, "learning_rate": 4.7652848503795536e-05, "loss": 4.4535, "step": 4552 }, { "epoch": 0.13906536346976175, "grad_norm": 0.3855209946632385, "learning_rate": 4.7651833586112404e-05, "loss": 4.4236, "step": 4553 }, { "epoch": 0.13909590714722053, "grad_norm": 0.4075007438659668, "learning_rate": 4.76508184598622e-05, "loss": 4.4153, "step": 4554 }, { "epoch": 0.13912645082467928, "grad_norm": 0.3899100124835968, "learning_rate": 4.764980312505426e-05, "loss": 4.3429, "step": 4555 }, { "epoch": 0.13915699450213806, "grad_norm": 0.403152734041214, "learning_rate": 4.764878758169794e-05, "loss": 4.3385, "step": 4556 }, { "epoch": 0.13918753817959684, "grad_norm": 0.3904716670513153, "learning_rate": 4.764777182980259e-05, "loss": 4.4115, "step": 4557 }, { "epoch": 0.1392180818570556, "grad_norm": 0.4062970280647278, "learning_rate": 4.764675586937756e-05, "loss": 4.4377, "step": 4558 }, { "epoch": 0.13924862553451436, "grad_norm": 0.39869633316993713, "learning_rate": 4.7645739700432195e-05, "loss": 4.4386, "step": 4559 }, { "epoch": 0.13927916921197311, "grad_norm": 0.39486342668533325, "learning_rate": 4.764472332297587e-05, "loss": 4.4578, "step": 4560 }, { "epoch": 0.1393097128894319, "grad_norm": 0.4104459285736084, "learning_rate": 4.764370673701793e-05, "loss": 4.4257, "step": 4561 }, { "epoch": 0.13934025656689064, "grad_norm": 0.39639148116111755, "learning_rate": 4.764268994256775e-05, "loss": 4.3803, "step": 4562 }, { "epoch": 0.13937080024434942, "grad_norm": 0.39042869210243225, "learning_rate": 4.7641672939634673e-05, "loss": 4.4331, "step": 4563 }, { "epoch": 0.1394013439218082, "grad_norm": 0.37731316685676575, "learning_rate": 4.7640655728228075e-05, "loss": 4.3705, "step": 4564 }, { "epoch": 0.13943188759926695, "grad_norm": 0.39381399750709534, "learning_rate": 4.763963830835732e-05, "loss": 4.3792, "step": 4565 }, { "epoch": 0.13946243127672572, "grad_norm": 0.39455127716064453, "learning_rate": 4.7638620680031765e-05, "loss": 4.3469, "step": 4566 }, { "epoch": 0.13949297495418447, "grad_norm": 0.40536588430404663, "learning_rate": 4.7637602843260796e-05, "loss": 4.4401, "step": 4567 }, { "epoch": 0.13952351863164325, "grad_norm": 0.40755683183670044, "learning_rate": 4.763658479805378e-05, "loss": 4.3397, "step": 4568 }, { "epoch": 0.13955406230910203, "grad_norm": 0.40224793553352356, "learning_rate": 4.7635566544420095e-05, "loss": 4.4021, "step": 4569 }, { "epoch": 0.13958460598656078, "grad_norm": 0.4041112959384918, "learning_rate": 4.7634548082369106e-05, "loss": 4.4312, "step": 4570 }, { "epoch": 0.13961514966401956, "grad_norm": 0.38668888807296753, "learning_rate": 4.7633529411910194e-05, "loss": 4.4095, "step": 4571 }, { "epoch": 0.1396456933414783, "grad_norm": 0.38764798641204834, "learning_rate": 4.7632510533052744e-05, "loss": 4.3422, "step": 4572 }, { "epoch": 0.13967623701893708, "grad_norm": 0.3969093859195709, "learning_rate": 4.763149144580613e-05, "loss": 4.391, "step": 4573 }, { "epoch": 0.13970678069639583, "grad_norm": 0.3827251195907593, "learning_rate": 4.7630472150179735e-05, "loss": 4.4648, "step": 4574 }, { "epoch": 0.1397373243738546, "grad_norm": 0.40941280126571655, "learning_rate": 4.762945264618295e-05, "loss": 4.4379, "step": 4575 }, { "epoch": 0.1397678680513134, "grad_norm": 0.39665764570236206, "learning_rate": 4.7628432933825154e-05, "loss": 4.4171, "step": 4576 }, { "epoch": 0.13979841172877214, "grad_norm": 0.3926980495452881, "learning_rate": 4.762741301311575e-05, "loss": 4.4185, "step": 4577 }, { "epoch": 0.13982895540623091, "grad_norm": 0.3860379755496979, "learning_rate": 4.7626392884064116e-05, "loss": 4.4245, "step": 4578 }, { "epoch": 0.13985949908368966, "grad_norm": 0.4044193923473358, "learning_rate": 4.762537254667966e-05, "loss": 4.4039, "step": 4579 }, { "epoch": 0.13989004276114844, "grad_norm": 0.396444171667099, "learning_rate": 4.762435200097175e-05, "loss": 4.3173, "step": 4580 }, { "epoch": 0.13992058643860722, "grad_norm": 0.39658430218696594, "learning_rate": 4.7623331246949806e-05, "loss": 4.4271, "step": 4581 }, { "epoch": 0.13995113011606597, "grad_norm": 0.3768465518951416, "learning_rate": 4.7622310284623217e-05, "loss": 4.3764, "step": 4582 }, { "epoch": 0.13998167379352475, "grad_norm": 0.3967011570930481, "learning_rate": 4.7621289114001386e-05, "loss": 4.3862, "step": 4583 }, { "epoch": 0.1400122174709835, "grad_norm": 0.38218390941619873, "learning_rate": 4.762026773509373e-05, "loss": 4.4272, "step": 4584 }, { "epoch": 0.14004276114844227, "grad_norm": 0.40228214859962463, "learning_rate": 4.7619246147909624e-05, "loss": 4.3563, "step": 4585 }, { "epoch": 0.14007330482590105, "grad_norm": 0.3902318775653839, "learning_rate": 4.761822435245848e-05, "loss": 4.4182, "step": 4586 }, { "epoch": 0.1401038485033598, "grad_norm": 0.37568554282188416, "learning_rate": 4.761720234874974e-05, "loss": 4.3678, "step": 4587 }, { "epoch": 0.14013439218081858, "grad_norm": 0.3772679269313812, "learning_rate": 4.761618013679277e-05, "loss": 4.4151, "step": 4588 }, { "epoch": 0.14016493585827733, "grad_norm": 0.4051959216594696, "learning_rate": 4.7615157716597016e-05, "loss": 4.4472, "step": 4589 }, { "epoch": 0.1401954795357361, "grad_norm": 0.3918793201446533, "learning_rate": 4.7614135088171865e-05, "loss": 4.3343, "step": 4590 }, { "epoch": 0.14022602321319486, "grad_norm": 0.37525832653045654, "learning_rate": 4.7613112251526745e-05, "loss": 4.381, "step": 4591 }, { "epoch": 0.14025656689065363, "grad_norm": 0.3984050750732422, "learning_rate": 4.761208920667109e-05, "loss": 4.3218, "step": 4592 }, { "epoch": 0.1402871105681124, "grad_norm": 0.39255693554878235, "learning_rate": 4.761106595361428e-05, "loss": 4.3471, "step": 4593 }, { "epoch": 0.14031765424557116, "grad_norm": 0.39545899629592896, "learning_rate": 4.761004249236577e-05, "loss": 4.2912, "step": 4594 }, { "epoch": 0.14034819792302994, "grad_norm": 0.38888657093048096, "learning_rate": 4.760901882293498e-05, "loss": 4.419, "step": 4595 }, { "epoch": 0.1403787416004887, "grad_norm": 0.40657874941825867, "learning_rate": 4.760799494533132e-05, "loss": 4.4254, "step": 4596 }, { "epoch": 0.14040928527794747, "grad_norm": 0.4006454050540924, "learning_rate": 4.7606970859564235e-05, "loss": 4.4341, "step": 4597 }, { "epoch": 0.14043982895540624, "grad_norm": 0.3977065086364746, "learning_rate": 4.7605946565643144e-05, "loss": 4.4246, "step": 4598 }, { "epoch": 0.140470372632865, "grad_norm": 0.3831108510494232, "learning_rate": 4.760492206357748e-05, "loss": 4.3504, "step": 4599 }, { "epoch": 0.14050091631032377, "grad_norm": 0.3881545066833496, "learning_rate": 4.760389735337668e-05, "loss": 4.4154, "step": 4600 }, { "epoch": 0.14053145998778252, "grad_norm": 0.3891919255256653, "learning_rate": 4.760287243505017e-05, "loss": 4.5086, "step": 4601 }, { "epoch": 0.1405620036652413, "grad_norm": 0.37791475653648376, "learning_rate": 4.760184730860739e-05, "loss": 4.3988, "step": 4602 }, { "epoch": 0.14059254734270007, "grad_norm": 0.3892107307910919, "learning_rate": 4.7600821974057787e-05, "loss": 4.4096, "step": 4603 }, { "epoch": 0.14062309102015882, "grad_norm": 0.3923680782318115, "learning_rate": 4.7599796431410794e-05, "loss": 4.3987, "step": 4604 }, { "epoch": 0.1406536346976176, "grad_norm": 0.3769950866699219, "learning_rate": 4.759877068067585e-05, "loss": 4.4478, "step": 4605 }, { "epoch": 0.14068417837507635, "grad_norm": 0.38116028904914856, "learning_rate": 4.759774472186242e-05, "loss": 4.2914, "step": 4606 }, { "epoch": 0.14071472205253513, "grad_norm": 0.388854444026947, "learning_rate": 4.759671855497991e-05, "loss": 4.4172, "step": 4607 }, { "epoch": 0.14074526572999388, "grad_norm": 0.3870851993560791, "learning_rate": 4.7595692180037816e-05, "loss": 4.4296, "step": 4608 }, { "epoch": 0.14077580940745266, "grad_norm": 0.39530590176582336, "learning_rate": 4.7594665597045563e-05, "loss": 4.4117, "step": 4609 }, { "epoch": 0.14080635308491143, "grad_norm": 0.3800412118434906, "learning_rate": 4.75936388060126e-05, "loss": 4.3551, "step": 4610 }, { "epoch": 0.14083689676237018, "grad_norm": 0.3812347650527954, "learning_rate": 4.759261180694839e-05, "loss": 4.4386, "step": 4611 }, { "epoch": 0.14086744043982896, "grad_norm": 0.38461968302726746, "learning_rate": 4.7591584599862394e-05, "loss": 4.4383, "step": 4612 }, { "epoch": 0.1408979841172877, "grad_norm": 0.39001771807670593, "learning_rate": 4.7590557184764056e-05, "loss": 4.4306, "step": 4613 }, { "epoch": 0.1409285277947465, "grad_norm": 0.38092654943466187, "learning_rate": 4.7589529561662846e-05, "loss": 4.3586, "step": 4614 }, { "epoch": 0.14095907147220527, "grad_norm": 0.3833761513233185, "learning_rate": 4.7588501730568224e-05, "loss": 4.2919, "step": 4615 }, { "epoch": 0.14098961514966402, "grad_norm": 0.394389808177948, "learning_rate": 4.758747369148965e-05, "loss": 4.4352, "step": 4616 }, { "epoch": 0.1410201588271228, "grad_norm": 0.38739073276519775, "learning_rate": 4.758644544443659e-05, "loss": 4.3992, "step": 4617 }, { "epoch": 0.14105070250458154, "grad_norm": 0.3685208261013031, "learning_rate": 4.758541698941852e-05, "loss": 4.2971, "step": 4618 }, { "epoch": 0.14108124618204032, "grad_norm": 0.37150201201438904, "learning_rate": 4.7584388326444904e-05, "loss": 4.4028, "step": 4619 }, { "epoch": 0.14111178985949907, "grad_norm": 0.3824283480644226, "learning_rate": 4.758335945552521e-05, "loss": 4.3847, "step": 4620 }, { "epoch": 0.14114233353695785, "grad_norm": 0.3907910883426666, "learning_rate": 4.758233037666891e-05, "loss": 4.4851, "step": 4621 }, { "epoch": 0.14117287721441663, "grad_norm": 0.3890376091003418, "learning_rate": 4.758130108988549e-05, "loss": 4.3873, "step": 4622 }, { "epoch": 0.14120342089187538, "grad_norm": 0.38415348529815674, "learning_rate": 4.7580271595184414e-05, "loss": 4.4089, "step": 4623 }, { "epoch": 0.14123396456933415, "grad_norm": 0.3786576986312866, "learning_rate": 4.757924189257518e-05, "loss": 4.329, "step": 4624 }, { "epoch": 0.1412645082467929, "grad_norm": 0.39027488231658936, "learning_rate": 4.7578211982067246e-05, "loss": 4.4308, "step": 4625 }, { "epoch": 0.14129505192425168, "grad_norm": 0.39051198959350586, "learning_rate": 4.757718186367011e-05, "loss": 4.4073, "step": 4626 }, { "epoch": 0.14132559560171046, "grad_norm": 0.3856974244117737, "learning_rate": 4.757615153739325e-05, "loss": 4.45, "step": 4627 }, { "epoch": 0.1413561392791692, "grad_norm": 0.3906041383743286, "learning_rate": 4.757512100324616e-05, "loss": 4.336, "step": 4628 }, { "epoch": 0.14138668295662798, "grad_norm": 0.4006592929363251, "learning_rate": 4.757409026123831e-05, "loss": 4.4601, "step": 4629 }, { "epoch": 0.14141722663408673, "grad_norm": 0.4032314419746399, "learning_rate": 4.757305931137922e-05, "loss": 4.4312, "step": 4630 }, { "epoch": 0.1414477703115455, "grad_norm": 0.4051947593688965, "learning_rate": 4.757202815367836e-05, "loss": 4.3742, "step": 4631 }, { "epoch": 0.1414783139890043, "grad_norm": 0.3750022351741791, "learning_rate": 4.7570996788145236e-05, "loss": 4.3708, "step": 4632 }, { "epoch": 0.14150885766646304, "grad_norm": 0.39807218313217163, "learning_rate": 4.756996521478934e-05, "loss": 4.3944, "step": 4633 }, { "epoch": 0.14153940134392182, "grad_norm": 0.3978291451931, "learning_rate": 4.756893343362017e-05, "loss": 4.3626, "step": 4634 }, { "epoch": 0.14156994502138057, "grad_norm": 0.3836364448070526, "learning_rate": 4.756790144464722e-05, "loss": 4.4107, "step": 4635 }, { "epoch": 0.14160048869883934, "grad_norm": 0.39220184087753296, "learning_rate": 4.756686924788e-05, "loss": 4.3473, "step": 4636 }, { "epoch": 0.1416310323762981, "grad_norm": 0.38981881737709045, "learning_rate": 4.7565836843328015e-05, "loss": 4.4174, "step": 4637 }, { "epoch": 0.14166157605375687, "grad_norm": 0.38274505734443665, "learning_rate": 4.7564804231000765e-05, "loss": 4.4024, "step": 4638 }, { "epoch": 0.14169211973121565, "grad_norm": 0.39467746019363403, "learning_rate": 4.7563771410907766e-05, "loss": 4.4815, "step": 4639 }, { "epoch": 0.1417226634086744, "grad_norm": 0.40058979392051697, "learning_rate": 4.7562738383058516e-05, "loss": 4.3626, "step": 4640 }, { "epoch": 0.14175320708613318, "grad_norm": 0.38546618819236755, "learning_rate": 4.756170514746253e-05, "loss": 4.3705, "step": 4641 }, { "epoch": 0.14178375076359193, "grad_norm": 0.39563360810279846, "learning_rate": 4.7560671704129335e-05, "loss": 4.4559, "step": 4642 }, { "epoch": 0.1418142944410507, "grad_norm": 0.4216350018978119, "learning_rate": 4.755963805306843e-05, "loss": 4.4371, "step": 4643 }, { "epoch": 0.14184483811850948, "grad_norm": 0.41190820932388306, "learning_rate": 4.7558604194289334e-05, "loss": 4.4118, "step": 4644 }, { "epoch": 0.14187538179596823, "grad_norm": 0.40127313137054443, "learning_rate": 4.755757012780158e-05, "loss": 4.4017, "step": 4645 }, { "epoch": 0.141905925473427, "grad_norm": 0.3759022355079651, "learning_rate": 4.755653585361468e-05, "loss": 4.3718, "step": 4646 }, { "epoch": 0.14193646915088576, "grad_norm": 0.40257322788238525, "learning_rate": 4.7555501371738154e-05, "loss": 4.3663, "step": 4647 }, { "epoch": 0.14196701282834454, "grad_norm": 0.39206433296203613, "learning_rate": 4.755446668218153e-05, "loss": 4.4257, "step": 4648 }, { "epoch": 0.14199755650580329, "grad_norm": 0.3859638273715973, "learning_rate": 4.755343178495433e-05, "loss": 4.3759, "step": 4649 }, { "epoch": 0.14202810018326206, "grad_norm": 0.40467721223831177, "learning_rate": 4.755239668006609e-05, "loss": 4.3593, "step": 4650 }, { "epoch": 0.14205864386072084, "grad_norm": 0.3864457905292511, "learning_rate": 4.755136136752635e-05, "loss": 4.2509, "step": 4651 }, { "epoch": 0.1420891875381796, "grad_norm": 0.4075835645198822, "learning_rate": 4.755032584734462e-05, "loss": 4.3779, "step": 4652 }, { "epoch": 0.14211973121563837, "grad_norm": 0.38879597187042236, "learning_rate": 4.7549290119530445e-05, "loss": 4.3972, "step": 4653 }, { "epoch": 0.14215027489309712, "grad_norm": 0.3821451961994171, "learning_rate": 4.754825418409337e-05, "loss": 4.3122, "step": 4654 }, { "epoch": 0.1421808185705559, "grad_norm": 0.3954058587551117, "learning_rate": 4.7547218041042914e-05, "loss": 4.3967, "step": 4655 }, { "epoch": 0.14221136224801467, "grad_norm": 0.3972316384315491, "learning_rate": 4.7546181690388634e-05, "loss": 4.2746, "step": 4656 }, { "epoch": 0.14224190592547342, "grad_norm": 0.38999029994010925, "learning_rate": 4.754514513214007e-05, "loss": 4.2532, "step": 4657 }, { "epoch": 0.1422724496029322, "grad_norm": 0.3882652521133423, "learning_rate": 4.7544108366306763e-05, "loss": 4.3839, "step": 4658 }, { "epoch": 0.14230299328039095, "grad_norm": 0.3946808874607086, "learning_rate": 4.7543071392898255e-05, "loss": 4.4212, "step": 4659 }, { "epoch": 0.14233353695784973, "grad_norm": 0.3926997780799866, "learning_rate": 4.7542034211924106e-05, "loss": 4.4493, "step": 4660 }, { "epoch": 0.1423640806353085, "grad_norm": 0.379131555557251, "learning_rate": 4.7540996823393843e-05, "loss": 4.3939, "step": 4661 }, { "epoch": 0.14239462431276725, "grad_norm": 0.3827004134654999, "learning_rate": 4.753995922731704e-05, "loss": 4.4142, "step": 4662 }, { "epoch": 0.14242516799022603, "grad_norm": 0.38696444034576416, "learning_rate": 4.753892142370325e-05, "loss": 4.4129, "step": 4663 }, { "epoch": 0.14245571166768478, "grad_norm": 0.3863506615161896, "learning_rate": 4.7537883412562025e-05, "loss": 4.4344, "step": 4664 }, { "epoch": 0.14248625534514356, "grad_norm": 0.37813499569892883, "learning_rate": 4.753684519390291e-05, "loss": 4.3898, "step": 4665 }, { "epoch": 0.1425167990226023, "grad_norm": 0.3815448582172394, "learning_rate": 4.7535806767735474e-05, "loss": 4.337, "step": 4666 }, { "epoch": 0.14254734270006109, "grad_norm": 0.39332735538482666, "learning_rate": 4.753476813406928e-05, "loss": 4.4173, "step": 4667 }, { "epoch": 0.14257788637751986, "grad_norm": 0.39308711886405945, "learning_rate": 4.753372929291389e-05, "loss": 4.4258, "step": 4668 }, { "epoch": 0.1426084300549786, "grad_norm": 0.39815986156463623, "learning_rate": 4.753269024427887e-05, "loss": 4.3675, "step": 4669 }, { "epoch": 0.1426389737324374, "grad_norm": 0.3850265145301819, "learning_rate": 4.7531650988173784e-05, "loss": 4.365, "step": 4670 }, { "epoch": 0.14266951740989614, "grad_norm": 0.3908674716949463, "learning_rate": 4.75306115246082e-05, "loss": 4.4415, "step": 4671 }, { "epoch": 0.14270006108735492, "grad_norm": 0.3881368637084961, "learning_rate": 4.752957185359171e-05, "loss": 4.4013, "step": 4672 }, { "epoch": 0.1427306047648137, "grad_norm": 0.389556348323822, "learning_rate": 4.752853197513384e-05, "loss": 4.4379, "step": 4673 }, { "epoch": 0.14276114844227245, "grad_norm": 0.40565308928489685, "learning_rate": 4.7527491889244215e-05, "loss": 4.3451, "step": 4674 }, { "epoch": 0.14279169211973122, "grad_norm": 0.38129809498786926, "learning_rate": 4.7526451595932374e-05, "loss": 4.3397, "step": 4675 }, { "epoch": 0.14282223579718997, "grad_norm": 0.38400712609291077, "learning_rate": 4.752541109520792e-05, "loss": 4.3851, "step": 4676 }, { "epoch": 0.14285277947464875, "grad_norm": 0.38469454646110535, "learning_rate": 4.752437038708042e-05, "loss": 4.3957, "step": 4677 }, { "epoch": 0.14288332315210753, "grad_norm": 0.4078788161277771, "learning_rate": 4.752332947155947e-05, "loss": 4.3886, "step": 4678 }, { "epoch": 0.14291386682956628, "grad_norm": 0.3864705562591553, "learning_rate": 4.752228834865464e-05, "loss": 4.4778, "step": 4679 }, { "epoch": 0.14294441050702505, "grad_norm": 0.3910903334617615, "learning_rate": 4.752124701837552e-05, "loss": 4.4712, "step": 4680 }, { "epoch": 0.1429749541844838, "grad_norm": 0.3885872960090637, "learning_rate": 4.75202054807317e-05, "loss": 4.4798, "step": 4681 }, { "epoch": 0.14300549786194258, "grad_norm": 0.3987191915512085, "learning_rate": 4.7519163735732767e-05, "loss": 4.4089, "step": 4682 }, { "epoch": 0.14303604153940133, "grad_norm": 0.3817742168903351, "learning_rate": 4.751812178338832e-05, "loss": 4.4245, "step": 4683 }, { "epoch": 0.1430665852168601, "grad_norm": 0.40341368317604065, "learning_rate": 4.751707962370795e-05, "loss": 4.4066, "step": 4684 }, { "epoch": 0.1430971288943189, "grad_norm": 0.3963698148727417, "learning_rate": 4.751603725670124e-05, "loss": 4.4373, "step": 4685 }, { "epoch": 0.14312767257177764, "grad_norm": 0.39235982298851013, "learning_rate": 4.751499468237781e-05, "loss": 4.4904, "step": 4686 }, { "epoch": 0.14315821624923641, "grad_norm": 0.40277567505836487, "learning_rate": 4.751395190074724e-05, "loss": 4.412, "step": 4687 }, { "epoch": 0.14318875992669516, "grad_norm": 0.3899131417274475, "learning_rate": 4.751290891181914e-05, "loss": 4.4326, "step": 4688 }, { "epoch": 0.14321930360415394, "grad_norm": 0.389110803604126, "learning_rate": 4.751186571560312e-05, "loss": 4.4103, "step": 4689 }, { "epoch": 0.14324984728161272, "grad_norm": 0.4029225707054138, "learning_rate": 4.751082231210877e-05, "loss": 4.3826, "step": 4690 }, { "epoch": 0.14328039095907147, "grad_norm": 0.38193488121032715, "learning_rate": 4.750977870134571e-05, "loss": 4.4339, "step": 4691 }, { "epoch": 0.14331093463653025, "grad_norm": 0.3840940296649933, "learning_rate": 4.750873488332354e-05, "loss": 4.3306, "step": 4692 }, { "epoch": 0.143341478313989, "grad_norm": 0.38260921835899353, "learning_rate": 4.7507690858051875e-05, "loss": 4.2825, "step": 4693 }, { "epoch": 0.14337202199144777, "grad_norm": 0.4026864767074585, "learning_rate": 4.750664662554033e-05, "loss": 4.4432, "step": 4694 }, { "epoch": 0.14340256566890652, "grad_norm": 0.3952406942844391, "learning_rate": 4.750560218579853e-05, "loss": 4.469, "step": 4695 }, { "epoch": 0.1434331093463653, "grad_norm": 0.40435561537742615, "learning_rate": 4.750455753883606e-05, "loss": 4.4276, "step": 4696 }, { "epoch": 0.14346365302382408, "grad_norm": 0.4121648073196411, "learning_rate": 4.750351268466257e-05, "loss": 4.3833, "step": 4697 }, { "epoch": 0.14349419670128283, "grad_norm": 0.3860378563404083, "learning_rate": 4.750246762328766e-05, "loss": 4.3169, "step": 4698 }, { "epoch": 0.1435247403787416, "grad_norm": 0.3867098093032837, "learning_rate": 4.750142235472096e-05, "loss": 4.452, "step": 4699 }, { "epoch": 0.14355528405620036, "grad_norm": 0.4003431797027588, "learning_rate": 4.7500376878972104e-05, "loss": 4.3702, "step": 4700 }, { "epoch": 0.14358582773365913, "grad_norm": 0.38590070605278015, "learning_rate": 4.74993311960507e-05, "loss": 4.4723, "step": 4701 }, { "epoch": 0.1436163714111179, "grad_norm": 0.38632509112358093, "learning_rate": 4.74982853059664e-05, "loss": 4.3503, "step": 4702 }, { "epoch": 0.14364691508857666, "grad_norm": 0.38562119007110596, "learning_rate": 4.74972392087288e-05, "loss": 4.2531, "step": 4703 }, { "epoch": 0.14367745876603544, "grad_norm": 0.3891685903072357, "learning_rate": 4.7496192904347566e-05, "loss": 4.3709, "step": 4704 }, { "epoch": 0.1437080024434942, "grad_norm": 0.384648859500885, "learning_rate": 4.749514639283232e-05, "loss": 4.4035, "step": 4705 }, { "epoch": 0.14373854612095296, "grad_norm": 0.3875444829463959, "learning_rate": 4.749409967419269e-05, "loss": 4.4298, "step": 4706 }, { "epoch": 0.14376908979841174, "grad_norm": 0.40078064799308777, "learning_rate": 4.7493052748438315e-05, "loss": 4.5002, "step": 4707 }, { "epoch": 0.1437996334758705, "grad_norm": 0.383451908826828, "learning_rate": 4.749200561557884e-05, "loss": 4.3675, "step": 4708 }, { "epoch": 0.14383017715332927, "grad_norm": 0.38660314679145813, "learning_rate": 4.7490958275623906e-05, "loss": 4.3991, "step": 4709 }, { "epoch": 0.14386072083078802, "grad_norm": 0.38608986139297485, "learning_rate": 4.7489910728583163e-05, "loss": 4.3429, "step": 4710 }, { "epoch": 0.1438912645082468, "grad_norm": 0.38075536489486694, "learning_rate": 4.748886297446624e-05, "loss": 4.3294, "step": 4711 }, { "epoch": 0.14392180818570555, "grad_norm": 0.38769474625587463, "learning_rate": 4.74878150132828e-05, "loss": 4.394, "step": 4712 }, { "epoch": 0.14395235186316432, "grad_norm": 0.37623873353004456, "learning_rate": 4.7486766845042475e-05, "loss": 4.3534, "step": 4713 }, { "epoch": 0.1439828955406231, "grad_norm": 0.38670945167541504, "learning_rate": 4.748571846975493e-05, "loss": 4.3543, "step": 4714 }, { "epoch": 0.14401343921808185, "grad_norm": 0.3961171805858612, "learning_rate": 4.748466988742982e-05, "loss": 4.4609, "step": 4715 }, { "epoch": 0.14404398289554063, "grad_norm": 0.39488375186920166, "learning_rate": 4.7483621098076784e-05, "loss": 4.4183, "step": 4716 }, { "epoch": 0.14407452657299938, "grad_norm": 0.387503057718277, "learning_rate": 4.74825721017055e-05, "loss": 4.3487, "step": 4717 }, { "epoch": 0.14410507025045816, "grad_norm": 0.3950214087963104, "learning_rate": 4.7481522898325606e-05, "loss": 4.3084, "step": 4718 }, { "epoch": 0.14413561392791693, "grad_norm": 0.40841981768608093, "learning_rate": 4.748047348794677e-05, "loss": 4.4541, "step": 4719 }, { "epoch": 0.14416615760537568, "grad_norm": 0.3869541883468628, "learning_rate": 4.747942387057867e-05, "loss": 4.3999, "step": 4720 }, { "epoch": 0.14419670128283446, "grad_norm": 0.3834840655326843, "learning_rate": 4.747837404623094e-05, "loss": 4.3419, "step": 4721 }, { "epoch": 0.1442272449602932, "grad_norm": 0.3786635398864746, "learning_rate": 4.7477324014913275e-05, "loss": 4.4413, "step": 4722 }, { "epoch": 0.144257788637752, "grad_norm": 0.3975512385368347, "learning_rate": 4.7476273776635325e-05, "loss": 4.4507, "step": 4723 }, { "epoch": 0.14428833231521074, "grad_norm": 0.40712836384773254, "learning_rate": 4.747522333140677e-05, "loss": 4.4347, "step": 4724 }, { "epoch": 0.14431887599266952, "grad_norm": 0.3899441659450531, "learning_rate": 4.7474172679237276e-05, "loss": 4.4287, "step": 4725 }, { "epoch": 0.1443494196701283, "grad_norm": 0.4058639109134674, "learning_rate": 4.747312182013652e-05, "loss": 4.4123, "step": 4726 }, { "epoch": 0.14437996334758704, "grad_norm": 0.3872821629047394, "learning_rate": 4.747207075411418e-05, "loss": 4.3008, "step": 4727 }, { "epoch": 0.14441050702504582, "grad_norm": 0.3856718838214874, "learning_rate": 4.747101948117992e-05, "loss": 4.3925, "step": 4728 }, { "epoch": 0.14444105070250457, "grad_norm": 0.4061943590641022, "learning_rate": 4.7469968001343445e-05, "loss": 4.3825, "step": 4729 }, { "epoch": 0.14447159437996335, "grad_norm": 0.38844987750053406, "learning_rate": 4.746891631461441e-05, "loss": 4.4755, "step": 4730 }, { "epoch": 0.14450213805742212, "grad_norm": 0.41014623641967773, "learning_rate": 4.7467864421002515e-05, "loss": 4.3682, "step": 4731 }, { "epoch": 0.14453268173488087, "grad_norm": 0.39390829205513, "learning_rate": 4.746681232051744e-05, "loss": 4.3466, "step": 4732 }, { "epoch": 0.14456322541233965, "grad_norm": 0.3880085349082947, "learning_rate": 4.746576001316887e-05, "loss": 4.4213, "step": 4733 }, { "epoch": 0.1445937690897984, "grad_norm": 0.3872724771499634, "learning_rate": 4.74647074989665e-05, "loss": 4.4173, "step": 4734 }, { "epoch": 0.14462431276725718, "grad_norm": 0.3899673521518707, "learning_rate": 4.746365477792002e-05, "loss": 4.3454, "step": 4735 }, { "epoch": 0.14465485644471596, "grad_norm": 0.3868001699447632, "learning_rate": 4.746260185003911e-05, "loss": 4.4185, "step": 4736 }, { "epoch": 0.1446854001221747, "grad_norm": 0.38160574436187744, "learning_rate": 4.7461548715333484e-05, "loss": 4.3872, "step": 4737 }, { "epoch": 0.14471594379963348, "grad_norm": 0.39999204874038696, "learning_rate": 4.746049537381283e-05, "loss": 4.4074, "step": 4738 }, { "epoch": 0.14474648747709223, "grad_norm": 0.38140225410461426, "learning_rate": 4.745944182548685e-05, "loss": 4.4744, "step": 4739 }, { "epoch": 0.144777031154551, "grad_norm": 0.39520910382270813, "learning_rate": 4.7458388070365236e-05, "loss": 4.3742, "step": 4740 }, { "epoch": 0.14480757483200976, "grad_norm": 0.39698395133018494, "learning_rate": 4.7457334108457694e-05, "loss": 4.3935, "step": 4741 }, { "epoch": 0.14483811850946854, "grad_norm": 0.39802807569503784, "learning_rate": 4.745627993977394e-05, "loss": 4.3971, "step": 4742 }, { "epoch": 0.14486866218692732, "grad_norm": 0.3822372257709503, "learning_rate": 4.745522556432367e-05, "loss": 4.3611, "step": 4743 }, { "epoch": 0.14489920586438607, "grad_norm": 0.40537726879119873, "learning_rate": 4.7454170982116584e-05, "loss": 4.4315, "step": 4744 }, { "epoch": 0.14492974954184484, "grad_norm": 0.3820617198944092, "learning_rate": 4.7453116193162406e-05, "loss": 4.331, "step": 4745 }, { "epoch": 0.1449602932193036, "grad_norm": 0.39985236525535583, "learning_rate": 4.7452061197470843e-05, "loss": 4.3662, "step": 4746 }, { "epoch": 0.14499083689676237, "grad_norm": 0.3878493905067444, "learning_rate": 4.7451005995051606e-05, "loss": 4.4599, "step": 4747 }, { "epoch": 0.14502138057422115, "grad_norm": 0.3796314299106598, "learning_rate": 4.744995058591441e-05, "loss": 4.4757, "step": 4748 }, { "epoch": 0.1450519242516799, "grad_norm": 0.38143619894981384, "learning_rate": 4.744889497006899e-05, "loss": 4.3193, "step": 4749 }, { "epoch": 0.14508246792913868, "grad_norm": 0.3978855609893799, "learning_rate": 4.744783914752504e-05, "loss": 4.4097, "step": 4750 }, { "epoch": 0.14511301160659743, "grad_norm": 0.39208605885505676, "learning_rate": 4.7446783118292306e-05, "loss": 4.4881, "step": 4751 }, { "epoch": 0.1451435552840562, "grad_norm": 0.3841816484928131, "learning_rate": 4.744572688238048e-05, "loss": 4.3991, "step": 4752 }, { "epoch": 0.14517409896151498, "grad_norm": 0.37809687852859497, "learning_rate": 4.744467043979932e-05, "loss": 4.3419, "step": 4753 }, { "epoch": 0.14520464263897373, "grad_norm": 0.38390663266181946, "learning_rate": 4.744361379055854e-05, "loss": 4.4281, "step": 4754 }, { "epoch": 0.1452351863164325, "grad_norm": 0.38931775093078613, "learning_rate": 4.744255693466786e-05, "loss": 4.428, "step": 4755 }, { "epoch": 0.14526572999389126, "grad_norm": 0.3716176152229309, "learning_rate": 4.7441499872137025e-05, "loss": 4.3829, "step": 4756 }, { "epoch": 0.14529627367135003, "grad_norm": 0.3823729455471039, "learning_rate": 4.744044260297576e-05, "loss": 4.4573, "step": 4757 }, { "epoch": 0.14532681734880878, "grad_norm": 0.3850756287574768, "learning_rate": 4.7439385127193805e-05, "loss": 4.482, "step": 4758 }, { "epoch": 0.14535736102626756, "grad_norm": 0.38633474707603455, "learning_rate": 4.743832744480089e-05, "loss": 4.3824, "step": 4759 }, { "epoch": 0.14538790470372634, "grad_norm": 0.3772365152835846, "learning_rate": 4.743726955580676e-05, "loss": 4.3876, "step": 4760 }, { "epoch": 0.1454184483811851, "grad_norm": 0.3854401409626007, "learning_rate": 4.743621146022116e-05, "loss": 4.3543, "step": 4761 }, { "epoch": 0.14544899205864387, "grad_norm": 0.3895481526851654, "learning_rate": 4.7435153158053815e-05, "loss": 4.4111, "step": 4762 }, { "epoch": 0.14547953573610262, "grad_norm": 0.4034373462200165, "learning_rate": 4.743409464931448e-05, "loss": 4.3736, "step": 4763 }, { "epoch": 0.1455100794135614, "grad_norm": 0.39472395181655884, "learning_rate": 4.7433035934012904e-05, "loss": 4.458, "step": 4764 }, { "epoch": 0.14554062309102017, "grad_norm": 0.3871419429779053, "learning_rate": 4.743197701215883e-05, "loss": 4.394, "step": 4765 }, { "epoch": 0.14557116676847892, "grad_norm": 0.37575283646583557, "learning_rate": 4.743091788376202e-05, "loss": 4.3962, "step": 4766 }, { "epoch": 0.1456017104459377, "grad_norm": 0.4072701036930084, "learning_rate": 4.742985854883221e-05, "loss": 4.4121, "step": 4767 }, { "epoch": 0.14563225412339645, "grad_norm": 0.39462026953697205, "learning_rate": 4.7428799007379154e-05, "loss": 4.3755, "step": 4768 }, { "epoch": 0.14566279780085523, "grad_norm": 0.38704177737236023, "learning_rate": 4.7427739259412615e-05, "loss": 4.3052, "step": 4769 }, { "epoch": 0.14569334147831398, "grad_norm": 0.4036296010017395, "learning_rate": 4.742667930494236e-05, "loss": 4.4424, "step": 4770 }, { "epoch": 0.14572388515577275, "grad_norm": 0.3920794725418091, "learning_rate": 4.7425619143978126e-05, "loss": 4.4138, "step": 4771 }, { "epoch": 0.14575442883323153, "grad_norm": 0.3872860372066498, "learning_rate": 4.742455877652969e-05, "loss": 4.4191, "step": 4772 }, { "epoch": 0.14578497251069028, "grad_norm": 0.39057764410972595, "learning_rate": 4.742349820260682e-05, "loss": 4.4092, "step": 4773 }, { "epoch": 0.14581551618814906, "grad_norm": 0.39108210802078247, "learning_rate": 4.742243742221927e-05, "loss": 4.3648, "step": 4774 }, { "epoch": 0.1458460598656078, "grad_norm": 0.3951932489871979, "learning_rate": 4.7421376435376806e-05, "loss": 4.4564, "step": 4775 }, { "epoch": 0.14587660354306659, "grad_norm": 0.4051594138145447, "learning_rate": 4.74203152420892e-05, "loss": 4.4636, "step": 4776 }, { "epoch": 0.14590714722052536, "grad_norm": 0.4088689982891083, "learning_rate": 4.741925384236623e-05, "loss": 4.426, "step": 4777 }, { "epoch": 0.1459376908979841, "grad_norm": 0.3896114230155945, "learning_rate": 4.741819223621766e-05, "loss": 4.3614, "step": 4778 }, { "epoch": 0.1459682345754429, "grad_norm": 0.3841766119003296, "learning_rate": 4.741713042365326e-05, "loss": 4.4363, "step": 4779 }, { "epoch": 0.14599877825290164, "grad_norm": 0.40580981969833374, "learning_rate": 4.7416068404682826e-05, "loss": 4.4261, "step": 4780 }, { "epoch": 0.14602932193036042, "grad_norm": 0.40376585721969604, "learning_rate": 4.741500617931612e-05, "loss": 4.4418, "step": 4781 }, { "epoch": 0.1460598656078192, "grad_norm": 0.38338905572891235, "learning_rate": 4.741394374756293e-05, "loss": 4.2774, "step": 4782 }, { "epoch": 0.14609040928527794, "grad_norm": 0.39539554715156555, "learning_rate": 4.741288110943303e-05, "loss": 4.4313, "step": 4783 }, { "epoch": 0.14612095296273672, "grad_norm": 0.4055115282535553, "learning_rate": 4.7411818264936214e-05, "loss": 4.3897, "step": 4784 }, { "epoch": 0.14615149664019547, "grad_norm": 0.39765429496765137, "learning_rate": 4.7410755214082265e-05, "loss": 4.4493, "step": 4785 }, { "epoch": 0.14618204031765425, "grad_norm": 0.3909164071083069, "learning_rate": 4.740969195688097e-05, "loss": 4.4963, "step": 4786 }, { "epoch": 0.146212583995113, "grad_norm": 0.4018389880657196, "learning_rate": 4.740862849334212e-05, "loss": 4.3274, "step": 4787 }, { "epoch": 0.14624312767257178, "grad_norm": 0.38403111696243286, "learning_rate": 4.74075648234755e-05, "loss": 4.4226, "step": 4788 }, { "epoch": 0.14627367135003055, "grad_norm": 0.3864014446735382, "learning_rate": 4.740650094729092e-05, "loss": 4.3894, "step": 4789 }, { "epoch": 0.1463042150274893, "grad_norm": 0.3822750747203827, "learning_rate": 4.740543686479816e-05, "loss": 4.4011, "step": 4790 }, { "epoch": 0.14633475870494808, "grad_norm": 0.4070213735103607, "learning_rate": 4.7404372576007015e-05, "loss": 4.4435, "step": 4791 }, { "epoch": 0.14636530238240683, "grad_norm": 0.3944932818412781, "learning_rate": 4.7403308080927306e-05, "loss": 4.3811, "step": 4792 }, { "epoch": 0.1463958460598656, "grad_norm": 0.41245096921920776, "learning_rate": 4.740224337956881e-05, "loss": 4.4028, "step": 4793 }, { "epoch": 0.14642638973732439, "grad_norm": 0.40876221656799316, "learning_rate": 4.740117847194136e-05, "loss": 4.3934, "step": 4794 }, { "epoch": 0.14645693341478314, "grad_norm": 0.4077862799167633, "learning_rate": 4.740011335805472e-05, "loss": 4.4382, "step": 4795 }, { "epoch": 0.1464874770922419, "grad_norm": 0.374273419380188, "learning_rate": 4.739904803791873e-05, "loss": 4.3418, "step": 4796 }, { "epoch": 0.14651802076970066, "grad_norm": 0.3796681761741638, "learning_rate": 4.739798251154318e-05, "loss": 4.306, "step": 4797 }, { "epoch": 0.14654856444715944, "grad_norm": 0.4132246971130371, "learning_rate": 4.73969167789379e-05, "loss": 4.4481, "step": 4798 }, { "epoch": 0.1465791081246182, "grad_norm": 0.3935680091381073, "learning_rate": 4.739585084011269e-05, "loss": 4.4273, "step": 4799 }, { "epoch": 0.14660965180207697, "grad_norm": 0.4102557599544525, "learning_rate": 4.739478469507736e-05, "loss": 4.4354, "step": 4800 }, { "epoch": 0.14664019547953575, "grad_norm": 0.3985564708709717, "learning_rate": 4.739371834384174e-05, "loss": 4.3682, "step": 4801 }, { "epoch": 0.1466707391569945, "grad_norm": 0.3859991729259491, "learning_rate": 4.7392651786415634e-05, "loss": 4.38, "step": 4802 }, { "epoch": 0.14670128283445327, "grad_norm": 0.39985254406929016, "learning_rate": 4.739158502280888e-05, "loss": 4.3872, "step": 4803 }, { "epoch": 0.14673182651191202, "grad_norm": 0.3778911530971527, "learning_rate": 4.739051805303128e-05, "loss": 4.4246, "step": 4804 }, { "epoch": 0.1467623701893708, "grad_norm": 0.39752236008644104, "learning_rate": 4.738945087709267e-05, "loss": 4.422, "step": 4805 }, { "epoch": 0.14679291386682958, "grad_norm": 0.39033573865890503, "learning_rate": 4.738838349500288e-05, "loss": 4.3634, "step": 4806 }, { "epoch": 0.14682345754428833, "grad_norm": 0.40986520051956177, "learning_rate": 4.738731590677173e-05, "loss": 4.3781, "step": 4807 }, { "epoch": 0.1468540012217471, "grad_norm": 0.3971671760082245, "learning_rate": 4.7386248112409046e-05, "loss": 4.4498, "step": 4808 }, { "epoch": 0.14688454489920585, "grad_norm": 0.38529717922210693, "learning_rate": 4.738518011192468e-05, "loss": 4.2606, "step": 4809 }, { "epoch": 0.14691508857666463, "grad_norm": 0.40009984374046326, "learning_rate": 4.738411190532844e-05, "loss": 4.3299, "step": 4810 }, { "epoch": 0.1469456322541234, "grad_norm": 0.40225183963775635, "learning_rate": 4.7383043492630176e-05, "loss": 4.2984, "step": 4811 }, { "epoch": 0.14697617593158216, "grad_norm": 0.40179356932640076, "learning_rate": 4.738197487383972e-05, "loss": 4.3713, "step": 4812 }, { "epoch": 0.14700671960904094, "grad_norm": 0.4060264229774475, "learning_rate": 4.738090604896691e-05, "loss": 4.3589, "step": 4813 }, { "epoch": 0.1470372632864997, "grad_norm": 0.39277780055999756, "learning_rate": 4.73798370180216e-05, "loss": 4.407, "step": 4814 }, { "epoch": 0.14706780696395846, "grad_norm": 0.39100414514541626, "learning_rate": 4.737876778101362e-05, "loss": 4.4136, "step": 4815 }, { "epoch": 0.1470983506414172, "grad_norm": 0.39618319272994995, "learning_rate": 4.737769833795282e-05, "loss": 4.4427, "step": 4816 }, { "epoch": 0.147128894318876, "grad_norm": 0.3829238712787628, "learning_rate": 4.737662868884904e-05, "loss": 4.3814, "step": 4817 }, { "epoch": 0.14715943799633477, "grad_norm": 0.3844204843044281, "learning_rate": 4.737555883371214e-05, "loss": 4.4569, "step": 4818 }, { "epoch": 0.14718998167379352, "grad_norm": 0.40601852536201477, "learning_rate": 4.737448877255197e-05, "loss": 4.4123, "step": 4819 }, { "epoch": 0.1472205253512523, "grad_norm": 0.3870425820350647, "learning_rate": 4.737341850537837e-05, "loss": 4.321, "step": 4820 }, { "epoch": 0.14725106902871105, "grad_norm": 0.39010611176490784, "learning_rate": 4.737234803220121e-05, "loss": 4.4766, "step": 4821 }, { "epoch": 0.14728161270616982, "grad_norm": 0.39626169204711914, "learning_rate": 4.737127735303033e-05, "loss": 4.4336, "step": 4822 }, { "epoch": 0.1473121563836286, "grad_norm": 0.3933098316192627, "learning_rate": 4.73702064678756e-05, "loss": 4.4346, "step": 4823 }, { "epoch": 0.14734270006108735, "grad_norm": 0.3923516869544983, "learning_rate": 4.736913537674688e-05, "loss": 4.427, "step": 4824 }, { "epoch": 0.14737324373854613, "grad_norm": 0.38519591093063354, "learning_rate": 4.736806407965403e-05, "loss": 4.4289, "step": 4825 }, { "epoch": 0.14740378741600488, "grad_norm": 0.3872932493686676, "learning_rate": 4.736699257660692e-05, "loss": 4.3123, "step": 4826 }, { "epoch": 0.14743433109346366, "grad_norm": 0.39338672161102295, "learning_rate": 4.7365920867615395e-05, "loss": 4.419, "step": 4827 }, { "epoch": 0.14746487477092243, "grad_norm": 0.39772653579711914, "learning_rate": 4.7364848952689346e-05, "loss": 4.471, "step": 4828 }, { "epoch": 0.14749541844838118, "grad_norm": 0.3807772099971771, "learning_rate": 4.736377683183863e-05, "loss": 4.3992, "step": 4829 }, { "epoch": 0.14752596212583996, "grad_norm": 0.3893548846244812, "learning_rate": 4.736270450507312e-05, "loss": 4.4517, "step": 4830 }, { "epoch": 0.1475565058032987, "grad_norm": 0.38506171107292175, "learning_rate": 4.7361631972402696e-05, "loss": 4.4051, "step": 4831 }, { "epoch": 0.1475870494807575, "grad_norm": 0.3964652717113495, "learning_rate": 4.736055923383723e-05, "loss": 4.4311, "step": 4832 }, { "epoch": 0.14761759315821624, "grad_norm": 0.3879786431789398, "learning_rate": 4.73594862893866e-05, "loss": 4.5113, "step": 4833 }, { "epoch": 0.14764813683567501, "grad_norm": 0.3867301940917969, "learning_rate": 4.735841313906068e-05, "loss": 4.3898, "step": 4834 }, { "epoch": 0.1476786805131338, "grad_norm": 0.38824015855789185, "learning_rate": 4.7357339782869356e-05, "loss": 4.4104, "step": 4835 }, { "epoch": 0.14770922419059254, "grad_norm": 0.378303200006485, "learning_rate": 4.735626622082251e-05, "loss": 4.4218, "step": 4836 }, { "epoch": 0.14773976786805132, "grad_norm": 0.3866661787033081, "learning_rate": 4.7355192452930026e-05, "loss": 4.3768, "step": 4837 }, { "epoch": 0.14777031154551007, "grad_norm": 0.36584168672561646, "learning_rate": 4.735411847920179e-05, "loss": 4.3532, "step": 4838 }, { "epoch": 0.14780085522296885, "grad_norm": 0.3830776512622833, "learning_rate": 4.7353044299647696e-05, "loss": 4.3815, "step": 4839 }, { "epoch": 0.14783139890042762, "grad_norm": 0.3956747055053711, "learning_rate": 4.7351969914277624e-05, "loss": 4.3399, "step": 4840 }, { "epoch": 0.14786194257788637, "grad_norm": 0.3780020773410797, "learning_rate": 4.735089532310148e-05, "loss": 4.357, "step": 4841 }, { "epoch": 0.14789248625534515, "grad_norm": 0.389981210231781, "learning_rate": 4.734982052612914e-05, "loss": 4.4149, "step": 4842 }, { "epoch": 0.1479230299328039, "grad_norm": 0.3861784040927887, "learning_rate": 4.7348745523370524e-05, "loss": 4.4321, "step": 4843 }, { "epoch": 0.14795357361026268, "grad_norm": 0.38993993401527405, "learning_rate": 4.734767031483551e-05, "loss": 4.3821, "step": 4844 }, { "epoch": 0.14798411728772143, "grad_norm": 0.38300105929374695, "learning_rate": 4.734659490053401e-05, "loss": 4.3155, "step": 4845 }, { "epoch": 0.1480146609651802, "grad_norm": 0.3803233504295349, "learning_rate": 4.7345519280475914e-05, "loss": 4.4168, "step": 4846 }, { "epoch": 0.14804520464263898, "grad_norm": 0.3826195299625397, "learning_rate": 4.7344443454671136e-05, "loss": 4.4246, "step": 4847 }, { "epoch": 0.14807574832009773, "grad_norm": 0.3995177447795868, "learning_rate": 4.7343367423129584e-05, "loss": 4.4289, "step": 4848 }, { "epoch": 0.1481062919975565, "grad_norm": 0.3875936269760132, "learning_rate": 4.734229118586115e-05, "loss": 4.3536, "step": 4849 }, { "epoch": 0.14813683567501526, "grad_norm": 0.3958425521850586, "learning_rate": 4.7341214742875764e-05, "loss": 4.4271, "step": 4850 }, { "epoch": 0.14816737935247404, "grad_norm": 0.38133594393730164, "learning_rate": 4.734013809418333e-05, "loss": 4.3464, "step": 4851 }, { "epoch": 0.14819792302993282, "grad_norm": 0.39460253715515137, "learning_rate": 4.733906123979375e-05, "loss": 4.4326, "step": 4852 }, { "epoch": 0.14822846670739157, "grad_norm": 0.3925498127937317, "learning_rate": 4.733798417971695e-05, "loss": 4.3686, "step": 4853 }, { "epoch": 0.14825901038485034, "grad_norm": 0.3850044310092926, "learning_rate": 4.733690691396284e-05, "loss": 4.4406, "step": 4854 }, { "epoch": 0.1482895540623091, "grad_norm": 0.4158641993999481, "learning_rate": 4.733582944254135e-05, "loss": 4.3887, "step": 4855 }, { "epoch": 0.14832009773976787, "grad_norm": 0.3933291733264923, "learning_rate": 4.733475176546239e-05, "loss": 4.4424, "step": 4856 }, { "epoch": 0.14835064141722665, "grad_norm": 0.3838435411453247, "learning_rate": 4.733367388273589e-05, "loss": 4.3604, "step": 4857 }, { "epoch": 0.1483811850946854, "grad_norm": 0.386440247297287, "learning_rate": 4.733259579437177e-05, "loss": 4.3694, "step": 4858 }, { "epoch": 0.14841172877214417, "grad_norm": 0.4058396816253662, "learning_rate": 4.733151750037996e-05, "loss": 4.4228, "step": 4859 }, { "epoch": 0.14844227244960292, "grad_norm": 0.38133135437965393, "learning_rate": 4.733043900077039e-05, "loss": 4.4303, "step": 4860 }, { "epoch": 0.1484728161270617, "grad_norm": 0.39341625571250916, "learning_rate": 4.732936029555298e-05, "loss": 4.4605, "step": 4861 }, { "epoch": 0.14850335980452045, "grad_norm": 0.39043039083480835, "learning_rate": 4.732828138473767e-05, "loss": 4.4454, "step": 4862 }, { "epoch": 0.14853390348197923, "grad_norm": 0.39491939544677734, "learning_rate": 4.7327202268334395e-05, "loss": 4.2744, "step": 4863 }, { "epoch": 0.148564447159438, "grad_norm": 0.37862712144851685, "learning_rate": 4.732612294635309e-05, "loss": 4.3913, "step": 4864 }, { "epoch": 0.14859499083689676, "grad_norm": 0.3778449594974518, "learning_rate": 4.7325043418803693e-05, "loss": 4.4164, "step": 4865 }, { "epoch": 0.14862553451435553, "grad_norm": 0.4010164439678192, "learning_rate": 4.732396368569614e-05, "loss": 4.4724, "step": 4866 }, { "epoch": 0.14865607819181428, "grad_norm": 0.3781326413154602, "learning_rate": 4.7322883747040376e-05, "loss": 4.3888, "step": 4867 }, { "epoch": 0.14868662186927306, "grad_norm": 0.3968519866466522, "learning_rate": 4.7321803602846345e-05, "loss": 4.3733, "step": 4868 }, { "epoch": 0.14871716554673184, "grad_norm": 0.38480502367019653, "learning_rate": 4.732072325312399e-05, "loss": 4.4455, "step": 4869 }, { "epoch": 0.1487477092241906, "grad_norm": 0.38387352228164673, "learning_rate": 4.731964269788326e-05, "loss": 4.4025, "step": 4870 }, { "epoch": 0.14877825290164937, "grad_norm": 0.3761664927005768, "learning_rate": 4.731856193713411e-05, "loss": 4.3769, "step": 4871 }, { "epoch": 0.14880879657910812, "grad_norm": 0.3953249454498291, "learning_rate": 4.731748097088647e-05, "loss": 4.4349, "step": 4872 }, { "epoch": 0.1488393402565669, "grad_norm": 0.4016065299510956, "learning_rate": 4.731639979915032e-05, "loss": 4.4235, "step": 4873 }, { "epoch": 0.14886988393402564, "grad_norm": 0.4017185568809509, "learning_rate": 4.7315318421935605e-05, "loss": 4.3273, "step": 4874 }, { "epoch": 0.14890042761148442, "grad_norm": 0.39591193199157715, "learning_rate": 4.731423683925228e-05, "loss": 4.4483, "step": 4875 }, { "epoch": 0.1489309712889432, "grad_norm": 0.4039098024368286, "learning_rate": 4.7313155051110297e-05, "loss": 4.3765, "step": 4876 }, { "epoch": 0.14896151496640195, "grad_norm": 0.4002418518066406, "learning_rate": 4.7312073057519626e-05, "loss": 4.3245, "step": 4877 }, { "epoch": 0.14899205864386073, "grad_norm": 0.39526957273483276, "learning_rate": 4.731099085849023e-05, "loss": 4.4259, "step": 4878 }, { "epoch": 0.14902260232131948, "grad_norm": 0.39072439074516296, "learning_rate": 4.730990845403206e-05, "loss": 4.4502, "step": 4879 }, { "epoch": 0.14905314599877825, "grad_norm": 0.3891407549381256, "learning_rate": 4.73088258441551e-05, "loss": 4.3448, "step": 4880 }, { "epoch": 0.14908368967623703, "grad_norm": 0.37676867842674255, "learning_rate": 4.7307743028869314e-05, "loss": 4.4033, "step": 4881 }, { "epoch": 0.14911423335369578, "grad_norm": 0.4118727147579193, "learning_rate": 4.7306660008184665e-05, "loss": 4.3615, "step": 4882 }, { "epoch": 0.14914477703115456, "grad_norm": 0.3864165246486664, "learning_rate": 4.730557678211113e-05, "loss": 4.4352, "step": 4883 }, { "epoch": 0.1491753207086133, "grad_norm": 0.37638118863105774, "learning_rate": 4.730449335065867e-05, "loss": 4.3205, "step": 4884 }, { "epoch": 0.14920586438607208, "grad_norm": 0.38680657744407654, "learning_rate": 4.7303409713837284e-05, "loss": 4.2982, "step": 4885 }, { "epoch": 0.14923640806353086, "grad_norm": 0.3828500509262085, "learning_rate": 4.730232587165693e-05, "loss": 4.4779, "step": 4886 }, { "epoch": 0.1492669517409896, "grad_norm": 0.3961436152458191, "learning_rate": 4.7301241824127603e-05, "loss": 4.4465, "step": 4887 }, { "epoch": 0.1492974954184484, "grad_norm": 0.392037570476532, "learning_rate": 4.7300157571259274e-05, "loss": 4.2721, "step": 4888 }, { "epoch": 0.14932803909590714, "grad_norm": 0.39753854274749756, "learning_rate": 4.729907311306192e-05, "loss": 4.481, "step": 4889 }, { "epoch": 0.14935858277336592, "grad_norm": 0.3969157040119171, "learning_rate": 4.7297988449545546e-05, "loss": 4.3607, "step": 4890 }, { "epoch": 0.14938912645082467, "grad_norm": 0.3840113580226898, "learning_rate": 4.729690358072012e-05, "loss": 4.3397, "step": 4891 }, { "epoch": 0.14941967012828344, "grad_norm": 0.38425543904304504, "learning_rate": 4.7295818506595645e-05, "loss": 4.3567, "step": 4892 }, { "epoch": 0.14945021380574222, "grad_norm": 0.3896098732948303, "learning_rate": 4.72947332271821e-05, "loss": 4.3611, "step": 4893 }, { "epoch": 0.14948075748320097, "grad_norm": 0.37642693519592285, "learning_rate": 4.729364774248949e-05, "loss": 4.4604, "step": 4894 }, { "epoch": 0.14951130116065975, "grad_norm": 0.37867221236228943, "learning_rate": 4.72925620525278e-05, "loss": 4.3711, "step": 4895 }, { "epoch": 0.1495418448381185, "grad_norm": 0.3823448717594147, "learning_rate": 4.729147615730702e-05, "loss": 4.2526, "step": 4896 }, { "epoch": 0.14957238851557728, "grad_norm": 0.38131386041641235, "learning_rate": 4.7290390056837174e-05, "loss": 4.3917, "step": 4897 }, { "epoch": 0.14960293219303605, "grad_norm": 0.38810089230537415, "learning_rate": 4.7289303751128234e-05, "loss": 4.455, "step": 4898 }, { "epoch": 0.1496334758704948, "grad_norm": 0.38682490587234497, "learning_rate": 4.7288217240190225e-05, "loss": 4.3678, "step": 4899 }, { "epoch": 0.14966401954795358, "grad_norm": 0.371347039937973, "learning_rate": 4.728713052403313e-05, "loss": 4.4354, "step": 4900 }, { "epoch": 0.14969456322541233, "grad_norm": 0.38480931520462036, "learning_rate": 4.7286043602666976e-05, "loss": 4.3419, "step": 4901 }, { "epoch": 0.1497251069028711, "grad_norm": 0.38383299112319946, "learning_rate": 4.728495647610175e-05, "loss": 4.4317, "step": 4902 }, { "epoch": 0.14975565058032989, "grad_norm": 0.3827291429042816, "learning_rate": 4.728386914434748e-05, "loss": 4.311, "step": 4903 }, { "epoch": 0.14978619425778864, "grad_norm": 0.390034556388855, "learning_rate": 4.728278160741416e-05, "loss": 4.4813, "step": 4904 }, { "epoch": 0.1498167379352474, "grad_norm": 0.41640153527259827, "learning_rate": 4.7281693865311816e-05, "loss": 4.3546, "step": 4905 }, { "epoch": 0.14984728161270616, "grad_norm": 0.3835924565792084, "learning_rate": 4.728060591805047e-05, "loss": 4.3639, "step": 4906 }, { "epoch": 0.14987782529016494, "grad_norm": 0.38097020983695984, "learning_rate": 4.727951776564012e-05, "loss": 4.386, "step": 4907 }, { "epoch": 0.1499083689676237, "grad_norm": 0.38459187746047974, "learning_rate": 4.7278429408090795e-05, "loss": 4.3501, "step": 4908 }, { "epoch": 0.14993891264508247, "grad_norm": 0.3888055086135864, "learning_rate": 4.7277340845412524e-05, "loss": 4.4663, "step": 4909 }, { "epoch": 0.14996945632254124, "grad_norm": 0.38636845350265503, "learning_rate": 4.727625207761531e-05, "loss": 4.391, "step": 4910 }, { "epoch": 0.15, "grad_norm": 0.3853428363800049, "learning_rate": 4.72751631047092e-05, "loss": 4.4841, "step": 4911 }, { "epoch": 0.15003054367745877, "grad_norm": 0.38837340474128723, "learning_rate": 4.727407392670421e-05, "loss": 4.4531, "step": 4912 }, { "epoch": 0.15006108735491752, "grad_norm": 0.4040376543998718, "learning_rate": 4.7272984543610366e-05, "loss": 4.4619, "step": 4913 }, { "epoch": 0.1500916310323763, "grad_norm": 0.37702736258506775, "learning_rate": 4.72718949554377e-05, "loss": 4.3495, "step": 4914 }, { "epoch": 0.15012217470983508, "grad_norm": 0.38910335302352905, "learning_rate": 4.727080516219625e-05, "loss": 4.3929, "step": 4915 }, { "epoch": 0.15015271838729383, "grad_norm": 0.3877011835575104, "learning_rate": 4.726971516389604e-05, "loss": 4.3456, "step": 4916 }, { "epoch": 0.1501832620647526, "grad_norm": 0.37939921021461487, "learning_rate": 4.7268624960547115e-05, "loss": 4.3666, "step": 4917 }, { "epoch": 0.15021380574221135, "grad_norm": 0.3808557689189911, "learning_rate": 4.7267534552159515e-05, "loss": 4.3354, "step": 4918 }, { "epoch": 0.15024434941967013, "grad_norm": 0.38671988248825073, "learning_rate": 4.7266443938743274e-05, "loss": 4.3526, "step": 4919 }, { "epoch": 0.15027489309712888, "grad_norm": 0.3755980432033539, "learning_rate": 4.7265353120308434e-05, "loss": 4.4391, "step": 4920 }, { "epoch": 0.15030543677458766, "grad_norm": 0.3876818120479584, "learning_rate": 4.7264262096865045e-05, "loss": 4.2995, "step": 4921 }, { "epoch": 0.15033598045204644, "grad_norm": 0.3852507770061493, "learning_rate": 4.7263170868423134e-05, "loss": 4.4047, "step": 4922 }, { "epoch": 0.15036652412950519, "grad_norm": 0.381369411945343, "learning_rate": 4.726207943499277e-05, "loss": 4.327, "step": 4923 }, { "epoch": 0.15039706780696396, "grad_norm": 0.38515549898147583, "learning_rate": 4.7260987796584e-05, "loss": 4.3627, "step": 4924 }, { "epoch": 0.1504276114844227, "grad_norm": 0.3893296718597412, "learning_rate": 4.7259895953206865e-05, "loss": 4.3047, "step": 4925 }, { "epoch": 0.1504581551618815, "grad_norm": 0.3900722861289978, "learning_rate": 4.7258803904871424e-05, "loss": 4.3974, "step": 4926 }, { "epoch": 0.15048869883934027, "grad_norm": 0.39412859082221985, "learning_rate": 4.7257711651587735e-05, "loss": 4.4443, "step": 4927 }, { "epoch": 0.15051924251679902, "grad_norm": 0.38400131464004517, "learning_rate": 4.725661919336585e-05, "loss": 4.3354, "step": 4928 }, { "epoch": 0.1505497861942578, "grad_norm": 0.397957444190979, "learning_rate": 4.7255526530215824e-05, "loss": 4.3958, "step": 4929 }, { "epoch": 0.15058032987171655, "grad_norm": 0.3824980556964874, "learning_rate": 4.725443366214772e-05, "loss": 4.3433, "step": 4930 }, { "epoch": 0.15061087354917532, "grad_norm": 0.39926913380622864, "learning_rate": 4.725334058917161e-05, "loss": 4.4351, "step": 4931 }, { "epoch": 0.1506414172266341, "grad_norm": 0.3973643481731415, "learning_rate": 4.725224731129755e-05, "loss": 4.4233, "step": 4932 }, { "epoch": 0.15067196090409285, "grad_norm": 0.39010483026504517, "learning_rate": 4.72511538285356e-05, "loss": 4.3695, "step": 4933 }, { "epoch": 0.15070250458155163, "grad_norm": 0.37790435552597046, "learning_rate": 4.725006014089585e-05, "loss": 4.2653, "step": 4934 }, { "epoch": 0.15073304825901038, "grad_norm": 0.39379554986953735, "learning_rate": 4.724896624838835e-05, "loss": 4.3989, "step": 4935 }, { "epoch": 0.15076359193646915, "grad_norm": 0.3916170597076416, "learning_rate": 4.724787215102318e-05, "loss": 4.3854, "step": 4936 }, { "epoch": 0.1507941356139279, "grad_norm": 0.3833298981189728, "learning_rate": 4.724677784881041e-05, "loss": 4.3219, "step": 4937 }, { "epoch": 0.15082467929138668, "grad_norm": 0.4007095992565155, "learning_rate": 4.7245683341760116e-05, "loss": 4.3846, "step": 4938 }, { "epoch": 0.15085522296884546, "grad_norm": 0.38327398896217346, "learning_rate": 4.724458862988238e-05, "loss": 4.3874, "step": 4939 }, { "epoch": 0.1508857666463042, "grad_norm": 0.3949730396270752, "learning_rate": 4.7243493713187285e-05, "loss": 4.3634, "step": 4940 }, { "epoch": 0.150916310323763, "grad_norm": 0.40244340896606445, "learning_rate": 4.72423985916849e-05, "loss": 4.4578, "step": 4941 }, { "epoch": 0.15094685400122174, "grad_norm": 0.39440736174583435, "learning_rate": 4.7241303265385315e-05, "loss": 4.467, "step": 4942 }, { "epoch": 0.1509773976786805, "grad_norm": 0.3761913776397705, "learning_rate": 4.7240207734298616e-05, "loss": 4.3729, "step": 4943 }, { "epoch": 0.1510079413561393, "grad_norm": 0.38452279567718506, "learning_rate": 4.723911199843489e-05, "loss": 4.3445, "step": 4944 }, { "epoch": 0.15103848503359804, "grad_norm": 0.402288019657135, "learning_rate": 4.723801605780423e-05, "loss": 4.3549, "step": 4945 }, { "epoch": 0.15106902871105682, "grad_norm": 0.39446812868118286, "learning_rate": 4.723691991241672e-05, "loss": 4.3991, "step": 4946 }, { "epoch": 0.15109957238851557, "grad_norm": 0.39173460006713867, "learning_rate": 4.7235823562282455e-05, "loss": 4.3588, "step": 4947 }, { "epoch": 0.15113011606597435, "grad_norm": 0.3900526762008667, "learning_rate": 4.7234727007411536e-05, "loss": 4.4156, "step": 4948 }, { "epoch": 0.1511606597434331, "grad_norm": 0.39665794372558594, "learning_rate": 4.723363024781404e-05, "loss": 4.4035, "step": 4949 }, { "epoch": 0.15119120342089187, "grad_norm": 0.396027535200119, "learning_rate": 4.7232533283500094e-05, "loss": 4.3612, "step": 4950 }, { "epoch": 0.15122174709835065, "grad_norm": 0.38171491026878357, "learning_rate": 4.723143611447978e-05, "loss": 4.418, "step": 4951 }, { "epoch": 0.1512522907758094, "grad_norm": 0.38407742977142334, "learning_rate": 4.723033874076319e-05, "loss": 4.3437, "step": 4952 }, { "epoch": 0.15128283445326818, "grad_norm": 0.37531372904777527, "learning_rate": 4.722924116236045e-05, "loss": 4.383, "step": 4953 }, { "epoch": 0.15131337813072693, "grad_norm": 0.37511876225471497, "learning_rate": 4.722814337928166e-05, "loss": 4.3885, "step": 4954 }, { "epoch": 0.1513439218081857, "grad_norm": 0.39540430903434753, "learning_rate": 4.722704539153693e-05, "loss": 4.4784, "step": 4955 }, { "epoch": 0.15137446548564448, "grad_norm": 0.3963756263256073, "learning_rate": 4.7225947199136355e-05, "loss": 4.4416, "step": 4956 }, { "epoch": 0.15140500916310323, "grad_norm": 0.3881111145019531, "learning_rate": 4.7224848802090064e-05, "loss": 4.4255, "step": 4957 }, { "epoch": 0.151435552840562, "grad_norm": 0.3922273516654968, "learning_rate": 4.7223750200408155e-05, "loss": 4.3306, "step": 4958 }, { "epoch": 0.15146609651802076, "grad_norm": 0.39505666494369507, "learning_rate": 4.722265139410075e-05, "loss": 4.3908, "step": 4959 }, { "epoch": 0.15149664019547954, "grad_norm": 0.4039328098297119, "learning_rate": 4.7221552383177984e-05, "loss": 4.4496, "step": 4960 }, { "epoch": 0.15152718387293831, "grad_norm": 0.40386101603507996, "learning_rate": 4.722045316764994e-05, "loss": 4.3709, "step": 4961 }, { "epoch": 0.15155772755039706, "grad_norm": 0.3832661509513855, "learning_rate": 4.721935374752677e-05, "loss": 4.423, "step": 4962 }, { "epoch": 0.15158827122785584, "grad_norm": 0.4000338912010193, "learning_rate": 4.721825412281858e-05, "loss": 4.4336, "step": 4963 }, { "epoch": 0.1516188149053146, "grad_norm": 0.39760226011276245, "learning_rate": 4.7217154293535514e-05, "loss": 4.4134, "step": 4964 }, { "epoch": 0.15164935858277337, "grad_norm": 0.3864138126373291, "learning_rate": 4.7216054259687675e-05, "loss": 4.3872, "step": 4965 }, { "epoch": 0.15167990226023212, "grad_norm": 0.394002765417099, "learning_rate": 4.721495402128521e-05, "loss": 4.346, "step": 4966 }, { "epoch": 0.1517104459376909, "grad_norm": 0.39114290475845337, "learning_rate": 4.721385357833823e-05, "loss": 4.3381, "step": 4967 }, { "epoch": 0.15174098961514967, "grad_norm": 0.38896000385284424, "learning_rate": 4.7212752930856885e-05, "loss": 4.3598, "step": 4968 }, { "epoch": 0.15177153329260842, "grad_norm": 0.3921855390071869, "learning_rate": 4.72116520788513e-05, "loss": 4.3971, "step": 4969 }, { "epoch": 0.1518020769700672, "grad_norm": 0.38099202513694763, "learning_rate": 4.7210551022331615e-05, "loss": 4.4302, "step": 4970 }, { "epoch": 0.15183262064752595, "grad_norm": 0.39462071657180786, "learning_rate": 4.720944976130798e-05, "loss": 4.3492, "step": 4971 }, { "epoch": 0.15186316432498473, "grad_norm": 0.39411839842796326, "learning_rate": 4.72083482957905e-05, "loss": 4.4223, "step": 4972 }, { "epoch": 0.1518937080024435, "grad_norm": 0.39585062861442566, "learning_rate": 4.7207246625789354e-05, "loss": 4.4292, "step": 4973 }, { "epoch": 0.15192425167990226, "grad_norm": 0.37498196959495544, "learning_rate": 4.720614475131467e-05, "loss": 4.3226, "step": 4974 }, { "epoch": 0.15195479535736103, "grad_norm": 0.41313305497169495, "learning_rate": 4.7205042672376584e-05, "loss": 4.3448, "step": 4975 }, { "epoch": 0.15198533903481978, "grad_norm": 0.39095285534858704, "learning_rate": 4.7203940388985265e-05, "loss": 4.4077, "step": 4976 }, { "epoch": 0.15201588271227856, "grad_norm": 0.3865242302417755, "learning_rate": 4.720283790115084e-05, "loss": 4.3981, "step": 4977 }, { "epoch": 0.15204642638973734, "grad_norm": 0.37651246786117554, "learning_rate": 4.720173520888348e-05, "loss": 4.3624, "step": 4978 }, { "epoch": 0.1520769700671961, "grad_norm": 0.38390982151031494, "learning_rate": 4.720063231219333e-05, "loss": 4.3536, "step": 4979 }, { "epoch": 0.15210751374465487, "grad_norm": 0.39256376028060913, "learning_rate": 4.719952921109053e-05, "loss": 4.4476, "step": 4980 }, { "epoch": 0.15213805742211362, "grad_norm": 0.3963310122489929, "learning_rate": 4.7198425905585266e-05, "loss": 4.3854, "step": 4981 }, { "epoch": 0.1521686010995724, "grad_norm": 0.385456383228302, "learning_rate": 4.719732239568767e-05, "loss": 4.474, "step": 4982 }, { "epoch": 0.15219914477703114, "grad_norm": 0.3812547028064728, "learning_rate": 4.719621868140792e-05, "loss": 4.392, "step": 4983 }, { "epoch": 0.15222968845448992, "grad_norm": 0.40229400992393494, "learning_rate": 4.7195114762756174e-05, "loss": 4.4097, "step": 4984 }, { "epoch": 0.1522602321319487, "grad_norm": 0.40073418617248535, "learning_rate": 4.719401063974259e-05, "loss": 4.4451, "step": 4985 }, { "epoch": 0.15229077580940745, "grad_norm": 0.40804240107536316, "learning_rate": 4.719290631237735e-05, "loss": 4.3943, "step": 4986 }, { "epoch": 0.15232131948686622, "grad_norm": 0.4038657248020172, "learning_rate": 4.71918017806706e-05, "loss": 4.4764, "step": 4987 }, { "epoch": 0.15235186316432497, "grad_norm": 0.3757275938987732, "learning_rate": 4.7190697044632525e-05, "loss": 4.3164, "step": 4988 }, { "epoch": 0.15238240684178375, "grad_norm": 0.405484676361084, "learning_rate": 4.718959210427329e-05, "loss": 4.374, "step": 4989 }, { "epoch": 0.15241295051924253, "grad_norm": 0.3964695930480957, "learning_rate": 4.7188486959603076e-05, "loss": 4.4144, "step": 4990 }, { "epoch": 0.15244349419670128, "grad_norm": 0.3824530839920044, "learning_rate": 4.7187381610632045e-05, "loss": 4.386, "step": 4991 }, { "epoch": 0.15247403787416006, "grad_norm": 0.39465007185935974, "learning_rate": 4.7186276057370396e-05, "loss": 4.4597, "step": 4992 }, { "epoch": 0.1525045815516188, "grad_norm": 0.390718013048172, "learning_rate": 4.7185170299828286e-05, "loss": 4.4572, "step": 4993 }, { "epoch": 0.15253512522907758, "grad_norm": 0.4056754410266876, "learning_rate": 4.7184064338015913e-05, "loss": 4.3802, "step": 4994 }, { "epoch": 0.15256566890653633, "grad_norm": 0.38928893208503723, "learning_rate": 4.718295817194345e-05, "loss": 4.3529, "step": 4995 }, { "epoch": 0.1525962125839951, "grad_norm": 0.3832278847694397, "learning_rate": 4.7181851801621094e-05, "loss": 4.4187, "step": 4996 }, { "epoch": 0.1526267562614539, "grad_norm": 0.39728790521621704, "learning_rate": 4.7180745227059016e-05, "loss": 4.4274, "step": 4997 }, { "epoch": 0.15265729993891264, "grad_norm": 0.3938366770744324, "learning_rate": 4.7179638448267415e-05, "loss": 4.3989, "step": 4998 }, { "epoch": 0.15268784361637142, "grad_norm": 0.393830269575119, "learning_rate": 4.7178531465256476e-05, "loss": 4.4258, "step": 4999 }, { "epoch": 0.15271838729383017, "grad_norm": 0.38265401124954224, "learning_rate": 4.7177424278036395e-05, "loss": 4.3283, "step": 5000 }, { "epoch": 0.15274893097128894, "grad_norm": 0.39662477374076843, "learning_rate": 4.717631688661737e-05, "loss": 4.378, "step": 5001 }, { "epoch": 0.15277947464874772, "grad_norm": 0.39265647530555725, "learning_rate": 4.7175209291009594e-05, "loss": 4.449, "step": 5002 }, { "epoch": 0.15281001832620647, "grad_norm": 0.4016954302787781, "learning_rate": 4.717410149122327e-05, "loss": 4.3946, "step": 5003 }, { "epoch": 0.15284056200366525, "grad_norm": 0.3848099410533905, "learning_rate": 4.717299348726858e-05, "loss": 4.4282, "step": 5004 }, { "epoch": 0.152871105681124, "grad_norm": 0.3813588619232178, "learning_rate": 4.717188527915574e-05, "loss": 4.3574, "step": 5005 }, { "epoch": 0.15290164935858278, "grad_norm": 0.3825642764568329, "learning_rate": 4.717077686689496e-05, "loss": 4.4223, "step": 5006 }, { "epoch": 0.15293219303604155, "grad_norm": 0.41261789202690125, "learning_rate": 4.716966825049644e-05, "loss": 4.4542, "step": 5007 }, { "epoch": 0.1529627367135003, "grad_norm": 0.3882347643375397, "learning_rate": 4.716855942997037e-05, "loss": 4.2923, "step": 5008 }, { "epoch": 0.15299328039095908, "grad_norm": 0.371092289686203, "learning_rate": 4.716745040532699e-05, "loss": 4.4671, "step": 5009 }, { "epoch": 0.15302382406841783, "grad_norm": 0.39451202750205994, "learning_rate": 4.716634117657649e-05, "loss": 4.4338, "step": 5010 }, { "epoch": 0.1530543677458766, "grad_norm": 0.3964473605155945, "learning_rate": 4.71652317437291e-05, "loss": 4.3883, "step": 5011 }, { "epoch": 0.15308491142333536, "grad_norm": 0.3894945979118347, "learning_rate": 4.716412210679502e-05, "loss": 4.2726, "step": 5012 }, { "epoch": 0.15311545510079413, "grad_norm": 0.38984066247940063, "learning_rate": 4.7163012265784467e-05, "loss": 4.4136, "step": 5013 }, { "epoch": 0.1531459987782529, "grad_norm": 0.38136452436447144, "learning_rate": 4.716190222070767e-05, "loss": 4.4903, "step": 5014 }, { "epoch": 0.15317654245571166, "grad_norm": 0.40210628509521484, "learning_rate": 4.716079197157484e-05, "loss": 4.3926, "step": 5015 }, { "epoch": 0.15320708613317044, "grad_norm": 0.37805265188217163, "learning_rate": 4.71596815183962e-05, "loss": 4.3104, "step": 5016 }, { "epoch": 0.1532376298106292, "grad_norm": 0.8795464634895325, "learning_rate": 4.715857086118199e-05, "loss": 4.4182, "step": 5017 }, { "epoch": 0.15326817348808797, "grad_norm": 0.3865940272808075, "learning_rate": 4.715745999994242e-05, "loss": 4.4003, "step": 5018 }, { "epoch": 0.15329871716554674, "grad_norm": 0.38204440474510193, "learning_rate": 4.715634893468773e-05, "loss": 4.3565, "step": 5019 }, { "epoch": 0.1533292608430055, "grad_norm": 0.3769178092479706, "learning_rate": 4.7155237665428135e-05, "loss": 4.4315, "step": 5020 }, { "epoch": 0.15335980452046427, "grad_norm": 0.38338664174079895, "learning_rate": 4.715412619217388e-05, "loss": 4.3876, "step": 5021 }, { "epoch": 0.15339034819792302, "grad_norm": 0.37626752257347107, "learning_rate": 4.7153014514935194e-05, "loss": 4.4152, "step": 5022 }, { "epoch": 0.1534208918753818, "grad_norm": 0.3900286853313446, "learning_rate": 4.715190263372231e-05, "loss": 4.3551, "step": 5023 }, { "epoch": 0.15345143555284055, "grad_norm": 0.39324676990509033, "learning_rate": 4.715079054854548e-05, "loss": 4.3679, "step": 5024 }, { "epoch": 0.15348197923029933, "grad_norm": 0.39343565702438354, "learning_rate": 4.714967825941492e-05, "loss": 4.4616, "step": 5025 }, { "epoch": 0.1535125229077581, "grad_norm": 0.3873358964920044, "learning_rate": 4.714856576634089e-05, "loss": 4.3772, "step": 5026 }, { "epoch": 0.15354306658521685, "grad_norm": 0.40393537282943726, "learning_rate": 4.7147453069333625e-05, "loss": 4.3506, "step": 5027 }, { "epoch": 0.15357361026267563, "grad_norm": 0.3906819820404053, "learning_rate": 4.714634016840337e-05, "loss": 4.4256, "step": 5028 }, { "epoch": 0.15360415394013438, "grad_norm": 0.375334233045578, "learning_rate": 4.714522706356038e-05, "loss": 4.4206, "step": 5029 }, { "epoch": 0.15363469761759316, "grad_norm": 0.3979925513267517, "learning_rate": 4.71441137548149e-05, "loss": 4.4605, "step": 5030 }, { "epoch": 0.15366524129505194, "grad_norm": 0.3830603063106537, "learning_rate": 4.7143000242177174e-05, "loss": 4.3858, "step": 5031 }, { "epoch": 0.15369578497251069, "grad_norm": 0.3921062648296356, "learning_rate": 4.7141886525657465e-05, "loss": 4.3722, "step": 5032 }, { "epoch": 0.15372632864996946, "grad_norm": 0.3788239359855652, "learning_rate": 4.714077260526602e-05, "loss": 4.2948, "step": 5033 }, { "epoch": 0.1537568723274282, "grad_norm": 0.3948690891265869, "learning_rate": 4.7139658481013094e-05, "loss": 4.4443, "step": 5034 }, { "epoch": 0.153787416004887, "grad_norm": 0.38586416840553284, "learning_rate": 4.713854415290896e-05, "loss": 4.3181, "step": 5035 }, { "epoch": 0.15381795968234577, "grad_norm": 0.388850599527359, "learning_rate": 4.713742962096386e-05, "loss": 4.3744, "step": 5036 }, { "epoch": 0.15384850335980452, "grad_norm": 0.39268815517425537, "learning_rate": 4.713631488518806e-05, "loss": 4.3636, "step": 5037 }, { "epoch": 0.1538790470372633, "grad_norm": 0.3888375461101532, "learning_rate": 4.713519994559184e-05, "loss": 4.3914, "step": 5038 }, { "epoch": 0.15390959071472204, "grad_norm": 0.3955232501029968, "learning_rate": 4.713408480218544e-05, "loss": 4.3932, "step": 5039 }, { "epoch": 0.15394013439218082, "grad_norm": 0.37529730796813965, "learning_rate": 4.713296945497914e-05, "loss": 4.3471, "step": 5040 }, { "epoch": 0.15397067806963957, "grad_norm": 0.38846325874328613, "learning_rate": 4.713185390398322e-05, "loss": 4.3763, "step": 5041 }, { "epoch": 0.15400122174709835, "grad_norm": 0.3909803032875061, "learning_rate": 4.713073814920794e-05, "loss": 4.3406, "step": 5042 }, { "epoch": 0.15403176542455713, "grad_norm": 0.3821331262588501, "learning_rate": 4.712962219066357e-05, "loss": 4.3435, "step": 5043 }, { "epoch": 0.15406230910201588, "grad_norm": 0.38340094685554504, "learning_rate": 4.7128506028360395e-05, "loss": 4.3173, "step": 5044 }, { "epoch": 0.15409285277947465, "grad_norm": 0.3978935480117798, "learning_rate": 4.7127389662308684e-05, "loss": 4.3333, "step": 5045 }, { "epoch": 0.1541233964569334, "grad_norm": 0.3896740674972534, "learning_rate": 4.712627309251872e-05, "loss": 4.3288, "step": 5046 }, { "epoch": 0.15415394013439218, "grad_norm": 0.3831506371498108, "learning_rate": 4.712515631900079e-05, "loss": 4.381, "step": 5047 }, { "epoch": 0.15418448381185096, "grad_norm": 0.39165735244750977, "learning_rate": 4.712403934176517e-05, "loss": 4.3655, "step": 5048 }, { "epoch": 0.1542150274893097, "grad_norm": 0.39403235912323, "learning_rate": 4.712292216082214e-05, "loss": 4.3117, "step": 5049 }, { "epoch": 0.15424557116676849, "grad_norm": 0.37968313694000244, "learning_rate": 4.7121804776181986e-05, "loss": 4.3469, "step": 5050 }, { "epoch": 0.15427611484422724, "grad_norm": 0.3978191614151001, "learning_rate": 4.712068718785501e-05, "loss": 4.4357, "step": 5051 }, { "epoch": 0.154306658521686, "grad_norm": 0.3747222125530243, "learning_rate": 4.7119569395851494e-05, "loss": 4.4045, "step": 5052 }, { "epoch": 0.1543372021991448, "grad_norm": 0.38681572675704956, "learning_rate": 4.711845140018173e-05, "loss": 4.3769, "step": 5053 }, { "epoch": 0.15436774587660354, "grad_norm": 0.37976041436195374, "learning_rate": 4.711733320085601e-05, "loss": 4.4206, "step": 5054 }, { "epoch": 0.15439828955406232, "grad_norm": 0.3834320306777954, "learning_rate": 4.7116214797884626e-05, "loss": 4.4304, "step": 5055 }, { "epoch": 0.15442883323152107, "grad_norm": 0.3909872770309448, "learning_rate": 4.711509619127788e-05, "loss": 4.361, "step": 5056 }, { "epoch": 0.15445937690897985, "grad_norm": 0.3834088146686554, "learning_rate": 4.711397738104608e-05, "loss": 4.427, "step": 5057 }, { "epoch": 0.1544899205864386, "grad_norm": 0.38718241453170776, "learning_rate": 4.711285836719952e-05, "loss": 4.3346, "step": 5058 }, { "epoch": 0.15452046426389737, "grad_norm": 0.39797264337539673, "learning_rate": 4.7111739149748505e-05, "loss": 4.3404, "step": 5059 }, { "epoch": 0.15455100794135615, "grad_norm": 0.39035359025001526, "learning_rate": 4.711061972870334e-05, "loss": 4.371, "step": 5060 }, { "epoch": 0.1545815516188149, "grad_norm": 0.3957643508911133, "learning_rate": 4.710950010407432e-05, "loss": 4.3351, "step": 5061 }, { "epoch": 0.15461209529627368, "grad_norm": 0.38298577070236206, "learning_rate": 4.7108380275871776e-05, "loss": 4.3853, "step": 5062 }, { "epoch": 0.15464263897373243, "grad_norm": 0.3938506841659546, "learning_rate": 4.7107260244106004e-05, "loss": 4.4297, "step": 5063 }, { "epoch": 0.1546731826511912, "grad_norm": 0.3885323703289032, "learning_rate": 4.7106140008787325e-05, "loss": 4.473, "step": 5064 }, { "epoch": 0.15470372632864998, "grad_norm": 0.3829442262649536, "learning_rate": 4.7105019569926046e-05, "loss": 4.3756, "step": 5065 }, { "epoch": 0.15473427000610873, "grad_norm": 0.37933245301246643, "learning_rate": 4.710389892753249e-05, "loss": 4.4209, "step": 5066 }, { "epoch": 0.1547648136835675, "grad_norm": 0.3940412998199463, "learning_rate": 4.710277808161696e-05, "loss": 4.4479, "step": 5067 }, { "epoch": 0.15479535736102626, "grad_norm": 0.39702460169792175, "learning_rate": 4.710165703218979e-05, "loss": 4.368, "step": 5068 }, { "epoch": 0.15482590103848504, "grad_norm": 0.3840528428554535, "learning_rate": 4.710053577926131e-05, "loss": 4.4768, "step": 5069 }, { "epoch": 0.1548564447159438, "grad_norm": 0.3965763449668884, "learning_rate": 4.709941432284183e-05, "loss": 4.4179, "step": 5070 }, { "epoch": 0.15488698839340256, "grad_norm": 0.3781406283378601, "learning_rate": 4.709829266294168e-05, "loss": 4.4122, "step": 5071 }, { "epoch": 0.15491753207086134, "grad_norm": 0.3954662084579468, "learning_rate": 4.709717079957119e-05, "loss": 4.4334, "step": 5072 }, { "epoch": 0.1549480757483201, "grad_norm": 0.3887535333633423, "learning_rate": 4.709604873274068e-05, "loss": 4.3945, "step": 5073 }, { "epoch": 0.15497861942577887, "grad_norm": 0.3883860409259796, "learning_rate": 4.70949264624605e-05, "loss": 4.4136, "step": 5074 }, { "epoch": 0.15500916310323762, "grad_norm": 0.38365933299064636, "learning_rate": 4.709380398874096e-05, "loss": 4.3523, "step": 5075 }, { "epoch": 0.1550397067806964, "grad_norm": 0.38254478573799133, "learning_rate": 4.709268131159241e-05, "loss": 4.3062, "step": 5076 }, { "epoch": 0.15507025045815517, "grad_norm": 0.38126951456069946, "learning_rate": 4.709155843102519e-05, "loss": 4.423, "step": 5077 }, { "epoch": 0.15510079413561392, "grad_norm": 0.3839385509490967, "learning_rate": 4.7090435347049634e-05, "loss": 4.348, "step": 5078 }, { "epoch": 0.1551313378130727, "grad_norm": 0.3884999454021454, "learning_rate": 4.708931205967607e-05, "loss": 4.3806, "step": 5079 }, { "epoch": 0.15516188149053145, "grad_norm": 0.392952561378479, "learning_rate": 4.7088188568914864e-05, "loss": 4.3235, "step": 5080 }, { "epoch": 0.15519242516799023, "grad_norm": 0.3738135099411011, "learning_rate": 4.7087064874776346e-05, "loss": 4.3864, "step": 5081 }, { "epoch": 0.155222968845449, "grad_norm": 0.3955651819705963, "learning_rate": 4.708594097727086e-05, "loss": 4.4231, "step": 5082 }, { "epoch": 0.15525351252290776, "grad_norm": 0.3766222298145294, "learning_rate": 4.7084816876408765e-05, "loss": 4.3791, "step": 5083 }, { "epoch": 0.15528405620036653, "grad_norm": 0.3858892321586609, "learning_rate": 4.708369257220041e-05, "loss": 4.3486, "step": 5084 }, { "epoch": 0.15531459987782528, "grad_norm": 0.38285067677497864, "learning_rate": 4.708256806465614e-05, "loss": 4.3675, "step": 5085 }, { "epoch": 0.15534514355528406, "grad_norm": 0.37862229347229004, "learning_rate": 4.708144335378631e-05, "loss": 4.363, "step": 5086 }, { "epoch": 0.1553756872327428, "grad_norm": 0.38028720021247864, "learning_rate": 4.708031843960128e-05, "loss": 4.4508, "step": 5087 }, { "epoch": 0.1554062309102016, "grad_norm": 0.3811970055103302, "learning_rate": 4.7079193322111406e-05, "loss": 4.4634, "step": 5088 }, { "epoch": 0.15543677458766036, "grad_norm": 0.3768051862716675, "learning_rate": 4.707806800132705e-05, "loss": 4.3455, "step": 5089 }, { "epoch": 0.15546731826511911, "grad_norm": 0.3824557065963745, "learning_rate": 4.707694247725857e-05, "loss": 4.4221, "step": 5090 }, { "epoch": 0.1554978619425779, "grad_norm": 0.3923514187335968, "learning_rate": 4.707581674991632e-05, "loss": 4.3635, "step": 5091 }, { "epoch": 0.15552840562003664, "grad_norm": 0.38482335209846497, "learning_rate": 4.707469081931069e-05, "loss": 4.4147, "step": 5092 }, { "epoch": 0.15555894929749542, "grad_norm": 0.3866509795188904, "learning_rate": 4.707356468545202e-05, "loss": 4.4052, "step": 5093 }, { "epoch": 0.1555894929749542, "grad_norm": 0.38711634278297424, "learning_rate": 4.7072438348350686e-05, "loss": 4.4365, "step": 5094 }, { "epoch": 0.15562003665241295, "grad_norm": 0.3872348666191101, "learning_rate": 4.707131180801708e-05, "loss": 4.3663, "step": 5095 }, { "epoch": 0.15565058032987172, "grad_norm": 0.38697314262390137, "learning_rate": 4.7070185064461546e-05, "loss": 4.4444, "step": 5096 }, { "epoch": 0.15568112400733047, "grad_norm": 0.3917246460914612, "learning_rate": 4.7069058117694474e-05, "loss": 4.4486, "step": 5097 }, { "epoch": 0.15571166768478925, "grad_norm": 0.3940229117870331, "learning_rate": 4.706793096772624e-05, "loss": 4.4795, "step": 5098 }, { "epoch": 0.155742211362248, "grad_norm": 0.3836883008480072, "learning_rate": 4.706680361456721e-05, "loss": 4.4293, "step": 5099 }, { "epoch": 0.15577275503970678, "grad_norm": 0.3805634081363678, "learning_rate": 4.706567605822779e-05, "loss": 4.3904, "step": 5100 }, { "epoch": 0.15580329871716556, "grad_norm": 0.3941746950149536, "learning_rate": 4.706454829871833e-05, "loss": 4.4154, "step": 5101 }, { "epoch": 0.1558338423946243, "grad_norm": 0.4000145196914673, "learning_rate": 4.706342033604924e-05, "loss": 4.3764, "step": 5102 }, { "epoch": 0.15586438607208308, "grad_norm": 0.3901158571243286, "learning_rate": 4.706229217023089e-05, "loss": 4.3708, "step": 5103 }, { "epoch": 0.15589492974954183, "grad_norm": 0.3955637812614441, "learning_rate": 4.7061163801273674e-05, "loss": 4.2913, "step": 5104 }, { "epoch": 0.1559254734270006, "grad_norm": 0.40228357911109924, "learning_rate": 4.7060035229187975e-05, "loss": 4.417, "step": 5105 }, { "epoch": 0.1559560171044594, "grad_norm": 0.38710805773735046, "learning_rate": 4.7058906453984195e-05, "loss": 4.4769, "step": 5106 }, { "epoch": 0.15598656078191814, "grad_norm": 0.3884885013103485, "learning_rate": 4.705777747567273e-05, "loss": 4.3618, "step": 5107 }, { "epoch": 0.15601710445937692, "grad_norm": 0.38185569643974304, "learning_rate": 4.705664829426395e-05, "loss": 4.3381, "step": 5108 }, { "epoch": 0.15604764813683566, "grad_norm": 0.393356055021286, "learning_rate": 4.705551890976827e-05, "loss": 4.3934, "step": 5109 }, { "epoch": 0.15607819181429444, "grad_norm": 0.3902234733104706, "learning_rate": 4.7054389322196105e-05, "loss": 4.3641, "step": 5110 }, { "epoch": 0.15610873549175322, "grad_norm": 0.37849289178848267, "learning_rate": 4.705325953155782e-05, "loss": 4.4289, "step": 5111 }, { "epoch": 0.15613927916921197, "grad_norm": 0.37284767627716064, "learning_rate": 4.7052129537863844e-05, "loss": 4.3834, "step": 5112 }, { "epoch": 0.15616982284667075, "grad_norm": 0.37385016679763794, "learning_rate": 4.705099934112457e-05, "loss": 4.3674, "step": 5113 }, { "epoch": 0.1562003665241295, "grad_norm": 0.39557933807373047, "learning_rate": 4.7049868941350416e-05, "loss": 4.3674, "step": 5114 }, { "epoch": 0.15623091020158827, "grad_norm": 0.37154754996299744, "learning_rate": 4.704873833855177e-05, "loss": 4.3776, "step": 5115 }, { "epoch": 0.15626145387904702, "grad_norm": 0.3822951912879944, "learning_rate": 4.704760753273906e-05, "loss": 4.3922, "step": 5116 }, { "epoch": 0.1562919975565058, "grad_norm": 0.3852044343948364, "learning_rate": 4.704647652392269e-05, "loss": 4.4881, "step": 5117 }, { "epoch": 0.15632254123396458, "grad_norm": 0.39319661259651184, "learning_rate": 4.704534531211308e-05, "loss": 4.3361, "step": 5118 }, { "epoch": 0.15635308491142333, "grad_norm": 0.3840312361717224, "learning_rate": 4.704421389732063e-05, "loss": 4.3619, "step": 5119 }, { "epoch": 0.1563836285888821, "grad_norm": 0.3906394839286804, "learning_rate": 4.7043082279555785e-05, "loss": 4.4026, "step": 5120 }, { "epoch": 0.15641417226634086, "grad_norm": 0.37843969464302063, "learning_rate": 4.7041950458828936e-05, "loss": 4.3385, "step": 5121 }, { "epoch": 0.15644471594379963, "grad_norm": 0.3975173532962799, "learning_rate": 4.704081843515052e-05, "loss": 4.4226, "step": 5122 }, { "epoch": 0.1564752596212584, "grad_norm": 0.37752676010131836, "learning_rate": 4.703968620853095e-05, "loss": 4.3051, "step": 5123 }, { "epoch": 0.15650580329871716, "grad_norm": 0.38281822204589844, "learning_rate": 4.7038553778980665e-05, "loss": 4.3836, "step": 5124 }, { "epoch": 0.15653634697617594, "grad_norm": 0.3966373801231384, "learning_rate": 4.7037421146510085e-05, "loss": 4.3459, "step": 5125 }, { "epoch": 0.1565668906536347, "grad_norm": 0.38633450865745544, "learning_rate": 4.703628831112964e-05, "loss": 4.3903, "step": 5126 }, { "epoch": 0.15659743433109347, "grad_norm": 0.3733331561088562, "learning_rate": 4.703515527284975e-05, "loss": 4.4085, "step": 5127 }, { "epoch": 0.15662797800855224, "grad_norm": 0.377572625875473, "learning_rate": 4.703402203168086e-05, "loss": 4.3441, "step": 5128 }, { "epoch": 0.156658521686011, "grad_norm": 0.3841075301170349, "learning_rate": 4.7032888587633405e-05, "loss": 4.4305, "step": 5129 }, { "epoch": 0.15668906536346977, "grad_norm": 0.37994539737701416, "learning_rate": 4.703175494071781e-05, "loss": 4.3278, "step": 5130 }, { "epoch": 0.15671960904092852, "grad_norm": 0.39098310470581055, "learning_rate": 4.703062109094452e-05, "loss": 4.392, "step": 5131 }, { "epoch": 0.1567501527183873, "grad_norm": 0.38674241304397583, "learning_rate": 4.702948703832398e-05, "loss": 4.3914, "step": 5132 }, { "epoch": 0.15678069639584605, "grad_norm": 0.3934377431869507, "learning_rate": 4.702835278286662e-05, "loss": 4.4397, "step": 5133 }, { "epoch": 0.15681124007330483, "grad_norm": 0.39138051867485046, "learning_rate": 4.702721832458289e-05, "loss": 4.4298, "step": 5134 }, { "epoch": 0.1568417837507636, "grad_norm": 0.3941621780395508, "learning_rate": 4.702608366348324e-05, "loss": 4.4188, "step": 5135 }, { "epoch": 0.15687232742822235, "grad_norm": 0.39108985662460327, "learning_rate": 4.702494879957811e-05, "loss": 4.3878, "step": 5136 }, { "epoch": 0.15690287110568113, "grad_norm": 0.39047664403915405, "learning_rate": 4.7023813732877955e-05, "loss": 4.4505, "step": 5137 }, { "epoch": 0.15693341478313988, "grad_norm": 0.4128592610359192, "learning_rate": 4.702267846339322e-05, "loss": 4.3918, "step": 5138 }, { "epoch": 0.15696395846059866, "grad_norm": 0.3873942792415619, "learning_rate": 4.702154299113437e-05, "loss": 4.3022, "step": 5139 }, { "epoch": 0.15699450213805743, "grad_norm": 0.37633565068244934, "learning_rate": 4.702040731611184e-05, "loss": 4.3874, "step": 5140 }, { "epoch": 0.15702504581551618, "grad_norm": 0.3979484438896179, "learning_rate": 4.701927143833611e-05, "loss": 4.3245, "step": 5141 }, { "epoch": 0.15705558949297496, "grad_norm": 0.39985787868499756, "learning_rate": 4.7018135357817615e-05, "loss": 4.3946, "step": 5142 }, { "epoch": 0.1570861331704337, "grad_norm": 0.3806106150150299, "learning_rate": 4.701699907456683e-05, "loss": 4.4005, "step": 5143 }, { "epoch": 0.1571166768478925, "grad_norm": 0.3839300870895386, "learning_rate": 4.701586258859422e-05, "loss": 4.4253, "step": 5144 }, { "epoch": 0.15714722052535124, "grad_norm": 0.3906993865966797, "learning_rate": 4.701472589991024e-05, "loss": 4.4103, "step": 5145 }, { "epoch": 0.15717776420281002, "grad_norm": 0.39348000288009644, "learning_rate": 4.701358900852536e-05, "loss": 4.3531, "step": 5146 }, { "epoch": 0.1572083078802688, "grad_norm": 0.40704047679901123, "learning_rate": 4.7012451914450045e-05, "loss": 4.4852, "step": 5147 }, { "epoch": 0.15723885155772754, "grad_norm": 0.39680013060569763, "learning_rate": 4.7011314617694765e-05, "loss": 4.3582, "step": 5148 }, { "epoch": 0.15726939523518632, "grad_norm": 0.40024682879447937, "learning_rate": 4.701017711827001e-05, "loss": 4.4108, "step": 5149 }, { "epoch": 0.15729993891264507, "grad_norm": 0.4067518711090088, "learning_rate": 4.700903941618622e-05, "loss": 4.3881, "step": 5150 }, { "epoch": 0.15733048259010385, "grad_norm": 0.39152616262435913, "learning_rate": 4.70079015114539e-05, "loss": 4.3952, "step": 5151 }, { "epoch": 0.15736102626756263, "grad_norm": 0.38899147510528564, "learning_rate": 4.700676340408351e-05, "loss": 4.4046, "step": 5152 }, { "epoch": 0.15739156994502138, "grad_norm": 0.39964911341667175, "learning_rate": 4.700562509408554e-05, "loss": 4.4498, "step": 5153 }, { "epoch": 0.15742211362248015, "grad_norm": 0.39239659905433655, "learning_rate": 4.7004486581470455e-05, "loss": 4.3921, "step": 5154 }, { "epoch": 0.1574526572999389, "grad_norm": 0.39844509959220886, "learning_rate": 4.700334786624876e-05, "loss": 4.4529, "step": 5155 }, { "epoch": 0.15748320097739768, "grad_norm": 0.3961831331253052, "learning_rate": 4.700220894843091e-05, "loss": 4.4611, "step": 5156 }, { "epoch": 0.15751374465485646, "grad_norm": 0.3745395243167877, "learning_rate": 4.700106982802743e-05, "loss": 4.4881, "step": 5157 }, { "epoch": 0.1575442883323152, "grad_norm": 0.39712682366371155, "learning_rate": 4.699993050504878e-05, "loss": 4.3652, "step": 5158 }, { "epoch": 0.15757483200977399, "grad_norm": 0.39709576964378357, "learning_rate": 4.699879097950546e-05, "loss": 4.4401, "step": 5159 }, { "epoch": 0.15760537568723273, "grad_norm": 0.3924799859523773, "learning_rate": 4.699765125140796e-05, "loss": 4.3592, "step": 5160 }, { "epoch": 0.1576359193646915, "grad_norm": 0.3829495906829834, "learning_rate": 4.6996511320766776e-05, "loss": 4.3488, "step": 5161 }, { "epoch": 0.15766646304215026, "grad_norm": 0.39528095722198486, "learning_rate": 4.6995371187592395e-05, "loss": 4.3707, "step": 5162 }, { "epoch": 0.15769700671960904, "grad_norm": 0.3932473361492157, "learning_rate": 4.699423085189533e-05, "loss": 4.3733, "step": 5163 }, { "epoch": 0.15772755039706782, "grad_norm": 0.4043354392051697, "learning_rate": 4.699309031368607e-05, "loss": 4.4393, "step": 5164 }, { "epoch": 0.15775809407452657, "grad_norm": 0.39448219537734985, "learning_rate": 4.6991949572975126e-05, "loss": 4.3764, "step": 5165 }, { "epoch": 0.15778863775198534, "grad_norm": 0.3920935094356537, "learning_rate": 4.6990808629772994e-05, "loss": 4.4307, "step": 5166 }, { "epoch": 0.1578191814294441, "grad_norm": 0.3818049430847168, "learning_rate": 4.6989667484090176e-05, "loss": 4.5065, "step": 5167 }, { "epoch": 0.15784972510690287, "grad_norm": 0.3800413906574249, "learning_rate": 4.6988526135937184e-05, "loss": 4.343, "step": 5168 }, { "epoch": 0.15788026878436165, "grad_norm": 0.3893407881259918, "learning_rate": 4.698738458532453e-05, "loss": 4.3253, "step": 5169 }, { "epoch": 0.1579108124618204, "grad_norm": 0.3774779140949249, "learning_rate": 4.6986242832262714e-05, "loss": 4.4038, "step": 5170 }, { "epoch": 0.15794135613927918, "grad_norm": 0.372111439704895, "learning_rate": 4.6985100876762264e-05, "loss": 4.4163, "step": 5171 }, { "epoch": 0.15797189981673793, "grad_norm": 0.3935592770576477, "learning_rate": 4.6983958718833685e-05, "loss": 4.3781, "step": 5172 }, { "epoch": 0.1580024434941967, "grad_norm": 0.3780232071876526, "learning_rate": 4.698281635848749e-05, "loss": 4.4563, "step": 5173 }, { "epoch": 0.15803298717165545, "grad_norm": 0.38711661100387573, "learning_rate": 4.698167379573421e-05, "loss": 4.3221, "step": 5174 }, { "epoch": 0.15806353084911423, "grad_norm": 0.40106117725372314, "learning_rate": 4.6980531030584354e-05, "loss": 4.4512, "step": 5175 }, { "epoch": 0.158094074526573, "grad_norm": 0.3787069022655487, "learning_rate": 4.6979388063048443e-05, "loss": 4.1864, "step": 5176 }, { "epoch": 0.15812461820403176, "grad_norm": 0.3919989764690399, "learning_rate": 4.6978244893137016e-05, "loss": 4.2535, "step": 5177 }, { "epoch": 0.15815516188149054, "grad_norm": 0.38815656304359436, "learning_rate": 4.697710152086058e-05, "loss": 4.4711, "step": 5178 }, { "epoch": 0.15818570555894929, "grad_norm": 0.39860770106315613, "learning_rate": 4.697595794622967e-05, "loss": 4.402, "step": 5179 }, { "epoch": 0.15821624923640806, "grad_norm": 0.3852061331272125, "learning_rate": 4.697481416925482e-05, "loss": 4.3344, "step": 5180 }, { "epoch": 0.15824679291386684, "grad_norm": 0.3845238983631134, "learning_rate": 4.6973670189946554e-05, "loss": 4.4082, "step": 5181 }, { "epoch": 0.1582773365913256, "grad_norm": 0.38416123390197754, "learning_rate": 4.6972526008315406e-05, "loss": 4.397, "step": 5182 }, { "epoch": 0.15830788026878437, "grad_norm": 0.39192867279052734, "learning_rate": 4.697138162437192e-05, "loss": 4.4502, "step": 5183 }, { "epoch": 0.15833842394624312, "grad_norm": 0.3983924090862274, "learning_rate": 4.697023703812663e-05, "loss": 4.4227, "step": 5184 }, { "epoch": 0.1583689676237019, "grad_norm": 0.38830074667930603, "learning_rate": 4.696909224959007e-05, "loss": 4.3879, "step": 5185 }, { "epoch": 0.15839951130116067, "grad_norm": 0.38173767924308777, "learning_rate": 4.6967947258772784e-05, "loss": 4.4695, "step": 5186 }, { "epoch": 0.15843005497861942, "grad_norm": 0.39083170890808105, "learning_rate": 4.69668020656853e-05, "loss": 4.3416, "step": 5187 }, { "epoch": 0.1584605986560782, "grad_norm": 0.4005633294582367, "learning_rate": 4.6965656670338184e-05, "loss": 4.3724, "step": 5188 }, { "epoch": 0.15849114233353695, "grad_norm": 0.3925754725933075, "learning_rate": 4.696451107274198e-05, "loss": 4.3938, "step": 5189 }, { "epoch": 0.15852168601099573, "grad_norm": 0.3935936987400055, "learning_rate": 4.696336527290722e-05, "loss": 4.402, "step": 5190 }, { "epoch": 0.15855222968845448, "grad_norm": 0.3811657130718231, "learning_rate": 4.6962219270844464e-05, "loss": 4.4747, "step": 5191 }, { "epoch": 0.15858277336591325, "grad_norm": 0.39446941018104553, "learning_rate": 4.696107306656427e-05, "loss": 4.3608, "step": 5192 }, { "epoch": 0.15861331704337203, "grad_norm": 0.4007313549518585, "learning_rate": 4.695992666007718e-05, "loss": 4.4534, "step": 5193 }, { "epoch": 0.15864386072083078, "grad_norm": 0.38644781708717346, "learning_rate": 4.695878005139375e-05, "loss": 4.366, "step": 5194 }, { "epoch": 0.15867440439828956, "grad_norm": 0.3777678906917572, "learning_rate": 4.695763324052454e-05, "loss": 4.462, "step": 5195 }, { "epoch": 0.1587049480757483, "grad_norm": 0.3865177035331726, "learning_rate": 4.695648622748013e-05, "loss": 4.4639, "step": 5196 }, { "epoch": 0.1587354917532071, "grad_norm": 0.38053473830223083, "learning_rate": 4.695533901227105e-05, "loss": 4.3664, "step": 5197 }, { "epoch": 0.15876603543066586, "grad_norm": 0.3885878026485443, "learning_rate": 4.695419159490787e-05, "loss": 4.387, "step": 5198 }, { "epoch": 0.1587965791081246, "grad_norm": 0.3865068852901459, "learning_rate": 4.695304397540117e-05, "loss": 4.3887, "step": 5199 }, { "epoch": 0.1588271227855834, "grad_norm": 0.39474645256996155, "learning_rate": 4.695189615376151e-05, "loss": 4.4004, "step": 5200 }, { "epoch": 0.15885766646304214, "grad_norm": 0.39493492245674133, "learning_rate": 4.695074812999945e-05, "loss": 4.4056, "step": 5201 }, { "epoch": 0.15888821014050092, "grad_norm": 0.4013608694076538, "learning_rate": 4.6949599904125556e-05, "loss": 4.2946, "step": 5202 }, { "epoch": 0.1589187538179597, "grad_norm": 0.3837446868419647, "learning_rate": 4.694845147615042e-05, "loss": 4.4036, "step": 5203 }, { "epoch": 0.15894929749541845, "grad_norm": 0.3925156891345978, "learning_rate": 4.6947302846084605e-05, "loss": 4.3948, "step": 5204 }, { "epoch": 0.15897984117287722, "grad_norm": 0.38353028893470764, "learning_rate": 4.6946154013938695e-05, "loss": 4.4026, "step": 5205 }, { "epoch": 0.15901038485033597, "grad_norm": 0.3901325464248657, "learning_rate": 4.694500497972325e-05, "loss": 4.3816, "step": 5206 }, { "epoch": 0.15904092852779475, "grad_norm": 0.39701348543167114, "learning_rate": 4.694385574344887e-05, "loss": 4.4217, "step": 5207 }, { "epoch": 0.1590714722052535, "grad_norm": 0.38514190912246704, "learning_rate": 4.694270630512612e-05, "loss": 4.4482, "step": 5208 }, { "epoch": 0.15910201588271228, "grad_norm": 0.3929244875907898, "learning_rate": 4.69415566647656e-05, "loss": 4.4318, "step": 5209 }, { "epoch": 0.15913255956017106, "grad_norm": 0.39034971594810486, "learning_rate": 4.694040682237788e-05, "loss": 4.4201, "step": 5210 }, { "epoch": 0.1591631032376298, "grad_norm": 0.39466798305511475, "learning_rate": 4.693925677797356e-05, "loss": 4.3614, "step": 5211 }, { "epoch": 0.15919364691508858, "grad_norm": 0.3934239149093628, "learning_rate": 4.693810653156322e-05, "loss": 4.4224, "step": 5212 }, { "epoch": 0.15922419059254733, "grad_norm": 0.3931204378604889, "learning_rate": 4.693695608315745e-05, "loss": 4.3353, "step": 5213 }, { "epoch": 0.1592547342700061, "grad_norm": 0.3903048634529114, "learning_rate": 4.6935805432766845e-05, "loss": 4.4305, "step": 5214 }, { "epoch": 0.1592852779474649, "grad_norm": 0.38823843002319336, "learning_rate": 4.6934654580402e-05, "loss": 4.3646, "step": 5215 }, { "epoch": 0.15931582162492364, "grad_norm": 0.38619083166122437, "learning_rate": 4.6933503526073524e-05, "loss": 4.4228, "step": 5216 }, { "epoch": 0.15934636530238241, "grad_norm": 0.38865238428115845, "learning_rate": 4.6932352269792e-05, "loss": 4.3459, "step": 5217 }, { "epoch": 0.15937690897984116, "grad_norm": 0.39076662063598633, "learning_rate": 4.693120081156803e-05, "loss": 4.4518, "step": 5218 }, { "epoch": 0.15940745265729994, "grad_norm": 0.3922930359840393, "learning_rate": 4.6930049151412215e-05, "loss": 4.2917, "step": 5219 }, { "epoch": 0.1594379963347587, "grad_norm": 0.380416601896286, "learning_rate": 4.692889728933517e-05, "loss": 4.3684, "step": 5220 }, { "epoch": 0.15946854001221747, "grad_norm": 0.38485294580459595, "learning_rate": 4.692774522534749e-05, "loss": 4.3117, "step": 5221 }, { "epoch": 0.15949908368967625, "grad_norm": 0.39140748977661133, "learning_rate": 4.692659295945978e-05, "loss": 4.3966, "step": 5222 }, { "epoch": 0.159529627367135, "grad_norm": 0.3881591260433197, "learning_rate": 4.692544049168266e-05, "loss": 4.4032, "step": 5223 }, { "epoch": 0.15956017104459377, "grad_norm": 0.39643892645835876, "learning_rate": 4.692428782202674e-05, "loss": 4.4675, "step": 5224 }, { "epoch": 0.15959071472205252, "grad_norm": 0.39515769481658936, "learning_rate": 4.692313495050262e-05, "loss": 4.4041, "step": 5225 }, { "epoch": 0.1596212583995113, "grad_norm": 0.3837876617908478, "learning_rate": 4.692198187712092e-05, "loss": 4.3567, "step": 5226 }, { "epoch": 0.15965180207697008, "grad_norm": 0.38355159759521484, "learning_rate": 4.692082860189228e-05, "loss": 4.4513, "step": 5227 }, { "epoch": 0.15968234575442883, "grad_norm": 0.39910784363746643, "learning_rate": 4.691967512482729e-05, "loss": 4.4418, "step": 5228 }, { "epoch": 0.1597128894318876, "grad_norm": 0.41437655687332153, "learning_rate": 4.691852144593658e-05, "loss": 4.4395, "step": 5229 }, { "epoch": 0.15974343310934636, "grad_norm": 0.3856206238269806, "learning_rate": 4.691736756523078e-05, "loss": 4.3219, "step": 5230 }, { "epoch": 0.15977397678680513, "grad_norm": 0.4013921022415161, "learning_rate": 4.6916213482720504e-05, "loss": 4.3974, "step": 5231 }, { "epoch": 0.1598045204642639, "grad_norm": 0.38877472281455994, "learning_rate": 4.6915059198416386e-05, "loss": 4.5195, "step": 5232 }, { "epoch": 0.15983506414172266, "grad_norm": 0.40904825925827026, "learning_rate": 4.691390471232904e-05, "loss": 4.3565, "step": 5233 }, { "epoch": 0.15986560781918144, "grad_norm": 0.380718857049942, "learning_rate": 4.691275002446912e-05, "loss": 4.3404, "step": 5234 }, { "epoch": 0.1598961514966402, "grad_norm": 0.39832746982574463, "learning_rate": 4.691159513484724e-05, "loss": 4.4401, "step": 5235 }, { "epoch": 0.15992669517409897, "grad_norm": 0.40455809235572815, "learning_rate": 4.691044004347403e-05, "loss": 4.4541, "step": 5236 }, { "epoch": 0.15995723885155771, "grad_norm": 0.38335534930229187, "learning_rate": 4.690928475036014e-05, "loss": 4.3698, "step": 5237 }, { "epoch": 0.1599877825290165, "grad_norm": 0.3860411047935486, "learning_rate": 4.6908129255516194e-05, "loss": 4.3537, "step": 5238 }, { "epoch": 0.16001832620647527, "grad_norm": 0.38181912899017334, "learning_rate": 4.690697355895285e-05, "loss": 4.4371, "step": 5239 }, { "epoch": 0.16004886988393402, "grad_norm": 0.3818131685256958, "learning_rate": 4.6905817660680726e-05, "loss": 4.3918, "step": 5240 }, { "epoch": 0.1600794135613928, "grad_norm": 0.40681561827659607, "learning_rate": 4.6904661560710487e-05, "loss": 4.4103, "step": 5241 }, { "epoch": 0.16010995723885155, "grad_norm": 0.38523995876312256, "learning_rate": 4.690350525905276e-05, "loss": 4.3066, "step": 5242 }, { "epoch": 0.16014050091631032, "grad_norm": 0.42564719915390015, "learning_rate": 4.690234875571819e-05, "loss": 4.3295, "step": 5243 }, { "epoch": 0.1601710445937691, "grad_norm": 0.39167237281799316, "learning_rate": 4.690119205071745e-05, "loss": 4.4122, "step": 5244 }, { "epoch": 0.16020158827122785, "grad_norm": 0.3841569423675537, "learning_rate": 4.690003514406116e-05, "loss": 4.4108, "step": 5245 }, { "epoch": 0.16023213194868663, "grad_norm": 0.39969512820243835, "learning_rate": 4.6898878035759995e-05, "loss": 4.3412, "step": 5246 }, { "epoch": 0.16026267562614538, "grad_norm": 0.3852080702781677, "learning_rate": 4.6897720725824604e-05, "loss": 4.3541, "step": 5247 }, { "epoch": 0.16029321930360416, "grad_norm": 0.39055660367012024, "learning_rate": 4.689656321426563e-05, "loss": 4.3558, "step": 5248 }, { "epoch": 0.1603237629810629, "grad_norm": 0.4040445387363434, "learning_rate": 4.6895405501093747e-05, "loss": 4.4133, "step": 5249 }, { "epoch": 0.16035430665852168, "grad_norm": 0.37848374247550964, "learning_rate": 4.6894247586319605e-05, "loss": 4.3937, "step": 5250 }, { "epoch": 0.16038485033598046, "grad_norm": 0.386942982673645, "learning_rate": 4.6893089469953866e-05, "loss": 4.3292, "step": 5251 }, { "epoch": 0.1604153940134392, "grad_norm": 0.37460020184516907, "learning_rate": 4.68919311520072e-05, "loss": 4.4028, "step": 5252 }, { "epoch": 0.160445937690898, "grad_norm": 0.3878578841686249, "learning_rate": 4.689077263249027e-05, "loss": 4.3744, "step": 5253 }, { "epoch": 0.16047648136835674, "grad_norm": 0.39639925956726074, "learning_rate": 4.688961391141374e-05, "loss": 4.4193, "step": 5254 }, { "epoch": 0.16050702504581552, "grad_norm": 0.39848044514656067, "learning_rate": 4.688845498878828e-05, "loss": 4.4223, "step": 5255 }, { "epoch": 0.1605375687232743, "grad_norm": 0.39428576827049255, "learning_rate": 4.688729586462456e-05, "loss": 4.3871, "step": 5256 }, { "epoch": 0.16056811240073304, "grad_norm": 0.38845714926719666, "learning_rate": 4.688613653893325e-05, "loss": 4.3828, "step": 5257 }, { "epoch": 0.16059865607819182, "grad_norm": 0.4356577694416046, "learning_rate": 4.688497701172503e-05, "loss": 4.4804, "step": 5258 }, { "epoch": 0.16062919975565057, "grad_norm": 0.38892942667007446, "learning_rate": 4.688381728301058e-05, "loss": 4.4773, "step": 5259 }, { "epoch": 0.16065974343310935, "grad_norm": 0.37620246410369873, "learning_rate": 4.6882657352800566e-05, "loss": 4.2828, "step": 5260 }, { "epoch": 0.16069028711056813, "grad_norm": 0.4036180377006531, "learning_rate": 4.688149722110568e-05, "loss": 4.4682, "step": 5261 }, { "epoch": 0.16072083078802687, "grad_norm": 0.38935402035713196, "learning_rate": 4.688033688793659e-05, "loss": 4.3172, "step": 5262 }, { "epoch": 0.16075137446548565, "grad_norm": 0.39483481645584106, "learning_rate": 4.6879176353304e-05, "loss": 4.3698, "step": 5263 }, { "epoch": 0.1607819181429444, "grad_norm": 0.398753821849823, "learning_rate": 4.687801561721858e-05, "loss": 4.3939, "step": 5264 }, { "epoch": 0.16081246182040318, "grad_norm": 0.3911130428314209, "learning_rate": 4.687685467969102e-05, "loss": 4.4306, "step": 5265 }, { "epoch": 0.16084300549786193, "grad_norm": 0.38983064889907837, "learning_rate": 4.687569354073201e-05, "loss": 4.3119, "step": 5266 }, { "epoch": 0.1608735491753207, "grad_norm": 0.40907034277915955, "learning_rate": 4.687453220035225e-05, "loss": 4.3076, "step": 5267 }, { "epoch": 0.16090409285277948, "grad_norm": 0.3808722198009491, "learning_rate": 4.687337065856241e-05, "loss": 4.4058, "step": 5268 }, { "epoch": 0.16093463653023823, "grad_norm": 0.40503326058387756, "learning_rate": 4.6872208915373216e-05, "loss": 4.4043, "step": 5269 }, { "epoch": 0.160965180207697, "grad_norm": 0.38153958320617676, "learning_rate": 4.687104697079534e-05, "loss": 4.419, "step": 5270 }, { "epoch": 0.16099572388515576, "grad_norm": 0.3936544954776764, "learning_rate": 4.686988482483949e-05, "loss": 4.4027, "step": 5271 }, { "epoch": 0.16102626756261454, "grad_norm": 0.38893935084342957, "learning_rate": 4.686872247751637e-05, "loss": 4.3916, "step": 5272 }, { "epoch": 0.16105681124007332, "grad_norm": 0.3919186294078827, "learning_rate": 4.686755992883668e-05, "loss": 4.3641, "step": 5273 }, { "epoch": 0.16108735491753207, "grad_norm": 0.3898884952068329, "learning_rate": 4.6866397178811116e-05, "loss": 4.4083, "step": 5274 }, { "epoch": 0.16111789859499084, "grad_norm": 0.3847140073776245, "learning_rate": 4.6865234227450396e-05, "loss": 4.4, "step": 5275 }, { "epoch": 0.1611484422724496, "grad_norm": 0.3773585557937622, "learning_rate": 4.686407107476522e-05, "loss": 4.3398, "step": 5276 }, { "epoch": 0.16117898594990837, "grad_norm": 0.3838149905204773, "learning_rate": 4.68629077207663e-05, "loss": 4.3472, "step": 5277 }, { "epoch": 0.16120952962736715, "grad_norm": 0.372386634349823, "learning_rate": 4.686174416546435e-05, "loss": 4.451, "step": 5278 }, { "epoch": 0.1612400733048259, "grad_norm": 0.40311726927757263, "learning_rate": 4.6860580408870076e-05, "loss": 4.2898, "step": 5279 }, { "epoch": 0.16127061698228468, "grad_norm": 0.3903075158596039, "learning_rate": 4.6859416450994207e-05, "loss": 4.3758, "step": 5280 }, { "epoch": 0.16130116065974343, "grad_norm": 0.37653371691703796, "learning_rate": 4.6858252291847445e-05, "loss": 4.3913, "step": 5281 }, { "epoch": 0.1613317043372022, "grad_norm": 0.38608306646347046, "learning_rate": 4.685708793144051e-05, "loss": 4.3515, "step": 5282 }, { "epoch": 0.16136224801466095, "grad_norm": 0.3992820978164673, "learning_rate": 4.6855923369784135e-05, "loss": 4.4476, "step": 5283 }, { "epoch": 0.16139279169211973, "grad_norm": 0.3960295021533966, "learning_rate": 4.6854758606889046e-05, "loss": 4.3889, "step": 5284 }, { "epoch": 0.1614233353695785, "grad_norm": 0.3968068063259125, "learning_rate": 4.685359364276595e-05, "loss": 4.4366, "step": 5285 }, { "epoch": 0.16145387904703726, "grad_norm": 0.3943564295768738, "learning_rate": 4.6852428477425576e-05, "loss": 4.3858, "step": 5286 }, { "epoch": 0.16148442272449604, "grad_norm": 0.40382087230682373, "learning_rate": 4.685126311087866e-05, "loss": 4.4409, "step": 5287 }, { "epoch": 0.16151496640195478, "grad_norm": 0.3709610402584076, "learning_rate": 4.6850097543135936e-05, "loss": 4.2859, "step": 5288 }, { "epoch": 0.16154551007941356, "grad_norm": 0.386211633682251, "learning_rate": 4.684893177420813e-05, "loss": 4.3857, "step": 5289 }, { "epoch": 0.16157605375687234, "grad_norm": 0.39967817068099976, "learning_rate": 4.684776580410596e-05, "loss": 4.3422, "step": 5290 }, { "epoch": 0.1616065974343311, "grad_norm": 0.40226981043815613, "learning_rate": 4.684659963284019e-05, "loss": 4.3751, "step": 5291 }, { "epoch": 0.16163714111178987, "grad_norm": 0.3966761827468872, "learning_rate": 4.684543326042155e-05, "loss": 4.3525, "step": 5292 }, { "epoch": 0.16166768478924862, "grad_norm": 0.38744086027145386, "learning_rate": 4.684426668686076e-05, "loss": 4.3527, "step": 5293 }, { "epoch": 0.1616982284667074, "grad_norm": 0.38625678420066833, "learning_rate": 4.6843099912168584e-05, "loss": 4.4182, "step": 5294 }, { "epoch": 0.16172877214416614, "grad_norm": 0.40040022134780884, "learning_rate": 4.684193293635576e-05, "loss": 4.2951, "step": 5295 }, { "epoch": 0.16175931582162492, "grad_norm": 0.3939926326274872, "learning_rate": 4.684076575943303e-05, "loss": 4.4009, "step": 5296 }, { "epoch": 0.1617898594990837, "grad_norm": 0.3853403925895691, "learning_rate": 4.683959838141113e-05, "loss": 4.3952, "step": 5297 }, { "epoch": 0.16182040317654245, "grad_norm": 0.3831114172935486, "learning_rate": 4.683843080230082e-05, "loss": 4.2319, "step": 5298 }, { "epoch": 0.16185094685400123, "grad_norm": 0.3829857409000397, "learning_rate": 4.683726302211285e-05, "loss": 4.3912, "step": 5299 }, { "epoch": 0.16188149053145998, "grad_norm": 0.3981530964374542, "learning_rate": 4.683609504085798e-05, "loss": 4.3476, "step": 5300 }, { "epoch": 0.16191203420891875, "grad_norm": 0.3841606378555298, "learning_rate": 4.683492685854695e-05, "loss": 4.2412, "step": 5301 }, { "epoch": 0.16194257788637753, "grad_norm": 0.39736270904541016, "learning_rate": 4.683375847519053e-05, "loss": 4.2913, "step": 5302 }, { "epoch": 0.16197312156383628, "grad_norm": 0.4021187424659729, "learning_rate": 4.683258989079946e-05, "loss": 4.2941, "step": 5303 }, { "epoch": 0.16200366524129506, "grad_norm": 0.38022518157958984, "learning_rate": 4.683142110538451e-05, "loss": 4.2923, "step": 5304 }, { "epoch": 0.1620342089187538, "grad_norm": 0.38531386852264404, "learning_rate": 4.683025211895644e-05, "loss": 4.3627, "step": 5305 }, { "epoch": 0.16206475259621259, "grad_norm": 0.3863678574562073, "learning_rate": 4.682908293152602e-05, "loss": 4.4388, "step": 5306 }, { "epoch": 0.16209529627367136, "grad_norm": 0.39182746410369873, "learning_rate": 4.682791354310401e-05, "loss": 4.3076, "step": 5307 }, { "epoch": 0.1621258399511301, "grad_norm": 0.3885228931903839, "learning_rate": 4.6826743953701176e-05, "loss": 4.4308, "step": 5308 }, { "epoch": 0.1621563836285889, "grad_norm": 0.3850066065788269, "learning_rate": 4.682557416332829e-05, "loss": 4.3769, "step": 5309 }, { "epoch": 0.16218692730604764, "grad_norm": 0.3941796123981476, "learning_rate": 4.6824404171996114e-05, "loss": 4.4177, "step": 5310 }, { "epoch": 0.16221747098350642, "grad_norm": 0.3847837746143341, "learning_rate": 4.6823233979715433e-05, "loss": 4.3552, "step": 5311 }, { "epoch": 0.16224801466096517, "grad_norm": 0.3835618495941162, "learning_rate": 4.682206358649702e-05, "loss": 4.4174, "step": 5312 }, { "epoch": 0.16227855833842394, "grad_norm": 0.37327033281326294, "learning_rate": 4.6820892992351636e-05, "loss": 4.4329, "step": 5313 }, { "epoch": 0.16230910201588272, "grad_norm": 0.4063704013824463, "learning_rate": 4.681972219729008e-05, "loss": 4.4707, "step": 5314 }, { "epoch": 0.16233964569334147, "grad_norm": 0.3840923607349396, "learning_rate": 4.681855120132312e-05, "loss": 4.3337, "step": 5315 }, { "epoch": 0.16237018937080025, "grad_norm": 0.3938545286655426, "learning_rate": 4.6817380004461555e-05, "loss": 4.3907, "step": 5316 }, { "epoch": 0.162400733048259, "grad_norm": 0.3882731795310974, "learning_rate": 4.681620860671614e-05, "loss": 4.5424, "step": 5317 }, { "epoch": 0.16243127672571778, "grad_norm": 0.39310550689697266, "learning_rate": 4.6815037008097675e-05, "loss": 4.3081, "step": 5318 }, { "epoch": 0.16246182040317655, "grad_norm": 0.40403327345848083, "learning_rate": 4.681386520861695e-05, "loss": 4.4764, "step": 5319 }, { "epoch": 0.1624923640806353, "grad_norm": 0.3773139715194702, "learning_rate": 4.681269320828476e-05, "loss": 4.3902, "step": 5320 }, { "epoch": 0.16252290775809408, "grad_norm": 0.38920119404792786, "learning_rate": 4.681152100711188e-05, "loss": 4.3232, "step": 5321 }, { "epoch": 0.16255345143555283, "grad_norm": 0.38292258977890015, "learning_rate": 4.681034860510911e-05, "loss": 4.4497, "step": 5322 }, { "epoch": 0.1625839951130116, "grad_norm": 0.3864124119281769, "learning_rate": 4.680917600228726e-05, "loss": 4.4405, "step": 5323 }, { "epoch": 0.1626145387904704, "grad_norm": 0.3872841000556946, "learning_rate": 4.68080031986571e-05, "loss": 4.5136, "step": 5324 }, { "epoch": 0.16264508246792914, "grad_norm": 0.3901233375072479, "learning_rate": 4.680683019422945e-05, "loss": 4.3932, "step": 5325 }, { "epoch": 0.1626756261453879, "grad_norm": 0.3787444829940796, "learning_rate": 4.6805656989015094e-05, "loss": 4.3757, "step": 5326 }, { "epoch": 0.16270616982284666, "grad_norm": 0.40359875559806824, "learning_rate": 4.680448358302485e-05, "loss": 4.368, "step": 5327 }, { "epoch": 0.16273671350030544, "grad_norm": 0.38593462109565735, "learning_rate": 4.680330997626952e-05, "loss": 4.4668, "step": 5328 }, { "epoch": 0.1627672571777642, "grad_norm": 0.39874279499053955, "learning_rate": 4.680213616875989e-05, "loss": 4.3542, "step": 5329 }, { "epoch": 0.16279780085522297, "grad_norm": 0.39162349700927734, "learning_rate": 4.680096216050679e-05, "loss": 4.4431, "step": 5330 }, { "epoch": 0.16282834453268175, "grad_norm": 0.37593212723731995, "learning_rate": 4.6799787951521024e-05, "loss": 4.3323, "step": 5331 }, { "epoch": 0.1628588882101405, "grad_norm": 0.3928072154521942, "learning_rate": 4.67986135418134e-05, "loss": 4.3748, "step": 5332 }, { "epoch": 0.16288943188759927, "grad_norm": 0.3787771463394165, "learning_rate": 4.679743893139473e-05, "loss": 4.4029, "step": 5333 }, { "epoch": 0.16291997556505802, "grad_norm": 0.3943442702293396, "learning_rate": 4.679626412027584e-05, "loss": 4.3912, "step": 5334 }, { "epoch": 0.1629505192425168, "grad_norm": 0.37689974904060364, "learning_rate": 4.679508910846754e-05, "loss": 4.3398, "step": 5335 }, { "epoch": 0.16298106291997558, "grad_norm": 0.3921367824077606, "learning_rate": 4.6793913895980645e-05, "loss": 4.3807, "step": 5336 }, { "epoch": 0.16301160659743433, "grad_norm": 0.403221070766449, "learning_rate": 4.679273848282598e-05, "loss": 4.4563, "step": 5337 }, { "epoch": 0.1630421502748931, "grad_norm": 0.38284832239151, "learning_rate": 4.679156286901436e-05, "loss": 4.396, "step": 5338 }, { "epoch": 0.16307269395235185, "grad_norm": 0.3901779353618622, "learning_rate": 4.679038705455663e-05, "loss": 4.3599, "step": 5339 }, { "epoch": 0.16310323762981063, "grad_norm": 0.4076771140098572, "learning_rate": 4.6789211039463596e-05, "loss": 4.4209, "step": 5340 }, { "epoch": 0.16313378130726938, "grad_norm": 0.38850122690200806, "learning_rate": 4.6788034823746093e-05, "loss": 4.3837, "step": 5341 }, { "epoch": 0.16316432498472816, "grad_norm": 0.3886488676071167, "learning_rate": 4.678685840741495e-05, "loss": 4.3234, "step": 5342 }, { "epoch": 0.16319486866218694, "grad_norm": 0.38712984323501587, "learning_rate": 4.678568179048099e-05, "loss": 4.4005, "step": 5343 }, { "epoch": 0.1632254123396457, "grad_norm": 0.3824112117290497, "learning_rate": 4.678450497295508e-05, "loss": 4.3896, "step": 5344 }, { "epoch": 0.16325595601710446, "grad_norm": 0.40491896867752075, "learning_rate": 4.6783327954848014e-05, "loss": 4.4831, "step": 5345 }, { "epoch": 0.16328649969456321, "grad_norm": 0.3856253921985626, "learning_rate": 4.678215073617066e-05, "loss": 4.3538, "step": 5346 }, { "epoch": 0.163317043372022, "grad_norm": 0.38280153274536133, "learning_rate": 4.6780973316933834e-05, "loss": 4.3663, "step": 5347 }, { "epoch": 0.16334758704948077, "grad_norm": 0.3776925206184387, "learning_rate": 4.6779795697148396e-05, "loss": 4.3882, "step": 5348 }, { "epoch": 0.16337813072693952, "grad_norm": 0.4018184542655945, "learning_rate": 4.6778617876825176e-05, "loss": 4.3592, "step": 5349 }, { "epoch": 0.1634086744043983, "grad_norm": 0.3752368092536926, "learning_rate": 4.6777439855975024e-05, "loss": 4.4188, "step": 5350 }, { "epoch": 0.16343921808185705, "grad_norm": 0.3749089241027832, "learning_rate": 4.677626163460879e-05, "loss": 4.3796, "step": 5351 }, { "epoch": 0.16346976175931582, "grad_norm": 0.38083696365356445, "learning_rate": 4.677508321273731e-05, "loss": 4.3095, "step": 5352 }, { "epoch": 0.1635003054367746, "grad_norm": 0.39174938201904297, "learning_rate": 4.6773904590371455e-05, "loss": 4.4641, "step": 5353 }, { "epoch": 0.16353084911423335, "grad_norm": 0.3831963539123535, "learning_rate": 4.677272576752206e-05, "loss": 4.4181, "step": 5354 }, { "epoch": 0.16356139279169213, "grad_norm": 0.3748581111431122, "learning_rate": 4.6771546744199987e-05, "loss": 4.3492, "step": 5355 }, { "epoch": 0.16359193646915088, "grad_norm": 0.3922302722930908, "learning_rate": 4.677036752041608e-05, "loss": 4.3265, "step": 5356 }, { "epoch": 0.16362248014660966, "grad_norm": 0.3951053023338318, "learning_rate": 4.6769188096181214e-05, "loss": 4.4315, "step": 5357 }, { "epoch": 0.1636530238240684, "grad_norm": 0.3952294588088989, "learning_rate": 4.676800847150624e-05, "loss": 4.4423, "step": 5358 }, { "epoch": 0.16368356750152718, "grad_norm": 0.39445585012435913, "learning_rate": 4.6766828646402024e-05, "loss": 4.3868, "step": 5359 }, { "epoch": 0.16371411117898596, "grad_norm": 0.39259424805641174, "learning_rate": 4.676564862087942e-05, "loss": 4.3824, "step": 5360 }, { "epoch": 0.1637446548564447, "grad_norm": 0.3918786346912384, "learning_rate": 4.67644683949493e-05, "loss": 4.3759, "step": 5361 }, { "epoch": 0.1637751985339035, "grad_norm": 0.3866915702819824, "learning_rate": 4.6763287968622526e-05, "loss": 4.458, "step": 5362 }, { "epoch": 0.16380574221136224, "grad_norm": 0.3987632393836975, "learning_rate": 4.6762107341909975e-05, "loss": 4.3866, "step": 5363 }, { "epoch": 0.16383628588882101, "grad_norm": 0.38678476214408875, "learning_rate": 4.676092651482251e-05, "loss": 4.4499, "step": 5364 }, { "epoch": 0.1638668295662798, "grad_norm": 0.39818161725997925, "learning_rate": 4.6759745487371e-05, "loss": 4.4559, "step": 5365 }, { "epoch": 0.16389737324373854, "grad_norm": 0.3815871775150299, "learning_rate": 4.675856425956634e-05, "loss": 4.3958, "step": 5366 }, { "epoch": 0.16392791692119732, "grad_norm": 0.3969651460647583, "learning_rate": 4.6757382831419384e-05, "loss": 4.4469, "step": 5367 }, { "epoch": 0.16395846059865607, "grad_norm": 0.3900319039821625, "learning_rate": 4.675620120294101e-05, "loss": 4.3322, "step": 5368 }, { "epoch": 0.16398900427611485, "grad_norm": 0.3973914682865143, "learning_rate": 4.675501937414212e-05, "loss": 4.4054, "step": 5369 }, { "epoch": 0.1640195479535736, "grad_norm": 0.3912517726421356, "learning_rate": 4.6753837345033566e-05, "loss": 4.4617, "step": 5370 }, { "epoch": 0.16405009163103237, "grad_norm": 0.3934994339942932, "learning_rate": 4.6752655115626266e-05, "loss": 4.3364, "step": 5371 }, { "epoch": 0.16408063530849115, "grad_norm": 0.4045864939689636, "learning_rate": 4.6751472685931067e-05, "loss": 4.396, "step": 5372 }, { "epoch": 0.1641111789859499, "grad_norm": 0.37978196144104004, "learning_rate": 4.675029005595889e-05, "loss": 4.3877, "step": 5373 }, { "epoch": 0.16414172266340868, "grad_norm": 0.7107993364334106, "learning_rate": 4.67491072257206e-05, "loss": 4.3903, "step": 5374 }, { "epoch": 0.16417226634086743, "grad_norm": 0.388007789850235, "learning_rate": 4.67479241952271e-05, "loss": 4.3711, "step": 5375 }, { "epoch": 0.1642028100183262, "grad_norm": 0.39625006914138794, "learning_rate": 4.6746740964489285e-05, "loss": 4.3907, "step": 5376 }, { "epoch": 0.16423335369578498, "grad_norm": 0.38986366987228394, "learning_rate": 4.674555753351804e-05, "loss": 4.3179, "step": 5377 }, { "epoch": 0.16426389737324373, "grad_norm": 0.3723742961883545, "learning_rate": 4.674437390232427e-05, "loss": 4.3549, "step": 5378 }, { "epoch": 0.1642944410507025, "grad_norm": 0.3904188871383667, "learning_rate": 4.6743190070918866e-05, "loss": 4.376, "step": 5379 }, { "epoch": 0.16432498472816126, "grad_norm": 0.3876647651195526, "learning_rate": 4.674200603931273e-05, "loss": 4.3068, "step": 5380 }, { "epoch": 0.16435552840562004, "grad_norm": 0.3909134268760681, "learning_rate": 4.674082180751677e-05, "loss": 4.425, "step": 5381 }, { "epoch": 0.16438607208307882, "grad_norm": 0.38154101371765137, "learning_rate": 4.6739637375541886e-05, "loss": 4.4483, "step": 5382 }, { "epoch": 0.16441661576053757, "grad_norm": 0.39698323607444763, "learning_rate": 4.673845274339898e-05, "loss": 4.3886, "step": 5383 }, { "epoch": 0.16444715943799634, "grad_norm": 0.3751308023929596, "learning_rate": 4.673726791109896e-05, "loss": 4.4404, "step": 5384 }, { "epoch": 0.1644777031154551, "grad_norm": 0.36903297901153564, "learning_rate": 4.673608287865274e-05, "loss": 4.3976, "step": 5385 }, { "epoch": 0.16450824679291387, "grad_norm": 0.3791888654232025, "learning_rate": 4.673489764607124e-05, "loss": 4.4117, "step": 5386 }, { "epoch": 0.16453879047037262, "grad_norm": 0.3773234188556671, "learning_rate": 4.673371221336535e-05, "loss": 4.4468, "step": 5387 }, { "epoch": 0.1645693341478314, "grad_norm": 0.37949565052986145, "learning_rate": 4.6732526580546006e-05, "loss": 4.4282, "step": 5388 }, { "epoch": 0.16459987782529018, "grad_norm": 0.3934479057788849, "learning_rate": 4.673134074762411e-05, "loss": 4.3664, "step": 5389 }, { "epoch": 0.16463042150274892, "grad_norm": 0.3758947253227234, "learning_rate": 4.6730154714610584e-05, "loss": 4.4129, "step": 5390 }, { "epoch": 0.1646609651802077, "grad_norm": 0.3775101602077484, "learning_rate": 4.6728968481516355e-05, "loss": 4.3705, "step": 5391 }, { "epoch": 0.16469150885766645, "grad_norm": 0.390265554189682, "learning_rate": 4.672778204835234e-05, "loss": 4.4165, "step": 5392 }, { "epoch": 0.16472205253512523, "grad_norm": 0.40712234377861023, "learning_rate": 4.672659541512947e-05, "loss": 4.4479, "step": 5393 }, { "epoch": 0.164752596212584, "grad_norm": 0.38214996457099915, "learning_rate": 4.6725408581858665e-05, "loss": 4.386, "step": 5394 }, { "epoch": 0.16478313989004276, "grad_norm": 0.37420329451560974, "learning_rate": 4.672422154855084e-05, "loss": 4.3819, "step": 5395 }, { "epoch": 0.16481368356750153, "grad_norm": 0.38323891162872314, "learning_rate": 4.6723034315216955e-05, "loss": 4.385, "step": 5396 }, { "epoch": 0.16484422724496028, "grad_norm": 0.395756334066391, "learning_rate": 4.672184688186791e-05, "loss": 4.3792, "step": 5397 }, { "epoch": 0.16487477092241906, "grad_norm": 0.38697105646133423, "learning_rate": 4.6720659248514665e-05, "loss": 4.4505, "step": 5398 }, { "epoch": 0.16490531459987784, "grad_norm": 0.39340993762016296, "learning_rate": 4.671947141516813e-05, "loss": 4.3719, "step": 5399 }, { "epoch": 0.1649358582773366, "grad_norm": 0.38675376772880554, "learning_rate": 4.6718283381839264e-05, "loss": 4.3458, "step": 5400 }, { "epoch": 0.16496640195479537, "grad_norm": 0.3814619779586792, "learning_rate": 4.671709514853899e-05, "loss": 4.3414, "step": 5401 }, { "epoch": 0.16499694563225412, "grad_norm": 0.39740103483200073, "learning_rate": 4.671590671527826e-05, "loss": 4.3298, "step": 5402 }, { "epoch": 0.1650274893097129, "grad_norm": 0.3887655735015869, "learning_rate": 4.671471808206801e-05, "loss": 4.4266, "step": 5403 }, { "epoch": 0.16505803298717164, "grad_norm": 0.38118278980255127, "learning_rate": 4.6713529248919183e-05, "loss": 4.3385, "step": 5404 }, { "epoch": 0.16508857666463042, "grad_norm": 0.40116921067237854, "learning_rate": 4.671234021584273e-05, "loss": 4.3061, "step": 5405 }, { "epoch": 0.1651191203420892, "grad_norm": 0.3983495235443115, "learning_rate": 4.67111509828496e-05, "loss": 4.377, "step": 5406 }, { "epoch": 0.16514966401954795, "grad_norm": 0.389069139957428, "learning_rate": 4.670996154995074e-05, "loss": 4.3569, "step": 5407 }, { "epoch": 0.16518020769700673, "grad_norm": 0.3769966661930084, "learning_rate": 4.67087719171571e-05, "loss": 4.4402, "step": 5408 }, { "epoch": 0.16521075137446548, "grad_norm": 0.38551557064056396, "learning_rate": 4.670758208447964e-05, "loss": 4.4723, "step": 5409 }, { "epoch": 0.16524129505192425, "grad_norm": 0.40107834339141846, "learning_rate": 4.67063920519293e-05, "loss": 4.4082, "step": 5410 }, { "epoch": 0.16527183872938303, "grad_norm": 0.3863200843334198, "learning_rate": 4.6705201819517066e-05, "loss": 4.4028, "step": 5411 }, { "epoch": 0.16530238240684178, "grad_norm": 0.39501890540122986, "learning_rate": 4.6704011387253864e-05, "loss": 4.312, "step": 5412 }, { "epoch": 0.16533292608430056, "grad_norm": 0.3852823078632355, "learning_rate": 4.670282075515067e-05, "loss": 4.4193, "step": 5413 }, { "epoch": 0.1653634697617593, "grad_norm": 0.39334410429000854, "learning_rate": 4.670162992321845e-05, "loss": 4.4693, "step": 5414 }, { "epoch": 0.16539401343921808, "grad_norm": 0.4733470380306244, "learning_rate": 4.670043889146817e-05, "loss": 4.4207, "step": 5415 }, { "epoch": 0.16542455711667683, "grad_norm": 0.3840055465698242, "learning_rate": 4.669924765991079e-05, "loss": 4.2848, "step": 5416 }, { "epoch": 0.1654551007941356, "grad_norm": 0.38514113426208496, "learning_rate": 4.669805622855728e-05, "loss": 4.4069, "step": 5417 }, { "epoch": 0.1654856444715944, "grad_norm": 0.3881450891494751, "learning_rate": 4.6696864597418604e-05, "loss": 4.4683, "step": 5418 }, { "epoch": 0.16551618814905314, "grad_norm": 0.37935781478881836, "learning_rate": 4.6695672766505746e-05, "loss": 4.4017, "step": 5419 }, { "epoch": 0.16554673182651192, "grad_norm": 0.3741579055786133, "learning_rate": 4.669448073582967e-05, "loss": 4.3468, "step": 5420 }, { "epoch": 0.16557727550397067, "grad_norm": 0.3770871162414551, "learning_rate": 4.6693288505401354e-05, "loss": 4.378, "step": 5421 }, { "epoch": 0.16560781918142944, "grad_norm": 0.37816786766052246, "learning_rate": 4.669209607523178e-05, "loss": 4.3887, "step": 5422 }, { "epoch": 0.16563836285888822, "grad_norm": 0.3779619336128235, "learning_rate": 4.6690903445331935e-05, "loss": 4.4076, "step": 5423 }, { "epoch": 0.16566890653634697, "grad_norm": 0.37729042768478394, "learning_rate": 4.668971061571278e-05, "loss": 4.3884, "step": 5424 }, { "epoch": 0.16569945021380575, "grad_norm": 0.3816327452659607, "learning_rate": 4.66885175863853e-05, "loss": 4.41, "step": 5425 }, { "epoch": 0.1657299938912645, "grad_norm": 0.3842281997203827, "learning_rate": 4.6687324357360505e-05, "loss": 4.419, "step": 5426 }, { "epoch": 0.16576053756872328, "grad_norm": 0.38003164529800415, "learning_rate": 4.668613092864935e-05, "loss": 4.3858, "step": 5427 }, { "epoch": 0.16579108124618205, "grad_norm": 0.3875017464160919, "learning_rate": 4.6684937300262845e-05, "loss": 4.2996, "step": 5428 }, { "epoch": 0.1658216249236408, "grad_norm": 0.3823326826095581, "learning_rate": 4.668374347221197e-05, "loss": 4.4042, "step": 5429 }, { "epoch": 0.16585216860109958, "grad_norm": 0.3784897029399872, "learning_rate": 4.668254944450772e-05, "loss": 4.403, "step": 5430 }, { "epoch": 0.16588271227855833, "grad_norm": 0.3860461711883545, "learning_rate": 4.6681355217161094e-05, "loss": 4.4185, "step": 5431 }, { "epoch": 0.1659132559560171, "grad_norm": 0.37171006202697754, "learning_rate": 4.6680160790183075e-05, "loss": 4.4216, "step": 5432 }, { "epoch": 0.16594379963347586, "grad_norm": 0.38884592056274414, "learning_rate": 4.667896616358467e-05, "loss": 4.4114, "step": 5433 }, { "epoch": 0.16597434331093464, "grad_norm": 0.3963721692562103, "learning_rate": 4.6677771337376885e-05, "loss": 4.3172, "step": 5434 }, { "epoch": 0.1660048869883934, "grad_norm": 0.46067172288894653, "learning_rate": 4.667657631157071e-05, "loss": 4.4035, "step": 5435 }, { "epoch": 0.16603543066585216, "grad_norm": 0.3832271695137024, "learning_rate": 4.667538108617715e-05, "loss": 4.3743, "step": 5436 }, { "epoch": 0.16606597434331094, "grad_norm": 0.3877086937427521, "learning_rate": 4.6674185661207214e-05, "loss": 4.4186, "step": 5437 }, { "epoch": 0.1660965180207697, "grad_norm": 0.39065515995025635, "learning_rate": 4.66729900366719e-05, "loss": 4.385, "step": 5438 }, { "epoch": 0.16612706169822847, "grad_norm": 0.39586564898490906, "learning_rate": 4.667179421258223e-05, "loss": 4.4365, "step": 5439 }, { "epoch": 0.16615760537568725, "grad_norm": 0.385449081659317, "learning_rate": 4.667059818894921e-05, "loss": 4.3741, "step": 5440 }, { "epoch": 0.166188149053146, "grad_norm": 0.3856888711452484, "learning_rate": 4.666940196578384e-05, "loss": 4.3335, "step": 5441 }, { "epoch": 0.16621869273060477, "grad_norm": 0.3771575093269348, "learning_rate": 4.666820554309715e-05, "loss": 4.4584, "step": 5442 }, { "epoch": 0.16624923640806352, "grad_norm": 0.3851591944694519, "learning_rate": 4.6667008920900164e-05, "loss": 4.3185, "step": 5443 }, { "epoch": 0.1662797800855223, "grad_norm": 0.39343762397766113, "learning_rate": 4.666581209920388e-05, "loss": 4.37, "step": 5444 }, { "epoch": 0.16631032376298105, "grad_norm": 0.3758326768875122, "learning_rate": 4.666461507801931e-05, "loss": 4.3643, "step": 5445 }, { "epoch": 0.16634086744043983, "grad_norm": 0.38473832607269287, "learning_rate": 4.6663417857357504e-05, "loss": 4.4681, "step": 5446 }, { "epoch": 0.1663714111178986, "grad_norm": 0.38338232040405273, "learning_rate": 4.666222043722947e-05, "loss": 4.3264, "step": 5447 }, { "epoch": 0.16640195479535735, "grad_norm": 0.3925809860229492, "learning_rate": 4.666102281764623e-05, "loss": 4.43, "step": 5448 }, { "epoch": 0.16643249847281613, "grad_norm": 0.39440321922302246, "learning_rate": 4.665982499861882e-05, "loss": 4.3898, "step": 5449 }, { "epoch": 0.16646304215027488, "grad_norm": 0.3903487026691437, "learning_rate": 4.665862698015827e-05, "loss": 4.3643, "step": 5450 }, { "epoch": 0.16649358582773366, "grad_norm": 0.39465513825416565, "learning_rate": 4.665742876227559e-05, "loss": 4.4292, "step": 5451 }, { "epoch": 0.16652412950519244, "grad_norm": 0.4084297716617584, "learning_rate": 4.6656230344981846e-05, "loss": 4.3777, "step": 5452 }, { "epoch": 0.1665546731826512, "grad_norm": 0.3884940445423126, "learning_rate": 4.665503172828805e-05, "loss": 4.3506, "step": 5453 }, { "epoch": 0.16658521686010996, "grad_norm": 0.3783304691314697, "learning_rate": 4.665383291220523e-05, "loss": 4.3176, "step": 5454 }, { "epoch": 0.1666157605375687, "grad_norm": 0.3884836733341217, "learning_rate": 4.665263389674445e-05, "loss": 4.3026, "step": 5455 }, { "epoch": 0.1666463042150275, "grad_norm": 0.3998306691646576, "learning_rate": 4.6651434681916734e-05, "loss": 4.3126, "step": 5456 }, { "epoch": 0.16667684789248627, "grad_norm": 0.391642689704895, "learning_rate": 4.665023526773312e-05, "loss": 4.3727, "step": 5457 }, { "epoch": 0.16670739156994502, "grad_norm": 0.38237348198890686, "learning_rate": 4.664903565420467e-05, "loss": 4.335, "step": 5458 }, { "epoch": 0.1667379352474038, "grad_norm": 0.39904502034187317, "learning_rate": 4.664783584134241e-05, "loss": 4.4281, "step": 5459 }, { "epoch": 0.16676847892486255, "grad_norm": 0.3938644528388977, "learning_rate": 4.6646635829157405e-05, "loss": 4.4669, "step": 5460 }, { "epoch": 0.16679902260232132, "grad_norm": 0.3897945284843445, "learning_rate": 4.664543561766068e-05, "loss": 4.4795, "step": 5461 }, { "epoch": 0.16682956627978007, "grad_norm": 0.40514498949050903, "learning_rate": 4.6644235206863314e-05, "loss": 4.388, "step": 5462 }, { "epoch": 0.16686010995723885, "grad_norm": 0.3830806314945221, "learning_rate": 4.664303459677634e-05, "loss": 4.4021, "step": 5463 }, { "epoch": 0.16689065363469763, "grad_norm": 0.37502291798591614, "learning_rate": 4.6641833787410815e-05, "loss": 4.3925, "step": 5464 }, { "epoch": 0.16692119731215638, "grad_norm": 0.37986433506011963, "learning_rate": 4.66406327787778e-05, "loss": 4.4597, "step": 5465 }, { "epoch": 0.16695174098961515, "grad_norm": 0.38449627161026, "learning_rate": 4.663943157088836e-05, "loss": 4.364, "step": 5466 }, { "epoch": 0.1669822846670739, "grad_norm": 0.3875654637813568, "learning_rate": 4.663823016375354e-05, "loss": 4.4901, "step": 5467 }, { "epoch": 0.16701282834453268, "grad_norm": 0.3800183832645416, "learning_rate": 4.663702855738442e-05, "loss": 4.3452, "step": 5468 }, { "epoch": 0.16704337202199146, "grad_norm": 0.37898555397987366, "learning_rate": 4.663582675179204e-05, "loss": 4.3989, "step": 5469 }, { "epoch": 0.1670739156994502, "grad_norm": 0.39837130904197693, "learning_rate": 4.663462474698749e-05, "loss": 4.3896, "step": 5470 }, { "epoch": 0.167104459376909, "grad_norm": 0.38476046919822693, "learning_rate": 4.663342254298181e-05, "loss": 4.4649, "step": 5471 }, { "epoch": 0.16713500305436774, "grad_norm": 0.3871326148509979, "learning_rate": 4.66322201397861e-05, "loss": 4.4125, "step": 5472 }, { "epoch": 0.16716554673182651, "grad_norm": 0.40336209535598755, "learning_rate": 4.663101753741141e-05, "loss": 4.5291, "step": 5473 }, { "epoch": 0.1671960904092853, "grad_norm": 0.37679916620254517, "learning_rate": 4.662981473586883e-05, "loss": 4.4349, "step": 5474 }, { "epoch": 0.16722663408674404, "grad_norm": 0.3740946054458618, "learning_rate": 4.662861173516942e-05, "loss": 4.4989, "step": 5475 }, { "epoch": 0.16725717776420282, "grad_norm": 0.3866991698741913, "learning_rate": 4.6627408535324256e-05, "loss": 4.3918, "step": 5476 }, { "epoch": 0.16728772144166157, "grad_norm": 0.38243669271469116, "learning_rate": 4.662620513634443e-05, "loss": 4.3457, "step": 5477 }, { "epoch": 0.16731826511912035, "grad_norm": 0.3953832685947418, "learning_rate": 4.6625001538241006e-05, "loss": 4.428, "step": 5478 }, { "epoch": 0.1673488087965791, "grad_norm": 0.39895209670066833, "learning_rate": 4.6623797741025084e-05, "loss": 4.4441, "step": 5479 }, { "epoch": 0.16737935247403787, "grad_norm": 0.3803284764289856, "learning_rate": 4.662259374470773e-05, "loss": 4.4112, "step": 5480 }, { "epoch": 0.16740989615149665, "grad_norm": 0.38536131381988525, "learning_rate": 4.6621389549300043e-05, "loss": 4.4222, "step": 5481 }, { "epoch": 0.1674404398289554, "grad_norm": 0.38390082120895386, "learning_rate": 4.66201851548131e-05, "loss": 4.4561, "step": 5482 }, { "epoch": 0.16747098350641418, "grad_norm": 0.3886963129043579, "learning_rate": 4.661898056125801e-05, "loss": 4.4351, "step": 5483 }, { "epoch": 0.16750152718387293, "grad_norm": 0.3896923065185547, "learning_rate": 4.661777576864584e-05, "loss": 4.3368, "step": 5484 }, { "epoch": 0.1675320708613317, "grad_norm": 0.3912919759750366, "learning_rate": 4.661657077698769e-05, "loss": 4.4213, "step": 5485 }, { "epoch": 0.16756261453879048, "grad_norm": 0.39807114005088806, "learning_rate": 4.661536558629467e-05, "loss": 4.4524, "step": 5486 }, { "epoch": 0.16759315821624923, "grad_norm": 0.3918576240539551, "learning_rate": 4.661416019657785e-05, "loss": 4.4762, "step": 5487 }, { "epoch": 0.167623701893708, "grad_norm": 0.39393332600593567, "learning_rate": 4.6612954607848356e-05, "loss": 4.4083, "step": 5488 }, { "epoch": 0.16765424557116676, "grad_norm": 0.3786848783493042, "learning_rate": 4.6611748820117274e-05, "loss": 4.3827, "step": 5489 }, { "epoch": 0.16768478924862554, "grad_norm": 0.3977106809616089, "learning_rate": 4.661054283339571e-05, "loss": 4.4191, "step": 5490 }, { "epoch": 0.1677153329260843, "grad_norm": 0.39422425627708435, "learning_rate": 4.660933664769477e-05, "loss": 4.3427, "step": 5491 }, { "epoch": 0.16774587660354306, "grad_norm": 0.3934214413166046, "learning_rate": 4.660813026302555e-05, "loss": 4.487, "step": 5492 }, { "epoch": 0.16777642028100184, "grad_norm": 0.3791116178035736, "learning_rate": 4.660692367939916e-05, "loss": 4.4049, "step": 5493 }, { "epoch": 0.1678069639584606, "grad_norm": 0.3785405158996582, "learning_rate": 4.660571689682673e-05, "loss": 4.3262, "step": 5494 }, { "epoch": 0.16783750763591937, "grad_norm": 0.3902338445186615, "learning_rate": 4.660450991531935e-05, "loss": 4.4368, "step": 5495 }, { "epoch": 0.16786805131337812, "grad_norm": 0.39518120884895325, "learning_rate": 4.660330273488813e-05, "loss": 4.4473, "step": 5496 }, { "epoch": 0.1678985949908369, "grad_norm": 0.3865361213684082, "learning_rate": 4.6602095355544206e-05, "loss": 4.3759, "step": 5497 }, { "epoch": 0.16792913866829567, "grad_norm": 0.3920730948448181, "learning_rate": 4.660088777729868e-05, "loss": 4.3936, "step": 5498 }, { "epoch": 0.16795968234575442, "grad_norm": 0.38583335280418396, "learning_rate": 4.659968000016267e-05, "loss": 4.403, "step": 5499 }, { "epoch": 0.1679902260232132, "grad_norm": 0.39302152395248413, "learning_rate": 4.659847202414731e-05, "loss": 4.396, "step": 5500 }, { "epoch": 0.16802076970067195, "grad_norm": 0.3951582610607147, "learning_rate": 4.659726384926371e-05, "loss": 4.4068, "step": 5501 }, { "epoch": 0.16805131337813073, "grad_norm": 0.3942042589187622, "learning_rate": 4.6596055475522985e-05, "loss": 4.3334, "step": 5502 }, { "epoch": 0.1680818570555895, "grad_norm": 0.38928574323654175, "learning_rate": 4.6594846902936284e-05, "loss": 4.4127, "step": 5503 }, { "epoch": 0.16811240073304826, "grad_norm": 0.3823111355304718, "learning_rate": 4.6593638131514724e-05, "loss": 4.3556, "step": 5504 }, { "epoch": 0.16814294441050703, "grad_norm": 0.3934011161327362, "learning_rate": 4.659242916126943e-05, "loss": 4.4345, "step": 5505 }, { "epoch": 0.16817348808796578, "grad_norm": 0.389751136302948, "learning_rate": 4.6591219992211556e-05, "loss": 4.3793, "step": 5506 }, { "epoch": 0.16820403176542456, "grad_norm": 0.3830115497112274, "learning_rate": 4.659001062435221e-05, "loss": 4.3883, "step": 5507 }, { "epoch": 0.1682345754428833, "grad_norm": 0.38799506425857544, "learning_rate": 4.658880105770253e-05, "loss": 4.3747, "step": 5508 }, { "epoch": 0.1682651191203421, "grad_norm": 0.391139954328537, "learning_rate": 4.6587591292273655e-05, "loss": 4.3981, "step": 5509 }, { "epoch": 0.16829566279780087, "grad_norm": 0.38038915395736694, "learning_rate": 4.658638132807673e-05, "loss": 4.3638, "step": 5510 }, { "epoch": 0.16832620647525962, "grad_norm": 0.38765236735343933, "learning_rate": 4.658517116512291e-05, "loss": 4.4061, "step": 5511 }, { "epoch": 0.1683567501527184, "grad_norm": 0.3835907280445099, "learning_rate": 4.6583960803423304e-05, "loss": 4.3003, "step": 5512 }, { "epoch": 0.16838729383017714, "grad_norm": 0.389777272939682, "learning_rate": 4.658275024298908e-05, "loss": 4.3486, "step": 5513 }, { "epoch": 0.16841783750763592, "grad_norm": 0.3821081817150116, "learning_rate": 4.6581539483831373e-05, "loss": 4.4145, "step": 5514 }, { "epoch": 0.1684483811850947, "grad_norm": 0.3976480960845947, "learning_rate": 4.658032852596134e-05, "loss": 4.3804, "step": 5515 }, { "epoch": 0.16847892486255345, "grad_norm": 0.3869412839412689, "learning_rate": 4.657911736939012e-05, "loss": 4.3734, "step": 5516 }, { "epoch": 0.16850946854001222, "grad_norm": 0.3769197165966034, "learning_rate": 4.657790601412888e-05, "loss": 4.4198, "step": 5517 }, { "epoch": 0.16854001221747097, "grad_norm": 0.3890969753265381, "learning_rate": 4.6576694460188766e-05, "loss": 4.3599, "step": 5518 }, { "epoch": 0.16857055589492975, "grad_norm": 0.36784806847572327, "learning_rate": 4.657548270758093e-05, "loss": 4.3388, "step": 5519 }, { "epoch": 0.1686010995723885, "grad_norm": 0.370087206363678, "learning_rate": 4.657427075631653e-05, "loss": 4.3674, "step": 5520 }, { "epoch": 0.16863164324984728, "grad_norm": 0.38761255145072937, "learning_rate": 4.6573058606406725e-05, "loss": 4.4427, "step": 5521 }, { "epoch": 0.16866218692730606, "grad_norm": 0.3909359574317932, "learning_rate": 4.657184625786269e-05, "loss": 4.4119, "step": 5522 }, { "epoch": 0.1686927306047648, "grad_norm": 0.37683114409446716, "learning_rate": 4.6570633710695555e-05, "loss": 4.3264, "step": 5523 }, { "epoch": 0.16872327428222358, "grad_norm": 0.38259565830230713, "learning_rate": 4.656942096491652e-05, "loss": 4.3932, "step": 5524 }, { "epoch": 0.16875381795968233, "grad_norm": 0.38889268040657043, "learning_rate": 4.656820802053673e-05, "loss": 4.3723, "step": 5525 }, { "epoch": 0.1687843616371411, "grad_norm": 0.39027705788612366, "learning_rate": 4.656699487756736e-05, "loss": 4.3163, "step": 5526 }, { "epoch": 0.1688149053145999, "grad_norm": 0.3991444408893585, "learning_rate": 4.656578153601958e-05, "loss": 4.3695, "step": 5527 }, { "epoch": 0.16884544899205864, "grad_norm": 0.384138822555542, "learning_rate": 4.656456799590456e-05, "loss": 4.3985, "step": 5528 }, { "epoch": 0.16887599266951742, "grad_norm": 0.38203564286231995, "learning_rate": 4.6563354257233474e-05, "loss": 4.3573, "step": 5529 }, { "epoch": 0.16890653634697617, "grad_norm": 0.3918568789958954, "learning_rate": 4.6562140320017506e-05, "loss": 4.4219, "step": 5530 }, { "epoch": 0.16893708002443494, "grad_norm": 0.374971866607666, "learning_rate": 4.656092618426782e-05, "loss": 4.3633, "step": 5531 }, { "epoch": 0.16896762370189372, "grad_norm": 0.3852115571498871, "learning_rate": 4.65597118499956e-05, "loss": 4.3996, "step": 5532 }, { "epoch": 0.16899816737935247, "grad_norm": 0.39344123005867004, "learning_rate": 4.655849731721203e-05, "loss": 4.3926, "step": 5533 }, { "epoch": 0.16902871105681125, "grad_norm": 0.3905058801174164, "learning_rate": 4.65572825859283e-05, "loss": 4.3594, "step": 5534 }, { "epoch": 0.16905925473427, "grad_norm": 0.3664369285106659, "learning_rate": 4.655606765615557e-05, "loss": 4.2762, "step": 5535 }, { "epoch": 0.16908979841172878, "grad_norm": 0.3846016824245453, "learning_rate": 4.6554852527905044e-05, "loss": 4.4053, "step": 5536 }, { "epoch": 0.16912034208918753, "grad_norm": 0.3793063759803772, "learning_rate": 4.655363720118792e-05, "loss": 4.4131, "step": 5537 }, { "epoch": 0.1691508857666463, "grad_norm": 0.3922726511955261, "learning_rate": 4.6552421676015365e-05, "loss": 4.4264, "step": 5538 }, { "epoch": 0.16918142944410508, "grad_norm": 0.3998384475708008, "learning_rate": 4.655120595239859e-05, "loss": 4.2568, "step": 5539 }, { "epoch": 0.16921197312156383, "grad_norm": 0.3901744782924652, "learning_rate": 4.6549990030348776e-05, "loss": 4.4175, "step": 5540 }, { "epoch": 0.1692425167990226, "grad_norm": 0.39926770329475403, "learning_rate": 4.654877390987713e-05, "loss": 4.4047, "step": 5541 }, { "epoch": 0.16927306047648136, "grad_norm": 0.38312020897865295, "learning_rate": 4.654755759099484e-05, "loss": 4.3838, "step": 5542 }, { "epoch": 0.16930360415394013, "grad_norm": 0.4255481958389282, "learning_rate": 4.654634107371311e-05, "loss": 4.4007, "step": 5543 }, { "epoch": 0.1693341478313989, "grad_norm": 0.38968977332115173, "learning_rate": 4.654512435804313e-05, "loss": 4.327, "step": 5544 }, { "epoch": 0.16936469150885766, "grad_norm": 0.3938654065132141, "learning_rate": 4.6543907443996123e-05, "loss": 4.4646, "step": 5545 }, { "epoch": 0.16939523518631644, "grad_norm": 0.3914112448692322, "learning_rate": 4.654269033158328e-05, "loss": 4.3173, "step": 5546 }, { "epoch": 0.1694257788637752, "grad_norm": 0.384186327457428, "learning_rate": 4.6541473020815815e-05, "loss": 4.4266, "step": 5547 }, { "epoch": 0.16945632254123397, "grad_norm": 0.3796835243701935, "learning_rate": 4.654025551170493e-05, "loss": 4.3192, "step": 5548 }, { "epoch": 0.16948686621869274, "grad_norm": 0.3892373740673065, "learning_rate": 4.653903780426184e-05, "loss": 4.364, "step": 5549 }, { "epoch": 0.1695174098961515, "grad_norm": 0.3824256658554077, "learning_rate": 4.6537819898497746e-05, "loss": 4.3895, "step": 5550 }, { "epoch": 0.16954795357361027, "grad_norm": 0.38533252477645874, "learning_rate": 4.653660179442389e-05, "loss": 4.379, "step": 5551 }, { "epoch": 0.16957849725106902, "grad_norm": 0.40833523869514465, "learning_rate": 4.653538349205144e-05, "loss": 4.2686, "step": 5552 }, { "epoch": 0.1696090409285278, "grad_norm": 0.37707018852233887, "learning_rate": 4.653416499139166e-05, "loss": 4.387, "step": 5553 }, { "epoch": 0.16963958460598655, "grad_norm": 0.37178748846054077, "learning_rate": 4.6532946292455745e-05, "loss": 4.3808, "step": 5554 }, { "epoch": 0.16967012828344533, "grad_norm": 0.39351484179496765, "learning_rate": 4.653172739525493e-05, "loss": 4.4585, "step": 5555 }, { "epoch": 0.1697006719609041, "grad_norm": 0.37821319699287415, "learning_rate": 4.653050829980043e-05, "loss": 4.4094, "step": 5556 }, { "epoch": 0.16973121563836285, "grad_norm": 0.3778822422027588, "learning_rate": 4.652928900610346e-05, "loss": 4.4224, "step": 5557 }, { "epoch": 0.16976175931582163, "grad_norm": 0.4041855037212372, "learning_rate": 4.6528069514175265e-05, "loss": 4.4746, "step": 5558 }, { "epoch": 0.16979230299328038, "grad_norm": 0.38463094830513, "learning_rate": 4.652684982402706e-05, "loss": 4.3799, "step": 5559 }, { "epoch": 0.16982284667073916, "grad_norm": 0.399958074092865, "learning_rate": 4.652562993567008e-05, "loss": 4.3376, "step": 5560 }, { "epoch": 0.16985339034819794, "grad_norm": 0.3897896111011505, "learning_rate": 4.652440984911556e-05, "loss": 4.524, "step": 5561 }, { "epoch": 0.16988393402565669, "grad_norm": 0.3891705274581909, "learning_rate": 4.652318956437474e-05, "loss": 4.4001, "step": 5562 }, { "epoch": 0.16991447770311546, "grad_norm": 0.3910857141017914, "learning_rate": 4.652196908145884e-05, "loss": 4.4029, "step": 5563 }, { "epoch": 0.1699450213805742, "grad_norm": 0.38139939308166504, "learning_rate": 4.65207484003791e-05, "loss": 4.3321, "step": 5564 }, { "epoch": 0.169975565058033, "grad_norm": 0.37202903628349304, "learning_rate": 4.651952752114677e-05, "loss": 4.4434, "step": 5565 }, { "epoch": 0.17000610873549174, "grad_norm": 0.38164904713630676, "learning_rate": 4.6518306443773085e-05, "loss": 4.2618, "step": 5566 }, { "epoch": 0.17003665241295052, "grad_norm": 0.3933054208755493, "learning_rate": 4.651708516826929e-05, "loss": 4.4029, "step": 5567 }, { "epoch": 0.1700671960904093, "grad_norm": 0.38328397274017334, "learning_rate": 4.6515863694646636e-05, "loss": 4.3496, "step": 5568 }, { "epoch": 0.17009773976786804, "grad_norm": 0.37921249866485596, "learning_rate": 4.651464202291635e-05, "loss": 4.4666, "step": 5569 }, { "epoch": 0.17012828344532682, "grad_norm": 0.3828587532043457, "learning_rate": 4.65134201530897e-05, "loss": 4.2985, "step": 5570 }, { "epoch": 0.17015882712278557, "grad_norm": 0.3846670687198639, "learning_rate": 4.6512198085177924e-05, "loss": 4.4399, "step": 5571 }, { "epoch": 0.17018937080024435, "grad_norm": 0.38023239374160767, "learning_rate": 4.651097581919229e-05, "loss": 4.3947, "step": 5572 }, { "epoch": 0.17021991447770313, "grad_norm": 0.3944858908653259, "learning_rate": 4.650975335514403e-05, "loss": 4.384, "step": 5573 }, { "epoch": 0.17025045815516188, "grad_norm": 0.3947773277759552, "learning_rate": 4.650853069304442e-05, "loss": 4.3522, "step": 5574 }, { "epoch": 0.17028100183262065, "grad_norm": 0.3853848874568939, "learning_rate": 4.650730783290471e-05, "loss": 4.3977, "step": 5575 }, { "epoch": 0.1703115455100794, "grad_norm": 0.38274121284484863, "learning_rate": 4.650608477473615e-05, "loss": 4.2575, "step": 5576 }, { "epoch": 0.17034208918753818, "grad_norm": 0.38807711005210876, "learning_rate": 4.6504861518550015e-05, "loss": 4.3871, "step": 5577 }, { "epoch": 0.17037263286499696, "grad_norm": 0.3922170400619507, "learning_rate": 4.650363806435757e-05, "loss": 4.3101, "step": 5578 }, { "epoch": 0.1704031765424557, "grad_norm": 0.3805498480796814, "learning_rate": 4.650241441217006e-05, "loss": 4.3206, "step": 5579 }, { "epoch": 0.1704337202199145, "grad_norm": 0.38892272114753723, "learning_rate": 4.650119056199878e-05, "loss": 4.3872, "step": 5580 }, { "epoch": 0.17046426389737324, "grad_norm": 0.3771079480648041, "learning_rate": 4.649996651385497e-05, "loss": 4.4782, "step": 5581 }, { "epoch": 0.170494807574832, "grad_norm": 0.3817082643508911, "learning_rate": 4.6498742267749924e-05, "loss": 4.3883, "step": 5582 }, { "epoch": 0.17052535125229076, "grad_norm": 0.4032316207885742, "learning_rate": 4.6497517823694906e-05, "loss": 4.357, "step": 5583 }, { "epoch": 0.17055589492974954, "grad_norm": 0.3755421042442322, "learning_rate": 4.6496293181701176e-05, "loss": 4.3826, "step": 5584 }, { "epoch": 0.17058643860720832, "grad_norm": 0.3808068335056305, "learning_rate": 4.649506834178003e-05, "loss": 4.3925, "step": 5585 }, { "epoch": 0.17061698228466707, "grad_norm": 0.3732621669769287, "learning_rate": 4.649384330394273e-05, "loss": 4.4656, "step": 5586 }, { "epoch": 0.17064752596212585, "grad_norm": 0.38404351472854614, "learning_rate": 4.649261806820058e-05, "loss": 4.3696, "step": 5587 }, { "epoch": 0.1706780696395846, "grad_norm": 0.4072269797325134, "learning_rate": 4.6491392634564834e-05, "loss": 4.3625, "step": 5588 }, { "epoch": 0.17070861331704337, "grad_norm": 0.38498279452323914, "learning_rate": 4.6490167003046785e-05, "loss": 4.3791, "step": 5589 }, { "epoch": 0.17073915699450215, "grad_norm": 0.37115365266799927, "learning_rate": 4.6488941173657726e-05, "loss": 4.3338, "step": 5590 }, { "epoch": 0.1707697006719609, "grad_norm": 0.37507572770118713, "learning_rate": 4.6487715146408926e-05, "loss": 4.2805, "step": 5591 }, { "epoch": 0.17080024434941968, "grad_norm": 0.3783951997756958, "learning_rate": 4.64864889213117e-05, "loss": 4.4473, "step": 5592 }, { "epoch": 0.17083078802687843, "grad_norm": 0.38889017701148987, "learning_rate": 4.6485262498377316e-05, "loss": 4.4963, "step": 5593 }, { "epoch": 0.1708613317043372, "grad_norm": 0.39764106273651123, "learning_rate": 4.648403587761707e-05, "loss": 4.4039, "step": 5594 }, { "epoch": 0.17089187538179595, "grad_norm": 0.38574087619781494, "learning_rate": 4.648280905904226e-05, "loss": 4.3772, "step": 5595 }, { "epoch": 0.17092241905925473, "grad_norm": 0.3797881007194519, "learning_rate": 4.6481582042664185e-05, "loss": 4.3841, "step": 5596 }, { "epoch": 0.1709529627367135, "grad_norm": 0.3836442828178406, "learning_rate": 4.6480354828494144e-05, "loss": 4.3744, "step": 5597 }, { "epoch": 0.17098350641417226, "grad_norm": 0.3871574103832245, "learning_rate": 4.647912741654342e-05, "loss": 4.4331, "step": 5598 }, { "epoch": 0.17101405009163104, "grad_norm": 0.38589876890182495, "learning_rate": 4.647789980682334e-05, "loss": 4.3907, "step": 5599 }, { "epoch": 0.1710445937690898, "grad_norm": 0.3810274302959442, "learning_rate": 4.647667199934518e-05, "loss": 4.3567, "step": 5600 }, { "epoch": 0.17107513744654856, "grad_norm": 0.3942650258541107, "learning_rate": 4.647544399412027e-05, "loss": 4.3588, "step": 5601 }, { "epoch": 0.17110568112400734, "grad_norm": 0.39662009477615356, "learning_rate": 4.64742157911599e-05, "loss": 4.4514, "step": 5602 }, { "epoch": 0.1711362248014661, "grad_norm": 0.3948637545108795, "learning_rate": 4.6472987390475383e-05, "loss": 4.3253, "step": 5603 }, { "epoch": 0.17116676847892487, "grad_norm": 0.40148577094078064, "learning_rate": 4.6471758792078035e-05, "loss": 4.4507, "step": 5604 }, { "epoch": 0.17119731215638362, "grad_norm": 0.38388246297836304, "learning_rate": 4.647052999597916e-05, "loss": 4.421, "step": 5605 }, { "epoch": 0.1712278558338424, "grad_norm": 0.4375688135623932, "learning_rate": 4.646930100219008e-05, "loss": 4.4007, "step": 5606 }, { "epoch": 0.17125839951130117, "grad_norm": 0.38368698954582214, "learning_rate": 4.6468071810722106e-05, "loss": 4.4125, "step": 5607 }, { "epoch": 0.17128894318875992, "grad_norm": 0.3772123456001282, "learning_rate": 4.646684242158656e-05, "loss": 4.336, "step": 5608 }, { "epoch": 0.1713194868662187, "grad_norm": 0.38819053769111633, "learning_rate": 4.6465612834794755e-05, "loss": 4.4149, "step": 5609 }, { "epoch": 0.17135003054367745, "grad_norm": 0.4056474268436432, "learning_rate": 4.6464383050358015e-05, "loss": 4.3972, "step": 5610 }, { "epoch": 0.17138057422113623, "grad_norm": 0.39678508043289185, "learning_rate": 4.6463153068287665e-05, "loss": 4.357, "step": 5611 }, { "epoch": 0.17141111789859498, "grad_norm": 0.3824288845062256, "learning_rate": 4.6461922888595035e-05, "loss": 4.365, "step": 5612 }, { "epoch": 0.17144166157605376, "grad_norm": 0.40455007553100586, "learning_rate": 4.6460692511291434e-05, "loss": 4.4156, "step": 5613 }, { "epoch": 0.17147220525351253, "grad_norm": 0.39557933807373047, "learning_rate": 4.645946193638821e-05, "loss": 4.4079, "step": 5614 }, { "epoch": 0.17150274893097128, "grad_norm": 0.37912052869796753, "learning_rate": 4.6458231163896694e-05, "loss": 4.3577, "step": 5615 }, { "epoch": 0.17153329260843006, "grad_norm": 0.3804471790790558, "learning_rate": 4.64570001938282e-05, "loss": 4.4222, "step": 5616 }, { "epoch": 0.1715638362858888, "grad_norm": 0.3889213502407074, "learning_rate": 4.6455769026194086e-05, "loss": 4.3981, "step": 5617 }, { "epoch": 0.1715943799633476, "grad_norm": 0.4040849208831787, "learning_rate": 4.645453766100566e-05, "loss": 4.5028, "step": 5618 }, { "epoch": 0.17162492364080636, "grad_norm": 0.3790966868400574, "learning_rate": 4.645330609827429e-05, "loss": 4.4283, "step": 5619 }, { "epoch": 0.17165546731826511, "grad_norm": 0.4088180661201477, "learning_rate": 4.645207433801129e-05, "loss": 4.4265, "step": 5620 }, { "epoch": 0.1716860109957239, "grad_norm": 0.4127112030982971, "learning_rate": 4.645084238022801e-05, "loss": 4.3077, "step": 5621 }, { "epoch": 0.17171655467318264, "grad_norm": 0.3919907212257385, "learning_rate": 4.6449610224935803e-05, "loss": 4.4224, "step": 5622 }, { "epoch": 0.17174709835064142, "grad_norm": 0.38805636763572693, "learning_rate": 4.6448377872146e-05, "loss": 4.4521, "step": 5623 }, { "epoch": 0.1717776420281002, "grad_norm": 0.3931783437728882, "learning_rate": 4.644714532186995e-05, "loss": 4.3853, "step": 5624 }, { "epoch": 0.17180818570555895, "grad_norm": 0.3989301323890686, "learning_rate": 4.644591257411902e-05, "loss": 4.4255, "step": 5625 }, { "epoch": 0.17183872938301772, "grad_norm": 0.39923861622810364, "learning_rate": 4.644467962890454e-05, "loss": 4.4503, "step": 5626 }, { "epoch": 0.17186927306047647, "grad_norm": 0.37732580304145813, "learning_rate": 4.644344648623786e-05, "loss": 4.4321, "step": 5627 }, { "epoch": 0.17189981673793525, "grad_norm": 0.41260451078414917, "learning_rate": 4.644221314613035e-05, "loss": 4.3863, "step": 5628 }, { "epoch": 0.171930360415394, "grad_norm": 0.39723214507102966, "learning_rate": 4.644097960859337e-05, "loss": 4.378, "step": 5629 }, { "epoch": 0.17196090409285278, "grad_norm": 0.3807816803455353, "learning_rate": 4.643974587363825e-05, "loss": 4.3268, "step": 5630 }, { "epoch": 0.17199144777031156, "grad_norm": 0.37816014885902405, "learning_rate": 4.643851194127638e-05, "loss": 4.401, "step": 5631 }, { "epoch": 0.1720219914477703, "grad_norm": 0.3826638460159302, "learning_rate": 4.64372778115191e-05, "loss": 4.3553, "step": 5632 }, { "epoch": 0.17205253512522908, "grad_norm": 0.3905216157436371, "learning_rate": 4.643604348437778e-05, "loss": 4.4029, "step": 5633 }, { "epoch": 0.17208307880268783, "grad_norm": 0.36978790163993835, "learning_rate": 4.6434808959863794e-05, "loss": 4.3618, "step": 5634 }, { "epoch": 0.1721136224801466, "grad_norm": 0.3762195408344269, "learning_rate": 4.64335742379885e-05, "loss": 4.4503, "step": 5635 }, { "epoch": 0.1721441661576054, "grad_norm": 0.38076913356781006, "learning_rate": 4.6432339318763265e-05, "loss": 4.4006, "step": 5636 }, { "epoch": 0.17217470983506414, "grad_norm": 0.38619914650917053, "learning_rate": 4.643110420219946e-05, "loss": 4.4361, "step": 5637 }, { "epoch": 0.17220525351252292, "grad_norm": 0.37713623046875, "learning_rate": 4.6429868888308456e-05, "loss": 4.3138, "step": 5638 }, { "epoch": 0.17223579718998167, "grad_norm": 0.38794785737991333, "learning_rate": 4.642863337710164e-05, "loss": 4.3895, "step": 5639 }, { "epoch": 0.17226634086744044, "grad_norm": 0.38196730613708496, "learning_rate": 4.642739766859038e-05, "loss": 4.3614, "step": 5640 }, { "epoch": 0.1722968845448992, "grad_norm": 0.3808937668800354, "learning_rate": 4.642616176278605e-05, "loss": 4.4361, "step": 5641 }, { "epoch": 0.17232742822235797, "grad_norm": 0.3844855725765228, "learning_rate": 4.642492565970002e-05, "loss": 4.384, "step": 5642 }, { "epoch": 0.17235797189981675, "grad_norm": 0.3758593797683716, "learning_rate": 4.64236893593437e-05, "loss": 4.3907, "step": 5643 }, { "epoch": 0.1723885155772755, "grad_norm": 0.38705411553382874, "learning_rate": 4.642245286172845e-05, "loss": 4.3768, "step": 5644 }, { "epoch": 0.17241905925473427, "grad_norm": 0.39923667907714844, "learning_rate": 4.6421216166865666e-05, "loss": 4.4299, "step": 5645 }, { "epoch": 0.17244960293219302, "grad_norm": 0.38364511728286743, "learning_rate": 4.6419979274766736e-05, "loss": 4.368, "step": 5646 }, { "epoch": 0.1724801466096518, "grad_norm": 0.3756561279296875, "learning_rate": 4.641874218544303e-05, "loss": 4.3352, "step": 5647 }, { "epoch": 0.17251069028711058, "grad_norm": 0.3766981363296509, "learning_rate": 4.641750489890596e-05, "loss": 4.2898, "step": 5648 }, { "epoch": 0.17254123396456933, "grad_norm": 0.3918282389640808, "learning_rate": 4.641626741516691e-05, "loss": 4.3728, "step": 5649 }, { "epoch": 0.1725717776420281, "grad_norm": 0.3841163218021393, "learning_rate": 4.641502973423728e-05, "loss": 4.3371, "step": 5650 }, { "epoch": 0.17260232131948686, "grad_norm": 0.37905973196029663, "learning_rate": 4.641379185612845e-05, "loss": 4.4222, "step": 5651 }, { "epoch": 0.17263286499694563, "grad_norm": 0.38014325499534607, "learning_rate": 4.641255378085183e-05, "loss": 4.364, "step": 5652 }, { "epoch": 0.1726634086744044, "grad_norm": 0.3729250729084015, "learning_rate": 4.641131550841883e-05, "loss": 4.3446, "step": 5653 }, { "epoch": 0.17269395235186316, "grad_norm": 0.3732716143131256, "learning_rate": 4.6410077038840826e-05, "loss": 4.3869, "step": 5654 }, { "epoch": 0.17272449602932194, "grad_norm": 0.3895731568336487, "learning_rate": 4.640883837212924e-05, "loss": 4.3812, "step": 5655 }, { "epoch": 0.1727550397067807, "grad_norm": 0.3883117735385895, "learning_rate": 4.6407599508295476e-05, "loss": 4.3863, "step": 5656 }, { "epoch": 0.17278558338423947, "grad_norm": 0.3923362195491791, "learning_rate": 4.6406360447350924e-05, "loss": 4.4155, "step": 5657 }, { "epoch": 0.17281612706169822, "grad_norm": 0.3794252574443817, "learning_rate": 4.6405121189307023e-05, "loss": 4.3229, "step": 5658 }, { "epoch": 0.172846670739157, "grad_norm": 0.39515310525894165, "learning_rate": 4.640388173417515e-05, "loss": 4.4188, "step": 5659 }, { "epoch": 0.17287721441661577, "grad_norm": 0.3963027894496918, "learning_rate": 4.640264208196674e-05, "loss": 4.425, "step": 5660 }, { "epoch": 0.17290775809407452, "grad_norm": 0.37203121185302734, "learning_rate": 4.64014022326932e-05, "loss": 4.3175, "step": 5661 }, { "epoch": 0.1729383017715333, "grad_norm": 0.3791271150112152, "learning_rate": 4.640016218636595e-05, "loss": 4.4339, "step": 5662 }, { "epoch": 0.17296884544899205, "grad_norm": 0.3783060908317566, "learning_rate": 4.63989219429964e-05, "loss": 4.4052, "step": 5663 }, { "epoch": 0.17299938912645083, "grad_norm": 0.38378697633743286, "learning_rate": 4.639768150259598e-05, "loss": 4.424, "step": 5664 }, { "epoch": 0.1730299328039096, "grad_norm": 0.38348886370658875, "learning_rate": 4.639644086517609e-05, "loss": 4.3176, "step": 5665 }, { "epoch": 0.17306047648136835, "grad_norm": 0.3852616846561432, "learning_rate": 4.6395200030748176e-05, "loss": 4.3951, "step": 5666 }, { "epoch": 0.17309102015882713, "grad_norm": 0.40700608491897583, "learning_rate": 4.639395899932366e-05, "loss": 4.3389, "step": 5667 }, { "epoch": 0.17312156383628588, "grad_norm": 0.39750945568084717, "learning_rate": 4.639271777091396e-05, "loss": 4.3778, "step": 5668 }, { "epoch": 0.17315210751374466, "grad_norm": 0.38753026723861694, "learning_rate": 4.63914763455305e-05, "loss": 4.3432, "step": 5669 }, { "epoch": 0.1731826511912034, "grad_norm": 0.3850792348384857, "learning_rate": 4.639023472318473e-05, "loss": 4.3879, "step": 5670 }, { "epoch": 0.17321319486866218, "grad_norm": 0.38620835542678833, "learning_rate": 4.638899290388806e-05, "loss": 4.3936, "step": 5671 }, { "epoch": 0.17324373854612096, "grad_norm": 0.38143813610076904, "learning_rate": 4.638775088765195e-05, "loss": 4.3618, "step": 5672 }, { "epoch": 0.1732742822235797, "grad_norm": 0.3767234683036804, "learning_rate": 4.638650867448782e-05, "loss": 4.3791, "step": 5673 }, { "epoch": 0.1733048259010385, "grad_norm": 0.39171668887138367, "learning_rate": 4.638526626440709e-05, "loss": 4.3949, "step": 5674 }, { "epoch": 0.17333536957849724, "grad_norm": 0.39460569620132446, "learning_rate": 4.638402365742124e-05, "loss": 4.4075, "step": 5675 }, { "epoch": 0.17336591325595602, "grad_norm": 0.39800286293029785, "learning_rate": 4.6382780853541675e-05, "loss": 4.3351, "step": 5676 }, { "epoch": 0.1733964569334148, "grad_norm": 0.37890490889549255, "learning_rate": 4.638153785277985e-05, "loss": 4.2677, "step": 5677 }, { "epoch": 0.17342700061087354, "grad_norm": 0.3933829367160797, "learning_rate": 4.6380294655147226e-05, "loss": 4.4308, "step": 5678 }, { "epoch": 0.17345754428833232, "grad_norm": 0.38607755303382874, "learning_rate": 4.637905126065524e-05, "loss": 4.3891, "step": 5679 }, { "epoch": 0.17348808796579107, "grad_norm": 0.38655534386634827, "learning_rate": 4.637780766931532e-05, "loss": 4.4029, "step": 5680 }, { "epoch": 0.17351863164324985, "grad_norm": 0.38242843747138977, "learning_rate": 4.6376563881138944e-05, "loss": 4.3953, "step": 5681 }, { "epoch": 0.17354917532070863, "grad_norm": 0.3992307782173157, "learning_rate": 4.637531989613755e-05, "loss": 4.3904, "step": 5682 }, { "epoch": 0.17357971899816738, "grad_norm": 0.40264278650283813, "learning_rate": 4.6374075714322595e-05, "loss": 4.4144, "step": 5683 }, { "epoch": 0.17361026267562615, "grad_norm": 0.3745940029621124, "learning_rate": 4.637283133570554e-05, "loss": 4.3664, "step": 5684 }, { "epoch": 0.1736408063530849, "grad_norm": 0.38735726475715637, "learning_rate": 4.6371586760297834e-05, "loss": 4.427, "step": 5685 }, { "epoch": 0.17367135003054368, "grad_norm": 0.4043811857700348, "learning_rate": 4.6370341988110944e-05, "loss": 4.3746, "step": 5686 }, { "epoch": 0.17370189370800243, "grad_norm": 0.3777353763580322, "learning_rate": 4.636909701915633e-05, "loss": 4.2827, "step": 5687 }, { "epoch": 0.1737324373854612, "grad_norm": 0.3925071656703949, "learning_rate": 4.636785185344544e-05, "loss": 4.4521, "step": 5688 }, { "epoch": 0.17376298106291999, "grad_norm": 0.3794148862361908, "learning_rate": 4.6366606490989764e-05, "loss": 4.4078, "step": 5689 }, { "epoch": 0.17379352474037874, "grad_norm": 0.38081488013267517, "learning_rate": 4.636536093180076e-05, "loss": 4.4401, "step": 5690 }, { "epoch": 0.1738240684178375, "grad_norm": 0.3792157769203186, "learning_rate": 4.6364115175889874e-05, "loss": 4.424, "step": 5691 }, { "epoch": 0.17385461209529626, "grad_norm": 0.38840121030807495, "learning_rate": 4.636286922326861e-05, "loss": 4.3461, "step": 5692 }, { "epoch": 0.17388515577275504, "grad_norm": 0.3699234426021576, "learning_rate": 4.6361623073948426e-05, "loss": 4.3521, "step": 5693 }, { "epoch": 0.17391569945021382, "grad_norm": 0.38403862714767456, "learning_rate": 4.636037672794079e-05, "loss": 4.4062, "step": 5694 }, { "epoch": 0.17394624312767257, "grad_norm": 0.3794884979724884, "learning_rate": 4.635913018525718e-05, "loss": 4.3379, "step": 5695 }, { "epoch": 0.17397678680513134, "grad_norm": 0.3743480443954468, "learning_rate": 4.635788344590909e-05, "loss": 4.3484, "step": 5696 }, { "epoch": 0.1740073304825901, "grad_norm": 0.38424304127693176, "learning_rate": 4.6356636509907974e-05, "loss": 4.4915, "step": 5697 }, { "epoch": 0.17403787416004887, "grad_norm": 0.3782161772251129, "learning_rate": 4.635538937726533e-05, "loss": 4.4934, "step": 5698 }, { "epoch": 0.17406841783750765, "grad_norm": 0.37860971689224243, "learning_rate": 4.6354142047992635e-05, "loss": 4.369, "step": 5699 }, { "epoch": 0.1740989615149664, "grad_norm": 0.38001498579978943, "learning_rate": 4.6352894522101376e-05, "loss": 4.3898, "step": 5700 }, { "epoch": 0.17412950519242518, "grad_norm": 0.36935609579086304, "learning_rate": 4.635164679960303e-05, "loss": 4.4392, "step": 5701 }, { "epoch": 0.17416004886988393, "grad_norm": 0.3798295259475708, "learning_rate": 4.63503988805091e-05, "loss": 4.3301, "step": 5702 }, { "epoch": 0.1741905925473427, "grad_norm": 0.37617945671081543, "learning_rate": 4.634915076483107e-05, "loss": 4.3237, "step": 5703 }, { "epoch": 0.17422113622480145, "grad_norm": 0.3949432969093323, "learning_rate": 4.634790245258044e-05, "loss": 4.3956, "step": 5704 }, { "epoch": 0.17425167990226023, "grad_norm": 0.4007193148136139, "learning_rate": 4.634665394376869e-05, "loss": 4.415, "step": 5705 }, { "epoch": 0.174282223579719, "grad_norm": 0.3824465572834015, "learning_rate": 4.634540523840732e-05, "loss": 4.4331, "step": 5706 }, { "epoch": 0.17431276725717776, "grad_norm": 0.39106008410453796, "learning_rate": 4.6344156336507835e-05, "loss": 4.4613, "step": 5707 }, { "epoch": 0.17434331093463654, "grad_norm": 0.38565441966056824, "learning_rate": 4.634290723808172e-05, "loss": 4.4297, "step": 5708 }, { "epoch": 0.17437385461209529, "grad_norm": 0.39331164956092834, "learning_rate": 4.634165794314049e-05, "loss": 4.4129, "step": 5709 }, { "epoch": 0.17440439828955406, "grad_norm": 0.38329365849494934, "learning_rate": 4.6340408451695636e-05, "loss": 4.369, "step": 5710 }, { "epoch": 0.17443494196701284, "grad_norm": 0.38702258467674255, "learning_rate": 4.6339158763758675e-05, "loss": 4.3444, "step": 5711 }, { "epoch": 0.1744654856444716, "grad_norm": 0.392318993806839, "learning_rate": 4.6337908879341106e-05, "loss": 4.4375, "step": 5712 }, { "epoch": 0.17449602932193037, "grad_norm": 0.39661601185798645, "learning_rate": 4.633665879845445e-05, "loss": 4.431, "step": 5713 }, { "epoch": 0.17452657299938912, "grad_norm": 0.3937036991119385, "learning_rate": 4.633540852111019e-05, "loss": 4.3868, "step": 5714 }, { "epoch": 0.1745571166768479, "grad_norm": 0.3740355670452118, "learning_rate": 4.633415804731987e-05, "loss": 4.2848, "step": 5715 }, { "epoch": 0.17458766035430665, "grad_norm": 0.38163501024246216, "learning_rate": 4.633290737709497e-05, "loss": 4.4076, "step": 5716 }, { "epoch": 0.17461820403176542, "grad_norm": 0.38529953360557556, "learning_rate": 4.633165651044703e-05, "loss": 4.3832, "step": 5717 }, { "epoch": 0.1746487477092242, "grad_norm": 0.378057599067688, "learning_rate": 4.633040544738756e-05, "loss": 4.3629, "step": 5718 }, { "epoch": 0.17467929138668295, "grad_norm": 0.38482967019081116, "learning_rate": 4.6329154187928094e-05, "loss": 4.3958, "step": 5719 }, { "epoch": 0.17470983506414173, "grad_norm": 0.38566771149635315, "learning_rate": 4.632790273208012e-05, "loss": 4.3221, "step": 5720 }, { "epoch": 0.17474037874160048, "grad_norm": 0.3963521122932434, "learning_rate": 4.632665107985519e-05, "loss": 4.4068, "step": 5721 }, { "epoch": 0.17477092241905925, "grad_norm": 0.3795883357524872, "learning_rate": 4.6325399231264815e-05, "loss": 4.4239, "step": 5722 }, { "epoch": 0.17480146609651803, "grad_norm": 0.4010990262031555, "learning_rate": 4.6324147186320524e-05, "loss": 4.4139, "step": 5723 }, { "epoch": 0.17483200977397678, "grad_norm": 0.3791094720363617, "learning_rate": 4.632289494503385e-05, "loss": 4.4182, "step": 5724 }, { "epoch": 0.17486255345143556, "grad_norm": 0.3878706991672516, "learning_rate": 4.6321642507416316e-05, "loss": 4.3691, "step": 5725 }, { "epoch": 0.1748930971288943, "grad_norm": 0.37092483043670654, "learning_rate": 4.6320389873479465e-05, "loss": 4.311, "step": 5726 }, { "epoch": 0.1749236408063531, "grad_norm": 0.37913772463798523, "learning_rate": 4.6319137043234814e-05, "loss": 4.2798, "step": 5727 }, { "epoch": 0.17495418448381186, "grad_norm": 0.37488415837287903, "learning_rate": 4.631788401669391e-05, "loss": 4.3843, "step": 5728 }, { "epoch": 0.17498472816127061, "grad_norm": 0.381668359041214, "learning_rate": 4.6316630793868286e-05, "loss": 4.3288, "step": 5729 }, { "epoch": 0.1750152718387294, "grad_norm": 0.3856382966041565, "learning_rate": 4.631537737476948e-05, "loss": 4.4334, "step": 5730 }, { "epoch": 0.17504581551618814, "grad_norm": 0.37662070989608765, "learning_rate": 4.6314123759409036e-05, "loss": 4.4156, "step": 5731 }, { "epoch": 0.17507635919364692, "grad_norm": 0.38941141963005066, "learning_rate": 4.63128699477985e-05, "loss": 4.3824, "step": 5732 }, { "epoch": 0.17510690287110567, "grad_norm": 0.38733360171318054, "learning_rate": 4.631161593994941e-05, "loss": 4.4014, "step": 5733 }, { "epoch": 0.17513744654856445, "grad_norm": 0.3915613293647766, "learning_rate": 4.631036173587331e-05, "loss": 4.2407, "step": 5734 }, { "epoch": 0.17516799022602322, "grad_norm": 0.37943974137306213, "learning_rate": 4.630910733558176e-05, "loss": 4.4551, "step": 5735 }, { "epoch": 0.17519853390348197, "grad_norm": 0.38526591658592224, "learning_rate": 4.63078527390863e-05, "loss": 4.3872, "step": 5736 }, { "epoch": 0.17522907758094075, "grad_norm": 0.37956616282463074, "learning_rate": 4.630659794639849e-05, "loss": 4.368, "step": 5737 }, { "epoch": 0.1752596212583995, "grad_norm": 0.38124799728393555, "learning_rate": 4.6305342957529866e-05, "loss": 4.353, "step": 5738 }, { "epoch": 0.17529016493585828, "grad_norm": 0.3853168189525604, "learning_rate": 4.6304087772492e-05, "loss": 4.3828, "step": 5739 }, { "epoch": 0.17532070861331706, "grad_norm": 0.38154366612434387, "learning_rate": 4.6302832391296446e-05, "loss": 4.3402, "step": 5740 }, { "epoch": 0.1753512522907758, "grad_norm": 0.3831058442592621, "learning_rate": 4.6301576813954764e-05, "loss": 4.3869, "step": 5741 }, { "epoch": 0.17538179596823458, "grad_norm": 0.398293137550354, "learning_rate": 4.630032104047851e-05, "loss": 4.356, "step": 5742 }, { "epoch": 0.17541233964569333, "grad_norm": 0.4077283442020416, "learning_rate": 4.629906507087925e-05, "loss": 4.3534, "step": 5743 }, { "epoch": 0.1754428833231521, "grad_norm": 0.4021378457546234, "learning_rate": 4.629780890516855e-05, "loss": 4.413, "step": 5744 }, { "epoch": 0.17547342700061086, "grad_norm": 0.3964713215827942, "learning_rate": 4.629655254335796e-05, "loss": 4.3948, "step": 5745 }, { "epoch": 0.17550397067806964, "grad_norm": 0.3809678852558136, "learning_rate": 4.629529598545907e-05, "loss": 4.3954, "step": 5746 }, { "epoch": 0.17553451435552841, "grad_norm": 0.3887732923030853, "learning_rate": 4.6294039231483446e-05, "loss": 4.343, "step": 5747 }, { "epoch": 0.17556505803298716, "grad_norm": 0.3948400020599365, "learning_rate": 4.629278228144265e-05, "loss": 4.4221, "step": 5748 }, { "epoch": 0.17559560171044594, "grad_norm": 0.3935920298099518, "learning_rate": 4.629152513534826e-05, "loss": 4.3298, "step": 5749 }, { "epoch": 0.1756261453879047, "grad_norm": 0.4015059173107147, "learning_rate": 4.629026779321185e-05, "loss": 4.3362, "step": 5750 }, { "epoch": 0.17565668906536347, "grad_norm": 0.3947207033634186, "learning_rate": 4.628901025504499e-05, "loss": 4.407, "step": 5751 }, { "epoch": 0.17568723274282225, "grad_norm": 0.4011167585849762, "learning_rate": 4.628775252085928e-05, "loss": 4.3999, "step": 5752 }, { "epoch": 0.175717776420281, "grad_norm": 0.37387922406196594, "learning_rate": 4.6286494590666284e-05, "loss": 4.3836, "step": 5753 }, { "epoch": 0.17574832009773977, "grad_norm": 0.3860800862312317, "learning_rate": 4.6285236464477585e-05, "loss": 4.3435, "step": 5754 }, { "epoch": 0.17577886377519852, "grad_norm": 0.3708031475543976, "learning_rate": 4.628397814230477e-05, "loss": 4.3855, "step": 5755 }, { "epoch": 0.1758094074526573, "grad_norm": 0.37552571296691895, "learning_rate": 4.6282719624159424e-05, "loss": 4.4265, "step": 5756 }, { "epoch": 0.17583995113011608, "grad_norm": 0.39390215277671814, "learning_rate": 4.6281460910053145e-05, "loss": 4.4492, "step": 5757 }, { "epoch": 0.17587049480757483, "grad_norm": 0.3875550925731659, "learning_rate": 4.62802019999975e-05, "loss": 4.4313, "step": 5758 }, { "epoch": 0.1759010384850336, "grad_norm": 0.3718439042568207, "learning_rate": 4.62789428940041e-05, "loss": 4.3333, "step": 5759 }, { "epoch": 0.17593158216249236, "grad_norm": 0.38335829973220825, "learning_rate": 4.6277683592084534e-05, "loss": 4.3669, "step": 5760 }, { "epoch": 0.17596212583995113, "grad_norm": 0.3836645483970642, "learning_rate": 4.6276424094250395e-05, "loss": 4.4427, "step": 5761 }, { "epoch": 0.17599266951740988, "grad_norm": 0.3971838355064392, "learning_rate": 4.627516440051328e-05, "loss": 4.3962, "step": 5762 }, { "epoch": 0.17602321319486866, "grad_norm": 0.3841167092323303, "learning_rate": 4.627390451088479e-05, "loss": 4.4493, "step": 5763 }, { "epoch": 0.17605375687232744, "grad_norm": 0.39395368099212646, "learning_rate": 4.627264442537652e-05, "loss": 4.3858, "step": 5764 }, { "epoch": 0.1760843005497862, "grad_norm": 0.38301676511764526, "learning_rate": 4.6271384144000075e-05, "loss": 4.3236, "step": 5765 }, { "epoch": 0.17611484422724497, "grad_norm": 0.4221208393573761, "learning_rate": 4.627012366676706e-05, "loss": 4.3578, "step": 5766 }, { "epoch": 0.17614538790470372, "grad_norm": 0.38791441917419434, "learning_rate": 4.6268862993689075e-05, "loss": 4.3975, "step": 5767 }, { "epoch": 0.1761759315821625, "grad_norm": 0.3823210895061493, "learning_rate": 4.626760212477774e-05, "loss": 4.3643, "step": 5768 }, { "epoch": 0.17620647525962127, "grad_norm": 0.3744346499443054, "learning_rate": 4.626634106004466e-05, "loss": 4.3947, "step": 5769 }, { "epoch": 0.17623701893708002, "grad_norm": 0.3970473110675812, "learning_rate": 4.6265079799501444e-05, "loss": 4.4191, "step": 5770 }, { "epoch": 0.1762675626145388, "grad_norm": 0.3788202702999115, "learning_rate": 4.6263818343159696e-05, "loss": 4.3403, "step": 5771 }, { "epoch": 0.17629810629199755, "grad_norm": 0.3746839761734009, "learning_rate": 4.626255669103105e-05, "loss": 4.4266, "step": 5772 }, { "epoch": 0.17632864996945632, "grad_norm": 0.39626753330230713, "learning_rate": 4.62612948431271e-05, "loss": 4.397, "step": 5773 }, { "epoch": 0.1763591936469151, "grad_norm": 0.3962087035179138, "learning_rate": 4.6260032799459486e-05, "loss": 4.3909, "step": 5774 }, { "epoch": 0.17638973732437385, "grad_norm": 0.3858213722705841, "learning_rate": 4.6258770560039824e-05, "loss": 4.4269, "step": 5775 }, { "epoch": 0.17642028100183263, "grad_norm": 0.3856048583984375, "learning_rate": 4.6257508124879725e-05, "loss": 4.4366, "step": 5776 }, { "epoch": 0.17645082467929138, "grad_norm": 0.3928299844264984, "learning_rate": 4.625624549399081e-05, "loss": 4.3289, "step": 5777 }, { "epoch": 0.17648136835675016, "grad_norm": 0.38761165738105774, "learning_rate": 4.625498266738473e-05, "loss": 4.4387, "step": 5778 }, { "epoch": 0.1765119120342089, "grad_norm": 0.38110366463661194, "learning_rate": 4.6253719645073085e-05, "loss": 4.2758, "step": 5779 }, { "epoch": 0.17654245571166768, "grad_norm": 0.38997918367385864, "learning_rate": 4.625245642706752e-05, "loss": 4.4317, "step": 5780 }, { "epoch": 0.17657299938912646, "grad_norm": 0.39863041043281555, "learning_rate": 4.6251193013379654e-05, "loss": 4.4194, "step": 5781 }, { "epoch": 0.1766035430665852, "grad_norm": 0.3745485842227936, "learning_rate": 4.624992940402114e-05, "loss": 4.36, "step": 5782 }, { "epoch": 0.176634086744044, "grad_norm": 0.3791861832141876, "learning_rate": 4.6248665599003595e-05, "loss": 4.3844, "step": 5783 }, { "epoch": 0.17666463042150274, "grad_norm": 0.396297425031662, "learning_rate": 4.624740159833866e-05, "loss": 4.3647, "step": 5784 }, { "epoch": 0.17669517409896152, "grad_norm": 0.3870113790035248, "learning_rate": 4.624613740203798e-05, "loss": 4.4304, "step": 5785 }, { "epoch": 0.1767257177764203, "grad_norm": 0.39483144879341125, "learning_rate": 4.624487301011318e-05, "loss": 4.4879, "step": 5786 }, { "epoch": 0.17675626145387904, "grad_norm": 0.3707180619239807, "learning_rate": 4.6243608422575915e-05, "loss": 4.3716, "step": 5787 }, { "epoch": 0.17678680513133782, "grad_norm": 0.38765668869018555, "learning_rate": 4.6242343639437824e-05, "loss": 4.3305, "step": 5788 }, { "epoch": 0.17681734880879657, "grad_norm": 0.3889486491680145, "learning_rate": 4.6241078660710554e-05, "loss": 4.338, "step": 5789 }, { "epoch": 0.17684789248625535, "grad_norm": 0.37699416279792786, "learning_rate": 4.6239813486405756e-05, "loss": 4.387, "step": 5790 }, { "epoch": 0.1768784361637141, "grad_norm": 0.39259666204452515, "learning_rate": 4.623854811653508e-05, "loss": 4.3476, "step": 5791 }, { "epoch": 0.17690897984117288, "grad_norm": 0.38312533497810364, "learning_rate": 4.623728255111016e-05, "loss": 4.4052, "step": 5792 }, { "epoch": 0.17693952351863165, "grad_norm": 0.38228291273117065, "learning_rate": 4.623601679014266e-05, "loss": 4.4319, "step": 5793 }, { "epoch": 0.1769700671960904, "grad_norm": 0.3875662684440613, "learning_rate": 4.623475083364423e-05, "loss": 4.4544, "step": 5794 }, { "epoch": 0.17700061087354918, "grad_norm": 0.3983558416366577, "learning_rate": 4.623348468162655e-05, "loss": 4.4826, "step": 5795 }, { "epoch": 0.17703115455100793, "grad_norm": 0.39335736632347107, "learning_rate": 4.6232218334101253e-05, "loss": 4.3636, "step": 5796 }, { "epoch": 0.1770616982284667, "grad_norm": 0.36748388409614563, "learning_rate": 4.6230951791079995e-05, "loss": 4.3095, "step": 5797 }, { "epoch": 0.17709224190592548, "grad_norm": 0.4052797257900238, "learning_rate": 4.6229685052574455e-05, "loss": 4.3383, "step": 5798 }, { "epoch": 0.17712278558338423, "grad_norm": 0.38277187943458557, "learning_rate": 4.622841811859629e-05, "loss": 4.3999, "step": 5799 }, { "epoch": 0.177153329260843, "grad_norm": 0.379967600107193, "learning_rate": 4.622715098915716e-05, "loss": 4.4111, "step": 5800 }, { "epoch": 0.17718387293830176, "grad_norm": 0.37813472747802734, "learning_rate": 4.6225883664268744e-05, "loss": 4.4403, "step": 5801 }, { "epoch": 0.17721441661576054, "grad_norm": 0.38059568405151367, "learning_rate": 4.62246161439427e-05, "loss": 4.3949, "step": 5802 }, { "epoch": 0.17724496029321932, "grad_norm": 0.37885963916778564, "learning_rate": 4.6223348428190706e-05, "loss": 4.3178, "step": 5803 }, { "epoch": 0.17727550397067807, "grad_norm": 0.38244226574897766, "learning_rate": 4.622208051702442e-05, "loss": 4.3568, "step": 5804 }, { "epoch": 0.17730604764813684, "grad_norm": 0.38848522305488586, "learning_rate": 4.622081241045554e-05, "loss": 4.403, "step": 5805 }, { "epoch": 0.1773365913255956, "grad_norm": 0.39347514510154724, "learning_rate": 4.6219544108495726e-05, "loss": 4.418, "step": 5806 }, { "epoch": 0.17736713500305437, "grad_norm": 0.3854250907897949, "learning_rate": 4.6218275611156656e-05, "loss": 4.381, "step": 5807 }, { "epoch": 0.17739767868051312, "grad_norm": 0.3875439763069153, "learning_rate": 4.621700691845002e-05, "loss": 4.4451, "step": 5808 }, { "epoch": 0.1774282223579719, "grad_norm": 0.3853923976421356, "learning_rate": 4.621573803038749e-05, "loss": 4.4267, "step": 5809 }, { "epoch": 0.17745876603543068, "grad_norm": 0.3823937773704529, "learning_rate": 4.621446894698074e-05, "loss": 4.4194, "step": 5810 }, { "epoch": 0.17748930971288943, "grad_norm": 0.3791348338127136, "learning_rate": 4.621319966824148e-05, "loss": 4.435, "step": 5811 }, { "epoch": 0.1775198533903482, "grad_norm": 0.37899860739707947, "learning_rate": 4.621193019418139e-05, "loss": 4.2568, "step": 5812 }, { "epoch": 0.17755039706780695, "grad_norm": 0.3778458535671234, "learning_rate": 4.621066052481214e-05, "loss": 4.3554, "step": 5813 }, { "epoch": 0.17758094074526573, "grad_norm": 0.37982413172721863, "learning_rate": 4.620939066014543e-05, "loss": 4.425, "step": 5814 }, { "epoch": 0.1776114844227245, "grad_norm": 0.39728987216949463, "learning_rate": 4.620812060019296e-05, "loss": 4.3142, "step": 5815 }, { "epoch": 0.17764202810018326, "grad_norm": 0.40071338415145874, "learning_rate": 4.620685034496642e-05, "loss": 4.3944, "step": 5816 }, { "epoch": 0.17767257177764204, "grad_norm": 0.3907138407230377, "learning_rate": 4.620557989447751e-05, "loss": 4.4047, "step": 5817 }, { "epoch": 0.17770311545510079, "grad_norm": 0.3838149607181549, "learning_rate": 4.620430924873792e-05, "loss": 4.3409, "step": 5818 }, { "epoch": 0.17773365913255956, "grad_norm": 0.39534783363342285, "learning_rate": 4.620303840775936e-05, "loss": 4.415, "step": 5819 }, { "epoch": 0.1777642028100183, "grad_norm": 0.38702622056007385, "learning_rate": 4.6201767371553515e-05, "loss": 4.42, "step": 5820 }, { "epoch": 0.1777947464874771, "grad_norm": 0.3754216730594635, "learning_rate": 4.6200496140132096e-05, "loss": 4.376, "step": 5821 }, { "epoch": 0.17782529016493587, "grad_norm": 0.37317144870758057, "learning_rate": 4.6199224713506804e-05, "loss": 4.4148, "step": 5822 }, { "epoch": 0.17785583384239462, "grad_norm": 0.3763870298862457, "learning_rate": 4.6197953091689364e-05, "loss": 4.3079, "step": 5823 }, { "epoch": 0.1778863775198534, "grad_norm": 0.38462111353874207, "learning_rate": 4.619668127469147e-05, "loss": 4.3057, "step": 5824 }, { "epoch": 0.17791692119731214, "grad_norm": 0.3783192038536072, "learning_rate": 4.6195409262524824e-05, "loss": 4.3482, "step": 5825 }, { "epoch": 0.17794746487477092, "grad_norm": 0.37977904081344604, "learning_rate": 4.619413705520115e-05, "loss": 4.3422, "step": 5826 }, { "epoch": 0.1779780085522297, "grad_norm": 0.39344125986099243, "learning_rate": 4.619286465273216e-05, "loss": 4.3812, "step": 5827 }, { "epoch": 0.17800855222968845, "grad_norm": 0.38434621691703796, "learning_rate": 4.6191592055129564e-05, "loss": 4.4023, "step": 5828 }, { "epoch": 0.17803909590714723, "grad_norm": 0.3781650960445404, "learning_rate": 4.619031926240509e-05, "loss": 4.4228, "step": 5829 }, { "epoch": 0.17806963958460598, "grad_norm": 0.37706848978996277, "learning_rate": 4.618904627457046e-05, "loss": 4.303, "step": 5830 }, { "epoch": 0.17810018326206475, "grad_norm": 0.381330668926239, "learning_rate": 4.618777309163737e-05, "loss": 4.3509, "step": 5831 }, { "epoch": 0.17813072693952353, "grad_norm": 0.3909473717212677, "learning_rate": 4.6186499713617573e-05, "loss": 4.2969, "step": 5832 }, { "epoch": 0.17816127061698228, "grad_norm": 0.38950982689857483, "learning_rate": 4.618522614052278e-05, "loss": 4.3601, "step": 5833 }, { "epoch": 0.17819181429444106, "grad_norm": 0.3858862817287445, "learning_rate": 4.61839523723647e-05, "loss": 4.4135, "step": 5834 }, { "epoch": 0.1782223579718998, "grad_norm": 0.3802115321159363, "learning_rate": 4.618267840915509e-05, "loss": 4.3591, "step": 5835 }, { "epoch": 0.17825290164935859, "grad_norm": 0.38388675451278687, "learning_rate": 4.618140425090567e-05, "loss": 4.3318, "step": 5836 }, { "epoch": 0.17828344532681734, "grad_norm": 0.3882875442504883, "learning_rate": 4.618012989762818e-05, "loss": 4.4609, "step": 5837 }, { "epoch": 0.1783139890042761, "grad_norm": 0.3832733929157257, "learning_rate": 4.617885534933433e-05, "loss": 4.3146, "step": 5838 }, { "epoch": 0.1783445326817349, "grad_norm": 0.3861561119556427, "learning_rate": 4.617758060603587e-05, "loss": 4.3902, "step": 5839 }, { "epoch": 0.17837507635919364, "grad_norm": 0.36983487010002136, "learning_rate": 4.617630566774455e-05, "loss": 4.2452, "step": 5840 }, { "epoch": 0.17840562003665242, "grad_norm": 0.37818852066993713, "learning_rate": 4.617503053447208e-05, "loss": 4.3234, "step": 5841 }, { "epoch": 0.17843616371411117, "grad_norm": 0.3834742307662964, "learning_rate": 4.617375520623022e-05, "loss": 4.4139, "step": 5842 }, { "epoch": 0.17846670739156995, "grad_norm": 0.3976164758205414, "learning_rate": 4.6172479683030714e-05, "loss": 4.3598, "step": 5843 }, { "epoch": 0.17849725106902872, "grad_norm": 0.37469246983528137, "learning_rate": 4.61712039648853e-05, "loss": 4.3288, "step": 5844 }, { "epoch": 0.17852779474648747, "grad_norm": 0.38023462891578674, "learning_rate": 4.616992805180573e-05, "loss": 4.3351, "step": 5845 }, { "epoch": 0.17855833842394625, "grad_norm": 0.38569188117980957, "learning_rate": 4.616865194380374e-05, "loss": 4.3179, "step": 5846 }, { "epoch": 0.178588882101405, "grad_norm": 0.3779413104057312, "learning_rate": 4.6167375640891094e-05, "loss": 4.3943, "step": 5847 }, { "epoch": 0.17861942577886378, "grad_norm": 0.3819608986377716, "learning_rate": 4.616609914307954e-05, "loss": 4.4526, "step": 5848 }, { "epoch": 0.17864996945632255, "grad_norm": 0.3788492679595947, "learning_rate": 4.616482245038082e-05, "loss": 4.429, "step": 5849 }, { "epoch": 0.1786805131337813, "grad_norm": 0.3847413659095764, "learning_rate": 4.61635455628067e-05, "loss": 4.4669, "step": 5850 }, { "epoch": 0.17871105681124008, "grad_norm": 0.38213685154914856, "learning_rate": 4.616226848036894e-05, "loss": 4.3533, "step": 5851 }, { "epoch": 0.17874160048869883, "grad_norm": 0.3790266811847687, "learning_rate": 4.6160991203079296e-05, "loss": 4.4256, "step": 5852 }, { "epoch": 0.1787721441661576, "grad_norm": 0.39978039264678955, "learning_rate": 4.6159713730949515e-05, "loss": 4.3573, "step": 5853 }, { "epoch": 0.17880268784361636, "grad_norm": 0.3866180181503296, "learning_rate": 4.615843606399138e-05, "loss": 4.3446, "step": 5854 }, { "epoch": 0.17883323152107514, "grad_norm": 0.3860291838645935, "learning_rate": 4.615715820221664e-05, "loss": 4.3277, "step": 5855 }, { "epoch": 0.17886377519853391, "grad_norm": 0.40518707036972046, "learning_rate": 4.6155880145637064e-05, "loss": 4.4295, "step": 5856 }, { "epoch": 0.17889431887599266, "grad_norm": 0.3818109333515167, "learning_rate": 4.615460189426443e-05, "loss": 4.3445, "step": 5857 }, { "epoch": 0.17892486255345144, "grad_norm": 0.38794514536857605, "learning_rate": 4.6153323448110496e-05, "loss": 4.3474, "step": 5858 }, { "epoch": 0.1789554062309102, "grad_norm": 0.40528684854507446, "learning_rate": 4.6152044807187035e-05, "loss": 4.3828, "step": 5859 }, { "epoch": 0.17898594990836897, "grad_norm": 0.39761632680892944, "learning_rate": 4.6150765971505824e-05, "loss": 4.3921, "step": 5860 }, { "epoch": 0.17901649358582775, "grad_norm": 0.37595415115356445, "learning_rate": 4.6149486941078633e-05, "loss": 4.3961, "step": 5861 }, { "epoch": 0.1790470372632865, "grad_norm": 0.3836875855922699, "learning_rate": 4.614820771591725e-05, "loss": 4.349, "step": 5862 }, { "epoch": 0.17907758094074527, "grad_norm": 0.3888269364833832, "learning_rate": 4.614692829603344e-05, "loss": 4.3414, "step": 5863 }, { "epoch": 0.17910812461820402, "grad_norm": 0.3756563365459442, "learning_rate": 4.6145648681438994e-05, "loss": 4.3581, "step": 5864 }, { "epoch": 0.1791386682956628, "grad_norm": 0.3735103905200958, "learning_rate": 4.6144368872145676e-05, "loss": 4.4569, "step": 5865 }, { "epoch": 0.17916921197312155, "grad_norm": 0.4038097560405731, "learning_rate": 4.614308886816529e-05, "loss": 4.3595, "step": 5866 }, { "epoch": 0.17919975565058033, "grad_norm": 0.3895014226436615, "learning_rate": 4.6141808669509615e-05, "loss": 4.4603, "step": 5867 }, { "epoch": 0.1792302993280391, "grad_norm": 0.38087978959083557, "learning_rate": 4.6140528276190434e-05, "loss": 4.2848, "step": 5868 }, { "epoch": 0.17926084300549786, "grad_norm": 0.38209691643714905, "learning_rate": 4.6139247688219544e-05, "loss": 4.3264, "step": 5869 }, { "epoch": 0.17929138668295663, "grad_norm": 0.3883209824562073, "learning_rate": 4.613796690560873e-05, "loss": 4.4292, "step": 5870 }, { "epoch": 0.17932193036041538, "grad_norm": 0.3863183259963989, "learning_rate": 4.613668592836978e-05, "loss": 4.2854, "step": 5871 }, { "epoch": 0.17935247403787416, "grad_norm": 0.38178688287734985, "learning_rate": 4.613540475651451e-05, "loss": 4.3965, "step": 5872 }, { "epoch": 0.17938301771533294, "grad_norm": 0.38464823365211487, "learning_rate": 4.6134123390054693e-05, "loss": 4.3539, "step": 5873 }, { "epoch": 0.1794135613927917, "grad_norm": 0.3852030634880066, "learning_rate": 4.6132841829002135e-05, "loss": 4.3649, "step": 5874 }, { "epoch": 0.17944410507025046, "grad_norm": 0.3987814784049988, "learning_rate": 4.613156007336864e-05, "loss": 4.4053, "step": 5875 }, { "epoch": 0.17947464874770921, "grad_norm": 0.3833346962928772, "learning_rate": 4.6130278123166005e-05, "loss": 4.3473, "step": 5876 }, { "epoch": 0.179505192425168, "grad_norm": 0.386977881193161, "learning_rate": 4.6128995978406034e-05, "loss": 4.3239, "step": 5877 }, { "epoch": 0.17953573610262677, "grad_norm": 0.39193496108055115, "learning_rate": 4.612771363910053e-05, "loss": 4.4021, "step": 5878 }, { "epoch": 0.17956627978008552, "grad_norm": 0.38224512338638306, "learning_rate": 4.612643110526132e-05, "loss": 4.4065, "step": 5879 }, { "epoch": 0.1795968234575443, "grad_norm": 0.38926851749420166, "learning_rate": 4.612514837690018e-05, "loss": 4.3717, "step": 5880 }, { "epoch": 0.17962736713500305, "grad_norm": 0.3970465660095215, "learning_rate": 4.612386545402894e-05, "loss": 4.4201, "step": 5881 }, { "epoch": 0.17965791081246182, "grad_norm": 0.38714703917503357, "learning_rate": 4.612258233665941e-05, "loss": 4.3292, "step": 5882 }, { "epoch": 0.17968845448992057, "grad_norm": 0.39681005477905273, "learning_rate": 4.612129902480341e-05, "loss": 4.3936, "step": 5883 }, { "epoch": 0.17971899816737935, "grad_norm": 0.3957800269126892, "learning_rate": 4.612001551847275e-05, "loss": 4.4155, "step": 5884 }, { "epoch": 0.17974954184483813, "grad_norm": 0.39360305666923523, "learning_rate": 4.611873181767924e-05, "loss": 4.4642, "step": 5885 }, { "epoch": 0.17978008552229688, "grad_norm": 0.40646612644195557, "learning_rate": 4.611744792243472e-05, "loss": 4.4267, "step": 5886 }, { "epoch": 0.17981062919975566, "grad_norm": 0.38012662529945374, "learning_rate": 4.611616383275099e-05, "loss": 4.3771, "step": 5887 }, { "epoch": 0.1798411728772144, "grad_norm": 0.38456737995147705, "learning_rate": 4.6114879548639886e-05, "loss": 4.3971, "step": 5888 }, { "epoch": 0.17987171655467318, "grad_norm": 0.3839851915836334, "learning_rate": 4.6113595070113225e-05, "loss": 4.448, "step": 5889 }, { "epoch": 0.17990226023213196, "grad_norm": 0.4122838079929352, "learning_rate": 4.6112310397182846e-05, "loss": 4.4229, "step": 5890 }, { "epoch": 0.1799328039095907, "grad_norm": 0.39340025186538696, "learning_rate": 4.611102552986056e-05, "loss": 4.348, "step": 5891 }, { "epoch": 0.1799633475870495, "grad_norm": 0.3919939398765564, "learning_rate": 4.6109740468158226e-05, "loss": 4.3811, "step": 5892 }, { "epoch": 0.17999389126450824, "grad_norm": 0.37850120663642883, "learning_rate": 4.610845521208764e-05, "loss": 4.3979, "step": 5893 }, { "epoch": 0.18002443494196702, "grad_norm": 0.3906676769256592, "learning_rate": 4.6107169761660666e-05, "loss": 4.4575, "step": 5894 }, { "epoch": 0.18005497861942577, "grad_norm": 0.39652523398399353, "learning_rate": 4.610588411688912e-05, "loss": 4.4361, "step": 5895 }, { "epoch": 0.18008552229688454, "grad_norm": 0.38083919882774353, "learning_rate": 4.610459827778485e-05, "loss": 4.3245, "step": 5896 }, { "epoch": 0.18011606597434332, "grad_norm": 0.3773418664932251, "learning_rate": 4.610331224435969e-05, "loss": 4.3416, "step": 5897 }, { "epoch": 0.18014660965180207, "grad_norm": 0.3986356556415558, "learning_rate": 4.6102026016625486e-05, "loss": 4.2881, "step": 5898 }, { "epoch": 0.18017715332926085, "grad_norm": 0.3899363875389099, "learning_rate": 4.610073959459408e-05, "loss": 4.3311, "step": 5899 }, { "epoch": 0.1802076970067196, "grad_norm": 0.37814414501190186, "learning_rate": 4.609945297827732e-05, "loss": 4.3302, "step": 5900 }, { "epoch": 0.18023824068417837, "grad_norm": 0.3890136480331421, "learning_rate": 4.609816616768704e-05, "loss": 4.3326, "step": 5901 }, { "epoch": 0.18026878436163715, "grad_norm": 0.3860202729701996, "learning_rate": 4.60968791628351e-05, "loss": 4.3363, "step": 5902 }, { "epoch": 0.1802993280390959, "grad_norm": 0.39304113388061523, "learning_rate": 4.609559196373335e-05, "loss": 4.3822, "step": 5903 }, { "epoch": 0.18032987171655468, "grad_norm": 0.37965020537376404, "learning_rate": 4.6094304570393634e-05, "loss": 4.2716, "step": 5904 }, { "epoch": 0.18036041539401343, "grad_norm": 0.38090118765830994, "learning_rate": 4.609301698282781e-05, "loss": 4.3482, "step": 5905 }, { "epoch": 0.1803909590714722, "grad_norm": 0.40156376361846924, "learning_rate": 4.609172920104773e-05, "loss": 4.4255, "step": 5906 }, { "epoch": 0.18042150274893098, "grad_norm": 0.39599475264549255, "learning_rate": 4.609044122506526e-05, "loss": 4.3528, "step": 5907 }, { "epoch": 0.18045204642638973, "grad_norm": 0.3823041021823883, "learning_rate": 4.608915305489226e-05, "loss": 4.2854, "step": 5908 }, { "epoch": 0.1804825901038485, "grad_norm": 0.3937775790691376, "learning_rate": 4.608786469054058e-05, "loss": 4.3118, "step": 5909 }, { "epoch": 0.18051313378130726, "grad_norm": 0.38202452659606934, "learning_rate": 4.608657613202209e-05, "loss": 4.3415, "step": 5910 }, { "epoch": 0.18054367745876604, "grad_norm": 0.3859085142612457, "learning_rate": 4.608528737934864e-05, "loss": 4.3988, "step": 5911 }, { "epoch": 0.1805742211362248, "grad_norm": 0.38339462876319885, "learning_rate": 4.608399843253212e-05, "loss": 4.3361, "step": 5912 }, { "epoch": 0.18060476481368357, "grad_norm": 0.3871786296367645, "learning_rate": 4.608270929158438e-05, "loss": 4.2655, "step": 5913 }, { "epoch": 0.18063530849114234, "grad_norm": 0.3886522650718689, "learning_rate": 4.60814199565173e-05, "loss": 4.3237, "step": 5914 }, { "epoch": 0.1806658521686011, "grad_norm": 0.3824763894081116, "learning_rate": 4.608013042734275e-05, "loss": 4.3476, "step": 5915 }, { "epoch": 0.18069639584605987, "grad_norm": 0.38724300265312195, "learning_rate": 4.607884070407259e-05, "loss": 4.3905, "step": 5916 }, { "epoch": 0.18072693952351862, "grad_norm": 0.3902628719806671, "learning_rate": 4.607755078671872e-05, "loss": 4.3557, "step": 5917 }, { "epoch": 0.1807574832009774, "grad_norm": 0.38750696182250977, "learning_rate": 4.6076260675292994e-05, "loss": 4.3521, "step": 5918 }, { "epoch": 0.18078802687843618, "grad_norm": 0.3898320496082306, "learning_rate": 4.607497036980729e-05, "loss": 4.3652, "step": 5919 }, { "epoch": 0.18081857055589493, "grad_norm": 0.39832228422164917, "learning_rate": 4.6073679870273514e-05, "loss": 4.3582, "step": 5920 }, { "epoch": 0.1808491142333537, "grad_norm": 0.39050206542015076, "learning_rate": 4.607238917670352e-05, "loss": 4.4211, "step": 5921 }, { "epoch": 0.18087965791081245, "grad_norm": 0.37509864568710327, "learning_rate": 4.607109828910922e-05, "loss": 4.4903, "step": 5922 }, { "epoch": 0.18091020158827123, "grad_norm": 0.3884924650192261, "learning_rate": 4.606980720750248e-05, "loss": 4.3248, "step": 5923 }, { "epoch": 0.18094074526573, "grad_norm": 0.3821834623813629, "learning_rate": 4.606851593189518e-05, "loss": 4.3285, "step": 5924 }, { "epoch": 0.18097128894318876, "grad_norm": 0.38214755058288574, "learning_rate": 4.6067224462299236e-05, "loss": 4.4145, "step": 5925 }, { "epoch": 0.18100183262064753, "grad_norm": 0.38752079010009766, "learning_rate": 4.606593279872652e-05, "loss": 4.332, "step": 5926 }, { "epoch": 0.18103237629810628, "grad_norm": 0.393771231174469, "learning_rate": 4.606464094118893e-05, "loss": 4.3345, "step": 5927 }, { "epoch": 0.18106291997556506, "grad_norm": 0.3661939799785614, "learning_rate": 4.606334888969836e-05, "loss": 4.3446, "step": 5928 }, { "epoch": 0.1810934636530238, "grad_norm": 0.3779580295085907, "learning_rate": 4.6062056644266704e-05, "loss": 4.4555, "step": 5929 }, { "epoch": 0.1811240073304826, "grad_norm": 0.3838405907154083, "learning_rate": 4.606076420490586e-05, "loss": 4.3559, "step": 5930 }, { "epoch": 0.18115455100794137, "grad_norm": 0.39191317558288574, "learning_rate": 4.6059471571627736e-05, "loss": 4.4088, "step": 5931 }, { "epoch": 0.18118509468540012, "grad_norm": 0.37606561183929443, "learning_rate": 4.605817874444424e-05, "loss": 4.4315, "step": 5932 }, { "epoch": 0.1812156383628589, "grad_norm": 0.38269349932670593, "learning_rate": 4.605688572336725e-05, "loss": 4.4067, "step": 5933 }, { "epoch": 0.18124618204031764, "grad_norm": 0.38864126801490784, "learning_rate": 4.6055592508408695e-05, "loss": 4.3482, "step": 5934 }, { "epoch": 0.18127672571777642, "grad_norm": 0.3863019645214081, "learning_rate": 4.605429909958047e-05, "loss": 4.3423, "step": 5935 }, { "epoch": 0.1813072693952352, "grad_norm": 0.3880296051502228, "learning_rate": 4.6053005496894485e-05, "loss": 4.3276, "step": 5936 }, { "epoch": 0.18133781307269395, "grad_norm": 0.3883475661277771, "learning_rate": 4.605171170036266e-05, "loss": 4.4119, "step": 5937 }, { "epoch": 0.18136835675015273, "grad_norm": 0.3897360861301422, "learning_rate": 4.60504177099969e-05, "loss": 4.3725, "step": 5938 }, { "epoch": 0.18139890042761148, "grad_norm": 0.3898230791091919, "learning_rate": 4.604912352580912e-05, "loss": 4.4621, "step": 5939 }, { "epoch": 0.18142944410507025, "grad_norm": 0.37335067987442017, "learning_rate": 4.6047829147811236e-05, "loss": 4.3579, "step": 5940 }, { "epoch": 0.181459987782529, "grad_norm": 0.3743492364883423, "learning_rate": 4.6046534576015174e-05, "loss": 4.3879, "step": 5941 }, { "epoch": 0.18149053145998778, "grad_norm": 0.37500500679016113, "learning_rate": 4.604523981043284e-05, "loss": 4.3028, "step": 5942 }, { "epoch": 0.18152107513744656, "grad_norm": 0.3710181415081024, "learning_rate": 4.604394485107617e-05, "loss": 4.4358, "step": 5943 }, { "epoch": 0.1815516188149053, "grad_norm": 0.3781682252883911, "learning_rate": 4.604264969795707e-05, "loss": 4.3739, "step": 5944 }, { "epoch": 0.18158216249236409, "grad_norm": 0.3748794198036194, "learning_rate": 4.604135435108748e-05, "loss": 4.4197, "step": 5945 }, { "epoch": 0.18161270616982284, "grad_norm": 0.3992546796798706, "learning_rate": 4.6040058810479334e-05, "loss": 4.411, "step": 5946 }, { "epoch": 0.1816432498472816, "grad_norm": 0.3664136528968811, "learning_rate": 4.603876307614453e-05, "loss": 4.4133, "step": 5947 }, { "epoch": 0.1816737935247404, "grad_norm": 0.38221660256385803, "learning_rate": 4.603746714809503e-05, "loss": 4.418, "step": 5948 }, { "epoch": 0.18170433720219914, "grad_norm": 0.381005197763443, "learning_rate": 4.6036171026342744e-05, "loss": 4.3603, "step": 5949 }, { "epoch": 0.18173488087965792, "grad_norm": 0.38523998856544495, "learning_rate": 4.6034874710899626e-05, "loss": 4.4348, "step": 5950 }, { "epoch": 0.18176542455711667, "grad_norm": 0.38029274344444275, "learning_rate": 4.603357820177759e-05, "loss": 4.3121, "step": 5951 }, { "epoch": 0.18179596823457544, "grad_norm": 0.3909039795398712, "learning_rate": 4.603228149898859e-05, "loss": 4.4078, "step": 5952 }, { "epoch": 0.18182651191203422, "grad_norm": 0.3872474431991577, "learning_rate": 4.603098460254457e-05, "loss": 4.4355, "step": 5953 }, { "epoch": 0.18185705558949297, "grad_norm": 0.3820672333240509, "learning_rate": 4.6029687512457456e-05, "loss": 4.2877, "step": 5954 }, { "epoch": 0.18188759926695175, "grad_norm": 0.385830283164978, "learning_rate": 4.602839022873919e-05, "loss": 4.3847, "step": 5955 }, { "epoch": 0.1819181429444105, "grad_norm": 0.38351762294769287, "learning_rate": 4.6027092751401725e-05, "loss": 4.4041, "step": 5956 }, { "epoch": 0.18194868662186928, "grad_norm": 0.3819050192832947, "learning_rate": 4.602579508045701e-05, "loss": 4.2515, "step": 5957 }, { "epoch": 0.18197923029932803, "grad_norm": 0.3813822865486145, "learning_rate": 4.6024497215916984e-05, "loss": 4.366, "step": 5958 }, { "epoch": 0.1820097739767868, "grad_norm": 0.38368552923202515, "learning_rate": 4.6023199157793606e-05, "loss": 4.3698, "step": 5959 }, { "epoch": 0.18204031765424558, "grad_norm": 0.4018534719944, "learning_rate": 4.6021900906098825e-05, "loss": 4.4356, "step": 5960 }, { "epoch": 0.18207086133170433, "grad_norm": 0.38179245591163635, "learning_rate": 4.6020602460844596e-05, "loss": 4.3923, "step": 5961 }, { "epoch": 0.1821014050091631, "grad_norm": 0.38873791694641113, "learning_rate": 4.601930382204287e-05, "loss": 4.4027, "step": 5962 }, { "epoch": 0.18213194868662186, "grad_norm": 0.38552162051200867, "learning_rate": 4.60180049897056e-05, "loss": 4.4056, "step": 5963 }, { "epoch": 0.18216249236408064, "grad_norm": 0.398260235786438, "learning_rate": 4.6016705963844764e-05, "loss": 4.4377, "step": 5964 }, { "epoch": 0.1821930360415394, "grad_norm": 0.38182222843170166, "learning_rate": 4.60154067444723e-05, "loss": 4.3599, "step": 5965 }, { "epoch": 0.18222357971899816, "grad_norm": 0.3874923288822174, "learning_rate": 4.601410733160019e-05, "loss": 4.3965, "step": 5966 }, { "epoch": 0.18225412339645694, "grad_norm": 0.38571828603744507, "learning_rate": 4.6012807725240384e-05, "loss": 4.4167, "step": 5967 }, { "epoch": 0.1822846670739157, "grad_norm": 0.3994870185852051, "learning_rate": 4.601150792540485e-05, "loss": 4.3228, "step": 5968 }, { "epoch": 0.18231521075137447, "grad_norm": 0.3949964940547943, "learning_rate": 4.601020793210556e-05, "loss": 4.3816, "step": 5969 }, { "epoch": 0.18234575442883322, "grad_norm": 0.3887075185775757, "learning_rate": 4.6008907745354494e-05, "loss": 4.3895, "step": 5970 }, { "epoch": 0.182376298106292, "grad_norm": 0.37844422459602356, "learning_rate": 4.600760736516361e-05, "loss": 4.416, "step": 5971 }, { "epoch": 0.18240684178375077, "grad_norm": 0.39884209632873535, "learning_rate": 4.600630679154487e-05, "loss": 4.483, "step": 5972 }, { "epoch": 0.18243738546120952, "grad_norm": 0.3941596448421478, "learning_rate": 4.6005006024510274e-05, "loss": 4.3543, "step": 5973 }, { "epoch": 0.1824679291386683, "grad_norm": 0.3914479613304138, "learning_rate": 4.600370506407179e-05, "loss": 4.3849, "step": 5974 }, { "epoch": 0.18249847281612705, "grad_norm": 0.3800186216831207, "learning_rate": 4.600240391024139e-05, "loss": 4.3279, "step": 5975 }, { "epoch": 0.18252901649358583, "grad_norm": 0.37466707825660706, "learning_rate": 4.600110256303106e-05, "loss": 4.3937, "step": 5976 }, { "epoch": 0.1825595601710446, "grad_norm": 0.38587939739227295, "learning_rate": 4.599980102245278e-05, "loss": 4.3456, "step": 5977 }, { "epoch": 0.18259010384850335, "grad_norm": 0.38378217816352844, "learning_rate": 4.599849928851854e-05, "loss": 4.3762, "step": 5978 }, { "epoch": 0.18262064752596213, "grad_norm": 0.3825676739215851, "learning_rate": 4.599719736124032e-05, "loss": 4.3432, "step": 5979 }, { "epoch": 0.18265119120342088, "grad_norm": 0.3920356333255768, "learning_rate": 4.59958952406301e-05, "loss": 4.4582, "step": 5980 }, { "epoch": 0.18268173488087966, "grad_norm": 0.37908175587654114, "learning_rate": 4.5994592926699886e-05, "loss": 4.3599, "step": 5981 }, { "epoch": 0.18271227855833844, "grad_norm": 0.38667288422584534, "learning_rate": 4.599329041946166e-05, "loss": 4.3624, "step": 5982 }, { "epoch": 0.1827428222357972, "grad_norm": 0.38178879022598267, "learning_rate": 4.599198771892741e-05, "loss": 4.3635, "step": 5983 }, { "epoch": 0.18277336591325596, "grad_norm": 0.39715176820755005, "learning_rate": 4.599068482510913e-05, "loss": 4.417, "step": 5984 }, { "epoch": 0.1828039095907147, "grad_norm": 0.4006270170211792, "learning_rate": 4.598938173801883e-05, "loss": 4.4165, "step": 5985 }, { "epoch": 0.1828344532681735, "grad_norm": 0.402792751789093, "learning_rate": 4.5988078457668504e-05, "loss": 4.3992, "step": 5986 }, { "epoch": 0.18286499694563224, "grad_norm": 0.3886999487876892, "learning_rate": 4.5986774984070146e-05, "loss": 4.3253, "step": 5987 }, { "epoch": 0.18289554062309102, "grad_norm": 0.38280022144317627, "learning_rate": 4.598547131723576e-05, "loss": 4.3998, "step": 5988 }, { "epoch": 0.1829260843005498, "grad_norm": 0.37872764468193054, "learning_rate": 4.598416745717735e-05, "loss": 4.3755, "step": 5989 }, { "epoch": 0.18295662797800855, "grad_norm": 0.3793218433856964, "learning_rate": 4.598286340390693e-05, "loss": 4.3557, "step": 5990 }, { "epoch": 0.18298717165546732, "grad_norm": 0.3805047273635864, "learning_rate": 4.5981559157436484e-05, "loss": 4.4039, "step": 5991 }, { "epoch": 0.18301771533292607, "grad_norm": 0.3808726668357849, "learning_rate": 4.598025471777804e-05, "loss": 4.3797, "step": 5992 }, { "epoch": 0.18304825901038485, "grad_norm": 0.37739235162734985, "learning_rate": 4.5978950084943606e-05, "loss": 4.3598, "step": 5993 }, { "epoch": 0.18307880268784363, "grad_norm": 0.3832218050956726, "learning_rate": 4.597764525894519e-05, "loss": 4.4415, "step": 5994 }, { "epoch": 0.18310934636530238, "grad_norm": 0.3837890028953552, "learning_rate": 4.5976340239794816e-05, "loss": 4.3411, "step": 5995 }, { "epoch": 0.18313989004276116, "grad_norm": 0.38639533519744873, "learning_rate": 4.597503502750448e-05, "loss": 4.3885, "step": 5996 }, { "epoch": 0.1831704337202199, "grad_norm": 0.3921240568161011, "learning_rate": 4.597372962208622e-05, "loss": 4.4057, "step": 5997 }, { "epoch": 0.18320097739767868, "grad_norm": 0.39030981063842773, "learning_rate": 4.597242402355205e-05, "loss": 4.4535, "step": 5998 }, { "epoch": 0.18323152107513746, "grad_norm": 0.3730093240737915, "learning_rate": 4.5971118231913976e-05, "loss": 4.3531, "step": 5999 }, { "epoch": 0.1832620647525962, "grad_norm": 0.38657495379447937, "learning_rate": 4.596981224718405e-05, "loss": 4.4825, "step": 6000 }, { "epoch": 0.183292608430055, "grad_norm": 0.3795913755893707, "learning_rate": 4.596850606937427e-05, "loss": 4.3297, "step": 6001 }, { "epoch": 0.18332315210751374, "grad_norm": 0.37428024411201477, "learning_rate": 4.596719969849668e-05, "loss": 4.3922, "step": 6002 }, { "epoch": 0.18335369578497251, "grad_norm": 0.3753879964351654, "learning_rate": 4.59658931345633e-05, "loss": 4.3405, "step": 6003 }, { "epoch": 0.18338423946243126, "grad_norm": 0.37883487343788147, "learning_rate": 4.596458637758616e-05, "loss": 4.3543, "step": 6004 }, { "epoch": 0.18341478313989004, "grad_norm": 0.3940635025501251, "learning_rate": 4.59632794275773e-05, "loss": 4.3614, "step": 6005 }, { "epoch": 0.18344532681734882, "grad_norm": 0.37992799282073975, "learning_rate": 4.5961972284548746e-05, "loss": 4.4333, "step": 6006 }, { "epoch": 0.18347587049480757, "grad_norm": 0.3736821115016937, "learning_rate": 4.596066494851253e-05, "loss": 4.4006, "step": 6007 }, { "epoch": 0.18350641417226635, "grad_norm": 0.39133673906326294, "learning_rate": 4.59593574194807e-05, "loss": 4.4293, "step": 6008 }, { "epoch": 0.1835369578497251, "grad_norm": 0.3813900947570801, "learning_rate": 4.595804969746529e-05, "loss": 4.3417, "step": 6009 }, { "epoch": 0.18356750152718387, "grad_norm": 0.3742583692073822, "learning_rate": 4.595674178247834e-05, "loss": 4.3548, "step": 6010 }, { "epoch": 0.18359804520464265, "grad_norm": 0.38871803879737854, "learning_rate": 4.5955433674531896e-05, "loss": 4.3665, "step": 6011 }, { "epoch": 0.1836285888821014, "grad_norm": 0.3929346203804016, "learning_rate": 4.5954125373638e-05, "loss": 4.3204, "step": 6012 }, { "epoch": 0.18365913255956018, "grad_norm": 0.37928298115730286, "learning_rate": 4.595281687980869e-05, "loss": 4.2673, "step": 6013 }, { "epoch": 0.18368967623701893, "grad_norm": 0.3947575092315674, "learning_rate": 4.595150819305603e-05, "loss": 4.3678, "step": 6014 }, { "epoch": 0.1837202199144777, "grad_norm": 0.3907679319381714, "learning_rate": 4.595019931339206e-05, "loss": 4.2891, "step": 6015 }, { "epoch": 0.18375076359193646, "grad_norm": 0.39558300375938416, "learning_rate": 4.594889024082884e-05, "loss": 4.3202, "step": 6016 }, { "epoch": 0.18378130726939523, "grad_norm": 0.36497148871421814, "learning_rate": 4.59475809753784e-05, "loss": 4.3428, "step": 6017 }, { "epoch": 0.183811850946854, "grad_norm": 0.3946310579776764, "learning_rate": 4.594627151705282e-05, "loss": 4.3883, "step": 6018 }, { "epoch": 0.18384239462431276, "grad_norm": 0.398971289396286, "learning_rate": 4.594496186586416e-05, "loss": 4.3975, "step": 6019 }, { "epoch": 0.18387293830177154, "grad_norm": 0.3699309229850769, "learning_rate": 4.5943652021824455e-05, "loss": 4.3813, "step": 6020 }, { "epoch": 0.1839034819792303, "grad_norm": 0.3953927755355835, "learning_rate": 4.594234198494578e-05, "loss": 4.3902, "step": 6021 }, { "epoch": 0.18393402565668907, "grad_norm": 0.41643500328063965, "learning_rate": 4.5941031755240194e-05, "loss": 4.4413, "step": 6022 }, { "epoch": 0.18396456933414784, "grad_norm": 0.3871234655380249, "learning_rate": 4.593972133271977e-05, "loss": 4.3272, "step": 6023 }, { "epoch": 0.1839951130116066, "grad_norm": 0.3949369192123413, "learning_rate": 4.5938410717396555e-05, "loss": 4.3596, "step": 6024 }, { "epoch": 0.18402565668906537, "grad_norm": 0.38999390602111816, "learning_rate": 4.593709990928263e-05, "loss": 4.2907, "step": 6025 }, { "epoch": 0.18405620036652412, "grad_norm": 0.37665101885795593, "learning_rate": 4.593578890839006e-05, "loss": 4.3438, "step": 6026 }, { "epoch": 0.1840867440439829, "grad_norm": 0.37744227051734924, "learning_rate": 4.5934477714730916e-05, "loss": 4.4438, "step": 6027 }, { "epoch": 0.18411728772144167, "grad_norm": 0.382030725479126, "learning_rate": 4.593316632831728e-05, "loss": 4.3674, "step": 6028 }, { "epoch": 0.18414783139890042, "grad_norm": 0.3825869858264923, "learning_rate": 4.593185474916121e-05, "loss": 4.4213, "step": 6029 }, { "epoch": 0.1841783750763592, "grad_norm": 0.3825843930244446, "learning_rate": 4.593054297727479e-05, "loss": 4.4154, "step": 6030 }, { "epoch": 0.18420891875381795, "grad_norm": 0.38383764028549194, "learning_rate": 4.5929231012670114e-05, "loss": 4.4167, "step": 6031 }, { "epoch": 0.18423946243127673, "grad_norm": 0.38438108563423157, "learning_rate": 4.5927918855359234e-05, "loss": 4.3453, "step": 6032 }, { "epoch": 0.18427000610873548, "grad_norm": 0.3869606852531433, "learning_rate": 4.5926606505354254e-05, "loss": 4.4504, "step": 6033 }, { "epoch": 0.18430054978619426, "grad_norm": 0.39316484332084656, "learning_rate": 4.5925293962667235e-05, "loss": 4.4506, "step": 6034 }, { "epoch": 0.18433109346365303, "grad_norm": 0.3840089440345764, "learning_rate": 4.5923981227310294e-05, "loss": 4.4544, "step": 6035 }, { "epoch": 0.18436163714111178, "grad_norm": 0.39203590154647827, "learning_rate": 4.592266829929549e-05, "loss": 4.3814, "step": 6036 }, { "epoch": 0.18439218081857056, "grad_norm": 0.3783802092075348, "learning_rate": 4.592135517863492e-05, "loss": 4.3343, "step": 6037 }, { "epoch": 0.1844227244960293, "grad_norm": 0.37023067474365234, "learning_rate": 4.5920041865340676e-05, "loss": 4.396, "step": 6038 }, { "epoch": 0.1844532681734881, "grad_norm": 0.385078102350235, "learning_rate": 4.591872835942486e-05, "loss": 4.4145, "step": 6039 }, { "epoch": 0.18448381185094687, "grad_norm": 0.39616450667381287, "learning_rate": 4.5917414660899544e-05, "loss": 4.4368, "step": 6040 }, { "epoch": 0.18451435552840562, "grad_norm": 0.3790123164653778, "learning_rate": 4.591610076977684e-05, "loss": 4.4145, "step": 6041 }, { "epoch": 0.1845448992058644, "grad_norm": 0.36956802010536194, "learning_rate": 4.591478668606884e-05, "loss": 4.3926, "step": 6042 }, { "epoch": 0.18457544288332314, "grad_norm": 0.3781340420246124, "learning_rate": 4.591347240978766e-05, "loss": 4.3612, "step": 6043 }, { "epoch": 0.18460598656078192, "grad_norm": 0.40350592136383057, "learning_rate": 4.5912157940945374e-05, "loss": 4.425, "step": 6044 }, { "epoch": 0.18463653023824067, "grad_norm": 0.39491209387779236, "learning_rate": 4.59108432795541e-05, "loss": 4.4198, "step": 6045 }, { "epoch": 0.18466707391569945, "grad_norm": 0.3731314539909363, "learning_rate": 4.590952842562594e-05, "loss": 4.3282, "step": 6046 }, { "epoch": 0.18469761759315823, "grad_norm": 0.37012770771980286, "learning_rate": 4.5908213379173e-05, "loss": 4.3355, "step": 6047 }, { "epoch": 0.18472816127061698, "grad_norm": 0.3855454921722412, "learning_rate": 4.590689814020739e-05, "loss": 4.3896, "step": 6048 }, { "epoch": 0.18475870494807575, "grad_norm": 0.3862574100494385, "learning_rate": 4.5905582708741226e-05, "loss": 4.3226, "step": 6049 }, { "epoch": 0.1847892486255345, "grad_norm": 0.3903246223926544, "learning_rate": 4.5904267084786605e-05, "loss": 4.4191, "step": 6050 }, { "epoch": 0.18481979230299328, "grad_norm": 0.38307687640190125, "learning_rate": 4.5902951268355654e-05, "loss": 4.4716, "step": 6051 }, { "epoch": 0.18485033598045206, "grad_norm": 0.37848567962646484, "learning_rate": 4.5901635259460486e-05, "loss": 4.3757, "step": 6052 }, { "epoch": 0.1848808796579108, "grad_norm": 0.38569164276123047, "learning_rate": 4.5900319058113206e-05, "loss": 4.4079, "step": 6053 }, { "epoch": 0.18491142333536958, "grad_norm": 0.38243845105171204, "learning_rate": 4.589900266432595e-05, "loss": 4.2743, "step": 6054 }, { "epoch": 0.18494196701282833, "grad_norm": 0.39083990454673767, "learning_rate": 4.589768607811084e-05, "loss": 4.24, "step": 6055 }, { "epoch": 0.1849725106902871, "grad_norm": 0.373352974653244, "learning_rate": 4.589636929947997e-05, "loss": 4.3999, "step": 6056 }, { "epoch": 0.1850030543677459, "grad_norm": 0.37233415246009827, "learning_rate": 4.589505232844549e-05, "loss": 4.3637, "step": 6057 }, { "epoch": 0.18503359804520464, "grad_norm": 0.37933090329170227, "learning_rate": 4.589373516501953e-05, "loss": 4.416, "step": 6058 }, { "epoch": 0.18506414172266342, "grad_norm": 0.38713470101356506, "learning_rate": 4.58924178092142e-05, "loss": 4.3779, "step": 6059 }, { "epoch": 0.18509468540012217, "grad_norm": 0.38397496938705444, "learning_rate": 4.589110026104164e-05, "loss": 4.332, "step": 6060 }, { "epoch": 0.18512522907758094, "grad_norm": 0.3875270187854767, "learning_rate": 4.588978252051398e-05, "loss": 4.396, "step": 6061 }, { "epoch": 0.1851557727550397, "grad_norm": 0.36640405654907227, "learning_rate": 4.5888464587643345e-05, "loss": 4.287, "step": 6062 }, { "epoch": 0.18518631643249847, "grad_norm": 0.37130704522132874, "learning_rate": 4.588714646244188e-05, "loss": 4.3733, "step": 6063 }, { "epoch": 0.18521686010995725, "grad_norm": 0.39232054352760315, "learning_rate": 4.588582814492172e-05, "loss": 4.3761, "step": 6064 }, { "epoch": 0.185247403787416, "grad_norm": 0.38236069679260254, "learning_rate": 4.5884509635095e-05, "loss": 4.3856, "step": 6065 }, { "epoch": 0.18527794746487478, "grad_norm": 0.3797653615474701, "learning_rate": 4.5883190932973866e-05, "loss": 4.3951, "step": 6066 }, { "epoch": 0.18530849114233353, "grad_norm": 0.38492101430892944, "learning_rate": 4.5881872038570454e-05, "loss": 4.4425, "step": 6067 }, { "epoch": 0.1853390348197923, "grad_norm": 0.3725815415382385, "learning_rate": 4.5880552951896905e-05, "loss": 4.3426, "step": 6068 }, { "epoch": 0.18536957849725108, "grad_norm": 0.37502530217170715, "learning_rate": 4.587923367296537e-05, "loss": 4.3188, "step": 6069 }, { "epoch": 0.18540012217470983, "grad_norm": 0.38294222950935364, "learning_rate": 4.587791420178801e-05, "loss": 4.4466, "step": 6070 }, { "epoch": 0.1854306658521686, "grad_norm": 0.3880009353160858, "learning_rate": 4.5876594538376944e-05, "loss": 4.3318, "step": 6071 }, { "epoch": 0.18546120952962736, "grad_norm": 0.41428130865097046, "learning_rate": 4.587527468274434e-05, "loss": 4.2987, "step": 6072 }, { "epoch": 0.18549175320708614, "grad_norm": 0.39949196577072144, "learning_rate": 4.587395463490235e-05, "loss": 4.37, "step": 6073 }, { "epoch": 0.1855222968845449, "grad_norm": 0.38360467553138733, "learning_rate": 4.5872634394863136e-05, "loss": 4.4141, "step": 6074 }, { "epoch": 0.18555284056200366, "grad_norm": 0.38846665620803833, "learning_rate": 4.587131396263884e-05, "loss": 4.3939, "step": 6075 }, { "epoch": 0.18558338423946244, "grad_norm": 0.39827802777290344, "learning_rate": 4.586999333824162e-05, "loss": 4.4395, "step": 6076 }, { "epoch": 0.1856139279169212, "grad_norm": 0.3870140016078949, "learning_rate": 4.586867252168364e-05, "loss": 4.439, "step": 6077 }, { "epoch": 0.18564447159437997, "grad_norm": 0.38741207122802734, "learning_rate": 4.586735151297708e-05, "loss": 4.323, "step": 6078 }, { "epoch": 0.18567501527183872, "grad_norm": 0.3846638798713684, "learning_rate": 4.586603031213407e-05, "loss": 4.3475, "step": 6079 }, { "epoch": 0.1857055589492975, "grad_norm": 0.3835076093673706, "learning_rate": 4.5864708919166785e-05, "loss": 4.4108, "step": 6080 }, { "epoch": 0.18573610262675627, "grad_norm": 0.3829612135887146, "learning_rate": 4.586338733408741e-05, "loss": 4.3577, "step": 6081 }, { "epoch": 0.18576664630421502, "grad_norm": 0.3953486680984497, "learning_rate": 4.5862065556908096e-05, "loss": 4.4208, "step": 6082 }, { "epoch": 0.1857971899816738, "grad_norm": 0.3926447331905365, "learning_rate": 4.586074358764102e-05, "loss": 4.3859, "step": 6083 }, { "epoch": 0.18582773365913255, "grad_norm": 0.38769957423210144, "learning_rate": 4.5859421426298354e-05, "loss": 4.4727, "step": 6084 }, { "epoch": 0.18585827733659133, "grad_norm": 0.3689429461956024, "learning_rate": 4.585809907289227e-05, "loss": 4.287, "step": 6085 }, { "epoch": 0.1858888210140501, "grad_norm": 0.38470685482025146, "learning_rate": 4.585677652743494e-05, "loss": 4.3789, "step": 6086 }, { "epoch": 0.18591936469150885, "grad_norm": 0.39461550116539, "learning_rate": 4.585545378993855e-05, "loss": 4.2533, "step": 6087 }, { "epoch": 0.18594990836896763, "grad_norm": 0.38752952218055725, "learning_rate": 4.585413086041527e-05, "loss": 4.4112, "step": 6088 }, { "epoch": 0.18598045204642638, "grad_norm": 0.3867229223251343, "learning_rate": 4.585280773887728e-05, "loss": 4.457, "step": 6089 }, { "epoch": 0.18601099572388516, "grad_norm": 0.3828178942203522, "learning_rate": 4.585148442533678e-05, "loss": 4.4041, "step": 6090 }, { "epoch": 0.1860415394013439, "grad_norm": 0.3859512209892273, "learning_rate": 4.5850160919805926e-05, "loss": 4.4969, "step": 6091 }, { "epoch": 0.18607208307880269, "grad_norm": 0.3775486946105957, "learning_rate": 4.5848837222296934e-05, "loss": 4.3867, "step": 6092 }, { "epoch": 0.18610262675626146, "grad_norm": 0.3998769223690033, "learning_rate": 4.584751333282198e-05, "loss": 4.4646, "step": 6093 }, { "epoch": 0.1861331704337202, "grad_norm": 0.3831676244735718, "learning_rate": 4.5846189251393244e-05, "loss": 4.3425, "step": 6094 }, { "epoch": 0.186163714111179, "grad_norm": 0.3808479309082031, "learning_rate": 4.584486497802293e-05, "loss": 4.3935, "step": 6095 }, { "epoch": 0.18619425778863774, "grad_norm": 0.3742274343967438, "learning_rate": 4.5843540512723224e-05, "loss": 4.3463, "step": 6096 }, { "epoch": 0.18622480146609652, "grad_norm": 0.4026676416397095, "learning_rate": 4.584221585550632e-05, "loss": 4.3372, "step": 6097 }, { "epoch": 0.1862553451435553, "grad_norm": 0.387513667345047, "learning_rate": 4.5840891006384425e-05, "loss": 4.3861, "step": 6098 }, { "epoch": 0.18628588882101405, "grad_norm": 0.381515771150589, "learning_rate": 4.583956596536973e-05, "loss": 4.4457, "step": 6099 }, { "epoch": 0.18631643249847282, "grad_norm": 0.3893846571445465, "learning_rate": 4.583824073247444e-05, "loss": 4.3843, "step": 6100 }, { "epoch": 0.18634697617593157, "grad_norm": 0.38912129402160645, "learning_rate": 4.583691530771074e-05, "loss": 4.2701, "step": 6101 }, { "epoch": 0.18637751985339035, "grad_norm": 0.38505905866622925, "learning_rate": 4.583558969109086e-05, "loss": 4.376, "step": 6102 }, { "epoch": 0.18640806353084913, "grad_norm": 0.38325220346450806, "learning_rate": 4.583426388262699e-05, "loss": 4.3876, "step": 6103 }, { "epoch": 0.18643860720830788, "grad_norm": 0.38300076127052307, "learning_rate": 4.583293788233134e-05, "loss": 4.3379, "step": 6104 }, { "epoch": 0.18646915088576665, "grad_norm": 0.3720015287399292, "learning_rate": 4.5831611690216114e-05, "loss": 4.3608, "step": 6105 }, { "epoch": 0.1864996945632254, "grad_norm": 0.38331735134124756, "learning_rate": 4.5830285306293544e-05, "loss": 4.3694, "step": 6106 }, { "epoch": 0.18653023824068418, "grad_norm": 0.40892574191093445, "learning_rate": 4.582895873057581e-05, "loss": 4.3633, "step": 6107 }, { "epoch": 0.18656078191814293, "grad_norm": 0.3804311454296112, "learning_rate": 4.582763196307516e-05, "loss": 4.3347, "step": 6108 }, { "epoch": 0.1865913255956017, "grad_norm": 0.3857845366001129, "learning_rate": 4.582630500380378e-05, "loss": 4.4154, "step": 6109 }, { "epoch": 0.1866218692730605, "grad_norm": 0.3882373869419098, "learning_rate": 4.582497785277391e-05, "loss": 4.4219, "step": 6110 }, { "epoch": 0.18665241295051924, "grad_norm": 0.3828182518482208, "learning_rate": 4.582365050999776e-05, "loss": 4.4348, "step": 6111 }, { "epoch": 0.18668295662797801, "grad_norm": 0.38703855872154236, "learning_rate": 4.582232297548755e-05, "loss": 4.3623, "step": 6112 }, { "epoch": 0.18671350030543676, "grad_norm": 0.3844517767429352, "learning_rate": 4.582099524925551e-05, "loss": 4.3817, "step": 6113 }, { "epoch": 0.18674404398289554, "grad_norm": 0.3959568738937378, "learning_rate": 4.581966733131386e-05, "loss": 4.4048, "step": 6114 }, { "epoch": 0.18677458766035432, "grad_norm": 0.39420098066329956, "learning_rate": 4.581833922167483e-05, "loss": 4.3227, "step": 6115 }, { "epoch": 0.18680513133781307, "grad_norm": 0.38612061738967896, "learning_rate": 4.581701092035065e-05, "loss": 4.3695, "step": 6116 }, { "epoch": 0.18683567501527185, "grad_norm": 0.391357421875, "learning_rate": 4.581568242735354e-05, "loss": 4.3632, "step": 6117 }, { "epoch": 0.1868662186927306, "grad_norm": 0.369991660118103, "learning_rate": 4.5814353742695745e-05, "loss": 4.3582, "step": 6118 }, { "epoch": 0.18689676237018937, "grad_norm": 0.37216469645500183, "learning_rate": 4.5813024866389496e-05, "loss": 4.3279, "step": 6119 }, { "epoch": 0.18692730604764812, "grad_norm": 0.38633963465690613, "learning_rate": 4.5811695798447016e-05, "loss": 4.4317, "step": 6120 }, { "epoch": 0.1869578497251069, "grad_norm": 0.3854799270629883, "learning_rate": 4.5810366538880557e-05, "loss": 4.2971, "step": 6121 }, { "epoch": 0.18698839340256568, "grad_norm": 0.3871774673461914, "learning_rate": 4.5809037087702356e-05, "loss": 4.2752, "step": 6122 }, { "epoch": 0.18701893708002443, "grad_norm": 0.393332302570343, "learning_rate": 4.580770744492465e-05, "loss": 4.3418, "step": 6123 }, { "epoch": 0.1870494807574832, "grad_norm": 0.3753369450569153, "learning_rate": 4.5806377610559684e-05, "loss": 4.3869, "step": 6124 }, { "epoch": 0.18708002443494195, "grad_norm": 0.40355029702186584, "learning_rate": 4.58050475846197e-05, "loss": 4.385, "step": 6125 }, { "epoch": 0.18711056811240073, "grad_norm": 0.3938513994216919, "learning_rate": 4.580371736711695e-05, "loss": 4.3545, "step": 6126 }, { "epoch": 0.1871411117898595, "grad_norm": 0.3785783350467682, "learning_rate": 4.580238695806368e-05, "loss": 4.3567, "step": 6127 }, { "epoch": 0.18717165546731826, "grad_norm": 0.3782497048377991, "learning_rate": 4.5801056357472126e-05, "loss": 4.4523, "step": 6128 }, { "epoch": 0.18720219914477704, "grad_norm": 0.3865745961666107, "learning_rate": 4.579972556535457e-05, "loss": 4.382, "step": 6129 }, { "epoch": 0.1872327428222358, "grad_norm": 0.3759440779685974, "learning_rate": 4.579839458172323e-05, "loss": 4.3047, "step": 6130 }, { "epoch": 0.18726328649969456, "grad_norm": 0.372567355632782, "learning_rate": 4.579706340659038e-05, "loss": 4.3159, "step": 6131 }, { "epoch": 0.18729383017715334, "grad_norm": 0.377484530210495, "learning_rate": 4.579573203996827e-05, "loss": 4.4145, "step": 6132 }, { "epoch": 0.1873243738546121, "grad_norm": 0.39325958490371704, "learning_rate": 4.579440048186918e-05, "loss": 4.2316, "step": 6133 }, { "epoch": 0.18735491753207087, "grad_norm": 0.3768465518951416, "learning_rate": 4.579306873230534e-05, "loss": 4.4187, "step": 6134 }, { "epoch": 0.18738546120952962, "grad_norm": 0.38210344314575195, "learning_rate": 4.579173679128903e-05, "loss": 4.4338, "step": 6135 }, { "epoch": 0.1874160048869884, "grad_norm": 0.37610772252082825, "learning_rate": 4.579040465883251e-05, "loss": 4.3279, "step": 6136 }, { "epoch": 0.18744654856444715, "grad_norm": 0.38815927505493164, "learning_rate": 4.578907233494805e-05, "loss": 4.4254, "step": 6137 }, { "epoch": 0.18747709224190592, "grad_norm": 0.4048967659473419, "learning_rate": 4.57877398196479e-05, "loss": 4.3452, "step": 6138 }, { "epoch": 0.1875076359193647, "grad_norm": 0.37998518347740173, "learning_rate": 4.578640711294435e-05, "loss": 4.3713, "step": 6139 }, { "epoch": 0.18753817959682345, "grad_norm": 0.3807547092437744, "learning_rate": 4.5785074214849655e-05, "loss": 4.3558, "step": 6140 }, { "epoch": 0.18756872327428223, "grad_norm": 0.38300228118896484, "learning_rate": 4.57837411253761e-05, "loss": 4.3125, "step": 6141 }, { "epoch": 0.18759926695174098, "grad_norm": 0.3920634984970093, "learning_rate": 4.578240784453596e-05, "loss": 4.3051, "step": 6142 }, { "epoch": 0.18762981062919976, "grad_norm": 0.3838866055011749, "learning_rate": 4.578107437234149e-05, "loss": 4.4188, "step": 6143 }, { "epoch": 0.18766035430665853, "grad_norm": 0.38729754090309143, "learning_rate": 4.5779740708805e-05, "loss": 4.4435, "step": 6144 }, { "epoch": 0.18769089798411728, "grad_norm": 0.39501941204071045, "learning_rate": 4.577840685393875e-05, "loss": 4.4375, "step": 6145 }, { "epoch": 0.18772144166157606, "grad_norm": 0.38792407512664795, "learning_rate": 4.5777072807755016e-05, "loss": 4.4462, "step": 6146 }, { "epoch": 0.1877519853390348, "grad_norm": 0.38357633352279663, "learning_rate": 4.57757385702661e-05, "loss": 4.4368, "step": 6147 }, { "epoch": 0.1877825290164936, "grad_norm": 0.37967899441719055, "learning_rate": 4.5774404141484275e-05, "loss": 4.3768, "step": 6148 }, { "epoch": 0.18781307269395237, "grad_norm": 0.3930467963218689, "learning_rate": 4.5773069521421826e-05, "loss": 4.386, "step": 6149 }, { "epoch": 0.18784361637141112, "grad_norm": 0.40030255913734436, "learning_rate": 4.5771734710091044e-05, "loss": 4.4167, "step": 6150 }, { "epoch": 0.1878741600488699, "grad_norm": 0.3800835609436035, "learning_rate": 4.577039970750423e-05, "loss": 4.4097, "step": 6151 }, { "epoch": 0.18790470372632864, "grad_norm": 0.37217047810554504, "learning_rate": 4.5769064513673654e-05, "loss": 4.3629, "step": 6152 }, { "epoch": 0.18793524740378742, "grad_norm": 0.39087051153182983, "learning_rate": 4.576772912861164e-05, "loss": 4.4424, "step": 6153 }, { "epoch": 0.18796579108124617, "grad_norm": 0.3939850926399231, "learning_rate": 4.576639355233045e-05, "loss": 4.4129, "step": 6154 }, { "epoch": 0.18799633475870495, "grad_norm": 0.38191884756088257, "learning_rate": 4.57650577848424e-05, "loss": 4.339, "step": 6155 }, { "epoch": 0.18802687843616372, "grad_norm": 0.38735663890838623, "learning_rate": 4.5763721826159786e-05, "loss": 4.428, "step": 6156 }, { "epoch": 0.18805742211362247, "grad_norm": 0.3946320414543152, "learning_rate": 4.576238567629492e-05, "loss": 4.4229, "step": 6157 }, { "epoch": 0.18808796579108125, "grad_norm": 0.38294023275375366, "learning_rate": 4.5761049335260084e-05, "loss": 4.3939, "step": 6158 }, { "epoch": 0.18811850946854, "grad_norm": 0.38664281368255615, "learning_rate": 4.57597128030676e-05, "loss": 4.2642, "step": 6159 }, { "epoch": 0.18814905314599878, "grad_norm": 0.38644781708717346, "learning_rate": 4.575837607972976e-05, "loss": 4.3609, "step": 6160 }, { "epoch": 0.18817959682345756, "grad_norm": 0.3852393329143524, "learning_rate": 4.575703916525889e-05, "loss": 4.3773, "step": 6161 }, { "epoch": 0.1882101405009163, "grad_norm": 0.3903200030326843, "learning_rate": 4.575570205966727e-05, "loss": 4.4085, "step": 6162 }, { "epoch": 0.18824068417837508, "grad_norm": 0.3884216845035553, "learning_rate": 4.5754364762967236e-05, "loss": 4.3878, "step": 6163 }, { "epoch": 0.18827122785583383, "grad_norm": 0.39040860533714294, "learning_rate": 4.57530272751711e-05, "loss": 4.4282, "step": 6164 }, { "epoch": 0.1883017715332926, "grad_norm": 0.4049907922744751, "learning_rate": 4.575168959629117e-05, "loss": 4.3669, "step": 6165 }, { "epoch": 0.18833231521075136, "grad_norm": 0.3757362961769104, "learning_rate": 4.5750351726339766e-05, "loss": 4.413, "step": 6166 }, { "epoch": 0.18836285888821014, "grad_norm": 0.38950660824775696, "learning_rate": 4.57490136653292e-05, "loss": 4.3751, "step": 6167 }, { "epoch": 0.18839340256566892, "grad_norm": 0.41557905077934265, "learning_rate": 4.574767541327181e-05, "loss": 4.3145, "step": 6168 }, { "epoch": 0.18842394624312767, "grad_norm": 0.3959970474243164, "learning_rate": 4.5746336970179894e-05, "loss": 4.3369, "step": 6169 }, { "epoch": 0.18845448992058644, "grad_norm": 0.37720122933387756, "learning_rate": 4.574499833606578e-05, "loss": 4.3481, "step": 6170 }, { "epoch": 0.1884850335980452, "grad_norm": 0.38867029547691345, "learning_rate": 4.5743659510941815e-05, "loss": 4.4327, "step": 6171 }, { "epoch": 0.18851557727550397, "grad_norm": 0.3935726583003998, "learning_rate": 4.57423204948203e-05, "loss": 4.4595, "step": 6172 }, { "epoch": 0.18854612095296275, "grad_norm": 0.40348654985427856, "learning_rate": 4.574098128771358e-05, "loss": 4.4996, "step": 6173 }, { "epoch": 0.1885766646304215, "grad_norm": 0.40437230467796326, "learning_rate": 4.5739641889633985e-05, "loss": 4.2924, "step": 6174 }, { "epoch": 0.18860720830788028, "grad_norm": 0.3834817707538605, "learning_rate": 4.573830230059384e-05, "loss": 4.4288, "step": 6175 }, { "epoch": 0.18863775198533902, "grad_norm": 0.38944464921951294, "learning_rate": 4.5736962520605486e-05, "loss": 4.4408, "step": 6176 }, { "epoch": 0.1886682956627978, "grad_norm": 0.3818299472332001, "learning_rate": 4.573562254968125e-05, "loss": 4.4192, "step": 6177 }, { "epoch": 0.18869883934025658, "grad_norm": 0.3953198790550232, "learning_rate": 4.573428238783348e-05, "loss": 4.4305, "step": 6178 }, { "epoch": 0.18872938301771533, "grad_norm": 0.3898683786392212, "learning_rate": 4.573294203507451e-05, "loss": 4.3918, "step": 6179 }, { "epoch": 0.1887599266951741, "grad_norm": 0.39347949624061584, "learning_rate": 4.5731601491416685e-05, "loss": 4.423, "step": 6180 }, { "epoch": 0.18879047037263286, "grad_norm": 0.3807319104671478, "learning_rate": 4.5730260756872343e-05, "loss": 4.3114, "step": 6181 }, { "epoch": 0.18882101405009163, "grad_norm": 0.3736087381839752, "learning_rate": 4.572891983145384e-05, "loss": 4.3722, "step": 6182 }, { "epoch": 0.18885155772755038, "grad_norm": 0.3909890055656433, "learning_rate": 4.5727578715173504e-05, "loss": 4.3639, "step": 6183 }, { "epoch": 0.18888210140500916, "grad_norm": 0.38112112879753113, "learning_rate": 4.5726237408043706e-05, "loss": 4.4363, "step": 6184 }, { "epoch": 0.18891264508246794, "grad_norm": 0.3840116560459137, "learning_rate": 4.572489591007677e-05, "loss": 4.2886, "step": 6185 }, { "epoch": 0.1889431887599267, "grad_norm": 0.3921772837638855, "learning_rate": 4.572355422128507e-05, "loss": 4.4025, "step": 6186 }, { "epoch": 0.18897373243738547, "grad_norm": 0.4046435058116913, "learning_rate": 4.572221234168095e-05, "loss": 4.3372, "step": 6187 }, { "epoch": 0.18900427611484422, "grad_norm": 0.3808860778808594, "learning_rate": 4.5720870271276764e-05, "loss": 4.4189, "step": 6188 }, { "epoch": 0.189034819792303, "grad_norm": 0.37334850430488586, "learning_rate": 4.5719528010084874e-05, "loss": 4.3868, "step": 6189 }, { "epoch": 0.18906536346976177, "grad_norm": 0.3799338936805725, "learning_rate": 4.571818555811763e-05, "loss": 4.3432, "step": 6190 }, { "epoch": 0.18909590714722052, "grad_norm": 0.39609864354133606, "learning_rate": 4.5716842915387406e-05, "loss": 4.3811, "step": 6191 }, { "epoch": 0.1891264508246793, "grad_norm": 0.3881756067276001, "learning_rate": 4.571550008190656e-05, "loss": 4.38, "step": 6192 }, { "epoch": 0.18915699450213805, "grad_norm": 0.3889784514904022, "learning_rate": 4.571415705768745e-05, "loss": 4.4229, "step": 6193 }, { "epoch": 0.18918753817959683, "grad_norm": 0.390678346157074, "learning_rate": 4.5712813842742444e-05, "loss": 4.3639, "step": 6194 }, { "epoch": 0.1892180818570556, "grad_norm": 0.39148879051208496, "learning_rate": 4.571147043708391e-05, "loss": 4.4579, "step": 6195 }, { "epoch": 0.18924862553451435, "grad_norm": 0.3853214681148529, "learning_rate": 4.571012684072423e-05, "loss": 4.382, "step": 6196 }, { "epoch": 0.18927916921197313, "grad_norm": 0.38382089138031006, "learning_rate": 4.570878305367576e-05, "loss": 4.3782, "step": 6197 }, { "epoch": 0.18930971288943188, "grad_norm": 0.3823772668838501, "learning_rate": 4.570743907595088e-05, "loss": 4.4235, "step": 6198 }, { "epoch": 0.18934025656689066, "grad_norm": 0.38118284940719604, "learning_rate": 4.5706094907561945e-05, "loss": 4.4072, "step": 6199 }, { "epoch": 0.1893708002443494, "grad_norm": 0.37896621227264404, "learning_rate": 4.5704750548521365e-05, "loss": 4.3973, "step": 6200 }, { "epoch": 0.18940134392180819, "grad_norm": 0.39071333408355713, "learning_rate": 4.570340599884149e-05, "loss": 4.459, "step": 6201 }, { "epoch": 0.18943188759926696, "grad_norm": 0.38177651166915894, "learning_rate": 4.570206125853472e-05, "loss": 4.4193, "step": 6202 }, { "epoch": 0.1894624312767257, "grad_norm": 0.3971388339996338, "learning_rate": 4.570071632761342e-05, "loss": 4.3624, "step": 6203 }, { "epoch": 0.1894929749541845, "grad_norm": 0.3813058137893677, "learning_rate": 4.569937120608999e-05, "loss": 4.3519, "step": 6204 }, { "epoch": 0.18952351863164324, "grad_norm": 0.36710450053215027, "learning_rate": 4.5698025893976804e-05, "loss": 4.3364, "step": 6205 }, { "epoch": 0.18955406230910202, "grad_norm": 0.38414275646209717, "learning_rate": 4.569668039128625e-05, "loss": 4.3639, "step": 6206 }, { "epoch": 0.1895846059865608, "grad_norm": 0.38500311970710754, "learning_rate": 4.569533469803072e-05, "loss": 4.3163, "step": 6207 }, { "epoch": 0.18961514966401954, "grad_norm": 0.38988468050956726, "learning_rate": 4.56939888142226e-05, "loss": 4.3637, "step": 6208 }, { "epoch": 0.18964569334147832, "grad_norm": 0.3882198929786682, "learning_rate": 4.569264273987429e-05, "loss": 4.3466, "step": 6209 }, { "epoch": 0.18967623701893707, "grad_norm": 0.3823203146457672, "learning_rate": 4.569129647499818e-05, "loss": 4.3741, "step": 6210 }, { "epoch": 0.18970678069639585, "grad_norm": 0.40310314297676086, "learning_rate": 4.568995001960665e-05, "loss": 4.4158, "step": 6211 }, { "epoch": 0.1897373243738546, "grad_norm": 0.37485381960868835, "learning_rate": 4.568860337371213e-05, "loss": 4.4372, "step": 6212 }, { "epoch": 0.18976786805131338, "grad_norm": 0.37661710381507874, "learning_rate": 4.5687256537327e-05, "loss": 4.4095, "step": 6213 }, { "epoch": 0.18979841172877215, "grad_norm": 0.38263675570487976, "learning_rate": 4.5685909510463654e-05, "loss": 4.417, "step": 6214 }, { "epoch": 0.1898289554062309, "grad_norm": 0.3886273503303528, "learning_rate": 4.568456229313451e-05, "loss": 4.4205, "step": 6215 }, { "epoch": 0.18985949908368968, "grad_norm": 0.3889353275299072, "learning_rate": 4.568321488535197e-05, "loss": 4.3152, "step": 6216 }, { "epoch": 0.18989004276114843, "grad_norm": 0.3837534487247467, "learning_rate": 4.5681867287128425e-05, "loss": 4.2734, "step": 6217 }, { "epoch": 0.1899205864386072, "grad_norm": 0.4077836275100708, "learning_rate": 4.56805194984763e-05, "loss": 4.3225, "step": 6218 }, { "epoch": 0.18995113011606599, "grad_norm": 0.389843612909317, "learning_rate": 4.567917151940799e-05, "loss": 4.4447, "step": 6219 }, { "epoch": 0.18998167379352474, "grad_norm": 0.3857339918613434, "learning_rate": 4.5677823349935936e-05, "loss": 4.4321, "step": 6220 }, { "epoch": 0.1900122174709835, "grad_norm": 0.38527587056159973, "learning_rate": 4.567647499007252e-05, "loss": 4.3914, "step": 6221 }, { "epoch": 0.19004276114844226, "grad_norm": 0.39165446162223816, "learning_rate": 4.567512643983016e-05, "loss": 4.437, "step": 6222 }, { "epoch": 0.19007330482590104, "grad_norm": 0.40311750769615173, "learning_rate": 4.567377769922129e-05, "loss": 4.2765, "step": 6223 }, { "epoch": 0.19010384850335982, "grad_norm": 0.385752409696579, "learning_rate": 4.567242876825831e-05, "loss": 4.4119, "step": 6224 }, { "epoch": 0.19013439218081857, "grad_norm": 0.3796834647655487, "learning_rate": 4.567107964695366e-05, "loss": 4.3991, "step": 6225 }, { "epoch": 0.19016493585827735, "grad_norm": 0.3764076828956604, "learning_rate": 4.566973033531975e-05, "loss": 4.3386, "step": 6226 }, { "epoch": 0.1901954795357361, "grad_norm": 0.3864111304283142, "learning_rate": 4.566838083336901e-05, "loss": 4.3485, "step": 6227 }, { "epoch": 0.19022602321319487, "grad_norm": 0.3800775706768036, "learning_rate": 4.5667031141113846e-05, "loss": 4.3378, "step": 6228 }, { "epoch": 0.19025656689065362, "grad_norm": 0.378700315952301, "learning_rate": 4.5665681258566714e-05, "loss": 4.3509, "step": 6229 }, { "epoch": 0.1902871105681124, "grad_norm": 0.37371182441711426, "learning_rate": 4.566433118574003e-05, "loss": 4.3681, "step": 6230 }, { "epoch": 0.19031765424557118, "grad_norm": 0.3970519006252289, "learning_rate": 4.5662980922646215e-05, "loss": 4.4061, "step": 6231 }, { "epoch": 0.19034819792302993, "grad_norm": 0.3858143091201782, "learning_rate": 4.566163046929771e-05, "loss": 4.3953, "step": 6232 }, { "epoch": 0.1903787416004887, "grad_norm": 0.38784486055374146, "learning_rate": 4.566027982570696e-05, "loss": 4.3921, "step": 6233 }, { "epoch": 0.19040928527794745, "grad_norm": 0.3801525831222534, "learning_rate": 4.5658928991886383e-05, "loss": 4.2932, "step": 6234 }, { "epoch": 0.19043982895540623, "grad_norm": 0.3766458332538605, "learning_rate": 4.565757796784843e-05, "loss": 4.3081, "step": 6235 }, { "epoch": 0.190470372632865, "grad_norm": 0.380209743976593, "learning_rate": 4.5656226753605535e-05, "loss": 4.3499, "step": 6236 }, { "epoch": 0.19050091631032376, "grad_norm": 0.37979400157928467, "learning_rate": 4.5654875349170136e-05, "loss": 4.3766, "step": 6237 }, { "epoch": 0.19053145998778254, "grad_norm": 0.3821054995059967, "learning_rate": 4.5653523754554685e-05, "loss": 4.3134, "step": 6238 }, { "epoch": 0.1905620036652413, "grad_norm": 0.38142552971839905, "learning_rate": 4.5652171969771617e-05, "loss": 4.4279, "step": 6239 }, { "epoch": 0.19059254734270006, "grad_norm": 0.3929543197154999, "learning_rate": 4.5650819994833385e-05, "loss": 4.4694, "step": 6240 }, { "epoch": 0.1906230910201588, "grad_norm": 0.376198410987854, "learning_rate": 4.564946782975244e-05, "loss": 4.3276, "step": 6241 }, { "epoch": 0.1906536346976176, "grad_norm": 0.384147971868515, "learning_rate": 4.564811547454122e-05, "loss": 4.436, "step": 6242 }, { "epoch": 0.19068417837507637, "grad_norm": 0.3798484802246094, "learning_rate": 4.564676292921219e-05, "loss": 4.3023, "step": 6243 }, { "epoch": 0.19071472205253512, "grad_norm": 0.3821509778499603, "learning_rate": 4.56454101937778e-05, "loss": 4.4009, "step": 6244 }, { "epoch": 0.1907452657299939, "grad_norm": 0.391369104385376, "learning_rate": 4.56440572682505e-05, "loss": 4.3125, "step": 6245 }, { "epoch": 0.19077580940745265, "grad_norm": 0.3787171244621277, "learning_rate": 4.564270415264275e-05, "loss": 4.2948, "step": 6246 }, { "epoch": 0.19080635308491142, "grad_norm": 0.392039030790329, "learning_rate": 4.564135084696701e-05, "loss": 4.3481, "step": 6247 }, { "epoch": 0.1908368967623702, "grad_norm": 0.3924655318260193, "learning_rate": 4.563999735123574e-05, "loss": 4.3298, "step": 6248 }, { "epoch": 0.19086744043982895, "grad_norm": 0.3814888894557953, "learning_rate": 4.5638643665461404e-05, "loss": 4.3394, "step": 6249 }, { "epoch": 0.19089798411728773, "grad_norm": 0.3780725598335266, "learning_rate": 4.563728978965647e-05, "loss": 4.3361, "step": 6250 }, { "epoch": 0.19092852779474648, "grad_norm": 0.38439467549324036, "learning_rate": 4.563593572383339e-05, "loss": 4.3833, "step": 6251 }, { "epoch": 0.19095907147220526, "grad_norm": 0.39891695976257324, "learning_rate": 4.5634581468004636e-05, "loss": 4.4258, "step": 6252 }, { "epoch": 0.19098961514966403, "grad_norm": 0.3810618221759796, "learning_rate": 4.563322702218269e-05, "loss": 4.3464, "step": 6253 }, { "epoch": 0.19102015882712278, "grad_norm": 0.3790327310562134, "learning_rate": 4.563187238638002e-05, "loss": 4.3961, "step": 6254 }, { "epoch": 0.19105070250458156, "grad_norm": 0.3832866847515106, "learning_rate": 4.563051756060908e-05, "loss": 4.4229, "step": 6255 }, { "epoch": 0.1910812461820403, "grad_norm": 0.38293924927711487, "learning_rate": 4.562916254488235e-05, "loss": 4.3688, "step": 6256 }, { "epoch": 0.1911117898594991, "grad_norm": 0.3854275345802307, "learning_rate": 4.562780733921234e-05, "loss": 4.4684, "step": 6257 }, { "epoch": 0.19114233353695784, "grad_norm": 0.37143853306770325, "learning_rate": 4.562645194361148e-05, "loss": 4.3919, "step": 6258 }, { "epoch": 0.19117287721441661, "grad_norm": 0.3825559914112091, "learning_rate": 4.562509635809228e-05, "loss": 4.2569, "step": 6259 }, { "epoch": 0.1912034208918754, "grad_norm": 0.38467562198638916, "learning_rate": 4.562374058266721e-05, "loss": 4.3252, "step": 6260 }, { "epoch": 0.19123396456933414, "grad_norm": 0.37794142961502075, "learning_rate": 4.5622384617348764e-05, "loss": 4.4613, "step": 6261 }, { "epoch": 0.19126450824679292, "grad_norm": 0.3863769471645355, "learning_rate": 4.5621028462149415e-05, "loss": 4.3532, "step": 6262 }, { "epoch": 0.19129505192425167, "grad_norm": 0.3919130563735962, "learning_rate": 4.561967211708166e-05, "loss": 4.4027, "step": 6263 }, { "epoch": 0.19132559560171045, "grad_norm": 0.40138861536979675, "learning_rate": 4.561831558215797e-05, "loss": 4.3254, "step": 6264 }, { "epoch": 0.19135613927916922, "grad_norm": 0.3831004202365875, "learning_rate": 4.561695885739086e-05, "loss": 4.3481, "step": 6265 }, { "epoch": 0.19138668295662797, "grad_norm": 0.38817548751831055, "learning_rate": 4.56156019427928e-05, "loss": 4.3729, "step": 6266 }, { "epoch": 0.19141722663408675, "grad_norm": 0.38083821535110474, "learning_rate": 4.56142448383763e-05, "loss": 4.4076, "step": 6267 }, { "epoch": 0.1914477703115455, "grad_norm": 0.3752167820930481, "learning_rate": 4.561288754415385e-05, "loss": 4.4248, "step": 6268 }, { "epoch": 0.19147831398900428, "grad_norm": 0.37864571809768677, "learning_rate": 4.561153006013794e-05, "loss": 4.337, "step": 6269 }, { "epoch": 0.19150885766646306, "grad_norm": 0.3840488791465759, "learning_rate": 4.561017238634108e-05, "loss": 4.3892, "step": 6270 }, { "epoch": 0.1915394013439218, "grad_norm": 0.3844580352306366, "learning_rate": 4.5608814522775766e-05, "loss": 4.2321, "step": 6271 }, { "epoch": 0.19156994502138058, "grad_norm": 0.39337220788002014, "learning_rate": 4.56074564694545e-05, "loss": 4.4151, "step": 6272 }, { "epoch": 0.19160048869883933, "grad_norm": 0.376540869474411, "learning_rate": 4.560609822638979e-05, "loss": 4.3413, "step": 6273 }, { "epoch": 0.1916310323762981, "grad_norm": 0.3976597487926483, "learning_rate": 4.5604739793594134e-05, "loss": 4.3458, "step": 6274 }, { "epoch": 0.19166157605375686, "grad_norm": 0.38380128145217896, "learning_rate": 4.560338117108005e-05, "loss": 4.3837, "step": 6275 }, { "epoch": 0.19169211973121564, "grad_norm": 0.3744547963142395, "learning_rate": 4.560202235886003e-05, "loss": 4.4237, "step": 6276 }, { "epoch": 0.19172266340867442, "grad_norm": 0.3970402777194977, "learning_rate": 4.5600663356946613e-05, "loss": 4.3435, "step": 6277 }, { "epoch": 0.19175320708613317, "grad_norm": 0.38105836510658264, "learning_rate": 4.559930416535228e-05, "loss": 4.3811, "step": 6278 }, { "epoch": 0.19178375076359194, "grad_norm": 0.38870251178741455, "learning_rate": 4.559794478408958e-05, "loss": 4.3716, "step": 6279 }, { "epoch": 0.1918142944410507, "grad_norm": 0.3840183913707733, "learning_rate": 4.559658521317101e-05, "loss": 4.4531, "step": 6280 }, { "epoch": 0.19184483811850947, "grad_norm": 0.3914925158023834, "learning_rate": 4.559522545260908e-05, "loss": 4.3765, "step": 6281 }, { "epoch": 0.19187538179596825, "grad_norm": 0.39233991503715515, "learning_rate": 4.559386550241632e-05, "loss": 4.3771, "step": 6282 }, { "epoch": 0.191905925473427, "grad_norm": 0.38480710983276367, "learning_rate": 4.5592505362605265e-05, "loss": 4.4323, "step": 6283 }, { "epoch": 0.19193646915088577, "grad_norm": 0.3876912295818329, "learning_rate": 4.559114503318841e-05, "loss": 4.4489, "step": 6284 }, { "epoch": 0.19196701282834452, "grad_norm": 0.3830241858959198, "learning_rate": 4.5589784514178304e-05, "loss": 4.3764, "step": 6285 }, { "epoch": 0.1919975565058033, "grad_norm": 0.3876721262931824, "learning_rate": 4.5588423805587464e-05, "loss": 4.3235, "step": 6286 }, { "epoch": 0.19202810018326205, "grad_norm": 0.386078417301178, "learning_rate": 4.558706290742842e-05, "loss": 4.3972, "step": 6287 }, { "epoch": 0.19205864386072083, "grad_norm": 0.3801453411579132, "learning_rate": 4.558570181971371e-05, "loss": 4.3753, "step": 6288 }, { "epoch": 0.1920891875381796, "grad_norm": 0.39891374111175537, "learning_rate": 4.558434054245585e-05, "loss": 4.3675, "step": 6289 }, { "epoch": 0.19211973121563836, "grad_norm": 0.3892359137535095, "learning_rate": 4.5582979075667394e-05, "loss": 4.3552, "step": 6290 }, { "epoch": 0.19215027489309713, "grad_norm": 0.36655858159065247, "learning_rate": 4.558161741936085e-05, "loss": 4.3384, "step": 6291 }, { "epoch": 0.19218081857055588, "grad_norm": 0.38169485330581665, "learning_rate": 4.558025557354879e-05, "loss": 4.3145, "step": 6292 }, { "epoch": 0.19221136224801466, "grad_norm": 0.3815331757068634, "learning_rate": 4.5578893538243724e-05, "loss": 4.338, "step": 6293 }, { "epoch": 0.19224190592547344, "grad_norm": 0.3746444284915924, "learning_rate": 4.557753131345821e-05, "loss": 4.2674, "step": 6294 }, { "epoch": 0.1922724496029322, "grad_norm": 0.3728092908859253, "learning_rate": 4.557616889920479e-05, "loss": 4.3852, "step": 6295 }, { "epoch": 0.19230299328039097, "grad_norm": 0.3749500513076782, "learning_rate": 4.5574806295495994e-05, "loss": 4.2782, "step": 6296 }, { "epoch": 0.19233353695784972, "grad_norm": 0.3737810254096985, "learning_rate": 4.557344350234438e-05, "loss": 4.2405, "step": 6297 }, { "epoch": 0.1923640806353085, "grad_norm": 0.38438957929611206, "learning_rate": 4.557208051976249e-05, "loss": 4.3855, "step": 6298 }, { "epoch": 0.19239462431276727, "grad_norm": 0.39011436700820923, "learning_rate": 4.557071734776289e-05, "loss": 4.3843, "step": 6299 }, { "epoch": 0.19242516799022602, "grad_norm": 0.38950029015541077, "learning_rate": 4.556935398635811e-05, "loss": 4.3137, "step": 6300 }, { "epoch": 0.1924557116676848, "grad_norm": 0.4128091633319855, "learning_rate": 4.5567990435560714e-05, "loss": 4.4411, "step": 6301 }, { "epoch": 0.19248625534514355, "grad_norm": 0.38459450006484985, "learning_rate": 4.5566626695383254e-05, "loss": 4.3471, "step": 6302 }, { "epoch": 0.19251679902260233, "grad_norm": 0.3754955530166626, "learning_rate": 4.556526276583829e-05, "loss": 4.433, "step": 6303 }, { "epoch": 0.19254734270006107, "grad_norm": 0.38528069853782654, "learning_rate": 4.5563898646938375e-05, "loss": 4.3876, "step": 6304 }, { "epoch": 0.19257788637751985, "grad_norm": 0.38797813653945923, "learning_rate": 4.5562534338696074e-05, "loss": 4.3788, "step": 6305 }, { "epoch": 0.19260843005497863, "grad_norm": 0.37653371691703796, "learning_rate": 4.5561169841123946e-05, "loss": 4.454, "step": 6306 }, { "epoch": 0.19263897373243738, "grad_norm": 0.3963988721370697, "learning_rate": 4.555980515423456e-05, "loss": 4.3413, "step": 6307 }, { "epoch": 0.19266951740989616, "grad_norm": 0.3946227431297302, "learning_rate": 4.555844027804047e-05, "loss": 4.3526, "step": 6308 }, { "epoch": 0.1927000610873549, "grad_norm": 0.38937968015670776, "learning_rate": 4.5557075212554254e-05, "loss": 4.3779, "step": 6309 }, { "epoch": 0.19273060476481368, "grad_norm": 0.3725259602069855, "learning_rate": 4.555570995778848e-05, "loss": 4.3416, "step": 6310 }, { "epoch": 0.19276114844227246, "grad_norm": 0.39500296115875244, "learning_rate": 4.555434451375571e-05, "loss": 4.4675, "step": 6311 }, { "epoch": 0.1927916921197312, "grad_norm": 0.39538946747779846, "learning_rate": 4.5552978880468525e-05, "loss": 4.4602, "step": 6312 }, { "epoch": 0.19282223579719, "grad_norm": 0.38453224301338196, "learning_rate": 4.55516130579395e-05, "loss": 4.4717, "step": 6313 }, { "epoch": 0.19285277947464874, "grad_norm": 0.37835967540740967, "learning_rate": 4.5550247046181204e-05, "loss": 4.3873, "step": 6314 }, { "epoch": 0.19288332315210752, "grad_norm": 0.3839690685272217, "learning_rate": 4.5548880845206215e-05, "loss": 4.3066, "step": 6315 }, { "epoch": 0.19291386682956627, "grad_norm": 0.364006906747818, "learning_rate": 4.554751445502712e-05, "loss": 4.3405, "step": 6316 }, { "epoch": 0.19294441050702504, "grad_norm": 0.37809717655181885, "learning_rate": 4.5546147875656484e-05, "loss": 4.3938, "step": 6317 }, { "epoch": 0.19297495418448382, "grad_norm": 0.38134434819221497, "learning_rate": 4.5544781107106916e-05, "loss": 4.4175, "step": 6318 }, { "epoch": 0.19300549786194257, "grad_norm": 0.38846278190612793, "learning_rate": 4.554341414939097e-05, "loss": 4.3907, "step": 6319 }, { "epoch": 0.19303604153940135, "grad_norm": 0.3876793384552002, "learning_rate": 4.554204700252126e-05, "loss": 4.3586, "step": 6320 }, { "epoch": 0.1930665852168601, "grad_norm": 0.37886232137680054, "learning_rate": 4.5540679666510357e-05, "loss": 4.2708, "step": 6321 }, { "epoch": 0.19309712889431888, "grad_norm": 0.3764360547065735, "learning_rate": 4.553931214137086e-05, "loss": 4.3724, "step": 6322 }, { "epoch": 0.19312767257177765, "grad_norm": 0.3758552372455597, "learning_rate": 4.5537944427115344e-05, "loss": 4.3875, "step": 6323 }, { "epoch": 0.1931582162492364, "grad_norm": 0.38696417212486267, "learning_rate": 4.553657652375643e-05, "loss": 4.3652, "step": 6324 }, { "epoch": 0.19318875992669518, "grad_norm": 0.3987788259983063, "learning_rate": 4.553520843130669e-05, "loss": 4.3351, "step": 6325 }, { "epoch": 0.19321930360415393, "grad_norm": 0.3807372450828552, "learning_rate": 4.553384014977872e-05, "loss": 4.3388, "step": 6326 }, { "epoch": 0.1932498472816127, "grad_norm": 0.39251866936683655, "learning_rate": 4.553247167918513e-05, "loss": 4.3755, "step": 6327 }, { "epoch": 0.19328039095907149, "grad_norm": 0.3796459436416626, "learning_rate": 4.553110301953852e-05, "loss": 4.392, "step": 6328 }, { "epoch": 0.19331093463653024, "grad_norm": 0.3948148190975189, "learning_rate": 4.552973417085149e-05, "loss": 4.4156, "step": 6329 }, { "epoch": 0.193341478313989, "grad_norm": 0.38318881392478943, "learning_rate": 4.552836513313664e-05, "loss": 4.429, "step": 6330 }, { "epoch": 0.19337202199144776, "grad_norm": 0.3892822861671448, "learning_rate": 4.5526995906406575e-05, "loss": 4.3483, "step": 6331 }, { "epoch": 0.19340256566890654, "grad_norm": 0.38352325558662415, "learning_rate": 4.55256264906739e-05, "loss": 4.3089, "step": 6332 }, { "epoch": 0.1934331093463653, "grad_norm": 0.37290892004966736, "learning_rate": 4.5524256885951245e-05, "loss": 4.3547, "step": 6333 }, { "epoch": 0.19346365302382407, "grad_norm": 0.37695324420928955, "learning_rate": 4.552288709225119e-05, "loss": 4.4007, "step": 6334 }, { "epoch": 0.19349419670128284, "grad_norm": 0.3729456961154938, "learning_rate": 4.5521517109586366e-05, "loss": 4.4137, "step": 6335 }, { "epoch": 0.1935247403787416, "grad_norm": 0.3893248736858368, "learning_rate": 4.5520146937969385e-05, "loss": 4.3301, "step": 6336 }, { "epoch": 0.19355528405620037, "grad_norm": 0.38435831665992737, "learning_rate": 4.5518776577412856e-05, "loss": 4.4207, "step": 6337 }, { "epoch": 0.19358582773365912, "grad_norm": 0.37300243973731995, "learning_rate": 4.55174060279294e-05, "loss": 4.3712, "step": 6338 }, { "epoch": 0.1936163714111179, "grad_norm": 0.3708723485469818, "learning_rate": 4.551603528953164e-05, "loss": 4.3706, "step": 6339 }, { "epoch": 0.19364691508857668, "grad_norm": 0.37612855434417725, "learning_rate": 4.5514664362232205e-05, "loss": 4.3651, "step": 6340 }, { "epoch": 0.19367745876603543, "grad_norm": 0.38252362608909607, "learning_rate": 4.5513293246043695e-05, "loss": 4.4029, "step": 6341 }, { "epoch": 0.1937080024434942, "grad_norm": 0.37160253524780273, "learning_rate": 4.551192194097875e-05, "loss": 4.3827, "step": 6342 }, { "epoch": 0.19373854612095295, "grad_norm": 0.41052135825157166, "learning_rate": 4.551055044705e-05, "loss": 4.404, "step": 6343 }, { "epoch": 0.19376908979841173, "grad_norm": 0.38214460015296936, "learning_rate": 4.5509178764270064e-05, "loss": 4.3232, "step": 6344 }, { "epoch": 0.1937996334758705, "grad_norm": 0.3776252567768097, "learning_rate": 4.5507806892651575e-05, "loss": 4.4072, "step": 6345 }, { "epoch": 0.19383017715332926, "grad_norm": 0.3893711268901825, "learning_rate": 4.5506434832207155e-05, "loss": 4.3741, "step": 6346 }, { "epoch": 0.19386072083078804, "grad_norm": 0.3855076730251312, "learning_rate": 4.5505062582949455e-05, "loss": 4.4425, "step": 6347 }, { "epoch": 0.19389126450824679, "grad_norm": 0.37722015380859375, "learning_rate": 4.55036901448911e-05, "loss": 4.3324, "step": 6348 }, { "epoch": 0.19392180818570556, "grad_norm": 0.37860673666000366, "learning_rate": 4.550231751804473e-05, "loss": 4.3838, "step": 6349 }, { "epoch": 0.1939523518631643, "grad_norm": 0.38664042949676514, "learning_rate": 4.550094470242297e-05, "loss": 4.4693, "step": 6350 }, { "epoch": 0.1939828955406231, "grad_norm": 0.38697487115859985, "learning_rate": 4.549957169803848e-05, "loss": 4.4335, "step": 6351 }, { "epoch": 0.19401343921808187, "grad_norm": 0.38337668776512146, "learning_rate": 4.549819850490389e-05, "loss": 4.3868, "step": 6352 }, { "epoch": 0.19404398289554062, "grad_norm": 0.39003869891166687, "learning_rate": 4.549682512303185e-05, "loss": 4.3112, "step": 6353 }, { "epoch": 0.1940745265729994, "grad_norm": 0.39117538928985596, "learning_rate": 4.5495451552435e-05, "loss": 4.4316, "step": 6354 }, { "epoch": 0.19410507025045814, "grad_norm": 0.39147552847862244, "learning_rate": 4.5494077793125994e-05, "loss": 4.4333, "step": 6355 }, { "epoch": 0.19413561392791692, "grad_norm": 0.39653924107551575, "learning_rate": 4.549270384511748e-05, "loss": 4.2712, "step": 6356 }, { "epoch": 0.1941661576053757, "grad_norm": 0.3738888204097748, "learning_rate": 4.549132970842209e-05, "loss": 4.3264, "step": 6357 }, { "epoch": 0.19419670128283445, "grad_norm": 0.38672733306884766, "learning_rate": 4.548995538305251e-05, "loss": 4.326, "step": 6358 }, { "epoch": 0.19422724496029323, "grad_norm": 0.3754465579986572, "learning_rate": 4.548858086902137e-05, "loss": 4.3586, "step": 6359 }, { "epoch": 0.19425778863775198, "grad_norm": 0.3768683075904846, "learning_rate": 4.548720616634132e-05, "loss": 4.3589, "step": 6360 }, { "epoch": 0.19428833231521075, "grad_norm": 0.38930052518844604, "learning_rate": 4.548583127502505e-05, "loss": 4.4268, "step": 6361 }, { "epoch": 0.1943188759926695, "grad_norm": 0.36474162340164185, "learning_rate": 4.548445619508519e-05, "loss": 4.2754, "step": 6362 }, { "epoch": 0.19434941967012828, "grad_norm": 0.3752158582210541, "learning_rate": 4.54830809265344e-05, "loss": 4.2999, "step": 6363 }, { "epoch": 0.19437996334758706, "grad_norm": 0.37593501806259155, "learning_rate": 4.548170546938536e-05, "loss": 4.3545, "step": 6364 }, { "epoch": 0.1944105070250458, "grad_norm": 0.38329145312309265, "learning_rate": 4.548032982365073e-05, "loss": 4.3846, "step": 6365 }, { "epoch": 0.1944410507025046, "grad_norm": 0.39711013436317444, "learning_rate": 4.5478953989343164e-05, "loss": 4.4301, "step": 6366 }, { "epoch": 0.19447159437996334, "grad_norm": 0.3831869065761566, "learning_rate": 4.547757796647535e-05, "loss": 4.4201, "step": 6367 }, { "epoch": 0.1945021380574221, "grad_norm": 0.3838089108467102, "learning_rate": 4.547620175505994e-05, "loss": 4.3854, "step": 6368 }, { "epoch": 0.1945326817348809, "grad_norm": 0.3902703523635864, "learning_rate": 4.547482535510962e-05, "loss": 4.4057, "step": 6369 }, { "epoch": 0.19456322541233964, "grad_norm": 0.3678881824016571, "learning_rate": 4.547344876663705e-05, "loss": 4.3979, "step": 6370 }, { "epoch": 0.19459376908979842, "grad_norm": 0.3911750018596649, "learning_rate": 4.5472071989654913e-05, "loss": 4.43, "step": 6371 }, { "epoch": 0.19462431276725717, "grad_norm": 0.3857634663581848, "learning_rate": 4.5470695024175883e-05, "loss": 4.2965, "step": 6372 }, { "epoch": 0.19465485644471595, "grad_norm": 0.38549286127090454, "learning_rate": 4.5469317870212636e-05, "loss": 4.4227, "step": 6373 }, { "epoch": 0.19468540012217472, "grad_norm": 0.38598597049713135, "learning_rate": 4.546794052777786e-05, "loss": 4.3721, "step": 6374 }, { "epoch": 0.19471594379963347, "grad_norm": 0.3760993182659149, "learning_rate": 4.5466562996884235e-05, "loss": 4.3573, "step": 6375 }, { "epoch": 0.19474648747709225, "grad_norm": 0.3860737979412079, "learning_rate": 4.546518527754443e-05, "loss": 4.3169, "step": 6376 }, { "epoch": 0.194777031154551, "grad_norm": 0.39063408970832825, "learning_rate": 4.546380736977115e-05, "loss": 4.4298, "step": 6377 }, { "epoch": 0.19480757483200978, "grad_norm": 0.3803039491176605, "learning_rate": 4.546242927357707e-05, "loss": 4.3402, "step": 6378 }, { "epoch": 0.19483811850946853, "grad_norm": 0.3803309500217438, "learning_rate": 4.546105098897489e-05, "loss": 4.3539, "step": 6379 }, { "epoch": 0.1948686621869273, "grad_norm": 0.38912323117256165, "learning_rate": 4.5459672515977294e-05, "loss": 4.3555, "step": 6380 }, { "epoch": 0.19489920586438608, "grad_norm": 0.3955095410346985, "learning_rate": 4.5458293854596964e-05, "loss": 4.3719, "step": 6381 }, { "epoch": 0.19492974954184483, "grad_norm": 0.37815019488334656, "learning_rate": 4.545691500484661e-05, "loss": 4.333, "step": 6382 }, { "epoch": 0.1949602932193036, "grad_norm": 0.37832382321357727, "learning_rate": 4.545553596673892e-05, "loss": 4.3573, "step": 6383 }, { "epoch": 0.19499083689676236, "grad_norm": 0.38098353147506714, "learning_rate": 4.545415674028659e-05, "loss": 4.3432, "step": 6384 }, { "epoch": 0.19502138057422114, "grad_norm": 0.39159896969795227, "learning_rate": 4.5452777325502324e-05, "loss": 4.441, "step": 6385 }, { "epoch": 0.19505192425167991, "grad_norm": 0.38003653287887573, "learning_rate": 4.545139772239883e-05, "loss": 4.3758, "step": 6386 }, { "epoch": 0.19508246792913866, "grad_norm": 0.40774470567703247, "learning_rate": 4.545001793098879e-05, "loss": 4.3456, "step": 6387 }, { "epoch": 0.19511301160659744, "grad_norm": 0.38023415207862854, "learning_rate": 4.544863795128493e-05, "loss": 4.2946, "step": 6388 }, { "epoch": 0.1951435552840562, "grad_norm": 0.38375189900398254, "learning_rate": 4.544725778329995e-05, "loss": 4.3884, "step": 6389 }, { "epoch": 0.19517409896151497, "grad_norm": 0.373043030500412, "learning_rate": 4.5445877427046536e-05, "loss": 4.3176, "step": 6390 }, { "epoch": 0.19520464263897372, "grad_norm": 0.37002965807914734, "learning_rate": 4.544449688253743e-05, "loss": 4.3609, "step": 6391 }, { "epoch": 0.1952351863164325, "grad_norm": 0.3703603148460388, "learning_rate": 4.5443116149785324e-05, "loss": 4.2732, "step": 6392 }, { "epoch": 0.19526572999389127, "grad_norm": 0.37792402505874634, "learning_rate": 4.5441735228802937e-05, "loss": 4.3636, "step": 6393 }, { "epoch": 0.19529627367135002, "grad_norm": 0.3734963834285736, "learning_rate": 4.544035411960299e-05, "loss": 4.2818, "step": 6394 }, { "epoch": 0.1953268173488088, "grad_norm": 0.36850622296333313, "learning_rate": 4.543897282219819e-05, "loss": 4.3689, "step": 6395 }, { "epoch": 0.19535736102626755, "grad_norm": 0.3789593577384949, "learning_rate": 4.543759133660126e-05, "loss": 4.363, "step": 6396 }, { "epoch": 0.19538790470372633, "grad_norm": 0.3763258159160614, "learning_rate": 4.543620966282492e-05, "loss": 4.3121, "step": 6397 }, { "epoch": 0.1954184483811851, "grad_norm": 0.3879006803035736, "learning_rate": 4.5434827800881884e-05, "loss": 4.366, "step": 6398 }, { "epoch": 0.19544899205864386, "grad_norm": 0.37644705176353455, "learning_rate": 4.5433445750784886e-05, "loss": 4.385, "step": 6399 }, { "epoch": 0.19547953573610263, "grad_norm": 0.3887500464916229, "learning_rate": 4.543206351254665e-05, "loss": 4.3722, "step": 6400 }, { "epoch": 0.19551007941356138, "grad_norm": 0.38345015048980713, "learning_rate": 4.54306810861799e-05, "loss": 4.3459, "step": 6401 }, { "epoch": 0.19554062309102016, "grad_norm": 0.3823298215866089, "learning_rate": 4.542929847169736e-05, "loss": 4.3657, "step": 6402 }, { "epoch": 0.19557116676847894, "grad_norm": 0.3780704438686371, "learning_rate": 4.5427915669111766e-05, "loss": 4.3028, "step": 6403 }, { "epoch": 0.1956017104459377, "grad_norm": 0.37923794984817505, "learning_rate": 4.5426532678435854e-05, "loss": 4.3712, "step": 6404 }, { "epoch": 0.19563225412339647, "grad_norm": 0.38264530897140503, "learning_rate": 4.542514949968234e-05, "loss": 4.3855, "step": 6405 }, { "epoch": 0.19566279780085521, "grad_norm": 0.37977299094200134, "learning_rate": 4.5423766132863986e-05, "loss": 4.4222, "step": 6406 }, { "epoch": 0.195693341478314, "grad_norm": 0.3691263198852539, "learning_rate": 4.5422382577993516e-05, "loss": 4.2608, "step": 6407 }, { "epoch": 0.19572388515577274, "grad_norm": 0.3868829607963562, "learning_rate": 4.542099883508366e-05, "loss": 4.3206, "step": 6408 }, { "epoch": 0.19575442883323152, "grad_norm": 0.3805558681488037, "learning_rate": 4.541961490414718e-05, "loss": 4.3871, "step": 6409 }, { "epoch": 0.1957849725106903, "grad_norm": 0.38721799850463867, "learning_rate": 4.5418230785196805e-05, "loss": 4.3601, "step": 6410 }, { "epoch": 0.19581551618814905, "grad_norm": 0.3742574155330658, "learning_rate": 4.541684647824527e-05, "loss": 4.336, "step": 6411 }, { "epoch": 0.19584605986560782, "grad_norm": 0.38012978434562683, "learning_rate": 4.541546198330534e-05, "loss": 4.4298, "step": 6412 }, { "epoch": 0.19587660354306657, "grad_norm": 0.382066011428833, "learning_rate": 4.541407730038976e-05, "loss": 4.4003, "step": 6413 }, { "epoch": 0.19590714722052535, "grad_norm": 0.36837372183799744, "learning_rate": 4.541269242951127e-05, "loss": 4.3152, "step": 6414 }, { "epoch": 0.19593769089798413, "grad_norm": 0.37365445494651794, "learning_rate": 4.541130737068262e-05, "loss": 4.3808, "step": 6415 }, { "epoch": 0.19596823457544288, "grad_norm": 0.39269644021987915, "learning_rate": 4.540992212391658e-05, "loss": 4.4243, "step": 6416 }, { "epoch": 0.19599877825290166, "grad_norm": 0.3858519494533539, "learning_rate": 4.540853668922588e-05, "loss": 4.3554, "step": 6417 }, { "epoch": 0.1960293219303604, "grad_norm": 0.3898617625236511, "learning_rate": 4.54071510666233e-05, "loss": 4.4006, "step": 6418 }, { "epoch": 0.19605986560781918, "grad_norm": 0.3807952105998993, "learning_rate": 4.5405765256121576e-05, "loss": 4.3628, "step": 6419 }, { "epoch": 0.19609040928527796, "grad_norm": 0.37986111640930176, "learning_rate": 4.5404379257733496e-05, "loss": 4.3874, "step": 6420 }, { "epoch": 0.1961209529627367, "grad_norm": 0.3896695375442505, "learning_rate": 4.540299307147179e-05, "loss": 4.395, "step": 6421 }, { "epoch": 0.1961514966401955, "grad_norm": 0.39959433674812317, "learning_rate": 4.540160669734925e-05, "loss": 4.3997, "step": 6422 }, { "epoch": 0.19618204031765424, "grad_norm": 0.3722896873950958, "learning_rate": 4.540022013537862e-05, "loss": 4.4389, "step": 6423 }, { "epoch": 0.19621258399511302, "grad_norm": 0.3883250057697296, "learning_rate": 4.539883338557268e-05, "loss": 4.4118, "step": 6424 }, { "epoch": 0.19624312767257177, "grad_norm": 0.37810179591178894, "learning_rate": 4.539744644794418e-05, "loss": 4.3247, "step": 6425 }, { "epoch": 0.19627367135003054, "grad_norm": 0.37615448236465454, "learning_rate": 4.5396059322505916e-05, "loss": 4.3055, "step": 6426 }, { "epoch": 0.19630421502748932, "grad_norm": 0.3743390440940857, "learning_rate": 4.5394672009270644e-05, "loss": 4.4435, "step": 6427 }, { "epoch": 0.19633475870494807, "grad_norm": 0.37738674879074097, "learning_rate": 4.539328450825114e-05, "loss": 4.455, "step": 6428 }, { "epoch": 0.19636530238240685, "grad_norm": 0.3943881392478943, "learning_rate": 4.539189681946018e-05, "loss": 4.3652, "step": 6429 }, { "epoch": 0.1963958460598656, "grad_norm": 0.38278496265411377, "learning_rate": 4.5390508942910545e-05, "loss": 4.3481, "step": 6430 }, { "epoch": 0.19642638973732438, "grad_norm": 0.3855501115322113, "learning_rate": 4.538912087861501e-05, "loss": 4.3137, "step": 6431 }, { "epoch": 0.19645693341478315, "grad_norm": 0.3922938108444214, "learning_rate": 4.538773262658634e-05, "loss": 4.4057, "step": 6432 }, { "epoch": 0.1964874770922419, "grad_norm": 0.3797539174556732, "learning_rate": 4.538634418683735e-05, "loss": 4.3734, "step": 6433 }, { "epoch": 0.19651802076970068, "grad_norm": 0.3796371519565582, "learning_rate": 4.538495555938081e-05, "loss": 4.4746, "step": 6434 }, { "epoch": 0.19654856444715943, "grad_norm": 0.3748513162136078, "learning_rate": 4.53835667442295e-05, "loss": 4.3479, "step": 6435 }, { "epoch": 0.1965791081246182, "grad_norm": 0.3949018120765686, "learning_rate": 4.538217774139621e-05, "loss": 4.3112, "step": 6436 }, { "epoch": 0.19660965180207696, "grad_norm": 0.3922695815563202, "learning_rate": 4.538078855089373e-05, "loss": 4.367, "step": 6437 }, { "epoch": 0.19664019547953573, "grad_norm": 0.38446372747421265, "learning_rate": 4.5379399172734845e-05, "loss": 4.3094, "step": 6438 }, { "epoch": 0.1966707391569945, "grad_norm": 0.37508702278137207, "learning_rate": 4.537800960693236e-05, "loss": 4.3404, "step": 6439 }, { "epoch": 0.19670128283445326, "grad_norm": 0.36988842487335205, "learning_rate": 4.5376619853499055e-05, "loss": 4.3607, "step": 6440 }, { "epoch": 0.19673182651191204, "grad_norm": 0.3907703757286072, "learning_rate": 4.537522991244774e-05, "loss": 4.3785, "step": 6441 }, { "epoch": 0.1967623701893708, "grad_norm": 0.38244688510894775, "learning_rate": 4.5373839783791213e-05, "loss": 4.4161, "step": 6442 }, { "epoch": 0.19679291386682957, "grad_norm": 0.40009331703186035, "learning_rate": 4.537244946754226e-05, "loss": 4.3516, "step": 6443 }, { "epoch": 0.19682345754428834, "grad_norm": 0.3854966461658478, "learning_rate": 4.5371058963713696e-05, "loss": 4.2743, "step": 6444 }, { "epoch": 0.1968540012217471, "grad_norm": 0.3755997121334076, "learning_rate": 4.5369668272318314e-05, "loss": 4.4014, "step": 6445 }, { "epoch": 0.19688454489920587, "grad_norm": 0.36980724334716797, "learning_rate": 4.5368277393368925e-05, "loss": 4.4283, "step": 6446 }, { "epoch": 0.19691508857666462, "grad_norm": 0.3822985887527466, "learning_rate": 4.536688632687833e-05, "loss": 4.3439, "step": 6447 }, { "epoch": 0.1969456322541234, "grad_norm": 0.3938159644603729, "learning_rate": 4.5365495072859346e-05, "loss": 4.4027, "step": 6448 }, { "epoch": 0.19697617593158218, "grad_norm": 0.3842093050479889, "learning_rate": 4.5364103631324775e-05, "loss": 4.2845, "step": 6449 }, { "epoch": 0.19700671960904093, "grad_norm": 0.37074175477027893, "learning_rate": 4.536271200228744e-05, "loss": 4.3947, "step": 6450 }, { "epoch": 0.1970372632864997, "grad_norm": 0.42092186212539673, "learning_rate": 4.5361320185760136e-05, "loss": 4.4164, "step": 6451 }, { "epoch": 0.19706780696395845, "grad_norm": 0.3891981244087219, "learning_rate": 4.5359928181755695e-05, "loss": 4.3842, "step": 6452 }, { "epoch": 0.19709835064141723, "grad_norm": 0.3905564546585083, "learning_rate": 4.535853599028692e-05, "loss": 4.4041, "step": 6453 }, { "epoch": 0.19712889431887598, "grad_norm": 0.38192448019981384, "learning_rate": 4.5357143611366634e-05, "loss": 4.4016, "step": 6454 }, { "epoch": 0.19715943799633476, "grad_norm": 0.39491361379623413, "learning_rate": 4.5355751045007675e-05, "loss": 4.3392, "step": 6455 }, { "epoch": 0.19718998167379354, "grad_norm": 0.37142467498779297, "learning_rate": 4.535435829122284e-05, "loss": 4.4184, "step": 6456 }, { "epoch": 0.19722052535125228, "grad_norm": 0.37180402874946594, "learning_rate": 4.535296535002497e-05, "loss": 4.384, "step": 6457 }, { "epoch": 0.19725106902871106, "grad_norm": 0.3812692165374756, "learning_rate": 4.535157222142687e-05, "loss": 4.4566, "step": 6458 }, { "epoch": 0.1972816127061698, "grad_norm": 0.3782108426094055, "learning_rate": 4.535017890544139e-05, "loss": 4.3532, "step": 6459 }, { "epoch": 0.1973121563836286, "grad_norm": 0.38287290930747986, "learning_rate": 4.534878540208135e-05, "loss": 4.3617, "step": 6460 }, { "epoch": 0.19734270006108737, "grad_norm": 0.3824610412120819, "learning_rate": 4.5347391711359575e-05, "loss": 4.3244, "step": 6461 }, { "epoch": 0.19737324373854612, "grad_norm": 0.3690340518951416, "learning_rate": 4.534599783328891e-05, "loss": 4.3786, "step": 6462 }, { "epoch": 0.1974037874160049, "grad_norm": 0.3780086040496826, "learning_rate": 4.5344603767882185e-05, "loss": 4.3225, "step": 6463 }, { "epoch": 0.19743433109346364, "grad_norm": 0.3707115650177002, "learning_rate": 4.534320951515223e-05, "loss": 4.3765, "step": 6464 }, { "epoch": 0.19746487477092242, "grad_norm": 0.38928139209747314, "learning_rate": 4.534181507511188e-05, "loss": 4.3613, "step": 6465 }, { "epoch": 0.19749541844838117, "grad_norm": 0.3669370114803314, "learning_rate": 4.5340420447773985e-05, "loss": 4.291, "step": 6466 }, { "epoch": 0.19752596212583995, "grad_norm": 0.3819655478000641, "learning_rate": 4.533902563315138e-05, "loss": 4.369, "step": 6467 }, { "epoch": 0.19755650580329873, "grad_norm": 0.3777024745941162, "learning_rate": 4.53376306312569e-05, "loss": 4.4557, "step": 6468 }, { "epoch": 0.19758704948075748, "grad_norm": 0.3841567039489746, "learning_rate": 4.533623544210341e-05, "loss": 4.3781, "step": 6469 }, { "epoch": 0.19761759315821625, "grad_norm": 0.36915892362594604, "learning_rate": 4.5334840065703744e-05, "loss": 4.3383, "step": 6470 }, { "epoch": 0.197648136835675, "grad_norm": 0.382188081741333, "learning_rate": 4.5333444502070745e-05, "loss": 4.333, "step": 6471 }, { "epoch": 0.19767868051313378, "grad_norm": 0.3855147063732147, "learning_rate": 4.533204875121727e-05, "loss": 4.3646, "step": 6472 }, { "epoch": 0.19770922419059256, "grad_norm": 0.38609442114830017, "learning_rate": 4.533065281315617e-05, "loss": 4.2979, "step": 6473 }, { "epoch": 0.1977397678680513, "grad_norm": 0.4086572527885437, "learning_rate": 4.532925668790029e-05, "loss": 4.4038, "step": 6474 }, { "epoch": 0.19777031154551009, "grad_norm": 0.3797316253185272, "learning_rate": 4.532786037546249e-05, "loss": 4.3199, "step": 6475 }, { "epoch": 0.19780085522296884, "grad_norm": 0.37646108865737915, "learning_rate": 4.532646387585564e-05, "loss": 4.4551, "step": 6476 }, { "epoch": 0.1978313989004276, "grad_norm": 0.38819417357444763, "learning_rate": 4.532506718909258e-05, "loss": 4.3565, "step": 6477 }, { "epoch": 0.1978619425778864, "grad_norm": 0.3924347460269928, "learning_rate": 4.5323670315186176e-05, "loss": 4.3855, "step": 6478 }, { "epoch": 0.19789248625534514, "grad_norm": 0.38979393243789673, "learning_rate": 4.532227325414929e-05, "loss": 4.3315, "step": 6479 }, { "epoch": 0.19792302993280392, "grad_norm": 0.3891661763191223, "learning_rate": 4.532087600599479e-05, "loss": 4.3695, "step": 6480 }, { "epoch": 0.19795357361026267, "grad_norm": 0.3805835247039795, "learning_rate": 4.531947857073553e-05, "loss": 4.3742, "step": 6481 }, { "epoch": 0.19798411728772145, "grad_norm": 0.3934665322303772, "learning_rate": 4.531808094838439e-05, "loss": 4.3906, "step": 6482 }, { "epoch": 0.1980146609651802, "grad_norm": 0.38514378666877747, "learning_rate": 4.531668313895423e-05, "loss": 4.399, "step": 6483 }, { "epoch": 0.19804520464263897, "grad_norm": 0.38124531507492065, "learning_rate": 4.531528514245792e-05, "loss": 4.4232, "step": 6484 }, { "epoch": 0.19807574832009775, "grad_norm": 0.3742673397064209, "learning_rate": 4.5313886958908336e-05, "loss": 4.4128, "step": 6485 }, { "epoch": 0.1981062919975565, "grad_norm": 0.39291784167289734, "learning_rate": 4.5312488588318345e-05, "loss": 4.4318, "step": 6486 }, { "epoch": 0.19813683567501528, "grad_norm": 0.37212714552879333, "learning_rate": 4.531109003070083e-05, "loss": 4.3387, "step": 6487 }, { "epoch": 0.19816737935247403, "grad_norm": 0.3768979012966156, "learning_rate": 4.5309691286068674e-05, "loss": 4.302, "step": 6488 }, { "epoch": 0.1981979230299328, "grad_norm": 0.3789615333080292, "learning_rate": 4.530829235443474e-05, "loss": 4.3609, "step": 6489 }, { "epoch": 0.19822846670739158, "grad_norm": 0.3857806622982025, "learning_rate": 4.530689323581192e-05, "loss": 4.3609, "step": 6490 }, { "epoch": 0.19825901038485033, "grad_norm": 0.3752036690711975, "learning_rate": 4.5305493930213097e-05, "loss": 4.4112, "step": 6491 }, { "epoch": 0.1982895540623091, "grad_norm": 0.3808744251728058, "learning_rate": 4.5304094437651145e-05, "loss": 4.2564, "step": 6492 }, { "epoch": 0.19832009773976786, "grad_norm": 0.389994353055954, "learning_rate": 4.5302694758138967e-05, "loss": 4.3478, "step": 6493 }, { "epoch": 0.19835064141722664, "grad_norm": 0.38323646783828735, "learning_rate": 4.530129489168943e-05, "loss": 4.3942, "step": 6494 }, { "epoch": 0.1983811850946854, "grad_norm": 0.37192168831825256, "learning_rate": 4.5299894838315426e-05, "loss": 4.4019, "step": 6495 }, { "epoch": 0.19841172877214416, "grad_norm": 0.3883044123649597, "learning_rate": 4.529849459802986e-05, "loss": 4.4287, "step": 6496 }, { "epoch": 0.19844227244960294, "grad_norm": 0.3703518807888031, "learning_rate": 4.5297094170845625e-05, "loss": 4.3641, "step": 6497 }, { "epoch": 0.1984728161270617, "grad_norm": 0.38433289527893066, "learning_rate": 4.52956935567756e-05, "loss": 4.3753, "step": 6498 }, { "epoch": 0.19850335980452047, "grad_norm": 0.3866836726665497, "learning_rate": 4.529429275583269e-05, "loss": 4.3602, "step": 6499 }, { "epoch": 0.19853390348197922, "grad_norm": 0.3839622139930725, "learning_rate": 4.52928917680298e-05, "loss": 4.4296, "step": 6500 }, { "epoch": 0.198564447159438, "grad_norm": 0.4057130813598633, "learning_rate": 4.5291490593379815e-05, "loss": 4.4134, "step": 6501 }, { "epoch": 0.19859499083689677, "grad_norm": 0.37654316425323486, "learning_rate": 4.5290089231895644e-05, "loss": 4.3393, "step": 6502 }, { "epoch": 0.19862553451435552, "grad_norm": 0.3794741630554199, "learning_rate": 4.528868768359019e-05, "loss": 4.3665, "step": 6503 }, { "epoch": 0.1986560781918143, "grad_norm": 0.39167577028274536, "learning_rate": 4.528728594847635e-05, "loss": 4.4029, "step": 6504 }, { "epoch": 0.19868662186927305, "grad_norm": 0.397073894739151, "learning_rate": 4.528588402656705e-05, "loss": 4.2855, "step": 6505 }, { "epoch": 0.19871716554673183, "grad_norm": 0.3749995529651642, "learning_rate": 4.528448191787518e-05, "loss": 4.3131, "step": 6506 }, { "epoch": 0.1987477092241906, "grad_norm": 0.388698935508728, "learning_rate": 4.528307962241366e-05, "loss": 4.3849, "step": 6507 }, { "epoch": 0.19877825290164935, "grad_norm": 0.40466275811195374, "learning_rate": 4.528167714019539e-05, "loss": 4.4709, "step": 6508 }, { "epoch": 0.19880879657910813, "grad_norm": 0.3812762200832367, "learning_rate": 4.52802744712333e-05, "loss": 4.3269, "step": 6509 }, { "epoch": 0.19883934025656688, "grad_norm": 0.3818407654762268, "learning_rate": 4.5278871615540285e-05, "loss": 4.3922, "step": 6510 }, { "epoch": 0.19886988393402566, "grad_norm": 0.3755342662334442, "learning_rate": 4.527746857312928e-05, "loss": 4.4076, "step": 6511 }, { "epoch": 0.1989004276114844, "grad_norm": 0.3929102420806885, "learning_rate": 4.52760653440132e-05, "loss": 4.3877, "step": 6512 }, { "epoch": 0.1989309712889432, "grad_norm": 0.40025049448013306, "learning_rate": 4.527466192820495e-05, "loss": 4.3895, "step": 6513 }, { "epoch": 0.19896151496640196, "grad_norm": 0.3917146921157837, "learning_rate": 4.5273258325717464e-05, "loss": 4.4351, "step": 6514 }, { "epoch": 0.19899205864386071, "grad_norm": 0.3750517666339874, "learning_rate": 4.5271854536563676e-05, "loss": 4.3411, "step": 6515 }, { "epoch": 0.1990226023213195, "grad_norm": 0.38439232110977173, "learning_rate": 4.5270450560756495e-05, "loss": 4.3091, "step": 6516 }, { "epoch": 0.19905314599877824, "grad_norm": 0.3824501037597656, "learning_rate": 4.526904639830885e-05, "loss": 4.407, "step": 6517 }, { "epoch": 0.19908368967623702, "grad_norm": 0.38575851917266846, "learning_rate": 4.5267642049233677e-05, "loss": 4.3436, "step": 6518 }, { "epoch": 0.1991142333536958, "grad_norm": 0.3953336179256439, "learning_rate": 4.52662375135439e-05, "loss": 4.3928, "step": 6519 }, { "epoch": 0.19914477703115455, "grad_norm": 0.37654516100883484, "learning_rate": 4.526483279125246e-05, "loss": 4.344, "step": 6520 }, { "epoch": 0.19917532070861332, "grad_norm": 0.38908132910728455, "learning_rate": 4.526342788237228e-05, "loss": 4.3357, "step": 6521 }, { "epoch": 0.19920586438607207, "grad_norm": 0.38686975836753845, "learning_rate": 4.52620227869163e-05, "loss": 4.2531, "step": 6522 }, { "epoch": 0.19923640806353085, "grad_norm": 0.39225661754608154, "learning_rate": 4.526061750489746e-05, "loss": 4.4121, "step": 6523 }, { "epoch": 0.19926695174098963, "grad_norm": 0.38470184803009033, "learning_rate": 4.52592120363287e-05, "loss": 4.4233, "step": 6524 }, { "epoch": 0.19929749541844838, "grad_norm": 0.3859160840511322, "learning_rate": 4.525780638122297e-05, "loss": 4.3595, "step": 6525 }, { "epoch": 0.19932803909590716, "grad_norm": 0.3724077641963959, "learning_rate": 4.525640053959318e-05, "loss": 4.3528, "step": 6526 }, { "epoch": 0.1993585827733659, "grad_norm": 0.38118404150009155, "learning_rate": 4.525499451145231e-05, "loss": 4.3407, "step": 6527 }, { "epoch": 0.19938912645082468, "grad_norm": 0.3881205916404724, "learning_rate": 4.5253588296813284e-05, "loss": 4.3766, "step": 6528 }, { "epoch": 0.19941967012828343, "grad_norm": 0.3836633563041687, "learning_rate": 4.525218189568906e-05, "loss": 4.4724, "step": 6529 }, { "epoch": 0.1994502138057422, "grad_norm": 0.39395999908447266, "learning_rate": 4.5250775308092584e-05, "loss": 4.4872, "step": 6530 }, { "epoch": 0.199480757483201, "grad_norm": 0.37858283519744873, "learning_rate": 4.5249368534036804e-05, "loss": 4.3758, "step": 6531 }, { "epoch": 0.19951130116065974, "grad_norm": 0.39643028378486633, "learning_rate": 4.524796157353468e-05, "loss": 4.1984, "step": 6532 }, { "epoch": 0.19954184483811852, "grad_norm": 0.3850492238998413, "learning_rate": 4.524655442659916e-05, "loss": 4.3711, "step": 6533 }, { "epoch": 0.19957238851557726, "grad_norm": 0.37699636816978455, "learning_rate": 4.524514709324321e-05, "loss": 4.3316, "step": 6534 }, { "epoch": 0.19960293219303604, "grad_norm": 0.38083505630493164, "learning_rate": 4.524373957347978e-05, "loss": 4.3381, "step": 6535 }, { "epoch": 0.19963347587049482, "grad_norm": 0.3909952938556671, "learning_rate": 4.5242331867321836e-05, "loss": 4.4033, "step": 6536 }, { "epoch": 0.19966401954795357, "grad_norm": 0.3904511332511902, "learning_rate": 4.5240923974782326e-05, "loss": 4.3989, "step": 6537 }, { "epoch": 0.19969456322541235, "grad_norm": 0.3713643252849579, "learning_rate": 4.523951589587423e-05, "loss": 4.404, "step": 6538 }, { "epoch": 0.1997251069028711, "grad_norm": 0.40206238627433777, "learning_rate": 4.52381076306105e-05, "loss": 4.3864, "step": 6539 }, { "epoch": 0.19975565058032987, "grad_norm": 0.3841652274131775, "learning_rate": 4.523669917900411e-05, "loss": 4.2639, "step": 6540 }, { "epoch": 0.19978619425778862, "grad_norm": 0.3967689275741577, "learning_rate": 4.523529054106802e-05, "loss": 4.3705, "step": 6541 }, { "epoch": 0.1998167379352474, "grad_norm": 0.3839797377586365, "learning_rate": 4.5233881716815207e-05, "loss": 4.3909, "step": 6542 }, { "epoch": 0.19984728161270618, "grad_norm": 0.3815070688724518, "learning_rate": 4.523247270625864e-05, "loss": 4.442, "step": 6543 }, { "epoch": 0.19987782529016493, "grad_norm": 0.37221992015838623, "learning_rate": 4.523106350941131e-05, "loss": 4.3684, "step": 6544 }, { "epoch": 0.1999083689676237, "grad_norm": 0.3818424940109253, "learning_rate": 4.522965412628616e-05, "loss": 4.3311, "step": 6545 }, { "epoch": 0.19993891264508246, "grad_norm": 0.39134544134140015, "learning_rate": 4.522824455689619e-05, "loss": 4.4226, "step": 6546 }, { "epoch": 0.19996945632254123, "grad_norm": 0.39644941687583923, "learning_rate": 4.522683480125437e-05, "loss": 4.3962, "step": 6547 }, { "epoch": 0.2, "grad_norm": 0.3760039806365967, "learning_rate": 4.522542485937369e-05, "loss": 4.3945, "step": 6548 }, { "epoch": 0.20003054367745876, "grad_norm": 0.3873273730278015, "learning_rate": 4.5224014731267116e-05, "loss": 4.3208, "step": 6549 }, { "epoch": 0.20006108735491754, "grad_norm": 0.40331923961639404, "learning_rate": 4.5222604416947646e-05, "loss": 4.4481, "step": 6550 }, { "epoch": 0.2000916310323763, "grad_norm": 0.373126745223999, "learning_rate": 4.522119391642825e-05, "loss": 4.388, "step": 6551 }, { "epoch": 0.20012217470983507, "grad_norm": 0.39044585824012756, "learning_rate": 4.521978322972193e-05, "loss": 4.4091, "step": 6552 }, { "epoch": 0.20015271838729384, "grad_norm": 0.3711497187614441, "learning_rate": 4.5218372356841676e-05, "loss": 4.3957, "step": 6553 }, { "epoch": 0.2001832620647526, "grad_norm": 0.37892404198646545, "learning_rate": 4.5216961297800465e-05, "loss": 4.3324, "step": 6554 }, { "epoch": 0.20021380574221137, "grad_norm": 0.3983915150165558, "learning_rate": 4.52155500526113e-05, "loss": 4.3845, "step": 6555 }, { "epoch": 0.20024434941967012, "grad_norm": 0.3814716041088104, "learning_rate": 4.521413862128717e-05, "loss": 4.4714, "step": 6556 }, { "epoch": 0.2002748930971289, "grad_norm": 0.3892207741737366, "learning_rate": 4.521272700384107e-05, "loss": 4.4301, "step": 6557 }, { "epoch": 0.20030543677458765, "grad_norm": 0.3744385540485382, "learning_rate": 4.521131520028601e-05, "loss": 4.3736, "step": 6558 }, { "epoch": 0.20033598045204642, "grad_norm": 0.38033705949783325, "learning_rate": 4.5209903210634967e-05, "loss": 4.409, "step": 6559 }, { "epoch": 0.2003665241295052, "grad_norm": 0.38692590594291687, "learning_rate": 4.5208491034900964e-05, "loss": 4.3286, "step": 6560 }, { "epoch": 0.20039706780696395, "grad_norm": 0.3759671449661255, "learning_rate": 4.520707867309699e-05, "loss": 4.3833, "step": 6561 }, { "epoch": 0.20042761148442273, "grad_norm": 0.40006089210510254, "learning_rate": 4.520566612523605e-05, "loss": 4.3353, "step": 6562 }, { "epoch": 0.20045815516188148, "grad_norm": 0.3795979917049408, "learning_rate": 4.520425339133116e-05, "loss": 4.3862, "step": 6563 }, { "epoch": 0.20048869883934026, "grad_norm": 0.38200685381889343, "learning_rate": 4.520284047139531e-05, "loss": 4.4042, "step": 6564 }, { "epoch": 0.20051924251679903, "grad_norm": 0.3669901490211487, "learning_rate": 4.5201427365441534e-05, "loss": 4.3704, "step": 6565 }, { "epoch": 0.20054978619425778, "grad_norm": 0.3734855353832245, "learning_rate": 4.5200014073482825e-05, "loss": 4.4169, "step": 6566 }, { "epoch": 0.20058032987171656, "grad_norm": 0.3704136312007904, "learning_rate": 4.51986005955322e-05, "loss": 4.1929, "step": 6567 }, { "epoch": 0.2006108735491753, "grad_norm": 0.37518560886383057, "learning_rate": 4.519718693160268e-05, "loss": 4.2724, "step": 6568 }, { "epoch": 0.2006414172266341, "grad_norm": 0.3685116469860077, "learning_rate": 4.519577308170726e-05, "loss": 4.3987, "step": 6569 }, { "epoch": 0.20067196090409287, "grad_norm": 0.39072829484939575, "learning_rate": 4.5194359045858984e-05, "loss": 4.3325, "step": 6570 }, { "epoch": 0.20070250458155162, "grad_norm": 0.38018497824668884, "learning_rate": 4.519294482407086e-05, "loss": 4.4571, "step": 6571 }, { "epoch": 0.2007330482590104, "grad_norm": 0.37733545899391174, "learning_rate": 4.519153041635591e-05, "loss": 4.3764, "step": 6572 }, { "epoch": 0.20076359193646914, "grad_norm": 0.39818206429481506, "learning_rate": 4.519011582272716e-05, "loss": 4.3941, "step": 6573 }, { "epoch": 0.20079413561392792, "grad_norm": 0.37788891792297363, "learning_rate": 4.5188701043197636e-05, "loss": 4.3522, "step": 6574 }, { "epoch": 0.20082467929138667, "grad_norm": 0.39155131578445435, "learning_rate": 4.5187286077780354e-05, "loss": 4.3823, "step": 6575 }, { "epoch": 0.20085522296884545, "grad_norm": 0.3878858685493469, "learning_rate": 4.518587092648835e-05, "loss": 4.465, "step": 6576 }, { "epoch": 0.20088576664630423, "grad_norm": 0.3790525496006012, "learning_rate": 4.5184455589334656e-05, "loss": 4.3522, "step": 6577 }, { "epoch": 0.20091631032376298, "grad_norm": 0.36352965235710144, "learning_rate": 4.51830400663323e-05, "loss": 4.4188, "step": 6578 }, { "epoch": 0.20094685400122175, "grad_norm": 0.37950727343559265, "learning_rate": 4.518162435749432e-05, "loss": 4.3042, "step": 6579 }, { "epoch": 0.2009773976786805, "grad_norm": 0.38002118468284607, "learning_rate": 4.518020846283375e-05, "loss": 4.4439, "step": 6580 }, { "epoch": 0.20100794135613928, "grad_norm": 0.38895148038864136, "learning_rate": 4.517879238236362e-05, "loss": 4.4125, "step": 6581 }, { "epoch": 0.20103848503359806, "grad_norm": 0.37161123752593994, "learning_rate": 4.517737611609698e-05, "loss": 4.2025, "step": 6582 }, { "epoch": 0.2010690287110568, "grad_norm": 0.38176172971725464, "learning_rate": 4.5175959664046865e-05, "loss": 4.307, "step": 6583 }, { "epoch": 0.20109957238851559, "grad_norm": 0.3696669042110443, "learning_rate": 4.5174543026226305e-05, "loss": 4.3618, "step": 6584 }, { "epoch": 0.20113011606597433, "grad_norm": 0.3688143789768219, "learning_rate": 4.5173126202648364e-05, "loss": 4.2765, "step": 6585 }, { "epoch": 0.2011606597434331, "grad_norm": 0.3897705674171448, "learning_rate": 4.517170919332607e-05, "loss": 4.3557, "step": 6586 }, { "epoch": 0.20119120342089186, "grad_norm": 0.3879549205303192, "learning_rate": 4.517029199827249e-05, "loss": 4.3926, "step": 6587 }, { "epoch": 0.20122174709835064, "grad_norm": 0.3855804204940796, "learning_rate": 4.516887461750065e-05, "loss": 4.3852, "step": 6588 }, { "epoch": 0.20125229077580942, "grad_norm": 0.38236019015312195, "learning_rate": 4.516745705102362e-05, "loss": 4.3441, "step": 6589 }, { "epoch": 0.20128283445326817, "grad_norm": 0.3896971642971039, "learning_rate": 4.5166039298854434e-05, "loss": 4.3422, "step": 6590 }, { "epoch": 0.20131337813072694, "grad_norm": 0.3762684166431427, "learning_rate": 4.516462136100616e-05, "loss": 4.3997, "step": 6591 }, { "epoch": 0.2013439218081857, "grad_norm": 0.3768809735774994, "learning_rate": 4.516320323749186e-05, "loss": 4.3334, "step": 6592 }, { "epoch": 0.20137446548564447, "grad_norm": 0.3857104778289795, "learning_rate": 4.516178492832457e-05, "loss": 4.3007, "step": 6593 }, { "epoch": 0.20140500916310325, "grad_norm": 0.39837008714675903, "learning_rate": 4.5160366433517353e-05, "loss": 4.3081, "step": 6594 }, { "epoch": 0.201435552840562, "grad_norm": 0.38144463300704956, "learning_rate": 4.515894775308329e-05, "loss": 4.3127, "step": 6595 }, { "epoch": 0.20146609651802078, "grad_norm": 0.37964776158332825, "learning_rate": 4.5157528887035426e-05, "loss": 4.3701, "step": 6596 }, { "epoch": 0.20149664019547953, "grad_norm": 0.38340720534324646, "learning_rate": 4.515610983538683e-05, "loss": 4.3433, "step": 6597 }, { "epoch": 0.2015271838729383, "grad_norm": 0.37712985277175903, "learning_rate": 4.515469059815057e-05, "loss": 4.3583, "step": 6598 }, { "epoch": 0.20155772755039708, "grad_norm": 0.4040764570236206, "learning_rate": 4.5153271175339704e-05, "loss": 4.3213, "step": 6599 }, { "epoch": 0.20158827122785583, "grad_norm": 0.36530229449272156, "learning_rate": 4.515185156696732e-05, "loss": 4.3298, "step": 6600 }, { "epoch": 0.2016188149053146, "grad_norm": 0.38489478826522827, "learning_rate": 4.515043177304646e-05, "loss": 4.4057, "step": 6601 }, { "epoch": 0.20164935858277336, "grad_norm": 0.38641422986984253, "learning_rate": 4.514901179359023e-05, "loss": 4.3723, "step": 6602 }, { "epoch": 0.20167990226023214, "grad_norm": 0.3755445182323456, "learning_rate": 4.514759162861169e-05, "loss": 4.3492, "step": 6603 }, { "epoch": 0.20171044593769089, "grad_norm": 0.381683886051178, "learning_rate": 4.51461712781239e-05, "loss": 4.465, "step": 6604 }, { "epoch": 0.20174098961514966, "grad_norm": 0.3798746168613434, "learning_rate": 4.514475074213996e-05, "loss": 4.4102, "step": 6605 }, { "epoch": 0.20177153329260844, "grad_norm": 0.39328813552856445, "learning_rate": 4.5143330020672944e-05, "loss": 4.3514, "step": 6606 }, { "epoch": 0.2018020769700672, "grad_norm": 0.3664446473121643, "learning_rate": 4.514190911373594e-05, "loss": 4.2985, "step": 6607 }, { "epoch": 0.20183262064752597, "grad_norm": 0.3854987323284149, "learning_rate": 4.514048802134201e-05, "loss": 4.4107, "step": 6608 }, { "epoch": 0.20186316432498472, "grad_norm": 0.38892221450805664, "learning_rate": 4.5139066743504254e-05, "loss": 4.3849, "step": 6609 }, { "epoch": 0.2018937080024435, "grad_norm": 0.37952250242233276, "learning_rate": 4.513764528023576e-05, "loss": 4.4045, "step": 6610 }, { "epoch": 0.20192425167990227, "grad_norm": 0.38091081380844116, "learning_rate": 4.513622363154961e-05, "loss": 4.3785, "step": 6611 }, { "epoch": 0.20195479535736102, "grad_norm": 0.38027897477149963, "learning_rate": 4.513480179745889e-05, "loss": 4.3441, "step": 6612 }, { "epoch": 0.2019853390348198, "grad_norm": 0.3919437527656555, "learning_rate": 4.51333797779767e-05, "loss": 4.4091, "step": 6613 }, { "epoch": 0.20201588271227855, "grad_norm": 0.36929717659950256, "learning_rate": 4.513195757311614e-05, "loss": 4.4112, "step": 6614 }, { "epoch": 0.20204642638973733, "grad_norm": 0.37907442450523376, "learning_rate": 4.513053518289029e-05, "loss": 4.4175, "step": 6615 }, { "epoch": 0.20207697006719608, "grad_norm": 0.4025716483592987, "learning_rate": 4.5129112607312256e-05, "loss": 4.3788, "step": 6616 }, { "epoch": 0.20210751374465485, "grad_norm": 0.3716020882129669, "learning_rate": 4.5127689846395126e-05, "loss": 4.3488, "step": 6617 }, { "epoch": 0.20213805742211363, "grad_norm": 0.3663199841976166, "learning_rate": 4.512626690015201e-05, "loss": 4.2959, "step": 6618 }, { "epoch": 0.20216860109957238, "grad_norm": 0.37682440876960754, "learning_rate": 4.512484376859601e-05, "loss": 4.4232, "step": 6619 }, { "epoch": 0.20219914477703116, "grad_norm": 0.3739565312862396, "learning_rate": 4.5123420451740225e-05, "loss": 4.4309, "step": 6620 }, { "epoch": 0.2022296884544899, "grad_norm": 0.3752053380012512, "learning_rate": 4.5121996949597756e-05, "loss": 4.3416, "step": 6621 }, { "epoch": 0.2022602321319487, "grad_norm": 0.3912557363510132, "learning_rate": 4.512057326218172e-05, "loss": 4.4685, "step": 6622 }, { "epoch": 0.20229077580940746, "grad_norm": 0.38068556785583496, "learning_rate": 4.511914938950522e-05, "loss": 4.4441, "step": 6623 }, { "epoch": 0.2023213194868662, "grad_norm": 0.377683162689209, "learning_rate": 4.511772533158137e-05, "loss": 4.4223, "step": 6624 }, { "epoch": 0.202351863164325, "grad_norm": 0.38533830642700195, "learning_rate": 4.511630108842328e-05, "loss": 4.363, "step": 6625 }, { "epoch": 0.20238240684178374, "grad_norm": 0.38553932309150696, "learning_rate": 4.511487666004406e-05, "loss": 4.4148, "step": 6626 }, { "epoch": 0.20241295051924252, "grad_norm": 0.3721525967121124, "learning_rate": 4.5113452046456826e-05, "loss": 4.354, "step": 6627 }, { "epoch": 0.2024434941967013, "grad_norm": 0.3766971826553345, "learning_rate": 4.51120272476747e-05, "loss": 4.3556, "step": 6628 }, { "epoch": 0.20247403787416005, "grad_norm": 0.3854678273200989, "learning_rate": 4.51106022637108e-05, "loss": 4.3707, "step": 6629 }, { "epoch": 0.20250458155161882, "grad_norm": 0.3805990517139435, "learning_rate": 4.510917709457825e-05, "loss": 4.3833, "step": 6630 }, { "epoch": 0.20253512522907757, "grad_norm": 0.37471359968185425, "learning_rate": 4.510775174029016e-05, "loss": 4.4184, "step": 6631 }, { "epoch": 0.20256566890653635, "grad_norm": 0.38914331793785095, "learning_rate": 4.5106326200859664e-05, "loss": 4.4412, "step": 6632 }, { "epoch": 0.2025962125839951, "grad_norm": 0.3719627261161804, "learning_rate": 4.510490047629988e-05, "loss": 4.3544, "step": 6633 }, { "epoch": 0.20262675626145388, "grad_norm": 0.3810819983482361, "learning_rate": 4.510347456662395e-05, "loss": 4.4014, "step": 6634 }, { "epoch": 0.20265729993891266, "grad_norm": 0.3719702959060669, "learning_rate": 4.510204847184498e-05, "loss": 4.4063, "step": 6635 }, { "epoch": 0.2026878436163714, "grad_norm": 0.36931753158569336, "learning_rate": 4.510062219197613e-05, "loss": 4.3804, "step": 6636 }, { "epoch": 0.20271838729383018, "grad_norm": 0.3757176399230957, "learning_rate": 4.50991957270305e-05, "loss": 4.4149, "step": 6637 }, { "epoch": 0.20274893097128893, "grad_norm": 0.38373035192489624, "learning_rate": 4.509776907702126e-05, "loss": 4.3681, "step": 6638 }, { "epoch": 0.2027794746487477, "grad_norm": 0.38820815086364746, "learning_rate": 4.5096342241961506e-05, "loss": 4.3432, "step": 6639 }, { "epoch": 0.2028100183262065, "grad_norm": 0.38819700479507446, "learning_rate": 4.5094915221864406e-05, "loss": 4.3828, "step": 6640 }, { "epoch": 0.20284056200366524, "grad_norm": 0.3595496416091919, "learning_rate": 4.509348801674309e-05, "loss": 4.3368, "step": 6641 }, { "epoch": 0.20287110568112401, "grad_norm": 0.3858878016471863, "learning_rate": 4.509206062661071e-05, "loss": 4.389, "step": 6642 }, { "epoch": 0.20290164935858276, "grad_norm": 0.39561206102371216, "learning_rate": 4.509063305148038e-05, "loss": 4.2285, "step": 6643 }, { "epoch": 0.20293219303604154, "grad_norm": 0.3850754201412201, "learning_rate": 4.508920529136527e-05, "loss": 4.4555, "step": 6644 }, { "epoch": 0.20296273671350032, "grad_norm": 0.3837096393108368, "learning_rate": 4.5087777346278517e-05, "loss": 4.2692, "step": 6645 }, { "epoch": 0.20299328039095907, "grad_norm": 0.378202348947525, "learning_rate": 4.508634921623327e-05, "loss": 4.2984, "step": 6646 }, { "epoch": 0.20302382406841785, "grad_norm": 0.37479835748672485, "learning_rate": 4.508492090124268e-05, "loss": 4.3985, "step": 6647 }, { "epoch": 0.2030543677458766, "grad_norm": 0.3814903199672699, "learning_rate": 4.5083492401319895e-05, "loss": 4.4127, "step": 6648 }, { "epoch": 0.20308491142333537, "grad_norm": 0.37745922803878784, "learning_rate": 4.508206371647807e-05, "loss": 4.452, "step": 6649 }, { "epoch": 0.20311545510079412, "grad_norm": 0.36742010712623596, "learning_rate": 4.508063484673036e-05, "loss": 4.4221, "step": 6650 }, { "epoch": 0.2031459987782529, "grad_norm": 0.38428619503974915, "learning_rate": 4.507920579208992e-05, "loss": 4.3616, "step": 6651 }, { "epoch": 0.20317654245571168, "grad_norm": 0.3845733106136322, "learning_rate": 4.5077776552569904e-05, "loss": 4.316, "step": 6652 }, { "epoch": 0.20320708613317043, "grad_norm": 0.4213883578777313, "learning_rate": 4.5076347128183484e-05, "loss": 4.3728, "step": 6653 }, { "epoch": 0.2032376298106292, "grad_norm": 0.37725380063056946, "learning_rate": 4.5074917518943806e-05, "loss": 4.3602, "step": 6654 }, { "epoch": 0.20326817348808796, "grad_norm": 0.3789113163948059, "learning_rate": 4.507348772486405e-05, "loss": 4.4137, "step": 6655 }, { "epoch": 0.20329871716554673, "grad_norm": 0.3836890459060669, "learning_rate": 4.507205774595736e-05, "loss": 4.3092, "step": 6656 }, { "epoch": 0.2033292608430055, "grad_norm": 0.3936988413333893, "learning_rate": 4.5070627582236925e-05, "loss": 4.4281, "step": 6657 }, { "epoch": 0.20335980452046426, "grad_norm": 0.3960903584957123, "learning_rate": 4.5069197233715896e-05, "loss": 4.4108, "step": 6658 }, { "epoch": 0.20339034819792304, "grad_norm": 0.3844824433326721, "learning_rate": 4.5067766700407454e-05, "loss": 4.3596, "step": 6659 }, { "epoch": 0.2034208918753818, "grad_norm": 0.3793344795703888, "learning_rate": 4.506633598232476e-05, "loss": 4.4114, "step": 6660 }, { "epoch": 0.20345143555284056, "grad_norm": 0.4059494137763977, "learning_rate": 4.5064905079481e-05, "loss": 4.3364, "step": 6661 }, { "epoch": 0.20348197923029931, "grad_norm": 0.37946078181266785, "learning_rate": 4.5063473991889336e-05, "loss": 4.415, "step": 6662 }, { "epoch": 0.2035125229077581, "grad_norm": 0.37607964873313904, "learning_rate": 4.506204271956296e-05, "loss": 4.3092, "step": 6663 }, { "epoch": 0.20354306658521687, "grad_norm": 0.38370659947395325, "learning_rate": 4.5060611262515036e-05, "loss": 4.4345, "step": 6664 }, { "epoch": 0.20357361026267562, "grad_norm": 0.37171387672424316, "learning_rate": 4.5059179620758754e-05, "loss": 4.32, "step": 6665 }, { "epoch": 0.2036041539401344, "grad_norm": 2.1971473693847656, "learning_rate": 4.505774779430729e-05, "loss": 4.3856, "step": 6666 }, { "epoch": 0.20363469761759315, "grad_norm": 0.37969303131103516, "learning_rate": 4.505631578317383e-05, "loss": 4.3978, "step": 6667 }, { "epoch": 0.20366524129505192, "grad_norm": 0.3815217614173889, "learning_rate": 4.5054883587371556e-05, "loss": 4.3522, "step": 6668 }, { "epoch": 0.2036957849725107, "grad_norm": 0.3806360960006714, "learning_rate": 4.505345120691365e-05, "loss": 4.2931, "step": 6669 }, { "epoch": 0.20372632864996945, "grad_norm": 0.38390761613845825, "learning_rate": 4.505201864181332e-05, "loss": 4.362, "step": 6670 }, { "epoch": 0.20375687232742823, "grad_norm": 0.3956787586212158, "learning_rate": 4.505058589208374e-05, "loss": 4.4039, "step": 6671 }, { "epoch": 0.20378741600488698, "grad_norm": 0.37588921189308167, "learning_rate": 4.504915295773812e-05, "loss": 4.3719, "step": 6672 }, { "epoch": 0.20381795968234576, "grad_norm": 0.375267893075943, "learning_rate": 4.504771983878963e-05, "loss": 4.3769, "step": 6673 }, { "epoch": 0.20384850335980453, "grad_norm": 0.36669161915779114, "learning_rate": 4.504628653525147e-05, "loss": 4.2862, "step": 6674 }, { "epoch": 0.20387904703726328, "grad_norm": 0.3699110150337219, "learning_rate": 4.5044853047136846e-05, "loss": 4.4144, "step": 6675 }, { "epoch": 0.20390959071472206, "grad_norm": 0.396857351064682, "learning_rate": 4.504341937445895e-05, "loss": 4.4601, "step": 6676 }, { "epoch": 0.2039401343921808, "grad_norm": 0.3644106686115265, "learning_rate": 4.5041985517231e-05, "loss": 4.3875, "step": 6677 }, { "epoch": 0.2039706780696396, "grad_norm": 0.3857939541339874, "learning_rate": 4.504055147546617e-05, "loss": 4.4488, "step": 6678 }, { "epoch": 0.20400122174709834, "grad_norm": 0.3717113733291626, "learning_rate": 4.5039117249177686e-05, "loss": 4.3132, "step": 6679 }, { "epoch": 0.20403176542455712, "grad_norm": 0.38232624530792236, "learning_rate": 4.5037682838378745e-05, "loss": 4.3287, "step": 6680 }, { "epoch": 0.2040623091020159, "grad_norm": 0.37524279952049255, "learning_rate": 4.503624824308256e-05, "loss": 4.337, "step": 6681 }, { "epoch": 0.20409285277947464, "grad_norm": 0.3856392204761505, "learning_rate": 4.5034813463302336e-05, "loss": 4.4198, "step": 6682 }, { "epoch": 0.20412339645693342, "grad_norm": 0.3780060112476349, "learning_rate": 4.5033378499051275e-05, "loss": 4.3562, "step": 6683 }, { "epoch": 0.20415394013439217, "grad_norm": 0.3807491362094879, "learning_rate": 4.503194335034261e-05, "loss": 4.3072, "step": 6684 }, { "epoch": 0.20418448381185095, "grad_norm": 0.3840015232563019, "learning_rate": 4.5030508017189535e-05, "loss": 4.3822, "step": 6685 }, { "epoch": 0.20421502748930973, "grad_norm": 0.3868524432182312, "learning_rate": 4.5029072499605276e-05, "loss": 4.3979, "step": 6686 }, { "epoch": 0.20424557116676847, "grad_norm": 0.3799070715904236, "learning_rate": 4.5027636797603046e-05, "loss": 4.3789, "step": 6687 }, { "epoch": 0.20427611484422725, "grad_norm": 0.3882623314857483, "learning_rate": 4.502620091119607e-05, "loss": 4.2855, "step": 6688 }, { "epoch": 0.204306658521686, "grad_norm": 0.37838515639305115, "learning_rate": 4.502476484039757e-05, "loss": 4.3894, "step": 6689 }, { "epoch": 0.20433720219914478, "grad_norm": 0.38102057576179504, "learning_rate": 4.502332858522075e-05, "loss": 4.3117, "step": 6690 }, { "epoch": 0.20436774587660353, "grad_norm": 0.3859788179397583, "learning_rate": 4.5021892145678854e-05, "loss": 4.3949, "step": 6691 }, { "epoch": 0.2043982895540623, "grad_norm": 0.37433406710624695, "learning_rate": 4.502045552178511e-05, "loss": 4.4169, "step": 6692 }, { "epoch": 0.20442883323152108, "grad_norm": 0.3840698003768921, "learning_rate": 4.501901871355274e-05, "loss": 4.3569, "step": 6693 }, { "epoch": 0.20445937690897983, "grad_norm": 0.3840738534927368, "learning_rate": 4.501758172099496e-05, "loss": 4.2828, "step": 6694 }, { "epoch": 0.2044899205864386, "grad_norm": 0.3985194265842438, "learning_rate": 4.5016144544125025e-05, "loss": 4.3671, "step": 6695 }, { "epoch": 0.20452046426389736, "grad_norm": 0.37983083724975586, "learning_rate": 4.501470718295615e-05, "loss": 4.3806, "step": 6696 }, { "epoch": 0.20455100794135614, "grad_norm": 0.3897450268268585, "learning_rate": 4.5013269637501574e-05, "loss": 4.3523, "step": 6697 }, { "epoch": 0.20458155161881492, "grad_norm": 0.3887423872947693, "learning_rate": 4.501183190777454e-05, "loss": 4.4052, "step": 6698 }, { "epoch": 0.20461209529627367, "grad_norm": 0.40898266434669495, "learning_rate": 4.501039399378828e-05, "loss": 4.3117, "step": 6699 }, { "epoch": 0.20464263897373244, "grad_norm": 0.38920921087265015, "learning_rate": 4.500895589555603e-05, "loss": 4.3042, "step": 6700 }, { "epoch": 0.2046731826511912, "grad_norm": 0.38600432872772217, "learning_rate": 4.500751761309104e-05, "loss": 4.4113, "step": 6701 }, { "epoch": 0.20470372632864997, "grad_norm": 0.38291728496551514, "learning_rate": 4.500607914640655e-05, "loss": 4.3465, "step": 6702 }, { "epoch": 0.20473427000610875, "grad_norm": 0.3981982469558716, "learning_rate": 4.5004640495515794e-05, "loss": 4.3479, "step": 6703 }, { "epoch": 0.2047648136835675, "grad_norm": 0.387092649936676, "learning_rate": 4.500320166043203e-05, "loss": 4.3406, "step": 6704 }, { "epoch": 0.20479535736102628, "grad_norm": 0.3758310079574585, "learning_rate": 4.500176264116851e-05, "loss": 4.3569, "step": 6705 }, { "epoch": 0.20482590103848503, "grad_norm": 0.3854058086872101, "learning_rate": 4.500032343773847e-05, "loss": 4.371, "step": 6706 }, { "epoch": 0.2048564447159438, "grad_norm": 0.3704536557197571, "learning_rate": 4.499888405015517e-05, "loss": 4.3614, "step": 6707 }, { "epoch": 0.20488698839340255, "grad_norm": 0.49175024032592773, "learning_rate": 4.499744447843187e-05, "loss": 4.3454, "step": 6708 }, { "epoch": 0.20491753207086133, "grad_norm": 0.3868463933467865, "learning_rate": 4.499600472258181e-05, "loss": 4.3383, "step": 6709 }, { "epoch": 0.2049480757483201, "grad_norm": 0.3784193694591522, "learning_rate": 4.499456478261825e-05, "loss": 4.3835, "step": 6710 }, { "epoch": 0.20497861942577886, "grad_norm": 0.3958324193954468, "learning_rate": 4.499312465855446e-05, "loss": 4.3508, "step": 6711 }, { "epoch": 0.20500916310323763, "grad_norm": 0.37880563735961914, "learning_rate": 4.4991684350403694e-05, "loss": 4.3637, "step": 6712 }, { "epoch": 0.20503970678069638, "grad_norm": 0.39817479252815247, "learning_rate": 4.49902438581792e-05, "loss": 4.301, "step": 6713 }, { "epoch": 0.20507025045815516, "grad_norm": 0.3852537274360657, "learning_rate": 4.498880318189426e-05, "loss": 4.4518, "step": 6714 }, { "epoch": 0.20510079413561394, "grad_norm": 0.3696282207965851, "learning_rate": 4.498736232156213e-05, "loss": 4.3191, "step": 6715 }, { "epoch": 0.2051313378130727, "grad_norm": 0.38712751865386963, "learning_rate": 4.498592127719609e-05, "loss": 4.3688, "step": 6716 }, { "epoch": 0.20516188149053147, "grad_norm": 0.3727889955043793, "learning_rate": 4.498448004880938e-05, "loss": 4.4219, "step": 6717 }, { "epoch": 0.20519242516799022, "grad_norm": 0.3829730451107025, "learning_rate": 4.4983038636415295e-05, "loss": 4.3675, "step": 6718 }, { "epoch": 0.205222968845449, "grad_norm": 0.3742084503173828, "learning_rate": 4.49815970400271e-05, "loss": 4.3422, "step": 6719 }, { "epoch": 0.20525351252290777, "grad_norm": 0.3948827385902405, "learning_rate": 4.498015525965806e-05, "loss": 4.4017, "step": 6720 }, { "epoch": 0.20528405620036652, "grad_norm": 0.37901541590690613, "learning_rate": 4.4978713295321465e-05, "loss": 4.376, "step": 6721 }, { "epoch": 0.2053145998778253, "grad_norm": 0.3954245150089264, "learning_rate": 4.497727114703059e-05, "loss": 4.288, "step": 6722 }, { "epoch": 0.20534514355528405, "grad_norm": 0.38223448395729065, "learning_rate": 4.4975828814798696e-05, "loss": 4.3738, "step": 6723 }, { "epoch": 0.20537568723274283, "grad_norm": 0.389758825302124, "learning_rate": 4.497438629863908e-05, "loss": 4.3983, "step": 6724 }, { "epoch": 0.20540623091020158, "grad_norm": 0.3927246928215027, "learning_rate": 4.497294359856502e-05, "loss": 4.2636, "step": 6725 }, { "epoch": 0.20543677458766035, "grad_norm": 0.3846893310546875, "learning_rate": 4.49715007145898e-05, "loss": 4.4226, "step": 6726 }, { "epoch": 0.20546731826511913, "grad_norm": 0.37964287400245667, "learning_rate": 4.4970057646726705e-05, "loss": 4.3348, "step": 6727 }, { "epoch": 0.20549786194257788, "grad_norm": 0.3881772458553314, "learning_rate": 4.496861439498902e-05, "loss": 4.3341, "step": 6728 }, { "epoch": 0.20552840562003666, "grad_norm": 0.381579726934433, "learning_rate": 4.4967170959390035e-05, "loss": 4.5055, "step": 6729 }, { "epoch": 0.2055589492974954, "grad_norm": 0.39337071776390076, "learning_rate": 4.496572733994304e-05, "loss": 4.2714, "step": 6730 }, { "epoch": 0.20558949297495419, "grad_norm": 0.36771711707115173, "learning_rate": 4.496428353666133e-05, "loss": 4.3232, "step": 6731 }, { "epoch": 0.20562003665241296, "grad_norm": 0.39144864678382874, "learning_rate": 4.49628395495582e-05, "loss": 4.3422, "step": 6732 }, { "epoch": 0.2056505803298717, "grad_norm": 0.42113685607910156, "learning_rate": 4.496139537864694e-05, "loss": 4.3543, "step": 6733 }, { "epoch": 0.2056811240073305, "grad_norm": 0.38899025321006775, "learning_rate": 4.495995102394085e-05, "loss": 4.3027, "step": 6734 }, { "epoch": 0.20571166768478924, "grad_norm": 0.3864937126636505, "learning_rate": 4.4958506485453233e-05, "loss": 4.3971, "step": 6735 }, { "epoch": 0.20574221136224802, "grad_norm": 0.38151654601097107, "learning_rate": 4.495706176319738e-05, "loss": 4.3636, "step": 6736 }, { "epoch": 0.20577275503970677, "grad_norm": 0.3868406414985657, "learning_rate": 4.495561685718659e-05, "loss": 4.4607, "step": 6737 }, { "epoch": 0.20580329871716554, "grad_norm": 0.3837806284427643, "learning_rate": 4.495417176743419e-05, "loss": 4.3694, "step": 6738 }, { "epoch": 0.20583384239462432, "grad_norm": 0.3652885854244232, "learning_rate": 4.495272649395346e-05, "loss": 4.3432, "step": 6739 }, { "epoch": 0.20586438607208307, "grad_norm": 0.37571775913238525, "learning_rate": 4.495128103675773e-05, "loss": 4.4022, "step": 6740 }, { "epoch": 0.20589492974954185, "grad_norm": 0.38176044821739197, "learning_rate": 4.494983539586028e-05, "loss": 4.4045, "step": 6741 }, { "epoch": 0.2059254734270006, "grad_norm": 0.38173437118530273, "learning_rate": 4.4948389571274454e-05, "loss": 4.3082, "step": 6742 }, { "epoch": 0.20595601710445938, "grad_norm": 0.3856898844242096, "learning_rate": 4.494694356301354e-05, "loss": 4.3061, "step": 6743 }, { "epoch": 0.20598656078191815, "grad_norm": 0.3961508572101593, "learning_rate": 4.494549737109087e-05, "loss": 4.4819, "step": 6744 }, { "epoch": 0.2060171044593769, "grad_norm": 0.3770577311515808, "learning_rate": 4.4944050995519746e-05, "loss": 4.3327, "step": 6745 }, { "epoch": 0.20604764813683568, "grad_norm": 0.3825669586658478, "learning_rate": 4.494260443631349e-05, "loss": 4.3386, "step": 6746 }, { "epoch": 0.20607819181429443, "grad_norm": 0.3816249966621399, "learning_rate": 4.494115769348542e-05, "loss": 4.3999, "step": 6747 }, { "epoch": 0.2061087354917532, "grad_norm": 0.38305506110191345, "learning_rate": 4.493971076704886e-05, "loss": 4.3423, "step": 6748 }, { "epoch": 0.206139279169212, "grad_norm": 0.3943970799446106, "learning_rate": 4.493826365701713e-05, "loss": 4.3437, "step": 6749 }, { "epoch": 0.20616982284667074, "grad_norm": 0.3782045841217041, "learning_rate": 4.493681636340356e-05, "loss": 4.3731, "step": 6750 }, { "epoch": 0.2062003665241295, "grad_norm": 0.3935438096523285, "learning_rate": 4.4935368886221464e-05, "loss": 4.4323, "step": 6751 }, { "epoch": 0.20623091020158826, "grad_norm": 0.37847015261650085, "learning_rate": 4.493392122548418e-05, "loss": 4.3411, "step": 6752 }, { "epoch": 0.20626145387904704, "grad_norm": 0.376152902841568, "learning_rate": 4.493247338120503e-05, "loss": 4.2775, "step": 6753 }, { "epoch": 0.2062919975565058, "grad_norm": 0.3886082172393799, "learning_rate": 4.493102535339736e-05, "loss": 4.3924, "step": 6754 }, { "epoch": 0.20632254123396457, "grad_norm": 0.3727920949459076, "learning_rate": 4.4929577142074484e-05, "loss": 4.3892, "step": 6755 }, { "epoch": 0.20635308491142335, "grad_norm": 0.3837887644767761, "learning_rate": 4.4928128747249746e-05, "loss": 4.331, "step": 6756 }, { "epoch": 0.2063836285888821, "grad_norm": 0.3790915906429291, "learning_rate": 4.492668016893648e-05, "loss": 4.3947, "step": 6757 }, { "epoch": 0.20641417226634087, "grad_norm": 0.3811296820640564, "learning_rate": 4.492523140714803e-05, "loss": 4.4086, "step": 6758 }, { "epoch": 0.20644471594379962, "grad_norm": 0.38610926270484924, "learning_rate": 4.492378246189772e-05, "loss": 4.3254, "step": 6759 }, { "epoch": 0.2064752596212584, "grad_norm": 0.38378357887268066, "learning_rate": 4.492233333319891e-05, "loss": 4.3743, "step": 6760 }, { "epoch": 0.20650580329871718, "grad_norm": 0.38224127888679504, "learning_rate": 4.4920884021064925e-05, "loss": 4.365, "step": 6761 }, { "epoch": 0.20653634697617593, "grad_norm": 0.3767879605293274, "learning_rate": 4.491943452550913e-05, "loss": 4.401, "step": 6762 }, { "epoch": 0.2065668906536347, "grad_norm": 0.36967194080352783, "learning_rate": 4.491798484654485e-05, "loss": 4.3961, "step": 6763 }, { "epoch": 0.20659743433109345, "grad_norm": 0.3693285882472992, "learning_rate": 4.4916534984185446e-05, "loss": 4.362, "step": 6764 }, { "epoch": 0.20662797800855223, "grad_norm": 0.379219114780426, "learning_rate": 4.4915084938444264e-05, "loss": 4.3169, "step": 6765 }, { "epoch": 0.20665852168601098, "grad_norm": 0.38336849212646484, "learning_rate": 4.491363470933466e-05, "loss": 4.4047, "step": 6766 }, { "epoch": 0.20668906536346976, "grad_norm": 0.3964349329471588, "learning_rate": 4.4912184296869974e-05, "loss": 4.3431, "step": 6767 }, { "epoch": 0.20671960904092854, "grad_norm": 0.37775298953056335, "learning_rate": 4.491073370106358e-05, "loss": 4.4558, "step": 6768 }, { "epoch": 0.2067501527183873, "grad_norm": 0.3809986412525177, "learning_rate": 4.490928292192881e-05, "loss": 4.4279, "step": 6769 }, { "epoch": 0.20678069639584606, "grad_norm": 0.37910303473472595, "learning_rate": 4.4907831959479046e-05, "loss": 4.3126, "step": 6770 }, { "epoch": 0.20681124007330481, "grad_norm": 0.3767971396446228, "learning_rate": 4.490638081372764e-05, "loss": 4.3934, "step": 6771 }, { "epoch": 0.2068417837507636, "grad_norm": 0.37762731313705444, "learning_rate": 4.490492948468794e-05, "loss": 4.271, "step": 6772 }, { "epoch": 0.20687232742822237, "grad_norm": 0.3700612485408783, "learning_rate": 4.490347797237333e-05, "loss": 4.2969, "step": 6773 }, { "epoch": 0.20690287110568112, "grad_norm": 0.3748133182525635, "learning_rate": 4.490202627679716e-05, "loss": 4.3299, "step": 6774 }, { "epoch": 0.2069334147831399, "grad_norm": 0.3869541585445404, "learning_rate": 4.49005743979728e-05, "loss": 4.3537, "step": 6775 }, { "epoch": 0.20696395846059865, "grad_norm": 0.3806922733783722, "learning_rate": 4.489912233591362e-05, "loss": 4.3269, "step": 6776 }, { "epoch": 0.20699450213805742, "grad_norm": 0.37878596782684326, "learning_rate": 4.4897670090633e-05, "loss": 4.3349, "step": 6777 }, { "epoch": 0.2070250458155162, "grad_norm": 0.3833353519439697, "learning_rate": 4.489621766214429e-05, "loss": 4.3689, "step": 6778 }, { "epoch": 0.20705558949297495, "grad_norm": 0.3759971857070923, "learning_rate": 4.489476505046088e-05, "loss": 4.4074, "step": 6779 }, { "epoch": 0.20708613317043373, "grad_norm": 0.3758271634578705, "learning_rate": 4.4893312255596134e-05, "loss": 4.3773, "step": 6780 }, { "epoch": 0.20711667684789248, "grad_norm": 0.37755343317985535, "learning_rate": 4.4891859277563445e-05, "loss": 4.3985, "step": 6781 }, { "epoch": 0.20714722052535126, "grad_norm": 0.39060020446777344, "learning_rate": 4.489040611637616e-05, "loss": 4.4405, "step": 6782 }, { "epoch": 0.20717776420281, "grad_norm": 0.3723330497741699, "learning_rate": 4.48889527720477e-05, "loss": 4.3815, "step": 6783 }, { "epoch": 0.20720830788026878, "grad_norm": 0.3843698501586914, "learning_rate": 4.488749924459141e-05, "loss": 4.3883, "step": 6784 }, { "epoch": 0.20723885155772756, "grad_norm": 0.39182740449905396, "learning_rate": 4.48860455340207e-05, "loss": 4.4371, "step": 6785 }, { "epoch": 0.2072693952351863, "grad_norm": 0.37745919823646545, "learning_rate": 4.488459164034894e-05, "loss": 4.3581, "step": 6786 }, { "epoch": 0.2072999389126451, "grad_norm": 0.3767198324203491, "learning_rate": 4.4883137563589525e-05, "loss": 4.4479, "step": 6787 }, { "epoch": 0.20733048259010384, "grad_norm": 0.38641446828842163, "learning_rate": 4.4881683303755835e-05, "loss": 4.4006, "step": 6788 }, { "epoch": 0.20736102626756261, "grad_norm": 0.37592747807502747, "learning_rate": 4.488022886086126e-05, "loss": 4.3867, "step": 6789 }, { "epoch": 0.2073915699450214, "grad_norm": 0.38074979186058044, "learning_rate": 4.4878774234919204e-05, "loss": 4.402, "step": 6790 }, { "epoch": 0.20742211362248014, "grad_norm": 0.3739074766635895, "learning_rate": 4.487731942594306e-05, "loss": 4.3806, "step": 6791 }, { "epoch": 0.20745265729993892, "grad_norm": 0.3816525340080261, "learning_rate": 4.4875864433946204e-05, "loss": 4.4154, "step": 6792 }, { "epoch": 0.20748320097739767, "grad_norm": 0.3919471204280853, "learning_rate": 4.4874409258942054e-05, "loss": 4.3524, "step": 6793 }, { "epoch": 0.20751374465485645, "grad_norm": 0.39406514167785645, "learning_rate": 4.4872953900943986e-05, "loss": 4.4655, "step": 6794 }, { "epoch": 0.20754428833231522, "grad_norm": 0.36359903216362, "learning_rate": 4.487149835996543e-05, "loss": 4.3601, "step": 6795 }, { "epoch": 0.20757483200977397, "grad_norm": 0.3944893479347229, "learning_rate": 4.487004263601976e-05, "loss": 4.3689, "step": 6796 }, { "epoch": 0.20760537568723275, "grad_norm": 0.37635481357574463, "learning_rate": 4.4868586729120385e-05, "loss": 4.3304, "step": 6797 }, { "epoch": 0.2076359193646915, "grad_norm": 0.40904465317726135, "learning_rate": 4.486713063928073e-05, "loss": 4.3171, "step": 6798 }, { "epoch": 0.20766646304215028, "grad_norm": 0.3778882920742035, "learning_rate": 4.486567436651419e-05, "loss": 4.3538, "step": 6799 }, { "epoch": 0.20769700671960903, "grad_norm": 0.3684704601764679, "learning_rate": 4.486421791083417e-05, "loss": 4.371, "step": 6800 }, { "epoch": 0.2077275503970678, "grad_norm": 0.391075074672699, "learning_rate": 4.4862761272254075e-05, "loss": 4.4172, "step": 6801 }, { "epoch": 0.20775809407452658, "grad_norm": 0.3794844150543213, "learning_rate": 4.486130445078733e-05, "loss": 4.3576, "step": 6802 }, { "epoch": 0.20778863775198533, "grad_norm": 0.3810451030731201, "learning_rate": 4.4859847446447345e-05, "loss": 4.3651, "step": 6803 }, { "epoch": 0.2078191814294441, "grad_norm": 0.3761134445667267, "learning_rate": 4.485839025924753e-05, "loss": 4.3119, "step": 6804 }, { "epoch": 0.20784972510690286, "grad_norm": 0.3884481191635132, "learning_rate": 4.485693288920131e-05, "loss": 4.4824, "step": 6805 }, { "epoch": 0.20788026878436164, "grad_norm": 0.41816553473472595, "learning_rate": 4.485547533632209e-05, "loss": 4.4281, "step": 6806 }, { "epoch": 0.20791081246182042, "grad_norm": 0.37210196256637573, "learning_rate": 4.485401760062331e-05, "loss": 4.3345, "step": 6807 }, { "epoch": 0.20794135613927917, "grad_norm": 0.3746488690376282, "learning_rate": 4.4852559682118376e-05, "loss": 4.3303, "step": 6808 }, { "epoch": 0.20797189981673794, "grad_norm": 0.3838720917701721, "learning_rate": 4.485110158082072e-05, "loss": 4.3483, "step": 6809 }, { "epoch": 0.2080024434941967, "grad_norm": 0.3762653172016144, "learning_rate": 4.484964329674377e-05, "loss": 4.3718, "step": 6810 }, { "epoch": 0.20803298717165547, "grad_norm": 0.3796347975730896, "learning_rate": 4.484818482990094e-05, "loss": 4.3919, "step": 6811 }, { "epoch": 0.20806353084911422, "grad_norm": 0.373958557844162, "learning_rate": 4.484672618030568e-05, "loss": 4.2788, "step": 6812 }, { "epoch": 0.208094074526573, "grad_norm": 0.38316282629966736, "learning_rate": 4.484526734797139e-05, "loss": 4.3533, "step": 6813 }, { "epoch": 0.20812461820403177, "grad_norm": 0.3867934048175812, "learning_rate": 4.484380833291153e-05, "loss": 4.4044, "step": 6814 }, { "epoch": 0.20815516188149052, "grad_norm": 0.3934990167617798, "learning_rate": 4.484234913513953e-05, "loss": 4.3601, "step": 6815 }, { "epoch": 0.2081857055589493, "grad_norm": 0.37259525060653687, "learning_rate": 4.4840889754668805e-05, "loss": 4.4194, "step": 6816 }, { "epoch": 0.20821624923640805, "grad_norm": 0.3822293281555176, "learning_rate": 4.483943019151282e-05, "loss": 4.4095, "step": 6817 }, { "epoch": 0.20824679291386683, "grad_norm": 0.38209715485572815, "learning_rate": 4.4837970445685e-05, "loss": 4.3232, "step": 6818 }, { "epoch": 0.2082773365913256, "grad_norm": 0.38507896661758423, "learning_rate": 4.483651051719877e-05, "loss": 4.3236, "step": 6819 }, { "epoch": 0.20830788026878436, "grad_norm": 0.37145647406578064, "learning_rate": 4.4835050406067605e-05, "loss": 4.2609, "step": 6820 }, { "epoch": 0.20833842394624313, "grad_norm": 0.3720773756504059, "learning_rate": 4.483359011230493e-05, "loss": 4.4042, "step": 6821 }, { "epoch": 0.20836896762370188, "grad_norm": 0.3901122808456421, "learning_rate": 4.4832129635924195e-05, "loss": 4.3693, "step": 6822 }, { "epoch": 0.20839951130116066, "grad_norm": 0.38044309616088867, "learning_rate": 4.4830668976938836e-05, "loss": 4.3437, "step": 6823 }, { "epoch": 0.20843005497861944, "grad_norm": 0.38105228543281555, "learning_rate": 4.482920813536232e-05, "loss": 4.4436, "step": 6824 }, { "epoch": 0.2084605986560782, "grad_norm": 0.3874141573905945, "learning_rate": 4.482774711120809e-05, "loss": 4.3483, "step": 6825 }, { "epoch": 0.20849114233353697, "grad_norm": 0.3931618630886078, "learning_rate": 4.48262859044896e-05, "loss": 4.4146, "step": 6826 }, { "epoch": 0.20852168601099572, "grad_norm": 0.3847823441028595, "learning_rate": 4.482482451522029e-05, "loss": 4.3525, "step": 6827 }, { "epoch": 0.2085522296884545, "grad_norm": 0.3840641677379608, "learning_rate": 4.482336294341364e-05, "loss": 4.4236, "step": 6828 }, { "epoch": 0.20858277336591324, "grad_norm": 0.3788039982318878, "learning_rate": 4.482190118908309e-05, "loss": 4.2808, "step": 6829 }, { "epoch": 0.20861331704337202, "grad_norm": 0.37967151403427124, "learning_rate": 4.482043925224211e-05, "loss": 4.4326, "step": 6830 }, { "epoch": 0.2086438607208308, "grad_norm": 0.3946921229362488, "learning_rate": 4.481897713290414e-05, "loss": 4.3641, "step": 6831 }, { "epoch": 0.20867440439828955, "grad_norm": 0.37257131934165955, "learning_rate": 4.4817514831082674e-05, "loss": 4.3618, "step": 6832 }, { "epoch": 0.20870494807574833, "grad_norm": 0.388439804315567, "learning_rate": 4.4816052346791147e-05, "loss": 4.353, "step": 6833 }, { "epoch": 0.20873549175320708, "grad_norm": 0.3879040777683258, "learning_rate": 4.481458968004305e-05, "loss": 4.3895, "step": 6834 }, { "epoch": 0.20876603543066585, "grad_norm": 0.3863896429538727, "learning_rate": 4.481312683085184e-05, "loss": 4.2872, "step": 6835 }, { "epoch": 0.20879657910812463, "grad_norm": 0.3844464421272278, "learning_rate": 4.481166379923097e-05, "loss": 4.4137, "step": 6836 }, { "epoch": 0.20882712278558338, "grad_norm": 0.38697513937950134, "learning_rate": 4.481020058519393e-05, "loss": 4.3582, "step": 6837 }, { "epoch": 0.20885766646304216, "grad_norm": 0.3965260088443756, "learning_rate": 4.480873718875419e-05, "loss": 4.3648, "step": 6838 }, { "epoch": 0.2088882101405009, "grad_norm": 0.37218454480171204, "learning_rate": 4.480727360992522e-05, "loss": 4.3802, "step": 6839 }, { "epoch": 0.20891875381795968, "grad_norm": 0.38697266578674316, "learning_rate": 4.48058098487205e-05, "loss": 4.4489, "step": 6840 }, { "epoch": 0.20894929749541843, "grad_norm": 0.3784089982509613, "learning_rate": 4.480434590515351e-05, "loss": 4.3499, "step": 6841 }, { "epoch": 0.2089798411728772, "grad_norm": 0.38083988428115845, "learning_rate": 4.480288177923772e-05, "loss": 4.2689, "step": 6842 }, { "epoch": 0.209010384850336, "grad_norm": 0.3716978132724762, "learning_rate": 4.480141747098662e-05, "loss": 4.3202, "step": 6843 }, { "epoch": 0.20904092852779474, "grad_norm": 0.38080093264579773, "learning_rate": 4.479995298041369e-05, "loss": 4.3601, "step": 6844 }, { "epoch": 0.20907147220525352, "grad_norm": 0.39153653383255005, "learning_rate": 4.47984883075324e-05, "loss": 4.3846, "step": 6845 }, { "epoch": 0.20910201588271227, "grad_norm": 0.37991592288017273, "learning_rate": 4.479702345235626e-05, "loss": 4.3529, "step": 6846 }, { "epoch": 0.20913255956017104, "grad_norm": 0.382686585187912, "learning_rate": 4.479555841489874e-05, "loss": 4.373, "step": 6847 }, { "epoch": 0.20916310323762982, "grad_norm": 0.37934064865112305, "learning_rate": 4.479409319517334e-05, "loss": 4.3245, "step": 6848 }, { "epoch": 0.20919364691508857, "grad_norm": 0.38298287987709045, "learning_rate": 4.4792627793193544e-05, "loss": 4.4061, "step": 6849 }, { "epoch": 0.20922419059254735, "grad_norm": 0.39051908254623413, "learning_rate": 4.479116220897285e-05, "loss": 4.3468, "step": 6850 }, { "epoch": 0.2092547342700061, "grad_norm": 0.38798093795776367, "learning_rate": 4.4789696442524745e-05, "loss": 4.394, "step": 6851 }, { "epoch": 0.20928527794746488, "grad_norm": 0.3796584904193878, "learning_rate": 4.478823049386274e-05, "loss": 4.2997, "step": 6852 }, { "epoch": 0.20931582162492365, "grad_norm": 0.39825183153152466, "learning_rate": 4.478676436300031e-05, "loss": 4.3842, "step": 6853 }, { "epoch": 0.2093463653023824, "grad_norm": 0.3930568993091583, "learning_rate": 4.478529804995098e-05, "loss": 4.3425, "step": 6854 }, { "epoch": 0.20937690897984118, "grad_norm": 0.38728201389312744, "learning_rate": 4.478383155472823e-05, "loss": 4.3715, "step": 6855 }, { "epoch": 0.20940745265729993, "grad_norm": 0.3829840421676636, "learning_rate": 4.4782364877345575e-05, "loss": 4.4682, "step": 6856 }, { "epoch": 0.2094379963347587, "grad_norm": 0.3754340410232544, "learning_rate": 4.478089801781651e-05, "loss": 4.3697, "step": 6857 }, { "epoch": 0.20946854001221746, "grad_norm": 0.3738268315792084, "learning_rate": 4.477943097615456e-05, "loss": 4.16, "step": 6858 }, { "epoch": 0.20949908368967624, "grad_norm": 0.376179039478302, "learning_rate": 4.47779637523732e-05, "loss": 4.4277, "step": 6859 }, { "epoch": 0.209529627367135, "grad_norm": 0.3732030987739563, "learning_rate": 4.4776496346485966e-05, "loss": 4.3194, "step": 6860 }, { "epoch": 0.20956017104459376, "grad_norm": 0.381256639957428, "learning_rate": 4.477502875850637e-05, "loss": 4.4674, "step": 6861 }, { "epoch": 0.20959071472205254, "grad_norm": 0.4006280303001404, "learning_rate": 4.477356098844791e-05, "loss": 4.2916, "step": 6862 }, { "epoch": 0.2096212583995113, "grad_norm": 0.3721768856048584, "learning_rate": 4.477209303632411e-05, "loss": 4.3268, "step": 6863 }, { "epoch": 0.20965180207697007, "grad_norm": 0.3803441524505615, "learning_rate": 4.477062490214849e-05, "loss": 4.3593, "step": 6864 }, { "epoch": 0.20968234575442884, "grad_norm": 0.38758745789527893, "learning_rate": 4.4769156585934544e-05, "loss": 4.4619, "step": 6865 }, { "epoch": 0.2097128894318876, "grad_norm": 0.3878169655799866, "learning_rate": 4.4767688087695824e-05, "loss": 4.3704, "step": 6866 }, { "epoch": 0.20974343310934637, "grad_norm": 0.3811439275741577, "learning_rate": 4.476621940744583e-05, "loss": 4.3369, "step": 6867 }, { "epoch": 0.20977397678680512, "grad_norm": 0.37627336382865906, "learning_rate": 4.4764750545198095e-05, "loss": 4.4096, "step": 6868 }, { "epoch": 0.2098045204642639, "grad_norm": 0.3863586187362671, "learning_rate": 4.476328150096614e-05, "loss": 4.3911, "step": 6869 }, { "epoch": 0.20983506414172268, "grad_norm": 0.38302695751190186, "learning_rate": 4.476181227476348e-05, "loss": 4.4089, "step": 6870 }, { "epoch": 0.20986560781918143, "grad_norm": 0.3893939256668091, "learning_rate": 4.4760342866603664e-05, "loss": 4.4081, "step": 6871 }, { "epoch": 0.2098961514966402, "grad_norm": 0.37428703904151917, "learning_rate": 4.4758873276500206e-05, "loss": 4.345, "step": 6872 }, { "epoch": 0.20992669517409895, "grad_norm": 0.40137529373168945, "learning_rate": 4.4757403504466654e-05, "loss": 4.387, "step": 6873 }, { "epoch": 0.20995723885155773, "grad_norm": 0.37103894352912903, "learning_rate": 4.4755933550516514e-05, "loss": 4.2373, "step": 6874 }, { "epoch": 0.20998778252901648, "grad_norm": 0.3814537525177002, "learning_rate": 4.475446341466335e-05, "loss": 4.4143, "step": 6875 }, { "epoch": 0.21001832620647526, "grad_norm": 0.3759920597076416, "learning_rate": 4.475299309692068e-05, "loss": 4.1973, "step": 6876 }, { "epoch": 0.21004886988393404, "grad_norm": 0.3879978060722351, "learning_rate": 4.475152259730204e-05, "loss": 4.3591, "step": 6877 }, { "epoch": 0.21007941356139279, "grad_norm": 0.37315526604652405, "learning_rate": 4.4750051915820984e-05, "loss": 4.4432, "step": 6878 }, { "epoch": 0.21010995723885156, "grad_norm": 0.3889768421649933, "learning_rate": 4.474858105249105e-05, "loss": 4.3896, "step": 6879 }, { "epoch": 0.2101405009163103, "grad_norm": 0.3828710615634918, "learning_rate": 4.474711000732576e-05, "loss": 4.3533, "step": 6880 }, { "epoch": 0.2101710445937691, "grad_norm": 0.38841620087623596, "learning_rate": 4.474563878033869e-05, "loss": 4.4052, "step": 6881 }, { "epoch": 0.21020158827122787, "grad_norm": 0.37614378333091736, "learning_rate": 4.4744167371543366e-05, "loss": 4.412, "step": 6882 }, { "epoch": 0.21023213194868662, "grad_norm": 0.3794427514076233, "learning_rate": 4.474269578095334e-05, "loss": 4.3065, "step": 6883 }, { "epoch": 0.2102626756261454, "grad_norm": 0.37493282556533813, "learning_rate": 4.474122400858217e-05, "loss": 4.3525, "step": 6884 }, { "epoch": 0.21029321930360415, "grad_norm": 0.37519100308418274, "learning_rate": 4.47397520544434e-05, "loss": 4.3958, "step": 6885 }, { "epoch": 0.21032376298106292, "grad_norm": 0.3899987041950226, "learning_rate": 4.4738279918550576e-05, "loss": 4.3347, "step": 6886 }, { "epoch": 0.21035430665852167, "grad_norm": 0.3895268142223358, "learning_rate": 4.4736807600917266e-05, "loss": 4.4122, "step": 6887 }, { "epoch": 0.21038485033598045, "grad_norm": 0.37838730216026306, "learning_rate": 4.473533510155701e-05, "loss": 4.2641, "step": 6888 }, { "epoch": 0.21041539401343923, "grad_norm": 0.3774062693119049, "learning_rate": 4.473386242048338e-05, "loss": 4.3502, "step": 6889 }, { "epoch": 0.21044593769089798, "grad_norm": 0.38097813725471497, "learning_rate": 4.473238955770994e-05, "loss": 4.439, "step": 6890 }, { "epoch": 0.21047648136835675, "grad_norm": 0.3895505964756012, "learning_rate": 4.473091651325024e-05, "loss": 4.3982, "step": 6891 }, { "epoch": 0.2105070250458155, "grad_norm": 0.3749045729637146, "learning_rate": 4.4729443287117853e-05, "loss": 4.416, "step": 6892 }, { "epoch": 0.21053756872327428, "grad_norm": 0.37919625639915466, "learning_rate": 4.4727969879326334e-05, "loss": 4.3565, "step": 6893 }, { "epoch": 0.21056811240073306, "grad_norm": 0.38295087218284607, "learning_rate": 4.4726496289889256e-05, "loss": 4.3328, "step": 6894 }, { "epoch": 0.2105986560781918, "grad_norm": 0.3932417631149292, "learning_rate": 4.472502251882018e-05, "loss": 4.3706, "step": 6895 }, { "epoch": 0.2106291997556506, "grad_norm": 0.3895527422428131, "learning_rate": 4.472354856613268e-05, "loss": 4.3274, "step": 6896 }, { "epoch": 0.21065974343310934, "grad_norm": 0.3791539669036865, "learning_rate": 4.472207443184033e-05, "loss": 4.3715, "step": 6897 }, { "epoch": 0.21069028711056811, "grad_norm": 0.36807388067245483, "learning_rate": 4.47206001159567e-05, "loss": 4.361, "step": 6898 }, { "epoch": 0.2107208307880269, "grad_norm": 0.387688547372818, "learning_rate": 4.471912561849536e-05, "loss": 4.4109, "step": 6899 }, { "epoch": 0.21075137446548564, "grad_norm": 0.377176970243454, "learning_rate": 4.47176509394699e-05, "loss": 4.3752, "step": 6900 }, { "epoch": 0.21078191814294442, "grad_norm": 0.37825971841812134, "learning_rate": 4.471617607889389e-05, "loss": 4.3297, "step": 6901 }, { "epoch": 0.21081246182040317, "grad_norm": 0.38573476672172546, "learning_rate": 4.4714701036780905e-05, "loss": 4.4504, "step": 6902 }, { "epoch": 0.21084300549786195, "grad_norm": 0.3926021456718445, "learning_rate": 4.4713225813144534e-05, "loss": 4.3683, "step": 6903 }, { "epoch": 0.2108735491753207, "grad_norm": 0.3918910622596741, "learning_rate": 4.471175040799835e-05, "loss": 4.4289, "step": 6904 }, { "epoch": 0.21090409285277947, "grad_norm": 0.39187419414520264, "learning_rate": 4.471027482135596e-05, "loss": 4.4087, "step": 6905 }, { "epoch": 0.21093463653023825, "grad_norm": 0.370574027299881, "learning_rate": 4.4708799053230923e-05, "loss": 4.3853, "step": 6906 }, { "epoch": 0.210965180207697, "grad_norm": 0.37478873133659363, "learning_rate": 4.470732310363685e-05, "loss": 4.4701, "step": 6907 }, { "epoch": 0.21099572388515578, "grad_norm": 0.37094515562057495, "learning_rate": 4.470584697258731e-05, "loss": 4.2873, "step": 6908 }, { "epoch": 0.21102626756261453, "grad_norm": 0.3895094692707062, "learning_rate": 4.470437066009591e-05, "loss": 4.351, "step": 6909 }, { "epoch": 0.2110568112400733, "grad_norm": 0.37938714027404785, "learning_rate": 4.4702894166176235e-05, "loss": 4.4644, "step": 6910 }, { "epoch": 0.21108735491753208, "grad_norm": 0.4087308645248413, "learning_rate": 4.470141749084189e-05, "loss": 4.3361, "step": 6911 }, { "epoch": 0.21111789859499083, "grad_norm": 0.384813517332077, "learning_rate": 4.469994063410646e-05, "loss": 4.3705, "step": 6912 }, { "epoch": 0.2111484422724496, "grad_norm": 0.38706427812576294, "learning_rate": 4.4698463595983554e-05, "loss": 4.2985, "step": 6913 }, { "epoch": 0.21117898594990836, "grad_norm": 0.3907209038734436, "learning_rate": 4.469698637648676e-05, "loss": 4.2417, "step": 6914 }, { "epoch": 0.21120952962736714, "grad_norm": 0.3862916827201843, "learning_rate": 4.469550897562969e-05, "loss": 4.4659, "step": 6915 }, { "epoch": 0.2112400733048259, "grad_norm": 0.3782653510570526, "learning_rate": 4.469403139342593e-05, "loss": 4.3607, "step": 6916 }, { "epoch": 0.21127061698228466, "grad_norm": 0.37065035104751587, "learning_rate": 4.46925536298891e-05, "loss": 4.3387, "step": 6917 }, { "epoch": 0.21130116065974344, "grad_norm": 0.3840900957584381, "learning_rate": 4.4691075685032815e-05, "loss": 4.3061, "step": 6918 }, { "epoch": 0.2113317043372022, "grad_norm": 0.37687551975250244, "learning_rate": 4.468959755887066e-05, "loss": 4.3782, "step": 6919 }, { "epoch": 0.21136224801466097, "grad_norm": 0.38079214096069336, "learning_rate": 4.4688119251416274e-05, "loss": 4.4262, "step": 6920 }, { "epoch": 0.21139279169211972, "grad_norm": 0.38944754004478455, "learning_rate": 4.468664076268324e-05, "loss": 4.4268, "step": 6921 }, { "epoch": 0.2114233353695785, "grad_norm": 0.39827990531921387, "learning_rate": 4.468516209268518e-05, "loss": 4.3708, "step": 6922 }, { "epoch": 0.21145387904703727, "grad_norm": 0.38219302892684937, "learning_rate": 4.468368324143572e-05, "loss": 4.3985, "step": 6923 }, { "epoch": 0.21148442272449602, "grad_norm": 0.3809141218662262, "learning_rate": 4.468220420894846e-05, "loss": 4.3526, "step": 6924 }, { "epoch": 0.2115149664019548, "grad_norm": 0.37383344769477844, "learning_rate": 4.468072499523703e-05, "loss": 4.3613, "step": 6925 }, { "epoch": 0.21154551007941355, "grad_norm": 0.3799000382423401, "learning_rate": 4.4679245600315046e-05, "loss": 4.3443, "step": 6926 }, { "epoch": 0.21157605375687233, "grad_norm": 0.3787612318992615, "learning_rate": 4.467776602419612e-05, "loss": 4.378, "step": 6927 }, { "epoch": 0.2116065974343311, "grad_norm": 0.38279828429222107, "learning_rate": 4.4676286266893894e-05, "loss": 4.3886, "step": 6928 }, { "epoch": 0.21163714111178986, "grad_norm": 0.38631168007850647, "learning_rate": 4.467480632842199e-05, "loss": 4.4289, "step": 6929 }, { "epoch": 0.21166768478924863, "grad_norm": 0.3806989789009094, "learning_rate": 4.467332620879402e-05, "loss": 4.3089, "step": 6930 }, { "epoch": 0.21169822846670738, "grad_norm": 0.3797719180583954, "learning_rate": 4.467184590802363e-05, "loss": 4.3728, "step": 6931 }, { "epoch": 0.21172877214416616, "grad_norm": 0.3950240910053253, "learning_rate": 4.467036542612443e-05, "loss": 4.4556, "step": 6932 }, { "epoch": 0.2117593158216249, "grad_norm": 0.38195088505744934, "learning_rate": 4.4668884763110066e-05, "loss": 4.4133, "step": 6933 }, { "epoch": 0.2117898594990837, "grad_norm": 0.37896430492401123, "learning_rate": 4.466740391899416e-05, "loss": 4.295, "step": 6934 }, { "epoch": 0.21182040317654247, "grad_norm": 0.3967898190021515, "learning_rate": 4.466592289379036e-05, "loss": 4.242, "step": 6935 }, { "epoch": 0.21185094685400122, "grad_norm": 0.3788953423500061, "learning_rate": 4.466444168751231e-05, "loss": 4.4794, "step": 6936 }, { "epoch": 0.21188149053146, "grad_norm": 0.3639508783817291, "learning_rate": 4.466296030017361e-05, "loss": 4.3358, "step": 6937 }, { "epoch": 0.21191203420891874, "grad_norm": 0.37693873047828674, "learning_rate": 4.466147873178794e-05, "loss": 4.367, "step": 6938 }, { "epoch": 0.21194257788637752, "grad_norm": 0.3644152283668518, "learning_rate": 4.465999698236892e-05, "loss": 4.3351, "step": 6939 }, { "epoch": 0.2119731215638363, "grad_norm": 0.37220779061317444, "learning_rate": 4.465851505193021e-05, "loss": 4.4246, "step": 6940 }, { "epoch": 0.21200366524129505, "grad_norm": 0.3834647536277771, "learning_rate": 4.465703294048543e-05, "loss": 4.4053, "step": 6941 }, { "epoch": 0.21203420891875382, "grad_norm": 0.377776563167572, "learning_rate": 4.465555064804825e-05, "loss": 4.4716, "step": 6942 }, { "epoch": 0.21206475259621257, "grad_norm": 0.3720308840274811, "learning_rate": 4.465406817463231e-05, "loss": 4.346, "step": 6943 }, { "epoch": 0.21209529627367135, "grad_norm": 0.39079150557518005, "learning_rate": 4.4652585520251254e-05, "loss": 4.374, "step": 6944 }, { "epoch": 0.21212583995113013, "grad_norm": 0.38549208641052246, "learning_rate": 4.4651102684918745e-05, "loss": 4.4275, "step": 6945 }, { "epoch": 0.21215638362858888, "grad_norm": 0.373058557510376, "learning_rate": 4.4649619668648424e-05, "loss": 4.2901, "step": 6946 }, { "epoch": 0.21218692730604766, "grad_norm": 0.385140061378479, "learning_rate": 4.464813647145396e-05, "loss": 4.3759, "step": 6947 }, { "epoch": 0.2122174709835064, "grad_norm": 0.3800239861011505, "learning_rate": 4.464665309334899e-05, "loss": 4.3119, "step": 6948 }, { "epoch": 0.21224801466096518, "grad_norm": 0.3655844032764435, "learning_rate": 4.46451695343472e-05, "loss": 4.2991, "step": 6949 }, { "epoch": 0.21227855833842393, "grad_norm": 0.38505983352661133, "learning_rate": 4.464368579446222e-05, "loss": 4.4067, "step": 6950 }, { "epoch": 0.2123091020158827, "grad_norm": 0.37646180391311646, "learning_rate": 4.464220187370772e-05, "loss": 4.3745, "step": 6951 }, { "epoch": 0.2123396456933415, "grad_norm": 0.3695542812347412, "learning_rate": 4.464071777209739e-05, "loss": 4.2719, "step": 6952 }, { "epoch": 0.21237018937080024, "grad_norm": 0.39590883255004883, "learning_rate": 4.463923348964485e-05, "loss": 4.3869, "step": 6953 }, { "epoch": 0.21240073304825902, "grad_norm": 0.37394121289253235, "learning_rate": 4.46377490263638e-05, "loss": 4.4038, "step": 6954 }, { "epoch": 0.21243127672571777, "grad_norm": 0.39306506514549255, "learning_rate": 4.46362643822679e-05, "loss": 4.4153, "step": 6955 }, { "epoch": 0.21246182040317654, "grad_norm": 0.3881324827671051, "learning_rate": 4.463477955737082e-05, "loss": 4.2907, "step": 6956 }, { "epoch": 0.21249236408063532, "grad_norm": 0.37298858165740967, "learning_rate": 4.463329455168622e-05, "loss": 4.4286, "step": 6957 }, { "epoch": 0.21252290775809407, "grad_norm": 0.3772020936012268, "learning_rate": 4.4631809365227786e-05, "loss": 4.3929, "step": 6958 }, { "epoch": 0.21255345143555285, "grad_norm": 0.391848087310791, "learning_rate": 4.463032399800919e-05, "loss": 4.3499, "step": 6959 }, { "epoch": 0.2125839951130116, "grad_norm": 0.37979549169540405, "learning_rate": 4.4628838450044115e-05, "loss": 4.3549, "step": 6960 }, { "epoch": 0.21261453879047038, "grad_norm": 0.38027194142341614, "learning_rate": 4.462735272134623e-05, "loss": 4.4196, "step": 6961 }, { "epoch": 0.21264508246792913, "grad_norm": 0.38304367661476135, "learning_rate": 4.462586681192921e-05, "loss": 4.378, "step": 6962 }, { "epoch": 0.2126756261453879, "grad_norm": 0.3855019807815552, "learning_rate": 4.462438072180675e-05, "loss": 4.3582, "step": 6963 }, { "epoch": 0.21270616982284668, "grad_norm": 0.3751838207244873, "learning_rate": 4.462289445099252e-05, "loss": 4.3251, "step": 6964 }, { "epoch": 0.21273671350030543, "grad_norm": 0.37564000487327576, "learning_rate": 4.462140799950021e-05, "loss": 4.3368, "step": 6965 }, { "epoch": 0.2127672571777642, "grad_norm": 0.38877835869789124, "learning_rate": 4.461992136734352e-05, "loss": 4.3486, "step": 6966 }, { "epoch": 0.21279780085522296, "grad_norm": 0.3949674963951111, "learning_rate": 4.461843455453612e-05, "loss": 4.312, "step": 6967 }, { "epoch": 0.21282834453268173, "grad_norm": 0.3762555420398712, "learning_rate": 4.4616947561091705e-05, "loss": 4.3789, "step": 6968 }, { "epoch": 0.2128588882101405, "grad_norm": 0.3837481737136841, "learning_rate": 4.461546038702397e-05, "loss": 4.2985, "step": 6969 }, { "epoch": 0.21288943188759926, "grad_norm": 0.3812617361545563, "learning_rate": 4.46139730323466e-05, "loss": 4.3778, "step": 6970 }, { "epoch": 0.21291997556505804, "grad_norm": 0.3908730745315552, "learning_rate": 4.461248549707331e-05, "loss": 4.411, "step": 6971 }, { "epoch": 0.2129505192425168, "grad_norm": 0.3860103189945221, "learning_rate": 4.4610997781217764e-05, "loss": 4.3734, "step": 6972 }, { "epoch": 0.21298106291997557, "grad_norm": 0.3836783468723297, "learning_rate": 4.4609509884793695e-05, "loss": 4.3956, "step": 6973 }, { "epoch": 0.21301160659743434, "grad_norm": 0.3789370656013489, "learning_rate": 4.460802180781478e-05, "loss": 4.4162, "step": 6974 }, { "epoch": 0.2130421502748931, "grad_norm": 0.37694260478019714, "learning_rate": 4.4606533550294725e-05, "loss": 4.3073, "step": 6975 }, { "epoch": 0.21307269395235187, "grad_norm": 0.3856047987937927, "learning_rate": 4.4605045112247235e-05, "loss": 4.3874, "step": 6976 }, { "epoch": 0.21310323762981062, "grad_norm": 0.38281136751174927, "learning_rate": 4.460355649368602e-05, "loss": 4.3891, "step": 6977 }, { "epoch": 0.2131337813072694, "grad_norm": 0.39127272367477417, "learning_rate": 4.460206769462477e-05, "loss": 4.3429, "step": 6978 }, { "epoch": 0.21316432498472815, "grad_norm": 0.3982844948768616, "learning_rate": 4.4600578715077216e-05, "loss": 4.4337, "step": 6979 }, { "epoch": 0.21319486866218693, "grad_norm": 0.37191078066825867, "learning_rate": 4.459908955505705e-05, "loss": 4.3117, "step": 6980 }, { "epoch": 0.2132254123396457, "grad_norm": 0.3912276327610016, "learning_rate": 4.4597600214577984e-05, "loss": 4.2489, "step": 6981 }, { "epoch": 0.21325595601710445, "grad_norm": 0.37724918127059937, "learning_rate": 4.4596110693653745e-05, "loss": 4.2717, "step": 6982 }, { "epoch": 0.21328649969456323, "grad_norm": 0.39589640498161316, "learning_rate": 4.4594620992298044e-05, "loss": 4.3384, "step": 6983 }, { "epoch": 0.21331704337202198, "grad_norm": 0.3911004662513733, "learning_rate": 4.459313111052459e-05, "loss": 4.4405, "step": 6984 }, { "epoch": 0.21334758704948076, "grad_norm": 0.381931871175766, "learning_rate": 4.4591641048347096e-05, "loss": 4.3337, "step": 6985 }, { "epoch": 0.21337813072693954, "grad_norm": 0.38504505157470703, "learning_rate": 4.4590150805779294e-05, "loss": 4.3777, "step": 6986 }, { "epoch": 0.21340867440439829, "grad_norm": 0.3733905255794525, "learning_rate": 4.4588660382834904e-05, "loss": 4.3255, "step": 6987 }, { "epoch": 0.21343921808185706, "grad_norm": 0.3911367356777191, "learning_rate": 4.458716977952764e-05, "loss": 4.4345, "step": 6988 }, { "epoch": 0.2134697617593158, "grad_norm": 0.39688095450401306, "learning_rate": 4.458567899587124e-05, "loss": 4.287, "step": 6989 }, { "epoch": 0.2135003054367746, "grad_norm": 0.3709327280521393, "learning_rate": 4.4584188031879426e-05, "loss": 4.3903, "step": 6990 }, { "epoch": 0.21353084911423337, "grad_norm": 0.38839930295944214, "learning_rate": 4.458269688756591e-05, "loss": 4.2784, "step": 6991 }, { "epoch": 0.21356139279169212, "grad_norm": 0.3827759325504303, "learning_rate": 4.458120556294445e-05, "loss": 4.4429, "step": 6992 }, { "epoch": 0.2135919364691509, "grad_norm": 0.3828699290752411, "learning_rate": 4.457971405802875e-05, "loss": 4.3897, "step": 6993 }, { "epoch": 0.21362248014660964, "grad_norm": 0.37556061148643494, "learning_rate": 4.457822237283257e-05, "loss": 4.2763, "step": 6994 }, { "epoch": 0.21365302382406842, "grad_norm": 0.3865252435207367, "learning_rate": 4.4576730507369623e-05, "loss": 4.4574, "step": 6995 }, { "epoch": 0.21368356750152717, "grad_norm": 0.3749418556690216, "learning_rate": 4.4575238461653655e-05, "loss": 4.3575, "step": 6996 }, { "epoch": 0.21371411117898595, "grad_norm": 0.3928515911102295, "learning_rate": 4.45737462356984e-05, "loss": 4.3489, "step": 6997 }, { "epoch": 0.21374465485644473, "grad_norm": 0.3924694061279297, "learning_rate": 4.45722538295176e-05, "loss": 4.4169, "step": 6998 }, { "epoch": 0.21377519853390348, "grad_norm": 0.3792368769645691, "learning_rate": 4.4570761243124995e-05, "loss": 4.3424, "step": 6999 }, { "epoch": 0.21380574221136225, "grad_norm": 0.37702274322509766, "learning_rate": 4.4569268476534325e-05, "loss": 4.4378, "step": 7000 }, { "epoch": 0.213836285888821, "grad_norm": 0.37366893887519836, "learning_rate": 4.456777552975935e-05, "loss": 4.3902, "step": 7001 }, { "epoch": 0.21386682956627978, "grad_norm": 0.37447062134742737, "learning_rate": 4.4566282402813794e-05, "loss": 4.3473, "step": 7002 }, { "epoch": 0.21389737324373856, "grad_norm": 0.37820443511009216, "learning_rate": 4.456478909571142e-05, "loss": 4.3824, "step": 7003 }, { "epoch": 0.2139279169211973, "grad_norm": 0.383794367313385, "learning_rate": 4.456329560846597e-05, "loss": 4.3431, "step": 7004 }, { "epoch": 0.2139584605986561, "grad_norm": 0.37773457169532776, "learning_rate": 4.45618019410912e-05, "loss": 4.3956, "step": 7005 }, { "epoch": 0.21398900427611484, "grad_norm": 0.3823487460613251, "learning_rate": 4.4560308093600864e-05, "loss": 4.3445, "step": 7006 }, { "epoch": 0.2140195479535736, "grad_norm": 0.37131986021995544, "learning_rate": 4.455881406600872e-05, "loss": 4.3086, "step": 7007 }, { "epoch": 0.21405009163103236, "grad_norm": 0.3744848668575287, "learning_rate": 4.455731985832852e-05, "loss": 4.2309, "step": 7008 }, { "epoch": 0.21408063530849114, "grad_norm": 0.3677964508533478, "learning_rate": 4.4555825470574005e-05, "loss": 4.3606, "step": 7009 }, { "epoch": 0.21411117898594992, "grad_norm": 0.37293100357055664, "learning_rate": 4.4554330902758964e-05, "loss": 4.3948, "step": 7010 }, { "epoch": 0.21414172266340867, "grad_norm": 0.37924477458000183, "learning_rate": 4.4552836154897135e-05, "loss": 4.3789, "step": 7011 }, { "epoch": 0.21417226634086745, "grad_norm": 0.38945940136909485, "learning_rate": 4.4551341227002296e-05, "loss": 4.2976, "step": 7012 }, { "epoch": 0.2142028100183262, "grad_norm": 0.3794018626213074, "learning_rate": 4.454984611908821e-05, "loss": 4.3617, "step": 7013 }, { "epoch": 0.21423335369578497, "grad_norm": 0.37419337034225464, "learning_rate": 4.454835083116863e-05, "loss": 4.3414, "step": 7014 }, { "epoch": 0.21426389737324375, "grad_norm": 0.36350110173225403, "learning_rate": 4.454685536325734e-05, "loss": 4.2751, "step": 7015 }, { "epoch": 0.2142944410507025, "grad_norm": 0.3822810649871826, "learning_rate": 4.4545359715368096e-05, "loss": 4.3865, "step": 7016 }, { "epoch": 0.21432498472816128, "grad_norm": 0.3772166967391968, "learning_rate": 4.454386388751468e-05, "loss": 4.3305, "step": 7017 }, { "epoch": 0.21435552840562003, "grad_norm": 0.38510042428970337, "learning_rate": 4.454236787971087e-05, "loss": 4.4224, "step": 7018 }, { "epoch": 0.2143860720830788, "grad_norm": 0.36968088150024414, "learning_rate": 4.454087169197042e-05, "loss": 4.2712, "step": 7019 }, { "epoch": 0.21441661576053758, "grad_norm": 0.39499855041503906, "learning_rate": 4.453937532430712e-05, "loss": 4.3938, "step": 7020 }, { "epoch": 0.21444715943799633, "grad_norm": 0.37758615612983704, "learning_rate": 4.453787877673474e-05, "loss": 4.4121, "step": 7021 }, { "epoch": 0.2144777031154551, "grad_norm": 0.3796750009059906, "learning_rate": 4.4536382049267075e-05, "loss": 4.317, "step": 7022 }, { "epoch": 0.21450824679291386, "grad_norm": 0.39347079396247864, "learning_rate": 4.453488514191789e-05, "loss": 4.3894, "step": 7023 }, { "epoch": 0.21453879047037264, "grad_norm": 0.3876686990261078, "learning_rate": 4.453338805470097e-05, "loss": 4.384, "step": 7024 }, { "epoch": 0.2145693341478314, "grad_norm": 0.40546658635139465, "learning_rate": 4.453189078763011e-05, "loss": 4.3329, "step": 7025 }, { "epoch": 0.21459987782529016, "grad_norm": 0.37528178095817566, "learning_rate": 4.453039334071909e-05, "loss": 4.2626, "step": 7026 }, { "epoch": 0.21463042150274894, "grad_norm": 0.3757719099521637, "learning_rate": 4.452889571398169e-05, "loss": 4.3232, "step": 7027 }, { "epoch": 0.2146609651802077, "grad_norm": 0.3798154294490814, "learning_rate": 4.452739790743171e-05, "loss": 4.3462, "step": 7028 }, { "epoch": 0.21469150885766647, "grad_norm": 0.40540197491645813, "learning_rate": 4.4525899921082936e-05, "loss": 4.3734, "step": 7029 }, { "epoch": 0.21472205253512522, "grad_norm": 0.39551758766174316, "learning_rate": 4.452440175494916e-05, "loss": 4.3876, "step": 7030 }, { "epoch": 0.214752596212584, "grad_norm": 0.3799687922000885, "learning_rate": 4.4522903409044186e-05, "loss": 4.422, "step": 7031 }, { "epoch": 0.21478313989004277, "grad_norm": 0.37554487586021423, "learning_rate": 4.45214048833818e-05, "loss": 4.3985, "step": 7032 }, { "epoch": 0.21481368356750152, "grad_norm": 0.39937761425971985, "learning_rate": 4.45199061779758e-05, "loss": 4.3495, "step": 7033 }, { "epoch": 0.2148442272449603, "grad_norm": 0.3709573745727539, "learning_rate": 4.4518407292839994e-05, "loss": 4.2904, "step": 7034 }, { "epoch": 0.21487477092241905, "grad_norm": 0.3870699107646942, "learning_rate": 4.451690822798816e-05, "loss": 4.3209, "step": 7035 }, { "epoch": 0.21490531459987783, "grad_norm": 0.37414854764938354, "learning_rate": 4.451540898343414e-05, "loss": 4.4031, "step": 7036 }, { "epoch": 0.21493585827733658, "grad_norm": 0.37281307578086853, "learning_rate": 4.45139095591917e-05, "loss": 4.3939, "step": 7037 }, { "epoch": 0.21496640195479536, "grad_norm": 0.3786470293998718, "learning_rate": 4.4512409955274666e-05, "loss": 4.3691, "step": 7038 }, { "epoch": 0.21499694563225413, "grad_norm": 0.37616828083992004, "learning_rate": 4.451091017169684e-05, "loss": 4.3853, "step": 7039 }, { "epoch": 0.21502748930971288, "grad_norm": 0.3738337457180023, "learning_rate": 4.450941020847204e-05, "loss": 4.1527, "step": 7040 }, { "epoch": 0.21505803298717166, "grad_norm": 0.3800468444824219, "learning_rate": 4.4507910065614054e-05, "loss": 4.3535, "step": 7041 }, { "epoch": 0.2150885766646304, "grad_norm": 0.3898496627807617, "learning_rate": 4.450640974313672e-05, "loss": 4.2559, "step": 7042 }, { "epoch": 0.2151191203420892, "grad_norm": 0.3778424859046936, "learning_rate": 4.4504909241053846e-05, "loss": 4.4042, "step": 7043 }, { "epoch": 0.21514966401954796, "grad_norm": 0.38151219487190247, "learning_rate": 4.450340855937924e-05, "loss": 4.405, "step": 7044 }, { "epoch": 0.21518020769700671, "grad_norm": 0.3799569308757782, "learning_rate": 4.4501907698126724e-05, "loss": 4.4427, "step": 7045 }, { "epoch": 0.2152107513744655, "grad_norm": 0.38493725657463074, "learning_rate": 4.450040665731011e-05, "loss": 4.4537, "step": 7046 }, { "epoch": 0.21524129505192424, "grad_norm": 0.3897477686405182, "learning_rate": 4.449890543694324e-05, "loss": 4.3358, "step": 7047 }, { "epoch": 0.21527183872938302, "grad_norm": 0.37597358226776123, "learning_rate": 4.4497404037039913e-05, "loss": 4.3775, "step": 7048 }, { "epoch": 0.2153023824068418, "grad_norm": 0.3873814642429352, "learning_rate": 4.4495902457613955e-05, "loss": 4.4073, "step": 7049 }, { "epoch": 0.21533292608430055, "grad_norm": 0.3793831467628479, "learning_rate": 4.449440069867922e-05, "loss": 4.3971, "step": 7050 }, { "epoch": 0.21536346976175932, "grad_norm": 0.38016191124916077, "learning_rate": 4.44928987602495e-05, "loss": 4.3415, "step": 7051 }, { "epoch": 0.21539401343921807, "grad_norm": 0.3826659917831421, "learning_rate": 4.449139664233864e-05, "loss": 4.3714, "step": 7052 }, { "epoch": 0.21542455711667685, "grad_norm": 0.38357990980148315, "learning_rate": 4.448989434496047e-05, "loss": 4.3897, "step": 7053 }, { "epoch": 0.2154551007941356, "grad_norm": 0.3784109055995941, "learning_rate": 4.4488391868128826e-05, "loss": 4.3637, "step": 7054 }, { "epoch": 0.21548564447159438, "grad_norm": 0.38472694158554077, "learning_rate": 4.4486889211857535e-05, "loss": 4.3367, "step": 7055 }, { "epoch": 0.21551618814905316, "grad_norm": 0.3781936764717102, "learning_rate": 4.4485386376160435e-05, "loss": 4.3568, "step": 7056 }, { "epoch": 0.2155467318265119, "grad_norm": 0.37793993949890137, "learning_rate": 4.448388336105137e-05, "loss": 4.399, "step": 7057 }, { "epoch": 0.21557727550397068, "grad_norm": 0.36724230647087097, "learning_rate": 4.448238016654417e-05, "loss": 4.3674, "step": 7058 }, { "epoch": 0.21560781918142943, "grad_norm": 0.3978705108165741, "learning_rate": 4.448087679265268e-05, "loss": 4.3695, "step": 7059 }, { "epoch": 0.2156383628588882, "grad_norm": 0.3876137435436249, "learning_rate": 4.4479373239390734e-05, "loss": 4.3906, "step": 7060 }, { "epoch": 0.215668906536347, "grad_norm": 0.39001259207725525, "learning_rate": 4.447786950677219e-05, "loss": 4.3678, "step": 7061 }, { "epoch": 0.21569945021380574, "grad_norm": 0.3869231045246124, "learning_rate": 4.447636559481089e-05, "loss": 4.3308, "step": 7062 }, { "epoch": 0.21572999389126452, "grad_norm": 0.3832705616950989, "learning_rate": 4.447486150352067e-05, "loss": 4.256, "step": 7063 }, { "epoch": 0.21576053756872327, "grad_norm": 0.39550527930259705, "learning_rate": 4.4473357232915394e-05, "loss": 4.3792, "step": 7064 }, { "epoch": 0.21579108124618204, "grad_norm": 0.38716503977775574, "learning_rate": 4.44718527830089e-05, "loss": 4.3721, "step": 7065 }, { "epoch": 0.21582162492364082, "grad_norm": 0.3821936249732971, "learning_rate": 4.447034815381504e-05, "loss": 4.3525, "step": 7066 }, { "epoch": 0.21585216860109957, "grad_norm": 0.3931942582130432, "learning_rate": 4.446884334534769e-05, "loss": 4.2531, "step": 7067 }, { "epoch": 0.21588271227855835, "grad_norm": 0.38812166452407837, "learning_rate": 4.446733835762068e-05, "loss": 4.3321, "step": 7068 }, { "epoch": 0.2159132559560171, "grad_norm": 0.3855256736278534, "learning_rate": 4.446583319064788e-05, "loss": 4.3589, "step": 7069 }, { "epoch": 0.21594379963347587, "grad_norm": 0.3714802861213684, "learning_rate": 4.446432784444314e-05, "loss": 4.317, "step": 7070 }, { "epoch": 0.21597434331093462, "grad_norm": 0.3822749853134155, "learning_rate": 4.4462822319020334e-05, "loss": 4.4172, "step": 7071 }, { "epoch": 0.2160048869883934, "grad_norm": 0.385185182094574, "learning_rate": 4.446131661439331e-05, "loss": 4.4039, "step": 7072 }, { "epoch": 0.21603543066585218, "grad_norm": 0.3749528229236603, "learning_rate": 4.4459810730575944e-05, "loss": 4.3658, "step": 7073 }, { "epoch": 0.21606597434331093, "grad_norm": 0.3853505253791809, "learning_rate": 4.445830466758209e-05, "loss": 4.3898, "step": 7074 }, { "epoch": 0.2160965180207697, "grad_norm": 0.38554447889328003, "learning_rate": 4.4456798425425624e-05, "loss": 4.3615, "step": 7075 }, { "epoch": 0.21612706169822846, "grad_norm": 0.37064459919929504, "learning_rate": 4.445529200412041e-05, "loss": 4.326, "step": 7076 }, { "epoch": 0.21615760537568723, "grad_norm": 0.3905785083770752, "learning_rate": 4.4453785403680314e-05, "loss": 4.3424, "step": 7077 }, { "epoch": 0.216188149053146, "grad_norm": 0.3762499988079071, "learning_rate": 4.445227862411922e-05, "loss": 4.3683, "step": 7078 }, { "epoch": 0.21621869273060476, "grad_norm": 0.3808180093765259, "learning_rate": 4.4450771665450996e-05, "loss": 4.4301, "step": 7079 }, { "epoch": 0.21624923640806354, "grad_norm": 0.3805929124355316, "learning_rate": 4.4449264527689515e-05, "loss": 4.3898, "step": 7080 }, { "epoch": 0.2162797800855223, "grad_norm": 0.385050892829895, "learning_rate": 4.444775721084865e-05, "loss": 4.343, "step": 7081 }, { "epoch": 0.21631032376298107, "grad_norm": 0.3845735192298889, "learning_rate": 4.444624971494229e-05, "loss": 4.3051, "step": 7082 }, { "epoch": 0.21634086744043982, "grad_norm": 0.3776951730251312, "learning_rate": 4.444474203998431e-05, "loss": 4.2264, "step": 7083 }, { "epoch": 0.2163714111178986, "grad_norm": 0.3692701756954193, "learning_rate": 4.44432341859886e-05, "loss": 4.2986, "step": 7084 }, { "epoch": 0.21640195479535737, "grad_norm": 0.39132776856422424, "learning_rate": 4.4441726152969024e-05, "loss": 4.3295, "step": 7085 }, { "epoch": 0.21643249847281612, "grad_norm": 0.41046375036239624, "learning_rate": 4.444021794093949e-05, "loss": 4.281, "step": 7086 }, { "epoch": 0.2164630421502749, "grad_norm": 0.38257455825805664, "learning_rate": 4.443870954991387e-05, "loss": 4.3865, "step": 7087 }, { "epoch": 0.21649358582773365, "grad_norm": 0.3921200931072235, "learning_rate": 4.443720097990606e-05, "loss": 4.3928, "step": 7088 }, { "epoch": 0.21652412950519243, "grad_norm": 0.3632165789604187, "learning_rate": 4.443569223092994e-05, "loss": 4.3278, "step": 7089 }, { "epoch": 0.2165546731826512, "grad_norm": 0.38501548767089844, "learning_rate": 4.443418330299941e-05, "loss": 4.2591, "step": 7090 }, { "epoch": 0.21658521686010995, "grad_norm": 0.3858863413333893, "learning_rate": 4.4432674196128366e-05, "loss": 4.3607, "step": 7091 }, { "epoch": 0.21661576053756873, "grad_norm": 0.3779291808605194, "learning_rate": 4.4431164910330693e-05, "loss": 4.3084, "step": 7092 }, { "epoch": 0.21664630421502748, "grad_norm": 0.40003111958503723, "learning_rate": 4.44296554456203e-05, "loss": 4.2928, "step": 7093 }, { "epoch": 0.21667684789248626, "grad_norm": 0.3889622092247009, "learning_rate": 4.442814580201108e-05, "loss": 4.3568, "step": 7094 }, { "epoch": 0.21670739156994503, "grad_norm": 0.3979185223579407, "learning_rate": 4.442663597951693e-05, "loss": 4.2998, "step": 7095 }, { "epoch": 0.21673793524740378, "grad_norm": 0.38892942667007446, "learning_rate": 4.4425125978151755e-05, "loss": 4.3491, "step": 7096 }, { "epoch": 0.21676847892486256, "grad_norm": 0.3901890516281128, "learning_rate": 4.442361579792945e-05, "loss": 4.3938, "step": 7097 }, { "epoch": 0.2167990226023213, "grad_norm": 0.37619122862815857, "learning_rate": 4.442210543886394e-05, "loss": 4.3218, "step": 7098 }, { "epoch": 0.2168295662797801, "grad_norm": 0.39234495162963867, "learning_rate": 4.4420594900969115e-05, "loss": 4.3925, "step": 7099 }, { "epoch": 0.21686010995723884, "grad_norm": 0.3762603998184204, "learning_rate": 4.441908418425889e-05, "loss": 4.3888, "step": 7100 }, { "epoch": 0.21689065363469762, "grad_norm": 0.37767279148101807, "learning_rate": 4.4417573288747175e-05, "loss": 4.2297, "step": 7101 }, { "epoch": 0.2169211973121564, "grad_norm": 0.3784467875957489, "learning_rate": 4.441606221444787e-05, "loss": 4.3815, "step": 7102 }, { "epoch": 0.21695174098961514, "grad_norm": 0.3898187577724457, "learning_rate": 4.4414550961374904e-05, "loss": 4.3246, "step": 7103 }, { "epoch": 0.21698228466707392, "grad_norm": 0.3799775540828705, "learning_rate": 4.441303952954218e-05, "loss": 4.4074, "step": 7104 }, { "epoch": 0.21701282834453267, "grad_norm": 0.37332025170326233, "learning_rate": 4.441152791896362e-05, "loss": 4.3046, "step": 7105 }, { "epoch": 0.21704337202199145, "grad_norm": 0.3877909481525421, "learning_rate": 4.4410016129653145e-05, "loss": 4.3393, "step": 7106 }, { "epoch": 0.21707391569945023, "grad_norm": 0.3769341707229614, "learning_rate": 4.440850416162468e-05, "loss": 4.4412, "step": 7107 }, { "epoch": 0.21710445937690898, "grad_norm": 0.3808756172657013, "learning_rate": 4.440699201489212e-05, "loss": 4.3876, "step": 7108 }, { "epoch": 0.21713500305436775, "grad_norm": 0.3877844512462616, "learning_rate": 4.440547968946942e-05, "loss": 4.377, "step": 7109 }, { "epoch": 0.2171655467318265, "grad_norm": 0.3705284893512726, "learning_rate": 4.440396718537049e-05, "loss": 4.3865, "step": 7110 }, { "epoch": 0.21719609040928528, "grad_norm": 0.380827933549881, "learning_rate": 4.440245450260926e-05, "loss": 4.3234, "step": 7111 }, { "epoch": 0.21722663408674403, "grad_norm": 0.3916170001029968, "learning_rate": 4.440094164119965e-05, "loss": 4.4019, "step": 7112 }, { "epoch": 0.2172571777642028, "grad_norm": 0.37916749715805054, "learning_rate": 4.439942860115559e-05, "loss": 4.3698, "step": 7113 }, { "epoch": 0.21728772144166159, "grad_norm": 0.38612058758735657, "learning_rate": 4.439791538249103e-05, "loss": 4.2231, "step": 7114 }, { "epoch": 0.21731826511912034, "grad_norm": 0.3719905912876129, "learning_rate": 4.4396401985219884e-05, "loss": 4.381, "step": 7115 }, { "epoch": 0.2173488087965791, "grad_norm": 0.3800596594810486, "learning_rate": 4.4394888409356086e-05, "loss": 4.3624, "step": 7116 }, { "epoch": 0.21737935247403786, "grad_norm": 0.37961462140083313, "learning_rate": 4.4393374654913586e-05, "loss": 4.2509, "step": 7117 }, { "epoch": 0.21740989615149664, "grad_norm": 0.3732321858406067, "learning_rate": 4.439186072190631e-05, "loss": 4.4, "step": 7118 }, { "epoch": 0.21744043982895542, "grad_norm": 0.3754345178604126, "learning_rate": 4.4390346610348205e-05, "loss": 4.4838, "step": 7119 }, { "epoch": 0.21747098350641417, "grad_norm": 0.3696676194667816, "learning_rate": 4.43888323202532e-05, "loss": 4.4022, "step": 7120 }, { "epoch": 0.21750152718387294, "grad_norm": 0.3900339901447296, "learning_rate": 4.4387317851635264e-05, "loss": 4.3492, "step": 7121 }, { "epoch": 0.2175320708613317, "grad_norm": 0.3776836395263672, "learning_rate": 4.438580320450831e-05, "loss": 4.3612, "step": 7122 }, { "epoch": 0.21756261453879047, "grad_norm": 0.3707750737667084, "learning_rate": 4.438428837888631e-05, "loss": 4.4085, "step": 7123 }, { "epoch": 0.21759315821624925, "grad_norm": 0.38614070415496826, "learning_rate": 4.4382773374783196e-05, "loss": 4.4494, "step": 7124 }, { "epoch": 0.217623701893708, "grad_norm": 0.3915430009365082, "learning_rate": 4.438125819221292e-05, "loss": 4.3978, "step": 7125 }, { "epoch": 0.21765424557116678, "grad_norm": 0.3902095854282379, "learning_rate": 4.437974283118943e-05, "loss": 4.3759, "step": 7126 }, { "epoch": 0.21768478924862553, "grad_norm": 0.38476890325546265, "learning_rate": 4.4378227291726694e-05, "loss": 4.3546, "step": 7127 }, { "epoch": 0.2177153329260843, "grad_norm": 0.3930061161518097, "learning_rate": 4.4376711573838653e-05, "loss": 4.3511, "step": 7128 }, { "epoch": 0.21774587660354305, "grad_norm": 0.3804614543914795, "learning_rate": 4.4375195677539264e-05, "loss": 4.32, "step": 7129 }, { "epoch": 0.21777642028100183, "grad_norm": 0.37078192830085754, "learning_rate": 4.437367960284249e-05, "loss": 4.3204, "step": 7130 }, { "epoch": 0.2178069639584606, "grad_norm": 0.4843137562274933, "learning_rate": 4.4372163349762287e-05, "loss": 4.4014, "step": 7131 }, { "epoch": 0.21783750763591936, "grad_norm": 0.38050371408462524, "learning_rate": 4.437064691831261e-05, "loss": 4.4979, "step": 7132 }, { "epoch": 0.21786805131337814, "grad_norm": 0.39668458700180054, "learning_rate": 4.436913030850743e-05, "loss": 4.4082, "step": 7133 }, { "epoch": 0.21789859499083689, "grad_norm": 0.39670589566230774, "learning_rate": 4.4367613520360706e-05, "loss": 4.3675, "step": 7134 }, { "epoch": 0.21792913866829566, "grad_norm": 0.3781221807003021, "learning_rate": 4.4366096553886416e-05, "loss": 4.3601, "step": 7135 }, { "epoch": 0.21795968234575444, "grad_norm": 0.38631564378738403, "learning_rate": 4.4364579409098504e-05, "loss": 4.3559, "step": 7136 }, { "epoch": 0.2179902260232132, "grad_norm": 0.37460100650787354, "learning_rate": 4.436306208601096e-05, "loss": 4.3856, "step": 7137 }, { "epoch": 0.21802076970067197, "grad_norm": 0.3980661928653717, "learning_rate": 4.436154458463775e-05, "loss": 4.3154, "step": 7138 }, { "epoch": 0.21805131337813072, "grad_norm": 0.3884260952472687, "learning_rate": 4.4360026904992844e-05, "loss": 4.3714, "step": 7139 }, { "epoch": 0.2180818570555895, "grad_norm": 0.36932775378227234, "learning_rate": 4.435850904709021e-05, "loss": 4.2478, "step": 7140 }, { "epoch": 0.21811240073304827, "grad_norm": 0.38804471492767334, "learning_rate": 4.435699101094384e-05, "loss": 4.3683, "step": 7141 }, { "epoch": 0.21814294441050702, "grad_norm": 0.38460826873779297, "learning_rate": 4.4355472796567696e-05, "loss": 4.2839, "step": 7142 }, { "epoch": 0.2181734880879658, "grad_norm": 0.3677446246147156, "learning_rate": 4.4353954403975766e-05, "loss": 4.3922, "step": 7143 }, { "epoch": 0.21820403176542455, "grad_norm": 0.3784294128417969, "learning_rate": 4.435243583318203e-05, "loss": 4.3969, "step": 7144 }, { "epoch": 0.21823457544288333, "grad_norm": 0.3834185004234314, "learning_rate": 4.435091708420046e-05, "loss": 4.3862, "step": 7145 }, { "epoch": 0.21826511912034208, "grad_norm": 0.3760821223258972, "learning_rate": 4.434939815704504e-05, "loss": 4.3134, "step": 7146 }, { "epoch": 0.21829566279780085, "grad_norm": 0.3847289979457855, "learning_rate": 4.434787905172978e-05, "loss": 4.2823, "step": 7147 }, { "epoch": 0.21832620647525963, "grad_norm": 0.37113672494888306, "learning_rate": 4.4346359768268635e-05, "loss": 4.3599, "step": 7148 }, { "epoch": 0.21835675015271838, "grad_norm": 0.3848331868648529, "learning_rate": 4.4344840306675616e-05, "loss": 4.4461, "step": 7149 }, { "epoch": 0.21838729383017716, "grad_norm": 0.38488543033599854, "learning_rate": 4.434332066696471e-05, "loss": 4.3653, "step": 7150 }, { "epoch": 0.2184178375076359, "grad_norm": 0.3786883056163788, "learning_rate": 4.4341800849149896e-05, "loss": 4.416, "step": 7151 }, { "epoch": 0.2184483811850947, "grad_norm": 0.38485920429229736, "learning_rate": 4.434028085324518e-05, "loss": 4.4294, "step": 7152 }, { "epoch": 0.21847892486255346, "grad_norm": 0.3775574266910553, "learning_rate": 4.4338760679264554e-05, "loss": 4.3704, "step": 7153 }, { "epoch": 0.2185094685400122, "grad_norm": 0.3804085850715637, "learning_rate": 4.4337240327222017e-05, "loss": 4.4273, "step": 7154 }, { "epoch": 0.218540012217471, "grad_norm": 0.3788023293018341, "learning_rate": 4.433571979713157e-05, "loss": 4.3751, "step": 7155 }, { "epoch": 0.21857055589492974, "grad_norm": 0.4095972776412964, "learning_rate": 4.43341990890072e-05, "loss": 4.3943, "step": 7156 }, { "epoch": 0.21860109957238852, "grad_norm": 0.3794080317020416, "learning_rate": 4.4332678202862924e-05, "loss": 4.257, "step": 7157 }, { "epoch": 0.21863164324984727, "grad_norm": 0.3851058781147003, "learning_rate": 4.433115713871274e-05, "loss": 4.3094, "step": 7158 }, { "epoch": 0.21866218692730605, "grad_norm": 0.3774069845676422, "learning_rate": 4.432963589657065e-05, "loss": 4.3836, "step": 7159 }, { "epoch": 0.21869273060476482, "grad_norm": 0.3937806189060211, "learning_rate": 4.432811447645067e-05, "loss": 4.4103, "step": 7160 }, { "epoch": 0.21872327428222357, "grad_norm": 0.3811713755130768, "learning_rate": 4.4326592878366805e-05, "loss": 4.3382, "step": 7161 }, { "epoch": 0.21875381795968235, "grad_norm": 0.36970263719558716, "learning_rate": 4.432507110233305e-05, "loss": 4.3885, "step": 7162 }, { "epoch": 0.2187843616371411, "grad_norm": 0.37907910346984863, "learning_rate": 4.432354914836344e-05, "loss": 4.3527, "step": 7163 }, { "epoch": 0.21881490531459988, "grad_norm": 0.4081551432609558, "learning_rate": 4.432202701647197e-05, "loss": 4.4204, "step": 7164 }, { "epoch": 0.21884544899205866, "grad_norm": 0.4031103253364563, "learning_rate": 4.432050470667267e-05, "loss": 4.3801, "step": 7165 }, { "epoch": 0.2188759926695174, "grad_norm": 0.39291641116142273, "learning_rate": 4.431898221897955e-05, "loss": 4.407, "step": 7166 }, { "epoch": 0.21890653634697618, "grad_norm": 0.36472272872924805, "learning_rate": 4.431745955340662e-05, "loss": 4.3987, "step": 7167 }, { "epoch": 0.21893708002443493, "grad_norm": 0.3977838158607483, "learning_rate": 4.431593670996792e-05, "loss": 4.3245, "step": 7168 }, { "epoch": 0.2189676237018937, "grad_norm": 0.3906078040599823, "learning_rate": 4.431441368867745e-05, "loss": 4.3742, "step": 7169 }, { "epoch": 0.2189981673793525, "grad_norm": 0.3802950084209442, "learning_rate": 4.4312890489549244e-05, "loss": 4.3654, "step": 7170 }, { "epoch": 0.21902871105681124, "grad_norm": 0.3767176568508148, "learning_rate": 4.431136711259732e-05, "loss": 4.3724, "step": 7171 }, { "epoch": 0.21905925473427001, "grad_norm": 0.40502965450286865, "learning_rate": 4.430984355783572e-05, "loss": 4.3518, "step": 7172 }, { "epoch": 0.21908979841172876, "grad_norm": 0.37858253717422485, "learning_rate": 4.4308319825278454e-05, "loss": 4.2892, "step": 7173 }, { "epoch": 0.21912034208918754, "grad_norm": 0.3754473924636841, "learning_rate": 4.430679591493957e-05, "loss": 4.499, "step": 7174 }, { "epoch": 0.2191508857666463, "grad_norm": 0.39420196413993835, "learning_rate": 4.4305271826833087e-05, "loss": 4.4395, "step": 7175 }, { "epoch": 0.21918142944410507, "grad_norm": 0.38935768604278564, "learning_rate": 4.430374756097303e-05, "loss": 4.3978, "step": 7176 }, { "epoch": 0.21921197312156385, "grad_norm": 0.3856978118419647, "learning_rate": 4.430222311737345e-05, "loss": 4.3082, "step": 7177 }, { "epoch": 0.2192425167990226, "grad_norm": 0.3844062387943268, "learning_rate": 4.430069849604838e-05, "loss": 4.3652, "step": 7178 }, { "epoch": 0.21927306047648137, "grad_norm": 0.3851185441017151, "learning_rate": 4.4299173697011856e-05, "loss": 4.2922, "step": 7179 }, { "epoch": 0.21930360415394012, "grad_norm": 0.37492942810058594, "learning_rate": 4.4297648720277915e-05, "loss": 4.3114, "step": 7180 }, { "epoch": 0.2193341478313989, "grad_norm": 0.3774230182170868, "learning_rate": 4.42961235658606e-05, "loss": 4.273, "step": 7181 }, { "epoch": 0.21936469150885768, "grad_norm": 0.37443259358406067, "learning_rate": 4.4294598233773954e-05, "loss": 4.3092, "step": 7182 }, { "epoch": 0.21939523518631643, "grad_norm": 0.38994789123535156, "learning_rate": 4.429307272403203e-05, "loss": 4.3175, "step": 7183 }, { "epoch": 0.2194257788637752, "grad_norm": 0.3942069709300995, "learning_rate": 4.429154703664885e-05, "loss": 4.3864, "step": 7184 }, { "epoch": 0.21945632254123396, "grad_norm": 0.3811340034008026, "learning_rate": 4.429002117163848e-05, "loss": 4.2848, "step": 7185 }, { "epoch": 0.21948686621869273, "grad_norm": 0.3715560734272003, "learning_rate": 4.4288495129014984e-05, "loss": 4.3913, "step": 7186 }, { "epoch": 0.21951740989615148, "grad_norm": 0.3964807689189911, "learning_rate": 4.428696890879238e-05, "loss": 4.351, "step": 7187 }, { "epoch": 0.21954795357361026, "grad_norm": 0.38304734230041504, "learning_rate": 4.4285442510984744e-05, "loss": 4.3644, "step": 7188 }, { "epoch": 0.21957849725106904, "grad_norm": 0.37869584560394287, "learning_rate": 4.4283915935606124e-05, "loss": 4.4009, "step": 7189 }, { "epoch": 0.2196090409285278, "grad_norm": 0.39548853039741516, "learning_rate": 4.4282389182670574e-05, "loss": 4.4344, "step": 7190 }, { "epoch": 0.21963958460598657, "grad_norm": 0.39706382155418396, "learning_rate": 4.428086225219215e-05, "loss": 4.2733, "step": 7191 }, { "epoch": 0.21967012828344532, "grad_norm": 0.3889729380607605, "learning_rate": 4.427933514418492e-05, "loss": 4.3443, "step": 7192 }, { "epoch": 0.2197006719609041, "grad_norm": 0.403232216835022, "learning_rate": 4.427780785866294e-05, "loss": 4.4078, "step": 7193 }, { "epoch": 0.21973121563836287, "grad_norm": 0.37841272354125977, "learning_rate": 4.427628039564026e-05, "loss": 4.4131, "step": 7194 }, { "epoch": 0.21976175931582162, "grad_norm": 0.3998901844024658, "learning_rate": 4.427475275513096e-05, "loss": 4.3997, "step": 7195 }, { "epoch": 0.2197923029932804, "grad_norm": 0.38219937682151794, "learning_rate": 4.42732249371491e-05, "loss": 4.274, "step": 7196 }, { "epoch": 0.21982284667073915, "grad_norm": 0.3834400773048401, "learning_rate": 4.4271696941708755e-05, "loss": 4.3126, "step": 7197 }, { "epoch": 0.21985339034819792, "grad_norm": 0.3863794505596161, "learning_rate": 4.4270168768823984e-05, "loss": 4.3506, "step": 7198 }, { "epoch": 0.2198839340256567, "grad_norm": 0.37770554423332214, "learning_rate": 4.426864041850886e-05, "loss": 4.3816, "step": 7199 }, { "epoch": 0.21991447770311545, "grad_norm": 0.3988114893436432, "learning_rate": 4.4267111890777454e-05, "loss": 4.3858, "step": 7200 }, { "epoch": 0.21994502138057423, "grad_norm": 0.37427952885627747, "learning_rate": 4.426558318564386e-05, "loss": 4.2644, "step": 7201 }, { "epoch": 0.21997556505803298, "grad_norm": 0.3800545334815979, "learning_rate": 4.4264054303122114e-05, "loss": 4.3561, "step": 7202 }, { "epoch": 0.22000610873549176, "grad_norm": 0.37419450283050537, "learning_rate": 4.4262525243226324e-05, "loss": 4.4019, "step": 7203 }, { "epoch": 0.2200366524129505, "grad_norm": 0.3673171103000641, "learning_rate": 4.426099600597057e-05, "loss": 4.3463, "step": 7204 }, { "epoch": 0.22006719609040928, "grad_norm": 0.38569772243499756, "learning_rate": 4.4259466591368906e-05, "loss": 4.3323, "step": 7205 }, { "epoch": 0.22009773976786806, "grad_norm": 0.3816061019897461, "learning_rate": 4.425793699943544e-05, "loss": 4.4083, "step": 7206 }, { "epoch": 0.2201282834453268, "grad_norm": 0.39504384994506836, "learning_rate": 4.425640723018425e-05, "loss": 4.2697, "step": 7207 }, { "epoch": 0.2201588271227856, "grad_norm": 0.3880605697631836, "learning_rate": 4.425487728362941e-05, "loss": 4.3517, "step": 7208 }, { "epoch": 0.22018937080024434, "grad_norm": 0.3879750072956085, "learning_rate": 4.425334715978502e-05, "loss": 4.3483, "step": 7209 }, { "epoch": 0.22021991447770312, "grad_norm": 0.36904460191726685, "learning_rate": 4.425181685866516e-05, "loss": 4.2564, "step": 7210 }, { "epoch": 0.2202504581551619, "grad_norm": 0.3768385052680969, "learning_rate": 4.4250286380283926e-05, "loss": 4.3632, "step": 7211 }, { "epoch": 0.22028100183262064, "grad_norm": 0.38700926303863525, "learning_rate": 4.424875572465541e-05, "loss": 4.3829, "step": 7212 }, { "epoch": 0.22031154551007942, "grad_norm": 0.38440948724746704, "learning_rate": 4.4247224891793696e-05, "loss": 4.3407, "step": 7213 }, { "epoch": 0.22034208918753817, "grad_norm": 0.38519829511642456, "learning_rate": 4.424569388171289e-05, "loss": 4.3976, "step": 7214 }, { "epoch": 0.22037263286499695, "grad_norm": 0.3674139678478241, "learning_rate": 4.424416269442709e-05, "loss": 4.342, "step": 7215 }, { "epoch": 0.22040317654245573, "grad_norm": 0.4106805622577667, "learning_rate": 4.424263132995038e-05, "loss": 4.3634, "step": 7216 }, { "epoch": 0.22043372021991448, "grad_norm": 0.39219680428504944, "learning_rate": 4.424109978829688e-05, "loss": 4.4255, "step": 7217 }, { "epoch": 0.22046426389737325, "grad_norm": 0.38624268770217896, "learning_rate": 4.423956806948068e-05, "loss": 4.2746, "step": 7218 }, { "epoch": 0.220494807574832, "grad_norm": 0.3972055912017822, "learning_rate": 4.423803617351588e-05, "loss": 4.3816, "step": 7219 }, { "epoch": 0.22052535125229078, "grad_norm": 0.3819591701030731, "learning_rate": 4.423650410041659e-05, "loss": 4.354, "step": 7220 }, { "epoch": 0.22055589492974953, "grad_norm": 0.39346516132354736, "learning_rate": 4.423497185019692e-05, "loss": 4.4005, "step": 7221 }, { "epoch": 0.2205864386072083, "grad_norm": 0.3975733518600464, "learning_rate": 4.423343942287097e-05, "loss": 4.3877, "step": 7222 }, { "epoch": 0.22061698228466708, "grad_norm": 0.3856096565723419, "learning_rate": 4.423190681845286e-05, "loss": 4.3893, "step": 7223 }, { "epoch": 0.22064752596212583, "grad_norm": 0.38589856028556824, "learning_rate": 4.423037403695669e-05, "loss": 4.3989, "step": 7224 }, { "epoch": 0.2206780696395846, "grad_norm": 0.379731148481369, "learning_rate": 4.422884107839659e-05, "loss": 4.3191, "step": 7225 }, { "epoch": 0.22070861331704336, "grad_norm": 0.37700846791267395, "learning_rate": 4.4227307942786656e-05, "loss": 4.3607, "step": 7226 }, { "epoch": 0.22073915699450214, "grad_norm": 0.3930186629295349, "learning_rate": 4.4225774630141e-05, "loss": 4.3628, "step": 7227 }, { "epoch": 0.22076970067196092, "grad_norm": 0.3869374096393585, "learning_rate": 4.422424114047377e-05, "loss": 4.4053, "step": 7228 }, { "epoch": 0.22080024434941967, "grad_norm": 0.39111167192459106, "learning_rate": 4.4222707473799065e-05, "loss": 4.3943, "step": 7229 }, { "epoch": 0.22083078802687844, "grad_norm": 0.3775792717933655, "learning_rate": 4.4221173630131e-05, "loss": 4.4086, "step": 7230 }, { "epoch": 0.2208613317043372, "grad_norm": 0.3966130018234253, "learning_rate": 4.4219639609483715e-05, "loss": 4.3789, "step": 7231 }, { "epoch": 0.22089187538179597, "grad_norm": 0.38321542739868164, "learning_rate": 4.4218105411871325e-05, "loss": 4.1815, "step": 7232 }, { "epoch": 0.22092241905925472, "grad_norm": 0.3945852816104889, "learning_rate": 4.421657103730795e-05, "loss": 4.3483, "step": 7233 }, { "epoch": 0.2209529627367135, "grad_norm": 0.37796157598495483, "learning_rate": 4.421503648580774e-05, "loss": 4.3902, "step": 7234 }, { "epoch": 0.22098350641417228, "grad_norm": 0.3944447636604309, "learning_rate": 4.42135017573848e-05, "loss": 4.3488, "step": 7235 }, { "epoch": 0.22101405009163103, "grad_norm": 0.40575605630874634, "learning_rate": 4.421196685205327e-05, "loss": 4.4129, "step": 7236 }, { "epoch": 0.2210445937690898, "grad_norm": 0.3756587505340576, "learning_rate": 4.421043176982729e-05, "loss": 4.4053, "step": 7237 }, { "epoch": 0.22107513744654855, "grad_norm": 0.3771292269229889, "learning_rate": 4.4208896510720974e-05, "loss": 4.3385, "step": 7238 }, { "epoch": 0.22110568112400733, "grad_norm": 0.38101983070373535, "learning_rate": 4.420736107474848e-05, "loss": 4.3838, "step": 7239 }, { "epoch": 0.2211362248014661, "grad_norm": 0.38770508766174316, "learning_rate": 4.420582546192395e-05, "loss": 4.2296, "step": 7240 }, { "epoch": 0.22116676847892486, "grad_norm": 0.36885562539100647, "learning_rate": 4.420428967226149e-05, "loss": 4.3731, "step": 7241 }, { "epoch": 0.22119731215638364, "grad_norm": 0.38767749071121216, "learning_rate": 4.420275370577527e-05, "loss": 4.3284, "step": 7242 }, { "epoch": 0.22122785583384239, "grad_norm": 0.38498589396476746, "learning_rate": 4.4201217562479424e-05, "loss": 4.4211, "step": 7243 }, { "epoch": 0.22125839951130116, "grad_norm": 0.3888000547885895, "learning_rate": 4.419968124238809e-05, "loss": 4.3596, "step": 7244 }, { "epoch": 0.22128894318875994, "grad_norm": 0.3726462423801422, "learning_rate": 4.4198144745515425e-05, "loss": 4.3812, "step": 7245 }, { "epoch": 0.2213194868662187, "grad_norm": 0.3861471712589264, "learning_rate": 4.419660807187557e-05, "loss": 4.3069, "step": 7246 }, { "epoch": 0.22135003054367747, "grad_norm": 0.3836537301540375, "learning_rate": 4.419507122148267e-05, "loss": 4.3427, "step": 7247 }, { "epoch": 0.22138057422113622, "grad_norm": 0.38733309507369995, "learning_rate": 4.4193534194350886e-05, "loss": 4.3697, "step": 7248 }, { "epoch": 0.221411117898595, "grad_norm": 0.3705956041812897, "learning_rate": 4.4191996990494364e-05, "loss": 4.2958, "step": 7249 }, { "epoch": 0.22144166157605374, "grad_norm": 0.37560367584228516, "learning_rate": 4.419045960992726e-05, "loss": 4.3312, "step": 7250 }, { "epoch": 0.22147220525351252, "grad_norm": 0.3864402174949646, "learning_rate": 4.418892205266372e-05, "loss": 4.4166, "step": 7251 }, { "epoch": 0.2215027489309713, "grad_norm": 0.390729159116745, "learning_rate": 4.418738431871791e-05, "loss": 4.324, "step": 7252 }, { "epoch": 0.22153329260843005, "grad_norm": 0.37197813391685486, "learning_rate": 4.418584640810399e-05, "loss": 4.4119, "step": 7253 }, { "epoch": 0.22156383628588883, "grad_norm": 0.39742347598075867, "learning_rate": 4.418430832083612e-05, "loss": 4.4198, "step": 7254 }, { "epoch": 0.22159437996334758, "grad_norm": 0.3718373477458954, "learning_rate": 4.418277005692846e-05, "loss": 4.34, "step": 7255 }, { "epoch": 0.22162492364080635, "grad_norm": 0.3872128427028656, "learning_rate": 4.418123161639517e-05, "loss": 4.3571, "step": 7256 }, { "epoch": 0.22165546731826513, "grad_norm": 0.399437814950943, "learning_rate": 4.417969299925042e-05, "loss": 4.4621, "step": 7257 }, { "epoch": 0.22168601099572388, "grad_norm": 0.3881261944770813, "learning_rate": 4.417815420550837e-05, "loss": 4.3166, "step": 7258 }, { "epoch": 0.22171655467318266, "grad_norm": 0.39638134837150574, "learning_rate": 4.41766152351832e-05, "loss": 4.3613, "step": 7259 }, { "epoch": 0.2217470983506414, "grad_norm": 0.37707769870758057, "learning_rate": 4.417507608828907e-05, "loss": 4.409, "step": 7260 }, { "epoch": 0.22177764202810019, "grad_norm": 0.3838326334953308, "learning_rate": 4.417353676484016e-05, "loss": 4.3533, "step": 7261 }, { "epoch": 0.22180818570555894, "grad_norm": 0.3815280497074127, "learning_rate": 4.4171997264850636e-05, "loss": 4.3178, "step": 7262 }, { "epoch": 0.2218387293830177, "grad_norm": 0.4000099301338196, "learning_rate": 4.417045758833468e-05, "loss": 4.3636, "step": 7263 }, { "epoch": 0.2218692730604765, "grad_norm": 0.37248700857162476, "learning_rate": 4.416891773530646e-05, "loss": 4.3918, "step": 7264 }, { "epoch": 0.22189981673793524, "grad_norm": 0.37475886940956116, "learning_rate": 4.416737770578016e-05, "loss": 4.3126, "step": 7265 }, { "epoch": 0.22193036041539402, "grad_norm": 0.3813038468360901, "learning_rate": 4.4165837499769955e-05, "loss": 4.3686, "step": 7266 }, { "epoch": 0.22196090409285277, "grad_norm": 0.3830084502696991, "learning_rate": 4.416429711729003e-05, "loss": 4.3621, "step": 7267 }, { "epoch": 0.22199144777031155, "grad_norm": 0.3833886981010437, "learning_rate": 4.416275655835458e-05, "loss": 4.2861, "step": 7268 }, { "epoch": 0.22202199144777032, "grad_norm": 0.3790096044540405, "learning_rate": 4.416121582297776e-05, "loss": 4.4217, "step": 7269 }, { "epoch": 0.22205253512522907, "grad_norm": 0.3853486478328705, "learning_rate": 4.4159674911173784e-05, "loss": 4.3592, "step": 7270 }, { "epoch": 0.22208307880268785, "grad_norm": 0.38427218794822693, "learning_rate": 4.415813382295684e-05, "loss": 4.2401, "step": 7271 }, { "epoch": 0.2221136224801466, "grad_norm": 0.37881094217300415, "learning_rate": 4.4156592558341095e-05, "loss": 4.3767, "step": 7272 }, { "epoch": 0.22214416615760538, "grad_norm": 0.3844209611415863, "learning_rate": 4.4155051117340754e-05, "loss": 4.2816, "step": 7273 }, { "epoch": 0.22217470983506415, "grad_norm": 0.3892326056957245, "learning_rate": 4.4153509499970014e-05, "loss": 4.3783, "step": 7274 }, { "epoch": 0.2222052535125229, "grad_norm": 0.38481175899505615, "learning_rate": 4.415196770624306e-05, "loss": 4.337, "step": 7275 }, { "epoch": 0.22223579718998168, "grad_norm": 0.3936178684234619, "learning_rate": 4.4150425736174093e-05, "loss": 4.3793, "step": 7276 }, { "epoch": 0.22226634086744043, "grad_norm": 0.37715283036231995, "learning_rate": 4.414888358977731e-05, "loss": 4.3619, "step": 7277 }, { "epoch": 0.2222968845448992, "grad_norm": 0.38285765051841736, "learning_rate": 4.414734126706691e-05, "loss": 4.3523, "step": 7278 }, { "epoch": 0.22232742822235796, "grad_norm": 0.39074960350990295, "learning_rate": 4.4145798768057094e-05, "loss": 4.3804, "step": 7279 }, { "epoch": 0.22235797189981674, "grad_norm": 0.39190664887428284, "learning_rate": 4.414425609276207e-05, "loss": 4.401, "step": 7280 }, { "epoch": 0.22238851557727551, "grad_norm": 0.378680020570755, "learning_rate": 4.414271324119603e-05, "loss": 4.3507, "step": 7281 }, { "epoch": 0.22241905925473426, "grad_norm": 0.38210079073905945, "learning_rate": 4.414117021337319e-05, "loss": 4.3323, "step": 7282 }, { "epoch": 0.22244960293219304, "grad_norm": 0.3869526982307434, "learning_rate": 4.413962700930775e-05, "loss": 4.3556, "step": 7283 }, { "epoch": 0.2224801466096518, "grad_norm": 0.3844250738620758, "learning_rate": 4.4138083629013934e-05, "loss": 4.3834, "step": 7284 }, { "epoch": 0.22251069028711057, "grad_norm": 0.38556107878685, "learning_rate": 4.4136540072505935e-05, "loss": 4.4224, "step": 7285 }, { "epoch": 0.22254123396456935, "grad_norm": 0.3885752558708191, "learning_rate": 4.413499633979797e-05, "loss": 4.4056, "step": 7286 }, { "epoch": 0.2225717776420281, "grad_norm": 0.3893570601940155, "learning_rate": 4.4133452430904257e-05, "loss": 4.3386, "step": 7287 }, { "epoch": 0.22260232131948687, "grad_norm": 0.4019570052623749, "learning_rate": 4.413190834583902e-05, "loss": 4.3785, "step": 7288 }, { "epoch": 0.22263286499694562, "grad_norm": 0.3924458920955658, "learning_rate": 4.413036408461645e-05, "loss": 4.4356, "step": 7289 }, { "epoch": 0.2226634086744044, "grad_norm": 0.3780626058578491, "learning_rate": 4.4128819647250796e-05, "loss": 4.3754, "step": 7290 }, { "epoch": 0.22269395235186318, "grad_norm": 0.36772143840789795, "learning_rate": 4.4127275033756254e-05, "loss": 4.3204, "step": 7291 }, { "epoch": 0.22272449602932193, "grad_norm": 0.38093483448028564, "learning_rate": 4.412573024414707e-05, "loss": 4.347, "step": 7292 }, { "epoch": 0.2227550397067807, "grad_norm": 0.39039722084999084, "learning_rate": 4.412418527843744e-05, "loss": 4.4381, "step": 7293 }, { "epoch": 0.22278558338423946, "grad_norm": 0.37346982955932617, "learning_rate": 4.412264013664161e-05, "loss": 4.2811, "step": 7294 }, { "epoch": 0.22281612706169823, "grad_norm": 0.37499120831489563, "learning_rate": 4.41210948187738e-05, "loss": 4.3815, "step": 7295 }, { "epoch": 0.22284667073915698, "grad_norm": 0.3748958110809326, "learning_rate": 4.411954932484824e-05, "loss": 4.3392, "step": 7296 }, { "epoch": 0.22287721441661576, "grad_norm": 0.3774597942829132, "learning_rate": 4.411800365487916e-05, "loss": 4.3866, "step": 7297 }, { "epoch": 0.22290775809407454, "grad_norm": 0.38680699467658997, "learning_rate": 4.411645780888079e-05, "loss": 4.3222, "step": 7298 }, { "epoch": 0.2229383017715333, "grad_norm": 0.3733089566230774, "learning_rate": 4.411491178686736e-05, "loss": 4.3829, "step": 7299 }, { "epoch": 0.22296884544899206, "grad_norm": 0.37519267201423645, "learning_rate": 4.4113365588853105e-05, "loss": 4.3862, "step": 7300 }, { "epoch": 0.22299938912645081, "grad_norm": 0.3776358366012573, "learning_rate": 4.411181921485228e-05, "loss": 4.318, "step": 7301 }, { "epoch": 0.2230299328039096, "grad_norm": 0.37843018770217896, "learning_rate": 4.4110272664879095e-05, "loss": 4.3854, "step": 7302 }, { "epoch": 0.22306047648136837, "grad_norm": 0.37433767318725586, "learning_rate": 4.4108725938947815e-05, "loss": 4.3781, "step": 7303 }, { "epoch": 0.22309102015882712, "grad_norm": 0.38551175594329834, "learning_rate": 4.4107179037072666e-05, "loss": 4.271, "step": 7304 }, { "epoch": 0.2231215638362859, "grad_norm": 0.3834992051124573, "learning_rate": 4.410563195926789e-05, "loss": 4.3001, "step": 7305 }, { "epoch": 0.22315210751374465, "grad_norm": 0.37303170561790466, "learning_rate": 4.410408470554774e-05, "loss": 4.3954, "step": 7306 }, { "epoch": 0.22318265119120342, "grad_norm": 0.3864552676677704, "learning_rate": 4.410253727592647e-05, "loss": 4.3772, "step": 7307 }, { "epoch": 0.22321319486866217, "grad_norm": 0.3824940025806427, "learning_rate": 4.410098967041831e-05, "loss": 4.3499, "step": 7308 }, { "epoch": 0.22324373854612095, "grad_norm": 0.3885323107242584, "learning_rate": 4.409944188903752e-05, "loss": 4.2427, "step": 7309 }, { "epoch": 0.22327428222357973, "grad_norm": 0.3743108808994293, "learning_rate": 4.4097893931798344e-05, "loss": 4.4487, "step": 7310 }, { "epoch": 0.22330482590103848, "grad_norm": 0.393000066280365, "learning_rate": 4.409634579871505e-05, "loss": 4.2903, "step": 7311 }, { "epoch": 0.22333536957849726, "grad_norm": 0.38816171884536743, "learning_rate": 4.4094797489801865e-05, "loss": 4.4313, "step": 7312 }, { "epoch": 0.223365913255956, "grad_norm": 0.37406060099601746, "learning_rate": 4.409324900507308e-05, "loss": 4.3623, "step": 7313 }, { "epoch": 0.22339645693341478, "grad_norm": 0.37455540895462036, "learning_rate": 4.409170034454292e-05, "loss": 4.3472, "step": 7314 }, { "epoch": 0.22342700061087356, "grad_norm": 0.3806658983230591, "learning_rate": 4.409015150822566e-05, "loss": 4.3336, "step": 7315 }, { "epoch": 0.2234575442883323, "grad_norm": 0.38781991600990295, "learning_rate": 4.4088602496135565e-05, "loss": 4.4219, "step": 7316 }, { "epoch": 0.2234880879657911, "grad_norm": 0.3639446496963501, "learning_rate": 4.4087053308286896e-05, "loss": 4.4402, "step": 7317 }, { "epoch": 0.22351863164324984, "grad_norm": 0.3852636516094208, "learning_rate": 4.4085503944693906e-05, "loss": 4.3259, "step": 7318 }, { "epoch": 0.22354917532070862, "grad_norm": 0.3821796178817749, "learning_rate": 4.4083954405370874e-05, "loss": 4.453, "step": 7319 }, { "epoch": 0.2235797189981674, "grad_norm": 0.4017960727214813, "learning_rate": 4.4082404690332056e-05, "loss": 4.3512, "step": 7320 }, { "epoch": 0.22361026267562614, "grad_norm": 0.381877601146698, "learning_rate": 4.408085479959174e-05, "loss": 4.436, "step": 7321 }, { "epoch": 0.22364080635308492, "grad_norm": 0.3725229501724243, "learning_rate": 4.407930473316417e-05, "loss": 4.3061, "step": 7322 }, { "epoch": 0.22367135003054367, "grad_norm": 0.4039309322834015, "learning_rate": 4.407775449106364e-05, "loss": 4.344, "step": 7323 }, { "epoch": 0.22370189370800245, "grad_norm": 0.3958226442337036, "learning_rate": 4.407620407330441e-05, "loss": 4.3466, "step": 7324 }, { "epoch": 0.2237324373854612, "grad_norm": 0.37172043323516846, "learning_rate": 4.4074653479900765e-05, "loss": 4.3419, "step": 7325 }, { "epoch": 0.22376298106291997, "grad_norm": 0.39969345927238464, "learning_rate": 4.407310271086696e-05, "loss": 4.4466, "step": 7326 }, { "epoch": 0.22379352474037875, "grad_norm": 0.3955458402633667, "learning_rate": 4.4071551766217316e-05, "loss": 4.4115, "step": 7327 }, { "epoch": 0.2238240684178375, "grad_norm": 0.38944002985954285, "learning_rate": 4.407000064596608e-05, "loss": 4.3426, "step": 7328 }, { "epoch": 0.22385461209529628, "grad_norm": 0.3807593286037445, "learning_rate": 4.406844935012755e-05, "loss": 4.3908, "step": 7329 }, { "epoch": 0.22388515577275503, "grad_norm": 0.38404086232185364, "learning_rate": 4.406689787871599e-05, "loss": 4.4356, "step": 7330 }, { "epoch": 0.2239156994502138, "grad_norm": 0.3863130211830139, "learning_rate": 4.4065346231745706e-05, "loss": 4.4131, "step": 7331 }, { "epoch": 0.22394624312767258, "grad_norm": 0.38878950476646423, "learning_rate": 4.406379440923097e-05, "loss": 4.3331, "step": 7332 }, { "epoch": 0.22397678680513133, "grad_norm": 0.38704028725624084, "learning_rate": 4.406224241118609e-05, "loss": 4.4264, "step": 7333 }, { "epoch": 0.2240073304825901, "grad_norm": 0.387911319732666, "learning_rate": 4.406069023762534e-05, "loss": 4.3677, "step": 7334 }, { "epoch": 0.22403787416004886, "grad_norm": 0.3817611038684845, "learning_rate": 4.405913788856301e-05, "loss": 4.3014, "step": 7335 }, { "epoch": 0.22406841783750764, "grad_norm": 0.3871864080429077, "learning_rate": 4.40575853640134e-05, "loss": 4.4159, "step": 7336 }, { "epoch": 0.2240989615149664, "grad_norm": 0.3844921290874481, "learning_rate": 4.40560326639908e-05, "loss": 4.452, "step": 7337 }, { "epoch": 0.22412950519242517, "grad_norm": 0.38068923354148865, "learning_rate": 4.405447978850951e-05, "loss": 4.3507, "step": 7338 }, { "epoch": 0.22416004886988394, "grad_norm": 0.3994307219982147, "learning_rate": 4.405292673758383e-05, "loss": 4.3312, "step": 7339 }, { "epoch": 0.2241905925473427, "grad_norm": 0.3880048990249634, "learning_rate": 4.405137351122805e-05, "loss": 4.3626, "step": 7340 }, { "epoch": 0.22422113622480147, "grad_norm": 1.2189112901687622, "learning_rate": 4.40498201094565e-05, "loss": 4.3755, "step": 7341 }, { "epoch": 0.22425167990226022, "grad_norm": 0.38655886054039, "learning_rate": 4.404826653228344e-05, "loss": 4.2787, "step": 7342 }, { "epoch": 0.224282223579719, "grad_norm": 0.3912176191806793, "learning_rate": 4.404671277972321e-05, "loss": 4.4746, "step": 7343 }, { "epoch": 0.22431276725717778, "grad_norm": 0.38329654932022095, "learning_rate": 4.404515885179009e-05, "loss": 4.3741, "step": 7344 }, { "epoch": 0.22434331093463653, "grad_norm": 0.3813895285129547, "learning_rate": 4.4043604748498415e-05, "loss": 4.4178, "step": 7345 }, { "epoch": 0.2243738546120953, "grad_norm": 0.38269856572151184, "learning_rate": 4.4042050469862464e-05, "loss": 4.3773, "step": 7346 }, { "epoch": 0.22440439828955405, "grad_norm": 0.3928188979625702, "learning_rate": 4.4040496015896574e-05, "loss": 4.3452, "step": 7347 }, { "epoch": 0.22443494196701283, "grad_norm": 0.3862619996070862, "learning_rate": 4.4038941386615044e-05, "loss": 4.3735, "step": 7348 }, { "epoch": 0.2244654856444716, "grad_norm": 0.38668203353881836, "learning_rate": 4.403738658203219e-05, "loss": 4.3339, "step": 7349 }, { "epoch": 0.22449602932193036, "grad_norm": 0.3800432085990906, "learning_rate": 4.403583160216234e-05, "loss": 4.3043, "step": 7350 }, { "epoch": 0.22452657299938913, "grad_norm": 0.38132545351982117, "learning_rate": 4.4034276447019795e-05, "loss": 4.3846, "step": 7351 }, { "epoch": 0.22455711667684788, "grad_norm": 0.38061225414276123, "learning_rate": 4.403272111661888e-05, "loss": 4.2792, "step": 7352 }, { "epoch": 0.22458766035430666, "grad_norm": 0.38421785831451416, "learning_rate": 4.4031165610973915e-05, "loss": 4.4009, "step": 7353 }, { "epoch": 0.2246182040317654, "grad_norm": 0.6033231616020203, "learning_rate": 4.4029609930099226e-05, "loss": 4.3275, "step": 7354 }, { "epoch": 0.2246487477092242, "grad_norm": 0.37441691756248474, "learning_rate": 4.402805407400913e-05, "loss": 4.43, "step": 7355 }, { "epoch": 0.22467929138668297, "grad_norm": 0.3735823929309845, "learning_rate": 4.4026498042717956e-05, "loss": 4.3351, "step": 7356 }, { "epoch": 0.22470983506414172, "grad_norm": 0.38516828417778015, "learning_rate": 4.402494183624004e-05, "loss": 4.3195, "step": 7357 }, { "epoch": 0.2247403787416005, "grad_norm": 0.3900096118450165, "learning_rate": 4.4023385454589696e-05, "loss": 4.2937, "step": 7358 }, { "epoch": 0.22477092241905924, "grad_norm": 0.3824787139892578, "learning_rate": 4.402182889778126e-05, "loss": 4.2806, "step": 7359 }, { "epoch": 0.22480146609651802, "grad_norm": 0.3795916736125946, "learning_rate": 4.402027216582907e-05, "loss": 4.4009, "step": 7360 }, { "epoch": 0.2248320097739768, "grad_norm": 0.38708481192588806, "learning_rate": 4.401871525874745e-05, "loss": 4.35, "step": 7361 }, { "epoch": 0.22486255345143555, "grad_norm": 0.40495553612709045, "learning_rate": 4.401715817655075e-05, "loss": 4.3281, "step": 7362 }, { "epoch": 0.22489309712889433, "grad_norm": 0.38173747062683105, "learning_rate": 4.4015600919253286e-05, "loss": 4.3692, "step": 7363 }, { "epoch": 0.22492364080635308, "grad_norm": 0.38425561785697937, "learning_rate": 4.4014043486869415e-05, "loss": 4.3555, "step": 7364 }, { "epoch": 0.22495418448381185, "grad_norm": 0.377789169549942, "learning_rate": 4.401248587941347e-05, "loss": 4.3838, "step": 7365 }, { "epoch": 0.22498472816127063, "grad_norm": 0.3737274706363678, "learning_rate": 4.401092809689978e-05, "loss": 4.2268, "step": 7366 }, { "epoch": 0.22501527183872938, "grad_norm": 0.38478517532348633, "learning_rate": 4.400937013934272e-05, "loss": 4.38, "step": 7367 }, { "epoch": 0.22504581551618816, "grad_norm": 0.3772468864917755, "learning_rate": 4.40078120067566e-05, "loss": 4.3474, "step": 7368 }, { "epoch": 0.2250763591936469, "grad_norm": 0.38600537180900574, "learning_rate": 4.4006253699155784e-05, "loss": 4.354, "step": 7369 }, { "epoch": 0.22510690287110569, "grad_norm": 0.37260377407073975, "learning_rate": 4.400469521655463e-05, "loss": 4.333, "step": 7370 }, { "epoch": 0.22513744654856443, "grad_norm": 0.3740110993385315, "learning_rate": 4.400313655896746e-05, "loss": 4.3323, "step": 7371 }, { "epoch": 0.2251679902260232, "grad_norm": 0.38464590907096863, "learning_rate": 4.400157772640865e-05, "loss": 4.3565, "step": 7372 }, { "epoch": 0.225198533903482, "grad_norm": 0.37781891226768494, "learning_rate": 4.4000018718892544e-05, "loss": 4.3335, "step": 7373 }, { "epoch": 0.22522907758094074, "grad_norm": 0.37680327892303467, "learning_rate": 4.399845953643349e-05, "loss": 4.3088, "step": 7374 }, { "epoch": 0.22525962125839952, "grad_norm": 0.36112362146377563, "learning_rate": 4.399690017904586e-05, "loss": 4.3942, "step": 7375 }, { "epoch": 0.22529016493585827, "grad_norm": 0.39137792587280273, "learning_rate": 4.3995340646743995e-05, "loss": 4.3206, "step": 7376 }, { "epoch": 0.22532070861331704, "grad_norm": 0.38084667921066284, "learning_rate": 4.3993780939542265e-05, "loss": 4.3517, "step": 7377 }, { "epoch": 0.22535125229077582, "grad_norm": 0.39465779066085815, "learning_rate": 4.399222105745503e-05, "loss": 4.4368, "step": 7378 }, { "epoch": 0.22538179596823457, "grad_norm": 0.376547634601593, "learning_rate": 4.399066100049665e-05, "loss": 4.3309, "step": 7379 }, { "epoch": 0.22541233964569335, "grad_norm": 0.3765086233615875, "learning_rate": 4.3989100768681494e-05, "loss": 4.4274, "step": 7380 }, { "epoch": 0.2254428833231521, "grad_norm": 0.3818274140357971, "learning_rate": 4.398754036202392e-05, "loss": 4.3688, "step": 7381 }, { "epoch": 0.22547342700061088, "grad_norm": 0.37872767448425293, "learning_rate": 4.39859797805383e-05, "loss": 4.3626, "step": 7382 }, { "epoch": 0.22550397067806963, "grad_norm": 0.3779405653476715, "learning_rate": 4.3984419024239004e-05, "loss": 4.4299, "step": 7383 }, { "epoch": 0.2255345143555284, "grad_norm": 0.39019790291786194, "learning_rate": 4.39828580931404e-05, "loss": 4.2981, "step": 7384 }, { "epoch": 0.22556505803298718, "grad_norm": 0.4043363928794861, "learning_rate": 4.398129698725686e-05, "loss": 4.3627, "step": 7385 }, { "epoch": 0.22559560171044593, "grad_norm": 0.3790976107120514, "learning_rate": 4.397973570660276e-05, "loss": 4.3984, "step": 7386 }, { "epoch": 0.2256261453879047, "grad_norm": 0.3752617835998535, "learning_rate": 4.397817425119248e-05, "loss": 4.336, "step": 7387 }, { "epoch": 0.22565668906536346, "grad_norm": 0.3840654790401459, "learning_rate": 4.397661262104038e-05, "loss": 4.3813, "step": 7388 }, { "epoch": 0.22568723274282224, "grad_norm": 0.40089428424835205, "learning_rate": 4.397505081616087e-05, "loss": 4.3413, "step": 7389 }, { "epoch": 0.225717776420281, "grad_norm": 0.38521653413772583, "learning_rate": 4.397348883656829e-05, "loss": 4.3919, "step": 7390 }, { "epoch": 0.22574832009773976, "grad_norm": 0.3756844401359558, "learning_rate": 4.397192668227705e-05, "loss": 4.3837, "step": 7391 }, { "epoch": 0.22577886377519854, "grad_norm": 0.38444897532463074, "learning_rate": 4.397036435330153e-05, "loss": 4.2945, "step": 7392 }, { "epoch": 0.2258094074526573, "grad_norm": 0.3866959512233734, "learning_rate": 4.3968801849656114e-05, "loss": 4.4015, "step": 7393 }, { "epoch": 0.22583995113011607, "grad_norm": 0.37585529685020447, "learning_rate": 4.396723917135519e-05, "loss": 4.3998, "step": 7394 }, { "epoch": 0.22587049480757485, "grad_norm": 0.3935324549674988, "learning_rate": 4.396567631841313e-05, "loss": 4.298, "step": 7395 }, { "epoch": 0.2259010384850336, "grad_norm": 0.3789638876914978, "learning_rate": 4.3964113290844345e-05, "loss": 4.3791, "step": 7396 }, { "epoch": 0.22593158216249237, "grad_norm": 0.37284255027770996, "learning_rate": 4.3962550088663216e-05, "loss": 4.4129, "step": 7397 }, { "epoch": 0.22596212583995112, "grad_norm": 0.3771553933620453, "learning_rate": 4.396098671188415e-05, "loss": 4.3757, "step": 7398 }, { "epoch": 0.2259926695174099, "grad_norm": 0.38500410318374634, "learning_rate": 4.395942316052151e-05, "loss": 4.3837, "step": 7399 }, { "epoch": 0.22602321319486865, "grad_norm": 0.38154301047325134, "learning_rate": 4.3957859434589724e-05, "loss": 4.3503, "step": 7400 }, { "epoch": 0.22605375687232743, "grad_norm": 0.3925555348396301, "learning_rate": 4.395629553410318e-05, "loss": 4.3129, "step": 7401 }, { "epoch": 0.2260843005497862, "grad_norm": 0.3842985928058624, "learning_rate": 4.395473145907628e-05, "loss": 4.3966, "step": 7402 }, { "epoch": 0.22611484422724495, "grad_norm": 0.3823118507862091, "learning_rate": 4.395316720952342e-05, "loss": 4.3913, "step": 7403 }, { "epoch": 0.22614538790470373, "grad_norm": 0.3920469284057617, "learning_rate": 4.3951602785459e-05, "loss": 4.3676, "step": 7404 }, { "epoch": 0.22617593158216248, "grad_norm": 0.39950597286224365, "learning_rate": 4.395003818689742e-05, "loss": 4.3374, "step": 7405 }, { "epoch": 0.22620647525962126, "grad_norm": 0.37914377450942993, "learning_rate": 4.3948473413853116e-05, "loss": 4.3689, "step": 7406 }, { "epoch": 0.22623701893708004, "grad_norm": 0.385006308555603, "learning_rate": 4.394690846634047e-05, "loss": 4.3712, "step": 7407 }, { "epoch": 0.2262675626145388, "grad_norm": 0.410762220621109, "learning_rate": 4.394534334437388e-05, "loss": 4.4009, "step": 7408 }, { "epoch": 0.22629810629199756, "grad_norm": 0.39710533618927, "learning_rate": 4.3943778047967785e-05, "loss": 4.3778, "step": 7409 }, { "epoch": 0.2263286499694563, "grad_norm": 0.39855679869651794, "learning_rate": 4.3942212577136585e-05, "loss": 4.4036, "step": 7410 }, { "epoch": 0.2263591936469151, "grad_norm": 0.3853161036968231, "learning_rate": 4.3940646931894695e-05, "loss": 4.4001, "step": 7411 }, { "epoch": 0.22638973732437384, "grad_norm": 0.3872332274913788, "learning_rate": 4.393908111225653e-05, "loss": 4.4363, "step": 7412 }, { "epoch": 0.22642028100183262, "grad_norm": 0.3929193615913391, "learning_rate": 4.393751511823651e-05, "loss": 4.39, "step": 7413 }, { "epoch": 0.2264508246792914, "grad_norm": 0.37650349736213684, "learning_rate": 4.393594894984905e-05, "loss": 4.358, "step": 7414 }, { "epoch": 0.22648136835675015, "grad_norm": 0.3802952468395233, "learning_rate": 4.393438260710857e-05, "loss": 4.3996, "step": 7415 }, { "epoch": 0.22651191203420892, "grad_norm": 0.3812743127346039, "learning_rate": 4.3932816090029497e-05, "loss": 4.4642, "step": 7416 }, { "epoch": 0.22654245571166767, "grad_norm": 0.3762672245502472, "learning_rate": 4.393124939862625e-05, "loss": 4.3956, "step": 7417 }, { "epoch": 0.22657299938912645, "grad_norm": 0.38174477219581604, "learning_rate": 4.3929682532913264e-05, "loss": 4.3636, "step": 7418 }, { "epoch": 0.22660354306658523, "grad_norm": 0.3839252293109894, "learning_rate": 4.392811549290494e-05, "loss": 4.3005, "step": 7419 }, { "epoch": 0.22663408674404398, "grad_norm": 0.39306527376174927, "learning_rate": 4.3926548278615745e-05, "loss": 4.3247, "step": 7420 }, { "epoch": 0.22666463042150276, "grad_norm": 0.3826419413089752, "learning_rate": 4.3924980890060075e-05, "loss": 4.3451, "step": 7421 }, { "epoch": 0.2266951740989615, "grad_norm": 0.3770398795604706, "learning_rate": 4.392341332725238e-05, "loss": 4.3914, "step": 7422 }, { "epoch": 0.22672571777642028, "grad_norm": 0.3810080289840698, "learning_rate": 4.3921845590207096e-05, "loss": 4.4288, "step": 7423 }, { "epoch": 0.22675626145387906, "grad_norm": 0.36953264474868774, "learning_rate": 4.392027767893864e-05, "loss": 4.3544, "step": 7424 }, { "epoch": 0.2267868051313378, "grad_norm": 0.3755212724208832, "learning_rate": 4.391870959346147e-05, "loss": 4.3941, "step": 7425 }, { "epoch": 0.2268173488087966, "grad_norm": 0.3930457532405853, "learning_rate": 4.391714133379e-05, "loss": 4.4028, "step": 7426 }, { "epoch": 0.22684789248625534, "grad_norm": 0.3854157030582428, "learning_rate": 4.391557289993869e-05, "loss": 4.3446, "step": 7427 }, { "epoch": 0.22687843616371411, "grad_norm": 0.37966787815093994, "learning_rate": 4.391400429192198e-05, "loss": 4.3217, "step": 7428 }, { "epoch": 0.22690897984117286, "grad_norm": 0.38225558400154114, "learning_rate": 4.391243550975431e-05, "loss": 4.2987, "step": 7429 }, { "epoch": 0.22693952351863164, "grad_norm": 0.39889395236968994, "learning_rate": 4.3910866553450115e-05, "loss": 4.2986, "step": 7430 }, { "epoch": 0.22697006719609042, "grad_norm": 0.39073970913887024, "learning_rate": 4.390929742302385e-05, "loss": 4.3402, "step": 7431 }, { "epoch": 0.22700061087354917, "grad_norm": 0.40029409527778625, "learning_rate": 4.390772811848996e-05, "loss": 4.4185, "step": 7432 }, { "epoch": 0.22703115455100795, "grad_norm": 0.38644465804100037, "learning_rate": 4.39061586398629e-05, "loss": 4.3824, "step": 7433 }, { "epoch": 0.2270616982284667, "grad_norm": 0.3768864870071411, "learning_rate": 4.390458898715711e-05, "loss": 4.261, "step": 7434 }, { "epoch": 0.22709224190592547, "grad_norm": 0.4166802763938904, "learning_rate": 4.390301916038706e-05, "loss": 4.2915, "step": 7435 }, { "epoch": 0.22712278558338425, "grad_norm": 0.38264933228492737, "learning_rate": 4.390144915956719e-05, "loss": 4.3807, "step": 7436 }, { "epoch": 0.227153329260843, "grad_norm": 0.39819177985191345, "learning_rate": 4.389987898471195e-05, "loss": 4.3642, "step": 7437 }, { "epoch": 0.22718387293830178, "grad_norm": 0.38250404596328735, "learning_rate": 4.3898308635835814e-05, "loss": 4.3487, "step": 7438 }, { "epoch": 0.22721441661576053, "grad_norm": 0.38835054636001587, "learning_rate": 4.389673811295324e-05, "loss": 4.3869, "step": 7439 }, { "epoch": 0.2272449602932193, "grad_norm": 0.38523879647254944, "learning_rate": 4.389516741607867e-05, "loss": 4.3719, "step": 7440 }, { "epoch": 0.22727550397067808, "grad_norm": 0.3744996190071106, "learning_rate": 4.389359654522659e-05, "loss": 4.3684, "step": 7441 }, { "epoch": 0.22730604764813683, "grad_norm": 0.38425201177597046, "learning_rate": 4.389202550041145e-05, "loss": 4.3611, "step": 7442 }, { "epoch": 0.2273365913255956, "grad_norm": 0.3761027157306671, "learning_rate": 4.389045428164771e-05, "loss": 4.3775, "step": 7443 }, { "epoch": 0.22736713500305436, "grad_norm": 0.3853130340576172, "learning_rate": 4.388888288894985e-05, "loss": 4.4167, "step": 7444 }, { "epoch": 0.22739767868051314, "grad_norm": 0.3755721151828766, "learning_rate": 4.3887311322332336e-05, "loss": 4.407, "step": 7445 }, { "epoch": 0.2274282223579719, "grad_norm": 0.3784348666667938, "learning_rate": 4.388573958180963e-05, "loss": 4.3631, "step": 7446 }, { "epoch": 0.22745876603543067, "grad_norm": 0.3888155519962311, "learning_rate": 4.388416766739621e-05, "loss": 4.4664, "step": 7447 }, { "epoch": 0.22748930971288944, "grad_norm": 0.38067519664764404, "learning_rate": 4.388259557910656e-05, "loss": 4.3554, "step": 7448 }, { "epoch": 0.2275198533903482, "grad_norm": 0.387551873922348, "learning_rate": 4.388102331695513e-05, "loss": 4.398, "step": 7449 }, { "epoch": 0.22755039706780697, "grad_norm": 0.38571518659591675, "learning_rate": 4.3879450880956416e-05, "loss": 4.3672, "step": 7450 }, { "epoch": 0.22758094074526572, "grad_norm": 0.3813524842262268, "learning_rate": 4.3877878271124894e-05, "loss": 4.3326, "step": 7451 }, { "epoch": 0.2276114844227245, "grad_norm": 0.38197270035743713, "learning_rate": 4.3876305487475036e-05, "loss": 4.2771, "step": 7452 }, { "epoch": 0.22764202810018327, "grad_norm": 0.3861806094646454, "learning_rate": 4.3874732530021335e-05, "loss": 4.4328, "step": 7453 }, { "epoch": 0.22767257177764202, "grad_norm": 0.40168848633766174, "learning_rate": 4.387315939877826e-05, "loss": 4.3195, "step": 7454 }, { "epoch": 0.2277031154551008, "grad_norm": 0.37934157252311707, "learning_rate": 4.387158609376031e-05, "loss": 4.3674, "step": 7455 }, { "epoch": 0.22773365913255955, "grad_norm": 0.3770461976528168, "learning_rate": 4.387001261498196e-05, "loss": 4.3897, "step": 7456 }, { "epoch": 0.22776420281001833, "grad_norm": 0.3775775134563446, "learning_rate": 4.38684389624577e-05, "loss": 4.3866, "step": 7457 }, { "epoch": 0.22779474648747708, "grad_norm": 0.3680552840232849, "learning_rate": 4.386686513620202e-05, "loss": 4.2928, "step": 7458 }, { "epoch": 0.22782529016493586, "grad_norm": 0.3969310522079468, "learning_rate": 4.386529113622942e-05, "loss": 4.3555, "step": 7459 }, { "epoch": 0.22785583384239463, "grad_norm": 0.3710169196128845, "learning_rate": 4.386371696255437e-05, "loss": 4.2725, "step": 7460 }, { "epoch": 0.22788637751985338, "grad_norm": 0.39338719844818115, "learning_rate": 4.386214261519139e-05, "loss": 4.4121, "step": 7461 }, { "epoch": 0.22791692119731216, "grad_norm": 0.38357576727867126, "learning_rate": 4.386056809415497e-05, "loss": 4.4379, "step": 7462 }, { "epoch": 0.2279474648747709, "grad_norm": 0.375576376914978, "learning_rate": 4.385899339945959e-05, "loss": 4.4733, "step": 7463 }, { "epoch": 0.2279780085522297, "grad_norm": 0.38215139508247375, "learning_rate": 4.385741853111978e-05, "loss": 4.3345, "step": 7464 }, { "epoch": 0.22800855222968847, "grad_norm": 0.38308656215667725, "learning_rate": 4.385584348915e-05, "loss": 4.3463, "step": 7465 }, { "epoch": 0.22803909590714722, "grad_norm": 0.3838683068752289, "learning_rate": 4.3854268273564785e-05, "loss": 4.3886, "step": 7466 }, { "epoch": 0.228069639584606, "grad_norm": 0.3834410011768341, "learning_rate": 4.385269288437863e-05, "loss": 4.386, "step": 7467 }, { "epoch": 0.22810018326206474, "grad_norm": 0.3783167600631714, "learning_rate": 4.385111732160604e-05, "loss": 4.3421, "step": 7468 }, { "epoch": 0.22813072693952352, "grad_norm": 0.38424983620643616, "learning_rate": 4.3849541585261514e-05, "loss": 4.3757, "step": 7469 }, { "epoch": 0.2281612706169823, "grad_norm": 0.36771804094314575, "learning_rate": 4.3847965675359564e-05, "loss": 4.3807, "step": 7470 }, { "epoch": 0.22819181429444105, "grad_norm": 0.37012434005737305, "learning_rate": 4.384638959191471e-05, "loss": 4.2914, "step": 7471 }, { "epoch": 0.22822235797189983, "grad_norm": 0.39512836933135986, "learning_rate": 4.384481333494146e-05, "loss": 4.3107, "step": 7472 }, { "epoch": 0.22825290164935857, "grad_norm": 0.3694372773170471, "learning_rate": 4.384323690445432e-05, "loss": 4.3205, "step": 7473 }, { "epoch": 0.22828344532681735, "grad_norm": 0.37903186678886414, "learning_rate": 4.384166030046781e-05, "loss": 4.2798, "step": 7474 }, { "epoch": 0.2283139890042761, "grad_norm": 0.38430458307266235, "learning_rate": 4.384008352299644e-05, "loss": 4.2955, "step": 7475 }, { "epoch": 0.22834453268173488, "grad_norm": 0.3676183819770813, "learning_rate": 4.3838506572054746e-05, "loss": 4.3947, "step": 7476 }, { "epoch": 0.22837507635919366, "grad_norm": 0.3785143196582794, "learning_rate": 4.3836929447657224e-05, "loss": 4.3291, "step": 7477 }, { "epoch": 0.2284056200366524, "grad_norm": 0.3765997588634491, "learning_rate": 4.383535214981842e-05, "loss": 4.3285, "step": 7478 }, { "epoch": 0.22843616371411118, "grad_norm": 0.3866611123085022, "learning_rate": 4.383377467855284e-05, "loss": 4.3596, "step": 7479 }, { "epoch": 0.22846670739156993, "grad_norm": 0.3665941655635834, "learning_rate": 4.383219703387501e-05, "loss": 4.4048, "step": 7480 }, { "epoch": 0.2284972510690287, "grad_norm": 0.37821733951568604, "learning_rate": 4.3830619215799464e-05, "loss": 4.3766, "step": 7481 }, { "epoch": 0.2285277947464875, "grad_norm": 0.3677181899547577, "learning_rate": 4.382904122434072e-05, "loss": 4.4108, "step": 7482 }, { "epoch": 0.22855833842394624, "grad_norm": 0.380848228931427, "learning_rate": 4.382746305951332e-05, "loss": 4.4029, "step": 7483 }, { "epoch": 0.22858888210140502, "grad_norm": 0.3803642690181732, "learning_rate": 4.382588472133178e-05, "loss": 4.3991, "step": 7484 }, { "epoch": 0.22861942577886377, "grad_norm": 0.37873825430870056, "learning_rate": 4.382430620981064e-05, "loss": 4.361, "step": 7485 }, { "epoch": 0.22864996945632254, "grad_norm": 0.3715992867946625, "learning_rate": 4.3822727524964434e-05, "loss": 4.4091, "step": 7486 }, { "epoch": 0.2286805131337813, "grad_norm": 0.38930702209472656, "learning_rate": 4.382114866680771e-05, "loss": 4.323, "step": 7487 }, { "epoch": 0.22871105681124007, "grad_norm": 0.3723128139972687, "learning_rate": 4.381956963535499e-05, "loss": 4.359, "step": 7488 }, { "epoch": 0.22874160048869885, "grad_norm": 0.3786458671092987, "learning_rate": 4.38179904306208e-05, "loss": 4.4021, "step": 7489 }, { "epoch": 0.2287721441661576, "grad_norm": 0.36428841948509216, "learning_rate": 4.381641105261971e-05, "loss": 4.4097, "step": 7490 }, { "epoch": 0.22880268784361638, "grad_norm": 0.376018762588501, "learning_rate": 4.3814831501366246e-05, "loss": 4.3555, "step": 7491 }, { "epoch": 0.22883323152107513, "grad_norm": 0.3896365165710449, "learning_rate": 4.381325177687495e-05, "loss": 4.2952, "step": 7492 }, { "epoch": 0.2288637751985339, "grad_norm": 0.3926129937171936, "learning_rate": 4.3811671879160385e-05, "loss": 4.3983, "step": 7493 }, { "epoch": 0.22889431887599268, "grad_norm": 0.38126346468925476, "learning_rate": 4.3810091808237074e-05, "loss": 4.3629, "step": 7494 }, { "epoch": 0.22892486255345143, "grad_norm": 0.38261210918426514, "learning_rate": 4.380851156411958e-05, "loss": 4.327, "step": 7495 }, { "epoch": 0.2289554062309102, "grad_norm": 0.38974326848983765, "learning_rate": 4.380693114682245e-05, "loss": 4.3647, "step": 7496 }, { "epoch": 0.22898594990836896, "grad_norm": 0.3854213058948517, "learning_rate": 4.380535055636024e-05, "loss": 4.388, "step": 7497 }, { "epoch": 0.22901649358582774, "grad_norm": 0.3792496621608734, "learning_rate": 4.3803769792747484e-05, "loss": 4.4342, "step": 7498 }, { "epoch": 0.2290470372632865, "grad_norm": 0.37858542799949646, "learning_rate": 4.380218885599876e-05, "loss": 4.3623, "step": 7499 }, { "epoch": 0.22907758094074526, "grad_norm": 0.3928380012512207, "learning_rate": 4.3800607746128624e-05, "loss": 4.328, "step": 7500 }, { "epoch": 0.22910812461820404, "grad_norm": 0.3892550766468048, "learning_rate": 4.3799026463151615e-05, "loss": 4.4204, "step": 7501 }, { "epoch": 0.2291386682956628, "grad_norm": 0.3796616196632385, "learning_rate": 4.379744500708231e-05, "loss": 4.299, "step": 7502 }, { "epoch": 0.22916921197312157, "grad_norm": 0.4017066955566406, "learning_rate": 4.379586337793526e-05, "loss": 4.317, "step": 7503 }, { "epoch": 0.22919975565058032, "grad_norm": 0.3907511830329895, "learning_rate": 4.379428157572504e-05, "loss": 4.3244, "step": 7504 }, { "epoch": 0.2292302993280391, "grad_norm": 0.385285884141922, "learning_rate": 4.3792699600466205e-05, "loss": 4.3565, "step": 7505 }, { "epoch": 0.22926084300549787, "grad_norm": 0.3776879608631134, "learning_rate": 4.3791117452173314e-05, "loss": 4.3376, "step": 7506 }, { "epoch": 0.22929138668295662, "grad_norm": 0.37760311365127563, "learning_rate": 4.3789535130860946e-05, "loss": 4.2817, "step": 7507 }, { "epoch": 0.2293219303604154, "grad_norm": 0.38801857829093933, "learning_rate": 4.378795263654367e-05, "loss": 4.343, "step": 7508 }, { "epoch": 0.22935247403787415, "grad_norm": 0.3782876133918762, "learning_rate": 4.378636996923605e-05, "loss": 4.39, "step": 7509 }, { "epoch": 0.22938301771533293, "grad_norm": 0.376252144575119, "learning_rate": 4.378478712895267e-05, "loss": 4.277, "step": 7510 }, { "epoch": 0.2294135613927917, "grad_norm": 0.3739373981952667, "learning_rate": 4.3783204115708084e-05, "loss": 4.3552, "step": 7511 }, { "epoch": 0.22944410507025045, "grad_norm": 0.3879033327102661, "learning_rate": 4.3781620929516896e-05, "loss": 4.3671, "step": 7512 }, { "epoch": 0.22947464874770923, "grad_norm": 0.37778767943382263, "learning_rate": 4.378003757039366e-05, "loss": 4.3382, "step": 7513 }, { "epoch": 0.22950519242516798, "grad_norm": 0.3801458775997162, "learning_rate": 4.377845403835297e-05, "loss": 4.3995, "step": 7514 }, { "epoch": 0.22953573610262676, "grad_norm": 0.38829296827316284, "learning_rate": 4.377687033340939e-05, "loss": 4.3783, "step": 7515 }, { "epoch": 0.22956627978008554, "grad_norm": 0.3766031861305237, "learning_rate": 4.377528645557751e-05, "loss": 4.3854, "step": 7516 }, { "epoch": 0.22959682345754429, "grad_norm": 0.39176028966903687, "learning_rate": 4.377370240487191e-05, "loss": 4.4094, "step": 7517 }, { "epoch": 0.22962736713500306, "grad_norm": 0.3838873505592346, "learning_rate": 4.377211818130719e-05, "loss": 4.3238, "step": 7518 }, { "epoch": 0.2296579108124618, "grad_norm": 0.3702404797077179, "learning_rate": 4.3770533784897925e-05, "loss": 4.3309, "step": 7519 }, { "epoch": 0.2296884544899206, "grad_norm": 0.37395262718200684, "learning_rate": 4.37689492156587e-05, "loss": 4.3505, "step": 7520 }, { "epoch": 0.22971899816737934, "grad_norm": 0.3846184015274048, "learning_rate": 4.376736447360411e-05, "loss": 4.3569, "step": 7521 }, { "epoch": 0.22974954184483812, "grad_norm": 0.38148993253707886, "learning_rate": 4.3765779558748756e-05, "loss": 4.4511, "step": 7522 }, { "epoch": 0.2297800855222969, "grad_norm": 0.38998323678970337, "learning_rate": 4.37641944711072e-05, "loss": 4.3393, "step": 7523 }, { "epoch": 0.22981062919975564, "grad_norm": 0.3776419758796692, "learning_rate": 4.376260921069408e-05, "loss": 4.3697, "step": 7524 }, { "epoch": 0.22984117287721442, "grad_norm": 0.3672977089881897, "learning_rate": 4.376102377752396e-05, "loss": 4.2826, "step": 7525 }, { "epoch": 0.22987171655467317, "grad_norm": 0.3743589222431183, "learning_rate": 4.375943817161145e-05, "loss": 4.3396, "step": 7526 }, { "epoch": 0.22990226023213195, "grad_norm": 0.3731088936328888, "learning_rate": 4.375785239297114e-05, "loss": 4.4236, "step": 7527 }, { "epoch": 0.22993280390959073, "grad_norm": 0.3858288526535034, "learning_rate": 4.375626644161764e-05, "loss": 4.3748, "step": 7528 }, { "epoch": 0.22996334758704948, "grad_norm": 0.40287476778030396, "learning_rate": 4.375468031756557e-05, "loss": 4.4217, "step": 7529 }, { "epoch": 0.22999389126450825, "grad_norm": 0.3724273443222046, "learning_rate": 4.37530940208295e-05, "loss": 4.4111, "step": 7530 }, { "epoch": 0.230024434941967, "grad_norm": 0.3622615933418274, "learning_rate": 4.3751507551424055e-05, "loss": 4.3943, "step": 7531 }, { "epoch": 0.23005497861942578, "grad_norm": 0.38138121366500854, "learning_rate": 4.374992090936383e-05, "loss": 4.3137, "step": 7532 }, { "epoch": 0.23008552229688453, "grad_norm": 0.3811790943145752, "learning_rate": 4.3748334094663456e-05, "loss": 4.3076, "step": 7533 }, { "epoch": 0.2301160659743433, "grad_norm": 0.3742063641548157, "learning_rate": 4.374674710733753e-05, "loss": 4.3957, "step": 7534 }, { "epoch": 0.2301466096518021, "grad_norm": 0.3811294734477997, "learning_rate": 4.374515994740065e-05, "loss": 4.3857, "step": 7535 }, { "epoch": 0.23017715332926084, "grad_norm": 0.39529985189437866, "learning_rate": 4.374357261486745e-05, "loss": 4.3559, "step": 7536 }, { "epoch": 0.2302076970067196, "grad_norm": 0.3820917010307312, "learning_rate": 4.374198510975255e-05, "loss": 4.3003, "step": 7537 }, { "epoch": 0.23023824068417836, "grad_norm": 0.3967095911502838, "learning_rate": 4.3740397432070555e-05, "loss": 4.3205, "step": 7538 }, { "epoch": 0.23026878436163714, "grad_norm": 0.3911973237991333, "learning_rate": 4.373880958183608e-05, "loss": 4.3165, "step": 7539 }, { "epoch": 0.23029932803909592, "grad_norm": 0.3864220380783081, "learning_rate": 4.373722155906375e-05, "loss": 4.4228, "step": 7540 }, { "epoch": 0.23032987171655467, "grad_norm": 0.3753587305545807, "learning_rate": 4.373563336376819e-05, "loss": 4.3285, "step": 7541 }, { "epoch": 0.23036041539401345, "grad_norm": 0.3938602805137634, "learning_rate": 4.3734044995964025e-05, "loss": 4.2794, "step": 7542 }, { "epoch": 0.2303909590714722, "grad_norm": 0.401251882314682, "learning_rate": 4.373245645566587e-05, "loss": 4.4074, "step": 7543 }, { "epoch": 0.23042150274893097, "grad_norm": 0.37307649850845337, "learning_rate": 4.373086774288836e-05, "loss": 4.3243, "step": 7544 }, { "epoch": 0.23045204642638975, "grad_norm": 0.37200042605400085, "learning_rate": 4.3729278857646116e-05, "loss": 4.2844, "step": 7545 }, { "epoch": 0.2304825901038485, "grad_norm": 0.39050745964050293, "learning_rate": 4.372768979995377e-05, "loss": 4.4351, "step": 7546 }, { "epoch": 0.23051313378130728, "grad_norm": 0.37728556990623474, "learning_rate": 4.372610056982597e-05, "loss": 4.3652, "step": 7547 }, { "epoch": 0.23054367745876603, "grad_norm": 0.3750688433647156, "learning_rate": 4.372451116727731e-05, "loss": 4.4085, "step": 7548 }, { "epoch": 0.2305742211362248, "grad_norm": 0.38502204418182373, "learning_rate": 4.372292159232247e-05, "loss": 4.394, "step": 7549 }, { "epoch": 0.23060476481368355, "grad_norm": 0.3848962187767029, "learning_rate": 4.3721331844976056e-05, "loss": 4.3656, "step": 7550 }, { "epoch": 0.23063530849114233, "grad_norm": 0.38594895601272583, "learning_rate": 4.371974192525272e-05, "loss": 4.3913, "step": 7551 }, { "epoch": 0.2306658521686011, "grad_norm": 0.38112178444862366, "learning_rate": 4.371815183316709e-05, "loss": 4.3439, "step": 7552 }, { "epoch": 0.23069639584605986, "grad_norm": 0.37847596406936646, "learning_rate": 4.37165615687338e-05, "loss": 4.3899, "step": 7553 }, { "epoch": 0.23072693952351864, "grad_norm": 0.39276984333992004, "learning_rate": 4.371497113196753e-05, "loss": 4.3657, "step": 7554 }, { "epoch": 0.2307574832009774, "grad_norm": 0.38372135162353516, "learning_rate": 4.3713380522882884e-05, "loss": 4.3788, "step": 7555 }, { "epoch": 0.23078802687843616, "grad_norm": 0.3823340833187103, "learning_rate": 4.371178974149452e-05, "loss": 4.3681, "step": 7556 }, { "epoch": 0.23081857055589494, "grad_norm": 0.38178855180740356, "learning_rate": 4.371019878781709e-05, "loss": 4.3814, "step": 7557 }, { "epoch": 0.2308491142333537, "grad_norm": 0.3754444420337677, "learning_rate": 4.370860766186524e-05, "loss": 4.2886, "step": 7558 }, { "epoch": 0.23087965791081247, "grad_norm": 0.3835233151912689, "learning_rate": 4.370701636365362e-05, "loss": 4.2328, "step": 7559 }, { "epoch": 0.23091020158827122, "grad_norm": 0.39739683270454407, "learning_rate": 4.370542489319689e-05, "loss": 4.3454, "step": 7560 }, { "epoch": 0.23094074526573, "grad_norm": 0.37632760405540466, "learning_rate": 4.3703833250509686e-05, "loss": 4.4453, "step": 7561 }, { "epoch": 0.23097128894318875, "grad_norm": 0.37659433484077454, "learning_rate": 4.370224143560667e-05, "loss": 4.3283, "step": 7562 }, { "epoch": 0.23100183262064752, "grad_norm": 0.38642922043800354, "learning_rate": 4.370064944850251e-05, "loss": 4.3982, "step": 7563 }, { "epoch": 0.2310323762981063, "grad_norm": 0.37886106967926025, "learning_rate": 4.369905728921186e-05, "loss": 4.3963, "step": 7564 }, { "epoch": 0.23106291997556505, "grad_norm": 0.38227856159210205, "learning_rate": 4.369746495774936e-05, "loss": 4.2961, "step": 7565 }, { "epoch": 0.23109346365302383, "grad_norm": 0.3911778926849365, "learning_rate": 4.3695872454129694e-05, "loss": 4.3202, "step": 7566 }, { "epoch": 0.23112400733048258, "grad_norm": 0.37356334924697876, "learning_rate": 4.369427977836752e-05, "loss": 4.4412, "step": 7567 }, { "epoch": 0.23115455100794136, "grad_norm": 0.38296329975128174, "learning_rate": 4.36926869304775e-05, "loss": 4.3741, "step": 7568 }, { "epoch": 0.23118509468540013, "grad_norm": 0.3762243390083313, "learning_rate": 4.36910939104743e-05, "loss": 4.3871, "step": 7569 }, { "epoch": 0.23121563836285888, "grad_norm": 0.38359352946281433, "learning_rate": 4.368950071837259e-05, "loss": 4.2853, "step": 7570 }, { "epoch": 0.23124618204031766, "grad_norm": 0.38253822922706604, "learning_rate": 4.368790735418703e-05, "loss": 4.39, "step": 7571 }, { "epoch": 0.2312767257177764, "grad_norm": 0.37661871314048767, "learning_rate": 4.368631381793231e-05, "loss": 4.3824, "step": 7572 }, { "epoch": 0.2313072693952352, "grad_norm": 0.38048118352890015, "learning_rate": 4.368472010962308e-05, "loss": 4.3572, "step": 7573 }, { "epoch": 0.23133781307269397, "grad_norm": 0.3976784348487854, "learning_rate": 4.368312622927403e-05, "loss": 4.2566, "step": 7574 }, { "epoch": 0.23136835675015271, "grad_norm": 0.3812856078147888, "learning_rate": 4.368153217689983e-05, "loss": 4.41, "step": 7575 }, { "epoch": 0.2313989004276115, "grad_norm": 0.39336076378822327, "learning_rate": 4.367993795251516e-05, "loss": 4.3811, "step": 7576 }, { "epoch": 0.23142944410507024, "grad_norm": 0.37754106521606445, "learning_rate": 4.36783435561347e-05, "loss": 4.3446, "step": 7577 }, { "epoch": 0.23145998778252902, "grad_norm": 0.39901670813560486, "learning_rate": 4.367674898777312e-05, "loss": 4.411, "step": 7578 }, { "epoch": 0.23149053145998777, "grad_norm": 0.3775501251220703, "learning_rate": 4.3675154247445116e-05, "loss": 4.3433, "step": 7579 }, { "epoch": 0.23152107513744655, "grad_norm": 0.3907816708087921, "learning_rate": 4.3673559335165356e-05, "loss": 4.2924, "step": 7580 }, { "epoch": 0.23155161881490532, "grad_norm": 0.375244140625, "learning_rate": 4.367196425094855e-05, "loss": 4.3366, "step": 7581 }, { "epoch": 0.23158216249236407, "grad_norm": 0.38202497363090515, "learning_rate": 4.367036899480936e-05, "loss": 4.347, "step": 7582 }, { "epoch": 0.23161270616982285, "grad_norm": 0.3919948637485504, "learning_rate": 4.3668773566762475e-05, "loss": 4.3608, "step": 7583 }, { "epoch": 0.2316432498472816, "grad_norm": 0.37088268995285034, "learning_rate": 4.36671779668226e-05, "loss": 4.4411, "step": 7584 }, { "epoch": 0.23167379352474038, "grad_norm": 0.3749975860118866, "learning_rate": 4.366558219500443e-05, "loss": 4.3441, "step": 7585 }, { "epoch": 0.23170433720219916, "grad_norm": 0.37844792008399963, "learning_rate": 4.366398625132263e-05, "loss": 4.4064, "step": 7586 }, { "epoch": 0.2317348808796579, "grad_norm": 0.3885854184627533, "learning_rate": 4.366239013579193e-05, "loss": 4.3442, "step": 7587 }, { "epoch": 0.23176542455711668, "grad_norm": 0.37351006269454956, "learning_rate": 4.3660793848426995e-05, "loss": 4.4029, "step": 7588 }, { "epoch": 0.23179596823457543, "grad_norm": 0.38429027795791626, "learning_rate": 4.365919738924255e-05, "loss": 4.3921, "step": 7589 }, { "epoch": 0.2318265119120342, "grad_norm": 0.389568954706192, "learning_rate": 4.365760075825326e-05, "loss": 4.3605, "step": 7590 }, { "epoch": 0.231857055589493, "grad_norm": 0.3867895007133484, "learning_rate": 4.3656003955473864e-05, "loss": 4.4362, "step": 7591 }, { "epoch": 0.23188759926695174, "grad_norm": 0.37474632263183594, "learning_rate": 4.3654406980919044e-05, "loss": 4.238, "step": 7592 }, { "epoch": 0.23191814294441052, "grad_norm": 0.38235941529273987, "learning_rate": 4.3652809834603506e-05, "loss": 4.3364, "step": 7593 }, { "epoch": 0.23194868662186927, "grad_norm": 0.36777523159980774, "learning_rate": 4.365121251654196e-05, "loss": 4.3142, "step": 7594 }, { "epoch": 0.23197923029932804, "grad_norm": 0.382455438375473, "learning_rate": 4.364961502674911e-05, "loss": 4.2719, "step": 7595 }, { "epoch": 0.2320097739767868, "grad_norm": 0.3701004683971405, "learning_rate": 4.364801736523967e-05, "loss": 4.3944, "step": 7596 }, { "epoch": 0.23204031765424557, "grad_norm": 0.3810102343559265, "learning_rate": 4.3646419532028334e-05, "loss": 4.3706, "step": 7597 }, { "epoch": 0.23207086133170435, "grad_norm": 0.37109124660491943, "learning_rate": 4.364482152712983e-05, "loss": 4.3982, "step": 7598 }, { "epoch": 0.2321014050091631, "grad_norm": 0.37669071555137634, "learning_rate": 4.3643223350558875e-05, "loss": 4.4016, "step": 7599 }, { "epoch": 0.23213194868662188, "grad_norm": 0.3900139331817627, "learning_rate": 4.3641625002330175e-05, "loss": 4.3555, "step": 7600 }, { "epoch": 0.23216249236408062, "grad_norm": 0.3793511688709259, "learning_rate": 4.3640026482458454e-05, "loss": 4.3691, "step": 7601 }, { "epoch": 0.2321930360415394, "grad_norm": 0.3841911256313324, "learning_rate": 4.363842779095842e-05, "loss": 4.3677, "step": 7602 }, { "epoch": 0.23222357971899818, "grad_norm": 0.37549611926078796, "learning_rate": 4.3636828927844795e-05, "loss": 4.3359, "step": 7603 }, { "epoch": 0.23225412339645693, "grad_norm": 0.3703928589820862, "learning_rate": 4.36352298931323e-05, "loss": 4.3972, "step": 7604 }, { "epoch": 0.2322846670739157, "grad_norm": 0.3895407021045685, "learning_rate": 4.363363068683568e-05, "loss": 4.4259, "step": 7605 }, { "epoch": 0.23231521075137446, "grad_norm": 0.38298216462135315, "learning_rate": 4.363203130896962e-05, "loss": 4.3529, "step": 7606 }, { "epoch": 0.23234575442883323, "grad_norm": 0.38811126351356506, "learning_rate": 4.3630431759548884e-05, "loss": 4.3989, "step": 7607 }, { "epoch": 0.23237629810629198, "grad_norm": 0.37027764320373535, "learning_rate": 4.362883203858818e-05, "loss": 4.4173, "step": 7608 }, { "epoch": 0.23240684178375076, "grad_norm": 0.3761351704597473, "learning_rate": 4.3627232146102235e-05, "loss": 4.2932, "step": 7609 }, { "epoch": 0.23243738546120954, "grad_norm": 0.3913845419883728, "learning_rate": 4.3625632082105796e-05, "loss": 4.2978, "step": 7610 }, { "epoch": 0.2324679291386683, "grad_norm": 0.38441401720046997, "learning_rate": 4.362403184661358e-05, "loss": 4.383, "step": 7611 }, { "epoch": 0.23249847281612707, "grad_norm": 0.3725701570510864, "learning_rate": 4.362243143964033e-05, "loss": 4.3389, "step": 7612 }, { "epoch": 0.23252901649358582, "grad_norm": 0.38407841324806213, "learning_rate": 4.3620830861200776e-05, "loss": 4.3369, "step": 7613 }, { "epoch": 0.2325595601710446, "grad_norm": 0.37431207299232483, "learning_rate": 4.361923011130966e-05, "loss": 4.3707, "step": 7614 }, { "epoch": 0.23259010384850337, "grad_norm": 0.3820478618144989, "learning_rate": 4.3617629189981724e-05, "loss": 4.3846, "step": 7615 }, { "epoch": 0.23262064752596212, "grad_norm": 0.3840683102607727, "learning_rate": 4.36160280972317e-05, "loss": 4.3366, "step": 7616 }, { "epoch": 0.2326511912034209, "grad_norm": 0.37979984283447266, "learning_rate": 4.361442683307433e-05, "loss": 4.3682, "step": 7617 }, { "epoch": 0.23268173488087965, "grad_norm": 0.38236573338508606, "learning_rate": 4.3612825397524365e-05, "loss": 4.3672, "step": 7618 }, { "epoch": 0.23271227855833843, "grad_norm": 0.37561386823654175, "learning_rate": 4.361122379059655e-05, "loss": 4.2799, "step": 7619 }, { "epoch": 0.2327428222357972, "grad_norm": 0.3868814706802368, "learning_rate": 4.3609622012305624e-05, "loss": 4.3899, "step": 7620 }, { "epoch": 0.23277336591325595, "grad_norm": 0.39205363392829895, "learning_rate": 4.3608020062666345e-05, "loss": 4.3086, "step": 7621 }, { "epoch": 0.23280390959071473, "grad_norm": 0.396070659160614, "learning_rate": 4.360641794169344e-05, "loss": 4.3576, "step": 7622 }, { "epoch": 0.23283445326817348, "grad_norm": 0.3884665071964264, "learning_rate": 4.3604815649401696e-05, "loss": 4.3304, "step": 7623 }, { "epoch": 0.23286499694563226, "grad_norm": 0.38005319237709045, "learning_rate": 4.360321318580585e-05, "loss": 4.3094, "step": 7624 }, { "epoch": 0.232895540623091, "grad_norm": 0.3905373811721802, "learning_rate": 4.360161055092066e-05, "loss": 4.4071, "step": 7625 }, { "epoch": 0.23292608430054978, "grad_norm": 0.3873605728149414, "learning_rate": 4.360000774476086e-05, "loss": 4.341, "step": 7626 }, { "epoch": 0.23295662797800856, "grad_norm": 0.3821406066417694, "learning_rate": 4.359840476734123e-05, "loss": 4.3431, "step": 7627 }, { "epoch": 0.2329871716554673, "grad_norm": 0.37882182002067566, "learning_rate": 4.3596801618676536e-05, "loss": 4.3685, "step": 7628 }, { "epoch": 0.2330177153329261, "grad_norm": 0.3732980191707611, "learning_rate": 4.359519829878152e-05, "loss": 4.4108, "step": 7629 }, { "epoch": 0.23304825901038484, "grad_norm": 0.3791508376598358, "learning_rate": 4.359359480767096e-05, "loss": 4.3728, "step": 7630 }, { "epoch": 0.23307880268784362, "grad_norm": 0.39530718326568604, "learning_rate": 4.35919911453596e-05, "loss": 4.4304, "step": 7631 }, { "epoch": 0.2331093463653024, "grad_norm": 0.36955350637435913, "learning_rate": 4.359038731186222e-05, "loss": 4.3719, "step": 7632 }, { "epoch": 0.23313989004276114, "grad_norm": 0.3946397006511688, "learning_rate": 4.3588783307193593e-05, "loss": 4.3856, "step": 7633 }, { "epoch": 0.23317043372021992, "grad_norm": 0.37611037492752075, "learning_rate": 4.3587179131368485e-05, "loss": 4.425, "step": 7634 }, { "epoch": 0.23320097739767867, "grad_norm": 0.36825835704803467, "learning_rate": 4.358557478440165e-05, "loss": 4.3699, "step": 7635 }, { "epoch": 0.23323152107513745, "grad_norm": 0.3809547424316406, "learning_rate": 4.3583970266307876e-05, "loss": 4.3551, "step": 7636 }, { "epoch": 0.2332620647525962, "grad_norm": 0.38112178444862366, "learning_rate": 4.358236557710193e-05, "loss": 4.3717, "step": 7637 }, { "epoch": 0.23329260843005498, "grad_norm": 0.3646893799304962, "learning_rate": 4.3580760716798594e-05, "loss": 4.3734, "step": 7638 }, { "epoch": 0.23332315210751375, "grad_norm": 0.3705843687057495, "learning_rate": 4.3579155685412645e-05, "loss": 4.3063, "step": 7639 }, { "epoch": 0.2333536957849725, "grad_norm": 0.3752652704715729, "learning_rate": 4.357755048295886e-05, "loss": 4.4275, "step": 7640 }, { "epoch": 0.23338423946243128, "grad_norm": 0.38198143243789673, "learning_rate": 4.3575945109452005e-05, "loss": 4.4073, "step": 7641 }, { "epoch": 0.23341478313989003, "grad_norm": 0.3806532025337219, "learning_rate": 4.357433956490687e-05, "loss": 4.3421, "step": 7642 }, { "epoch": 0.2334453268173488, "grad_norm": 0.37366923689842224, "learning_rate": 4.357273384933825e-05, "loss": 4.3034, "step": 7643 }, { "epoch": 0.23347587049480759, "grad_norm": 0.3762403428554535, "learning_rate": 4.3571127962760925e-05, "loss": 4.3702, "step": 7644 }, { "epoch": 0.23350641417226634, "grad_norm": 0.383281409740448, "learning_rate": 4.356952190518967e-05, "loss": 4.377, "step": 7645 }, { "epoch": 0.2335369578497251, "grad_norm": 0.3857268691062927, "learning_rate": 4.3567915676639274e-05, "loss": 4.3869, "step": 7646 }, { "epoch": 0.23356750152718386, "grad_norm": 0.38004323840141296, "learning_rate": 4.3566309277124536e-05, "loss": 4.3818, "step": 7647 }, { "epoch": 0.23359804520464264, "grad_norm": 0.37595421075820923, "learning_rate": 4.356470270666024e-05, "loss": 4.3429, "step": 7648 }, { "epoch": 0.23362858888210142, "grad_norm": 0.37125879526138306, "learning_rate": 4.356309596526119e-05, "loss": 4.3278, "step": 7649 }, { "epoch": 0.23365913255956017, "grad_norm": 0.38486447930336, "learning_rate": 4.3561489052942164e-05, "loss": 4.373, "step": 7650 }, { "epoch": 0.23368967623701895, "grad_norm": 0.3748518228530884, "learning_rate": 4.355988196971797e-05, "loss": 4.319, "step": 7651 }, { "epoch": 0.2337202199144777, "grad_norm": 0.382488876581192, "learning_rate": 4.35582747156034e-05, "loss": 4.3991, "step": 7652 }, { "epoch": 0.23375076359193647, "grad_norm": 0.3799755275249481, "learning_rate": 4.355666729061324e-05, "loss": 4.3461, "step": 7653 }, { "epoch": 0.23378130726939522, "grad_norm": 0.36824020743370056, "learning_rate": 4.3555059694762316e-05, "loss": 4.4068, "step": 7654 }, { "epoch": 0.233811850946854, "grad_norm": 0.37439244985580444, "learning_rate": 4.355345192806541e-05, "loss": 4.3622, "step": 7655 }, { "epoch": 0.23384239462431278, "grad_norm": 0.3773443400859833, "learning_rate": 4.355184399053735e-05, "loss": 4.3565, "step": 7656 }, { "epoch": 0.23387293830177153, "grad_norm": 0.3876146972179413, "learning_rate": 4.35502358821929e-05, "loss": 4.3773, "step": 7657 }, { "epoch": 0.2339034819792303, "grad_norm": 0.37819820642471313, "learning_rate": 4.35486276030469e-05, "loss": 4.2181, "step": 7658 }, { "epoch": 0.23393402565668905, "grad_norm": 0.37755340337753296, "learning_rate": 4.3547019153114155e-05, "loss": 4.3046, "step": 7659 }, { "epoch": 0.23396456933414783, "grad_norm": 0.38495323061943054, "learning_rate": 4.354541053240947e-05, "loss": 4.3697, "step": 7660 }, { "epoch": 0.2339951130116066, "grad_norm": 0.4132660925388336, "learning_rate": 4.3543801740947645e-05, "loss": 4.3689, "step": 7661 }, { "epoch": 0.23402565668906536, "grad_norm": 0.3810148239135742, "learning_rate": 4.354219277874351e-05, "loss": 4.2797, "step": 7662 }, { "epoch": 0.23405620036652414, "grad_norm": 0.3866206407546997, "learning_rate": 4.354058364581187e-05, "loss": 4.4095, "step": 7663 }, { "epoch": 0.2340867440439829, "grad_norm": 0.3866916298866272, "learning_rate": 4.3538974342167544e-05, "loss": 4.2461, "step": 7664 }, { "epoch": 0.23411728772144166, "grad_norm": 0.4124705493450165, "learning_rate": 4.3537364867825345e-05, "loss": 4.3068, "step": 7665 }, { "epoch": 0.23414783139890044, "grad_norm": 0.3892253041267395, "learning_rate": 4.35357552228001e-05, "loss": 4.3482, "step": 7666 }, { "epoch": 0.2341783750763592, "grad_norm": 0.37238505482673645, "learning_rate": 4.353414540710663e-05, "loss": 4.2711, "step": 7667 }, { "epoch": 0.23420891875381797, "grad_norm": 0.3752419054508209, "learning_rate": 4.3532535420759754e-05, "loss": 4.3697, "step": 7668 }, { "epoch": 0.23423946243127672, "grad_norm": 0.3908306658267975, "learning_rate": 4.353092526377429e-05, "loss": 4.2717, "step": 7669 }, { "epoch": 0.2342700061087355, "grad_norm": 0.39787882566452026, "learning_rate": 4.352931493616508e-05, "loss": 4.3713, "step": 7670 }, { "epoch": 0.23430054978619425, "grad_norm": 0.385795921087265, "learning_rate": 4.352770443794693e-05, "loss": 4.4538, "step": 7671 }, { "epoch": 0.23433109346365302, "grad_norm": 0.38637223839759827, "learning_rate": 4.352609376913468e-05, "loss": 4.3488, "step": 7672 }, { "epoch": 0.2343616371411118, "grad_norm": 0.3899838924407959, "learning_rate": 4.352448292974316e-05, "loss": 4.3912, "step": 7673 }, { "epoch": 0.23439218081857055, "grad_norm": 0.3994702398777008, "learning_rate": 4.352287191978721e-05, "loss": 4.3513, "step": 7674 }, { "epoch": 0.23442272449602933, "grad_norm": 0.4063411355018616, "learning_rate": 4.3521260739281646e-05, "loss": 4.336, "step": 7675 }, { "epoch": 0.23445326817348808, "grad_norm": 0.37587061524391174, "learning_rate": 4.3519649388241315e-05, "loss": 4.321, "step": 7676 }, { "epoch": 0.23448381185094685, "grad_norm": 0.37555739283561707, "learning_rate": 4.351803786668105e-05, "loss": 4.1987, "step": 7677 }, { "epoch": 0.23451435552840563, "grad_norm": 0.3904743492603302, "learning_rate": 4.3516426174615686e-05, "loss": 4.3427, "step": 7678 }, { "epoch": 0.23454489920586438, "grad_norm": 0.39407485723495483, "learning_rate": 4.351481431206007e-05, "loss": 4.3328, "step": 7679 }, { "epoch": 0.23457544288332316, "grad_norm": 0.40040653944015503, "learning_rate": 4.351320227902904e-05, "loss": 4.3523, "step": 7680 }, { "epoch": 0.2346059865607819, "grad_norm": 0.3842999339103699, "learning_rate": 4.3511590075537434e-05, "loss": 4.3761, "step": 7681 }, { "epoch": 0.2346365302382407, "grad_norm": 0.39634063839912415, "learning_rate": 4.35099777016001e-05, "loss": 4.2566, "step": 7682 }, { "epoch": 0.23466707391569944, "grad_norm": 0.39453819394111633, "learning_rate": 4.350836515723189e-05, "loss": 4.3504, "step": 7683 }, { "epoch": 0.23469761759315821, "grad_norm": 0.38772326707839966, "learning_rate": 4.350675244244764e-05, "loss": 4.3301, "step": 7684 }, { "epoch": 0.234728161270617, "grad_norm": 0.4739828407764435, "learning_rate": 4.350513955726221e-05, "loss": 4.3588, "step": 7685 }, { "epoch": 0.23475870494807574, "grad_norm": 0.38211849331855774, "learning_rate": 4.350352650169044e-05, "loss": 4.3306, "step": 7686 }, { "epoch": 0.23478924862553452, "grad_norm": 0.3867216110229492, "learning_rate": 4.350191327574719e-05, "loss": 4.4606, "step": 7687 }, { "epoch": 0.23481979230299327, "grad_norm": 0.3775610327720642, "learning_rate": 4.350029987944732e-05, "loss": 4.3826, "step": 7688 }, { "epoch": 0.23485033598045205, "grad_norm": 0.38221660256385803, "learning_rate": 4.349868631280566e-05, "loss": 4.3629, "step": 7689 }, { "epoch": 0.23488087965791082, "grad_norm": 0.3803935945034027, "learning_rate": 4.34970725758371e-05, "loss": 4.3508, "step": 7690 }, { "epoch": 0.23491142333536957, "grad_norm": 0.37755918502807617, "learning_rate": 4.3495458668556474e-05, "loss": 4.314, "step": 7691 }, { "epoch": 0.23494196701282835, "grad_norm": 0.37984699010849, "learning_rate": 4.3493844590978655e-05, "loss": 4.3627, "step": 7692 }, { "epoch": 0.2349725106902871, "grad_norm": 0.3829807639122009, "learning_rate": 4.3492230343118504e-05, "loss": 4.3414, "step": 7693 }, { "epoch": 0.23500305436774588, "grad_norm": 0.38859090209007263, "learning_rate": 4.349061592499087e-05, "loss": 4.3338, "step": 7694 }, { "epoch": 0.23503359804520466, "grad_norm": 0.37738898396492004, "learning_rate": 4.3489001336610635e-05, "loss": 4.3329, "step": 7695 }, { "epoch": 0.2350641417226634, "grad_norm": 0.3801710903644562, "learning_rate": 4.348738657799266e-05, "loss": 4.3809, "step": 7696 }, { "epoch": 0.23509468540012218, "grad_norm": 0.3831639587879181, "learning_rate": 4.3485771649151804e-05, "loss": 4.3941, "step": 7697 }, { "epoch": 0.23512522907758093, "grad_norm": 0.38763928413391113, "learning_rate": 4.348415655010295e-05, "loss": 4.4168, "step": 7698 }, { "epoch": 0.2351557727550397, "grad_norm": 0.37246277928352356, "learning_rate": 4.3482541280860955e-05, "loss": 4.3435, "step": 7699 }, { "epoch": 0.23518631643249846, "grad_norm": 0.39249786734580994, "learning_rate": 4.3480925841440715e-05, "loss": 4.3421, "step": 7700 }, { "epoch": 0.23521686010995724, "grad_norm": 0.3991323411464691, "learning_rate": 4.347931023185707e-05, "loss": 4.3644, "step": 7701 }, { "epoch": 0.23524740378741602, "grad_norm": 0.38601115345954895, "learning_rate": 4.3477694452124926e-05, "loss": 4.351, "step": 7702 }, { "epoch": 0.23527794746487476, "grad_norm": 0.3745500445365906, "learning_rate": 4.347607850225915e-05, "loss": 4.358, "step": 7703 }, { "epoch": 0.23530849114233354, "grad_norm": 0.3849572539329529, "learning_rate": 4.347446238227462e-05, "loss": 4.4335, "step": 7704 }, { "epoch": 0.2353390348197923, "grad_norm": 0.38834071159362793, "learning_rate": 4.347284609218621e-05, "loss": 4.3647, "step": 7705 }, { "epoch": 0.23536957849725107, "grad_norm": 0.3852819800376892, "learning_rate": 4.347122963200881e-05, "loss": 4.3609, "step": 7706 }, { "epoch": 0.23540012217470985, "grad_norm": 0.3872893750667572, "learning_rate": 4.3469613001757306e-05, "loss": 4.3557, "step": 7707 }, { "epoch": 0.2354306658521686, "grad_norm": 0.38443729281425476, "learning_rate": 4.346799620144657e-05, "loss": 4.3807, "step": 7708 }, { "epoch": 0.23546120952962737, "grad_norm": 0.3813024163246155, "learning_rate": 4.346637923109151e-05, "loss": 4.2847, "step": 7709 }, { "epoch": 0.23549175320708612, "grad_norm": 0.38028228282928467, "learning_rate": 4.3464762090707e-05, "loss": 4.3251, "step": 7710 }, { "epoch": 0.2355222968845449, "grad_norm": 0.3825351893901825, "learning_rate": 4.346314478030792e-05, "loss": 4.3784, "step": 7711 }, { "epoch": 0.23555284056200365, "grad_norm": 0.3717947006225586, "learning_rate": 4.346152729990919e-05, "loss": 4.4233, "step": 7712 }, { "epoch": 0.23558338423946243, "grad_norm": 0.38504138588905334, "learning_rate": 4.345990964952567e-05, "loss": 4.3546, "step": 7713 }, { "epoch": 0.2356139279169212, "grad_norm": 0.39322102069854736, "learning_rate": 4.345829182917228e-05, "loss": 4.4107, "step": 7714 }, { "epoch": 0.23564447159437996, "grad_norm": 0.38027307391166687, "learning_rate": 4.3456673838863904e-05, "loss": 4.4055, "step": 7715 }, { "epoch": 0.23567501527183873, "grad_norm": 0.38768231868743896, "learning_rate": 4.345505567861544e-05, "loss": 4.4465, "step": 7716 }, { "epoch": 0.23570555894929748, "grad_norm": 0.37018251419067383, "learning_rate": 4.3453437348441796e-05, "loss": 4.4159, "step": 7717 }, { "epoch": 0.23573610262675626, "grad_norm": 0.37628841400146484, "learning_rate": 4.345181884835786e-05, "loss": 4.3347, "step": 7718 }, { "epoch": 0.23576664630421504, "grad_norm": 0.37697187066078186, "learning_rate": 4.3450200178378545e-05, "loss": 4.3775, "step": 7719 }, { "epoch": 0.2357971899816738, "grad_norm": 0.37081456184387207, "learning_rate": 4.3448581338518754e-05, "loss": 4.3285, "step": 7720 }, { "epoch": 0.23582773365913257, "grad_norm": 0.37376439571380615, "learning_rate": 4.3446962328793384e-05, "loss": 4.3457, "step": 7721 }, { "epoch": 0.23585827733659132, "grad_norm": 0.36810606718063354, "learning_rate": 4.344534314921735e-05, "loss": 4.2878, "step": 7722 }, { "epoch": 0.2358888210140501, "grad_norm": 0.37171217799186707, "learning_rate": 4.3443723799805556e-05, "loss": 4.3321, "step": 7723 }, { "epoch": 0.23591936469150887, "grad_norm": 0.3844967484474182, "learning_rate": 4.3442104280572914e-05, "loss": 4.3477, "step": 7724 }, { "epoch": 0.23594990836896762, "grad_norm": 0.3899426758289337, "learning_rate": 4.344048459153434e-05, "loss": 4.4171, "step": 7725 }, { "epoch": 0.2359804520464264, "grad_norm": 0.37207651138305664, "learning_rate": 4.343886473270473e-05, "loss": 4.3739, "step": 7726 }, { "epoch": 0.23601099572388515, "grad_norm": 0.3702429533004761, "learning_rate": 4.343724470409903e-05, "loss": 4.3359, "step": 7727 }, { "epoch": 0.23604153940134392, "grad_norm": 0.3821173310279846, "learning_rate": 4.343562450573213e-05, "loss": 4.4189, "step": 7728 }, { "epoch": 0.23607208307880267, "grad_norm": 0.3638280928134918, "learning_rate": 4.3434004137618956e-05, "loss": 4.3726, "step": 7729 }, { "epoch": 0.23610262675626145, "grad_norm": 0.3773541748523712, "learning_rate": 4.343238359977443e-05, "loss": 4.4263, "step": 7730 }, { "epoch": 0.23613317043372023, "grad_norm": 0.3980938494205475, "learning_rate": 4.343076289221347e-05, "loss": 4.4738, "step": 7731 }, { "epoch": 0.23616371411117898, "grad_norm": 0.3779374063014984, "learning_rate": 4.3429142014950994e-05, "loss": 4.4021, "step": 7732 }, { "epoch": 0.23619425778863776, "grad_norm": 0.3813480734825134, "learning_rate": 4.342752096800194e-05, "loss": 4.3632, "step": 7733 }, { "epoch": 0.2362248014660965, "grad_norm": 0.37967416644096375, "learning_rate": 4.342589975138123e-05, "loss": 4.4032, "step": 7734 }, { "epoch": 0.23625534514355528, "grad_norm": 0.3874136209487915, "learning_rate": 4.342427836510378e-05, "loss": 4.3706, "step": 7735 }, { "epoch": 0.23628588882101406, "grad_norm": 0.37965473532676697, "learning_rate": 4.342265680918453e-05, "loss": 4.3231, "step": 7736 }, { "epoch": 0.2363164324984728, "grad_norm": 0.3804449439048767, "learning_rate": 4.3421035083638404e-05, "loss": 4.2858, "step": 7737 }, { "epoch": 0.2363469761759316, "grad_norm": 0.374416321516037, "learning_rate": 4.341941318848034e-05, "loss": 4.3451, "step": 7738 }, { "epoch": 0.23637751985339034, "grad_norm": 0.37266406416893005, "learning_rate": 4.341779112372526e-05, "loss": 4.3555, "step": 7739 }, { "epoch": 0.23640806353084912, "grad_norm": 0.3805920481681824, "learning_rate": 4.341616888938811e-05, "loss": 4.3431, "step": 7740 }, { "epoch": 0.2364386072083079, "grad_norm": 0.3813464343547821, "learning_rate": 4.3414546485483834e-05, "loss": 4.4134, "step": 7741 }, { "epoch": 0.23646915088576664, "grad_norm": 0.38259562849998474, "learning_rate": 4.3412923912027346e-05, "loss": 4.417, "step": 7742 }, { "epoch": 0.23649969456322542, "grad_norm": 0.38369840383529663, "learning_rate": 4.3411301169033615e-05, "loss": 4.3778, "step": 7743 }, { "epoch": 0.23653023824068417, "grad_norm": 0.3830687999725342, "learning_rate": 4.3409678256517564e-05, "loss": 4.3801, "step": 7744 }, { "epoch": 0.23656078191814295, "grad_norm": 0.3741706609725952, "learning_rate": 4.340805517449413e-05, "loss": 4.3551, "step": 7745 }, { "epoch": 0.2365913255956017, "grad_norm": 0.38527318835258484, "learning_rate": 4.3406431922978284e-05, "loss": 4.3782, "step": 7746 }, { "epoch": 0.23662186927306048, "grad_norm": 0.37719112634658813, "learning_rate": 4.3404808501984945e-05, "loss": 4.4475, "step": 7747 }, { "epoch": 0.23665241295051925, "grad_norm": 0.3762025237083435, "learning_rate": 4.340318491152907e-05, "loss": 4.2827, "step": 7748 }, { "epoch": 0.236682956627978, "grad_norm": 0.41551610827445984, "learning_rate": 4.3401561151625614e-05, "loss": 4.3689, "step": 7749 }, { "epoch": 0.23671350030543678, "grad_norm": 0.3635751008987427, "learning_rate": 4.3399937222289525e-05, "loss": 4.3426, "step": 7750 }, { "epoch": 0.23674404398289553, "grad_norm": 0.3745557963848114, "learning_rate": 4.339831312353575e-05, "loss": 4.3536, "step": 7751 }, { "epoch": 0.2367745876603543, "grad_norm": 0.37515988945961, "learning_rate": 4.339668885537925e-05, "loss": 4.4217, "step": 7752 }, { "epoch": 0.23680513133781309, "grad_norm": 0.3684614598751068, "learning_rate": 4.339506441783497e-05, "loss": 4.3664, "step": 7753 }, { "epoch": 0.23683567501527183, "grad_norm": 0.37792542576789856, "learning_rate": 4.339343981091788e-05, "loss": 4.2822, "step": 7754 }, { "epoch": 0.2368662186927306, "grad_norm": 0.3823339343070984, "learning_rate": 4.339181503464294e-05, "loss": 4.3811, "step": 7755 }, { "epoch": 0.23689676237018936, "grad_norm": 0.39908719062805176, "learning_rate": 4.339019008902508e-05, "loss": 4.3823, "step": 7756 }, { "epoch": 0.23692730604764814, "grad_norm": 0.3754068613052368, "learning_rate": 4.3388564974079305e-05, "loss": 4.2852, "step": 7757 }, { "epoch": 0.2369578497251069, "grad_norm": 0.3677866756916046, "learning_rate": 4.338693968982055e-05, "loss": 4.3252, "step": 7758 }, { "epoch": 0.23698839340256567, "grad_norm": 0.39493829011917114, "learning_rate": 4.33853142362638e-05, "loss": 4.3257, "step": 7759 }, { "epoch": 0.23701893708002444, "grad_norm": 0.38887497782707214, "learning_rate": 4.338368861342399e-05, "loss": 4.3591, "step": 7760 }, { "epoch": 0.2370494807574832, "grad_norm": 0.3831619322299957, "learning_rate": 4.3382062821316114e-05, "loss": 4.3203, "step": 7761 }, { "epoch": 0.23708002443494197, "grad_norm": 0.3964426517486572, "learning_rate": 4.338043685995514e-05, "loss": 4.4364, "step": 7762 }, { "epoch": 0.23711056811240072, "grad_norm": 0.38146698474884033, "learning_rate": 4.337881072935603e-05, "loss": 4.382, "step": 7763 }, { "epoch": 0.2371411117898595, "grad_norm": 0.3783756196498871, "learning_rate": 4.337718442953376e-05, "loss": 4.3576, "step": 7764 }, { "epoch": 0.23717165546731828, "grad_norm": 0.373658150434494, "learning_rate": 4.33755579605033e-05, "loss": 4.3301, "step": 7765 }, { "epoch": 0.23720219914477703, "grad_norm": 0.3738115429878235, "learning_rate": 4.337393132227964e-05, "loss": 4.278, "step": 7766 }, { "epoch": 0.2372327428222358, "grad_norm": 0.37785160541534424, "learning_rate": 4.3372304514877734e-05, "loss": 4.2549, "step": 7767 }, { "epoch": 0.23726328649969455, "grad_norm": 0.3855786621570587, "learning_rate": 4.3370677538312584e-05, "loss": 4.3681, "step": 7768 }, { "epoch": 0.23729383017715333, "grad_norm": 0.3858896493911743, "learning_rate": 4.3369050392599156e-05, "loss": 4.4272, "step": 7769 }, { "epoch": 0.2373243738546121, "grad_norm": 0.37515807151794434, "learning_rate": 4.3367423077752445e-05, "loss": 4.4107, "step": 7770 }, { "epoch": 0.23735491753207086, "grad_norm": 0.3797822594642639, "learning_rate": 4.336579559378742e-05, "loss": 4.3069, "step": 7771 }, { "epoch": 0.23738546120952964, "grad_norm": 0.3781377077102661, "learning_rate": 4.336416794071907e-05, "loss": 4.3139, "step": 7772 }, { "epoch": 0.23741600488698839, "grad_norm": 0.3708740472793579, "learning_rate": 4.3362540118562386e-05, "loss": 4.2939, "step": 7773 }, { "epoch": 0.23744654856444716, "grad_norm": 0.3805061876773834, "learning_rate": 4.3360912127332355e-05, "loss": 4.4462, "step": 7774 }, { "epoch": 0.2374770922419059, "grad_norm": 0.3761034607887268, "learning_rate": 4.335928396704396e-05, "loss": 4.306, "step": 7775 }, { "epoch": 0.2375076359193647, "grad_norm": 0.37685075402259827, "learning_rate": 4.3357655637712204e-05, "loss": 4.4363, "step": 7776 }, { "epoch": 0.23753817959682347, "grad_norm": 0.37272047996520996, "learning_rate": 4.3356027139352075e-05, "loss": 4.3661, "step": 7777 }, { "epoch": 0.23756872327428222, "grad_norm": 0.3899679481983185, "learning_rate": 4.335439847197856e-05, "loss": 4.3814, "step": 7778 }, { "epoch": 0.237599266951741, "grad_norm": 0.3772837221622467, "learning_rate": 4.335276963560667e-05, "loss": 4.3953, "step": 7779 }, { "epoch": 0.23762981062919974, "grad_norm": 0.37642744183540344, "learning_rate": 4.335114063025139e-05, "loss": 4.3544, "step": 7780 }, { "epoch": 0.23766035430665852, "grad_norm": 0.3804225027561188, "learning_rate": 4.334951145592772e-05, "loss": 4.4146, "step": 7781 }, { "epoch": 0.2376908979841173, "grad_norm": 0.37656569480895996, "learning_rate": 4.334788211265067e-05, "loss": 4.3453, "step": 7782 }, { "epoch": 0.23772144166157605, "grad_norm": 0.3831039071083069, "learning_rate": 4.334625260043523e-05, "loss": 4.4744, "step": 7783 }, { "epoch": 0.23775198533903483, "grad_norm": 0.3761255443096161, "learning_rate": 4.334462291929641e-05, "loss": 4.4407, "step": 7784 }, { "epoch": 0.23778252901649358, "grad_norm": 0.3792409598827362, "learning_rate": 4.334299306924922e-05, "loss": 4.2134, "step": 7785 }, { "epoch": 0.23781307269395235, "grad_norm": 0.49825143814086914, "learning_rate": 4.334136305030866e-05, "loss": 4.3127, "step": 7786 }, { "epoch": 0.23784361637141113, "grad_norm": 0.3797796964645386, "learning_rate": 4.3339732862489735e-05, "loss": 4.3125, "step": 7787 }, { "epoch": 0.23787416004886988, "grad_norm": 0.37326329946517944, "learning_rate": 4.333810250580746e-05, "loss": 4.2978, "step": 7788 }, { "epoch": 0.23790470372632866, "grad_norm": 0.3739628791809082, "learning_rate": 4.3336471980276856e-05, "loss": 4.3222, "step": 7789 }, { "epoch": 0.2379352474037874, "grad_norm": 0.3700340986251831, "learning_rate": 4.333484128591292e-05, "loss": 4.3892, "step": 7790 }, { "epoch": 0.2379657910812462, "grad_norm": 0.38239043951034546, "learning_rate": 4.333321042273067e-05, "loss": 4.4004, "step": 7791 }, { "epoch": 0.23799633475870494, "grad_norm": 0.3805643320083618, "learning_rate": 4.3331579390745134e-05, "loss": 4.3504, "step": 7792 }, { "epoch": 0.2380268784361637, "grad_norm": 0.38713422417640686, "learning_rate": 4.332994818997132e-05, "loss": 4.3363, "step": 7793 }, { "epoch": 0.2380574221136225, "grad_norm": 0.3803383708000183, "learning_rate": 4.332831682042424e-05, "loss": 4.374, "step": 7794 }, { "epoch": 0.23808796579108124, "grad_norm": 0.3848682641983032, "learning_rate": 4.332668528211894e-05, "loss": 4.4402, "step": 7795 }, { "epoch": 0.23811850946854002, "grad_norm": 0.3825368285179138, "learning_rate": 4.3325053575070415e-05, "loss": 4.3885, "step": 7796 }, { "epoch": 0.23814905314599877, "grad_norm": 0.374642014503479, "learning_rate": 4.33234216992937e-05, "loss": 4.3884, "step": 7797 }, { "epoch": 0.23817959682345755, "grad_norm": 0.37923553586006165, "learning_rate": 4.332178965480382e-05, "loss": 4.3363, "step": 7798 }, { "epoch": 0.23821014050091632, "grad_norm": 0.36955198645591736, "learning_rate": 4.332015744161581e-05, "loss": 4.3246, "step": 7799 }, { "epoch": 0.23824068417837507, "grad_norm": 0.3848564028739929, "learning_rate": 4.331852505974468e-05, "loss": 4.3409, "step": 7800 }, { "epoch": 0.23827122785583385, "grad_norm": 0.39633503556251526, "learning_rate": 4.3316892509205474e-05, "loss": 4.3871, "step": 7801 }, { "epoch": 0.2383017715332926, "grad_norm": 0.3787018656730652, "learning_rate": 4.3315259790013227e-05, "loss": 4.3809, "step": 7802 }, { "epoch": 0.23833231521075138, "grad_norm": 0.38610804080963135, "learning_rate": 4.331362690218296e-05, "loss": 4.3187, "step": 7803 }, { "epoch": 0.23836285888821013, "grad_norm": 0.3844090402126312, "learning_rate": 4.331199384572971e-05, "loss": 4.3883, "step": 7804 }, { "epoch": 0.2383934025656689, "grad_norm": 0.3714215159416199, "learning_rate": 4.331036062066853e-05, "loss": 4.3128, "step": 7805 }, { "epoch": 0.23842394624312768, "grad_norm": 0.37020495533943176, "learning_rate": 4.330872722701444e-05, "loss": 4.2507, "step": 7806 }, { "epoch": 0.23845448992058643, "grad_norm": 0.38294723629951477, "learning_rate": 4.3307093664782484e-05, "loss": 4.4527, "step": 7807 }, { "epoch": 0.2384850335980452, "grad_norm": 0.3833285868167877, "learning_rate": 4.3305459933987705e-05, "loss": 4.2753, "step": 7808 }, { "epoch": 0.23851557727550396, "grad_norm": 0.38427653908729553, "learning_rate": 4.3303826034645147e-05, "loss": 4.3165, "step": 7809 }, { "epoch": 0.23854612095296274, "grad_norm": 0.38382488489151, "learning_rate": 4.3302191966769845e-05, "loss": 4.3818, "step": 7810 }, { "epoch": 0.23857666463042151, "grad_norm": 0.38178423047065735, "learning_rate": 4.330055773037686e-05, "loss": 4.4568, "step": 7811 }, { "epoch": 0.23860720830788026, "grad_norm": 0.3859720826148987, "learning_rate": 4.329892332548123e-05, "loss": 4.3623, "step": 7812 }, { "epoch": 0.23863775198533904, "grad_norm": 0.39266037940979004, "learning_rate": 4.3297288752098e-05, "loss": 4.3569, "step": 7813 }, { "epoch": 0.2386682956627978, "grad_norm": 0.3680567741394043, "learning_rate": 4.329565401024223e-05, "loss": 4.2328, "step": 7814 }, { "epoch": 0.23869883934025657, "grad_norm": 0.38889989256858826, "learning_rate": 4.329401909992896e-05, "loss": 4.2853, "step": 7815 }, { "epoch": 0.23872938301771535, "grad_norm": 0.38197067379951477, "learning_rate": 4.329238402117325e-05, "loss": 4.3644, "step": 7816 }, { "epoch": 0.2387599266951741, "grad_norm": 0.371942400932312, "learning_rate": 4.329074877399016e-05, "loss": 4.4228, "step": 7817 }, { "epoch": 0.23879047037263287, "grad_norm": 0.3808620274066925, "learning_rate": 4.328911335839474e-05, "loss": 4.3766, "step": 7818 }, { "epoch": 0.23882101405009162, "grad_norm": 0.37565433979034424, "learning_rate": 4.328747777440205e-05, "loss": 4.2994, "step": 7819 }, { "epoch": 0.2388515577275504, "grad_norm": 0.3839142918586731, "learning_rate": 4.328584202202715e-05, "loss": 4.415, "step": 7820 }, { "epoch": 0.23888210140500915, "grad_norm": 0.40125030279159546, "learning_rate": 4.32842061012851e-05, "loss": 4.3226, "step": 7821 }, { "epoch": 0.23891264508246793, "grad_norm": 0.38593441247940063, "learning_rate": 4.328257001219097e-05, "loss": 4.4018, "step": 7822 }, { "epoch": 0.2389431887599267, "grad_norm": 0.3903988003730774, "learning_rate": 4.328093375475981e-05, "loss": 4.2806, "step": 7823 }, { "epoch": 0.23897373243738546, "grad_norm": 0.3717270791530609, "learning_rate": 4.3279297329006695e-05, "loss": 4.3408, "step": 7824 }, { "epoch": 0.23900427611484423, "grad_norm": 0.384817510843277, "learning_rate": 4.327766073494669e-05, "loss": 4.3271, "step": 7825 }, { "epoch": 0.23903481979230298, "grad_norm": 0.3916303813457489, "learning_rate": 4.327602397259487e-05, "loss": 4.3568, "step": 7826 }, { "epoch": 0.23906536346976176, "grad_norm": 0.3850465714931488, "learning_rate": 4.32743870419663e-05, "loss": 4.2598, "step": 7827 }, { "epoch": 0.23909590714722054, "grad_norm": 0.3864630162715912, "learning_rate": 4.327274994307605e-05, "loss": 4.3502, "step": 7828 }, { "epoch": 0.2391264508246793, "grad_norm": 0.37240660190582275, "learning_rate": 4.3271112675939196e-05, "loss": 4.3931, "step": 7829 }, { "epoch": 0.23915699450213806, "grad_norm": 0.393360435962677, "learning_rate": 4.326947524057081e-05, "loss": 4.3442, "step": 7830 }, { "epoch": 0.23918753817959681, "grad_norm": 0.3838528096675873, "learning_rate": 4.326783763698599e-05, "loss": 4.3519, "step": 7831 }, { "epoch": 0.2392180818570556, "grad_norm": 0.3883674740791321, "learning_rate": 4.326619986519978e-05, "loss": 4.4081, "step": 7832 }, { "epoch": 0.23924862553451434, "grad_norm": 0.37166136503219604, "learning_rate": 4.3264561925227274e-05, "loss": 4.3408, "step": 7833 }, { "epoch": 0.23927916921197312, "grad_norm": 0.39258620142936707, "learning_rate": 4.326292381708357e-05, "loss": 4.4291, "step": 7834 }, { "epoch": 0.2393097128894319, "grad_norm": 0.3879447877407074, "learning_rate": 4.3261285540783724e-05, "loss": 4.4197, "step": 7835 }, { "epoch": 0.23934025656689065, "grad_norm": 0.37521612644195557, "learning_rate": 4.325964709634284e-05, "loss": 4.3458, "step": 7836 }, { "epoch": 0.23937080024434942, "grad_norm": 0.3939193785190582, "learning_rate": 4.325800848377599e-05, "loss": 4.381, "step": 7837 }, { "epoch": 0.23940134392180817, "grad_norm": 0.3804961144924164, "learning_rate": 4.3256369703098275e-05, "loss": 4.384, "step": 7838 }, { "epoch": 0.23943188759926695, "grad_norm": 0.3771040737628937, "learning_rate": 4.325473075432477e-05, "loss": 4.4368, "step": 7839 }, { "epoch": 0.23946243127672573, "grad_norm": 0.384162962436676, "learning_rate": 4.325309163747058e-05, "loss": 4.4809, "step": 7840 }, { "epoch": 0.23949297495418448, "grad_norm": 0.37982073426246643, "learning_rate": 4.325145235255079e-05, "loss": 4.3567, "step": 7841 }, { "epoch": 0.23952351863164326, "grad_norm": 0.3742477297782898, "learning_rate": 4.324981289958049e-05, "loss": 4.3021, "step": 7842 }, { "epoch": 0.239554062309102, "grad_norm": 0.3879527747631073, "learning_rate": 4.324817327857479e-05, "loss": 4.3735, "step": 7843 }, { "epoch": 0.23958460598656078, "grad_norm": 0.381307989358902, "learning_rate": 4.324653348954877e-05, "loss": 4.3511, "step": 7844 }, { "epoch": 0.23961514966401956, "grad_norm": 0.3799598217010498, "learning_rate": 4.324489353251753e-05, "loss": 4.3611, "step": 7845 }, { "epoch": 0.2396456933414783, "grad_norm": 0.3837761878967285, "learning_rate": 4.324325340749618e-05, "loss": 4.2574, "step": 7846 }, { "epoch": 0.2396762370189371, "grad_norm": 0.3847442865371704, "learning_rate": 4.324161311449981e-05, "loss": 4.3981, "step": 7847 }, { "epoch": 0.23970678069639584, "grad_norm": 0.3829289972782135, "learning_rate": 4.3239972653543533e-05, "loss": 4.3083, "step": 7848 }, { "epoch": 0.23973732437385462, "grad_norm": 0.38454848527908325, "learning_rate": 4.3238332024642455e-05, "loss": 4.3471, "step": 7849 }, { "epoch": 0.23976786805131337, "grad_norm": 0.38910138607025146, "learning_rate": 4.3236691227811674e-05, "loss": 4.2926, "step": 7850 }, { "epoch": 0.23979841172877214, "grad_norm": 0.38536250591278076, "learning_rate": 4.32350502630663e-05, "loss": 4.3228, "step": 7851 }, { "epoch": 0.23982895540623092, "grad_norm": 0.39240357279777527, "learning_rate": 4.323340913042144e-05, "loss": 4.3894, "step": 7852 }, { "epoch": 0.23985949908368967, "grad_norm": 0.37392449378967285, "learning_rate": 4.323176782989221e-05, "loss": 4.4496, "step": 7853 }, { "epoch": 0.23989004276114845, "grad_norm": 0.3866807520389557, "learning_rate": 4.3230126361493715e-05, "loss": 4.3944, "step": 7854 }, { "epoch": 0.2399205864386072, "grad_norm": 0.3787795901298523, "learning_rate": 4.322848472524108e-05, "loss": 4.3762, "step": 7855 }, { "epoch": 0.23995113011606597, "grad_norm": 0.37599605321884155, "learning_rate": 4.3226842921149413e-05, "loss": 4.3699, "step": 7856 }, { "epoch": 0.23998167379352475, "grad_norm": 0.36779287457466125, "learning_rate": 4.322520094923383e-05, "loss": 4.3681, "step": 7857 }, { "epoch": 0.2400122174709835, "grad_norm": 0.3832489252090454, "learning_rate": 4.322355880950945e-05, "loss": 4.3765, "step": 7858 }, { "epoch": 0.24004276114844228, "grad_norm": 0.3871012032032013, "learning_rate": 4.32219165019914e-05, "loss": 4.3553, "step": 7859 }, { "epoch": 0.24007330482590103, "grad_norm": 0.39240318536758423, "learning_rate": 4.322027402669479e-05, "loss": 4.3176, "step": 7860 }, { "epoch": 0.2401038485033598, "grad_norm": 0.3936251699924469, "learning_rate": 4.321863138363475e-05, "loss": 4.1792, "step": 7861 }, { "epoch": 0.24013439218081858, "grad_norm": 0.38806477189064026, "learning_rate": 4.3216988572826404e-05, "loss": 4.2551, "step": 7862 }, { "epoch": 0.24016493585827733, "grad_norm": 0.3871682286262512, "learning_rate": 4.3215345594284885e-05, "loss": 4.3222, "step": 7863 }, { "epoch": 0.2401954795357361, "grad_norm": 0.383151650428772, "learning_rate": 4.3213702448025306e-05, "loss": 4.3984, "step": 7864 }, { "epoch": 0.24022602321319486, "grad_norm": 0.3740839958190918, "learning_rate": 4.3212059134062805e-05, "loss": 4.3217, "step": 7865 }, { "epoch": 0.24025656689065364, "grad_norm": 0.3803129196166992, "learning_rate": 4.321041565241251e-05, "loss": 4.3231, "step": 7866 }, { "epoch": 0.2402871105681124, "grad_norm": 0.3833844065666199, "learning_rate": 4.320877200308956e-05, "loss": 4.3993, "step": 7867 }, { "epoch": 0.24031765424557117, "grad_norm": 0.38123610615730286, "learning_rate": 4.320712818610908e-05, "loss": 4.385, "step": 7868 }, { "epoch": 0.24034819792302994, "grad_norm": 0.38447409868240356, "learning_rate": 4.3205484201486215e-05, "loss": 4.3746, "step": 7869 }, { "epoch": 0.2403787416004887, "grad_norm": 0.3838975727558136, "learning_rate": 4.320384004923609e-05, "loss": 4.355, "step": 7870 }, { "epoch": 0.24040928527794747, "grad_norm": 0.39037737250328064, "learning_rate": 4.320219572937385e-05, "loss": 4.4436, "step": 7871 }, { "epoch": 0.24043982895540622, "grad_norm": 0.3772982358932495, "learning_rate": 4.320055124191464e-05, "loss": 4.2841, "step": 7872 }, { "epoch": 0.240470372632865, "grad_norm": 0.3704492449760437, "learning_rate": 4.31989065868736e-05, "loss": 4.3084, "step": 7873 }, { "epoch": 0.24050091631032378, "grad_norm": 0.3814336061477661, "learning_rate": 4.319726176426586e-05, "loss": 4.3386, "step": 7874 }, { "epoch": 0.24053145998778253, "grad_norm": 0.390101820230484, "learning_rate": 4.319561677410658e-05, "loss": 4.341, "step": 7875 }, { "epoch": 0.2405620036652413, "grad_norm": 0.38038915395736694, "learning_rate": 4.31939716164109e-05, "loss": 4.3692, "step": 7876 }, { "epoch": 0.24059254734270005, "grad_norm": 0.3765856623649597, "learning_rate": 4.319232629119398e-05, "loss": 4.3475, "step": 7877 }, { "epoch": 0.24062309102015883, "grad_norm": 0.3762561082839966, "learning_rate": 4.319068079847095e-05, "loss": 4.3606, "step": 7878 }, { "epoch": 0.24065363469761758, "grad_norm": 0.37972599267959595, "learning_rate": 4.318903513825696e-05, "loss": 4.4026, "step": 7879 }, { "epoch": 0.24068417837507636, "grad_norm": 0.3714233338832855, "learning_rate": 4.318738931056718e-05, "loss": 4.334, "step": 7880 }, { "epoch": 0.24071472205253513, "grad_norm": 0.3780321180820465, "learning_rate": 4.318574331541675e-05, "loss": 4.3664, "step": 7881 }, { "epoch": 0.24074526572999388, "grad_norm": 0.38165080547332764, "learning_rate": 4.318409715282085e-05, "loss": 4.3687, "step": 7882 }, { "epoch": 0.24077580940745266, "grad_norm": 0.36610493063926697, "learning_rate": 4.3182450822794597e-05, "loss": 4.3302, "step": 7883 }, { "epoch": 0.2408063530849114, "grad_norm": 0.3775465190410614, "learning_rate": 4.318080432535318e-05, "loss": 4.3735, "step": 7884 }, { "epoch": 0.2408368967623702, "grad_norm": 0.3714609146118164, "learning_rate": 4.317915766051174e-05, "loss": 4.3828, "step": 7885 }, { "epoch": 0.24086744043982897, "grad_norm": 0.3681780695915222, "learning_rate": 4.3177510828285464e-05, "loss": 4.4178, "step": 7886 }, { "epoch": 0.24089798411728772, "grad_norm": 0.37124690413475037, "learning_rate": 4.3175863828689486e-05, "loss": 4.3394, "step": 7887 }, { "epoch": 0.2409285277947465, "grad_norm": 0.370187908411026, "learning_rate": 4.3174216661738996e-05, "loss": 4.3044, "step": 7888 }, { "epoch": 0.24095907147220524, "grad_norm": 0.3767825961112976, "learning_rate": 4.3172569327449143e-05, "loss": 4.3414, "step": 7889 }, { "epoch": 0.24098961514966402, "grad_norm": 0.37656262516975403, "learning_rate": 4.31709218258351e-05, "loss": 4.3327, "step": 7890 }, { "epoch": 0.2410201588271228, "grad_norm": 0.3672179579734802, "learning_rate": 4.316927415691204e-05, "loss": 4.4042, "step": 7891 }, { "epoch": 0.24105070250458155, "grad_norm": 0.37781423330307007, "learning_rate": 4.316762632069513e-05, "loss": 4.3987, "step": 7892 }, { "epoch": 0.24108124618204033, "grad_norm": 0.3799057900905609, "learning_rate": 4.316597831719954e-05, "loss": 4.4017, "step": 7893 }, { "epoch": 0.24111178985949908, "grad_norm": 0.3774152100086212, "learning_rate": 4.3164330146440455e-05, "loss": 4.3856, "step": 7894 }, { "epoch": 0.24114233353695785, "grad_norm": 0.37250930070877075, "learning_rate": 4.316268180843304e-05, "loss": 4.3858, "step": 7895 }, { "epoch": 0.2411728772144166, "grad_norm": 0.38572850823402405, "learning_rate": 4.3161033303192475e-05, "loss": 4.3864, "step": 7896 }, { "epoch": 0.24120342089187538, "grad_norm": 0.3897775113582611, "learning_rate": 4.315938463073394e-05, "loss": 4.2835, "step": 7897 }, { "epoch": 0.24123396456933416, "grad_norm": 0.3776484727859497, "learning_rate": 4.3157735791072615e-05, "loss": 4.3616, "step": 7898 }, { "epoch": 0.2412645082467929, "grad_norm": 0.37949591875076294, "learning_rate": 4.315608678422368e-05, "loss": 4.3926, "step": 7899 }, { "epoch": 0.24129505192425169, "grad_norm": 0.3829502761363983, "learning_rate": 4.3154437610202314e-05, "loss": 4.3677, "step": 7900 }, { "epoch": 0.24132559560171044, "grad_norm": 0.37261149287223816, "learning_rate": 4.3152788269023714e-05, "loss": 4.4311, "step": 7901 }, { "epoch": 0.2413561392791692, "grad_norm": 0.4046393036842346, "learning_rate": 4.315113876070305e-05, "loss": 4.2902, "step": 7902 }, { "epoch": 0.241386682956628, "grad_norm": 0.3953284025192261, "learning_rate": 4.314948908525552e-05, "loss": 4.3767, "step": 7903 }, { "epoch": 0.24141722663408674, "grad_norm": 0.3815954625606537, "learning_rate": 4.314783924269632e-05, "loss": 4.3468, "step": 7904 }, { "epoch": 0.24144777031154552, "grad_norm": 0.3813023865222931, "learning_rate": 4.314618923304064e-05, "loss": 4.3305, "step": 7905 }, { "epoch": 0.24147831398900427, "grad_norm": 0.3798258900642395, "learning_rate": 4.314453905630365e-05, "loss": 4.3546, "step": 7906 }, { "epoch": 0.24150885766646304, "grad_norm": 0.37123769521713257, "learning_rate": 4.3142888712500565e-05, "loss": 4.3229, "step": 7907 }, { "epoch": 0.2415394013439218, "grad_norm": 0.3870074450969696, "learning_rate": 4.314123820164658e-05, "loss": 4.3415, "step": 7908 }, { "epoch": 0.24156994502138057, "grad_norm": 0.3765280842781067, "learning_rate": 4.313958752375689e-05, "loss": 4.3874, "step": 7909 }, { "epoch": 0.24160048869883935, "grad_norm": 0.37884753942489624, "learning_rate": 4.313793667884668e-05, "loss": 4.3657, "step": 7910 }, { "epoch": 0.2416310323762981, "grad_norm": 0.38051164150238037, "learning_rate": 4.3136285666931165e-05, "loss": 4.3859, "step": 7911 }, { "epoch": 0.24166157605375688, "grad_norm": 0.3807138502597809, "learning_rate": 4.3134634488025546e-05, "loss": 4.3823, "step": 7912 }, { "epoch": 0.24169211973121563, "grad_norm": 0.402308851480484, "learning_rate": 4.3132983142145026e-05, "loss": 4.3622, "step": 7913 }, { "epoch": 0.2417226634086744, "grad_norm": 0.39607393741607666, "learning_rate": 4.31313316293048e-05, "loss": 4.3316, "step": 7914 }, { "epoch": 0.24175320708613318, "grad_norm": 0.37582752108573914, "learning_rate": 4.312967994952008e-05, "loss": 4.3216, "step": 7915 }, { "epoch": 0.24178375076359193, "grad_norm": 0.3922688066959381, "learning_rate": 4.3128028102806084e-05, "loss": 4.4062, "step": 7916 }, { "epoch": 0.2418142944410507, "grad_norm": 0.38320547342300415, "learning_rate": 4.312637608917801e-05, "loss": 4.2827, "step": 7917 }, { "epoch": 0.24184483811850946, "grad_norm": 0.3789088726043701, "learning_rate": 4.312472390865107e-05, "loss": 4.3865, "step": 7918 }, { "epoch": 0.24187538179596824, "grad_norm": 0.38360247015953064, "learning_rate": 4.312307156124048e-05, "loss": 4.1937, "step": 7919 }, { "epoch": 0.241905925473427, "grad_norm": 0.37487420439720154, "learning_rate": 4.3121419046961454e-05, "loss": 4.3633, "step": 7920 }, { "epoch": 0.24193646915088576, "grad_norm": 0.38812050223350525, "learning_rate": 4.3119766365829194e-05, "loss": 4.332, "step": 7921 }, { "epoch": 0.24196701282834454, "grad_norm": 0.37803328037261963, "learning_rate": 4.311811351785894e-05, "loss": 4.4272, "step": 7922 }, { "epoch": 0.2419975565058033, "grad_norm": 0.38441142439842224, "learning_rate": 4.31164605030659e-05, "loss": 4.2451, "step": 7923 }, { "epoch": 0.24202810018326207, "grad_norm": 0.3873039484024048, "learning_rate": 4.311480732146529e-05, "loss": 4.4154, "step": 7924 }, { "epoch": 0.24205864386072082, "grad_norm": 0.39378082752227783, "learning_rate": 4.311315397307234e-05, "loss": 4.3101, "step": 7925 }, { "epoch": 0.2420891875381796, "grad_norm": 0.37217602133750916, "learning_rate": 4.3111500457902266e-05, "loss": 4.3763, "step": 7926 }, { "epoch": 0.24211973121563837, "grad_norm": 0.38465845584869385, "learning_rate": 4.310984677597029e-05, "loss": 4.4106, "step": 7927 }, { "epoch": 0.24215027489309712, "grad_norm": 0.3953212797641754, "learning_rate": 4.310819292729164e-05, "loss": 4.318, "step": 7928 }, { "epoch": 0.2421808185705559, "grad_norm": 0.3717583119869232, "learning_rate": 4.310653891188156e-05, "loss": 4.3988, "step": 7929 }, { "epoch": 0.24221136224801465, "grad_norm": 0.3701154291629791, "learning_rate": 4.310488472975527e-05, "loss": 4.4331, "step": 7930 }, { "epoch": 0.24224190592547343, "grad_norm": 0.39026397466659546, "learning_rate": 4.310323038092798e-05, "loss": 4.4146, "step": 7931 }, { "epoch": 0.2422724496029322, "grad_norm": 0.3845636546611786, "learning_rate": 4.310157586541495e-05, "loss": 4.2842, "step": 7932 }, { "epoch": 0.24230299328039095, "grad_norm": 0.3791220784187317, "learning_rate": 4.309992118323141e-05, "loss": 4.3381, "step": 7933 }, { "epoch": 0.24233353695784973, "grad_norm": 0.3958445191383362, "learning_rate": 4.3098266334392576e-05, "loss": 4.3797, "step": 7934 }, { "epoch": 0.24236408063530848, "grad_norm": 0.37956303358078003, "learning_rate": 4.309661131891371e-05, "loss": 4.4161, "step": 7935 }, { "epoch": 0.24239462431276726, "grad_norm": 0.39041051268577576, "learning_rate": 4.309495613681003e-05, "loss": 4.3574, "step": 7936 }, { "epoch": 0.24242516799022604, "grad_norm": 0.39392539858818054, "learning_rate": 4.309330078809679e-05, "loss": 4.4371, "step": 7937 }, { "epoch": 0.2424557116676848, "grad_norm": 0.3823375999927521, "learning_rate": 4.3091645272789226e-05, "loss": 4.3319, "step": 7938 }, { "epoch": 0.24248625534514356, "grad_norm": 0.38659828901290894, "learning_rate": 4.308998959090259e-05, "loss": 4.4583, "step": 7939 }, { "epoch": 0.24251679902260231, "grad_norm": 0.3950401842594147, "learning_rate": 4.3088333742452116e-05, "loss": 4.412, "step": 7940 }, { "epoch": 0.2425473427000611, "grad_norm": 0.38993018865585327, "learning_rate": 4.308667772745304e-05, "loss": 4.2918, "step": 7941 }, { "epoch": 0.24257788637751984, "grad_norm": 0.3740045130252838, "learning_rate": 4.308502154592063e-05, "loss": 4.4068, "step": 7942 }, { "epoch": 0.24260843005497862, "grad_norm": 0.37369218468666077, "learning_rate": 4.308336519787014e-05, "loss": 4.361, "step": 7943 }, { "epoch": 0.2426389737324374, "grad_norm": 0.39611393213272095, "learning_rate": 4.308170868331679e-05, "loss": 4.3894, "step": 7944 }, { "epoch": 0.24266951740989615, "grad_norm": 0.3776607811450958, "learning_rate": 4.308005200227587e-05, "loss": 4.3712, "step": 7945 }, { "epoch": 0.24270006108735492, "grad_norm": 0.3729943037033081, "learning_rate": 4.3078395154762607e-05, "loss": 4.4428, "step": 7946 }, { "epoch": 0.24273060476481367, "grad_norm": 0.3851970136165619, "learning_rate": 4.307673814079226e-05, "loss": 4.3657, "step": 7947 }, { "epoch": 0.24276114844227245, "grad_norm": 0.3815667927265167, "learning_rate": 4.30750809603801e-05, "loss": 4.2599, "step": 7948 }, { "epoch": 0.24279169211973123, "grad_norm": 0.3806457817554474, "learning_rate": 4.307342361354137e-05, "loss": 4.3735, "step": 7949 }, { "epoch": 0.24282223579718998, "grad_norm": 0.3881925642490387, "learning_rate": 4.3071766100291334e-05, "loss": 4.3129, "step": 7950 }, { "epoch": 0.24285277947464876, "grad_norm": 0.3769289255142212, "learning_rate": 4.3070108420645264e-05, "loss": 4.312, "step": 7951 }, { "epoch": 0.2428833231521075, "grad_norm": 0.3762659728527069, "learning_rate": 4.306845057461841e-05, "loss": 4.3103, "step": 7952 }, { "epoch": 0.24291386682956628, "grad_norm": 0.3770974576473236, "learning_rate": 4.3066792562226044e-05, "loss": 4.3314, "step": 7953 }, { "epoch": 0.24294441050702503, "grad_norm": 0.3928605318069458, "learning_rate": 4.306513438348343e-05, "loss": 4.3403, "step": 7954 }, { "epoch": 0.2429749541844838, "grad_norm": 0.38172927498817444, "learning_rate": 4.306347603840583e-05, "loss": 4.2726, "step": 7955 }, { "epoch": 0.2430054978619426, "grad_norm": 0.3825191259384155, "learning_rate": 4.306181752700852e-05, "loss": 4.3913, "step": 7956 }, { "epoch": 0.24303604153940134, "grad_norm": 0.3878686726093292, "learning_rate": 4.306015884930677e-05, "loss": 4.4011, "step": 7957 }, { "epoch": 0.24306658521686011, "grad_norm": 0.3877595365047455, "learning_rate": 4.305850000531586e-05, "loss": 4.3823, "step": 7958 }, { "epoch": 0.24309712889431886, "grad_norm": 0.3773774802684784, "learning_rate": 4.3056840995051054e-05, "loss": 4.3832, "step": 7959 }, { "epoch": 0.24312767257177764, "grad_norm": 0.36806589365005493, "learning_rate": 4.305518181852762e-05, "loss": 4.3205, "step": 7960 }, { "epoch": 0.24315821624923642, "grad_norm": 0.3799486756324768, "learning_rate": 4.3053522475760846e-05, "loss": 4.3409, "step": 7961 }, { "epoch": 0.24318875992669517, "grad_norm": 0.3717198073863983, "learning_rate": 4.305186296676601e-05, "loss": 4.2897, "step": 7962 }, { "epoch": 0.24321930360415395, "grad_norm": 0.38347816467285156, "learning_rate": 4.3050203291558395e-05, "loss": 4.3899, "step": 7963 }, { "epoch": 0.2432498472816127, "grad_norm": 0.37687334418296814, "learning_rate": 4.304854345015327e-05, "loss": 4.431, "step": 7964 }, { "epoch": 0.24328039095907147, "grad_norm": 0.37186941504478455, "learning_rate": 4.3046883442565936e-05, "loss": 4.4811, "step": 7965 }, { "epoch": 0.24331093463653025, "grad_norm": 0.3928302824497223, "learning_rate": 4.3045223268811654e-05, "loss": 4.347, "step": 7966 }, { "epoch": 0.243341478313989, "grad_norm": 0.37385767698287964, "learning_rate": 4.3043562928905734e-05, "loss": 4.3101, "step": 7967 }, { "epoch": 0.24337202199144778, "grad_norm": 0.3832816183567047, "learning_rate": 4.3041902422863456e-05, "loss": 4.3854, "step": 7968 }, { "epoch": 0.24340256566890653, "grad_norm": 0.37235790491104126, "learning_rate": 4.3040241750700094e-05, "loss": 4.344, "step": 7969 }, { "epoch": 0.2434331093463653, "grad_norm": 0.3823671340942383, "learning_rate": 4.303858091243096e-05, "loss": 4.3905, "step": 7970 }, { "epoch": 0.24346365302382406, "grad_norm": 0.3657970130443573, "learning_rate": 4.3036919908071334e-05, "loss": 4.3471, "step": 7971 }, { "epoch": 0.24349419670128283, "grad_norm": 0.3799463212490082, "learning_rate": 4.303525873763651e-05, "loss": 4.3014, "step": 7972 }, { "epoch": 0.2435247403787416, "grad_norm": 0.38947007060050964, "learning_rate": 4.303359740114179e-05, "loss": 4.3584, "step": 7973 }, { "epoch": 0.24355528405620036, "grad_norm": 0.3731362223625183, "learning_rate": 4.303193589860247e-05, "loss": 4.3797, "step": 7974 }, { "epoch": 0.24358582773365914, "grad_norm": 0.37804651260375977, "learning_rate": 4.3030274230033836e-05, "loss": 4.2893, "step": 7975 }, { "epoch": 0.2436163714111179, "grad_norm": 0.3949446678161621, "learning_rate": 4.30286123954512e-05, "loss": 4.335, "step": 7976 }, { "epoch": 0.24364691508857667, "grad_norm": 0.3823438882827759, "learning_rate": 4.302695039486986e-05, "loss": 4.3495, "step": 7977 }, { "epoch": 0.24367745876603544, "grad_norm": 0.38593241572380066, "learning_rate": 4.3025288228305124e-05, "loss": 4.3299, "step": 7978 }, { "epoch": 0.2437080024434942, "grad_norm": 0.3957042992115021, "learning_rate": 4.302362589577229e-05, "loss": 4.3143, "step": 7979 }, { "epoch": 0.24373854612095297, "grad_norm": 0.3826337158679962, "learning_rate": 4.302196339728666e-05, "loss": 4.3879, "step": 7980 }, { "epoch": 0.24376908979841172, "grad_norm": 0.38370829820632935, "learning_rate": 4.302030073286355e-05, "loss": 4.3006, "step": 7981 }, { "epoch": 0.2437996334758705, "grad_norm": 0.3968338072299957, "learning_rate": 4.3018637902518264e-05, "loss": 4.3503, "step": 7982 }, { "epoch": 0.24383017715332925, "grad_norm": 0.391996830701828, "learning_rate": 4.3016974906266124e-05, "loss": 4.3504, "step": 7983 }, { "epoch": 0.24386072083078802, "grad_norm": 0.3758169710636139, "learning_rate": 4.301531174412243e-05, "loss": 4.3389, "step": 7984 }, { "epoch": 0.2438912645082468, "grad_norm": 0.3840371072292328, "learning_rate": 4.301364841610249e-05, "loss": 4.4707, "step": 7985 }, { "epoch": 0.24392180818570555, "grad_norm": 0.385905385017395, "learning_rate": 4.301198492222163e-05, "loss": 4.2639, "step": 7986 }, { "epoch": 0.24395235186316433, "grad_norm": 0.38607123494148254, "learning_rate": 4.3010321262495166e-05, "loss": 4.3828, "step": 7987 }, { "epoch": 0.24398289554062308, "grad_norm": 0.38170376420021057, "learning_rate": 4.300865743693842e-05, "loss": 4.2925, "step": 7988 }, { "epoch": 0.24401343921808186, "grad_norm": 0.38302475214004517, "learning_rate": 4.30069934455667e-05, "loss": 4.3619, "step": 7989 }, { "epoch": 0.24404398289554063, "grad_norm": 0.4305451512336731, "learning_rate": 4.3005329288395324e-05, "loss": 4.3818, "step": 7990 }, { "epoch": 0.24407452657299938, "grad_norm": 0.3960309624671936, "learning_rate": 4.300366496543964e-05, "loss": 4.2967, "step": 7991 }, { "epoch": 0.24410507025045816, "grad_norm": 0.38927608728408813, "learning_rate": 4.3002000476714946e-05, "loss": 4.3629, "step": 7992 }, { "epoch": 0.2441356139279169, "grad_norm": 0.3867769241333008, "learning_rate": 4.3000335822236584e-05, "loss": 4.2314, "step": 7993 }, { "epoch": 0.2441661576053757, "grad_norm": 0.3875998854637146, "learning_rate": 4.299867100201986e-05, "loss": 4.3485, "step": 7994 }, { "epoch": 0.24419670128283447, "grad_norm": 0.39121583104133606, "learning_rate": 4.299700601608014e-05, "loss": 4.4538, "step": 7995 }, { "epoch": 0.24422724496029322, "grad_norm": 0.3805336058139801, "learning_rate": 4.299534086443272e-05, "loss": 4.4073, "step": 7996 }, { "epoch": 0.244257788637752, "grad_norm": 0.39496201276779175, "learning_rate": 4.299367554709295e-05, "loss": 4.2964, "step": 7997 }, { "epoch": 0.24428833231521074, "grad_norm": 0.38910526037216187, "learning_rate": 4.299201006407615e-05, "loss": 4.3818, "step": 7998 }, { "epoch": 0.24431887599266952, "grad_norm": 0.3836728632450104, "learning_rate": 4.2990344415397664e-05, "loss": 4.4126, "step": 7999 }, { "epoch": 0.24434941967012827, "grad_norm": 0.3688953220844269, "learning_rate": 4.298867860107284e-05, "loss": 4.4293, "step": 8000 }, { "epoch": 0.24437996334758705, "grad_norm": 0.38247567415237427, "learning_rate": 4.298701262111699e-05, "loss": 4.3518, "step": 8001 }, { "epoch": 0.24441050702504583, "grad_norm": 0.39194920659065247, "learning_rate": 4.298534647554547e-05, "loss": 4.2842, "step": 8002 }, { "epoch": 0.24444105070250458, "grad_norm": 0.40301215648651123, "learning_rate": 4.298368016437362e-05, "loss": 4.351, "step": 8003 }, { "epoch": 0.24447159437996335, "grad_norm": 0.36539730429649353, "learning_rate": 4.298201368761678e-05, "loss": 4.3418, "step": 8004 }, { "epoch": 0.2445021380574221, "grad_norm": 0.3867579400539398, "learning_rate": 4.298034704529029e-05, "loss": 4.3269, "step": 8005 }, { "epoch": 0.24453268173488088, "grad_norm": 0.3754277229309082, "learning_rate": 4.2978680237409506e-05, "loss": 4.401, "step": 8006 }, { "epoch": 0.24456322541233966, "grad_norm": 0.38695594668388367, "learning_rate": 4.2977013263989765e-05, "loss": 4.309, "step": 8007 }, { "epoch": 0.2445937690897984, "grad_norm": 0.3880660831928253, "learning_rate": 4.2975346125046425e-05, "loss": 4.4278, "step": 8008 }, { "epoch": 0.24462431276725718, "grad_norm": 0.37217608094215393, "learning_rate": 4.2973678820594824e-05, "loss": 4.2458, "step": 8009 }, { "epoch": 0.24465485644471593, "grad_norm": 0.3810853660106659, "learning_rate": 4.297201135065033e-05, "loss": 4.3918, "step": 8010 }, { "epoch": 0.2446854001221747, "grad_norm": 0.37742117047309875, "learning_rate": 4.297034371522828e-05, "loss": 4.3066, "step": 8011 }, { "epoch": 0.2447159437996335, "grad_norm": 0.40634703636169434, "learning_rate": 4.296867591434404e-05, "loss": 4.4342, "step": 8012 }, { "epoch": 0.24474648747709224, "grad_norm": 0.3703579008579254, "learning_rate": 4.296700794801296e-05, "loss": 4.2865, "step": 8013 }, { "epoch": 0.24477703115455102, "grad_norm": 0.3791322708129883, "learning_rate": 4.2965339816250394e-05, "loss": 4.3358, "step": 8014 }, { "epoch": 0.24480757483200977, "grad_norm": 0.3833213746547699, "learning_rate": 4.296367151907172e-05, "loss": 4.4478, "step": 8015 }, { "epoch": 0.24483811850946854, "grad_norm": 0.3781159222126007, "learning_rate": 4.296200305649228e-05, "loss": 4.3493, "step": 8016 }, { "epoch": 0.2448686621869273, "grad_norm": 0.3740268051624298, "learning_rate": 4.296033442852744e-05, "loss": 4.4705, "step": 8017 }, { "epoch": 0.24489920586438607, "grad_norm": 0.376777708530426, "learning_rate": 4.295866563519257e-05, "loss": 4.3833, "step": 8018 }, { "epoch": 0.24492974954184485, "grad_norm": 0.37468084692955017, "learning_rate": 4.2956996676503034e-05, "loss": 4.3583, "step": 8019 }, { "epoch": 0.2449602932193036, "grad_norm": 0.37369266152381897, "learning_rate": 4.2955327552474196e-05, "loss": 4.3364, "step": 8020 }, { "epoch": 0.24499083689676238, "grad_norm": 0.37246114015579224, "learning_rate": 4.295365826312142e-05, "loss": 4.3066, "step": 8021 }, { "epoch": 0.24502138057422113, "grad_norm": 0.39955219626426697, "learning_rate": 4.295198880846009e-05, "loss": 4.275, "step": 8022 }, { "epoch": 0.2450519242516799, "grad_norm": 0.37761276960372925, "learning_rate": 4.295031918850557e-05, "loss": 4.4129, "step": 8023 }, { "epoch": 0.24508246792913868, "grad_norm": 0.38325127959251404, "learning_rate": 4.2948649403273225e-05, "loss": 4.3806, "step": 8024 }, { "epoch": 0.24511301160659743, "grad_norm": 0.38305383920669556, "learning_rate": 4.2946979452778436e-05, "loss": 4.381, "step": 8025 }, { "epoch": 0.2451435552840562, "grad_norm": 0.38532304763793945, "learning_rate": 4.294530933703658e-05, "loss": 4.2625, "step": 8026 }, { "epoch": 0.24517409896151496, "grad_norm": 0.3768005669116974, "learning_rate": 4.294363905606304e-05, "loss": 4.2424, "step": 8027 }, { "epoch": 0.24520464263897374, "grad_norm": 0.38304394483566284, "learning_rate": 4.2941968609873184e-05, "loss": 4.3211, "step": 8028 }, { "epoch": 0.24523518631643249, "grad_norm": 0.3826166093349457, "learning_rate": 4.29402979984824e-05, "loss": 4.35, "step": 8029 }, { "epoch": 0.24526572999389126, "grad_norm": 0.3685954809188843, "learning_rate": 4.293862722190607e-05, "loss": 4.3257, "step": 8030 }, { "epoch": 0.24529627367135004, "grad_norm": 0.38495704531669617, "learning_rate": 4.293695628015958e-05, "loss": 4.2645, "step": 8031 }, { "epoch": 0.2453268173488088, "grad_norm": 0.3969435691833496, "learning_rate": 4.29352851732583e-05, "loss": 4.3492, "step": 8032 }, { "epoch": 0.24535736102626757, "grad_norm": 0.391698956489563, "learning_rate": 4.293361390121763e-05, "loss": 4.315, "step": 8033 }, { "epoch": 0.24538790470372632, "grad_norm": 0.39246898889541626, "learning_rate": 4.2931942464052966e-05, "loss": 4.3396, "step": 8034 }, { "epoch": 0.2454184483811851, "grad_norm": 0.3847370147705078, "learning_rate": 4.2930270861779685e-05, "loss": 4.3586, "step": 8035 }, { "epoch": 0.24544899205864387, "grad_norm": 0.3796629309654236, "learning_rate": 4.292859909441318e-05, "loss": 4.3514, "step": 8036 }, { "epoch": 0.24547953573610262, "grad_norm": 0.3881111145019531, "learning_rate": 4.2926927161968845e-05, "loss": 4.3595, "step": 8037 }, { "epoch": 0.2455100794135614, "grad_norm": 0.3869291841983795, "learning_rate": 4.2925255064462064e-05, "loss": 4.379, "step": 8038 }, { "epoch": 0.24554062309102015, "grad_norm": 0.38557547330856323, "learning_rate": 4.292358280190826e-05, "loss": 4.2918, "step": 8039 }, { "epoch": 0.24557116676847893, "grad_norm": 0.374370813369751, "learning_rate": 4.2921910374322806e-05, "loss": 4.3852, "step": 8040 }, { "epoch": 0.2456017104459377, "grad_norm": 0.3809816241264343, "learning_rate": 4.292023778172111e-05, "loss": 4.3395, "step": 8041 }, { "epoch": 0.24563225412339645, "grad_norm": 0.38689157366752625, "learning_rate": 4.291856502411857e-05, "loss": 4.2888, "step": 8042 }, { "epoch": 0.24566279780085523, "grad_norm": 0.3847194314002991, "learning_rate": 4.291689210153059e-05, "loss": 4.3184, "step": 8043 }, { "epoch": 0.24569334147831398, "grad_norm": 0.38307854533195496, "learning_rate": 4.291521901397257e-05, "loss": 4.2701, "step": 8044 }, { "epoch": 0.24572388515577276, "grad_norm": 0.3853375315666199, "learning_rate": 4.291354576145992e-05, "loss": 4.377, "step": 8045 }, { "epoch": 0.2457544288332315, "grad_norm": 0.37576037645339966, "learning_rate": 4.291187234400804e-05, "loss": 4.3945, "step": 8046 }, { "epoch": 0.24578497251069029, "grad_norm": 0.3737238049507141, "learning_rate": 4.291019876163235e-05, "loss": 4.4473, "step": 8047 }, { "epoch": 0.24581551618814906, "grad_norm": 0.3818131387233734, "learning_rate": 4.290852501434824e-05, "loss": 4.4283, "step": 8048 }, { "epoch": 0.2458460598656078, "grad_norm": 0.3714452385902405, "learning_rate": 4.290685110217114e-05, "loss": 4.3321, "step": 8049 }, { "epoch": 0.2458766035430666, "grad_norm": 0.37803253531455994, "learning_rate": 4.290517702511646e-05, "loss": 4.2697, "step": 8050 }, { "epoch": 0.24590714722052534, "grad_norm": 0.380347341299057, "learning_rate": 4.29035027831996e-05, "loss": 4.4107, "step": 8051 }, { "epoch": 0.24593769089798412, "grad_norm": 0.39182811975479126, "learning_rate": 4.290182837643599e-05, "loss": 4.3891, "step": 8052 }, { "epoch": 0.2459682345754429, "grad_norm": 0.37459883093833923, "learning_rate": 4.2900153804841034e-05, "loss": 4.4041, "step": 8053 }, { "epoch": 0.24599877825290165, "grad_norm": 0.3870634138584137, "learning_rate": 4.289847906843017e-05, "loss": 4.4277, "step": 8054 }, { "epoch": 0.24602932193036042, "grad_norm": 0.37551239132881165, "learning_rate": 4.28968041672188e-05, "loss": 4.4121, "step": 8055 }, { "epoch": 0.24605986560781917, "grad_norm": 0.3878798484802246, "learning_rate": 4.2895129101222356e-05, "loss": 4.2892, "step": 8056 }, { "epoch": 0.24609040928527795, "grad_norm": 0.3881808817386627, "learning_rate": 4.289345387045626e-05, "loss": 4.4429, "step": 8057 }, { "epoch": 0.2461209529627367, "grad_norm": 0.38196733593940735, "learning_rate": 4.289177847493592e-05, "loss": 4.4058, "step": 8058 }, { "epoch": 0.24615149664019548, "grad_norm": 0.373383104801178, "learning_rate": 4.289010291467679e-05, "loss": 4.4115, "step": 8059 }, { "epoch": 0.24618204031765425, "grad_norm": 0.39827343821525574, "learning_rate": 4.2888427189694284e-05, "loss": 4.2015, "step": 8060 }, { "epoch": 0.246212583995113, "grad_norm": 0.37582170963287354, "learning_rate": 4.288675130000383e-05, "loss": 4.2513, "step": 8061 }, { "epoch": 0.24624312767257178, "grad_norm": 0.38668742775917053, "learning_rate": 4.288507524562085e-05, "loss": 4.374, "step": 8062 }, { "epoch": 0.24627367135003053, "grad_norm": 0.39848774671554565, "learning_rate": 4.28833990265608e-05, "loss": 4.4546, "step": 8063 }, { "epoch": 0.2463042150274893, "grad_norm": 0.3764899969100952, "learning_rate": 4.2881722642839094e-05, "loss": 4.311, "step": 8064 }, { "epoch": 0.2463347587049481, "grad_norm": 0.3749160170555115, "learning_rate": 4.288004609447117e-05, "loss": 4.3193, "step": 8065 }, { "epoch": 0.24636530238240684, "grad_norm": 0.3744361698627472, "learning_rate": 4.287836938147248e-05, "loss": 4.3792, "step": 8066 }, { "epoch": 0.24639584605986561, "grad_norm": 0.373089462518692, "learning_rate": 4.2876692503858444e-05, "loss": 4.3727, "step": 8067 }, { "epoch": 0.24642638973732436, "grad_norm": 0.38262277841567993, "learning_rate": 4.287501546164451e-05, "loss": 4.3535, "step": 8068 }, { "epoch": 0.24645693341478314, "grad_norm": 0.3687574863433838, "learning_rate": 4.287333825484612e-05, "loss": 4.3428, "step": 8069 }, { "epoch": 0.24648747709224192, "grad_norm": 0.3792444169521332, "learning_rate": 4.287166088347872e-05, "loss": 4.323, "step": 8070 }, { "epoch": 0.24651802076970067, "grad_norm": 0.3784383535385132, "learning_rate": 4.286998334755774e-05, "loss": 4.3598, "step": 8071 }, { "epoch": 0.24654856444715945, "grad_norm": 0.37300270795822144, "learning_rate": 4.286830564709863e-05, "loss": 4.3134, "step": 8072 }, { "epoch": 0.2465791081246182, "grad_norm": 0.3734360337257385, "learning_rate": 4.286662778211685e-05, "loss": 4.3997, "step": 8073 }, { "epoch": 0.24660965180207697, "grad_norm": 0.376944363117218, "learning_rate": 4.286494975262785e-05, "loss": 4.3535, "step": 8074 }, { "epoch": 0.24664019547953572, "grad_norm": 0.37242287397384644, "learning_rate": 4.286327155864706e-05, "loss": 4.2021, "step": 8075 }, { "epoch": 0.2466707391569945, "grad_norm": 0.384003609418869, "learning_rate": 4.286159320018995e-05, "loss": 4.3865, "step": 8076 }, { "epoch": 0.24670128283445328, "grad_norm": 0.37373650074005127, "learning_rate": 4.285991467727197e-05, "loss": 4.4257, "step": 8077 }, { "epoch": 0.24673182651191203, "grad_norm": 0.38127774000167847, "learning_rate": 4.2858235989908566e-05, "loss": 4.4448, "step": 8078 }, { "epoch": 0.2467623701893708, "grad_norm": 0.39081788063049316, "learning_rate": 4.285655713811521e-05, "loss": 4.3763, "step": 8079 }, { "epoch": 0.24679291386682956, "grad_norm": 0.3763573169708252, "learning_rate": 4.285487812190735e-05, "loss": 4.348, "step": 8080 }, { "epoch": 0.24682345754428833, "grad_norm": 0.36250966787338257, "learning_rate": 4.285319894130044e-05, "loss": 4.3484, "step": 8081 }, { "epoch": 0.2468540012217471, "grad_norm": 0.3671613931655884, "learning_rate": 4.2851519596309955e-05, "loss": 4.3359, "step": 8082 }, { "epoch": 0.24688454489920586, "grad_norm": 0.3698235750198364, "learning_rate": 4.284984008695135e-05, "loss": 4.3119, "step": 8083 }, { "epoch": 0.24691508857666464, "grad_norm": 0.39593589305877686, "learning_rate": 4.2848160413240085e-05, "loss": 4.2704, "step": 8084 }, { "epoch": 0.2469456322541234, "grad_norm": 0.3856072723865509, "learning_rate": 4.284648057519163e-05, "loss": 4.3348, "step": 8085 }, { "epoch": 0.24697617593158216, "grad_norm": 0.3808339834213257, "learning_rate": 4.284480057282147e-05, "loss": 4.3201, "step": 8086 }, { "epoch": 0.24700671960904094, "grad_norm": 0.39581024646759033, "learning_rate": 4.284312040614503e-05, "loss": 4.3622, "step": 8087 }, { "epoch": 0.2470372632864997, "grad_norm": 0.38842371106147766, "learning_rate": 4.284144007517782e-05, "loss": 4.4329, "step": 8088 }, { "epoch": 0.24706780696395847, "grad_norm": 0.3668983578681946, "learning_rate": 4.28397595799353e-05, "loss": 4.3727, "step": 8089 }, { "epoch": 0.24709835064141722, "grad_norm": 0.3813583552837372, "learning_rate": 4.283807892043293e-05, "loss": 4.3559, "step": 8090 }, { "epoch": 0.247128894318876, "grad_norm": 0.3727545142173767, "learning_rate": 4.283639809668621e-05, "loss": 4.3026, "step": 8091 }, { "epoch": 0.24715943799633475, "grad_norm": 0.38479703664779663, "learning_rate": 4.28347171087106e-05, "loss": 4.2453, "step": 8092 }, { "epoch": 0.24718998167379352, "grad_norm": 0.3764162063598633, "learning_rate": 4.2833035956521575e-05, "loss": 4.3816, "step": 8093 }, { "epoch": 0.2472205253512523, "grad_norm": 0.4054447114467621, "learning_rate": 4.283135464013462e-05, "loss": 4.349, "step": 8094 }, { "epoch": 0.24725106902871105, "grad_norm": 0.37807244062423706, "learning_rate": 4.282967315956521e-05, "loss": 4.4285, "step": 8095 }, { "epoch": 0.24728161270616983, "grad_norm": 0.3804961144924164, "learning_rate": 4.2827991514828834e-05, "loss": 4.3512, "step": 8096 }, { "epoch": 0.24731215638362858, "grad_norm": 0.37144774198532104, "learning_rate": 4.282630970594098e-05, "loss": 4.3341, "step": 8097 }, { "epoch": 0.24734270006108736, "grad_norm": 0.3740253150463104, "learning_rate": 4.282462773291713e-05, "loss": 4.3206, "step": 8098 }, { "epoch": 0.24737324373854613, "grad_norm": 0.37761470675468445, "learning_rate": 4.2822945595772756e-05, "loss": 4.3674, "step": 8099 }, { "epoch": 0.24740378741600488, "grad_norm": 0.38539618253707886, "learning_rate": 4.282126329452337e-05, "loss": 4.3704, "step": 8100 }, { "epoch": 0.24743433109346366, "grad_norm": 0.37538427114486694, "learning_rate": 4.281958082918445e-05, "loss": 4.3985, "step": 8101 }, { "epoch": 0.2474648747709224, "grad_norm": 0.37799814343452454, "learning_rate": 4.281789819977148e-05, "loss": 4.3861, "step": 8102 }, { "epoch": 0.2474954184483812, "grad_norm": 0.3900858163833618, "learning_rate": 4.281621540629995e-05, "loss": 4.2616, "step": 8103 }, { "epoch": 0.24752596212583994, "grad_norm": 0.37732401490211487, "learning_rate": 4.281453244878538e-05, "loss": 4.3665, "step": 8104 }, { "epoch": 0.24755650580329872, "grad_norm": 0.3617797791957855, "learning_rate": 4.2812849327243256e-05, "loss": 4.338, "step": 8105 }, { "epoch": 0.2475870494807575, "grad_norm": 0.3790527284145355, "learning_rate": 4.281116604168905e-05, "loss": 4.3042, "step": 8106 }, { "epoch": 0.24761759315821624, "grad_norm": 0.3742660880088806, "learning_rate": 4.280948259213829e-05, "loss": 4.3559, "step": 8107 }, { "epoch": 0.24764813683567502, "grad_norm": 0.3803006410598755, "learning_rate": 4.280779897860647e-05, "loss": 4.3444, "step": 8108 }, { "epoch": 0.24767868051313377, "grad_norm": 0.3808775842189789, "learning_rate": 4.280611520110909e-05, "loss": 4.3845, "step": 8109 }, { "epoch": 0.24770922419059255, "grad_norm": 0.3777596354484558, "learning_rate": 4.2804431259661654e-05, "loss": 4.3555, "step": 8110 }, { "epoch": 0.24773976786805132, "grad_norm": 0.3830794394016266, "learning_rate": 4.280274715427966e-05, "loss": 4.329, "step": 8111 }, { "epoch": 0.24777031154551007, "grad_norm": 0.392027348279953, "learning_rate": 4.280106288497862e-05, "loss": 4.3026, "step": 8112 }, { "epoch": 0.24780085522296885, "grad_norm": 0.3816913366317749, "learning_rate": 4.2799378451774044e-05, "loss": 4.3973, "step": 8113 }, { "epoch": 0.2478313989004276, "grad_norm": 0.3763977587223053, "learning_rate": 4.2797693854681444e-05, "loss": 4.3515, "step": 8114 }, { "epoch": 0.24786194257788638, "grad_norm": 0.38629359006881714, "learning_rate": 4.2796009093716314e-05, "loss": 4.2818, "step": 8115 }, { "epoch": 0.24789248625534516, "grad_norm": 0.388473778963089, "learning_rate": 4.2794324168894186e-05, "loss": 4.3624, "step": 8116 }, { "epoch": 0.2479230299328039, "grad_norm": 0.3855680823326111, "learning_rate": 4.279263908023056e-05, "loss": 4.1837, "step": 8117 }, { "epoch": 0.24795357361026268, "grad_norm": 0.3872683346271515, "learning_rate": 4.279095382774097e-05, "loss": 4.3953, "step": 8118 }, { "epoch": 0.24798411728772143, "grad_norm": 0.3820204436779022, "learning_rate": 4.278926841144091e-05, "loss": 4.2983, "step": 8119 }, { "epoch": 0.2480146609651802, "grad_norm": 0.3821331560611725, "learning_rate": 4.2787582831345905e-05, "loss": 4.2243, "step": 8120 }, { "epoch": 0.24804520464263896, "grad_norm": 0.3707014322280884, "learning_rate": 4.278589708747149e-05, "loss": 4.2905, "step": 8121 }, { "epoch": 0.24807574832009774, "grad_norm": 0.3629818558692932, "learning_rate": 4.278421117983318e-05, "loss": 4.3794, "step": 8122 }, { "epoch": 0.24810629199755652, "grad_norm": 0.3759966492652893, "learning_rate": 4.278252510844648e-05, "loss": 4.3517, "step": 8123 }, { "epoch": 0.24813683567501527, "grad_norm": 0.3741943836212158, "learning_rate": 4.2780838873326936e-05, "loss": 4.3415, "step": 8124 }, { "epoch": 0.24816737935247404, "grad_norm": 0.3806881904602051, "learning_rate": 4.277915247449007e-05, "loss": 4.3752, "step": 8125 }, { "epoch": 0.2481979230299328, "grad_norm": 0.37511900067329407, "learning_rate": 4.2777465911951395e-05, "loss": 4.4424, "step": 8126 }, { "epoch": 0.24822846670739157, "grad_norm": 0.3744611144065857, "learning_rate": 4.277577918572646e-05, "loss": 4.3026, "step": 8127 }, { "epoch": 0.24825901038485035, "grad_norm": 0.3724229335784912, "learning_rate": 4.277409229583079e-05, "loss": 4.362, "step": 8128 }, { "epoch": 0.2482895540623091, "grad_norm": 0.3707875907421112, "learning_rate": 4.277240524227991e-05, "loss": 4.1856, "step": 8129 }, { "epoch": 0.24832009773976788, "grad_norm": 0.38122037053108215, "learning_rate": 4.277071802508935e-05, "loss": 4.2579, "step": 8130 }, { "epoch": 0.24835064141722663, "grad_norm": 0.38887926936149597, "learning_rate": 4.276903064427466e-05, "loss": 4.4071, "step": 8131 }, { "epoch": 0.2483811850946854, "grad_norm": 0.38004839420318604, "learning_rate": 4.2767343099851365e-05, "loss": 4.3897, "step": 8132 }, { "epoch": 0.24841172877214415, "grad_norm": 0.37414950132369995, "learning_rate": 4.2765655391835015e-05, "loss": 4.4184, "step": 8133 }, { "epoch": 0.24844227244960293, "grad_norm": 0.3908078670501709, "learning_rate": 4.276396752024113e-05, "loss": 4.3731, "step": 8134 }, { "epoch": 0.2484728161270617, "grad_norm": 0.3759799003601074, "learning_rate": 4.2762279485085264e-05, "loss": 4.3485, "step": 8135 }, { "epoch": 0.24850335980452046, "grad_norm": 0.38685843348503113, "learning_rate": 4.2760591286382965e-05, "loss": 4.4116, "step": 8136 }, { "epoch": 0.24853390348197923, "grad_norm": 0.39715370535850525, "learning_rate": 4.275890292414977e-05, "loss": 4.3501, "step": 8137 }, { "epoch": 0.24856444715943798, "grad_norm": 0.3973960280418396, "learning_rate": 4.2757214398401225e-05, "loss": 4.3977, "step": 8138 }, { "epoch": 0.24859499083689676, "grad_norm": 0.3854576051235199, "learning_rate": 4.275552570915287e-05, "loss": 4.3446, "step": 8139 }, { "epoch": 0.24862553451435554, "grad_norm": 0.3780432343482971, "learning_rate": 4.275383685642027e-05, "loss": 4.422, "step": 8140 }, { "epoch": 0.2486560781918143, "grad_norm": 0.3678838908672333, "learning_rate": 4.275214784021896e-05, "loss": 4.3083, "step": 8141 }, { "epoch": 0.24868662186927307, "grad_norm": 0.382764995098114, "learning_rate": 4.2750458660564494e-05, "loss": 4.3803, "step": 8142 }, { "epoch": 0.24871716554673182, "grad_norm": 0.368148535490036, "learning_rate": 4.2748769317472436e-05, "loss": 4.4081, "step": 8143 }, { "epoch": 0.2487477092241906, "grad_norm": 0.37530162930488586, "learning_rate": 4.2747079810958334e-05, "loss": 4.3758, "step": 8144 }, { "epoch": 0.24877825290164937, "grad_norm": 0.3648572862148285, "learning_rate": 4.274539014103775e-05, "loss": 4.3373, "step": 8145 }, { "epoch": 0.24880879657910812, "grad_norm": 0.3790290653705597, "learning_rate": 4.274370030772622e-05, "loss": 4.3932, "step": 8146 }, { "epoch": 0.2488393402565669, "grad_norm": 0.3956959545612335, "learning_rate": 4.274201031103933e-05, "loss": 4.4437, "step": 8147 }, { "epoch": 0.24886988393402565, "grad_norm": 0.3794923424720764, "learning_rate": 4.274032015099262e-05, "loss": 4.3972, "step": 8148 }, { "epoch": 0.24890042761148443, "grad_norm": 0.36810803413391113, "learning_rate": 4.273862982760166e-05, "loss": 4.3787, "step": 8149 }, { "epoch": 0.24893097128894318, "grad_norm": 0.3901703357696533, "learning_rate": 4.273693934088202e-05, "loss": 4.3708, "step": 8150 }, { "epoch": 0.24896151496640195, "grad_norm": 0.3643042743206024, "learning_rate": 4.273524869084926e-05, "loss": 4.3711, "step": 8151 }, { "epoch": 0.24899205864386073, "grad_norm": 0.37402063608169556, "learning_rate": 4.2733557877518946e-05, "loss": 4.3524, "step": 8152 }, { "epoch": 0.24902260232131948, "grad_norm": 0.3800906240940094, "learning_rate": 4.273186690090665e-05, "loss": 4.3412, "step": 8153 }, { "epoch": 0.24905314599877826, "grad_norm": 0.3808123767375946, "learning_rate": 4.273017576102794e-05, "loss": 4.3696, "step": 8154 }, { "epoch": 0.249083689676237, "grad_norm": 0.39353659749031067, "learning_rate": 4.272848445789838e-05, "loss": 4.3392, "step": 8155 }, { "epoch": 0.24911423335369579, "grad_norm": 0.39346829056739807, "learning_rate": 4.2726792991533546e-05, "loss": 4.4034, "step": 8156 }, { "epoch": 0.24914477703115456, "grad_norm": 0.3898848593235016, "learning_rate": 4.272510136194902e-05, "loss": 4.3767, "step": 8157 }, { "epoch": 0.2491753207086133, "grad_norm": 0.3813275098800659, "learning_rate": 4.2723409569160377e-05, "loss": 4.4188, "step": 8158 }, { "epoch": 0.2492058643860721, "grad_norm": 0.3823460042476654, "learning_rate": 4.272171761318318e-05, "loss": 4.2997, "step": 8159 }, { "epoch": 0.24923640806353084, "grad_norm": 0.38350406289100647, "learning_rate": 4.272002549403302e-05, "loss": 4.3911, "step": 8160 }, { "epoch": 0.24926695174098962, "grad_norm": 0.3722648322582245, "learning_rate": 4.271833321172548e-05, "loss": 4.3342, "step": 8161 }, { "epoch": 0.2492974954184484, "grad_norm": 0.3786756694316864, "learning_rate": 4.271664076627613e-05, "loss": 4.3896, "step": 8162 }, { "epoch": 0.24932803909590714, "grad_norm": 0.3841063380241394, "learning_rate": 4.2714948157700565e-05, "loss": 4.3015, "step": 8163 }, { "epoch": 0.24935858277336592, "grad_norm": 0.37569889426231384, "learning_rate": 4.271325538601436e-05, "loss": 4.2706, "step": 8164 }, { "epoch": 0.24938912645082467, "grad_norm": 0.38114333152770996, "learning_rate": 4.271156245123311e-05, "loss": 4.4044, "step": 8165 }, { "epoch": 0.24941967012828345, "grad_norm": 0.3741404414176941, "learning_rate": 4.270986935337239e-05, "loss": 4.4014, "step": 8166 }, { "epoch": 0.2494502138057422, "grad_norm": 0.3983359932899475, "learning_rate": 4.2708176092447805e-05, "loss": 4.2057, "step": 8167 }, { "epoch": 0.24948075748320098, "grad_norm": 0.3823733329772949, "learning_rate": 4.270648266847493e-05, "loss": 4.2975, "step": 8168 }, { "epoch": 0.24951130116065975, "grad_norm": 0.37043431401252747, "learning_rate": 4.270478908146938e-05, "loss": 4.3325, "step": 8169 }, { "epoch": 0.2495418448381185, "grad_norm": 0.37890270352363586, "learning_rate": 4.270309533144672e-05, "loss": 4.3308, "step": 8170 }, { "epoch": 0.24957238851557728, "grad_norm": 0.385548859834671, "learning_rate": 4.270140141842256e-05, "loss": 4.4036, "step": 8171 }, { "epoch": 0.24960293219303603, "grad_norm": 0.380070298910141, "learning_rate": 4.26997073424125e-05, "loss": 4.3857, "step": 8172 }, { "epoch": 0.2496334758704948, "grad_norm": 0.3833872377872467, "learning_rate": 4.2698013103432134e-05, "loss": 4.3626, "step": 8173 }, { "epoch": 0.2496640195479536, "grad_norm": 0.376506507396698, "learning_rate": 4.269631870149706e-05, "loss": 4.3711, "step": 8174 }, { "epoch": 0.24969456322541234, "grad_norm": 0.3746635615825653, "learning_rate": 4.2694624136622886e-05, "loss": 4.3916, "step": 8175 }, { "epoch": 0.2497251069028711, "grad_norm": 0.38996657729148865, "learning_rate": 4.269292940882521e-05, "loss": 4.3903, "step": 8176 }, { "epoch": 0.24975565058032986, "grad_norm": 0.37807655334472656, "learning_rate": 4.269123451811963e-05, "loss": 4.3043, "step": 8177 }, { "epoch": 0.24978619425778864, "grad_norm": 0.3740815818309784, "learning_rate": 4.268953946452176e-05, "loss": 4.315, "step": 8178 }, { "epoch": 0.2498167379352474, "grad_norm": 0.3877895772457123, "learning_rate": 4.2687844248047204e-05, "loss": 4.3645, "step": 8179 }, { "epoch": 0.24984728161270617, "grad_norm": 0.3720357418060303, "learning_rate": 4.268614886871157e-05, "loss": 4.3034, "step": 8180 }, { "epoch": 0.24987782529016495, "grad_norm": 0.37423163652420044, "learning_rate": 4.2684453326530475e-05, "loss": 4.3104, "step": 8181 }, { "epoch": 0.2499083689676237, "grad_norm": 0.4074244201183319, "learning_rate": 4.268275762151953e-05, "loss": 4.2653, "step": 8182 }, { "epoch": 0.24993891264508247, "grad_norm": 0.37414732575416565, "learning_rate": 4.268106175369434e-05, "loss": 4.4101, "step": 8183 }, { "epoch": 0.24996945632254122, "grad_norm": 0.3890308737754822, "learning_rate": 4.267936572307052e-05, "loss": 4.3834, "step": 8184 }, { "epoch": 0.25, "grad_norm": 0.3788660764694214, "learning_rate": 4.267766952966369e-05, "loss": 4.3816, "step": 8185 }, { "epoch": 0.25003054367745875, "grad_norm": 0.37561896443367004, "learning_rate": 4.267597317348947e-05, "loss": 4.3136, "step": 8186 }, { "epoch": 0.25006108735491756, "grad_norm": 0.3879825174808502, "learning_rate": 4.267427665456348e-05, "loss": 4.2892, "step": 8187 }, { "epoch": 0.2500916310323763, "grad_norm": 0.415176659822464, "learning_rate": 4.267257997290133e-05, "loss": 4.4134, "step": 8188 }, { "epoch": 0.25012217470983505, "grad_norm": 0.3871424198150635, "learning_rate": 4.2670883128518654e-05, "loss": 4.3843, "step": 8189 }, { "epoch": 0.2501527183872938, "grad_norm": 0.3952713906764984, "learning_rate": 4.266918612143107e-05, "loss": 4.3755, "step": 8190 }, { "epoch": 0.2501832620647526, "grad_norm": 0.3817841410636902, "learning_rate": 4.266748895165421e-05, "loss": 4.3599, "step": 8191 }, { "epoch": 0.25021380574221136, "grad_norm": 0.38415542244911194, "learning_rate": 4.266579161920369e-05, "loss": 4.3701, "step": 8192 }, { "epoch": 0.2502443494196701, "grad_norm": 0.3724521994590759, "learning_rate": 4.266409412409515e-05, "loss": 4.3548, "step": 8193 }, { "epoch": 0.2502748930971289, "grad_norm": 0.38057851791381836, "learning_rate": 4.26623964663442e-05, "loss": 4.4282, "step": 8194 }, { "epoch": 0.25030543677458766, "grad_norm": 0.3890267014503479, "learning_rate": 4.26606986459665e-05, "loss": 4.4049, "step": 8195 }, { "epoch": 0.2503359804520464, "grad_norm": 0.39701157808303833, "learning_rate": 4.265900066297767e-05, "loss": 4.3662, "step": 8196 }, { "epoch": 0.2503665241295052, "grad_norm": 0.39842233061790466, "learning_rate": 4.2657302517393326e-05, "loss": 4.3773, "step": 8197 }, { "epoch": 0.25039706780696397, "grad_norm": 0.3787887692451477, "learning_rate": 4.265560420922913e-05, "loss": 4.4013, "step": 8198 }, { "epoch": 0.2504276114844227, "grad_norm": 0.37875133752822876, "learning_rate": 4.26539057385007e-05, "loss": 4.2707, "step": 8199 }, { "epoch": 0.25045815516188147, "grad_norm": 0.3864957392215729, "learning_rate": 4.265220710522369e-05, "loss": 4.4136, "step": 8200 }, { "epoch": 0.2504886988393403, "grad_norm": 0.3780252933502197, "learning_rate": 4.2650508309413725e-05, "loss": 4.3422, "step": 8201 }, { "epoch": 0.250519242516799, "grad_norm": 0.37688279151916504, "learning_rate": 4.264880935108646e-05, "loss": 4.3375, "step": 8202 }, { "epoch": 0.2505497861942578, "grad_norm": 0.3903290331363678, "learning_rate": 4.264711023025754e-05, "loss": 4.3074, "step": 8203 }, { "epoch": 0.2505803298717166, "grad_norm": 0.3869493901729584, "learning_rate": 4.2645410946942595e-05, "loss": 4.3135, "step": 8204 }, { "epoch": 0.25061087354917533, "grad_norm": 0.39443346858024597, "learning_rate": 4.264371150115728e-05, "loss": 4.3936, "step": 8205 }, { "epoch": 0.2506414172266341, "grad_norm": 0.3909751772880554, "learning_rate": 4.264201189291724e-05, "loss": 4.321, "step": 8206 }, { "epoch": 0.2506719609040928, "grad_norm": 0.37257498502731323, "learning_rate": 4.2640312122238135e-05, "loss": 4.2981, "step": 8207 }, { "epoch": 0.25070250458155163, "grad_norm": 0.37787362933158875, "learning_rate": 4.2638612189135594e-05, "loss": 4.4429, "step": 8208 }, { "epoch": 0.2507330482590104, "grad_norm": 0.38180407881736755, "learning_rate": 4.2636912093625294e-05, "loss": 4.3701, "step": 8209 }, { "epoch": 0.25076359193646913, "grad_norm": 0.41462287306785583, "learning_rate": 4.263521183572287e-05, "loss": 4.4377, "step": 8210 }, { "epoch": 0.25079413561392794, "grad_norm": 0.3853569030761719, "learning_rate": 4.263351141544398e-05, "loss": 4.419, "step": 8211 }, { "epoch": 0.2508246792913867, "grad_norm": 0.3822508454322815, "learning_rate": 4.2631810832804286e-05, "loss": 4.383, "step": 8212 }, { "epoch": 0.25085522296884544, "grad_norm": 0.3825225830078125, "learning_rate": 4.263011008781945e-05, "loss": 4.2843, "step": 8213 }, { "epoch": 0.25088576664630424, "grad_norm": 0.39102110266685486, "learning_rate": 4.262840918050512e-05, "loss": 4.3023, "step": 8214 }, { "epoch": 0.250916310323763, "grad_norm": 0.3776035010814667, "learning_rate": 4.262670811087697e-05, "loss": 4.387, "step": 8215 }, { "epoch": 0.25094685400122174, "grad_norm": 0.38284051418304443, "learning_rate": 4.262500687895065e-05, "loss": 4.402, "step": 8216 }, { "epoch": 0.2509773976786805, "grad_norm": 0.38979607820510864, "learning_rate": 4.262330548474183e-05, "loss": 4.2731, "step": 8217 }, { "epoch": 0.2510079413561393, "grad_norm": 0.3895605802536011, "learning_rate": 4.262160392826617e-05, "loss": 4.2819, "step": 8218 }, { "epoch": 0.25103848503359805, "grad_norm": 0.3775154948234558, "learning_rate": 4.261990220953935e-05, "loss": 4.4294, "step": 8219 }, { "epoch": 0.2510690287110568, "grad_norm": 0.38858720660209656, "learning_rate": 4.261820032857703e-05, "loss": 4.4242, "step": 8220 }, { "epoch": 0.2510995723885156, "grad_norm": 0.37493211030960083, "learning_rate": 4.261649828539488e-05, "loss": 4.2194, "step": 8221 }, { "epoch": 0.25113011606597435, "grad_norm": 0.3740535378456116, "learning_rate": 4.261479608000858e-05, "loss": 4.3506, "step": 8222 }, { "epoch": 0.2511606597434331, "grad_norm": 0.3864191472530365, "learning_rate": 4.261309371243378e-05, "loss": 4.2696, "step": 8223 }, { "epoch": 0.25119120342089185, "grad_norm": 0.4113329350948334, "learning_rate": 4.261139118268619e-05, "loss": 4.3931, "step": 8224 }, { "epoch": 0.25122174709835066, "grad_norm": 0.3949941396713257, "learning_rate": 4.2609688490781454e-05, "loss": 4.3977, "step": 8225 }, { "epoch": 0.2512522907758094, "grad_norm": 0.38112279772758484, "learning_rate": 4.260798563673526e-05, "loss": 4.3134, "step": 8226 }, { "epoch": 0.25128283445326816, "grad_norm": 0.3803026080131531, "learning_rate": 4.2606282620563296e-05, "loss": 4.3448, "step": 8227 }, { "epoch": 0.25131337813072696, "grad_norm": 0.3759392201900482, "learning_rate": 4.2604579442281226e-05, "loss": 4.345, "step": 8228 }, { "epoch": 0.2513439218081857, "grad_norm": 0.3896273970603943, "learning_rate": 4.260287610190475e-05, "loss": 4.3546, "step": 8229 }, { "epoch": 0.25137446548564446, "grad_norm": 0.37919890880584717, "learning_rate": 4.2601172599449545e-05, "loss": 4.3621, "step": 8230 }, { "epoch": 0.2514050091631032, "grad_norm": 0.3908684253692627, "learning_rate": 4.2599468934931294e-05, "loss": 4.3334, "step": 8231 }, { "epoch": 0.251435552840562, "grad_norm": 0.3797938823699951, "learning_rate": 4.259776510836568e-05, "loss": 4.3866, "step": 8232 }, { "epoch": 0.25146609651802077, "grad_norm": 0.3813674747943878, "learning_rate": 4.2596061119768396e-05, "loss": 4.27, "step": 8233 }, { "epoch": 0.2514966401954795, "grad_norm": 0.378425657749176, "learning_rate": 4.259435696915512e-05, "loss": 4.3921, "step": 8234 }, { "epoch": 0.2515271838729383, "grad_norm": 0.3918302059173584, "learning_rate": 4.259265265654157e-05, "loss": 4.3216, "step": 8235 }, { "epoch": 0.25155772755039707, "grad_norm": 0.39888012409210205, "learning_rate": 4.259094818194341e-05, "loss": 4.4966, "step": 8236 }, { "epoch": 0.2515882712278558, "grad_norm": 0.3800114095211029, "learning_rate": 4.258924354537636e-05, "loss": 4.1595, "step": 8237 }, { "epoch": 0.2516188149053146, "grad_norm": 0.3790337145328522, "learning_rate": 4.2587538746856084e-05, "loss": 4.3549, "step": 8238 }, { "epoch": 0.2516493585827734, "grad_norm": 0.3870041072368622, "learning_rate": 4.258583378639831e-05, "loss": 4.3039, "step": 8239 }, { "epoch": 0.2516799022602321, "grad_norm": 0.38679468631744385, "learning_rate": 4.258412866401872e-05, "loss": 4.3677, "step": 8240 }, { "epoch": 0.2517104459376909, "grad_norm": 0.38087335228919983, "learning_rate": 4.258242337973301e-05, "loss": 4.4289, "step": 8241 }, { "epoch": 0.2517409896151497, "grad_norm": 0.41110870242118835, "learning_rate": 4.258071793355689e-05, "loss": 4.4188, "step": 8242 }, { "epoch": 0.25177153329260843, "grad_norm": 0.38481366634368896, "learning_rate": 4.257901232550606e-05, "loss": 4.3436, "step": 8243 }, { "epoch": 0.2518020769700672, "grad_norm": 0.3792811930179596, "learning_rate": 4.257730655559623e-05, "loss": 4.3149, "step": 8244 }, { "epoch": 0.251832620647526, "grad_norm": 0.3987763524055481, "learning_rate": 4.25756006238431e-05, "loss": 4.3547, "step": 8245 }, { "epoch": 0.25186316432498473, "grad_norm": 0.416940301656723, "learning_rate": 4.257389453026238e-05, "loss": 4.3295, "step": 8246 }, { "epoch": 0.2518937080024435, "grad_norm": 0.39507922530174255, "learning_rate": 4.257218827486977e-05, "loss": 4.3679, "step": 8247 }, { "epoch": 0.25192425167990223, "grad_norm": 0.3868568539619446, "learning_rate": 4.2570481857680995e-05, "loss": 4.3235, "step": 8248 }, { "epoch": 0.25195479535736104, "grad_norm": 0.3948149085044861, "learning_rate": 4.2568775278711756e-05, "loss": 4.2711, "step": 8249 }, { "epoch": 0.2519853390348198, "grad_norm": 0.40036290884017944, "learning_rate": 4.256706853797777e-05, "loss": 4.4241, "step": 8250 }, { "epoch": 0.25201588271227854, "grad_norm": 0.3800930082798004, "learning_rate": 4.2565361635494753e-05, "loss": 4.3492, "step": 8251 }, { "epoch": 0.25204642638973734, "grad_norm": 0.3915810286998749, "learning_rate": 4.2563654571278425e-05, "loss": 4.3452, "step": 8252 }, { "epoch": 0.2520769700671961, "grad_norm": 0.39825916290283203, "learning_rate": 4.2561947345344486e-05, "loss": 4.3357, "step": 8253 }, { "epoch": 0.25210751374465484, "grad_norm": 0.38093966245651245, "learning_rate": 4.2560239957708684e-05, "loss": 4.2863, "step": 8254 }, { "epoch": 0.25213805742211365, "grad_norm": 0.39685171842575073, "learning_rate": 4.255853240838671e-05, "loss": 4.4359, "step": 8255 }, { "epoch": 0.2521686010995724, "grad_norm": 0.388062447309494, "learning_rate": 4.25568246973943e-05, "loss": 4.4138, "step": 8256 }, { "epoch": 0.25219914477703115, "grad_norm": 0.37927818298339844, "learning_rate": 4.255511682474719e-05, "loss": 4.3861, "step": 8257 }, { "epoch": 0.2522296884544899, "grad_norm": 0.3769436180591583, "learning_rate": 4.2553408790461094e-05, "loss": 4.329, "step": 8258 }, { "epoch": 0.2522602321319487, "grad_norm": 0.3807542026042938, "learning_rate": 4.255170059455173e-05, "loss": 4.3333, "step": 8259 }, { "epoch": 0.25229077580940745, "grad_norm": 0.40442755818367004, "learning_rate": 4.254999223703484e-05, "loss": 4.3659, "step": 8260 }, { "epoch": 0.2523213194868662, "grad_norm": 0.40075623989105225, "learning_rate": 4.2548283717926146e-05, "loss": 4.4669, "step": 8261 }, { "epoch": 0.252351863164325, "grad_norm": 0.38314884901046753, "learning_rate": 4.254657503724138e-05, "loss": 4.4369, "step": 8262 }, { "epoch": 0.25238240684178376, "grad_norm": 0.37396225333213806, "learning_rate": 4.254486619499628e-05, "loss": 4.4064, "step": 8263 }, { "epoch": 0.2524129505192425, "grad_norm": 0.38621261715888977, "learning_rate": 4.254315719120657e-05, "loss": 4.4571, "step": 8264 }, { "epoch": 0.25244349419670126, "grad_norm": 0.3970656394958496, "learning_rate": 4.2541448025888e-05, "loss": 4.3488, "step": 8265 }, { "epoch": 0.25247403787416006, "grad_norm": 0.39486587047576904, "learning_rate": 4.2539738699056284e-05, "loss": 4.4353, "step": 8266 }, { "epoch": 0.2525045815516188, "grad_norm": 0.37512364983558655, "learning_rate": 4.253802921072719e-05, "loss": 4.3779, "step": 8267 }, { "epoch": 0.25253512522907756, "grad_norm": 0.37739166617393494, "learning_rate": 4.2536319560916446e-05, "loss": 4.3773, "step": 8268 }, { "epoch": 0.25256566890653637, "grad_norm": 0.3870053291320801, "learning_rate": 4.253460974963978e-05, "loss": 4.3664, "step": 8269 }, { "epoch": 0.2525962125839951, "grad_norm": 0.3703470528125763, "learning_rate": 4.253289977691295e-05, "loss": 4.3497, "step": 8270 }, { "epoch": 0.25262675626145387, "grad_norm": 0.3914886713027954, "learning_rate": 4.25311896427517e-05, "loss": 4.3644, "step": 8271 }, { "epoch": 0.25265729993891267, "grad_norm": 0.3836403489112854, "learning_rate": 4.252947934717178e-05, "loss": 4.3739, "step": 8272 }, { "epoch": 0.2526878436163714, "grad_norm": 0.3904104232788086, "learning_rate": 4.252776889018892e-05, "loss": 4.3305, "step": 8273 }, { "epoch": 0.25271838729383017, "grad_norm": 0.3845826983451843, "learning_rate": 4.252605827181888e-05, "loss": 4.3546, "step": 8274 }, { "epoch": 0.2527489309712889, "grad_norm": 0.385710746049881, "learning_rate": 4.252434749207742e-05, "loss": 4.3748, "step": 8275 }, { "epoch": 0.2527794746487477, "grad_norm": 0.3833864629268646, "learning_rate": 4.2522636550980265e-05, "loss": 4.3021, "step": 8276 }, { "epoch": 0.2528100183262065, "grad_norm": 0.3762345612049103, "learning_rate": 4.2520925448543204e-05, "loss": 4.4622, "step": 8277 }, { "epoch": 0.2528405620036652, "grad_norm": 0.37143969535827637, "learning_rate": 4.251921418478197e-05, "loss": 4.422, "step": 8278 }, { "epoch": 0.25287110568112403, "grad_norm": 0.38703271746635437, "learning_rate": 4.2517502759712313e-05, "loss": 4.2814, "step": 8279 }, { "epoch": 0.2529016493585828, "grad_norm": 0.3888823688030243, "learning_rate": 4.2515791173350015e-05, "loss": 4.4001, "step": 8280 }, { "epoch": 0.25293219303604153, "grad_norm": 0.38650962710380554, "learning_rate": 4.251407942571082e-05, "loss": 4.3826, "step": 8281 }, { "epoch": 0.2529627367135003, "grad_norm": 0.39353469014167786, "learning_rate": 4.2512367516810484e-05, "loss": 4.3838, "step": 8282 }, { "epoch": 0.2529932803909591, "grad_norm": 0.3817727565765381, "learning_rate": 4.251065544666478e-05, "loss": 4.4051, "step": 8283 }, { "epoch": 0.25302382406841784, "grad_norm": 0.37041375041007996, "learning_rate": 4.250894321528946e-05, "loss": 4.4161, "step": 8284 }, { "epoch": 0.2530543677458766, "grad_norm": 0.39178621768951416, "learning_rate": 4.2507230822700314e-05, "loss": 4.4044, "step": 8285 }, { "epoch": 0.2530849114233354, "grad_norm": 0.37462836503982544, "learning_rate": 4.250551826891308e-05, "loss": 4.4603, "step": 8286 }, { "epoch": 0.25311545510079414, "grad_norm": 0.3764724135398865, "learning_rate": 4.250380555394354e-05, "loss": 4.3673, "step": 8287 }, { "epoch": 0.2531459987782529, "grad_norm": 0.3786930739879608, "learning_rate": 4.250209267780747e-05, "loss": 4.3315, "step": 8288 }, { "epoch": 0.2531765424557117, "grad_norm": 0.38294559717178345, "learning_rate": 4.250037964052063e-05, "loss": 4.3604, "step": 8289 }, { "epoch": 0.25320708613317044, "grad_norm": 0.37505069375038147, "learning_rate": 4.24986664420988e-05, "loss": 4.3497, "step": 8290 }, { "epoch": 0.2532376298106292, "grad_norm": 0.383296400308609, "learning_rate": 4.249695308255774e-05, "loss": 4.3806, "step": 8291 }, { "epoch": 0.25326817348808794, "grad_norm": 0.38289421796798706, "learning_rate": 4.249523956191325e-05, "loss": 4.4338, "step": 8292 }, { "epoch": 0.25329871716554675, "grad_norm": 0.3744172155857086, "learning_rate": 4.2493525880181084e-05, "loss": 4.3588, "step": 8293 }, { "epoch": 0.2533292608430055, "grad_norm": 0.39948564767837524, "learning_rate": 4.249181203737704e-05, "loss": 4.3084, "step": 8294 }, { "epoch": 0.25335980452046425, "grad_norm": 0.37930384278297424, "learning_rate": 4.2490098033516887e-05, "loss": 4.4354, "step": 8295 }, { "epoch": 0.25339034819792305, "grad_norm": 0.37627077102661133, "learning_rate": 4.24883838686164e-05, "loss": 4.4825, "step": 8296 }, { "epoch": 0.2534208918753818, "grad_norm": 0.3897319734096527, "learning_rate": 4.248666954269138e-05, "loss": 4.4068, "step": 8297 }, { "epoch": 0.25345143555284055, "grad_norm": 0.3744967579841614, "learning_rate": 4.2484955055757605e-05, "loss": 4.3473, "step": 8298 }, { "epoch": 0.2534819792302993, "grad_norm": 0.3922426700592041, "learning_rate": 4.248324040783085e-05, "loss": 4.4312, "step": 8299 }, { "epoch": 0.2535125229077581, "grad_norm": 0.390216588973999, "learning_rate": 4.248152559892692e-05, "loss": 4.3555, "step": 8300 }, { "epoch": 0.25354306658521686, "grad_norm": 0.3900797963142395, "learning_rate": 4.247981062906159e-05, "loss": 4.3629, "step": 8301 }, { "epoch": 0.2535736102626756, "grad_norm": 0.38530823588371277, "learning_rate": 4.247809549825066e-05, "loss": 4.2939, "step": 8302 }, { "epoch": 0.2536041539401344, "grad_norm": 0.37989047169685364, "learning_rate": 4.2476380206509916e-05, "loss": 4.3102, "step": 8303 }, { "epoch": 0.25363469761759316, "grad_norm": 0.40639495849609375, "learning_rate": 4.247466475385515e-05, "loss": 4.29, "step": 8304 }, { "epoch": 0.2536652412950519, "grad_norm": 0.36821261048316956, "learning_rate": 4.247294914030216e-05, "loss": 4.3576, "step": 8305 }, { "epoch": 0.25369578497251066, "grad_norm": 0.37160322070121765, "learning_rate": 4.247123336586676e-05, "loss": 4.3648, "step": 8306 }, { "epoch": 0.25372632864996947, "grad_norm": 0.3840083181858063, "learning_rate": 4.246951743056471e-05, "loss": 4.2816, "step": 8307 }, { "epoch": 0.2537568723274282, "grad_norm": 0.3789529800415039, "learning_rate": 4.246780133441185e-05, "loss": 4.3992, "step": 8308 }, { "epoch": 0.25378741600488697, "grad_norm": 0.38755717873573303, "learning_rate": 4.246608507742396e-05, "loss": 4.3612, "step": 8309 }, { "epoch": 0.2538179596823458, "grad_norm": 0.3830241560935974, "learning_rate": 4.246436865961683e-05, "loss": 4.3667, "step": 8310 }, { "epoch": 0.2538485033598045, "grad_norm": 0.3964923918247223, "learning_rate": 4.2462652081006285e-05, "loss": 4.4447, "step": 8311 }, { "epoch": 0.2538790470372633, "grad_norm": 0.38355696201324463, "learning_rate": 4.2460935341608124e-05, "loss": 4.4517, "step": 8312 }, { "epoch": 0.2539095907147221, "grad_norm": 0.38575708866119385, "learning_rate": 4.245921844143815e-05, "loss": 4.3208, "step": 8313 }, { "epoch": 0.2539401343921808, "grad_norm": 0.38355979323387146, "learning_rate": 4.2457501380512185e-05, "loss": 4.1999, "step": 8314 }, { "epoch": 0.2539706780696396, "grad_norm": 0.38231170177459717, "learning_rate": 4.245578415884603e-05, "loss": 4.4502, "step": 8315 }, { "epoch": 0.2540012217470983, "grad_norm": 0.3937806189060211, "learning_rate": 4.245406677645549e-05, "loss": 4.2982, "step": 8316 }, { "epoch": 0.25403176542455713, "grad_norm": 0.38667625188827515, "learning_rate": 4.245234923335638e-05, "loss": 4.3427, "step": 8317 }, { "epoch": 0.2540623091020159, "grad_norm": 0.3785587251186371, "learning_rate": 4.245063152956452e-05, "loss": 4.3835, "step": 8318 }, { "epoch": 0.25409285277947463, "grad_norm": 0.3777271807193756, "learning_rate": 4.244891366509573e-05, "loss": 4.3362, "step": 8319 }, { "epoch": 0.25412339645693344, "grad_norm": 0.38555455207824707, "learning_rate": 4.244719563996581e-05, "loss": 4.3935, "step": 8320 }, { "epoch": 0.2541539401343922, "grad_norm": 0.3842775821685791, "learning_rate": 4.2445477454190595e-05, "loss": 4.366, "step": 8321 }, { "epoch": 0.25418448381185094, "grad_norm": 0.37877750396728516, "learning_rate": 4.2443759107785894e-05, "loss": 4.3323, "step": 8322 }, { "epoch": 0.2542150274893097, "grad_norm": 0.3829072415828705, "learning_rate": 4.244204060076754e-05, "loss": 4.3897, "step": 8323 }, { "epoch": 0.2542455711667685, "grad_norm": 0.3807034492492676, "learning_rate": 4.244032193315135e-05, "loss": 4.3798, "step": 8324 }, { "epoch": 0.25427611484422724, "grad_norm": 0.38547584414482117, "learning_rate": 4.243860310495315e-05, "loss": 4.4474, "step": 8325 }, { "epoch": 0.254306658521686, "grad_norm": 0.3722260296344757, "learning_rate": 4.2436884116188766e-05, "loss": 4.3201, "step": 8326 }, { "epoch": 0.2543372021991448, "grad_norm": 0.39764204621315, "learning_rate": 4.243516496687401e-05, "loss": 4.3898, "step": 8327 }, { "epoch": 0.25436774587660355, "grad_norm": 0.3802752196788788, "learning_rate": 4.2433445657024744e-05, "loss": 4.3049, "step": 8328 }, { "epoch": 0.2543982895540623, "grad_norm": 0.3705696165561676, "learning_rate": 4.2431726186656775e-05, "loss": 4.3801, "step": 8329 }, { "epoch": 0.2544288332315211, "grad_norm": 0.3895391523838043, "learning_rate": 4.243000655578594e-05, "loss": 4.3179, "step": 8330 }, { "epoch": 0.25445937690897985, "grad_norm": 0.37329527735710144, "learning_rate": 4.242828676442807e-05, "loss": 4.3223, "step": 8331 }, { "epoch": 0.2544899205864386, "grad_norm": 0.39079394936561584, "learning_rate": 4.242656681259901e-05, "loss": 4.3947, "step": 8332 }, { "epoch": 0.25452046426389735, "grad_norm": 0.3841128647327423, "learning_rate": 4.242484670031458e-05, "loss": 4.3419, "step": 8333 }, { "epoch": 0.25455100794135616, "grad_norm": 0.37143856287002563, "learning_rate": 4.242312642759063e-05, "loss": 4.3799, "step": 8334 }, { "epoch": 0.2545815516188149, "grad_norm": 0.3757513463497162, "learning_rate": 4.2421405994443006e-05, "loss": 4.4107, "step": 8335 }, { "epoch": 0.25461209529627365, "grad_norm": 0.38026052713394165, "learning_rate": 4.241968540088753e-05, "loss": 4.2666, "step": 8336 }, { "epoch": 0.25464263897373246, "grad_norm": 0.3775828182697296, "learning_rate": 4.2417964646940056e-05, "loss": 4.3855, "step": 8337 }, { "epoch": 0.2546731826511912, "grad_norm": 0.3843933641910553, "learning_rate": 4.2416243732616435e-05, "loss": 4.3581, "step": 8338 }, { "epoch": 0.25470372632864996, "grad_norm": 0.36847150325775146, "learning_rate": 4.2414522657932495e-05, "loss": 4.3757, "step": 8339 }, { "epoch": 0.2547342700061087, "grad_norm": 0.3778327703475952, "learning_rate": 4.2412801422904093e-05, "loss": 4.3932, "step": 8340 }, { "epoch": 0.2547648136835675, "grad_norm": 0.3875722289085388, "learning_rate": 4.2411080027547066e-05, "loss": 4.3789, "step": 8341 }, { "epoch": 0.25479535736102626, "grad_norm": 0.3761765956878662, "learning_rate": 4.2409358471877284e-05, "loss": 4.3876, "step": 8342 }, { "epoch": 0.254825901038485, "grad_norm": 0.379064679145813, "learning_rate": 4.240763675591059e-05, "loss": 4.3486, "step": 8343 }, { "epoch": 0.2548564447159438, "grad_norm": 0.37281277775764465, "learning_rate": 4.240591487966283e-05, "loss": 4.3752, "step": 8344 }, { "epoch": 0.25488698839340257, "grad_norm": 0.36760127544403076, "learning_rate": 4.240419284314986e-05, "loss": 4.3606, "step": 8345 }, { "epoch": 0.2549175320708613, "grad_norm": 0.37992236018180847, "learning_rate": 4.2402470646387536e-05, "loss": 4.3423, "step": 8346 }, { "epoch": 0.2549480757483201, "grad_norm": 0.3871617019176483, "learning_rate": 4.240074828939172e-05, "loss": 4.3828, "step": 8347 }, { "epoch": 0.2549786194257789, "grad_norm": 0.3914221525192261, "learning_rate": 4.239902577217828e-05, "loss": 4.3924, "step": 8348 }, { "epoch": 0.2550091631032376, "grad_norm": 0.3742081820964813, "learning_rate": 4.2397303094763054e-05, "loss": 4.4329, "step": 8349 }, { "epoch": 0.2550397067806964, "grad_norm": 0.3908711373806, "learning_rate": 4.239558025716191e-05, "loss": 4.3095, "step": 8350 }, { "epoch": 0.2550702504581552, "grad_norm": 0.38839274644851685, "learning_rate": 4.239385725939072e-05, "loss": 4.3792, "step": 8351 }, { "epoch": 0.25510079413561393, "grad_norm": 0.3909786641597748, "learning_rate": 4.239213410146534e-05, "loss": 4.2631, "step": 8352 }, { "epoch": 0.2551313378130727, "grad_norm": 0.3886222541332245, "learning_rate": 4.239041078340164e-05, "loss": 4.3898, "step": 8353 }, { "epoch": 0.2551618814905315, "grad_norm": 0.38590213656425476, "learning_rate": 4.238868730521548e-05, "loss": 4.3287, "step": 8354 }, { "epoch": 0.25519242516799023, "grad_norm": 0.36683568358421326, "learning_rate": 4.238696366692275e-05, "loss": 4.345, "step": 8355 }, { "epoch": 0.255222968845449, "grad_norm": 0.38243794441223145, "learning_rate": 4.238523986853929e-05, "loss": 4.2187, "step": 8356 }, { "epoch": 0.25525351252290773, "grad_norm": 0.387277215719223, "learning_rate": 4.2383515910081004e-05, "loss": 4.4222, "step": 8357 }, { "epoch": 0.25528405620036654, "grad_norm": 0.3795536160469055, "learning_rate": 4.238179179156374e-05, "loss": 4.3021, "step": 8358 }, { "epoch": 0.2553145998778253, "grad_norm": 0.37398433685302734, "learning_rate": 4.2380067513003384e-05, "loss": 4.364, "step": 8359 }, { "epoch": 0.25534514355528404, "grad_norm": 0.3796558082103729, "learning_rate": 4.237834307441581e-05, "loss": 4.3349, "step": 8360 }, { "epoch": 0.25537568723274284, "grad_norm": 0.37451472878456116, "learning_rate": 4.2376618475816895e-05, "loss": 4.3732, "step": 8361 }, { "epoch": 0.2554062309102016, "grad_norm": 0.375553160905838, "learning_rate": 4.2374893717222526e-05, "loss": 4.3818, "step": 8362 }, { "epoch": 0.25543677458766034, "grad_norm": 0.38289883732795715, "learning_rate": 4.237316879864857e-05, "loss": 4.3297, "step": 8363 }, { "epoch": 0.25546731826511915, "grad_norm": 0.39016756415367126, "learning_rate": 4.237144372011092e-05, "loss": 4.3965, "step": 8364 }, { "epoch": 0.2554978619425779, "grad_norm": 0.38279879093170166, "learning_rate": 4.236971848162545e-05, "loss": 4.3953, "step": 8365 }, { "epoch": 0.25552840562003665, "grad_norm": 0.3928937315940857, "learning_rate": 4.236799308320806e-05, "loss": 4.354, "step": 8366 }, { "epoch": 0.2555589492974954, "grad_norm": 0.381294846534729, "learning_rate": 4.236626752487462e-05, "loss": 4.3359, "step": 8367 }, { "epoch": 0.2555894929749542, "grad_norm": 0.3849790394306183, "learning_rate": 4.236454180664103e-05, "loss": 4.3476, "step": 8368 }, { "epoch": 0.25562003665241295, "grad_norm": 0.3941763937473297, "learning_rate": 4.236281592852318e-05, "loss": 4.3376, "step": 8369 }, { "epoch": 0.2556505803298717, "grad_norm": 0.3699842691421509, "learning_rate": 4.236108989053695e-05, "loss": 4.3417, "step": 8370 }, { "epoch": 0.2556811240073305, "grad_norm": 0.3785075843334198, "learning_rate": 4.2359363692698244e-05, "loss": 4.3234, "step": 8371 }, { "epoch": 0.25571166768478926, "grad_norm": 0.3908839821815491, "learning_rate": 4.235763733502295e-05, "loss": 4.2088, "step": 8372 }, { "epoch": 0.255742211362248, "grad_norm": 0.37649181485176086, "learning_rate": 4.235591081752697e-05, "loss": 4.3069, "step": 8373 }, { "epoch": 0.25577275503970676, "grad_norm": 0.36729222536087036, "learning_rate": 4.235418414022618e-05, "loss": 4.4299, "step": 8374 }, { "epoch": 0.25580329871716556, "grad_norm": 0.3824925422668457, "learning_rate": 4.2352457303136504e-05, "loss": 4.3391, "step": 8375 }, { "epoch": 0.2558338423946243, "grad_norm": 0.3807773292064667, "learning_rate": 4.2350730306273835e-05, "loss": 4.3421, "step": 8376 }, { "epoch": 0.25586438607208306, "grad_norm": 0.38349947333335876, "learning_rate": 4.2349003149654065e-05, "loss": 4.4032, "step": 8377 }, { "epoch": 0.25589492974954187, "grad_norm": 0.3698146641254425, "learning_rate": 4.23472758332931e-05, "loss": 4.4064, "step": 8378 }, { "epoch": 0.2559254734270006, "grad_norm": 0.3979642391204834, "learning_rate": 4.234554835720686e-05, "loss": 4.3408, "step": 8379 }, { "epoch": 0.25595601710445937, "grad_norm": 0.3901624083518982, "learning_rate": 4.234382072141123e-05, "loss": 4.3279, "step": 8380 }, { "epoch": 0.2559865607819181, "grad_norm": 0.3760823607444763, "learning_rate": 4.234209292592213e-05, "loss": 4.368, "step": 8381 }, { "epoch": 0.2560171044593769, "grad_norm": 0.403605192899704, "learning_rate": 4.234036497075545e-05, "loss": 4.4324, "step": 8382 }, { "epoch": 0.25604764813683567, "grad_norm": 0.36943626403808594, "learning_rate": 4.233863685592713e-05, "loss": 4.3845, "step": 8383 }, { "epoch": 0.2560781918142944, "grad_norm": 0.37771305441856384, "learning_rate": 4.233690858145306e-05, "loss": 4.3241, "step": 8384 }, { "epoch": 0.2561087354917532, "grad_norm": 0.39989346265792847, "learning_rate": 4.233518014734916e-05, "loss": 4.265, "step": 8385 }, { "epoch": 0.256139279169212, "grad_norm": 0.39070925116539, "learning_rate": 4.233345155363134e-05, "loss": 4.3636, "step": 8386 }, { "epoch": 0.2561698228466707, "grad_norm": 0.38365015387535095, "learning_rate": 4.233172280031553e-05, "loss": 4.249, "step": 8387 }, { "epoch": 0.25620036652412953, "grad_norm": 0.3737625777721405, "learning_rate": 4.232999388741762e-05, "loss": 4.2236, "step": 8388 }, { "epoch": 0.2562309102015883, "grad_norm": 0.380868524312973, "learning_rate": 4.2328264814953554e-05, "loss": 4.3723, "step": 8389 }, { "epoch": 0.25626145387904703, "grad_norm": 0.38888928294181824, "learning_rate": 4.232653558293925e-05, "loss": 4.3562, "step": 8390 }, { "epoch": 0.2562919975565058, "grad_norm": 0.41020065546035767, "learning_rate": 4.232480619139062e-05, "loss": 4.37, "step": 8391 }, { "epoch": 0.2563225412339646, "grad_norm": 0.3717392683029175, "learning_rate": 4.232307664032359e-05, "loss": 4.3722, "step": 8392 }, { "epoch": 0.25635308491142333, "grad_norm": 0.38144758343696594, "learning_rate": 4.2321346929754093e-05, "loss": 4.3841, "step": 8393 }, { "epoch": 0.2563836285888821, "grad_norm": 0.37635159492492676, "learning_rate": 4.231961705969805e-05, "loss": 4.3629, "step": 8394 }, { "epoch": 0.2564141722663409, "grad_norm": 0.3589358329772949, "learning_rate": 4.2317887030171376e-05, "loss": 4.3838, "step": 8395 }, { "epoch": 0.25644471594379964, "grad_norm": 0.3906913101673126, "learning_rate": 4.231615684119002e-05, "loss": 4.2437, "step": 8396 }, { "epoch": 0.2564752596212584, "grad_norm": 0.39479687809944153, "learning_rate": 4.23144264927699e-05, "loss": 4.2504, "step": 8397 }, { "epoch": 0.25650580329871714, "grad_norm": 0.37437355518341064, "learning_rate": 4.231269598492696e-05, "loss": 4.3332, "step": 8398 }, { "epoch": 0.25653634697617594, "grad_norm": 0.3851245939731598, "learning_rate": 4.231096531767712e-05, "loss": 4.3038, "step": 8399 }, { "epoch": 0.2565668906536347, "grad_norm": 0.37975335121154785, "learning_rate": 4.2309234491036334e-05, "loss": 4.4231, "step": 8400 }, { "epoch": 0.25659743433109344, "grad_norm": 0.3780101239681244, "learning_rate": 4.2307503505020514e-05, "loss": 4.3503, "step": 8401 }, { "epoch": 0.25662797800855225, "grad_norm": 0.37317803502082825, "learning_rate": 4.230577235964561e-05, "loss": 4.3436, "step": 8402 }, { "epoch": 0.256658521686011, "grad_norm": 0.37412771582603455, "learning_rate": 4.2304041054927565e-05, "loss": 4.3573, "step": 8403 }, { "epoch": 0.25668906536346975, "grad_norm": 0.3723258674144745, "learning_rate": 4.2302309590882325e-05, "loss": 4.3717, "step": 8404 }, { "epoch": 0.25671960904092855, "grad_norm": 0.38076311349868774, "learning_rate": 4.230057796752581e-05, "loss": 4.4212, "step": 8405 }, { "epoch": 0.2567501527183873, "grad_norm": 0.3778185248374939, "learning_rate": 4.2298846184873995e-05, "loss": 4.3863, "step": 8406 }, { "epoch": 0.25678069639584605, "grad_norm": 0.37821927666664124, "learning_rate": 4.22971142429428e-05, "loss": 4.3551, "step": 8407 }, { "epoch": 0.2568112400733048, "grad_norm": 0.37870290875434875, "learning_rate": 4.2295382141748184e-05, "loss": 4.3758, "step": 8408 }, { "epoch": 0.2568417837507636, "grad_norm": 0.3738004267215729, "learning_rate": 4.229364988130609e-05, "loss": 4.4104, "step": 8409 }, { "epoch": 0.25687232742822236, "grad_norm": 0.37849003076553345, "learning_rate": 4.229191746163247e-05, "loss": 4.2897, "step": 8410 }, { "epoch": 0.2569028711056811, "grad_norm": 0.37954649329185486, "learning_rate": 4.229018488274328e-05, "loss": 4.4036, "step": 8411 }, { "epoch": 0.2569334147831399, "grad_norm": 0.3721438944339752, "learning_rate": 4.228845214465445e-05, "loss": 4.3638, "step": 8412 }, { "epoch": 0.25696395846059866, "grad_norm": 0.3794623613357544, "learning_rate": 4.228671924738197e-05, "loss": 4.3854, "step": 8413 }, { "epoch": 0.2569945021380574, "grad_norm": 0.3675267994403839, "learning_rate": 4.228498619094178e-05, "loss": 4.2928, "step": 8414 }, { "epoch": 0.25702504581551616, "grad_norm": 0.3950991630554199, "learning_rate": 4.228325297534983e-05, "loss": 4.456, "step": 8415 }, { "epoch": 0.25705558949297497, "grad_norm": 0.385130912065506, "learning_rate": 4.2281519600622074e-05, "loss": 4.301, "step": 8416 }, { "epoch": 0.2570861331704337, "grad_norm": 0.3792385458946228, "learning_rate": 4.22797860667745e-05, "loss": 4.3418, "step": 8417 }, { "epoch": 0.25711667684789247, "grad_norm": 0.3709896206855774, "learning_rate": 4.227805237382304e-05, "loss": 4.4623, "step": 8418 }, { "epoch": 0.25714722052535127, "grad_norm": 0.372885137796402, "learning_rate": 4.227631852178366e-05, "loss": 4.4382, "step": 8419 }, { "epoch": 0.25717776420281, "grad_norm": 0.3959248960018158, "learning_rate": 4.227458451067235e-05, "loss": 4.2993, "step": 8420 }, { "epoch": 0.25720830788026877, "grad_norm": 0.37052595615386963, "learning_rate": 4.227285034050505e-05, "loss": 4.3347, "step": 8421 }, { "epoch": 0.2572388515577276, "grad_norm": 0.3792558014392853, "learning_rate": 4.227111601129774e-05, "loss": 4.2108, "step": 8422 }, { "epoch": 0.2572693952351863, "grad_norm": 0.3852512836456299, "learning_rate": 4.226938152306638e-05, "loss": 4.3326, "step": 8423 }, { "epoch": 0.2572999389126451, "grad_norm": 0.3770584762096405, "learning_rate": 4.226764687582695e-05, "loss": 4.3096, "step": 8424 }, { "epoch": 0.2573304825901038, "grad_norm": 0.37465959787368774, "learning_rate": 4.2265912069595416e-05, "loss": 4.2847, "step": 8425 }, { "epoch": 0.25736102626756263, "grad_norm": 0.38567447662353516, "learning_rate": 4.226417710438775e-05, "loss": 4.3791, "step": 8426 }, { "epoch": 0.2573915699450214, "grad_norm": 0.3797268867492676, "learning_rate": 4.226244198021992e-05, "loss": 4.3956, "step": 8427 }, { "epoch": 0.25742211362248013, "grad_norm": 0.38673529028892517, "learning_rate": 4.226070669710793e-05, "loss": 4.4985, "step": 8428 }, { "epoch": 0.25745265729993894, "grad_norm": 0.3791191875934601, "learning_rate": 4.225897125506773e-05, "loss": 4.4615, "step": 8429 }, { "epoch": 0.2574832009773977, "grad_norm": 0.37650105357170105, "learning_rate": 4.225723565411531e-05, "loss": 4.4259, "step": 8430 }, { "epoch": 0.25751374465485644, "grad_norm": 0.3861980736255646, "learning_rate": 4.225549989426665e-05, "loss": 4.2736, "step": 8431 }, { "epoch": 0.2575442883323152, "grad_norm": 0.3834536373615265, "learning_rate": 4.225376397553772e-05, "loss": 4.3502, "step": 8432 }, { "epoch": 0.257574832009774, "grad_norm": 0.3779304027557373, "learning_rate": 4.225202789794452e-05, "loss": 4.4119, "step": 8433 }, { "epoch": 0.25760537568723274, "grad_norm": 0.39581599831581116, "learning_rate": 4.225029166150304e-05, "loss": 4.3417, "step": 8434 }, { "epoch": 0.2576359193646915, "grad_norm": 0.3984937071800232, "learning_rate": 4.224855526622924e-05, "loss": 4.366, "step": 8435 }, { "epoch": 0.2576664630421503, "grad_norm": 0.38026902079582214, "learning_rate": 4.224681871213913e-05, "loss": 4.3687, "step": 8436 }, { "epoch": 0.25769700671960905, "grad_norm": 0.3769298493862152, "learning_rate": 4.224508199924869e-05, "loss": 4.35, "step": 8437 }, { "epoch": 0.2577275503970678, "grad_norm": 0.3779561519622803, "learning_rate": 4.224334512757392e-05, "loss": 4.4319, "step": 8438 }, { "epoch": 0.2577580940745266, "grad_norm": 0.38658201694488525, "learning_rate": 4.2241608097130794e-05, "loss": 4.343, "step": 8439 }, { "epoch": 0.25778863775198535, "grad_norm": 0.3881346583366394, "learning_rate": 4.223987090793533e-05, "loss": 4.3086, "step": 8440 }, { "epoch": 0.2578191814294441, "grad_norm": 0.373573362827301, "learning_rate": 4.22381335600035e-05, "loss": 4.3967, "step": 8441 }, { "epoch": 0.25784972510690285, "grad_norm": 0.3705849349498749, "learning_rate": 4.223639605335132e-05, "loss": 4.3273, "step": 8442 }, { "epoch": 0.25788026878436165, "grad_norm": 0.3724445700645447, "learning_rate": 4.2234658387994774e-05, "loss": 4.3546, "step": 8443 }, { "epoch": 0.2579108124618204, "grad_norm": 0.3649871051311493, "learning_rate": 4.2232920563949876e-05, "loss": 4.3664, "step": 8444 }, { "epoch": 0.25794135613927915, "grad_norm": 0.3673572242259979, "learning_rate": 4.2231182581232606e-05, "loss": 4.3598, "step": 8445 }, { "epoch": 0.25797189981673796, "grad_norm": 0.37977099418640137, "learning_rate": 4.2229444439858985e-05, "loss": 4.3494, "step": 8446 }, { "epoch": 0.2580024434941967, "grad_norm": 0.3748451769351959, "learning_rate": 4.222770613984501e-05, "loss": 4.2037, "step": 8447 }, { "epoch": 0.25803298717165546, "grad_norm": 0.3787255585193634, "learning_rate": 4.2225967681206686e-05, "loss": 4.3499, "step": 8448 }, { "epoch": 0.2580635308491142, "grad_norm": 0.401019811630249, "learning_rate": 4.222422906396002e-05, "loss": 4.4279, "step": 8449 }, { "epoch": 0.258094074526573, "grad_norm": 0.37499821186065674, "learning_rate": 4.222249028812102e-05, "loss": 4.3116, "step": 8450 }, { "epoch": 0.25812461820403176, "grad_norm": 0.38054415583610535, "learning_rate": 4.22207513537057e-05, "loss": 4.3685, "step": 8451 }, { "epoch": 0.2581551618814905, "grad_norm": 0.3918173611164093, "learning_rate": 4.221901226073007e-05, "loss": 4.3183, "step": 8452 }, { "epoch": 0.2581857055589493, "grad_norm": 0.36851966381073, "learning_rate": 4.2217273009210134e-05, "loss": 4.25, "step": 8453 }, { "epoch": 0.25821624923640807, "grad_norm": 0.3749760687351227, "learning_rate": 4.221553359916192e-05, "loss": 4.2908, "step": 8454 }, { "epoch": 0.2582467929138668, "grad_norm": 0.38175708055496216, "learning_rate": 4.221379403060144e-05, "loss": 4.4345, "step": 8455 }, { "epoch": 0.25827733659132557, "grad_norm": 0.38162508606910706, "learning_rate": 4.22120543035447e-05, "loss": 4.4008, "step": 8456 }, { "epoch": 0.2583078802687844, "grad_norm": 0.3999214768409729, "learning_rate": 4.221031441800773e-05, "loss": 4.3137, "step": 8457 }, { "epoch": 0.2583384239462431, "grad_norm": 0.3730642795562744, "learning_rate": 4.220857437400654e-05, "loss": 4.2974, "step": 8458 }, { "epoch": 0.2583689676237019, "grad_norm": 0.3728121519088745, "learning_rate": 4.220683417155716e-05, "loss": 4.2415, "step": 8459 }, { "epoch": 0.2583995113011607, "grad_norm": 0.3790700435638428, "learning_rate": 4.220509381067562e-05, "loss": 4.3487, "step": 8460 }, { "epoch": 0.25843005497861943, "grad_norm": 0.39180833101272583, "learning_rate": 4.220335329137793e-05, "loss": 4.3624, "step": 8461 }, { "epoch": 0.2584605986560782, "grad_norm": 0.3864022493362427, "learning_rate": 4.220161261368012e-05, "loss": 4.3618, "step": 8462 }, { "epoch": 0.258491142333537, "grad_norm": 0.3845137059688568, "learning_rate": 4.2199871777598224e-05, "loss": 4.34, "step": 8463 }, { "epoch": 0.25852168601099573, "grad_norm": 0.3748812973499298, "learning_rate": 4.219813078314825e-05, "loss": 4.3953, "step": 8464 }, { "epoch": 0.2585522296884545, "grad_norm": 0.37125369906425476, "learning_rate": 4.2196389630346264e-05, "loss": 4.3644, "step": 8465 }, { "epoch": 0.25858277336591323, "grad_norm": 0.4059460163116455, "learning_rate": 4.2194648319208265e-05, "loss": 4.4253, "step": 8466 }, { "epoch": 0.25861331704337204, "grad_norm": 0.36988887190818787, "learning_rate": 4.2192906849750294e-05, "loss": 4.3882, "step": 8467 }, { "epoch": 0.2586438607208308, "grad_norm": 0.37840765714645386, "learning_rate": 4.21911652219884e-05, "loss": 4.3183, "step": 8468 }, { "epoch": 0.25867440439828954, "grad_norm": 0.3975393772125244, "learning_rate": 4.21894234359386e-05, "loss": 4.416, "step": 8469 }, { "epoch": 0.25870494807574834, "grad_norm": 0.36861947178840637, "learning_rate": 4.218768149161695e-05, "loss": 4.3013, "step": 8470 }, { "epoch": 0.2587354917532071, "grad_norm": 0.38406428694725037, "learning_rate": 4.2185939389039473e-05, "loss": 4.3929, "step": 8471 }, { "epoch": 0.25876603543066584, "grad_norm": 0.38663896918296814, "learning_rate": 4.218419712822222e-05, "loss": 4.393, "step": 8472 }, { "epoch": 0.2587965791081246, "grad_norm": 0.37437793612480164, "learning_rate": 4.218245470918123e-05, "loss": 4.3573, "step": 8473 }, { "epoch": 0.2588271227855834, "grad_norm": 0.3706629276275635, "learning_rate": 4.2180712131932544e-05, "loss": 4.3928, "step": 8474 }, { "epoch": 0.25885766646304215, "grad_norm": 0.3841342628002167, "learning_rate": 4.2178969396492205e-05, "loss": 4.3154, "step": 8475 }, { "epoch": 0.2588882101405009, "grad_norm": 0.3840445578098297, "learning_rate": 4.217722650287626e-05, "loss": 4.3998, "step": 8476 }, { "epoch": 0.2589187538179597, "grad_norm": 0.3851517140865326, "learning_rate": 4.217548345110076e-05, "loss": 4.3444, "step": 8477 }, { "epoch": 0.25894929749541845, "grad_norm": 0.38378608226776123, "learning_rate": 4.217374024118176e-05, "loss": 4.3248, "step": 8478 }, { "epoch": 0.2589798411728772, "grad_norm": 0.37762829661369324, "learning_rate": 4.21719968731353e-05, "loss": 4.4167, "step": 8479 }, { "epoch": 0.259010384850336, "grad_norm": 0.3811649680137634, "learning_rate": 4.217025334697743e-05, "loss": 4.2863, "step": 8480 }, { "epoch": 0.25904092852779476, "grad_norm": 0.3652648627758026, "learning_rate": 4.2168509662724215e-05, "loss": 4.3629, "step": 8481 }, { "epoch": 0.2590714722052535, "grad_norm": 0.39123526215553284, "learning_rate": 4.216676582039171e-05, "loss": 4.2939, "step": 8482 }, { "epoch": 0.25910201588271226, "grad_norm": 0.39415404200553894, "learning_rate": 4.216502181999595e-05, "loss": 4.4344, "step": 8483 }, { "epoch": 0.25913255956017106, "grad_norm": 0.37691158056259155, "learning_rate": 4.216327766155303e-05, "loss": 4.4587, "step": 8484 }, { "epoch": 0.2591631032376298, "grad_norm": 0.3824508786201477, "learning_rate": 4.216153334507897e-05, "loss": 4.3461, "step": 8485 }, { "epoch": 0.25919364691508856, "grad_norm": 0.37363144755363464, "learning_rate": 4.215978887058986e-05, "loss": 4.4147, "step": 8486 }, { "epoch": 0.25922419059254737, "grad_norm": 0.3878296911716461, "learning_rate": 4.215804423810173e-05, "loss": 4.3677, "step": 8487 }, { "epoch": 0.2592547342700061, "grad_norm": 0.3790278732776642, "learning_rate": 4.215629944763069e-05, "loss": 4.4024, "step": 8488 }, { "epoch": 0.25928527794746487, "grad_norm": 0.3818981647491455, "learning_rate": 4.2154554499192774e-05, "loss": 4.3539, "step": 8489 }, { "epoch": 0.2593158216249236, "grad_norm": 0.3786701560020447, "learning_rate": 4.215280939280405e-05, "loss": 4.3652, "step": 8490 }, { "epoch": 0.2593463653023824, "grad_norm": 0.3912792205810547, "learning_rate": 4.2151064128480585e-05, "loss": 4.3776, "step": 8491 }, { "epoch": 0.25937690897984117, "grad_norm": 0.3871515393257141, "learning_rate": 4.214931870623847e-05, "loss": 4.3552, "step": 8492 }, { "epoch": 0.2594074526572999, "grad_norm": 0.37196433544158936, "learning_rate": 4.214757312609375e-05, "loss": 4.3382, "step": 8493 }, { "epoch": 0.2594379963347587, "grad_norm": 0.37185096740722656, "learning_rate": 4.2145827388062506e-05, "loss": 4.3565, "step": 8494 }, { "epoch": 0.2594685400122175, "grad_norm": 0.3879925608634949, "learning_rate": 4.2144081492160827e-05, "loss": 4.3604, "step": 8495 }, { "epoch": 0.2594990836896762, "grad_norm": 0.3858656585216522, "learning_rate": 4.2142335438404765e-05, "loss": 4.3529, "step": 8496 }, { "epoch": 0.25952962736713503, "grad_norm": 0.38202378153800964, "learning_rate": 4.214058922681041e-05, "loss": 4.3456, "step": 8497 }, { "epoch": 0.2595601710445938, "grad_norm": 0.3758775293827057, "learning_rate": 4.213884285739383e-05, "loss": 4.3219, "step": 8498 }, { "epoch": 0.25959071472205253, "grad_norm": 0.3795255422592163, "learning_rate": 4.213709633017112e-05, "loss": 4.3684, "step": 8499 }, { "epoch": 0.2596212583995113, "grad_norm": 0.38384613394737244, "learning_rate": 4.213534964515835e-05, "loss": 4.2747, "step": 8500 }, { "epoch": 0.2596518020769701, "grad_norm": 0.39425697922706604, "learning_rate": 4.213360280237161e-05, "loss": 4.3675, "step": 8501 }, { "epoch": 0.25968234575442883, "grad_norm": 0.38945040106773376, "learning_rate": 4.213185580182697e-05, "loss": 4.2976, "step": 8502 }, { "epoch": 0.2597128894318876, "grad_norm": 0.3806120455265045, "learning_rate": 4.213010864354053e-05, "loss": 4.2476, "step": 8503 }, { "epoch": 0.2597434331093464, "grad_norm": 0.389024555683136, "learning_rate": 4.212836132752838e-05, "loss": 4.3505, "step": 8504 }, { "epoch": 0.25977397678680514, "grad_norm": 0.3817577660083771, "learning_rate": 4.212661385380659e-05, "loss": 4.3374, "step": 8505 }, { "epoch": 0.2598045204642639, "grad_norm": 0.3803268074989319, "learning_rate": 4.2124866222391266e-05, "loss": 4.3579, "step": 8506 }, { "epoch": 0.25983506414172264, "grad_norm": 0.385400652885437, "learning_rate": 4.212311843329849e-05, "loss": 4.3622, "step": 8507 }, { "epoch": 0.25986560781918144, "grad_norm": 0.39334139227867126, "learning_rate": 4.212137048654436e-05, "loss": 4.4309, "step": 8508 }, { "epoch": 0.2598961514966402, "grad_norm": 0.39480507373809814, "learning_rate": 4.2119622382144975e-05, "loss": 4.3947, "step": 8509 }, { "epoch": 0.25992669517409894, "grad_norm": 0.3729502856731415, "learning_rate": 4.2117874120116415e-05, "loss": 4.3874, "step": 8510 }, { "epoch": 0.25995723885155775, "grad_norm": 0.3789709806442261, "learning_rate": 4.21161257004748e-05, "loss": 4.3621, "step": 8511 }, { "epoch": 0.2599877825290165, "grad_norm": 0.3883737623691559, "learning_rate": 4.21143771232362e-05, "loss": 4.2988, "step": 8512 }, { "epoch": 0.26001832620647525, "grad_norm": 0.3965030014514923, "learning_rate": 4.211262838841674e-05, "loss": 4.284, "step": 8513 }, { "epoch": 0.26004886988393405, "grad_norm": 0.3715359568595886, "learning_rate": 4.211087949603251e-05, "loss": 4.3761, "step": 8514 }, { "epoch": 0.2600794135613928, "grad_norm": 0.38583987951278687, "learning_rate": 4.210913044609961e-05, "loss": 4.3891, "step": 8515 }, { "epoch": 0.26010995723885155, "grad_norm": 0.39655232429504395, "learning_rate": 4.2107381238634156e-05, "loss": 4.3767, "step": 8516 }, { "epoch": 0.2601405009163103, "grad_norm": 0.3891277015209198, "learning_rate": 4.210563187365225e-05, "loss": 4.3188, "step": 8517 }, { "epoch": 0.2601710445937691, "grad_norm": 0.39210715889930725, "learning_rate": 4.2103882351169986e-05, "loss": 4.4009, "step": 8518 }, { "epoch": 0.26020158827122786, "grad_norm": 0.382041335105896, "learning_rate": 4.210213267120349e-05, "loss": 4.3364, "step": 8519 }, { "epoch": 0.2602321319486866, "grad_norm": 0.37488439679145813, "learning_rate": 4.210038283376887e-05, "loss": 4.4548, "step": 8520 }, { "epoch": 0.2602626756261454, "grad_norm": 0.39371997117996216, "learning_rate": 4.2098632838882225e-05, "loss": 4.3182, "step": 8521 }, { "epoch": 0.26029321930360416, "grad_norm": 0.3836307227611542, "learning_rate": 4.209688268655968e-05, "loss": 4.2941, "step": 8522 }, { "epoch": 0.2603237629810629, "grad_norm": 0.38784000277519226, "learning_rate": 4.209513237681734e-05, "loss": 4.3286, "step": 8523 }, { "epoch": 0.26035430665852166, "grad_norm": 0.37668275833129883, "learning_rate": 4.209338190967134e-05, "loss": 4.444, "step": 8524 }, { "epoch": 0.26038485033598047, "grad_norm": 0.37429606914520264, "learning_rate": 4.2091631285137765e-05, "loss": 4.3425, "step": 8525 }, { "epoch": 0.2604153940134392, "grad_norm": 0.38763824105262756, "learning_rate": 4.208988050323277e-05, "loss": 4.3987, "step": 8526 }, { "epoch": 0.26044593769089797, "grad_norm": 0.3884838819503784, "learning_rate": 4.208812956397245e-05, "loss": 4.3205, "step": 8527 }, { "epoch": 0.26047648136835677, "grad_norm": 0.3772537410259247, "learning_rate": 4.2086378467372937e-05, "loss": 4.4209, "step": 8528 }, { "epoch": 0.2605070250458155, "grad_norm": 0.38743409514427185, "learning_rate": 4.208462721345035e-05, "loss": 4.2962, "step": 8529 }, { "epoch": 0.26053756872327427, "grad_norm": 0.37773463129997253, "learning_rate": 4.208287580222082e-05, "loss": 4.4085, "step": 8530 }, { "epoch": 0.260568112400733, "grad_norm": 0.37694069743156433, "learning_rate": 4.208112423370047e-05, "loss": 4.3508, "step": 8531 }, { "epoch": 0.2605986560781918, "grad_norm": 0.3828778564929962, "learning_rate": 4.207937250790542e-05, "loss": 4.2958, "step": 8532 }, { "epoch": 0.2606291997556506, "grad_norm": 0.39247170090675354, "learning_rate": 4.2077620624851814e-05, "loss": 4.2984, "step": 8533 }, { "epoch": 0.2606597434331093, "grad_norm": 0.3828425109386444, "learning_rate": 4.207586858455578e-05, "loss": 4.3465, "step": 8534 }, { "epoch": 0.26069028711056813, "grad_norm": 0.3800862431526184, "learning_rate": 4.207411638703343e-05, "loss": 4.2989, "step": 8535 }, { "epoch": 0.2607208307880269, "grad_norm": 0.37546542286872864, "learning_rate": 4.207236403230091e-05, "loss": 4.3816, "step": 8536 }, { "epoch": 0.26075137446548563, "grad_norm": 0.3669728934764862, "learning_rate": 4.207061152037437e-05, "loss": 4.3205, "step": 8537 }, { "epoch": 0.26078191814294444, "grad_norm": 0.379659503698349, "learning_rate": 4.2068858851269926e-05, "loss": 4.3328, "step": 8538 }, { "epoch": 0.2608124618204032, "grad_norm": 0.3863960802555084, "learning_rate": 4.206710602500373e-05, "loss": 4.3673, "step": 8539 }, { "epoch": 0.26084300549786194, "grad_norm": 0.3754126727581024, "learning_rate": 4.20653530415919e-05, "loss": 4.3698, "step": 8540 }, { "epoch": 0.2608735491753207, "grad_norm": 0.38334348797798157, "learning_rate": 4.20635999010506e-05, "loss": 4.2393, "step": 8541 }, { "epoch": 0.2609040928527795, "grad_norm": 0.37000688910484314, "learning_rate": 4.206184660339596e-05, "loss": 4.3429, "step": 8542 }, { "epoch": 0.26093463653023824, "grad_norm": 0.3738555610179901, "learning_rate": 4.206009314864413e-05, "loss": 4.1407, "step": 8543 }, { "epoch": 0.260965180207697, "grad_norm": 0.36172929406166077, "learning_rate": 4.2058339536811254e-05, "loss": 4.3576, "step": 8544 }, { "epoch": 0.2609957238851558, "grad_norm": 0.38404494524002075, "learning_rate": 4.205658576791346e-05, "loss": 4.4352, "step": 8545 }, { "epoch": 0.26102626756261454, "grad_norm": 0.38546302914619446, "learning_rate": 4.2054831841966925e-05, "loss": 4.3718, "step": 8546 }, { "epoch": 0.2610568112400733, "grad_norm": 0.37366464734077454, "learning_rate": 4.205307775898778e-05, "loss": 4.3815, "step": 8547 }, { "epoch": 0.26108735491753204, "grad_norm": 0.37321123480796814, "learning_rate": 4.205132351899218e-05, "loss": 4.3092, "step": 8548 }, { "epoch": 0.26111789859499085, "grad_norm": 0.37352025508880615, "learning_rate": 4.204956912199627e-05, "loss": 4.1849, "step": 8549 }, { "epoch": 0.2611484422724496, "grad_norm": 0.37774524092674255, "learning_rate": 4.204781456801623e-05, "loss": 4.2588, "step": 8550 }, { "epoch": 0.26117898594990835, "grad_norm": 0.3576265275478363, "learning_rate": 4.204605985706818e-05, "loss": 4.2999, "step": 8551 }, { "epoch": 0.26120952962736715, "grad_norm": 0.37407734990119934, "learning_rate": 4.204430498916829e-05, "loss": 4.3222, "step": 8552 }, { "epoch": 0.2612400733048259, "grad_norm": 0.37422510981559753, "learning_rate": 4.2042549964332736e-05, "loss": 4.4584, "step": 8553 }, { "epoch": 0.26127061698228465, "grad_norm": 0.3754587173461914, "learning_rate": 4.204079478257765e-05, "loss": 4.4131, "step": 8554 }, { "epoch": 0.26130116065974346, "grad_norm": 0.3745045065879822, "learning_rate": 4.203903944391921e-05, "loss": 4.2844, "step": 8555 }, { "epoch": 0.2613317043372022, "grad_norm": 0.37022295594215393, "learning_rate": 4.203728394837357e-05, "loss": 4.3812, "step": 8556 }, { "epoch": 0.26136224801466096, "grad_norm": 0.4266577959060669, "learning_rate": 4.203552829595691e-05, "loss": 4.3249, "step": 8557 }, { "epoch": 0.2613927916921197, "grad_norm": 0.36712646484375, "learning_rate": 4.2033772486685366e-05, "loss": 4.4413, "step": 8558 }, { "epoch": 0.2614233353695785, "grad_norm": 0.39100518822669983, "learning_rate": 4.203201652057512e-05, "loss": 4.3813, "step": 8559 }, { "epoch": 0.26145387904703726, "grad_norm": 0.37774139642715454, "learning_rate": 4.203026039764235e-05, "loss": 4.3152, "step": 8560 }, { "epoch": 0.261484422724496, "grad_norm": 0.3716515898704529, "learning_rate": 4.202850411790321e-05, "loss": 4.3398, "step": 8561 }, { "epoch": 0.2615149664019548, "grad_norm": 0.38895660638809204, "learning_rate": 4.2026747681373886e-05, "loss": 4.3764, "step": 8562 }, { "epoch": 0.26154551007941357, "grad_norm": 0.3916933834552765, "learning_rate": 4.2024991088070536e-05, "loss": 4.328, "step": 8563 }, { "epoch": 0.2615760537568723, "grad_norm": 0.3879670202732086, "learning_rate": 4.2023234338009345e-05, "loss": 4.3098, "step": 8564 }, { "epoch": 0.26160659743433107, "grad_norm": 0.37820562720298767, "learning_rate": 4.202147743120648e-05, "loss": 4.3521, "step": 8565 }, { "epoch": 0.2616371411117899, "grad_norm": 0.3792601227760315, "learning_rate": 4.201972036767811e-05, "loss": 4.2463, "step": 8566 }, { "epoch": 0.2616676847892486, "grad_norm": 0.3923583924770355, "learning_rate": 4.201796314744044e-05, "loss": 4.3129, "step": 8567 }, { "epoch": 0.26169822846670737, "grad_norm": 0.3707694411277771, "learning_rate": 4.201620577050962e-05, "loss": 4.2416, "step": 8568 }, { "epoch": 0.2617287721441662, "grad_norm": 0.362697035074234, "learning_rate": 4.201444823690185e-05, "loss": 4.3552, "step": 8569 }, { "epoch": 0.2617593158216249, "grad_norm": 0.3734370470046997, "learning_rate": 4.2012690546633307e-05, "loss": 4.3907, "step": 8570 }, { "epoch": 0.2617898594990837, "grad_norm": 0.38719579577445984, "learning_rate": 4.2010932699720184e-05, "loss": 4.3043, "step": 8571 }, { "epoch": 0.2618204031765425, "grad_norm": 0.3724766969680786, "learning_rate": 4.200917469617864e-05, "loss": 4.2614, "step": 8572 }, { "epoch": 0.26185094685400123, "grad_norm": 0.3836674690246582, "learning_rate": 4.200741653602489e-05, "loss": 4.3278, "step": 8573 }, { "epoch": 0.26188149053146, "grad_norm": 0.37377601861953735, "learning_rate": 4.2005658219275114e-05, "loss": 4.3522, "step": 8574 }, { "epoch": 0.26191203420891873, "grad_norm": 0.3600129783153534, "learning_rate": 4.20038997459455e-05, "loss": 4.4129, "step": 8575 }, { "epoch": 0.26194257788637754, "grad_norm": 0.39615771174430847, "learning_rate": 4.200214111605223e-05, "loss": 4.3309, "step": 8576 }, { "epoch": 0.2619731215638363, "grad_norm": 0.37391746044158936, "learning_rate": 4.200038232961151e-05, "loss": 4.4056, "step": 8577 }, { "epoch": 0.26200366524129504, "grad_norm": 0.37314480543136597, "learning_rate": 4.199862338663953e-05, "loss": 4.3938, "step": 8578 }, { "epoch": 0.26203420891875384, "grad_norm": 0.36764875054359436, "learning_rate": 4.199686428715248e-05, "loss": 4.3413, "step": 8579 }, { "epoch": 0.2620647525962126, "grad_norm": 0.38094043731689453, "learning_rate": 4.199510503116657e-05, "loss": 4.3166, "step": 8580 }, { "epoch": 0.26209529627367134, "grad_norm": 0.37694820761680603, "learning_rate": 4.199334561869799e-05, "loss": 4.3774, "step": 8581 }, { "epoch": 0.2621258399511301, "grad_norm": 0.3806740641593933, "learning_rate": 4.199158604976293e-05, "loss": 4.3103, "step": 8582 }, { "epoch": 0.2621563836285889, "grad_norm": 0.3824121057987213, "learning_rate": 4.19898263243776e-05, "loss": 4.2914, "step": 8583 }, { "epoch": 0.26218692730604765, "grad_norm": 0.37151622772216797, "learning_rate": 4.1988066442558214e-05, "loss": 4.3662, "step": 8584 }, { "epoch": 0.2622174709835064, "grad_norm": 0.3833732604980469, "learning_rate": 4.1986306404320963e-05, "loss": 4.304, "step": 8585 }, { "epoch": 0.2622480146609652, "grad_norm": 0.37608587741851807, "learning_rate": 4.1984546209682054e-05, "loss": 4.379, "step": 8586 }, { "epoch": 0.26227855833842395, "grad_norm": 0.37362128496170044, "learning_rate": 4.1982785858657695e-05, "loss": 4.4035, "step": 8587 }, { "epoch": 0.2623091020158827, "grad_norm": 0.3738861083984375, "learning_rate": 4.1981025351264094e-05, "loss": 4.314, "step": 8588 }, { "epoch": 0.2623396456933415, "grad_norm": 0.38411271572113037, "learning_rate": 4.197926468751746e-05, "loss": 4.3861, "step": 8589 }, { "epoch": 0.26237018937080026, "grad_norm": 0.37295767664909363, "learning_rate": 4.197750386743401e-05, "loss": 4.3995, "step": 8590 }, { "epoch": 0.262400733048259, "grad_norm": 0.38347873091697693, "learning_rate": 4.197574289102996e-05, "loss": 4.3208, "step": 8591 }, { "epoch": 0.26243127672571775, "grad_norm": 0.3762531876564026, "learning_rate": 4.19739817583215e-05, "loss": 4.3487, "step": 8592 }, { "epoch": 0.26246182040317656, "grad_norm": 0.36825013160705566, "learning_rate": 4.1972220469324875e-05, "loss": 4.4013, "step": 8593 }, { "epoch": 0.2624923640806353, "grad_norm": 0.38100552558898926, "learning_rate": 4.1970459024056287e-05, "loss": 4.3299, "step": 8594 }, { "epoch": 0.26252290775809406, "grad_norm": 0.37825140357017517, "learning_rate": 4.196869742253195e-05, "loss": 4.3757, "step": 8595 }, { "epoch": 0.26255345143555286, "grad_norm": 0.3880497217178345, "learning_rate": 4.19669356647681e-05, "loss": 4.3513, "step": 8596 }, { "epoch": 0.2625839951130116, "grad_norm": 0.36703383922576904, "learning_rate": 4.196517375078095e-05, "loss": 4.3983, "step": 8597 }, { "epoch": 0.26261453879047036, "grad_norm": 0.3741912543773651, "learning_rate": 4.196341168058673e-05, "loss": 4.3862, "step": 8598 }, { "epoch": 0.2626450824679291, "grad_norm": 0.3835613429546356, "learning_rate": 4.196164945420165e-05, "loss": 4.3634, "step": 8599 }, { "epoch": 0.2626756261453879, "grad_norm": 0.3988499641418457, "learning_rate": 4.1959887071641934e-05, "loss": 4.3104, "step": 8600 }, { "epoch": 0.26270616982284667, "grad_norm": 0.38530829548835754, "learning_rate": 4.195812453292382e-05, "loss": 4.2701, "step": 8601 }, { "epoch": 0.2627367135003054, "grad_norm": 0.37797096371650696, "learning_rate": 4.195636183806354e-05, "loss": 4.4444, "step": 8602 }, { "epoch": 0.2627672571777642, "grad_norm": 0.3810168206691742, "learning_rate": 4.1954598987077324e-05, "loss": 4.115, "step": 8603 }, { "epoch": 0.262797800855223, "grad_norm": 0.3867945969104767, "learning_rate": 4.195283597998139e-05, "loss": 4.3645, "step": 8604 }, { "epoch": 0.2628283445326817, "grad_norm": 0.37952300906181335, "learning_rate": 4.195107281679198e-05, "loss": 4.3459, "step": 8605 }, { "epoch": 0.2628588882101405, "grad_norm": 0.3824155032634735, "learning_rate": 4.1949309497525326e-05, "loss": 4.4486, "step": 8606 }, { "epoch": 0.2628894318875993, "grad_norm": 0.37106752395629883, "learning_rate": 4.194754602219767e-05, "loss": 4.2185, "step": 8607 }, { "epoch": 0.26291997556505803, "grad_norm": 0.38507819175720215, "learning_rate": 4.194578239082524e-05, "loss": 4.3856, "step": 8608 }, { "epoch": 0.2629505192425168, "grad_norm": 0.3736856281757355, "learning_rate": 4.194401860342427e-05, "loss": 4.3951, "step": 8609 }, { "epoch": 0.2629810629199756, "grad_norm": 0.37489792704582214, "learning_rate": 4.194225466001103e-05, "loss": 4.4091, "step": 8610 }, { "epoch": 0.26301160659743433, "grad_norm": 0.3737068474292755, "learning_rate": 4.194049056060172e-05, "loss": 4.3149, "step": 8611 }, { "epoch": 0.2630421502748931, "grad_norm": 0.3864813446998596, "learning_rate": 4.193872630521262e-05, "loss": 4.3264, "step": 8612 }, { "epoch": 0.2630726939523519, "grad_norm": 0.3765697181224823, "learning_rate": 4.193696189385995e-05, "loss": 4.3063, "step": 8613 }, { "epoch": 0.26310323762981064, "grad_norm": 0.3864601254463196, "learning_rate": 4.193519732655996e-05, "loss": 4.3755, "step": 8614 }, { "epoch": 0.2631337813072694, "grad_norm": 0.3883637487888336, "learning_rate": 4.1933432603328905e-05, "loss": 4.412, "step": 8615 }, { "epoch": 0.26316432498472814, "grad_norm": 0.36980241537094116, "learning_rate": 4.193166772418303e-05, "loss": 4.3996, "step": 8616 }, { "epoch": 0.26319486866218694, "grad_norm": 0.407528817653656, "learning_rate": 4.1929902689138584e-05, "loss": 4.3019, "step": 8617 }, { "epoch": 0.2632254123396457, "grad_norm": 0.37351176142692566, "learning_rate": 4.192813749821182e-05, "loss": 4.3949, "step": 8618 }, { "epoch": 0.26325595601710444, "grad_norm": 0.3752727508544922, "learning_rate": 4.1926372151418993e-05, "loss": 4.2814, "step": 8619 }, { "epoch": 0.26328649969456325, "grad_norm": 0.3830817937850952, "learning_rate": 4.1924606648776346e-05, "loss": 4.3026, "step": 8620 }, { "epoch": 0.263317043372022, "grad_norm": 0.3802070617675781, "learning_rate": 4.192284099030015e-05, "loss": 4.2244, "step": 8621 }, { "epoch": 0.26334758704948075, "grad_norm": 0.3777290880680084, "learning_rate": 4.192107517600666e-05, "loss": 4.3652, "step": 8622 }, { "epoch": 0.2633781307269395, "grad_norm": 0.3964546024799347, "learning_rate": 4.1919309205912125e-05, "loss": 4.3612, "step": 8623 }, { "epoch": 0.2634086744043983, "grad_norm": 0.39648309350013733, "learning_rate": 4.191754308003282e-05, "loss": 4.3303, "step": 8624 }, { "epoch": 0.26343921808185705, "grad_norm": 0.37220901250839233, "learning_rate": 4.191577679838499e-05, "loss": 4.4094, "step": 8625 }, { "epoch": 0.2634697617593158, "grad_norm": 0.38057082891464233, "learning_rate": 4.191401036098491e-05, "loss": 4.3077, "step": 8626 }, { "epoch": 0.2635003054367746, "grad_norm": 0.3763940632343292, "learning_rate": 4.191224376784883e-05, "loss": 4.3793, "step": 8627 }, { "epoch": 0.26353084911423336, "grad_norm": 0.3724691867828369, "learning_rate": 4.1910477018993035e-05, "loss": 4.3118, "step": 8628 }, { "epoch": 0.2635613927916921, "grad_norm": 0.3938385844230652, "learning_rate": 4.190871011443378e-05, "loss": 4.371, "step": 8629 }, { "epoch": 0.2635919364691509, "grad_norm": 0.3823850154876709, "learning_rate": 4.190694305418734e-05, "loss": 4.2588, "step": 8630 }, { "epoch": 0.26362248014660966, "grad_norm": 0.3892841339111328, "learning_rate": 4.190517583826998e-05, "loss": 4.3816, "step": 8631 }, { "epoch": 0.2636530238240684, "grad_norm": 0.38586053252220154, "learning_rate": 4.190340846669798e-05, "loss": 4.4088, "step": 8632 }, { "epoch": 0.26368356750152716, "grad_norm": 0.381996750831604, "learning_rate": 4.1901640939487605e-05, "loss": 4.2865, "step": 8633 }, { "epoch": 0.26371411117898597, "grad_norm": 0.37792250514030457, "learning_rate": 4.189987325665513e-05, "loss": 4.3336, "step": 8634 }, { "epoch": 0.2637446548564447, "grad_norm": 0.3952014744281769, "learning_rate": 4.189810541821683e-05, "loss": 4.4035, "step": 8635 }, { "epoch": 0.26377519853390347, "grad_norm": 0.4650968909263611, "learning_rate": 4.189633742418899e-05, "loss": 4.3177, "step": 8636 }, { "epoch": 0.26380574221136227, "grad_norm": 0.37712955474853516, "learning_rate": 4.189456927458788e-05, "loss": 4.3276, "step": 8637 }, { "epoch": 0.263836285888821, "grad_norm": 0.37089547514915466, "learning_rate": 4.189280096942979e-05, "loss": 4.3984, "step": 8638 }, { "epoch": 0.26386682956627977, "grad_norm": 0.39086586236953735, "learning_rate": 4.1891032508730994e-05, "loss": 4.3438, "step": 8639 }, { "epoch": 0.2638973732437385, "grad_norm": 0.37030309438705444, "learning_rate": 4.188926389250778e-05, "loss": 4.3978, "step": 8640 }, { "epoch": 0.2639279169211973, "grad_norm": 0.3701561689376831, "learning_rate": 4.1887495120776424e-05, "loss": 4.4162, "step": 8641 }, { "epoch": 0.2639584605986561, "grad_norm": 0.37242433428764343, "learning_rate": 4.188572619355322e-05, "loss": 4.3729, "step": 8642 }, { "epoch": 0.2639890042761148, "grad_norm": 0.38384294509887695, "learning_rate": 4.188395711085446e-05, "loss": 4.3813, "step": 8643 }, { "epoch": 0.26401954795357363, "grad_norm": 0.3664158582687378, "learning_rate": 4.188218787269641e-05, "loss": 4.3028, "step": 8644 }, { "epoch": 0.2640500916310324, "grad_norm": 0.37113243341445923, "learning_rate": 4.188041847909538e-05, "loss": 4.4129, "step": 8645 }, { "epoch": 0.26408063530849113, "grad_norm": 0.39623379707336426, "learning_rate": 4.187864893006766e-05, "loss": 4.4159, "step": 8646 }, { "epoch": 0.26411117898594993, "grad_norm": 0.38611817359924316, "learning_rate": 4.187687922562955e-05, "loss": 4.3576, "step": 8647 }, { "epoch": 0.2641417226634087, "grad_norm": 0.3946218192577362, "learning_rate": 4.187510936579733e-05, "loss": 4.3856, "step": 8648 }, { "epoch": 0.26417226634086743, "grad_norm": 0.37851959466934204, "learning_rate": 4.187333935058731e-05, "loss": 4.4137, "step": 8649 }, { "epoch": 0.2642028100183262, "grad_norm": 0.4012744426727295, "learning_rate": 4.187156918001577e-05, "loss": 4.3805, "step": 8650 }, { "epoch": 0.264233353695785, "grad_norm": 0.37557995319366455, "learning_rate": 4.1869798854099016e-05, "loss": 4.3997, "step": 8651 }, { "epoch": 0.26426389737324374, "grad_norm": 0.37119060754776, "learning_rate": 4.186802837285335e-05, "loss": 4.3541, "step": 8652 }, { "epoch": 0.2642944410507025, "grad_norm": 0.40191206336021423, "learning_rate": 4.186625773629508e-05, "loss": 4.3881, "step": 8653 }, { "epoch": 0.2643249847281613, "grad_norm": 0.38506168127059937, "learning_rate": 4.18644869444405e-05, "loss": 4.3414, "step": 8654 }, { "epoch": 0.26435552840562004, "grad_norm": 0.38191837072372437, "learning_rate": 4.186271599730592e-05, "loss": 4.3184, "step": 8655 }, { "epoch": 0.2643860720830788, "grad_norm": 0.3708588182926178, "learning_rate": 4.186094489490764e-05, "loss": 4.4513, "step": 8656 }, { "epoch": 0.26441661576053754, "grad_norm": 0.37862372398376465, "learning_rate": 4.185917363726198e-05, "loss": 4.3461, "step": 8657 }, { "epoch": 0.26444715943799635, "grad_norm": 0.39868080615997314, "learning_rate": 4.185740222438523e-05, "loss": 4.3936, "step": 8658 }, { "epoch": 0.2644777031154551, "grad_norm": 0.37309372425079346, "learning_rate": 4.185563065629371e-05, "loss": 4.3819, "step": 8659 }, { "epoch": 0.26450824679291385, "grad_norm": 0.3796900808811188, "learning_rate": 4.185385893300374e-05, "loss": 4.4145, "step": 8660 }, { "epoch": 0.26453879047037265, "grad_norm": 0.3858306109905243, "learning_rate": 4.185208705453162e-05, "loss": 4.3394, "step": 8661 }, { "epoch": 0.2645693341478314, "grad_norm": 0.3845285475254059, "learning_rate": 4.1850315020893676e-05, "loss": 4.3793, "step": 8662 }, { "epoch": 0.26459987782529015, "grad_norm": 0.39973700046539307, "learning_rate": 4.184854283210622e-05, "loss": 4.3442, "step": 8663 }, { "epoch": 0.26463042150274896, "grad_norm": 0.38190731406211853, "learning_rate": 4.1846770488185554e-05, "loss": 4.3376, "step": 8664 }, { "epoch": 0.2646609651802077, "grad_norm": 0.37056922912597656, "learning_rate": 4.1844997989148015e-05, "loss": 4.2611, "step": 8665 }, { "epoch": 0.26469150885766646, "grad_norm": 0.37842291593551636, "learning_rate": 4.184322533500993e-05, "loss": 4.4089, "step": 8666 }, { "epoch": 0.2647220525351252, "grad_norm": 0.38948437571525574, "learning_rate": 4.18414525257876e-05, "loss": 4.3693, "step": 8667 }, { "epoch": 0.264752596212584, "grad_norm": 0.378600150346756, "learning_rate": 4.1839679561497356e-05, "loss": 4.3681, "step": 8668 }, { "epoch": 0.26478313989004276, "grad_norm": 0.3817940354347229, "learning_rate": 4.1837906442155526e-05, "loss": 4.3318, "step": 8669 }, { "epoch": 0.2648136835675015, "grad_norm": 0.37727728486061096, "learning_rate": 4.183613316777844e-05, "loss": 4.4411, "step": 8670 }, { "epoch": 0.2648442272449603, "grad_norm": 0.3915143311023712, "learning_rate": 4.183435973838241e-05, "loss": 4.2578, "step": 8671 }, { "epoch": 0.26487477092241907, "grad_norm": 0.41782763600349426, "learning_rate": 4.1832586153983785e-05, "loss": 4.4454, "step": 8672 }, { "epoch": 0.2649053145998778, "grad_norm": 0.38659167289733887, "learning_rate": 4.1830812414598876e-05, "loss": 4.387, "step": 8673 }, { "epoch": 0.26493585827733657, "grad_norm": 0.3824698030948639, "learning_rate": 4.1829038520244024e-05, "loss": 4.3618, "step": 8674 }, { "epoch": 0.26496640195479537, "grad_norm": 0.3758711516857147, "learning_rate": 4.182726447093557e-05, "loss": 4.3685, "step": 8675 }, { "epoch": 0.2649969456322541, "grad_norm": 0.38021764159202576, "learning_rate": 4.182549026668983e-05, "loss": 4.3765, "step": 8676 }, { "epoch": 0.26502748930971287, "grad_norm": 0.4064481854438782, "learning_rate": 4.182371590752316e-05, "loss": 4.4099, "step": 8677 }, { "epoch": 0.2650580329871717, "grad_norm": 0.3622288703918457, "learning_rate": 4.182194139345188e-05, "loss": 4.3495, "step": 8678 }, { "epoch": 0.2650885766646304, "grad_norm": 0.38627517223358154, "learning_rate": 4.1820166724492335e-05, "loss": 4.3898, "step": 8679 }, { "epoch": 0.2651191203420892, "grad_norm": 0.3802172839641571, "learning_rate": 4.1818391900660875e-05, "loss": 4.3855, "step": 8680 }, { "epoch": 0.2651496640195479, "grad_norm": 0.37146371603012085, "learning_rate": 4.181661692197383e-05, "loss": 4.3532, "step": 8681 }, { "epoch": 0.26518020769700673, "grad_norm": 0.37436962127685547, "learning_rate": 4.1814841788447545e-05, "loss": 4.3552, "step": 8682 }, { "epoch": 0.2652107513744655, "grad_norm": 0.3915540874004364, "learning_rate": 4.181306650009837e-05, "loss": 4.433, "step": 8683 }, { "epoch": 0.26524129505192423, "grad_norm": 0.404000461101532, "learning_rate": 4.181129105694265e-05, "loss": 4.3935, "step": 8684 }, { "epoch": 0.26527183872938304, "grad_norm": 0.3832020163536072, "learning_rate": 4.180951545899672e-05, "loss": 4.4064, "step": 8685 }, { "epoch": 0.2653023824068418, "grad_norm": 0.40226393938064575, "learning_rate": 4.180773970627694e-05, "loss": 4.2894, "step": 8686 }, { "epoch": 0.26533292608430054, "grad_norm": 0.39119088649749756, "learning_rate": 4.1805963798799664e-05, "loss": 4.362, "step": 8687 }, { "epoch": 0.26536346976175934, "grad_norm": 0.3779550790786743, "learning_rate": 4.180418773658123e-05, "loss": 4.3435, "step": 8688 }, { "epoch": 0.2653940134392181, "grad_norm": 0.37849563360214233, "learning_rate": 4.180241151963801e-05, "loss": 4.2881, "step": 8689 }, { "epoch": 0.26542455711667684, "grad_norm": 0.3726576864719391, "learning_rate": 4.180063514798635e-05, "loss": 4.3643, "step": 8690 }, { "epoch": 0.2654551007941356, "grad_norm": 0.37739402055740356, "learning_rate": 4.17988586216426e-05, "loss": 4.3175, "step": 8691 }, { "epoch": 0.2654856444715944, "grad_norm": 0.3738376200199127, "learning_rate": 4.1797081940623117e-05, "loss": 4.3363, "step": 8692 }, { "epoch": 0.26551618814905315, "grad_norm": 0.37015852332115173, "learning_rate": 4.179530510494427e-05, "loss": 4.3199, "step": 8693 }, { "epoch": 0.2655467318265119, "grad_norm": 0.38030195236206055, "learning_rate": 4.179352811462241e-05, "loss": 4.4087, "step": 8694 }, { "epoch": 0.2655772755039707, "grad_norm": 0.3754418194293976, "learning_rate": 4.1791750969673904e-05, "loss": 4.3928, "step": 8695 }, { "epoch": 0.26560781918142945, "grad_norm": 0.380696564912796, "learning_rate": 4.178997367011511e-05, "loss": 4.3287, "step": 8696 }, { "epoch": 0.2656383628588882, "grad_norm": 0.39109697937965393, "learning_rate": 4.1788196215962403e-05, "loss": 4.1864, "step": 8697 }, { "epoch": 0.26566890653634695, "grad_norm": 0.38635578751564026, "learning_rate": 4.178641860723214e-05, "loss": 4.3255, "step": 8698 }, { "epoch": 0.26569945021380575, "grad_norm": 0.3790591061115265, "learning_rate": 4.178464084394068e-05, "loss": 4.3348, "step": 8699 }, { "epoch": 0.2657299938912645, "grad_norm": 0.379559189081192, "learning_rate": 4.1782862926104414e-05, "loss": 4.3189, "step": 8700 }, { "epoch": 0.26576053756872325, "grad_norm": 0.3920324742794037, "learning_rate": 4.1781084853739695e-05, "loss": 4.3629, "step": 8701 }, { "epoch": 0.26579108124618206, "grad_norm": 0.36601895093917847, "learning_rate": 4.17793066268629e-05, "loss": 4.4059, "step": 8702 }, { "epoch": 0.2658216249236408, "grad_norm": 0.3733638823032379, "learning_rate": 4.17775282454904e-05, "loss": 4.3601, "step": 8703 }, { "epoch": 0.26585216860109956, "grad_norm": 0.37642958760261536, "learning_rate": 4.177574970963858e-05, "loss": 4.3676, "step": 8704 }, { "epoch": 0.26588271227855836, "grad_norm": 0.3608722686767578, "learning_rate": 4.17739710193238e-05, "loss": 4.2745, "step": 8705 }, { "epoch": 0.2659132559560171, "grad_norm": 0.376697301864624, "learning_rate": 4.177219217456244e-05, "loss": 4.3718, "step": 8706 }, { "epoch": 0.26594379963347586, "grad_norm": 0.38869407773017883, "learning_rate": 4.177041317537089e-05, "loss": 4.3055, "step": 8707 }, { "epoch": 0.2659743433109346, "grad_norm": 0.36979302763938904, "learning_rate": 4.1768634021765526e-05, "loss": 4.3842, "step": 8708 }, { "epoch": 0.2660048869883934, "grad_norm": 0.3696725070476532, "learning_rate": 4.1766854713762724e-05, "loss": 4.413, "step": 8709 }, { "epoch": 0.26603543066585217, "grad_norm": 0.40272068977355957, "learning_rate": 4.176507525137887e-05, "loss": 4.3848, "step": 8710 }, { "epoch": 0.2660659743433109, "grad_norm": 0.3857851028442383, "learning_rate": 4.176329563463034e-05, "loss": 4.3226, "step": 8711 }, { "epoch": 0.2660965180207697, "grad_norm": 0.3907656669616699, "learning_rate": 4.176151586353354e-05, "loss": 4.3729, "step": 8712 }, { "epoch": 0.2661270616982285, "grad_norm": 0.3842995762825012, "learning_rate": 4.175973593810484e-05, "loss": 4.2974, "step": 8713 }, { "epoch": 0.2661576053756872, "grad_norm": 0.37824249267578125, "learning_rate": 4.175795585836064e-05, "loss": 4.4263, "step": 8714 }, { "epoch": 0.266188149053146, "grad_norm": 0.38633984327316284, "learning_rate": 4.175617562431732e-05, "loss": 4.2342, "step": 8715 }, { "epoch": 0.2662186927306048, "grad_norm": 0.3800511956214905, "learning_rate": 4.1754395235991274e-05, "loss": 4.4304, "step": 8716 }, { "epoch": 0.2662492364080635, "grad_norm": 0.3895553946495056, "learning_rate": 4.175261469339889e-05, "loss": 4.2901, "step": 8717 }, { "epoch": 0.2662797800855223, "grad_norm": 0.38124674558639526, "learning_rate": 4.175083399655659e-05, "loss": 4.3318, "step": 8718 }, { "epoch": 0.2663103237629811, "grad_norm": 0.3746105134487152, "learning_rate": 4.174905314548073e-05, "loss": 4.3414, "step": 8719 }, { "epoch": 0.26634086744043983, "grad_norm": 0.4058884084224701, "learning_rate": 4.174727214018773e-05, "loss": 4.271, "step": 8720 }, { "epoch": 0.2663714111178986, "grad_norm": 0.3895011842250824, "learning_rate": 4.174549098069399e-05, "loss": 4.3689, "step": 8721 }, { "epoch": 0.2664019547953574, "grad_norm": 0.3957642912864685, "learning_rate": 4.1743709667015904e-05, "loss": 4.3353, "step": 8722 }, { "epoch": 0.26643249847281614, "grad_norm": 0.38082796335220337, "learning_rate": 4.1741928199169875e-05, "loss": 4.3561, "step": 8723 }, { "epoch": 0.2664630421502749, "grad_norm": 0.3769889771938324, "learning_rate": 4.17401465771723e-05, "loss": 4.3199, "step": 8724 }, { "epoch": 0.26649358582773364, "grad_norm": 0.3732025921344757, "learning_rate": 4.1738364801039595e-05, "loss": 4.3935, "step": 8725 }, { "epoch": 0.26652412950519244, "grad_norm": 0.39403316378593445, "learning_rate": 4.1736582870788156e-05, "loss": 4.3567, "step": 8726 }, { "epoch": 0.2665546731826512, "grad_norm": 0.3706537187099457, "learning_rate": 4.173480078643439e-05, "loss": 4.4289, "step": 8727 }, { "epoch": 0.26658521686010994, "grad_norm": 0.3751775324344635, "learning_rate": 4.173301854799472e-05, "loss": 4.3672, "step": 8728 }, { "epoch": 0.26661576053756875, "grad_norm": 0.38455960154533386, "learning_rate": 4.173123615548553e-05, "loss": 4.3867, "step": 8729 }, { "epoch": 0.2666463042150275, "grad_norm": 0.378290593624115, "learning_rate": 4.172945360892325e-05, "loss": 4.2845, "step": 8730 }, { "epoch": 0.26667684789248625, "grad_norm": 0.38491329550743103, "learning_rate": 4.17276709083243e-05, "loss": 4.3463, "step": 8731 }, { "epoch": 0.266707391569945, "grad_norm": 0.3895285427570343, "learning_rate": 4.1725888053705074e-05, "loss": 4.3513, "step": 8732 }, { "epoch": 0.2667379352474038, "grad_norm": 0.3847741186618805, "learning_rate": 4.1724105045082e-05, "loss": 4.2841, "step": 8733 }, { "epoch": 0.26676847892486255, "grad_norm": 0.3840460479259491, "learning_rate": 4.1722321882471494e-05, "loss": 4.2625, "step": 8734 }, { "epoch": 0.2667990226023213, "grad_norm": 0.3791728615760803, "learning_rate": 4.1720538565889965e-05, "loss": 4.3333, "step": 8735 }, { "epoch": 0.2668295662797801, "grad_norm": 0.3878225088119507, "learning_rate": 4.171875509535385e-05, "loss": 4.3305, "step": 8736 }, { "epoch": 0.26686010995723886, "grad_norm": 0.39096105098724365, "learning_rate": 4.171697147087955e-05, "loss": 4.3622, "step": 8737 }, { "epoch": 0.2668906536346976, "grad_norm": 0.3850492835044861, "learning_rate": 4.1715187692483507e-05, "loss": 4.3081, "step": 8738 }, { "epoch": 0.2669211973121564, "grad_norm": 0.37255021929740906, "learning_rate": 4.1713403760182134e-05, "loss": 4.3204, "step": 8739 }, { "epoch": 0.26695174098961516, "grad_norm": 0.3750649690628052, "learning_rate": 4.171161967399186e-05, "loss": 4.3513, "step": 8740 }, { "epoch": 0.2669822846670739, "grad_norm": 0.36278367042541504, "learning_rate": 4.170983543392912e-05, "loss": 4.3483, "step": 8741 }, { "epoch": 0.26701282834453266, "grad_norm": 0.3774007260799408, "learning_rate": 4.170805104001032e-05, "loss": 4.3696, "step": 8742 }, { "epoch": 0.26704337202199147, "grad_norm": 0.3670843243598938, "learning_rate": 4.170626649225191e-05, "loss": 4.2067, "step": 8743 }, { "epoch": 0.2670739156994502, "grad_norm": 0.37290751934051514, "learning_rate": 4.170448179067031e-05, "loss": 4.4096, "step": 8744 }, { "epoch": 0.26710445937690896, "grad_norm": 0.3696901500225067, "learning_rate": 4.170269693528197e-05, "loss": 4.3707, "step": 8745 }, { "epoch": 0.26713500305436777, "grad_norm": 0.37355005741119385, "learning_rate": 4.1700911926103306e-05, "loss": 4.2317, "step": 8746 }, { "epoch": 0.2671655467318265, "grad_norm": 0.3861129581928253, "learning_rate": 4.169912676315075e-05, "loss": 4.3682, "step": 8747 }, { "epoch": 0.26719609040928527, "grad_norm": 0.37411558628082275, "learning_rate": 4.169734144644076e-05, "loss": 4.3904, "step": 8748 }, { "epoch": 0.267226634086744, "grad_norm": 0.38506218791007996, "learning_rate": 4.1695555975989754e-05, "loss": 4.3285, "step": 8749 }, { "epoch": 0.2672571777642028, "grad_norm": 0.3756333291530609, "learning_rate": 4.169377035181418e-05, "loss": 4.2901, "step": 8750 }, { "epoch": 0.2672877214416616, "grad_norm": 0.37437698245048523, "learning_rate": 4.169198457393049e-05, "loss": 4.3147, "step": 8751 }, { "epoch": 0.2673182651191203, "grad_norm": 0.36292240023612976, "learning_rate": 4.1690198642355103e-05, "loss": 4.3742, "step": 8752 }, { "epoch": 0.26734880879657913, "grad_norm": 0.38777783513069153, "learning_rate": 4.1688412557104484e-05, "loss": 4.33, "step": 8753 }, { "epoch": 0.2673793524740379, "grad_norm": 0.3669907748699188, "learning_rate": 4.168662631819507e-05, "loss": 4.3791, "step": 8754 }, { "epoch": 0.26740989615149663, "grad_norm": 0.38877564668655396, "learning_rate": 4.16848399256433e-05, "loss": 4.3196, "step": 8755 }, { "epoch": 0.2674404398289554, "grad_norm": 0.37210512161254883, "learning_rate": 4.168305337946564e-05, "loss": 4.4101, "step": 8756 }, { "epoch": 0.2674709835064142, "grad_norm": 0.3712170124053955, "learning_rate": 4.168126667967852e-05, "loss": 4.325, "step": 8757 }, { "epoch": 0.26750152718387293, "grad_norm": 0.3769455850124359, "learning_rate": 4.167947982629841e-05, "loss": 4.2961, "step": 8758 }, { "epoch": 0.2675320708613317, "grad_norm": 0.3744564354419708, "learning_rate": 4.1677692819341753e-05, "loss": 4.3307, "step": 8759 }, { "epoch": 0.2675626145387905, "grad_norm": 0.38581278920173645, "learning_rate": 4.1675905658825e-05, "loss": 4.3312, "step": 8760 }, { "epoch": 0.26759315821624924, "grad_norm": 0.37052038311958313, "learning_rate": 4.1674118344764606e-05, "loss": 4.3224, "step": 8761 }, { "epoch": 0.267623701893708, "grad_norm": 0.3769625723361969, "learning_rate": 4.167233087717703e-05, "loss": 4.3591, "step": 8762 }, { "epoch": 0.2676542455711668, "grad_norm": 0.36970993876457214, "learning_rate": 4.167054325607874e-05, "loss": 4.4523, "step": 8763 }, { "epoch": 0.26768478924862554, "grad_norm": 0.38156476616859436, "learning_rate": 4.166875548148619e-05, "loss": 4.3717, "step": 8764 }, { "epoch": 0.2677153329260843, "grad_norm": 0.38241851329803467, "learning_rate": 4.166696755341583e-05, "loss": 4.2873, "step": 8765 }, { "epoch": 0.26774587660354304, "grad_norm": 0.3805479407310486, "learning_rate": 4.166517947188413e-05, "loss": 4.3266, "step": 8766 }, { "epoch": 0.26777642028100185, "grad_norm": 0.4092687964439392, "learning_rate": 4.166339123690755e-05, "loss": 4.2843, "step": 8767 }, { "epoch": 0.2678069639584606, "grad_norm": 0.38952645659446716, "learning_rate": 4.1661602848502576e-05, "loss": 4.3675, "step": 8768 }, { "epoch": 0.26783750763591935, "grad_norm": 0.37069442868232727, "learning_rate": 4.1659814306685655e-05, "loss": 4.3531, "step": 8769 }, { "epoch": 0.26786805131337815, "grad_norm": 0.37125444412231445, "learning_rate": 4.165802561147324e-05, "loss": 4.3774, "step": 8770 }, { "epoch": 0.2678985949908369, "grad_norm": 0.3659966289997101, "learning_rate": 4.165623676288184e-05, "loss": 4.2298, "step": 8771 }, { "epoch": 0.26792913866829565, "grad_norm": 0.3802545964717865, "learning_rate": 4.1654447760927895e-05, "loss": 4.376, "step": 8772 }, { "epoch": 0.2679596823457544, "grad_norm": 0.38306936621665955, "learning_rate": 4.165265860562788e-05, "loss": 4.4302, "step": 8773 }, { "epoch": 0.2679902260232132, "grad_norm": 0.3811262845993042, "learning_rate": 4.1650869296998286e-05, "loss": 4.2775, "step": 8774 }, { "epoch": 0.26802076970067196, "grad_norm": 0.38116857409477234, "learning_rate": 4.164907983505557e-05, "loss": 4.3377, "step": 8775 }, { "epoch": 0.2680513133781307, "grad_norm": 0.3833892047405243, "learning_rate": 4.164729021981622e-05, "loss": 4.3294, "step": 8776 }, { "epoch": 0.2680818570555895, "grad_norm": 0.38005468249320984, "learning_rate": 4.16455004512967e-05, "loss": 4.3638, "step": 8777 }, { "epoch": 0.26811240073304826, "grad_norm": 0.36712509393692017, "learning_rate": 4.1643710529513516e-05, "loss": 4.3348, "step": 8778 }, { "epoch": 0.268142944410507, "grad_norm": 0.37877634167671204, "learning_rate": 4.164192045448312e-05, "loss": 4.4205, "step": 8779 }, { "epoch": 0.2681734880879658, "grad_norm": 0.3797244727611542, "learning_rate": 4.1640130226222005e-05, "loss": 4.423, "step": 8780 }, { "epoch": 0.26820403176542457, "grad_norm": 0.3789200484752655, "learning_rate": 4.163833984474667e-05, "loss": 4.2856, "step": 8781 }, { "epoch": 0.2682345754428833, "grad_norm": 0.3788582384586334, "learning_rate": 4.163654931007357e-05, "loss": 4.3484, "step": 8782 }, { "epoch": 0.26826511912034207, "grad_norm": 0.38450366258621216, "learning_rate": 4.163475862221922e-05, "loss": 4.3992, "step": 8783 }, { "epoch": 0.26829566279780087, "grad_norm": 0.37576451897621155, "learning_rate": 4.163296778120008e-05, "loss": 4.4409, "step": 8784 }, { "epoch": 0.2683262064752596, "grad_norm": 0.38483014702796936, "learning_rate": 4.163117678703265e-05, "loss": 4.1631, "step": 8785 }, { "epoch": 0.26835675015271837, "grad_norm": 0.3919932544231415, "learning_rate": 4.162938563973344e-05, "loss": 4.3405, "step": 8786 }, { "epoch": 0.2683872938301772, "grad_norm": 0.3776364326477051, "learning_rate": 4.162759433931892e-05, "loss": 4.3242, "step": 8787 }, { "epoch": 0.2684178375076359, "grad_norm": 0.3835386335849762, "learning_rate": 4.16258028858056e-05, "loss": 4.3715, "step": 8788 }, { "epoch": 0.2684483811850947, "grad_norm": 0.386176735162735, "learning_rate": 4.1624011279209954e-05, "loss": 4.2154, "step": 8789 }, { "epoch": 0.2684789248625534, "grad_norm": 0.3843417763710022, "learning_rate": 4.162221951954849e-05, "loss": 4.328, "step": 8790 }, { "epoch": 0.26850946854001223, "grad_norm": 0.37952834367752075, "learning_rate": 4.1620427606837706e-05, "loss": 4.3797, "step": 8791 }, { "epoch": 0.268540012217471, "grad_norm": 0.3936159014701843, "learning_rate": 4.16186355410941e-05, "loss": 4.4802, "step": 8792 }, { "epoch": 0.26857055589492973, "grad_norm": 0.38255494832992554, "learning_rate": 4.161684332233416e-05, "loss": 4.3409, "step": 8793 }, { "epoch": 0.26860109957238854, "grad_norm": 0.37458112835884094, "learning_rate": 4.161505095057442e-05, "loss": 4.3463, "step": 8794 }, { "epoch": 0.2686316432498473, "grad_norm": 0.372761994600296, "learning_rate": 4.1613258425831356e-05, "loss": 4.288, "step": 8795 }, { "epoch": 0.26866218692730603, "grad_norm": 0.38740429282188416, "learning_rate": 4.161146574812148e-05, "loss": 4.2544, "step": 8796 }, { "epoch": 0.26869273060476484, "grad_norm": 0.3738347887992859, "learning_rate": 4.160967291746129e-05, "loss": 4.3071, "step": 8797 }, { "epoch": 0.2687232742822236, "grad_norm": 0.3692891001701355, "learning_rate": 4.160787993386731e-05, "loss": 4.2935, "step": 8798 }, { "epoch": 0.26875381795968234, "grad_norm": 0.38314443826675415, "learning_rate": 4.160608679735603e-05, "loss": 4.3793, "step": 8799 }, { "epoch": 0.2687843616371411, "grad_norm": 0.3647797703742981, "learning_rate": 4.1604293507943986e-05, "loss": 4.2627, "step": 8800 }, { "epoch": 0.2688149053145999, "grad_norm": 0.3864874243736267, "learning_rate": 4.160250006564766e-05, "loss": 4.3461, "step": 8801 }, { "epoch": 0.26884544899205864, "grad_norm": 0.39887726306915283, "learning_rate": 4.1600706470483596e-05, "loss": 4.344, "step": 8802 }, { "epoch": 0.2688759926695174, "grad_norm": 0.3749789595603943, "learning_rate": 4.159891272246829e-05, "loss": 4.3629, "step": 8803 }, { "epoch": 0.2689065363469762, "grad_norm": 0.3792596757411957, "learning_rate": 4.159711882161824e-05, "loss": 4.3762, "step": 8804 }, { "epoch": 0.26893708002443495, "grad_norm": 0.3745446503162384, "learning_rate": 4.1595324767950004e-05, "loss": 4.3986, "step": 8805 }, { "epoch": 0.2689676237018937, "grad_norm": 0.4059751629829407, "learning_rate": 4.159353056148008e-05, "loss": 4.3, "step": 8806 }, { "epoch": 0.26899816737935245, "grad_norm": 0.3692556917667389, "learning_rate": 4.159173620222498e-05, "loss": 4.3869, "step": 8807 }, { "epoch": 0.26902871105681125, "grad_norm": 0.3838859498500824, "learning_rate": 4.158994169020123e-05, "loss": 4.2927, "step": 8808 }, { "epoch": 0.26905925473427, "grad_norm": 0.3750994801521301, "learning_rate": 4.158814702542537e-05, "loss": 4.3664, "step": 8809 }, { "epoch": 0.26908979841172875, "grad_norm": 0.3728691041469574, "learning_rate": 4.15863522079139e-05, "loss": 4.349, "step": 8810 }, { "epoch": 0.26912034208918756, "grad_norm": 0.38993340730667114, "learning_rate": 4.1584557237683365e-05, "loss": 4.3743, "step": 8811 }, { "epoch": 0.2691508857666463, "grad_norm": 0.37453824281692505, "learning_rate": 4.1582762114750285e-05, "loss": 4.3621, "step": 8812 }, { "epoch": 0.26918142944410506, "grad_norm": 0.37513598799705505, "learning_rate": 4.158096683913119e-05, "loss": 4.376, "step": 8813 }, { "epoch": 0.26921197312156386, "grad_norm": 0.380134642124176, "learning_rate": 4.15791714108426e-05, "loss": 4.3612, "step": 8814 }, { "epoch": 0.2692425167990226, "grad_norm": 0.3848583996295929, "learning_rate": 4.157737582990105e-05, "loss": 4.3138, "step": 8815 }, { "epoch": 0.26927306047648136, "grad_norm": 0.37563106417655945, "learning_rate": 4.15755800963231e-05, "loss": 4.3902, "step": 8816 }, { "epoch": 0.2693036041539401, "grad_norm": 0.37212228775024414, "learning_rate": 4.1573784210125247e-05, "loss": 4.4178, "step": 8817 }, { "epoch": 0.2693341478313989, "grad_norm": 0.37733566761016846, "learning_rate": 4.1571988171324036e-05, "loss": 4.3509, "step": 8818 }, { "epoch": 0.26936469150885767, "grad_norm": 0.3768376410007477, "learning_rate": 4.157019197993602e-05, "loss": 4.2754, "step": 8819 }, { "epoch": 0.2693952351863164, "grad_norm": 0.36984169483184814, "learning_rate": 4.156839563597772e-05, "loss": 4.3712, "step": 8820 }, { "epoch": 0.2694257788637752, "grad_norm": 0.373629629611969, "learning_rate": 4.156659913946568e-05, "loss": 4.343, "step": 8821 }, { "epoch": 0.269456322541234, "grad_norm": 0.3727216422557831, "learning_rate": 4.1564802490416455e-05, "loss": 4.299, "step": 8822 }, { "epoch": 0.2694868662186927, "grad_norm": 0.39973580837249756, "learning_rate": 4.1563005688846565e-05, "loss": 4.3188, "step": 8823 }, { "epoch": 0.26951740989615147, "grad_norm": 0.37680917978286743, "learning_rate": 4.156120873477258e-05, "loss": 4.3596, "step": 8824 }, { "epoch": 0.2695479535736103, "grad_norm": 0.3808879852294922, "learning_rate": 4.155941162821102e-05, "loss": 4.373, "step": 8825 }, { "epoch": 0.269578497251069, "grad_norm": 0.36485588550567627, "learning_rate": 4.1557614369178444e-05, "loss": 4.2809, "step": 8826 }, { "epoch": 0.2696090409285278, "grad_norm": 0.36996787786483765, "learning_rate": 4.155581695769141e-05, "loss": 4.2884, "step": 8827 }, { "epoch": 0.2696395846059866, "grad_norm": 0.37595412135124207, "learning_rate": 4.155401939376644e-05, "loss": 4.4206, "step": 8828 }, { "epoch": 0.26967012828344533, "grad_norm": 0.3793613910675049, "learning_rate": 4.155222167742011e-05, "loss": 4.3517, "step": 8829 }, { "epoch": 0.2697006719609041, "grad_norm": 0.37431564927101135, "learning_rate": 4.155042380866897e-05, "loss": 4.3581, "step": 8830 }, { "epoch": 0.26973121563836283, "grad_norm": 0.383543998003006, "learning_rate": 4.1548625787529566e-05, "loss": 4.4227, "step": 8831 }, { "epoch": 0.26976175931582164, "grad_norm": 0.3828253746032715, "learning_rate": 4.1546827614018446e-05, "loss": 4.3988, "step": 8832 }, { "epoch": 0.2697923029932804, "grad_norm": 0.38694000244140625, "learning_rate": 4.1545029288152195e-05, "loss": 4.3542, "step": 8833 }, { "epoch": 0.26982284667073914, "grad_norm": 0.377789169549942, "learning_rate": 4.1543230809947345e-05, "loss": 4.3956, "step": 8834 }, { "epoch": 0.26985339034819794, "grad_norm": 0.3796637952327728, "learning_rate": 4.154143217942045e-05, "loss": 4.3767, "step": 8835 }, { "epoch": 0.2698839340256567, "grad_norm": 0.38230636715888977, "learning_rate": 4.15396333965881e-05, "loss": 4.3511, "step": 8836 }, { "epoch": 0.26991447770311544, "grad_norm": 0.38375529646873474, "learning_rate": 4.153783446146684e-05, "loss": 4.3778, "step": 8837 }, { "epoch": 0.26994502138057425, "grad_norm": 0.38115763664245605, "learning_rate": 4.153603537407322e-05, "loss": 4.3197, "step": 8838 }, { "epoch": 0.269975565058033, "grad_norm": 0.3809185028076172, "learning_rate": 4.1534236134423835e-05, "loss": 4.3552, "step": 8839 }, { "epoch": 0.27000610873549175, "grad_norm": 0.37163543701171875, "learning_rate": 4.153243674253524e-05, "loss": 4.4019, "step": 8840 }, { "epoch": 0.2700366524129505, "grad_norm": 0.3750469982624054, "learning_rate": 4.153063719842399e-05, "loss": 4.4114, "step": 8841 }, { "epoch": 0.2700671960904093, "grad_norm": 0.40069082379341125, "learning_rate": 4.1528837502106666e-05, "loss": 4.2875, "step": 8842 }, { "epoch": 0.27009773976786805, "grad_norm": 0.38798585534095764, "learning_rate": 4.152703765359984e-05, "loss": 4.3145, "step": 8843 }, { "epoch": 0.2701282834453268, "grad_norm": 0.3871361017227173, "learning_rate": 4.152523765292008e-05, "loss": 4.3855, "step": 8844 }, { "epoch": 0.2701588271227856, "grad_norm": 0.3836093842983246, "learning_rate": 4.152343750008396e-05, "loss": 4.3272, "step": 8845 }, { "epoch": 0.27018937080024436, "grad_norm": 0.3801654875278473, "learning_rate": 4.1521637195108056e-05, "loss": 4.3703, "step": 8846 }, { "epoch": 0.2702199144777031, "grad_norm": 0.3805307447910309, "learning_rate": 4.1519836738008945e-05, "loss": 4.4329, "step": 8847 }, { "epoch": 0.27025045815516185, "grad_norm": 0.3909810185432434, "learning_rate": 4.15180361288032e-05, "loss": 4.4176, "step": 8848 }, { "epoch": 0.27028100183262066, "grad_norm": 0.3923875391483307, "learning_rate": 4.1516235367507406e-05, "loss": 4.2893, "step": 8849 }, { "epoch": 0.2703115455100794, "grad_norm": 0.380367636680603, "learning_rate": 4.151443445413814e-05, "loss": 4.2701, "step": 8850 }, { "epoch": 0.27034208918753816, "grad_norm": 0.38313767313957214, "learning_rate": 4.151263338871199e-05, "loss": 4.3623, "step": 8851 }, { "epoch": 0.27037263286499696, "grad_norm": 0.3775413930416107, "learning_rate": 4.151083217124552e-05, "loss": 4.2663, "step": 8852 }, { "epoch": 0.2704031765424557, "grad_norm": 0.39072608947753906, "learning_rate": 4.1509030801755344e-05, "loss": 4.3141, "step": 8853 }, { "epoch": 0.27043372021991446, "grad_norm": 0.38145309686660767, "learning_rate": 4.150722928025803e-05, "loss": 4.351, "step": 8854 }, { "epoch": 0.27046426389737327, "grad_norm": 0.3714999854564667, "learning_rate": 4.1505427606770166e-05, "loss": 4.3088, "step": 8855 }, { "epoch": 0.270494807574832, "grad_norm": 0.37931180000305176, "learning_rate": 4.150362578130834e-05, "loss": 4.2536, "step": 8856 }, { "epoch": 0.27052535125229077, "grad_norm": 0.3768925070762634, "learning_rate": 4.1501823803889154e-05, "loss": 4.287, "step": 8857 }, { "epoch": 0.2705558949297495, "grad_norm": 0.37701699137687683, "learning_rate": 4.150002167452919e-05, "loss": 4.3604, "step": 8858 }, { "epoch": 0.2705864386072083, "grad_norm": 0.38209307193756104, "learning_rate": 4.149821939324504e-05, "loss": 4.4115, "step": 8859 }, { "epoch": 0.2706169822846671, "grad_norm": 0.37781864404678345, "learning_rate": 4.149641696005331e-05, "loss": 4.3662, "step": 8860 }, { "epoch": 0.2706475259621258, "grad_norm": 0.3839210271835327, "learning_rate": 4.1494614374970575e-05, "loss": 4.3673, "step": 8861 }, { "epoch": 0.27067806963958463, "grad_norm": 0.3709511458873749, "learning_rate": 4.149281163801345e-05, "loss": 4.3281, "step": 8862 }, { "epoch": 0.2707086133170434, "grad_norm": 0.37679266929626465, "learning_rate": 4.149100874919853e-05, "loss": 4.2676, "step": 8863 }, { "epoch": 0.27073915699450213, "grad_norm": 0.37290167808532715, "learning_rate": 4.148920570854241e-05, "loss": 4.4457, "step": 8864 }, { "epoch": 0.2707697006719609, "grad_norm": 0.38995784521102905, "learning_rate": 4.1487402516061705e-05, "loss": 4.3843, "step": 8865 }, { "epoch": 0.2708002443494197, "grad_norm": 0.3805916905403137, "learning_rate": 4.1485599171772995e-05, "loss": 4.3342, "step": 8866 }, { "epoch": 0.27083078802687843, "grad_norm": 0.3660428524017334, "learning_rate": 4.1483795675692904e-05, "loss": 4.3435, "step": 8867 }, { "epoch": 0.2708613317043372, "grad_norm": 0.38375815749168396, "learning_rate": 4.1481992027838034e-05, "loss": 4.2577, "step": 8868 }, { "epoch": 0.270891875381796, "grad_norm": 0.3739652931690216, "learning_rate": 4.148018822822498e-05, "loss": 4.3803, "step": 8869 }, { "epoch": 0.27092241905925474, "grad_norm": 0.3770633339881897, "learning_rate": 4.1478384276870366e-05, "loss": 4.2906, "step": 8870 }, { "epoch": 0.2709529627367135, "grad_norm": 0.3805040419101715, "learning_rate": 4.1476580173790805e-05, "loss": 4.3373, "step": 8871 }, { "epoch": 0.2709835064141723, "grad_norm": 0.379150927066803, "learning_rate": 4.147477591900289e-05, "loss": 4.3624, "step": 8872 }, { "epoch": 0.27101405009163104, "grad_norm": 0.376430481672287, "learning_rate": 4.1472971512523226e-05, "loss": 4.3424, "step": 8873 }, { "epoch": 0.2710445937690898, "grad_norm": 0.37744230031967163, "learning_rate": 4.1471166954368465e-05, "loss": 4.3298, "step": 8874 }, { "epoch": 0.27107513744654854, "grad_norm": 0.3758583068847656, "learning_rate": 4.14693622445552e-05, "loss": 4.3062, "step": 8875 }, { "epoch": 0.27110568112400735, "grad_norm": 0.37353965640068054, "learning_rate": 4.1467557383100044e-05, "loss": 4.1896, "step": 8876 }, { "epoch": 0.2711362248014661, "grad_norm": 0.38202103972435, "learning_rate": 4.1465752370019615e-05, "loss": 4.3715, "step": 8877 }, { "epoch": 0.27116676847892485, "grad_norm": 0.37996482849121094, "learning_rate": 4.146394720533055e-05, "loss": 4.3312, "step": 8878 }, { "epoch": 0.27119731215638365, "grad_norm": 0.38487452268600464, "learning_rate": 4.146214188904945e-05, "loss": 4.2721, "step": 8879 }, { "epoch": 0.2712278558338424, "grad_norm": 0.39671143889427185, "learning_rate": 4.1460336421192946e-05, "loss": 4.1997, "step": 8880 }, { "epoch": 0.27125839951130115, "grad_norm": 0.37224990129470825, "learning_rate": 4.145853080177766e-05, "loss": 4.317, "step": 8881 }, { "epoch": 0.2712889431887599, "grad_norm": 0.3803226947784424, "learning_rate": 4.145672503082023e-05, "loss": 4.238, "step": 8882 }, { "epoch": 0.2713194868662187, "grad_norm": 0.3868083953857422, "learning_rate": 4.1454919108337256e-05, "loss": 4.3543, "step": 8883 }, { "epoch": 0.27135003054367746, "grad_norm": 0.36723101139068604, "learning_rate": 4.145311303434539e-05, "loss": 4.3924, "step": 8884 }, { "epoch": 0.2713805742211362, "grad_norm": 0.38158944249153137, "learning_rate": 4.1451306808861255e-05, "loss": 4.3243, "step": 8885 }, { "epoch": 0.271411117898595, "grad_norm": 0.3927447199821472, "learning_rate": 4.144950043190148e-05, "loss": 4.3151, "step": 8886 }, { "epoch": 0.27144166157605376, "grad_norm": 0.37648436427116394, "learning_rate": 4.1447693903482686e-05, "loss": 4.3166, "step": 8887 }, { "epoch": 0.2714722052535125, "grad_norm": 0.3854231536388397, "learning_rate": 4.144588722362153e-05, "loss": 4.2938, "step": 8888 }, { "epoch": 0.2715027489309713, "grad_norm": 0.39049866795539856, "learning_rate": 4.1444080392334626e-05, "loss": 4.3913, "step": 8889 }, { "epoch": 0.27153329260843007, "grad_norm": 0.3771812319755554, "learning_rate": 4.144227340963862e-05, "loss": 4.3024, "step": 8890 }, { "epoch": 0.2715638362858888, "grad_norm": 0.3716731369495392, "learning_rate": 4.144046627555016e-05, "loss": 4.4209, "step": 8891 }, { "epoch": 0.27159437996334757, "grad_norm": 0.382518470287323, "learning_rate": 4.143865899008587e-05, "loss": 4.3693, "step": 8892 }, { "epoch": 0.27162492364080637, "grad_norm": 0.3712935149669647, "learning_rate": 4.143685155326239e-05, "loss": 4.3763, "step": 8893 }, { "epoch": 0.2716554673182651, "grad_norm": 0.3812462091445923, "learning_rate": 4.143504396509637e-05, "loss": 4.4155, "step": 8894 }, { "epoch": 0.27168601099572387, "grad_norm": 0.38220688700675964, "learning_rate": 4.143323622560444e-05, "loss": 4.3383, "step": 8895 }, { "epoch": 0.2717165546731827, "grad_norm": 0.3798859417438507, "learning_rate": 4.1431428334803265e-05, "loss": 4.3403, "step": 8896 }, { "epoch": 0.2717470983506414, "grad_norm": 0.3830864131450653, "learning_rate": 4.142962029270948e-05, "loss": 4.3878, "step": 8897 }, { "epoch": 0.2717776420281002, "grad_norm": 0.36754310131073, "learning_rate": 4.142781209933973e-05, "loss": 4.4197, "step": 8898 }, { "epoch": 0.2718081857055589, "grad_norm": 0.39002320170402527, "learning_rate": 4.1426003754710673e-05, "loss": 4.3486, "step": 8899 }, { "epoch": 0.27183872938301773, "grad_norm": 0.36799678206443787, "learning_rate": 4.142419525883895e-05, "loss": 4.377, "step": 8900 }, { "epoch": 0.2718692730604765, "grad_norm": 0.37075841426849365, "learning_rate": 4.1422386611741215e-05, "loss": 4.3689, "step": 8901 }, { "epoch": 0.27189981673793523, "grad_norm": 0.38325417041778564, "learning_rate": 4.142057781343413e-05, "loss": 4.3238, "step": 8902 }, { "epoch": 0.27193036041539403, "grad_norm": 0.39722827076911926, "learning_rate": 4.1418768863934334e-05, "loss": 4.3869, "step": 8903 }, { "epoch": 0.2719609040928528, "grad_norm": 0.3791460394859314, "learning_rate": 4.14169597632585e-05, "loss": 4.2945, "step": 8904 }, { "epoch": 0.27199144777031153, "grad_norm": 0.38109466433525085, "learning_rate": 4.1415150511423273e-05, "loss": 4.2739, "step": 8905 }, { "epoch": 0.2720219914477703, "grad_norm": 0.3939448297023773, "learning_rate": 4.1413341108445314e-05, "loss": 4.341, "step": 8906 }, { "epoch": 0.2720525351252291, "grad_norm": 0.37745174765586853, "learning_rate": 4.141153155434129e-05, "loss": 4.3396, "step": 8907 }, { "epoch": 0.27208307880268784, "grad_norm": 0.375742107629776, "learning_rate": 4.1409721849127844e-05, "loss": 4.2742, "step": 8908 }, { "epoch": 0.2721136224801466, "grad_norm": 0.3824021518230438, "learning_rate": 4.140791199282167e-05, "loss": 4.2834, "step": 8909 }, { "epoch": 0.2721441661576054, "grad_norm": 0.3776208162307739, "learning_rate": 4.14061019854394e-05, "loss": 4.3729, "step": 8910 }, { "epoch": 0.27217470983506414, "grad_norm": 0.379751592874527, "learning_rate": 4.140429182699772e-05, "loss": 4.3944, "step": 8911 }, { "epoch": 0.2722052535125229, "grad_norm": 0.3818002939224243, "learning_rate": 4.140248151751329e-05, "loss": 4.3925, "step": 8912 }, { "epoch": 0.2722357971899817, "grad_norm": 0.3773232102394104, "learning_rate": 4.140067105700277e-05, "loss": 4.3427, "step": 8913 }, { "epoch": 0.27226634086744045, "grad_norm": 0.3858805000782013, "learning_rate": 4.139886044548285e-05, "loss": 4.4492, "step": 8914 }, { "epoch": 0.2722968845448992, "grad_norm": 0.380057692527771, "learning_rate": 4.139704968297019e-05, "loss": 4.3684, "step": 8915 }, { "epoch": 0.27232742822235795, "grad_norm": 0.3807010054588318, "learning_rate": 4.139523876948146e-05, "loss": 4.4271, "step": 8916 }, { "epoch": 0.27235797189981675, "grad_norm": 0.39319247007369995, "learning_rate": 4.139342770503334e-05, "loss": 4.3862, "step": 8917 }, { "epoch": 0.2723885155772755, "grad_norm": 0.3789297938346863, "learning_rate": 4.13916164896425e-05, "loss": 4.3713, "step": 8918 }, { "epoch": 0.27241905925473425, "grad_norm": 0.37490832805633545, "learning_rate": 4.138980512332562e-05, "loss": 4.4156, "step": 8919 }, { "epoch": 0.27244960293219306, "grad_norm": 0.3768698573112488, "learning_rate": 4.138799360609937e-05, "loss": 4.3046, "step": 8920 }, { "epoch": 0.2724801466096518, "grad_norm": 0.37925466895103455, "learning_rate": 4.138618193798045e-05, "loss": 4.3202, "step": 8921 }, { "epoch": 0.27251069028711056, "grad_norm": 0.39351677894592285, "learning_rate": 4.1384370118985524e-05, "loss": 4.3883, "step": 8922 }, { "epoch": 0.2725412339645693, "grad_norm": 0.3843001425266266, "learning_rate": 4.138255814913128e-05, "loss": 4.3387, "step": 8923 }, { "epoch": 0.2725717776420281, "grad_norm": 0.3762722611427307, "learning_rate": 4.138074602843439e-05, "loss": 4.3713, "step": 8924 }, { "epoch": 0.27260232131948686, "grad_norm": 0.35868600010871887, "learning_rate": 4.137893375691156e-05, "loss": 4.3102, "step": 8925 }, { "epoch": 0.2726328649969456, "grad_norm": 0.37079912424087524, "learning_rate": 4.137712133457946e-05, "loss": 4.3218, "step": 8926 }, { "epoch": 0.2726634086744044, "grad_norm": 0.37608909606933594, "learning_rate": 4.137530876145478e-05, "loss": 4.4519, "step": 8927 }, { "epoch": 0.27269395235186317, "grad_norm": 0.3737427890300751, "learning_rate": 4.1373496037554224e-05, "loss": 4.3813, "step": 8928 }, { "epoch": 0.2727244960293219, "grad_norm": 0.3849286437034607, "learning_rate": 4.137168316289447e-05, "loss": 4.3753, "step": 8929 }, { "epoch": 0.2727550397067807, "grad_norm": 0.37547048926353455, "learning_rate": 4.136987013749221e-05, "loss": 4.3547, "step": 8930 }, { "epoch": 0.27278558338423947, "grad_norm": 0.3827504515647888, "learning_rate": 4.1368056961364134e-05, "loss": 4.3632, "step": 8931 }, { "epoch": 0.2728161270616982, "grad_norm": 0.3779693841934204, "learning_rate": 4.1366243634526944e-05, "loss": 4.3862, "step": 8932 }, { "epoch": 0.27284667073915697, "grad_norm": 0.38520997762680054, "learning_rate": 4.136443015699733e-05, "loss": 4.4233, "step": 8933 }, { "epoch": 0.2728772144166158, "grad_norm": 0.40033695101737976, "learning_rate": 4.1362616528791996e-05, "loss": 4.2393, "step": 8934 }, { "epoch": 0.2729077580940745, "grad_norm": 0.39849528670310974, "learning_rate": 4.136080274992764e-05, "loss": 4.2139, "step": 8935 }, { "epoch": 0.2729383017715333, "grad_norm": 0.3744693696498871, "learning_rate": 4.135898882042096e-05, "loss": 4.3492, "step": 8936 }, { "epoch": 0.2729688454489921, "grad_norm": 0.37815913558006287, "learning_rate": 4.135717474028866e-05, "loss": 4.328, "step": 8937 }, { "epoch": 0.27299938912645083, "grad_norm": 0.37786874175071716, "learning_rate": 4.1355360509547446e-05, "loss": 4.3276, "step": 8938 }, { "epoch": 0.2730299328039096, "grad_norm": 0.37258562445640564, "learning_rate": 4.1353546128214024e-05, "loss": 4.3252, "step": 8939 }, { "epoch": 0.27306047648136833, "grad_norm": 0.38544729351997375, "learning_rate": 4.135173159630509e-05, "loss": 4.3297, "step": 8940 }, { "epoch": 0.27309102015882714, "grad_norm": 0.3717024028301239, "learning_rate": 4.1349916913837344e-05, "loss": 4.2852, "step": 8941 }, { "epoch": 0.2731215638362859, "grad_norm": 0.3813020586967468, "learning_rate": 4.134810208082752e-05, "loss": 4.459, "step": 8942 }, { "epoch": 0.27315210751374464, "grad_norm": 0.3745417296886444, "learning_rate": 4.134628709729231e-05, "loss": 4.3624, "step": 8943 }, { "epoch": 0.27318265119120344, "grad_norm": 0.3726627826690674, "learning_rate": 4.134447196324842e-05, "loss": 4.2184, "step": 8944 }, { "epoch": 0.2732131948686622, "grad_norm": 0.3887917697429657, "learning_rate": 4.1342656678712585e-05, "loss": 4.439, "step": 8945 }, { "epoch": 0.27324373854612094, "grad_norm": 0.3830944001674652, "learning_rate": 4.134084124370151e-05, "loss": 4.3785, "step": 8946 }, { "epoch": 0.27327428222357975, "grad_norm": 0.3713243007659912, "learning_rate": 4.13390256582319e-05, "loss": 4.407, "step": 8947 }, { "epoch": 0.2733048259010385, "grad_norm": 0.37104979157447815, "learning_rate": 4.133720992232049e-05, "loss": 4.2662, "step": 8948 }, { "epoch": 0.27333536957849724, "grad_norm": 0.3771907389163971, "learning_rate": 4.133539403598398e-05, "loss": 4.3322, "step": 8949 }, { "epoch": 0.273365913255956, "grad_norm": 0.3858771026134491, "learning_rate": 4.133357799923911e-05, "loss": 4.2649, "step": 8950 }, { "epoch": 0.2733964569334148, "grad_norm": 0.3862280547618866, "learning_rate": 4.133176181210257e-05, "loss": 4.4022, "step": 8951 }, { "epoch": 0.27342700061087355, "grad_norm": 0.3745979964733124, "learning_rate": 4.132994547459111e-05, "loss": 4.421, "step": 8952 }, { "epoch": 0.2734575442883323, "grad_norm": 0.3768307566642761, "learning_rate": 4.132812898672145e-05, "loss": 4.4095, "step": 8953 }, { "epoch": 0.2734880879657911, "grad_norm": 0.38987842202186584, "learning_rate": 4.132631234851031e-05, "loss": 4.3844, "step": 8954 }, { "epoch": 0.27351863164324985, "grad_norm": 0.3709476888179779, "learning_rate": 4.132449555997442e-05, "loss": 4.2945, "step": 8955 }, { "epoch": 0.2735491753207086, "grad_norm": 0.380523681640625, "learning_rate": 4.1322678621130503e-05, "loss": 4.329, "step": 8956 }, { "epoch": 0.27357971899816735, "grad_norm": 0.37325334548950195, "learning_rate": 4.132086153199529e-05, "loss": 4.4224, "step": 8957 }, { "epoch": 0.27361026267562616, "grad_norm": 0.3692275583744049, "learning_rate": 4.131904429258552e-05, "loss": 4.2664, "step": 8958 }, { "epoch": 0.2736408063530849, "grad_norm": 0.37240245938301086, "learning_rate": 4.1317226902917914e-05, "loss": 4.2617, "step": 8959 }, { "epoch": 0.27367135003054366, "grad_norm": 0.379172682762146, "learning_rate": 4.131540936300921e-05, "loss": 4.2334, "step": 8960 }, { "epoch": 0.27370189370800246, "grad_norm": 0.38141509890556335, "learning_rate": 4.131359167287614e-05, "loss": 4.3734, "step": 8961 }, { "epoch": 0.2737324373854612, "grad_norm": 0.3783419132232666, "learning_rate": 4.1311773832535456e-05, "loss": 4.3816, "step": 8962 }, { "epoch": 0.27376298106291996, "grad_norm": 0.3790365755558014, "learning_rate": 4.1309955842003875e-05, "loss": 4.304, "step": 8963 }, { "epoch": 0.27379352474037877, "grad_norm": 0.3772009313106537, "learning_rate": 4.130813770129814e-05, "loss": 4.3805, "step": 8964 }, { "epoch": 0.2738240684178375, "grad_norm": 0.3896392285823822, "learning_rate": 4.1306319410435e-05, "loss": 4.4151, "step": 8965 }, { "epoch": 0.27385461209529627, "grad_norm": 0.37566933035850525, "learning_rate": 4.1304500969431204e-05, "loss": 4.2514, "step": 8966 }, { "epoch": 0.273885155772755, "grad_norm": 0.37633442878723145, "learning_rate": 4.130268237830348e-05, "loss": 4.3972, "step": 8967 }, { "epoch": 0.2739156994502138, "grad_norm": 0.3727110028266907, "learning_rate": 4.1300863637068565e-05, "loss": 4.3435, "step": 8968 }, { "epoch": 0.2739462431276726, "grad_norm": 0.3795904815196991, "learning_rate": 4.129904474574323e-05, "loss": 4.3522, "step": 8969 }, { "epoch": 0.2739767868051313, "grad_norm": 0.3749704658985138, "learning_rate": 4.129722570434421e-05, "loss": 4.3893, "step": 8970 }, { "epoch": 0.27400733048259013, "grad_norm": 0.37631165981292725, "learning_rate": 4.129540651288825e-05, "loss": 4.2584, "step": 8971 }, { "epoch": 0.2740378741600489, "grad_norm": 0.38058218359947205, "learning_rate": 4.12935871713921e-05, "loss": 4.3473, "step": 8972 }, { "epoch": 0.2740684178375076, "grad_norm": 0.3772212564945221, "learning_rate": 4.129176767987252e-05, "loss": 4.3589, "step": 8973 }, { "epoch": 0.2740989615149664, "grad_norm": 0.36991187930107117, "learning_rate": 4.1289948038346256e-05, "loss": 4.3411, "step": 8974 }, { "epoch": 0.2741295051924252, "grad_norm": 0.40346887707710266, "learning_rate": 4.128812824683007e-05, "loss": 4.2902, "step": 8975 }, { "epoch": 0.27416004886988393, "grad_norm": 0.37090548872947693, "learning_rate": 4.128630830534071e-05, "loss": 4.3919, "step": 8976 }, { "epoch": 0.2741905925473427, "grad_norm": 0.3715347647666931, "learning_rate": 4.1284488213894936e-05, "loss": 4.2423, "step": 8977 }, { "epoch": 0.2742211362248015, "grad_norm": 0.39299002289772034, "learning_rate": 4.12826679725095e-05, "loss": 4.2889, "step": 8978 }, { "epoch": 0.27425167990226024, "grad_norm": 0.37653908133506775, "learning_rate": 4.128084758120118e-05, "loss": 4.2716, "step": 8979 }, { "epoch": 0.274282223579719, "grad_norm": 0.3865956664085388, "learning_rate": 4.127902703998672e-05, "loss": 4.298, "step": 8980 }, { "epoch": 0.27431276725717774, "grad_norm": 0.3722035586833954, "learning_rate": 4.127720634888288e-05, "loss": 4.2992, "step": 8981 }, { "epoch": 0.27434331093463654, "grad_norm": 0.37795060873031616, "learning_rate": 4.127538550790644e-05, "loss": 4.3823, "step": 8982 }, { "epoch": 0.2743738546120953, "grad_norm": 0.3664575517177582, "learning_rate": 4.127356451707416e-05, "loss": 4.3691, "step": 8983 }, { "epoch": 0.27440439828955404, "grad_norm": 0.38487860560417175, "learning_rate": 4.12717433764028e-05, "loss": 4.3171, "step": 8984 }, { "epoch": 0.27443494196701285, "grad_norm": 0.38543862104415894, "learning_rate": 4.126992208590913e-05, "loss": 4.3578, "step": 8985 }, { "epoch": 0.2744654856444716, "grad_norm": 0.372076153755188, "learning_rate": 4.126810064560993e-05, "loss": 4.4111, "step": 8986 }, { "epoch": 0.27449602932193035, "grad_norm": 0.38590505719184875, "learning_rate": 4.1266279055521964e-05, "loss": 4.3486, "step": 8987 }, { "epoch": 0.27452657299938915, "grad_norm": 0.3865105211734772, "learning_rate": 4.1264457315662e-05, "loss": 4.3644, "step": 8988 }, { "epoch": 0.2745571166768479, "grad_norm": 0.3873436748981476, "learning_rate": 4.1262635426046815e-05, "loss": 4.3357, "step": 8989 }, { "epoch": 0.27458766035430665, "grad_norm": 0.38880279660224915, "learning_rate": 4.126081338669318e-05, "loss": 4.4207, "step": 8990 }, { "epoch": 0.2746182040317654, "grad_norm": 0.3876362442970276, "learning_rate": 4.125899119761788e-05, "loss": 4.3591, "step": 8991 }, { "epoch": 0.2746487477092242, "grad_norm": 0.37896227836608887, "learning_rate": 4.125716885883768e-05, "loss": 4.3528, "step": 8992 }, { "epoch": 0.27467929138668296, "grad_norm": 0.38649237155914307, "learning_rate": 4.125534637036939e-05, "loss": 4.3687, "step": 8993 }, { "epoch": 0.2747098350641417, "grad_norm": 0.400379478931427, "learning_rate": 4.125352373222975e-05, "loss": 4.2588, "step": 8994 }, { "epoch": 0.2747403787416005, "grad_norm": 0.39859363436698914, "learning_rate": 4.125170094443555e-05, "loss": 4.3158, "step": 8995 }, { "epoch": 0.27477092241905926, "grad_norm": 0.36992570757865906, "learning_rate": 4.1249878007003607e-05, "loss": 4.2217, "step": 8996 }, { "epoch": 0.274801466096518, "grad_norm": 0.3824039399623871, "learning_rate": 4.1248054919950676e-05, "loss": 4.402, "step": 8997 }, { "epoch": 0.27483200977397676, "grad_norm": 0.3834644556045532, "learning_rate": 4.124623168329355e-05, "loss": 4.3637, "step": 8998 }, { "epoch": 0.27486255345143557, "grad_norm": 0.3805016279220581, "learning_rate": 4.1244408297049e-05, "loss": 4.2986, "step": 8999 }, { "epoch": 0.2748930971288943, "grad_norm": 0.38665199279785156, "learning_rate": 4.124258476123385e-05, "loss": 4.2998, "step": 9000 }, { "epoch": 0.27492364080635306, "grad_norm": 0.3806636929512024, "learning_rate": 4.1240761075864865e-05, "loss": 4.2686, "step": 9001 }, { "epoch": 0.27495418448381187, "grad_norm": 0.38967984914779663, "learning_rate": 4.123893724095884e-05, "loss": 4.3739, "step": 9002 }, { "epoch": 0.2749847281612706, "grad_norm": 0.3781239092350006, "learning_rate": 4.123711325653257e-05, "loss": 4.3316, "step": 9003 }, { "epoch": 0.27501527183872937, "grad_norm": 0.37682080268859863, "learning_rate": 4.1235289122602854e-05, "loss": 4.2816, "step": 9004 }, { "epoch": 0.2750458155161882, "grad_norm": 0.3658684194087982, "learning_rate": 4.123346483918648e-05, "loss": 4.4889, "step": 9005 }, { "epoch": 0.2750763591936469, "grad_norm": 0.37824591994285583, "learning_rate": 4.1231640406300254e-05, "loss": 4.3148, "step": 9006 }, { "epoch": 0.2751069028711057, "grad_norm": 0.3748096823692322, "learning_rate": 4.1229815823960966e-05, "loss": 4.3653, "step": 9007 }, { "epoch": 0.2751374465485644, "grad_norm": 0.37354937195777893, "learning_rate": 4.122799109218542e-05, "loss": 4.322, "step": 9008 }, { "epoch": 0.27516799022602323, "grad_norm": 0.3713046908378601, "learning_rate": 4.1226166210990414e-05, "loss": 4.3475, "step": 9009 }, { "epoch": 0.275198533903482, "grad_norm": 0.37806299328804016, "learning_rate": 4.122434118039276e-05, "loss": 4.3051, "step": 9010 }, { "epoch": 0.27522907758094073, "grad_norm": 0.3751234710216522, "learning_rate": 4.122251600040924e-05, "loss": 4.3405, "step": 9011 }, { "epoch": 0.27525962125839953, "grad_norm": 0.3786211311817169, "learning_rate": 4.1220690671056685e-05, "loss": 4.3598, "step": 9012 }, { "epoch": 0.2752901649358583, "grad_norm": 0.38100579380989075, "learning_rate": 4.1218865192351896e-05, "loss": 4.395, "step": 9013 }, { "epoch": 0.27532070861331703, "grad_norm": 0.37914198637008667, "learning_rate": 4.121703956431167e-05, "loss": 4.3078, "step": 9014 }, { "epoch": 0.2753512522907758, "grad_norm": 0.3803291320800781, "learning_rate": 4.121521378695282e-05, "loss": 4.3028, "step": 9015 }, { "epoch": 0.2753817959682346, "grad_norm": 0.37510746717453003, "learning_rate": 4.121338786029216e-05, "loss": 4.3929, "step": 9016 }, { "epoch": 0.27541233964569334, "grad_norm": 0.3849732279777527, "learning_rate": 4.121156178434651e-05, "loss": 4.3666, "step": 9017 }, { "epoch": 0.2754428833231521, "grad_norm": 0.396642804145813, "learning_rate": 4.1209735559132664e-05, "loss": 4.3191, "step": 9018 }, { "epoch": 0.2754734270006109, "grad_norm": 0.3875449299812317, "learning_rate": 4.120790918466746e-05, "loss": 4.4325, "step": 9019 }, { "epoch": 0.27550397067806964, "grad_norm": 0.37823957204818726, "learning_rate": 4.1206082660967696e-05, "loss": 4.3661, "step": 9020 }, { "epoch": 0.2755345143555284, "grad_norm": 0.3816978335380554, "learning_rate": 4.12042559880502e-05, "loss": 4.3133, "step": 9021 }, { "epoch": 0.2755650580329872, "grad_norm": 0.38931557536125183, "learning_rate": 4.1202429165931786e-05, "loss": 4.3592, "step": 9022 }, { "epoch": 0.27559560171044595, "grad_norm": 0.3889407515525818, "learning_rate": 4.120060219462927e-05, "loss": 4.3863, "step": 9023 }, { "epoch": 0.2756261453879047, "grad_norm": 0.3755837380886078, "learning_rate": 4.119877507415949e-05, "loss": 4.3497, "step": 9024 }, { "epoch": 0.27565668906536345, "grad_norm": 0.3819480836391449, "learning_rate": 4.1196947804539256e-05, "loss": 4.3384, "step": 9025 }, { "epoch": 0.27568723274282225, "grad_norm": 0.36675509810447693, "learning_rate": 4.1195120385785394e-05, "loss": 4.2902, "step": 9026 }, { "epoch": 0.275717776420281, "grad_norm": 0.37257400155067444, "learning_rate": 4.119329281791473e-05, "loss": 4.3946, "step": 9027 }, { "epoch": 0.27574832009773975, "grad_norm": 0.37599700689315796, "learning_rate": 4.11914651009441e-05, "loss": 4.2912, "step": 9028 }, { "epoch": 0.27577886377519856, "grad_norm": 0.3835657238960266, "learning_rate": 4.1189637234890324e-05, "loss": 4.4196, "step": 9029 }, { "epoch": 0.2758094074526573, "grad_norm": 0.37845781445503235, "learning_rate": 4.118780921977023e-05, "loss": 4.271, "step": 9030 }, { "epoch": 0.27583995113011606, "grad_norm": 0.36952516436576843, "learning_rate": 4.1185981055600655e-05, "loss": 4.313, "step": 9031 }, { "epoch": 0.2758704948075748, "grad_norm": 0.3783247768878937, "learning_rate": 4.118415274239844e-05, "loss": 4.3135, "step": 9032 }, { "epoch": 0.2759010384850336, "grad_norm": 0.3776697516441345, "learning_rate": 4.118232428018039e-05, "loss": 4.2826, "step": 9033 }, { "epoch": 0.27593158216249236, "grad_norm": 0.37726035714149475, "learning_rate": 4.1180495668963375e-05, "loss": 4.4279, "step": 9034 }, { "epoch": 0.2759621258399511, "grad_norm": 0.38269710540771484, "learning_rate": 4.117866690876422e-05, "loss": 4.319, "step": 9035 }, { "epoch": 0.2759926695174099, "grad_norm": 0.37217679619789124, "learning_rate": 4.1176837999599746e-05, "loss": 4.3742, "step": 9036 }, { "epoch": 0.27602321319486867, "grad_norm": 0.3779340386390686, "learning_rate": 4.117500894148682e-05, "loss": 4.4216, "step": 9037 }, { "epoch": 0.2760537568723274, "grad_norm": 0.3736778497695923, "learning_rate": 4.117317973444226e-05, "loss": 4.4018, "step": 9038 }, { "epoch": 0.2760843005497862, "grad_norm": 0.3727174401283264, "learning_rate": 4.1171350378482924e-05, "loss": 4.282, "step": 9039 }, { "epoch": 0.27611484422724497, "grad_norm": 0.36705997586250305, "learning_rate": 4.1169520873625656e-05, "loss": 4.3001, "step": 9040 }, { "epoch": 0.2761453879047037, "grad_norm": 0.3809087872505188, "learning_rate": 4.11676912198873e-05, "loss": 4.3782, "step": 9041 }, { "epoch": 0.27617593158216247, "grad_norm": 0.3669109344482422, "learning_rate": 4.116586141728468e-05, "loss": 4.3272, "step": 9042 }, { "epoch": 0.2762064752596213, "grad_norm": 0.3734937906265259, "learning_rate": 4.1164031465834666e-05, "loss": 4.4185, "step": 9043 }, { "epoch": 0.27623701893708, "grad_norm": 0.3735652267932892, "learning_rate": 4.116220136555412e-05, "loss": 4.3664, "step": 9044 }, { "epoch": 0.2762675626145388, "grad_norm": 0.38161957263946533, "learning_rate": 4.116037111645986e-05, "loss": 4.2992, "step": 9045 }, { "epoch": 0.2762981062919976, "grad_norm": 0.3740847706794739, "learning_rate": 4.115854071856876e-05, "loss": 4.3176, "step": 9046 }, { "epoch": 0.27632864996945633, "grad_norm": 0.3701704740524292, "learning_rate": 4.115671017189766e-05, "loss": 4.3675, "step": 9047 }, { "epoch": 0.2763591936469151, "grad_norm": 0.4104536473751068, "learning_rate": 4.1154879476463436e-05, "loss": 4.3732, "step": 9048 }, { "epoch": 0.27638973732437383, "grad_norm": 0.3628978133201599, "learning_rate": 4.1153048632282924e-05, "loss": 4.3119, "step": 9049 }, { "epoch": 0.27642028100183264, "grad_norm": 0.3670038878917694, "learning_rate": 4.115121763937299e-05, "loss": 4.2915, "step": 9050 }, { "epoch": 0.2764508246792914, "grad_norm": 0.36863186955451965, "learning_rate": 4.1149386497750486e-05, "loss": 4.3693, "step": 9051 }, { "epoch": 0.27648136835675013, "grad_norm": 0.36940351128578186, "learning_rate": 4.114755520743228e-05, "loss": 4.3946, "step": 9052 }, { "epoch": 0.27651191203420894, "grad_norm": 0.36825838685035706, "learning_rate": 4.1145723768435226e-05, "loss": 4.2806, "step": 9053 }, { "epoch": 0.2765424557116677, "grad_norm": 0.37161538004875183, "learning_rate": 4.114389218077621e-05, "loss": 4.422, "step": 9054 }, { "epoch": 0.27657299938912644, "grad_norm": 0.3711296319961548, "learning_rate": 4.1142060444472066e-05, "loss": 4.3906, "step": 9055 }, { "epoch": 0.27660354306658524, "grad_norm": 0.3768231272697449, "learning_rate": 4.1140228559539665e-05, "loss": 4.3551, "step": 9056 }, { "epoch": 0.276634086744044, "grad_norm": 0.3882772922515869, "learning_rate": 4.1138396525995895e-05, "loss": 4.2997, "step": 9057 }, { "epoch": 0.27666463042150274, "grad_norm": 0.3652805685997009, "learning_rate": 4.1136564343857596e-05, "loss": 4.3784, "step": 9058 }, { "epoch": 0.2766951740989615, "grad_norm": 0.3780054748058319, "learning_rate": 4.113473201314166e-05, "loss": 4.24, "step": 9059 }, { "epoch": 0.2767257177764203, "grad_norm": 0.37797805666923523, "learning_rate": 4.1132899533864956e-05, "loss": 4.4136, "step": 9060 }, { "epoch": 0.27675626145387905, "grad_norm": 0.37805813550949097, "learning_rate": 4.113106690604435e-05, "loss": 4.3267, "step": 9061 }, { "epoch": 0.2767868051313378, "grad_norm": 0.3895326852798462, "learning_rate": 4.1129234129696715e-05, "loss": 4.3844, "step": 9062 }, { "epoch": 0.2768173488087966, "grad_norm": 0.38158848881721497, "learning_rate": 4.1127401204838924e-05, "loss": 4.249, "step": 9063 }, { "epoch": 0.27684789248625535, "grad_norm": 0.3780001997947693, "learning_rate": 4.1125568131487856e-05, "loss": 4.3636, "step": 9064 }, { "epoch": 0.2768784361637141, "grad_norm": 0.37793025374412537, "learning_rate": 4.11237349096604e-05, "loss": 4.3087, "step": 9065 }, { "epoch": 0.27690897984117285, "grad_norm": 0.3977431058883667, "learning_rate": 4.112190153937342e-05, "loss": 4.3653, "step": 9066 }, { "epoch": 0.27693952351863166, "grad_norm": 0.37613004446029663, "learning_rate": 4.112006802064381e-05, "loss": 4.3964, "step": 9067 }, { "epoch": 0.2769700671960904, "grad_norm": 0.3847426176071167, "learning_rate": 4.111823435348845e-05, "loss": 4.2696, "step": 9068 }, { "epoch": 0.27700061087354916, "grad_norm": 0.39015787839889526, "learning_rate": 4.11164005379242e-05, "loss": 4.3925, "step": 9069 }, { "epoch": 0.27703115455100796, "grad_norm": 0.3727329671382904, "learning_rate": 4.111456657396798e-05, "loss": 4.3443, "step": 9070 }, { "epoch": 0.2770616982284667, "grad_norm": 0.37722915410995483, "learning_rate": 4.1112732461636654e-05, "loss": 4.2931, "step": 9071 }, { "epoch": 0.27709224190592546, "grad_norm": 0.38683241605758667, "learning_rate": 4.111089820094712e-05, "loss": 4.3903, "step": 9072 }, { "epoch": 0.2771227855833842, "grad_norm": 0.3826976418495178, "learning_rate": 4.110906379191626e-05, "loss": 4.2993, "step": 9073 }, { "epoch": 0.277153329260843, "grad_norm": 0.3897358477115631, "learning_rate": 4.1107229234560965e-05, "loss": 4.2813, "step": 9074 }, { "epoch": 0.27718387293830177, "grad_norm": 0.3762635290622711, "learning_rate": 4.110539452889813e-05, "loss": 4.3797, "step": 9075 }, { "epoch": 0.2772144166157605, "grad_norm": 0.3759833574295044, "learning_rate": 4.110355967494466e-05, "loss": 4.311, "step": 9076 }, { "epoch": 0.2772449602932193, "grad_norm": 0.39768412709236145, "learning_rate": 4.1101724672717414e-05, "loss": 4.427, "step": 9077 }, { "epoch": 0.27727550397067807, "grad_norm": 0.3885560929775238, "learning_rate": 4.1099889522233325e-05, "loss": 4.4147, "step": 9078 }, { "epoch": 0.2773060476481368, "grad_norm": 0.3704238831996918, "learning_rate": 4.1098054223509274e-05, "loss": 4.3647, "step": 9079 }, { "epoch": 0.2773365913255956, "grad_norm": 0.3778234124183655, "learning_rate": 4.1096218776562155e-05, "loss": 4.2835, "step": 9080 }, { "epoch": 0.2773671350030544, "grad_norm": 0.37853431701660156, "learning_rate": 4.109438318140888e-05, "loss": 4.3466, "step": 9081 }, { "epoch": 0.2773976786805131, "grad_norm": 0.39147520065307617, "learning_rate": 4.109254743806634e-05, "loss": 4.4279, "step": 9082 }, { "epoch": 0.2774282223579719, "grad_norm": 0.3902781009674072, "learning_rate": 4.1090711546551444e-05, "loss": 4.3356, "step": 9083 }, { "epoch": 0.2774587660354307, "grad_norm": 0.37588101625442505, "learning_rate": 4.1088875506881094e-05, "loss": 4.3729, "step": 9084 }, { "epoch": 0.27748930971288943, "grad_norm": 0.38140159845352173, "learning_rate": 4.10870393190722e-05, "loss": 4.3497, "step": 9085 }, { "epoch": 0.2775198533903482, "grad_norm": 0.37409141659736633, "learning_rate": 4.108520298314166e-05, "loss": 4.3631, "step": 9086 }, { "epoch": 0.277550397067807, "grad_norm": 0.37495896220207214, "learning_rate": 4.108336649910638e-05, "loss": 4.2656, "step": 9087 }, { "epoch": 0.27758094074526574, "grad_norm": 0.38239526748657227, "learning_rate": 4.108152986698328e-05, "loss": 4.4289, "step": 9088 }, { "epoch": 0.2776114844227245, "grad_norm": 0.38417255878448486, "learning_rate": 4.107969308678926e-05, "loss": 4.3164, "step": 9089 }, { "epoch": 0.27764202810018324, "grad_norm": 0.38342252373695374, "learning_rate": 4.107785615854125e-05, "loss": 4.3752, "step": 9090 }, { "epoch": 0.27767257177764204, "grad_norm": 0.3716830015182495, "learning_rate": 4.1076019082256145e-05, "loss": 4.2935, "step": 9091 }, { "epoch": 0.2777031154551008, "grad_norm": 0.37781038880348206, "learning_rate": 4.1074181857950865e-05, "loss": 4.3588, "step": 9092 }, { "epoch": 0.27773365913255954, "grad_norm": 0.37134048342704773, "learning_rate": 4.107234448564233e-05, "loss": 4.3956, "step": 9093 }, { "epoch": 0.27776420281001835, "grad_norm": 0.3794681131839752, "learning_rate": 4.1070506965347454e-05, "loss": 4.323, "step": 9094 }, { "epoch": 0.2777947464874771, "grad_norm": 0.3839279115200043, "learning_rate": 4.106866929708316e-05, "loss": 4.253, "step": 9095 }, { "epoch": 0.27782529016493585, "grad_norm": 0.3778873085975647, "learning_rate": 4.1066831480866374e-05, "loss": 4.3575, "step": 9096 }, { "epoch": 0.27785583384239465, "grad_norm": 0.3680250644683838, "learning_rate": 4.1064993516714e-05, "loss": 4.373, "step": 9097 }, { "epoch": 0.2778863775198534, "grad_norm": 0.3939468562602997, "learning_rate": 4.1063155404642974e-05, "loss": 4.4302, "step": 9098 }, { "epoch": 0.27791692119731215, "grad_norm": 0.39077872037887573, "learning_rate": 4.106131714467022e-05, "loss": 4.4252, "step": 9099 }, { "epoch": 0.2779474648747709, "grad_norm": 0.3897320330142975, "learning_rate": 4.105947873681266e-05, "loss": 4.387, "step": 9100 }, { "epoch": 0.2779780085522297, "grad_norm": 0.37752464413642883, "learning_rate": 4.1057640181087215e-05, "loss": 4.3915, "step": 9101 }, { "epoch": 0.27800855222968845, "grad_norm": 0.3688341975212097, "learning_rate": 4.105580147751082e-05, "loss": 4.363, "step": 9102 }, { "epoch": 0.2780390959071472, "grad_norm": 0.40340620279312134, "learning_rate": 4.1053962626100415e-05, "loss": 4.417, "step": 9103 }, { "epoch": 0.278069639584606, "grad_norm": 0.3880245089530945, "learning_rate": 4.105212362687292e-05, "loss": 4.315, "step": 9104 }, { "epoch": 0.27810018326206476, "grad_norm": 0.396876722574234, "learning_rate": 4.105028447984527e-05, "loss": 4.3077, "step": 9105 }, { "epoch": 0.2781307269395235, "grad_norm": 0.3840775787830353, "learning_rate": 4.1048445185034396e-05, "loss": 4.3752, "step": 9106 }, { "epoch": 0.27816127061698226, "grad_norm": 0.38628441095352173, "learning_rate": 4.104660574245723e-05, "loss": 4.4138, "step": 9107 }, { "epoch": 0.27819181429444106, "grad_norm": 0.3888738751411438, "learning_rate": 4.104476615213073e-05, "loss": 4.2362, "step": 9108 }, { "epoch": 0.2782223579718998, "grad_norm": 0.40271657705307007, "learning_rate": 4.104292641407181e-05, "loss": 4.3723, "step": 9109 }, { "epoch": 0.27825290164935856, "grad_norm": 0.38585489988327026, "learning_rate": 4.1041086528297415e-05, "loss": 4.3276, "step": 9110 }, { "epoch": 0.27828344532681737, "grad_norm": 0.37503862380981445, "learning_rate": 4.103924649482449e-05, "loss": 4.3673, "step": 9111 }, { "epoch": 0.2783139890042761, "grad_norm": 0.38432639837265015, "learning_rate": 4.103740631366998e-05, "loss": 4.4406, "step": 9112 }, { "epoch": 0.27834453268173487, "grad_norm": 0.3846382200717926, "learning_rate": 4.103556598485082e-05, "loss": 4.3661, "step": 9113 }, { "epoch": 0.2783750763591937, "grad_norm": 0.37131941318511963, "learning_rate": 4.1033725508383966e-05, "loss": 4.3019, "step": 9114 }, { "epoch": 0.2784056200366524, "grad_norm": 0.36710798740386963, "learning_rate": 4.1031884884286356e-05, "loss": 4.4087, "step": 9115 }, { "epoch": 0.2784361637141112, "grad_norm": 0.37140709161758423, "learning_rate": 4.1030044112574926e-05, "loss": 4.3783, "step": 9116 }, { "epoch": 0.2784667073915699, "grad_norm": 0.3701474368572235, "learning_rate": 4.102820319326666e-05, "loss": 4.3394, "step": 9117 }, { "epoch": 0.27849725106902873, "grad_norm": 0.38072365522384644, "learning_rate": 4.102636212637847e-05, "loss": 4.2925, "step": 9118 }, { "epoch": 0.2785277947464875, "grad_norm": 0.39115679264068604, "learning_rate": 4.102452091192733e-05, "loss": 4.2877, "step": 9119 }, { "epoch": 0.27855833842394623, "grad_norm": 0.3788241147994995, "learning_rate": 4.102267954993018e-05, "loss": 4.387, "step": 9120 }, { "epoch": 0.27858888210140503, "grad_norm": 0.37500596046447754, "learning_rate": 4.102083804040399e-05, "loss": 4.2959, "step": 9121 }, { "epoch": 0.2786194257788638, "grad_norm": 0.37006640434265137, "learning_rate": 4.1018996383365706e-05, "loss": 4.3015, "step": 9122 }, { "epoch": 0.27864996945632253, "grad_norm": 0.38423681259155273, "learning_rate": 4.101715457883228e-05, "loss": 4.2922, "step": 9123 }, { "epoch": 0.2786805131337813, "grad_norm": 0.38903969526290894, "learning_rate": 4.101531262682068e-05, "loss": 4.4357, "step": 9124 }, { "epoch": 0.2787110568112401, "grad_norm": 0.3856046497821808, "learning_rate": 4.101347052734787e-05, "loss": 4.3371, "step": 9125 }, { "epoch": 0.27874160048869884, "grad_norm": 0.37868332862854004, "learning_rate": 4.101162828043079e-05, "loss": 4.2991, "step": 9126 }, { "epoch": 0.2787721441661576, "grad_norm": 0.3809138238430023, "learning_rate": 4.1009785886086425e-05, "loss": 4.2297, "step": 9127 }, { "epoch": 0.2788026878436164, "grad_norm": 0.37737250328063965, "learning_rate": 4.100794334433172e-05, "loss": 4.3723, "step": 9128 }, { "epoch": 0.27883323152107514, "grad_norm": 0.3882783353328705, "learning_rate": 4.1006100655183665e-05, "loss": 4.3103, "step": 9129 }, { "epoch": 0.2788637751985339, "grad_norm": 0.3679334223270416, "learning_rate": 4.1004257818659206e-05, "loss": 4.3183, "step": 9130 }, { "epoch": 0.2788943188759927, "grad_norm": 0.3852643370628357, "learning_rate": 4.100241483477531e-05, "loss": 4.3057, "step": 9131 }, { "epoch": 0.27892486255345145, "grad_norm": 0.3899974226951599, "learning_rate": 4.100057170354896e-05, "loss": 4.3142, "step": 9132 }, { "epoch": 0.2789554062309102, "grad_norm": 0.38724344968795776, "learning_rate": 4.0998728424997115e-05, "loss": 4.2659, "step": 9133 }, { "epoch": 0.27898594990836895, "grad_norm": 0.3709093928337097, "learning_rate": 4.099688499913675e-05, "loss": 4.2201, "step": 9134 }, { "epoch": 0.27901649358582775, "grad_norm": 0.3752816319465637, "learning_rate": 4.099504142598485e-05, "loss": 4.2472, "step": 9135 }, { "epoch": 0.2790470372632865, "grad_norm": 0.3905070424079895, "learning_rate": 4.099319770555837e-05, "loss": 4.3347, "step": 9136 }, { "epoch": 0.27907758094074525, "grad_norm": 0.36369746923446655, "learning_rate": 4.0991353837874305e-05, "loss": 4.3244, "step": 9137 }, { "epoch": 0.27910812461820406, "grad_norm": 0.3798092007637024, "learning_rate": 4.098950982294962e-05, "loss": 4.3573, "step": 9138 }, { "epoch": 0.2791386682956628, "grad_norm": 0.3851829171180725, "learning_rate": 4.098766566080129e-05, "loss": 4.2868, "step": 9139 }, { "epoch": 0.27916921197312156, "grad_norm": 0.3744977116584778, "learning_rate": 4.098582135144631e-05, "loss": 4.3151, "step": 9140 }, { "epoch": 0.2791997556505803, "grad_norm": 0.3713647723197937, "learning_rate": 4.098397689490165e-05, "loss": 4.3399, "step": 9141 }, { "epoch": 0.2792302993280391, "grad_norm": 0.36979982256889343, "learning_rate": 4.09821322911843e-05, "loss": 4.3192, "step": 9142 }, { "epoch": 0.27926084300549786, "grad_norm": 0.37589165568351746, "learning_rate": 4.0980287540311234e-05, "loss": 4.3151, "step": 9143 }, { "epoch": 0.2792913866829566, "grad_norm": 0.3854902386665344, "learning_rate": 4.0978442642299455e-05, "loss": 4.3936, "step": 9144 }, { "epoch": 0.2793219303604154, "grad_norm": 0.3653302490711212, "learning_rate": 4.0976597597165934e-05, "loss": 4.3957, "step": 9145 }, { "epoch": 0.27935247403787417, "grad_norm": 0.3904730975627899, "learning_rate": 4.0974752404927666e-05, "loss": 4.3177, "step": 9146 }, { "epoch": 0.2793830177153329, "grad_norm": 0.39356914162635803, "learning_rate": 4.097290706560163e-05, "loss": 4.4058, "step": 9147 }, { "epoch": 0.27941356139279167, "grad_norm": 0.38179758191108704, "learning_rate": 4.097106157920484e-05, "loss": 4.3034, "step": 9148 }, { "epoch": 0.27944410507025047, "grad_norm": 0.37951287627220154, "learning_rate": 4.096921594575426e-05, "loss": 4.3186, "step": 9149 }, { "epoch": 0.2794746487477092, "grad_norm": 0.38339880108833313, "learning_rate": 4.096737016526691e-05, "loss": 4.4105, "step": 9150 }, { "epoch": 0.27950519242516797, "grad_norm": 0.3700897693634033, "learning_rate": 4.096552423775977e-05, "loss": 4.3467, "step": 9151 }, { "epoch": 0.2795357361026268, "grad_norm": 0.38016068935394287, "learning_rate": 4.0963678163249834e-05, "loss": 4.3629, "step": 9152 }, { "epoch": 0.2795662797800855, "grad_norm": 0.3735184669494629, "learning_rate": 4.096183194175412e-05, "loss": 4.3855, "step": 9153 }, { "epoch": 0.2795968234575443, "grad_norm": 0.37377360463142395, "learning_rate": 4.09599855732896e-05, "loss": 4.3803, "step": 9154 }, { "epoch": 0.2796273671350031, "grad_norm": 0.37345337867736816, "learning_rate": 4.0958139057873286e-05, "loss": 4.3103, "step": 9155 }, { "epoch": 0.27965791081246183, "grad_norm": 0.390403687953949, "learning_rate": 4.095629239552219e-05, "loss": 4.4083, "step": 9156 }, { "epoch": 0.2796884544899206, "grad_norm": 0.37680330872535706, "learning_rate": 4.09544455862533e-05, "loss": 4.3439, "step": 9157 }, { "epoch": 0.27971899816737933, "grad_norm": 0.38219472765922546, "learning_rate": 4.0952598630083624e-05, "loss": 4.4246, "step": 9158 }, { "epoch": 0.27974954184483813, "grad_norm": 0.3796100616455078, "learning_rate": 4.0950751527030175e-05, "loss": 4.3364, "step": 9159 }, { "epoch": 0.2797800855222969, "grad_norm": 0.3877556622028351, "learning_rate": 4.0948904277109954e-05, "loss": 4.3519, "step": 9160 }, { "epoch": 0.27981062919975563, "grad_norm": 0.3790649473667145, "learning_rate": 4.0947056880339976e-05, "loss": 4.3281, "step": 9161 }, { "epoch": 0.27984117287721444, "grad_norm": 0.3960990011692047, "learning_rate": 4.094520933673724e-05, "loss": 4.347, "step": 9162 }, { "epoch": 0.2798717165546732, "grad_norm": 0.365917444229126, "learning_rate": 4.0943361646318765e-05, "loss": 4.3093, "step": 9163 }, { "epoch": 0.27990226023213194, "grad_norm": 0.37348034977912903, "learning_rate": 4.094151380910156e-05, "loss": 4.3769, "step": 9164 }, { "epoch": 0.2799328039095907, "grad_norm": 0.3860335350036621, "learning_rate": 4.093966582510265e-05, "loss": 4.399, "step": 9165 }, { "epoch": 0.2799633475870495, "grad_norm": 0.37840214371681213, "learning_rate": 4.093781769433903e-05, "loss": 4.3568, "step": 9166 }, { "epoch": 0.27999389126450824, "grad_norm": 0.380524218082428, "learning_rate": 4.093596941682773e-05, "loss": 4.3436, "step": 9167 }, { "epoch": 0.280024434941967, "grad_norm": 0.38558733463287354, "learning_rate": 4.093412099258577e-05, "loss": 4.4096, "step": 9168 }, { "epoch": 0.2800549786194258, "grad_norm": 0.3762461245059967, "learning_rate": 4.0932272421630156e-05, "loss": 4.2364, "step": 9169 }, { "epoch": 0.28008552229688455, "grad_norm": 0.3745407164096832, "learning_rate": 4.093042370397793e-05, "loss": 4.3275, "step": 9170 }, { "epoch": 0.2801160659743433, "grad_norm": 0.3717701733112335, "learning_rate": 4.0928574839646104e-05, "loss": 4.0853, "step": 9171 }, { "epoch": 0.2801466096518021, "grad_norm": 0.40626153349876404, "learning_rate": 4.092672582865169e-05, "loss": 4.414, "step": 9172 }, { "epoch": 0.28017715332926085, "grad_norm": 0.37782686948776245, "learning_rate": 4.092487667101173e-05, "loss": 4.3317, "step": 9173 }, { "epoch": 0.2802076970067196, "grad_norm": 0.3782396614551544, "learning_rate": 4.092302736674324e-05, "loss": 4.2564, "step": 9174 }, { "epoch": 0.28023824068417835, "grad_norm": 0.3713034689426422, "learning_rate": 4.092117791586325e-05, "loss": 4.3354, "step": 9175 }, { "epoch": 0.28026878436163716, "grad_norm": 0.3900907337665558, "learning_rate": 4.0919328318388785e-05, "loss": 4.3337, "step": 9176 }, { "epoch": 0.2802993280390959, "grad_norm": 0.372063010931015, "learning_rate": 4.0917478574336886e-05, "loss": 4.3637, "step": 9177 }, { "epoch": 0.28032987171655466, "grad_norm": 0.3893425762653351, "learning_rate": 4.0915628683724577e-05, "loss": 4.2724, "step": 9178 }, { "epoch": 0.28036041539401346, "grad_norm": 0.3937656879425049, "learning_rate": 4.091377864656889e-05, "loss": 4.4274, "step": 9179 }, { "epoch": 0.2803909590714722, "grad_norm": 0.38064664602279663, "learning_rate": 4.0911928462886864e-05, "loss": 4.3937, "step": 9180 }, { "epoch": 0.28042150274893096, "grad_norm": 0.3737526834011078, "learning_rate": 4.091007813269553e-05, "loss": 4.2763, "step": 9181 }, { "epoch": 0.2804520464263897, "grad_norm": 0.37445592880249023, "learning_rate": 4.090822765601192e-05, "loss": 4.3132, "step": 9182 }, { "epoch": 0.2804825901038485, "grad_norm": 0.38000956177711487, "learning_rate": 4.090637703285308e-05, "loss": 4.313, "step": 9183 }, { "epoch": 0.28051313378130727, "grad_norm": 0.3804168999195099, "learning_rate": 4.090452626323605e-05, "loss": 4.4387, "step": 9184 }, { "epoch": 0.280543677458766, "grad_norm": 0.3953810930252075, "learning_rate": 4.0902675347177875e-05, "loss": 4.2476, "step": 9185 }, { "epoch": 0.2805742211362248, "grad_norm": 0.37445852160453796, "learning_rate": 4.090082428469559e-05, "loss": 4.3917, "step": 9186 }, { "epoch": 0.28060476481368357, "grad_norm": 0.3880477845668793, "learning_rate": 4.089897307580624e-05, "loss": 4.2995, "step": 9187 }, { "epoch": 0.2806353084911423, "grad_norm": 0.39646923542022705, "learning_rate": 4.089712172052687e-05, "loss": 4.3825, "step": 9188 }, { "epoch": 0.2806658521686011, "grad_norm": 0.38211289048194885, "learning_rate": 4.0895270218874526e-05, "loss": 4.2721, "step": 9189 }, { "epoch": 0.2806963958460599, "grad_norm": 0.37331995368003845, "learning_rate": 4.089341857086626e-05, "loss": 4.4369, "step": 9190 }, { "epoch": 0.2807269395235186, "grad_norm": 0.3928954601287842, "learning_rate": 4.089156677651911e-05, "loss": 4.3797, "step": 9191 }, { "epoch": 0.2807574832009774, "grad_norm": 0.4070569574832916, "learning_rate": 4.088971483585014e-05, "loss": 4.3925, "step": 9192 }, { "epoch": 0.2807880268784362, "grad_norm": 0.39798933267593384, "learning_rate": 4.088786274887639e-05, "loss": 4.3775, "step": 9193 }, { "epoch": 0.28081857055589493, "grad_norm": 0.3814595639705658, "learning_rate": 4.0886010515614924e-05, "loss": 4.4274, "step": 9194 }, { "epoch": 0.2808491142333537, "grad_norm": 0.38139107823371887, "learning_rate": 4.08841581360828e-05, "loss": 4.2517, "step": 9195 }, { "epoch": 0.2808796579108125, "grad_norm": 0.3966667354106903, "learning_rate": 4.0882305610297044e-05, "loss": 4.3604, "step": 9196 }, { "epoch": 0.28091020158827124, "grad_norm": 0.39982762932777405, "learning_rate": 4.088045293827475e-05, "loss": 4.4196, "step": 9197 }, { "epoch": 0.28094074526573, "grad_norm": 0.3803657591342926, "learning_rate": 4.087860012003296e-05, "loss": 4.2659, "step": 9198 }, { "epoch": 0.28097128894318874, "grad_norm": 0.3785025477409363, "learning_rate": 4.087674715558873e-05, "loss": 4.3298, "step": 9199 }, { "epoch": 0.28100183262064754, "grad_norm": 0.37396755814552307, "learning_rate": 4.087489404495912e-05, "loss": 4.335, "step": 9200 }, { "epoch": 0.2810323762981063, "grad_norm": 0.37346065044403076, "learning_rate": 4.087304078816121e-05, "loss": 4.3122, "step": 9201 }, { "epoch": 0.28106291997556504, "grad_norm": 0.3835063874721527, "learning_rate": 4.087118738521205e-05, "loss": 4.3863, "step": 9202 }, { "epoch": 0.28109346365302385, "grad_norm": 0.37680134177207947, "learning_rate": 4.08693338361287e-05, "loss": 4.336, "step": 9203 }, { "epoch": 0.2811240073304826, "grad_norm": 0.38938790559768677, "learning_rate": 4.086748014092825e-05, "loss": 4.3522, "step": 9204 }, { "epoch": 0.28115455100794134, "grad_norm": 0.3895485997200012, "learning_rate": 4.086562629962774e-05, "loss": 4.311, "step": 9205 }, { "epoch": 0.28118509468540015, "grad_norm": 0.3768469989299774, "learning_rate": 4.086377231224425e-05, "loss": 4.3839, "step": 9206 }, { "epoch": 0.2812156383628589, "grad_norm": 0.3803463876247406, "learning_rate": 4.086191817879486e-05, "loss": 4.3366, "step": 9207 }, { "epoch": 0.28124618204031765, "grad_norm": 0.37825652956962585, "learning_rate": 4.086006389929663e-05, "loss": 4.3778, "step": 9208 }, { "epoch": 0.2812767257177764, "grad_norm": 0.37945324182510376, "learning_rate": 4.085820947376664e-05, "loss": 4.3753, "step": 9209 }, { "epoch": 0.2813072693952352, "grad_norm": 0.3820759356021881, "learning_rate": 4.0856354902221946e-05, "loss": 4.3152, "step": 9210 }, { "epoch": 0.28133781307269395, "grad_norm": 0.3902844190597534, "learning_rate": 4.085450018467966e-05, "loss": 4.4328, "step": 9211 }, { "epoch": 0.2813683567501527, "grad_norm": 0.38987258076667786, "learning_rate": 4.085264532115684e-05, "loss": 4.2723, "step": 9212 }, { "epoch": 0.2813989004276115, "grad_norm": 0.39950478076934814, "learning_rate": 4.085079031167055e-05, "loss": 4.389, "step": 9213 }, { "epoch": 0.28142944410507026, "grad_norm": 0.3894566297531128, "learning_rate": 4.084893515623789e-05, "loss": 4.3448, "step": 9214 }, { "epoch": 0.281459987782529, "grad_norm": 0.38008809089660645, "learning_rate": 4.084707985487593e-05, "loss": 4.388, "step": 9215 }, { "epoch": 0.28149053145998776, "grad_norm": 0.3846989572048187, "learning_rate": 4.084522440760177e-05, "loss": 4.4271, "step": 9216 }, { "epoch": 0.28152107513744656, "grad_norm": 0.38649609684944153, "learning_rate": 4.084336881443247e-05, "loss": 4.3396, "step": 9217 }, { "epoch": 0.2815516188149053, "grad_norm": 0.38436222076416016, "learning_rate": 4.084151307538513e-05, "loss": 4.3537, "step": 9218 }, { "epoch": 0.28158216249236406, "grad_norm": 0.3710196316242218, "learning_rate": 4.0839657190476836e-05, "loss": 4.3603, "step": 9219 }, { "epoch": 0.28161270616982287, "grad_norm": 0.3803540766239166, "learning_rate": 4.083780115972468e-05, "loss": 4.4003, "step": 9220 }, { "epoch": 0.2816432498472816, "grad_norm": 0.3710896074771881, "learning_rate": 4.0835944983145735e-05, "loss": 4.4281, "step": 9221 }, { "epoch": 0.28167379352474037, "grad_norm": 0.385799378156662, "learning_rate": 4.083408866075711e-05, "loss": 4.3802, "step": 9222 }, { "epoch": 0.2817043372021991, "grad_norm": 0.39346903562545776, "learning_rate": 4.0832232192575894e-05, "loss": 4.2559, "step": 9223 }, { "epoch": 0.2817348808796579, "grad_norm": 0.3711031377315521, "learning_rate": 4.083037557861916e-05, "loss": 4.3133, "step": 9224 }, { "epoch": 0.2817654245571167, "grad_norm": 0.38532206416130066, "learning_rate": 4.082851881890404e-05, "loss": 4.3944, "step": 9225 }, { "epoch": 0.2817959682345754, "grad_norm": 0.37947142124176025, "learning_rate": 4.0826661913447594e-05, "loss": 4.3336, "step": 9226 }, { "epoch": 0.2818265119120342, "grad_norm": 0.37281137704849243, "learning_rate": 4.082480486226693e-05, "loss": 4.2733, "step": 9227 }, { "epoch": 0.281857055589493, "grad_norm": 0.39582109451293945, "learning_rate": 4.082294766537916e-05, "loss": 4.2685, "step": 9228 }, { "epoch": 0.2818875992669517, "grad_norm": 0.3925245702266693, "learning_rate": 4.0821090322801384e-05, "loss": 4.334, "step": 9229 }, { "epoch": 0.28191814294441053, "grad_norm": 0.37102535367012024, "learning_rate": 4.081923283455068e-05, "loss": 4.369, "step": 9230 }, { "epoch": 0.2819486866218693, "grad_norm": 0.369791716337204, "learning_rate": 4.081737520064417e-05, "loss": 4.4396, "step": 9231 }, { "epoch": 0.28197923029932803, "grad_norm": 0.3798595070838928, "learning_rate": 4.0815517421098956e-05, "loss": 4.3822, "step": 9232 }, { "epoch": 0.2820097739767868, "grad_norm": 0.3838631808757782, "learning_rate": 4.0813659495932146e-05, "loss": 4.3481, "step": 9233 }, { "epoch": 0.2820403176542456, "grad_norm": 0.3739463984966278, "learning_rate": 4.081180142516083e-05, "loss": 4.3275, "step": 9234 }, { "epoch": 0.28207086133170434, "grad_norm": 0.3738369345664978, "learning_rate": 4.080994320880214e-05, "loss": 4.225, "step": 9235 }, { "epoch": 0.2821014050091631, "grad_norm": 0.367460161447525, "learning_rate": 4.080808484687317e-05, "loss": 4.3639, "step": 9236 }, { "epoch": 0.2821319486866219, "grad_norm": 0.3855478763580322, "learning_rate": 4.080622633939104e-05, "loss": 4.3877, "step": 9237 }, { "epoch": 0.28216249236408064, "grad_norm": 0.3737527132034302, "learning_rate": 4.0804367686372855e-05, "loss": 4.3341, "step": 9238 }, { "epoch": 0.2821930360415394, "grad_norm": 0.38140740990638733, "learning_rate": 4.080250888783573e-05, "loss": 4.3581, "step": 9239 }, { "epoch": 0.28222357971899814, "grad_norm": 0.40659433603286743, "learning_rate": 4.0800649943796776e-05, "loss": 4.3459, "step": 9240 }, { "epoch": 0.28225412339645695, "grad_norm": 0.3766627311706543, "learning_rate": 4.079879085427312e-05, "loss": 4.3589, "step": 9241 }, { "epoch": 0.2822846670739157, "grad_norm": 0.37130245566368103, "learning_rate": 4.0796931619281875e-05, "loss": 4.3036, "step": 9242 }, { "epoch": 0.28231521075137445, "grad_norm": 0.38657864928245544, "learning_rate": 4.079507223884015e-05, "loss": 4.3161, "step": 9243 }, { "epoch": 0.28234575442883325, "grad_norm": 0.37529051303863525, "learning_rate": 4.079321271296508e-05, "loss": 4.34, "step": 9244 }, { "epoch": 0.282376298106292, "grad_norm": 0.39322537183761597, "learning_rate": 4.0791353041673786e-05, "loss": 4.2972, "step": 9245 }, { "epoch": 0.28240684178375075, "grad_norm": 0.3816508650779724, "learning_rate": 4.0789493224983376e-05, "loss": 4.438, "step": 9246 }, { "epoch": 0.28243738546120956, "grad_norm": 0.3835759162902832, "learning_rate": 4.078763326291098e-05, "loss": 4.3099, "step": 9247 }, { "epoch": 0.2824679291386683, "grad_norm": 0.38223960995674133, "learning_rate": 4.0785773155473736e-05, "loss": 4.4034, "step": 9248 }, { "epoch": 0.28249847281612706, "grad_norm": 0.39212945103645325, "learning_rate": 4.0783912902688765e-05, "loss": 4.3497, "step": 9249 }, { "epoch": 0.2825290164935858, "grad_norm": 0.3753974437713623, "learning_rate": 4.078205250457319e-05, "loss": 4.4031, "step": 9250 }, { "epoch": 0.2825595601710446, "grad_norm": 0.37910196185112, "learning_rate": 4.0780191961144143e-05, "loss": 4.2805, "step": 9251 }, { "epoch": 0.28259010384850336, "grad_norm": 0.38175109028816223, "learning_rate": 4.077833127241875e-05, "loss": 4.3486, "step": 9252 }, { "epoch": 0.2826206475259621, "grad_norm": 0.38284435868263245, "learning_rate": 4.0776470438414146e-05, "loss": 4.3628, "step": 9253 }, { "epoch": 0.2826511912034209, "grad_norm": 0.3883930444717407, "learning_rate": 4.0774609459147476e-05, "loss": 4.3971, "step": 9254 }, { "epoch": 0.28268173488087966, "grad_norm": 0.3967059850692749, "learning_rate": 4.077274833463587e-05, "loss": 4.3362, "step": 9255 }, { "epoch": 0.2827122785583384, "grad_norm": 0.3752882778644562, "learning_rate": 4.077088706489645e-05, "loss": 4.3521, "step": 9256 }, { "epoch": 0.28274282223579716, "grad_norm": 0.368984192609787, "learning_rate": 4.076902564994637e-05, "loss": 4.3662, "step": 9257 }, { "epoch": 0.28277336591325597, "grad_norm": 0.3862445056438446, "learning_rate": 4.076716408980276e-05, "loss": 4.3578, "step": 9258 }, { "epoch": 0.2828039095907147, "grad_norm": 0.3854330778121948, "learning_rate": 4.076530238448276e-05, "loss": 4.2392, "step": 9259 }, { "epoch": 0.28283445326817347, "grad_norm": 0.3951733708381653, "learning_rate": 4.0763440534003525e-05, "loss": 4.3268, "step": 9260 }, { "epoch": 0.2828649969456323, "grad_norm": 0.3680588901042938, "learning_rate": 4.0761578538382184e-05, "loss": 4.3869, "step": 9261 }, { "epoch": 0.282895540623091, "grad_norm": 0.3733896315097809, "learning_rate": 4.075971639763588e-05, "loss": 4.3765, "step": 9262 }, { "epoch": 0.2829260843005498, "grad_norm": 0.3884017765522003, "learning_rate": 4.075785411178178e-05, "loss": 4.3782, "step": 9263 }, { "epoch": 0.2829566279780086, "grad_norm": 0.3765377402305603, "learning_rate": 4.0755991680837e-05, "loss": 4.3149, "step": 9264 }, { "epoch": 0.28298717165546733, "grad_norm": 0.38389334082603455, "learning_rate": 4.0754129104818704e-05, "loss": 4.3616, "step": 9265 }, { "epoch": 0.2830177153329261, "grad_norm": 0.3957889974117279, "learning_rate": 4.0752266383744055e-05, "loss": 4.4263, "step": 9266 }, { "epoch": 0.28304825901038483, "grad_norm": 0.3817996084690094, "learning_rate": 4.075040351763017e-05, "loss": 4.2732, "step": 9267 }, { "epoch": 0.28307880268784363, "grad_norm": 0.378639817237854, "learning_rate": 4.0748540506494234e-05, "loss": 4.2506, "step": 9268 }, { "epoch": 0.2831093463653024, "grad_norm": 0.39639905095100403, "learning_rate": 4.074667735035339e-05, "loss": 4.3169, "step": 9269 }, { "epoch": 0.28313989004276113, "grad_norm": 0.3748275339603424, "learning_rate": 4.074481404922479e-05, "loss": 4.412, "step": 9270 }, { "epoch": 0.28317043372021994, "grad_norm": 0.38003087043762207, "learning_rate": 4.07429506031256e-05, "loss": 4.3706, "step": 9271 }, { "epoch": 0.2832009773976787, "grad_norm": 0.3677970767021179, "learning_rate": 4.074108701207296e-05, "loss": 4.3218, "step": 9272 }, { "epoch": 0.28323152107513744, "grad_norm": 0.39523249864578247, "learning_rate": 4.073922327608404e-05, "loss": 4.3344, "step": 9273 }, { "epoch": 0.2832620647525962, "grad_norm": 0.37586116790771484, "learning_rate": 4.0737359395175986e-05, "loss": 4.2758, "step": 9274 }, { "epoch": 0.283292608430055, "grad_norm": 0.37177541851997375, "learning_rate": 4.073549536936599e-05, "loss": 4.3384, "step": 9275 }, { "epoch": 0.28332315210751374, "grad_norm": 0.3637706935405731, "learning_rate": 4.0733631198671196e-05, "loss": 4.3397, "step": 9276 }, { "epoch": 0.2833536957849725, "grad_norm": 0.3722606599330902, "learning_rate": 4.073176688310877e-05, "loss": 4.3786, "step": 9277 }, { "epoch": 0.2833842394624313, "grad_norm": 0.3642060160636902, "learning_rate": 4.0729902422695865e-05, "loss": 4.3432, "step": 9278 }, { "epoch": 0.28341478313989005, "grad_norm": 0.36757412552833557, "learning_rate": 4.072803781744967e-05, "loss": 4.3285, "step": 9279 }, { "epoch": 0.2834453268173488, "grad_norm": 0.37622562050819397, "learning_rate": 4.0726173067387355e-05, "loss": 4.3472, "step": 9280 }, { "epoch": 0.2834758704948076, "grad_norm": 0.36977314949035645, "learning_rate": 4.072430817252606e-05, "loss": 4.3516, "step": 9281 }, { "epoch": 0.28350641417226635, "grad_norm": 0.37285366654396057, "learning_rate": 4.072244313288298e-05, "loss": 4.3807, "step": 9282 }, { "epoch": 0.2835369578497251, "grad_norm": 0.3730317950248718, "learning_rate": 4.072057794847529e-05, "loss": 4.3897, "step": 9283 }, { "epoch": 0.28356750152718385, "grad_norm": 0.3783912658691406, "learning_rate": 4.0718712619320153e-05, "loss": 4.204, "step": 9284 }, { "epoch": 0.28359804520464266, "grad_norm": 0.37659522891044617, "learning_rate": 4.071684714543474e-05, "loss": 4.3746, "step": 9285 }, { "epoch": 0.2836285888821014, "grad_norm": 0.37902432680130005, "learning_rate": 4.071498152683625e-05, "loss": 4.2436, "step": 9286 }, { "epoch": 0.28365913255956016, "grad_norm": 0.3827705979347229, "learning_rate": 4.0713115763541834e-05, "loss": 4.3825, "step": 9287 }, { "epoch": 0.28368967623701896, "grad_norm": 0.38842475414276123, "learning_rate": 4.071124985556868e-05, "loss": 4.3549, "step": 9288 }, { "epoch": 0.2837202199144777, "grad_norm": 0.3777303099632263, "learning_rate": 4.070938380293397e-05, "loss": 4.3461, "step": 9289 }, { "epoch": 0.28375076359193646, "grad_norm": 0.3793317377567291, "learning_rate": 4.07075176056549e-05, "loss": 4.3751, "step": 9290 }, { "epoch": 0.2837813072693952, "grad_norm": 0.38226577639579773, "learning_rate": 4.070565126374863e-05, "loss": 4.3055, "step": 9291 }, { "epoch": 0.283811850946854, "grad_norm": 0.377689927816391, "learning_rate": 4.0703784777232355e-05, "loss": 4.3098, "step": 9292 }, { "epoch": 0.28384239462431277, "grad_norm": 0.36831575632095337, "learning_rate": 4.070191814612326e-05, "loss": 4.2937, "step": 9293 }, { "epoch": 0.2838729383017715, "grad_norm": 0.37630900740623474, "learning_rate": 4.070005137043853e-05, "loss": 4.3267, "step": 9294 }, { "epoch": 0.2839034819792303, "grad_norm": 0.3799389898777008, "learning_rate": 4.0698184450195354e-05, "loss": 4.2645, "step": 9295 }, { "epoch": 0.28393402565668907, "grad_norm": 0.3763970732688904, "learning_rate": 4.069631738541092e-05, "loss": 4.4024, "step": 9296 }, { "epoch": 0.2839645693341478, "grad_norm": 0.3739558458328247, "learning_rate": 4.069445017610243e-05, "loss": 4.4161, "step": 9297 }, { "epoch": 0.28399511301160657, "grad_norm": 0.37093815207481384, "learning_rate": 4.0692582822287064e-05, "loss": 4.2779, "step": 9298 }, { "epoch": 0.2840256566890654, "grad_norm": 0.38473108410835266, "learning_rate": 4.069071532398202e-05, "loss": 4.2923, "step": 9299 }, { "epoch": 0.2840562003665241, "grad_norm": 0.37871110439300537, "learning_rate": 4.068884768120449e-05, "loss": 4.3021, "step": 9300 }, { "epoch": 0.2840867440439829, "grad_norm": 0.3793526291847229, "learning_rate": 4.068697989397168e-05, "loss": 4.4187, "step": 9301 }, { "epoch": 0.2841172877214417, "grad_norm": 0.3694527745246887, "learning_rate": 4.068511196230077e-05, "loss": 4.3316, "step": 9302 }, { "epoch": 0.28414783139890043, "grad_norm": 0.3778304159641266, "learning_rate": 4.0683243886208975e-05, "loss": 4.2724, "step": 9303 }, { "epoch": 0.2841783750763592, "grad_norm": 0.3919622004032135, "learning_rate": 4.068137566571349e-05, "loss": 4.3352, "step": 9304 }, { "epoch": 0.284208918753818, "grad_norm": 0.3887127935886383, "learning_rate": 4.067950730083151e-05, "loss": 4.4029, "step": 9305 }, { "epoch": 0.28423946243127673, "grad_norm": 0.3754628896713257, "learning_rate": 4.067763879158026e-05, "loss": 4.3413, "step": 9306 }, { "epoch": 0.2842700061087355, "grad_norm": 0.3924931585788727, "learning_rate": 4.067577013797692e-05, "loss": 4.3255, "step": 9307 }, { "epoch": 0.28430054978619423, "grad_norm": 0.38518229126930237, "learning_rate": 4.06739013400387e-05, "loss": 4.3158, "step": 9308 }, { "epoch": 0.28433109346365304, "grad_norm": 0.3779066503047943, "learning_rate": 4.0672032397782814e-05, "loss": 4.3955, "step": 9309 }, { "epoch": 0.2843616371411118, "grad_norm": 0.3712374269962311, "learning_rate": 4.0670163311226476e-05, "loss": 4.4567, "step": 9310 }, { "epoch": 0.28439218081857054, "grad_norm": 0.3852667212486267, "learning_rate": 4.0668294080386884e-05, "loss": 4.3037, "step": 9311 }, { "epoch": 0.28442272449602934, "grad_norm": 0.3969469666481018, "learning_rate": 4.0666424705281245e-05, "loss": 4.3058, "step": 9312 }, { "epoch": 0.2844532681734881, "grad_norm": 0.3712579309940338, "learning_rate": 4.066455518592679e-05, "loss": 4.3721, "step": 9313 }, { "epoch": 0.28448381185094684, "grad_norm": 0.3647131025791168, "learning_rate": 4.0662685522340714e-05, "loss": 4.2884, "step": 9314 }, { "epoch": 0.2845143555284056, "grad_norm": 0.3724605441093445, "learning_rate": 4.0660815714540247e-05, "loss": 4.3379, "step": 9315 }, { "epoch": 0.2845448992058644, "grad_norm": 0.37108147144317627, "learning_rate": 4.065894576254259e-05, "loss": 4.3479, "step": 9316 }, { "epoch": 0.28457544288332315, "grad_norm": 0.37082672119140625, "learning_rate": 4.0657075666364966e-05, "loss": 4.3073, "step": 9317 }, { "epoch": 0.2846059865607819, "grad_norm": 0.3702670931816101, "learning_rate": 4.06552054260246e-05, "loss": 4.323, "step": 9318 }, { "epoch": 0.2846365302382407, "grad_norm": 0.37402796745300293, "learning_rate": 4.065333504153871e-05, "loss": 4.3643, "step": 9319 }, { "epoch": 0.28466707391569945, "grad_norm": 0.37171149253845215, "learning_rate": 4.065146451292452e-05, "loss": 4.3448, "step": 9320 }, { "epoch": 0.2846976175931582, "grad_norm": 0.37749043107032776, "learning_rate": 4.064959384019924e-05, "loss": 4.4, "step": 9321 }, { "epoch": 0.284728161270617, "grad_norm": 0.3692066967487335, "learning_rate": 4.0647723023380105e-05, "loss": 4.3283, "step": 9322 }, { "epoch": 0.28475870494807576, "grad_norm": 0.37585780024528503, "learning_rate": 4.0645852062484345e-05, "loss": 4.3614, "step": 9323 }, { "epoch": 0.2847892486255345, "grad_norm": 0.3712768852710724, "learning_rate": 4.064398095752918e-05, "loss": 4.374, "step": 9324 }, { "epoch": 0.28481979230299326, "grad_norm": 0.36496853828430176, "learning_rate": 4.064210970853184e-05, "loss": 4.3473, "step": 9325 }, { "epoch": 0.28485033598045206, "grad_norm": 0.36385950446128845, "learning_rate": 4.064023831550954e-05, "loss": 4.3758, "step": 9326 }, { "epoch": 0.2848808796579108, "grad_norm": 0.38611701130867004, "learning_rate": 4.063836677847954e-05, "loss": 4.4112, "step": 9327 }, { "epoch": 0.28491142333536956, "grad_norm": 0.3744564354419708, "learning_rate": 4.063649509745905e-05, "loss": 4.3736, "step": 9328 }, { "epoch": 0.28494196701282837, "grad_norm": 0.3776489198207855, "learning_rate": 4.0634623272465314e-05, "loss": 4.3346, "step": 9329 }, { "epoch": 0.2849725106902871, "grad_norm": 0.3826882541179657, "learning_rate": 4.063275130351556e-05, "loss": 4.3884, "step": 9330 }, { "epoch": 0.28500305436774587, "grad_norm": 0.38540297746658325, "learning_rate": 4.063087919062702e-05, "loss": 4.3284, "step": 9331 }, { "epoch": 0.2850335980452046, "grad_norm": 0.3725733458995819, "learning_rate": 4.062900693381695e-05, "loss": 4.3314, "step": 9332 }, { "epoch": 0.2850641417226634, "grad_norm": 0.3776695430278778, "learning_rate": 4.0627134533102577e-05, "loss": 4.3596, "step": 9333 }, { "epoch": 0.28509468540012217, "grad_norm": 0.3741585612297058, "learning_rate": 4.062526198850114e-05, "loss": 4.332, "step": 9334 }, { "epoch": 0.2851252290775809, "grad_norm": 0.3659586012363434, "learning_rate": 4.0623389300029876e-05, "loss": 4.3626, "step": 9335 }, { "epoch": 0.2851557727550397, "grad_norm": 0.3894880712032318, "learning_rate": 4.0621516467706034e-05, "loss": 4.2086, "step": 9336 }, { "epoch": 0.2851863164324985, "grad_norm": 0.39590853452682495, "learning_rate": 4.0619643491546864e-05, "loss": 4.3456, "step": 9337 }, { "epoch": 0.2852168601099572, "grad_norm": 0.3772444427013397, "learning_rate": 4.061777037156961e-05, "loss": 4.3774, "step": 9338 }, { "epoch": 0.28524740378741603, "grad_norm": 0.38144373893737793, "learning_rate": 4.06158971077915e-05, "loss": 4.3571, "step": 9339 }, { "epoch": 0.2852779474648748, "grad_norm": 0.37690719962120056, "learning_rate": 4.061402370022981e-05, "loss": 4.3653, "step": 9340 }, { "epoch": 0.28530849114233353, "grad_norm": 0.37805676460266113, "learning_rate": 4.061215014890177e-05, "loss": 4.3108, "step": 9341 }, { "epoch": 0.2853390348197923, "grad_norm": 0.3929198086261749, "learning_rate": 4.0610276453824635e-05, "loss": 4.3708, "step": 9342 }, { "epoch": 0.2853695784972511, "grad_norm": 0.36725980043411255, "learning_rate": 4.060840261501566e-05, "loss": 4.3696, "step": 9343 }, { "epoch": 0.28540012217470984, "grad_norm": 0.3759170174598694, "learning_rate": 4.06065286324921e-05, "loss": 4.3662, "step": 9344 }, { "epoch": 0.2854306658521686, "grad_norm": 0.3780410885810852, "learning_rate": 4.060465450627121e-05, "loss": 4.2526, "step": 9345 }, { "epoch": 0.2854612095296274, "grad_norm": 0.387675404548645, "learning_rate": 4.060278023637023e-05, "loss": 4.3739, "step": 9346 }, { "epoch": 0.28549175320708614, "grad_norm": 0.3882080018520355, "learning_rate": 4.060090582280644e-05, "loss": 4.3324, "step": 9347 }, { "epoch": 0.2855222968845449, "grad_norm": 0.39349907636642456, "learning_rate": 4.059903126559709e-05, "loss": 4.3748, "step": 9348 }, { "epoch": 0.28555284056200364, "grad_norm": 0.36571115255355835, "learning_rate": 4.059715656475944e-05, "loss": 4.327, "step": 9349 }, { "epoch": 0.28558338423946245, "grad_norm": 0.384804904460907, "learning_rate": 4.059528172031074e-05, "loss": 4.3819, "step": 9350 }, { "epoch": 0.2856139279169212, "grad_norm": 0.38383522629737854, "learning_rate": 4.059340673226827e-05, "loss": 4.3502, "step": 9351 }, { "epoch": 0.28564447159437995, "grad_norm": 0.3848511576652527, "learning_rate": 4.059153160064929e-05, "loss": 4.428, "step": 9352 }, { "epoch": 0.28567501527183875, "grad_norm": 0.37602999806404114, "learning_rate": 4.058965632547105e-05, "loss": 4.3481, "step": 9353 }, { "epoch": 0.2857055589492975, "grad_norm": 0.3795161843299866, "learning_rate": 4.058778090675084e-05, "loss": 4.2593, "step": 9354 }, { "epoch": 0.28573610262675625, "grad_norm": 0.393824964761734, "learning_rate": 4.058590534450591e-05, "loss": 4.3305, "step": 9355 }, { "epoch": 0.28576664630421506, "grad_norm": 0.3953612744808197, "learning_rate": 4.058402963875354e-05, "loss": 4.4079, "step": 9356 }, { "epoch": 0.2857971899816738, "grad_norm": 0.37932878732681274, "learning_rate": 4.0582153789511005e-05, "loss": 4.4188, "step": 9357 }, { "epoch": 0.28582773365913255, "grad_norm": 0.3887954354286194, "learning_rate": 4.058027779679555e-05, "loss": 4.4225, "step": 9358 }, { "epoch": 0.2858582773365913, "grad_norm": 0.3748892843723297, "learning_rate": 4.0578401660624476e-05, "loss": 4.4228, "step": 9359 }, { "epoch": 0.2858888210140501, "grad_norm": 0.37528863549232483, "learning_rate": 4.057652538101505e-05, "loss": 4.361, "step": 9360 }, { "epoch": 0.28591936469150886, "grad_norm": 0.3906351923942566, "learning_rate": 4.057464895798455e-05, "loss": 4.311, "step": 9361 }, { "epoch": 0.2859499083689676, "grad_norm": 0.3924412131309509, "learning_rate": 4.057277239155024e-05, "loss": 4.3648, "step": 9362 }, { "epoch": 0.2859804520464264, "grad_norm": 0.37765422463417053, "learning_rate": 4.057089568172941e-05, "loss": 4.409, "step": 9363 }, { "epoch": 0.28601099572388516, "grad_norm": 0.3746543228626251, "learning_rate": 4.056901882853934e-05, "loss": 4.4608, "step": 9364 }, { "epoch": 0.2860415394013439, "grad_norm": 0.3821300268173218, "learning_rate": 4.056714183199731e-05, "loss": 4.3815, "step": 9365 }, { "epoch": 0.28607208307880266, "grad_norm": 0.42265602946281433, "learning_rate": 4.05652646921206e-05, "loss": 4.3541, "step": 9366 }, { "epoch": 0.28610262675626147, "grad_norm": 0.3682973086833954, "learning_rate": 4.056338740892649e-05, "loss": 4.354, "step": 9367 }, { "epoch": 0.2861331704337202, "grad_norm": 0.38457122445106506, "learning_rate": 4.0561509982432274e-05, "loss": 4.3788, "step": 9368 }, { "epoch": 0.28616371411117897, "grad_norm": 0.38430336117744446, "learning_rate": 4.055963241265524e-05, "loss": 4.282, "step": 9369 }, { "epoch": 0.2861942577886378, "grad_norm": 0.3738933503627777, "learning_rate": 4.0557754699612664e-05, "loss": 4.4607, "step": 9370 }, { "epoch": 0.2862248014660965, "grad_norm": 0.37295809388160706, "learning_rate": 4.055587684332185e-05, "loss": 4.3942, "step": 9371 }, { "epoch": 0.2862553451435553, "grad_norm": 0.37939321994781494, "learning_rate": 4.0553998843800066e-05, "loss": 4.4159, "step": 9372 }, { "epoch": 0.286285888821014, "grad_norm": 0.3635539412498474, "learning_rate": 4.0552120701064636e-05, "loss": 4.3155, "step": 9373 }, { "epoch": 0.28631643249847283, "grad_norm": 0.3843502402305603, "learning_rate": 4.055024241513282e-05, "loss": 4.3641, "step": 9374 }, { "epoch": 0.2863469761759316, "grad_norm": 0.3742418885231018, "learning_rate": 4.054836398602193e-05, "loss": 4.3711, "step": 9375 }, { "epoch": 0.2863775198533903, "grad_norm": 0.397505521774292, "learning_rate": 4.0546485413749257e-05, "loss": 4.3456, "step": 9376 }, { "epoch": 0.28640806353084913, "grad_norm": 0.37515008449554443, "learning_rate": 4.05446066983321e-05, "loss": 4.3898, "step": 9377 }, { "epoch": 0.2864386072083079, "grad_norm": 0.38469478487968445, "learning_rate": 4.054272783978777e-05, "loss": 4.3836, "step": 9378 }, { "epoch": 0.28646915088576663, "grad_norm": 0.3866010904312134, "learning_rate": 4.054084883813353e-05, "loss": 4.2939, "step": 9379 }, { "epoch": 0.28649969456322544, "grad_norm": 0.3713730275630951, "learning_rate": 4.053896969338672e-05, "loss": 4.3555, "step": 9380 }, { "epoch": 0.2865302382406842, "grad_norm": 0.37713125348091125, "learning_rate": 4.053709040556463e-05, "loss": 4.2675, "step": 9381 }, { "epoch": 0.28656078191814294, "grad_norm": 0.39055898785591125, "learning_rate": 4.0535210974684545e-05, "loss": 4.4578, "step": 9382 }, { "epoch": 0.2865913255956017, "grad_norm": 0.38788726925849915, "learning_rate": 4.05333314007638e-05, "loss": 4.2953, "step": 9383 }, { "epoch": 0.2866218692730605, "grad_norm": 0.38603898882865906, "learning_rate": 4.0531451683819675e-05, "loss": 4.3934, "step": 9384 }, { "epoch": 0.28665241295051924, "grad_norm": 0.38010546565055847, "learning_rate": 4.0529571823869496e-05, "loss": 4.3356, "step": 9385 }, { "epoch": 0.286682956627978, "grad_norm": 0.3617893159389496, "learning_rate": 4.052769182093056e-05, "loss": 4.3608, "step": 9386 }, { "epoch": 0.2867135003054368, "grad_norm": 0.37502509355545044, "learning_rate": 4.052581167502019e-05, "loss": 4.3435, "step": 9387 }, { "epoch": 0.28674404398289555, "grad_norm": 0.38499799370765686, "learning_rate": 4.052393138615568e-05, "loss": 4.4069, "step": 9388 }, { "epoch": 0.2867745876603543, "grad_norm": 0.37836122512817383, "learning_rate": 4.052205095435436e-05, "loss": 4.2972, "step": 9389 }, { "epoch": 0.28680513133781305, "grad_norm": 0.38470765948295593, "learning_rate": 4.052017037963353e-05, "loss": 4.3294, "step": 9390 }, { "epoch": 0.28683567501527185, "grad_norm": 0.383660227060318, "learning_rate": 4.051828966201051e-05, "loss": 4.3558, "step": 9391 }, { "epoch": 0.2868662186927306, "grad_norm": 0.3764565885066986, "learning_rate": 4.051640880150263e-05, "loss": 4.3017, "step": 9392 }, { "epoch": 0.28689676237018935, "grad_norm": 0.37970417737960815, "learning_rate": 4.051452779812718e-05, "loss": 4.2996, "step": 9393 }, { "epoch": 0.28692730604764816, "grad_norm": 0.378829687833786, "learning_rate": 4.05126466519015e-05, "loss": 4.3574, "step": 9394 }, { "epoch": 0.2869578497251069, "grad_norm": 0.37051528692245483, "learning_rate": 4.051076536284292e-05, "loss": 4.3578, "step": 9395 }, { "epoch": 0.28698839340256566, "grad_norm": 0.38049885630607605, "learning_rate": 4.050888393096873e-05, "loss": 4.3186, "step": 9396 }, { "epoch": 0.28701893708002446, "grad_norm": 0.3820972740650177, "learning_rate": 4.050700235629629e-05, "loss": 4.4065, "step": 9397 }, { "epoch": 0.2870494807574832, "grad_norm": 0.38005486130714417, "learning_rate": 4.0505120638842895e-05, "loss": 4.3192, "step": 9398 }, { "epoch": 0.28708002443494196, "grad_norm": 0.3755459785461426, "learning_rate": 4.050323877862589e-05, "loss": 4.429, "step": 9399 }, { "epoch": 0.2871105681124007, "grad_norm": 0.36453869938850403, "learning_rate": 4.0501356775662586e-05, "loss": 4.3635, "step": 9400 }, { "epoch": 0.2871411117898595, "grad_norm": 0.37354475259780884, "learning_rate": 4.049947462997032e-05, "loss": 4.4187, "step": 9401 }, { "epoch": 0.28717165546731827, "grad_norm": 0.3730901777744293, "learning_rate": 4.0497592341566424e-05, "loss": 4.3214, "step": 9402 }, { "epoch": 0.287202199144777, "grad_norm": 0.3826301395893097, "learning_rate": 4.049570991046823e-05, "loss": 4.3574, "step": 9403 }, { "epoch": 0.2872327428222358, "grad_norm": 0.37846747040748596, "learning_rate": 4.049382733669307e-05, "loss": 4.3832, "step": 9404 }, { "epoch": 0.28726328649969457, "grad_norm": 0.3719896972179413, "learning_rate": 4.049194462025827e-05, "loss": 4.3809, "step": 9405 }, { "epoch": 0.2872938301771533, "grad_norm": 0.3766058385372162, "learning_rate": 4.049006176118118e-05, "loss": 4.3229, "step": 9406 }, { "epoch": 0.28732437385461207, "grad_norm": 0.37502071261405945, "learning_rate": 4.048817875947911e-05, "loss": 4.3492, "step": 9407 }, { "epoch": 0.2873549175320709, "grad_norm": 0.3824225068092346, "learning_rate": 4.0486295615169427e-05, "loss": 4.4068, "step": 9408 }, { "epoch": 0.2873854612095296, "grad_norm": 0.3635256588459015, "learning_rate": 4.048441232826946e-05, "loss": 4.3738, "step": 9409 }, { "epoch": 0.2874160048869884, "grad_norm": 0.37913668155670166, "learning_rate": 4.048252889879655e-05, "loss": 4.4022, "step": 9410 }, { "epoch": 0.2874465485644472, "grad_norm": 0.3816557824611664, "learning_rate": 4.048064532676802e-05, "loss": 4.3035, "step": 9411 }, { "epoch": 0.28747709224190593, "grad_norm": 0.3859657347202301, "learning_rate": 4.047876161220124e-05, "loss": 4.4378, "step": 9412 }, { "epoch": 0.2875076359193647, "grad_norm": 0.3643015921115875, "learning_rate": 4.047687775511354e-05, "loss": 4.3016, "step": 9413 }, { "epoch": 0.2875381795968235, "grad_norm": 0.3804222643375397, "learning_rate": 4.0474993755522274e-05, "loss": 4.3178, "step": 9414 }, { "epoch": 0.28756872327428223, "grad_norm": 0.3741113245487213, "learning_rate": 4.0473109613444776e-05, "loss": 4.3824, "step": 9415 }, { "epoch": 0.287599266951741, "grad_norm": 0.38949036598205566, "learning_rate": 4.047122532889841e-05, "loss": 4.2963, "step": 9416 }, { "epoch": 0.28762981062919973, "grad_norm": 0.3839455842971802, "learning_rate": 4.046934090190052e-05, "loss": 4.4233, "step": 9417 }, { "epoch": 0.28766035430665854, "grad_norm": 0.3837294280529022, "learning_rate": 4.0467456332468446e-05, "loss": 4.3452, "step": 9418 }, { "epoch": 0.2876908979841173, "grad_norm": 0.37329137325286865, "learning_rate": 4.046557162061955e-05, "loss": 4.3558, "step": 9419 }, { "epoch": 0.28772144166157604, "grad_norm": 0.37283387780189514, "learning_rate": 4.046368676637119e-05, "loss": 4.3629, "step": 9420 }, { "epoch": 0.28775198533903484, "grad_norm": 0.37750086188316345, "learning_rate": 4.046180176974071e-05, "loss": 4.28, "step": 9421 }, { "epoch": 0.2877825290164936, "grad_norm": 0.38071513175964355, "learning_rate": 4.0459916630745475e-05, "loss": 4.3225, "step": 9422 }, { "epoch": 0.28781307269395234, "grad_norm": 0.38728803396224976, "learning_rate": 4.0458031349402835e-05, "loss": 4.3274, "step": 9423 }, { "epoch": 0.2878436163714111, "grad_norm": 0.38409554958343506, "learning_rate": 4.045614592573016e-05, "loss": 4.3787, "step": 9424 }, { "epoch": 0.2878741600488699, "grad_norm": 0.37782856822013855, "learning_rate": 4.04542603597448e-05, "loss": 4.3591, "step": 9425 }, { "epoch": 0.28790470372632865, "grad_norm": 0.3972877264022827, "learning_rate": 4.045237465146412e-05, "loss": 4.3459, "step": 9426 }, { "epoch": 0.2879352474037874, "grad_norm": 0.3818018138408661, "learning_rate": 4.045048880090547e-05, "loss": 4.2917, "step": 9427 }, { "epoch": 0.2879657910812462, "grad_norm": 0.38002434372901917, "learning_rate": 4.044860280808624e-05, "loss": 4.3232, "step": 9428 }, { "epoch": 0.28799633475870495, "grad_norm": 0.3981337249279022, "learning_rate": 4.0446716673023775e-05, "loss": 4.4369, "step": 9429 }, { "epoch": 0.2880268784361637, "grad_norm": 0.3974531888961792, "learning_rate": 4.044483039573545e-05, "loss": 4.3753, "step": 9430 }, { "epoch": 0.2880574221136225, "grad_norm": 0.39534181356430054, "learning_rate": 4.044294397623863e-05, "loss": 4.3486, "step": 9431 }, { "epoch": 0.28808796579108126, "grad_norm": 0.37715771794319153, "learning_rate": 4.044105741455069e-05, "loss": 4.2992, "step": 9432 }, { "epoch": 0.28811850946854, "grad_norm": 0.38319411873817444, "learning_rate": 4.043917071068898e-05, "loss": 4.3739, "step": 9433 }, { "epoch": 0.28814905314599876, "grad_norm": 0.3896946907043457, "learning_rate": 4.0437283864670904e-05, "loss": 4.366, "step": 9434 }, { "epoch": 0.28817959682345756, "grad_norm": 0.38771477341651917, "learning_rate": 4.043539687651381e-05, "loss": 4.2988, "step": 9435 }, { "epoch": 0.2882101405009163, "grad_norm": 0.3755221962928772, "learning_rate": 4.043350974623508e-05, "loss": 4.4193, "step": 9436 }, { "epoch": 0.28824068417837506, "grad_norm": 0.39316269755363464, "learning_rate": 4.043162247385209e-05, "loss": 4.2907, "step": 9437 }, { "epoch": 0.28827122785583387, "grad_norm": 0.3677310645580292, "learning_rate": 4.0429735059382227e-05, "loss": 4.3084, "step": 9438 }, { "epoch": 0.2883017715332926, "grad_norm": 0.38142651319503784, "learning_rate": 4.042784750284285e-05, "loss": 4.3941, "step": 9439 }, { "epoch": 0.28833231521075137, "grad_norm": 0.39405229687690735, "learning_rate": 4.0425959804251356e-05, "loss": 4.264, "step": 9440 }, { "epoch": 0.2883628588882101, "grad_norm": 0.3718923032283783, "learning_rate": 4.042407196362511e-05, "loss": 4.3314, "step": 9441 }, { "epoch": 0.2883934025656689, "grad_norm": 0.3818957507610321, "learning_rate": 4.042218398098151e-05, "loss": 4.2851, "step": 9442 }, { "epoch": 0.28842394624312767, "grad_norm": 0.3780149519443512, "learning_rate": 4.042029585633793e-05, "loss": 4.3161, "step": 9443 }, { "epoch": 0.2884544899205864, "grad_norm": 0.38056692481040955, "learning_rate": 4.041840758971176e-05, "loss": 4.3478, "step": 9444 }, { "epoch": 0.2884850335980452, "grad_norm": 0.3751384913921356, "learning_rate": 4.0416519181120385e-05, "loss": 4.2467, "step": 9445 }, { "epoch": 0.288515577275504, "grad_norm": 0.3959280848503113, "learning_rate": 4.0414630630581185e-05, "loss": 4.4028, "step": 9446 }, { "epoch": 0.2885461209529627, "grad_norm": 0.39355728030204773, "learning_rate": 4.0412741938111567e-05, "loss": 4.3195, "step": 9447 }, { "epoch": 0.2885766646304215, "grad_norm": 0.3643343448638916, "learning_rate": 4.0410853103728896e-05, "loss": 4.3107, "step": 9448 }, { "epoch": 0.2886072083078803, "grad_norm": 0.38211649656295776, "learning_rate": 4.040896412745058e-05, "loss": 4.3729, "step": 9449 }, { "epoch": 0.28863775198533903, "grad_norm": 0.37346866726875305, "learning_rate": 4.040707500929402e-05, "loss": 4.3796, "step": 9450 }, { "epoch": 0.2886682956627978, "grad_norm": 0.40616780519485474, "learning_rate": 4.0405185749276586e-05, "loss": 4.3523, "step": 9451 }, { "epoch": 0.2886988393402566, "grad_norm": 0.37556880712509155, "learning_rate": 4.0403296347415695e-05, "loss": 4.3723, "step": 9452 }, { "epoch": 0.28872938301771534, "grad_norm": 0.3820568919181824, "learning_rate": 4.0401406803728726e-05, "loss": 4.3113, "step": 9453 }, { "epoch": 0.2887599266951741, "grad_norm": 0.38422465324401855, "learning_rate": 4.039951711823309e-05, "loss": 4.3554, "step": 9454 }, { "epoch": 0.2887904703726329, "grad_norm": 0.3845154345035553, "learning_rate": 4.039762729094618e-05, "loss": 4.4123, "step": 9455 }, { "epoch": 0.28882101405009164, "grad_norm": 0.3698563277721405, "learning_rate": 4.0395737321885406e-05, "loss": 4.3839, "step": 9456 }, { "epoch": 0.2888515577275504, "grad_norm": 0.3717011511325836, "learning_rate": 4.039384721106816e-05, "loss": 4.399, "step": 9457 }, { "epoch": 0.28888210140500914, "grad_norm": 0.37917187809944153, "learning_rate": 4.039195695851185e-05, "loss": 4.4299, "step": 9458 }, { "epoch": 0.28891264508246794, "grad_norm": 0.37067711353302, "learning_rate": 4.039006656423387e-05, "loss": 4.2632, "step": 9459 }, { "epoch": 0.2889431887599267, "grad_norm": 0.37404865026474, "learning_rate": 4.038817602825165e-05, "loss": 4.3213, "step": 9460 }, { "epoch": 0.28897373243738544, "grad_norm": 0.3659322261810303, "learning_rate": 4.038628535058256e-05, "loss": 4.3448, "step": 9461 }, { "epoch": 0.28900427611484425, "grad_norm": 0.36556917428970337, "learning_rate": 4.0384394531244044e-05, "loss": 4.3099, "step": 9462 }, { "epoch": 0.289034819792303, "grad_norm": 0.37798112630844116, "learning_rate": 4.03825035702535e-05, "loss": 4.3711, "step": 9463 }, { "epoch": 0.28906536346976175, "grad_norm": 0.3672083616256714, "learning_rate": 4.0380612467628334e-05, "loss": 4.3119, "step": 9464 }, { "epoch": 0.2890959071472205, "grad_norm": 0.39605796337127686, "learning_rate": 4.037872122338596e-05, "loss": 4.4255, "step": 9465 }, { "epoch": 0.2891264508246793, "grad_norm": 0.3847227990627289, "learning_rate": 4.037682983754378e-05, "loss": 4.3263, "step": 9466 }, { "epoch": 0.28915699450213805, "grad_norm": 0.3709736764431, "learning_rate": 4.0374938310119236e-05, "loss": 4.345, "step": 9467 }, { "epoch": 0.2891875381795968, "grad_norm": 0.3726027309894562, "learning_rate": 4.037304664112973e-05, "loss": 4.374, "step": 9468 }, { "epoch": 0.2892180818570556, "grad_norm": 0.376356303691864, "learning_rate": 4.037115483059267e-05, "loss": 4.3679, "step": 9469 }, { "epoch": 0.28924862553451436, "grad_norm": 0.37687671184539795, "learning_rate": 4.036926287852549e-05, "loss": 4.3336, "step": 9470 }, { "epoch": 0.2892791692119731, "grad_norm": 0.3821198046207428, "learning_rate": 4.0367370784945616e-05, "loss": 4.3785, "step": 9471 }, { "epoch": 0.2893097128894319, "grad_norm": 0.3728315830230713, "learning_rate": 4.0365478549870437e-05, "loss": 4.3519, "step": 9472 }, { "epoch": 0.28934025656689066, "grad_norm": 0.38442370295524597, "learning_rate": 4.036358617331741e-05, "loss": 4.3754, "step": 9473 }, { "epoch": 0.2893708002443494, "grad_norm": 0.36595243215560913, "learning_rate": 4.036169365530395e-05, "loss": 4.3241, "step": 9474 }, { "epoch": 0.28940134392180816, "grad_norm": 0.3779531717300415, "learning_rate": 4.0359800995847474e-05, "loss": 4.3075, "step": 9475 }, { "epoch": 0.28943188759926697, "grad_norm": 0.3718838691711426, "learning_rate": 4.0357908194965406e-05, "loss": 4.2768, "step": 9476 }, { "epoch": 0.2894624312767257, "grad_norm": 0.36534157395362854, "learning_rate": 4.0356015252675185e-05, "loss": 4.3454, "step": 9477 }, { "epoch": 0.28949297495418447, "grad_norm": 0.37955549359321594, "learning_rate": 4.0354122168994234e-05, "loss": 4.4094, "step": 9478 }, { "epoch": 0.2895235186316433, "grad_norm": 0.393275648355484, "learning_rate": 4.0352228943939994e-05, "loss": 4.3186, "step": 9479 }, { "epoch": 0.289554062309102, "grad_norm": 0.4009445309638977, "learning_rate": 4.035033557752989e-05, "loss": 4.3466, "step": 9480 }, { "epoch": 0.2895846059865608, "grad_norm": 0.37841248512268066, "learning_rate": 4.034844206978134e-05, "loss": 4.2893, "step": 9481 }, { "epoch": 0.2896151496640195, "grad_norm": 0.3752228915691376, "learning_rate": 4.034654842071181e-05, "loss": 4.3429, "step": 9482 }, { "epoch": 0.2896456933414783, "grad_norm": 0.3779584765434265, "learning_rate": 4.03446546303387e-05, "loss": 4.3895, "step": 9483 }, { "epoch": 0.2896762370189371, "grad_norm": 0.39483481645584106, "learning_rate": 4.034276069867947e-05, "loss": 4.3733, "step": 9484 }, { "epoch": 0.2897067806963958, "grad_norm": 0.371783971786499, "learning_rate": 4.034086662575156e-05, "loss": 4.3362, "step": 9485 }, { "epoch": 0.28973732437385463, "grad_norm": 0.3864280581474304, "learning_rate": 4.03389724115724e-05, "loss": 4.3059, "step": 9486 }, { "epoch": 0.2897678680513134, "grad_norm": 0.3829041123390198, "learning_rate": 4.033707805615944e-05, "loss": 4.3918, "step": 9487 }, { "epoch": 0.28979841172877213, "grad_norm": 0.3747446537017822, "learning_rate": 4.033518355953011e-05, "loss": 4.2906, "step": 9488 }, { "epoch": 0.28982895540623094, "grad_norm": 0.3767159581184387, "learning_rate": 4.033328892170186e-05, "loss": 4.4196, "step": 9489 }, { "epoch": 0.2898594990836897, "grad_norm": 0.391064316034317, "learning_rate": 4.033139414269214e-05, "loss": 4.3733, "step": 9490 }, { "epoch": 0.28989004276114844, "grad_norm": 0.37325844168663025, "learning_rate": 4.032949922251839e-05, "loss": 4.3607, "step": 9491 }, { "epoch": 0.2899205864386072, "grad_norm": 0.3865317106246948, "learning_rate": 4.032760416119806e-05, "loss": 4.3345, "step": 9492 }, { "epoch": 0.289951130116066, "grad_norm": 0.3726642429828644, "learning_rate": 4.032570895874859e-05, "loss": 4.4096, "step": 9493 }, { "epoch": 0.28998167379352474, "grad_norm": 0.3708396852016449, "learning_rate": 4.032381361518745e-05, "loss": 4.3293, "step": 9494 }, { "epoch": 0.2900122174709835, "grad_norm": 0.3864379823207855, "learning_rate": 4.032191813053208e-05, "loss": 4.3381, "step": 9495 }, { "epoch": 0.2900427611484423, "grad_norm": 0.3700654208660126, "learning_rate": 4.032002250479992e-05, "loss": 4.3466, "step": 9496 }, { "epoch": 0.29007330482590105, "grad_norm": 0.37230029702186584, "learning_rate": 4.0318126738008444e-05, "loss": 4.2652, "step": 9497 }, { "epoch": 0.2901038485033598, "grad_norm": 0.3999656140804291, "learning_rate": 4.0316230830175095e-05, "loss": 4.4605, "step": 9498 }, { "epoch": 0.29013439218081855, "grad_norm": 0.379806250333786, "learning_rate": 4.0314334781317334e-05, "loss": 4.2941, "step": 9499 }, { "epoch": 0.29016493585827735, "grad_norm": 0.37259045243263245, "learning_rate": 4.0312438591452615e-05, "loss": 4.4064, "step": 9500 }, { "epoch": 0.2901954795357361, "grad_norm": 0.37178847193717957, "learning_rate": 4.0310542260598415e-05, "loss": 4.357, "step": 9501 }, { "epoch": 0.29022602321319485, "grad_norm": 0.37770384550094604, "learning_rate": 4.030864578877217e-05, "loss": 4.3339, "step": 9502 }, { "epoch": 0.29025656689065366, "grad_norm": 0.3787900507450104, "learning_rate": 4.0306749175991355e-05, "loss": 4.3869, "step": 9503 }, { "epoch": 0.2902871105681124, "grad_norm": 0.3765522837638855, "learning_rate": 4.030485242227343e-05, "loss": 4.4155, "step": 9504 }, { "epoch": 0.29031765424557116, "grad_norm": 0.3825289011001587, "learning_rate": 4.030295552763586e-05, "loss": 4.2492, "step": 9505 }, { "epoch": 0.29034819792302996, "grad_norm": 0.39025476574897766, "learning_rate": 4.030105849209611e-05, "loss": 4.3848, "step": 9506 }, { "epoch": 0.2903787416004887, "grad_norm": 0.3784462511539459, "learning_rate": 4.0299161315671644e-05, "loss": 4.3206, "step": 9507 }, { "epoch": 0.29040928527794746, "grad_norm": 0.38314226269721985, "learning_rate": 4.0297263998379944e-05, "loss": 4.2963, "step": 9508 }, { "epoch": 0.2904398289554062, "grad_norm": 0.38205254077911377, "learning_rate": 4.029536654023846e-05, "loss": 4.3633, "step": 9509 }, { "epoch": 0.290470372632865, "grad_norm": 0.3854254186153412, "learning_rate": 4.0293468941264674e-05, "loss": 4.3878, "step": 9510 }, { "epoch": 0.29050091631032376, "grad_norm": 0.3862828016281128, "learning_rate": 4.0291571201476056e-05, "loss": 4.3755, "step": 9511 }, { "epoch": 0.2905314599877825, "grad_norm": 0.3813233971595764, "learning_rate": 4.0289673320890085e-05, "loss": 4.35, "step": 9512 }, { "epoch": 0.2905620036652413, "grad_norm": 0.3735314607620239, "learning_rate": 4.028777529952422e-05, "loss": 4.3071, "step": 9513 }, { "epoch": 0.29059254734270007, "grad_norm": 0.3879857063293457, "learning_rate": 4.028587713739596e-05, "loss": 4.3373, "step": 9514 }, { "epoch": 0.2906230910201588, "grad_norm": 0.374808669090271, "learning_rate": 4.028397883452276e-05, "loss": 4.2752, "step": 9515 }, { "epoch": 0.29065363469761757, "grad_norm": 0.39366811513900757, "learning_rate": 4.0282080390922114e-05, "loss": 4.3626, "step": 9516 }, { "epoch": 0.2906841783750764, "grad_norm": 0.3731006681919098, "learning_rate": 4.0280181806611494e-05, "loss": 4.373, "step": 9517 }, { "epoch": 0.2907147220525351, "grad_norm": 0.3694031536579132, "learning_rate": 4.027828308160839e-05, "loss": 4.2655, "step": 9518 }, { "epoch": 0.2907452657299939, "grad_norm": 0.36509403586387634, "learning_rate": 4.0276384215930276e-05, "loss": 4.3842, "step": 9519 }, { "epoch": 0.2907758094074527, "grad_norm": 0.38925856351852417, "learning_rate": 4.0274485209594624e-05, "loss": 4.3943, "step": 9520 }, { "epoch": 0.29080635308491143, "grad_norm": 0.37224069237709045, "learning_rate": 4.027258606261896e-05, "loss": 4.331, "step": 9521 }, { "epoch": 0.2908368967623702, "grad_norm": 0.3747269809246063, "learning_rate": 4.027068677502072e-05, "loss": 4.3923, "step": 9522 }, { "epoch": 0.29086744043982893, "grad_norm": 0.3868370056152344, "learning_rate": 4.0268787346817424e-05, "loss": 4.3403, "step": 9523 }, { "epoch": 0.29089798411728773, "grad_norm": 0.3788883686065674, "learning_rate": 4.026688777802655e-05, "loss": 4.3732, "step": 9524 }, { "epoch": 0.2909285277947465, "grad_norm": 0.391166090965271, "learning_rate": 4.02649880686656e-05, "loss": 4.3677, "step": 9525 }, { "epoch": 0.29095907147220523, "grad_norm": 0.37437576055526733, "learning_rate": 4.026308821875205e-05, "loss": 4.4078, "step": 9526 }, { "epoch": 0.29098961514966404, "grad_norm": 0.3722379505634308, "learning_rate": 4.026118822830339e-05, "loss": 4.4144, "step": 9527 }, { "epoch": 0.2910201588271228, "grad_norm": 0.3709111213684082, "learning_rate": 4.025928809733713e-05, "loss": 4.3684, "step": 9528 }, { "epoch": 0.29105070250458154, "grad_norm": 0.3865855932235718, "learning_rate": 4.025738782587077e-05, "loss": 4.3714, "step": 9529 }, { "epoch": 0.29108124618204034, "grad_norm": 0.37093570828437805, "learning_rate": 4.0255487413921785e-05, "loss": 4.3043, "step": 9530 }, { "epoch": 0.2911117898594991, "grad_norm": 0.3788433074951172, "learning_rate": 4.025358686150769e-05, "loss": 4.3834, "step": 9531 }, { "epoch": 0.29114233353695784, "grad_norm": 0.3703692853450775, "learning_rate": 4.0251686168645975e-05, "loss": 4.3933, "step": 9532 }, { "epoch": 0.2911728772144166, "grad_norm": 0.3768925666809082, "learning_rate": 4.024978533535414e-05, "loss": 4.2931, "step": 9533 }, { "epoch": 0.2912034208918754, "grad_norm": 0.36893826723098755, "learning_rate": 4.024788436164969e-05, "loss": 4.3514, "step": 9534 }, { "epoch": 0.29123396456933415, "grad_norm": 0.38047924637794495, "learning_rate": 4.0245983247550137e-05, "loss": 4.3927, "step": 9535 }, { "epoch": 0.2912645082467929, "grad_norm": 0.37419041991233826, "learning_rate": 4.0244081993072965e-05, "loss": 4.4201, "step": 9536 }, { "epoch": 0.2912950519242517, "grad_norm": 0.386650413274765, "learning_rate": 4.0242180598235706e-05, "loss": 4.3939, "step": 9537 }, { "epoch": 0.29132559560171045, "grad_norm": 0.38360631465911865, "learning_rate": 4.0240279063055854e-05, "loss": 4.3463, "step": 9538 }, { "epoch": 0.2913561392791692, "grad_norm": 0.3839948773384094, "learning_rate": 4.023837738755091e-05, "loss": 4.2402, "step": 9539 }, { "epoch": 0.29138668295662795, "grad_norm": 0.3762914538383484, "learning_rate": 4.023647557173839e-05, "loss": 4.2871, "step": 9540 }, { "epoch": 0.29141722663408676, "grad_norm": 0.378007173538208, "learning_rate": 4.0234573615635806e-05, "loss": 4.4019, "step": 9541 }, { "epoch": 0.2914477703115455, "grad_norm": 0.36836886405944824, "learning_rate": 4.0232671519260666e-05, "loss": 4.3775, "step": 9542 }, { "epoch": 0.29147831398900426, "grad_norm": 0.3806062936782837, "learning_rate": 4.0230769282630496e-05, "loss": 4.3745, "step": 9543 }, { "epoch": 0.29150885766646306, "grad_norm": 0.3925808072090149, "learning_rate": 4.0228866905762794e-05, "loss": 4.424, "step": 9544 }, { "epoch": 0.2915394013439218, "grad_norm": 0.3736344277858734, "learning_rate": 4.022696438867509e-05, "loss": 4.391, "step": 9545 }, { "epoch": 0.29156994502138056, "grad_norm": 0.386453241109848, "learning_rate": 4.02250617313849e-05, "loss": 4.3506, "step": 9546 }, { "epoch": 0.29160048869883937, "grad_norm": 0.37931519746780396, "learning_rate": 4.022315893390973e-05, "loss": 4.2899, "step": 9547 }, { "epoch": 0.2916310323762981, "grad_norm": 0.3662174940109253, "learning_rate": 4.022125599626711e-05, "loss": 4.319, "step": 9548 }, { "epoch": 0.29166157605375687, "grad_norm": 0.3888475298881531, "learning_rate": 4.021935291847457e-05, "loss": 4.3923, "step": 9549 }, { "epoch": 0.2916921197312156, "grad_norm": 0.37201055884361267, "learning_rate": 4.021744970054962e-05, "loss": 4.347, "step": 9550 }, { "epoch": 0.2917226634086744, "grad_norm": 0.36726969480514526, "learning_rate": 4.021554634250977e-05, "loss": 4.3282, "step": 9551 }, { "epoch": 0.29175320708613317, "grad_norm": 0.38192781805992126, "learning_rate": 4.021364284437258e-05, "loss": 4.3255, "step": 9552 }, { "epoch": 0.2917837507635919, "grad_norm": 0.38839754462242126, "learning_rate": 4.0211739206155554e-05, "loss": 4.3863, "step": 9553 }, { "epoch": 0.2918142944410507, "grad_norm": 0.37968161702156067, "learning_rate": 4.020983542787622e-05, "loss": 4.3179, "step": 9554 }, { "epoch": 0.2918448381185095, "grad_norm": 0.38477033376693726, "learning_rate": 4.020793150955211e-05, "loss": 4.4717, "step": 9555 }, { "epoch": 0.2918753817959682, "grad_norm": 0.3795011639595032, "learning_rate": 4.020602745120076e-05, "loss": 4.372, "step": 9556 }, { "epoch": 0.291905925473427, "grad_norm": 0.3811773657798767, "learning_rate": 4.02041232528397e-05, "loss": 4.3188, "step": 9557 }, { "epoch": 0.2919364691508858, "grad_norm": 0.39204975962638855, "learning_rate": 4.020221891448645e-05, "loss": 4.4075, "step": 9558 }, { "epoch": 0.29196701282834453, "grad_norm": 0.38466861844062805, "learning_rate": 4.020031443615856e-05, "loss": 4.3198, "step": 9559 }, { "epoch": 0.2919975565058033, "grad_norm": 0.39324915409088135, "learning_rate": 4.019840981787356e-05, "loss": 4.3889, "step": 9560 }, { "epoch": 0.2920281001832621, "grad_norm": 0.40501582622528076, "learning_rate": 4.019650505964898e-05, "loss": 4.3487, "step": 9561 }, { "epoch": 0.29205864386072083, "grad_norm": 0.3823486864566803, "learning_rate": 4.019460016150238e-05, "loss": 4.3694, "step": 9562 }, { "epoch": 0.2920891875381796, "grad_norm": 0.3793715238571167, "learning_rate": 4.0192695123451276e-05, "loss": 4.2681, "step": 9563 }, { "epoch": 0.2921197312156384, "grad_norm": 0.38605958223342896, "learning_rate": 4.019078994551321e-05, "loss": 4.3022, "step": 9564 }, { "epoch": 0.29215027489309714, "grad_norm": 0.3849632740020752, "learning_rate": 4.018888462770574e-05, "loss": 4.3971, "step": 9565 }, { "epoch": 0.2921808185705559, "grad_norm": 0.37209615111351013, "learning_rate": 4.018697917004639e-05, "loss": 4.3973, "step": 9566 }, { "epoch": 0.29221136224801464, "grad_norm": 0.36695677042007446, "learning_rate": 4.018507357255272e-05, "loss": 4.3526, "step": 9567 }, { "epoch": 0.29224190592547344, "grad_norm": 0.3673492968082428, "learning_rate": 4.018316783524228e-05, "loss": 4.3209, "step": 9568 }, { "epoch": 0.2922724496029322, "grad_norm": 0.3837507963180542, "learning_rate": 4.0181261958132595e-05, "loss": 4.3991, "step": 9569 }, { "epoch": 0.29230299328039094, "grad_norm": 0.36682406067848206, "learning_rate": 4.0179355941241226e-05, "loss": 4.343, "step": 9570 }, { "epoch": 0.29233353695784975, "grad_norm": 0.3759762942790985, "learning_rate": 4.017744978458572e-05, "loss": 4.286, "step": 9571 }, { "epoch": 0.2923640806353085, "grad_norm": 0.385257363319397, "learning_rate": 4.0175543488183644e-05, "loss": 4.2728, "step": 9572 }, { "epoch": 0.29239462431276725, "grad_norm": 0.3745923638343811, "learning_rate": 4.0173637052052525e-05, "loss": 4.2953, "step": 9573 }, { "epoch": 0.292425167990226, "grad_norm": 0.3978198170661926, "learning_rate": 4.0171730476209935e-05, "loss": 4.4396, "step": 9574 }, { "epoch": 0.2924557116676848, "grad_norm": 0.38416633009910583, "learning_rate": 4.016982376067341e-05, "loss": 4.3805, "step": 9575 }, { "epoch": 0.29248625534514355, "grad_norm": 0.3746511936187744, "learning_rate": 4.016791690546054e-05, "loss": 4.4214, "step": 9576 }, { "epoch": 0.2925167990226023, "grad_norm": 0.37418419122695923, "learning_rate": 4.0166009910588844e-05, "loss": 4.3404, "step": 9577 }, { "epoch": 0.2925473427000611, "grad_norm": 0.38208669424057007, "learning_rate": 4.016410277607589e-05, "loss": 4.3428, "step": 9578 }, { "epoch": 0.29257788637751986, "grad_norm": 0.36569926142692566, "learning_rate": 4.016219550193926e-05, "loss": 4.2983, "step": 9579 }, { "epoch": 0.2926084300549786, "grad_norm": 0.3835737407207489, "learning_rate": 4.0160288088196495e-05, "loss": 4.3517, "step": 9580 }, { "epoch": 0.2926389737324374, "grad_norm": 0.3730294108390808, "learning_rate": 4.015838053486516e-05, "loss": 4.1995, "step": 9581 }, { "epoch": 0.29266951740989616, "grad_norm": 0.3852464556694031, "learning_rate": 4.015647284196282e-05, "loss": 4.3575, "step": 9582 }, { "epoch": 0.2927000610873549, "grad_norm": 0.368847131729126, "learning_rate": 4.015456500950705e-05, "loss": 4.2786, "step": 9583 }, { "epoch": 0.29273060476481366, "grad_norm": 0.38825348019599915, "learning_rate": 4.015265703751541e-05, "loss": 4.3052, "step": 9584 }, { "epoch": 0.29276114844227247, "grad_norm": 0.38177669048309326, "learning_rate": 4.0150748926005454e-05, "loss": 4.4425, "step": 9585 }, { "epoch": 0.2927916921197312, "grad_norm": 0.372658371925354, "learning_rate": 4.0148840674994776e-05, "loss": 4.3001, "step": 9586 }, { "epoch": 0.29282223579718997, "grad_norm": 0.3721309006214142, "learning_rate": 4.0146932284500926e-05, "loss": 4.3644, "step": 9587 }, { "epoch": 0.29285277947464877, "grad_norm": 0.3763625919818878, "learning_rate": 4.014502375454148e-05, "loss": 4.3682, "step": 9588 }, { "epoch": 0.2928833231521075, "grad_norm": 0.380202978849411, "learning_rate": 4.014311508513402e-05, "loss": 4.2072, "step": 9589 }, { "epoch": 0.29291386682956627, "grad_norm": 0.38139885663986206, "learning_rate": 4.0141206276296114e-05, "loss": 4.32, "step": 9590 }, { "epoch": 0.292944410507025, "grad_norm": 0.3702651858329773, "learning_rate": 4.013929732804533e-05, "loss": 4.3121, "step": 9591 }, { "epoch": 0.2929749541844838, "grad_norm": 0.3726825714111328, "learning_rate": 4.013738824039925e-05, "loss": 4.3182, "step": 9592 }, { "epoch": 0.2930054978619426, "grad_norm": 0.3785035312175751, "learning_rate": 4.013547901337547e-05, "loss": 4.4077, "step": 9593 }, { "epoch": 0.2930360415394013, "grad_norm": 0.3745345175266266, "learning_rate": 4.013356964699154e-05, "loss": 4.3219, "step": 9594 }, { "epoch": 0.29306658521686013, "grad_norm": 0.3914155960083008, "learning_rate": 4.0131660141265056e-05, "loss": 4.4126, "step": 9595 }, { "epoch": 0.2930971288943189, "grad_norm": 0.381564199924469, "learning_rate": 4.012975049621359e-05, "loss": 4.4154, "step": 9596 }, { "epoch": 0.29312767257177763, "grad_norm": 0.38264259696006775, "learning_rate": 4.0127840711854744e-05, "loss": 4.3758, "step": 9597 }, { "epoch": 0.2931582162492364, "grad_norm": 0.373331218957901, "learning_rate": 4.012593078820609e-05, "loss": 4.3484, "step": 9598 }, { "epoch": 0.2931887599266952, "grad_norm": 0.38327011466026306, "learning_rate": 4.012402072528521e-05, "loss": 4.3313, "step": 9599 }, { "epoch": 0.29321930360415394, "grad_norm": 0.3789607286453247, "learning_rate": 4.0122110523109693e-05, "loss": 4.4038, "step": 9600 }, { "epoch": 0.2932498472816127, "grad_norm": 0.38193511962890625, "learning_rate": 4.0120200181697135e-05, "loss": 4.3718, "step": 9601 }, { "epoch": 0.2932803909590715, "grad_norm": 0.36911314725875854, "learning_rate": 4.01182897010651e-05, "loss": 4.366, "step": 9602 }, { "epoch": 0.29331093463653024, "grad_norm": 0.3661730885505676, "learning_rate": 4.011637908123123e-05, "loss": 4.3601, "step": 9603 }, { "epoch": 0.293341478313989, "grad_norm": 0.384926974773407, "learning_rate": 4.0114468322213064e-05, "loss": 4.2598, "step": 9604 }, { "epoch": 0.2933720219914478, "grad_norm": 0.36672765016555786, "learning_rate": 4.011255742402822e-05, "loss": 4.3437, "step": 9605 }, { "epoch": 0.29340256566890655, "grad_norm": 0.3778432011604309, "learning_rate": 4.011064638669429e-05, "loss": 4.3425, "step": 9606 }, { "epoch": 0.2934331093463653, "grad_norm": 0.3741753101348877, "learning_rate": 4.0108735210228875e-05, "loss": 4.4041, "step": 9607 }, { "epoch": 0.29346365302382404, "grad_norm": 0.3721978962421417, "learning_rate": 4.010682389464957e-05, "loss": 4.2862, "step": 9608 }, { "epoch": 0.29349419670128285, "grad_norm": 0.3643692135810852, "learning_rate": 4.010491243997396e-05, "loss": 4.3395, "step": 9609 }, { "epoch": 0.2935247403787416, "grad_norm": 0.3839614987373352, "learning_rate": 4.0103000846219666e-05, "loss": 4.3134, "step": 9610 }, { "epoch": 0.29355528405620035, "grad_norm": 0.381232887506485, "learning_rate": 4.0101089113404265e-05, "loss": 4.33, "step": 9611 }, { "epoch": 0.29358582773365915, "grad_norm": 0.3831663131713867, "learning_rate": 4.0099177241545385e-05, "loss": 4.2716, "step": 9612 }, { "epoch": 0.2936163714111179, "grad_norm": 0.37375378608703613, "learning_rate": 4.009726523066061e-05, "loss": 4.3906, "step": 9613 }, { "epoch": 0.29364691508857665, "grad_norm": 0.39057743549346924, "learning_rate": 4.009535308076755e-05, "loss": 4.337, "step": 9614 }, { "epoch": 0.2936774587660354, "grad_norm": 0.3736397624015808, "learning_rate": 4.009344079188382e-05, "loss": 4.3689, "step": 9615 }, { "epoch": 0.2937080024434942, "grad_norm": 0.36800044775009155, "learning_rate": 4.009152836402701e-05, "loss": 4.3749, "step": 9616 }, { "epoch": 0.29373854612095296, "grad_norm": 0.37049922347068787, "learning_rate": 4.008961579721475e-05, "loss": 4.2437, "step": 9617 }, { "epoch": 0.2937690897984117, "grad_norm": 0.3887965977191925, "learning_rate": 4.008770309146464e-05, "loss": 4.3201, "step": 9618 }, { "epoch": 0.2937996334758705, "grad_norm": 0.37274935841560364, "learning_rate": 4.008579024679427e-05, "loss": 4.3529, "step": 9619 }, { "epoch": 0.29383017715332926, "grad_norm": 0.3759754002094269, "learning_rate": 4.008387726322129e-05, "loss": 4.4108, "step": 9620 }, { "epoch": 0.293860720830788, "grad_norm": 0.36996349692344666, "learning_rate": 4.00819641407633e-05, "loss": 4.3337, "step": 9621 }, { "epoch": 0.2938912645082468, "grad_norm": 0.38485851883888245, "learning_rate": 4.00800508794379e-05, "loss": 4.3487, "step": 9622 }, { "epoch": 0.29392180818570557, "grad_norm": 0.37897592782974243, "learning_rate": 4.007813747926273e-05, "loss": 4.3369, "step": 9623 }, { "epoch": 0.2939523518631643, "grad_norm": 0.3864706754684448, "learning_rate": 4.0076223940255385e-05, "loss": 4.414, "step": 9624 }, { "epoch": 0.29398289554062307, "grad_norm": 0.38594406843185425, "learning_rate": 4.00743102624335e-05, "loss": 4.3956, "step": 9625 }, { "epoch": 0.2940134392180819, "grad_norm": 0.3854176700115204, "learning_rate": 4.0072396445814686e-05, "loss": 4.2976, "step": 9626 }, { "epoch": 0.2940439828955406, "grad_norm": 0.3861720860004425, "learning_rate": 4.007048249041658e-05, "loss": 4.4066, "step": 9627 }, { "epoch": 0.2940745265729994, "grad_norm": 0.39141079783439636, "learning_rate": 4.006856839625678e-05, "loss": 4.2829, "step": 9628 }, { "epoch": 0.2941050702504582, "grad_norm": 0.38218048214912415, "learning_rate": 4.006665416335293e-05, "loss": 4.2773, "step": 9629 }, { "epoch": 0.29413561392791693, "grad_norm": 0.3833375573158264, "learning_rate": 4.006473979172265e-05, "loss": 4.4235, "step": 9630 }, { "epoch": 0.2941661576053757, "grad_norm": 0.3719359338283539, "learning_rate": 4.0062825281383566e-05, "loss": 4.2701, "step": 9631 }, { "epoch": 0.2941967012828344, "grad_norm": 0.37622901797294617, "learning_rate": 4.0060910632353296e-05, "loss": 4.3301, "step": 9632 }, { "epoch": 0.29422724496029323, "grad_norm": 0.38212263584136963, "learning_rate": 4.005899584464948e-05, "loss": 4.33, "step": 9633 }, { "epoch": 0.294257788637752, "grad_norm": 0.3888854682445526, "learning_rate": 4.0057080918289755e-05, "loss": 4.3565, "step": 9634 }, { "epoch": 0.29428833231521073, "grad_norm": 0.357612282037735, "learning_rate": 4.0055165853291735e-05, "loss": 4.3426, "step": 9635 }, { "epoch": 0.29431887599266954, "grad_norm": 0.3695046901702881, "learning_rate": 4.0053250649673066e-05, "loss": 4.3953, "step": 9636 }, { "epoch": 0.2943494196701283, "grad_norm": 0.3764056861400604, "learning_rate": 4.005133530745139e-05, "loss": 4.2715, "step": 9637 }, { "epoch": 0.29437996334758704, "grad_norm": 0.37568339705467224, "learning_rate": 4.004941982664432e-05, "loss": 4.3495, "step": 9638 }, { "epoch": 0.29441050702504584, "grad_norm": 0.36340585350990295, "learning_rate": 4.00475042072695e-05, "loss": 4.3461, "step": 9639 }, { "epoch": 0.2944410507025046, "grad_norm": 0.3832017183303833, "learning_rate": 4.004558844934457e-05, "loss": 4.3549, "step": 9640 }, { "epoch": 0.29447159437996334, "grad_norm": 0.36760038137435913, "learning_rate": 4.0043672552887184e-05, "loss": 4.3045, "step": 9641 }, { "epoch": 0.2945021380574221, "grad_norm": 0.3775261342525482, "learning_rate": 4.004175651791496e-05, "loss": 4.3533, "step": 9642 }, { "epoch": 0.2945326817348809, "grad_norm": 0.3676427900791168, "learning_rate": 4.003984034444556e-05, "loss": 4.4071, "step": 9643 }, { "epoch": 0.29456322541233965, "grad_norm": 0.37069737911224365, "learning_rate": 4.003792403249661e-05, "loss": 4.3258, "step": 9644 }, { "epoch": 0.2945937690897984, "grad_norm": 0.3708670735359192, "learning_rate": 4.0036007582085764e-05, "loss": 4.2511, "step": 9645 }, { "epoch": 0.2946243127672572, "grad_norm": 0.37004587054252625, "learning_rate": 4.003409099323067e-05, "loss": 4.3631, "step": 9646 }, { "epoch": 0.29465485644471595, "grad_norm": 0.3706473708152771, "learning_rate": 4.003217426594896e-05, "loss": 4.3394, "step": 9647 }, { "epoch": 0.2946854001221747, "grad_norm": 0.384011447429657, "learning_rate": 4.00302574002583e-05, "loss": 4.3694, "step": 9648 }, { "epoch": 0.29471594379963345, "grad_norm": 0.38006457686424255, "learning_rate": 4.002834039617633e-05, "loss": 4.3906, "step": 9649 }, { "epoch": 0.29474648747709226, "grad_norm": 0.39423900842666626, "learning_rate": 4.0026423253720706e-05, "loss": 4.3569, "step": 9650 }, { "epoch": 0.294777031154551, "grad_norm": 0.3743114769458771, "learning_rate": 4.002450597290907e-05, "loss": 4.3069, "step": 9651 }, { "epoch": 0.29480757483200976, "grad_norm": 0.3833884596824646, "learning_rate": 4.002258855375909e-05, "loss": 4.3275, "step": 9652 }, { "epoch": 0.29483811850946856, "grad_norm": 0.37715211510658264, "learning_rate": 4.002067099628841e-05, "loss": 4.2547, "step": 9653 }, { "epoch": 0.2948686621869273, "grad_norm": 0.38334131240844727, "learning_rate": 4.0018753300514695e-05, "loss": 4.3874, "step": 9654 }, { "epoch": 0.29489920586438606, "grad_norm": 0.36501753330230713, "learning_rate": 4.001683546645559e-05, "loss": 4.3642, "step": 9655 }, { "epoch": 0.29492974954184487, "grad_norm": 0.3826865553855896, "learning_rate": 4.001491749412876e-05, "loss": 4.3693, "step": 9656 }, { "epoch": 0.2949602932193036, "grad_norm": 0.37093278765678406, "learning_rate": 4.001299938355187e-05, "loss": 4.373, "step": 9657 }, { "epoch": 0.29499083689676237, "grad_norm": 0.3700196146965027, "learning_rate": 4.001108113474257e-05, "loss": 4.4204, "step": 9658 }, { "epoch": 0.2950213805742211, "grad_norm": 0.36806023120880127, "learning_rate": 4.000916274771853e-05, "loss": 4.2922, "step": 9659 }, { "epoch": 0.2950519242516799, "grad_norm": 0.3732700049877167, "learning_rate": 4.000724422249741e-05, "loss": 4.3722, "step": 9660 }, { "epoch": 0.29508246792913867, "grad_norm": 0.3723771870136261, "learning_rate": 4.000532555909689e-05, "loss": 4.3419, "step": 9661 }, { "epoch": 0.2951130116065974, "grad_norm": 0.3726128339767456, "learning_rate": 4.00034067575346e-05, "loss": 4.3239, "step": 9662 }, { "epoch": 0.2951435552840562, "grad_norm": 0.3799857795238495, "learning_rate": 4.0001487817828245e-05, "loss": 4.352, "step": 9663 }, { "epoch": 0.295174098961515, "grad_norm": 0.3872850239276886, "learning_rate": 3.9999568739995476e-05, "loss": 4.4361, "step": 9664 }, { "epoch": 0.2952046426389737, "grad_norm": 0.3770477771759033, "learning_rate": 3.999764952405396e-05, "loss": 4.3917, "step": 9665 }, { "epoch": 0.2952351863164325, "grad_norm": 0.36574333906173706, "learning_rate": 3.999573017002138e-05, "loss": 4.3106, "step": 9666 }, { "epoch": 0.2952657299938913, "grad_norm": 0.3692619800567627, "learning_rate": 3.9993810677915396e-05, "loss": 4.3054, "step": 9667 }, { "epoch": 0.29529627367135003, "grad_norm": 0.3829798102378845, "learning_rate": 3.999189104775369e-05, "loss": 4.4472, "step": 9668 }, { "epoch": 0.2953268173488088, "grad_norm": 0.38243138790130615, "learning_rate": 3.998997127955394e-05, "loss": 4.3202, "step": 9669 }, { "epoch": 0.2953573610262676, "grad_norm": 0.37790215015411377, "learning_rate": 3.998805137333382e-05, "loss": 4.3186, "step": 9670 }, { "epoch": 0.29538790470372633, "grad_norm": 0.3751680254936218, "learning_rate": 3.9986131329111e-05, "loss": 4.2633, "step": 9671 }, { "epoch": 0.2954184483811851, "grad_norm": 0.3722073435783386, "learning_rate": 3.998421114690316e-05, "loss": 4.385, "step": 9672 }, { "epoch": 0.29544899205864383, "grad_norm": 0.38308706879615784, "learning_rate": 3.998229082672799e-05, "loss": 4.3288, "step": 9673 }, { "epoch": 0.29547953573610264, "grad_norm": 0.37675315141677856, "learning_rate": 3.998037036860316e-05, "loss": 4.4069, "step": 9674 }, { "epoch": 0.2955100794135614, "grad_norm": 0.37873589992523193, "learning_rate": 3.9978449772546365e-05, "loss": 4.2709, "step": 9675 }, { "epoch": 0.29554062309102014, "grad_norm": 0.37122413516044617, "learning_rate": 3.9976529038575275e-05, "loss": 4.3525, "step": 9676 }, { "epoch": 0.29557116676847894, "grad_norm": 0.3727489113807678, "learning_rate": 3.997460816670758e-05, "loss": 4.3543, "step": 9677 }, { "epoch": 0.2956017104459377, "grad_norm": 0.3841424882411957, "learning_rate": 3.9972687156960974e-05, "loss": 4.4068, "step": 9678 }, { "epoch": 0.29563225412339644, "grad_norm": 0.3767288029193878, "learning_rate": 3.997076600935314e-05, "loss": 4.3539, "step": 9679 }, { "epoch": 0.29566279780085525, "grad_norm": 0.36876389384269714, "learning_rate": 3.996884472390176e-05, "loss": 4.3438, "step": 9680 }, { "epoch": 0.295693341478314, "grad_norm": 0.3711697459220886, "learning_rate": 3.996692330062454e-05, "loss": 4.3725, "step": 9681 }, { "epoch": 0.29572388515577275, "grad_norm": 0.39078372716903687, "learning_rate": 3.996500173953915e-05, "loss": 4.3949, "step": 9682 }, { "epoch": 0.2957544288332315, "grad_norm": 0.38196638226509094, "learning_rate": 3.996308004066331e-05, "loss": 4.3246, "step": 9683 }, { "epoch": 0.2957849725106903, "grad_norm": 0.3632243275642395, "learning_rate": 3.996115820401468e-05, "loss": 4.2871, "step": 9684 }, { "epoch": 0.29581551618814905, "grad_norm": 0.38025230169296265, "learning_rate": 3.995923622961099e-05, "loss": 4.3056, "step": 9685 }, { "epoch": 0.2958460598656078, "grad_norm": 0.38975951075553894, "learning_rate": 3.995731411746992e-05, "loss": 4.3657, "step": 9686 }, { "epoch": 0.2958766035430666, "grad_norm": 0.3837070167064667, "learning_rate": 3.995539186760916e-05, "loss": 4.2852, "step": 9687 }, { "epoch": 0.29590714722052536, "grad_norm": 0.370034396648407, "learning_rate": 3.995346948004642e-05, "loss": 4.295, "step": 9688 }, { "epoch": 0.2959376908979841, "grad_norm": 0.3826579451560974, "learning_rate": 3.99515469547994e-05, "loss": 4.3062, "step": 9689 }, { "epoch": 0.29596823457544286, "grad_norm": 0.37966081500053406, "learning_rate": 3.99496242918858e-05, "loss": 4.4103, "step": 9690 }, { "epoch": 0.29599877825290166, "grad_norm": 0.3808811604976654, "learning_rate": 3.994770149132332e-05, "loss": 4.3662, "step": 9691 }, { "epoch": 0.2960293219303604, "grad_norm": 0.374801903963089, "learning_rate": 3.994577855312967e-05, "loss": 4.3464, "step": 9692 }, { "epoch": 0.29605986560781916, "grad_norm": 0.3779473900794983, "learning_rate": 3.9943855477322553e-05, "loss": 4.3839, "step": 9693 }, { "epoch": 0.29609040928527797, "grad_norm": 0.3740035891532898, "learning_rate": 3.994193226391967e-05, "loss": 4.3383, "step": 9694 }, { "epoch": 0.2961209529627367, "grad_norm": 0.38803938031196594, "learning_rate": 3.994000891293874e-05, "loss": 4.2662, "step": 9695 }, { "epoch": 0.29615149664019547, "grad_norm": 0.381316602230072, "learning_rate": 3.9938085424397464e-05, "loss": 4.4053, "step": 9696 }, { "epoch": 0.29618204031765427, "grad_norm": 0.3783867359161377, "learning_rate": 3.9936161798313556e-05, "loss": 4.3527, "step": 9697 }, { "epoch": 0.296212583995113, "grad_norm": 0.37739378213882446, "learning_rate": 3.993423803470473e-05, "loss": 4.3135, "step": 9698 }, { "epoch": 0.29624312767257177, "grad_norm": 0.3761720359325409, "learning_rate": 3.9932314133588685e-05, "loss": 4.3201, "step": 9699 }, { "epoch": 0.2962736713500305, "grad_norm": 0.3785618245601654, "learning_rate": 3.9930390094983163e-05, "loss": 4.3079, "step": 9700 }, { "epoch": 0.2963042150274893, "grad_norm": 0.37077566981315613, "learning_rate": 3.992846591890585e-05, "loss": 4.3235, "step": 9701 }, { "epoch": 0.2963347587049481, "grad_norm": 0.37778618931770325, "learning_rate": 3.992654160537448e-05, "loss": 4.358, "step": 9702 }, { "epoch": 0.2963653023824068, "grad_norm": 0.4046842157840729, "learning_rate": 3.992461715440676e-05, "loss": 4.319, "step": 9703 }, { "epoch": 0.29639584605986563, "grad_norm": 0.3787088096141815, "learning_rate": 3.9922692566020424e-05, "loss": 4.1952, "step": 9704 }, { "epoch": 0.2964263897373244, "grad_norm": 0.38393929600715637, "learning_rate": 3.9920767840233186e-05, "loss": 4.3174, "step": 9705 }, { "epoch": 0.29645693341478313, "grad_norm": 0.38684678077697754, "learning_rate": 3.991884297706277e-05, "loss": 4.2878, "step": 9706 }, { "epoch": 0.2964874770922419, "grad_norm": 0.3803368806838989, "learning_rate": 3.9916917976526894e-05, "loss": 4.2197, "step": 9707 }, { "epoch": 0.2965180207697007, "grad_norm": 0.3937932550907135, "learning_rate": 3.9914992838643274e-05, "loss": 4.3633, "step": 9708 }, { "epoch": 0.29654856444715944, "grad_norm": 0.38829195499420166, "learning_rate": 3.991306756342966e-05, "loss": 4.3248, "step": 9709 }, { "epoch": 0.2965791081246182, "grad_norm": 0.37204283475875854, "learning_rate": 3.991114215090376e-05, "loss": 4.3275, "step": 9710 }, { "epoch": 0.296609651802077, "grad_norm": 0.37648430466651917, "learning_rate": 3.99092166010833e-05, "loss": 4.339, "step": 9711 }, { "epoch": 0.29664019547953574, "grad_norm": 0.39262518286705017, "learning_rate": 3.9907290913986025e-05, "loss": 4.3802, "step": 9712 }, { "epoch": 0.2966707391569945, "grad_norm": 0.3872503936290741, "learning_rate": 3.990536508962966e-05, "loss": 4.3356, "step": 9713 }, { "epoch": 0.2967012828344533, "grad_norm": 0.37816253304481506, "learning_rate": 3.990343912803193e-05, "loss": 4.3784, "step": 9714 }, { "epoch": 0.29673182651191204, "grad_norm": 0.37561020255088806, "learning_rate": 3.990151302921058e-05, "loss": 4.3415, "step": 9715 }, { "epoch": 0.2967623701893708, "grad_norm": 0.39243271946907043, "learning_rate": 3.989958679318333e-05, "loss": 4.361, "step": 9716 }, { "epoch": 0.29679291386682954, "grad_norm": 0.36817437410354614, "learning_rate": 3.989766041996793e-05, "loss": 4.332, "step": 9717 }, { "epoch": 0.29682345754428835, "grad_norm": 0.37890830636024475, "learning_rate": 3.989573390958211e-05, "loss": 4.3247, "step": 9718 }, { "epoch": 0.2968540012217471, "grad_norm": 0.3838628828525543, "learning_rate": 3.989380726204361e-05, "loss": 4.3075, "step": 9719 }, { "epoch": 0.29688454489920585, "grad_norm": 0.383217453956604, "learning_rate": 3.9891880477370166e-05, "loss": 4.4139, "step": 9720 }, { "epoch": 0.29691508857666465, "grad_norm": 0.3601672649383545, "learning_rate": 3.988995355557952e-05, "loss": 4.3988, "step": 9721 }, { "epoch": 0.2969456322541234, "grad_norm": 0.37696143984794617, "learning_rate": 3.988802649668943e-05, "loss": 4.3394, "step": 9722 }, { "epoch": 0.29697617593158215, "grad_norm": 0.3708280324935913, "learning_rate": 3.98860993007176e-05, "loss": 4.3509, "step": 9723 }, { "epoch": 0.2970067196090409, "grad_norm": 0.3787931203842163, "learning_rate": 3.9884171967681814e-05, "loss": 4.2796, "step": 9724 }, { "epoch": 0.2970372632864997, "grad_norm": 0.37948277592658997, "learning_rate": 3.988224449759981e-05, "loss": 4.3721, "step": 9725 }, { "epoch": 0.29706780696395846, "grad_norm": 0.38736146688461304, "learning_rate": 3.9880316890489324e-05, "loss": 4.3566, "step": 9726 }, { "epoch": 0.2970983506414172, "grad_norm": 0.3683060109615326, "learning_rate": 3.9878389146368104e-05, "loss": 4.3883, "step": 9727 }, { "epoch": 0.297128894318876, "grad_norm": 0.37623342871665955, "learning_rate": 3.9876461265253914e-05, "loss": 4.3126, "step": 9728 }, { "epoch": 0.29715943799633476, "grad_norm": 0.3808709681034088, "learning_rate": 3.9874533247164495e-05, "loss": 4.4081, "step": 9729 }, { "epoch": 0.2971899816737935, "grad_norm": 0.3792557716369629, "learning_rate": 3.98726050921176e-05, "loss": 4.3095, "step": 9730 }, { "epoch": 0.2972205253512523, "grad_norm": 0.3852802515029907, "learning_rate": 3.9870676800130977e-05, "loss": 4.3635, "step": 9731 }, { "epoch": 0.29725106902871107, "grad_norm": 0.365181565284729, "learning_rate": 3.9868748371222385e-05, "loss": 4.2484, "step": 9732 }, { "epoch": 0.2972816127061698, "grad_norm": 0.36990559101104736, "learning_rate": 3.9866819805409594e-05, "loss": 4.4064, "step": 9733 }, { "epoch": 0.29731215638362857, "grad_norm": 0.3665747046470642, "learning_rate": 3.986489110271034e-05, "loss": 4.408, "step": 9734 }, { "epoch": 0.2973427000610874, "grad_norm": 0.37171027064323425, "learning_rate": 3.98629622631424e-05, "loss": 4.3733, "step": 9735 }, { "epoch": 0.2973732437385461, "grad_norm": 0.38351839780807495, "learning_rate": 3.986103328672351e-05, "loss": 4.3394, "step": 9736 }, { "epoch": 0.29740378741600487, "grad_norm": 0.37641438841819763, "learning_rate": 3.9859104173471464e-05, "loss": 4.4041, "step": 9737 }, { "epoch": 0.2974343310934637, "grad_norm": 0.36541762948036194, "learning_rate": 3.9857174923403997e-05, "loss": 4.3818, "step": 9738 }, { "epoch": 0.2974648747709224, "grad_norm": 0.3782201409339905, "learning_rate": 3.985524553653888e-05, "loss": 4.3404, "step": 9739 }, { "epoch": 0.2974954184483812, "grad_norm": 0.37255215644836426, "learning_rate": 3.9853316012893885e-05, "loss": 4.3433, "step": 9740 }, { "epoch": 0.2975259621258399, "grad_norm": 0.3771304190158844, "learning_rate": 3.985138635248677e-05, "loss": 4.3196, "step": 9741 }, { "epoch": 0.29755650580329873, "grad_norm": 0.37426048517227173, "learning_rate": 3.9849456555335297e-05, "loss": 4.3637, "step": 9742 }, { "epoch": 0.2975870494807575, "grad_norm": 0.375843346118927, "learning_rate": 3.984752662145726e-05, "loss": 4.3828, "step": 9743 }, { "epoch": 0.29761759315821623, "grad_norm": 0.3834055960178375, "learning_rate": 3.98455965508704e-05, "loss": 4.3328, "step": 9744 }, { "epoch": 0.29764813683567504, "grad_norm": 0.39436447620391846, "learning_rate": 3.98436663435925e-05, "loss": 4.3279, "step": 9745 }, { "epoch": 0.2976786805131338, "grad_norm": 0.3704582452774048, "learning_rate": 3.9841735999641326e-05, "loss": 4.3084, "step": 9746 }, { "epoch": 0.29770922419059254, "grad_norm": 0.3728600740432739, "learning_rate": 3.983980551903467e-05, "loss": 4.4321, "step": 9747 }, { "epoch": 0.2977397678680513, "grad_norm": 0.3824459910392761, "learning_rate": 3.983787490179028e-05, "loss": 4.2721, "step": 9748 }, { "epoch": 0.2977703115455101, "grad_norm": 0.3813267648220062, "learning_rate": 3.9835944147925966e-05, "loss": 4.3444, "step": 9749 }, { "epoch": 0.29780085522296884, "grad_norm": 0.3803819715976715, "learning_rate": 3.983401325745947e-05, "loss": 4.3772, "step": 9750 }, { "epoch": 0.2978313989004276, "grad_norm": 0.39256346225738525, "learning_rate": 3.983208223040859e-05, "loss": 4.4045, "step": 9751 }, { "epoch": 0.2978619425778864, "grad_norm": 0.3885410726070404, "learning_rate": 3.983015106679112e-05, "loss": 4.3125, "step": 9752 }, { "epoch": 0.29789248625534515, "grad_norm": 0.3819476366043091, "learning_rate": 3.9828219766624805e-05, "loss": 4.3468, "step": 9753 }, { "epoch": 0.2979230299328039, "grad_norm": 0.37002888321876526, "learning_rate": 3.982628832992745e-05, "loss": 4.408, "step": 9754 }, { "epoch": 0.2979535736102627, "grad_norm": 0.38071316480636597, "learning_rate": 3.9824356756716844e-05, "loss": 4.3537, "step": 9755 }, { "epoch": 0.29798411728772145, "grad_norm": 0.3864198923110962, "learning_rate": 3.982242504701076e-05, "loss": 4.3688, "step": 9756 }, { "epoch": 0.2980146609651802, "grad_norm": 0.37338271737098694, "learning_rate": 3.982049320082698e-05, "loss": 4.3565, "step": 9757 }, { "epoch": 0.29804520464263895, "grad_norm": 0.3833291828632355, "learning_rate": 3.9818561218183305e-05, "loss": 4.3182, "step": 9758 }, { "epoch": 0.29807574832009776, "grad_norm": 0.37511512637138367, "learning_rate": 3.9816629099097515e-05, "loss": 4.3813, "step": 9759 }, { "epoch": 0.2981062919975565, "grad_norm": 0.397784024477005, "learning_rate": 3.9814696843587406e-05, "loss": 4.3981, "step": 9760 }, { "epoch": 0.29813683567501525, "grad_norm": 0.36893001198768616, "learning_rate": 3.981276445167077e-05, "loss": 4.3835, "step": 9761 }, { "epoch": 0.29816737935247406, "grad_norm": 0.37425997853279114, "learning_rate": 3.981083192336539e-05, "loss": 4.3853, "step": 9762 }, { "epoch": 0.2981979230299328, "grad_norm": 0.40216755867004395, "learning_rate": 3.980889925868906e-05, "loss": 4.3357, "step": 9763 }, { "epoch": 0.29822846670739156, "grad_norm": 0.38436293601989746, "learning_rate": 3.9806966457659586e-05, "loss": 4.3318, "step": 9764 }, { "epoch": 0.2982590103848503, "grad_norm": 0.3872595727443695, "learning_rate": 3.9805033520294765e-05, "loss": 4.292, "step": 9765 }, { "epoch": 0.2982895540623091, "grad_norm": 0.37060633301734924, "learning_rate": 3.9803100446612384e-05, "loss": 4.3285, "step": 9766 }, { "epoch": 0.29832009773976786, "grad_norm": 0.38091546297073364, "learning_rate": 3.9801167236630245e-05, "loss": 4.3835, "step": 9767 }, { "epoch": 0.2983506414172266, "grad_norm": 0.36931830644607544, "learning_rate": 3.979923389036615e-05, "loss": 4.2843, "step": 9768 }, { "epoch": 0.2983811850946854, "grad_norm": 0.3739318251609802, "learning_rate": 3.97973004078379e-05, "loss": 4.3407, "step": 9769 }, { "epoch": 0.29841172877214417, "grad_norm": 0.392188161611557, "learning_rate": 3.9795366789063295e-05, "loss": 4.3864, "step": 9770 }, { "epoch": 0.2984422724496029, "grad_norm": 0.37206852436065674, "learning_rate": 3.9793433034060145e-05, "loss": 4.3811, "step": 9771 }, { "epoch": 0.2984728161270617, "grad_norm": 0.3889906406402588, "learning_rate": 3.979149914284624e-05, "loss": 4.3408, "step": 9772 }, { "epoch": 0.2985033598045205, "grad_norm": 0.3730085790157318, "learning_rate": 3.978956511543942e-05, "loss": 4.2781, "step": 9773 }, { "epoch": 0.2985339034819792, "grad_norm": 0.370069682598114, "learning_rate": 3.978763095185745e-05, "loss": 4.3332, "step": 9774 }, { "epoch": 0.298564447159438, "grad_norm": 0.3705922067165375, "learning_rate": 3.978569665211817e-05, "loss": 4.2783, "step": 9775 }, { "epoch": 0.2985949908368968, "grad_norm": 0.3786734342575073, "learning_rate": 3.9783762216239366e-05, "loss": 4.4258, "step": 9776 }, { "epoch": 0.29862553451435553, "grad_norm": 0.3693810999393463, "learning_rate": 3.978182764423887e-05, "loss": 4.3176, "step": 9777 }, { "epoch": 0.2986560781918143, "grad_norm": 0.38532039523124695, "learning_rate": 3.977989293613449e-05, "loss": 4.2439, "step": 9778 }, { "epoch": 0.2986866218692731, "grad_norm": 0.3848631680011749, "learning_rate": 3.977795809194403e-05, "loss": 4.2051, "step": 9779 }, { "epoch": 0.29871716554673183, "grad_norm": 0.3870796263217926, "learning_rate": 3.9776023111685315e-05, "loss": 4.2886, "step": 9780 }, { "epoch": 0.2987477092241906, "grad_norm": 0.3713463544845581, "learning_rate": 3.9774087995376165e-05, "loss": 4.3479, "step": 9781 }, { "epoch": 0.29877825290164933, "grad_norm": 0.3697362244129181, "learning_rate": 3.977215274303438e-05, "loss": 4.4703, "step": 9782 }, { "epoch": 0.29880879657910814, "grad_norm": 0.3810351490974426, "learning_rate": 3.9770217354677795e-05, "loss": 4.3494, "step": 9783 }, { "epoch": 0.2988393402565669, "grad_norm": 0.36999407410621643, "learning_rate": 3.9768281830324224e-05, "loss": 4.4105, "step": 9784 }, { "epoch": 0.29886988393402564, "grad_norm": 0.38389626145362854, "learning_rate": 3.976634616999149e-05, "loss": 4.3005, "step": 9785 }, { "epoch": 0.29890042761148444, "grad_norm": 0.38089630007743835, "learning_rate": 3.97644103736974e-05, "loss": 4.3493, "step": 9786 }, { "epoch": 0.2989309712889432, "grad_norm": 0.3705242872238159, "learning_rate": 3.9762474441459816e-05, "loss": 4.4013, "step": 9787 }, { "epoch": 0.29896151496640194, "grad_norm": 0.38748425245285034, "learning_rate": 3.976053837329653e-05, "loss": 4.4105, "step": 9788 }, { "epoch": 0.29899205864386075, "grad_norm": 0.3838464915752411, "learning_rate": 3.975860216922537e-05, "loss": 4.2838, "step": 9789 }, { "epoch": 0.2990226023213195, "grad_norm": 0.37713623046875, "learning_rate": 3.9756665829264184e-05, "loss": 4.2631, "step": 9790 }, { "epoch": 0.29905314599877825, "grad_norm": 0.3785203993320465, "learning_rate": 3.9754729353430786e-05, "loss": 4.3742, "step": 9791 }, { "epoch": 0.299083689676237, "grad_norm": 0.3746117055416107, "learning_rate": 3.9752792741743006e-05, "loss": 4.2854, "step": 9792 }, { "epoch": 0.2991142333536958, "grad_norm": 0.38893815875053406, "learning_rate": 3.9750855994218674e-05, "loss": 4.3767, "step": 9793 }, { "epoch": 0.29914477703115455, "grad_norm": 0.3699991703033447, "learning_rate": 3.974891911087563e-05, "loss": 4.2942, "step": 9794 }, { "epoch": 0.2991753207086133, "grad_norm": 0.40180280804634094, "learning_rate": 3.974698209173171e-05, "loss": 4.3991, "step": 9795 }, { "epoch": 0.2992058643860721, "grad_norm": 0.38400405645370483, "learning_rate": 3.974504493680474e-05, "loss": 4.3116, "step": 9796 }, { "epoch": 0.29923640806353086, "grad_norm": 0.3748064637184143, "learning_rate": 3.974310764611255e-05, "loss": 4.284, "step": 9797 }, { "epoch": 0.2992669517409896, "grad_norm": 0.3824021518230438, "learning_rate": 3.974117021967301e-05, "loss": 4.2945, "step": 9798 }, { "epoch": 0.29929749541844836, "grad_norm": 0.39879077672958374, "learning_rate": 3.973923265750392e-05, "loss": 4.3352, "step": 9799 }, { "epoch": 0.29932803909590716, "grad_norm": 0.3802162706851959, "learning_rate": 3.973729495962314e-05, "loss": 4.4016, "step": 9800 }, { "epoch": 0.2993585827733659, "grad_norm": 0.3811735510826111, "learning_rate": 3.973535712604851e-05, "loss": 4.3775, "step": 9801 }, { "epoch": 0.29938912645082466, "grad_norm": 0.38083720207214355, "learning_rate": 3.973341915679787e-05, "loss": 4.407, "step": 9802 }, { "epoch": 0.29941967012828347, "grad_norm": 0.38585665822029114, "learning_rate": 3.973148105188906e-05, "loss": 4.2611, "step": 9803 }, { "epoch": 0.2994502138057422, "grad_norm": 0.37796682119369507, "learning_rate": 3.9729542811339936e-05, "loss": 4.3723, "step": 9804 }, { "epoch": 0.29948075748320097, "grad_norm": 0.3867664039134979, "learning_rate": 3.972760443516834e-05, "loss": 4.3684, "step": 9805 }, { "epoch": 0.29951130116065977, "grad_norm": 0.3671659827232361, "learning_rate": 3.972566592339211e-05, "loss": 4.3231, "step": 9806 }, { "epoch": 0.2995418448381185, "grad_norm": 0.389892041683197, "learning_rate": 3.972372727602911e-05, "loss": 4.2848, "step": 9807 }, { "epoch": 0.29957238851557727, "grad_norm": 0.3736213445663452, "learning_rate": 3.972178849309718e-05, "loss": 4.3427, "step": 9808 }, { "epoch": 0.299602932193036, "grad_norm": 0.37999966740608215, "learning_rate": 3.9719849574614174e-05, "loss": 4.2941, "step": 9809 }, { "epoch": 0.2996334758704948, "grad_norm": 0.38253679871559143, "learning_rate": 3.971791052059794e-05, "loss": 4.4054, "step": 9810 }, { "epoch": 0.2996640195479536, "grad_norm": 0.381125807762146, "learning_rate": 3.971597133106634e-05, "loss": 4.4165, "step": 9811 }, { "epoch": 0.2996945632254123, "grad_norm": 0.3705863058567047, "learning_rate": 3.9714032006037224e-05, "loss": 4.3712, "step": 9812 }, { "epoch": 0.29972510690287113, "grad_norm": 0.3765886425971985, "learning_rate": 3.971209254552846e-05, "loss": 4.3685, "step": 9813 }, { "epoch": 0.2997556505803299, "grad_norm": 0.3775480091571808, "learning_rate": 3.971015294955789e-05, "loss": 4.3884, "step": 9814 }, { "epoch": 0.29978619425778863, "grad_norm": 0.38999485969543457, "learning_rate": 3.970821321814338e-05, "loss": 4.383, "step": 9815 }, { "epoch": 0.2998167379352474, "grad_norm": 0.3709666132926941, "learning_rate": 3.9706273351302784e-05, "loss": 4.3369, "step": 9816 }, { "epoch": 0.2998472816127062, "grad_norm": 0.37923726439476013, "learning_rate": 3.9704333349053965e-05, "loss": 4.2841, "step": 9817 }, { "epoch": 0.29987782529016493, "grad_norm": 0.3751599192619324, "learning_rate": 3.970239321141479e-05, "loss": 4.2575, "step": 9818 }, { "epoch": 0.2999083689676237, "grad_norm": 0.37693995237350464, "learning_rate": 3.970045293840313e-05, "loss": 4.2899, "step": 9819 }, { "epoch": 0.2999389126450825, "grad_norm": 0.3707006275653839, "learning_rate": 3.9698512530036836e-05, "loss": 4.3008, "step": 9820 }, { "epoch": 0.29996945632254124, "grad_norm": 0.3830489218235016, "learning_rate": 3.969657198633378e-05, "loss": 4.316, "step": 9821 }, { "epoch": 0.3, "grad_norm": 0.38439759612083435, "learning_rate": 3.969463130731183e-05, "loss": 4.3222, "step": 9822 }, { "epoch": 0.30003054367745874, "grad_norm": 0.3622502088546753, "learning_rate": 3.969269049298886e-05, "loss": 4.3139, "step": 9823 }, { "epoch": 0.30006108735491754, "grad_norm": 0.3822859525680542, "learning_rate": 3.969074954338272e-05, "loss": 4.3883, "step": 9824 }, { "epoch": 0.3000916310323763, "grad_norm": 0.3836230933666229, "learning_rate": 3.968880845851131e-05, "loss": 4.4031, "step": 9825 }, { "epoch": 0.30012217470983504, "grad_norm": 0.3758622109889984, "learning_rate": 3.968686723839248e-05, "loss": 4.3572, "step": 9826 }, { "epoch": 0.30015271838729385, "grad_norm": 0.387540727853775, "learning_rate": 3.968492588304412e-05, "loss": 4.3269, "step": 9827 }, { "epoch": 0.3001832620647526, "grad_norm": 0.3839552700519562, "learning_rate": 3.968298439248409e-05, "loss": 4.3598, "step": 9828 }, { "epoch": 0.30021380574221135, "grad_norm": 0.3888583779335022, "learning_rate": 3.968104276673028e-05, "loss": 4.3403, "step": 9829 }, { "epoch": 0.30024434941967015, "grad_norm": 0.37679344415664673, "learning_rate": 3.967910100580054e-05, "loss": 4.37, "step": 9830 }, { "epoch": 0.3002748930971289, "grad_norm": 0.3812817931175232, "learning_rate": 3.96771591097128e-05, "loss": 4.3587, "step": 9831 }, { "epoch": 0.30030543677458765, "grad_norm": 0.38583099842071533, "learning_rate": 3.9675217078484896e-05, "loss": 4.3063, "step": 9832 }, { "epoch": 0.3003359804520464, "grad_norm": 0.3789534866809845, "learning_rate": 3.9673274912134714e-05, "loss": 4.3131, "step": 9833 }, { "epoch": 0.3003665241295052, "grad_norm": 0.38380032777786255, "learning_rate": 3.9671332610680155e-05, "loss": 4.367, "step": 9834 }, { "epoch": 0.30039706780696396, "grad_norm": 0.3796879053115845, "learning_rate": 3.96693901741391e-05, "loss": 4.3751, "step": 9835 }, { "epoch": 0.3004276114844227, "grad_norm": 0.3818758726119995, "learning_rate": 3.966744760252942e-05, "loss": 4.3323, "step": 9836 }, { "epoch": 0.3004581551618815, "grad_norm": 0.37777405977249146, "learning_rate": 3.9665504895869004e-05, "loss": 4.3218, "step": 9837 }, { "epoch": 0.30048869883934026, "grad_norm": 0.3722052276134491, "learning_rate": 3.966356205417575e-05, "loss": 4.215, "step": 9838 }, { "epoch": 0.300519242516799, "grad_norm": 0.38285359740257263, "learning_rate": 3.966161907746755e-05, "loss": 4.3517, "step": 9839 }, { "epoch": 0.30054978619425776, "grad_norm": 0.38109922409057617, "learning_rate": 3.9659675965762274e-05, "loss": 4.2881, "step": 9840 }, { "epoch": 0.30058032987171657, "grad_norm": 0.3924720287322998, "learning_rate": 3.9657732719077825e-05, "loss": 4.4313, "step": 9841 }, { "epoch": 0.3006108735491753, "grad_norm": 0.37707045674324036, "learning_rate": 3.965578933743209e-05, "loss": 4.365, "step": 9842 }, { "epoch": 0.30064141722663407, "grad_norm": 0.36438560485839844, "learning_rate": 3.965384582084297e-05, "loss": 4.3624, "step": 9843 }, { "epoch": 0.30067196090409287, "grad_norm": 0.38681966066360474, "learning_rate": 3.965190216932836e-05, "loss": 4.3465, "step": 9844 }, { "epoch": 0.3007025045815516, "grad_norm": 0.39779964089393616, "learning_rate": 3.9649958382906157e-05, "loss": 4.2792, "step": 9845 }, { "epoch": 0.30073304825901037, "grad_norm": 0.40114668011665344, "learning_rate": 3.964801446159425e-05, "loss": 4.4216, "step": 9846 }, { "epoch": 0.3007635919364692, "grad_norm": 0.37137964367866516, "learning_rate": 3.964607040541054e-05, "loss": 4.3332, "step": 9847 }, { "epoch": 0.3007941356139279, "grad_norm": 0.3812026381492615, "learning_rate": 3.964412621437293e-05, "loss": 4.3739, "step": 9848 }, { "epoch": 0.3008246792913867, "grad_norm": 0.39091405272483826, "learning_rate": 3.964218188849933e-05, "loss": 4.3944, "step": 9849 }, { "epoch": 0.3008552229688454, "grad_norm": 0.3750297725200653, "learning_rate": 3.9640237427807625e-05, "loss": 4.3784, "step": 9850 }, { "epoch": 0.30088576664630423, "grad_norm": 0.38416725397109985, "learning_rate": 3.9638292832315724e-05, "loss": 4.3394, "step": 9851 }, { "epoch": 0.300916310323763, "grad_norm": 0.37118566036224365, "learning_rate": 3.963634810204154e-05, "loss": 4.3362, "step": 9852 }, { "epoch": 0.30094685400122173, "grad_norm": 0.36677536368370056, "learning_rate": 3.963440323700298e-05, "loss": 4.2998, "step": 9853 }, { "epoch": 0.30097739767868054, "grad_norm": 0.37128424644470215, "learning_rate": 3.9632458237217935e-05, "loss": 4.3146, "step": 9854 }, { "epoch": 0.3010079413561393, "grad_norm": 0.37255242466926575, "learning_rate": 3.9630513102704325e-05, "loss": 4.3984, "step": 9855 }, { "epoch": 0.30103848503359804, "grad_norm": 0.37710919976234436, "learning_rate": 3.962856783348006e-05, "loss": 4.3413, "step": 9856 }, { "epoch": 0.3010690287110568, "grad_norm": 0.3798981010913849, "learning_rate": 3.9626622429563053e-05, "loss": 4.3369, "step": 9857 }, { "epoch": 0.3010995723885156, "grad_norm": 0.3656614422798157, "learning_rate": 3.962467689097121e-05, "loss": 4.3859, "step": 9858 }, { "epoch": 0.30113011606597434, "grad_norm": 0.36911821365356445, "learning_rate": 3.962273121772245e-05, "loss": 4.3556, "step": 9859 }, { "epoch": 0.3011606597434331, "grad_norm": 0.3819763958454132, "learning_rate": 3.962078540983468e-05, "loss": 4.3608, "step": 9860 }, { "epoch": 0.3011912034208919, "grad_norm": 0.38786637783050537, "learning_rate": 3.9618839467325825e-05, "loss": 4.2343, "step": 9861 }, { "epoch": 0.30122174709835065, "grad_norm": 0.3688848614692688, "learning_rate": 3.96168933902138e-05, "loss": 4.3954, "step": 9862 }, { "epoch": 0.3012522907758094, "grad_norm": 0.37482979893684387, "learning_rate": 3.961494717851652e-05, "loss": 4.3282, "step": 9863 }, { "epoch": 0.3012828344532682, "grad_norm": 0.3739694356918335, "learning_rate": 3.9613000832251906e-05, "loss": 4.3362, "step": 9864 }, { "epoch": 0.30131337813072695, "grad_norm": 0.3672737777233124, "learning_rate": 3.9611054351437885e-05, "loss": 4.371, "step": 9865 }, { "epoch": 0.3013439218081857, "grad_norm": 0.37148794531822205, "learning_rate": 3.960910773609237e-05, "loss": 4.407, "step": 9866 }, { "epoch": 0.30137446548564445, "grad_norm": 0.3708875775337219, "learning_rate": 3.960716098623329e-05, "loss": 4.3298, "step": 9867 }, { "epoch": 0.30140500916310325, "grad_norm": 0.3765994906425476, "learning_rate": 3.9605214101878565e-05, "loss": 4.3355, "step": 9868 }, { "epoch": 0.301435552840562, "grad_norm": 0.384113073348999, "learning_rate": 3.960326708304613e-05, "loss": 4.39, "step": 9869 }, { "epoch": 0.30146609651802075, "grad_norm": 0.3857795298099518, "learning_rate": 3.960131992975391e-05, "loss": 4.3928, "step": 9870 }, { "epoch": 0.30149664019547956, "grad_norm": 0.37445327639579773, "learning_rate": 3.959937264201982e-05, "loss": 4.2776, "step": 9871 }, { "epoch": 0.3015271838729383, "grad_norm": 0.37695568799972534, "learning_rate": 3.9597425219861804e-05, "loss": 4.1646, "step": 9872 }, { "epoch": 0.30155772755039706, "grad_norm": 0.38012298941612244, "learning_rate": 3.959547766329779e-05, "loss": 4.3607, "step": 9873 }, { "epoch": 0.3015882712278558, "grad_norm": 0.3887239992618561, "learning_rate": 3.959352997234571e-05, "loss": 4.3672, "step": 9874 }, { "epoch": 0.3016188149053146, "grad_norm": 0.3743123710155487, "learning_rate": 3.959158214702349e-05, "loss": 4.341, "step": 9875 }, { "epoch": 0.30164935858277336, "grad_norm": 0.3742733895778656, "learning_rate": 3.9589634187349076e-05, "loss": 4.3342, "step": 9876 }, { "epoch": 0.3016799022602321, "grad_norm": 0.3809216022491455, "learning_rate": 3.9587686093340404e-05, "loss": 4.2295, "step": 9877 }, { "epoch": 0.3017104459376909, "grad_norm": 0.3856380581855774, "learning_rate": 3.958573786501539e-05, "loss": 4.2861, "step": 9878 }, { "epoch": 0.30174098961514967, "grad_norm": 0.36737194657325745, "learning_rate": 3.958378950239201e-05, "loss": 4.3584, "step": 9879 }, { "epoch": 0.3017715332926084, "grad_norm": 0.3838968575000763, "learning_rate": 3.9581841005488164e-05, "loss": 4.3871, "step": 9880 }, { "epoch": 0.3018020769700672, "grad_norm": 0.37323978543281555, "learning_rate": 3.957989237432181e-05, "loss": 4.3757, "step": 9881 }, { "epoch": 0.301832620647526, "grad_norm": 0.37942391633987427, "learning_rate": 3.957794360891091e-05, "loss": 4.3199, "step": 9882 }, { "epoch": 0.3018631643249847, "grad_norm": 0.3829757571220398, "learning_rate": 3.957599470927337e-05, "loss": 4.4258, "step": 9883 }, { "epoch": 0.3018937080024435, "grad_norm": 0.3620629608631134, "learning_rate": 3.957404567542716e-05, "loss": 4.316, "step": 9884 }, { "epoch": 0.3019242516799023, "grad_norm": 0.3705888092517853, "learning_rate": 3.9572096507390214e-05, "loss": 4.3088, "step": 9885 }, { "epoch": 0.301954795357361, "grad_norm": 0.3834453821182251, "learning_rate": 3.957014720518049e-05, "loss": 4.2526, "step": 9886 }, { "epoch": 0.3019853390348198, "grad_norm": 0.3648393452167511, "learning_rate": 3.956819776881592e-05, "loss": 4.3295, "step": 9887 }, { "epoch": 0.3020158827122786, "grad_norm": 0.3708308935165405, "learning_rate": 3.956624819831447e-05, "loss": 4.3195, "step": 9888 }, { "epoch": 0.30204642638973733, "grad_norm": 0.3914233148097992, "learning_rate": 3.9564298493694086e-05, "loss": 4.3813, "step": 9889 }, { "epoch": 0.3020769700671961, "grad_norm": 0.37440741062164307, "learning_rate": 3.9562348654972716e-05, "loss": 4.31, "step": 9890 }, { "epoch": 0.30210751374465483, "grad_norm": 0.42093023657798767, "learning_rate": 3.956039868216831e-05, "loss": 4.3204, "step": 9891 }, { "epoch": 0.30213805742211364, "grad_norm": 0.37907159328460693, "learning_rate": 3.955844857529882e-05, "loss": 4.2869, "step": 9892 }, { "epoch": 0.3021686010995724, "grad_norm": 0.37655726075172424, "learning_rate": 3.955649833438222e-05, "loss": 4.3666, "step": 9893 }, { "epoch": 0.30219914477703114, "grad_norm": 0.38113927841186523, "learning_rate": 3.955454795943645e-05, "loss": 4.2909, "step": 9894 }, { "epoch": 0.30222968845448994, "grad_norm": 0.3872371315956116, "learning_rate": 3.955259745047948e-05, "loss": 4.3769, "step": 9895 }, { "epoch": 0.3022602321319487, "grad_norm": 0.38030192255973816, "learning_rate": 3.9550646807529255e-05, "loss": 4.3587, "step": 9896 }, { "epoch": 0.30229077580940744, "grad_norm": 0.39112618565559387, "learning_rate": 3.954869603060375e-05, "loss": 4.3721, "step": 9897 }, { "epoch": 0.3023213194868662, "grad_norm": 0.37486135959625244, "learning_rate": 3.9546745119720926e-05, "loss": 4.3929, "step": 9898 }, { "epoch": 0.302351863164325, "grad_norm": 0.381638765335083, "learning_rate": 3.954479407489873e-05, "loss": 4.3151, "step": 9899 }, { "epoch": 0.30238240684178375, "grad_norm": 0.3902083933353424, "learning_rate": 3.9542842896155144e-05, "loss": 4.3275, "step": 9900 }, { "epoch": 0.3024129505192425, "grad_norm": 0.37759923934936523, "learning_rate": 3.9540891583508124e-05, "loss": 4.298, "step": 9901 }, { "epoch": 0.3024434941967013, "grad_norm": 0.37195757031440735, "learning_rate": 3.9538940136975634e-05, "loss": 4.3399, "step": 9902 }, { "epoch": 0.30247403787416005, "grad_norm": 0.37299612164497375, "learning_rate": 3.953698855657565e-05, "loss": 4.2689, "step": 9903 }, { "epoch": 0.3025045815516188, "grad_norm": 0.37737902998924255, "learning_rate": 3.953503684232614e-05, "loss": 4.3438, "step": 9904 }, { "epoch": 0.3025351252290776, "grad_norm": 0.3772638142108917, "learning_rate": 3.953308499424507e-05, "loss": 4.3863, "step": 9905 }, { "epoch": 0.30256566890653636, "grad_norm": 0.3826656639575958, "learning_rate": 3.953113301235042e-05, "loss": 4.395, "step": 9906 }, { "epoch": 0.3025962125839951, "grad_norm": 0.39269429445266724, "learning_rate": 3.952918089666015e-05, "loss": 4.3667, "step": 9907 }, { "epoch": 0.30262675626145386, "grad_norm": 0.3861483633518219, "learning_rate": 3.952722864719225e-05, "loss": 4.3565, "step": 9908 }, { "epoch": 0.30265729993891266, "grad_norm": 0.3782549202442169, "learning_rate": 3.952527626396467e-05, "loss": 4.3133, "step": 9909 }, { "epoch": 0.3026878436163714, "grad_norm": 0.3843095302581787, "learning_rate": 3.952332374699542e-05, "loss": 4.2735, "step": 9910 }, { "epoch": 0.30271838729383016, "grad_norm": 0.38964539766311646, "learning_rate": 3.9521371096302454e-05, "loss": 4.3315, "step": 9911 }, { "epoch": 0.30274893097128897, "grad_norm": 0.3736797869205475, "learning_rate": 3.951941831190376e-05, "loss": 4.3352, "step": 9912 }, { "epoch": 0.3027794746487477, "grad_norm": 0.37427592277526855, "learning_rate": 3.9517465393817316e-05, "loss": 4.301, "step": 9913 }, { "epoch": 0.30281001832620646, "grad_norm": 0.39371687173843384, "learning_rate": 3.95155123420611e-05, "loss": 4.267, "step": 9914 }, { "epoch": 0.3028405620036652, "grad_norm": 0.3792767822742462, "learning_rate": 3.951355915665311e-05, "loss": 4.3094, "step": 9915 }, { "epoch": 0.302871105681124, "grad_norm": 0.3708314001560211, "learning_rate": 3.951160583761131e-05, "loss": 4.3464, "step": 9916 }, { "epoch": 0.30290164935858277, "grad_norm": 0.38905245065689087, "learning_rate": 3.9509652384953694e-05, "loss": 4.3168, "step": 9917 }, { "epoch": 0.3029321930360415, "grad_norm": 0.3767615258693695, "learning_rate": 3.950769879869825e-05, "loss": 4.2895, "step": 9918 }, { "epoch": 0.3029627367135003, "grad_norm": 0.38012003898620605, "learning_rate": 3.950574507886296e-05, "loss": 4.3812, "step": 9919 }, { "epoch": 0.3029932803909591, "grad_norm": 0.38016796112060547, "learning_rate": 3.950379122546582e-05, "loss": 4.3662, "step": 9920 }, { "epoch": 0.3030238240684178, "grad_norm": 0.3840892016887665, "learning_rate": 3.950183723852482e-05, "loss": 4.3689, "step": 9921 }, { "epoch": 0.30305436774587663, "grad_norm": 0.3739337921142578, "learning_rate": 3.9499883118057946e-05, "loss": 4.3454, "step": 9922 }, { "epoch": 0.3030849114233354, "grad_norm": 0.36787670850753784, "learning_rate": 3.949792886408319e-05, "loss": 4.3691, "step": 9923 }, { "epoch": 0.30311545510079413, "grad_norm": 0.37369948625564575, "learning_rate": 3.949597447661856e-05, "loss": 4.3318, "step": 9924 }, { "epoch": 0.3031459987782529, "grad_norm": 0.38815590739250183, "learning_rate": 3.949401995568203e-05, "loss": 4.3493, "step": 9925 }, { "epoch": 0.3031765424557117, "grad_norm": 0.3880855143070221, "learning_rate": 3.94920653012916e-05, "loss": 4.2566, "step": 9926 }, { "epoch": 0.30320708613317043, "grad_norm": 0.37612301111221313, "learning_rate": 3.9490110513465285e-05, "loss": 4.3897, "step": 9927 }, { "epoch": 0.3032376298106292, "grad_norm": 0.37795352935791016, "learning_rate": 3.948815559222107e-05, "loss": 4.2955, "step": 9928 }, { "epoch": 0.303268173488088, "grad_norm": 0.3844577670097351, "learning_rate": 3.9486200537576956e-05, "loss": 4.3577, "step": 9929 }, { "epoch": 0.30329871716554674, "grad_norm": 0.3870249390602112, "learning_rate": 3.948424534955095e-05, "loss": 4.3269, "step": 9930 }, { "epoch": 0.3033292608430055, "grad_norm": 0.3682626783847809, "learning_rate": 3.948229002816104e-05, "loss": 4.3482, "step": 9931 }, { "epoch": 0.30335980452046424, "grad_norm": 0.3821259140968323, "learning_rate": 3.948033457342525e-05, "loss": 4.375, "step": 9932 }, { "epoch": 0.30339034819792304, "grad_norm": 0.39015379548072815, "learning_rate": 3.947837898536157e-05, "loss": 4.3009, "step": 9933 }, { "epoch": 0.3034208918753818, "grad_norm": 0.38575977087020874, "learning_rate": 3.947642326398801e-05, "loss": 4.2505, "step": 9934 }, { "epoch": 0.30345143555284054, "grad_norm": 0.39121052622795105, "learning_rate": 3.947446740932258e-05, "loss": 4.4117, "step": 9935 }, { "epoch": 0.30348197923029935, "grad_norm": 0.38414207100868225, "learning_rate": 3.947251142138329e-05, "loss": 4.3772, "step": 9936 }, { "epoch": 0.3035125229077581, "grad_norm": 0.37796658277511597, "learning_rate": 3.9470555300188136e-05, "loss": 4.2955, "step": 9937 }, { "epoch": 0.30354306658521685, "grad_norm": 0.3783069849014282, "learning_rate": 3.946859904575515e-05, "loss": 4.3082, "step": 9938 }, { "epoch": 0.30357361026267565, "grad_norm": 0.3894554376602173, "learning_rate": 3.9466642658102324e-05, "loss": 4.3287, "step": 9939 }, { "epoch": 0.3036041539401344, "grad_norm": 0.37708160281181335, "learning_rate": 3.9464686137247686e-05, "loss": 4.3768, "step": 9940 }, { "epoch": 0.30363469761759315, "grad_norm": 0.36255404353141785, "learning_rate": 3.946272948320925e-05, "loss": 4.3969, "step": 9941 }, { "epoch": 0.3036652412950519, "grad_norm": 0.369479775428772, "learning_rate": 3.9460772696005025e-05, "loss": 4.3009, "step": 9942 }, { "epoch": 0.3036957849725107, "grad_norm": 0.3810105323791504, "learning_rate": 3.9458815775653023e-05, "loss": 4.2559, "step": 9943 }, { "epoch": 0.30372632864996946, "grad_norm": 0.390560507774353, "learning_rate": 3.9456858722171275e-05, "loss": 4.3393, "step": 9944 }, { "epoch": 0.3037568723274282, "grad_norm": 0.3756517767906189, "learning_rate": 3.94549015355778e-05, "loss": 4.3045, "step": 9945 }, { "epoch": 0.303787416004887, "grad_norm": 0.3858628571033478, "learning_rate": 3.945294421589061e-05, "loss": 4.3334, "step": 9946 }, { "epoch": 0.30381795968234576, "grad_norm": 0.3819393515586853, "learning_rate": 3.945098676312773e-05, "loss": 4.3735, "step": 9947 }, { "epoch": 0.3038485033598045, "grad_norm": 0.38050299882888794, "learning_rate": 3.944902917730719e-05, "loss": 4.3397, "step": 9948 }, { "epoch": 0.30387904703726326, "grad_norm": 0.3830631375312805, "learning_rate": 3.944707145844701e-05, "loss": 4.4238, "step": 9949 }, { "epoch": 0.30390959071472207, "grad_norm": 0.3801966905593872, "learning_rate": 3.944511360656521e-05, "loss": 4.3444, "step": 9950 }, { "epoch": 0.3039401343921808, "grad_norm": 0.37627288699150085, "learning_rate": 3.9443155621679824e-05, "loss": 4.3626, "step": 9951 }, { "epoch": 0.30397067806963957, "grad_norm": 0.3847006857395172, "learning_rate": 3.944119750380888e-05, "loss": 4.1542, "step": 9952 }, { "epoch": 0.30400122174709837, "grad_norm": 0.37409335374832153, "learning_rate": 3.94392392529704e-05, "loss": 4.2757, "step": 9953 }, { "epoch": 0.3040317654245571, "grad_norm": 0.38167256116867065, "learning_rate": 3.9437280869182426e-05, "loss": 4.3017, "step": 9954 }, { "epoch": 0.30406230910201587, "grad_norm": 0.38067519664764404, "learning_rate": 3.9435322352462985e-05, "loss": 4.4041, "step": 9955 }, { "epoch": 0.3040928527794747, "grad_norm": 0.3866977393627167, "learning_rate": 3.943336370283011e-05, "loss": 4.2876, "step": 9956 }, { "epoch": 0.3041233964569334, "grad_norm": 0.37153953313827515, "learning_rate": 3.943140492030183e-05, "loss": 4.2873, "step": 9957 }, { "epoch": 0.3041539401343922, "grad_norm": 0.377890408039093, "learning_rate": 3.942944600489619e-05, "loss": 4.2734, "step": 9958 }, { "epoch": 0.3041844838118509, "grad_norm": 0.37023279070854187, "learning_rate": 3.942748695663121e-05, "loss": 4.3467, "step": 9959 }, { "epoch": 0.30421502748930973, "grad_norm": 0.380555123090744, "learning_rate": 3.942552777552495e-05, "loss": 4.3058, "step": 9960 }, { "epoch": 0.3042455711667685, "grad_norm": 0.3737746477127075, "learning_rate": 3.942356846159544e-05, "loss": 4.2359, "step": 9961 }, { "epoch": 0.30427611484422723, "grad_norm": 0.38616085052490234, "learning_rate": 3.942160901486072e-05, "loss": 4.3642, "step": 9962 }, { "epoch": 0.30430665852168604, "grad_norm": 0.38148218393325806, "learning_rate": 3.941964943533882e-05, "loss": 4.3414, "step": 9963 }, { "epoch": 0.3043372021991448, "grad_norm": 0.3756113350391388, "learning_rate": 3.94176897230478e-05, "loss": 4.3657, "step": 9964 }, { "epoch": 0.30436774587660353, "grad_norm": 0.38926222920417786, "learning_rate": 3.9415729878005705e-05, "loss": 4.3669, "step": 9965 }, { "epoch": 0.3043982895540623, "grad_norm": 0.3767375349998474, "learning_rate": 3.941376990023057e-05, "loss": 4.2926, "step": 9966 }, { "epoch": 0.3044288332315211, "grad_norm": 0.3693491518497467, "learning_rate": 3.941180978974043e-05, "loss": 4.3068, "step": 9967 }, { "epoch": 0.30445937690897984, "grad_norm": 0.3817253112792969, "learning_rate": 3.9409849546553367e-05, "loss": 4.3979, "step": 9968 }, { "epoch": 0.3044899205864386, "grad_norm": 0.38451629877090454, "learning_rate": 3.94078891706874e-05, "loss": 4.3258, "step": 9969 }, { "epoch": 0.3045204642638974, "grad_norm": 0.3684500753879547, "learning_rate": 3.940592866216059e-05, "loss": 4.3217, "step": 9970 }, { "epoch": 0.30455100794135614, "grad_norm": 0.3726428151130676, "learning_rate": 3.940396802099099e-05, "loss": 4.3481, "step": 9971 }, { "epoch": 0.3045815516188149, "grad_norm": 0.3798452615737915, "learning_rate": 3.940200724719665e-05, "loss": 4.3265, "step": 9972 }, { "epoch": 0.30461209529627364, "grad_norm": 0.37734436988830566, "learning_rate": 3.9400046340795624e-05, "loss": 4.3266, "step": 9973 }, { "epoch": 0.30464263897373245, "grad_norm": 0.3751029670238495, "learning_rate": 3.939808530180597e-05, "loss": 4.3897, "step": 9974 }, { "epoch": 0.3046731826511912, "grad_norm": 0.3758823871612549, "learning_rate": 3.939612413024574e-05, "loss": 4.2659, "step": 9975 }, { "epoch": 0.30470372632864995, "grad_norm": 0.37118253111839294, "learning_rate": 3.9394162826133e-05, "loss": 4.3746, "step": 9976 }, { "epoch": 0.30473427000610875, "grad_norm": 0.38137319684028625, "learning_rate": 3.9392201389485795e-05, "loss": 4.4162, "step": 9977 }, { "epoch": 0.3047648136835675, "grad_norm": 0.3811282515525818, "learning_rate": 3.939023982032219e-05, "loss": 4.3608, "step": 9978 }, { "epoch": 0.30479535736102625, "grad_norm": 0.3741460144519806, "learning_rate": 3.938827811866025e-05, "loss": 4.2643, "step": 9979 }, { "epoch": 0.30482590103848506, "grad_norm": 0.3736923038959503, "learning_rate": 3.9386316284518045e-05, "loss": 4.4049, "step": 9980 }, { "epoch": 0.3048564447159438, "grad_norm": 0.3783639073371887, "learning_rate": 3.938435431791362e-05, "loss": 4.3645, "step": 9981 }, { "epoch": 0.30488698839340256, "grad_norm": 0.3787083923816681, "learning_rate": 3.938239221886505e-05, "loss": 4.2798, "step": 9982 }, { "epoch": 0.3049175320708613, "grad_norm": 0.3728366196155548, "learning_rate": 3.93804299873904e-05, "loss": 4.3008, "step": 9983 }, { "epoch": 0.3049480757483201, "grad_norm": 0.3826559782028198, "learning_rate": 3.9378467623507734e-05, "loss": 4.4189, "step": 9984 }, { "epoch": 0.30497861942577886, "grad_norm": 0.372962087392807, "learning_rate": 3.937650512723513e-05, "loss": 4.344, "step": 9985 }, { "epoch": 0.3050091631032376, "grad_norm": 0.37210696935653687, "learning_rate": 3.937454249859065e-05, "loss": 4.4054, "step": 9986 }, { "epoch": 0.3050397067806964, "grad_norm": 0.37565428018569946, "learning_rate": 3.9372579737592366e-05, "loss": 4.3307, "step": 9987 }, { "epoch": 0.30507025045815517, "grad_norm": 0.3754740059375763, "learning_rate": 3.9370616844258355e-05, "loss": 4.3079, "step": 9988 }, { "epoch": 0.3051007941356139, "grad_norm": 0.37209248542785645, "learning_rate": 3.9368653818606684e-05, "loss": 4.365, "step": 9989 }, { "epoch": 0.30513133781307267, "grad_norm": 0.3802163898944855, "learning_rate": 3.9366690660655426e-05, "loss": 4.2788, "step": 9990 }, { "epoch": 0.3051618814905315, "grad_norm": 0.3767695128917694, "learning_rate": 3.936472737042266e-05, "loss": 4.2927, "step": 9991 }, { "epoch": 0.3051924251679902, "grad_norm": 0.3684440553188324, "learning_rate": 3.9362763947926464e-05, "loss": 4.3998, "step": 9992 }, { "epoch": 0.30522296884544897, "grad_norm": 0.3646261990070343, "learning_rate": 3.936080039318491e-05, "loss": 4.3433, "step": 9993 }, { "epoch": 0.3052535125229078, "grad_norm": 0.3762752115726471, "learning_rate": 3.93588367062161e-05, "loss": 4.2915, "step": 9994 }, { "epoch": 0.3052840562003665, "grad_norm": 0.37190377712249756, "learning_rate": 3.935687288703809e-05, "loss": 4.2749, "step": 9995 }, { "epoch": 0.3053145998778253, "grad_norm": 0.38220223784446716, "learning_rate": 3.935490893566897e-05, "loss": 4.3671, "step": 9996 }, { "epoch": 0.3053451435552841, "grad_norm": 0.382325679063797, "learning_rate": 3.9352944852126815e-05, "loss": 4.3461, "step": 9997 }, { "epoch": 0.30537568723274283, "grad_norm": 0.3901817500591278, "learning_rate": 3.9350980636429726e-05, "loss": 4.368, "step": 9998 }, { "epoch": 0.3054062309102016, "grad_norm": 0.37142255902290344, "learning_rate": 3.9349016288595776e-05, "loss": 4.2944, "step": 9999 }, { "epoch": 0.30543677458766033, "grad_norm": 0.36567458510398865, "learning_rate": 3.934705180864306e-05, "loss": 4.3119, "step": 10000 }, { "epoch": 0.30546731826511914, "grad_norm": 0.37399300932884216, "learning_rate": 3.9345087196589654e-05, "loss": 4.3035, "step": 10001 }, { "epoch": 0.3054978619425779, "grad_norm": 0.3769164979457855, "learning_rate": 3.934312245245366e-05, "loss": 4.3599, "step": 10002 }, { "epoch": 0.30552840562003664, "grad_norm": 0.38170409202575684, "learning_rate": 3.934115757625316e-05, "loss": 4.3639, "step": 10003 }, { "epoch": 0.30555894929749544, "grad_norm": 0.38447320461273193, "learning_rate": 3.933919256800625e-05, "loss": 4.3695, "step": 10004 }, { "epoch": 0.3055894929749542, "grad_norm": 0.3812507688999176, "learning_rate": 3.933722742773102e-05, "loss": 4.3103, "step": 10005 }, { "epoch": 0.30562003665241294, "grad_norm": 0.372233122587204, "learning_rate": 3.9335262155445574e-05, "loss": 4.2836, "step": 10006 }, { "epoch": 0.3056505803298717, "grad_norm": 0.38720038533210754, "learning_rate": 3.933329675116799e-05, "loss": 4.2779, "step": 10007 }, { "epoch": 0.3056811240073305, "grad_norm": 0.3834717273712158, "learning_rate": 3.9331331214916374e-05, "loss": 4.3313, "step": 10008 }, { "epoch": 0.30571166768478925, "grad_norm": 0.38256534934043884, "learning_rate": 3.9329365546708824e-05, "loss": 4.359, "step": 10009 }, { "epoch": 0.305742211362248, "grad_norm": 0.3706648051738739, "learning_rate": 3.9327399746563445e-05, "loss": 4.3592, "step": 10010 }, { "epoch": 0.3057727550397068, "grad_norm": 0.3847225308418274, "learning_rate": 3.9325433814498315e-05, "loss": 4.409, "step": 10011 }, { "epoch": 0.30580329871716555, "grad_norm": 0.38095712661743164, "learning_rate": 3.932346775053156e-05, "loss": 4.4075, "step": 10012 }, { "epoch": 0.3058338423946243, "grad_norm": 0.37824898958206177, "learning_rate": 3.932150155468127e-05, "loss": 4.3235, "step": 10013 }, { "epoch": 0.3058643860720831, "grad_norm": 0.38486582040786743, "learning_rate": 3.931953522696556e-05, "loss": 4.3383, "step": 10014 }, { "epoch": 0.30589492974954186, "grad_norm": 0.3860843777656555, "learning_rate": 3.931756876740252e-05, "loss": 4.2438, "step": 10015 }, { "epoch": 0.3059254734270006, "grad_norm": 0.38541683554649353, "learning_rate": 3.931560217601027e-05, "loss": 4.3903, "step": 10016 }, { "epoch": 0.30595601710445935, "grad_norm": 0.38769522309303284, "learning_rate": 3.93136354528069e-05, "loss": 4.3596, "step": 10017 }, { "epoch": 0.30598656078191816, "grad_norm": 0.3837808072566986, "learning_rate": 3.9311668597810536e-05, "loss": 4.3326, "step": 10018 }, { "epoch": 0.3060171044593769, "grad_norm": 0.36839011311531067, "learning_rate": 3.930970161103927e-05, "loss": 4.3347, "step": 10019 }, { "epoch": 0.30604764813683566, "grad_norm": 0.37082189321517944, "learning_rate": 3.930773449251124e-05, "loss": 4.2599, "step": 10020 }, { "epoch": 0.30607819181429446, "grad_norm": 0.38309144973754883, "learning_rate": 3.930576724224453e-05, "loss": 4.2721, "step": 10021 }, { "epoch": 0.3061087354917532, "grad_norm": 0.37735486030578613, "learning_rate": 3.930379986025727e-05, "loss": 4.4027, "step": 10022 }, { "epoch": 0.30613927916921196, "grad_norm": 0.38711100816726685, "learning_rate": 3.9301832346567574e-05, "loss": 4.3101, "step": 10023 }, { "epoch": 0.3061698228466707, "grad_norm": 0.37120017409324646, "learning_rate": 3.929986470119355e-05, "loss": 4.3194, "step": 10024 }, { "epoch": 0.3062003665241295, "grad_norm": 0.3863920271396637, "learning_rate": 3.929789692415332e-05, "loss": 4.3458, "step": 10025 }, { "epoch": 0.30623091020158827, "grad_norm": 0.3813595473766327, "learning_rate": 3.9295929015465e-05, "loss": 4.3451, "step": 10026 }, { "epoch": 0.306261453879047, "grad_norm": 0.38420823216438293, "learning_rate": 3.929396097514672e-05, "loss": 4.3588, "step": 10027 }, { "epoch": 0.3062919975565058, "grad_norm": 0.3946548402309418, "learning_rate": 3.9291992803216584e-05, "loss": 4.4093, "step": 10028 }, { "epoch": 0.3063225412339646, "grad_norm": 0.3837268352508545, "learning_rate": 3.929002449969272e-05, "loss": 4.2191, "step": 10029 }, { "epoch": 0.3063530849114233, "grad_norm": 0.3882180154323578, "learning_rate": 3.928805606459326e-05, "loss": 4.3729, "step": 10030 }, { "epoch": 0.30638362858888213, "grad_norm": 0.374828964471817, "learning_rate": 3.9286087497936315e-05, "loss": 4.3175, "step": 10031 }, { "epoch": 0.3064141722663409, "grad_norm": 0.3776428699493408, "learning_rate": 3.928411879974002e-05, "loss": 4.347, "step": 10032 }, { "epoch": 0.30644471594379963, "grad_norm": 0.3886454999446869, "learning_rate": 3.92821499700225e-05, "loss": 4.3565, "step": 10033 }, { "epoch": 0.3064752596212584, "grad_norm": 0.37459489703178406, "learning_rate": 3.9280181008801884e-05, "loss": 4.3406, "step": 10034 }, { "epoch": 0.3065058032987172, "grad_norm": 0.37271931767463684, "learning_rate": 3.9278211916096297e-05, "loss": 4.357, "step": 10035 }, { "epoch": 0.30653634697617593, "grad_norm": 0.3753812313079834, "learning_rate": 3.927624269192387e-05, "loss": 4.3035, "step": 10036 }, { "epoch": 0.3065668906536347, "grad_norm": 0.38706374168395996, "learning_rate": 3.927427333630273e-05, "loss": 4.2898, "step": 10037 }, { "epoch": 0.3065974343310935, "grad_norm": 0.382090300321579, "learning_rate": 3.927230384925104e-05, "loss": 4.3109, "step": 10038 }, { "epoch": 0.30662797800855224, "grad_norm": 0.38906237483024597, "learning_rate": 3.927033423078689e-05, "loss": 4.4605, "step": 10039 }, { "epoch": 0.306658521686011, "grad_norm": 0.36248964071273804, "learning_rate": 3.926836448092844e-05, "loss": 4.3644, "step": 10040 }, { "epoch": 0.30668906536346974, "grad_norm": 0.3737287223339081, "learning_rate": 3.926639459969382e-05, "loss": 4.2724, "step": 10041 }, { "epoch": 0.30671960904092854, "grad_norm": 0.37252604961395264, "learning_rate": 3.926442458710117e-05, "loss": 4.3761, "step": 10042 }, { "epoch": 0.3067501527183873, "grad_norm": 0.3763158619403839, "learning_rate": 3.926245444316864e-05, "loss": 4.28, "step": 10043 }, { "epoch": 0.30678069639584604, "grad_norm": 0.39126524329185486, "learning_rate": 3.9260484167914345e-05, "loss": 4.3081, "step": 10044 }, { "epoch": 0.30681124007330485, "grad_norm": 0.3836003839969635, "learning_rate": 3.9258513761356445e-05, "loss": 4.33, "step": 10045 }, { "epoch": 0.3068417837507636, "grad_norm": 0.37221017479896545, "learning_rate": 3.925654322351308e-05, "loss": 4.4496, "step": 10046 }, { "epoch": 0.30687232742822235, "grad_norm": 0.37353360652923584, "learning_rate": 3.925457255440239e-05, "loss": 4.3506, "step": 10047 }, { "epoch": 0.3069028711056811, "grad_norm": 0.3815779983997345, "learning_rate": 3.925260175404252e-05, "loss": 4.2385, "step": 10048 }, { "epoch": 0.3069334147831399, "grad_norm": 0.37793147563934326, "learning_rate": 3.925063082245162e-05, "loss": 4.294, "step": 10049 }, { "epoch": 0.30696395846059865, "grad_norm": 0.3726727068424225, "learning_rate": 3.9248659759647835e-05, "loss": 4.2629, "step": 10050 }, { "epoch": 0.3069945021380574, "grad_norm": 0.38901108503341675, "learning_rate": 3.924668856564931e-05, "loss": 4.3487, "step": 10051 }, { "epoch": 0.3070250458155162, "grad_norm": 0.3747803568840027, "learning_rate": 3.9244717240474206e-05, "loss": 4.3157, "step": 10052 }, { "epoch": 0.30705558949297496, "grad_norm": 0.37656646966934204, "learning_rate": 3.9242745784140655e-05, "loss": 4.2428, "step": 10053 }, { "epoch": 0.3070861331704337, "grad_norm": 0.3795841336250305, "learning_rate": 3.924077419666683e-05, "loss": 4.3143, "step": 10054 }, { "epoch": 0.3071166768478925, "grad_norm": 0.3789004683494568, "learning_rate": 3.923880247807087e-05, "loss": 4.3313, "step": 10055 }, { "epoch": 0.30714722052535126, "grad_norm": 0.3756283223628998, "learning_rate": 3.923683062837094e-05, "loss": 4.2782, "step": 10056 }, { "epoch": 0.30717776420281, "grad_norm": 0.3909161388874054, "learning_rate": 3.923485864758519e-05, "loss": 4.4626, "step": 10057 }, { "epoch": 0.30720830788026876, "grad_norm": 0.3770867884159088, "learning_rate": 3.9232886535731775e-05, "loss": 4.2524, "step": 10058 }, { "epoch": 0.30723885155772757, "grad_norm": 0.3670847415924072, "learning_rate": 3.923091429282886e-05, "loss": 4.2308, "step": 10059 }, { "epoch": 0.3072693952351863, "grad_norm": 0.3776012361049652, "learning_rate": 3.922894191889459e-05, "loss": 4.3838, "step": 10060 }, { "epoch": 0.30729993891264507, "grad_norm": 0.3860922157764435, "learning_rate": 3.922696941394715e-05, "loss": 4.2716, "step": 10061 }, { "epoch": 0.30733048259010387, "grad_norm": 0.39789822697639465, "learning_rate": 3.9224996778004675e-05, "loss": 4.3601, "step": 10062 }, { "epoch": 0.3073610262675626, "grad_norm": 0.3728954792022705, "learning_rate": 3.922302401108534e-05, "loss": 4.4126, "step": 10063 }, { "epoch": 0.30739156994502137, "grad_norm": 0.38387638330459595, "learning_rate": 3.922105111320732e-05, "loss": 4.3742, "step": 10064 }, { "epoch": 0.3074221136224801, "grad_norm": 0.37758034467697144, "learning_rate": 3.921907808438877e-05, "loss": 4.3558, "step": 10065 }, { "epoch": 0.3074526572999389, "grad_norm": 0.38040828704833984, "learning_rate": 3.921710492464785e-05, "loss": 4.2899, "step": 10066 }, { "epoch": 0.3074832009773977, "grad_norm": 0.3750576674938202, "learning_rate": 3.9215131634002746e-05, "loss": 4.3056, "step": 10067 }, { "epoch": 0.3075137446548564, "grad_norm": 0.38291457295417786, "learning_rate": 3.9213158212471606e-05, "loss": 4.3659, "step": 10068 }, { "epoch": 0.30754428833231523, "grad_norm": 0.3753359317779541, "learning_rate": 3.9211184660072614e-05, "loss": 4.3311, "step": 10069 }, { "epoch": 0.307574832009774, "grad_norm": 0.3746318519115448, "learning_rate": 3.920921097682394e-05, "loss": 4.3318, "step": 10070 }, { "epoch": 0.30760537568723273, "grad_norm": 0.3700651526451111, "learning_rate": 3.9207237162743755e-05, "loss": 4.341, "step": 10071 }, { "epoch": 0.30763591936469153, "grad_norm": 0.37748727202415466, "learning_rate": 3.920526321785023e-05, "loss": 4.2464, "step": 10072 }, { "epoch": 0.3076664630421503, "grad_norm": 0.3736054003238678, "learning_rate": 3.9203289142161545e-05, "loss": 4.3297, "step": 10073 }, { "epoch": 0.30769700671960903, "grad_norm": 0.38336679339408875, "learning_rate": 3.9201314935695876e-05, "loss": 4.2989, "step": 10074 }, { "epoch": 0.3077275503970678, "grad_norm": 0.35971972346305847, "learning_rate": 3.91993405984714e-05, "loss": 4.324, "step": 10075 }, { "epoch": 0.3077580940745266, "grad_norm": 0.38021472096443176, "learning_rate": 3.919736613050629e-05, "loss": 4.3384, "step": 10076 }, { "epoch": 0.30778863775198534, "grad_norm": 0.39139336347579956, "learning_rate": 3.9195391531818726e-05, "loss": 4.3601, "step": 10077 }, { "epoch": 0.3078191814294441, "grad_norm": 0.38738876581192017, "learning_rate": 3.91934168024269e-05, "loss": 4.2615, "step": 10078 }, { "epoch": 0.3078497251069029, "grad_norm": 0.37600186467170715, "learning_rate": 3.9191441942348986e-05, "loss": 4.2339, "step": 10079 }, { "epoch": 0.30788026878436164, "grad_norm": 0.37724560499191284, "learning_rate": 3.918946695160317e-05, "loss": 4.4177, "step": 10080 }, { "epoch": 0.3079108124618204, "grad_norm": 0.3768536448478699, "learning_rate": 3.918749183020763e-05, "loss": 4.3499, "step": 10081 }, { "epoch": 0.30794135613927914, "grad_norm": 0.39068281650543213, "learning_rate": 3.918551657818057e-05, "loss": 4.3599, "step": 10082 }, { "epoch": 0.30797189981673795, "grad_norm": 0.3758848011493683, "learning_rate": 3.9183541195540165e-05, "loss": 4.3625, "step": 10083 }, { "epoch": 0.3080024434941967, "grad_norm": 0.37845227122306824, "learning_rate": 3.91815656823046e-05, "loss": 4.2378, "step": 10084 }, { "epoch": 0.30803298717165545, "grad_norm": 0.3775695860385895, "learning_rate": 3.917959003849206e-05, "loss": 4.3853, "step": 10085 }, { "epoch": 0.30806353084911425, "grad_norm": 0.4653177559375763, "learning_rate": 3.917761426412076e-05, "loss": 4.356, "step": 10086 }, { "epoch": 0.308094074526573, "grad_norm": 0.39077505469322205, "learning_rate": 3.917563835920887e-05, "loss": 4.3073, "step": 10087 }, { "epoch": 0.30812461820403175, "grad_norm": 0.38586652278900146, "learning_rate": 3.917366232377458e-05, "loss": 4.3607, "step": 10088 }, { "epoch": 0.30815516188149056, "grad_norm": 0.3875451683998108, "learning_rate": 3.91716861578361e-05, "loss": 4.2988, "step": 10089 }, { "epoch": 0.3081857055589493, "grad_norm": 0.3726305067539215, "learning_rate": 3.916970986141162e-05, "loss": 4.3746, "step": 10090 }, { "epoch": 0.30821624923640806, "grad_norm": 0.36832326650619507, "learning_rate": 3.9167733434519335e-05, "loss": 4.3281, "step": 10091 }, { "epoch": 0.3082467929138668, "grad_norm": 0.3784646689891815, "learning_rate": 3.9165756877177444e-05, "loss": 4.3618, "step": 10092 }, { "epoch": 0.3082773365913256, "grad_norm": 0.36729738116264343, "learning_rate": 3.916378018940415e-05, "loss": 4.3524, "step": 10093 }, { "epoch": 0.30830788026878436, "grad_norm": 0.3862168788909912, "learning_rate": 3.916180337121764e-05, "loss": 4.4526, "step": 10094 }, { "epoch": 0.3083384239462431, "grad_norm": 0.3885417580604553, "learning_rate": 3.915982642263614e-05, "loss": 4.2747, "step": 10095 }, { "epoch": 0.3083689676237019, "grad_norm": 0.39210203289985657, "learning_rate": 3.915784934367782e-05, "loss": 4.2557, "step": 10096 }, { "epoch": 0.30839951130116067, "grad_norm": 0.37613317370414734, "learning_rate": 3.915587213436092e-05, "loss": 4.3591, "step": 10097 }, { "epoch": 0.3084300549786194, "grad_norm": 0.3705528676509857, "learning_rate": 3.915389479470362e-05, "loss": 4.3721, "step": 10098 }, { "epoch": 0.30846059865607817, "grad_norm": 0.37126588821411133, "learning_rate": 3.915191732472413e-05, "loss": 4.281, "step": 10099 }, { "epoch": 0.30849114233353697, "grad_norm": 0.4011937975883484, "learning_rate": 3.914993972444065e-05, "loss": 4.4366, "step": 10100 }, { "epoch": 0.3085216860109957, "grad_norm": 0.3897208571434021, "learning_rate": 3.914796199387142e-05, "loss": 4.4114, "step": 10101 }, { "epoch": 0.30855222968845447, "grad_norm": 0.36913731694221497, "learning_rate": 3.9145984133034626e-05, "loss": 4.3459, "step": 10102 }, { "epoch": 0.3085827733659133, "grad_norm": 0.3891198933124542, "learning_rate": 3.914400614194848e-05, "loss": 4.4175, "step": 10103 }, { "epoch": 0.308613317043372, "grad_norm": 0.3785168528556824, "learning_rate": 3.91420280206312e-05, "loss": 4.3562, "step": 10104 }, { "epoch": 0.3086438607208308, "grad_norm": 0.3708343505859375, "learning_rate": 3.9140049769100985e-05, "loss": 4.304, "step": 10105 }, { "epoch": 0.3086744043982896, "grad_norm": 0.3703913986682892, "learning_rate": 3.913807138737607e-05, "loss": 4.2629, "step": 10106 }, { "epoch": 0.30870494807574833, "grad_norm": 0.3659088909626007, "learning_rate": 3.9136092875474665e-05, "loss": 4.4336, "step": 10107 }, { "epoch": 0.3087354917532071, "grad_norm": 0.36817628145217896, "learning_rate": 3.913411423341498e-05, "loss": 4.1934, "step": 10108 }, { "epoch": 0.30876603543066583, "grad_norm": 0.36780497431755066, "learning_rate": 3.913213546121524e-05, "loss": 4.2489, "step": 10109 }, { "epoch": 0.30879657910812464, "grad_norm": 0.38029512763023376, "learning_rate": 3.913015655889366e-05, "loss": 4.4211, "step": 10110 }, { "epoch": 0.3088271227855834, "grad_norm": 0.3823501765727997, "learning_rate": 3.912817752646847e-05, "loss": 4.2582, "step": 10111 }, { "epoch": 0.30885766646304214, "grad_norm": 0.3864339590072632, "learning_rate": 3.912619836395789e-05, "loss": 4.1314, "step": 10112 }, { "epoch": 0.30888821014050094, "grad_norm": 0.3817446827888489, "learning_rate": 3.9124219071380116e-05, "loss": 4.3024, "step": 10113 }, { "epoch": 0.3089187538179597, "grad_norm": 0.3810003697872162, "learning_rate": 3.912223964875342e-05, "loss": 4.3827, "step": 10114 }, { "epoch": 0.30894929749541844, "grad_norm": 0.3751448392868042, "learning_rate": 3.912026009609599e-05, "loss": 4.2904, "step": 10115 }, { "epoch": 0.3089798411728772, "grad_norm": 0.3834860324859619, "learning_rate": 3.911828041342607e-05, "loss": 4.2679, "step": 10116 }, { "epoch": 0.309010384850336, "grad_norm": 0.377543568611145, "learning_rate": 3.911630060076188e-05, "loss": 4.3711, "step": 10117 }, { "epoch": 0.30904092852779474, "grad_norm": 0.391895055770874, "learning_rate": 3.911432065812165e-05, "loss": 4.3411, "step": 10118 }, { "epoch": 0.3090714722052535, "grad_norm": 0.3633246123790741, "learning_rate": 3.911234058552362e-05, "loss": 4.2664, "step": 10119 }, { "epoch": 0.3091020158827123, "grad_norm": 0.38797688484191895, "learning_rate": 3.911036038298601e-05, "loss": 4.2921, "step": 10120 }, { "epoch": 0.30913255956017105, "grad_norm": 0.3675020635128021, "learning_rate": 3.910838005052706e-05, "loss": 4.3051, "step": 10121 }, { "epoch": 0.3091631032376298, "grad_norm": 0.38165563344955444, "learning_rate": 3.9106399588165e-05, "loss": 4.3588, "step": 10122 }, { "epoch": 0.30919364691508855, "grad_norm": 0.37693390250205994, "learning_rate": 3.910441899591807e-05, "loss": 4.3818, "step": 10123 }, { "epoch": 0.30922419059254735, "grad_norm": 0.3796682357788086, "learning_rate": 3.9102438273804495e-05, "loss": 4.3899, "step": 10124 }, { "epoch": 0.3092547342700061, "grad_norm": 0.3740340769290924, "learning_rate": 3.9100457421842525e-05, "loss": 4.3013, "step": 10125 }, { "epoch": 0.30928527794746485, "grad_norm": 0.3882094621658325, "learning_rate": 3.9098476440050394e-05, "loss": 4.3774, "step": 10126 }, { "epoch": 0.30931582162492366, "grad_norm": 0.3755975663661957, "learning_rate": 3.909649532844633e-05, "loss": 4.3996, "step": 10127 }, { "epoch": 0.3093463653023824, "grad_norm": 0.39908185601234436, "learning_rate": 3.90945140870486e-05, "loss": 4.336, "step": 10128 }, { "epoch": 0.30937690897984116, "grad_norm": 0.38571861386299133, "learning_rate": 3.909253271587543e-05, "loss": 4.3921, "step": 10129 }, { "epoch": 0.30940745265729996, "grad_norm": 0.38266515731811523, "learning_rate": 3.909055121494506e-05, "loss": 4.3959, "step": 10130 }, { "epoch": 0.3094379963347587, "grad_norm": 0.3819456696510315, "learning_rate": 3.908856958427574e-05, "loss": 4.3025, "step": 10131 }, { "epoch": 0.30946854001221746, "grad_norm": 0.3804680109024048, "learning_rate": 3.908658782388572e-05, "loss": 4.3542, "step": 10132 }, { "epoch": 0.3094990836896762, "grad_norm": 0.3729795217514038, "learning_rate": 3.9084605933793254e-05, "loss": 4.3481, "step": 10133 }, { "epoch": 0.309529627367135, "grad_norm": 0.3768253028392792, "learning_rate": 3.908262391401656e-05, "loss": 4.2775, "step": 10134 }, { "epoch": 0.30956017104459377, "grad_norm": 0.36896979808807373, "learning_rate": 3.9080641764573916e-05, "loss": 4.3093, "step": 10135 }, { "epoch": 0.3095907147220525, "grad_norm": 0.379312664270401, "learning_rate": 3.907865948548357e-05, "loss": 4.2979, "step": 10136 }, { "epoch": 0.3096212583995113, "grad_norm": 0.38473939895629883, "learning_rate": 3.907667707676376e-05, "loss": 4.3488, "step": 10137 }, { "epoch": 0.3096518020769701, "grad_norm": 0.3664337396621704, "learning_rate": 3.9074694538432747e-05, "loss": 4.3628, "step": 10138 }, { "epoch": 0.3096823457544288, "grad_norm": 0.3917972445487976, "learning_rate": 3.9072711870508783e-05, "loss": 4.3925, "step": 10139 }, { "epoch": 0.3097128894318876, "grad_norm": 0.3797960877418518, "learning_rate": 3.9070729073010125e-05, "loss": 4.2998, "step": 10140 }, { "epoch": 0.3097434331093464, "grad_norm": 0.3746923804283142, "learning_rate": 3.906874614595504e-05, "loss": 4.3561, "step": 10141 }, { "epoch": 0.3097739767868051, "grad_norm": 0.3924974799156189, "learning_rate": 3.906676308936176e-05, "loss": 4.2798, "step": 10142 }, { "epoch": 0.3098045204642639, "grad_norm": 0.3737184703350067, "learning_rate": 3.9064779903248574e-05, "loss": 4.3387, "step": 10143 }, { "epoch": 0.3098350641417227, "grad_norm": 0.3813203275203705, "learning_rate": 3.906279658763372e-05, "loss": 4.2747, "step": 10144 }, { "epoch": 0.30986560781918143, "grad_norm": 0.37260910868644714, "learning_rate": 3.906081314253547e-05, "loss": 4.2848, "step": 10145 }, { "epoch": 0.3098961514966402, "grad_norm": 0.38154658675193787, "learning_rate": 3.905882956797209e-05, "loss": 4.3277, "step": 10146 }, { "epoch": 0.309926695174099, "grad_norm": 0.37835484743118286, "learning_rate": 3.905684586396182e-05, "loss": 4.3351, "step": 10147 }, { "epoch": 0.30995723885155774, "grad_norm": 0.3753001391887665, "learning_rate": 3.905486203052296e-05, "loss": 4.364, "step": 10148 }, { "epoch": 0.3099877825290165, "grad_norm": 0.3904855251312256, "learning_rate": 3.905287806767375e-05, "loss": 4.3898, "step": 10149 }, { "epoch": 0.31001832620647524, "grad_norm": 0.379155695438385, "learning_rate": 3.905089397543248e-05, "loss": 4.3004, "step": 10150 }, { "epoch": 0.31004886988393404, "grad_norm": 0.37837347388267517, "learning_rate": 3.904890975381739e-05, "loss": 4.2876, "step": 10151 }, { "epoch": 0.3100794135613928, "grad_norm": 0.37509095668792725, "learning_rate": 3.904692540284677e-05, "loss": 4.3697, "step": 10152 }, { "epoch": 0.31010995723885154, "grad_norm": 0.37235790491104126, "learning_rate": 3.9044940922538886e-05, "loss": 4.2951, "step": 10153 }, { "epoch": 0.31014050091631035, "grad_norm": 0.36705318093299866, "learning_rate": 3.904295631291201e-05, "loss": 4.3878, "step": 10154 }, { "epoch": 0.3101710445937691, "grad_norm": 0.39540356397628784, "learning_rate": 3.904097157398441e-05, "loss": 4.4063, "step": 10155 }, { "epoch": 0.31020158827122785, "grad_norm": 0.3953526020050049, "learning_rate": 3.903898670577437e-05, "loss": 4.3544, "step": 10156 }, { "epoch": 0.3102321319486866, "grad_norm": 0.3824154734611511, "learning_rate": 3.903700170830017e-05, "loss": 4.3471, "step": 10157 }, { "epoch": 0.3102626756261454, "grad_norm": 0.37663525342941284, "learning_rate": 3.903501658158006e-05, "loss": 4.3775, "step": 10158 }, { "epoch": 0.31029321930360415, "grad_norm": 0.3906511068344116, "learning_rate": 3.9033031325632345e-05, "loss": 4.443, "step": 10159 }, { "epoch": 0.3103237629810629, "grad_norm": 0.38563811779022217, "learning_rate": 3.90310459404753e-05, "loss": 4.2916, "step": 10160 }, { "epoch": 0.3103543066585217, "grad_norm": 0.3782460391521454, "learning_rate": 3.902906042612719e-05, "loss": 4.3207, "step": 10161 }, { "epoch": 0.31038485033598046, "grad_norm": 0.3780345022678375, "learning_rate": 3.9027074782606313e-05, "loss": 4.3183, "step": 10162 }, { "epoch": 0.3104153940134392, "grad_norm": 0.37758946418762207, "learning_rate": 3.902508900993095e-05, "loss": 4.3755, "step": 10163 }, { "epoch": 0.310445937690898, "grad_norm": 0.3857477009296417, "learning_rate": 3.9023103108119376e-05, "loss": 4.3547, "step": 10164 }, { "epoch": 0.31047648136835676, "grad_norm": 0.3880336880683899, "learning_rate": 3.902111707718989e-05, "loss": 4.3141, "step": 10165 }, { "epoch": 0.3105070250458155, "grad_norm": 0.3797926902770996, "learning_rate": 3.901913091716076e-05, "loss": 4.4123, "step": 10166 }, { "epoch": 0.31053756872327426, "grad_norm": 0.3694222867488861, "learning_rate": 3.9017144628050295e-05, "loss": 4.3864, "step": 10167 }, { "epoch": 0.31056811240073307, "grad_norm": 0.3919951319694519, "learning_rate": 3.9015158209876764e-05, "loss": 4.2203, "step": 10168 }, { "epoch": 0.3105986560781918, "grad_norm": 0.374952107667923, "learning_rate": 3.901317166265847e-05, "loss": 4.3485, "step": 10169 }, { "epoch": 0.31062919975565056, "grad_norm": 0.3804813623428345, "learning_rate": 3.9011184986413696e-05, "loss": 4.3221, "step": 10170 }, { "epoch": 0.31065974343310937, "grad_norm": 0.3808862864971161, "learning_rate": 3.900919818116074e-05, "loss": 4.2698, "step": 10171 }, { "epoch": 0.3106902871105681, "grad_norm": 0.3751707971096039, "learning_rate": 3.900721124691789e-05, "loss": 4.3388, "step": 10172 }, { "epoch": 0.31072083078802687, "grad_norm": 0.3763144910335541, "learning_rate": 3.900522418370345e-05, "loss": 4.296, "step": 10173 }, { "epoch": 0.3107513744654856, "grad_norm": 0.3820700943470001, "learning_rate": 3.900323699153571e-05, "loss": 4.3404, "step": 10174 }, { "epoch": 0.3107819181429444, "grad_norm": 0.36749187111854553, "learning_rate": 3.900124967043296e-05, "loss": 4.3911, "step": 10175 }, { "epoch": 0.3108124618204032, "grad_norm": 0.3700146973133087, "learning_rate": 3.899926222041351e-05, "loss": 4.3013, "step": 10176 }, { "epoch": 0.3108430054978619, "grad_norm": 0.3741632401943207, "learning_rate": 3.8997274641495655e-05, "loss": 4.3589, "step": 10177 }, { "epoch": 0.31087354917532073, "grad_norm": 0.3871890902519226, "learning_rate": 3.89952869336977e-05, "loss": 4.3891, "step": 10178 }, { "epoch": 0.3109040928527795, "grad_norm": 0.3896532356739044, "learning_rate": 3.899329909703794e-05, "loss": 4.3061, "step": 10179 }, { "epoch": 0.31093463653023823, "grad_norm": 0.3750642240047455, "learning_rate": 3.899131113153468e-05, "loss": 4.3654, "step": 10180 }, { "epoch": 0.31096518020769703, "grad_norm": 0.38135144114494324, "learning_rate": 3.898932303720621e-05, "loss": 4.4178, "step": 10181 }, { "epoch": 0.3109957238851558, "grad_norm": 0.3734155595302582, "learning_rate": 3.8987334814070875e-05, "loss": 4.3454, "step": 10182 }, { "epoch": 0.31102626756261453, "grad_norm": 0.3749455511569977, "learning_rate": 3.898534646214694e-05, "loss": 4.2688, "step": 10183 }, { "epoch": 0.3110568112400733, "grad_norm": 0.39515939354896545, "learning_rate": 3.898335798145274e-05, "loss": 4.3221, "step": 10184 }, { "epoch": 0.3110873549175321, "grad_norm": 0.3708561360836029, "learning_rate": 3.8981369372006565e-05, "loss": 4.3305, "step": 10185 }, { "epoch": 0.31111789859499084, "grad_norm": 0.374543696641922, "learning_rate": 3.897938063382674e-05, "loss": 4.314, "step": 10186 }, { "epoch": 0.3111484422724496, "grad_norm": 0.3886965215206146, "learning_rate": 3.897739176693157e-05, "loss": 4.4014, "step": 10187 }, { "epoch": 0.3111789859499084, "grad_norm": 0.3692709803581238, "learning_rate": 3.8975402771339364e-05, "loss": 4.3853, "step": 10188 }, { "epoch": 0.31120952962736714, "grad_norm": 0.38091397285461426, "learning_rate": 3.8973413647068435e-05, "loss": 4.3424, "step": 10189 }, { "epoch": 0.3112400733048259, "grad_norm": 0.3780058026313782, "learning_rate": 3.897142439413711e-05, "loss": 4.3869, "step": 10190 }, { "epoch": 0.31127061698228464, "grad_norm": 0.3801012933254242, "learning_rate": 3.89694350125637e-05, "loss": 4.317, "step": 10191 }, { "epoch": 0.31130116065974345, "grad_norm": 0.3738704323768616, "learning_rate": 3.896744550236651e-05, "loss": 4.3511, "step": 10192 }, { "epoch": 0.3113317043372022, "grad_norm": 0.3847537934780121, "learning_rate": 3.8965455863563874e-05, "loss": 4.3241, "step": 10193 }, { "epoch": 0.31136224801466095, "grad_norm": 0.3789367377758026, "learning_rate": 3.896346609617411e-05, "loss": 4.2896, "step": 10194 }, { "epoch": 0.31139279169211975, "grad_norm": 0.3706429600715637, "learning_rate": 3.896147620021552e-05, "loss": 4.1504, "step": 10195 }, { "epoch": 0.3114233353695785, "grad_norm": 0.3803776502609253, "learning_rate": 3.895948617570645e-05, "loss": 4.2403, "step": 10196 }, { "epoch": 0.31145387904703725, "grad_norm": 0.3785650432109833, "learning_rate": 3.8957496022665216e-05, "loss": 4.185, "step": 10197 }, { "epoch": 0.311484422724496, "grad_norm": 0.3803681433200836, "learning_rate": 3.895550574111013e-05, "loss": 4.3577, "step": 10198 }, { "epoch": 0.3115149664019548, "grad_norm": 0.37515103816986084, "learning_rate": 3.8953515331059534e-05, "loss": 4.3401, "step": 10199 }, { "epoch": 0.31154551007941356, "grad_norm": 0.37401336431503296, "learning_rate": 3.8951524792531744e-05, "loss": 4.3967, "step": 10200 }, { "epoch": 0.3115760537568723, "grad_norm": 0.3817266821861267, "learning_rate": 3.89495341255451e-05, "loss": 4.3325, "step": 10201 }, { "epoch": 0.3116065974343311, "grad_norm": 0.38008883595466614, "learning_rate": 3.894754333011792e-05, "loss": 4.3877, "step": 10202 }, { "epoch": 0.31163714111178986, "grad_norm": 0.3673711121082306, "learning_rate": 3.8945552406268536e-05, "loss": 4.2759, "step": 10203 }, { "epoch": 0.3116676847892486, "grad_norm": 0.3696867823600769, "learning_rate": 3.8943561354015277e-05, "loss": 4.3511, "step": 10204 }, { "epoch": 0.3116982284667074, "grad_norm": 0.3724689483642578, "learning_rate": 3.894157017337648e-05, "loss": 4.2521, "step": 10205 }, { "epoch": 0.31172877214416617, "grad_norm": 0.3732963502407074, "learning_rate": 3.893957886437049e-05, "loss": 4.3601, "step": 10206 }, { "epoch": 0.3117593158216249, "grad_norm": 0.37134885787963867, "learning_rate": 3.8937587427015623e-05, "loss": 4.3721, "step": 10207 }, { "epoch": 0.31178985949908367, "grad_norm": 0.3693453371524811, "learning_rate": 3.893559586133022e-05, "loss": 4.2687, "step": 10208 }, { "epoch": 0.31182040317654247, "grad_norm": 0.37440070509910583, "learning_rate": 3.893360416733261e-05, "loss": 4.3053, "step": 10209 }, { "epoch": 0.3118509468540012, "grad_norm": 0.3743169903755188, "learning_rate": 3.8931612345041166e-05, "loss": 4.2443, "step": 10210 }, { "epoch": 0.31188149053145997, "grad_norm": 0.3869295120239258, "learning_rate": 3.8929620394474196e-05, "loss": 4.4159, "step": 10211 }, { "epoch": 0.3119120342089188, "grad_norm": 0.36750710010528564, "learning_rate": 3.8927628315650046e-05, "loss": 4.3152, "step": 10212 }, { "epoch": 0.3119425778863775, "grad_norm": 0.3726519048213959, "learning_rate": 3.892563610858706e-05, "loss": 4.2667, "step": 10213 }, { "epoch": 0.3119731215638363, "grad_norm": 0.3807070553302765, "learning_rate": 3.8923643773303587e-05, "loss": 4.3904, "step": 10214 }, { "epoch": 0.312003665241295, "grad_norm": 0.3877291679382324, "learning_rate": 3.8921651309817963e-05, "loss": 4.3441, "step": 10215 }, { "epoch": 0.31203420891875383, "grad_norm": 0.3725229799747467, "learning_rate": 3.8919658718148534e-05, "loss": 4.3227, "step": 10216 }, { "epoch": 0.3120647525962126, "grad_norm": 0.37995609641075134, "learning_rate": 3.8917665998313654e-05, "loss": 4.2531, "step": 10217 }, { "epoch": 0.31209529627367133, "grad_norm": 0.3774724304676056, "learning_rate": 3.8915673150331675e-05, "loss": 4.4297, "step": 10218 }, { "epoch": 0.31212583995113014, "grad_norm": 0.3932768404483795, "learning_rate": 3.8913680174220927e-05, "loss": 4.3583, "step": 10219 }, { "epoch": 0.3121563836285889, "grad_norm": 0.3822563588619232, "learning_rate": 3.891168706999978e-05, "loss": 4.3454, "step": 10220 }, { "epoch": 0.31218692730604763, "grad_norm": 0.3693101108074188, "learning_rate": 3.890969383768658e-05, "loss": 4.3037, "step": 10221 }, { "epoch": 0.31221747098350644, "grad_norm": 0.3888700306415558, "learning_rate": 3.890770047729967e-05, "loss": 4.2967, "step": 10222 }, { "epoch": 0.3122480146609652, "grad_norm": 0.37524932622909546, "learning_rate": 3.890570698885741e-05, "loss": 4.2699, "step": 10223 }, { "epoch": 0.31227855833842394, "grad_norm": 0.39377301931381226, "learning_rate": 3.890371337237816e-05, "loss": 4.3952, "step": 10224 }, { "epoch": 0.3123091020158827, "grad_norm": 0.36998769640922546, "learning_rate": 3.8901719627880275e-05, "loss": 4.3739, "step": 10225 }, { "epoch": 0.3123396456933415, "grad_norm": 0.37446022033691406, "learning_rate": 3.8899725755382097e-05, "loss": 4.3616, "step": 10226 }, { "epoch": 0.31237018937080024, "grad_norm": 0.3741670250892639, "learning_rate": 3.889773175490201e-05, "loss": 4.3343, "step": 10227 }, { "epoch": 0.312400733048259, "grad_norm": 0.38439783453941345, "learning_rate": 3.889573762645836e-05, "loss": 4.1905, "step": 10228 }, { "epoch": 0.3124312767257178, "grad_norm": 9.707382202148438, "learning_rate": 3.88937433700695e-05, "loss": 4.424, "step": 10229 }, { "epoch": 0.31246182040317655, "grad_norm": 0.3760547637939453, "learning_rate": 3.889174898575382e-05, "loss": 4.3736, "step": 10230 }, { "epoch": 0.3124923640806353, "grad_norm": 0.3750693202018738, "learning_rate": 3.888975447352965e-05, "loss": 4.2748, "step": 10231 }, { "epoch": 0.31252290775809405, "grad_norm": 0.3889581263065338, "learning_rate": 3.888775983341537e-05, "loss": 4.3425, "step": 10232 }, { "epoch": 0.31255345143555285, "grad_norm": 0.37030312418937683, "learning_rate": 3.888576506542935e-05, "loss": 4.3627, "step": 10233 }, { "epoch": 0.3125839951130116, "grad_norm": 0.36742138862609863, "learning_rate": 3.888377016958994e-05, "loss": 4.2774, "step": 10234 }, { "epoch": 0.31261453879047035, "grad_norm": 0.369526743888855, "learning_rate": 3.8881775145915536e-05, "loss": 4.3292, "step": 10235 }, { "epoch": 0.31264508246792916, "grad_norm": 0.3811206519603729, "learning_rate": 3.887977999442448e-05, "loss": 4.4303, "step": 10236 }, { "epoch": 0.3126756261453879, "grad_norm": 0.3741215765476227, "learning_rate": 3.887778471513516e-05, "loss": 4.3534, "step": 10237 }, { "epoch": 0.31270616982284666, "grad_norm": 0.38809600472450256, "learning_rate": 3.887578930806594e-05, "loss": 4.2787, "step": 10238 }, { "epoch": 0.31273671350030546, "grad_norm": 0.3788292109966278, "learning_rate": 3.887379377323518e-05, "loss": 4.2937, "step": 10239 }, { "epoch": 0.3127672571777642, "grad_norm": 0.3746509850025177, "learning_rate": 3.887179811066128e-05, "loss": 4.2489, "step": 10240 }, { "epoch": 0.31279780085522296, "grad_norm": 0.37697476148605347, "learning_rate": 3.88698023203626e-05, "loss": 4.3395, "step": 10241 }, { "epoch": 0.3128283445326817, "grad_norm": 0.39210638403892517, "learning_rate": 3.8867806402357534e-05, "loss": 4.3044, "step": 10242 }, { "epoch": 0.3128588882101405, "grad_norm": 0.3813919723033905, "learning_rate": 3.886581035666442e-05, "loss": 4.2754, "step": 10243 }, { "epoch": 0.31288943188759927, "grad_norm": 0.38265305757522583, "learning_rate": 3.8863814183301674e-05, "loss": 4.3156, "step": 10244 }, { "epoch": 0.312919975565058, "grad_norm": 0.3678315281867981, "learning_rate": 3.886181788228766e-05, "loss": 4.3066, "step": 10245 }, { "epoch": 0.3129505192425168, "grad_norm": 0.3884100019931793, "learning_rate": 3.885982145364077e-05, "loss": 4.3271, "step": 10246 }, { "epoch": 0.3129810629199756, "grad_norm": 0.3877611756324768, "learning_rate": 3.8857824897379364e-05, "loss": 4.3618, "step": 10247 }, { "epoch": 0.3130116065974343, "grad_norm": 0.3823680877685547, "learning_rate": 3.8855828213521846e-05, "loss": 4.347, "step": 10248 }, { "epoch": 0.31304215027489307, "grad_norm": 0.3726481795310974, "learning_rate": 3.8853831402086596e-05, "loss": 4.3683, "step": 10249 }, { "epoch": 0.3130726939523519, "grad_norm": 0.3891960680484772, "learning_rate": 3.885183446309199e-05, "loss": 4.3104, "step": 10250 }, { "epoch": 0.3131032376298106, "grad_norm": 0.38257738947868347, "learning_rate": 3.884983739655642e-05, "loss": 4.2621, "step": 10251 }, { "epoch": 0.3131337813072694, "grad_norm": 0.3759239614009857, "learning_rate": 3.884784020249829e-05, "loss": 4.2911, "step": 10252 }, { "epoch": 0.3131643249847282, "grad_norm": 0.37603282928466797, "learning_rate": 3.8845842880935964e-05, "loss": 4.314, "step": 10253 }, { "epoch": 0.31319486866218693, "grad_norm": 0.3810168504714966, "learning_rate": 3.884384543188785e-05, "loss": 4.3733, "step": 10254 }, { "epoch": 0.3132254123396457, "grad_norm": 0.37455716729164124, "learning_rate": 3.884184785537233e-05, "loss": 4.3554, "step": 10255 }, { "epoch": 0.3132559560171045, "grad_norm": 0.36771926283836365, "learning_rate": 3.88398501514078e-05, "loss": 4.2993, "step": 10256 }, { "epoch": 0.31328649969456324, "grad_norm": 0.3713022768497467, "learning_rate": 3.883785232001266e-05, "loss": 4.4104, "step": 10257 }, { "epoch": 0.313317043372022, "grad_norm": 0.3691039979457855, "learning_rate": 3.8835854361205294e-05, "loss": 4.2782, "step": 10258 }, { "epoch": 0.31334758704948074, "grad_norm": 0.37772759795188904, "learning_rate": 3.88338562750041e-05, "loss": 4.4246, "step": 10259 }, { "epoch": 0.31337813072693954, "grad_norm": 0.38443803787231445, "learning_rate": 3.883185806142748e-05, "loss": 4.347, "step": 10260 }, { "epoch": 0.3134086744043983, "grad_norm": 0.37484627962112427, "learning_rate": 3.8829859720493835e-05, "loss": 4.3966, "step": 10261 }, { "epoch": 0.31343921808185704, "grad_norm": 0.3712417781352997, "learning_rate": 3.882786125222156e-05, "loss": 4.3744, "step": 10262 }, { "epoch": 0.31346976175931585, "grad_norm": 0.3920925557613373, "learning_rate": 3.8825862656629055e-05, "loss": 4.3457, "step": 10263 }, { "epoch": 0.3135003054367746, "grad_norm": 0.41030147671699524, "learning_rate": 3.8823863933734716e-05, "loss": 4.3083, "step": 10264 }, { "epoch": 0.31353084911423335, "grad_norm": 0.39911678433418274, "learning_rate": 3.8821865083556974e-05, "loss": 4.3394, "step": 10265 }, { "epoch": 0.3135613927916921, "grad_norm": 0.38310930132865906, "learning_rate": 3.88198661061142e-05, "loss": 4.3492, "step": 10266 }, { "epoch": 0.3135919364691509, "grad_norm": 0.3779779374599457, "learning_rate": 3.8817867001424814e-05, "loss": 4.3397, "step": 10267 }, { "epoch": 0.31362248014660965, "grad_norm": 0.38017529249191284, "learning_rate": 3.881586776950722e-05, "loss": 4.2927, "step": 10268 }, { "epoch": 0.3136530238240684, "grad_norm": 0.3775016963481903, "learning_rate": 3.8813868410379837e-05, "loss": 4.2881, "step": 10269 }, { "epoch": 0.3136835675015272, "grad_norm": 0.3806970715522766, "learning_rate": 3.881186892406106e-05, "loss": 4.3788, "step": 10270 }, { "epoch": 0.31371411117898595, "grad_norm": 0.3740880489349365, "learning_rate": 3.8809869310569303e-05, "loss": 4.3838, "step": 10271 }, { "epoch": 0.3137446548564447, "grad_norm": 0.38771870732307434, "learning_rate": 3.880786956992298e-05, "loss": 4.2931, "step": 10272 }, { "epoch": 0.31377519853390345, "grad_norm": 0.3602534234523773, "learning_rate": 3.880586970214051e-05, "loss": 4.2721, "step": 10273 }, { "epoch": 0.31380574221136226, "grad_norm": 0.3820606470108032, "learning_rate": 3.880386970724028e-05, "loss": 4.358, "step": 10274 }, { "epoch": 0.313836285888821, "grad_norm": 0.3781184256076813, "learning_rate": 3.880186958524074e-05, "loss": 4.3883, "step": 10275 }, { "epoch": 0.31386682956627976, "grad_norm": 0.3693568706512451, "learning_rate": 3.879986933616029e-05, "loss": 4.3632, "step": 10276 }, { "epoch": 0.31389737324373856, "grad_norm": 0.3756024241447449, "learning_rate": 3.8797868960017346e-05, "loss": 4.2926, "step": 10277 }, { "epoch": 0.3139279169211973, "grad_norm": 0.3699030876159668, "learning_rate": 3.8795868456830325e-05, "loss": 4.4112, "step": 10278 }, { "epoch": 0.31395846059865606, "grad_norm": 0.3839053213596344, "learning_rate": 3.8793867826617655e-05, "loss": 4.372, "step": 10279 }, { "epoch": 0.31398900427611487, "grad_norm": 0.37915733456611633, "learning_rate": 3.879186706939775e-05, "loss": 4.3458, "step": 10280 }, { "epoch": 0.3140195479535736, "grad_norm": 0.37405455112457275, "learning_rate": 3.878986618518903e-05, "loss": 4.372, "step": 10281 }, { "epoch": 0.31405009163103237, "grad_norm": 0.37215694785118103, "learning_rate": 3.878786517400993e-05, "loss": 4.3635, "step": 10282 }, { "epoch": 0.3140806353084911, "grad_norm": 0.37284713983535767, "learning_rate": 3.878586403587886e-05, "loss": 4.432, "step": 10283 }, { "epoch": 0.3141111789859499, "grad_norm": 0.3779950737953186, "learning_rate": 3.878386277081425e-05, "loss": 4.2498, "step": 10284 }, { "epoch": 0.3141417226634087, "grad_norm": 0.36711186170578003, "learning_rate": 3.878186137883453e-05, "loss": 4.3042, "step": 10285 }, { "epoch": 0.3141722663408674, "grad_norm": 0.3858819603919983, "learning_rate": 3.8779859859958134e-05, "loss": 4.313, "step": 10286 }, { "epoch": 0.31420281001832623, "grad_norm": 0.3733796775341034, "learning_rate": 3.877785821420347e-05, "loss": 4.2924, "step": 10287 }, { "epoch": 0.314233353695785, "grad_norm": 0.3662481904029846, "learning_rate": 3.8775856441588994e-05, "loss": 4.3119, "step": 10288 }, { "epoch": 0.31426389737324373, "grad_norm": 0.36928409337997437, "learning_rate": 3.8773854542133123e-05, "loss": 4.368, "step": 10289 }, { "epoch": 0.3142944410507025, "grad_norm": 0.3863319754600525, "learning_rate": 3.877185251585428e-05, "loss": 4.3145, "step": 10290 }, { "epoch": 0.3143249847281613, "grad_norm": 0.3793307840824127, "learning_rate": 3.876985036277092e-05, "loss": 4.3588, "step": 10291 }, { "epoch": 0.31435552840562003, "grad_norm": 0.3825172483921051, "learning_rate": 3.876784808290147e-05, "loss": 4.3143, "step": 10292 }, { "epoch": 0.3143860720830788, "grad_norm": 0.3713172376155853, "learning_rate": 3.876584567626436e-05, "loss": 4.2967, "step": 10293 }, { "epoch": 0.3144166157605376, "grad_norm": 0.3703991174697876, "learning_rate": 3.876384314287803e-05, "loss": 4.292, "step": 10294 }, { "epoch": 0.31444715943799634, "grad_norm": 0.38092416524887085, "learning_rate": 3.876184048276092e-05, "loss": 4.2989, "step": 10295 }, { "epoch": 0.3144777031154551, "grad_norm": 0.36684995889663696, "learning_rate": 3.875983769593147e-05, "loss": 4.2702, "step": 10296 }, { "epoch": 0.3145082467929139, "grad_norm": 0.3745887577533722, "learning_rate": 3.875783478240812e-05, "loss": 4.388, "step": 10297 }, { "epoch": 0.31453879047037264, "grad_norm": 0.37031975388526917, "learning_rate": 3.875583174220932e-05, "loss": 4.2904, "step": 10298 }, { "epoch": 0.3145693341478314, "grad_norm": 0.3725544810295105, "learning_rate": 3.875382857535349e-05, "loss": 4.2512, "step": 10299 }, { "epoch": 0.31459987782529014, "grad_norm": 0.37649714946746826, "learning_rate": 3.8751825281859096e-05, "loss": 4.2732, "step": 10300 }, { "epoch": 0.31463042150274895, "grad_norm": 0.3842613995075226, "learning_rate": 3.874982186174457e-05, "loss": 4.3952, "step": 10301 }, { "epoch": 0.3146609651802077, "grad_norm": 0.3803052306175232, "learning_rate": 3.874781831502837e-05, "loss": 4.3905, "step": 10302 }, { "epoch": 0.31469150885766645, "grad_norm": 0.3773050606250763, "learning_rate": 3.874581464172894e-05, "loss": 4.3316, "step": 10303 }, { "epoch": 0.31472205253512525, "grad_norm": 0.3706974983215332, "learning_rate": 3.8743810841864726e-05, "loss": 4.4292, "step": 10304 }, { "epoch": 0.314752596212584, "grad_norm": 0.3702557682991028, "learning_rate": 3.8741806915454174e-05, "loss": 4.3081, "step": 10305 }, { "epoch": 0.31478313989004275, "grad_norm": 0.37700924277305603, "learning_rate": 3.873980286251575e-05, "loss": 4.2861, "step": 10306 }, { "epoch": 0.3148136835675015, "grad_norm": 0.3846946060657501, "learning_rate": 3.873779868306789e-05, "loss": 4.2467, "step": 10307 }, { "epoch": 0.3148442272449603, "grad_norm": 0.37496352195739746, "learning_rate": 3.873579437712905e-05, "loss": 4.3719, "step": 10308 }, { "epoch": 0.31487477092241906, "grad_norm": 0.37550270557403564, "learning_rate": 3.87337899447177e-05, "loss": 4.2729, "step": 10309 }, { "epoch": 0.3149053145998778, "grad_norm": 0.37385737895965576, "learning_rate": 3.873178538585228e-05, "loss": 4.3885, "step": 10310 }, { "epoch": 0.3149358582773366, "grad_norm": 0.3770870566368103, "learning_rate": 3.872978070055125e-05, "loss": 4.3389, "step": 10311 }, { "epoch": 0.31496640195479536, "grad_norm": 0.3786814510822296, "learning_rate": 3.872777588883307e-05, "loss": 4.3774, "step": 10312 }, { "epoch": 0.3149969456322541, "grad_norm": 0.3795766234397888, "learning_rate": 3.87257709507162e-05, "loss": 4.2694, "step": 10313 }, { "epoch": 0.3150274893097129, "grad_norm": 0.37384092807769775, "learning_rate": 3.87237658862191e-05, "loss": 4.2569, "step": 10314 }, { "epoch": 0.31505803298717167, "grad_norm": 0.3729016184806824, "learning_rate": 3.872176069536023e-05, "loss": 4.4209, "step": 10315 }, { "epoch": 0.3150885766646304, "grad_norm": 0.36754417419433594, "learning_rate": 3.871975537815806e-05, "loss": 4.3628, "step": 10316 }, { "epoch": 0.31511912034208917, "grad_norm": 0.38169652223587036, "learning_rate": 3.871774993463104e-05, "loss": 4.2782, "step": 10317 }, { "epoch": 0.31514966401954797, "grad_norm": 0.39580783247947693, "learning_rate": 3.871574436479765e-05, "loss": 4.3789, "step": 10318 }, { "epoch": 0.3151802076970067, "grad_norm": 0.3767496347427368, "learning_rate": 3.871373866867635e-05, "loss": 4.2878, "step": 10319 }, { "epoch": 0.31521075137446547, "grad_norm": 0.375645250082016, "learning_rate": 3.8711732846285605e-05, "loss": 4.3749, "step": 10320 }, { "epoch": 0.3152412950519243, "grad_norm": 0.3748314082622528, "learning_rate": 3.8709726897643875e-05, "loss": 4.3237, "step": 10321 }, { "epoch": 0.315271838729383, "grad_norm": 0.37867894768714905, "learning_rate": 3.870772082276966e-05, "loss": 4.3916, "step": 10322 }, { "epoch": 0.3153023824068418, "grad_norm": 0.36707666516304016, "learning_rate": 3.87057146216814e-05, "loss": 4.3793, "step": 10323 }, { "epoch": 0.3153329260843005, "grad_norm": 0.3655923306941986, "learning_rate": 3.870370829439758e-05, "loss": 4.3142, "step": 10324 }, { "epoch": 0.31536346976175933, "grad_norm": 0.37268775701522827, "learning_rate": 3.8701701840936673e-05, "loss": 4.3235, "step": 10325 }, { "epoch": 0.3153940134392181, "grad_norm": 0.3854244649410248, "learning_rate": 3.869969526131715e-05, "loss": 4.3333, "step": 10326 }, { "epoch": 0.31542455711667683, "grad_norm": 0.37549421191215515, "learning_rate": 3.869768855555749e-05, "loss": 4.3566, "step": 10327 }, { "epoch": 0.31545510079413563, "grad_norm": 0.3775252401828766, "learning_rate": 3.869568172367617e-05, "loss": 4.3766, "step": 10328 }, { "epoch": 0.3154856444715944, "grad_norm": 0.39367350935935974, "learning_rate": 3.869367476569167e-05, "loss": 4.3425, "step": 10329 }, { "epoch": 0.31551618814905313, "grad_norm": 0.3748689889907837, "learning_rate": 3.869166768162246e-05, "loss": 4.2552, "step": 10330 }, { "epoch": 0.31554673182651194, "grad_norm": 0.3698574900627136, "learning_rate": 3.868966047148703e-05, "loss": 4.2459, "step": 10331 }, { "epoch": 0.3155772755039707, "grad_norm": 0.37433677911758423, "learning_rate": 3.868765313530386e-05, "loss": 4.3953, "step": 10332 }, { "epoch": 0.31560781918142944, "grad_norm": 0.3865460157394409, "learning_rate": 3.868564567309142e-05, "loss": 4.4255, "step": 10333 }, { "epoch": 0.3156383628588882, "grad_norm": 0.3857339918613434, "learning_rate": 3.868363808486821e-05, "loss": 4.3197, "step": 10334 }, { "epoch": 0.315668906536347, "grad_norm": 0.3684854507446289, "learning_rate": 3.868163037065271e-05, "loss": 4.3851, "step": 10335 }, { "epoch": 0.31569945021380574, "grad_norm": 0.3877834677696228, "learning_rate": 3.867962253046341e-05, "loss": 4.377, "step": 10336 }, { "epoch": 0.3157299938912645, "grad_norm": 0.388107031583786, "learning_rate": 3.867761456431879e-05, "loss": 4.2417, "step": 10337 }, { "epoch": 0.3157605375687233, "grad_norm": 0.37367919087409973, "learning_rate": 3.8675606472237323e-05, "loss": 4.2903, "step": 10338 }, { "epoch": 0.31579108124618205, "grad_norm": 0.3592057228088379, "learning_rate": 3.867359825423754e-05, "loss": 4.2999, "step": 10339 }, { "epoch": 0.3158216249236408, "grad_norm": 0.37390831112861633, "learning_rate": 3.867158991033789e-05, "loss": 4.2464, "step": 10340 }, { "epoch": 0.31585216860109955, "grad_norm": 0.37758535146713257, "learning_rate": 3.866958144055689e-05, "loss": 4.447, "step": 10341 }, { "epoch": 0.31588271227855835, "grad_norm": 0.3603300154209137, "learning_rate": 3.8667572844913026e-05, "loss": 4.2736, "step": 10342 }, { "epoch": 0.3159132559560171, "grad_norm": 0.36958566308021545, "learning_rate": 3.866556412342479e-05, "loss": 4.4162, "step": 10343 }, { "epoch": 0.31594379963347585, "grad_norm": 0.3902987241744995, "learning_rate": 3.866355527611069e-05, "loss": 4.3219, "step": 10344 }, { "epoch": 0.31597434331093466, "grad_norm": 0.37530383467674255, "learning_rate": 3.866154630298919e-05, "loss": 4.2829, "step": 10345 }, { "epoch": 0.3160048869883934, "grad_norm": 0.37932687997817993, "learning_rate": 3.865953720407882e-05, "loss": 4.245, "step": 10346 }, { "epoch": 0.31603543066585216, "grad_norm": 0.3754151463508606, "learning_rate": 3.865752797939807e-05, "loss": 4.3676, "step": 10347 }, { "epoch": 0.3160659743433109, "grad_norm": 0.38866376876831055, "learning_rate": 3.865551862896544e-05, "loss": 4.3658, "step": 10348 }, { "epoch": 0.3160965180207697, "grad_norm": 0.3707965612411499, "learning_rate": 3.8653509152799414e-05, "loss": 4.3968, "step": 10349 }, { "epoch": 0.31612706169822846, "grad_norm": 0.37564483284950256, "learning_rate": 3.865149955091852e-05, "loss": 4.4368, "step": 10350 }, { "epoch": 0.3161576053756872, "grad_norm": 0.37939220666885376, "learning_rate": 3.864948982334126e-05, "loss": 4.3412, "step": 10351 }, { "epoch": 0.316188149053146, "grad_norm": 0.37801241874694824, "learning_rate": 3.8647479970086114e-05, "loss": 4.3597, "step": 10352 }, { "epoch": 0.31621869273060477, "grad_norm": 0.36884719133377075, "learning_rate": 3.864546999117161e-05, "loss": 4.3526, "step": 10353 }, { "epoch": 0.3162492364080635, "grad_norm": 0.38070932030677795, "learning_rate": 3.864345988661625e-05, "loss": 4.3356, "step": 10354 }, { "epoch": 0.3162797800855223, "grad_norm": 0.3789372146129608, "learning_rate": 3.864144965643853e-05, "loss": 4.3344, "step": 10355 }, { "epoch": 0.31631032376298107, "grad_norm": 0.38487568497657776, "learning_rate": 3.8639439300656975e-05, "loss": 4.3069, "step": 10356 }, { "epoch": 0.3163408674404398, "grad_norm": 0.39039257168769836, "learning_rate": 3.86374288192901e-05, "loss": 4.2991, "step": 10357 }, { "epoch": 0.31637141111789857, "grad_norm": 0.3747464418411255, "learning_rate": 3.863541821235639e-05, "loss": 4.3468, "step": 10358 }, { "epoch": 0.3164019547953574, "grad_norm": 0.3843114376068115, "learning_rate": 3.863340747987438e-05, "loss": 4.3545, "step": 10359 }, { "epoch": 0.3164324984728161, "grad_norm": 0.38155439496040344, "learning_rate": 3.863139662186258e-05, "loss": 4.4312, "step": 10360 }, { "epoch": 0.3164630421502749, "grad_norm": 0.37319833040237427, "learning_rate": 3.862938563833951e-05, "loss": 4.3872, "step": 10361 }, { "epoch": 0.3164935858277337, "grad_norm": 0.3811170160770416, "learning_rate": 3.8627374529323666e-05, "loss": 4.3225, "step": 10362 }, { "epoch": 0.31652412950519243, "grad_norm": 0.3750993013381958, "learning_rate": 3.8625363294833585e-05, "loss": 4.3188, "step": 10363 }, { "epoch": 0.3165546731826512, "grad_norm": 0.3728724718093872, "learning_rate": 3.862335193488777e-05, "loss": 4.3856, "step": 10364 }, { "epoch": 0.31658521686010993, "grad_norm": 0.38416025042533875, "learning_rate": 3.8621340449504764e-05, "loss": 4.3728, "step": 10365 }, { "epoch": 0.31661576053756874, "grad_norm": 0.39222294092178345, "learning_rate": 3.8619328838703064e-05, "loss": 4.4208, "step": 10366 }, { "epoch": 0.3166463042150275, "grad_norm": 0.3718656599521637, "learning_rate": 3.86173171025012e-05, "loss": 4.3898, "step": 10367 }, { "epoch": 0.31667684789248624, "grad_norm": 0.3806035816669464, "learning_rate": 3.86153052409177e-05, "loss": 4.2662, "step": 10368 }, { "epoch": 0.31670739156994504, "grad_norm": 0.3682651221752167, "learning_rate": 3.861329325397107e-05, "loss": 4.2808, "step": 10369 }, { "epoch": 0.3167379352474038, "grad_norm": 0.3695540428161621, "learning_rate": 3.861128114167987e-05, "loss": 4.3381, "step": 10370 }, { "epoch": 0.31676847892486254, "grad_norm": 0.37980204820632935, "learning_rate": 3.86092689040626e-05, "loss": 4.3659, "step": 10371 }, { "epoch": 0.31679902260232135, "grad_norm": 0.3790188133716583, "learning_rate": 3.8607256541137785e-05, "loss": 4.295, "step": 10372 }, { "epoch": 0.3168295662797801, "grad_norm": 0.38076186180114746, "learning_rate": 3.8605244052923975e-05, "loss": 4.3494, "step": 10373 }, { "epoch": 0.31686010995723884, "grad_norm": 0.37748417258262634, "learning_rate": 3.860323143943968e-05, "loss": 4.4038, "step": 10374 }, { "epoch": 0.3168906536346976, "grad_norm": 0.36885523796081543, "learning_rate": 3.860121870070345e-05, "loss": 4.3767, "step": 10375 }, { "epoch": 0.3169211973121564, "grad_norm": 0.3818368911743164, "learning_rate": 3.8599205836733794e-05, "loss": 4.3236, "step": 10376 }, { "epoch": 0.31695174098961515, "grad_norm": 0.38111400604248047, "learning_rate": 3.859719284754926e-05, "loss": 4.3698, "step": 10377 }, { "epoch": 0.3169822846670739, "grad_norm": 0.3785496950149536, "learning_rate": 3.8595179733168384e-05, "loss": 4.3848, "step": 10378 }, { "epoch": 0.3170128283445327, "grad_norm": 0.3734147846698761, "learning_rate": 3.85931664936097e-05, "loss": 4.2844, "step": 10379 }, { "epoch": 0.31704337202199145, "grad_norm": 0.3781936764717102, "learning_rate": 3.859115312889174e-05, "loss": 4.3897, "step": 10380 }, { "epoch": 0.3170739156994502, "grad_norm": 0.3787905275821686, "learning_rate": 3.858913963903304e-05, "loss": 4.3202, "step": 10381 }, { "epoch": 0.31710445937690895, "grad_norm": 0.3759951591491699, "learning_rate": 3.858712602405216e-05, "loss": 4.2923, "step": 10382 }, { "epoch": 0.31713500305436776, "grad_norm": 0.3804484009742737, "learning_rate": 3.85851122839676e-05, "loss": 4.405, "step": 10383 }, { "epoch": 0.3171655467318265, "grad_norm": 0.37216442823410034, "learning_rate": 3.8583098418797946e-05, "loss": 4.3031, "step": 10384 }, { "epoch": 0.31719609040928526, "grad_norm": 0.37475624680519104, "learning_rate": 3.858108442856172e-05, "loss": 4.305, "step": 10385 }, { "epoch": 0.31722663408674406, "grad_norm": 0.37910231947898865, "learning_rate": 3.857907031327746e-05, "loss": 4.3772, "step": 10386 }, { "epoch": 0.3172571777642028, "grad_norm": 0.36553314328193665, "learning_rate": 3.857705607296372e-05, "loss": 4.3592, "step": 10387 }, { "epoch": 0.31728772144166156, "grad_norm": 0.3780486583709717, "learning_rate": 3.857504170763905e-05, "loss": 4.266, "step": 10388 }, { "epoch": 0.31731826511912037, "grad_norm": 0.3960303068161011, "learning_rate": 3.857302721732199e-05, "loss": 4.3713, "step": 10389 }, { "epoch": 0.3173488087965791, "grad_norm": 0.37353435158729553, "learning_rate": 3.8571012602031086e-05, "loss": 4.295, "step": 10390 }, { "epoch": 0.31737935247403787, "grad_norm": 0.39769306778907776, "learning_rate": 3.856899786178489e-05, "loss": 4.3562, "step": 10391 }, { "epoch": 0.3174098961514966, "grad_norm": 0.3886685073375702, "learning_rate": 3.856698299660196e-05, "loss": 4.303, "step": 10392 }, { "epoch": 0.3174404398289554, "grad_norm": 0.37731778621673584, "learning_rate": 3.8564968006500836e-05, "loss": 4.3145, "step": 10393 }, { "epoch": 0.3174709835064142, "grad_norm": 0.3731251358985901, "learning_rate": 3.856295289150008e-05, "loss": 4.2304, "step": 10394 }, { "epoch": 0.3175015271838729, "grad_norm": 0.37426328659057617, "learning_rate": 3.8560937651618245e-05, "loss": 4.2724, "step": 10395 }, { "epoch": 0.31753207086133173, "grad_norm": 0.3823374807834625, "learning_rate": 3.855892228687388e-05, "loss": 4.251, "step": 10396 }, { "epoch": 0.3175626145387905, "grad_norm": 0.3819817304611206, "learning_rate": 3.855690679728554e-05, "loss": 4.3997, "step": 10397 }, { "epoch": 0.3175931582162492, "grad_norm": 0.3830398619174957, "learning_rate": 3.8554891182871806e-05, "loss": 4.3128, "step": 10398 }, { "epoch": 0.317623701893708, "grad_norm": 0.38591423630714417, "learning_rate": 3.855287544365121e-05, "loss": 4.4103, "step": 10399 }, { "epoch": 0.3176542455711668, "grad_norm": 0.3812245726585388, "learning_rate": 3.8550859579642317e-05, "loss": 4.3514, "step": 10400 }, { "epoch": 0.31768478924862553, "grad_norm": 0.38467395305633545, "learning_rate": 3.8548843590863706e-05, "loss": 4.3416, "step": 10401 }, { "epoch": 0.3177153329260843, "grad_norm": 0.4000292420387268, "learning_rate": 3.8546827477333914e-05, "loss": 4.2805, "step": 10402 }, { "epoch": 0.3177458766035431, "grad_norm": 0.382599800825119, "learning_rate": 3.854481123907152e-05, "loss": 4.4004, "step": 10403 }, { "epoch": 0.31777642028100184, "grad_norm": 0.37010085582733154, "learning_rate": 3.854279487609509e-05, "loss": 4.3471, "step": 10404 }, { "epoch": 0.3178069639584606, "grad_norm": 0.3700402081012726, "learning_rate": 3.854077838842318e-05, "loss": 4.313, "step": 10405 }, { "epoch": 0.3178375076359194, "grad_norm": 0.37607747316360474, "learning_rate": 3.853876177607436e-05, "loss": 4.3353, "step": 10406 }, { "epoch": 0.31786805131337814, "grad_norm": 0.3772450387477875, "learning_rate": 3.85367450390672e-05, "loss": 4.3296, "step": 10407 }, { "epoch": 0.3178985949908369, "grad_norm": 0.36981862783432007, "learning_rate": 3.853472817742027e-05, "loss": 4.3129, "step": 10408 }, { "epoch": 0.31792913866829564, "grad_norm": 0.36230701208114624, "learning_rate": 3.8532711191152136e-05, "loss": 4.4136, "step": 10409 }, { "epoch": 0.31795968234575445, "grad_norm": 0.3823683559894562, "learning_rate": 3.853069408028137e-05, "loss": 4.403, "step": 10410 }, { "epoch": 0.3179902260232132, "grad_norm": 0.39313119649887085, "learning_rate": 3.852867684482656e-05, "loss": 4.4699, "step": 10411 }, { "epoch": 0.31802076970067195, "grad_norm": 0.3673509955406189, "learning_rate": 3.852665948480626e-05, "loss": 4.3496, "step": 10412 }, { "epoch": 0.31805131337813075, "grad_norm": 0.37361940741539, "learning_rate": 3.852464200023905e-05, "loss": 4.3861, "step": 10413 }, { "epoch": 0.3180818570555895, "grad_norm": 0.3789946734905243, "learning_rate": 3.85226243911435e-05, "loss": 4.3968, "step": 10414 }, { "epoch": 0.31811240073304825, "grad_norm": 0.36669138073921204, "learning_rate": 3.852060665753821e-05, "loss": 4.2584, "step": 10415 }, { "epoch": 0.318142944410507, "grad_norm": 0.372929185628891, "learning_rate": 3.851858879944173e-05, "loss": 4.3437, "step": 10416 }, { "epoch": 0.3181734880879658, "grad_norm": 0.37553977966308594, "learning_rate": 3.851657081687265e-05, "loss": 4.3095, "step": 10417 }, { "epoch": 0.31820403176542456, "grad_norm": 0.37222743034362793, "learning_rate": 3.8514552709849566e-05, "loss": 4.3034, "step": 10418 }, { "epoch": 0.3182345754428833, "grad_norm": 0.38304972648620605, "learning_rate": 3.8512534478391036e-05, "loss": 4.244, "step": 10419 }, { "epoch": 0.3182651191203421, "grad_norm": 0.3607712984085083, "learning_rate": 3.851051612251566e-05, "loss": 4.2745, "step": 10420 }, { "epoch": 0.31829566279780086, "grad_norm": 0.3669217824935913, "learning_rate": 3.8508497642242015e-05, "loss": 4.3475, "step": 10421 }, { "epoch": 0.3183262064752596, "grad_norm": 0.3853796422481537, "learning_rate": 3.8506479037588683e-05, "loss": 4.3823, "step": 10422 }, { "epoch": 0.31835675015271836, "grad_norm": 0.3695773780345917, "learning_rate": 3.8504460308574266e-05, "loss": 4.3655, "step": 10423 }, { "epoch": 0.31838729383017716, "grad_norm": 0.3734772503376007, "learning_rate": 3.850244145521732e-05, "loss": 4.3925, "step": 10424 }, { "epoch": 0.3184178375076359, "grad_norm": 0.376578152179718, "learning_rate": 3.850042247753647e-05, "loss": 4.4388, "step": 10425 }, { "epoch": 0.31844838118509466, "grad_norm": 0.39067506790161133, "learning_rate": 3.849840337555028e-05, "loss": 4.3504, "step": 10426 }, { "epoch": 0.31847892486255347, "grad_norm": 0.38089674711227417, "learning_rate": 3.8496384149277355e-05, "loss": 4.3758, "step": 10427 }, { "epoch": 0.3185094685400122, "grad_norm": 0.39067989587783813, "learning_rate": 3.849436479873628e-05, "loss": 4.3646, "step": 10428 }, { "epoch": 0.31854001221747097, "grad_norm": 0.3934325873851776, "learning_rate": 3.8492345323945644e-05, "loss": 4.3531, "step": 10429 }, { "epoch": 0.3185705558949298, "grad_norm": 0.3920464813709259, "learning_rate": 3.8490325724924056e-05, "loss": 4.3178, "step": 10430 }, { "epoch": 0.3186010995723885, "grad_norm": 0.3684944808483124, "learning_rate": 3.84883060016901e-05, "loss": 4.3246, "step": 10431 }, { "epoch": 0.3186316432498473, "grad_norm": 0.37008875608444214, "learning_rate": 3.848628615426237e-05, "loss": 4.2701, "step": 10432 }, { "epoch": 0.318662186927306, "grad_norm": 0.3768477439880371, "learning_rate": 3.848426618265948e-05, "loss": 4.3607, "step": 10433 }, { "epoch": 0.31869273060476483, "grad_norm": 0.39080944657325745, "learning_rate": 3.848224608690001e-05, "loss": 4.3959, "step": 10434 }, { "epoch": 0.3187232742822236, "grad_norm": 0.3779568076133728, "learning_rate": 3.8480225867002575e-05, "loss": 4.353, "step": 10435 }, { "epoch": 0.31875381795968233, "grad_norm": 0.39044249057769775, "learning_rate": 3.847820552298577e-05, "loss": 4.4273, "step": 10436 }, { "epoch": 0.31878436163714113, "grad_norm": 0.37695229053497314, "learning_rate": 3.847618505486819e-05, "loss": 4.3489, "step": 10437 }, { "epoch": 0.3188149053145999, "grad_norm": 0.3872216045856476, "learning_rate": 3.847416446266845e-05, "loss": 4.3467, "step": 10438 }, { "epoch": 0.31884544899205863, "grad_norm": 0.3757525682449341, "learning_rate": 3.847214374640514e-05, "loss": 4.339, "step": 10439 }, { "epoch": 0.3188759926695174, "grad_norm": 0.37441715598106384, "learning_rate": 3.8470122906096897e-05, "loss": 4.3437, "step": 10440 }, { "epoch": 0.3189065363469762, "grad_norm": 0.40631982684135437, "learning_rate": 3.846810194176229e-05, "loss": 4.3192, "step": 10441 }, { "epoch": 0.31893708002443494, "grad_norm": 0.3703807294368744, "learning_rate": 3.846608085341995e-05, "loss": 4.2595, "step": 10442 }, { "epoch": 0.3189676237018937, "grad_norm": 0.39541617035865784, "learning_rate": 3.846405964108847e-05, "loss": 4.3587, "step": 10443 }, { "epoch": 0.3189981673793525, "grad_norm": 0.37719395756721497, "learning_rate": 3.8462038304786486e-05, "loss": 4.3226, "step": 10444 }, { "epoch": 0.31902871105681124, "grad_norm": 0.3873535692691803, "learning_rate": 3.8460016844532585e-05, "loss": 4.3765, "step": 10445 }, { "epoch": 0.31905925473427, "grad_norm": 0.3818018138408661, "learning_rate": 3.845799526034539e-05, "loss": 4.3883, "step": 10446 }, { "epoch": 0.3190897984117288, "grad_norm": 0.39212533831596375, "learning_rate": 3.8455973552243505e-05, "loss": 4.2703, "step": 10447 }, { "epoch": 0.31912034208918755, "grad_norm": 0.3770270049571991, "learning_rate": 3.845395172024556e-05, "loss": 4.2593, "step": 10448 }, { "epoch": 0.3191508857666463, "grad_norm": 0.37685441970825195, "learning_rate": 3.845192976437018e-05, "loss": 4.3793, "step": 10449 }, { "epoch": 0.31918142944410505, "grad_norm": 0.38111239671707153, "learning_rate": 3.844990768463595e-05, "loss": 4.3321, "step": 10450 }, { "epoch": 0.31921197312156385, "grad_norm": 0.36857351660728455, "learning_rate": 3.84478854810615e-05, "loss": 4.3012, "step": 10451 }, { "epoch": 0.3192425167990226, "grad_norm": 0.38029131293296814, "learning_rate": 3.844586315366546e-05, "loss": 4.2925, "step": 10452 }, { "epoch": 0.31927306047648135, "grad_norm": 0.4313242733478546, "learning_rate": 3.844384070246645e-05, "loss": 4.2445, "step": 10453 }, { "epoch": 0.31930360415394016, "grad_norm": 0.3757711946964264, "learning_rate": 3.844181812748308e-05, "loss": 4.3112, "step": 10454 }, { "epoch": 0.3193341478313989, "grad_norm": 0.37369677424430847, "learning_rate": 3.8439795428733984e-05, "loss": 4.3148, "step": 10455 }, { "epoch": 0.31936469150885766, "grad_norm": 0.3720017075538635, "learning_rate": 3.8437772606237774e-05, "loss": 4.3106, "step": 10456 }, { "epoch": 0.3193952351863164, "grad_norm": 0.3722454607486725, "learning_rate": 3.843574966001309e-05, "loss": 4.3823, "step": 10457 }, { "epoch": 0.3194257788637752, "grad_norm": 0.371042937040329, "learning_rate": 3.8433726590078546e-05, "loss": 4.3648, "step": 10458 }, { "epoch": 0.31945632254123396, "grad_norm": 0.3895944356918335, "learning_rate": 3.8431703396452776e-05, "loss": 4.3257, "step": 10459 }, { "epoch": 0.3194868662186927, "grad_norm": 0.36566174030303955, "learning_rate": 3.842968007915441e-05, "loss": 4.2763, "step": 10460 }, { "epoch": 0.3195174098961515, "grad_norm": 0.3951677978038788, "learning_rate": 3.842765663820207e-05, "loss": 4.3166, "step": 10461 }, { "epoch": 0.31954795357361027, "grad_norm": 0.3783378005027771, "learning_rate": 3.84256330736144e-05, "loss": 4.3057, "step": 10462 }, { "epoch": 0.319578497251069, "grad_norm": 0.36833229660987854, "learning_rate": 3.842360938541001e-05, "loss": 4.2282, "step": 10463 }, { "epoch": 0.3196090409285278, "grad_norm": 0.38476985692977905, "learning_rate": 3.842158557360756e-05, "loss": 4.3063, "step": 10464 }, { "epoch": 0.31963958460598657, "grad_norm": 0.3759729266166687, "learning_rate": 3.841956163822565e-05, "loss": 4.3399, "step": 10465 }, { "epoch": 0.3196701282834453, "grad_norm": 0.3824616074562073, "learning_rate": 3.841753757928296e-05, "loss": 4.2937, "step": 10466 }, { "epoch": 0.31970067196090407, "grad_norm": 0.39222460985183716, "learning_rate": 3.84155133967981e-05, "loss": 4.3148, "step": 10467 }, { "epoch": 0.3197312156383629, "grad_norm": 0.3896017074584961, "learning_rate": 3.84134890907897e-05, "loss": 4.4152, "step": 10468 }, { "epoch": 0.3197617593158216, "grad_norm": 0.3940577507019043, "learning_rate": 3.841146466127641e-05, "loss": 4.3144, "step": 10469 }, { "epoch": 0.3197923029932804, "grad_norm": 0.3800131678581238, "learning_rate": 3.840944010827688e-05, "loss": 4.3142, "step": 10470 }, { "epoch": 0.3198228466707392, "grad_norm": 0.36733582615852356, "learning_rate": 3.840741543180973e-05, "loss": 4.4265, "step": 10471 }, { "epoch": 0.31985339034819793, "grad_norm": 0.37618228793144226, "learning_rate": 3.8405390631893615e-05, "loss": 4.3616, "step": 10472 }, { "epoch": 0.3198839340256567, "grad_norm": 0.3745684027671814, "learning_rate": 3.840336570854718e-05, "loss": 4.312, "step": 10473 }, { "epoch": 0.31991447770311543, "grad_norm": 0.38251662254333496, "learning_rate": 3.840134066178906e-05, "loss": 4.3153, "step": 10474 }, { "epoch": 0.31994502138057423, "grad_norm": 0.36794382333755493, "learning_rate": 3.839931549163791e-05, "loss": 4.3235, "step": 10475 }, { "epoch": 0.319975565058033, "grad_norm": 0.3732772171497345, "learning_rate": 3.839729019811238e-05, "loss": 4.4112, "step": 10476 }, { "epoch": 0.32000610873549173, "grad_norm": 0.3703988790512085, "learning_rate": 3.83952647812311e-05, "loss": 4.2501, "step": 10477 }, { "epoch": 0.32003665241295054, "grad_norm": 0.38070911169052124, "learning_rate": 3.839323924101273e-05, "loss": 4.2157, "step": 10478 }, { "epoch": 0.3200671960904093, "grad_norm": 0.36754295229911804, "learning_rate": 3.839121357747593e-05, "loss": 4.3429, "step": 10479 }, { "epoch": 0.32009773976786804, "grad_norm": 0.378907710313797, "learning_rate": 3.838918779063933e-05, "loss": 4.3539, "step": 10480 }, { "epoch": 0.32012828344532684, "grad_norm": 0.3792991042137146, "learning_rate": 3.83871618805216e-05, "loss": 4.2652, "step": 10481 }, { "epoch": 0.3201588271227856, "grad_norm": 0.37080076336860657, "learning_rate": 3.838513584714138e-05, "loss": 4.3608, "step": 10482 }, { "epoch": 0.32018937080024434, "grad_norm": 0.376213937997818, "learning_rate": 3.838310969051735e-05, "loss": 4.3217, "step": 10483 }, { "epoch": 0.3202199144777031, "grad_norm": 0.3730427324771881, "learning_rate": 3.838108341066814e-05, "loss": 4.3536, "step": 10484 }, { "epoch": 0.3202504581551619, "grad_norm": 0.3721662163734436, "learning_rate": 3.837905700761241e-05, "loss": 4.2483, "step": 10485 }, { "epoch": 0.32028100183262065, "grad_norm": 0.38813984394073486, "learning_rate": 3.837703048136882e-05, "loss": 4.2657, "step": 10486 }, { "epoch": 0.3203115455100794, "grad_norm": 0.3654096722602844, "learning_rate": 3.837500383195604e-05, "loss": 4.3302, "step": 10487 }, { "epoch": 0.3203420891875382, "grad_norm": 0.385548859834671, "learning_rate": 3.8372977059392714e-05, "loss": 4.2639, "step": 10488 }, { "epoch": 0.32037263286499695, "grad_norm": 0.3848058581352234, "learning_rate": 3.8370950163697525e-05, "loss": 4.4159, "step": 10489 }, { "epoch": 0.3204031765424557, "grad_norm": 0.3735301196575165, "learning_rate": 3.836892314488913e-05, "loss": 4.3189, "step": 10490 }, { "epoch": 0.32043372021991445, "grad_norm": 0.3815096616744995, "learning_rate": 3.8366896002986166e-05, "loss": 4.3644, "step": 10491 }, { "epoch": 0.32046426389737326, "grad_norm": 0.38332486152648926, "learning_rate": 3.836486873800732e-05, "loss": 4.3136, "step": 10492 }, { "epoch": 0.320494807574832, "grad_norm": 0.3690836429595947, "learning_rate": 3.836284134997127e-05, "loss": 4.315, "step": 10493 }, { "epoch": 0.32052535125229076, "grad_norm": 0.39531368017196655, "learning_rate": 3.8360813838896656e-05, "loss": 4.3413, "step": 10494 }, { "epoch": 0.32055589492974956, "grad_norm": 0.398515909910202, "learning_rate": 3.835878620480216e-05, "loss": 4.4241, "step": 10495 }, { "epoch": 0.3205864386072083, "grad_norm": 0.380704790353775, "learning_rate": 3.835675844770645e-05, "loss": 4.3314, "step": 10496 }, { "epoch": 0.32061698228466706, "grad_norm": 0.39142757654190063, "learning_rate": 3.835473056762821e-05, "loss": 4.3442, "step": 10497 }, { "epoch": 0.3206475259621258, "grad_norm": 0.3848225772380829, "learning_rate": 3.83527025645861e-05, "loss": 4.3497, "step": 10498 }, { "epoch": 0.3206780696395846, "grad_norm": 0.3968939185142517, "learning_rate": 3.835067443859878e-05, "loss": 4.2319, "step": 10499 }, { "epoch": 0.32070861331704337, "grad_norm": 0.38482362031936646, "learning_rate": 3.834864618968494e-05, "loss": 4.4872, "step": 10500 }, { "epoch": 0.3207391569945021, "grad_norm": 0.3757272958755493, "learning_rate": 3.834661781786325e-05, "loss": 4.3033, "step": 10501 }, { "epoch": 0.3207697006719609, "grad_norm": 0.37623903155326843, "learning_rate": 3.834458932315239e-05, "loss": 4.3878, "step": 10502 }, { "epoch": 0.32080024434941967, "grad_norm": 0.4039318859577179, "learning_rate": 3.834256070557104e-05, "loss": 4.2181, "step": 10503 }, { "epoch": 0.3208307880268784, "grad_norm": 0.377073734998703, "learning_rate": 3.834053196513786e-05, "loss": 4.2683, "step": 10504 }, { "epoch": 0.3208613317043372, "grad_norm": 0.389314204454422, "learning_rate": 3.833850310187156e-05, "loss": 4.3416, "step": 10505 }, { "epoch": 0.320891875381796, "grad_norm": 0.4225318133831024, "learning_rate": 3.833647411579079e-05, "loss": 4.2932, "step": 10506 }, { "epoch": 0.3209224190592547, "grad_norm": 0.3826349079608917, "learning_rate": 3.8334445006914255e-05, "loss": 4.1599, "step": 10507 }, { "epoch": 0.3209529627367135, "grad_norm": 0.3743135631084442, "learning_rate": 3.833241577526062e-05, "loss": 4.288, "step": 10508 }, { "epoch": 0.3209835064141723, "grad_norm": 0.38325783610343933, "learning_rate": 3.833038642084859e-05, "loss": 4.4323, "step": 10509 }, { "epoch": 0.32101405009163103, "grad_norm": 0.3742012679576874, "learning_rate": 3.832835694369683e-05, "loss": 4.2521, "step": 10510 }, { "epoch": 0.3210445937690898, "grad_norm": 0.37944161891937256, "learning_rate": 3.832632734382403e-05, "loss": 4.3383, "step": 10511 }, { "epoch": 0.3210751374465486, "grad_norm": 0.37270066142082214, "learning_rate": 3.832429762124889e-05, "loss": 4.3815, "step": 10512 }, { "epoch": 0.32110568112400734, "grad_norm": 0.3907017111778259, "learning_rate": 3.832226777599009e-05, "loss": 4.2773, "step": 10513 }, { "epoch": 0.3211362248014661, "grad_norm": 0.3725239038467407, "learning_rate": 3.832023780806633e-05, "loss": 4.2973, "step": 10514 }, { "epoch": 0.32116676847892484, "grad_norm": 0.3832005560398102, "learning_rate": 3.831820771749628e-05, "loss": 4.3417, "step": 10515 }, { "epoch": 0.32119731215638364, "grad_norm": 0.4008452296257019, "learning_rate": 3.8316177504298644e-05, "loss": 4.2767, "step": 10516 }, { "epoch": 0.3212278558338424, "grad_norm": 0.3811971843242645, "learning_rate": 3.831414716849212e-05, "loss": 4.3394, "step": 10517 }, { "epoch": 0.32125839951130114, "grad_norm": 0.3787597715854645, "learning_rate": 3.831211671009539e-05, "loss": 4.316, "step": 10518 }, { "epoch": 0.32128894318875995, "grad_norm": 0.3835720717906952, "learning_rate": 3.8310086129127164e-05, "loss": 4.3532, "step": 10519 }, { "epoch": 0.3213194868662187, "grad_norm": 0.37482908368110657, "learning_rate": 3.8308055425606135e-05, "loss": 4.2121, "step": 10520 }, { "epoch": 0.32135003054367745, "grad_norm": 0.3723105192184448, "learning_rate": 3.8306024599550995e-05, "loss": 4.3316, "step": 10521 }, { "epoch": 0.32138057422113625, "grad_norm": 0.3742869794368744, "learning_rate": 3.830399365098044e-05, "loss": 4.3445, "step": 10522 }, { "epoch": 0.321411117898595, "grad_norm": 0.3931580185890198, "learning_rate": 3.8301962579913175e-05, "loss": 4.3603, "step": 10523 }, { "epoch": 0.32144166157605375, "grad_norm": 0.3900575637817383, "learning_rate": 3.829993138636791e-05, "loss": 4.3454, "step": 10524 }, { "epoch": 0.3214722052535125, "grad_norm": 0.3806670010089874, "learning_rate": 3.829790007036334e-05, "loss": 4.4046, "step": 10525 }, { "epoch": 0.3215027489309713, "grad_norm": 0.38486307859420776, "learning_rate": 3.8295868631918156e-05, "loss": 4.291, "step": 10526 }, { "epoch": 0.32153329260843005, "grad_norm": 0.37364843487739563, "learning_rate": 3.829383707105107e-05, "loss": 4.317, "step": 10527 }, { "epoch": 0.3215638362858888, "grad_norm": 0.3725515902042389, "learning_rate": 3.8291805387780796e-05, "loss": 4.3255, "step": 10528 }, { "epoch": 0.3215943799633476, "grad_norm": 0.39006948471069336, "learning_rate": 3.828977358212604e-05, "loss": 4.3051, "step": 10529 }, { "epoch": 0.32162492364080636, "grad_norm": 0.3665837049484253, "learning_rate": 3.828774165410551e-05, "loss": 4.3762, "step": 10530 }, { "epoch": 0.3216554673182651, "grad_norm": 0.38110101222991943, "learning_rate": 3.828570960373791e-05, "loss": 4.3473, "step": 10531 }, { "epoch": 0.32168601099572386, "grad_norm": 1.1187163591384888, "learning_rate": 3.828367743104194e-05, "loss": 4.3253, "step": 10532 }, { "epoch": 0.32171655467318266, "grad_norm": 0.3685625493526459, "learning_rate": 3.828164513603632e-05, "loss": 4.3151, "step": 10533 }, { "epoch": 0.3217470983506414, "grad_norm": 0.3849989175796509, "learning_rate": 3.8279612718739777e-05, "loss": 4.4033, "step": 10534 }, { "epoch": 0.32177764202810016, "grad_norm": 0.37249305844306946, "learning_rate": 3.8277580179171015e-05, "loss": 4.311, "step": 10535 }, { "epoch": 0.32180818570555897, "grad_norm": 0.36691656708717346, "learning_rate": 3.827554751734873e-05, "loss": 4.3344, "step": 10536 }, { "epoch": 0.3218387293830177, "grad_norm": 0.37788131833076477, "learning_rate": 3.8273514733291666e-05, "loss": 4.3068, "step": 10537 }, { "epoch": 0.32186927306047647, "grad_norm": 0.37010282278060913, "learning_rate": 3.8271481827018523e-05, "loss": 4.3216, "step": 10538 }, { "epoch": 0.3218998167379353, "grad_norm": 0.36955952644348145, "learning_rate": 3.826944879854802e-05, "loss": 4.3357, "step": 10539 }, { "epoch": 0.321930360415394, "grad_norm": 0.3811326324939728, "learning_rate": 3.826741564789888e-05, "loss": 4.2685, "step": 10540 }, { "epoch": 0.3219609040928528, "grad_norm": 0.36728596687316895, "learning_rate": 3.826538237508983e-05, "loss": 4.3635, "step": 10541 }, { "epoch": 0.3219914477703115, "grad_norm": 0.38062217831611633, "learning_rate": 3.826334898013958e-05, "loss": 4.3042, "step": 10542 }, { "epoch": 0.32202199144777033, "grad_norm": 0.39787623286247253, "learning_rate": 3.826131546306685e-05, "loss": 4.3166, "step": 10543 }, { "epoch": 0.3220525351252291, "grad_norm": 0.381929874420166, "learning_rate": 3.825928182389038e-05, "loss": 4.3383, "step": 10544 }, { "epoch": 0.3220830788026878, "grad_norm": 0.3849766254425049, "learning_rate": 3.825724806262888e-05, "loss": 4.299, "step": 10545 }, { "epoch": 0.32211362248014663, "grad_norm": 0.3816312849521637, "learning_rate": 3.825521417930108e-05, "loss": 4.3924, "step": 10546 }, { "epoch": 0.3221441661576054, "grad_norm": 0.37530970573425293, "learning_rate": 3.8253180173925714e-05, "loss": 4.3513, "step": 10547 }, { "epoch": 0.32217470983506413, "grad_norm": 0.3749958574771881, "learning_rate": 3.82511460465215e-05, "loss": 4.2606, "step": 10548 }, { "epoch": 0.3222052535125229, "grad_norm": 0.37961387634277344, "learning_rate": 3.8249111797107175e-05, "loss": 4.3209, "step": 10549 }, { "epoch": 0.3222357971899817, "grad_norm": 0.3803858757019043, "learning_rate": 3.824707742570145e-05, "loss": 4.3004, "step": 10550 }, { "epoch": 0.32226634086744044, "grad_norm": 0.38041946291923523, "learning_rate": 3.8245042932323086e-05, "loss": 4.2738, "step": 10551 }, { "epoch": 0.3222968845448992, "grad_norm": 0.38549768924713135, "learning_rate": 3.82430083169908e-05, "loss": 4.3439, "step": 10552 }, { "epoch": 0.322327428222358, "grad_norm": 0.372995525598526, "learning_rate": 3.824097357972333e-05, "loss": 4.3777, "step": 10553 }, { "epoch": 0.32235797189981674, "grad_norm": 0.3721819818019867, "learning_rate": 3.8238938720539406e-05, "loss": 4.3767, "step": 10554 }, { "epoch": 0.3223885155772755, "grad_norm": 0.37144479155540466, "learning_rate": 3.8236903739457765e-05, "loss": 4.3223, "step": 10555 }, { "epoch": 0.3224190592547343, "grad_norm": 0.3745214343070984, "learning_rate": 3.823486863649714e-05, "loss": 4.3167, "step": 10556 }, { "epoch": 0.32244960293219305, "grad_norm": 0.3746185600757599, "learning_rate": 3.823283341167628e-05, "loss": 4.4085, "step": 10557 }, { "epoch": 0.3224801466096518, "grad_norm": 0.37292495369911194, "learning_rate": 3.823079806501393e-05, "loss": 4.3401, "step": 10558 }, { "epoch": 0.32251069028711055, "grad_norm": 0.37473103404045105, "learning_rate": 3.822876259652881e-05, "loss": 4.3878, "step": 10559 }, { "epoch": 0.32254123396456935, "grad_norm": 0.3766993582248688, "learning_rate": 3.822672700623967e-05, "loss": 4.2962, "step": 10560 }, { "epoch": 0.3225717776420281, "grad_norm": 0.3656834661960602, "learning_rate": 3.822469129416526e-05, "loss": 4.2824, "step": 10561 }, { "epoch": 0.32260232131948685, "grad_norm": 0.3812783360481262, "learning_rate": 3.822265546032431e-05, "loss": 4.3144, "step": 10562 }, { "epoch": 0.32263286499694566, "grad_norm": 0.3645671606063843, "learning_rate": 3.822061950473558e-05, "loss": 4.3685, "step": 10563 }, { "epoch": 0.3226634086744044, "grad_norm": 0.39260903000831604, "learning_rate": 3.82185834274178e-05, "loss": 4.3572, "step": 10564 }, { "epoch": 0.32269395235186316, "grad_norm": 0.3801555931568146, "learning_rate": 3.821654722838973e-05, "loss": 4.3163, "step": 10565 }, { "epoch": 0.3227244960293219, "grad_norm": 0.37579554319381714, "learning_rate": 3.821451090767012e-05, "loss": 4.3478, "step": 10566 }, { "epoch": 0.3227550397067807, "grad_norm": 0.36742982268333435, "learning_rate": 3.82124744652777e-05, "loss": 4.2729, "step": 10567 }, { "epoch": 0.32278558338423946, "grad_norm": 0.3765324652194977, "learning_rate": 3.821043790123125e-05, "loss": 4.3654, "step": 10568 }, { "epoch": 0.3228161270616982, "grad_norm": 0.3844006657600403, "learning_rate": 3.8208401215549496e-05, "loss": 4.3735, "step": 10569 }, { "epoch": 0.322846670739157, "grad_norm": 0.3862181305885315, "learning_rate": 3.820636440825121e-05, "loss": 4.3679, "step": 10570 }, { "epoch": 0.32287721441661577, "grad_norm": 0.3723951578140259, "learning_rate": 3.820432747935513e-05, "loss": 4.3066, "step": 10571 }, { "epoch": 0.3229077580940745, "grad_norm": 0.36877450346946716, "learning_rate": 3.820229042888002e-05, "loss": 4.3284, "step": 10572 }, { "epoch": 0.32293830177153326, "grad_norm": 0.3761518895626068, "learning_rate": 3.8200253256844634e-05, "loss": 4.3595, "step": 10573 }, { "epoch": 0.32296884544899207, "grad_norm": 0.38734984397888184, "learning_rate": 3.8198215963267725e-05, "loss": 4.2976, "step": 10574 }, { "epoch": 0.3229993891264508, "grad_norm": 0.393579363822937, "learning_rate": 3.819617854816806e-05, "loss": 4.1923, "step": 10575 }, { "epoch": 0.32302993280390957, "grad_norm": 0.3875121772289276, "learning_rate": 3.819414101156439e-05, "loss": 4.2939, "step": 10576 }, { "epoch": 0.3230604764813684, "grad_norm": 0.37279337644577026, "learning_rate": 3.8192103353475487e-05, "loss": 4.3804, "step": 10577 }, { "epoch": 0.3230910201588271, "grad_norm": 0.39747366309165955, "learning_rate": 3.8190065573920106e-05, "loss": 4.4131, "step": 10578 }, { "epoch": 0.3231215638362859, "grad_norm": 0.37426844239234924, "learning_rate": 3.8188027672917005e-05, "loss": 4.392, "step": 10579 }, { "epoch": 0.3231521075137447, "grad_norm": 0.38986319303512573, "learning_rate": 3.818598965048495e-05, "loss": 4.3398, "step": 10580 }, { "epoch": 0.32318265119120343, "grad_norm": 0.3845546841621399, "learning_rate": 3.818395150664271e-05, "loss": 4.3628, "step": 10581 }, { "epoch": 0.3232131948686622, "grad_norm": 0.37272968888282776, "learning_rate": 3.818191324140905e-05, "loss": 4.2392, "step": 10582 }, { "epoch": 0.32324373854612093, "grad_norm": 0.3730921745300293, "learning_rate": 3.8179874854802746e-05, "loss": 4.3244, "step": 10583 }, { "epoch": 0.32327428222357973, "grad_norm": 0.3755839765071869, "learning_rate": 3.8177836346842554e-05, "loss": 4.338, "step": 10584 }, { "epoch": 0.3233048259010385, "grad_norm": 0.3720683455467224, "learning_rate": 3.8175797717547244e-05, "loss": 4.2821, "step": 10585 }, { "epoch": 0.32333536957849723, "grad_norm": 0.37008658051490784, "learning_rate": 3.817375896693559e-05, "loss": 4.3446, "step": 10586 }, { "epoch": 0.32336591325595604, "grad_norm": 0.38083788752555847, "learning_rate": 3.8171720095026364e-05, "loss": 4.2896, "step": 10587 }, { "epoch": 0.3233964569334148, "grad_norm": 0.3688001036643982, "learning_rate": 3.816968110183834e-05, "loss": 4.3181, "step": 10588 }, { "epoch": 0.32342700061087354, "grad_norm": 0.3760835528373718, "learning_rate": 3.8167641987390294e-05, "loss": 4.3541, "step": 10589 }, { "epoch": 0.3234575442883323, "grad_norm": 0.36516639590263367, "learning_rate": 3.816560275170099e-05, "loss": 4.2908, "step": 10590 }, { "epoch": 0.3234880879657911, "grad_norm": 0.39105141162872314, "learning_rate": 3.8163563394789216e-05, "loss": 4.2783, "step": 10591 }, { "epoch": 0.32351863164324984, "grad_norm": 0.3825394809246063, "learning_rate": 3.8161523916673746e-05, "loss": 4.3719, "step": 10592 }, { "epoch": 0.3235491753207086, "grad_norm": 0.376953661441803, "learning_rate": 3.815948431737336e-05, "loss": 4.2899, "step": 10593 }, { "epoch": 0.3235797189981674, "grad_norm": 0.3821476101875305, "learning_rate": 3.815744459690683e-05, "loss": 4.3777, "step": 10594 }, { "epoch": 0.32361026267562615, "grad_norm": 0.3862498700618744, "learning_rate": 3.815540475529296e-05, "loss": 4.337, "step": 10595 }, { "epoch": 0.3236408063530849, "grad_norm": 0.383215993642807, "learning_rate": 3.8153364792550495e-05, "loss": 4.2809, "step": 10596 }, { "epoch": 0.3236713500305437, "grad_norm": 0.38046136498451233, "learning_rate": 3.8151324708698244e-05, "loss": 4.3492, "step": 10597 }, { "epoch": 0.32370189370800245, "grad_norm": 0.3728043735027313, "learning_rate": 3.8149284503754984e-05, "loss": 4.3484, "step": 10598 }, { "epoch": 0.3237324373854612, "grad_norm": 0.386028915643692, "learning_rate": 3.81472441777395e-05, "loss": 4.2707, "step": 10599 }, { "epoch": 0.32376298106291995, "grad_norm": 0.3805486857891083, "learning_rate": 3.8145203730670594e-05, "loss": 4.389, "step": 10600 }, { "epoch": 0.32379352474037876, "grad_norm": 0.376095175743103, "learning_rate": 3.814316316256702e-05, "loss": 4.3826, "step": 10601 }, { "epoch": 0.3238240684178375, "grad_norm": 0.3838109076023102, "learning_rate": 3.8141122473447595e-05, "loss": 4.3278, "step": 10602 }, { "epoch": 0.32385461209529626, "grad_norm": 0.3838157057762146, "learning_rate": 3.8139081663331095e-05, "loss": 4.2419, "step": 10603 }, { "epoch": 0.32388515577275506, "grad_norm": 0.375803679227829, "learning_rate": 3.813704073223631e-05, "loss": 4.3521, "step": 10604 }, { "epoch": 0.3239156994502138, "grad_norm": 2.426758289337158, "learning_rate": 3.813499968018204e-05, "loss": 4.38, "step": 10605 }, { "epoch": 0.32394624312767256, "grad_norm": 0.3884294927120209, "learning_rate": 3.813295850718708e-05, "loss": 4.3625, "step": 10606 }, { "epoch": 0.3239767868051313, "grad_norm": 0.3832447826862335, "learning_rate": 3.8130917213270215e-05, "loss": 4.3446, "step": 10607 }, { "epoch": 0.3240073304825901, "grad_norm": 0.3844737708568573, "learning_rate": 3.8128875798450246e-05, "loss": 4.3497, "step": 10608 }, { "epoch": 0.32403787416004887, "grad_norm": 0.3751254975795746, "learning_rate": 3.812683426274596e-05, "loss": 4.3856, "step": 10609 }, { "epoch": 0.3240684178375076, "grad_norm": 0.3979848027229309, "learning_rate": 3.812479260617618e-05, "loss": 4.3101, "step": 10610 }, { "epoch": 0.3240989615149664, "grad_norm": 0.39096710085868835, "learning_rate": 3.8122750828759665e-05, "loss": 4.3247, "step": 10611 }, { "epoch": 0.32412950519242517, "grad_norm": 0.36884424090385437, "learning_rate": 3.8120708930515245e-05, "loss": 4.3211, "step": 10612 }, { "epoch": 0.3241600488698839, "grad_norm": 0.37121713161468506, "learning_rate": 3.811866691146171e-05, "loss": 4.3851, "step": 10613 }, { "epoch": 0.3241905925473427, "grad_norm": 0.5071463584899902, "learning_rate": 3.811662477161787e-05, "loss": 4.3747, "step": 10614 }, { "epoch": 0.3242211362248015, "grad_norm": 0.38643527030944824, "learning_rate": 3.8114582511002516e-05, "loss": 4.3914, "step": 10615 }, { "epoch": 0.3242516799022602, "grad_norm": 0.3772129416465759, "learning_rate": 3.8112540129634456e-05, "loss": 4.3301, "step": 10616 }, { "epoch": 0.324282223579719, "grad_norm": 0.37258902192115784, "learning_rate": 3.81104976275325e-05, "loss": 4.3689, "step": 10617 }, { "epoch": 0.3243127672571778, "grad_norm": 0.38006868958473206, "learning_rate": 3.8108455004715446e-05, "loss": 4.294, "step": 10618 }, { "epoch": 0.32434331093463653, "grad_norm": 0.3724178075790405, "learning_rate": 3.8106412261202116e-05, "loss": 4.321, "step": 10619 }, { "epoch": 0.3243738546120953, "grad_norm": 0.3681780993938446, "learning_rate": 3.810436939701131e-05, "loss": 4.3984, "step": 10620 }, { "epoch": 0.3244043982895541, "grad_norm": 0.37901198863983154, "learning_rate": 3.810232641216183e-05, "loss": 4.348, "step": 10621 }, { "epoch": 0.32443494196701284, "grad_norm": 0.3916771709918976, "learning_rate": 3.81002833066725e-05, "loss": 4.3963, "step": 10622 }, { "epoch": 0.3244654856444716, "grad_norm": 0.3762214779853821, "learning_rate": 3.8098240080562134e-05, "loss": 4.2748, "step": 10623 }, { "epoch": 0.32449602932193033, "grad_norm": 0.3744577169418335, "learning_rate": 3.8096196733849524e-05, "loss": 4.3595, "step": 10624 }, { "epoch": 0.32452657299938914, "grad_norm": 0.3840920925140381, "learning_rate": 3.809415326655349e-05, "loss": 4.381, "step": 10625 }, { "epoch": 0.3245571166768479, "grad_norm": 0.37211909890174866, "learning_rate": 3.809210967869287e-05, "loss": 4.248, "step": 10626 }, { "epoch": 0.32458766035430664, "grad_norm": 0.374729186296463, "learning_rate": 3.809006597028646e-05, "loss": 4.3894, "step": 10627 }, { "epoch": 0.32461820403176544, "grad_norm": 0.4090368449687958, "learning_rate": 3.808802214135308e-05, "loss": 4.4375, "step": 10628 }, { "epoch": 0.3246487477092242, "grad_norm": 0.3823387324810028, "learning_rate": 3.808597819191155e-05, "loss": 4.3543, "step": 10629 }, { "epoch": 0.32467929138668294, "grad_norm": 0.385670006275177, "learning_rate": 3.80839341219807e-05, "loss": 4.344, "step": 10630 }, { "epoch": 0.32470983506414175, "grad_norm": 0.3760358393192291, "learning_rate": 3.808188993157934e-05, "loss": 4.2954, "step": 10631 }, { "epoch": 0.3247403787416005, "grad_norm": 0.3921259939670563, "learning_rate": 3.807984562072629e-05, "loss": 4.3264, "step": 10632 }, { "epoch": 0.32477092241905925, "grad_norm": 0.3747637867927551, "learning_rate": 3.807780118944037e-05, "loss": 4.3724, "step": 10633 }, { "epoch": 0.324801466096518, "grad_norm": 0.3793368637561798, "learning_rate": 3.8075756637740415e-05, "loss": 4.4708, "step": 10634 }, { "epoch": 0.3248320097739768, "grad_norm": 0.3868720829486847, "learning_rate": 3.8073711965645245e-05, "loss": 4.362, "step": 10635 }, { "epoch": 0.32486255345143555, "grad_norm": 0.39324313402175903, "learning_rate": 3.8071667173173684e-05, "loss": 4.3887, "step": 10636 }, { "epoch": 0.3248930971288943, "grad_norm": 0.3801177740097046, "learning_rate": 3.8069622260344574e-05, "loss": 4.3163, "step": 10637 }, { "epoch": 0.3249236408063531, "grad_norm": 0.38753488659858704, "learning_rate": 3.806757722717673e-05, "loss": 4.3989, "step": 10638 }, { "epoch": 0.32495418448381186, "grad_norm": 0.3907514810562134, "learning_rate": 3.806553207368898e-05, "loss": 4.2754, "step": 10639 }, { "epoch": 0.3249847281612706, "grad_norm": 0.38409313559532166, "learning_rate": 3.806348679990016e-05, "loss": 4.3552, "step": 10640 }, { "epoch": 0.32501527183872936, "grad_norm": 0.37713003158569336, "learning_rate": 3.806144140582909e-05, "loss": 4.2994, "step": 10641 }, { "epoch": 0.32504581551618816, "grad_norm": 0.36901232600212097, "learning_rate": 3.805939589149462e-05, "loss": 4.3708, "step": 10642 }, { "epoch": 0.3250763591936469, "grad_norm": 0.37310266494750977, "learning_rate": 3.805735025691558e-05, "loss": 4.3054, "step": 10643 }, { "epoch": 0.32510690287110566, "grad_norm": 0.3848605751991272, "learning_rate": 3.80553045021108e-05, "loss": 4.3118, "step": 10644 }, { "epoch": 0.32513744654856447, "grad_norm": 0.3768915832042694, "learning_rate": 3.805325862709912e-05, "loss": 4.3321, "step": 10645 }, { "epoch": 0.3251679902260232, "grad_norm": 0.3816128075122833, "learning_rate": 3.805121263189938e-05, "loss": 4.3071, "step": 10646 }, { "epoch": 0.32519853390348197, "grad_norm": 0.3844863474369049, "learning_rate": 3.804916651653042e-05, "loss": 4.1629, "step": 10647 }, { "epoch": 0.3252290775809408, "grad_norm": 0.37562990188598633, "learning_rate": 3.804712028101106e-05, "loss": 4.206, "step": 10648 }, { "epoch": 0.3252596212583995, "grad_norm": 0.3766126334667206, "learning_rate": 3.804507392536016e-05, "loss": 4.3515, "step": 10649 }, { "epoch": 0.3252901649358583, "grad_norm": 0.3787994980812073, "learning_rate": 3.8043027449596566e-05, "loss": 4.3731, "step": 10650 }, { "epoch": 0.325320708613317, "grad_norm": 0.3870636820793152, "learning_rate": 3.8040980853739106e-05, "loss": 4.3467, "step": 10651 }, { "epoch": 0.3253512522907758, "grad_norm": 0.3808680474758148, "learning_rate": 3.803893413780663e-05, "loss": 4.3424, "step": 10652 }, { "epoch": 0.3253817959682346, "grad_norm": 0.37641826272010803, "learning_rate": 3.803688730181798e-05, "loss": 4.3458, "step": 10653 }, { "epoch": 0.3254123396456933, "grad_norm": 0.3727019429206848, "learning_rate": 3.803484034579201e-05, "loss": 4.3095, "step": 10654 }, { "epoch": 0.32544288332315213, "grad_norm": 0.3733181059360504, "learning_rate": 3.8032793269747556e-05, "loss": 4.3887, "step": 10655 }, { "epoch": 0.3254734270006109, "grad_norm": 0.3682326674461365, "learning_rate": 3.803074607370348e-05, "loss": 4.3613, "step": 10656 }, { "epoch": 0.32550397067806963, "grad_norm": 0.3817079961299896, "learning_rate": 3.8028698757678634e-05, "loss": 4.2929, "step": 10657 }, { "epoch": 0.3255345143555284, "grad_norm": 0.37638020515441895, "learning_rate": 3.802665132169185e-05, "loss": 4.3507, "step": 10658 }, { "epoch": 0.3255650580329872, "grad_norm": 0.38039925694465637, "learning_rate": 3.802460376576199e-05, "loss": 4.318, "step": 10659 }, { "epoch": 0.32559560171044594, "grad_norm": 0.3743295967578888, "learning_rate": 3.80225560899079e-05, "loss": 4.3823, "step": 10660 }, { "epoch": 0.3256261453879047, "grad_norm": 0.3831205368041992, "learning_rate": 3.802050829414845e-05, "loss": 4.285, "step": 10661 }, { "epoch": 0.3256566890653635, "grad_norm": 0.3699066936969757, "learning_rate": 3.8018460378502486e-05, "loss": 4.3348, "step": 10662 }, { "epoch": 0.32568723274282224, "grad_norm": 0.3781251907348633, "learning_rate": 3.801641234298886e-05, "loss": 4.2966, "step": 10663 }, { "epoch": 0.325717776420281, "grad_norm": 0.3685525953769684, "learning_rate": 3.801436418762644e-05, "loss": 4.3034, "step": 10664 }, { "epoch": 0.32574832009773974, "grad_norm": 0.3878917098045349, "learning_rate": 3.801231591243407e-05, "loss": 4.3335, "step": 10665 }, { "epoch": 0.32577886377519855, "grad_norm": 0.36829856038093567, "learning_rate": 3.801026751743062e-05, "loss": 4.3076, "step": 10666 }, { "epoch": 0.3258094074526573, "grad_norm": 0.3755815625190735, "learning_rate": 3.800821900263495e-05, "loss": 4.3543, "step": 10667 }, { "epoch": 0.32583995113011605, "grad_norm": 0.3831794857978821, "learning_rate": 3.800617036806591e-05, "loss": 4.3916, "step": 10668 }, { "epoch": 0.32587049480757485, "grad_norm": 0.3732668161392212, "learning_rate": 3.800412161374238e-05, "loss": 4.302, "step": 10669 }, { "epoch": 0.3259010384850336, "grad_norm": 0.3880586326122284, "learning_rate": 3.8002072739683214e-05, "loss": 4.2561, "step": 10670 }, { "epoch": 0.32593158216249235, "grad_norm": 0.38360315561294556, "learning_rate": 3.800002374590729e-05, "loss": 4.301, "step": 10671 }, { "epoch": 0.32596212583995116, "grad_norm": 0.3801426291465759, "learning_rate": 3.7997974632433443e-05, "loss": 4.4061, "step": 10672 }, { "epoch": 0.3259926695174099, "grad_norm": 0.38049110770225525, "learning_rate": 3.799592539928057e-05, "loss": 4.3292, "step": 10673 }, { "epoch": 0.32602321319486866, "grad_norm": 0.38435354828834534, "learning_rate": 3.799387604646753e-05, "loss": 4.3548, "step": 10674 }, { "epoch": 0.3260537568723274, "grad_norm": 0.37304309010505676, "learning_rate": 3.7991826574013204e-05, "loss": 4.2805, "step": 10675 }, { "epoch": 0.3260843005497862, "grad_norm": 0.3739525377750397, "learning_rate": 3.798977698193643e-05, "loss": 4.2876, "step": 10676 }, { "epoch": 0.32611484422724496, "grad_norm": 0.37958577275276184, "learning_rate": 3.798772727025611e-05, "loss": 4.3987, "step": 10677 }, { "epoch": 0.3261453879047037, "grad_norm": 0.38154473900794983, "learning_rate": 3.798567743899112e-05, "loss": 4.3482, "step": 10678 }, { "epoch": 0.3261759315821625, "grad_norm": 0.3768325448036194, "learning_rate": 3.79836274881603e-05, "loss": 4.319, "step": 10679 }, { "epoch": 0.32620647525962126, "grad_norm": 0.3865991532802582, "learning_rate": 3.798157741778257e-05, "loss": 4.3706, "step": 10680 }, { "epoch": 0.32623701893708, "grad_norm": 0.38484612107276917, "learning_rate": 3.797952722787676e-05, "loss": 4.3329, "step": 10681 }, { "epoch": 0.32626756261453876, "grad_norm": 0.3745216131210327, "learning_rate": 3.797747691846178e-05, "loss": 4.3432, "step": 10682 }, { "epoch": 0.32629810629199757, "grad_norm": 0.38735833764076233, "learning_rate": 3.797542648955649e-05, "loss": 4.3338, "step": 10683 }, { "epoch": 0.3263286499694563, "grad_norm": 0.393619567155838, "learning_rate": 3.797337594117978e-05, "loss": 4.3636, "step": 10684 }, { "epoch": 0.32635919364691507, "grad_norm": 0.38380327820777893, "learning_rate": 3.797132527335053e-05, "loss": 4.3953, "step": 10685 }, { "epoch": 0.3263897373243739, "grad_norm": 0.3872072100639343, "learning_rate": 3.796927448608762e-05, "loss": 4.344, "step": 10686 }, { "epoch": 0.3264202810018326, "grad_norm": 0.39160358905792236, "learning_rate": 3.796722357940994e-05, "loss": 4.3717, "step": 10687 }, { "epoch": 0.3264508246792914, "grad_norm": 0.36989474296569824, "learning_rate": 3.796517255333635e-05, "loss": 4.3088, "step": 10688 }, { "epoch": 0.3264813683567502, "grad_norm": 0.38334083557128906, "learning_rate": 3.7963121407885754e-05, "loss": 4.346, "step": 10689 }, { "epoch": 0.32651191203420893, "grad_norm": 0.3900638818740845, "learning_rate": 3.796107014307704e-05, "loss": 4.3634, "step": 10690 }, { "epoch": 0.3265424557116677, "grad_norm": 0.38208577036857605, "learning_rate": 3.795901875892909e-05, "loss": 4.2911, "step": 10691 }, { "epoch": 0.32657299938912643, "grad_norm": 0.3756254017353058, "learning_rate": 3.7956967255460786e-05, "loss": 4.3648, "step": 10692 }, { "epoch": 0.32660354306658523, "grad_norm": 0.38925138115882874, "learning_rate": 3.795491563269102e-05, "loss": 4.3268, "step": 10693 }, { "epoch": 0.326634086744044, "grad_norm": 0.3879040479660034, "learning_rate": 3.795286389063869e-05, "loss": 4.3577, "step": 10694 }, { "epoch": 0.32666463042150273, "grad_norm": 0.39053118228912354, "learning_rate": 3.7950812029322684e-05, "loss": 4.3464, "step": 10695 }, { "epoch": 0.32669517409896154, "grad_norm": 0.38674396276474, "learning_rate": 3.7948760048761887e-05, "loss": 4.3514, "step": 10696 }, { "epoch": 0.3267257177764203, "grad_norm": 0.39873138070106506, "learning_rate": 3.7946707948975205e-05, "loss": 4.286, "step": 10697 }, { "epoch": 0.32675626145387904, "grad_norm": 0.37640181183815, "learning_rate": 3.794465572998152e-05, "loss": 4.361, "step": 10698 }, { "epoch": 0.3267868051313378, "grad_norm": 0.3942870795726776, "learning_rate": 3.7942603391799745e-05, "loss": 4.3412, "step": 10699 }, { "epoch": 0.3268173488087966, "grad_norm": 0.3872537910938263, "learning_rate": 3.794055093444875e-05, "loss": 4.289, "step": 10700 }, { "epoch": 0.32684789248625534, "grad_norm": 0.37509652972221375, "learning_rate": 3.793849835794746e-05, "loss": 4.3288, "step": 10701 }, { "epoch": 0.3268784361637141, "grad_norm": 0.37285953760147095, "learning_rate": 3.793644566231477e-05, "loss": 4.3199, "step": 10702 }, { "epoch": 0.3269089798411729, "grad_norm": 0.3881050944328308, "learning_rate": 3.793439284756956e-05, "loss": 4.3966, "step": 10703 }, { "epoch": 0.32693952351863165, "grad_norm": 0.3765927851200104, "learning_rate": 3.7932339913730743e-05, "loss": 4.3779, "step": 10704 }, { "epoch": 0.3269700671960904, "grad_norm": 0.3767249584197998, "learning_rate": 3.793028686081723e-05, "loss": 4.373, "step": 10705 }, { "epoch": 0.3270006108735492, "grad_norm": 0.37968340516090393, "learning_rate": 3.792823368884792e-05, "loss": 4.3639, "step": 10706 }, { "epoch": 0.32703115455100795, "grad_norm": 0.37531358003616333, "learning_rate": 3.7926180397841714e-05, "loss": 4.3334, "step": 10707 }, { "epoch": 0.3270616982284667, "grad_norm": 0.37630754709243774, "learning_rate": 3.7924126987817524e-05, "loss": 4.34, "step": 10708 }, { "epoch": 0.32709224190592545, "grad_norm": 0.38073447346687317, "learning_rate": 3.792207345879424e-05, "loss": 4.4579, "step": 10709 }, { "epoch": 0.32712278558338426, "grad_norm": 0.37174758315086365, "learning_rate": 3.792001981079079e-05, "loss": 4.32, "step": 10710 }, { "epoch": 0.327153329260843, "grad_norm": 0.37505608797073364, "learning_rate": 3.791796604382607e-05, "loss": 4.3481, "step": 10711 }, { "epoch": 0.32718387293830176, "grad_norm": 0.385176420211792, "learning_rate": 3.7915912157919e-05, "loss": 4.3476, "step": 10712 }, { "epoch": 0.32721441661576056, "grad_norm": 0.3699497580528259, "learning_rate": 3.7913858153088474e-05, "loss": 4.3203, "step": 10713 }, { "epoch": 0.3272449602932193, "grad_norm": 0.37477028369903564, "learning_rate": 3.7911804029353435e-05, "loss": 4.2975, "step": 10714 }, { "epoch": 0.32727550397067806, "grad_norm": 0.3696332275867462, "learning_rate": 3.790974978673277e-05, "loss": 4.3566, "step": 10715 }, { "epoch": 0.3273060476481368, "grad_norm": 0.3779963552951813, "learning_rate": 3.79076954252454e-05, "loss": 4.4199, "step": 10716 }, { "epoch": 0.3273365913255956, "grad_norm": 0.38442468643188477, "learning_rate": 3.7905640944910235e-05, "loss": 4.3653, "step": 10717 }, { "epoch": 0.32736713500305437, "grad_norm": 0.3753977119922638, "learning_rate": 3.7903586345746214e-05, "loss": 4.3835, "step": 10718 }, { "epoch": 0.3273976786805131, "grad_norm": 0.3820185959339142, "learning_rate": 3.790153162777222e-05, "loss": 4.3251, "step": 10719 }, { "epoch": 0.3274282223579719, "grad_norm": 0.36917316913604736, "learning_rate": 3.7899476791007206e-05, "loss": 4.2992, "step": 10720 }, { "epoch": 0.32745876603543067, "grad_norm": 0.37188827991485596, "learning_rate": 3.789742183547007e-05, "loss": 4.2782, "step": 10721 }, { "epoch": 0.3274893097128894, "grad_norm": 0.3743056356906891, "learning_rate": 3.789536676117974e-05, "loss": 4.3037, "step": 10722 }, { "epoch": 0.3275198533903482, "grad_norm": 0.3622032105922699, "learning_rate": 3.7893311568155144e-05, "loss": 4.3531, "step": 10723 }, { "epoch": 0.327550397067807, "grad_norm": 0.38150954246520996, "learning_rate": 3.78912562564152e-05, "loss": 4.3515, "step": 10724 }, { "epoch": 0.3275809407452657, "grad_norm": 0.38461917638778687, "learning_rate": 3.788920082597882e-05, "loss": 4.3738, "step": 10725 }, { "epoch": 0.3276114844227245, "grad_norm": 0.377603143453598, "learning_rate": 3.788714527686495e-05, "loss": 4.4375, "step": 10726 }, { "epoch": 0.3276420281001833, "grad_norm": 0.3848472237586975, "learning_rate": 3.7885089609092506e-05, "loss": 4.3062, "step": 10727 }, { "epoch": 0.32767257177764203, "grad_norm": 0.3870590925216675, "learning_rate": 3.788303382268041e-05, "loss": 4.3069, "step": 10728 }, { "epoch": 0.3277031154551008, "grad_norm": 0.38380032777786255, "learning_rate": 3.7880977917647606e-05, "loss": 4.4201, "step": 10729 }, { "epoch": 0.3277336591325596, "grad_norm": 0.3717021942138672, "learning_rate": 3.787892189401302e-05, "loss": 4.2992, "step": 10730 }, { "epoch": 0.32776420281001833, "grad_norm": 0.37962499260902405, "learning_rate": 3.7876865751795565e-05, "loss": 4.3741, "step": 10731 }, { "epoch": 0.3277947464874771, "grad_norm": 0.37883061170578003, "learning_rate": 3.7874809491014195e-05, "loss": 4.3363, "step": 10732 }, { "epoch": 0.32782529016493583, "grad_norm": 0.3681073784828186, "learning_rate": 3.787275311168784e-05, "loss": 4.2431, "step": 10733 }, { "epoch": 0.32785583384239464, "grad_norm": 0.3860173225402832, "learning_rate": 3.7870696613835424e-05, "loss": 4.3476, "step": 10734 }, { "epoch": 0.3278863775198534, "grad_norm": 0.3775070011615753, "learning_rate": 3.7868639997475884e-05, "loss": 4.4126, "step": 10735 }, { "epoch": 0.32791692119731214, "grad_norm": 0.3801286518573761, "learning_rate": 3.786658326262816e-05, "loss": 4.399, "step": 10736 }, { "epoch": 0.32794746487477094, "grad_norm": 0.4052402675151825, "learning_rate": 3.786452640931118e-05, "loss": 4.2879, "step": 10737 }, { "epoch": 0.3279780085522297, "grad_norm": 0.37762030959129333, "learning_rate": 3.78624694375439e-05, "loss": 4.4013, "step": 10738 }, { "epoch": 0.32800855222968844, "grad_norm": 0.3830469846725464, "learning_rate": 3.7860412347345254e-05, "loss": 4.2925, "step": 10739 }, { "epoch": 0.3280390959071472, "grad_norm": 0.3773075342178345, "learning_rate": 3.785835513873418e-05, "loss": 4.3113, "step": 10740 }, { "epoch": 0.328069639584606, "grad_norm": 0.37872615456581116, "learning_rate": 3.7856297811729614e-05, "loss": 4.3735, "step": 10741 }, { "epoch": 0.32810018326206475, "grad_norm": 0.3716592490673065, "learning_rate": 3.78542403663505e-05, "loss": 4.3503, "step": 10742 }, { "epoch": 0.3281307269395235, "grad_norm": 0.3758457601070404, "learning_rate": 3.7852182802615794e-05, "loss": 4.3586, "step": 10743 }, { "epoch": 0.3281612706169823, "grad_norm": 0.3923569619655609, "learning_rate": 3.7850125120544424e-05, "loss": 4.3398, "step": 10744 }, { "epoch": 0.32819181429444105, "grad_norm": 0.3762608468532562, "learning_rate": 3.784806732015536e-05, "loss": 4.3809, "step": 10745 }, { "epoch": 0.3282223579718998, "grad_norm": 0.38432639837265015, "learning_rate": 3.7846009401467516e-05, "loss": 4.3614, "step": 10746 }, { "epoch": 0.3282529016493586, "grad_norm": 0.394803524017334, "learning_rate": 3.784395136449987e-05, "loss": 4.28, "step": 10747 }, { "epoch": 0.32828344532681736, "grad_norm": 0.3817819654941559, "learning_rate": 3.7841893209271364e-05, "loss": 4.4266, "step": 10748 }, { "epoch": 0.3283139890042761, "grad_norm": 0.3938044011592865, "learning_rate": 3.783983493580093e-05, "loss": 4.3555, "step": 10749 }, { "epoch": 0.32834453268173486, "grad_norm": 0.37635889649391174, "learning_rate": 3.783777654410755e-05, "loss": 4.3428, "step": 10750 }, { "epoch": 0.32837507635919366, "grad_norm": 0.3760804831981659, "learning_rate": 3.7835718034210146e-05, "loss": 4.4287, "step": 10751 }, { "epoch": 0.3284056200366524, "grad_norm": 0.36847779154777527, "learning_rate": 3.78336594061277e-05, "loss": 4.4021, "step": 10752 }, { "epoch": 0.32843616371411116, "grad_norm": 0.3812924325466156, "learning_rate": 3.783160065987914e-05, "loss": 4.18, "step": 10753 }, { "epoch": 0.32846670739156997, "grad_norm": 0.3814414143562317, "learning_rate": 3.782954179548344e-05, "loss": 4.3624, "step": 10754 }, { "epoch": 0.3284972510690287, "grad_norm": 0.38919851183891296, "learning_rate": 3.782748281295956e-05, "loss": 4.3782, "step": 10755 }, { "epoch": 0.32852779474648747, "grad_norm": 0.3797706961631775, "learning_rate": 3.7825423712326447e-05, "loss": 4.3204, "step": 10756 }, { "epoch": 0.3285583384239462, "grad_norm": 0.3916946053504944, "learning_rate": 3.7823364493603066e-05, "loss": 4.3488, "step": 10757 }, { "epoch": 0.328588882101405, "grad_norm": 0.3763250410556793, "learning_rate": 3.782130515680837e-05, "loss": 4.3148, "step": 10758 }, { "epoch": 0.32861942577886377, "grad_norm": 0.3955687880516052, "learning_rate": 3.7819245701961325e-05, "loss": 4.2843, "step": 10759 }, { "epoch": 0.3286499694563225, "grad_norm": 0.37389588356018066, "learning_rate": 3.781718612908089e-05, "loss": 4.3777, "step": 10760 }, { "epoch": 0.3286805131337813, "grad_norm": 0.3808501660823822, "learning_rate": 3.781512643818604e-05, "loss": 4.2667, "step": 10761 }, { "epoch": 0.3287110568112401, "grad_norm": 0.37919557094573975, "learning_rate": 3.7813066629295734e-05, "loss": 4.443, "step": 10762 }, { "epoch": 0.3287416004886988, "grad_norm": 0.3797418773174286, "learning_rate": 3.781100670242893e-05, "loss": 4.2555, "step": 10763 }, { "epoch": 0.32877214416615763, "grad_norm": 0.3850764334201813, "learning_rate": 3.78089466576046e-05, "loss": 4.2355, "step": 10764 }, { "epoch": 0.3288026878436164, "grad_norm": 0.38219305872917175, "learning_rate": 3.780688649484172e-05, "loss": 4.4219, "step": 10765 }, { "epoch": 0.32883323152107513, "grad_norm": 0.3852579593658447, "learning_rate": 3.780482621415924e-05, "loss": 4.3993, "step": 10766 }, { "epoch": 0.3288637751985339, "grad_norm": 0.38070034980773926, "learning_rate": 3.780276581557615e-05, "loss": 4.302, "step": 10767 }, { "epoch": 0.3288943188759927, "grad_norm": 0.37562641501426697, "learning_rate": 3.78007052991114e-05, "loss": 4.3128, "step": 10768 }, { "epoch": 0.32892486255345144, "grad_norm": 0.378919780254364, "learning_rate": 3.779864466478399e-05, "loss": 4.4259, "step": 10769 }, { "epoch": 0.3289554062309102, "grad_norm": 0.38454240560531616, "learning_rate": 3.779658391261288e-05, "loss": 4.3464, "step": 10770 }, { "epoch": 0.328985949908369, "grad_norm": 0.3738976716995239, "learning_rate": 3.7794523042617035e-05, "loss": 4.3626, "step": 10771 }, { "epoch": 0.32901649358582774, "grad_norm": 0.3688863515853882, "learning_rate": 3.7792462054815436e-05, "loss": 4.3428, "step": 10772 }, { "epoch": 0.3290470372632865, "grad_norm": 0.37523046135902405, "learning_rate": 3.779040094922707e-05, "loss": 4.3357, "step": 10773 }, { "epoch": 0.32907758094074524, "grad_norm": 0.3811708092689514, "learning_rate": 3.77883397258709e-05, "loss": 4.3652, "step": 10774 }, { "epoch": 0.32910812461820405, "grad_norm": 0.3753378689289093, "learning_rate": 3.77862783847659e-05, "loss": 4.3776, "step": 10775 }, { "epoch": 0.3291386682956628, "grad_norm": 0.37778350710868835, "learning_rate": 3.7784216925931085e-05, "loss": 4.3166, "step": 10776 }, { "epoch": 0.32916921197312154, "grad_norm": 0.37395286560058594, "learning_rate": 3.778215534938539e-05, "loss": 4.2739, "step": 10777 }, { "epoch": 0.32919975565058035, "grad_norm": 0.37761226296424866, "learning_rate": 3.778009365514783e-05, "loss": 4.368, "step": 10778 }, { "epoch": 0.3292302993280391, "grad_norm": 0.3715204894542694, "learning_rate": 3.777803184323738e-05, "loss": 4.3084, "step": 10779 }, { "epoch": 0.32926084300549785, "grad_norm": 0.3767646253108978, "learning_rate": 3.7775969913673014e-05, "loss": 4.3455, "step": 10780 }, { "epoch": 0.32929138668295665, "grad_norm": 0.3797732889652252, "learning_rate": 3.777390786647372e-05, "loss": 4.2538, "step": 10781 }, { "epoch": 0.3293219303604154, "grad_norm": 0.37574031949043274, "learning_rate": 3.77718457016585e-05, "loss": 4.3513, "step": 10782 }, { "epoch": 0.32935247403787415, "grad_norm": 0.37602442502975464, "learning_rate": 3.776978341924632e-05, "loss": 4.3538, "step": 10783 }, { "epoch": 0.3293830177153329, "grad_norm": 0.38923096656799316, "learning_rate": 3.776772101925619e-05, "loss": 4.3203, "step": 10784 }, { "epoch": 0.3294135613927917, "grad_norm": 0.38271352648735046, "learning_rate": 3.7765658501707076e-05, "loss": 4.3081, "step": 10785 }, { "epoch": 0.32944410507025046, "grad_norm": 0.3887692093849182, "learning_rate": 3.776359586661799e-05, "loss": 4.2907, "step": 10786 }, { "epoch": 0.3294746487477092, "grad_norm": 0.38667526841163635, "learning_rate": 3.776153311400791e-05, "loss": 4.3585, "step": 10787 }, { "epoch": 0.329505192425168, "grad_norm": 0.3752491772174835, "learning_rate": 3.7759470243895834e-05, "loss": 4.1417, "step": 10788 }, { "epoch": 0.32953573610262676, "grad_norm": 0.3696643114089966, "learning_rate": 3.775740725630075e-05, "loss": 4.3195, "step": 10789 }, { "epoch": 0.3295662797800855, "grad_norm": 0.3763076961040497, "learning_rate": 3.7755344151241664e-05, "loss": 4.3395, "step": 10790 }, { "epoch": 0.32959682345754426, "grad_norm": 0.37386956810951233, "learning_rate": 3.7753280928737564e-05, "loss": 4.2832, "step": 10791 }, { "epoch": 0.32962736713500307, "grad_norm": 0.38035839796066284, "learning_rate": 3.775121758880745e-05, "loss": 4.3746, "step": 10792 }, { "epoch": 0.3296579108124618, "grad_norm": 0.3768217861652374, "learning_rate": 3.7749154131470323e-05, "loss": 4.3888, "step": 10793 }, { "epoch": 0.32968845448992057, "grad_norm": 0.37667185068130493, "learning_rate": 3.774709055674518e-05, "loss": 4.3345, "step": 10794 }, { "epoch": 0.3297189981673794, "grad_norm": 0.38196638226509094, "learning_rate": 3.774502686465101e-05, "loss": 4.3125, "step": 10795 }, { "epoch": 0.3297495418448381, "grad_norm": 0.3906063139438629, "learning_rate": 3.7742963055206836e-05, "loss": 4.308, "step": 10796 }, { "epoch": 0.3297800855222969, "grad_norm": 0.3770449459552765, "learning_rate": 3.774089912843164e-05, "loss": 4.3632, "step": 10797 }, { "epoch": 0.3298106291997557, "grad_norm": 0.371721088886261, "learning_rate": 3.773883508434444e-05, "loss": 4.3156, "step": 10798 }, { "epoch": 0.32984117287721443, "grad_norm": 0.3722301125526428, "learning_rate": 3.773677092296424e-05, "loss": 4.3324, "step": 10799 }, { "epoch": 0.3298717165546732, "grad_norm": 0.3754814565181732, "learning_rate": 3.773470664431004e-05, "loss": 4.356, "step": 10800 }, { "epoch": 0.3299022602321319, "grad_norm": 0.3798031508922577, "learning_rate": 3.773264224840084e-05, "loss": 4.3038, "step": 10801 }, { "epoch": 0.32993280390959073, "grad_norm": 0.37079325318336487, "learning_rate": 3.7730577735255665e-05, "loss": 4.3545, "step": 10802 }, { "epoch": 0.3299633475870495, "grad_norm": 0.37152132391929626, "learning_rate": 3.7728513104893516e-05, "loss": 4.3509, "step": 10803 }, { "epoch": 0.32999389126450823, "grad_norm": 0.37210583686828613, "learning_rate": 3.7726448357333395e-05, "loss": 4.2863, "step": 10804 }, { "epoch": 0.33002443494196704, "grad_norm": 0.3825910985469818, "learning_rate": 3.7724383492594315e-05, "loss": 4.2925, "step": 10805 }, { "epoch": 0.3300549786194258, "grad_norm": 0.3744872212409973, "learning_rate": 3.772231851069531e-05, "loss": 4.3485, "step": 10806 }, { "epoch": 0.33008552229688454, "grad_norm": 0.37275493144989014, "learning_rate": 3.772025341165537e-05, "loss": 4.3619, "step": 10807 }, { "epoch": 0.3301160659743433, "grad_norm": 0.39000898599624634, "learning_rate": 3.771818819549352e-05, "loss": 4.354, "step": 10808 }, { "epoch": 0.3301466096518021, "grad_norm": 0.3786885142326355, "learning_rate": 3.771612286222876e-05, "loss": 4.2632, "step": 10809 }, { "epoch": 0.33017715332926084, "grad_norm": 0.37396201491355896, "learning_rate": 3.771405741188013e-05, "loss": 4.2677, "step": 10810 }, { "epoch": 0.3302076970067196, "grad_norm": 0.3700827956199646, "learning_rate": 3.7711991844466644e-05, "loss": 4.2472, "step": 10811 }, { "epoch": 0.3302382406841784, "grad_norm": 0.3747355341911316, "learning_rate": 3.77099261600073e-05, "loss": 4.1842, "step": 10812 }, { "epoch": 0.33026878436163715, "grad_norm": 0.37967348098754883, "learning_rate": 3.770786035852114e-05, "loss": 4.4087, "step": 10813 }, { "epoch": 0.3302993280390959, "grad_norm": 0.38066771626472473, "learning_rate": 3.770579444002716e-05, "loss": 4.3692, "step": 10814 }, { "epoch": 0.33032987171655465, "grad_norm": 0.3981862962245941, "learning_rate": 3.770372840454441e-05, "loss": 4.4048, "step": 10815 }, { "epoch": 0.33036041539401345, "grad_norm": 0.3849943280220032, "learning_rate": 3.77016622520919e-05, "loss": 4.3809, "step": 10816 }, { "epoch": 0.3303909590714722, "grad_norm": 0.3681521713733673, "learning_rate": 3.7699595982688655e-05, "loss": 4.3847, "step": 10817 }, { "epoch": 0.33042150274893095, "grad_norm": 0.39332517981529236, "learning_rate": 3.7697529596353705e-05, "loss": 4.4025, "step": 10818 }, { "epoch": 0.33045204642638976, "grad_norm": 0.3648260831832886, "learning_rate": 3.769546309310606e-05, "loss": 4.3249, "step": 10819 }, { "epoch": 0.3304825901038485, "grad_norm": 0.3714940845966339, "learning_rate": 3.769339647296477e-05, "loss": 4.3539, "step": 10820 }, { "epoch": 0.33051313378130726, "grad_norm": 0.3745308816432953, "learning_rate": 3.7691329735948854e-05, "loss": 4.389, "step": 10821 }, { "epoch": 0.33054367745876606, "grad_norm": 0.3676679730415344, "learning_rate": 3.7689262882077324e-05, "loss": 4.3547, "step": 10822 }, { "epoch": 0.3305742211362248, "grad_norm": 0.3831978738307953, "learning_rate": 3.768719591136925e-05, "loss": 4.2815, "step": 10823 }, { "epoch": 0.33060476481368356, "grad_norm": 0.37205561995506287, "learning_rate": 3.768512882384362e-05, "loss": 4.2358, "step": 10824 }, { "epoch": 0.3306353084911423, "grad_norm": 0.37775877118110657, "learning_rate": 3.7683061619519496e-05, "loss": 4.3246, "step": 10825 }, { "epoch": 0.3306658521686011, "grad_norm": 0.38522329926490784, "learning_rate": 3.768099429841589e-05, "loss": 4.4092, "step": 10826 }, { "epoch": 0.33069639584605987, "grad_norm": 0.3855787217617035, "learning_rate": 3.7678926860551865e-05, "loss": 4.2145, "step": 10827 }, { "epoch": 0.3307269395235186, "grad_norm": 0.3743123412132263, "learning_rate": 3.7676859305946443e-05, "loss": 4.3226, "step": 10828 }, { "epoch": 0.3307574832009774, "grad_norm": 0.36522865295410156, "learning_rate": 3.767479163461864e-05, "loss": 4.3559, "step": 10829 }, { "epoch": 0.33078802687843617, "grad_norm": 0.372555673122406, "learning_rate": 3.767272384658753e-05, "loss": 4.3373, "step": 10830 }, { "epoch": 0.3308185705558949, "grad_norm": 0.3818649649620056, "learning_rate": 3.767065594187214e-05, "loss": 4.2941, "step": 10831 }, { "epoch": 0.33084911423335367, "grad_norm": 0.3774401545524597, "learning_rate": 3.766858792049149e-05, "loss": 4.2277, "step": 10832 }, { "epoch": 0.3308796579108125, "grad_norm": 0.3920446038246155, "learning_rate": 3.766651978246465e-05, "loss": 4.317, "step": 10833 }, { "epoch": 0.3309102015882712, "grad_norm": 0.3682629466056824, "learning_rate": 3.766445152781065e-05, "loss": 4.3073, "step": 10834 }, { "epoch": 0.33094074526573, "grad_norm": 0.3778783082962036, "learning_rate": 3.766238315654853e-05, "loss": 4.3233, "step": 10835 }, { "epoch": 0.3309712889431888, "grad_norm": 0.3777937889099121, "learning_rate": 3.766031466869733e-05, "loss": 4.3626, "step": 10836 }, { "epoch": 0.33100183262064753, "grad_norm": 0.3683871924877167, "learning_rate": 3.7658246064276117e-05, "loss": 4.3275, "step": 10837 }, { "epoch": 0.3310323762981063, "grad_norm": 0.3732130229473114, "learning_rate": 3.7656177343303915e-05, "loss": 4.2502, "step": 10838 }, { "epoch": 0.3310629199755651, "grad_norm": 0.3887333571910858, "learning_rate": 3.765410850579978e-05, "loss": 4.4177, "step": 10839 }, { "epoch": 0.33109346365302383, "grad_norm": 0.3746531009674072, "learning_rate": 3.765203955178277e-05, "loss": 4.3786, "step": 10840 }, { "epoch": 0.3311240073304826, "grad_norm": 0.38671326637268066, "learning_rate": 3.764997048127192e-05, "loss": 4.3728, "step": 10841 }, { "epoch": 0.33115455100794133, "grad_norm": 0.3818773925304413, "learning_rate": 3.764790129428629e-05, "loss": 4.3492, "step": 10842 }, { "epoch": 0.33118509468540014, "grad_norm": 0.36586225032806396, "learning_rate": 3.7645831990844935e-05, "loss": 4.3527, "step": 10843 }, { "epoch": 0.3312156383628589, "grad_norm": 0.3726333677768707, "learning_rate": 3.76437625709669e-05, "loss": 4.4369, "step": 10844 }, { "epoch": 0.33124618204031764, "grad_norm": 0.3782210350036621, "learning_rate": 3.7641693034671244e-05, "loss": 4.2704, "step": 10845 }, { "epoch": 0.33127672571777644, "grad_norm": 0.390424519777298, "learning_rate": 3.763962338197701e-05, "loss": 4.3192, "step": 10846 }, { "epoch": 0.3313072693952352, "grad_norm": 0.37186282873153687, "learning_rate": 3.7637553612903274e-05, "loss": 4.3819, "step": 10847 }, { "epoch": 0.33133781307269394, "grad_norm": 0.37664908170700073, "learning_rate": 3.7635483727469086e-05, "loss": 4.3559, "step": 10848 }, { "epoch": 0.3313683567501527, "grad_norm": 0.37073490023612976, "learning_rate": 3.76334137256935e-05, "loss": 4.3927, "step": 10849 }, { "epoch": 0.3313989004276115, "grad_norm": 0.3772907555103302, "learning_rate": 3.7631343607595575e-05, "loss": 4.3259, "step": 10850 }, { "epoch": 0.33142944410507025, "grad_norm": 0.3756866157054901, "learning_rate": 3.762927337319438e-05, "loss": 4.3186, "step": 10851 }, { "epoch": 0.331459987782529, "grad_norm": 0.38453924655914307, "learning_rate": 3.762720302250897e-05, "loss": 4.3056, "step": 10852 }, { "epoch": 0.3314905314599878, "grad_norm": 0.3791104257106781, "learning_rate": 3.762513255555841e-05, "loss": 4.3594, "step": 10853 }, { "epoch": 0.33152107513744655, "grad_norm": 0.3799912929534912, "learning_rate": 3.7623061972361754e-05, "loss": 4.3497, "step": 10854 }, { "epoch": 0.3315516188149053, "grad_norm": 0.3772457242012024, "learning_rate": 3.762099127293809e-05, "loss": 4.387, "step": 10855 }, { "epoch": 0.3315821624923641, "grad_norm": 0.3701479732990265, "learning_rate": 3.761892045730646e-05, "loss": 4.3042, "step": 10856 }, { "epoch": 0.33161270616982286, "grad_norm": 0.36362043023109436, "learning_rate": 3.7616849525485955e-05, "loss": 4.3288, "step": 10857 }, { "epoch": 0.3316432498472816, "grad_norm": 0.387999027967453, "learning_rate": 3.761477847749562e-05, "loss": 4.3239, "step": 10858 }, { "epoch": 0.33167379352474036, "grad_norm": 0.38055935502052307, "learning_rate": 3.761270731335453e-05, "loss": 4.2578, "step": 10859 }, { "epoch": 0.33170433720219916, "grad_norm": 0.37072932720184326, "learning_rate": 3.761063603308176e-05, "loss": 4.4051, "step": 10860 }, { "epoch": 0.3317348808796579, "grad_norm": 0.39124196767807007, "learning_rate": 3.760856463669638e-05, "loss": 4.348, "step": 10861 }, { "epoch": 0.33176542455711666, "grad_norm": 0.37893110513687134, "learning_rate": 3.760649312421747e-05, "loss": 4.4086, "step": 10862 }, { "epoch": 0.33179596823457547, "grad_norm": 0.38371050357818604, "learning_rate": 3.760442149566409e-05, "loss": 4.3789, "step": 10863 }, { "epoch": 0.3318265119120342, "grad_norm": 0.3709936738014221, "learning_rate": 3.7602349751055324e-05, "loss": 4.3456, "step": 10864 }, { "epoch": 0.33185705558949297, "grad_norm": 0.373006135225296, "learning_rate": 3.760027789041025e-05, "loss": 4.273, "step": 10865 }, { "epoch": 0.3318875992669517, "grad_norm": 0.3773508071899414, "learning_rate": 3.759820591374793e-05, "loss": 4.3387, "step": 10866 }, { "epoch": 0.3319181429444105, "grad_norm": 0.3814103305339813, "learning_rate": 3.7596133821087455e-05, "loss": 4.3157, "step": 10867 }, { "epoch": 0.33194868662186927, "grad_norm": 0.3817523717880249, "learning_rate": 3.75940616124479e-05, "loss": 4.3264, "step": 10868 }, { "epoch": 0.331979230299328, "grad_norm": 0.3907727003097534, "learning_rate": 3.7591989287848337e-05, "loss": 4.3391, "step": 10869 }, { "epoch": 0.3320097739767868, "grad_norm": 0.3807125389575958, "learning_rate": 3.758991684730786e-05, "loss": 4.3876, "step": 10870 }, { "epoch": 0.3320403176542456, "grad_norm": 0.37218600511550903, "learning_rate": 3.758784429084554e-05, "loss": 4.3181, "step": 10871 }, { "epoch": 0.3320708613317043, "grad_norm": 0.380248486995697, "learning_rate": 3.758577161848048e-05, "loss": 4.4206, "step": 10872 }, { "epoch": 0.33210140500916313, "grad_norm": 0.37970855832099915, "learning_rate": 3.758369883023174e-05, "loss": 4.2185, "step": 10873 }, { "epoch": 0.3321319486866219, "grad_norm": 0.3720247745513916, "learning_rate": 3.7581625926118416e-05, "loss": 4.3509, "step": 10874 }, { "epoch": 0.33216249236408063, "grad_norm": 0.37536928057670593, "learning_rate": 3.757955290615959e-05, "loss": 4.3186, "step": 10875 }, { "epoch": 0.3321930360415394, "grad_norm": 0.3764575719833374, "learning_rate": 3.757747977037436e-05, "loss": 4.4224, "step": 10876 }, { "epoch": 0.3322235797189982, "grad_norm": 0.37467247247695923, "learning_rate": 3.75754065187818e-05, "loss": 4.3057, "step": 10877 }, { "epoch": 0.33225412339645694, "grad_norm": 0.3853144943714142, "learning_rate": 3.7573333151401005e-05, "loss": 4.3447, "step": 10878 }, { "epoch": 0.3322846670739157, "grad_norm": 0.3723660707473755, "learning_rate": 3.757125966825108e-05, "loss": 4.3079, "step": 10879 }, { "epoch": 0.3323152107513745, "grad_norm": 0.37426528334617615, "learning_rate": 3.7569186069351095e-05, "loss": 4.3321, "step": 10880 }, { "epoch": 0.33234575442883324, "grad_norm": 0.3900652229785919, "learning_rate": 3.756711235472015e-05, "loss": 4.3353, "step": 10881 }, { "epoch": 0.332376298106292, "grad_norm": 0.3734818994998932, "learning_rate": 3.7565038524377336e-05, "loss": 4.3134, "step": 10882 }, { "epoch": 0.33240684178375074, "grad_norm": 0.37471458315849304, "learning_rate": 3.7562964578341764e-05, "loss": 4.2247, "step": 10883 }, { "epoch": 0.33243738546120954, "grad_norm": 0.378801167011261, "learning_rate": 3.756089051663251e-05, "loss": 4.3098, "step": 10884 }, { "epoch": 0.3324679291386683, "grad_norm": 0.3951450288295746, "learning_rate": 3.755881633926867e-05, "loss": 4.4112, "step": 10885 }, { "epoch": 0.33249847281612704, "grad_norm": 0.3895314633846283, "learning_rate": 3.7556742046269365e-05, "loss": 4.3659, "step": 10886 }, { "epoch": 0.33252901649358585, "grad_norm": 0.3712669909000397, "learning_rate": 3.755466763765368e-05, "loss": 4.3156, "step": 10887 }, { "epoch": 0.3325595601710446, "grad_norm": 0.3951459527015686, "learning_rate": 3.755259311344071e-05, "loss": 4.3337, "step": 10888 }, { "epoch": 0.33259010384850335, "grad_norm": 0.37401825189590454, "learning_rate": 3.7550518473649564e-05, "loss": 4.4274, "step": 10889 }, { "epoch": 0.3326206475259621, "grad_norm": 0.3854209780693054, "learning_rate": 3.754844371829934e-05, "loss": 4.4043, "step": 10890 }, { "epoch": 0.3326511912034209, "grad_norm": 0.38773661851882935, "learning_rate": 3.754636884740914e-05, "loss": 4.3599, "step": 10891 }, { "epoch": 0.33268173488087965, "grad_norm": 0.3828405737876892, "learning_rate": 3.754429386099808e-05, "loss": 4.4111, "step": 10892 }, { "epoch": 0.3327122785583384, "grad_norm": 0.3835000991821289, "learning_rate": 3.754221875908525e-05, "loss": 4.3578, "step": 10893 }, { "epoch": 0.3327428222357972, "grad_norm": 0.3810860514640808, "learning_rate": 3.754014354168977e-05, "loss": 4.3681, "step": 10894 }, { "epoch": 0.33277336591325596, "grad_norm": 0.39257141947746277, "learning_rate": 3.7538068208830726e-05, "loss": 4.3059, "step": 10895 }, { "epoch": 0.3328039095907147, "grad_norm": 0.37145528197288513, "learning_rate": 3.753599276052725e-05, "loss": 4.2538, "step": 10896 }, { "epoch": 0.3328344532681735, "grad_norm": 0.37968337535858154, "learning_rate": 3.753391719679845e-05, "loss": 4.3951, "step": 10897 }, { "epoch": 0.33286499694563226, "grad_norm": 0.37613317370414734, "learning_rate": 3.7531841517663424e-05, "loss": 4.3634, "step": 10898 }, { "epoch": 0.332895540623091, "grad_norm": 0.38073664903640747, "learning_rate": 3.752976572314129e-05, "loss": 4.3542, "step": 10899 }, { "epoch": 0.33292608430054976, "grad_norm": 0.37469586730003357, "learning_rate": 3.7527689813251166e-05, "loss": 4.3505, "step": 10900 }, { "epoch": 0.33295662797800857, "grad_norm": 0.3725137710571289, "learning_rate": 3.7525613788012146e-05, "loss": 4.3449, "step": 10901 }, { "epoch": 0.3329871716554673, "grad_norm": 0.37911808490753174, "learning_rate": 3.752353764744338e-05, "loss": 4.3759, "step": 10902 }, { "epoch": 0.33301771533292607, "grad_norm": 0.3858550190925598, "learning_rate": 3.752146139156395e-05, "loss": 4.3568, "step": 10903 }, { "epoch": 0.3330482590103849, "grad_norm": 0.3713454604148865, "learning_rate": 3.7519385020392987e-05, "loss": 4.3293, "step": 10904 }, { "epoch": 0.3330788026878436, "grad_norm": 0.3708900809288025, "learning_rate": 3.7517308533949617e-05, "loss": 4.3494, "step": 10905 }, { "epoch": 0.3331093463653024, "grad_norm": 0.37081342935562134, "learning_rate": 3.751523193225295e-05, "loss": 4.2949, "step": 10906 }, { "epoch": 0.3331398900427611, "grad_norm": 0.37382808327674866, "learning_rate": 3.7513155215322106e-05, "loss": 4.2179, "step": 10907 }, { "epoch": 0.3331704337202199, "grad_norm": 0.3800276517868042, "learning_rate": 3.75110783831762e-05, "loss": 4.4294, "step": 10908 }, { "epoch": 0.3332009773976787, "grad_norm": 0.3697581887245178, "learning_rate": 3.750900143583437e-05, "loss": 4.391, "step": 10909 }, { "epoch": 0.3332315210751374, "grad_norm": 0.38179248571395874, "learning_rate": 3.7506924373315735e-05, "loss": 4.2966, "step": 10910 }, { "epoch": 0.33326206475259623, "grad_norm": 0.3958777189254761, "learning_rate": 3.750484719563941e-05, "loss": 4.3278, "step": 10911 }, { "epoch": 0.333292608430055, "grad_norm": 0.38055935502052307, "learning_rate": 3.750276990282454e-05, "loss": 4.3375, "step": 10912 }, { "epoch": 0.33332315210751373, "grad_norm": 0.38259366154670715, "learning_rate": 3.750069249489023e-05, "loss": 4.2979, "step": 10913 }, { "epoch": 0.33335369578497254, "grad_norm": 0.3842620253562927, "learning_rate": 3.749861497185562e-05, "loss": 4.3252, "step": 10914 }, { "epoch": 0.3333842394624313, "grad_norm": 0.37665775418281555, "learning_rate": 3.7496537333739835e-05, "loss": 4.2223, "step": 10915 }, { "epoch": 0.33341478313989004, "grad_norm": 0.3867643177509308, "learning_rate": 3.7494459580562006e-05, "loss": 4.2627, "step": 10916 }, { "epoch": 0.3334453268173488, "grad_norm": 0.38186120986938477, "learning_rate": 3.749238171234126e-05, "loss": 4.3734, "step": 10917 }, { "epoch": 0.3334758704948076, "grad_norm": 0.3791998624801636, "learning_rate": 3.749030372909673e-05, "loss": 4.3303, "step": 10918 }, { "epoch": 0.33350641417226634, "grad_norm": 0.3738168776035309, "learning_rate": 3.7488225630847554e-05, "loss": 4.3897, "step": 10919 }, { "epoch": 0.3335369578497251, "grad_norm": 0.388732373714447, "learning_rate": 3.748614741761287e-05, "loss": 4.3431, "step": 10920 }, { "epoch": 0.3335675015271839, "grad_norm": 0.3842450678348541, "learning_rate": 3.7484069089411806e-05, "loss": 4.3371, "step": 10921 }, { "epoch": 0.33359804520464265, "grad_norm": 0.3668305575847626, "learning_rate": 3.7481990646263496e-05, "loss": 4.3795, "step": 10922 }, { "epoch": 0.3336285888821014, "grad_norm": 0.37801456451416016, "learning_rate": 3.7479912088187087e-05, "loss": 4.3318, "step": 10923 }, { "epoch": 0.33365913255956015, "grad_norm": 0.37889230251312256, "learning_rate": 3.74778334152017e-05, "loss": 4.3423, "step": 10924 }, { "epoch": 0.33368967623701895, "grad_norm": 0.36728382110595703, "learning_rate": 3.7475754627326484e-05, "loss": 4.31, "step": 10925 }, { "epoch": 0.3337202199144777, "grad_norm": 0.38701704144477844, "learning_rate": 3.747367572458059e-05, "loss": 4.3083, "step": 10926 }, { "epoch": 0.33375076359193645, "grad_norm": 0.38183072209358215, "learning_rate": 3.747159670698315e-05, "loss": 4.2915, "step": 10927 }, { "epoch": 0.33378130726939526, "grad_norm": 0.3701733350753784, "learning_rate": 3.74695175745533e-05, "loss": 4.3034, "step": 10928 }, { "epoch": 0.333811850946854, "grad_norm": 0.3805405795574188, "learning_rate": 3.74674383273102e-05, "loss": 4.3891, "step": 10929 }, { "epoch": 0.33384239462431275, "grad_norm": 0.3728264570236206, "learning_rate": 3.746535896527299e-05, "loss": 4.2707, "step": 10930 }, { "epoch": 0.33387293830177156, "grad_norm": 0.3738630712032318, "learning_rate": 3.746327948846079e-05, "loss": 4.3631, "step": 10931 }, { "epoch": 0.3339034819792303, "grad_norm": 0.380961537361145, "learning_rate": 3.746119989689278e-05, "loss": 4.273, "step": 10932 }, { "epoch": 0.33393402565668906, "grad_norm": 0.38308578729629517, "learning_rate": 3.7459120190588095e-05, "loss": 4.2913, "step": 10933 }, { "epoch": 0.3339645693341478, "grad_norm": 0.37695446610450745, "learning_rate": 3.745704036956588e-05, "loss": 4.3551, "step": 10934 }, { "epoch": 0.3339951130116066, "grad_norm": 0.3781619369983673, "learning_rate": 3.74549604338453e-05, "loss": 4.3851, "step": 10935 }, { "epoch": 0.33402565668906536, "grad_norm": 0.3924478590488434, "learning_rate": 3.745288038344549e-05, "loss": 4.334, "step": 10936 }, { "epoch": 0.3340562003665241, "grad_norm": 0.3731911778450012, "learning_rate": 3.745080021838561e-05, "loss": 4.3252, "step": 10937 }, { "epoch": 0.3340867440439829, "grad_norm": 0.3669017255306244, "learning_rate": 3.7448719938684804e-05, "loss": 4.317, "step": 10938 }, { "epoch": 0.33411728772144167, "grad_norm": 0.3947335183620453, "learning_rate": 3.744663954436223e-05, "loss": 4.357, "step": 10939 }, { "epoch": 0.3341478313989004, "grad_norm": 0.3907155990600586, "learning_rate": 3.744455903543705e-05, "loss": 4.4033, "step": 10940 }, { "epoch": 0.33417837507635917, "grad_norm": 0.38572224974632263, "learning_rate": 3.7442478411928425e-05, "loss": 4.318, "step": 10941 }, { "epoch": 0.334208918753818, "grad_norm": 0.4018951654434204, "learning_rate": 3.7440397673855496e-05, "loss": 4.2071, "step": 10942 }, { "epoch": 0.3342394624312767, "grad_norm": 0.381963849067688, "learning_rate": 3.7438316821237434e-05, "loss": 4.3092, "step": 10943 }, { "epoch": 0.3342700061087355, "grad_norm": 0.3891564905643463, "learning_rate": 3.7436235854093395e-05, "loss": 4.3249, "step": 10944 }, { "epoch": 0.3343005497861943, "grad_norm": 0.3816532492637634, "learning_rate": 3.743415477244253e-05, "loss": 4.3274, "step": 10945 }, { "epoch": 0.33433109346365303, "grad_norm": 0.38010671734809875, "learning_rate": 3.7432073576304016e-05, "loss": 4.3651, "step": 10946 }, { "epoch": 0.3343616371411118, "grad_norm": 0.36597880721092224, "learning_rate": 3.7429992265697014e-05, "loss": 4.3055, "step": 10947 }, { "epoch": 0.3343921808185706, "grad_norm": 0.39291319251060486, "learning_rate": 3.742791084064067e-05, "loss": 4.3054, "step": 10948 }, { "epoch": 0.33442272449602933, "grad_norm": 0.4024069011211395, "learning_rate": 3.7425829301154165e-05, "loss": 4.3215, "step": 10949 }, { "epoch": 0.3344532681734881, "grad_norm": 0.3936268985271454, "learning_rate": 3.742374764725666e-05, "loss": 4.3689, "step": 10950 }, { "epoch": 0.33448381185094683, "grad_norm": 0.36892169713974, "learning_rate": 3.742166587896733e-05, "loss": 4.3284, "step": 10951 }, { "epoch": 0.33451435552840564, "grad_norm": 0.38302767276763916, "learning_rate": 3.741958399630533e-05, "loss": 4.3069, "step": 10952 }, { "epoch": 0.3345448992058644, "grad_norm": 0.3876832127571106, "learning_rate": 3.741750199928983e-05, "loss": 4.2557, "step": 10953 }, { "epoch": 0.33457544288332314, "grad_norm": 0.38700971007347107, "learning_rate": 3.741541988794002e-05, "loss": 4.3365, "step": 10954 }, { "epoch": 0.33460598656078194, "grad_norm": 0.3756828010082245, "learning_rate": 3.741333766227504e-05, "loss": 4.3264, "step": 10955 }, { "epoch": 0.3346365302382407, "grad_norm": 0.3810821771621704, "learning_rate": 3.7411255322314084e-05, "loss": 4.3651, "step": 10956 }, { "epoch": 0.33466707391569944, "grad_norm": 0.3798895478248596, "learning_rate": 3.740917286807631e-05, "loss": 4.3718, "step": 10957 }, { "epoch": 0.3346976175931582, "grad_norm": 0.3768778443336487, "learning_rate": 3.740709029958092e-05, "loss": 4.3613, "step": 10958 }, { "epoch": 0.334728161270617, "grad_norm": 0.37976914644241333, "learning_rate": 3.740500761684705e-05, "loss": 4.3719, "step": 10959 }, { "epoch": 0.33475870494807575, "grad_norm": 0.3762844502925873, "learning_rate": 3.7402924819893916e-05, "loss": 4.192, "step": 10960 }, { "epoch": 0.3347892486255345, "grad_norm": 0.3788618743419647, "learning_rate": 3.740084190874067e-05, "loss": 4.4094, "step": 10961 }, { "epoch": 0.3348197923029933, "grad_norm": 0.37803158164024353, "learning_rate": 3.739875888340649e-05, "loss": 4.3238, "step": 10962 }, { "epoch": 0.33485033598045205, "grad_norm": 0.38075631856918335, "learning_rate": 3.739667574391056e-05, "loss": 4.2518, "step": 10963 }, { "epoch": 0.3348808796579108, "grad_norm": 0.382596880197525, "learning_rate": 3.7394592490272076e-05, "loss": 4.3739, "step": 10964 }, { "epoch": 0.33491142333536955, "grad_norm": 0.39758095145225525, "learning_rate": 3.73925091225102e-05, "loss": 4.3852, "step": 10965 }, { "epoch": 0.33494196701282836, "grad_norm": 0.3812670111656189, "learning_rate": 3.739042564064411e-05, "loss": 4.4026, "step": 10966 }, { "epoch": 0.3349725106902871, "grad_norm": 0.37949615716934204, "learning_rate": 3.738834204469302e-05, "loss": 4.2754, "step": 10967 }, { "epoch": 0.33500305436774586, "grad_norm": 0.37864089012145996, "learning_rate": 3.7386258334676084e-05, "loss": 4.3528, "step": 10968 }, { "epoch": 0.33503359804520466, "grad_norm": 0.3774194121360779, "learning_rate": 3.73841745106125e-05, "loss": 4.298, "step": 10969 }, { "epoch": 0.3350641417226634, "grad_norm": 0.37837928533554077, "learning_rate": 3.7382090572521456e-05, "loss": 4.2913, "step": 10970 }, { "epoch": 0.33509468540012216, "grad_norm": 0.3732316792011261, "learning_rate": 3.738000652042213e-05, "loss": 4.2766, "step": 10971 }, { "epoch": 0.33512522907758097, "grad_norm": 0.38749954104423523, "learning_rate": 3.737792235433373e-05, "loss": 4.2963, "step": 10972 }, { "epoch": 0.3351557727550397, "grad_norm": 0.37147510051727295, "learning_rate": 3.7375838074275424e-05, "loss": 4.2919, "step": 10973 }, { "epoch": 0.33518631643249847, "grad_norm": 0.38329869508743286, "learning_rate": 3.737375368026643e-05, "loss": 4.3961, "step": 10974 }, { "epoch": 0.3352168601099572, "grad_norm": 0.3770367205142975, "learning_rate": 3.737166917232591e-05, "loss": 4.3426, "step": 10975 }, { "epoch": 0.335247403787416, "grad_norm": 0.3961430788040161, "learning_rate": 3.736958455047308e-05, "loss": 4.2679, "step": 10976 }, { "epoch": 0.33527794746487477, "grad_norm": 0.37445369362831116, "learning_rate": 3.736749981472712e-05, "loss": 4.3884, "step": 10977 }, { "epoch": 0.3353084911423335, "grad_norm": 0.358097642660141, "learning_rate": 3.7365414965107224e-05, "loss": 4.2894, "step": 10978 }, { "epoch": 0.3353390348197923, "grad_norm": 0.3942072093486786, "learning_rate": 3.73633300016326e-05, "loss": 4.291, "step": 10979 }, { "epoch": 0.3353695784972511, "grad_norm": 0.378736674785614, "learning_rate": 3.7361244924322445e-05, "loss": 4.2542, "step": 10980 }, { "epoch": 0.3354001221747098, "grad_norm": 0.3713834583759308, "learning_rate": 3.735915973319595e-05, "loss": 4.4036, "step": 10981 }, { "epoch": 0.3354306658521686, "grad_norm": 0.37485426664352417, "learning_rate": 3.7357074428272324e-05, "loss": 4.3581, "step": 10982 }, { "epoch": 0.3354612095296274, "grad_norm": 0.38482019305229187, "learning_rate": 3.735498900957075e-05, "loss": 4.3241, "step": 10983 }, { "epoch": 0.33549175320708613, "grad_norm": 0.37995362281799316, "learning_rate": 3.735290347711044e-05, "loss": 4.2918, "step": 10984 }, { "epoch": 0.3355222968845449, "grad_norm": 0.38064515590667725, "learning_rate": 3.73508178309106e-05, "loss": 4.3735, "step": 10985 }, { "epoch": 0.3355528405620037, "grad_norm": 0.3851505517959595, "learning_rate": 3.734873207099042e-05, "loss": 4.3024, "step": 10986 }, { "epoch": 0.33558338423946243, "grad_norm": 0.39743009209632874, "learning_rate": 3.734664619736913e-05, "loss": 4.2998, "step": 10987 }, { "epoch": 0.3356139279169212, "grad_norm": 0.40174078941345215, "learning_rate": 3.734456021006592e-05, "loss": 4.3194, "step": 10988 }, { "epoch": 0.33564447159438, "grad_norm": 0.3854812681674957, "learning_rate": 3.734247410909998e-05, "loss": 4.3679, "step": 10989 }, { "epoch": 0.33567501527183874, "grad_norm": 0.38829344511032104, "learning_rate": 3.7340387894490554e-05, "loss": 4.1361, "step": 10990 }, { "epoch": 0.3357055589492975, "grad_norm": 0.3898332118988037, "learning_rate": 3.733830156625682e-05, "loss": 4.2587, "step": 10991 }, { "epoch": 0.33573610262675624, "grad_norm": 0.38069701194763184, "learning_rate": 3.7336215124418004e-05, "loss": 4.3784, "step": 10992 }, { "epoch": 0.33576664630421504, "grad_norm": 0.37345993518829346, "learning_rate": 3.733412856899331e-05, "loss": 4.2701, "step": 10993 }, { "epoch": 0.3357971899816738, "grad_norm": 0.3922768533229828, "learning_rate": 3.7332041900001956e-05, "loss": 4.2505, "step": 10994 }, { "epoch": 0.33582773365913254, "grad_norm": 0.3792918622493744, "learning_rate": 3.7329955117463155e-05, "loss": 4.214, "step": 10995 }, { "epoch": 0.33585827733659135, "grad_norm": 0.3698190748691559, "learning_rate": 3.732786822139611e-05, "loss": 4.3409, "step": 10996 }, { "epoch": 0.3358888210140501, "grad_norm": 0.39124295115470886, "learning_rate": 3.7325781211820045e-05, "loss": 4.3892, "step": 10997 }, { "epoch": 0.33591936469150885, "grad_norm": 0.38167044520378113, "learning_rate": 3.732369408875418e-05, "loss": 4.2921, "step": 10998 }, { "epoch": 0.3359499083689676, "grad_norm": 0.3963790237903595, "learning_rate": 3.7321606852217726e-05, "loss": 4.3885, "step": 10999 }, { "epoch": 0.3359804520464264, "grad_norm": 0.38442766666412354, "learning_rate": 3.73195195022299e-05, "loss": 4.3948, "step": 11000 }, { "epoch": 0.33601099572388515, "grad_norm": 0.3732680380344391, "learning_rate": 3.731743203880993e-05, "loss": 4.258, "step": 11001 }, { "epoch": 0.3360415394013439, "grad_norm": 0.3872181475162506, "learning_rate": 3.7315344461977026e-05, "loss": 4.2332, "step": 11002 }, { "epoch": 0.3360720830788027, "grad_norm": 0.37738490104675293, "learning_rate": 3.731325677175041e-05, "loss": 4.3561, "step": 11003 }, { "epoch": 0.33610262675626146, "grad_norm": 0.3780275285243988, "learning_rate": 3.731116896814931e-05, "loss": 4.2747, "step": 11004 }, { "epoch": 0.3361331704337202, "grad_norm": 0.38094526529312134, "learning_rate": 3.730908105119295e-05, "loss": 4.375, "step": 11005 }, { "epoch": 0.336163714111179, "grad_norm": 0.38654935359954834, "learning_rate": 3.7306993020900546e-05, "loss": 4.2118, "step": 11006 }, { "epoch": 0.33619425778863776, "grad_norm": 0.3853091299533844, "learning_rate": 3.730490487729134e-05, "loss": 4.4027, "step": 11007 }, { "epoch": 0.3362248014660965, "grad_norm": 0.3947567939758301, "learning_rate": 3.7302816620384544e-05, "loss": 4.3096, "step": 11008 }, { "epoch": 0.33625534514355526, "grad_norm": 0.3814314901828766, "learning_rate": 3.730072825019939e-05, "loss": 4.3704, "step": 11009 }, { "epoch": 0.33628588882101407, "grad_norm": 0.37307584285736084, "learning_rate": 3.72986397667551e-05, "loss": 4.4106, "step": 11010 }, { "epoch": 0.3363164324984728, "grad_norm": 0.36931008100509644, "learning_rate": 3.729655117007092e-05, "loss": 4.3916, "step": 11011 }, { "epoch": 0.33634697617593157, "grad_norm": 0.38616785407066345, "learning_rate": 3.729446246016607e-05, "loss": 4.3227, "step": 11012 }, { "epoch": 0.33637751985339037, "grad_norm": 0.38834163546562195, "learning_rate": 3.7292373637059777e-05, "loss": 4.3272, "step": 11013 }, { "epoch": 0.3364080635308491, "grad_norm": 0.3771938383579254, "learning_rate": 3.729028470077128e-05, "loss": 4.3461, "step": 11014 }, { "epoch": 0.33643860720830787, "grad_norm": 0.3773753345012665, "learning_rate": 3.728819565131982e-05, "loss": 4.3894, "step": 11015 }, { "epoch": 0.3364691508857666, "grad_norm": 0.3776476979255676, "learning_rate": 3.728610648872462e-05, "loss": 4.2944, "step": 11016 }, { "epoch": 0.3364996945632254, "grad_norm": 0.38563933968544006, "learning_rate": 3.728401721300492e-05, "loss": 4.3833, "step": 11017 }, { "epoch": 0.3365302382406842, "grad_norm": 0.3812176585197449, "learning_rate": 3.728192782417995e-05, "loss": 4.3105, "step": 11018 }, { "epoch": 0.3365607819181429, "grad_norm": 0.3719033896923065, "learning_rate": 3.7279838322268964e-05, "loss": 4.3079, "step": 11019 }, { "epoch": 0.33659132559560173, "grad_norm": 0.38080933690071106, "learning_rate": 3.7277748707291195e-05, "loss": 4.3449, "step": 11020 }, { "epoch": 0.3366218692730605, "grad_norm": 0.3757018744945526, "learning_rate": 3.727565897926588e-05, "loss": 4.2748, "step": 11021 }, { "epoch": 0.33665241295051923, "grad_norm": 0.3834093511104584, "learning_rate": 3.727356913821227e-05, "loss": 4.3503, "step": 11022 }, { "epoch": 0.33668295662797804, "grad_norm": 0.397906631231308, "learning_rate": 3.7271479184149584e-05, "loss": 4.4022, "step": 11023 }, { "epoch": 0.3367135003054368, "grad_norm": 0.3831927180290222, "learning_rate": 3.726938911709708e-05, "loss": 4.405, "step": 11024 }, { "epoch": 0.33674404398289554, "grad_norm": 0.39520007371902466, "learning_rate": 3.726729893707401e-05, "loss": 4.2331, "step": 11025 }, { "epoch": 0.3367745876603543, "grad_norm": 0.3820854127407074, "learning_rate": 3.726520864409961e-05, "loss": 4.343, "step": 11026 }, { "epoch": 0.3368051313378131, "grad_norm": 0.364333838224411, "learning_rate": 3.726311823819312e-05, "loss": 4.3605, "step": 11027 }, { "epoch": 0.33683567501527184, "grad_norm": 0.37858712673187256, "learning_rate": 3.72610277193738e-05, "loss": 4.4018, "step": 11028 }, { "epoch": 0.3368662186927306, "grad_norm": 0.38600680232048035, "learning_rate": 3.7258937087660894e-05, "loss": 4.4052, "step": 11029 }, { "epoch": 0.3368967623701894, "grad_norm": 0.38976871967315674, "learning_rate": 3.725684634307366e-05, "loss": 4.3323, "step": 11030 }, { "epoch": 0.33692730604764815, "grad_norm": 0.38253000378608704, "learning_rate": 3.725475548563133e-05, "loss": 4.2606, "step": 11031 }, { "epoch": 0.3369578497251069, "grad_norm": 0.374361127614975, "learning_rate": 3.7252664515353166e-05, "loss": 4.2717, "step": 11032 }, { "epoch": 0.33698839340256564, "grad_norm": 0.3762319087982178, "learning_rate": 3.725057343225843e-05, "loss": 4.3827, "step": 11033 }, { "epoch": 0.33701893708002445, "grad_norm": 0.3852883577346802, "learning_rate": 3.724848223636635e-05, "loss": 4.3461, "step": 11034 }, { "epoch": 0.3370494807574832, "grad_norm": 0.3790804445743561, "learning_rate": 3.724639092769621e-05, "loss": 4.2543, "step": 11035 }, { "epoch": 0.33708002443494195, "grad_norm": 0.36926427483558655, "learning_rate": 3.7244299506267245e-05, "loss": 4.3014, "step": 11036 }, { "epoch": 0.33711056811240075, "grad_norm": 0.37047824263572693, "learning_rate": 3.724220797209872e-05, "loss": 4.399, "step": 11037 }, { "epoch": 0.3371411117898595, "grad_norm": 0.3823380172252655, "learning_rate": 3.724011632520989e-05, "loss": 4.2853, "step": 11038 }, { "epoch": 0.33717165546731825, "grad_norm": 0.375001460313797, "learning_rate": 3.7238024565620024e-05, "loss": 4.3707, "step": 11039 }, { "epoch": 0.337202199144777, "grad_norm": 0.3801296651363373, "learning_rate": 3.723593269334836e-05, "loss": 4.3541, "step": 11040 }, { "epoch": 0.3372327428222358, "grad_norm": 0.37614911794662476, "learning_rate": 3.723384070841418e-05, "loss": 4.3539, "step": 11041 }, { "epoch": 0.33726328649969456, "grad_norm": 0.3815300464630127, "learning_rate": 3.723174861083674e-05, "loss": 4.302, "step": 11042 }, { "epoch": 0.3372938301771533, "grad_norm": 0.36465805768966675, "learning_rate": 3.72296564006353e-05, "loss": 4.2169, "step": 11043 }, { "epoch": 0.3373243738546121, "grad_norm": 0.3713703453540802, "learning_rate": 3.7227564077829125e-05, "loss": 4.3394, "step": 11044 }, { "epoch": 0.33735491753207086, "grad_norm": 0.3858162760734558, "learning_rate": 3.7225471642437484e-05, "loss": 4.3392, "step": 11045 }, { "epoch": 0.3373854612095296, "grad_norm": 0.3668470084667206, "learning_rate": 3.7223379094479636e-05, "loss": 4.3203, "step": 11046 }, { "epoch": 0.3374160048869884, "grad_norm": 0.3707481324672699, "learning_rate": 3.7221286433974854e-05, "loss": 4.335, "step": 11047 }, { "epoch": 0.33744654856444717, "grad_norm": 0.38195061683654785, "learning_rate": 3.721919366094241e-05, "loss": 4.3236, "step": 11048 }, { "epoch": 0.3374770922419059, "grad_norm": 0.3742053508758545, "learning_rate": 3.721710077540156e-05, "loss": 4.2663, "step": 11049 }, { "epoch": 0.33750763591936467, "grad_norm": 0.3766149580478668, "learning_rate": 3.721500777737158e-05, "loss": 4.2801, "step": 11050 }, { "epoch": 0.3375381795968235, "grad_norm": 0.3785940706729889, "learning_rate": 3.7212914666871746e-05, "loss": 4.3924, "step": 11051 }, { "epoch": 0.3375687232742822, "grad_norm": 0.3681170642375946, "learning_rate": 3.721082144392133e-05, "loss": 4.3946, "step": 11052 }, { "epoch": 0.337599266951741, "grad_norm": 0.3809899389743805, "learning_rate": 3.72087281085396e-05, "loss": 4.3347, "step": 11053 }, { "epoch": 0.3376298106291998, "grad_norm": 0.38192421197891235, "learning_rate": 3.720663466074583e-05, "loss": 4.2984, "step": 11054 }, { "epoch": 0.33766035430665853, "grad_norm": 0.3766922652721405, "learning_rate": 3.72045411005593e-05, "loss": 4.3907, "step": 11055 }, { "epoch": 0.3376908979841173, "grad_norm": 0.3782271444797516, "learning_rate": 3.7202447427999294e-05, "loss": 4.2992, "step": 11056 }, { "epoch": 0.337721441661576, "grad_norm": 0.38189929723739624, "learning_rate": 3.7200353643085074e-05, "loss": 4.303, "step": 11057 }, { "epoch": 0.33775198533903483, "grad_norm": 0.3750002384185791, "learning_rate": 3.719825974583592e-05, "loss": 4.3553, "step": 11058 }, { "epoch": 0.3377825290164936, "grad_norm": 0.3718121647834778, "learning_rate": 3.719616573627113e-05, "loss": 4.3059, "step": 11059 }, { "epoch": 0.33781307269395233, "grad_norm": 0.38087335228919983, "learning_rate": 3.7194071614409955e-05, "loss": 4.2168, "step": 11060 }, { "epoch": 0.33784361637141114, "grad_norm": 0.3706863522529602, "learning_rate": 3.719197738027171e-05, "loss": 4.2581, "step": 11061 }, { "epoch": 0.3378741600488699, "grad_norm": 0.4266839325428009, "learning_rate": 3.718988303387565e-05, "loss": 4.3246, "step": 11062 }, { "epoch": 0.33790470372632864, "grad_norm": 0.37325119972229004, "learning_rate": 3.718778857524107e-05, "loss": 4.2722, "step": 11063 }, { "epoch": 0.33793524740378744, "grad_norm": 0.3831527531147003, "learning_rate": 3.7185694004387254e-05, "loss": 4.3575, "step": 11064 }, { "epoch": 0.3379657910812462, "grad_norm": 0.3735586106777191, "learning_rate": 3.7183599321333493e-05, "loss": 4.3757, "step": 11065 }, { "epoch": 0.33799633475870494, "grad_norm": 0.38587838411331177, "learning_rate": 3.718150452609906e-05, "loss": 4.3024, "step": 11066 }, { "epoch": 0.3380268784361637, "grad_norm": 0.39479976892471313, "learning_rate": 3.7179409618703266e-05, "loss": 4.3328, "step": 11067 }, { "epoch": 0.3380574221136225, "grad_norm": 0.3807678818702698, "learning_rate": 3.717731459916537e-05, "loss": 4.3204, "step": 11068 }, { "epoch": 0.33808796579108125, "grad_norm": 0.38721713423728943, "learning_rate": 3.71752194675047e-05, "loss": 4.3862, "step": 11069 }, { "epoch": 0.33811850946854, "grad_norm": 0.37873363494873047, "learning_rate": 3.7173124223740504e-05, "loss": 4.3775, "step": 11070 }, { "epoch": 0.3381490531459988, "grad_norm": 0.41481712460517883, "learning_rate": 3.717102886789209e-05, "loss": 4.3203, "step": 11071 }, { "epoch": 0.33817959682345755, "grad_norm": 0.37535610795021057, "learning_rate": 3.7168933399978776e-05, "loss": 4.3284, "step": 11072 }, { "epoch": 0.3382101405009163, "grad_norm": 0.3704240024089813, "learning_rate": 3.716683782001982e-05, "loss": 4.3046, "step": 11073 }, { "epoch": 0.33824068417837505, "grad_norm": 0.38244614005088806, "learning_rate": 3.716474212803454e-05, "loss": 4.3528, "step": 11074 }, { "epoch": 0.33827122785583386, "grad_norm": 0.3804705739021301, "learning_rate": 3.716264632404221e-05, "loss": 4.3177, "step": 11075 }, { "epoch": 0.3383017715332926, "grad_norm": 0.3720270097255707, "learning_rate": 3.716055040806216e-05, "loss": 4.3488, "step": 11076 }, { "epoch": 0.33833231521075136, "grad_norm": 0.37269508838653564, "learning_rate": 3.715845438011367e-05, "loss": 4.3227, "step": 11077 }, { "epoch": 0.33836285888821016, "grad_norm": 0.37896397709846497, "learning_rate": 3.715635824021603e-05, "loss": 4.3275, "step": 11078 }, { "epoch": 0.3383934025656689, "grad_norm": 0.37180817127227783, "learning_rate": 3.7154261988388554e-05, "loss": 4.2861, "step": 11079 }, { "epoch": 0.33842394624312766, "grad_norm": 0.37362635135650635, "learning_rate": 3.7152165624650536e-05, "loss": 4.257, "step": 11080 }, { "epoch": 0.33845448992058647, "grad_norm": 0.3818986415863037, "learning_rate": 3.715006914902128e-05, "loss": 4.4028, "step": 11081 }, { "epoch": 0.3384850335980452, "grad_norm": 0.3785986602306366, "learning_rate": 3.71479725615201e-05, "loss": 4.3976, "step": 11082 }, { "epoch": 0.33851557727550396, "grad_norm": 0.373674601316452, "learning_rate": 3.714587586216628e-05, "loss": 4.3295, "step": 11083 }, { "epoch": 0.3385461209529627, "grad_norm": 0.37506020069122314, "learning_rate": 3.714377905097914e-05, "loss": 4.4361, "step": 11084 }, { "epoch": 0.3385766646304215, "grad_norm": 0.37611690163612366, "learning_rate": 3.7141682127977986e-05, "loss": 4.3876, "step": 11085 }, { "epoch": 0.33860720830788027, "grad_norm": 0.37459060549736023, "learning_rate": 3.713958509318212e-05, "loss": 4.2762, "step": 11086 }, { "epoch": 0.338637751985339, "grad_norm": 0.3814677298069, "learning_rate": 3.713748794661085e-05, "loss": 4.2954, "step": 11087 }, { "epoch": 0.3386682956627978, "grad_norm": 0.3711961805820465, "learning_rate": 3.713539068828349e-05, "loss": 4.3301, "step": 11088 }, { "epoch": 0.3386988393402566, "grad_norm": 0.3930070400238037, "learning_rate": 3.713329331821934e-05, "loss": 4.3452, "step": 11089 }, { "epoch": 0.3387293830177153, "grad_norm": 0.3880136013031006, "learning_rate": 3.713119583643773e-05, "loss": 4.3361, "step": 11090 }, { "epoch": 0.3387599266951741, "grad_norm": 0.3874931335449219, "learning_rate": 3.712909824295797e-05, "loss": 4.3644, "step": 11091 }, { "epoch": 0.3387904703726329, "grad_norm": 0.3832732141017914, "learning_rate": 3.712700053779935e-05, "loss": 4.3644, "step": 11092 }, { "epoch": 0.33882101405009163, "grad_norm": 0.383073091506958, "learning_rate": 3.712490272098122e-05, "loss": 4.3258, "step": 11093 }, { "epoch": 0.3388515577275504, "grad_norm": 0.3730582296848297, "learning_rate": 3.712280479252286e-05, "loss": 4.308, "step": 11094 }, { "epoch": 0.3388821014050092, "grad_norm": 0.38379210233688354, "learning_rate": 3.71207067524436e-05, "loss": 4.3396, "step": 11095 }, { "epoch": 0.33891264508246793, "grad_norm": 0.3849024772644043, "learning_rate": 3.711860860076277e-05, "loss": 4.2541, "step": 11096 }, { "epoch": 0.3389431887599267, "grad_norm": 0.3748692274093628, "learning_rate": 3.711651033749968e-05, "loss": 4.3143, "step": 11097 }, { "epoch": 0.3389737324373855, "grad_norm": 0.3823433220386505, "learning_rate": 3.711441196267365e-05, "loss": 4.2898, "step": 11098 }, { "epoch": 0.33900427611484424, "grad_norm": 0.38168901205062866, "learning_rate": 3.7112313476303996e-05, "loss": 4.3274, "step": 11099 }, { "epoch": 0.339034819792303, "grad_norm": 0.38632965087890625, "learning_rate": 3.711021487841005e-05, "loss": 4.2838, "step": 11100 }, { "epoch": 0.33906536346976174, "grad_norm": 0.39210498332977295, "learning_rate": 3.710811616901113e-05, "loss": 4.3651, "step": 11101 }, { "epoch": 0.33909590714722054, "grad_norm": 0.3787112832069397, "learning_rate": 3.710601734812655e-05, "loss": 4.3722, "step": 11102 }, { "epoch": 0.3391264508246793, "grad_norm": 0.37296614050865173, "learning_rate": 3.7103918415775655e-05, "loss": 4.2793, "step": 11103 }, { "epoch": 0.33915699450213804, "grad_norm": 0.37995290756225586, "learning_rate": 3.710181937197775e-05, "loss": 4.3899, "step": 11104 }, { "epoch": 0.33918753817959685, "grad_norm": 0.39192917943000793, "learning_rate": 3.709972021675217e-05, "loss": 4.3614, "step": 11105 }, { "epoch": 0.3392180818570556, "grad_norm": 0.38211843371391296, "learning_rate": 3.709762095011825e-05, "loss": 4.3428, "step": 11106 }, { "epoch": 0.33924862553451435, "grad_norm": 0.37170764803886414, "learning_rate": 3.709552157209532e-05, "loss": 4.3878, "step": 11107 }, { "epoch": 0.3392791692119731, "grad_norm": 0.3815653920173645, "learning_rate": 3.70934220827027e-05, "loss": 4.3616, "step": 11108 }, { "epoch": 0.3393097128894319, "grad_norm": 0.38656800985336304, "learning_rate": 3.709132248195972e-05, "loss": 4.3527, "step": 11109 }, { "epoch": 0.33934025656689065, "grad_norm": 0.39012590050697327, "learning_rate": 3.7089222769885726e-05, "loss": 4.3344, "step": 11110 }, { "epoch": 0.3393708002443494, "grad_norm": 0.39679139852523804, "learning_rate": 3.708712294650003e-05, "loss": 4.3718, "step": 11111 }, { "epoch": 0.3394013439218082, "grad_norm": 0.3846285939216614, "learning_rate": 3.708502301182199e-05, "loss": 4.3566, "step": 11112 }, { "epoch": 0.33943188759926696, "grad_norm": 0.3816451132297516, "learning_rate": 3.708292296587093e-05, "loss": 4.3294, "step": 11113 }, { "epoch": 0.3394624312767257, "grad_norm": 0.3912537395954132, "learning_rate": 3.7080822808666176e-05, "loss": 4.3792, "step": 11114 }, { "epoch": 0.33949297495418446, "grad_norm": 0.37041395902633667, "learning_rate": 3.7078722540227085e-05, "loss": 4.3516, "step": 11115 }, { "epoch": 0.33952351863164326, "grad_norm": 0.38175228238105774, "learning_rate": 3.7076622160572975e-05, "loss": 4.2999, "step": 11116 }, { "epoch": 0.339554062309102, "grad_norm": 0.37216660380363464, "learning_rate": 3.7074521669723205e-05, "loss": 4.3435, "step": 11117 }, { "epoch": 0.33958460598656076, "grad_norm": 0.3830213248729706, "learning_rate": 3.707242106769711e-05, "loss": 4.3059, "step": 11118 }, { "epoch": 0.33961514966401957, "grad_norm": 0.37833383679389954, "learning_rate": 3.707032035451401e-05, "loss": 4.3213, "step": 11119 }, { "epoch": 0.3396456933414783, "grad_norm": 0.3897190988063812, "learning_rate": 3.706821953019327e-05, "loss": 4.324, "step": 11120 }, { "epoch": 0.33967623701893707, "grad_norm": 0.366187185049057, "learning_rate": 3.7066118594754236e-05, "loss": 4.282, "step": 11121 }, { "epoch": 0.33970678069639587, "grad_norm": 0.3934278190135956, "learning_rate": 3.706401754821623e-05, "loss": 4.3376, "step": 11122 }, { "epoch": 0.3397373243738546, "grad_norm": 0.3954334855079651, "learning_rate": 3.706191639059863e-05, "loss": 4.3137, "step": 11123 }, { "epoch": 0.33976786805131337, "grad_norm": 0.39244344830513, "learning_rate": 3.705981512192076e-05, "loss": 4.349, "step": 11124 }, { "epoch": 0.3397984117287721, "grad_norm": 0.37531715631484985, "learning_rate": 3.705771374220197e-05, "loss": 4.2953, "step": 11125 }, { "epoch": 0.3398289554062309, "grad_norm": 0.37639856338500977, "learning_rate": 3.70556122514616e-05, "loss": 4.2879, "step": 11126 }, { "epoch": 0.3398594990836897, "grad_norm": 0.3867456912994385, "learning_rate": 3.705351064971902e-05, "loss": 4.3085, "step": 11127 }, { "epoch": 0.3398900427611484, "grad_norm": 0.38133570551872253, "learning_rate": 3.705140893699357e-05, "loss": 4.3703, "step": 11128 }, { "epoch": 0.33992058643860723, "grad_norm": 0.37815311551094055, "learning_rate": 3.704930711330459e-05, "loss": 4.3277, "step": 11129 }, { "epoch": 0.339951130116066, "grad_norm": 0.40383437275886536, "learning_rate": 3.7047205178671456e-05, "loss": 4.3844, "step": 11130 }, { "epoch": 0.33998167379352473, "grad_norm": 0.3815922737121582, "learning_rate": 3.7045103133113515e-05, "loss": 4.3288, "step": 11131 }, { "epoch": 0.3400122174709835, "grad_norm": 0.3667145073413849, "learning_rate": 3.704300097665011e-05, "loss": 4.3019, "step": 11132 }, { "epoch": 0.3400427611484423, "grad_norm": 0.3625470697879791, "learning_rate": 3.70408987093006e-05, "loss": 4.3899, "step": 11133 }, { "epoch": 0.34007330482590103, "grad_norm": 0.36941438913345337, "learning_rate": 3.7038796331084346e-05, "loss": 4.2851, "step": 11134 }, { "epoch": 0.3401038485033598, "grad_norm": 0.38298484683036804, "learning_rate": 3.7036693842020706e-05, "loss": 4.3501, "step": 11135 }, { "epoch": 0.3401343921808186, "grad_norm": 0.3860020637512207, "learning_rate": 3.703459124212903e-05, "loss": 4.3219, "step": 11136 }, { "epoch": 0.34016493585827734, "grad_norm": 0.36949753761291504, "learning_rate": 3.70324885314287e-05, "loss": 4.3154, "step": 11137 }, { "epoch": 0.3401954795357361, "grad_norm": 0.38809260725975037, "learning_rate": 3.703038570993905e-05, "loss": 4.3041, "step": 11138 }, { "epoch": 0.3402260232131949, "grad_norm": 0.37548404932022095, "learning_rate": 3.702828277767946e-05, "loss": 4.3197, "step": 11139 }, { "epoch": 0.34025656689065364, "grad_norm": 0.3758710026741028, "learning_rate": 3.7026179734669274e-05, "loss": 4.3522, "step": 11140 }, { "epoch": 0.3402871105681124, "grad_norm": 0.3780566155910492, "learning_rate": 3.702407658092788e-05, "loss": 4.3669, "step": 11141 }, { "epoch": 0.34031765424557114, "grad_norm": 0.3807891607284546, "learning_rate": 3.702197331647463e-05, "loss": 4.3068, "step": 11142 }, { "epoch": 0.34034819792302995, "grad_norm": 0.3851608633995056, "learning_rate": 3.7019869941328886e-05, "loss": 4.3931, "step": 11143 }, { "epoch": 0.3403787416004887, "grad_norm": 0.3756418526172638, "learning_rate": 3.7017766455510016e-05, "loss": 4.3379, "step": 11144 }, { "epoch": 0.34040928527794745, "grad_norm": 0.37391000986099243, "learning_rate": 3.70156628590374e-05, "loss": 4.3939, "step": 11145 }, { "epoch": 0.34043982895540625, "grad_norm": 0.3743402659893036, "learning_rate": 3.701355915193039e-05, "loss": 4.3664, "step": 11146 }, { "epoch": 0.340470372632865, "grad_norm": 0.38031822443008423, "learning_rate": 3.7011455334208376e-05, "loss": 4.3864, "step": 11147 }, { "epoch": 0.34050091631032375, "grad_norm": 0.36276718974113464, "learning_rate": 3.7009351405890705e-05, "loss": 4.3568, "step": 11148 }, { "epoch": 0.3405314599877825, "grad_norm": 0.3730919361114502, "learning_rate": 3.7007247366996766e-05, "loss": 4.401, "step": 11149 }, { "epoch": 0.3405620036652413, "grad_norm": 0.39755699038505554, "learning_rate": 3.7005143217545925e-05, "loss": 4.2628, "step": 11150 }, { "epoch": 0.34059254734270006, "grad_norm": 0.39043423533439636, "learning_rate": 3.700303895755756e-05, "loss": 4.3768, "step": 11151 }, { "epoch": 0.3406230910201588, "grad_norm": 0.38246679306030273, "learning_rate": 3.7000934587051044e-05, "loss": 4.3125, "step": 11152 }, { "epoch": 0.3406536346976176, "grad_norm": 0.3739319443702698, "learning_rate": 3.699883010604575e-05, "loss": 4.2665, "step": 11153 }, { "epoch": 0.34068417837507636, "grad_norm": 0.3915385901927948, "learning_rate": 3.6996725514561056e-05, "loss": 4.3042, "step": 11154 }, { "epoch": 0.3407147220525351, "grad_norm": 0.38534578680992126, "learning_rate": 3.699462081261636e-05, "loss": 4.3259, "step": 11155 }, { "epoch": 0.3407452657299939, "grad_norm": 0.3764784038066864, "learning_rate": 3.6992516000231e-05, "loss": 4.3558, "step": 11156 }, { "epoch": 0.34077580940745267, "grad_norm": 0.37475717067718506, "learning_rate": 3.699041107742439e-05, "loss": 4.3016, "step": 11157 }, { "epoch": 0.3408063530849114, "grad_norm": 0.3778882920742035, "learning_rate": 3.69883060442159e-05, "loss": 4.2734, "step": 11158 }, { "epoch": 0.34083689676237017, "grad_norm": 0.3811834752559662, "learning_rate": 3.698620090062492e-05, "loss": 4.4254, "step": 11159 }, { "epoch": 0.340867440439829, "grad_norm": 0.378678560256958, "learning_rate": 3.698409564667081e-05, "loss": 4.3551, "step": 11160 }, { "epoch": 0.3408979841172877, "grad_norm": 0.37158235907554626, "learning_rate": 3.698199028237298e-05, "loss": 4.2603, "step": 11161 }, { "epoch": 0.34092852779474647, "grad_norm": 0.36556532979011536, "learning_rate": 3.69798848077508e-05, "loss": 4.3646, "step": 11162 }, { "epoch": 0.3409590714722053, "grad_norm": 0.37530478835105896, "learning_rate": 3.6977779222823665e-05, "loss": 4.3701, "step": 11163 }, { "epoch": 0.340989615149664, "grad_norm": 0.3746007978916168, "learning_rate": 3.697567352761096e-05, "loss": 4.405, "step": 11164 }, { "epoch": 0.3410201588271228, "grad_norm": 0.3785947263240814, "learning_rate": 3.697356772213207e-05, "loss": 4.3683, "step": 11165 }, { "epoch": 0.3410507025045815, "grad_norm": 0.37761378288269043, "learning_rate": 3.6971461806406384e-05, "loss": 4.3095, "step": 11166 }, { "epoch": 0.34108124618204033, "grad_norm": 0.3870518207550049, "learning_rate": 3.696935578045329e-05, "loss": 4.3829, "step": 11167 }, { "epoch": 0.3411117898594991, "grad_norm": 0.38800862431526184, "learning_rate": 3.6967249644292184e-05, "loss": 4.2611, "step": 11168 }, { "epoch": 0.34114233353695783, "grad_norm": 0.3779802620410919, "learning_rate": 3.696514339794246e-05, "loss": 4.3323, "step": 11169 }, { "epoch": 0.34117287721441664, "grad_norm": 0.3785538077354431, "learning_rate": 3.6963037041423516e-05, "loss": 4.313, "step": 11170 }, { "epoch": 0.3412034208918754, "grad_norm": 0.37592872977256775, "learning_rate": 3.696093057475473e-05, "loss": 4.2728, "step": 11171 }, { "epoch": 0.34123396456933414, "grad_norm": 0.3811757564544678, "learning_rate": 3.6958823997955515e-05, "loss": 4.3282, "step": 11172 }, { "epoch": 0.34126450824679294, "grad_norm": 0.37726038694381714, "learning_rate": 3.695671731104525e-05, "loss": 4.2618, "step": 11173 }, { "epoch": 0.3412950519242517, "grad_norm": 0.37837204337120056, "learning_rate": 3.6954610514043344e-05, "loss": 4.2237, "step": 11174 }, { "epoch": 0.34132559560171044, "grad_norm": 0.3928431570529938, "learning_rate": 3.695250360696919e-05, "loss": 4.3803, "step": 11175 }, { "epoch": 0.3413561392791692, "grad_norm": 0.38414475321769714, "learning_rate": 3.6950396589842194e-05, "loss": 4.2831, "step": 11176 }, { "epoch": 0.341386682956628, "grad_norm": 0.37201404571533203, "learning_rate": 3.694828946268175e-05, "loss": 4.3507, "step": 11177 }, { "epoch": 0.34141722663408675, "grad_norm": 0.37266167998313904, "learning_rate": 3.694618222550726e-05, "loss": 4.3409, "step": 11178 }, { "epoch": 0.3414477703115455, "grad_norm": 0.37335464358329773, "learning_rate": 3.694407487833814e-05, "loss": 4.3102, "step": 11179 }, { "epoch": 0.3414783139890043, "grad_norm": 0.3638593256473541, "learning_rate": 3.694196742119377e-05, "loss": 4.3818, "step": 11180 }, { "epoch": 0.34150885766646305, "grad_norm": 0.38145649433135986, "learning_rate": 3.6939859854093566e-05, "loss": 4.3883, "step": 11181 }, { "epoch": 0.3415394013439218, "grad_norm": 0.374906450510025, "learning_rate": 3.6937752177056936e-05, "loss": 4.2693, "step": 11182 }, { "epoch": 0.34156994502138055, "grad_norm": 0.37233319878578186, "learning_rate": 3.693564439010329e-05, "loss": 4.3463, "step": 11183 }, { "epoch": 0.34160048869883936, "grad_norm": 0.3742452561855316, "learning_rate": 3.693353649325202e-05, "loss": 4.3435, "step": 11184 }, { "epoch": 0.3416310323762981, "grad_norm": 0.36903002858161926, "learning_rate": 3.6931428486522545e-05, "loss": 4.2602, "step": 11185 }, { "epoch": 0.34166157605375685, "grad_norm": 0.3994799852371216, "learning_rate": 3.692932036993428e-05, "loss": 4.3353, "step": 11186 }, { "epoch": 0.34169211973121566, "grad_norm": 0.3881552517414093, "learning_rate": 3.6927212143506626e-05, "loss": 4.3067, "step": 11187 }, { "epoch": 0.3417226634086744, "grad_norm": 0.38223734498023987, "learning_rate": 3.6925103807258995e-05, "loss": 4.3612, "step": 11188 }, { "epoch": 0.34175320708613316, "grad_norm": 0.3729567527770996, "learning_rate": 3.69229953612108e-05, "loss": 4.3906, "step": 11189 }, { "epoch": 0.3417837507635919, "grad_norm": 0.38516825437545776, "learning_rate": 3.692088680538146e-05, "loss": 4.3212, "step": 11190 }, { "epoch": 0.3418142944410507, "grad_norm": 0.3780060410499573, "learning_rate": 3.6918778139790383e-05, "loss": 4.3107, "step": 11191 }, { "epoch": 0.34184483811850946, "grad_norm": 0.37887057662010193, "learning_rate": 3.691666936445699e-05, "loss": 4.2831, "step": 11192 }, { "epoch": 0.3418753817959682, "grad_norm": 0.3739869296550751, "learning_rate": 3.6914560479400703e-05, "loss": 4.3907, "step": 11193 }, { "epoch": 0.341905925473427, "grad_norm": 0.36967557668685913, "learning_rate": 3.691245148464092e-05, "loss": 4.3182, "step": 11194 }, { "epoch": 0.34193646915088577, "grad_norm": 0.3814275860786438, "learning_rate": 3.691034238019708e-05, "loss": 4.3368, "step": 11195 }, { "epoch": 0.3419670128283445, "grad_norm": 0.38938233256340027, "learning_rate": 3.690823316608859e-05, "loss": 4.3948, "step": 11196 }, { "epoch": 0.3419975565058033, "grad_norm": 0.3652997314929962, "learning_rate": 3.690612384233487e-05, "loss": 4.3139, "step": 11197 }, { "epoch": 0.3420281001832621, "grad_norm": 0.38091957569122314, "learning_rate": 3.690401440895535e-05, "loss": 4.4058, "step": 11198 }, { "epoch": 0.3420586438607208, "grad_norm": 0.3787601590156555, "learning_rate": 3.690190486596945e-05, "loss": 4.2135, "step": 11199 }, { "epoch": 0.3420891875381796, "grad_norm": 0.3712748885154724, "learning_rate": 3.689979521339659e-05, "loss": 4.3297, "step": 11200 }, { "epoch": 0.3421197312156384, "grad_norm": 0.38215872645378113, "learning_rate": 3.6897685451256196e-05, "loss": 4.2738, "step": 11201 }, { "epoch": 0.34215027489309713, "grad_norm": 0.3834553062915802, "learning_rate": 3.68955755795677e-05, "loss": 4.3639, "step": 11202 }, { "epoch": 0.3421808185705559, "grad_norm": 0.3705879747867584, "learning_rate": 3.689346559835053e-05, "loss": 4.4193, "step": 11203 }, { "epoch": 0.3422113622480147, "grad_norm": 0.38379645347595215, "learning_rate": 3.6891355507624095e-05, "loss": 4.3347, "step": 11204 }, { "epoch": 0.34224190592547343, "grad_norm": 0.3819294571876526, "learning_rate": 3.6889245307407835e-05, "loss": 4.3183, "step": 11205 }, { "epoch": 0.3422724496029322, "grad_norm": 0.39022019505500793, "learning_rate": 3.688713499772119e-05, "loss": 4.3627, "step": 11206 }, { "epoch": 0.34230299328039093, "grad_norm": 0.3738877475261688, "learning_rate": 3.688502457858358e-05, "loss": 4.3425, "step": 11207 }, { "epoch": 0.34233353695784974, "grad_norm": 0.3817920386791229, "learning_rate": 3.6882914050014426e-05, "loss": 4.3542, "step": 11208 }, { "epoch": 0.3423640806353085, "grad_norm": 0.38063833117485046, "learning_rate": 3.688080341203318e-05, "loss": 4.3623, "step": 11209 }, { "epoch": 0.34239462431276724, "grad_norm": 0.37535786628723145, "learning_rate": 3.687869266465928e-05, "loss": 4.3875, "step": 11210 }, { "epoch": 0.34242516799022604, "grad_norm": 0.3723975419998169, "learning_rate": 3.6876581807912134e-05, "loss": 4.3514, "step": 11211 }, { "epoch": 0.3424557116676848, "grad_norm": 0.39098021388053894, "learning_rate": 3.68744708418112e-05, "loss": 4.3407, "step": 11212 }, { "epoch": 0.34248625534514354, "grad_norm": 0.38383522629737854, "learning_rate": 3.6872359766375906e-05, "loss": 4.3623, "step": 11213 }, { "epoch": 0.34251679902260235, "grad_norm": 0.37522274255752563, "learning_rate": 3.6870248581625686e-05, "loss": 4.4064, "step": 11214 }, { "epoch": 0.3425473427000611, "grad_norm": 0.3789351284503937, "learning_rate": 3.686813728757999e-05, "loss": 4.3677, "step": 11215 }, { "epoch": 0.34257788637751985, "grad_norm": 0.38250020146369934, "learning_rate": 3.6866025884258254e-05, "loss": 4.415, "step": 11216 }, { "epoch": 0.3426084300549786, "grad_norm": 0.3663191497325897, "learning_rate": 3.686391437167992e-05, "loss": 4.2873, "step": 11217 }, { "epoch": 0.3426389737324374, "grad_norm": 0.38674646615982056, "learning_rate": 3.6861802749864416e-05, "loss": 4.3712, "step": 11218 }, { "epoch": 0.34266951740989615, "grad_norm": 0.37650468945503235, "learning_rate": 3.68596910188312e-05, "loss": 4.2998, "step": 11219 }, { "epoch": 0.3427000610873549, "grad_norm": 0.3766770362854004, "learning_rate": 3.6857579178599716e-05, "loss": 4.2744, "step": 11220 }, { "epoch": 0.3427306047648137, "grad_norm": 0.4018263816833496, "learning_rate": 3.685546722918939e-05, "loss": 4.2945, "step": 11221 }, { "epoch": 0.34276114844227246, "grad_norm": 0.3796345591545105, "learning_rate": 3.6853355170619695e-05, "loss": 4.339, "step": 11222 }, { "epoch": 0.3427916921197312, "grad_norm": 0.37013107538223267, "learning_rate": 3.685124300291006e-05, "loss": 4.26, "step": 11223 }, { "epoch": 0.34282223579718996, "grad_norm": 0.376179963350296, "learning_rate": 3.684913072607994e-05, "loss": 4.3232, "step": 11224 }, { "epoch": 0.34285277947464876, "grad_norm": 0.37294963002204895, "learning_rate": 3.6847018340148785e-05, "loss": 4.4128, "step": 11225 }, { "epoch": 0.3428833231521075, "grad_norm": 0.36822548508644104, "learning_rate": 3.684490584513604e-05, "loss": 4.1631, "step": 11226 }, { "epoch": 0.34291386682956626, "grad_norm": 0.3704652488231659, "learning_rate": 3.6842793241061145e-05, "loss": 4.3556, "step": 11227 }, { "epoch": 0.34294441050702507, "grad_norm": 0.38207489252090454, "learning_rate": 3.684068052794357e-05, "loss": 4.4324, "step": 11228 }, { "epoch": 0.3429749541844838, "grad_norm": 0.3854815661907196, "learning_rate": 3.683856770580276e-05, "loss": 4.2973, "step": 11229 }, { "epoch": 0.34300549786194257, "grad_norm": 0.3835380971431732, "learning_rate": 3.6836454774658176e-05, "loss": 4.3048, "step": 11230 }, { "epoch": 0.34303604153940137, "grad_norm": 0.3663885295391083, "learning_rate": 3.683434173452925e-05, "loss": 4.3322, "step": 11231 }, { "epoch": 0.3430665852168601, "grad_norm": 0.37823307514190674, "learning_rate": 3.6832228585435474e-05, "loss": 4.2293, "step": 11232 }, { "epoch": 0.34309712889431887, "grad_norm": 0.36814069747924805, "learning_rate": 3.6830115327396285e-05, "loss": 4.2965, "step": 11233 }, { "epoch": 0.3431276725717776, "grad_norm": 0.37168118357658386, "learning_rate": 3.682800196043114e-05, "loss": 4.2183, "step": 11234 }, { "epoch": 0.3431582162492364, "grad_norm": 0.38180944323539734, "learning_rate": 3.68258884845595e-05, "loss": 4.3602, "step": 11235 }, { "epoch": 0.3431887599266952, "grad_norm": 0.37672892212867737, "learning_rate": 3.6823774899800817e-05, "loss": 4.367, "step": 11236 }, { "epoch": 0.3432193036041539, "grad_norm": 0.3775474429130554, "learning_rate": 3.682166120617456e-05, "loss": 4.3231, "step": 11237 }, { "epoch": 0.34324984728161273, "grad_norm": 0.3755417466163635, "learning_rate": 3.6819547403700196e-05, "loss": 4.3603, "step": 11238 }, { "epoch": 0.3432803909590715, "grad_norm": 0.3733007609844208, "learning_rate": 3.681743349239718e-05, "loss": 4.376, "step": 11239 }, { "epoch": 0.34331093463653023, "grad_norm": 0.3990083336830139, "learning_rate": 3.681531947228498e-05, "loss": 4.3503, "step": 11240 }, { "epoch": 0.343341478313989, "grad_norm": 0.3859715759754181, "learning_rate": 3.681320534338305e-05, "loss": 4.3808, "step": 11241 }, { "epoch": 0.3433720219914478, "grad_norm": 0.37400829792022705, "learning_rate": 3.681109110571088e-05, "loss": 4.294, "step": 11242 }, { "epoch": 0.34340256566890653, "grad_norm": 0.3848240077495575, "learning_rate": 3.680897675928791e-05, "loss": 4.2561, "step": 11243 }, { "epoch": 0.3434331093463653, "grad_norm": 0.38033008575439453, "learning_rate": 3.680686230413363e-05, "loss": 4.2928, "step": 11244 }, { "epoch": 0.3434636530238241, "grad_norm": 0.3748527467250824, "learning_rate": 3.680474774026748e-05, "loss": 4.3192, "step": 11245 }, { "epoch": 0.34349419670128284, "grad_norm": 0.35893937945365906, "learning_rate": 3.680263306770896e-05, "loss": 4.3091, "step": 11246 }, { "epoch": 0.3435247403787416, "grad_norm": 0.38255876302719116, "learning_rate": 3.6800518286477524e-05, "loss": 4.4765, "step": 11247 }, { "epoch": 0.3435552840562004, "grad_norm": 0.378250390291214, "learning_rate": 3.6798403396592655e-05, "loss": 4.2234, "step": 11248 }, { "epoch": 0.34358582773365914, "grad_norm": 0.37192502617836, "learning_rate": 3.679628839807382e-05, "loss": 4.269, "step": 11249 }, { "epoch": 0.3436163714111179, "grad_norm": 0.383196085691452, "learning_rate": 3.679417329094049e-05, "loss": 4.3221, "step": 11250 }, { "epoch": 0.34364691508857664, "grad_norm": 0.38363900780677795, "learning_rate": 3.679205807521214e-05, "loss": 4.3225, "step": 11251 }, { "epoch": 0.34367745876603545, "grad_norm": 0.3839103877544403, "learning_rate": 3.678994275090825e-05, "loss": 4.3806, "step": 11252 }, { "epoch": 0.3437080024434942, "grad_norm": 0.37423503398895264, "learning_rate": 3.67878273180483e-05, "loss": 4.2403, "step": 11253 }, { "epoch": 0.34373854612095295, "grad_norm": 0.3770884871482849, "learning_rate": 3.678571177665176e-05, "loss": 4.2096, "step": 11254 }, { "epoch": 0.34376908979841175, "grad_norm": 0.3696136772632599, "learning_rate": 3.6783596126738105e-05, "loss": 4.3121, "step": 11255 }, { "epoch": 0.3437996334758705, "grad_norm": 0.386375367641449, "learning_rate": 3.6781480368326834e-05, "loss": 4.3364, "step": 11256 }, { "epoch": 0.34383017715332925, "grad_norm": 0.39425960183143616, "learning_rate": 3.677936450143741e-05, "loss": 4.3561, "step": 11257 }, { "epoch": 0.343860720830788, "grad_norm": 0.3765609860420227, "learning_rate": 3.6777248526089326e-05, "loss": 4.3595, "step": 11258 }, { "epoch": 0.3438912645082468, "grad_norm": 0.3817008137702942, "learning_rate": 3.677513244230205e-05, "loss": 4.4086, "step": 11259 }, { "epoch": 0.34392180818570556, "grad_norm": 0.3762184679508209, "learning_rate": 3.677301625009508e-05, "loss": 4.3576, "step": 11260 }, { "epoch": 0.3439523518631643, "grad_norm": 0.3761662244796753, "learning_rate": 3.67708999494879e-05, "loss": 4.3198, "step": 11261 }, { "epoch": 0.3439828955406231, "grad_norm": 0.3899098038673401, "learning_rate": 3.6768783540499983e-05, "loss": 4.3414, "step": 11262 }, { "epoch": 0.34401343921808186, "grad_norm": 0.37694206833839417, "learning_rate": 3.676666702315083e-05, "loss": 4.3689, "step": 11263 }, { "epoch": 0.3440439828955406, "grad_norm": 0.3775191307067871, "learning_rate": 3.676455039745993e-05, "loss": 4.3865, "step": 11264 }, { "epoch": 0.34407452657299936, "grad_norm": 0.37898725271224976, "learning_rate": 3.676243366344676e-05, "loss": 4.3843, "step": 11265 }, { "epoch": 0.34410507025045817, "grad_norm": 0.3938860595226288, "learning_rate": 3.676031682113081e-05, "loss": 4.341, "step": 11266 }, { "epoch": 0.3441356139279169, "grad_norm": 0.3814789950847626, "learning_rate": 3.6758199870531586e-05, "loss": 4.3611, "step": 11267 }, { "epoch": 0.34416615760537567, "grad_norm": 0.38341331481933594, "learning_rate": 3.6756082811668566e-05, "loss": 4.257, "step": 11268 }, { "epoch": 0.34419670128283447, "grad_norm": 0.3827205002307892, "learning_rate": 3.6753965644561246e-05, "loss": 4.3447, "step": 11269 }, { "epoch": 0.3442272449602932, "grad_norm": 0.37787047028541565, "learning_rate": 3.675184836922912e-05, "loss": 4.2904, "step": 11270 }, { "epoch": 0.34425778863775197, "grad_norm": 0.3764219284057617, "learning_rate": 3.6749730985691685e-05, "loss": 4.2878, "step": 11271 }, { "epoch": 0.3442883323152108, "grad_norm": 0.3666609525680542, "learning_rate": 3.674761349396845e-05, "loss": 4.27, "step": 11272 }, { "epoch": 0.3443188759926695, "grad_norm": 0.3711549937725067, "learning_rate": 3.674549589407888e-05, "loss": 4.3237, "step": 11273 }, { "epoch": 0.3443494196701283, "grad_norm": 0.3749474585056305, "learning_rate": 3.67433781860425e-05, "loss": 4.3236, "step": 11274 }, { "epoch": 0.344379963347587, "grad_norm": 0.3846426010131836, "learning_rate": 3.6741260369878794e-05, "loss": 4.4066, "step": 11275 }, { "epoch": 0.34441050702504583, "grad_norm": 0.3688271641731262, "learning_rate": 3.673914244560726e-05, "loss": 4.2586, "step": 11276 }, { "epoch": 0.3444410507025046, "grad_norm": 0.3768496811389923, "learning_rate": 3.673702441324741e-05, "loss": 4.3766, "step": 11277 }, { "epoch": 0.34447159437996333, "grad_norm": 0.38606199622154236, "learning_rate": 3.673490627281875e-05, "loss": 4.2872, "step": 11278 }, { "epoch": 0.34450213805742214, "grad_norm": 0.38060852885246277, "learning_rate": 3.673278802434076e-05, "loss": 4.3363, "step": 11279 }, { "epoch": 0.3445326817348809, "grad_norm": 0.3793468773365021, "learning_rate": 3.6730669667832975e-05, "loss": 4.3161, "step": 11280 }, { "epoch": 0.34456322541233964, "grad_norm": 0.37384986877441406, "learning_rate": 3.672855120331488e-05, "loss": 4.3304, "step": 11281 }, { "epoch": 0.3445937690897984, "grad_norm": 0.39251387119293213, "learning_rate": 3.672643263080598e-05, "loss": 4.3529, "step": 11282 }, { "epoch": 0.3446243127672572, "grad_norm": 0.39813801646232605, "learning_rate": 3.672431395032578e-05, "loss": 4.3939, "step": 11283 }, { "epoch": 0.34465485644471594, "grad_norm": 0.3832358419895172, "learning_rate": 3.67221951618938e-05, "loss": 4.3674, "step": 11284 }, { "epoch": 0.3446854001221747, "grad_norm": 0.37828463315963745, "learning_rate": 3.6720076265529544e-05, "loss": 4.3623, "step": 11285 }, { "epoch": 0.3447159437996335, "grad_norm": 0.38067975640296936, "learning_rate": 3.671795726125251e-05, "loss": 4.3493, "step": 11286 }, { "epoch": 0.34474648747709224, "grad_norm": 0.3916113078594208, "learning_rate": 3.6715838149082226e-05, "loss": 4.3351, "step": 11287 }, { "epoch": 0.344777031154551, "grad_norm": 0.39302611351013184, "learning_rate": 3.67137189290382e-05, "loss": 4.3017, "step": 11288 }, { "epoch": 0.3448075748320098, "grad_norm": 0.38454732298851013, "learning_rate": 3.671159960113993e-05, "loss": 4.3872, "step": 11289 }, { "epoch": 0.34483811850946855, "grad_norm": 0.3714401125907898, "learning_rate": 3.670948016540696e-05, "loss": 4.2632, "step": 11290 }, { "epoch": 0.3448686621869273, "grad_norm": 0.38214758038520813, "learning_rate": 3.670736062185877e-05, "loss": 4.3008, "step": 11291 }, { "epoch": 0.34489920586438605, "grad_norm": 0.3928494155406952, "learning_rate": 3.67052409705149e-05, "loss": 4.3561, "step": 11292 }, { "epoch": 0.34492974954184485, "grad_norm": 0.3781788647174835, "learning_rate": 3.670312121139485e-05, "loss": 4.3461, "step": 11293 }, { "epoch": 0.3449602932193036, "grad_norm": 0.3758922219276428, "learning_rate": 3.670100134451815e-05, "loss": 4.3043, "step": 11294 }, { "epoch": 0.34499083689676235, "grad_norm": 0.36572524905204773, "learning_rate": 3.6698881369904306e-05, "loss": 4.4064, "step": 11295 }, { "epoch": 0.34502138057422116, "grad_norm": 0.37254154682159424, "learning_rate": 3.669676128757285e-05, "loss": 4.3677, "step": 11296 }, { "epoch": 0.3450519242516799, "grad_norm": 0.3860666751861572, "learning_rate": 3.6694641097543316e-05, "loss": 4.3293, "step": 11297 }, { "epoch": 0.34508246792913866, "grad_norm": 0.3789353370666504, "learning_rate": 3.66925207998352e-05, "loss": 4.4061, "step": 11298 }, { "epoch": 0.3451130116065974, "grad_norm": 0.3779458999633789, "learning_rate": 3.6690400394468024e-05, "loss": 4.3509, "step": 11299 }, { "epoch": 0.3451435552840562, "grad_norm": 0.3938750922679901, "learning_rate": 3.668827988146132e-05, "loss": 4.2762, "step": 11300 }, { "epoch": 0.34517409896151496, "grad_norm": 0.37233999371528625, "learning_rate": 3.668615926083462e-05, "loss": 4.3768, "step": 11301 }, { "epoch": 0.3452046426389737, "grad_norm": 0.36769068241119385, "learning_rate": 3.6684038532607447e-05, "loss": 4.3951, "step": 11302 }, { "epoch": 0.3452351863164325, "grad_norm": 0.3843928575515747, "learning_rate": 3.668191769679932e-05, "loss": 4.2715, "step": 11303 }, { "epoch": 0.34526572999389127, "grad_norm": 0.37728917598724365, "learning_rate": 3.6679796753429765e-05, "loss": 4.3152, "step": 11304 }, { "epoch": 0.34529627367135, "grad_norm": 0.37975284457206726, "learning_rate": 3.6677675702518326e-05, "loss": 4.3356, "step": 11305 }, { "epoch": 0.3453268173488088, "grad_norm": 0.3811945617198944, "learning_rate": 3.667555454408451e-05, "loss": 4.4162, "step": 11306 }, { "epoch": 0.3453573610262676, "grad_norm": 0.3774314522743225, "learning_rate": 3.667343327814787e-05, "loss": 4.3097, "step": 11307 }, { "epoch": 0.3453879047037263, "grad_norm": 0.38141384720802307, "learning_rate": 3.667131190472793e-05, "loss": 4.2553, "step": 11308 }, { "epoch": 0.3454184483811851, "grad_norm": 0.3573949337005615, "learning_rate": 3.666919042384422e-05, "loss": 4.2806, "step": 11309 }, { "epoch": 0.3454489920586439, "grad_norm": 0.37845519185066223, "learning_rate": 3.6667068835516266e-05, "loss": 4.2673, "step": 11310 }, { "epoch": 0.3454795357361026, "grad_norm": 0.3698025047779083, "learning_rate": 3.666494713976362e-05, "loss": 4.3313, "step": 11311 }, { "epoch": 0.3455100794135614, "grad_norm": 0.3674454987049103, "learning_rate": 3.66628253366058e-05, "loss": 4.3632, "step": 11312 }, { "epoch": 0.3455406230910202, "grad_norm": 0.3716137409210205, "learning_rate": 3.666070342606235e-05, "loss": 4.2984, "step": 11313 }, { "epoch": 0.34557116676847893, "grad_norm": 0.36922550201416016, "learning_rate": 3.665858140815282e-05, "loss": 4.3559, "step": 11314 }, { "epoch": 0.3456017104459377, "grad_norm": 0.38989534974098206, "learning_rate": 3.6656459282896724e-05, "loss": 4.297, "step": 11315 }, { "epoch": 0.34563225412339643, "grad_norm": 0.37591010332107544, "learning_rate": 3.665433705031362e-05, "loss": 4.2543, "step": 11316 }, { "epoch": 0.34566279780085524, "grad_norm": 0.3741610050201416, "learning_rate": 3.6652214710423046e-05, "loss": 4.2768, "step": 11317 }, { "epoch": 0.345693341478314, "grad_norm": 0.37465402483940125, "learning_rate": 3.665009226324453e-05, "loss": 4.3105, "step": 11318 }, { "epoch": 0.34572388515577274, "grad_norm": 0.385413259267807, "learning_rate": 3.664796970879764e-05, "loss": 4.353, "step": 11319 }, { "epoch": 0.34575442883323154, "grad_norm": 0.40352773666381836, "learning_rate": 3.664584704710189e-05, "loss": 4.3825, "step": 11320 }, { "epoch": 0.3457849725106903, "grad_norm": 0.37929511070251465, "learning_rate": 3.664372427817685e-05, "loss": 4.3185, "step": 11321 }, { "epoch": 0.34581551618814904, "grad_norm": 0.3793031573295593, "learning_rate": 3.664160140204205e-05, "loss": 4.3383, "step": 11322 }, { "epoch": 0.34584605986560785, "grad_norm": 0.4004158079624176, "learning_rate": 3.663947841871703e-05, "loss": 4.2723, "step": 11323 }, { "epoch": 0.3458766035430666, "grad_norm": 0.3845061659812927, "learning_rate": 3.663735532822136e-05, "loss": 4.3655, "step": 11324 }, { "epoch": 0.34590714722052535, "grad_norm": 0.3817105293273926, "learning_rate": 3.663523213057457e-05, "loss": 4.3412, "step": 11325 }, { "epoch": 0.3459376908979841, "grad_norm": 0.37128713726997375, "learning_rate": 3.6633108825796214e-05, "loss": 4.379, "step": 11326 }, { "epoch": 0.3459682345754429, "grad_norm": 0.3735353946685791, "learning_rate": 3.663098541390585e-05, "loss": 4.2283, "step": 11327 }, { "epoch": 0.34599877825290165, "grad_norm": 0.375605970621109, "learning_rate": 3.662886189492302e-05, "loss": 4.3452, "step": 11328 }, { "epoch": 0.3460293219303604, "grad_norm": 0.3830678164958954, "learning_rate": 3.662673826886728e-05, "loss": 4.3056, "step": 11329 }, { "epoch": 0.3460598656078192, "grad_norm": 0.3837546110153198, "learning_rate": 3.6624614535758185e-05, "loss": 4.2851, "step": 11330 }, { "epoch": 0.34609040928527796, "grad_norm": 0.3812779486179352, "learning_rate": 3.662249069561529e-05, "loss": 4.2614, "step": 11331 }, { "epoch": 0.3461209529627367, "grad_norm": 0.38932085037231445, "learning_rate": 3.662036674845813e-05, "loss": 4.3374, "step": 11332 }, { "epoch": 0.34615149664019546, "grad_norm": 0.37352731823921204, "learning_rate": 3.6618242694306296e-05, "loss": 4.343, "step": 11333 }, { "epoch": 0.34618204031765426, "grad_norm": 0.37846237421035767, "learning_rate": 3.661611853317932e-05, "loss": 4.3738, "step": 11334 }, { "epoch": 0.346212583995113, "grad_norm": 0.3852069675922394, "learning_rate": 3.661399426509678e-05, "loss": 4.2727, "step": 11335 }, { "epoch": 0.34624312767257176, "grad_norm": 0.3821965456008911, "learning_rate": 3.6611869890078216e-05, "loss": 4.3171, "step": 11336 }, { "epoch": 0.34627367135003057, "grad_norm": 0.38095980882644653, "learning_rate": 3.660974540814319e-05, "loss": 4.2931, "step": 11337 }, { "epoch": 0.3463042150274893, "grad_norm": 0.38494113087654114, "learning_rate": 3.660762081931127e-05, "loss": 4.3132, "step": 11338 }, { "epoch": 0.34633475870494806, "grad_norm": 0.3904445767402649, "learning_rate": 3.660549612360203e-05, "loss": 4.3181, "step": 11339 }, { "epoch": 0.3463653023824068, "grad_norm": 0.38643527030944824, "learning_rate": 3.6603371321035004e-05, "loss": 4.2937, "step": 11340 }, { "epoch": 0.3463958460598656, "grad_norm": 0.396014004945755, "learning_rate": 3.660124641162978e-05, "loss": 4.3408, "step": 11341 }, { "epoch": 0.34642638973732437, "grad_norm": 0.3786205053329468, "learning_rate": 3.6599121395405914e-05, "loss": 4.3189, "step": 11342 }, { "epoch": 0.3464569334147831, "grad_norm": 0.3831437826156616, "learning_rate": 3.659699627238298e-05, "loss": 4.3424, "step": 11343 }, { "epoch": 0.3464874770922419, "grad_norm": 0.3936311900615692, "learning_rate": 3.659487104258053e-05, "loss": 4.378, "step": 11344 }, { "epoch": 0.3465180207697007, "grad_norm": 0.37719643115997314, "learning_rate": 3.659274570601815e-05, "loss": 4.2649, "step": 11345 }, { "epoch": 0.3465485644471594, "grad_norm": 0.3751769959926605, "learning_rate": 3.659062026271539e-05, "loss": 4.3658, "step": 11346 }, { "epoch": 0.34657910812461823, "grad_norm": 0.40179336071014404, "learning_rate": 3.6588494712691835e-05, "loss": 4.3535, "step": 11347 }, { "epoch": 0.346609651802077, "grad_norm": 0.37877920269966125, "learning_rate": 3.6586369055967046e-05, "loss": 4.114, "step": 11348 }, { "epoch": 0.34664019547953573, "grad_norm": 0.3905828893184662, "learning_rate": 3.6584243292560605e-05, "loss": 4.4121, "step": 11349 }, { "epoch": 0.3466707391569945, "grad_norm": 0.38793841004371643, "learning_rate": 3.658211742249208e-05, "loss": 4.3135, "step": 11350 }, { "epoch": 0.3467012828344533, "grad_norm": 0.39340677857398987, "learning_rate": 3.657999144578105e-05, "loss": 4.2909, "step": 11351 }, { "epoch": 0.34673182651191203, "grad_norm": 0.39680013060569763, "learning_rate": 3.657786536244707e-05, "loss": 4.3608, "step": 11352 }, { "epoch": 0.3467623701893708, "grad_norm": 0.3890434503555298, "learning_rate": 3.657573917250975e-05, "loss": 4.3345, "step": 11353 }, { "epoch": 0.3467929138668296, "grad_norm": 0.38123461604118347, "learning_rate": 3.657361287598863e-05, "loss": 4.3241, "step": 11354 }, { "epoch": 0.34682345754428834, "grad_norm": 0.3930378258228302, "learning_rate": 3.6571486472903315e-05, "loss": 4.1705, "step": 11355 }, { "epoch": 0.3468540012217471, "grad_norm": 0.3845456838607788, "learning_rate": 3.656935996327337e-05, "loss": 4.3105, "step": 11356 }, { "epoch": 0.34688454489920584, "grad_norm": 0.38933539390563965, "learning_rate": 3.6567233347118386e-05, "loss": 4.2893, "step": 11357 }, { "epoch": 0.34691508857666464, "grad_norm": 0.39859315752983093, "learning_rate": 3.656510662445793e-05, "loss": 4.3943, "step": 11358 }, { "epoch": 0.3469456322541234, "grad_norm": 0.3950563967227936, "learning_rate": 3.6562979795311596e-05, "loss": 4.3872, "step": 11359 }, { "epoch": 0.34697617593158214, "grad_norm": 0.3922472894191742, "learning_rate": 3.656085285969896e-05, "loss": 4.357, "step": 11360 }, { "epoch": 0.34700671960904095, "grad_norm": 0.3893844783306122, "learning_rate": 3.6558725817639604e-05, "loss": 4.256, "step": 11361 }, { "epoch": 0.3470372632864997, "grad_norm": 0.38079574704170227, "learning_rate": 3.6556598669153124e-05, "loss": 4.3703, "step": 11362 }, { "epoch": 0.34706780696395845, "grad_norm": 0.3818380534648895, "learning_rate": 3.655447141425909e-05, "loss": 4.3328, "step": 11363 }, { "epoch": 0.34709835064141725, "grad_norm": 0.3789111077785492, "learning_rate": 3.6552344052977106e-05, "loss": 4.3468, "step": 11364 }, { "epoch": 0.347128894318876, "grad_norm": 0.3842616379261017, "learning_rate": 3.655021658532675e-05, "loss": 4.3198, "step": 11365 }, { "epoch": 0.34715943799633475, "grad_norm": 0.3799876570701599, "learning_rate": 3.65480890113276e-05, "loss": 4.3446, "step": 11366 }, { "epoch": 0.3471899816737935, "grad_norm": 0.40025240182876587, "learning_rate": 3.654596133099928e-05, "loss": 4.2865, "step": 11367 }, { "epoch": 0.3472205253512523, "grad_norm": 0.3920329213142395, "learning_rate": 3.6543833544361334e-05, "loss": 4.3758, "step": 11368 }, { "epoch": 0.34725106902871106, "grad_norm": 0.39295467734336853, "learning_rate": 3.654170565143339e-05, "loss": 4.3246, "step": 11369 }, { "epoch": 0.3472816127061698, "grad_norm": 0.38226938247680664, "learning_rate": 3.653957765223502e-05, "loss": 4.3717, "step": 11370 }, { "epoch": 0.3473121563836286, "grad_norm": 0.4134790599346161, "learning_rate": 3.653744954678583e-05, "loss": 4.3153, "step": 11371 }, { "epoch": 0.34734270006108736, "grad_norm": 0.37918126583099365, "learning_rate": 3.653532133510541e-05, "loss": 4.3069, "step": 11372 }, { "epoch": 0.3473732437385461, "grad_norm": 0.3826363980770111, "learning_rate": 3.6533193017213355e-05, "loss": 4.3518, "step": 11373 }, { "epoch": 0.34740378741600486, "grad_norm": 0.37699270248413086, "learning_rate": 3.653106459312926e-05, "loss": 4.2214, "step": 11374 }, { "epoch": 0.34743433109346367, "grad_norm": 0.3974173069000244, "learning_rate": 3.652893606287273e-05, "loss": 4.3605, "step": 11375 }, { "epoch": 0.3474648747709224, "grad_norm": 0.38093098998069763, "learning_rate": 3.652680742646336e-05, "loss": 4.2956, "step": 11376 }, { "epoch": 0.34749541844838117, "grad_norm": 0.37477004528045654, "learning_rate": 3.652467868392074e-05, "loss": 4.3823, "step": 11377 }, { "epoch": 0.34752596212583997, "grad_norm": 0.37698274850845337, "learning_rate": 3.652254983526448e-05, "loss": 4.3838, "step": 11378 }, { "epoch": 0.3475565058032987, "grad_norm": 0.3888455927371979, "learning_rate": 3.652042088051417e-05, "loss": 4.3338, "step": 11379 }, { "epoch": 0.34758704948075747, "grad_norm": 0.3843234181404114, "learning_rate": 3.651829181968944e-05, "loss": 4.2223, "step": 11380 }, { "epoch": 0.3476175931582163, "grad_norm": 0.3828514814376831, "learning_rate": 3.651616265280986e-05, "loss": 4.2363, "step": 11381 }, { "epoch": 0.347648136835675, "grad_norm": 0.3904740512371063, "learning_rate": 3.651403337989506e-05, "loss": 4.3205, "step": 11382 }, { "epoch": 0.3476786805131338, "grad_norm": 0.3849189877510071, "learning_rate": 3.651190400096463e-05, "loss": 4.3088, "step": 11383 }, { "epoch": 0.3477092241905925, "grad_norm": 0.3637043237686157, "learning_rate": 3.6509774516038184e-05, "loss": 4.3541, "step": 11384 }, { "epoch": 0.34773976786805133, "grad_norm": 0.3958967626094818, "learning_rate": 3.650764492513532e-05, "loss": 4.2737, "step": 11385 }, { "epoch": 0.3477703115455101, "grad_norm": 0.39299219846725464, "learning_rate": 3.6505515228275656e-05, "loss": 4.2622, "step": 11386 }, { "epoch": 0.34780085522296883, "grad_norm": 0.3878558576107025, "learning_rate": 3.65033854254788e-05, "loss": 4.3636, "step": 11387 }, { "epoch": 0.34783139890042764, "grad_norm": 0.38648808002471924, "learning_rate": 3.650125551676435e-05, "loss": 4.266, "step": 11388 }, { "epoch": 0.3478619425778864, "grad_norm": 0.38322514295578003, "learning_rate": 3.649912550215194e-05, "loss": 4.3434, "step": 11389 }, { "epoch": 0.34789248625534513, "grad_norm": 0.38473600149154663, "learning_rate": 3.6496995381661167e-05, "loss": 4.3117, "step": 11390 }, { "epoch": 0.3479230299328039, "grad_norm": 0.41479066014289856, "learning_rate": 3.649486515531165e-05, "loss": 4.3055, "step": 11391 }, { "epoch": 0.3479535736102627, "grad_norm": 0.3802891671657562, "learning_rate": 3.6492734823122986e-05, "loss": 4.3257, "step": 11392 }, { "epoch": 0.34798411728772144, "grad_norm": 0.39240214228630066, "learning_rate": 3.6490604385114816e-05, "loss": 4.3901, "step": 11393 }, { "epoch": 0.3480146609651802, "grad_norm": 0.38897985219955444, "learning_rate": 3.6488473841306734e-05, "loss": 4.2398, "step": 11394 }, { "epoch": 0.348045204642639, "grad_norm": 0.3752250671386719, "learning_rate": 3.6486343191718367e-05, "loss": 4.1971, "step": 11395 }, { "epoch": 0.34807574832009774, "grad_norm": 0.3796219527721405, "learning_rate": 3.6484212436369336e-05, "loss": 4.3428, "step": 11396 }, { "epoch": 0.3481062919975565, "grad_norm": 0.39813604950904846, "learning_rate": 3.648208157527926e-05, "loss": 4.3928, "step": 11397 }, { "epoch": 0.3481368356750153, "grad_norm": 0.3875215947628021, "learning_rate": 3.647995060846775e-05, "loss": 4.3598, "step": 11398 }, { "epoch": 0.34816737935247405, "grad_norm": 0.37139371037483215, "learning_rate": 3.6477819535954436e-05, "loss": 4.3359, "step": 11399 }, { "epoch": 0.3481979230299328, "grad_norm": 0.3879948556423187, "learning_rate": 3.647568835775894e-05, "loss": 4.264, "step": 11400 }, { "epoch": 0.34822846670739155, "grad_norm": 0.3961273729801178, "learning_rate": 3.647355707390088e-05, "loss": 4.3458, "step": 11401 }, { "epoch": 0.34825901038485035, "grad_norm": 0.4096885621547699, "learning_rate": 3.647142568439987e-05, "loss": 4.1935, "step": 11402 }, { "epoch": 0.3482895540623091, "grad_norm": 0.37624290585517883, "learning_rate": 3.6469294189275547e-05, "loss": 4.3419, "step": 11403 }, { "epoch": 0.34832009773976785, "grad_norm": 0.36974021792411804, "learning_rate": 3.6467162588547546e-05, "loss": 4.3092, "step": 11404 }, { "epoch": 0.34835064141722666, "grad_norm": 0.38629305362701416, "learning_rate": 3.646503088223548e-05, "loss": 4.3066, "step": 11405 }, { "epoch": 0.3483811850946854, "grad_norm": 0.3764021694660187, "learning_rate": 3.646289907035898e-05, "loss": 4.3458, "step": 11406 }, { "epoch": 0.34841172877214416, "grad_norm": 0.3848969042301178, "learning_rate": 3.646076715293767e-05, "loss": 4.358, "step": 11407 }, { "epoch": 0.3484422724496029, "grad_norm": 0.3736945390701294, "learning_rate": 3.645863512999119e-05, "loss": 4.2579, "step": 11408 }, { "epoch": 0.3484728161270617, "grad_norm": 0.37754297256469727, "learning_rate": 3.6456503001539154e-05, "loss": 4.3936, "step": 11409 }, { "epoch": 0.34850335980452046, "grad_norm": 0.3745085299015045, "learning_rate": 3.645437076760122e-05, "loss": 4.3716, "step": 11410 }, { "epoch": 0.3485339034819792, "grad_norm": 0.3989584743976593, "learning_rate": 3.6452238428196995e-05, "loss": 4.3142, "step": 11411 }, { "epoch": 0.348564447159438, "grad_norm": 0.3852628767490387, "learning_rate": 3.645010598334612e-05, "loss": 4.2645, "step": 11412 }, { "epoch": 0.34859499083689677, "grad_norm": 0.3842942714691162, "learning_rate": 3.644797343306825e-05, "loss": 4.3619, "step": 11413 }, { "epoch": 0.3486255345143555, "grad_norm": 0.3803640604019165, "learning_rate": 3.644584077738299e-05, "loss": 4.3437, "step": 11414 }, { "epoch": 0.34865607819181427, "grad_norm": 0.38158118724823, "learning_rate": 3.6443708016309985e-05, "loss": 4.3829, "step": 11415 }, { "epoch": 0.3486866218692731, "grad_norm": 0.3956766128540039, "learning_rate": 3.644157514986888e-05, "loss": 4.3559, "step": 11416 }, { "epoch": 0.3487171655467318, "grad_norm": 0.39448291063308716, "learning_rate": 3.643944217807931e-05, "loss": 4.3411, "step": 11417 }, { "epoch": 0.34874770922419057, "grad_norm": 0.37931695580482483, "learning_rate": 3.6437309100960915e-05, "loss": 4.4122, "step": 11418 }, { "epoch": 0.3487782529016494, "grad_norm": 0.375252902507782, "learning_rate": 3.6435175918533334e-05, "loss": 4.2613, "step": 11419 }, { "epoch": 0.3488087965791081, "grad_norm": 0.36975282430648804, "learning_rate": 3.64330426308162e-05, "loss": 4.2927, "step": 11420 }, { "epoch": 0.3488393402565669, "grad_norm": 0.37616977095603943, "learning_rate": 3.643090923782918e-05, "loss": 4.295, "step": 11421 }, { "epoch": 0.3488698839340257, "grad_norm": 0.3675537407398224, "learning_rate": 3.64287757395919e-05, "loss": 4.3434, "step": 11422 }, { "epoch": 0.34890042761148443, "grad_norm": 0.36774569749832153, "learning_rate": 3.6426642136124e-05, "loss": 4.2405, "step": 11423 }, { "epoch": 0.3489309712889432, "grad_norm": 0.36905214190483093, "learning_rate": 3.642450842744513e-05, "loss": 4.355, "step": 11424 }, { "epoch": 0.34896151496640193, "grad_norm": 0.37365901470184326, "learning_rate": 3.642237461357494e-05, "loss": 4.2847, "step": 11425 }, { "epoch": 0.34899205864386074, "grad_norm": 0.36512452363967896, "learning_rate": 3.642024069453307e-05, "loss": 4.309, "step": 11426 }, { "epoch": 0.3490226023213195, "grad_norm": 0.36661726236343384, "learning_rate": 3.641810667033918e-05, "loss": 4.2523, "step": 11427 }, { "epoch": 0.34905314599877824, "grad_norm": 0.37285059690475464, "learning_rate": 3.64159725410129e-05, "loss": 4.3438, "step": 11428 }, { "epoch": 0.34908368967623704, "grad_norm": 0.40562334656715393, "learning_rate": 3.64138383065739e-05, "loss": 4.3191, "step": 11429 }, { "epoch": 0.3491142333536958, "grad_norm": 0.3745434582233429, "learning_rate": 3.641170396704182e-05, "loss": 4.3712, "step": 11430 }, { "epoch": 0.34914477703115454, "grad_norm": 0.37841060757637024, "learning_rate": 3.6409569522436315e-05, "loss": 4.2377, "step": 11431 }, { "epoch": 0.3491753207086133, "grad_norm": 0.3621341288089752, "learning_rate": 3.640743497277704e-05, "loss": 4.3692, "step": 11432 }, { "epoch": 0.3492058643860721, "grad_norm": 0.38019564747810364, "learning_rate": 3.6405300318083635e-05, "loss": 4.3378, "step": 11433 }, { "epoch": 0.34923640806353085, "grad_norm": 0.394336998462677, "learning_rate": 3.6403165558375776e-05, "loss": 4.3009, "step": 11434 }, { "epoch": 0.3492669517409896, "grad_norm": 0.38619720935821533, "learning_rate": 3.640103069367311e-05, "loss": 4.3617, "step": 11435 }, { "epoch": 0.3492974954184484, "grad_norm": 0.3803074359893799, "learning_rate": 3.639889572399529e-05, "loss": 4.3405, "step": 11436 }, { "epoch": 0.34932803909590715, "grad_norm": 0.3738940358161926, "learning_rate": 3.6396760649361974e-05, "loss": 4.337, "step": 11437 }, { "epoch": 0.3493585827733659, "grad_norm": 0.3747975528240204, "learning_rate": 3.639462546979282e-05, "loss": 4.3509, "step": 11438 }, { "epoch": 0.3493891264508247, "grad_norm": 0.3822539448738098, "learning_rate": 3.639249018530749e-05, "loss": 4.2857, "step": 11439 }, { "epoch": 0.34941967012828345, "grad_norm": 0.3796016275882721, "learning_rate": 3.639035479592565e-05, "loss": 4.3708, "step": 11440 }, { "epoch": 0.3494502138057422, "grad_norm": 0.3728255033493042, "learning_rate": 3.6388219301666966e-05, "loss": 4.3258, "step": 11441 }, { "epoch": 0.34948075748320095, "grad_norm": 0.38274720311164856, "learning_rate": 3.638608370255108e-05, "loss": 4.3687, "step": 11442 }, { "epoch": 0.34951130116065976, "grad_norm": 0.3785155415534973, "learning_rate": 3.6383947998597666e-05, "loss": 4.3616, "step": 11443 }, { "epoch": 0.3495418448381185, "grad_norm": 0.377017080783844, "learning_rate": 3.638181218982639e-05, "loss": 4.2961, "step": 11444 }, { "epoch": 0.34957238851557726, "grad_norm": 0.3804819583892822, "learning_rate": 3.637967627625694e-05, "loss": 4.3236, "step": 11445 }, { "epoch": 0.34960293219303606, "grad_norm": 0.3822551369667053, "learning_rate": 3.6377540257908927e-05, "loss": 4.3679, "step": 11446 }, { "epoch": 0.3496334758704948, "grad_norm": 0.3824303150177002, "learning_rate": 3.637540413480206e-05, "loss": 4.3092, "step": 11447 }, { "epoch": 0.34966401954795356, "grad_norm": 0.3692912757396698, "learning_rate": 3.637326790695601e-05, "loss": 4.2394, "step": 11448 }, { "epoch": 0.3496945632254123, "grad_norm": 0.3749457597732544, "learning_rate": 3.6371131574390436e-05, "loss": 4.399, "step": 11449 }, { "epoch": 0.3497251069028711, "grad_norm": 0.3819029629230499, "learning_rate": 3.636899513712499e-05, "loss": 4.3083, "step": 11450 }, { "epoch": 0.34975565058032987, "grad_norm": 0.37843698263168335, "learning_rate": 3.636685859517937e-05, "loss": 4.3206, "step": 11451 }, { "epoch": 0.3497861942577886, "grad_norm": 0.3731136620044708, "learning_rate": 3.6364721948573236e-05, "loss": 4.3197, "step": 11452 }, { "epoch": 0.3498167379352474, "grad_norm": 0.39149215817451477, "learning_rate": 3.636258519732627e-05, "loss": 4.2555, "step": 11453 }, { "epoch": 0.3498472816127062, "grad_norm": 0.3819781243801117, "learning_rate": 3.6360448341458134e-05, "loss": 4.3377, "step": 11454 }, { "epoch": 0.3498778252901649, "grad_norm": 0.3777129650115967, "learning_rate": 3.635831138098852e-05, "loss": 4.3833, "step": 11455 }, { "epoch": 0.34990836896762373, "grad_norm": 0.38175734877586365, "learning_rate": 3.6356174315937074e-05, "loss": 4.3505, "step": 11456 }, { "epoch": 0.3499389126450825, "grad_norm": 0.3895328640937805, "learning_rate": 3.6354037146323504e-05, "loss": 4.3633, "step": 11457 }, { "epoch": 0.34996945632254123, "grad_norm": 0.3726264238357544, "learning_rate": 3.6351899872167475e-05, "loss": 4.3557, "step": 11458 }, { "epoch": 0.35, "grad_norm": 0.3890838921070099, "learning_rate": 3.634976249348867e-05, "loss": 4.3451, "step": 11459 }, { "epoch": 0.3500305436774588, "grad_norm": 0.37181398272514343, "learning_rate": 3.634762501030677e-05, "loss": 4.3697, "step": 11460 }, { "epoch": 0.35006108735491753, "grad_norm": 0.37784233689308167, "learning_rate": 3.6345487422641445e-05, "loss": 4.3956, "step": 11461 }, { "epoch": 0.3500916310323763, "grad_norm": 0.38105812668800354, "learning_rate": 3.634334973051239e-05, "loss": 4.2818, "step": 11462 }, { "epoch": 0.3501221747098351, "grad_norm": 0.37833482027053833, "learning_rate": 3.634121193393927e-05, "loss": 4.2811, "step": 11463 }, { "epoch": 0.35015271838729384, "grad_norm": 0.3880592882633209, "learning_rate": 3.633907403294179e-05, "loss": 4.3853, "step": 11464 }, { "epoch": 0.3501832620647526, "grad_norm": 0.39075320959091187, "learning_rate": 3.633693602753962e-05, "loss": 4.3184, "step": 11465 }, { "epoch": 0.35021380574221134, "grad_norm": 0.3795863389968872, "learning_rate": 3.6334797917752455e-05, "loss": 4.3468, "step": 11466 }, { "epoch": 0.35024434941967014, "grad_norm": 0.36965563893318176, "learning_rate": 3.633265970359997e-05, "loss": 4.2095, "step": 11467 }, { "epoch": 0.3502748930971289, "grad_norm": 0.37518900632858276, "learning_rate": 3.633052138510188e-05, "loss": 4.2548, "step": 11468 }, { "epoch": 0.35030543677458764, "grad_norm": 0.37625300884246826, "learning_rate": 3.632838296227784e-05, "loss": 4.3556, "step": 11469 }, { "epoch": 0.35033598045204645, "grad_norm": 0.3828204870223999, "learning_rate": 3.632624443514755e-05, "loss": 4.2648, "step": 11470 }, { "epoch": 0.3503665241295052, "grad_norm": 0.39184871315956116, "learning_rate": 3.6324105803730706e-05, "loss": 4.385, "step": 11471 }, { "epoch": 0.35039706780696395, "grad_norm": 0.3753374218940735, "learning_rate": 3.6321967068047e-05, "loss": 4.2986, "step": 11472 }, { "epoch": 0.35042761148442275, "grad_norm": 0.37839844822883606, "learning_rate": 3.6319828228116124e-05, "loss": 4.3677, "step": 11473 }, { "epoch": 0.3504581551618815, "grad_norm": 0.38099944591522217, "learning_rate": 3.631768928395777e-05, "loss": 4.3515, "step": 11474 }, { "epoch": 0.35048869883934025, "grad_norm": 0.3925306499004364, "learning_rate": 3.631555023559163e-05, "loss": 4.3192, "step": 11475 }, { "epoch": 0.350519242516799, "grad_norm": 0.37300434708595276, "learning_rate": 3.6313411083037405e-05, "loss": 4.3809, "step": 11476 }, { "epoch": 0.3505497861942578, "grad_norm": 0.381997674703598, "learning_rate": 3.631127182631478e-05, "loss": 4.3145, "step": 11477 }, { "epoch": 0.35058032987171656, "grad_norm": 0.3830527365207672, "learning_rate": 3.630913246544346e-05, "loss": 4.3581, "step": 11478 }, { "epoch": 0.3506108735491753, "grad_norm": 0.39441704750061035, "learning_rate": 3.630699300044315e-05, "loss": 4.3227, "step": 11479 }, { "epoch": 0.3506414172266341, "grad_norm": 0.3642078936100006, "learning_rate": 3.6304853431333534e-05, "loss": 4.3464, "step": 11480 }, { "epoch": 0.35067196090409286, "grad_norm": 0.37386199831962585, "learning_rate": 3.630271375813432e-05, "loss": 4.2599, "step": 11481 }, { "epoch": 0.3507025045815516, "grad_norm": 0.3730279803276062, "learning_rate": 3.630057398086522e-05, "loss": 4.3373, "step": 11482 }, { "epoch": 0.35073304825901036, "grad_norm": 0.3801151514053345, "learning_rate": 3.629843409954592e-05, "loss": 4.3907, "step": 11483 }, { "epoch": 0.35076359193646917, "grad_norm": 0.37941205501556396, "learning_rate": 3.6296294114196125e-05, "loss": 4.3367, "step": 11484 }, { "epoch": 0.3507941356139279, "grad_norm": 0.3761518895626068, "learning_rate": 3.6294154024835544e-05, "loss": 4.3636, "step": 11485 }, { "epoch": 0.35082467929138667, "grad_norm": 0.37185683846473694, "learning_rate": 3.629201383148388e-05, "loss": 4.2347, "step": 11486 }, { "epoch": 0.35085522296884547, "grad_norm": 0.3751973807811737, "learning_rate": 3.6289873534160836e-05, "loss": 4.316, "step": 11487 }, { "epoch": 0.3508857666463042, "grad_norm": 0.3777065873146057, "learning_rate": 3.6287733132886125e-05, "loss": 4.3496, "step": 11488 }, { "epoch": 0.35091631032376297, "grad_norm": 0.3704730272293091, "learning_rate": 3.628559262767945e-05, "loss": 4.3331, "step": 11489 }, { "epoch": 0.3509468540012217, "grad_norm": 0.37690219283103943, "learning_rate": 3.628345201856052e-05, "loss": 4.3777, "step": 11490 }, { "epoch": 0.3509773976786805, "grad_norm": 0.37287184596061707, "learning_rate": 3.628131130554905e-05, "loss": 4.3316, "step": 11491 }, { "epoch": 0.3510079413561393, "grad_norm": 0.37549692392349243, "learning_rate": 3.627917048866474e-05, "loss": 4.3825, "step": 11492 }, { "epoch": 0.351038485033598, "grad_norm": 0.3990239202976227, "learning_rate": 3.6277029567927315e-05, "loss": 4.3371, "step": 11493 }, { "epoch": 0.35106902871105683, "grad_norm": 0.3830617666244507, "learning_rate": 3.627488854335648e-05, "loss": 4.3006, "step": 11494 }, { "epoch": 0.3510995723885156, "grad_norm": 0.38424280285835266, "learning_rate": 3.627274741497194e-05, "loss": 4.3008, "step": 11495 }, { "epoch": 0.35113011606597433, "grad_norm": 0.382831335067749, "learning_rate": 3.627060618279343e-05, "loss": 4.3135, "step": 11496 }, { "epoch": 0.35116065974343313, "grad_norm": 0.37586531043052673, "learning_rate": 3.6268464846840645e-05, "loss": 4.3332, "step": 11497 }, { "epoch": 0.3511912034208919, "grad_norm": 0.3771360218524933, "learning_rate": 3.6266323407133316e-05, "loss": 4.2855, "step": 11498 }, { "epoch": 0.35122174709835063, "grad_norm": 0.37782371044158936, "learning_rate": 3.626418186369116e-05, "loss": 4.3758, "step": 11499 }, { "epoch": 0.3512522907758094, "grad_norm": 0.38015028834342957, "learning_rate": 3.6262040216533885e-05, "loss": 4.3024, "step": 11500 }, { "epoch": 0.3512828344532682, "grad_norm": 0.386277973651886, "learning_rate": 3.6259898465681214e-05, "loss": 4.322, "step": 11501 }, { "epoch": 0.35131337813072694, "grad_norm": 0.3833402395248413, "learning_rate": 3.625775661115287e-05, "loss": 4.3563, "step": 11502 }, { "epoch": 0.3513439218081857, "grad_norm": 0.36829453706741333, "learning_rate": 3.6255614652968575e-05, "loss": 4.2874, "step": 11503 }, { "epoch": 0.3513744654856445, "grad_norm": 0.378144234418869, "learning_rate": 3.625347259114804e-05, "loss": 4.3019, "step": 11504 }, { "epoch": 0.35140500916310324, "grad_norm": 0.3809060752391815, "learning_rate": 3.6251330425711006e-05, "loss": 4.2799, "step": 11505 }, { "epoch": 0.351435552840562, "grad_norm": 0.4539368748664856, "learning_rate": 3.624918815667718e-05, "loss": 4.3258, "step": 11506 }, { "epoch": 0.35146609651802074, "grad_norm": 0.38685569167137146, "learning_rate": 3.6247045784066304e-05, "loss": 4.2504, "step": 11507 }, { "epoch": 0.35149664019547955, "grad_norm": 0.3760767877101898, "learning_rate": 3.6244903307898086e-05, "loss": 4.3758, "step": 11508 }, { "epoch": 0.3515271838729383, "grad_norm": 0.3743683993816376, "learning_rate": 3.624276072819227e-05, "loss": 4.3377, "step": 11509 }, { "epoch": 0.35155772755039705, "grad_norm": 0.38419461250305176, "learning_rate": 3.624061804496857e-05, "loss": 4.382, "step": 11510 }, { "epoch": 0.35158827122785585, "grad_norm": 0.37823405861854553, "learning_rate": 3.623847525824672e-05, "loss": 4.3785, "step": 11511 }, { "epoch": 0.3516188149053146, "grad_norm": 0.3745657205581665, "learning_rate": 3.623633236804645e-05, "loss": 4.312, "step": 11512 }, { "epoch": 0.35164935858277335, "grad_norm": 0.3747103214263916, "learning_rate": 3.6234189374387495e-05, "loss": 4.2902, "step": 11513 }, { "epoch": 0.35167990226023216, "grad_norm": 0.3733382523059845, "learning_rate": 3.6232046277289585e-05, "loss": 4.2906, "step": 11514 }, { "epoch": 0.3517104459376909, "grad_norm": 0.3824218213558197, "learning_rate": 3.622990307677244e-05, "loss": 4.3059, "step": 11515 }, { "epoch": 0.35174098961514966, "grad_norm": 0.38623592257499695, "learning_rate": 3.622775977285581e-05, "loss": 4.2811, "step": 11516 }, { "epoch": 0.3517715332926084, "grad_norm": 0.37060245871543884, "learning_rate": 3.622561636555942e-05, "loss": 4.3701, "step": 11517 }, { "epoch": 0.3518020769700672, "grad_norm": 0.386198490858078, "learning_rate": 3.622347285490301e-05, "loss": 4.355, "step": 11518 }, { "epoch": 0.35183262064752596, "grad_norm": 0.40564388036727905, "learning_rate": 3.622132924090632e-05, "loss": 4.2992, "step": 11519 }, { "epoch": 0.3518631643249847, "grad_norm": 0.3903542459011078, "learning_rate": 3.621918552358907e-05, "loss": 4.328, "step": 11520 }, { "epoch": 0.3518937080024435, "grad_norm": 0.38277682662010193, "learning_rate": 3.6217041702971015e-05, "loss": 4.2681, "step": 11521 }, { "epoch": 0.35192425167990227, "grad_norm": 0.3911685049533844, "learning_rate": 3.621489777907189e-05, "loss": 4.363, "step": 11522 }, { "epoch": 0.351954795357361, "grad_norm": 0.38852110505104065, "learning_rate": 3.621275375191145e-05, "loss": 4.3545, "step": 11523 }, { "epoch": 0.35198533903481977, "grad_norm": 0.38907739520072937, "learning_rate": 3.621060962150941e-05, "loss": 4.2893, "step": 11524 }, { "epoch": 0.35201588271227857, "grad_norm": 0.3926891088485718, "learning_rate": 3.620846538788551e-05, "loss": 4.3427, "step": 11525 }, { "epoch": 0.3520464263897373, "grad_norm": 0.3905818462371826, "learning_rate": 3.620632105105952e-05, "loss": 4.3261, "step": 11526 }, { "epoch": 0.35207697006719607, "grad_norm": 0.3870120346546173, "learning_rate": 3.6204176611051177e-05, "loss": 4.3153, "step": 11527 }, { "epoch": 0.3521075137446549, "grad_norm": 0.38947319984436035, "learning_rate": 3.62020320678802e-05, "loss": 4.3516, "step": 11528 }, { "epoch": 0.3521380574221136, "grad_norm": 0.3822344243526459, "learning_rate": 3.619988742156637e-05, "loss": 4.329, "step": 11529 }, { "epoch": 0.3521686010995724, "grad_norm": 0.3846587836742401, "learning_rate": 3.6197742672129414e-05, "loss": 4.3907, "step": 11530 }, { "epoch": 0.3521991447770312, "grad_norm": 0.3764711916446686, "learning_rate": 3.619559781958908e-05, "loss": 4.2991, "step": 11531 }, { "epoch": 0.35222968845448993, "grad_norm": 0.3627208471298218, "learning_rate": 3.619345286396513e-05, "loss": 4.3219, "step": 11532 }, { "epoch": 0.3522602321319487, "grad_norm": 0.3884298503398895, "learning_rate": 3.61913078052773e-05, "loss": 4.4234, "step": 11533 }, { "epoch": 0.35229077580940743, "grad_norm": 0.3853296637535095, "learning_rate": 3.618916264354534e-05, "loss": 4.3143, "step": 11534 }, { "epoch": 0.35232131948686624, "grad_norm": 0.3783392012119293, "learning_rate": 3.618701737878901e-05, "loss": 4.3467, "step": 11535 }, { "epoch": 0.352351863164325, "grad_norm": 0.3844376504421234, "learning_rate": 3.618487201102806e-05, "loss": 4.2656, "step": 11536 }, { "epoch": 0.35238240684178374, "grad_norm": 0.3825908601284027, "learning_rate": 3.618272654028224e-05, "loss": 4.3298, "step": 11537 }, { "epoch": 0.35241295051924254, "grad_norm": 0.3894050717353821, "learning_rate": 3.618058096657131e-05, "loss": 4.3288, "step": 11538 }, { "epoch": 0.3524434941967013, "grad_norm": 0.37347280979156494, "learning_rate": 3.6178435289915025e-05, "loss": 4.2383, "step": 11539 }, { "epoch": 0.35247403787416004, "grad_norm": 0.3810923993587494, "learning_rate": 3.6176289510333134e-05, "loss": 4.3681, "step": 11540 }, { "epoch": 0.3525045815516188, "grad_norm": 0.3761652410030365, "learning_rate": 3.6174143627845406e-05, "loss": 4.3381, "step": 11541 }, { "epoch": 0.3525351252290776, "grad_norm": 0.38570794463157654, "learning_rate": 3.617199764247158e-05, "loss": 4.1565, "step": 11542 }, { "epoch": 0.35256566890653634, "grad_norm": 0.38922932744026184, "learning_rate": 3.616985155423144e-05, "loss": 4.3165, "step": 11543 }, { "epoch": 0.3525962125839951, "grad_norm": 0.3920072019100189, "learning_rate": 3.616770536314472e-05, "loss": 4.3003, "step": 11544 }, { "epoch": 0.3526267562614539, "grad_norm": 0.38688161969184875, "learning_rate": 3.61655590692312e-05, "loss": 4.2486, "step": 11545 }, { "epoch": 0.35265729993891265, "grad_norm": 0.39334893226623535, "learning_rate": 3.616341267251065e-05, "loss": 4.3115, "step": 11546 }, { "epoch": 0.3526878436163714, "grad_norm": 0.3835625648498535, "learning_rate": 3.616126617300281e-05, "loss": 4.3342, "step": 11547 }, { "epoch": 0.3527183872938302, "grad_norm": 0.38263338804244995, "learning_rate": 3.615911957072745e-05, "loss": 4.3525, "step": 11548 }, { "epoch": 0.35274893097128895, "grad_norm": 0.3847258388996124, "learning_rate": 3.615697286570434e-05, "loss": 4.239, "step": 11549 }, { "epoch": 0.3527794746487477, "grad_norm": 0.3858319818973541, "learning_rate": 3.615482605795325e-05, "loss": 4.3405, "step": 11550 }, { "epoch": 0.35281001832620645, "grad_norm": 0.4027693271636963, "learning_rate": 3.615267914749394e-05, "loss": 4.2966, "step": 11551 }, { "epoch": 0.35284056200366526, "grad_norm": 0.37555310130119324, "learning_rate": 3.6150532134346174e-05, "loss": 4.3568, "step": 11552 }, { "epoch": 0.352871105681124, "grad_norm": 0.3673069477081299, "learning_rate": 3.614838501852973e-05, "loss": 4.3487, "step": 11553 }, { "epoch": 0.35290164935858276, "grad_norm": 0.3773822486400604, "learning_rate": 3.614623780006438e-05, "loss": 4.3543, "step": 11554 }, { "epoch": 0.35293219303604156, "grad_norm": 0.3730149269104004, "learning_rate": 3.6144090478969875e-05, "loss": 4.3272, "step": 11555 }, { "epoch": 0.3529627367135003, "grad_norm": 0.3944830596446991, "learning_rate": 3.6141943055266004e-05, "loss": 4.3327, "step": 11556 }, { "epoch": 0.35299328039095906, "grad_norm": 0.3712693154811859, "learning_rate": 3.613979552897254e-05, "loss": 4.2822, "step": 11557 }, { "epoch": 0.3530238240684178, "grad_norm": 0.3853023946285248, "learning_rate": 3.613764790010924e-05, "loss": 4.4531, "step": 11558 }, { "epoch": 0.3530543677458766, "grad_norm": 0.38949349522590637, "learning_rate": 3.613550016869589e-05, "loss": 4.3278, "step": 11559 }, { "epoch": 0.35308491142333537, "grad_norm": 0.3755459189414978, "learning_rate": 3.613335233475228e-05, "loss": 4.3354, "step": 11560 }, { "epoch": 0.3531154551007941, "grad_norm": 0.37674978375434875, "learning_rate": 3.6131204398298156e-05, "loss": 4.3826, "step": 11561 }, { "epoch": 0.3531459987782529, "grad_norm": 0.3867104947566986, "learning_rate": 3.6129056359353314e-05, "loss": 4.3674, "step": 11562 }, { "epoch": 0.3531765424557117, "grad_norm": 0.37964174151420593, "learning_rate": 3.612690821793753e-05, "loss": 4.38, "step": 11563 }, { "epoch": 0.3532070861331704, "grad_norm": 0.3783857822418213, "learning_rate": 3.612475997407058e-05, "loss": 4.3516, "step": 11564 }, { "epoch": 0.3532376298106292, "grad_norm": 0.39840424060821533, "learning_rate": 3.6122611627772244e-05, "loss": 4.3643, "step": 11565 }, { "epoch": 0.353268173488088, "grad_norm": 0.3784151077270508, "learning_rate": 3.6120463179062304e-05, "loss": 4.3015, "step": 11566 }, { "epoch": 0.3532987171655467, "grad_norm": 0.38248658180236816, "learning_rate": 3.611831462796054e-05, "loss": 4.2794, "step": 11567 }, { "epoch": 0.3533292608430055, "grad_norm": 0.387817919254303, "learning_rate": 3.611616597448674e-05, "loss": 4.4027, "step": 11568 }, { "epoch": 0.3533598045204643, "grad_norm": 0.3809382915496826, "learning_rate": 3.611401721866069e-05, "loss": 4.3167, "step": 11569 }, { "epoch": 0.35339034819792303, "grad_norm": 0.37826839089393616, "learning_rate": 3.6111868360502164e-05, "loss": 4.2519, "step": 11570 }, { "epoch": 0.3534208918753818, "grad_norm": 0.3961712419986725, "learning_rate": 3.610971940003095e-05, "loss": 4.3026, "step": 11571 }, { "epoch": 0.3534514355528406, "grad_norm": 0.3894616365432739, "learning_rate": 3.610757033726684e-05, "loss": 4.2243, "step": 11572 }, { "epoch": 0.35348197923029934, "grad_norm": 0.3846542239189148, "learning_rate": 3.6105421172229614e-05, "loss": 4.3296, "step": 11573 }, { "epoch": 0.3535125229077581, "grad_norm": 0.3737572133541107, "learning_rate": 3.610327190493907e-05, "loss": 4.3727, "step": 11574 }, { "epoch": 0.35354306658521684, "grad_norm": 0.38493791222572327, "learning_rate": 3.6101122535415e-05, "loss": 4.2956, "step": 11575 }, { "epoch": 0.35357361026267564, "grad_norm": 0.3808002471923828, "learning_rate": 3.609897306367718e-05, "loss": 4.3126, "step": 11576 }, { "epoch": 0.3536041539401344, "grad_norm": 0.3946625292301178, "learning_rate": 3.60968234897454e-05, "loss": 4.3191, "step": 11577 }, { "epoch": 0.35363469761759314, "grad_norm": 0.3733133375644684, "learning_rate": 3.609467381363948e-05, "loss": 4.2938, "step": 11578 }, { "epoch": 0.35366524129505195, "grad_norm": 0.37020885944366455, "learning_rate": 3.6092524035379176e-05, "loss": 4.3547, "step": 11579 }, { "epoch": 0.3536957849725107, "grad_norm": 0.37513068318367004, "learning_rate": 3.609037415498431e-05, "loss": 4.3384, "step": 11580 }, { "epoch": 0.35372632864996945, "grad_norm": 0.3862781226634979, "learning_rate": 3.608822417247467e-05, "loss": 4.4083, "step": 11581 }, { "epoch": 0.3537568723274282, "grad_norm": 0.3668144941329956, "learning_rate": 3.6086074087870035e-05, "loss": 4.3542, "step": 11582 }, { "epoch": 0.353787416004887, "grad_norm": 0.3742407262325287, "learning_rate": 3.6083923901190226e-05, "loss": 4.2828, "step": 11583 }, { "epoch": 0.35381795968234575, "grad_norm": 0.37246131896972656, "learning_rate": 3.608177361245503e-05, "loss": 4.3184, "step": 11584 }, { "epoch": 0.3538485033598045, "grad_norm": 0.384032666683197, "learning_rate": 3.6079623221684245e-05, "loss": 4.1587, "step": 11585 }, { "epoch": 0.3538790470372633, "grad_norm": 0.3896670937538147, "learning_rate": 3.6077472728897674e-05, "loss": 4.3714, "step": 11586 }, { "epoch": 0.35390959071472206, "grad_norm": 0.38109302520751953, "learning_rate": 3.607532213411512e-05, "loss": 4.2894, "step": 11587 }, { "epoch": 0.3539401343921808, "grad_norm": 0.3765600621700287, "learning_rate": 3.6073171437356375e-05, "loss": 4.3788, "step": 11588 }, { "epoch": 0.3539706780696396, "grad_norm": 0.3755037188529968, "learning_rate": 3.607102063864124e-05, "loss": 4.3434, "step": 11589 }, { "epoch": 0.35400122174709836, "grad_norm": 0.38257214426994324, "learning_rate": 3.6068869737989535e-05, "loss": 4.3605, "step": 11590 }, { "epoch": 0.3540317654245571, "grad_norm": 0.3843649923801422, "learning_rate": 3.6066718735421056e-05, "loss": 4.3712, "step": 11591 }, { "epoch": 0.35406230910201586, "grad_norm": 0.3960540294647217, "learning_rate": 3.606456763095561e-05, "loss": 4.2671, "step": 11592 }, { "epoch": 0.35409285277947466, "grad_norm": 0.3757435977458954, "learning_rate": 3.6062416424613e-05, "loss": 4.2876, "step": 11593 }, { "epoch": 0.3541233964569334, "grad_norm": 0.3747771382331848, "learning_rate": 3.6060265116413025e-05, "loss": 4.2375, "step": 11594 }, { "epoch": 0.35415394013439216, "grad_norm": 0.3827812075614929, "learning_rate": 3.605811370637551e-05, "loss": 4.3918, "step": 11595 }, { "epoch": 0.35418448381185097, "grad_norm": 0.3815864026546478, "learning_rate": 3.6055962194520253e-05, "loss": 4.3478, "step": 11596 }, { "epoch": 0.3542150274893097, "grad_norm": 0.37980034947395325, "learning_rate": 3.605381058086708e-05, "loss": 4.3255, "step": 11597 }, { "epoch": 0.35424557116676847, "grad_norm": 0.3896004855632782, "learning_rate": 3.605165886543577e-05, "loss": 4.368, "step": 11598 }, { "epoch": 0.3542761148442272, "grad_norm": 0.38458251953125, "learning_rate": 3.604950704824617e-05, "loss": 4.2609, "step": 11599 }, { "epoch": 0.354306658521686, "grad_norm": 0.3869820833206177, "learning_rate": 3.6047355129318065e-05, "loss": 4.3656, "step": 11600 }, { "epoch": 0.3543372021991448, "grad_norm": 0.3728727102279663, "learning_rate": 3.604520310867129e-05, "loss": 4.3646, "step": 11601 }, { "epoch": 0.3543677458766035, "grad_norm": 0.3762930929660797, "learning_rate": 3.6043050986325656e-05, "loss": 4.2429, "step": 11602 }, { "epoch": 0.35439828955406233, "grad_norm": 0.3791850805282593, "learning_rate": 3.604089876230096e-05, "loss": 4.3069, "step": 11603 }, { "epoch": 0.3544288332315211, "grad_norm": 0.37927311658859253, "learning_rate": 3.603874643661704e-05, "loss": 4.2197, "step": 11604 }, { "epoch": 0.35445937690897983, "grad_norm": 0.3749944269657135, "learning_rate": 3.603659400929371e-05, "loss": 4.3585, "step": 11605 }, { "epoch": 0.35448992058643863, "grad_norm": 0.3879776895046234, "learning_rate": 3.603444148035078e-05, "loss": 4.3651, "step": 11606 }, { "epoch": 0.3545204642638974, "grad_norm": 0.40679070353507996, "learning_rate": 3.603228884980807e-05, "loss": 4.3617, "step": 11607 }, { "epoch": 0.35455100794135613, "grad_norm": 0.3791145980358124, "learning_rate": 3.603013611768541e-05, "loss": 4.3205, "step": 11608 }, { "epoch": 0.3545815516188149, "grad_norm": 0.38091325759887695, "learning_rate": 3.6027983284002613e-05, "loss": 4.2982, "step": 11609 }, { "epoch": 0.3546120952962737, "grad_norm": 0.3880610167980194, "learning_rate": 3.60258303487795e-05, "loss": 4.2373, "step": 11610 }, { "epoch": 0.35464263897373244, "grad_norm": 0.3800610899925232, "learning_rate": 3.602367731203591e-05, "loss": 4.3116, "step": 11611 }, { "epoch": 0.3546731826511912, "grad_norm": 0.38028484582901, "learning_rate": 3.602152417379165e-05, "loss": 4.3767, "step": 11612 }, { "epoch": 0.35470372632865, "grad_norm": 0.3833942413330078, "learning_rate": 3.6019370934066546e-05, "loss": 4.3493, "step": 11613 }, { "epoch": 0.35473427000610874, "grad_norm": 0.4008159339427948, "learning_rate": 3.6017217592880425e-05, "loss": 4.2781, "step": 11614 }, { "epoch": 0.3547648136835675, "grad_norm": 0.38984188437461853, "learning_rate": 3.601506415025312e-05, "loss": 4.3604, "step": 11615 }, { "epoch": 0.35479535736102624, "grad_norm": 0.38386446237564087, "learning_rate": 3.601291060620446e-05, "loss": 4.3733, "step": 11616 }, { "epoch": 0.35482590103848505, "grad_norm": 0.37943676114082336, "learning_rate": 3.601075696075428e-05, "loss": 4.2827, "step": 11617 }, { "epoch": 0.3548564447159438, "grad_norm": 0.40204131603240967, "learning_rate": 3.600860321392239e-05, "loss": 4.3551, "step": 11618 }, { "epoch": 0.35488698839340255, "grad_norm": 0.39248156547546387, "learning_rate": 3.600644936572862e-05, "loss": 4.2758, "step": 11619 }, { "epoch": 0.35491753207086135, "grad_norm": 0.3759658634662628, "learning_rate": 3.600429541619282e-05, "loss": 4.3014, "step": 11620 }, { "epoch": 0.3549480757483201, "grad_norm": 0.3725275993347168, "learning_rate": 3.6002141365334815e-05, "loss": 4.3151, "step": 11621 }, { "epoch": 0.35497861942577885, "grad_norm": 0.38412290811538696, "learning_rate": 3.5999987213174434e-05, "loss": 4.3408, "step": 11622 }, { "epoch": 0.35500916310323766, "grad_norm": 0.3890344202518463, "learning_rate": 3.599783295973151e-05, "loss": 4.457, "step": 11623 }, { "epoch": 0.3550397067806964, "grad_norm": 0.38887882232666016, "learning_rate": 3.59956786050259e-05, "loss": 4.3174, "step": 11624 }, { "epoch": 0.35507025045815516, "grad_norm": 0.37117958068847656, "learning_rate": 3.599352414907742e-05, "loss": 4.2767, "step": 11625 }, { "epoch": 0.3551007941356139, "grad_norm": 0.3763509690761566, "learning_rate": 3.59913695919059e-05, "loss": 4.3537, "step": 11626 }, { "epoch": 0.3551313378130727, "grad_norm": 0.37939807772636414, "learning_rate": 3.5989214933531195e-05, "loss": 4.2316, "step": 11627 }, { "epoch": 0.35516188149053146, "grad_norm": 0.3807167112827301, "learning_rate": 3.5987060173973144e-05, "loss": 4.2667, "step": 11628 }, { "epoch": 0.3551924251679902, "grad_norm": 0.42674535512924194, "learning_rate": 3.598490531325157e-05, "loss": 4.3566, "step": 11629 }, { "epoch": 0.355222968845449, "grad_norm": 0.3761453628540039, "learning_rate": 3.5982750351386326e-05, "loss": 4.3385, "step": 11630 }, { "epoch": 0.35525351252290777, "grad_norm": 0.3802832365036011, "learning_rate": 3.5980595288397255e-05, "loss": 4.3743, "step": 11631 }, { "epoch": 0.3552840562003665, "grad_norm": 0.3886650502681732, "learning_rate": 3.59784401243042e-05, "loss": 4.3663, "step": 11632 }, { "epoch": 0.35531459987782527, "grad_norm": 0.4033145308494568, "learning_rate": 3.5976284859127005e-05, "loss": 4.3741, "step": 11633 }, { "epoch": 0.35534514355528407, "grad_norm": 0.38550126552581787, "learning_rate": 3.597412949288551e-05, "loss": 4.3045, "step": 11634 }, { "epoch": 0.3553756872327428, "grad_norm": 0.3851713240146637, "learning_rate": 3.597197402559956e-05, "loss": 4.2602, "step": 11635 }, { "epoch": 0.35540623091020157, "grad_norm": 0.4032842218875885, "learning_rate": 3.5969818457289004e-05, "loss": 4.3163, "step": 11636 }, { "epoch": 0.3554367745876604, "grad_norm": 0.39373916387557983, "learning_rate": 3.596766278797369e-05, "loss": 4.2627, "step": 11637 }, { "epoch": 0.3554673182651191, "grad_norm": 0.3856258988380432, "learning_rate": 3.596550701767346e-05, "loss": 4.3649, "step": 11638 }, { "epoch": 0.3554978619425779, "grad_norm": 0.3942515552043915, "learning_rate": 3.5963351146408176e-05, "loss": 4.3392, "step": 11639 }, { "epoch": 0.3555284056200366, "grad_norm": 0.38597801327705383, "learning_rate": 3.596119517419768e-05, "loss": 4.2264, "step": 11640 }, { "epoch": 0.35555894929749543, "grad_norm": 0.38549643754959106, "learning_rate": 3.5959039101061824e-05, "loss": 4.1576, "step": 11641 }, { "epoch": 0.3555894929749542, "grad_norm": 0.378386914730072, "learning_rate": 3.595688292702046e-05, "loss": 4.2561, "step": 11642 }, { "epoch": 0.35562003665241293, "grad_norm": 0.38203293085098267, "learning_rate": 3.5954726652093445e-05, "loss": 4.3677, "step": 11643 }, { "epoch": 0.35565058032987173, "grad_norm": 0.3770401179790497, "learning_rate": 3.5952570276300626e-05, "loss": 4.3089, "step": 11644 }, { "epoch": 0.3556811240073305, "grad_norm": 0.39661887288093567, "learning_rate": 3.595041379966186e-05, "loss": 4.3393, "step": 11645 }, { "epoch": 0.35571166768478923, "grad_norm": 0.38513702154159546, "learning_rate": 3.5948257222197e-05, "loss": 4.2799, "step": 11646 }, { "epoch": 0.35574221136224804, "grad_norm": 0.38040605187416077, "learning_rate": 3.594610054392592e-05, "loss": 4.3158, "step": 11647 }, { "epoch": 0.3557727550397068, "grad_norm": 0.3690931797027588, "learning_rate": 3.594394376486845e-05, "loss": 4.3018, "step": 11648 }, { "epoch": 0.35580329871716554, "grad_norm": 0.3752630650997162, "learning_rate": 3.5941786885044476e-05, "loss": 4.4118, "step": 11649 }, { "epoch": 0.3558338423946243, "grad_norm": 0.3802024722099304, "learning_rate": 3.593962990447384e-05, "loss": 4.3262, "step": 11650 }, { "epoch": 0.3558643860720831, "grad_norm": 0.38787421584129333, "learning_rate": 3.5937472823176396e-05, "loss": 4.3839, "step": 11651 }, { "epoch": 0.35589492974954184, "grad_norm": 0.37422919273376465, "learning_rate": 3.593531564117203e-05, "loss": 4.3469, "step": 11652 }, { "epoch": 0.3559254734270006, "grad_norm": 0.39246854186058044, "learning_rate": 3.593315835848058e-05, "loss": 4.3854, "step": 11653 }, { "epoch": 0.3559560171044594, "grad_norm": 0.3899499773979187, "learning_rate": 3.5931000975121926e-05, "loss": 4.181, "step": 11654 }, { "epoch": 0.35598656078191815, "grad_norm": 0.3821578919887543, "learning_rate": 3.592884349111593e-05, "loss": 4.3387, "step": 11655 }, { "epoch": 0.3560171044593769, "grad_norm": 0.377277135848999, "learning_rate": 3.592668590648245e-05, "loss": 4.3083, "step": 11656 }, { "epoch": 0.35604764813683565, "grad_norm": 0.3736712634563446, "learning_rate": 3.592452822124135e-05, "loss": 4.3436, "step": 11657 }, { "epoch": 0.35607819181429445, "grad_norm": 0.38813307881355286, "learning_rate": 3.59223704354125e-05, "loss": 4.382, "step": 11658 }, { "epoch": 0.3561087354917532, "grad_norm": 0.37467536330223083, "learning_rate": 3.592021254901578e-05, "loss": 4.2403, "step": 11659 }, { "epoch": 0.35613927916921195, "grad_norm": 0.37816157937049866, "learning_rate": 3.591805456207104e-05, "loss": 4.3641, "step": 11660 }, { "epoch": 0.35616982284667076, "grad_norm": 0.37731462717056274, "learning_rate": 3.591589647459815e-05, "loss": 4.344, "step": 11661 }, { "epoch": 0.3562003665241295, "grad_norm": 0.3932754099369049, "learning_rate": 3.5913738286617e-05, "loss": 4.3803, "step": 11662 }, { "epoch": 0.35623091020158826, "grad_norm": 0.3881865441799164, "learning_rate": 3.591157999814746e-05, "loss": 4.3031, "step": 11663 }, { "epoch": 0.35626145387904706, "grad_norm": 0.3884894847869873, "learning_rate": 3.590942160920938e-05, "loss": 4.3318, "step": 11664 }, { "epoch": 0.3562919975565058, "grad_norm": 0.3779699206352234, "learning_rate": 3.5907263119822656e-05, "loss": 4.3094, "step": 11665 }, { "epoch": 0.35632254123396456, "grad_norm": 0.3794870376586914, "learning_rate": 3.590510453000714e-05, "loss": 4.381, "step": 11666 }, { "epoch": 0.3563530849114233, "grad_norm": 0.38677725195884705, "learning_rate": 3.5902945839782726e-05, "loss": 4.2705, "step": 11667 }, { "epoch": 0.3563836285888821, "grad_norm": 0.38405683636665344, "learning_rate": 3.5900787049169285e-05, "loss": 4.3524, "step": 11668 }, { "epoch": 0.35641417226634087, "grad_norm": 0.3877004384994507, "learning_rate": 3.589862815818669e-05, "loss": 4.2919, "step": 11669 }, { "epoch": 0.3564447159437996, "grad_norm": 0.3802180886268616, "learning_rate": 3.589646916685482e-05, "loss": 4.3252, "step": 11670 }, { "epoch": 0.3564752596212584, "grad_norm": 0.4075413644313812, "learning_rate": 3.589431007519356e-05, "loss": 4.3736, "step": 11671 }, { "epoch": 0.35650580329871717, "grad_norm": 0.3862902820110321, "learning_rate": 3.589215088322279e-05, "loss": 4.3245, "step": 11672 }, { "epoch": 0.3565363469761759, "grad_norm": 0.3803028166294098, "learning_rate": 3.588999159096238e-05, "loss": 4.3251, "step": 11673 }, { "epoch": 0.35656689065363467, "grad_norm": 0.3899894058704376, "learning_rate": 3.588783219843222e-05, "loss": 4.2686, "step": 11674 }, { "epoch": 0.3565974343310935, "grad_norm": 0.37473055720329285, "learning_rate": 3.588567270565218e-05, "loss": 4.373, "step": 11675 }, { "epoch": 0.3566279780085522, "grad_norm": 0.3737730085849762, "learning_rate": 3.588351311264217e-05, "loss": 4.3354, "step": 11676 }, { "epoch": 0.356658521686011, "grad_norm": 0.3997020423412323, "learning_rate": 3.588135341942206e-05, "loss": 4.3121, "step": 11677 }, { "epoch": 0.3566890653634698, "grad_norm": 0.3933275640010834, "learning_rate": 3.587919362601172e-05, "loss": 4.2214, "step": 11678 }, { "epoch": 0.35671960904092853, "grad_norm": 0.3767818212509155, "learning_rate": 3.587703373243106e-05, "loss": 4.3334, "step": 11679 }, { "epoch": 0.3567501527183873, "grad_norm": 0.38438671827316284, "learning_rate": 3.5874873738699965e-05, "loss": 4.3033, "step": 11680 }, { "epoch": 0.3567806963958461, "grad_norm": 0.3922179043292999, "learning_rate": 3.587271364483831e-05, "loss": 4.299, "step": 11681 }, { "epoch": 0.35681124007330484, "grad_norm": 0.3826822340488434, "learning_rate": 3.587055345086598e-05, "loss": 4.3195, "step": 11682 }, { "epoch": 0.3568417837507636, "grad_norm": 0.37213027477264404, "learning_rate": 3.586839315680289e-05, "loss": 4.392, "step": 11683 }, { "epoch": 0.35687232742822234, "grad_norm": 0.5640621185302734, "learning_rate": 3.586623276266891e-05, "loss": 4.2658, "step": 11684 }, { "epoch": 0.35690287110568114, "grad_norm": 0.3833973705768585, "learning_rate": 3.5864072268483936e-05, "loss": 4.2315, "step": 11685 }, { "epoch": 0.3569334147831399, "grad_norm": 0.37731948494911194, "learning_rate": 3.5861911674267865e-05, "loss": 4.3168, "step": 11686 }, { "epoch": 0.35696395846059864, "grad_norm": 0.38395097851753235, "learning_rate": 3.585975098004059e-05, "loss": 4.3359, "step": 11687 }, { "epoch": 0.35699450213805745, "grad_norm": 0.3765326142311096, "learning_rate": 3.5857590185822006e-05, "loss": 4.3587, "step": 11688 }, { "epoch": 0.3570250458155162, "grad_norm": 0.3765801787376404, "learning_rate": 3.5855429291632e-05, "loss": 4.2832, "step": 11689 }, { "epoch": 0.35705558949297495, "grad_norm": 0.389078289270401, "learning_rate": 3.5853268297490484e-05, "loss": 4.2687, "step": 11690 }, { "epoch": 0.3570861331704337, "grad_norm": 0.38220101594924927, "learning_rate": 3.5851107203417346e-05, "loss": 4.3614, "step": 11691 }, { "epoch": 0.3571166768478925, "grad_norm": 0.3727320432662964, "learning_rate": 3.584894600943247e-05, "loss": 4.2711, "step": 11692 }, { "epoch": 0.35714722052535125, "grad_norm": 0.38835960626602173, "learning_rate": 3.584678471555578e-05, "loss": 4.3598, "step": 11693 }, { "epoch": 0.35717776420281, "grad_norm": 0.37905076146125793, "learning_rate": 3.584462332180717e-05, "loss": 4.3103, "step": 11694 }, { "epoch": 0.3572083078802688, "grad_norm": 0.3806871771812439, "learning_rate": 3.5842461828206537e-05, "loss": 4.3385, "step": 11695 }, { "epoch": 0.35723885155772755, "grad_norm": 0.37626758217811584, "learning_rate": 3.5840300234773785e-05, "loss": 4.3197, "step": 11696 }, { "epoch": 0.3572693952351863, "grad_norm": 0.37955406308174133, "learning_rate": 3.583813854152881e-05, "loss": 4.2621, "step": 11697 }, { "epoch": 0.3572999389126451, "grad_norm": 0.39431700110435486, "learning_rate": 3.583597674849152e-05, "loss": 4.3894, "step": 11698 }, { "epoch": 0.35733048259010386, "grad_norm": 0.38032224774360657, "learning_rate": 3.583381485568182e-05, "loss": 4.3238, "step": 11699 }, { "epoch": 0.3573610262675626, "grad_norm": 0.3804887533187866, "learning_rate": 3.583165286311962e-05, "loss": 4.3773, "step": 11700 }, { "epoch": 0.35739156994502136, "grad_norm": 0.37558433413505554, "learning_rate": 3.582949077082482e-05, "loss": 4.2563, "step": 11701 }, { "epoch": 0.35742211362248016, "grad_norm": 0.3789173662662506, "learning_rate": 3.582732857881734e-05, "loss": 4.3783, "step": 11702 }, { "epoch": 0.3574526572999389, "grad_norm": 0.38093605637550354, "learning_rate": 3.582516628711707e-05, "loss": 4.4253, "step": 11703 }, { "epoch": 0.35748320097739766, "grad_norm": 0.38223400712013245, "learning_rate": 3.582300389574393e-05, "loss": 4.2811, "step": 11704 }, { "epoch": 0.35751374465485647, "grad_norm": 0.3783707022666931, "learning_rate": 3.582084140471782e-05, "loss": 4.3429, "step": 11705 }, { "epoch": 0.3575442883323152, "grad_norm": 0.37728723883628845, "learning_rate": 3.581867881405867e-05, "loss": 4.3587, "step": 11706 }, { "epoch": 0.35757483200977397, "grad_norm": 0.37066832184791565, "learning_rate": 3.581651612378638e-05, "loss": 4.2904, "step": 11707 }, { "epoch": 0.3576053756872327, "grad_norm": 0.3729594945907593, "learning_rate": 3.581435333392087e-05, "loss": 4.3544, "step": 11708 }, { "epoch": 0.3576359193646915, "grad_norm": 0.37859073281288147, "learning_rate": 3.581219044448204e-05, "loss": 4.2297, "step": 11709 }, { "epoch": 0.3576664630421503, "grad_norm": 0.3701418936252594, "learning_rate": 3.581002745548981e-05, "loss": 4.3007, "step": 11710 }, { "epoch": 0.357697006719609, "grad_norm": 0.38510963320732117, "learning_rate": 3.580786436696412e-05, "loss": 4.2511, "step": 11711 }, { "epoch": 0.35772755039706783, "grad_norm": 0.3756438195705414, "learning_rate": 3.5805701178924846e-05, "loss": 4.2768, "step": 11712 }, { "epoch": 0.3577580940745266, "grad_norm": 0.3810621201992035, "learning_rate": 3.580353789139193e-05, "loss": 4.3151, "step": 11713 }, { "epoch": 0.35778863775198533, "grad_norm": 0.385087251663208, "learning_rate": 3.5801374504385285e-05, "loss": 4.1614, "step": 11714 }, { "epoch": 0.3578191814294441, "grad_norm": 0.37968629598617554, "learning_rate": 3.579921101792484e-05, "loss": 4.2433, "step": 11715 }, { "epoch": 0.3578497251069029, "grad_norm": 0.3972136676311493, "learning_rate": 3.5797047432030495e-05, "loss": 4.3757, "step": 11716 }, { "epoch": 0.35788026878436163, "grad_norm": 0.38778749108314514, "learning_rate": 3.579488374672219e-05, "loss": 4.2864, "step": 11717 }, { "epoch": 0.3579108124618204, "grad_norm": 0.3794906735420227, "learning_rate": 3.579271996201984e-05, "loss": 4.2783, "step": 11718 }, { "epoch": 0.3579413561392792, "grad_norm": 0.3843424320220947, "learning_rate": 3.5790556077943364e-05, "loss": 4.3538, "step": 11719 }, { "epoch": 0.35797189981673794, "grad_norm": 0.38428446650505066, "learning_rate": 3.57883920945127e-05, "loss": 4.2273, "step": 11720 }, { "epoch": 0.3580024434941967, "grad_norm": 0.3810209333896637, "learning_rate": 3.5786228011747754e-05, "loss": 4.3402, "step": 11721 }, { "epoch": 0.3580329871716555, "grad_norm": 0.3908182382583618, "learning_rate": 3.5784063829668454e-05, "loss": 4.33, "step": 11722 }, { "epoch": 0.35806353084911424, "grad_norm": 0.39366522431373596, "learning_rate": 3.578189954829475e-05, "loss": 4.366, "step": 11723 }, { "epoch": 0.358094074526573, "grad_norm": 0.377204954624176, "learning_rate": 3.5779735167646544e-05, "loss": 4.2313, "step": 11724 }, { "epoch": 0.35812461820403174, "grad_norm": 0.3812621533870697, "learning_rate": 3.577757068774378e-05, "loss": 4.263, "step": 11725 }, { "epoch": 0.35815516188149055, "grad_norm": 0.38464438915252686, "learning_rate": 3.5775406108606374e-05, "loss": 4.307, "step": 11726 }, { "epoch": 0.3581857055589493, "grad_norm": 0.38417062163352966, "learning_rate": 3.5773241430254265e-05, "loss": 4.3179, "step": 11727 }, { "epoch": 0.35821624923640805, "grad_norm": 0.39073458313941956, "learning_rate": 3.577107665270739e-05, "loss": 4.3392, "step": 11728 }, { "epoch": 0.35824679291386685, "grad_norm": 0.37596818804740906, "learning_rate": 3.5768911775985666e-05, "loss": 4.2854, "step": 11729 }, { "epoch": 0.3582773365913256, "grad_norm": 0.38627687096595764, "learning_rate": 3.576674680010904e-05, "loss": 4.3215, "step": 11730 }, { "epoch": 0.35830788026878435, "grad_norm": 0.37972119450569153, "learning_rate": 3.576458172509744e-05, "loss": 4.2908, "step": 11731 }, { "epoch": 0.3583384239462431, "grad_norm": 0.3872734606266022, "learning_rate": 3.57624165509708e-05, "loss": 4.3105, "step": 11732 }, { "epoch": 0.3583689676237019, "grad_norm": 0.365622341632843, "learning_rate": 3.576025127774905e-05, "loss": 4.3833, "step": 11733 }, { "epoch": 0.35839951130116066, "grad_norm": 0.4096470773220062, "learning_rate": 3.575808590545215e-05, "loss": 4.3867, "step": 11734 }, { "epoch": 0.3584300549786194, "grad_norm": 0.3779686987400055, "learning_rate": 3.575592043410002e-05, "loss": 4.2925, "step": 11735 }, { "epoch": 0.3584605986560782, "grad_norm": 0.3806343376636505, "learning_rate": 3.575375486371259e-05, "loss": 4.3511, "step": 11736 }, { "epoch": 0.35849114233353696, "grad_norm": 0.3792235553264618, "learning_rate": 3.575158919430981e-05, "loss": 4.4004, "step": 11737 }, { "epoch": 0.3585216860109957, "grad_norm": 0.375887006521225, "learning_rate": 3.574942342591162e-05, "loss": 4.2815, "step": 11738 }, { "epoch": 0.3585522296884545, "grad_norm": 0.368324339389801, "learning_rate": 3.574725755853797e-05, "loss": 4.3261, "step": 11739 }, { "epoch": 0.35858277336591327, "grad_norm": 0.39036083221435547, "learning_rate": 3.5745091592208784e-05, "loss": 4.2928, "step": 11740 }, { "epoch": 0.358613317043372, "grad_norm": 0.37904345989227295, "learning_rate": 3.574292552694403e-05, "loss": 4.2688, "step": 11741 }, { "epoch": 0.35864386072083076, "grad_norm": 0.40634992718696594, "learning_rate": 3.574075936276362e-05, "loss": 4.28, "step": 11742 }, { "epoch": 0.35867440439828957, "grad_norm": 0.38928934931755066, "learning_rate": 3.573859309968753e-05, "loss": 4.3523, "step": 11743 }, { "epoch": 0.3587049480757483, "grad_norm": 0.401149719953537, "learning_rate": 3.573642673773568e-05, "loss": 4.3753, "step": 11744 }, { "epoch": 0.35873549175320707, "grad_norm": 0.3831040561199188, "learning_rate": 3.573426027692804e-05, "loss": 4.3657, "step": 11745 }, { "epoch": 0.3587660354306659, "grad_norm": 0.38365688920021057, "learning_rate": 3.5732093717284546e-05, "loss": 4.3966, "step": 11746 }, { "epoch": 0.3587965791081246, "grad_norm": 0.3964404761791229, "learning_rate": 3.572992705882514e-05, "loss": 4.3759, "step": 11747 }, { "epoch": 0.3588271227855834, "grad_norm": 0.3775583803653717, "learning_rate": 3.572776030156978e-05, "loss": 4.2846, "step": 11748 }, { "epoch": 0.3588576664630421, "grad_norm": 0.37071099877357483, "learning_rate": 3.572559344553842e-05, "loss": 4.3691, "step": 11749 }, { "epoch": 0.35888821014050093, "grad_norm": 0.3810745179653168, "learning_rate": 3.5723426490751e-05, "loss": 4.3245, "step": 11750 }, { "epoch": 0.3589187538179597, "grad_norm": 0.37471485137939453, "learning_rate": 3.572125943722749e-05, "loss": 4.3209, "step": 11751 }, { "epoch": 0.35894929749541843, "grad_norm": 0.3709605932235718, "learning_rate": 3.571909228498782e-05, "loss": 4.3575, "step": 11752 }, { "epoch": 0.35897984117287723, "grad_norm": 0.37948504090309143, "learning_rate": 3.571692503405196e-05, "loss": 4.3551, "step": 11753 }, { "epoch": 0.359010384850336, "grad_norm": 0.3824581205844879, "learning_rate": 3.571475768443986e-05, "loss": 4.316, "step": 11754 }, { "epoch": 0.35904092852779473, "grad_norm": 0.36785179376602173, "learning_rate": 3.571259023617148e-05, "loss": 4.321, "step": 11755 }, { "epoch": 0.35907147220525354, "grad_norm": 0.383872389793396, "learning_rate": 3.571042268926677e-05, "loss": 4.3089, "step": 11756 }, { "epoch": 0.3591020158827123, "grad_norm": 0.3925527334213257, "learning_rate": 3.5708255043745696e-05, "loss": 4.3058, "step": 11757 }, { "epoch": 0.35913255956017104, "grad_norm": 0.37739747762680054, "learning_rate": 3.570608729962821e-05, "loss": 4.1837, "step": 11758 }, { "epoch": 0.3591631032376298, "grad_norm": 0.3713874816894531, "learning_rate": 3.570391945693428e-05, "loss": 4.2765, "step": 11759 }, { "epoch": 0.3591936469150886, "grad_norm": 0.379984974861145, "learning_rate": 3.5701751515683853e-05, "loss": 4.3161, "step": 11760 }, { "epoch": 0.35922419059254734, "grad_norm": 0.3839532136917114, "learning_rate": 3.5699583475896896e-05, "loss": 4.2313, "step": 11761 }, { "epoch": 0.3592547342700061, "grad_norm": 0.3780863881111145, "learning_rate": 3.569741533759338e-05, "loss": 4.3764, "step": 11762 }, { "epoch": 0.3592852779474649, "grad_norm": 0.3842940032482147, "learning_rate": 3.5695247100793247e-05, "loss": 4.3317, "step": 11763 }, { "epoch": 0.35931582162492365, "grad_norm": 0.3951128125190735, "learning_rate": 3.5693078765516494e-05, "loss": 4.2474, "step": 11764 }, { "epoch": 0.3593463653023824, "grad_norm": 0.38198885321617126, "learning_rate": 3.569091033178306e-05, "loss": 4.3314, "step": 11765 }, { "epoch": 0.35937690897984115, "grad_norm": 0.3775782287120819, "learning_rate": 3.5688741799612914e-05, "loss": 4.3093, "step": 11766 }, { "epoch": 0.35940745265729995, "grad_norm": 0.3809093236923218, "learning_rate": 3.5686573169026025e-05, "loss": 4.3699, "step": 11767 }, { "epoch": 0.3594379963347587, "grad_norm": 0.3815917670726776, "learning_rate": 3.568440444004236e-05, "loss": 4.4347, "step": 11768 }, { "epoch": 0.35946854001221745, "grad_norm": 0.3728066086769104, "learning_rate": 3.56822356126819e-05, "loss": 4.2965, "step": 11769 }, { "epoch": 0.35949908368967626, "grad_norm": 0.39202672243118286, "learning_rate": 3.5680066686964596e-05, "loss": 4.3482, "step": 11770 }, { "epoch": 0.359529627367135, "grad_norm": 0.3850124180316925, "learning_rate": 3.567789766291043e-05, "loss": 4.292, "step": 11771 }, { "epoch": 0.35956017104459376, "grad_norm": 0.37521690130233765, "learning_rate": 3.567572854053938e-05, "loss": 4.3882, "step": 11772 }, { "epoch": 0.35959071472205256, "grad_norm": 0.38801124691963196, "learning_rate": 3.56735593198714e-05, "loss": 4.3776, "step": 11773 }, { "epoch": 0.3596212583995113, "grad_norm": 0.38078993558883667, "learning_rate": 3.567139000092646e-05, "loss": 4.2318, "step": 11774 }, { "epoch": 0.35965180207697006, "grad_norm": 0.3776099383831024, "learning_rate": 3.566922058372456e-05, "loss": 4.3241, "step": 11775 }, { "epoch": 0.3596823457544288, "grad_norm": 0.39426368474960327, "learning_rate": 3.5667051068285664e-05, "loss": 4.2757, "step": 11776 }, { "epoch": 0.3597128894318876, "grad_norm": 0.38513240218162537, "learning_rate": 3.566488145462973e-05, "loss": 4.3151, "step": 11777 }, { "epoch": 0.35974343310934637, "grad_norm": 0.391170471906662, "learning_rate": 3.5662711742776754e-05, "loss": 4.2676, "step": 11778 }, { "epoch": 0.3597739767868051, "grad_norm": 0.3936609625816345, "learning_rate": 3.566054193274672e-05, "loss": 4.3165, "step": 11779 }, { "epoch": 0.3598045204642639, "grad_norm": 0.3818604350090027, "learning_rate": 3.5658372024559586e-05, "loss": 4.2608, "step": 11780 }, { "epoch": 0.35983506414172267, "grad_norm": 0.3754070997238159, "learning_rate": 3.5656202018235343e-05, "loss": 4.3655, "step": 11781 }, { "epoch": 0.3598656078191814, "grad_norm": 0.3805198669433594, "learning_rate": 3.565403191379396e-05, "loss": 4.2986, "step": 11782 }, { "epoch": 0.35989615149664017, "grad_norm": 0.3798852562904358, "learning_rate": 3.565186171125544e-05, "loss": 4.3291, "step": 11783 }, { "epoch": 0.359926695174099, "grad_norm": 0.36675307154655457, "learning_rate": 3.5649691410639744e-05, "loss": 4.3074, "step": 11784 }, { "epoch": 0.3599572388515577, "grad_norm": 0.38509443402290344, "learning_rate": 3.5647521011966866e-05, "loss": 4.4089, "step": 11785 }, { "epoch": 0.3599877825290165, "grad_norm": 0.3699657917022705, "learning_rate": 3.5645350515256795e-05, "loss": 4.2874, "step": 11786 }, { "epoch": 0.3600183262064753, "grad_norm": 0.3816354274749756, "learning_rate": 3.564317992052949e-05, "loss": 4.4408, "step": 11787 }, { "epoch": 0.36004886988393403, "grad_norm": 0.37959161400794983, "learning_rate": 3.5641009227804976e-05, "loss": 4.27, "step": 11788 }, { "epoch": 0.3600794135613928, "grad_norm": 0.4178468883037567, "learning_rate": 3.563883843710321e-05, "loss": 4.3442, "step": 11789 }, { "epoch": 0.36010995723885153, "grad_norm": 0.3836108148097992, "learning_rate": 3.563666754844419e-05, "loss": 4.3157, "step": 11790 }, { "epoch": 0.36014050091631034, "grad_norm": 0.3788021206855774, "learning_rate": 3.56344965618479e-05, "loss": 4.1586, "step": 11791 }, { "epoch": 0.3601710445937691, "grad_norm": 0.3766043782234192, "learning_rate": 3.5632325477334334e-05, "loss": 4.2744, "step": 11792 }, { "epoch": 0.36020158827122783, "grad_norm": 0.3850265145301819, "learning_rate": 3.563015429492348e-05, "loss": 4.4254, "step": 11793 }, { "epoch": 0.36023213194868664, "grad_norm": 0.37242090702056885, "learning_rate": 3.562798301463533e-05, "loss": 4.381, "step": 11794 }, { "epoch": 0.3602626756261454, "grad_norm": 0.3821583390235901, "learning_rate": 3.5625811636489874e-05, "loss": 4.2629, "step": 11795 }, { "epoch": 0.36029321930360414, "grad_norm": 0.3952350914478302, "learning_rate": 3.562364016050712e-05, "loss": 4.3221, "step": 11796 }, { "epoch": 0.36032376298106294, "grad_norm": 0.3747684359550476, "learning_rate": 3.562146858670704e-05, "loss": 4.4312, "step": 11797 }, { "epoch": 0.3603543066585217, "grad_norm": 0.3864167332649231, "learning_rate": 3.561929691510964e-05, "loss": 4.3386, "step": 11798 }, { "epoch": 0.36038485033598044, "grad_norm": 0.392443984746933, "learning_rate": 3.56171251457349e-05, "loss": 4.2257, "step": 11799 }, { "epoch": 0.3604153940134392, "grad_norm": 0.38308265805244446, "learning_rate": 3.561495327860284e-05, "loss": 4.31, "step": 11800 }, { "epoch": 0.360445937690898, "grad_norm": 0.391336053609848, "learning_rate": 3.561278131373345e-05, "loss": 4.293, "step": 11801 }, { "epoch": 0.36047648136835675, "grad_norm": 0.37488022446632385, "learning_rate": 3.561060925114672e-05, "loss": 4.3511, "step": 11802 }, { "epoch": 0.3605070250458155, "grad_norm": 0.37889084219932556, "learning_rate": 3.5608437090862665e-05, "loss": 4.3282, "step": 11803 }, { "epoch": 0.3605375687232743, "grad_norm": 0.3812027871608734, "learning_rate": 3.5606264832901266e-05, "loss": 4.3565, "step": 11804 }, { "epoch": 0.36056811240073305, "grad_norm": 0.3844068944454193, "learning_rate": 3.560409247728254e-05, "loss": 4.2212, "step": 11805 }, { "epoch": 0.3605986560781918, "grad_norm": 0.3998992145061493, "learning_rate": 3.560192002402647e-05, "loss": 4.4065, "step": 11806 }, { "epoch": 0.36062919975565055, "grad_norm": 0.3786546587944031, "learning_rate": 3.559974747315309e-05, "loss": 4.395, "step": 11807 }, { "epoch": 0.36065974343310936, "grad_norm": 0.38059085607528687, "learning_rate": 3.5597574824682365e-05, "loss": 4.3036, "step": 11808 }, { "epoch": 0.3606902871105681, "grad_norm": 0.38052743673324585, "learning_rate": 3.559540207863433e-05, "loss": 4.3292, "step": 11809 }, { "epoch": 0.36072083078802686, "grad_norm": 0.3699795603752136, "learning_rate": 3.559322923502899e-05, "loss": 4.4473, "step": 11810 }, { "epoch": 0.36075137446548566, "grad_norm": 0.3764496147632599, "learning_rate": 3.5591056293886326e-05, "loss": 4.3985, "step": 11811 }, { "epoch": 0.3607819181429444, "grad_norm": 0.3807041645050049, "learning_rate": 3.5588883255226376e-05, "loss": 4.3019, "step": 11812 }, { "epoch": 0.36081246182040316, "grad_norm": 0.39036083221435547, "learning_rate": 3.558671011906912e-05, "loss": 4.3129, "step": 11813 }, { "epoch": 0.36084300549786197, "grad_norm": 0.3830651044845581, "learning_rate": 3.558453688543459e-05, "loss": 4.3216, "step": 11814 }, { "epoch": 0.3608735491753207, "grad_norm": 0.376889705657959, "learning_rate": 3.558236355434278e-05, "loss": 4.3212, "step": 11815 }, { "epoch": 0.36090409285277947, "grad_norm": 0.3913128972053528, "learning_rate": 3.5580190125813715e-05, "loss": 4.3128, "step": 11816 }, { "epoch": 0.3609346365302382, "grad_norm": 0.3774620592594147, "learning_rate": 3.557801659986739e-05, "loss": 4.3342, "step": 11817 }, { "epoch": 0.360965180207697, "grad_norm": 0.39284104108810425, "learning_rate": 3.5575842976523835e-05, "loss": 4.318, "step": 11818 }, { "epoch": 0.3609957238851558, "grad_norm": 0.4044443964958191, "learning_rate": 3.557366925580305e-05, "loss": 4.3842, "step": 11819 }, { "epoch": 0.3610262675626145, "grad_norm": 0.37780293822288513, "learning_rate": 3.557149543772507e-05, "loss": 4.301, "step": 11820 }, { "epoch": 0.3610568112400733, "grad_norm": 0.38458341360092163, "learning_rate": 3.5569321522309886e-05, "loss": 4.297, "step": 11821 }, { "epoch": 0.3610873549175321, "grad_norm": 0.38365375995635986, "learning_rate": 3.5567147509577524e-05, "loss": 4.2878, "step": 11822 }, { "epoch": 0.3611178985949908, "grad_norm": 0.3866201937198639, "learning_rate": 3.5564973399548005e-05, "loss": 4.398, "step": 11823 }, { "epoch": 0.3611484422724496, "grad_norm": 0.3885010778903961, "learning_rate": 3.556279919224134e-05, "loss": 4.293, "step": 11824 }, { "epoch": 0.3611789859499084, "grad_norm": 0.3817393481731415, "learning_rate": 3.556062488767755e-05, "loss": 4.2432, "step": 11825 }, { "epoch": 0.36120952962736713, "grad_norm": 0.38374993205070496, "learning_rate": 3.555845048587666e-05, "loss": 4.3104, "step": 11826 }, { "epoch": 0.3612400733048259, "grad_norm": 0.3718864619731903, "learning_rate": 3.555627598685869e-05, "loss": 4.2734, "step": 11827 }, { "epoch": 0.3612706169822847, "grad_norm": 0.37481939792633057, "learning_rate": 3.5554101390643655e-05, "loss": 4.357, "step": 11828 }, { "epoch": 0.36130116065974344, "grad_norm": 0.3800692558288574, "learning_rate": 3.5551926697251595e-05, "loss": 4.3228, "step": 11829 }, { "epoch": 0.3613317043372022, "grad_norm": 0.37804996967315674, "learning_rate": 3.5549751906702504e-05, "loss": 4.3032, "step": 11830 }, { "epoch": 0.361362248014661, "grad_norm": 0.37742868065834045, "learning_rate": 3.5547577019016434e-05, "loss": 4.33, "step": 11831 }, { "epoch": 0.36139279169211974, "grad_norm": 0.375340074300766, "learning_rate": 3.5545402034213394e-05, "loss": 4.2952, "step": 11832 }, { "epoch": 0.3614233353695785, "grad_norm": 0.3836735486984253, "learning_rate": 3.554322695231341e-05, "loss": 4.3361, "step": 11833 }, { "epoch": 0.36145387904703724, "grad_norm": 0.3900061249732971, "learning_rate": 3.5541051773336524e-05, "loss": 4.306, "step": 11834 }, { "epoch": 0.36148442272449605, "grad_norm": 0.3866189420223236, "learning_rate": 3.5538876497302754e-05, "loss": 4.3127, "step": 11835 }, { "epoch": 0.3615149664019548, "grad_norm": 0.38521140813827515, "learning_rate": 3.553670112423213e-05, "loss": 4.2461, "step": 11836 }, { "epoch": 0.36154551007941355, "grad_norm": 0.3840392827987671, "learning_rate": 3.553452565414468e-05, "loss": 4.2166, "step": 11837 }, { "epoch": 0.36157605375687235, "grad_norm": 0.3864516615867615, "learning_rate": 3.553235008706043e-05, "loss": 4.3219, "step": 11838 }, { "epoch": 0.3616065974343311, "grad_norm": 0.3858247399330139, "learning_rate": 3.553017442299942e-05, "loss": 4.3538, "step": 11839 }, { "epoch": 0.36163714111178985, "grad_norm": 0.3744144141674042, "learning_rate": 3.552799866198169e-05, "loss": 4.2792, "step": 11840 }, { "epoch": 0.3616676847892486, "grad_norm": 0.3838754892349243, "learning_rate": 3.552582280402725e-05, "loss": 4.3613, "step": 11841 }, { "epoch": 0.3616982284667074, "grad_norm": 0.37929028272628784, "learning_rate": 3.552364684915615e-05, "loss": 4.3882, "step": 11842 }, { "epoch": 0.36172877214416616, "grad_norm": 0.38472795486450195, "learning_rate": 3.552147079738843e-05, "loss": 4.4306, "step": 11843 }, { "epoch": 0.3617593158216249, "grad_norm": 0.3711419701576233, "learning_rate": 3.5519294648744114e-05, "loss": 4.3973, "step": 11844 }, { "epoch": 0.3617898594990837, "grad_norm": 0.3814297318458557, "learning_rate": 3.551711840324324e-05, "loss": 4.3613, "step": 11845 }, { "epoch": 0.36182040317654246, "grad_norm": 0.37736383080482483, "learning_rate": 3.551494206090586e-05, "loss": 4.2982, "step": 11846 }, { "epoch": 0.3618509468540012, "grad_norm": 0.38724908232688904, "learning_rate": 3.5512765621752e-05, "loss": 4.4071, "step": 11847 }, { "epoch": 0.36188149053146, "grad_norm": 0.3736324608325958, "learning_rate": 3.5510589085801695e-05, "loss": 4.2957, "step": 11848 }, { "epoch": 0.36191203420891876, "grad_norm": 0.38680359721183777, "learning_rate": 3.550841245307499e-05, "loss": 4.3367, "step": 11849 }, { "epoch": 0.3619425778863775, "grad_norm": 0.369459867477417, "learning_rate": 3.5506235723591934e-05, "loss": 4.3292, "step": 11850 }, { "epoch": 0.36197312156383626, "grad_norm": 0.3874736428260803, "learning_rate": 3.5504058897372565e-05, "loss": 4.2631, "step": 11851 }, { "epoch": 0.36200366524129507, "grad_norm": 0.37550589442253113, "learning_rate": 3.550188197443692e-05, "loss": 4.3299, "step": 11852 }, { "epoch": 0.3620342089187538, "grad_norm": 0.39111658930778503, "learning_rate": 3.5499704954805055e-05, "loss": 4.3739, "step": 11853 }, { "epoch": 0.36206475259621257, "grad_norm": 0.3795223832130432, "learning_rate": 3.5497527838497014e-05, "loss": 4.332, "step": 11854 }, { "epoch": 0.3620952962736714, "grad_norm": 0.3887779712677002, "learning_rate": 3.549535062553282e-05, "loss": 4.3732, "step": 11855 }, { "epoch": 0.3621258399511301, "grad_norm": 0.38839077949523926, "learning_rate": 3.549317331593255e-05, "loss": 4.3802, "step": 11856 }, { "epoch": 0.3621563836285889, "grad_norm": 0.38304105401039124, "learning_rate": 3.549099590971623e-05, "loss": 4.3203, "step": 11857 }, { "epoch": 0.3621869273060476, "grad_norm": 0.3902426064014435, "learning_rate": 3.5488818406903915e-05, "loss": 4.292, "step": 11858 }, { "epoch": 0.36221747098350643, "grad_norm": 0.37723538279533386, "learning_rate": 3.5486640807515665e-05, "loss": 4.3381, "step": 11859 }, { "epoch": 0.3622480146609652, "grad_norm": 0.3933464288711548, "learning_rate": 3.548446311157152e-05, "loss": 4.3665, "step": 11860 }, { "epoch": 0.36227855833842393, "grad_norm": 0.39904019236564636, "learning_rate": 3.548228531909153e-05, "loss": 4.3402, "step": 11861 }, { "epoch": 0.36230910201588273, "grad_norm": 0.38929882645606995, "learning_rate": 3.548010743009574e-05, "loss": 4.374, "step": 11862 }, { "epoch": 0.3623396456933415, "grad_norm": 0.4057040810585022, "learning_rate": 3.547792944460423e-05, "loss": 4.3162, "step": 11863 }, { "epoch": 0.36237018937080023, "grad_norm": 0.38022422790527344, "learning_rate": 3.547575136263703e-05, "loss": 4.3704, "step": 11864 }, { "epoch": 0.362400733048259, "grad_norm": 0.3923702538013458, "learning_rate": 3.5473573184214194e-05, "loss": 4.2562, "step": 11865 }, { "epoch": 0.3624312767257178, "grad_norm": 0.3780810534954071, "learning_rate": 3.5471394909355786e-05, "loss": 4.2934, "step": 11866 }, { "epoch": 0.36246182040317654, "grad_norm": 0.3840852677822113, "learning_rate": 3.5469216538081874e-05, "loss": 4.2623, "step": 11867 }, { "epoch": 0.3624923640806353, "grad_norm": 0.38062357902526855, "learning_rate": 3.5467038070412495e-05, "loss": 4.2702, "step": 11868 }, { "epoch": 0.3625229077580941, "grad_norm": 0.37738320231437683, "learning_rate": 3.546485950636771e-05, "loss": 4.3313, "step": 11869 }, { "epoch": 0.36255345143555284, "grad_norm": 0.4640777111053467, "learning_rate": 3.546268084596759e-05, "loss": 4.3196, "step": 11870 }, { "epoch": 0.3625839951130116, "grad_norm": 0.3785044252872467, "learning_rate": 3.5460502089232186e-05, "loss": 4.3285, "step": 11871 }, { "epoch": 0.3626145387904704, "grad_norm": 0.3807697594165802, "learning_rate": 3.545832323618155e-05, "loss": 4.3072, "step": 11872 }, { "epoch": 0.36264508246792915, "grad_norm": 0.3940351903438568, "learning_rate": 3.545614428683577e-05, "loss": 4.283, "step": 11873 }, { "epoch": 0.3626756261453879, "grad_norm": 0.3933666944503784, "learning_rate": 3.545396524121488e-05, "loss": 4.3466, "step": 11874 }, { "epoch": 0.36270616982284665, "grad_norm": 0.3808508515357971, "learning_rate": 3.545178609933897e-05, "loss": 4.2784, "step": 11875 }, { "epoch": 0.36273671350030545, "grad_norm": 0.3805456757545471, "learning_rate": 3.544960686122809e-05, "loss": 4.3619, "step": 11876 }, { "epoch": 0.3627672571777642, "grad_norm": 0.39824751019477844, "learning_rate": 3.54474275269023e-05, "loss": 4.3409, "step": 11877 }, { "epoch": 0.36279780085522295, "grad_norm": 0.38213691115379333, "learning_rate": 3.544524809638168e-05, "loss": 4.2707, "step": 11878 }, { "epoch": 0.36282834453268176, "grad_norm": 0.3779834508895874, "learning_rate": 3.5443068569686285e-05, "loss": 4.3776, "step": 11879 }, { "epoch": 0.3628588882101405, "grad_norm": 0.3747318387031555, "learning_rate": 3.544088894683619e-05, "loss": 4.3274, "step": 11880 }, { "epoch": 0.36288943188759926, "grad_norm": 0.38582468032836914, "learning_rate": 3.5438709227851464e-05, "loss": 4.3615, "step": 11881 }, { "epoch": 0.362919975565058, "grad_norm": 0.3739810585975647, "learning_rate": 3.5436529412752174e-05, "loss": 4.2639, "step": 11882 }, { "epoch": 0.3629505192425168, "grad_norm": 0.37029197812080383, "learning_rate": 3.54343495015584e-05, "loss": 4.3148, "step": 11883 }, { "epoch": 0.36298106291997556, "grad_norm": 0.37558284401893616, "learning_rate": 3.543216949429019e-05, "loss": 4.2423, "step": 11884 }, { "epoch": 0.3630116065974343, "grad_norm": 0.38754209876060486, "learning_rate": 3.542998939096764e-05, "loss": 4.3483, "step": 11885 }, { "epoch": 0.3630421502748931, "grad_norm": 0.36871808767318726, "learning_rate": 3.542780919161081e-05, "loss": 4.3608, "step": 11886 }, { "epoch": 0.36307269395235187, "grad_norm": 0.37564727663993835, "learning_rate": 3.5425628896239786e-05, "loss": 4.16, "step": 11887 }, { "epoch": 0.3631032376298106, "grad_norm": 0.37068814039230347, "learning_rate": 3.5423448504874634e-05, "loss": 4.2906, "step": 11888 }, { "epoch": 0.3631337813072694, "grad_norm": 0.3898249566555023, "learning_rate": 3.542126801753543e-05, "loss": 4.3204, "step": 11889 }, { "epoch": 0.36316432498472817, "grad_norm": 0.3784398138523102, "learning_rate": 3.541908743424226e-05, "loss": 4.3577, "step": 11890 }, { "epoch": 0.3631948686621869, "grad_norm": 0.38691410422325134, "learning_rate": 3.54169067550152e-05, "loss": 4.3078, "step": 11891 }, { "epoch": 0.36322541233964567, "grad_norm": 0.40073007345199585, "learning_rate": 3.541472597987431e-05, "loss": 4.3635, "step": 11892 }, { "epoch": 0.3632559560171045, "grad_norm": 0.37137001752853394, "learning_rate": 3.541254510883968e-05, "loss": 4.3594, "step": 11893 }, { "epoch": 0.3632864996945632, "grad_norm": 0.38266611099243164, "learning_rate": 3.54103641419314e-05, "loss": 4.222, "step": 11894 }, { "epoch": 0.363317043372022, "grad_norm": 0.3664405941963196, "learning_rate": 3.540818307916955e-05, "loss": 4.2031, "step": 11895 }, { "epoch": 0.3633475870494808, "grad_norm": 0.397598534822464, "learning_rate": 3.54060019205742e-05, "loss": 4.3329, "step": 11896 }, { "epoch": 0.36337813072693953, "grad_norm": 0.3830227851867676, "learning_rate": 3.540382066616544e-05, "loss": 4.2915, "step": 11897 }, { "epoch": 0.3634086744043983, "grad_norm": 0.3843781650066376, "learning_rate": 3.540163931596336e-05, "loss": 4.2413, "step": 11898 }, { "epoch": 0.36343921808185703, "grad_norm": 0.3796113431453705, "learning_rate": 3.539945786998804e-05, "loss": 4.2945, "step": 11899 }, { "epoch": 0.36346976175931583, "grad_norm": 0.38802841305732727, "learning_rate": 3.539727632825956e-05, "loss": 4.281, "step": 11900 }, { "epoch": 0.3635003054367746, "grad_norm": 0.3990752398967743, "learning_rate": 3.539509469079801e-05, "loss": 4.2675, "step": 11901 }, { "epoch": 0.36353084911423333, "grad_norm": 0.38024309277534485, "learning_rate": 3.5392912957623484e-05, "loss": 4.3743, "step": 11902 }, { "epoch": 0.36356139279169214, "grad_norm": 0.37971216440200806, "learning_rate": 3.539073112875605e-05, "loss": 4.3048, "step": 11903 }, { "epoch": 0.3635919364691509, "grad_norm": 0.38307371735572815, "learning_rate": 3.5388549204215824e-05, "loss": 4.3135, "step": 11904 }, { "epoch": 0.36362248014660964, "grad_norm": 0.47544994950294495, "learning_rate": 3.538636718402289e-05, "loss": 4.3776, "step": 11905 }, { "epoch": 0.36365302382406844, "grad_norm": 0.38072752952575684, "learning_rate": 3.538418506819733e-05, "loss": 4.4381, "step": 11906 }, { "epoch": 0.3636835675015272, "grad_norm": 0.3685886561870575, "learning_rate": 3.538200285675923e-05, "loss": 4.3746, "step": 11907 }, { "epoch": 0.36371411117898594, "grad_norm": 0.37955158948898315, "learning_rate": 3.53798205497287e-05, "loss": 4.3077, "step": 11908 }, { "epoch": 0.3637446548564447, "grad_norm": 0.3743676245212555, "learning_rate": 3.5377638147125824e-05, "loss": 4.2976, "step": 11909 }, { "epoch": 0.3637751985339035, "grad_norm": 0.3914891481399536, "learning_rate": 3.537545564897069e-05, "loss": 4.3506, "step": 11910 }, { "epoch": 0.36380574221136225, "grad_norm": 0.38451358675956726, "learning_rate": 3.537327305528341e-05, "loss": 4.2849, "step": 11911 }, { "epoch": 0.363836285888821, "grad_norm": 0.37942105531692505, "learning_rate": 3.537109036608407e-05, "loss": 4.3114, "step": 11912 }, { "epoch": 0.3638668295662798, "grad_norm": 0.3900626003742218, "learning_rate": 3.536890758139277e-05, "loss": 4.2815, "step": 11913 }, { "epoch": 0.36389737324373855, "grad_norm": 0.3911755681037903, "learning_rate": 3.53667247012296e-05, "loss": 4.3117, "step": 11914 }, { "epoch": 0.3639279169211973, "grad_norm": 0.3843609094619751, "learning_rate": 3.536454172561467e-05, "loss": 4.2775, "step": 11915 }, { "epoch": 0.36395846059865605, "grad_norm": 0.40064746141433716, "learning_rate": 3.5362358654568085e-05, "loss": 4.3326, "step": 11916 }, { "epoch": 0.36398900427611486, "grad_norm": 0.3786144554615021, "learning_rate": 3.536017548810992e-05, "loss": 4.2824, "step": 11917 }, { "epoch": 0.3640195479535736, "grad_norm": 0.3868570327758789, "learning_rate": 3.535799222626031e-05, "loss": 4.2965, "step": 11918 }, { "epoch": 0.36405009163103236, "grad_norm": 0.3919965326786041, "learning_rate": 3.535580886903932e-05, "loss": 4.3429, "step": 11919 }, { "epoch": 0.36408063530849116, "grad_norm": 0.379991352558136, "learning_rate": 3.535362541646709e-05, "loss": 4.301, "step": 11920 }, { "epoch": 0.3641111789859499, "grad_norm": 0.3935886025428772, "learning_rate": 3.535144186856369e-05, "loss": 4.3324, "step": 11921 }, { "epoch": 0.36414172266340866, "grad_norm": 0.38887807726860046, "learning_rate": 3.534925822534926e-05, "loss": 4.3439, "step": 11922 }, { "epoch": 0.36417226634086747, "grad_norm": 0.39201799035072327, "learning_rate": 3.534707448684388e-05, "loss": 4.3752, "step": 11923 }, { "epoch": 0.3642028100183262, "grad_norm": 0.3784036934375763, "learning_rate": 3.534489065306766e-05, "loss": 4.3068, "step": 11924 }, { "epoch": 0.36423335369578497, "grad_norm": 0.37745821475982666, "learning_rate": 3.5342706724040734e-05, "loss": 4.3339, "step": 11925 }, { "epoch": 0.3642638973732437, "grad_norm": 0.38115212321281433, "learning_rate": 3.5340522699783166e-05, "loss": 4.435, "step": 11926 }, { "epoch": 0.3642944410507025, "grad_norm": 0.3802695870399475, "learning_rate": 3.53383385803151e-05, "loss": 4.3727, "step": 11927 }, { "epoch": 0.36432498472816127, "grad_norm": 0.38545820116996765, "learning_rate": 3.533615436565663e-05, "loss": 4.2764, "step": 11928 }, { "epoch": 0.36435552840562, "grad_norm": 0.38015249371528625, "learning_rate": 3.533397005582788e-05, "loss": 4.3429, "step": 11929 }, { "epoch": 0.3643860720830788, "grad_norm": 0.3960558772087097, "learning_rate": 3.533178565084895e-05, "loss": 4.3859, "step": 11930 }, { "epoch": 0.3644166157605376, "grad_norm": 0.3897336721420288, "learning_rate": 3.532960115073995e-05, "loss": 4.3055, "step": 11931 }, { "epoch": 0.3644471594379963, "grad_norm": 0.3787328898906708, "learning_rate": 3.532741655552102e-05, "loss": 4.3274, "step": 11932 }, { "epoch": 0.3644777031154551, "grad_norm": 0.38783490657806396, "learning_rate": 3.532523186521224e-05, "loss": 4.337, "step": 11933 }, { "epoch": 0.3645082467929139, "grad_norm": 0.38002467155456543, "learning_rate": 3.5323047079833745e-05, "loss": 4.3856, "step": 11934 }, { "epoch": 0.36453879047037263, "grad_norm": 0.38867485523223877, "learning_rate": 3.532086219940565e-05, "loss": 4.3108, "step": 11935 }, { "epoch": 0.3645693341478314, "grad_norm": 0.3818596601486206, "learning_rate": 3.531867722394807e-05, "loss": 4.3441, "step": 11936 }, { "epoch": 0.3645998778252902, "grad_norm": 0.3856024146080017, "learning_rate": 3.531649215348113e-05, "loss": 4.2677, "step": 11937 }, { "epoch": 0.36463042150274894, "grad_norm": 0.38417667150497437, "learning_rate": 3.5314306988024934e-05, "loss": 4.2969, "step": 11938 }, { "epoch": 0.3646609651802077, "grad_norm": 0.37175625562667847, "learning_rate": 3.531212172759961e-05, "loss": 4.3497, "step": 11939 }, { "epoch": 0.36469150885766644, "grad_norm": 0.3871558904647827, "learning_rate": 3.5309936372225285e-05, "loss": 4.4236, "step": 11940 }, { "epoch": 0.36472205253512524, "grad_norm": 0.3882213532924652, "learning_rate": 3.530775092192207e-05, "loss": 4.2777, "step": 11941 }, { "epoch": 0.364752596212584, "grad_norm": 0.38079237937927246, "learning_rate": 3.530556537671009e-05, "loss": 4.289, "step": 11942 }, { "epoch": 0.36478313989004274, "grad_norm": 0.38831669092178345, "learning_rate": 3.530337973660948e-05, "loss": 4.3469, "step": 11943 }, { "epoch": 0.36481368356750155, "grad_norm": 0.3780214190483093, "learning_rate": 3.530119400164034e-05, "loss": 4.3463, "step": 11944 }, { "epoch": 0.3648442272449603, "grad_norm": 0.3728168308734894, "learning_rate": 3.5299008171822826e-05, "loss": 4.3068, "step": 11945 }, { "epoch": 0.36487477092241904, "grad_norm": 0.3777100741863251, "learning_rate": 3.5296822247177046e-05, "loss": 4.3209, "step": 11946 }, { "epoch": 0.36490531459987785, "grad_norm": 0.38415995240211487, "learning_rate": 3.529463622772312e-05, "loss": 4.3023, "step": 11947 }, { "epoch": 0.3649358582773366, "grad_norm": 0.37695321440696716, "learning_rate": 3.5292450113481196e-05, "loss": 4.3914, "step": 11948 }, { "epoch": 0.36496640195479535, "grad_norm": 0.3851251006126404, "learning_rate": 3.5290263904471385e-05, "loss": 4.3884, "step": 11949 }, { "epoch": 0.3649969456322541, "grad_norm": 0.38641583919525146, "learning_rate": 3.528807760071383e-05, "loss": 4.3111, "step": 11950 }, { "epoch": 0.3650274893097129, "grad_norm": 0.38586321473121643, "learning_rate": 3.528589120222865e-05, "loss": 4.3036, "step": 11951 }, { "epoch": 0.36505803298717165, "grad_norm": 0.38917282223701477, "learning_rate": 3.528370470903598e-05, "loss": 4.2757, "step": 11952 }, { "epoch": 0.3650885766646304, "grad_norm": 0.38122865557670593, "learning_rate": 3.528151812115596e-05, "loss": 4.3061, "step": 11953 }, { "epoch": 0.3651191203420892, "grad_norm": 0.38209256529808044, "learning_rate": 3.527933143860871e-05, "loss": 4.2694, "step": 11954 }, { "epoch": 0.36514966401954796, "grad_norm": 0.37801480293273926, "learning_rate": 3.527714466141437e-05, "loss": 4.3329, "step": 11955 }, { "epoch": 0.3651802076970067, "grad_norm": 0.39550867676734924, "learning_rate": 3.527495778959308e-05, "loss": 4.3224, "step": 11956 }, { "epoch": 0.36521075137446546, "grad_norm": 0.37779515981674194, "learning_rate": 3.527277082316497e-05, "loss": 4.3872, "step": 11957 }, { "epoch": 0.36524129505192426, "grad_norm": 0.37559691071510315, "learning_rate": 3.527058376215017e-05, "loss": 4.3626, "step": 11958 }, { "epoch": 0.365271838729383, "grad_norm": 0.3773525357246399, "learning_rate": 3.526839660656884e-05, "loss": 4.402, "step": 11959 }, { "epoch": 0.36530238240684176, "grad_norm": 0.38016125559806824, "learning_rate": 3.5266209356441096e-05, "loss": 4.2157, "step": 11960 }, { "epoch": 0.36533292608430057, "grad_norm": 0.37153008580207825, "learning_rate": 3.526402201178708e-05, "loss": 4.3732, "step": 11961 }, { "epoch": 0.3653634697617593, "grad_norm": 0.3716167211532593, "learning_rate": 3.5261834572626935e-05, "loss": 4.302, "step": 11962 }, { "epoch": 0.36539401343921807, "grad_norm": 0.37649068236351013, "learning_rate": 3.525964703898081e-05, "loss": 4.2714, "step": 11963 }, { "epoch": 0.3654245571166769, "grad_norm": 0.3752545118331909, "learning_rate": 3.525745941086883e-05, "loss": 4.3699, "step": 11964 }, { "epoch": 0.3654551007941356, "grad_norm": 0.3796350359916687, "learning_rate": 3.525527168831115e-05, "loss": 4.3396, "step": 11965 }, { "epoch": 0.3654856444715944, "grad_norm": 0.3791279196739197, "learning_rate": 3.525308387132792e-05, "loss": 4.314, "step": 11966 }, { "epoch": 0.3655161881490531, "grad_norm": 0.3708548843860626, "learning_rate": 3.5250895959939266e-05, "loss": 4.3414, "step": 11967 }, { "epoch": 0.36554673182651193, "grad_norm": 0.3708648681640625, "learning_rate": 3.524870795416534e-05, "loss": 4.4015, "step": 11968 }, { "epoch": 0.3655772755039707, "grad_norm": 0.3793962001800537, "learning_rate": 3.52465198540263e-05, "loss": 4.2997, "step": 11969 }, { "epoch": 0.3656078191814294, "grad_norm": 0.39179620146751404, "learning_rate": 3.524433165954229e-05, "loss": 4.2511, "step": 11970 }, { "epoch": 0.36563836285888823, "grad_norm": 0.3733266294002533, "learning_rate": 3.524214337073343e-05, "loss": 4.2817, "step": 11971 }, { "epoch": 0.365668906536347, "grad_norm": 0.37834054231643677, "learning_rate": 3.52399549876199e-05, "loss": 4.2527, "step": 11972 }, { "epoch": 0.36569945021380573, "grad_norm": 0.3723812997341156, "learning_rate": 3.523776651022184e-05, "loss": 4.2765, "step": 11973 }, { "epoch": 0.3657299938912645, "grad_norm": 0.38150572776794434, "learning_rate": 3.52355779385594e-05, "loss": 4.3242, "step": 11974 }, { "epoch": 0.3657605375687233, "grad_norm": 0.3773115277290344, "learning_rate": 3.523338927265273e-05, "loss": 4.3272, "step": 11975 }, { "epoch": 0.36579108124618204, "grad_norm": 0.38578349351882935, "learning_rate": 3.523120051252199e-05, "loss": 4.3873, "step": 11976 }, { "epoch": 0.3658216249236408, "grad_norm": 0.3828534185886383, "learning_rate": 3.522901165818732e-05, "loss": 4.3958, "step": 11977 }, { "epoch": 0.3658521686010996, "grad_norm": 0.37623855471611023, "learning_rate": 3.5226822709668875e-05, "loss": 4.422, "step": 11978 }, { "epoch": 0.36588271227855834, "grad_norm": 0.37505918741226196, "learning_rate": 3.522463366698683e-05, "loss": 4.3464, "step": 11979 }, { "epoch": 0.3659132559560171, "grad_norm": 0.3702109754085541, "learning_rate": 3.5222444530161314e-05, "loss": 4.3937, "step": 11980 }, { "epoch": 0.3659437996334759, "grad_norm": 0.36976999044418335, "learning_rate": 3.5220255299212494e-05, "loss": 4.2797, "step": 11981 }, { "epoch": 0.36597434331093465, "grad_norm": 0.386533260345459, "learning_rate": 3.5218065974160536e-05, "loss": 4.2371, "step": 11982 }, { "epoch": 0.3660048869883934, "grad_norm": 0.3685789108276367, "learning_rate": 3.521587655502559e-05, "loss": 4.3503, "step": 11983 }, { "epoch": 0.36603543066585215, "grad_norm": 0.393221378326416, "learning_rate": 3.521368704182782e-05, "loss": 4.1671, "step": 11984 }, { "epoch": 0.36606597434331095, "grad_norm": 0.3737633228302002, "learning_rate": 3.521149743458737e-05, "loss": 4.3471, "step": 11985 }, { "epoch": 0.3660965180207697, "grad_norm": 0.3716346025466919, "learning_rate": 3.5209307733324426e-05, "loss": 4.3483, "step": 11986 }, { "epoch": 0.36612706169822845, "grad_norm": 0.3770924508571625, "learning_rate": 3.520711793805913e-05, "loss": 4.1503, "step": 11987 }, { "epoch": 0.36615760537568726, "grad_norm": 0.37404322624206543, "learning_rate": 3.5204928048811645e-05, "loss": 4.3314, "step": 11988 }, { "epoch": 0.366188149053146, "grad_norm": 0.3887651860713959, "learning_rate": 3.520273806560215e-05, "loss": 4.2998, "step": 11989 }, { "epoch": 0.36621869273060476, "grad_norm": 0.3817310333251953, "learning_rate": 3.52005479884508e-05, "loss": 4.2738, "step": 11990 }, { "epoch": 0.3662492364080635, "grad_norm": 0.3806688189506531, "learning_rate": 3.5198357817377755e-05, "loss": 4.3994, "step": 11991 }, { "epoch": 0.3662797800855223, "grad_norm": 0.3804086148738861, "learning_rate": 3.519616755240319e-05, "loss": 4.3693, "step": 11992 }, { "epoch": 0.36631032376298106, "grad_norm": 0.3843497037887573, "learning_rate": 3.5193977193547265e-05, "loss": 4.2989, "step": 11993 }, { "epoch": 0.3663408674404398, "grad_norm": 0.38353416323661804, "learning_rate": 3.519178674083016e-05, "loss": 4.2699, "step": 11994 }, { "epoch": 0.3663714111178986, "grad_norm": 0.3697720468044281, "learning_rate": 3.5189596194272016e-05, "loss": 4.2962, "step": 11995 }, { "epoch": 0.36640195479535737, "grad_norm": 0.3756287693977356, "learning_rate": 3.518740555389303e-05, "loss": 4.3579, "step": 11996 }, { "epoch": 0.3664324984728161, "grad_norm": 0.3811618983745575, "learning_rate": 3.518521481971337e-05, "loss": 4.2619, "step": 11997 }, { "epoch": 0.3664630421502749, "grad_norm": 0.3734477758407593, "learning_rate": 3.518302399175319e-05, "loss": 4.3722, "step": 11998 }, { "epoch": 0.36649358582773367, "grad_norm": 0.3831745684146881, "learning_rate": 3.5180833070032675e-05, "loss": 4.3148, "step": 11999 }, { "epoch": 0.3665241295051924, "grad_norm": 0.3789549767971039, "learning_rate": 3.5178642054572006e-05, "loss": 4.2461, "step": 12000 }, { "epoch": 0.36655467318265117, "grad_norm": 0.38121920824050903, "learning_rate": 3.5176450945391336e-05, "loss": 4.3607, "step": 12001 }, { "epoch": 0.36658521686011, "grad_norm": 0.37424877285957336, "learning_rate": 3.517425974251085e-05, "loss": 4.4052, "step": 12002 }, { "epoch": 0.3666157605375687, "grad_norm": 0.3795763850212097, "learning_rate": 3.517206844595073e-05, "loss": 4.3286, "step": 12003 }, { "epoch": 0.3666463042150275, "grad_norm": 0.38189998269081116, "learning_rate": 3.5169877055731136e-05, "loss": 4.3283, "step": 12004 }, { "epoch": 0.3666768478924863, "grad_norm": 0.3864187002182007, "learning_rate": 3.516768557187226e-05, "loss": 4.3453, "step": 12005 }, { "epoch": 0.36670739156994503, "grad_norm": 0.3865741491317749, "learning_rate": 3.516549399439428e-05, "loss": 4.3378, "step": 12006 }, { "epoch": 0.3667379352474038, "grad_norm": 0.3907926380634308, "learning_rate": 3.516330232331736e-05, "loss": 4.3087, "step": 12007 }, { "epoch": 0.36676847892486253, "grad_norm": 0.37564441561698914, "learning_rate": 3.5161110558661704e-05, "loss": 4.2414, "step": 12008 }, { "epoch": 0.36679902260232133, "grad_norm": 0.38599610328674316, "learning_rate": 3.515891870044747e-05, "loss": 4.3244, "step": 12009 }, { "epoch": 0.3668295662797801, "grad_norm": 0.381735622882843, "learning_rate": 3.515672674869485e-05, "loss": 4.3332, "step": 12010 }, { "epoch": 0.36686010995723883, "grad_norm": 0.365019291639328, "learning_rate": 3.5154534703424023e-05, "loss": 4.2922, "step": 12011 }, { "epoch": 0.36689065363469764, "grad_norm": 0.3861011564731598, "learning_rate": 3.515234256465517e-05, "loss": 4.3877, "step": 12012 }, { "epoch": 0.3669211973121564, "grad_norm": 0.4078198969364166, "learning_rate": 3.515015033240848e-05, "loss": 4.3219, "step": 12013 }, { "epoch": 0.36695174098961514, "grad_norm": 0.3986310362815857, "learning_rate": 3.5147958006704145e-05, "loss": 4.2404, "step": 12014 }, { "epoch": 0.3669822846670739, "grad_norm": 0.3995329439640045, "learning_rate": 3.514576558756234e-05, "loss": 4.2421, "step": 12015 }, { "epoch": 0.3670128283445327, "grad_norm": 0.3860873878002167, "learning_rate": 3.5143573075003256e-05, "loss": 4.319, "step": 12016 }, { "epoch": 0.36704337202199144, "grad_norm": 0.37973493337631226, "learning_rate": 3.5141380469047084e-05, "loss": 4.3526, "step": 12017 }, { "epoch": 0.3670739156994502, "grad_norm": 0.3833291232585907, "learning_rate": 3.5139187769714e-05, "loss": 4.2879, "step": 12018 }, { "epoch": 0.367104459376909, "grad_norm": 0.37924695014953613, "learning_rate": 3.5136994977024196e-05, "loss": 4.3907, "step": 12019 }, { "epoch": 0.36713500305436775, "grad_norm": 0.36970627307891846, "learning_rate": 3.5134802090997874e-05, "loss": 4.4, "step": 12020 }, { "epoch": 0.3671655467318265, "grad_norm": 0.3797956109046936, "learning_rate": 3.513260911165522e-05, "loss": 4.2912, "step": 12021 }, { "epoch": 0.3671960904092853, "grad_norm": 0.3832623362541199, "learning_rate": 3.513041603901642e-05, "loss": 4.2853, "step": 12022 }, { "epoch": 0.36722663408674405, "grad_norm": 0.3778877258300781, "learning_rate": 3.512822287310168e-05, "loss": 4.3323, "step": 12023 }, { "epoch": 0.3672571777642028, "grad_norm": 0.38494443893432617, "learning_rate": 3.5126029613931176e-05, "loss": 4.3038, "step": 12024 }, { "epoch": 0.36728772144166155, "grad_norm": 0.3924493193626404, "learning_rate": 3.512383626152511e-05, "loss": 4.3334, "step": 12025 }, { "epoch": 0.36731826511912036, "grad_norm": 0.37736424803733826, "learning_rate": 3.512164281590368e-05, "loss": 4.2259, "step": 12026 }, { "epoch": 0.3673488087965791, "grad_norm": 0.39241868257522583, "learning_rate": 3.5119449277087085e-05, "loss": 4.3904, "step": 12027 }, { "epoch": 0.36737935247403786, "grad_norm": 0.37759989500045776, "learning_rate": 3.5117255645095516e-05, "loss": 4.39, "step": 12028 }, { "epoch": 0.36740989615149666, "grad_norm": 0.38481655716896057, "learning_rate": 3.511506191994917e-05, "loss": 4.2539, "step": 12029 }, { "epoch": 0.3674404398289554, "grad_norm": 0.38112178444862366, "learning_rate": 3.5112868101668246e-05, "loss": 4.2469, "step": 12030 }, { "epoch": 0.36747098350641416, "grad_norm": 0.3933663070201874, "learning_rate": 3.511067419027295e-05, "loss": 4.3409, "step": 12031 }, { "epoch": 0.3675015271838729, "grad_norm": 0.3886698782444, "learning_rate": 3.510848018578348e-05, "loss": 4.2975, "step": 12032 }, { "epoch": 0.3675320708613317, "grad_norm": 0.3974146842956543, "learning_rate": 3.510628608822003e-05, "loss": 4.2835, "step": 12033 }, { "epoch": 0.36756261453879047, "grad_norm": 0.3770034909248352, "learning_rate": 3.510409189760282e-05, "loss": 4.3798, "step": 12034 }, { "epoch": 0.3675931582162492, "grad_norm": 0.37654784321784973, "learning_rate": 3.510189761395203e-05, "loss": 4.3121, "step": 12035 }, { "epoch": 0.367623701893708, "grad_norm": 0.3678385019302368, "learning_rate": 3.509970323728787e-05, "loss": 4.2767, "step": 12036 }, { "epoch": 0.36765424557116677, "grad_norm": 0.38292035460472107, "learning_rate": 3.5097508767630563e-05, "loss": 4.2907, "step": 12037 }, { "epoch": 0.3676847892486255, "grad_norm": 0.3718307912349701, "learning_rate": 3.509531420500029e-05, "loss": 4.3131, "step": 12038 }, { "epoch": 0.3677153329260843, "grad_norm": 0.37674418091773987, "learning_rate": 3.509311954941727e-05, "loss": 4.3133, "step": 12039 }, { "epoch": 0.3677458766035431, "grad_norm": 0.37361466884613037, "learning_rate": 3.5090924800901716e-05, "loss": 4.3586, "step": 12040 }, { "epoch": 0.3677764202810018, "grad_norm": 0.3742763102054596, "learning_rate": 3.508872995947383e-05, "loss": 4.3172, "step": 12041 }, { "epoch": 0.3678069639584606, "grad_norm": 0.38524582982063293, "learning_rate": 3.508653502515381e-05, "loss": 4.297, "step": 12042 }, { "epoch": 0.3678375076359194, "grad_norm": 0.39373138546943665, "learning_rate": 3.508433999796188e-05, "loss": 4.2617, "step": 12043 }, { "epoch": 0.36786805131337813, "grad_norm": 0.3818647563457489, "learning_rate": 3.508214487791825e-05, "loss": 4.292, "step": 12044 }, { "epoch": 0.3678985949908369, "grad_norm": 0.37577930092811584, "learning_rate": 3.5079949665043124e-05, "loss": 4.211, "step": 12045 }, { "epoch": 0.3679291386682957, "grad_norm": 0.3725276291370392, "learning_rate": 3.507775435935672e-05, "loss": 4.361, "step": 12046 }, { "epoch": 0.36795968234575444, "grad_norm": 0.3947746455669403, "learning_rate": 3.5075558960879256e-05, "loss": 4.3417, "step": 12047 }, { "epoch": 0.3679902260232132, "grad_norm": 0.39531758427619934, "learning_rate": 3.507336346963094e-05, "loss": 4.3057, "step": 12048 }, { "epoch": 0.36802076970067193, "grad_norm": 0.375556617975235, "learning_rate": 3.507116788563198e-05, "loss": 4.2786, "step": 12049 }, { "epoch": 0.36805131337813074, "grad_norm": 0.3781234920024872, "learning_rate": 3.506897220890259e-05, "loss": 4.3046, "step": 12050 }, { "epoch": 0.3680818570555895, "grad_norm": 0.377947598695755, "learning_rate": 3.5066776439463016e-05, "loss": 4.2195, "step": 12051 }, { "epoch": 0.36811240073304824, "grad_norm": 0.3949406147003174, "learning_rate": 3.506458057733345e-05, "loss": 4.3266, "step": 12052 }, { "epoch": 0.36814294441050704, "grad_norm": 0.3754715025424957, "learning_rate": 3.506238462253411e-05, "loss": 4.3771, "step": 12053 }, { "epoch": 0.3681734880879658, "grad_norm": 0.38131240010261536, "learning_rate": 3.506018857508522e-05, "loss": 4.3575, "step": 12054 }, { "epoch": 0.36820403176542454, "grad_norm": 0.39284786581993103, "learning_rate": 3.505799243500701e-05, "loss": 4.3565, "step": 12055 }, { "epoch": 0.36823457544288335, "grad_norm": 0.37011095881462097, "learning_rate": 3.505579620231969e-05, "loss": 4.3326, "step": 12056 }, { "epoch": 0.3682651191203421, "grad_norm": 0.3851582109928131, "learning_rate": 3.5053599877043484e-05, "loss": 4.4318, "step": 12057 }, { "epoch": 0.36829566279780085, "grad_norm": 0.39269348978996277, "learning_rate": 3.505140345919862e-05, "loss": 4.3303, "step": 12058 }, { "epoch": 0.3683262064752596, "grad_norm": 0.3722977936267853, "learning_rate": 3.504920694880531e-05, "loss": 4.3975, "step": 12059 }, { "epoch": 0.3683567501527184, "grad_norm": 0.37620794773101807, "learning_rate": 3.504701034588378e-05, "loss": 4.2861, "step": 12060 }, { "epoch": 0.36838729383017715, "grad_norm": 0.4014233350753784, "learning_rate": 3.504481365045426e-05, "loss": 4.3142, "step": 12061 }, { "epoch": 0.3684178375076359, "grad_norm": 0.38810309767723083, "learning_rate": 3.5042616862536983e-05, "loss": 4.3141, "step": 12062 }, { "epoch": 0.3684483811850947, "grad_norm": 0.39789891242980957, "learning_rate": 3.5040419982152174e-05, "loss": 4.3577, "step": 12063 }, { "epoch": 0.36847892486255346, "grad_norm": 0.38011717796325684, "learning_rate": 3.503822300932005e-05, "loss": 4.3226, "step": 12064 }, { "epoch": 0.3685094685400122, "grad_norm": 0.3764069378376007, "learning_rate": 3.503602594406084e-05, "loss": 4.3376, "step": 12065 }, { "epoch": 0.36854001221747096, "grad_norm": 0.39128589630126953, "learning_rate": 3.503382878639479e-05, "loss": 4.2545, "step": 12066 }, { "epoch": 0.36857055589492976, "grad_norm": 0.38242003321647644, "learning_rate": 3.5031631536342106e-05, "loss": 4.2834, "step": 12067 }, { "epoch": 0.3686010995723885, "grad_norm": 0.3897708058357239, "learning_rate": 3.502943419392304e-05, "loss": 4.2143, "step": 12068 }, { "epoch": 0.36863164324984726, "grad_norm": 0.3807123005390167, "learning_rate": 3.502723675915782e-05, "loss": 4.2342, "step": 12069 }, { "epoch": 0.36866218692730607, "grad_norm": 0.3767542243003845, "learning_rate": 3.502503923206667e-05, "loss": 4.3405, "step": 12070 }, { "epoch": 0.3686927306047648, "grad_norm": 0.394223153591156, "learning_rate": 3.502284161266983e-05, "loss": 4.3314, "step": 12071 }, { "epoch": 0.36872327428222357, "grad_norm": 0.3847419321537018, "learning_rate": 3.502064390098754e-05, "loss": 4.3642, "step": 12072 }, { "epoch": 0.3687538179596824, "grad_norm": 0.38012856245040894, "learning_rate": 3.501844609704003e-05, "loss": 4.2985, "step": 12073 }, { "epoch": 0.3687843616371411, "grad_norm": 0.3819974958896637, "learning_rate": 3.501624820084752e-05, "loss": 4.3188, "step": 12074 }, { "epoch": 0.3688149053145999, "grad_norm": 0.3865278661251068, "learning_rate": 3.5014050212430284e-05, "loss": 4.3961, "step": 12075 }, { "epoch": 0.3688454489920586, "grad_norm": 0.38769254088401794, "learning_rate": 3.501185213180852e-05, "loss": 4.2889, "step": 12076 }, { "epoch": 0.3688759926695174, "grad_norm": 0.3796493411064148, "learning_rate": 3.50096539590025e-05, "loss": 4.3179, "step": 12077 }, { "epoch": 0.3689065363469762, "grad_norm": 0.3827893137931824, "learning_rate": 3.500745569403245e-05, "loss": 4.3213, "step": 12078 }, { "epoch": 0.3689370800244349, "grad_norm": 0.3877360224723816, "learning_rate": 3.500525733691861e-05, "loss": 4.3054, "step": 12079 }, { "epoch": 0.36896762370189373, "grad_norm": 0.38147252798080444, "learning_rate": 3.500305888768121e-05, "loss": 4.4105, "step": 12080 }, { "epoch": 0.3689981673793525, "grad_norm": 0.3781808614730835, "learning_rate": 3.5000860346340506e-05, "loss": 4.3396, "step": 12081 }, { "epoch": 0.36902871105681123, "grad_norm": 0.37738677859306335, "learning_rate": 3.4998661712916746e-05, "loss": 4.323, "step": 12082 }, { "epoch": 0.36905925473427, "grad_norm": 0.3869275152683258, "learning_rate": 3.499646298743016e-05, "loss": 4.2498, "step": 12083 }, { "epoch": 0.3690897984117288, "grad_norm": 0.3926597833633423, "learning_rate": 3.4994264169901006e-05, "loss": 4.2179, "step": 12084 }, { "epoch": 0.36912034208918754, "grad_norm": 0.38046929240226746, "learning_rate": 3.499206526034951e-05, "loss": 4.3643, "step": 12085 }, { "epoch": 0.3691508857666463, "grad_norm": 0.37823083996772766, "learning_rate": 3.498986625879595e-05, "loss": 4.3946, "step": 12086 }, { "epoch": 0.3691814294441051, "grad_norm": 0.3979606330394745, "learning_rate": 3.498766716526055e-05, "loss": 4.31, "step": 12087 }, { "epoch": 0.36921197312156384, "grad_norm": 0.3987903594970703, "learning_rate": 3.498546797976356e-05, "loss": 4.3232, "step": 12088 }, { "epoch": 0.3692425167990226, "grad_norm": 0.38469067215919495, "learning_rate": 3.4983268702325236e-05, "loss": 4.2859, "step": 12089 }, { "epoch": 0.36927306047648134, "grad_norm": 0.36651596426963806, "learning_rate": 3.4981069332965824e-05, "loss": 4.3329, "step": 12090 }, { "epoch": 0.36930360415394015, "grad_norm": 0.3816641569137573, "learning_rate": 3.497886987170557e-05, "loss": 4.3911, "step": 12091 }, { "epoch": 0.3693341478313989, "grad_norm": 0.38129931688308716, "learning_rate": 3.4976670318564726e-05, "loss": 4.2889, "step": 12092 }, { "epoch": 0.36936469150885765, "grad_norm": 0.38694268465042114, "learning_rate": 3.497447067356356e-05, "loss": 4.3535, "step": 12093 }, { "epoch": 0.36939523518631645, "grad_norm": 0.38206472992897034, "learning_rate": 3.497227093672231e-05, "loss": 4.3537, "step": 12094 }, { "epoch": 0.3694257788637752, "grad_norm": 0.40528324246406555, "learning_rate": 3.497007110806123e-05, "loss": 4.2845, "step": 12095 }, { "epoch": 0.36945632254123395, "grad_norm": 0.39484256505966187, "learning_rate": 3.496787118760059e-05, "loss": 4.3609, "step": 12096 }, { "epoch": 0.36948686621869276, "grad_norm": 0.3773517310619354, "learning_rate": 3.496567117536062e-05, "loss": 4.2441, "step": 12097 }, { "epoch": 0.3695174098961515, "grad_norm": 0.3841818869113922, "learning_rate": 3.4963471071361596e-05, "loss": 4.2952, "step": 12098 }, { "epoch": 0.36954795357361025, "grad_norm": 0.38940203189849854, "learning_rate": 3.4961270875623784e-05, "loss": 4.3971, "step": 12099 }, { "epoch": 0.369578497251069, "grad_norm": 0.38372498750686646, "learning_rate": 3.4959070588167414e-05, "loss": 4.2935, "step": 12100 }, { "epoch": 0.3696090409285278, "grad_norm": 0.3740215599536896, "learning_rate": 3.495687020901277e-05, "loss": 4.2648, "step": 12101 }, { "epoch": 0.36963958460598656, "grad_norm": 0.37480732798576355, "learning_rate": 3.49546697381801e-05, "loss": 4.2082, "step": 12102 }, { "epoch": 0.3696701282834453, "grad_norm": 0.38458970189094543, "learning_rate": 3.4952469175689666e-05, "loss": 4.3269, "step": 12103 }, { "epoch": 0.3697006719609041, "grad_norm": 0.38439634442329407, "learning_rate": 3.495026852156173e-05, "loss": 4.2183, "step": 12104 }, { "epoch": 0.36973121563836286, "grad_norm": 0.3754994869232178, "learning_rate": 3.494806777581656e-05, "loss": 4.4159, "step": 12105 }, { "epoch": 0.3697617593158216, "grad_norm": 0.3788588047027588, "learning_rate": 3.494586693847442e-05, "loss": 4.1949, "step": 12106 }, { "epoch": 0.36979230299328036, "grad_norm": 0.3848138451576233, "learning_rate": 3.494366600955555e-05, "loss": 4.2622, "step": 12107 }, { "epoch": 0.36982284667073917, "grad_norm": 0.38926416635513306, "learning_rate": 3.494146498908025e-05, "loss": 4.3304, "step": 12108 }, { "epoch": 0.3698533903481979, "grad_norm": 0.3951534330844879, "learning_rate": 3.493926387706877e-05, "loss": 4.3771, "step": 12109 }, { "epoch": 0.36988393402565667, "grad_norm": 0.37974175810813904, "learning_rate": 3.493706267354138e-05, "loss": 4.261, "step": 12110 }, { "epoch": 0.3699144777031155, "grad_norm": 0.37236350774765015, "learning_rate": 3.493486137851833e-05, "loss": 4.3535, "step": 12111 }, { "epoch": 0.3699450213805742, "grad_norm": 0.3755040764808655, "learning_rate": 3.4932659992019915e-05, "loss": 4.2952, "step": 12112 }, { "epoch": 0.369975565058033, "grad_norm": 0.38677653670310974, "learning_rate": 3.4930458514066395e-05, "loss": 4.3431, "step": 12113 }, { "epoch": 0.3700061087354918, "grad_norm": 0.3913761377334595, "learning_rate": 3.4928256944678026e-05, "loss": 4.2563, "step": 12114 }, { "epoch": 0.37003665241295053, "grad_norm": 0.3684728741645813, "learning_rate": 3.4926055283875104e-05, "loss": 4.2809, "step": 12115 }, { "epoch": 0.3700671960904093, "grad_norm": 0.373172789812088, "learning_rate": 3.492385353167788e-05, "loss": 4.2508, "step": 12116 }, { "epoch": 0.37009773976786803, "grad_norm": 0.3727125823497772, "learning_rate": 3.4921651688106636e-05, "loss": 4.3158, "step": 12117 }, { "epoch": 0.37012828344532683, "grad_norm": 0.37038177251815796, "learning_rate": 3.4919449753181646e-05, "loss": 4.2438, "step": 12118 }, { "epoch": 0.3701588271227856, "grad_norm": 0.36795589327812195, "learning_rate": 3.491724772692318e-05, "loss": 4.3445, "step": 12119 }, { "epoch": 0.37018937080024433, "grad_norm": 0.3803277015686035, "learning_rate": 3.4915045609351514e-05, "loss": 4.2873, "step": 12120 }, { "epoch": 0.37021991447770314, "grad_norm": 0.37275904417037964, "learning_rate": 3.491284340048692e-05, "loss": 4.3252, "step": 12121 }, { "epoch": 0.3702504581551619, "grad_norm": 0.3854007124900818, "learning_rate": 3.491064110034969e-05, "loss": 4.3129, "step": 12122 }, { "epoch": 0.37028100183262064, "grad_norm": 0.3696020543575287, "learning_rate": 3.490843870896009e-05, "loss": 4.3348, "step": 12123 }, { "epoch": 0.3703115455100794, "grad_norm": 0.37791717052459717, "learning_rate": 3.49062362263384e-05, "loss": 4.3534, "step": 12124 }, { "epoch": 0.3703420891875382, "grad_norm": 0.3714600205421448, "learning_rate": 3.49040336525049e-05, "loss": 4.3087, "step": 12125 }, { "epoch": 0.37037263286499694, "grad_norm": 0.3855575621128082, "learning_rate": 3.490183098747987e-05, "loss": 4.3982, "step": 12126 }, { "epoch": 0.3704031765424557, "grad_norm": 0.4005040228366852, "learning_rate": 3.489962823128359e-05, "loss": 4.311, "step": 12127 }, { "epoch": 0.3704337202199145, "grad_norm": 0.37829986214637756, "learning_rate": 3.4897425383936336e-05, "loss": 4.2473, "step": 12128 }, { "epoch": 0.37046426389737325, "grad_norm": 0.38097792863845825, "learning_rate": 3.4895222445458406e-05, "loss": 4.2604, "step": 12129 }, { "epoch": 0.370494807574832, "grad_norm": 0.3797462284564972, "learning_rate": 3.489301941587007e-05, "loss": 4.3123, "step": 12130 }, { "epoch": 0.3705253512522908, "grad_norm": 0.3736781179904938, "learning_rate": 3.489081629519162e-05, "loss": 4.2747, "step": 12131 }, { "epoch": 0.37055589492974955, "grad_norm": 0.38049766421318054, "learning_rate": 3.488861308344334e-05, "loss": 4.3445, "step": 12132 }, { "epoch": 0.3705864386072083, "grad_norm": 0.3817465305328369, "learning_rate": 3.488640978064552e-05, "loss": 4.3348, "step": 12133 }, { "epoch": 0.37061698228466705, "grad_norm": 0.3825176954269409, "learning_rate": 3.488420638681844e-05, "loss": 4.4043, "step": 12134 }, { "epoch": 0.37064752596212586, "grad_norm": 0.38281819224357605, "learning_rate": 3.488200290198238e-05, "loss": 4.2793, "step": 12135 }, { "epoch": 0.3706780696395846, "grad_norm": 0.3760879635810852, "learning_rate": 3.487979932615765e-05, "loss": 4.3428, "step": 12136 }, { "epoch": 0.37070861331704336, "grad_norm": 0.4024777412414551, "learning_rate": 3.487759565936452e-05, "loss": 4.3164, "step": 12137 }, { "epoch": 0.37073915699450216, "grad_norm": 0.37470003962516785, "learning_rate": 3.487539190162329e-05, "loss": 4.2971, "step": 12138 }, { "epoch": 0.3707697006719609, "grad_norm": 0.38030219078063965, "learning_rate": 3.4873188052954254e-05, "loss": 4.3797, "step": 12139 }, { "epoch": 0.37080024434941966, "grad_norm": 0.38213685154914856, "learning_rate": 3.487098411337769e-05, "loss": 4.3985, "step": 12140 }, { "epoch": 0.3708307880268784, "grad_norm": 0.3945949971675873, "learning_rate": 3.486878008291391e-05, "loss": 4.2756, "step": 12141 }, { "epoch": 0.3708613317043372, "grad_norm": 0.3838873505592346, "learning_rate": 3.48665759615832e-05, "loss": 4.2534, "step": 12142 }, { "epoch": 0.37089187538179597, "grad_norm": 0.377149373292923, "learning_rate": 3.4864371749405846e-05, "loss": 4.4254, "step": 12143 }, { "epoch": 0.3709224190592547, "grad_norm": 0.3779476583003998, "learning_rate": 3.486216744640215e-05, "loss": 4.2833, "step": 12144 }, { "epoch": 0.3709529627367135, "grad_norm": 0.38462507724761963, "learning_rate": 3.4859963052592405e-05, "loss": 4.324, "step": 12145 }, { "epoch": 0.37098350641417227, "grad_norm": 0.3870343565940857, "learning_rate": 3.485775856799691e-05, "loss": 4.39, "step": 12146 }, { "epoch": 0.371014050091631, "grad_norm": 0.3806225061416626, "learning_rate": 3.485555399263597e-05, "loss": 4.3095, "step": 12147 }, { "epoch": 0.3710445937690898, "grad_norm": 0.37802281975746155, "learning_rate": 3.4853349326529874e-05, "loss": 4.2989, "step": 12148 }, { "epoch": 0.3710751374465486, "grad_norm": 0.3759315311908722, "learning_rate": 3.485114456969893e-05, "loss": 4.31, "step": 12149 }, { "epoch": 0.3711056811240073, "grad_norm": 0.3765518069267273, "learning_rate": 3.484893972216342e-05, "loss": 4.3176, "step": 12150 }, { "epoch": 0.3711362248014661, "grad_norm": 0.38125166296958923, "learning_rate": 3.484673478394367e-05, "loss": 4.3787, "step": 12151 }, { "epoch": 0.3711667684789249, "grad_norm": 0.37867575883865356, "learning_rate": 3.484452975505996e-05, "loss": 4.2343, "step": 12152 }, { "epoch": 0.37119731215638363, "grad_norm": 0.3691994547843933, "learning_rate": 3.484232463553261e-05, "loss": 4.4179, "step": 12153 }, { "epoch": 0.3712278558338424, "grad_norm": 0.386574387550354, "learning_rate": 3.4840119425381915e-05, "loss": 4.3003, "step": 12154 }, { "epoch": 0.3712583995113012, "grad_norm": 0.37699851393699646, "learning_rate": 3.483791412462818e-05, "loss": 4.3293, "step": 12155 }, { "epoch": 0.37128894318875993, "grad_norm": 0.37824493646621704, "learning_rate": 3.4835708733291714e-05, "loss": 4.3545, "step": 12156 }, { "epoch": 0.3713194868662187, "grad_norm": 0.3737007975578308, "learning_rate": 3.483350325139283e-05, "loss": 4.2823, "step": 12157 }, { "epoch": 0.37135003054367743, "grad_norm": 0.38740798830986023, "learning_rate": 3.4831297678951813e-05, "loss": 4.3121, "step": 12158 }, { "epoch": 0.37138057422113624, "grad_norm": 0.38244131207466125, "learning_rate": 3.482909201598899e-05, "loss": 4.3424, "step": 12159 }, { "epoch": 0.371411117898595, "grad_norm": 0.3790387511253357, "learning_rate": 3.482688626252465e-05, "loss": 4.3494, "step": 12160 }, { "epoch": 0.37144166157605374, "grad_norm": 0.3763464093208313, "learning_rate": 3.482468041857912e-05, "loss": 4.2109, "step": 12161 }, { "epoch": 0.37147220525351254, "grad_norm": 0.3781980872154236, "learning_rate": 3.4822474484172716e-05, "loss": 4.322, "step": 12162 }, { "epoch": 0.3715027489309713, "grad_norm": 0.4129895269870758, "learning_rate": 3.4820268459325735e-05, "loss": 4.3882, "step": 12163 }, { "epoch": 0.37153329260843004, "grad_norm": 0.37429457902908325, "learning_rate": 3.481806234405849e-05, "loss": 4.3781, "step": 12164 }, { "epoch": 0.3715638362858888, "grad_norm": 0.39992934465408325, "learning_rate": 3.4815856138391305e-05, "loss": 4.3662, "step": 12165 }, { "epoch": 0.3715943799633476, "grad_norm": 0.39306092262268066, "learning_rate": 3.481364984234447e-05, "loss": 4.3694, "step": 12166 }, { "epoch": 0.37162492364080635, "grad_norm": 0.38749992847442627, "learning_rate": 3.4811443455938335e-05, "loss": 4.3062, "step": 12167 }, { "epoch": 0.3716554673182651, "grad_norm": 0.3939531445503235, "learning_rate": 3.480923697919319e-05, "loss": 4.3583, "step": 12168 }, { "epoch": 0.3716860109957239, "grad_norm": 0.36657240986824036, "learning_rate": 3.4807030412129345e-05, "loss": 4.3464, "step": 12169 }, { "epoch": 0.37171655467318265, "grad_norm": 0.4028450846672058, "learning_rate": 3.480482375476714e-05, "loss": 4.3755, "step": 12170 }, { "epoch": 0.3717470983506414, "grad_norm": 0.3922569453716278, "learning_rate": 3.480261700712688e-05, "loss": 4.416, "step": 12171 }, { "epoch": 0.3717776420281002, "grad_norm": 0.37144434452056885, "learning_rate": 3.480041016922888e-05, "loss": 4.3243, "step": 12172 }, { "epoch": 0.37180818570555896, "grad_norm": 0.3639337420463562, "learning_rate": 3.479820324109347e-05, "loss": 4.3593, "step": 12173 }, { "epoch": 0.3718387293830177, "grad_norm": 0.38741815090179443, "learning_rate": 3.479599622274096e-05, "loss": 4.3652, "step": 12174 }, { "epoch": 0.37186927306047646, "grad_norm": 0.38414642214775085, "learning_rate": 3.4793789114191685e-05, "loss": 4.3374, "step": 12175 }, { "epoch": 0.37189981673793526, "grad_norm": 0.38080087304115295, "learning_rate": 3.479158191546594e-05, "loss": 4.4095, "step": 12176 }, { "epoch": 0.371930360415394, "grad_norm": 0.38009169697761536, "learning_rate": 3.478937462658409e-05, "loss": 4.2352, "step": 12177 }, { "epoch": 0.37196090409285276, "grad_norm": 0.3802106976509094, "learning_rate": 3.478716724756642e-05, "loss": 4.3724, "step": 12178 }, { "epoch": 0.37199144777031157, "grad_norm": 0.38645511865615845, "learning_rate": 3.478495977843327e-05, "loss": 4.343, "step": 12179 }, { "epoch": 0.3720219914477703, "grad_norm": 0.3942466974258423, "learning_rate": 3.478275221920497e-05, "loss": 4.3746, "step": 12180 }, { "epoch": 0.37205253512522907, "grad_norm": 0.3912349045276642, "learning_rate": 3.4780544569901836e-05, "loss": 4.3817, "step": 12181 }, { "epoch": 0.3720830788026878, "grad_norm": 0.3740338981151581, "learning_rate": 3.47783368305442e-05, "loss": 4.3489, "step": 12182 }, { "epoch": 0.3721136224801466, "grad_norm": 0.3805891275405884, "learning_rate": 3.4776129001152385e-05, "loss": 4.3412, "step": 12183 }, { "epoch": 0.37214416615760537, "grad_norm": 0.3739714026451111, "learning_rate": 3.477392108174673e-05, "loss": 4.3301, "step": 12184 }, { "epoch": 0.3721747098350641, "grad_norm": 0.3750925660133362, "learning_rate": 3.477171307234756e-05, "loss": 4.3707, "step": 12185 }, { "epoch": 0.3722052535125229, "grad_norm": 0.3978404998779297, "learning_rate": 3.47695049729752e-05, "loss": 4.4264, "step": 12186 }, { "epoch": 0.3722357971899817, "grad_norm": 0.3746967017650604, "learning_rate": 3.4767296783649984e-05, "loss": 4.315, "step": 12187 }, { "epoch": 0.3722663408674404, "grad_norm": 0.3746529817581177, "learning_rate": 3.4765088504392254e-05, "loss": 4.3255, "step": 12188 }, { "epoch": 0.37229688454489923, "grad_norm": 0.3839770257472992, "learning_rate": 3.476288013522232e-05, "loss": 4.2956, "step": 12189 }, { "epoch": 0.372327428222358, "grad_norm": 0.3833473026752472, "learning_rate": 3.476067167616053e-05, "loss": 4.2514, "step": 12190 }, { "epoch": 0.37235797189981673, "grad_norm": 0.3869752883911133, "learning_rate": 3.475846312722722e-05, "loss": 4.2762, "step": 12191 }, { "epoch": 0.3723885155772755, "grad_norm": 0.3937176764011383, "learning_rate": 3.475625448844273e-05, "loss": 4.3342, "step": 12192 }, { "epoch": 0.3724190592547343, "grad_norm": 0.3898079991340637, "learning_rate": 3.475404575982738e-05, "loss": 4.3415, "step": 12193 }, { "epoch": 0.37244960293219304, "grad_norm": 0.37509793043136597, "learning_rate": 3.475183694140152e-05, "loss": 4.277, "step": 12194 }, { "epoch": 0.3724801466096518, "grad_norm": 0.38174811005592346, "learning_rate": 3.4749628033185484e-05, "loss": 4.3463, "step": 12195 }, { "epoch": 0.3725106902871106, "grad_norm": 0.37939921021461487, "learning_rate": 3.474741903519961e-05, "loss": 4.2524, "step": 12196 }, { "epoch": 0.37254123396456934, "grad_norm": 0.3747628629207611, "learning_rate": 3.474520994746423e-05, "loss": 4.307, "step": 12197 }, { "epoch": 0.3725717776420281, "grad_norm": 0.38006871938705444, "learning_rate": 3.47430007699997e-05, "loss": 4.2764, "step": 12198 }, { "epoch": 0.37260232131948684, "grad_norm": 0.3833317458629608, "learning_rate": 3.474079150282635e-05, "loss": 4.2963, "step": 12199 }, { "epoch": 0.37263286499694565, "grad_norm": 0.3698008060455322, "learning_rate": 3.473858214596452e-05, "loss": 4.338, "step": 12200 }, { "epoch": 0.3726634086744044, "grad_norm": 0.38246792554855347, "learning_rate": 3.473637269943456e-05, "loss": 4.3402, "step": 12201 }, { "epoch": 0.37269395235186314, "grad_norm": 0.38024580478668213, "learning_rate": 3.4734163163256814e-05, "loss": 4.2401, "step": 12202 }, { "epoch": 0.37272449602932195, "grad_norm": 0.3734033405780792, "learning_rate": 3.4731953537451624e-05, "loss": 4.215, "step": 12203 }, { "epoch": 0.3727550397067807, "grad_norm": 0.4008275270462036, "learning_rate": 3.472974382203933e-05, "loss": 4.3081, "step": 12204 }, { "epoch": 0.37278558338423945, "grad_norm": 0.3843529224395752, "learning_rate": 3.4727534017040286e-05, "loss": 4.4111, "step": 12205 }, { "epoch": 0.37281612706169825, "grad_norm": 0.3914659023284912, "learning_rate": 3.472532412247482e-05, "loss": 4.3317, "step": 12206 }, { "epoch": 0.372846670739157, "grad_norm": 0.3892093300819397, "learning_rate": 3.472311413836331e-05, "loss": 4.2809, "step": 12207 }, { "epoch": 0.37287721441661575, "grad_norm": 0.36779773235321045, "learning_rate": 3.472090406472609e-05, "loss": 4.2751, "step": 12208 }, { "epoch": 0.3729077580940745, "grad_norm": 0.3848540186882019, "learning_rate": 3.4718693901583507e-05, "loss": 4.3561, "step": 12209 }, { "epoch": 0.3729383017715333, "grad_norm": 0.37836146354675293, "learning_rate": 3.47164836489559e-05, "loss": 4.3345, "step": 12210 }, { "epoch": 0.37296884544899206, "grad_norm": 0.3889971375465393, "learning_rate": 3.4714273306863645e-05, "loss": 4.2894, "step": 12211 }, { "epoch": 0.3729993891264508, "grad_norm": 0.3802507519721985, "learning_rate": 3.4712062875327085e-05, "loss": 4.1671, "step": 12212 }, { "epoch": 0.3730299328039096, "grad_norm": 0.36717355251312256, "learning_rate": 3.4709852354366554e-05, "loss": 4.3787, "step": 12213 }, { "epoch": 0.37306047648136836, "grad_norm": 0.38897505402565, "learning_rate": 3.4707641744002426e-05, "loss": 4.2645, "step": 12214 }, { "epoch": 0.3730910201588271, "grad_norm": 0.3744080364704132, "learning_rate": 3.470543104425505e-05, "loss": 4.3329, "step": 12215 }, { "epoch": 0.37312156383628586, "grad_norm": 0.38499361276626587, "learning_rate": 3.470322025514479e-05, "loss": 4.3767, "step": 12216 }, { "epoch": 0.37315210751374467, "grad_norm": 0.38074901700019836, "learning_rate": 3.4701009376691974e-05, "loss": 4.291, "step": 12217 }, { "epoch": 0.3731826511912034, "grad_norm": 0.3727312684059143, "learning_rate": 3.469879840891699e-05, "loss": 4.0924, "step": 12218 }, { "epoch": 0.37321319486866217, "grad_norm": 0.38044604659080505, "learning_rate": 3.469658735184017e-05, "loss": 4.2472, "step": 12219 }, { "epoch": 0.373243738546121, "grad_norm": 0.38842588663101196, "learning_rate": 3.46943762054819e-05, "loss": 4.3014, "step": 12220 }, { "epoch": 0.3732742822235797, "grad_norm": 0.38561978936195374, "learning_rate": 3.469216496986252e-05, "loss": 4.329, "step": 12221 }, { "epoch": 0.3733048259010385, "grad_norm": 0.38211676478385925, "learning_rate": 3.468995364500239e-05, "loss": 4.2337, "step": 12222 }, { "epoch": 0.3733353695784973, "grad_norm": 0.3803287148475647, "learning_rate": 3.4687742230921874e-05, "loss": 4.2796, "step": 12223 }, { "epoch": 0.37336591325595603, "grad_norm": 0.38024601340293884, "learning_rate": 3.4685530727641336e-05, "loss": 4.3048, "step": 12224 }, { "epoch": 0.3733964569334148, "grad_norm": 0.3796333074569702, "learning_rate": 3.468331913518114e-05, "loss": 4.3343, "step": 12225 }, { "epoch": 0.3734270006108735, "grad_norm": 0.3786540627479553, "learning_rate": 3.4681107453561635e-05, "loss": 4.3609, "step": 12226 }, { "epoch": 0.37345754428833233, "grad_norm": 0.3919838070869446, "learning_rate": 3.467889568280321e-05, "loss": 4.3731, "step": 12227 }, { "epoch": 0.3734880879657911, "grad_norm": 0.38028836250305176, "learning_rate": 3.4676683822926206e-05, "loss": 4.2897, "step": 12228 }, { "epoch": 0.37351863164324983, "grad_norm": 0.3940971791744232, "learning_rate": 3.4674471873951006e-05, "loss": 4.3559, "step": 12229 }, { "epoch": 0.37354917532070864, "grad_norm": 0.37863174080848694, "learning_rate": 3.4672259835897965e-05, "loss": 4.2899, "step": 12230 }, { "epoch": 0.3735797189981674, "grad_norm": 0.3741084337234497, "learning_rate": 3.4670047708787453e-05, "loss": 4.2801, "step": 12231 }, { "epoch": 0.37361026267562614, "grad_norm": 0.37114498019218445, "learning_rate": 3.466783549263985e-05, "loss": 4.2913, "step": 12232 }, { "epoch": 0.3736408063530849, "grad_norm": 0.381987601518631, "learning_rate": 3.46656231874755e-05, "loss": 4.3007, "step": 12233 }, { "epoch": 0.3736713500305437, "grad_norm": 0.3882400691509247, "learning_rate": 3.4663410793314794e-05, "loss": 4.3462, "step": 12234 }, { "epoch": 0.37370189370800244, "grad_norm": 0.37614670395851135, "learning_rate": 3.46611983101781e-05, "loss": 4.3332, "step": 12235 }, { "epoch": 0.3737324373854612, "grad_norm": 0.37479716539382935, "learning_rate": 3.465898573808579e-05, "loss": 4.338, "step": 12236 }, { "epoch": 0.37376298106292, "grad_norm": 0.3888867497444153, "learning_rate": 3.465677307705822e-05, "loss": 4.2286, "step": 12237 }, { "epoch": 0.37379352474037875, "grad_norm": 0.38059985637664795, "learning_rate": 3.465456032711578e-05, "loss": 4.2218, "step": 12238 }, { "epoch": 0.3738240684178375, "grad_norm": 0.3673456609249115, "learning_rate": 3.465234748827884e-05, "loss": 4.3824, "step": 12239 }, { "epoch": 0.37385461209529625, "grad_norm": 0.38403254747390747, "learning_rate": 3.4650134560567775e-05, "loss": 4.3224, "step": 12240 }, { "epoch": 0.37388515577275505, "grad_norm": 0.3938210606575012, "learning_rate": 3.4647921544002955e-05, "loss": 4.3444, "step": 12241 }, { "epoch": 0.3739156994502138, "grad_norm": 0.36765363812446594, "learning_rate": 3.464570843860476e-05, "loss": 4.374, "step": 12242 }, { "epoch": 0.37394624312767255, "grad_norm": 0.39716836810112, "learning_rate": 3.4643495244393584e-05, "loss": 4.4241, "step": 12243 }, { "epoch": 0.37397678680513136, "grad_norm": 0.3792808949947357, "learning_rate": 3.464128196138977e-05, "loss": 4.3221, "step": 12244 }, { "epoch": 0.3740073304825901, "grad_norm": 0.38071298599243164, "learning_rate": 3.463906858961373e-05, "loss": 4.2684, "step": 12245 }, { "epoch": 0.37403787416004886, "grad_norm": 0.38295885920524597, "learning_rate": 3.463685512908582e-05, "loss": 4.4005, "step": 12246 }, { "epoch": 0.37406841783750766, "grad_norm": 0.40802276134490967, "learning_rate": 3.463464157982643e-05, "loss": 4.2802, "step": 12247 }, { "epoch": 0.3740989615149664, "grad_norm": 0.37716197967529297, "learning_rate": 3.463242794185595e-05, "loss": 4.1112, "step": 12248 }, { "epoch": 0.37412950519242516, "grad_norm": 0.3836039900779724, "learning_rate": 3.463021421519474e-05, "loss": 4.3703, "step": 12249 }, { "epoch": 0.3741600488698839, "grad_norm": 0.37550273537635803, "learning_rate": 3.462800039986321e-05, "loss": 4.3954, "step": 12250 }, { "epoch": 0.3741905925473427, "grad_norm": 0.4027114808559418, "learning_rate": 3.462578649588172e-05, "loss": 4.3651, "step": 12251 }, { "epoch": 0.37422113622480146, "grad_norm": 0.3719639778137207, "learning_rate": 3.462357250327067e-05, "loss": 4.1411, "step": 12252 }, { "epoch": 0.3742516799022602, "grad_norm": 0.38384976983070374, "learning_rate": 3.462135842205044e-05, "loss": 4.2576, "step": 12253 }, { "epoch": 0.374282223579719, "grad_norm": 0.3816823959350586, "learning_rate": 3.461914425224141e-05, "loss": 4.3046, "step": 12254 }, { "epoch": 0.37431276725717777, "grad_norm": 0.3778165578842163, "learning_rate": 3.4616929993863984e-05, "loss": 4.3446, "step": 12255 }, { "epoch": 0.3743433109346365, "grad_norm": 0.3913555145263672, "learning_rate": 3.461471564693853e-05, "loss": 4.3715, "step": 12256 }, { "epoch": 0.37437385461209527, "grad_norm": 0.3887530565261841, "learning_rate": 3.4612501211485455e-05, "loss": 4.3052, "step": 12257 }, { "epoch": 0.3744043982895541, "grad_norm": 0.37733933329582214, "learning_rate": 3.4610286687525135e-05, "loss": 4.3589, "step": 12258 }, { "epoch": 0.3744349419670128, "grad_norm": 0.37165048718452454, "learning_rate": 3.4608072075077966e-05, "loss": 4.2833, "step": 12259 }, { "epoch": 0.3744654856444716, "grad_norm": 0.38624295592308044, "learning_rate": 3.460585737416433e-05, "loss": 4.3266, "step": 12260 }, { "epoch": 0.3744960293219304, "grad_norm": 0.38236740231513977, "learning_rate": 3.460364258480463e-05, "loss": 4.3387, "step": 12261 }, { "epoch": 0.37452657299938913, "grad_norm": 0.389584481716156, "learning_rate": 3.460142770701925e-05, "loss": 4.2759, "step": 12262 }, { "epoch": 0.3745571166768479, "grad_norm": 0.38047730922698975, "learning_rate": 3.45992127408286e-05, "loss": 4.4031, "step": 12263 }, { "epoch": 0.3745876603543067, "grad_norm": 0.3837253153324127, "learning_rate": 3.459699768625305e-05, "loss": 4.3212, "step": 12264 }, { "epoch": 0.37461820403176543, "grad_norm": 0.374399870634079, "learning_rate": 3.4594782543313015e-05, "loss": 4.2339, "step": 12265 }, { "epoch": 0.3746487477092242, "grad_norm": 0.3695216178894043, "learning_rate": 3.459256731202889e-05, "loss": 4.3637, "step": 12266 }, { "epoch": 0.37467929138668293, "grad_norm": 0.3723391592502594, "learning_rate": 3.459035199242106e-05, "loss": 4.373, "step": 12267 }, { "epoch": 0.37470983506414174, "grad_norm": 0.37469255924224854, "learning_rate": 3.4588136584509925e-05, "loss": 4.3531, "step": 12268 }, { "epoch": 0.3747403787416005, "grad_norm": 0.38846808671951294, "learning_rate": 3.4585921088315885e-05, "loss": 4.2952, "step": 12269 }, { "epoch": 0.37477092241905924, "grad_norm": 0.39906319975852966, "learning_rate": 3.458370550385936e-05, "loss": 4.3515, "step": 12270 }, { "epoch": 0.37480146609651804, "grad_norm": 0.3843607008457184, "learning_rate": 3.45814898311607e-05, "loss": 4.2598, "step": 12271 }, { "epoch": 0.3748320097739768, "grad_norm": 0.3900719881057739, "learning_rate": 3.457927407024036e-05, "loss": 4.3195, "step": 12272 }, { "epoch": 0.37486255345143554, "grad_norm": 0.3815338611602783, "learning_rate": 3.4577058221118706e-05, "loss": 4.3094, "step": 12273 }, { "epoch": 0.3748930971288943, "grad_norm": 0.374706506729126, "learning_rate": 3.4574842283816164e-05, "loss": 4.3444, "step": 12274 }, { "epoch": 0.3749236408063531, "grad_norm": 0.3801773190498352, "learning_rate": 3.457262625835312e-05, "loss": 4.3359, "step": 12275 }, { "epoch": 0.37495418448381185, "grad_norm": 0.3808535933494568, "learning_rate": 3.4570410144749986e-05, "loss": 4.3454, "step": 12276 }, { "epoch": 0.3749847281612706, "grad_norm": 0.3791535794734955, "learning_rate": 3.4568193943027164e-05, "loss": 4.3537, "step": 12277 }, { "epoch": 0.3750152718387294, "grad_norm": 0.38299620151519775, "learning_rate": 3.456597765320506e-05, "loss": 4.3892, "step": 12278 }, { "epoch": 0.37504581551618815, "grad_norm": 0.3786233365535736, "learning_rate": 3.456376127530409e-05, "loss": 4.323, "step": 12279 }, { "epoch": 0.3750763591936469, "grad_norm": 0.37794482707977295, "learning_rate": 3.4561544809344634e-05, "loss": 4.2983, "step": 12280 }, { "epoch": 0.3751069028711057, "grad_norm": 0.3798395097255707, "learning_rate": 3.455932825534713e-05, "loss": 4.3431, "step": 12281 }, { "epoch": 0.37513744654856446, "grad_norm": 0.3970732092857361, "learning_rate": 3.455711161333198e-05, "loss": 4.1978, "step": 12282 }, { "epoch": 0.3751679902260232, "grad_norm": 0.3895918130874634, "learning_rate": 3.455489488331959e-05, "loss": 4.2432, "step": 12283 }, { "epoch": 0.37519853390348196, "grad_norm": 0.3707330524921417, "learning_rate": 3.455267806533037e-05, "loss": 4.2792, "step": 12284 }, { "epoch": 0.37522907758094076, "grad_norm": 0.38290897011756897, "learning_rate": 3.455046115938472e-05, "loss": 4.2466, "step": 12285 }, { "epoch": 0.3752596212583995, "grad_norm": 0.3739137351512909, "learning_rate": 3.454824416550307e-05, "loss": 4.277, "step": 12286 }, { "epoch": 0.37529016493585826, "grad_norm": 0.3832017779350281, "learning_rate": 3.454602708370583e-05, "loss": 4.3446, "step": 12287 }, { "epoch": 0.37532070861331707, "grad_norm": 0.3700467050075531, "learning_rate": 3.45438099140134e-05, "loss": 4.3429, "step": 12288 }, { "epoch": 0.3753512522907758, "grad_norm": 0.3776700794696808, "learning_rate": 3.454159265644622e-05, "loss": 4.2836, "step": 12289 }, { "epoch": 0.37538179596823457, "grad_norm": 0.3848831057548523, "learning_rate": 3.4539375311024686e-05, "loss": 4.3383, "step": 12290 }, { "epoch": 0.3754123396456933, "grad_norm": 0.38897210359573364, "learning_rate": 3.453715787776922e-05, "loss": 4.2993, "step": 12291 }, { "epoch": 0.3754428833231521, "grad_norm": 0.3643801212310791, "learning_rate": 3.453494035670023e-05, "loss": 4.2505, "step": 12292 }, { "epoch": 0.37547342700061087, "grad_norm": 0.3732999563217163, "learning_rate": 3.453272274783815e-05, "loss": 4.2655, "step": 12293 }, { "epoch": 0.3755039706780696, "grad_norm": 0.3802299499511719, "learning_rate": 3.453050505120339e-05, "loss": 4.3973, "step": 12294 }, { "epoch": 0.3755345143555284, "grad_norm": 0.3911331295967102, "learning_rate": 3.452828726681636e-05, "loss": 4.3448, "step": 12295 }, { "epoch": 0.3755650580329872, "grad_norm": 0.3839174509048462, "learning_rate": 3.4526069394697495e-05, "loss": 4.393, "step": 12296 }, { "epoch": 0.3755956017104459, "grad_norm": 0.37342163920402527, "learning_rate": 3.452385143486722e-05, "loss": 4.306, "step": 12297 }, { "epoch": 0.37562614538790473, "grad_norm": 0.38783401250839233, "learning_rate": 3.452163338734594e-05, "loss": 4.4343, "step": 12298 }, { "epoch": 0.3756566890653635, "grad_norm": 0.37731122970581055, "learning_rate": 3.4519415252154086e-05, "loss": 4.3412, "step": 12299 }, { "epoch": 0.37568723274282223, "grad_norm": 0.3711182475090027, "learning_rate": 3.4517197029312084e-05, "loss": 4.2823, "step": 12300 }, { "epoch": 0.375717776420281, "grad_norm": 0.3799033761024475, "learning_rate": 3.451497871884035e-05, "loss": 4.2445, "step": 12301 }, { "epoch": 0.3757483200977398, "grad_norm": 0.38238033652305603, "learning_rate": 3.451276032075932e-05, "loss": 4.3961, "step": 12302 }, { "epoch": 0.37577886377519854, "grad_norm": 0.38495540618896484, "learning_rate": 3.4510541835089417e-05, "loss": 4.2891, "step": 12303 }, { "epoch": 0.3758094074526573, "grad_norm": 0.38564783334732056, "learning_rate": 3.450832326185106e-05, "loss": 4.2743, "step": 12304 }, { "epoch": 0.3758399511301161, "grad_norm": 0.37795764207839966, "learning_rate": 3.4506104601064685e-05, "loss": 4.3929, "step": 12305 }, { "epoch": 0.37587049480757484, "grad_norm": 0.3859926760196686, "learning_rate": 3.450388585275072e-05, "loss": 4.375, "step": 12306 }, { "epoch": 0.3759010384850336, "grad_norm": 0.3783622980117798, "learning_rate": 3.450166701692959e-05, "loss": 4.3087, "step": 12307 }, { "epoch": 0.37593158216249234, "grad_norm": 0.36976858973503113, "learning_rate": 3.449944809362172e-05, "loss": 4.3086, "step": 12308 }, { "epoch": 0.37596212583995114, "grad_norm": 0.37774813175201416, "learning_rate": 3.449722908284755e-05, "loss": 4.3511, "step": 12309 }, { "epoch": 0.3759926695174099, "grad_norm": 0.396266371011734, "learning_rate": 3.449500998462751e-05, "loss": 4.2829, "step": 12310 }, { "epoch": 0.37602321319486864, "grad_norm": 0.37431180477142334, "learning_rate": 3.449279079898204e-05, "loss": 4.2609, "step": 12311 }, { "epoch": 0.37605375687232745, "grad_norm": 0.3832229971885681, "learning_rate": 3.4490571525931544e-05, "loss": 4.3012, "step": 12312 }, { "epoch": 0.3760843005497862, "grad_norm": 0.38400566577911377, "learning_rate": 3.4488352165496504e-05, "loss": 4.3871, "step": 12313 }, { "epoch": 0.37611484422724495, "grad_norm": 0.37428951263427734, "learning_rate": 3.4486132717697314e-05, "loss": 4.369, "step": 12314 }, { "epoch": 0.37614538790470375, "grad_norm": 0.37995854020118713, "learning_rate": 3.448391318255441e-05, "loss": 4.2287, "step": 12315 }, { "epoch": 0.3761759315821625, "grad_norm": 0.37577497959136963, "learning_rate": 3.448169356008826e-05, "loss": 4.3997, "step": 12316 }, { "epoch": 0.37620647525962125, "grad_norm": 0.370965838432312, "learning_rate": 3.447947385031927e-05, "loss": 4.3472, "step": 12317 }, { "epoch": 0.37623701893708, "grad_norm": 0.38534003496170044, "learning_rate": 3.44772540532679e-05, "loss": 4.4125, "step": 12318 }, { "epoch": 0.3762675626145388, "grad_norm": 0.3709810674190521, "learning_rate": 3.447503416895457e-05, "loss": 4.4008, "step": 12319 }, { "epoch": 0.37629810629199756, "grad_norm": 0.37969544529914856, "learning_rate": 3.447281419739973e-05, "loss": 4.303, "step": 12320 }, { "epoch": 0.3763286499694563, "grad_norm": 0.37905630469322205, "learning_rate": 3.447059413862383e-05, "loss": 4.3412, "step": 12321 }, { "epoch": 0.3763591936469151, "grad_norm": 0.3932781517505646, "learning_rate": 3.446837399264729e-05, "loss": 4.2608, "step": 12322 }, { "epoch": 0.37638973732437386, "grad_norm": 0.3885907828807831, "learning_rate": 3.4466153759490564e-05, "loss": 4.3406, "step": 12323 }, { "epoch": 0.3764202810018326, "grad_norm": 0.3734748661518097, "learning_rate": 3.44639334391741e-05, "loss": 4.2803, "step": 12324 }, { "epoch": 0.37645082467929136, "grad_norm": 0.37222474813461304, "learning_rate": 3.4461713031718326e-05, "loss": 4.3869, "step": 12325 }, { "epoch": 0.37648136835675017, "grad_norm": 0.380430668592453, "learning_rate": 3.4459492537143696e-05, "loss": 4.4119, "step": 12326 }, { "epoch": 0.3765119120342089, "grad_norm": 0.37718695402145386, "learning_rate": 3.445727195547066e-05, "loss": 4.3265, "step": 12327 }, { "epoch": 0.37654245571166767, "grad_norm": 0.39286622405052185, "learning_rate": 3.445505128671965e-05, "loss": 4.4141, "step": 12328 }, { "epoch": 0.3765729993891265, "grad_norm": 0.3735254108905792, "learning_rate": 3.4452830530911136e-05, "loss": 4.348, "step": 12329 }, { "epoch": 0.3766035430665852, "grad_norm": 0.3788420557975769, "learning_rate": 3.445060968806554e-05, "loss": 4.1954, "step": 12330 }, { "epoch": 0.37663408674404397, "grad_norm": 0.3863968253135681, "learning_rate": 3.444838875820333e-05, "loss": 4.3157, "step": 12331 }, { "epoch": 0.3766646304215027, "grad_norm": 0.3783693015575409, "learning_rate": 3.444616774134494e-05, "loss": 4.3216, "step": 12332 }, { "epoch": 0.3766951740989615, "grad_norm": 0.3753964900970459, "learning_rate": 3.444394663751082e-05, "loss": 4.3542, "step": 12333 }, { "epoch": 0.3767257177764203, "grad_norm": 0.37453925609588623, "learning_rate": 3.444172544672144e-05, "loss": 4.306, "step": 12334 }, { "epoch": 0.376756261453879, "grad_norm": 0.37141451239585876, "learning_rate": 3.443950416899724e-05, "loss": 4.2729, "step": 12335 }, { "epoch": 0.37678680513133783, "grad_norm": 0.39803341031074524, "learning_rate": 3.443728280435866e-05, "loss": 4.238, "step": 12336 }, { "epoch": 0.3768173488087966, "grad_norm": 0.39067819714546204, "learning_rate": 3.443506135282618e-05, "loss": 4.4003, "step": 12337 }, { "epoch": 0.37684789248625533, "grad_norm": 0.37106484174728394, "learning_rate": 3.443283981442023e-05, "loss": 4.3473, "step": 12338 }, { "epoch": 0.37687843616371414, "grad_norm": 0.3833628296852112, "learning_rate": 3.4430618189161266e-05, "loss": 4.3577, "step": 12339 }, { "epoch": 0.3769089798411729, "grad_norm": 0.38476768136024475, "learning_rate": 3.4428396477069765e-05, "loss": 4.2599, "step": 12340 }, { "epoch": 0.37693952351863164, "grad_norm": 0.38196203112602234, "learning_rate": 3.442617467816617e-05, "loss": 4.2264, "step": 12341 }, { "epoch": 0.3769700671960904, "grad_norm": 0.3908887803554535, "learning_rate": 3.442395279247093e-05, "loss": 4.3766, "step": 12342 }, { "epoch": 0.3770006108735492, "grad_norm": 0.3882851302623749, "learning_rate": 3.442173082000451e-05, "loss": 4.3161, "step": 12343 }, { "epoch": 0.37703115455100794, "grad_norm": 0.36934694647789, "learning_rate": 3.4419508760787375e-05, "loss": 4.2723, "step": 12344 }, { "epoch": 0.3770616982284667, "grad_norm": 0.3715948164463043, "learning_rate": 3.441728661483999e-05, "loss": 4.2118, "step": 12345 }, { "epoch": 0.3770922419059255, "grad_norm": 0.3779076039791107, "learning_rate": 3.4415064382182794e-05, "loss": 4.3462, "step": 12346 }, { "epoch": 0.37712278558338425, "grad_norm": 0.37002032995224, "learning_rate": 3.441284206283626e-05, "loss": 4.3698, "step": 12347 }, { "epoch": 0.377153329260843, "grad_norm": 0.3763605058193207, "learning_rate": 3.4410619656820854e-05, "loss": 4.3268, "step": 12348 }, { "epoch": 0.37718387293830175, "grad_norm": 0.3777713477611542, "learning_rate": 3.440839716415703e-05, "loss": 4.2965, "step": 12349 }, { "epoch": 0.37721441661576055, "grad_norm": 0.37837982177734375, "learning_rate": 3.440617458486525e-05, "loss": 4.3458, "step": 12350 }, { "epoch": 0.3772449602932193, "grad_norm": 0.37379950284957886, "learning_rate": 3.440395191896599e-05, "loss": 4.3066, "step": 12351 }, { "epoch": 0.37727550397067805, "grad_norm": 0.37927618622779846, "learning_rate": 3.440172916647971e-05, "loss": 4.4029, "step": 12352 }, { "epoch": 0.37730604764813686, "grad_norm": 0.37337368726730347, "learning_rate": 3.4399506327426886e-05, "loss": 4.326, "step": 12353 }, { "epoch": 0.3773365913255956, "grad_norm": 0.383668452501297, "learning_rate": 3.439728340182796e-05, "loss": 4.263, "step": 12354 }, { "epoch": 0.37736713500305435, "grad_norm": 0.38877177238464355, "learning_rate": 3.439506038970343e-05, "loss": 4.38, "step": 12355 }, { "epoch": 0.37739767868051316, "grad_norm": 0.37363407015800476, "learning_rate": 3.4392837291073726e-05, "loss": 4.3515, "step": 12356 }, { "epoch": 0.3774282223579719, "grad_norm": 0.3798670768737793, "learning_rate": 3.439061410595935e-05, "loss": 4.2953, "step": 12357 }, { "epoch": 0.37745876603543066, "grad_norm": 0.38445723056793213, "learning_rate": 3.4388390834380766e-05, "loss": 4.3965, "step": 12358 }, { "epoch": 0.3774893097128894, "grad_norm": 0.39226022362709045, "learning_rate": 3.438616747635844e-05, "loss": 4.3311, "step": 12359 }, { "epoch": 0.3775198533903482, "grad_norm": 0.3907521665096283, "learning_rate": 3.438394403191284e-05, "loss": 4.3605, "step": 12360 }, { "epoch": 0.37755039706780696, "grad_norm": 0.3775629699230194, "learning_rate": 3.4381720501064445e-05, "loss": 4.2965, "step": 12361 }, { "epoch": 0.3775809407452657, "grad_norm": 0.384246289730072, "learning_rate": 3.437949688383373e-05, "loss": 4.3606, "step": 12362 }, { "epoch": 0.3776114844227245, "grad_norm": 0.37892159819602966, "learning_rate": 3.437727318024116e-05, "loss": 4.3366, "step": 12363 }, { "epoch": 0.37764202810018327, "grad_norm": 0.37872418761253357, "learning_rate": 3.4375049390307215e-05, "loss": 4.3508, "step": 12364 }, { "epoch": 0.377672571777642, "grad_norm": 0.3903324604034424, "learning_rate": 3.437282551405236e-05, "loss": 4.344, "step": 12365 }, { "epoch": 0.37770311545510077, "grad_norm": 0.3770184814929962, "learning_rate": 3.4370601551497096e-05, "loss": 4.3509, "step": 12366 }, { "epoch": 0.3777336591325596, "grad_norm": 0.3832276463508606, "learning_rate": 3.4368377502661875e-05, "loss": 4.3306, "step": 12367 }, { "epoch": 0.3777642028100183, "grad_norm": 0.38278985023498535, "learning_rate": 3.43661533675672e-05, "loss": 4.3755, "step": 12368 }, { "epoch": 0.3777947464874771, "grad_norm": 0.38277313113212585, "learning_rate": 3.4363929146233534e-05, "loss": 4.3072, "step": 12369 }, { "epoch": 0.3778252901649359, "grad_norm": 0.39183369278907776, "learning_rate": 3.436170483868134e-05, "loss": 4.2363, "step": 12370 }, { "epoch": 0.37785583384239463, "grad_norm": 0.3957512676715851, "learning_rate": 3.435948044493113e-05, "loss": 4.2024, "step": 12371 }, { "epoch": 0.3778863775198534, "grad_norm": 0.3763723373413086, "learning_rate": 3.435725596500337e-05, "loss": 4.3097, "step": 12372 }, { "epoch": 0.3779169211973122, "grad_norm": 0.38205617666244507, "learning_rate": 3.435503139891854e-05, "loss": 4.3156, "step": 12373 }, { "epoch": 0.37794746487477093, "grad_norm": 0.3940374255180359, "learning_rate": 3.435280674669712e-05, "loss": 4.3265, "step": 12374 }, { "epoch": 0.3779780085522297, "grad_norm": 0.3869519829750061, "learning_rate": 3.435058200835961e-05, "loss": 4.2392, "step": 12375 }, { "epoch": 0.37800855222968843, "grad_norm": 0.3816434144973755, "learning_rate": 3.434835718392649e-05, "loss": 4.3282, "step": 12376 }, { "epoch": 0.37803909590714724, "grad_norm": 0.3841530680656433, "learning_rate": 3.4346132273418224e-05, "loss": 4.3822, "step": 12377 }, { "epoch": 0.378069639584606, "grad_norm": 0.3846251964569092, "learning_rate": 3.434390727685532e-05, "loss": 4.3745, "step": 12378 }, { "epoch": 0.37810018326206474, "grad_norm": 0.38448742032051086, "learning_rate": 3.434168219425826e-05, "loss": 4.3026, "step": 12379 }, { "epoch": 0.37813072693952354, "grad_norm": 0.38139283657073975, "learning_rate": 3.4339457025647515e-05, "loss": 4.2874, "step": 12380 }, { "epoch": 0.3781612706169823, "grad_norm": 0.38708916306495667, "learning_rate": 3.43372317710436e-05, "loss": 4.3916, "step": 12381 }, { "epoch": 0.37819181429444104, "grad_norm": 0.39264389872550964, "learning_rate": 3.433500643046699e-05, "loss": 4.3471, "step": 12382 }, { "epoch": 0.3782223579718998, "grad_norm": 0.3726889193058014, "learning_rate": 3.4332781003938174e-05, "loss": 4.3555, "step": 12383 }, { "epoch": 0.3782529016493586, "grad_norm": 0.37417563796043396, "learning_rate": 3.433055549147765e-05, "loss": 4.3543, "step": 12384 }, { "epoch": 0.37828344532681735, "grad_norm": 0.39383113384246826, "learning_rate": 3.4328329893105896e-05, "loss": 4.3602, "step": 12385 }, { "epoch": 0.3783139890042761, "grad_norm": 0.3889303505420685, "learning_rate": 3.432610420884342e-05, "loss": 4.2296, "step": 12386 }, { "epoch": 0.3783445326817349, "grad_norm": 0.3766036331653595, "learning_rate": 3.43238784387107e-05, "loss": 4.2981, "step": 12387 }, { "epoch": 0.37837507635919365, "grad_norm": 0.37382665276527405, "learning_rate": 3.4321652582728245e-05, "loss": 4.3381, "step": 12388 }, { "epoch": 0.3784056200366524, "grad_norm": 0.3886749744415283, "learning_rate": 3.431942664091654e-05, "loss": 4.2168, "step": 12389 }, { "epoch": 0.3784361637141112, "grad_norm": 0.37279820442199707, "learning_rate": 3.431720061329607e-05, "loss": 4.1099, "step": 12390 }, { "epoch": 0.37846670739156996, "grad_norm": 0.37676504254341125, "learning_rate": 3.4314974499887364e-05, "loss": 4.2423, "step": 12391 }, { "epoch": 0.3784972510690287, "grad_norm": 0.36996930837631226, "learning_rate": 3.43127483007109e-05, "loss": 4.3635, "step": 12392 }, { "epoch": 0.37852779474648746, "grad_norm": 0.3835153877735138, "learning_rate": 3.431052201578715e-05, "loss": 4.3264, "step": 12393 }, { "epoch": 0.37855833842394626, "grad_norm": 0.3871364891529083, "learning_rate": 3.430829564513665e-05, "loss": 4.3084, "step": 12394 }, { "epoch": 0.378588882101405, "grad_norm": 0.3803408145904541, "learning_rate": 3.430606918877989e-05, "loss": 4.3014, "step": 12395 }, { "epoch": 0.37861942577886376, "grad_norm": 0.3770510256290436, "learning_rate": 3.430384264673736e-05, "loss": 4.3068, "step": 12396 }, { "epoch": 0.37864996945632257, "grad_norm": 0.37777838110923767, "learning_rate": 3.430161601902957e-05, "loss": 4.2771, "step": 12397 }, { "epoch": 0.3786805131337813, "grad_norm": 0.37230730056762695, "learning_rate": 3.4299389305677015e-05, "loss": 4.3148, "step": 12398 }, { "epoch": 0.37871105681124007, "grad_norm": 0.3721775412559509, "learning_rate": 3.429716250670021e-05, "loss": 4.2683, "step": 12399 }, { "epoch": 0.3787416004886988, "grad_norm": 0.3773269057273865, "learning_rate": 3.429493562211965e-05, "loss": 4.346, "step": 12400 }, { "epoch": 0.3787721441661576, "grad_norm": 0.385968416929245, "learning_rate": 3.429270865195583e-05, "loss": 4.3422, "step": 12401 }, { "epoch": 0.37880268784361637, "grad_norm": 0.38007813692092896, "learning_rate": 3.4290481596229264e-05, "loss": 4.3074, "step": 12402 }, { "epoch": 0.3788332315210751, "grad_norm": 0.3712228536605835, "learning_rate": 3.428825445496046e-05, "loss": 4.3737, "step": 12403 }, { "epoch": 0.3788637751985339, "grad_norm": 0.3687969744205475, "learning_rate": 3.428602722816992e-05, "loss": 4.3289, "step": 12404 }, { "epoch": 0.3788943188759927, "grad_norm": 0.38275232911109924, "learning_rate": 3.4283799915878155e-05, "loss": 4.3042, "step": 12405 }, { "epoch": 0.3789248625534514, "grad_norm": 0.37869206070899963, "learning_rate": 3.428157251810568e-05, "loss": 4.3036, "step": 12406 }, { "epoch": 0.3789554062309102, "grad_norm": 0.38057243824005127, "learning_rate": 3.4279345034872975e-05, "loss": 4.2944, "step": 12407 }, { "epoch": 0.378985949908369, "grad_norm": 0.38171491026878357, "learning_rate": 3.427711746620058e-05, "loss": 4.3803, "step": 12408 }, { "epoch": 0.37901649358582773, "grad_norm": 0.37748029828071594, "learning_rate": 3.4274889812109e-05, "loss": 4.3332, "step": 12409 }, { "epoch": 0.3790470372632865, "grad_norm": 0.38375529646873474, "learning_rate": 3.4272662072618734e-05, "loss": 4.28, "step": 12410 }, { "epoch": 0.3790775809407453, "grad_norm": 0.3777065575122833, "learning_rate": 3.42704342477503e-05, "loss": 4.3357, "step": 12411 }, { "epoch": 0.37910812461820403, "grad_norm": 0.3841806948184967, "learning_rate": 3.426820633752421e-05, "loss": 4.1992, "step": 12412 }, { "epoch": 0.3791386682956628, "grad_norm": 0.3864520788192749, "learning_rate": 3.4265978341960984e-05, "loss": 4.3823, "step": 12413 }, { "epoch": 0.3791692119731216, "grad_norm": 0.38227784633636475, "learning_rate": 3.4263750261081133e-05, "loss": 4.2408, "step": 12414 }, { "epoch": 0.37919975565058034, "grad_norm": 0.3932127058506012, "learning_rate": 3.426152209490517e-05, "loss": 4.2527, "step": 12415 }, { "epoch": 0.3792302993280391, "grad_norm": 0.3927702307701111, "learning_rate": 3.425929384345361e-05, "loss": 4.2853, "step": 12416 }, { "epoch": 0.37926084300549784, "grad_norm": 0.37557360529899597, "learning_rate": 3.4257065506746966e-05, "loss": 4.239, "step": 12417 }, { "epoch": 0.37929138668295664, "grad_norm": 0.3855343163013458, "learning_rate": 3.425483708480576e-05, "loss": 4.3128, "step": 12418 }, { "epoch": 0.3793219303604154, "grad_norm": 0.4055837094783783, "learning_rate": 3.425260857765052e-05, "loss": 4.2995, "step": 12419 }, { "epoch": 0.37935247403787414, "grad_norm": 0.506290078163147, "learning_rate": 3.425037998530175e-05, "loss": 4.2543, "step": 12420 }, { "epoch": 0.37938301771533295, "grad_norm": 0.37492990493774414, "learning_rate": 3.4248151307779966e-05, "loss": 4.3471, "step": 12421 }, { "epoch": 0.3794135613927917, "grad_norm": 0.3911283016204834, "learning_rate": 3.424592254510571e-05, "loss": 4.2059, "step": 12422 }, { "epoch": 0.37944410507025045, "grad_norm": 0.39953529834747314, "learning_rate": 3.42436936972995e-05, "loss": 4.3889, "step": 12423 }, { "epoch": 0.3794746487477092, "grad_norm": 0.37634798884391785, "learning_rate": 3.424146476438184e-05, "loss": 4.2783, "step": 12424 }, { "epoch": 0.379505192425168, "grad_norm": 0.37625500559806824, "learning_rate": 3.423923574637326e-05, "loss": 4.2617, "step": 12425 }, { "epoch": 0.37953573610262675, "grad_norm": 0.4009062945842743, "learning_rate": 3.423700664329428e-05, "loss": 4.3511, "step": 12426 }, { "epoch": 0.3795662797800855, "grad_norm": 0.39791446924209595, "learning_rate": 3.4234777455165436e-05, "loss": 4.3498, "step": 12427 }, { "epoch": 0.3795968234575443, "grad_norm": 0.38098466396331787, "learning_rate": 3.423254818200725e-05, "loss": 4.2004, "step": 12428 }, { "epoch": 0.37962736713500306, "grad_norm": 0.37925079464912415, "learning_rate": 3.423031882384025e-05, "loss": 4.2749, "step": 12429 }, { "epoch": 0.3796579108124618, "grad_norm": 0.3794362545013428, "learning_rate": 3.4228089380684947e-05, "loss": 4.2421, "step": 12430 }, { "epoch": 0.3796884544899206, "grad_norm": 0.3714078366756439, "learning_rate": 3.422585985256189e-05, "loss": 4.3459, "step": 12431 }, { "epoch": 0.37971899816737936, "grad_norm": 0.38066938519477844, "learning_rate": 3.42236302394916e-05, "loss": 4.4322, "step": 12432 }, { "epoch": 0.3797495418448381, "grad_norm": 0.372986763715744, "learning_rate": 3.4221400541494594e-05, "loss": 4.3367, "step": 12433 }, { "epoch": 0.37978008552229686, "grad_norm": 0.3755924701690674, "learning_rate": 3.421917075859142e-05, "loss": 4.4035, "step": 12434 }, { "epoch": 0.37981062919975567, "grad_norm": 0.3879166841506958, "learning_rate": 3.421694089080259e-05, "loss": 4.3421, "step": 12435 }, { "epoch": 0.3798411728772144, "grad_norm": 0.3769667148590088, "learning_rate": 3.421471093814866e-05, "loss": 4.3048, "step": 12436 }, { "epoch": 0.37987171655467317, "grad_norm": 0.37604472041130066, "learning_rate": 3.421248090065014e-05, "loss": 4.2817, "step": 12437 }, { "epoch": 0.37990226023213197, "grad_norm": 0.3830253779888153, "learning_rate": 3.421025077832758e-05, "loss": 4.2955, "step": 12438 }, { "epoch": 0.3799328039095907, "grad_norm": 0.389017790555954, "learning_rate": 3.42080205712015e-05, "loss": 4.3116, "step": 12439 }, { "epoch": 0.37996334758704947, "grad_norm": 0.3693438470363617, "learning_rate": 3.420579027929244e-05, "loss": 4.2926, "step": 12440 }, { "epoch": 0.3799938912645082, "grad_norm": 0.39689064025878906, "learning_rate": 3.420355990262094e-05, "loss": 4.4195, "step": 12441 }, { "epoch": 0.380024434941967, "grad_norm": 0.3781289756298065, "learning_rate": 3.420132944120752e-05, "loss": 4.3484, "step": 12442 }, { "epoch": 0.3800549786194258, "grad_norm": 0.37356051802635193, "learning_rate": 3.419909889507274e-05, "loss": 4.2532, "step": 12443 }, { "epoch": 0.3800855222968845, "grad_norm": 0.3727647662162781, "learning_rate": 3.419686826423713e-05, "loss": 4.3738, "step": 12444 }, { "epoch": 0.38011606597434333, "grad_norm": 0.37867218255996704, "learning_rate": 3.419463754872121e-05, "loss": 4.274, "step": 12445 }, { "epoch": 0.3801466096518021, "grad_norm": 0.3772226572036743, "learning_rate": 3.419240674854556e-05, "loss": 4.29, "step": 12446 }, { "epoch": 0.38017715332926083, "grad_norm": 0.3742380142211914, "learning_rate": 3.419017586373068e-05, "loss": 4.3051, "step": 12447 }, { "epoch": 0.38020769700671964, "grad_norm": 0.3741321265697479, "learning_rate": 3.418794489429712e-05, "loss": 4.3423, "step": 12448 }, { "epoch": 0.3802382406841784, "grad_norm": 0.381958544254303, "learning_rate": 3.4185713840265434e-05, "loss": 4.3189, "step": 12449 }, { "epoch": 0.38026878436163714, "grad_norm": 0.37235376238822937, "learning_rate": 3.4183482701656154e-05, "loss": 4.2817, "step": 12450 }, { "epoch": 0.3802993280390959, "grad_norm": 0.3877839744091034, "learning_rate": 3.418125147848983e-05, "loss": 4.3373, "step": 12451 }, { "epoch": 0.3803298717165547, "grad_norm": 0.38640907406806946, "learning_rate": 3.4179020170786996e-05, "loss": 4.2805, "step": 12452 }, { "epoch": 0.38036041539401344, "grad_norm": 0.37771129608154297, "learning_rate": 3.417678877856821e-05, "loss": 4.3788, "step": 12453 }, { "epoch": 0.3803909590714722, "grad_norm": 0.3873167932033539, "learning_rate": 3.417455730185401e-05, "loss": 4.327, "step": 12454 }, { "epoch": 0.380421502748931, "grad_norm": 0.3739362955093384, "learning_rate": 3.417232574066495e-05, "loss": 4.4028, "step": 12455 }, { "epoch": 0.38045204642638975, "grad_norm": 0.38600194454193115, "learning_rate": 3.417009409502157e-05, "loss": 4.3619, "step": 12456 }, { "epoch": 0.3804825901038485, "grad_norm": 0.37260526418685913, "learning_rate": 3.4167862364944414e-05, "loss": 4.2032, "step": 12457 }, { "epoch": 0.38051313378130724, "grad_norm": 0.37152227759361267, "learning_rate": 3.416563055045404e-05, "loss": 4.3668, "step": 12458 }, { "epoch": 0.38054367745876605, "grad_norm": 0.384717732667923, "learning_rate": 3.416339865157099e-05, "loss": 4.3728, "step": 12459 }, { "epoch": 0.3805742211362248, "grad_norm": 0.3934215009212494, "learning_rate": 3.4161166668315813e-05, "loss": 4.3146, "step": 12460 }, { "epoch": 0.38060476481368355, "grad_norm": 0.3779110908508301, "learning_rate": 3.415893460070907e-05, "loss": 4.3669, "step": 12461 }, { "epoch": 0.38063530849114235, "grad_norm": 0.37579208612442017, "learning_rate": 3.4156702448771306e-05, "loss": 4.3075, "step": 12462 }, { "epoch": 0.3806658521686011, "grad_norm": 0.37971311807632446, "learning_rate": 3.415447021252308e-05, "loss": 4.3137, "step": 12463 }, { "epoch": 0.38069639584605985, "grad_norm": 0.3737751841545105, "learning_rate": 3.415223789198493e-05, "loss": 4.3504, "step": 12464 }, { "epoch": 0.38072693952351866, "grad_norm": 0.3886799216270447, "learning_rate": 3.415000548717742e-05, "loss": 4.281, "step": 12465 }, { "epoch": 0.3807574832009774, "grad_norm": 0.381478488445282, "learning_rate": 3.4147772998121116e-05, "loss": 4.3001, "step": 12466 }, { "epoch": 0.38078802687843616, "grad_norm": 0.3769093155860901, "learning_rate": 3.4145540424836554e-05, "loss": 4.301, "step": 12467 }, { "epoch": 0.3808185705558949, "grad_norm": 0.39150819182395935, "learning_rate": 3.41433077673443e-05, "loss": 4.2898, "step": 12468 }, { "epoch": 0.3808491142333537, "grad_norm": 0.38011685013771057, "learning_rate": 3.414107502566492e-05, "loss": 4.3004, "step": 12469 }, { "epoch": 0.38087965791081246, "grad_norm": 0.37726303935050964, "learning_rate": 3.413884219981895e-05, "loss": 4.4481, "step": 12470 }, { "epoch": 0.3809102015882712, "grad_norm": 0.38779667019844055, "learning_rate": 3.4136609289826965e-05, "loss": 4.2915, "step": 12471 }, { "epoch": 0.38094074526573, "grad_norm": 0.39228254556655884, "learning_rate": 3.413437629570951e-05, "loss": 4.301, "step": 12472 }, { "epoch": 0.38097128894318877, "grad_norm": 0.38231000304222107, "learning_rate": 3.413214321748717e-05, "loss": 4.287, "step": 12473 }, { "epoch": 0.3810018326206475, "grad_norm": 0.38604241609573364, "learning_rate": 3.412991005518049e-05, "loss": 4.2514, "step": 12474 }, { "epoch": 0.38103237629810627, "grad_norm": 0.378726601600647, "learning_rate": 3.412767680881004e-05, "loss": 4.3462, "step": 12475 }, { "epoch": 0.3810629199755651, "grad_norm": 0.3781833052635193, "learning_rate": 3.412544347839636e-05, "loss": 4.3452, "step": 12476 }, { "epoch": 0.3810934636530238, "grad_norm": 0.39132359623908997, "learning_rate": 3.412321006396004e-05, "loss": 4.3214, "step": 12477 }, { "epoch": 0.3811240073304826, "grad_norm": 0.38023853302001953, "learning_rate": 3.4120976565521644e-05, "loss": 4.3621, "step": 12478 }, { "epoch": 0.3811545510079414, "grad_norm": 0.37972787022590637, "learning_rate": 3.411874298310171e-05, "loss": 4.3288, "step": 12479 }, { "epoch": 0.3811850946854001, "grad_norm": 0.3778274655342102, "learning_rate": 3.411650931672083e-05, "loss": 4.2924, "step": 12480 }, { "epoch": 0.3812156383628589, "grad_norm": 0.3923022449016571, "learning_rate": 3.411427556639956e-05, "loss": 4.3356, "step": 12481 }, { "epoch": 0.3812461820403176, "grad_norm": 0.38176488876342773, "learning_rate": 3.4112041732158475e-05, "loss": 4.3344, "step": 12482 }, { "epoch": 0.38127672571777643, "grad_norm": 0.39349448680877686, "learning_rate": 3.4109807814018126e-05, "loss": 4.3251, "step": 12483 }, { "epoch": 0.3813072693952352, "grad_norm": 0.3861919045448303, "learning_rate": 3.410757381199909e-05, "loss": 4.1772, "step": 12484 }, { "epoch": 0.38133781307269393, "grad_norm": 0.4008082151412964, "learning_rate": 3.410533972612195e-05, "loss": 4.3459, "step": 12485 }, { "epoch": 0.38136835675015274, "grad_norm": 0.3898569941520691, "learning_rate": 3.410310555640726e-05, "loss": 4.3041, "step": 12486 }, { "epoch": 0.3813989004276115, "grad_norm": 0.37764573097229004, "learning_rate": 3.41008713028756e-05, "loss": 4.3109, "step": 12487 }, { "epoch": 0.38142944410507024, "grad_norm": 0.3862380087375641, "learning_rate": 3.409863696554754e-05, "loss": 4.4602, "step": 12488 }, { "epoch": 0.38145998778252904, "grad_norm": 0.38634756207466125, "learning_rate": 3.409640254444365e-05, "loss": 4.3205, "step": 12489 }, { "epoch": 0.3814905314599878, "grad_norm": 0.3832958936691284, "learning_rate": 3.4094168039584494e-05, "loss": 4.3477, "step": 12490 }, { "epoch": 0.38152107513744654, "grad_norm": 0.38689324259757996, "learning_rate": 3.409193345099067e-05, "loss": 4.358, "step": 12491 }, { "epoch": 0.3815516188149053, "grad_norm": 0.3843834698200226, "learning_rate": 3.4089698778682736e-05, "loss": 4.2514, "step": 12492 }, { "epoch": 0.3815821624923641, "grad_norm": 0.3849010467529297, "learning_rate": 3.4087464022681276e-05, "loss": 4.3533, "step": 12493 }, { "epoch": 0.38161270616982285, "grad_norm": 0.37666556239128113, "learning_rate": 3.408522918300686e-05, "loss": 4.324, "step": 12494 }, { "epoch": 0.3816432498472816, "grad_norm": 0.3798036277294159, "learning_rate": 3.408299425968007e-05, "loss": 4.266, "step": 12495 }, { "epoch": 0.3816737935247404, "grad_norm": 0.39058375358581543, "learning_rate": 3.408075925272147e-05, "loss": 4.3955, "step": 12496 }, { "epoch": 0.38170433720219915, "grad_norm": 0.3834066390991211, "learning_rate": 3.4078524162151666e-05, "loss": 4.2851, "step": 12497 }, { "epoch": 0.3817348808796579, "grad_norm": 0.38591468334198, "learning_rate": 3.4076288987991215e-05, "loss": 4.3146, "step": 12498 }, { "epoch": 0.38176542455711665, "grad_norm": 0.3906782567501068, "learning_rate": 3.4074053730260705e-05, "loss": 4.3649, "step": 12499 }, { "epoch": 0.38179596823457546, "grad_norm": 0.39518776535987854, "learning_rate": 3.4071818388980715e-05, "loss": 4.3289, "step": 12500 }, { "epoch": 0.3818265119120342, "grad_norm": 0.3717390298843384, "learning_rate": 3.406958296417183e-05, "loss": 4.3852, "step": 12501 }, { "epoch": 0.38185705558949296, "grad_norm": 0.38295865058898926, "learning_rate": 3.406734745585464e-05, "loss": 4.3366, "step": 12502 }, { "epoch": 0.38188759926695176, "grad_norm": 0.3792131841182709, "learning_rate": 3.40651118640497e-05, "loss": 4.3271, "step": 12503 }, { "epoch": 0.3819181429444105, "grad_norm": 0.36960622668266296, "learning_rate": 3.406287618877764e-05, "loss": 4.2828, "step": 12504 }, { "epoch": 0.38194868662186926, "grad_norm": 0.38877972960472107, "learning_rate": 3.4060640430059e-05, "loss": 4.3172, "step": 12505 }, { "epoch": 0.38197923029932807, "grad_norm": 0.38674673438072205, "learning_rate": 3.405840458791439e-05, "loss": 4.2993, "step": 12506 }, { "epoch": 0.3820097739767868, "grad_norm": 0.38908252120018005, "learning_rate": 3.405616866236439e-05, "loss": 4.3689, "step": 12507 }, { "epoch": 0.38204031765424556, "grad_norm": 0.37376993894577026, "learning_rate": 3.405393265342959e-05, "loss": 4.3, "step": 12508 }, { "epoch": 0.3820708613317043, "grad_norm": 0.3920886814594269, "learning_rate": 3.405169656113058e-05, "loss": 4.2845, "step": 12509 }, { "epoch": 0.3821014050091631, "grad_norm": 0.3795073628425598, "learning_rate": 3.4049460385487944e-05, "loss": 4.2947, "step": 12510 }, { "epoch": 0.38213194868662187, "grad_norm": 0.3719545900821686, "learning_rate": 3.404722412652228e-05, "loss": 4.3644, "step": 12511 }, { "epoch": 0.3821624923640806, "grad_norm": 0.3716569244861603, "learning_rate": 3.4044987784254167e-05, "loss": 4.2817, "step": 12512 }, { "epoch": 0.3821930360415394, "grad_norm": 0.39411354064941406, "learning_rate": 3.4042751358704194e-05, "loss": 4.2392, "step": 12513 }, { "epoch": 0.3822235797189982, "grad_norm": 0.3838566839694977, "learning_rate": 3.404051484989297e-05, "loss": 4.2497, "step": 12514 }, { "epoch": 0.3822541233964569, "grad_norm": 0.37671464681625366, "learning_rate": 3.403827825784107e-05, "loss": 4.3575, "step": 12515 }, { "epoch": 0.3822846670739157, "grad_norm": 0.38258659839630127, "learning_rate": 3.40360415825691e-05, "loss": 4.2012, "step": 12516 }, { "epoch": 0.3823152107513745, "grad_norm": 0.3713822662830353, "learning_rate": 3.403380482409765e-05, "loss": 4.3034, "step": 12517 }, { "epoch": 0.38234575442883323, "grad_norm": 0.3787073493003845, "learning_rate": 3.403156798244731e-05, "loss": 4.3582, "step": 12518 }, { "epoch": 0.382376298106292, "grad_norm": 0.3898630738258362, "learning_rate": 3.402933105763869e-05, "loss": 4.3527, "step": 12519 }, { "epoch": 0.3824068417837508, "grad_norm": 0.391743540763855, "learning_rate": 3.402709404969236e-05, "loss": 4.3672, "step": 12520 }, { "epoch": 0.38243738546120953, "grad_norm": 0.39026206731796265, "learning_rate": 3.402485695862894e-05, "loss": 4.2926, "step": 12521 }, { "epoch": 0.3824679291386683, "grad_norm": 0.3719336688518524, "learning_rate": 3.402261978446902e-05, "loss": 4.264, "step": 12522 }, { "epoch": 0.3824984728161271, "grad_norm": 0.3803773522377014, "learning_rate": 3.4020382527233206e-05, "loss": 4.268, "step": 12523 }, { "epoch": 0.38252901649358584, "grad_norm": 0.3824269771575928, "learning_rate": 3.40181451869421e-05, "loss": 4.4538, "step": 12524 }, { "epoch": 0.3825595601710446, "grad_norm": 0.37737488746643066, "learning_rate": 3.401590776361628e-05, "loss": 4.3253, "step": 12525 }, { "epoch": 0.38259010384850334, "grad_norm": 0.36800047755241394, "learning_rate": 3.401367025727638e-05, "loss": 4.2953, "step": 12526 }, { "epoch": 0.38262064752596214, "grad_norm": 0.3898487389087677, "learning_rate": 3.401143266794296e-05, "loss": 4.3514, "step": 12527 }, { "epoch": 0.3826511912034209, "grad_norm": 0.37601810693740845, "learning_rate": 3.4009194995636655e-05, "loss": 4.3628, "step": 12528 }, { "epoch": 0.38268173488087964, "grad_norm": 0.3814619481563568, "learning_rate": 3.400695724037807e-05, "loss": 4.3223, "step": 12529 }, { "epoch": 0.38271227855833845, "grad_norm": 0.37831181287765503, "learning_rate": 3.400471940218778e-05, "loss": 4.3465, "step": 12530 }, { "epoch": 0.3827428222357972, "grad_norm": 0.3749072253704071, "learning_rate": 3.400248148108642e-05, "loss": 4.192, "step": 12531 }, { "epoch": 0.38277336591325595, "grad_norm": 0.38488656282424927, "learning_rate": 3.4000243477094585e-05, "loss": 4.3084, "step": 12532 }, { "epoch": 0.3828039095907147, "grad_norm": 0.38477861881256104, "learning_rate": 3.3998005390232886e-05, "loss": 4.2841, "step": 12533 }, { "epoch": 0.3828344532681735, "grad_norm": 0.38107550144195557, "learning_rate": 3.399576722052191e-05, "loss": 4.3659, "step": 12534 }, { "epoch": 0.38286499694563225, "grad_norm": 0.37116432189941406, "learning_rate": 3.399352896798229e-05, "loss": 4.2525, "step": 12535 }, { "epoch": 0.382895540623091, "grad_norm": 0.38187161087989807, "learning_rate": 3.3991290632634624e-05, "loss": 4.2937, "step": 12536 }, { "epoch": 0.3829260843005498, "grad_norm": 0.36724910140037537, "learning_rate": 3.398905221449952e-05, "loss": 4.261, "step": 12537 }, { "epoch": 0.38295662797800856, "grad_norm": 0.3820420205593109, "learning_rate": 3.398681371359759e-05, "loss": 4.2328, "step": 12538 }, { "epoch": 0.3829871716554673, "grad_norm": 0.37707722187042236, "learning_rate": 3.3984575129949455e-05, "loss": 4.2025, "step": 12539 }, { "epoch": 0.3830177153329261, "grad_norm": 0.37074461579322815, "learning_rate": 3.398233646357571e-05, "loss": 4.2805, "step": 12540 }, { "epoch": 0.38304825901038486, "grad_norm": 0.3925025761127472, "learning_rate": 3.398009771449697e-05, "loss": 4.2868, "step": 12541 }, { "epoch": 0.3830788026878436, "grad_norm": 0.3737733066082001, "learning_rate": 3.397785888273386e-05, "loss": 4.3319, "step": 12542 }, { "epoch": 0.38310934636530236, "grad_norm": 0.3875153064727783, "learning_rate": 3.397561996830699e-05, "loss": 4.2812, "step": 12543 }, { "epoch": 0.38313989004276117, "grad_norm": 0.37164726853370667, "learning_rate": 3.397338097123696e-05, "loss": 4.2458, "step": 12544 }, { "epoch": 0.3831704337202199, "grad_norm": 0.3773702085018158, "learning_rate": 3.397114189154441e-05, "loss": 4.3901, "step": 12545 }, { "epoch": 0.38320097739767867, "grad_norm": 0.3694912791252136, "learning_rate": 3.396890272924994e-05, "loss": 4.3441, "step": 12546 }, { "epoch": 0.38323152107513747, "grad_norm": 0.38052940368652344, "learning_rate": 3.396666348437417e-05, "loss": 4.2749, "step": 12547 }, { "epoch": 0.3832620647525962, "grad_norm": 0.38421422243118286, "learning_rate": 3.396442415693772e-05, "loss": 4.3021, "step": 12548 }, { "epoch": 0.38329260843005497, "grad_norm": 0.40821248292922974, "learning_rate": 3.396218474696121e-05, "loss": 4.2997, "step": 12549 }, { "epoch": 0.3833231521075137, "grad_norm": 0.3790523111820221, "learning_rate": 3.3959945254465255e-05, "loss": 4.2868, "step": 12550 }, { "epoch": 0.3833536957849725, "grad_norm": 0.38441020250320435, "learning_rate": 3.395770567947047e-05, "loss": 4.4197, "step": 12551 }, { "epoch": 0.3833842394624313, "grad_norm": 0.37538498640060425, "learning_rate": 3.39554660219975e-05, "loss": 4.2007, "step": 12552 }, { "epoch": 0.38341478313989, "grad_norm": 0.3722347617149353, "learning_rate": 3.3953226282066935e-05, "loss": 4.397, "step": 12553 }, { "epoch": 0.38344532681734883, "grad_norm": 0.38866880536079407, "learning_rate": 3.395098645969941e-05, "loss": 4.3088, "step": 12554 }, { "epoch": 0.3834758704948076, "grad_norm": 0.38271620869636536, "learning_rate": 3.3948746554915565e-05, "loss": 4.3591, "step": 12555 }, { "epoch": 0.38350641417226633, "grad_norm": 0.38447028398513794, "learning_rate": 3.3946506567736004e-05, "loss": 4.2527, "step": 12556 }, { "epoch": 0.3835369578497251, "grad_norm": 0.374265193939209, "learning_rate": 3.394426649818136e-05, "loss": 4.3294, "step": 12557 }, { "epoch": 0.3835675015271839, "grad_norm": 0.3832153081893921, "learning_rate": 3.3942026346272245e-05, "loss": 4.3509, "step": 12558 }, { "epoch": 0.38359804520464263, "grad_norm": 0.3834647536277771, "learning_rate": 3.39397861120293e-05, "loss": 4.3843, "step": 12559 }, { "epoch": 0.3836285888821014, "grad_norm": 0.3825426399707794, "learning_rate": 3.393754579547315e-05, "loss": 4.3751, "step": 12560 }, { "epoch": 0.3836591325595602, "grad_norm": 0.3747304081916809, "learning_rate": 3.393530539662442e-05, "loss": 4.3566, "step": 12561 }, { "epoch": 0.38368967623701894, "grad_norm": 0.38051801919937134, "learning_rate": 3.393306491550374e-05, "loss": 4.2355, "step": 12562 }, { "epoch": 0.3837202199144777, "grad_norm": 0.3728984296321869, "learning_rate": 3.393082435213174e-05, "loss": 4.2807, "step": 12563 }, { "epoch": 0.3837507635919365, "grad_norm": 0.3979022204875946, "learning_rate": 3.392858370652905e-05, "loss": 4.3374, "step": 12564 }, { "epoch": 0.38378130726939524, "grad_norm": 0.39215224981307983, "learning_rate": 3.392634297871629e-05, "loss": 4.2934, "step": 12565 }, { "epoch": 0.383811850946854, "grad_norm": 0.3835367262363434, "learning_rate": 3.392410216871411e-05, "loss": 4.3668, "step": 12566 }, { "epoch": 0.38384239462431274, "grad_norm": 0.38812941312789917, "learning_rate": 3.392186127654313e-05, "loss": 4.2536, "step": 12567 }, { "epoch": 0.38387293830177155, "grad_norm": 0.39020174741744995, "learning_rate": 3.391962030222398e-05, "loss": 4.3096, "step": 12568 }, { "epoch": 0.3839034819792303, "grad_norm": 0.3812785744667053, "learning_rate": 3.391737924577731e-05, "loss": 4.2642, "step": 12569 }, { "epoch": 0.38393402565668905, "grad_norm": 0.38028189539909363, "learning_rate": 3.391513810722374e-05, "loss": 4.1798, "step": 12570 }, { "epoch": 0.38396456933414785, "grad_norm": 0.38305023312568665, "learning_rate": 3.391289688658391e-05, "loss": 4.2816, "step": 12571 }, { "epoch": 0.3839951130116066, "grad_norm": 0.37803590297698975, "learning_rate": 3.3910655583878456e-05, "loss": 4.363, "step": 12572 }, { "epoch": 0.38402565668906535, "grad_norm": 0.39261049032211304, "learning_rate": 3.3908414199128014e-05, "loss": 4.2774, "step": 12573 }, { "epoch": 0.3840562003665241, "grad_norm": 0.3912326693534851, "learning_rate": 3.3906172732353225e-05, "loss": 4.3126, "step": 12574 }, { "epoch": 0.3840867440439829, "grad_norm": 0.38358378410339355, "learning_rate": 3.390393118357472e-05, "loss": 4.3691, "step": 12575 }, { "epoch": 0.38411728772144166, "grad_norm": 0.37147924304008484, "learning_rate": 3.3901689552813144e-05, "loss": 4.3579, "step": 12576 }, { "epoch": 0.3841478313989004, "grad_norm": 0.3792540431022644, "learning_rate": 3.389944784008913e-05, "loss": 4.2333, "step": 12577 }, { "epoch": 0.3841783750763592, "grad_norm": 0.37585875391960144, "learning_rate": 3.389720604542333e-05, "loss": 4.3455, "step": 12578 }, { "epoch": 0.38420891875381796, "grad_norm": 0.37336471676826477, "learning_rate": 3.389496416883638e-05, "loss": 4.3055, "step": 12579 }, { "epoch": 0.3842394624312767, "grad_norm": 0.3770163059234619, "learning_rate": 3.3892722210348925e-05, "loss": 4.3077, "step": 12580 }, { "epoch": 0.3842700061087355, "grad_norm": 0.4007945954799652, "learning_rate": 3.38904801699816e-05, "loss": 4.164, "step": 12581 }, { "epoch": 0.38430054978619427, "grad_norm": 0.37523460388183594, "learning_rate": 3.388823804775505e-05, "loss": 4.2934, "step": 12582 }, { "epoch": 0.384331093463653, "grad_norm": 0.3839217722415924, "learning_rate": 3.388599584368993e-05, "loss": 4.3473, "step": 12583 }, { "epoch": 0.38436163714111177, "grad_norm": 0.3836389183998108, "learning_rate": 3.388375355780687e-05, "loss": 4.2438, "step": 12584 }, { "epoch": 0.3843921808185706, "grad_norm": 0.38272222876548767, "learning_rate": 3.388151119012653e-05, "loss": 4.3716, "step": 12585 }, { "epoch": 0.3844227244960293, "grad_norm": 0.3832222819328308, "learning_rate": 3.387926874066955e-05, "loss": 4.3723, "step": 12586 }, { "epoch": 0.38445326817348807, "grad_norm": 0.3956788182258606, "learning_rate": 3.387702620945657e-05, "loss": 4.1441, "step": 12587 }, { "epoch": 0.3844838118509469, "grad_norm": 0.38333630561828613, "learning_rate": 3.387478359650825e-05, "loss": 4.3771, "step": 12588 }, { "epoch": 0.3845143555284056, "grad_norm": 0.39110276103019714, "learning_rate": 3.3872540901845236e-05, "loss": 4.3404, "step": 12589 }, { "epoch": 0.3845448992058644, "grad_norm": 0.38773688673973083, "learning_rate": 3.3870298125488176e-05, "loss": 4.3579, "step": 12590 }, { "epoch": 0.3845754428833231, "grad_norm": 0.3749578893184662, "learning_rate": 3.386805526745772e-05, "loss": 4.2283, "step": 12591 }, { "epoch": 0.38460598656078193, "grad_norm": 0.37324801087379456, "learning_rate": 3.386581232777451e-05, "loss": 4.357, "step": 12592 }, { "epoch": 0.3846365302382407, "grad_norm": 0.3709665834903717, "learning_rate": 3.386356930645922e-05, "loss": 4.2972, "step": 12593 }, { "epoch": 0.38466707391569943, "grad_norm": 0.37727418541908264, "learning_rate": 3.386132620353249e-05, "loss": 4.3325, "step": 12594 }, { "epoch": 0.38469761759315824, "grad_norm": 0.3808760941028595, "learning_rate": 3.385908301901497e-05, "loss": 4.2492, "step": 12595 }, { "epoch": 0.384728161270617, "grad_norm": 0.3882583975791931, "learning_rate": 3.385683975292731e-05, "loss": 4.2878, "step": 12596 }, { "epoch": 0.38475870494807574, "grad_norm": 0.3724842667579651, "learning_rate": 3.385459640529019e-05, "loss": 4.3253, "step": 12597 }, { "epoch": 0.38478924862553454, "grad_norm": 0.39334580302238464, "learning_rate": 3.3852352976124234e-05, "loss": 4.2684, "step": 12598 }, { "epoch": 0.3848197923029933, "grad_norm": 0.3788442611694336, "learning_rate": 3.385010946545012e-05, "loss": 4.2958, "step": 12599 }, { "epoch": 0.38485033598045204, "grad_norm": 0.38698810338974, "learning_rate": 3.384786587328849e-05, "loss": 4.2722, "step": 12600 }, { "epoch": 0.3848808796579108, "grad_norm": 0.388841837644577, "learning_rate": 3.384562219966002e-05, "loss": 4.2883, "step": 12601 }, { "epoch": 0.3849114233353696, "grad_norm": 0.3780221939086914, "learning_rate": 3.3843378444585356e-05, "loss": 4.3527, "step": 12602 }, { "epoch": 0.38494196701282835, "grad_norm": 0.3816045820713043, "learning_rate": 3.384113460808516e-05, "loss": 4.2924, "step": 12603 }, { "epoch": 0.3849725106902871, "grad_norm": 0.3878878355026245, "learning_rate": 3.383889069018009e-05, "loss": 4.3325, "step": 12604 }, { "epoch": 0.3850030543677459, "grad_norm": 0.387164443731308, "learning_rate": 3.38366466908908e-05, "loss": 4.3131, "step": 12605 }, { "epoch": 0.38503359804520465, "grad_norm": 0.37701481580734253, "learning_rate": 3.383440261023797e-05, "loss": 4.2072, "step": 12606 }, { "epoch": 0.3850641417226634, "grad_norm": 0.383565217256546, "learning_rate": 3.383215844824225e-05, "loss": 4.3146, "step": 12607 }, { "epoch": 0.38509468540012215, "grad_norm": 0.38587039709091187, "learning_rate": 3.382991420492431e-05, "loss": 4.2295, "step": 12608 }, { "epoch": 0.38512522907758096, "grad_norm": 0.38339656591415405, "learning_rate": 3.3827669880304805e-05, "loss": 4.3705, "step": 12609 }, { "epoch": 0.3851557727550397, "grad_norm": 0.37779611349105835, "learning_rate": 3.382542547440441e-05, "loss": 4.2377, "step": 12610 }, { "epoch": 0.38518631643249845, "grad_norm": 0.3776416778564453, "learning_rate": 3.3823180987243785e-05, "loss": 4.3572, "step": 12611 }, { "epoch": 0.38521686010995726, "grad_norm": 0.3751480281352997, "learning_rate": 3.382093641884359e-05, "loss": 4.3063, "step": 12612 }, { "epoch": 0.385247403787416, "grad_norm": 0.38534656167030334, "learning_rate": 3.381869176922451e-05, "loss": 4.3402, "step": 12613 }, { "epoch": 0.38527794746487476, "grad_norm": 0.3864700496196747, "learning_rate": 3.381644703840719e-05, "loss": 4.2129, "step": 12614 }, { "epoch": 0.38530849114233356, "grad_norm": 0.39018091559410095, "learning_rate": 3.3814202226412304e-05, "loss": 4.3852, "step": 12615 }, { "epoch": 0.3853390348197923, "grad_norm": 0.3706454336643219, "learning_rate": 3.3811957333260536e-05, "loss": 4.3362, "step": 12616 }, { "epoch": 0.38536957849725106, "grad_norm": 0.3811308741569519, "learning_rate": 3.3809712358972545e-05, "loss": 4.2606, "step": 12617 }, { "epoch": 0.3854001221747098, "grad_norm": 0.38813135027885437, "learning_rate": 3.3807467303569006e-05, "loss": 4.4332, "step": 12618 }, { "epoch": 0.3854306658521686, "grad_norm": 0.3795492649078369, "learning_rate": 3.380522216707058e-05, "loss": 4.3064, "step": 12619 }, { "epoch": 0.38546120952962737, "grad_norm": 0.39069539308547974, "learning_rate": 3.3802976949497956e-05, "loss": 4.2623, "step": 12620 }, { "epoch": 0.3854917532070861, "grad_norm": 0.37709662318229675, "learning_rate": 3.3800731650871793e-05, "loss": 4.2894, "step": 12621 }, { "epoch": 0.3855222968845449, "grad_norm": 0.38674455881118774, "learning_rate": 3.379848627121276e-05, "loss": 4.222, "step": 12622 }, { "epoch": 0.3855528405620037, "grad_norm": 0.3865036368370056, "learning_rate": 3.3796240810541544e-05, "loss": 4.385, "step": 12623 }, { "epoch": 0.3855833842394624, "grad_norm": 0.3776516318321228, "learning_rate": 3.379399526887883e-05, "loss": 4.3111, "step": 12624 }, { "epoch": 0.3856139279169212, "grad_norm": 0.37406599521636963, "learning_rate": 3.379174964624526e-05, "loss": 4.3626, "step": 12625 }, { "epoch": 0.38564447159438, "grad_norm": 0.4010489284992218, "learning_rate": 3.3789503942661545e-05, "loss": 4.3112, "step": 12626 }, { "epoch": 0.38567501527183873, "grad_norm": 0.4113706648349762, "learning_rate": 3.378725815814834e-05, "loss": 4.3073, "step": 12627 }, { "epoch": 0.3857055589492975, "grad_norm": 0.3762575089931488, "learning_rate": 3.3785012292726335e-05, "loss": 4.3347, "step": 12628 }, { "epoch": 0.3857361026267563, "grad_norm": 0.39137789607048035, "learning_rate": 3.3782766346416206e-05, "loss": 4.3066, "step": 12629 }, { "epoch": 0.38576664630421503, "grad_norm": 0.3857767879962921, "learning_rate": 3.378052031923863e-05, "loss": 4.3642, "step": 12630 }, { "epoch": 0.3857971899816738, "grad_norm": 0.381437212228775, "learning_rate": 3.377827421121429e-05, "loss": 4.4357, "step": 12631 }, { "epoch": 0.38582773365913253, "grad_norm": 0.3859114944934845, "learning_rate": 3.3776028022363865e-05, "loss": 4.3014, "step": 12632 }, { "epoch": 0.38585827733659134, "grad_norm": 0.3809695243835449, "learning_rate": 3.3773781752708036e-05, "loss": 4.3325, "step": 12633 }, { "epoch": 0.3858888210140501, "grad_norm": 0.3751005530357361, "learning_rate": 3.377153540226749e-05, "loss": 4.3284, "step": 12634 }, { "epoch": 0.38591936469150884, "grad_norm": 0.3768847584724426, "learning_rate": 3.376928897106291e-05, "loss": 4.266, "step": 12635 }, { "epoch": 0.38594990836896764, "grad_norm": 0.3827427327632904, "learning_rate": 3.376704245911497e-05, "loss": 4.4035, "step": 12636 }, { "epoch": 0.3859804520464264, "grad_norm": 0.38916677236557007, "learning_rate": 3.3764795866444366e-05, "loss": 4.3575, "step": 12637 }, { "epoch": 0.38601099572388514, "grad_norm": 0.3775802552700043, "learning_rate": 3.376254919307178e-05, "loss": 4.2598, "step": 12638 }, { "epoch": 0.38604153940134395, "grad_norm": 0.38044169545173645, "learning_rate": 3.3760302439017896e-05, "loss": 4.2676, "step": 12639 }, { "epoch": 0.3860720830788027, "grad_norm": 0.3664741814136505, "learning_rate": 3.3758055604303406e-05, "loss": 4.3273, "step": 12640 }, { "epoch": 0.38610262675626145, "grad_norm": 0.386255145072937, "learning_rate": 3.3755808688949e-05, "loss": 4.3817, "step": 12641 }, { "epoch": 0.3861331704337202, "grad_norm": 0.377835750579834, "learning_rate": 3.3753561692975355e-05, "loss": 4.3732, "step": 12642 }, { "epoch": 0.386163714111179, "grad_norm": 0.3815471827983856, "learning_rate": 3.375131461640317e-05, "loss": 4.3167, "step": 12643 }, { "epoch": 0.38619425778863775, "grad_norm": 0.38010677695274353, "learning_rate": 3.3749067459253134e-05, "loss": 4.3307, "step": 12644 }, { "epoch": 0.3862248014660965, "grad_norm": 0.38309603929519653, "learning_rate": 3.3746820221545935e-05, "loss": 4.3392, "step": 12645 }, { "epoch": 0.3862553451435553, "grad_norm": 0.3837074935436249, "learning_rate": 3.374457290330226e-05, "loss": 4.3988, "step": 12646 }, { "epoch": 0.38628588882101406, "grad_norm": 0.38170307874679565, "learning_rate": 3.3742325504542804e-05, "loss": 4.4374, "step": 12647 }, { "epoch": 0.3863164324984728, "grad_norm": 0.3760690987110138, "learning_rate": 3.374007802528827e-05, "loss": 4.3047, "step": 12648 }, { "epoch": 0.38634697617593156, "grad_norm": 0.3698138892650604, "learning_rate": 3.373783046555934e-05, "loss": 4.3035, "step": 12649 }, { "epoch": 0.38637751985339036, "grad_norm": 0.3737974762916565, "learning_rate": 3.373558282537672e-05, "loss": 4.1983, "step": 12650 }, { "epoch": 0.3864080635308491, "grad_norm": 0.3729560673236847, "learning_rate": 3.373333510476109e-05, "loss": 4.3452, "step": 12651 }, { "epoch": 0.38643860720830786, "grad_norm": 0.3947387635707855, "learning_rate": 3.373108730373316e-05, "loss": 4.4041, "step": 12652 }, { "epoch": 0.38646915088576667, "grad_norm": 0.37365761399269104, "learning_rate": 3.372883942231361e-05, "loss": 4.372, "step": 12653 }, { "epoch": 0.3864996945632254, "grad_norm": 0.3769378364086151, "learning_rate": 3.372659146052315e-05, "loss": 4.3963, "step": 12654 }, { "epoch": 0.38653023824068417, "grad_norm": 0.3766956031322479, "learning_rate": 3.3724343418382474e-05, "loss": 4.3268, "step": 12655 }, { "epoch": 0.38656078191814297, "grad_norm": 0.36956584453582764, "learning_rate": 3.372209529591228e-05, "loss": 4.367, "step": 12656 }, { "epoch": 0.3865913255956017, "grad_norm": 0.3851538300514221, "learning_rate": 3.371984709313329e-05, "loss": 4.3468, "step": 12657 }, { "epoch": 0.38662186927306047, "grad_norm": 0.3803946375846863, "learning_rate": 3.371759881006617e-05, "loss": 4.3246, "step": 12658 }, { "epoch": 0.3866524129505192, "grad_norm": 0.36386990547180176, "learning_rate": 3.3715350446731637e-05, "loss": 4.3121, "step": 12659 }, { "epoch": 0.386682956627978, "grad_norm": 0.38260582089424133, "learning_rate": 3.3713102003150386e-05, "loss": 4.2731, "step": 12660 }, { "epoch": 0.3867135003054368, "grad_norm": 0.3964010775089264, "learning_rate": 3.371085347934313e-05, "loss": 4.4307, "step": 12661 }, { "epoch": 0.3867440439828955, "grad_norm": 0.39290568232536316, "learning_rate": 3.3708604875330565e-05, "loss": 4.252, "step": 12662 }, { "epoch": 0.38677458766035433, "grad_norm": 0.38576915860176086, "learning_rate": 3.37063561911334e-05, "loss": 4.3663, "step": 12663 }, { "epoch": 0.3868051313378131, "grad_norm": 0.3974071443080902, "learning_rate": 3.370410742677233e-05, "loss": 4.3588, "step": 12664 }, { "epoch": 0.38683567501527183, "grad_norm": 0.385154128074646, "learning_rate": 3.370185858226809e-05, "loss": 4.3786, "step": 12665 }, { "epoch": 0.3868662186927306, "grad_norm": 0.3769989013671875, "learning_rate": 3.369960965764135e-05, "loss": 4.351, "step": 12666 }, { "epoch": 0.3868967623701894, "grad_norm": 0.3824450671672821, "learning_rate": 3.369736065291282e-05, "loss": 4.2806, "step": 12667 }, { "epoch": 0.38692730604764813, "grad_norm": 0.3847365081310272, "learning_rate": 3.3695111568103235e-05, "loss": 4.3109, "step": 12668 }, { "epoch": 0.3869578497251069, "grad_norm": 0.3763136863708496, "learning_rate": 3.369286240323328e-05, "loss": 4.3405, "step": 12669 }, { "epoch": 0.3869883934025657, "grad_norm": 0.3831380307674408, "learning_rate": 3.369061315832367e-05, "loss": 4.3015, "step": 12670 }, { "epoch": 0.38701893708002444, "grad_norm": 0.37736013531684875, "learning_rate": 3.368836383339511e-05, "loss": 4.1818, "step": 12671 }, { "epoch": 0.3870494807574832, "grad_norm": 0.38494598865509033, "learning_rate": 3.368611442846833e-05, "loss": 4.35, "step": 12672 }, { "epoch": 0.387080024434942, "grad_norm": 0.38323965668678284, "learning_rate": 3.3683864943564026e-05, "loss": 4.2246, "step": 12673 }, { "epoch": 0.38711056811240074, "grad_norm": 0.3862679898738861, "learning_rate": 3.3681615378702915e-05, "loss": 4.3502, "step": 12674 }, { "epoch": 0.3871411117898595, "grad_norm": 0.3822139799594879, "learning_rate": 3.36793657339057e-05, "loss": 4.3101, "step": 12675 }, { "epoch": 0.38717165546731824, "grad_norm": 0.3794493079185486, "learning_rate": 3.367711600919311e-05, "loss": 4.2788, "step": 12676 }, { "epoch": 0.38720219914477705, "grad_norm": 0.37737369537353516, "learning_rate": 3.3674866204585845e-05, "loss": 4.3163, "step": 12677 }, { "epoch": 0.3872327428222358, "grad_norm": 0.39322662353515625, "learning_rate": 3.3672616320104624e-05, "loss": 4.2951, "step": 12678 }, { "epoch": 0.38726328649969455, "grad_norm": 0.3875017762184143, "learning_rate": 3.367036635577017e-05, "loss": 4.2493, "step": 12679 }, { "epoch": 0.38729383017715335, "grad_norm": 0.38065090775489807, "learning_rate": 3.3668116311603195e-05, "loss": 4.3464, "step": 12680 }, { "epoch": 0.3873243738546121, "grad_norm": 0.3695931136608124, "learning_rate": 3.366586618762442e-05, "loss": 4.3487, "step": 12681 }, { "epoch": 0.38735491753207085, "grad_norm": 0.3950637876987457, "learning_rate": 3.366361598385456e-05, "loss": 4.33, "step": 12682 }, { "epoch": 0.3873854612095296, "grad_norm": 0.4000456631183624, "learning_rate": 3.366136570031433e-05, "loss": 4.3122, "step": 12683 }, { "epoch": 0.3874160048869884, "grad_norm": 0.41070204973220825, "learning_rate": 3.365911533702444e-05, "loss": 4.3076, "step": 12684 }, { "epoch": 0.38744654856444716, "grad_norm": 0.38216841220855713, "learning_rate": 3.365686489400564e-05, "loss": 4.2962, "step": 12685 }, { "epoch": 0.3874770922419059, "grad_norm": 0.38543763756752014, "learning_rate": 3.365461437127863e-05, "loss": 4.2835, "step": 12686 }, { "epoch": 0.3875076359193647, "grad_norm": 0.39338549971580505, "learning_rate": 3.3652363768864134e-05, "loss": 4.3152, "step": 12687 }, { "epoch": 0.38753817959682346, "grad_norm": 0.3921242356300354, "learning_rate": 3.3650113086782876e-05, "loss": 4.3142, "step": 12688 }, { "epoch": 0.3875687232742822, "grad_norm": 0.3835686147212982, "learning_rate": 3.3647862325055585e-05, "loss": 4.3788, "step": 12689 }, { "epoch": 0.387599266951741, "grad_norm": 0.3755212426185608, "learning_rate": 3.3645611483702974e-05, "loss": 4.3649, "step": 12690 }, { "epoch": 0.38762981062919977, "grad_norm": 0.3718660771846771, "learning_rate": 3.3643360562745774e-05, "loss": 4.2638, "step": 12691 }, { "epoch": 0.3876603543066585, "grad_norm": 0.3831847906112671, "learning_rate": 3.364110956220471e-05, "loss": 4.2974, "step": 12692 }, { "epoch": 0.38769089798411727, "grad_norm": 0.3731679618358612, "learning_rate": 3.3638858482100504e-05, "loss": 4.3288, "step": 12693 }, { "epoch": 0.38772144166157607, "grad_norm": 0.3891741633415222, "learning_rate": 3.3636607322453884e-05, "loss": 4.3325, "step": 12694 }, { "epoch": 0.3877519853390348, "grad_norm": 0.38442808389663696, "learning_rate": 3.363435608328558e-05, "loss": 4.3632, "step": 12695 }, { "epoch": 0.38778252901649357, "grad_norm": 0.3827371299266815, "learning_rate": 3.3632104764616334e-05, "loss": 4.2696, "step": 12696 }, { "epoch": 0.3878130726939524, "grad_norm": 0.3951757550239563, "learning_rate": 3.362985336646685e-05, "loss": 4.3303, "step": 12697 }, { "epoch": 0.3878436163714111, "grad_norm": 0.3759489059448242, "learning_rate": 3.3627601888857875e-05, "loss": 4.2992, "step": 12698 }, { "epoch": 0.3878741600488699, "grad_norm": 0.39328551292419434, "learning_rate": 3.362535033181013e-05, "loss": 4.3609, "step": 12699 }, { "epoch": 0.3879047037263286, "grad_norm": 0.38005316257476807, "learning_rate": 3.3623098695344343e-05, "loss": 4.2655, "step": 12700 }, { "epoch": 0.38793524740378743, "grad_norm": 0.38204705715179443, "learning_rate": 3.362084697948126e-05, "loss": 4.2529, "step": 12701 }, { "epoch": 0.3879657910812462, "grad_norm": 0.38013777136802673, "learning_rate": 3.361859518424161e-05, "loss": 4.2713, "step": 12702 }, { "epoch": 0.38799633475870493, "grad_norm": 0.38635310530662537, "learning_rate": 3.361634330964612e-05, "loss": 4.2099, "step": 12703 }, { "epoch": 0.38802687843616374, "grad_norm": 0.39442065358161926, "learning_rate": 3.361409135571552e-05, "loss": 4.3395, "step": 12704 }, { "epoch": 0.3880574221136225, "grad_norm": 0.3744988739490509, "learning_rate": 3.361183932247056e-05, "loss": 4.3205, "step": 12705 }, { "epoch": 0.38808796579108124, "grad_norm": 0.3859473764896393, "learning_rate": 3.360958720993196e-05, "loss": 4.357, "step": 12706 }, { "epoch": 0.38811850946854, "grad_norm": 0.3849368095397949, "learning_rate": 3.3607335018120476e-05, "loss": 4.2772, "step": 12707 }, { "epoch": 0.3881490531459988, "grad_norm": 0.38317134976387024, "learning_rate": 3.360508274705682e-05, "loss": 4.3539, "step": 12708 }, { "epoch": 0.38817959682345754, "grad_norm": 0.3826010823249817, "learning_rate": 3.360283039676175e-05, "loss": 4.252, "step": 12709 }, { "epoch": 0.3882101405009163, "grad_norm": 0.38185450434684753, "learning_rate": 3.3600577967255995e-05, "loss": 4.1544, "step": 12710 }, { "epoch": 0.3882406841783751, "grad_norm": 0.3825293779373169, "learning_rate": 3.3598325458560295e-05, "loss": 4.3012, "step": 12711 }, { "epoch": 0.38827122785583384, "grad_norm": 0.3918837308883667, "learning_rate": 3.359607287069541e-05, "loss": 4.3352, "step": 12712 }, { "epoch": 0.3883017715332926, "grad_norm": 0.38270285725593567, "learning_rate": 3.359382020368204e-05, "loss": 4.2842, "step": 12713 }, { "epoch": 0.3883323152107514, "grad_norm": 0.37686610221862793, "learning_rate": 3.359156745754095e-05, "loss": 4.4448, "step": 12714 }, { "epoch": 0.38836285888821015, "grad_norm": 0.38444721698760986, "learning_rate": 3.358931463229289e-05, "loss": 4.2652, "step": 12715 }, { "epoch": 0.3883934025656689, "grad_norm": 0.38169121742248535, "learning_rate": 3.358706172795859e-05, "loss": 4.2988, "step": 12716 }, { "epoch": 0.38842394624312765, "grad_norm": 0.37168067693710327, "learning_rate": 3.3584808744558806e-05, "loss": 4.3035, "step": 12717 }, { "epoch": 0.38845448992058645, "grad_norm": 0.38525938987731934, "learning_rate": 3.358255568211426e-05, "loss": 4.3476, "step": 12718 }, { "epoch": 0.3884850335980452, "grad_norm": 0.38041603565216064, "learning_rate": 3.3580302540645714e-05, "loss": 4.3516, "step": 12719 }, { "epoch": 0.38851557727550395, "grad_norm": 0.3830111622810364, "learning_rate": 3.3578049320173924e-05, "loss": 4.3707, "step": 12720 }, { "epoch": 0.38854612095296276, "grad_norm": 0.38314729928970337, "learning_rate": 3.3575796020719605e-05, "loss": 4.196, "step": 12721 }, { "epoch": 0.3885766646304215, "grad_norm": 0.3974449038505554, "learning_rate": 3.357354264230353e-05, "loss": 4.2429, "step": 12722 }, { "epoch": 0.38860720830788026, "grad_norm": 0.3844779133796692, "learning_rate": 3.357128918494645e-05, "loss": 4.2786, "step": 12723 }, { "epoch": 0.388637751985339, "grad_norm": 0.37754079699516296, "learning_rate": 3.356903564866909e-05, "loss": 4.2996, "step": 12724 }, { "epoch": 0.3886682956627978, "grad_norm": 0.37882161140441895, "learning_rate": 3.3566782033492214e-05, "loss": 4.2959, "step": 12725 }, { "epoch": 0.38869883934025656, "grad_norm": 0.3782145380973816, "learning_rate": 3.3564528339436585e-05, "loss": 4.3278, "step": 12726 }, { "epoch": 0.3887293830177153, "grad_norm": 0.37920984625816345, "learning_rate": 3.356227456652293e-05, "loss": 4.3168, "step": 12727 }, { "epoch": 0.3887599266951741, "grad_norm": 0.3741978704929352, "learning_rate": 3.356002071477201e-05, "loss": 4.3551, "step": 12728 }, { "epoch": 0.38879047037263287, "grad_norm": 0.39056646823883057, "learning_rate": 3.355776678420458e-05, "loss": 4.3504, "step": 12729 }, { "epoch": 0.3888210140500916, "grad_norm": 0.38334670662879944, "learning_rate": 3.355551277484139e-05, "loss": 4.2857, "step": 12730 }, { "epoch": 0.3888515577275504, "grad_norm": 0.3912966549396515, "learning_rate": 3.355325868670319e-05, "loss": 4.3484, "step": 12731 }, { "epoch": 0.3888821014050092, "grad_norm": 0.388803094625473, "learning_rate": 3.355100451981075e-05, "loss": 4.2653, "step": 12732 }, { "epoch": 0.3889126450824679, "grad_norm": 0.3771200180053711, "learning_rate": 3.354875027418481e-05, "loss": 4.3218, "step": 12733 }, { "epoch": 0.3889431887599267, "grad_norm": 0.3764488995075226, "learning_rate": 3.354649594984613e-05, "loss": 4.2793, "step": 12734 }, { "epoch": 0.3889737324373855, "grad_norm": 0.3808601498603821, "learning_rate": 3.354424154681548e-05, "loss": 4.3344, "step": 12735 }, { "epoch": 0.3890042761148442, "grad_norm": 0.3787725269794464, "learning_rate": 3.354198706511359e-05, "loss": 4.3522, "step": 12736 }, { "epoch": 0.389034819792303, "grad_norm": 0.3673238456249237, "learning_rate": 3.353973250476124e-05, "loss": 4.3249, "step": 12737 }, { "epoch": 0.3890653634697618, "grad_norm": 0.37683534622192383, "learning_rate": 3.3537477865779175e-05, "loss": 4.3684, "step": 12738 }, { "epoch": 0.38909590714722053, "grad_norm": 0.3942182958126068, "learning_rate": 3.353522314818816e-05, "loss": 4.3235, "step": 12739 }, { "epoch": 0.3891264508246793, "grad_norm": 0.3762376010417938, "learning_rate": 3.353296835200897e-05, "loss": 4.307, "step": 12740 }, { "epoch": 0.38915699450213803, "grad_norm": 0.3864403963088989, "learning_rate": 3.353071347726235e-05, "loss": 4.3831, "step": 12741 }, { "epoch": 0.38918753817959684, "grad_norm": 0.3789044916629791, "learning_rate": 3.352845852396905e-05, "loss": 4.3937, "step": 12742 }, { "epoch": 0.3892180818570556, "grad_norm": 0.36998698115348816, "learning_rate": 3.3526203492149865e-05, "loss": 4.331, "step": 12743 }, { "epoch": 0.38924862553451434, "grad_norm": 0.3981221616268158, "learning_rate": 3.352394838182554e-05, "loss": 4.3074, "step": 12744 }, { "epoch": 0.38927916921197314, "grad_norm": 0.38492345809936523, "learning_rate": 3.352169319301683e-05, "loss": 4.3073, "step": 12745 }, { "epoch": 0.3893097128894319, "grad_norm": 0.37150973081588745, "learning_rate": 3.351943792574451e-05, "loss": 4.2496, "step": 12746 }, { "epoch": 0.38934025656689064, "grad_norm": 0.3721790015697479, "learning_rate": 3.3517182580029354e-05, "loss": 4.3955, "step": 12747 }, { "epoch": 0.38937080024434945, "grad_norm": 0.3762829899787903, "learning_rate": 3.3514927155892105e-05, "loss": 4.3458, "step": 12748 }, { "epoch": 0.3894013439218082, "grad_norm": 0.38981524109840393, "learning_rate": 3.3512671653353554e-05, "loss": 4.3774, "step": 12749 }, { "epoch": 0.38943188759926695, "grad_norm": 0.38491231203079224, "learning_rate": 3.351041607243446e-05, "loss": 4.3437, "step": 12750 }, { "epoch": 0.3894624312767257, "grad_norm": 0.3780395984649658, "learning_rate": 3.350816041315559e-05, "loss": 4.2946, "step": 12751 }, { "epoch": 0.3894929749541845, "grad_norm": 0.3779726028442383, "learning_rate": 3.350590467553771e-05, "loss": 4.3395, "step": 12752 }, { "epoch": 0.38952351863164325, "grad_norm": 0.3819180130958557, "learning_rate": 3.350364885960159e-05, "loss": 4.3286, "step": 12753 }, { "epoch": 0.389554062309102, "grad_norm": 0.376300573348999, "learning_rate": 3.3501392965368006e-05, "loss": 4.3143, "step": 12754 }, { "epoch": 0.3895846059865608, "grad_norm": 0.3854542374610901, "learning_rate": 3.349913699285772e-05, "loss": 4.3588, "step": 12755 }, { "epoch": 0.38961514966401956, "grad_norm": 0.37826409935951233, "learning_rate": 3.349688094209151e-05, "loss": 4.3354, "step": 12756 }, { "epoch": 0.3896456933414783, "grad_norm": 0.3670383393764496, "learning_rate": 3.349462481309015e-05, "loss": 4.3295, "step": 12757 }, { "epoch": 0.38967623701893706, "grad_norm": 0.37920597195625305, "learning_rate": 3.349236860587442e-05, "loss": 4.2968, "step": 12758 }, { "epoch": 0.38970678069639586, "grad_norm": 0.3877696692943573, "learning_rate": 3.3490112320465076e-05, "loss": 4.4143, "step": 12759 }, { "epoch": 0.3897373243738546, "grad_norm": 0.3842470347881317, "learning_rate": 3.348785595688291e-05, "loss": 4.3269, "step": 12760 }, { "epoch": 0.38976786805131336, "grad_norm": 0.379366397857666, "learning_rate": 3.348559951514869e-05, "loss": 4.3115, "step": 12761 }, { "epoch": 0.38979841172877217, "grad_norm": 0.3761358857154846, "learning_rate": 3.348334299528318e-05, "loss": 4.2908, "step": 12762 }, { "epoch": 0.3898289554062309, "grad_norm": 0.39444008469581604, "learning_rate": 3.348108639730718e-05, "loss": 4.2917, "step": 12763 }, { "epoch": 0.38985949908368966, "grad_norm": 0.37432533502578735, "learning_rate": 3.3478829721241454e-05, "loss": 4.3385, "step": 12764 }, { "epoch": 0.38989004276114847, "grad_norm": 0.38053983449935913, "learning_rate": 3.347657296710679e-05, "loss": 4.1745, "step": 12765 }, { "epoch": 0.3899205864386072, "grad_norm": 0.37705492973327637, "learning_rate": 3.347431613492395e-05, "loss": 4.3304, "step": 12766 }, { "epoch": 0.38995113011606597, "grad_norm": 0.38421037793159485, "learning_rate": 3.347205922471374e-05, "loss": 4.2399, "step": 12767 }, { "epoch": 0.3899816737935247, "grad_norm": 0.3789527714252472, "learning_rate": 3.346980223649691e-05, "loss": 4.3115, "step": 12768 }, { "epoch": 0.3900122174709835, "grad_norm": 0.3810254633426666, "learning_rate": 3.3467545170294254e-05, "loss": 4.2724, "step": 12769 }, { "epoch": 0.3900427611484423, "grad_norm": 0.3819664716720581, "learning_rate": 3.346528802612657e-05, "loss": 4.2877, "step": 12770 }, { "epoch": 0.390073304825901, "grad_norm": 0.38935086131095886, "learning_rate": 3.3463030804014614e-05, "loss": 4.4304, "step": 12771 }, { "epoch": 0.39010384850335983, "grad_norm": 0.3889829218387604, "learning_rate": 3.3460773503979185e-05, "loss": 4.2541, "step": 12772 }, { "epoch": 0.3901343921808186, "grad_norm": 0.38493111729621887, "learning_rate": 3.3458516126041066e-05, "loss": 4.3639, "step": 12773 }, { "epoch": 0.39016493585827733, "grad_norm": 0.4190545678138733, "learning_rate": 3.345625867022104e-05, "loss": 4.3001, "step": 12774 }, { "epoch": 0.3901954795357361, "grad_norm": 0.3857395350933075, "learning_rate": 3.34540011365399e-05, "loss": 4.3439, "step": 12775 }, { "epoch": 0.3902260232131949, "grad_norm": 0.37300270795822144, "learning_rate": 3.345174352501842e-05, "loss": 4.3273, "step": 12776 }, { "epoch": 0.39025656689065363, "grad_norm": 0.3878750801086426, "learning_rate": 3.3449485835677384e-05, "loss": 4.424, "step": 12777 }, { "epoch": 0.3902871105681124, "grad_norm": 0.3904136121273041, "learning_rate": 3.34472280685376e-05, "loss": 4.3642, "step": 12778 }, { "epoch": 0.3903176542455712, "grad_norm": 0.38228586316108704, "learning_rate": 3.344497022361983e-05, "loss": 4.2511, "step": 12779 }, { "epoch": 0.39034819792302994, "grad_norm": 0.38631579279899597, "learning_rate": 3.344271230094489e-05, "loss": 4.3164, "step": 12780 }, { "epoch": 0.3903787416004887, "grad_norm": 0.4078418016433716, "learning_rate": 3.344045430053355e-05, "loss": 4.247, "step": 12781 }, { "epoch": 0.39040928527794744, "grad_norm": 0.37608200311660767, "learning_rate": 3.343819622240662e-05, "loss": 4.4483, "step": 12782 }, { "epoch": 0.39043982895540624, "grad_norm": 0.380309522151947, "learning_rate": 3.343593806658486e-05, "loss": 4.3933, "step": 12783 }, { "epoch": 0.390470372632865, "grad_norm": 0.37880486249923706, "learning_rate": 3.343367983308909e-05, "loss": 4.3602, "step": 12784 }, { "epoch": 0.39050091631032374, "grad_norm": 0.3798149824142456, "learning_rate": 3.34314215219401e-05, "loss": 4.3842, "step": 12785 }, { "epoch": 0.39053145998778255, "grad_norm": 0.3735947608947754, "learning_rate": 3.3429163133158655e-05, "loss": 4.1407, "step": 12786 }, { "epoch": 0.3905620036652413, "grad_norm": 0.39842694997787476, "learning_rate": 3.342690466676559e-05, "loss": 4.1904, "step": 12787 }, { "epoch": 0.39059254734270005, "grad_norm": 0.38870134949684143, "learning_rate": 3.342464612278168e-05, "loss": 4.3344, "step": 12788 }, { "epoch": 0.39062309102015885, "grad_norm": 0.3876188099384308, "learning_rate": 3.342238750122771e-05, "loss": 4.3677, "step": 12789 }, { "epoch": 0.3906536346976176, "grad_norm": 0.3889944851398468, "learning_rate": 3.3420128802124506e-05, "loss": 4.2918, "step": 12790 }, { "epoch": 0.39068417837507635, "grad_norm": 0.3817378878593445, "learning_rate": 3.341787002549284e-05, "loss": 4.3579, "step": 12791 }, { "epoch": 0.3907147220525351, "grad_norm": 0.3874548673629761, "learning_rate": 3.3415611171353514e-05, "loss": 4.3958, "step": 12792 }, { "epoch": 0.3907452657299939, "grad_norm": 0.3956975042819977, "learning_rate": 3.341335223972732e-05, "loss": 4.3719, "step": 12793 }, { "epoch": 0.39077580940745266, "grad_norm": 0.3948168456554413, "learning_rate": 3.341109323063508e-05, "loss": 4.2593, "step": 12794 }, { "epoch": 0.3908063530849114, "grad_norm": 0.38178369402885437, "learning_rate": 3.340883414409758e-05, "loss": 4.2971, "step": 12795 }, { "epoch": 0.3908368967623702, "grad_norm": 0.3941432237625122, "learning_rate": 3.340657498013561e-05, "loss": 4.2705, "step": 12796 }, { "epoch": 0.39086744043982896, "grad_norm": 0.37965884804725647, "learning_rate": 3.340431573876999e-05, "loss": 4.3354, "step": 12797 }, { "epoch": 0.3908979841172877, "grad_norm": 0.3805980384349823, "learning_rate": 3.340205642002152e-05, "loss": 4.3691, "step": 12798 }, { "epoch": 0.39092852779474646, "grad_norm": 0.3920157253742218, "learning_rate": 3.339979702391099e-05, "loss": 4.3103, "step": 12799 }, { "epoch": 0.39095907147220527, "grad_norm": 0.3847603499889374, "learning_rate": 3.33975375504592e-05, "loss": 4.193, "step": 12800 }, { "epoch": 0.390989615149664, "grad_norm": 0.38290074467658997, "learning_rate": 3.339527799968698e-05, "loss": 4.3742, "step": 12801 }, { "epoch": 0.39102015882712277, "grad_norm": 0.3928385078907013, "learning_rate": 3.339301837161511e-05, "loss": 4.2618, "step": 12802 }, { "epoch": 0.39105070250458157, "grad_norm": 0.385326623916626, "learning_rate": 3.3390758666264404e-05, "loss": 4.3149, "step": 12803 }, { "epoch": 0.3910812461820403, "grad_norm": 0.3838963508605957, "learning_rate": 3.338849888365567e-05, "loss": 4.3662, "step": 12804 }, { "epoch": 0.39111178985949907, "grad_norm": 0.3779052495956421, "learning_rate": 3.338623902380972e-05, "loss": 4.3136, "step": 12805 }, { "epoch": 0.3911423335369579, "grad_norm": 0.40002816915512085, "learning_rate": 3.3383979086747355e-05, "loss": 4.303, "step": 12806 }, { "epoch": 0.3911728772144166, "grad_norm": 0.38458722829818726, "learning_rate": 3.3381719072489376e-05, "loss": 4.3859, "step": 12807 }, { "epoch": 0.3912034208918754, "grad_norm": 0.3826366066932678, "learning_rate": 3.3379458981056605e-05, "loss": 4.2829, "step": 12808 }, { "epoch": 0.3912339645693341, "grad_norm": 0.3924775719642639, "learning_rate": 3.3377198812469847e-05, "loss": 4.2361, "step": 12809 }, { "epoch": 0.39126450824679293, "grad_norm": 0.40357810258865356, "learning_rate": 3.33749385667499e-05, "loss": 4.3399, "step": 12810 }, { "epoch": 0.3912950519242517, "grad_norm": 0.3949597477912903, "learning_rate": 3.3372678243917604e-05, "loss": 4.3141, "step": 12811 }, { "epoch": 0.39132559560171043, "grad_norm": 0.38667261600494385, "learning_rate": 3.3370417843993754e-05, "loss": 4.3901, "step": 12812 }, { "epoch": 0.39135613927916924, "grad_norm": 0.3920230567455292, "learning_rate": 3.336815736699916e-05, "loss": 4.2857, "step": 12813 }, { "epoch": 0.391386682956628, "grad_norm": 0.38714560866355896, "learning_rate": 3.336589681295463e-05, "loss": 4.3896, "step": 12814 }, { "epoch": 0.39141722663408673, "grad_norm": 0.38219568133354187, "learning_rate": 3.3363636181881e-05, "loss": 4.2679, "step": 12815 }, { "epoch": 0.3914477703115455, "grad_norm": 0.37545832991600037, "learning_rate": 3.336137547379907e-05, "loss": 4.3645, "step": 12816 }, { "epoch": 0.3914783139890043, "grad_norm": 0.3805733323097229, "learning_rate": 3.335911468872964e-05, "loss": 4.3071, "step": 12817 }, { "epoch": 0.39150885766646304, "grad_norm": 0.40165024995803833, "learning_rate": 3.335685382669356e-05, "loss": 4.2739, "step": 12818 }, { "epoch": 0.3915394013439218, "grad_norm": 0.3805573582649231, "learning_rate": 3.335459288771163e-05, "loss": 4.2067, "step": 12819 }, { "epoch": 0.3915699450213806, "grad_norm": 0.37877145409584045, "learning_rate": 3.335233187180466e-05, "loss": 4.2586, "step": 12820 }, { "epoch": 0.39160048869883934, "grad_norm": 0.3895342946052551, "learning_rate": 3.335007077899348e-05, "loss": 4.3592, "step": 12821 }, { "epoch": 0.3916310323762981, "grad_norm": 0.4010199308395386, "learning_rate": 3.334780960929891e-05, "loss": 4.2302, "step": 12822 }, { "epoch": 0.3916615760537569, "grad_norm": 0.39331457018852234, "learning_rate": 3.334554836274175e-05, "loss": 4.3211, "step": 12823 }, { "epoch": 0.39169211973121565, "grad_norm": 0.3840847909450531, "learning_rate": 3.334328703934285e-05, "loss": 4.3063, "step": 12824 }, { "epoch": 0.3917226634086744, "grad_norm": 0.3765396177768707, "learning_rate": 3.334102563912301e-05, "loss": 4.3205, "step": 12825 }, { "epoch": 0.39175320708613315, "grad_norm": 0.4020943343639374, "learning_rate": 3.3338764162103066e-05, "loss": 4.3566, "step": 12826 }, { "epoch": 0.39178375076359195, "grad_norm": 0.3999369442462921, "learning_rate": 3.333650260830382e-05, "loss": 4.2776, "step": 12827 }, { "epoch": 0.3918142944410507, "grad_norm": 0.3722470998764038, "learning_rate": 3.3334240977746116e-05, "loss": 4.2268, "step": 12828 }, { "epoch": 0.39184483811850945, "grad_norm": 0.37923669815063477, "learning_rate": 3.333197927045078e-05, "loss": 4.2779, "step": 12829 }, { "epoch": 0.39187538179596826, "grad_norm": 0.38699546456336975, "learning_rate": 3.332971748643861e-05, "loss": 4.3079, "step": 12830 }, { "epoch": 0.391905925473427, "grad_norm": 0.40014585852622986, "learning_rate": 3.332745562573046e-05, "loss": 4.386, "step": 12831 }, { "epoch": 0.39193646915088576, "grad_norm": 0.3726422190666199, "learning_rate": 3.332519368834714e-05, "loss": 4.3017, "step": 12832 }, { "epoch": 0.3919670128283445, "grad_norm": 0.379638671875, "learning_rate": 3.3322931674309476e-05, "loss": 4.3298, "step": 12833 }, { "epoch": 0.3919975565058033, "grad_norm": 0.37530621886253357, "learning_rate": 3.3320669583638304e-05, "loss": 4.2406, "step": 12834 }, { "epoch": 0.39202810018326206, "grad_norm": 0.3861815631389618, "learning_rate": 3.331840741635445e-05, "loss": 4.3203, "step": 12835 }, { "epoch": 0.3920586438607208, "grad_norm": 0.39047518372535706, "learning_rate": 3.3316145172478745e-05, "loss": 4.2803, "step": 12836 }, { "epoch": 0.3920891875381796, "grad_norm": 0.3875751793384552, "learning_rate": 3.331388285203201e-05, "loss": 4.388, "step": 12837 }, { "epoch": 0.39211973121563837, "grad_norm": 0.38498392701148987, "learning_rate": 3.3311620455035094e-05, "loss": 4.1757, "step": 12838 }, { "epoch": 0.3921502748930971, "grad_norm": 0.38912731409072876, "learning_rate": 3.3309357981508805e-05, "loss": 4.3239, "step": 12839 }, { "epoch": 0.3921808185705559, "grad_norm": 0.382699579000473, "learning_rate": 3.330709543147398e-05, "loss": 4.3817, "step": 12840 }, { "epoch": 0.39221136224801467, "grad_norm": 0.3826519250869751, "learning_rate": 3.3304832804951464e-05, "loss": 4.2824, "step": 12841 }, { "epoch": 0.3922419059254734, "grad_norm": 0.37227118015289307, "learning_rate": 3.330257010196208e-05, "loss": 4.1185, "step": 12842 }, { "epoch": 0.39227244960293217, "grad_norm": 0.39192450046539307, "learning_rate": 3.330030732252666e-05, "loss": 4.3263, "step": 12843 }, { "epoch": 0.392302993280391, "grad_norm": 0.3984135091304779, "learning_rate": 3.3298044466666045e-05, "loss": 4.3235, "step": 12844 }, { "epoch": 0.3923335369578497, "grad_norm": 0.41028350591659546, "learning_rate": 3.329578153440108e-05, "loss": 4.3039, "step": 12845 }, { "epoch": 0.3923640806353085, "grad_norm": 0.38036686182022095, "learning_rate": 3.3293518525752576e-05, "loss": 4.3031, "step": 12846 }, { "epoch": 0.3923946243127673, "grad_norm": 0.3845534026622772, "learning_rate": 3.3291255440741384e-05, "loss": 4.3308, "step": 12847 }, { "epoch": 0.39242516799022603, "grad_norm": 0.3829542100429535, "learning_rate": 3.328899227938834e-05, "loss": 4.359, "step": 12848 }, { "epoch": 0.3924557116676848, "grad_norm": 0.37389782071113586, "learning_rate": 3.328672904171429e-05, "loss": 4.2397, "step": 12849 }, { "epoch": 0.39248625534514353, "grad_norm": 0.38346680998802185, "learning_rate": 3.328446572774006e-05, "loss": 4.3094, "step": 12850 }, { "epoch": 0.39251679902260234, "grad_norm": 0.3725661039352417, "learning_rate": 3.328220233748649e-05, "loss": 4.3443, "step": 12851 }, { "epoch": 0.3925473427000611, "grad_norm": 0.3837326765060425, "learning_rate": 3.327993887097443e-05, "loss": 4.3, "step": 12852 }, { "epoch": 0.39257788637751984, "grad_norm": 0.3870351314544678, "learning_rate": 3.327767532822472e-05, "loss": 4.3513, "step": 12853 }, { "epoch": 0.39260843005497864, "grad_norm": 0.379317045211792, "learning_rate": 3.327541170925819e-05, "loss": 4.244, "step": 12854 }, { "epoch": 0.3926389737324374, "grad_norm": 0.38907596468925476, "learning_rate": 3.3273148014095695e-05, "loss": 4.2656, "step": 12855 }, { "epoch": 0.39266951740989614, "grad_norm": 0.3861120343208313, "learning_rate": 3.3270884242758074e-05, "loss": 4.3261, "step": 12856 }, { "epoch": 0.3927000610873549, "grad_norm": 0.3811911344528198, "learning_rate": 3.326862039526616e-05, "loss": 4.31, "step": 12857 }, { "epoch": 0.3927306047648137, "grad_norm": 0.38226234912872314, "learning_rate": 3.326635647164081e-05, "loss": 4.3728, "step": 12858 }, { "epoch": 0.39276114844227245, "grad_norm": 0.3844098150730133, "learning_rate": 3.326409247190287e-05, "loss": 4.3076, "step": 12859 }, { "epoch": 0.3927916921197312, "grad_norm": 0.38630351424217224, "learning_rate": 3.326182839607318e-05, "loss": 4.3441, "step": 12860 }, { "epoch": 0.39282223579719, "grad_norm": 0.3939475417137146, "learning_rate": 3.3259564244172586e-05, "loss": 4.2764, "step": 12861 }, { "epoch": 0.39285277947464875, "grad_norm": 0.3784434199333191, "learning_rate": 3.325730001622194e-05, "loss": 4.3868, "step": 12862 }, { "epoch": 0.3928833231521075, "grad_norm": 0.36986666917800903, "learning_rate": 3.325503571224209e-05, "loss": 4.3397, "step": 12863 }, { "epoch": 0.3929138668295663, "grad_norm": 0.3874076008796692, "learning_rate": 3.325277133225387e-05, "loss": 4.2998, "step": 12864 }, { "epoch": 0.39294441050702505, "grad_norm": 0.3765331208705902, "learning_rate": 3.3250506876278155e-05, "loss": 4.2573, "step": 12865 }, { "epoch": 0.3929749541844838, "grad_norm": 0.37877166271209717, "learning_rate": 3.324824234433577e-05, "loss": 4.3146, "step": 12866 }, { "epoch": 0.39300549786194255, "grad_norm": 0.38574105501174927, "learning_rate": 3.324597773644759e-05, "loss": 4.3084, "step": 12867 }, { "epoch": 0.39303604153940136, "grad_norm": 0.38610556721687317, "learning_rate": 3.324371305263444e-05, "loss": 4.2548, "step": 12868 }, { "epoch": 0.3930665852168601, "grad_norm": 0.3804262578487396, "learning_rate": 3.3241448292917195e-05, "loss": 4.3036, "step": 12869 }, { "epoch": 0.39309712889431886, "grad_norm": 0.39444655179977417, "learning_rate": 3.323918345731669e-05, "loss": 4.4073, "step": 12870 }, { "epoch": 0.39312767257177766, "grad_norm": 0.3839309811592102, "learning_rate": 3.323691854585379e-05, "loss": 4.3527, "step": 12871 }, { "epoch": 0.3931582162492364, "grad_norm": 0.3683931231498718, "learning_rate": 3.323465355854934e-05, "loss": 4.2937, "step": 12872 }, { "epoch": 0.39318875992669516, "grad_norm": 0.3843402862548828, "learning_rate": 3.3232388495424215e-05, "loss": 4.359, "step": 12873 }, { "epoch": 0.3932193036041539, "grad_norm": 0.3821541965007782, "learning_rate": 3.323012335649925e-05, "loss": 4.3421, "step": 12874 }, { "epoch": 0.3932498472816127, "grad_norm": 0.3748878538608551, "learning_rate": 3.322785814179531e-05, "loss": 4.3768, "step": 12875 }, { "epoch": 0.39328039095907147, "grad_norm": 0.3814595341682434, "learning_rate": 3.322559285133324e-05, "loss": 4.156, "step": 12876 }, { "epoch": 0.3933109346365302, "grad_norm": 0.37791168689727783, "learning_rate": 3.322332748513392e-05, "loss": 4.4168, "step": 12877 }, { "epoch": 0.393341478313989, "grad_norm": 0.3876991868019104, "learning_rate": 3.3221062043218185e-05, "loss": 4.4033, "step": 12878 }, { "epoch": 0.3933720219914478, "grad_norm": 0.3783547282218933, "learning_rate": 3.321879652560691e-05, "loss": 4.3724, "step": 12879 }, { "epoch": 0.3934025656689065, "grad_norm": 0.38569268584251404, "learning_rate": 3.321653093232095e-05, "loss": 4.2986, "step": 12880 }, { "epoch": 0.39343310934636533, "grad_norm": 0.37799271941185, "learning_rate": 3.3214265263381164e-05, "loss": 4.2416, "step": 12881 }, { "epoch": 0.3934636530238241, "grad_norm": 0.3689189553260803, "learning_rate": 3.321199951880841e-05, "loss": 4.3467, "step": 12882 }, { "epoch": 0.39349419670128283, "grad_norm": 0.39493420720100403, "learning_rate": 3.3209733698623564e-05, "loss": 4.3563, "step": 12883 }, { "epoch": 0.3935247403787416, "grad_norm": 0.3821980953216553, "learning_rate": 3.3207467802847473e-05, "loss": 4.3502, "step": 12884 }, { "epoch": 0.3935552840562004, "grad_norm": 0.3938975930213928, "learning_rate": 3.320520183150101e-05, "loss": 4.2941, "step": 12885 }, { "epoch": 0.39358582773365913, "grad_norm": 0.3730866312980652, "learning_rate": 3.320293578460503e-05, "loss": 4.3368, "step": 12886 }, { "epoch": 0.3936163714111179, "grad_norm": 0.3791210949420929, "learning_rate": 3.3200669662180404e-05, "loss": 4.2704, "step": 12887 }, { "epoch": 0.3936469150885767, "grad_norm": 0.3934895694255829, "learning_rate": 3.3198403464247996e-05, "loss": 4.3834, "step": 12888 }, { "epoch": 0.39367745876603544, "grad_norm": 0.38581573963165283, "learning_rate": 3.3196137190828676e-05, "loss": 4.2043, "step": 12889 }, { "epoch": 0.3937080024434942, "grad_norm": 0.37898561358451843, "learning_rate": 3.31938708419433e-05, "loss": 4.334, "step": 12890 }, { "epoch": 0.39373854612095294, "grad_norm": 0.4021212160587311, "learning_rate": 3.3191604417612756e-05, "loss": 4.4053, "step": 12891 }, { "epoch": 0.39376908979841174, "grad_norm": 0.38423314690589905, "learning_rate": 3.3189337917857884e-05, "loss": 4.3895, "step": 12892 }, { "epoch": 0.3937996334758705, "grad_norm": 0.3833100497722626, "learning_rate": 3.318707134269957e-05, "loss": 4.2982, "step": 12893 }, { "epoch": 0.39383017715332924, "grad_norm": 0.3798324763774872, "learning_rate": 3.318480469215869e-05, "loss": 4.3117, "step": 12894 }, { "epoch": 0.39386072083078805, "grad_norm": 0.3861099183559418, "learning_rate": 3.318253796625609e-05, "loss": 4.3302, "step": 12895 }, { "epoch": 0.3938912645082468, "grad_norm": 0.3773421049118042, "learning_rate": 3.318027116501267e-05, "loss": 4.2294, "step": 12896 }, { "epoch": 0.39392180818570555, "grad_norm": 0.3726162314414978, "learning_rate": 3.3178004288449275e-05, "loss": 4.1532, "step": 12897 }, { "epoch": 0.39395235186316435, "grad_norm": 0.4056928753852844, "learning_rate": 3.317573733658679e-05, "loss": 4.3857, "step": 12898 }, { "epoch": 0.3939828955406231, "grad_norm": 0.37905946373939514, "learning_rate": 3.31734703094461e-05, "loss": 4.3271, "step": 12899 }, { "epoch": 0.39401343921808185, "grad_norm": 0.38188686966896057, "learning_rate": 3.317120320704806e-05, "loss": 4.2595, "step": 12900 }, { "epoch": 0.3940439828955406, "grad_norm": 0.37732061743736267, "learning_rate": 3.3168936029413557e-05, "loss": 4.2825, "step": 12901 }, { "epoch": 0.3940745265729994, "grad_norm": 0.39558881521224976, "learning_rate": 3.3166668776563446e-05, "loss": 4.2225, "step": 12902 }, { "epoch": 0.39410507025045816, "grad_norm": 0.3895266652107239, "learning_rate": 3.316440144851862e-05, "loss": 4.3269, "step": 12903 }, { "epoch": 0.3941356139279169, "grad_norm": 0.38203513622283936, "learning_rate": 3.3162134045299964e-05, "loss": 4.3074, "step": 12904 }, { "epoch": 0.3941661576053757, "grad_norm": 0.3833335041999817, "learning_rate": 3.3159866566928335e-05, "loss": 4.3146, "step": 12905 }, { "epoch": 0.39419670128283446, "grad_norm": 0.3870137631893158, "learning_rate": 3.315759901342462e-05, "loss": 4.2544, "step": 12906 }, { "epoch": 0.3942272449602932, "grad_norm": 0.3767552375793457, "learning_rate": 3.315533138480969e-05, "loss": 4.3231, "step": 12907 }, { "epoch": 0.39425778863775196, "grad_norm": 0.38049617409706116, "learning_rate": 3.315306368110444e-05, "loss": 4.3116, "step": 12908 }, { "epoch": 0.39428833231521077, "grad_norm": 0.37281736731529236, "learning_rate": 3.3150795902329746e-05, "loss": 4.3833, "step": 12909 }, { "epoch": 0.3943188759926695, "grad_norm": 0.38618341088294983, "learning_rate": 3.314852804850647e-05, "loss": 4.2212, "step": 12910 }, { "epoch": 0.39434941967012827, "grad_norm": 0.39350947737693787, "learning_rate": 3.3146260119655515e-05, "loss": 4.326, "step": 12911 }, { "epoch": 0.39437996334758707, "grad_norm": 0.38472238183021545, "learning_rate": 3.314399211579775e-05, "loss": 4.3493, "step": 12912 }, { "epoch": 0.3944105070250458, "grad_norm": 0.38472411036491394, "learning_rate": 3.314172403695406e-05, "loss": 4.2714, "step": 12913 }, { "epoch": 0.39444105070250457, "grad_norm": 0.3784485161304474, "learning_rate": 3.3139455883145343e-05, "loss": 4.1525, "step": 12914 }, { "epoch": 0.3944715943799634, "grad_norm": 0.3711734414100647, "learning_rate": 3.3137187654392464e-05, "loss": 4.3352, "step": 12915 }, { "epoch": 0.3945021380574221, "grad_norm": 0.37132251262664795, "learning_rate": 3.3134919350716315e-05, "loss": 4.2199, "step": 12916 }, { "epoch": 0.3945326817348809, "grad_norm": 0.3809596300125122, "learning_rate": 3.313265097213778e-05, "loss": 4.3365, "step": 12917 }, { "epoch": 0.3945632254123396, "grad_norm": 0.3791162669658661, "learning_rate": 3.3130382518677747e-05, "loss": 4.3877, "step": 12918 }, { "epoch": 0.39459376908979843, "grad_norm": 0.39579710364341736, "learning_rate": 3.3128113990357096e-05, "loss": 4.3096, "step": 12919 }, { "epoch": 0.3946243127672572, "grad_norm": 0.3813970983028412, "learning_rate": 3.312584538719673e-05, "loss": 4.3371, "step": 12920 }, { "epoch": 0.39465485644471593, "grad_norm": 0.38828378915786743, "learning_rate": 3.312357670921752e-05, "loss": 4.3131, "step": 12921 }, { "epoch": 0.39468540012217473, "grad_norm": 0.3855428695678711, "learning_rate": 3.312130795644036e-05, "loss": 4.2814, "step": 12922 }, { "epoch": 0.3947159437996335, "grad_norm": 0.38250330090522766, "learning_rate": 3.311903912888615e-05, "loss": 4.3472, "step": 12923 }, { "epoch": 0.39474648747709223, "grad_norm": 0.37325969338417053, "learning_rate": 3.311677022657577e-05, "loss": 4.3182, "step": 12924 }, { "epoch": 0.394777031154551, "grad_norm": 0.38091859221458435, "learning_rate": 3.311450124953012e-05, "loss": 4.2727, "step": 12925 }, { "epoch": 0.3948075748320098, "grad_norm": 0.3896957039833069, "learning_rate": 3.311223219777007e-05, "loss": 4.3192, "step": 12926 }, { "epoch": 0.39483811850946854, "grad_norm": 0.37968069314956665, "learning_rate": 3.3109963071316534e-05, "loss": 4.3076, "step": 12927 }, { "epoch": 0.3948686621869273, "grad_norm": 0.3797353506088257, "learning_rate": 3.3107693870190404e-05, "loss": 4.4248, "step": 12928 }, { "epoch": 0.3948992058643861, "grad_norm": 0.37986692786216736, "learning_rate": 3.310542459441256e-05, "loss": 4.3599, "step": 12929 }, { "epoch": 0.39492974954184484, "grad_norm": 0.38854312896728516, "learning_rate": 3.31031552440039e-05, "loss": 4.2602, "step": 12930 }, { "epoch": 0.3949602932193036, "grad_norm": 0.3875948190689087, "learning_rate": 3.310088581898534e-05, "loss": 4.3049, "step": 12931 }, { "epoch": 0.39499083689676234, "grad_norm": 0.37521713972091675, "learning_rate": 3.3098616319377756e-05, "loss": 4.3471, "step": 12932 }, { "epoch": 0.39502138057422115, "grad_norm": 0.38073021173477173, "learning_rate": 3.309634674520203e-05, "loss": 4.3141, "step": 12933 }, { "epoch": 0.3950519242516799, "grad_norm": 0.3885267674922943, "learning_rate": 3.3094077096479095e-05, "loss": 4.1722, "step": 12934 }, { "epoch": 0.39508246792913865, "grad_norm": 0.38866662979125977, "learning_rate": 3.309180737322983e-05, "loss": 4.3933, "step": 12935 }, { "epoch": 0.39511301160659745, "grad_norm": 0.39202767610549927, "learning_rate": 3.308953757547512e-05, "loss": 4.4, "step": 12936 }, { "epoch": 0.3951435552840562, "grad_norm": 0.3809255361557007, "learning_rate": 3.308726770323589e-05, "loss": 4.2813, "step": 12937 }, { "epoch": 0.39517409896151495, "grad_norm": 0.3938029706478119, "learning_rate": 3.3084997756533024e-05, "loss": 4.3573, "step": 12938 }, { "epoch": 0.39520464263897376, "grad_norm": 0.3877980709075928, "learning_rate": 3.308272773538743e-05, "loss": 4.3177, "step": 12939 }, { "epoch": 0.3952351863164325, "grad_norm": 0.38522157073020935, "learning_rate": 3.308045763982e-05, "loss": 4.3221, "step": 12940 }, { "epoch": 0.39526572999389126, "grad_norm": 0.3825174570083618, "learning_rate": 3.307818746985165e-05, "loss": 4.2783, "step": 12941 }, { "epoch": 0.39529627367135, "grad_norm": 0.3804713785648346, "learning_rate": 3.307591722550327e-05, "loss": 4.2518, "step": 12942 }, { "epoch": 0.3953268173488088, "grad_norm": 0.3785845637321472, "learning_rate": 3.3073646906795764e-05, "loss": 4.2801, "step": 12943 }, { "epoch": 0.39535736102626756, "grad_norm": 0.3776141405105591, "learning_rate": 3.3071376513750044e-05, "loss": 4.28, "step": 12944 }, { "epoch": 0.3953879047037263, "grad_norm": 0.3818495571613312, "learning_rate": 3.306910604638701e-05, "loss": 4.3071, "step": 12945 }, { "epoch": 0.3954184483811851, "grad_norm": 0.37854889035224915, "learning_rate": 3.306683550472757e-05, "loss": 4.3831, "step": 12946 }, { "epoch": 0.39544899205864387, "grad_norm": 0.38856735825538635, "learning_rate": 3.306456488879263e-05, "loss": 4.3687, "step": 12947 }, { "epoch": 0.3954795357361026, "grad_norm": 0.3882121443748474, "learning_rate": 3.30622941986031e-05, "loss": 4.3301, "step": 12948 }, { "epoch": 0.39551007941356137, "grad_norm": 0.4069824516773224, "learning_rate": 3.306002343417987e-05, "loss": 4.2444, "step": 12949 }, { "epoch": 0.39554062309102017, "grad_norm": 0.39675164222717285, "learning_rate": 3.305775259554385e-05, "loss": 4.4113, "step": 12950 }, { "epoch": 0.3955711667684789, "grad_norm": 0.36911049485206604, "learning_rate": 3.305548168271598e-05, "loss": 4.343, "step": 12951 }, { "epoch": 0.39560171044593767, "grad_norm": 0.37989819049835205, "learning_rate": 3.305321069571714e-05, "loss": 4.3352, "step": 12952 }, { "epoch": 0.3956322541233965, "grad_norm": 0.38264748454093933, "learning_rate": 3.305093963456824e-05, "loss": 4.3665, "step": 12953 }, { "epoch": 0.3956627978008552, "grad_norm": 0.38255321979522705, "learning_rate": 3.304866849929021e-05, "loss": 4.321, "step": 12954 }, { "epoch": 0.395693341478314, "grad_norm": 0.37904953956604004, "learning_rate": 3.3046397289903966e-05, "loss": 4.401, "step": 12955 }, { "epoch": 0.3957238851557728, "grad_norm": 0.3897421658039093, "learning_rate": 3.304412600643038e-05, "loss": 4.3723, "step": 12956 }, { "epoch": 0.39575442883323153, "grad_norm": 0.38379645347595215, "learning_rate": 3.30418546488904e-05, "loss": 4.3952, "step": 12957 }, { "epoch": 0.3957849725106903, "grad_norm": 0.3713875412940979, "learning_rate": 3.303958321730493e-05, "loss": 4.2771, "step": 12958 }, { "epoch": 0.39581551618814903, "grad_norm": 0.3835383951663971, "learning_rate": 3.303731171169488e-05, "loss": 4.3063, "step": 12959 }, { "epoch": 0.39584605986560784, "grad_norm": 0.3866707980632782, "learning_rate": 3.303504013208117e-05, "loss": 4.1895, "step": 12960 }, { "epoch": 0.3958766035430666, "grad_norm": 0.3854411244392395, "learning_rate": 3.3032768478484716e-05, "loss": 4.3218, "step": 12961 }, { "epoch": 0.39590714722052534, "grad_norm": 0.37345579266548157, "learning_rate": 3.303049675092643e-05, "loss": 4.2914, "step": 12962 }, { "epoch": 0.39593769089798414, "grad_norm": 0.3793695867061615, "learning_rate": 3.302822494942723e-05, "loss": 4.3751, "step": 12963 }, { "epoch": 0.3959682345754429, "grad_norm": 0.3809078633785248, "learning_rate": 3.3025953074008043e-05, "loss": 4.2881, "step": 12964 }, { "epoch": 0.39599877825290164, "grad_norm": 0.3742901086807251, "learning_rate": 3.302368112468978e-05, "loss": 4.2983, "step": 12965 }, { "epoch": 0.3960293219303604, "grad_norm": 0.38341623544692993, "learning_rate": 3.302140910149335e-05, "loss": 4.2041, "step": 12966 }, { "epoch": 0.3960598656078192, "grad_norm": 0.3789467215538025, "learning_rate": 3.3019137004439684e-05, "loss": 4.2111, "step": 12967 }, { "epoch": 0.39609040928527794, "grad_norm": 0.37873750925064087, "learning_rate": 3.30168648335497e-05, "loss": 4.2968, "step": 12968 }, { "epoch": 0.3961209529627367, "grad_norm": 0.38919609785079956, "learning_rate": 3.301459258884433e-05, "loss": 4.2515, "step": 12969 }, { "epoch": 0.3961514966401955, "grad_norm": 0.3872409760951996, "learning_rate": 3.3012320270344474e-05, "loss": 4.2404, "step": 12970 }, { "epoch": 0.39618204031765425, "grad_norm": 0.3800050914287567, "learning_rate": 3.301004787807108e-05, "loss": 4.2878, "step": 12971 }, { "epoch": 0.396212583995113, "grad_norm": 0.3813292384147644, "learning_rate": 3.3007775412045036e-05, "loss": 4.3027, "step": 12972 }, { "epoch": 0.3962431276725718, "grad_norm": 0.38061872124671936, "learning_rate": 3.3005502872287295e-05, "loss": 4.3362, "step": 12973 }, { "epoch": 0.39627367135003055, "grad_norm": 0.3975140154361725, "learning_rate": 3.300323025881878e-05, "loss": 4.2615, "step": 12974 }, { "epoch": 0.3963042150274893, "grad_norm": 0.37433719635009766, "learning_rate": 3.300095757166041e-05, "loss": 4.291, "step": 12975 }, { "epoch": 0.39633475870494805, "grad_norm": 0.3873113691806793, "learning_rate": 3.29986848108331e-05, "loss": 4.3349, "step": 12976 }, { "epoch": 0.39636530238240686, "grad_norm": 0.3777373135089874, "learning_rate": 3.299641197635779e-05, "loss": 4.3656, "step": 12977 }, { "epoch": 0.3963958460598656, "grad_norm": 0.37515509128570557, "learning_rate": 3.299413906825541e-05, "loss": 4.3605, "step": 12978 }, { "epoch": 0.39642638973732436, "grad_norm": 0.3696388006210327, "learning_rate": 3.299186608654688e-05, "loss": 4.3018, "step": 12979 }, { "epoch": 0.39645693341478316, "grad_norm": 0.38355571031570435, "learning_rate": 3.298959303125312e-05, "loss": 4.3332, "step": 12980 }, { "epoch": 0.3964874770922419, "grad_norm": 0.3880525827407837, "learning_rate": 3.2987319902395075e-05, "loss": 4.38, "step": 12981 }, { "epoch": 0.39651802076970066, "grad_norm": 0.37871187925338745, "learning_rate": 3.298504669999367e-05, "loss": 4.239, "step": 12982 }, { "epoch": 0.3965485644471594, "grad_norm": 0.3915308713912964, "learning_rate": 3.2982773424069835e-05, "loss": 4.2885, "step": 12983 }, { "epoch": 0.3965791081246182, "grad_norm": 0.3699290156364441, "learning_rate": 3.2980500074644494e-05, "loss": 4.3315, "step": 12984 }, { "epoch": 0.39660965180207697, "grad_norm": 0.3698326647281647, "learning_rate": 3.2978226651738585e-05, "loss": 4.2709, "step": 12985 }, { "epoch": 0.3966401954795357, "grad_norm": 0.36895453929901123, "learning_rate": 3.297595315537305e-05, "loss": 4.2668, "step": 12986 }, { "epoch": 0.3966707391569945, "grad_norm": 0.3786069452762604, "learning_rate": 3.297367958556881e-05, "loss": 4.2915, "step": 12987 }, { "epoch": 0.3967012828344533, "grad_norm": 0.3799576461315155, "learning_rate": 3.297140594234681e-05, "loss": 4.2781, "step": 12988 }, { "epoch": 0.396731826511912, "grad_norm": 0.37669238448143005, "learning_rate": 3.296913222572797e-05, "loss": 4.2326, "step": 12989 }, { "epoch": 0.3967623701893708, "grad_norm": 0.377098947763443, "learning_rate": 3.2966858435733226e-05, "loss": 4.3458, "step": 12990 }, { "epoch": 0.3967929138668296, "grad_norm": 0.384835422039032, "learning_rate": 3.2964584572383526e-05, "loss": 4.3117, "step": 12991 }, { "epoch": 0.3968234575442883, "grad_norm": 0.39850613474845886, "learning_rate": 3.296231063569981e-05, "loss": 4.261, "step": 12992 }, { "epoch": 0.3968540012217471, "grad_norm": 0.38767868280410767, "learning_rate": 3.2960036625702996e-05, "loss": 4.2952, "step": 12993 }, { "epoch": 0.3968845448992059, "grad_norm": 0.38634106516838074, "learning_rate": 3.295776254241403e-05, "loss": 4.3759, "step": 12994 }, { "epoch": 0.39691508857666463, "grad_norm": 0.38333287835121155, "learning_rate": 3.295548838585386e-05, "loss": 4.3873, "step": 12995 }, { "epoch": 0.3969456322541234, "grad_norm": 0.39626172184944153, "learning_rate": 3.295321415604341e-05, "loss": 4.3337, "step": 12996 }, { "epoch": 0.3969761759315822, "grad_norm": 0.3791597783565521, "learning_rate": 3.295093985300363e-05, "loss": 4.3644, "step": 12997 }, { "epoch": 0.39700671960904094, "grad_norm": 0.3850422501564026, "learning_rate": 3.2948665476755465e-05, "loss": 4.2794, "step": 12998 }, { "epoch": 0.3970372632864997, "grad_norm": 0.3681638240814209, "learning_rate": 3.2946391027319844e-05, "loss": 4.4073, "step": 12999 }, { "epoch": 0.39706780696395844, "grad_norm": 0.37515002489089966, "learning_rate": 3.294411650471772e-05, "loss": 4.3271, "step": 13000 }, { "epoch": 0.39709835064141724, "grad_norm": 0.3894946277141571, "learning_rate": 3.2941841908970025e-05, "loss": 4.3452, "step": 13001 }, { "epoch": 0.397128894318876, "grad_norm": 0.38777050375938416, "learning_rate": 3.293956724009772e-05, "loss": 4.2896, "step": 13002 }, { "epoch": 0.39715943799633474, "grad_norm": 0.3994784355163574, "learning_rate": 3.293729249812173e-05, "loss": 4.2649, "step": 13003 }, { "epoch": 0.39718998167379355, "grad_norm": 0.38091060519218445, "learning_rate": 3.2935017683063004e-05, "loss": 4.2172, "step": 13004 }, { "epoch": 0.3972205253512523, "grad_norm": 0.3806350529193878, "learning_rate": 3.2932742794942487e-05, "loss": 4.1901, "step": 13005 }, { "epoch": 0.39725106902871105, "grad_norm": 0.3949447274208069, "learning_rate": 3.293046783378114e-05, "loss": 4.3275, "step": 13006 }, { "epoch": 0.3972816127061698, "grad_norm": 0.39869946241378784, "learning_rate": 3.292819279959989e-05, "loss": 4.2762, "step": 13007 }, { "epoch": 0.3973121563836286, "grad_norm": 0.39848414063453674, "learning_rate": 3.2925917692419696e-05, "loss": 4.3513, "step": 13008 }, { "epoch": 0.39734270006108735, "grad_norm": 0.3913853168487549, "learning_rate": 3.29236425122615e-05, "loss": 4.3089, "step": 13009 }, { "epoch": 0.3973732437385461, "grad_norm": 0.39481160044670105, "learning_rate": 3.2921367259146263e-05, "loss": 4.3851, "step": 13010 }, { "epoch": 0.3974037874160049, "grad_norm": 0.3853548765182495, "learning_rate": 3.2919091933094907e-05, "loss": 4.3447, "step": 13011 }, { "epoch": 0.39743433109346366, "grad_norm": 0.3848705291748047, "learning_rate": 3.291681653412841e-05, "loss": 4.2774, "step": 13012 }, { "epoch": 0.3974648747709224, "grad_norm": 0.3838709890842438, "learning_rate": 3.291454106226772e-05, "loss": 4.3136, "step": 13013 }, { "epoch": 0.3974954184483812, "grad_norm": 0.3833644986152649, "learning_rate": 3.291226551753377e-05, "loss": 4.364, "step": 13014 }, { "epoch": 0.39752596212583996, "grad_norm": 0.3835768401622772, "learning_rate": 3.290998989994753e-05, "loss": 4.333, "step": 13015 }, { "epoch": 0.3975565058032987, "grad_norm": 0.39560914039611816, "learning_rate": 3.290771420952994e-05, "loss": 4.3244, "step": 13016 }, { "epoch": 0.39758704948075746, "grad_norm": 0.3847331404685974, "learning_rate": 3.290543844630196e-05, "loss": 4.2944, "step": 13017 }, { "epoch": 0.39761759315821626, "grad_norm": 0.38485708832740784, "learning_rate": 3.290316261028455e-05, "loss": 4.3141, "step": 13018 }, { "epoch": 0.397648136835675, "grad_norm": 0.377040296792984, "learning_rate": 3.290088670149866e-05, "loss": 4.3148, "step": 13019 }, { "epoch": 0.39767868051313376, "grad_norm": 0.3949551582336426, "learning_rate": 3.2898610719965236e-05, "loss": 4.3146, "step": 13020 }, { "epoch": 0.39770922419059257, "grad_norm": 0.39299651980400085, "learning_rate": 3.289633466570524e-05, "loss": 4.3209, "step": 13021 }, { "epoch": 0.3977397678680513, "grad_norm": 0.38655781745910645, "learning_rate": 3.289405853873964e-05, "loss": 4.3325, "step": 13022 }, { "epoch": 0.39777031154551007, "grad_norm": 0.3827093243598938, "learning_rate": 3.289178233908938e-05, "loss": 4.3765, "step": 13023 }, { "epoch": 0.3978008552229688, "grad_norm": 0.3969796895980835, "learning_rate": 3.288950606677542e-05, "loss": 4.3997, "step": 13024 }, { "epoch": 0.3978313989004276, "grad_norm": 0.3895374536514282, "learning_rate": 3.288722972181872e-05, "loss": 4.3224, "step": 13025 }, { "epoch": 0.3978619425778864, "grad_norm": 0.3821442425251007, "learning_rate": 3.2884953304240254e-05, "loss": 4.2846, "step": 13026 }, { "epoch": 0.3978924862553451, "grad_norm": 0.38077643513679504, "learning_rate": 3.288267681406096e-05, "loss": 4.2829, "step": 13027 }, { "epoch": 0.39792302993280393, "grad_norm": 0.38168877363204956, "learning_rate": 3.28804002513018e-05, "loss": 4.3461, "step": 13028 }, { "epoch": 0.3979535736102627, "grad_norm": 0.3887786865234375, "learning_rate": 3.2878123615983754e-05, "loss": 4.3381, "step": 13029 }, { "epoch": 0.39798411728772143, "grad_norm": 0.3827921748161316, "learning_rate": 3.287584690812777e-05, "loss": 4.2686, "step": 13030 }, { "epoch": 0.39801466096518023, "grad_norm": 0.38747453689575195, "learning_rate": 3.28735701277548e-05, "loss": 4.3373, "step": 13031 }, { "epoch": 0.398045204642639, "grad_norm": 0.3865402638912201, "learning_rate": 3.2871293274885846e-05, "loss": 4.291, "step": 13032 }, { "epoch": 0.39807574832009773, "grad_norm": 0.37691494822502136, "learning_rate": 3.2869016349541844e-05, "loss": 4.0888, "step": 13033 }, { "epoch": 0.3981062919975565, "grad_norm": 0.37297263741493225, "learning_rate": 3.2866739351743755e-05, "loss": 4.2365, "step": 13034 }, { "epoch": 0.3981368356750153, "grad_norm": 0.39190220832824707, "learning_rate": 3.2864462281512545e-05, "loss": 4.3879, "step": 13035 }, { "epoch": 0.39816737935247404, "grad_norm": 0.3688155710697174, "learning_rate": 3.286218513886919e-05, "loss": 4.3265, "step": 13036 }, { "epoch": 0.3981979230299328, "grad_norm": 0.3816909193992615, "learning_rate": 3.2859907923834664e-05, "loss": 4.2214, "step": 13037 }, { "epoch": 0.3982284667073916, "grad_norm": 0.3743719756603241, "learning_rate": 3.285763063642992e-05, "loss": 4.3117, "step": 13038 }, { "epoch": 0.39825901038485034, "grad_norm": 0.38777631521224976, "learning_rate": 3.2855353276675935e-05, "loss": 4.347, "step": 13039 }, { "epoch": 0.3982895540623091, "grad_norm": 0.3757788836956024, "learning_rate": 3.2853075844593666e-05, "loss": 4.314, "step": 13040 }, { "epoch": 0.39832009773976784, "grad_norm": 0.38024622201919556, "learning_rate": 3.285079834020409e-05, "loss": 4.3583, "step": 13041 }, { "epoch": 0.39835064141722665, "grad_norm": 0.3776492178440094, "learning_rate": 3.284852076352819e-05, "loss": 4.2048, "step": 13042 }, { "epoch": 0.3983811850946854, "grad_norm": 0.3827245831489563, "learning_rate": 3.284624311458691e-05, "loss": 4.3666, "step": 13043 }, { "epoch": 0.39841172877214415, "grad_norm": 0.38401633501052856, "learning_rate": 3.2843965393401244e-05, "loss": 4.3263, "step": 13044 }, { "epoch": 0.39844227244960295, "grad_norm": 0.39000222086906433, "learning_rate": 3.284168759999214e-05, "loss": 4.2941, "step": 13045 }, { "epoch": 0.3984728161270617, "grad_norm": 0.3808242082595825, "learning_rate": 3.28394097343806e-05, "loss": 4.3179, "step": 13046 }, { "epoch": 0.39850335980452045, "grad_norm": 0.37428295612335205, "learning_rate": 3.2837131796587584e-05, "loss": 4.2907, "step": 13047 }, { "epoch": 0.39853390348197926, "grad_norm": 0.38441354036331177, "learning_rate": 3.283485378663407e-05, "loss": 4.2864, "step": 13048 }, { "epoch": 0.398564447159438, "grad_norm": 0.38726192712783813, "learning_rate": 3.2832575704541026e-05, "loss": 4.3264, "step": 13049 }, { "epoch": 0.39859499083689676, "grad_norm": 0.3814205825328827, "learning_rate": 3.283029755032942e-05, "loss": 4.2175, "step": 13050 }, { "epoch": 0.3986255345143555, "grad_norm": 0.3783305287361145, "learning_rate": 3.2828019324020253e-05, "loss": 4.2527, "step": 13051 }, { "epoch": 0.3986560781918143, "grad_norm": 0.3878549337387085, "learning_rate": 3.282574102563447e-05, "loss": 4.324, "step": 13052 }, { "epoch": 0.39868662186927306, "grad_norm": 0.4039941728115082, "learning_rate": 3.282346265519308e-05, "loss": 4.4239, "step": 13053 }, { "epoch": 0.3987171655467318, "grad_norm": 0.3736701011657715, "learning_rate": 3.2821184212717044e-05, "loss": 4.2975, "step": 13054 }, { "epoch": 0.3987477092241906, "grad_norm": 0.39073094725608826, "learning_rate": 3.2818905698227336e-05, "loss": 4.3549, "step": 13055 }, { "epoch": 0.39877825290164937, "grad_norm": 0.39203035831451416, "learning_rate": 3.281662711174496e-05, "loss": 4.3737, "step": 13056 }, { "epoch": 0.3988087965791081, "grad_norm": 0.38463783264160156, "learning_rate": 3.281434845329087e-05, "loss": 4.3035, "step": 13057 }, { "epoch": 0.39883934025656687, "grad_norm": 0.3730848431587219, "learning_rate": 3.281206972288605e-05, "loss": 4.3096, "step": 13058 }, { "epoch": 0.39886988393402567, "grad_norm": 0.3815056085586548, "learning_rate": 3.2809790920551495e-05, "loss": 4.3925, "step": 13059 }, { "epoch": 0.3989004276114844, "grad_norm": 0.3847832977771759, "learning_rate": 3.280751204630817e-05, "loss": 4.3568, "step": 13060 }, { "epoch": 0.39893097128894317, "grad_norm": 0.38306546211242676, "learning_rate": 3.280523310017708e-05, "loss": 4.2448, "step": 13061 }, { "epoch": 0.398961514966402, "grad_norm": 0.3818809390068054, "learning_rate": 3.280295408217919e-05, "loss": 4.2438, "step": 13062 }, { "epoch": 0.3989920586438607, "grad_norm": 0.3828831911087036, "learning_rate": 3.280067499233549e-05, "loss": 4.3758, "step": 13063 }, { "epoch": 0.3990226023213195, "grad_norm": 0.38376349210739136, "learning_rate": 3.2798395830666963e-05, "loss": 4.3554, "step": 13064 }, { "epoch": 0.3990531459987783, "grad_norm": 0.3715583384037018, "learning_rate": 3.2796116597194596e-05, "loss": 4.3324, "step": 13065 }, { "epoch": 0.39908368967623703, "grad_norm": 0.3841736912727356, "learning_rate": 3.2793837291939384e-05, "loss": 4.3674, "step": 13066 }, { "epoch": 0.3991142333536958, "grad_norm": 0.3697369396686554, "learning_rate": 3.2791557914922294e-05, "loss": 4.3797, "step": 13067 }, { "epoch": 0.39914477703115453, "grad_norm": 0.37413761019706726, "learning_rate": 3.278927846616433e-05, "loss": 4.3633, "step": 13068 }, { "epoch": 0.39917532070861333, "grad_norm": 0.3754139542579651, "learning_rate": 3.278699894568647e-05, "loss": 4.2571, "step": 13069 }, { "epoch": 0.3992058643860721, "grad_norm": 0.38339856266975403, "learning_rate": 3.2784719353509705e-05, "loss": 4.395, "step": 13070 }, { "epoch": 0.39923640806353083, "grad_norm": 0.3954220414161682, "learning_rate": 3.278243968965504e-05, "loss": 4.2885, "step": 13071 }, { "epoch": 0.39926695174098964, "grad_norm": 0.393588125705719, "learning_rate": 3.2780159954143444e-05, "loss": 4.349, "step": 13072 }, { "epoch": 0.3992974954184484, "grad_norm": 0.3854270577430725, "learning_rate": 3.277788014699591e-05, "loss": 4.2864, "step": 13073 }, { "epoch": 0.39932803909590714, "grad_norm": 0.3882896602153778, "learning_rate": 3.277560026823344e-05, "loss": 4.3389, "step": 13074 }, { "epoch": 0.3993585827733659, "grad_norm": 0.383711576461792, "learning_rate": 3.277332031787702e-05, "loss": 4.2994, "step": 13075 }, { "epoch": 0.3993891264508247, "grad_norm": 0.368056058883667, "learning_rate": 3.277104029594764e-05, "loss": 4.2794, "step": 13076 }, { "epoch": 0.39941967012828344, "grad_norm": 0.3890268802642822, "learning_rate": 3.27687602024663e-05, "loss": 4.2269, "step": 13077 }, { "epoch": 0.3994502138057422, "grad_norm": 0.38434797525405884, "learning_rate": 3.2766480037453985e-05, "loss": 4.3493, "step": 13078 }, { "epoch": 0.399480757483201, "grad_norm": 0.37912970781326294, "learning_rate": 3.27641998009317e-05, "loss": 4.3878, "step": 13079 }, { "epoch": 0.39951130116065975, "grad_norm": 0.37479928135871887, "learning_rate": 3.2761919492920436e-05, "loss": 4.3766, "step": 13080 }, { "epoch": 0.3995418448381185, "grad_norm": 0.38820552825927734, "learning_rate": 3.275963911344119e-05, "loss": 4.2514, "step": 13081 }, { "epoch": 0.39957238851557725, "grad_norm": 0.3856962323188782, "learning_rate": 3.275735866251495e-05, "loss": 4.2385, "step": 13082 }, { "epoch": 0.39960293219303605, "grad_norm": 0.3778127133846283, "learning_rate": 3.2755078140162723e-05, "loss": 4.2946, "step": 13083 }, { "epoch": 0.3996334758704948, "grad_norm": 0.37412625551223755, "learning_rate": 3.27527975464055e-05, "loss": 4.3474, "step": 13084 }, { "epoch": 0.39966401954795355, "grad_norm": 0.37087881565093994, "learning_rate": 3.2750516881264294e-05, "loss": 4.3414, "step": 13085 }, { "epoch": 0.39969456322541236, "grad_norm": 0.38630980253219604, "learning_rate": 3.274823614476008e-05, "loss": 4.3311, "step": 13086 }, { "epoch": 0.3997251069028711, "grad_norm": 0.3789551556110382, "learning_rate": 3.2745955336913885e-05, "loss": 4.2786, "step": 13087 }, { "epoch": 0.39975565058032986, "grad_norm": 0.3827025890350342, "learning_rate": 3.2743674457746707e-05, "loss": 4.2458, "step": 13088 }, { "epoch": 0.39978619425778866, "grad_norm": 0.3719705641269684, "learning_rate": 3.274139350727951e-05, "loss": 4.2771, "step": 13089 }, { "epoch": 0.3998167379352474, "grad_norm": 0.38615700602531433, "learning_rate": 3.273911248553334e-05, "loss": 4.358, "step": 13090 }, { "epoch": 0.39984728161270616, "grad_norm": 0.3778119683265686, "learning_rate": 3.2736831392529175e-05, "loss": 4.3192, "step": 13091 }, { "epoch": 0.3998778252901649, "grad_norm": 0.3870755434036255, "learning_rate": 3.273455022828804e-05, "loss": 4.3687, "step": 13092 }, { "epoch": 0.3999083689676237, "grad_norm": 0.37600380182266235, "learning_rate": 3.27322689928309e-05, "loss": 4.3818, "step": 13093 }, { "epoch": 0.39993891264508247, "grad_norm": 0.36667507886886597, "learning_rate": 3.27299876861788e-05, "loss": 4.2923, "step": 13094 }, { "epoch": 0.3999694563225412, "grad_norm": 0.37103211879730225, "learning_rate": 3.272770630835272e-05, "loss": 4.3833, "step": 13095 }, { "epoch": 0.4, "grad_norm": 0.3768084645271301, "learning_rate": 3.272542485937369e-05, "loss": 4.3412, "step": 13096 }, { "epoch": 0.40003054367745877, "grad_norm": 0.4052281081676483, "learning_rate": 3.272314333926269e-05, "loss": 4.3349, "step": 13097 }, { "epoch": 0.4000610873549175, "grad_norm": 0.3888164758682251, "learning_rate": 3.272086174804074e-05, "loss": 4.3658, "step": 13098 }, { "epoch": 0.40009163103237627, "grad_norm": 0.37712258100509644, "learning_rate": 3.271858008572885e-05, "loss": 4.2822, "step": 13099 }, { "epoch": 0.4001221747098351, "grad_norm": 0.3842390179634094, "learning_rate": 3.271629835234802e-05, "loss": 4.3618, "step": 13100 }, { "epoch": 0.4001527183872938, "grad_norm": 0.37163448333740234, "learning_rate": 3.271401654791926e-05, "loss": 4.3437, "step": 13101 }, { "epoch": 0.4001832620647526, "grad_norm": 0.3785625100135803, "learning_rate": 3.271173467246359e-05, "loss": 4.3474, "step": 13102 }, { "epoch": 0.4002138057422114, "grad_norm": 0.398274302482605, "learning_rate": 3.270945272600201e-05, "loss": 4.3167, "step": 13103 }, { "epoch": 0.40024434941967013, "grad_norm": 0.3793054521083832, "learning_rate": 3.2707170708555544e-05, "loss": 4.3213, "step": 13104 }, { "epoch": 0.4002748930971289, "grad_norm": 0.3835294246673584, "learning_rate": 3.270488862014519e-05, "loss": 4.3193, "step": 13105 }, { "epoch": 0.4003054367745877, "grad_norm": 0.3873582184314728, "learning_rate": 3.270260646079196e-05, "loss": 4.3752, "step": 13106 }, { "epoch": 0.40033598045204644, "grad_norm": 0.39336076378822327, "learning_rate": 3.2700324230516874e-05, "loss": 4.3816, "step": 13107 }, { "epoch": 0.4003665241295052, "grad_norm": 0.3914794623851776, "learning_rate": 3.2698041929340944e-05, "loss": 4.3175, "step": 13108 }, { "epoch": 0.40039706780696394, "grad_norm": 0.37476521730422974, "learning_rate": 3.269575955728519e-05, "loss": 4.3708, "step": 13109 }, { "epoch": 0.40042761148442274, "grad_norm": 0.3624558448791504, "learning_rate": 3.269347711437061e-05, "loss": 4.2992, "step": 13110 }, { "epoch": 0.4004581551618815, "grad_norm": 0.37967371940612793, "learning_rate": 3.269119460061824e-05, "loss": 4.3344, "step": 13111 }, { "epoch": 0.40048869883934024, "grad_norm": 0.40467551350593567, "learning_rate": 3.268891201604908e-05, "loss": 4.3203, "step": 13112 }, { "epoch": 0.40051924251679905, "grad_norm": 0.3792766332626343, "learning_rate": 3.268662936068416e-05, "loss": 4.3812, "step": 13113 }, { "epoch": 0.4005497861942578, "grad_norm": 0.6093744039535522, "learning_rate": 3.268434663454448e-05, "loss": 4.356, "step": 13114 }, { "epoch": 0.40058032987171655, "grad_norm": 0.3780127167701721, "learning_rate": 3.2682063837651084e-05, "loss": 4.3309, "step": 13115 }, { "epoch": 0.4006108735491753, "grad_norm": 0.38706639409065247, "learning_rate": 3.267978097002497e-05, "loss": 4.2443, "step": 13116 }, { "epoch": 0.4006414172266341, "grad_norm": 0.39354395866394043, "learning_rate": 3.267749803168716e-05, "loss": 4.3268, "step": 13117 }, { "epoch": 0.40067196090409285, "grad_norm": 0.3780622184276581, "learning_rate": 3.267521502265869e-05, "loss": 4.2673, "step": 13118 }, { "epoch": 0.4007025045815516, "grad_norm": 0.37284722924232483, "learning_rate": 3.267293194296056e-05, "loss": 4.3683, "step": 13119 }, { "epoch": 0.4007330482590104, "grad_norm": 0.3878716826438904, "learning_rate": 3.26706487926138e-05, "loss": 4.3152, "step": 13120 }, { "epoch": 0.40076359193646915, "grad_norm": 0.38327959179878235, "learning_rate": 3.2668365571639434e-05, "loss": 4.2874, "step": 13121 }, { "epoch": 0.4007941356139279, "grad_norm": 0.38137122988700867, "learning_rate": 3.2666082280058494e-05, "loss": 4.3307, "step": 13122 }, { "epoch": 0.4008246792913867, "grad_norm": 0.39668408036231995, "learning_rate": 3.2663798917891975e-05, "loss": 4.3561, "step": 13123 }, { "epoch": 0.40085522296884546, "grad_norm": 0.39035364985466003, "learning_rate": 3.266151548516093e-05, "loss": 4.4036, "step": 13124 }, { "epoch": 0.4008857666463042, "grad_norm": 0.3858160078525543, "learning_rate": 3.265923198188637e-05, "loss": 4.297, "step": 13125 }, { "epoch": 0.40091631032376296, "grad_norm": 0.3676231801509857, "learning_rate": 3.265694840808933e-05, "loss": 4.3462, "step": 13126 }, { "epoch": 0.40094685400122176, "grad_norm": 0.38026294112205505, "learning_rate": 3.2654664763790824e-05, "loss": 4.3652, "step": 13127 }, { "epoch": 0.4009773976786805, "grad_norm": 0.38883084058761597, "learning_rate": 3.2652381049011875e-05, "loss": 4.283, "step": 13128 }, { "epoch": 0.40100794135613926, "grad_norm": 0.3815830945968628, "learning_rate": 3.2650097263773533e-05, "loss": 4.3238, "step": 13129 }, { "epoch": 0.40103848503359807, "grad_norm": 0.37211599946022034, "learning_rate": 3.26478134080968e-05, "loss": 4.2429, "step": 13130 }, { "epoch": 0.4010690287110568, "grad_norm": 0.3853805661201477, "learning_rate": 3.264552948200273e-05, "loss": 4.3037, "step": 13131 }, { "epoch": 0.40109957238851557, "grad_norm": 0.3828321099281311, "learning_rate": 3.264324548551232e-05, "loss": 4.3424, "step": 13132 }, { "epoch": 0.4011301160659743, "grad_norm": 0.3885394036769867, "learning_rate": 3.264096141864664e-05, "loss": 4.2963, "step": 13133 }, { "epoch": 0.4011606597434331, "grad_norm": 0.3780926764011383, "learning_rate": 3.263867728142669e-05, "loss": 4.3581, "step": 13134 }, { "epoch": 0.4011912034208919, "grad_norm": 0.3895443379878998, "learning_rate": 3.263639307387351e-05, "loss": 4.2367, "step": 13135 }, { "epoch": 0.4012217470983506, "grad_norm": 0.3861364722251892, "learning_rate": 3.263410879600814e-05, "loss": 4.371, "step": 13136 }, { "epoch": 0.40125229077580943, "grad_norm": 0.3852876126766205, "learning_rate": 3.2631824447851595e-05, "loss": 4.267, "step": 13137 }, { "epoch": 0.4012828344532682, "grad_norm": 0.3913091719150543, "learning_rate": 3.262954002942492e-05, "loss": 4.3266, "step": 13138 }, { "epoch": 0.4013133781307269, "grad_norm": 0.3875420093536377, "learning_rate": 3.262725554074915e-05, "loss": 4.3199, "step": 13139 }, { "epoch": 0.40134392180818573, "grad_norm": 0.38896825909614563, "learning_rate": 3.262497098184531e-05, "loss": 4.2444, "step": 13140 }, { "epoch": 0.4013744654856445, "grad_norm": 0.3904961049556732, "learning_rate": 3.2622686352734454e-05, "loss": 4.2527, "step": 13141 }, { "epoch": 0.40140500916310323, "grad_norm": 0.38075003027915955, "learning_rate": 3.2620401653437604e-05, "loss": 4.2959, "step": 13142 }, { "epoch": 0.401435552840562, "grad_norm": 0.37894299626350403, "learning_rate": 3.26181168839758e-05, "loss": 4.4164, "step": 13143 }, { "epoch": 0.4014660965180208, "grad_norm": 0.3961702585220337, "learning_rate": 3.261583204437007e-05, "loss": 4.2521, "step": 13144 }, { "epoch": 0.40149664019547954, "grad_norm": 0.3727492690086365, "learning_rate": 3.2613547134641454e-05, "loss": 4.3294, "step": 13145 }, { "epoch": 0.4015271838729383, "grad_norm": 0.38826221227645874, "learning_rate": 3.2611262154811006e-05, "loss": 4.3939, "step": 13146 }, { "epoch": 0.4015577275503971, "grad_norm": 0.3816065788269043, "learning_rate": 3.260897710489974e-05, "loss": 4.3823, "step": 13147 }, { "epoch": 0.40158827122785584, "grad_norm": 0.39017724990844727, "learning_rate": 3.260669198492872e-05, "loss": 4.3629, "step": 13148 }, { "epoch": 0.4016188149053146, "grad_norm": 0.39091357588768005, "learning_rate": 3.260440679491898e-05, "loss": 4.2583, "step": 13149 }, { "epoch": 0.40164935858277334, "grad_norm": 0.37849125266075134, "learning_rate": 3.260212153489155e-05, "loss": 4.3276, "step": 13150 }, { "epoch": 0.40167990226023215, "grad_norm": 0.4024380147457123, "learning_rate": 3.259983620486748e-05, "loss": 4.2574, "step": 13151 }, { "epoch": 0.4017104459376909, "grad_norm": 0.3866727650165558, "learning_rate": 3.259755080486781e-05, "loss": 4.2366, "step": 13152 }, { "epoch": 0.40174098961514965, "grad_norm": 0.39056193828582764, "learning_rate": 3.259526533491359e-05, "loss": 4.2528, "step": 13153 }, { "epoch": 0.40177153329260845, "grad_norm": 0.382820725440979, "learning_rate": 3.259297979502584e-05, "loss": 4.1843, "step": 13154 }, { "epoch": 0.4018020769700672, "grad_norm": 0.3832453787326813, "learning_rate": 3.259069418522563e-05, "loss": 4.3842, "step": 13155 }, { "epoch": 0.40183262064752595, "grad_norm": 0.3896203637123108, "learning_rate": 3.2588408505534006e-05, "loss": 4.3705, "step": 13156 }, { "epoch": 0.4018631643249847, "grad_norm": 0.38562238216400146, "learning_rate": 3.2586122755971996e-05, "loss": 4.3425, "step": 13157 }, { "epoch": 0.4018937080024435, "grad_norm": 0.38348865509033203, "learning_rate": 3.2583836936560653e-05, "loss": 4.283, "step": 13158 }, { "epoch": 0.40192425167990226, "grad_norm": 0.386453241109848, "learning_rate": 3.2581551047321026e-05, "loss": 4.3488, "step": 13159 }, { "epoch": 0.401954795357361, "grad_norm": 0.3767314553260803, "learning_rate": 3.257926508827416e-05, "loss": 4.2577, "step": 13160 }, { "epoch": 0.4019853390348198, "grad_norm": 0.38458651304244995, "learning_rate": 3.257697905944109e-05, "loss": 4.3139, "step": 13161 }, { "epoch": 0.40201588271227856, "grad_norm": 0.38166549801826477, "learning_rate": 3.257469296084289e-05, "loss": 4.3587, "step": 13162 }, { "epoch": 0.4020464263897373, "grad_norm": 0.386147141456604, "learning_rate": 3.2572406792500597e-05, "loss": 4.438, "step": 13163 }, { "epoch": 0.4020769700671961, "grad_norm": 0.375283807516098, "learning_rate": 3.2570120554435265e-05, "loss": 4.3216, "step": 13164 }, { "epoch": 0.40210751374465487, "grad_norm": 0.3814009428024292, "learning_rate": 3.256783424666793e-05, "loss": 4.2877, "step": 13165 }, { "epoch": 0.4021380574221136, "grad_norm": 0.3837713897228241, "learning_rate": 3.256554786921967e-05, "loss": 4.3175, "step": 13166 }, { "epoch": 0.40216860109957236, "grad_norm": 0.4034217298030853, "learning_rate": 3.256326142211151e-05, "loss": 4.3208, "step": 13167 }, { "epoch": 0.40219914477703117, "grad_norm": 0.3836139142513275, "learning_rate": 3.256097490536452e-05, "loss": 4.247, "step": 13168 }, { "epoch": 0.4022296884544899, "grad_norm": 0.3784819543361664, "learning_rate": 3.255868831899974e-05, "loss": 4.2904, "step": 13169 }, { "epoch": 0.40226023213194867, "grad_norm": 0.39391282200813293, "learning_rate": 3.2556401663038236e-05, "loss": 4.3534, "step": 13170 }, { "epoch": 0.4022907758094075, "grad_norm": 0.37207692861557007, "learning_rate": 3.2554114937501045e-05, "loss": 4.2814, "step": 13171 }, { "epoch": 0.4023213194868662, "grad_norm": 0.37742704153060913, "learning_rate": 3.255182814240925e-05, "loss": 4.2878, "step": 13172 }, { "epoch": 0.402351863164325, "grad_norm": 0.37216663360595703, "learning_rate": 3.254954127778388e-05, "loss": 4.3785, "step": 13173 }, { "epoch": 0.4023824068417837, "grad_norm": 0.37239912152290344, "learning_rate": 3.2547254343646e-05, "loss": 4.2644, "step": 13174 }, { "epoch": 0.40241295051924253, "grad_norm": 0.38756605982780457, "learning_rate": 3.254496734001668e-05, "loss": 4.3686, "step": 13175 }, { "epoch": 0.4024434941967013, "grad_norm": 0.396090030670166, "learning_rate": 3.2542680266916956e-05, "loss": 4.4196, "step": 13176 }, { "epoch": 0.40247403787416003, "grad_norm": 0.37917304039001465, "learning_rate": 3.254039312436791e-05, "loss": 4.3888, "step": 13177 }, { "epoch": 0.40250458155161883, "grad_norm": 0.3777078092098236, "learning_rate": 3.253810591239057e-05, "loss": 4.3003, "step": 13178 }, { "epoch": 0.4025351252290776, "grad_norm": 0.378423273563385, "learning_rate": 3.253581863100602e-05, "loss": 4.3407, "step": 13179 }, { "epoch": 0.40256566890653633, "grad_norm": 0.365080326795578, "learning_rate": 3.2533531280235315e-05, "loss": 4.3804, "step": 13180 }, { "epoch": 0.40259621258399514, "grad_norm": 0.3868798017501831, "learning_rate": 3.253124386009952e-05, "loss": 4.2547, "step": 13181 }, { "epoch": 0.4026267562614539, "grad_norm": 0.38498398661613464, "learning_rate": 3.252895637061968e-05, "loss": 4.3231, "step": 13182 }, { "epoch": 0.40265729993891264, "grad_norm": 0.3915506899356842, "learning_rate": 3.2526668811816875e-05, "loss": 4.2655, "step": 13183 }, { "epoch": 0.4026878436163714, "grad_norm": 0.37497812509536743, "learning_rate": 3.252438118371216e-05, "loss": 4.3385, "step": 13184 }, { "epoch": 0.4027183872938302, "grad_norm": 0.39161422848701477, "learning_rate": 3.252209348632659e-05, "loss": 4.3106, "step": 13185 }, { "epoch": 0.40274893097128894, "grad_norm": 0.38790056109428406, "learning_rate": 3.2519805719681246e-05, "loss": 4.3529, "step": 13186 }, { "epoch": 0.4027794746487477, "grad_norm": 0.37743496894836426, "learning_rate": 3.251751788379718e-05, "loss": 4.3607, "step": 13187 }, { "epoch": 0.4028100183262065, "grad_norm": 0.3903738260269165, "learning_rate": 3.251522997869546e-05, "loss": 4.2194, "step": 13188 }, { "epoch": 0.40284056200366525, "grad_norm": 0.37204715609550476, "learning_rate": 3.2512942004397165e-05, "loss": 4.3959, "step": 13189 }, { "epoch": 0.402871105681124, "grad_norm": 0.395668089389801, "learning_rate": 3.251065396092334e-05, "loss": 4.3011, "step": 13190 }, { "epoch": 0.40290164935858275, "grad_norm": 0.37482964992523193, "learning_rate": 3.250836584829507e-05, "loss": 4.3545, "step": 13191 }, { "epoch": 0.40293219303604155, "grad_norm": 0.3807050287723541, "learning_rate": 3.2506077666533405e-05, "loss": 4.3337, "step": 13192 }, { "epoch": 0.4029627367135003, "grad_norm": 0.3729606866836548, "learning_rate": 3.250378941565944e-05, "loss": 4.3807, "step": 13193 }, { "epoch": 0.40299328039095905, "grad_norm": 0.3894347846508026, "learning_rate": 3.250150109569421e-05, "loss": 4.2703, "step": 13194 }, { "epoch": 0.40302382406841786, "grad_norm": 0.38771572709083557, "learning_rate": 3.2499212706658814e-05, "loss": 4.2927, "step": 13195 }, { "epoch": 0.4030543677458766, "grad_norm": 0.3912343978881836, "learning_rate": 3.24969242485743e-05, "loss": 4.3233, "step": 13196 }, { "epoch": 0.40308491142333536, "grad_norm": 0.3893074691295624, "learning_rate": 3.249463572146176e-05, "loss": 4.3264, "step": 13197 }, { "epoch": 0.40311545510079416, "grad_norm": 0.37641072273254395, "learning_rate": 3.249234712534225e-05, "loss": 4.2633, "step": 13198 }, { "epoch": 0.4031459987782529, "grad_norm": 0.37579137086868286, "learning_rate": 3.249005846023685e-05, "loss": 4.3558, "step": 13199 }, { "epoch": 0.40317654245571166, "grad_norm": 0.3838012218475342, "learning_rate": 3.248776972616663e-05, "loss": 4.314, "step": 13200 }, { "epoch": 0.4032070861331704, "grad_norm": 0.3987586200237274, "learning_rate": 3.2485480923152665e-05, "loss": 4.3628, "step": 13201 }, { "epoch": 0.4032376298106292, "grad_norm": 0.38594338297843933, "learning_rate": 3.248319205121603e-05, "loss": 4.2815, "step": 13202 }, { "epoch": 0.40326817348808797, "grad_norm": 0.39031723141670227, "learning_rate": 3.2480903110377796e-05, "loss": 4.2445, "step": 13203 }, { "epoch": 0.4032987171655467, "grad_norm": 0.38643041253089905, "learning_rate": 3.247861410065905e-05, "loss": 4.369, "step": 13204 }, { "epoch": 0.4033292608430055, "grad_norm": 0.4048345983028412, "learning_rate": 3.247632502208084e-05, "loss": 4.3345, "step": 13205 }, { "epoch": 0.40335980452046427, "grad_norm": 0.3816617429256439, "learning_rate": 3.247403587466428e-05, "loss": 4.3343, "step": 13206 }, { "epoch": 0.403390348197923, "grad_norm": 0.37490999698638916, "learning_rate": 3.247174665843042e-05, "loss": 4.2699, "step": 13207 }, { "epoch": 0.40342089187538177, "grad_norm": 0.3783985376358032, "learning_rate": 3.246945737340035e-05, "loss": 4.2634, "step": 13208 }, { "epoch": 0.4034514355528406, "grad_norm": 0.38547635078430176, "learning_rate": 3.246716801959514e-05, "loss": 4.2804, "step": 13209 }, { "epoch": 0.4034819792302993, "grad_norm": 0.4039207398891449, "learning_rate": 3.246487859703588e-05, "loss": 4.2465, "step": 13210 }, { "epoch": 0.4035125229077581, "grad_norm": 0.39362645149230957, "learning_rate": 3.246258910574364e-05, "loss": 4.3427, "step": 13211 }, { "epoch": 0.4035430665852169, "grad_norm": 0.37950441241264343, "learning_rate": 3.246029954573951e-05, "loss": 4.3731, "step": 13212 }, { "epoch": 0.40357361026267563, "grad_norm": 0.38032248616218567, "learning_rate": 3.245800991704456e-05, "loss": 4.2466, "step": 13213 }, { "epoch": 0.4036041539401344, "grad_norm": 0.3812936246395111, "learning_rate": 3.245572021967989e-05, "loss": 4.356, "step": 13214 }, { "epoch": 0.4036346976175932, "grad_norm": 0.39139312505722046, "learning_rate": 3.2453430453666556e-05, "loss": 4.3971, "step": 13215 }, { "epoch": 0.40366524129505194, "grad_norm": 0.3865748941898346, "learning_rate": 3.2451140619025665e-05, "loss": 4.2909, "step": 13216 }, { "epoch": 0.4036957849725107, "grad_norm": 0.377105176448822, "learning_rate": 3.244885071577829e-05, "loss": 4.3242, "step": 13217 }, { "epoch": 0.40372632864996943, "grad_norm": 0.3797759711742401, "learning_rate": 3.244656074394551e-05, "loss": 4.3616, "step": 13218 }, { "epoch": 0.40375687232742824, "grad_norm": 0.3967439830303192, "learning_rate": 3.244427070354843e-05, "loss": 4.1985, "step": 13219 }, { "epoch": 0.403787416004887, "grad_norm": 0.3857581913471222, "learning_rate": 3.2441980594608114e-05, "loss": 4.3076, "step": 13220 }, { "epoch": 0.40381795968234574, "grad_norm": 0.3745882511138916, "learning_rate": 3.2439690417145654e-05, "loss": 4.3645, "step": 13221 }, { "epoch": 0.40384850335980454, "grad_norm": 0.3711659908294678, "learning_rate": 3.243740017118214e-05, "loss": 4.2264, "step": 13222 }, { "epoch": 0.4038790470372633, "grad_norm": 0.38461369276046753, "learning_rate": 3.2435109856738666e-05, "loss": 4.3631, "step": 13223 }, { "epoch": 0.40390959071472204, "grad_norm": 0.3769506812095642, "learning_rate": 3.2432819473836307e-05, "loss": 4.2901, "step": 13224 }, { "epoch": 0.4039401343921808, "grad_norm": 0.3902747929096222, "learning_rate": 3.243052902249616e-05, "loss": 4.305, "step": 13225 }, { "epoch": 0.4039706780696396, "grad_norm": 0.386333703994751, "learning_rate": 3.24282385027393e-05, "loss": 4.3238, "step": 13226 }, { "epoch": 0.40400122174709835, "grad_norm": 0.39831990003585815, "learning_rate": 3.2425947914586846e-05, "loss": 4.2477, "step": 13227 }, { "epoch": 0.4040317654245571, "grad_norm": 0.42552241683006287, "learning_rate": 3.2423657258059865e-05, "loss": 4.1558, "step": 13228 }, { "epoch": 0.4040623091020159, "grad_norm": 0.38058149814605713, "learning_rate": 3.242136653317945e-05, "loss": 4.3067, "step": 13229 }, { "epoch": 0.40409285277947465, "grad_norm": 0.3899352550506592, "learning_rate": 3.241907573996671e-05, "loss": 4.3595, "step": 13230 }, { "epoch": 0.4041233964569334, "grad_norm": 0.37410056591033936, "learning_rate": 3.241678487844271e-05, "loss": 4.2729, "step": 13231 }, { "epoch": 0.40415394013439215, "grad_norm": 0.3909962475299835, "learning_rate": 3.241449394862857e-05, "loss": 4.3351, "step": 13232 }, { "epoch": 0.40418448381185096, "grad_norm": 0.38302603363990784, "learning_rate": 3.241220295054536e-05, "loss": 4.268, "step": 13233 }, { "epoch": 0.4042150274893097, "grad_norm": 0.4072360694408417, "learning_rate": 3.2409911884214203e-05, "loss": 4.2761, "step": 13234 }, { "epoch": 0.40424557116676846, "grad_norm": 0.38437172770500183, "learning_rate": 3.240762074965616e-05, "loss": 4.431, "step": 13235 }, { "epoch": 0.40427611484422726, "grad_norm": 0.37298384308815, "learning_rate": 3.240532954689236e-05, "loss": 4.2626, "step": 13236 }, { "epoch": 0.404306658521686, "grad_norm": 0.38431864976882935, "learning_rate": 3.240303827594388e-05, "loss": 4.3423, "step": 13237 }, { "epoch": 0.40433720219914476, "grad_norm": 0.3748871982097626, "learning_rate": 3.240074693683181e-05, "loss": 4.3305, "step": 13238 }, { "epoch": 0.40436774587660357, "grad_norm": 0.38019418716430664, "learning_rate": 3.239845552957726e-05, "loss": 4.3153, "step": 13239 }, { "epoch": 0.4043982895540623, "grad_norm": 0.3747193217277527, "learning_rate": 3.2396164054201335e-05, "loss": 4.2617, "step": 13240 }, { "epoch": 0.40442883323152107, "grad_norm": 0.37493032217025757, "learning_rate": 3.239387251072512e-05, "loss": 4.3314, "step": 13241 }, { "epoch": 0.4044593769089798, "grad_norm": 0.3957822322845459, "learning_rate": 3.239158089916972e-05, "loss": 4.3411, "step": 13242 }, { "epoch": 0.4044899205864386, "grad_norm": 0.3882518410682678, "learning_rate": 3.238928921955623e-05, "loss": 4.2722, "step": 13243 }, { "epoch": 0.4045204642638974, "grad_norm": 0.3785146176815033, "learning_rate": 3.2386997471905764e-05, "loss": 4.2458, "step": 13244 }, { "epoch": 0.4045510079413561, "grad_norm": 0.39018720388412476, "learning_rate": 3.238470565623941e-05, "loss": 4.2998, "step": 13245 }, { "epoch": 0.4045815516188149, "grad_norm": 0.37739160656929016, "learning_rate": 3.238241377257827e-05, "loss": 4.3024, "step": 13246 }, { "epoch": 0.4046120952962737, "grad_norm": 0.3883284330368042, "learning_rate": 3.238012182094345e-05, "loss": 4.3613, "step": 13247 }, { "epoch": 0.4046426389737324, "grad_norm": 0.382080614566803, "learning_rate": 3.237782980135606e-05, "loss": 4.3283, "step": 13248 }, { "epoch": 0.4046731826511912, "grad_norm": 0.37657618522644043, "learning_rate": 3.2375537713837196e-05, "loss": 4.3785, "step": 13249 }, { "epoch": 0.40470372632865, "grad_norm": 0.3926190435886383, "learning_rate": 3.237324555840796e-05, "loss": 4.3501, "step": 13250 }, { "epoch": 0.40473427000610873, "grad_norm": 0.38491731882095337, "learning_rate": 3.237095333508946e-05, "loss": 4.2974, "step": 13251 }, { "epoch": 0.4047648136835675, "grad_norm": 0.38941943645477295, "learning_rate": 3.2368661043902816e-05, "loss": 4.2822, "step": 13252 }, { "epoch": 0.4047953573610263, "grad_norm": 0.3808671534061432, "learning_rate": 3.236636868486911e-05, "loss": 4.2363, "step": 13253 }, { "epoch": 0.40482590103848504, "grad_norm": 0.3702510595321655, "learning_rate": 3.236407625800946e-05, "loss": 4.277, "step": 13254 }, { "epoch": 0.4048564447159438, "grad_norm": 0.3789461851119995, "learning_rate": 3.236178376334498e-05, "loss": 4.1784, "step": 13255 }, { "epoch": 0.4048869883934026, "grad_norm": 0.3838152289390564, "learning_rate": 3.235949120089676e-05, "loss": 4.2302, "step": 13256 }, { "epoch": 0.40491753207086134, "grad_norm": 0.38282474875450134, "learning_rate": 3.235719857068593e-05, "loss": 4.2979, "step": 13257 }, { "epoch": 0.4049480757483201, "grad_norm": 0.3791387677192688, "learning_rate": 3.235490587273359e-05, "loss": 4.3386, "step": 13258 }, { "epoch": 0.40497861942577884, "grad_norm": 0.38847875595092773, "learning_rate": 3.235261310706085e-05, "loss": 4.2824, "step": 13259 }, { "epoch": 0.40500916310323765, "grad_norm": 0.380545437335968, "learning_rate": 3.235032027368882e-05, "loss": 4.2492, "step": 13260 }, { "epoch": 0.4050397067806964, "grad_norm": 0.37354883551597595, "learning_rate": 3.2348027372638616e-05, "loss": 4.3222, "step": 13261 }, { "epoch": 0.40507025045815515, "grad_norm": 0.383354127407074, "learning_rate": 3.234573440393134e-05, "loss": 4.4179, "step": 13262 }, { "epoch": 0.40510079413561395, "grad_norm": 0.372079074382782, "learning_rate": 3.234344136758811e-05, "loss": 4.3459, "step": 13263 }, { "epoch": 0.4051313378130727, "grad_norm": 0.3872012495994568, "learning_rate": 3.2341148263630046e-05, "loss": 4.3211, "step": 13264 }, { "epoch": 0.40516188149053145, "grad_norm": 0.38889816403388977, "learning_rate": 3.2338855092078255e-05, "loss": 4.3229, "step": 13265 }, { "epoch": 0.4051924251679902, "grad_norm": 0.38851597905158997, "learning_rate": 3.233656185295385e-05, "loss": 4.2791, "step": 13266 }, { "epoch": 0.405222968845449, "grad_norm": 0.3827109634876251, "learning_rate": 3.233426854627795e-05, "loss": 4.3321, "step": 13267 }, { "epoch": 0.40525351252290776, "grad_norm": 0.37680569291114807, "learning_rate": 3.233197517207166e-05, "loss": 4.2611, "step": 13268 }, { "epoch": 0.4052840562003665, "grad_norm": 0.3699438273906708, "learning_rate": 3.232968173035611e-05, "loss": 4.3073, "step": 13269 }, { "epoch": 0.4053145998778253, "grad_norm": 0.382315456867218, "learning_rate": 3.2327388221152414e-05, "loss": 4.2255, "step": 13270 }, { "epoch": 0.40534514355528406, "grad_norm": 0.38491958379745483, "learning_rate": 3.232509464448168e-05, "loss": 4.3685, "step": 13271 }, { "epoch": 0.4053756872327428, "grad_norm": 0.3839673697948456, "learning_rate": 3.2322801000365035e-05, "loss": 4.2595, "step": 13272 }, { "epoch": 0.4054062309102016, "grad_norm": 0.3707515597343445, "learning_rate": 3.23205072888236e-05, "loss": 4.3582, "step": 13273 }, { "epoch": 0.40543677458766036, "grad_norm": 0.3746682405471802, "learning_rate": 3.231821350987849e-05, "loss": 4.3281, "step": 13274 }, { "epoch": 0.4054673182651191, "grad_norm": 0.37930721044540405, "learning_rate": 3.2315919663550824e-05, "loss": 4.2548, "step": 13275 }, { "epoch": 0.40549786194257786, "grad_norm": 0.38052865862846375, "learning_rate": 3.231362574986173e-05, "loss": 4.3892, "step": 13276 }, { "epoch": 0.40552840562003667, "grad_norm": 0.38780179619789124, "learning_rate": 3.231133176883232e-05, "loss": 4.3729, "step": 13277 }, { "epoch": 0.4055589492974954, "grad_norm": 0.3888530731201172, "learning_rate": 3.230903772048372e-05, "loss": 4.3481, "step": 13278 }, { "epoch": 0.40558949297495417, "grad_norm": 0.39325305819511414, "learning_rate": 3.230674360483705e-05, "loss": 4.2171, "step": 13279 }, { "epoch": 0.405620036652413, "grad_norm": 0.37010058760643005, "learning_rate": 3.230444942191343e-05, "loss": 4.3025, "step": 13280 }, { "epoch": 0.4056505803298717, "grad_norm": 0.38641053438186646, "learning_rate": 3.230215517173399e-05, "loss": 4.3043, "step": 13281 }, { "epoch": 0.4056811240073305, "grad_norm": 0.37868571281433105, "learning_rate": 3.2299860854319866e-05, "loss": 4.3728, "step": 13282 }, { "epoch": 0.4057116676847892, "grad_norm": 0.37759947776794434, "learning_rate": 3.229756646969216e-05, "loss": 4.2332, "step": 13283 }, { "epoch": 0.40574221136224803, "grad_norm": 0.3846500515937805, "learning_rate": 3.229527201787201e-05, "loss": 4.3393, "step": 13284 }, { "epoch": 0.4057727550397068, "grad_norm": 0.3804566264152527, "learning_rate": 3.229297749888054e-05, "loss": 4.2672, "step": 13285 }, { "epoch": 0.40580329871716553, "grad_norm": 0.3831746578216553, "learning_rate": 3.229068291273887e-05, "loss": 4.2911, "step": 13286 }, { "epoch": 0.40583384239462433, "grad_norm": 0.3801937699317932, "learning_rate": 3.2288388259468135e-05, "loss": 4.3905, "step": 13287 }, { "epoch": 0.4058643860720831, "grad_norm": 0.3937055468559265, "learning_rate": 3.228609353908947e-05, "loss": 4.2046, "step": 13288 }, { "epoch": 0.40589492974954183, "grad_norm": 0.3754380941390991, "learning_rate": 3.228379875162399e-05, "loss": 4.3507, "step": 13289 }, { "epoch": 0.40592547342700064, "grad_norm": 0.3842715322971344, "learning_rate": 3.2281503897092826e-05, "loss": 4.3096, "step": 13290 }, { "epoch": 0.4059560171044594, "grad_norm": 0.38151270151138306, "learning_rate": 3.227920897551712e-05, "loss": 4.3726, "step": 13291 }, { "epoch": 0.40598656078191814, "grad_norm": 0.36735427379608154, "learning_rate": 3.227691398691799e-05, "loss": 4.3665, "step": 13292 }, { "epoch": 0.4060171044593769, "grad_norm": 0.37821924686431885, "learning_rate": 3.2274618931316575e-05, "loss": 4.2185, "step": 13293 }, { "epoch": 0.4060476481368357, "grad_norm": 0.3768461048603058, "learning_rate": 3.2272323808733996e-05, "loss": 4.416, "step": 13294 }, { "epoch": 0.40607819181429444, "grad_norm": 0.37785497307777405, "learning_rate": 3.22700286191914e-05, "loss": 4.2691, "step": 13295 }, { "epoch": 0.4061087354917532, "grad_norm": 0.3898833990097046, "learning_rate": 3.226773336270991e-05, "loss": 4.3418, "step": 13296 }, { "epoch": 0.406139279169212, "grad_norm": 0.37536463141441345, "learning_rate": 3.226543803931066e-05, "loss": 4.3182, "step": 13297 }, { "epoch": 0.40616982284667075, "grad_norm": 0.3712543547153473, "learning_rate": 3.2263142649014785e-05, "loss": 4.2633, "step": 13298 }, { "epoch": 0.4062003665241295, "grad_norm": 0.37374675273895264, "learning_rate": 3.226084719184344e-05, "loss": 4.2707, "step": 13299 }, { "epoch": 0.40623091020158825, "grad_norm": 0.3859773278236389, "learning_rate": 3.225855166781772e-05, "loss": 4.4025, "step": 13300 }, { "epoch": 0.40626145387904705, "grad_norm": 0.36653512716293335, "learning_rate": 3.225625607695878e-05, "loss": 4.294, "step": 13301 }, { "epoch": 0.4062919975565058, "grad_norm": 0.37070733308792114, "learning_rate": 3.225396041928778e-05, "loss": 4.3293, "step": 13302 }, { "epoch": 0.40632254123396455, "grad_norm": 0.3889937400817871, "learning_rate": 3.2251664694825826e-05, "loss": 4.3242, "step": 13303 }, { "epoch": 0.40635308491142336, "grad_norm": 0.38309913873672485, "learning_rate": 3.2249368903594056e-05, "loss": 4.2884, "step": 13304 }, { "epoch": 0.4063836285888821, "grad_norm": 0.3990960121154785, "learning_rate": 3.224707304561364e-05, "loss": 4.1774, "step": 13305 }, { "epoch": 0.40641417226634086, "grad_norm": 0.3798691928386688, "learning_rate": 3.2244777120905676e-05, "loss": 4.387, "step": 13306 }, { "epoch": 0.4064447159437996, "grad_norm": 0.38631004095077515, "learning_rate": 3.2242481129491344e-05, "loss": 4.347, "step": 13307 }, { "epoch": 0.4064752596212584, "grad_norm": 0.3725852370262146, "learning_rate": 3.2240185071391754e-05, "loss": 4.3817, "step": 13308 }, { "epoch": 0.40650580329871716, "grad_norm": 0.38009607791900635, "learning_rate": 3.2237888946628056e-05, "loss": 4.3962, "step": 13309 }, { "epoch": 0.4065363469761759, "grad_norm": 0.39114317297935486, "learning_rate": 3.22355927552214e-05, "loss": 4.1547, "step": 13310 }, { "epoch": 0.4065668906536347, "grad_norm": 0.3832290470600128, "learning_rate": 3.223329649719291e-05, "loss": 4.3885, "step": 13311 }, { "epoch": 0.40659743433109347, "grad_norm": 0.38307076692581177, "learning_rate": 3.223100017256375e-05, "loss": 4.2912, "step": 13312 }, { "epoch": 0.4066279780085522, "grad_norm": 0.38605213165283203, "learning_rate": 3.222870378135505e-05, "loss": 4.2575, "step": 13313 }, { "epoch": 0.406658521686011, "grad_norm": 0.37191593647003174, "learning_rate": 3.222640732358796e-05, "loss": 4.3719, "step": 13314 }, { "epoch": 0.40668906536346977, "grad_norm": 0.38168957829475403, "learning_rate": 3.2224110799283616e-05, "loss": 4.2341, "step": 13315 }, { "epoch": 0.4067196090409285, "grad_norm": 0.37196117639541626, "learning_rate": 3.222181420846318e-05, "loss": 4.1979, "step": 13316 }, { "epoch": 0.40675015271838727, "grad_norm": 0.3802129626274109, "learning_rate": 3.221951755114778e-05, "loss": 4.3495, "step": 13317 }, { "epoch": 0.4067806963958461, "grad_norm": 0.38520485162734985, "learning_rate": 3.221722082735857e-05, "loss": 4.3092, "step": 13318 }, { "epoch": 0.4068112400733048, "grad_norm": 0.38316476345062256, "learning_rate": 3.22149240371167e-05, "loss": 4.3435, "step": 13319 }, { "epoch": 0.4068417837507636, "grad_norm": 0.3846156597137451, "learning_rate": 3.221262718044331e-05, "loss": 4.2837, "step": 13320 }, { "epoch": 0.4068723274282224, "grad_norm": 0.3773772120475769, "learning_rate": 3.221033025735956e-05, "loss": 4.2927, "step": 13321 }, { "epoch": 0.40690287110568113, "grad_norm": 0.3862740099430084, "learning_rate": 3.220803326788659e-05, "loss": 4.343, "step": 13322 }, { "epoch": 0.4069334147831399, "grad_norm": 0.3782208561897278, "learning_rate": 3.220573621204555e-05, "loss": 4.3008, "step": 13323 }, { "epoch": 0.40696395846059863, "grad_norm": 0.3788975179195404, "learning_rate": 3.2203439089857596e-05, "loss": 4.2953, "step": 13324 }, { "epoch": 0.40699450213805743, "grad_norm": 0.37998390197753906, "learning_rate": 3.2201141901343864e-05, "loss": 4.2418, "step": 13325 }, { "epoch": 0.4070250458155162, "grad_norm": 0.3807259202003479, "learning_rate": 3.2198844646525525e-05, "loss": 4.1744, "step": 13326 }, { "epoch": 0.40705558949297493, "grad_norm": 0.37116169929504395, "learning_rate": 3.219654732542372e-05, "loss": 4.3055, "step": 13327 }, { "epoch": 0.40708613317043374, "grad_norm": 0.3820745348930359, "learning_rate": 3.21942499380596e-05, "loss": 4.2011, "step": 13328 }, { "epoch": 0.4071166768478925, "grad_norm": 0.39305680990219116, "learning_rate": 3.219195248445433e-05, "loss": 4.3266, "step": 13329 }, { "epoch": 0.40714722052535124, "grad_norm": 0.37981635332107544, "learning_rate": 3.2189654964629054e-05, "loss": 4.2802, "step": 13330 }, { "epoch": 0.40717776420281004, "grad_norm": 0.3804645836353302, "learning_rate": 3.218735737860492e-05, "loss": 4.3727, "step": 13331 }, { "epoch": 0.4072083078802688, "grad_norm": 0.37541326880455017, "learning_rate": 3.21850597264031e-05, "loss": 4.3421, "step": 13332 }, { "epoch": 0.40723885155772754, "grad_norm": 0.3824491798877716, "learning_rate": 3.218276200804474e-05, "loss": 4.3102, "step": 13333 }, { "epoch": 0.4072693952351863, "grad_norm": 0.3871372640132904, "learning_rate": 3.2180464223551e-05, "loss": 4.323, "step": 13334 }, { "epoch": 0.4072999389126451, "grad_norm": 0.3769916296005249, "learning_rate": 3.217816637294302e-05, "loss": 4.3117, "step": 13335 }, { "epoch": 0.40733048259010385, "grad_norm": 0.3738853931427002, "learning_rate": 3.217586845624199e-05, "loss": 4.3835, "step": 13336 }, { "epoch": 0.4073610262675626, "grad_norm": 0.3827466070652008, "learning_rate": 3.217357047346903e-05, "loss": 4.3412, "step": 13337 }, { "epoch": 0.4073915699450214, "grad_norm": 0.3841923177242279, "learning_rate": 3.2171272424645336e-05, "loss": 4.3718, "step": 13338 }, { "epoch": 0.40742211362248015, "grad_norm": 0.37490570545196533, "learning_rate": 3.216897430979205e-05, "loss": 4.332, "step": 13339 }, { "epoch": 0.4074526572999389, "grad_norm": 0.38858866691589355, "learning_rate": 3.216667612893032e-05, "loss": 4.2431, "step": 13340 }, { "epoch": 0.40748320097739765, "grad_norm": 0.38667750358581543, "learning_rate": 3.216437788208132e-05, "loss": 4.2941, "step": 13341 }, { "epoch": 0.40751374465485646, "grad_norm": 0.3956146836280823, "learning_rate": 3.216207956926621e-05, "loss": 4.3701, "step": 13342 }, { "epoch": 0.4075442883323152, "grad_norm": 0.37512126564979553, "learning_rate": 3.215978119050615e-05, "loss": 4.318, "step": 13343 }, { "epoch": 0.40757483200977396, "grad_norm": 0.3883602023124695, "learning_rate": 3.215748274582231e-05, "loss": 4.3256, "step": 13344 }, { "epoch": 0.40760537568723276, "grad_norm": 0.38039901852607727, "learning_rate": 3.215518423523584e-05, "loss": 4.1862, "step": 13345 }, { "epoch": 0.4076359193646915, "grad_norm": 0.39259135723114014, "learning_rate": 3.215288565876791e-05, "loss": 4.3265, "step": 13346 }, { "epoch": 0.40766646304215026, "grad_norm": 0.3875690698623657, "learning_rate": 3.215058701643969e-05, "loss": 4.3271, "step": 13347 }, { "epoch": 0.40769700671960907, "grad_norm": 0.39156898856163025, "learning_rate": 3.2148288308272334e-05, "loss": 4.3017, "step": 13348 }, { "epoch": 0.4077275503970678, "grad_norm": 0.3790750801563263, "learning_rate": 3.2145989534287014e-05, "loss": 4.2734, "step": 13349 }, { "epoch": 0.40775809407452657, "grad_norm": 0.3788454234600067, "learning_rate": 3.214369069450489e-05, "loss": 4.3427, "step": 13350 }, { "epoch": 0.4077886377519853, "grad_norm": 0.3873099982738495, "learning_rate": 3.214139178894714e-05, "loss": 4.3042, "step": 13351 }, { "epoch": 0.4078191814294441, "grad_norm": 0.38796815276145935, "learning_rate": 3.213909281763491e-05, "loss": 4.3825, "step": 13352 }, { "epoch": 0.40784972510690287, "grad_norm": 0.3907690644264221, "learning_rate": 3.2136793780589394e-05, "loss": 4.19, "step": 13353 }, { "epoch": 0.4078802687843616, "grad_norm": 0.3811506927013397, "learning_rate": 3.213449467783176e-05, "loss": 4.2988, "step": 13354 }, { "epoch": 0.4079108124618204, "grad_norm": 0.37840980291366577, "learning_rate": 3.213219550938315e-05, "loss": 4.3508, "step": 13355 }, { "epoch": 0.4079413561392792, "grad_norm": 0.38138359785079956, "learning_rate": 3.212989627526475e-05, "loss": 4.3045, "step": 13356 }, { "epoch": 0.4079718998167379, "grad_norm": 0.4017839729785919, "learning_rate": 3.2127596975497735e-05, "loss": 4.2685, "step": 13357 }, { "epoch": 0.4080024434941967, "grad_norm": 0.38167905807495117, "learning_rate": 3.212529761010326e-05, "loss": 4.2834, "step": 13358 }, { "epoch": 0.4080329871716555, "grad_norm": 0.38651466369628906, "learning_rate": 3.2122998179102506e-05, "loss": 4.3633, "step": 13359 }, { "epoch": 0.40806353084911423, "grad_norm": 0.37777045369148254, "learning_rate": 3.212069868251665e-05, "loss": 4.4118, "step": 13360 }, { "epoch": 0.408094074526573, "grad_norm": 0.3799808621406555, "learning_rate": 3.211839912036686e-05, "loss": 4.1204, "step": 13361 }, { "epoch": 0.4081246182040318, "grad_norm": 0.3729403018951416, "learning_rate": 3.2116099492674315e-05, "loss": 4.3928, "step": 13362 }, { "epoch": 0.40815516188149054, "grad_norm": 0.3914738893508911, "learning_rate": 3.211379979946018e-05, "loss": 4.4094, "step": 13363 }, { "epoch": 0.4081857055589493, "grad_norm": 0.3701394498348236, "learning_rate": 3.211150004074563e-05, "loss": 4.3004, "step": 13364 }, { "epoch": 0.4082162492364081, "grad_norm": 0.3767291307449341, "learning_rate": 3.210920021655184e-05, "loss": 4.3074, "step": 13365 }, { "epoch": 0.40824679291386684, "grad_norm": 0.37953171133995056, "learning_rate": 3.2106900326899995e-05, "loss": 4.3397, "step": 13366 }, { "epoch": 0.4082773365913256, "grad_norm": 0.38029012084007263, "learning_rate": 3.210460037181127e-05, "loss": 4.3366, "step": 13367 }, { "epoch": 0.40830788026878434, "grad_norm": 0.40303346514701843, "learning_rate": 3.2102300351306826e-05, "loss": 4.3155, "step": 13368 }, { "epoch": 0.40833842394624315, "grad_norm": 0.3764176070690155, "learning_rate": 3.2100000265407855e-05, "loss": 4.2943, "step": 13369 }, { "epoch": 0.4083689676237019, "grad_norm": 0.38248345255851746, "learning_rate": 3.209770011413553e-05, "loss": 4.2346, "step": 13370 }, { "epoch": 0.40839951130116064, "grad_norm": 0.38775527477264404, "learning_rate": 3.209539989751103e-05, "loss": 4.3284, "step": 13371 }, { "epoch": 0.40843005497861945, "grad_norm": 0.38536307215690613, "learning_rate": 3.2093099615555536e-05, "loss": 4.263, "step": 13372 }, { "epoch": 0.4084605986560782, "grad_norm": 0.38028886914253235, "learning_rate": 3.2090799268290224e-05, "loss": 4.2493, "step": 13373 }, { "epoch": 0.40849114233353695, "grad_norm": 0.3933963179588318, "learning_rate": 3.208849885573628e-05, "loss": 4.3173, "step": 13374 }, { "epoch": 0.4085216860109957, "grad_norm": 0.3873499035835266, "learning_rate": 3.208619837791488e-05, "loss": 4.3663, "step": 13375 }, { "epoch": 0.4085522296884545, "grad_norm": 0.3847513198852539, "learning_rate": 3.208389783484721e-05, "loss": 4.2842, "step": 13376 }, { "epoch": 0.40858277336591325, "grad_norm": 0.379338800907135, "learning_rate": 3.208159722655446e-05, "loss": 4.2068, "step": 13377 }, { "epoch": 0.408613317043372, "grad_norm": 0.3711017966270447, "learning_rate": 3.2079296553057795e-05, "loss": 4.2185, "step": 13378 }, { "epoch": 0.4086438607208308, "grad_norm": 0.39555904269218445, "learning_rate": 3.2076995814378395e-05, "loss": 4.2341, "step": 13379 }, { "epoch": 0.40867440439828956, "grad_norm": 0.391806423664093, "learning_rate": 3.207469501053747e-05, "loss": 4.1714, "step": 13380 }, { "epoch": 0.4087049480757483, "grad_norm": 0.40716198086738586, "learning_rate": 3.207239414155619e-05, "loss": 4.2812, "step": 13381 }, { "epoch": 0.40873549175320706, "grad_norm": 1.8654628992080688, "learning_rate": 3.207009320745574e-05, "loss": 4.4206, "step": 13382 }, { "epoch": 0.40876603543066586, "grad_norm": 0.3925182521343231, "learning_rate": 3.2067792208257304e-05, "loss": 4.3115, "step": 13383 }, { "epoch": 0.4087965791081246, "grad_norm": 0.3829295337200165, "learning_rate": 3.206549114398207e-05, "loss": 4.3639, "step": 13384 }, { "epoch": 0.40882712278558336, "grad_norm": 0.37957924604415894, "learning_rate": 3.206319001465123e-05, "loss": 4.2878, "step": 13385 }, { "epoch": 0.40885766646304217, "grad_norm": 0.3792779743671417, "learning_rate": 3.2060888820285975e-05, "loss": 4.353, "step": 13386 }, { "epoch": 0.4088882101405009, "grad_norm": 0.3834354877471924, "learning_rate": 3.205858756090747e-05, "loss": 4.2422, "step": 13387 }, { "epoch": 0.40891875381795967, "grad_norm": 0.3764755427837372, "learning_rate": 3.2056286236536934e-05, "loss": 4.2563, "step": 13388 }, { "epoch": 0.4089492974954185, "grad_norm": 0.38318997621536255, "learning_rate": 3.2053984847195535e-05, "loss": 4.4462, "step": 13389 }, { "epoch": 0.4089798411728772, "grad_norm": 0.3787713050842285, "learning_rate": 3.2051683392904476e-05, "loss": 4.3122, "step": 13390 }, { "epoch": 0.409010384850336, "grad_norm": 0.39510202407836914, "learning_rate": 3.2049381873684934e-05, "loss": 4.3738, "step": 13391 }, { "epoch": 0.4090409285277947, "grad_norm": 0.371509313583374, "learning_rate": 3.204708028955812e-05, "loss": 4.2646, "step": 13392 }, { "epoch": 0.40907147220525353, "grad_norm": 0.37879952788352966, "learning_rate": 3.20447786405452e-05, "loss": 4.3457, "step": 13393 }, { "epoch": 0.4091020158827123, "grad_norm": 0.3896663784980774, "learning_rate": 3.20424769266674e-05, "loss": 4.3298, "step": 13394 }, { "epoch": 0.409132559560171, "grad_norm": 0.3810664415359497, "learning_rate": 3.204017514794588e-05, "loss": 4.3471, "step": 13395 }, { "epoch": 0.40916310323762983, "grad_norm": 0.38320866227149963, "learning_rate": 3.203787330440184e-05, "loss": 4.3273, "step": 13396 }, { "epoch": 0.4091936469150886, "grad_norm": 0.3947702646255493, "learning_rate": 3.20355713960565e-05, "loss": 4.3568, "step": 13397 }, { "epoch": 0.40922419059254733, "grad_norm": 0.371439129114151, "learning_rate": 3.203326942293103e-05, "loss": 4.2907, "step": 13398 }, { "epoch": 0.4092547342700061, "grad_norm": 0.3933624029159546, "learning_rate": 3.203096738504663e-05, "loss": 4.2676, "step": 13399 }, { "epoch": 0.4092852779474649, "grad_norm": 0.3741382956504822, "learning_rate": 3.20286652824245e-05, "loss": 4.3064, "step": 13400 }, { "epoch": 0.40931582162492364, "grad_norm": 0.38007909059524536, "learning_rate": 3.2026363115085846e-05, "loss": 4.2645, "step": 13401 }, { "epoch": 0.4093463653023824, "grad_norm": 0.37845125794410706, "learning_rate": 3.2024060883051845e-05, "loss": 4.3801, "step": 13402 }, { "epoch": 0.4093769089798412, "grad_norm": 0.3806544840335846, "learning_rate": 3.2021758586343695e-05, "loss": 4.3027, "step": 13403 }, { "epoch": 0.40940745265729994, "grad_norm": 0.38385331630706787, "learning_rate": 3.201945622498262e-05, "loss": 4.285, "step": 13404 }, { "epoch": 0.4094379963347587, "grad_norm": 0.5357521772384644, "learning_rate": 3.201715379898979e-05, "loss": 4.3481, "step": 13405 }, { "epoch": 0.4094685400122175, "grad_norm": 0.3642734885215759, "learning_rate": 3.201485130838641e-05, "loss": 4.3012, "step": 13406 }, { "epoch": 0.40949908368967625, "grad_norm": 0.3753870129585266, "learning_rate": 3.201254875319371e-05, "loss": 4.2111, "step": 13407 }, { "epoch": 0.409529627367135, "grad_norm": 0.38443320989608765, "learning_rate": 3.2010246133432856e-05, "loss": 4.3031, "step": 13408 }, { "epoch": 0.40956017104459375, "grad_norm": 0.38167837262153625, "learning_rate": 3.200794344912506e-05, "loss": 4.2719, "step": 13409 }, { "epoch": 0.40959071472205255, "grad_norm": 0.3855026364326477, "learning_rate": 3.200564070029153e-05, "loss": 4.2505, "step": 13410 }, { "epoch": 0.4096212583995113, "grad_norm": 0.384391188621521, "learning_rate": 3.2003337886953454e-05, "loss": 4.3366, "step": 13411 }, { "epoch": 0.40965180207697005, "grad_norm": 0.3826991021633148, "learning_rate": 3.2001035009132055e-05, "loss": 4.1836, "step": 13412 }, { "epoch": 0.40968234575442886, "grad_norm": 0.3825329840183258, "learning_rate": 3.199873206684853e-05, "loss": 4.2508, "step": 13413 }, { "epoch": 0.4097128894318876, "grad_norm": 0.39163440465927124, "learning_rate": 3.199642906012407e-05, "loss": 4.2264, "step": 13414 }, { "epoch": 0.40974343310934636, "grad_norm": 0.39964890480041504, "learning_rate": 3.1994125988979895e-05, "loss": 4.3275, "step": 13415 }, { "epoch": 0.4097739767868051, "grad_norm": 0.3700847625732422, "learning_rate": 3.199182285343721e-05, "loss": 4.3081, "step": 13416 }, { "epoch": 0.4098045204642639, "grad_norm": 0.39075297117233276, "learning_rate": 3.198951965351721e-05, "loss": 4.3676, "step": 13417 }, { "epoch": 0.40983506414172266, "grad_norm": 0.3849225342273712, "learning_rate": 3.198721638924112e-05, "loss": 4.3191, "step": 13418 }, { "epoch": 0.4098656078191814, "grad_norm": 0.38776519894599915, "learning_rate": 3.1984913060630125e-05, "loss": 4.3341, "step": 13419 }, { "epoch": 0.4098961514966402, "grad_norm": 0.3908579349517822, "learning_rate": 3.1982609667705446e-05, "loss": 4.2526, "step": 13420 }, { "epoch": 0.40992669517409897, "grad_norm": 0.38103941082954407, "learning_rate": 3.198030621048829e-05, "loss": 4.331, "step": 13421 }, { "epoch": 0.4099572388515577, "grad_norm": 0.38852691650390625, "learning_rate": 3.197800268899987e-05, "loss": 4.3313, "step": 13422 }, { "epoch": 0.4099877825290165, "grad_norm": 0.3939114809036255, "learning_rate": 3.1975699103261383e-05, "loss": 4.3032, "step": 13423 }, { "epoch": 0.41001832620647527, "grad_norm": 0.3885343372821808, "learning_rate": 3.197339545329407e-05, "loss": 4.3189, "step": 13424 }, { "epoch": 0.410048869883934, "grad_norm": 0.37556180357933044, "learning_rate": 3.19710917391191e-05, "loss": 4.3306, "step": 13425 }, { "epoch": 0.41007941356139277, "grad_norm": 0.39476102590560913, "learning_rate": 3.196878796075771e-05, "loss": 4.3542, "step": 13426 }, { "epoch": 0.4101099572388516, "grad_norm": 0.3951617181301117, "learning_rate": 3.19664841182311e-05, "loss": 4.3366, "step": 13427 }, { "epoch": 0.4101405009163103, "grad_norm": 0.37253326177597046, "learning_rate": 3.196418021156049e-05, "loss": 4.2636, "step": 13428 }, { "epoch": 0.4101710445937691, "grad_norm": 0.37755122780799866, "learning_rate": 3.19618762407671e-05, "loss": 4.2682, "step": 13429 }, { "epoch": 0.4102015882712279, "grad_norm": 0.38285914063453674, "learning_rate": 3.1959572205872125e-05, "loss": 4.2829, "step": 13430 }, { "epoch": 0.41023213194868663, "grad_norm": 0.38461634516716003, "learning_rate": 3.19572681068968e-05, "loss": 4.3684, "step": 13431 }, { "epoch": 0.4102626756261454, "grad_norm": 0.3831261098384857, "learning_rate": 3.195496394386233e-05, "loss": 4.3188, "step": 13432 }, { "epoch": 0.41029321930360413, "grad_norm": 0.3900810778141022, "learning_rate": 3.195265971678993e-05, "loss": 4.3775, "step": 13433 }, { "epoch": 0.41032376298106293, "grad_norm": 0.3783320188522339, "learning_rate": 3.195035542570081e-05, "loss": 4.2934, "step": 13434 }, { "epoch": 0.4103543066585217, "grad_norm": 0.40983477234840393, "learning_rate": 3.19480510706162e-05, "loss": 4.3471, "step": 13435 }, { "epoch": 0.41038485033598043, "grad_norm": 0.38586750626564026, "learning_rate": 3.1945746651557313e-05, "loss": 4.4635, "step": 13436 }, { "epoch": 0.41041539401343924, "grad_norm": 0.38749513030052185, "learning_rate": 3.194344216854536e-05, "loss": 4.3641, "step": 13437 }, { "epoch": 0.410445937690898, "grad_norm": 0.3836613893508911, "learning_rate": 3.194113762160157e-05, "loss": 4.3022, "step": 13438 }, { "epoch": 0.41047648136835674, "grad_norm": 0.3835817575454712, "learning_rate": 3.193883301074716e-05, "loss": 4.3265, "step": 13439 }, { "epoch": 0.41050702504581554, "grad_norm": 0.3821885883808136, "learning_rate": 3.193652833600334e-05, "loss": 4.3011, "step": 13440 }, { "epoch": 0.4105375687232743, "grad_norm": 0.37994420528411865, "learning_rate": 3.193422359739134e-05, "loss": 4.2574, "step": 13441 }, { "epoch": 0.41056811240073304, "grad_norm": 0.38647735118865967, "learning_rate": 3.193191879493238e-05, "loss": 4.3333, "step": 13442 }, { "epoch": 0.4105986560781918, "grad_norm": 0.39815276861190796, "learning_rate": 3.192961392864768e-05, "loss": 4.2339, "step": 13443 }, { "epoch": 0.4106291997556506, "grad_norm": 0.39729738235473633, "learning_rate": 3.192730899855845e-05, "loss": 4.3046, "step": 13444 }, { "epoch": 0.41065974343310935, "grad_norm": 0.3940884470939636, "learning_rate": 3.1925004004685936e-05, "loss": 4.2694, "step": 13445 }, { "epoch": 0.4106902871105681, "grad_norm": 0.381140798330307, "learning_rate": 3.192269894705135e-05, "loss": 4.2889, "step": 13446 }, { "epoch": 0.4107208307880269, "grad_norm": 0.38651007413864136, "learning_rate": 3.192039382567591e-05, "loss": 4.4176, "step": 13447 }, { "epoch": 0.41075137446548565, "grad_norm": 0.39205390214920044, "learning_rate": 3.191808864058085e-05, "loss": 4.322, "step": 13448 }, { "epoch": 0.4107819181429444, "grad_norm": 0.3847730755805969, "learning_rate": 3.191578339178739e-05, "loss": 4.3319, "step": 13449 }, { "epoch": 0.41081246182040315, "grad_norm": 0.3925156593322754, "learning_rate": 3.191347807931676e-05, "loss": 4.3859, "step": 13450 }, { "epoch": 0.41084300549786196, "grad_norm": 0.3952748775482178, "learning_rate": 3.1911172703190175e-05, "loss": 4.3573, "step": 13451 }, { "epoch": 0.4108735491753207, "grad_norm": 0.38165611028671265, "learning_rate": 3.190886726342887e-05, "loss": 4.3414, "step": 13452 }, { "epoch": 0.41090409285277946, "grad_norm": 0.3860543370246887, "learning_rate": 3.190656176005408e-05, "loss": 4.3009, "step": 13453 }, { "epoch": 0.41093463653023826, "grad_norm": 0.39099329710006714, "learning_rate": 3.1904256193087013e-05, "loss": 4.3247, "step": 13454 }, { "epoch": 0.410965180207697, "grad_norm": 0.38681021332740784, "learning_rate": 3.190195056254892e-05, "loss": 4.3591, "step": 13455 }, { "epoch": 0.41099572388515576, "grad_norm": 0.39688023924827576, "learning_rate": 3.189964486846102e-05, "loss": 4.3199, "step": 13456 }, { "epoch": 0.4110262675626145, "grad_norm": 0.3919859528541565, "learning_rate": 3.1897339110844545e-05, "loss": 4.2934, "step": 13457 }, { "epoch": 0.4110568112400733, "grad_norm": 0.37893179059028625, "learning_rate": 3.189503328972071e-05, "loss": 4.2239, "step": 13458 }, { "epoch": 0.41108735491753207, "grad_norm": 0.39649710059165955, "learning_rate": 3.189272740511076e-05, "loss": 4.3118, "step": 13459 }, { "epoch": 0.4111178985949908, "grad_norm": 0.3863458037376404, "learning_rate": 3.189042145703593e-05, "loss": 4.222, "step": 13460 }, { "epoch": 0.4111484422724496, "grad_norm": 0.39422407746315, "learning_rate": 3.188811544551745e-05, "loss": 4.3478, "step": 13461 }, { "epoch": 0.41117898594990837, "grad_norm": 0.3740788996219635, "learning_rate": 3.188580937057654e-05, "loss": 4.3637, "step": 13462 }, { "epoch": 0.4112095296273671, "grad_norm": 0.391109824180603, "learning_rate": 3.1883503232234454e-05, "loss": 4.2556, "step": 13463 }, { "epoch": 0.4112400733048259, "grad_norm": 0.3772464990615845, "learning_rate": 3.188119703051241e-05, "loss": 4.3033, "step": 13464 }, { "epoch": 0.4112706169822847, "grad_norm": 0.37624451518058777, "learning_rate": 3.1878890765431646e-05, "loss": 4.2887, "step": 13465 }, { "epoch": 0.4113011606597434, "grad_norm": 0.3813401162624359, "learning_rate": 3.18765844370134e-05, "loss": 4.3434, "step": 13466 }, { "epoch": 0.4113317043372022, "grad_norm": 0.37564000487327576, "learning_rate": 3.1874278045278906e-05, "loss": 4.2681, "step": 13467 }, { "epoch": 0.411362248014661, "grad_norm": 0.3962196111679077, "learning_rate": 3.187197159024939e-05, "loss": 4.3248, "step": 13468 }, { "epoch": 0.41139279169211973, "grad_norm": 0.3794620931148529, "learning_rate": 3.1869665071946106e-05, "loss": 4.3085, "step": 13469 }, { "epoch": 0.4114233353695785, "grad_norm": 0.3785220682621002, "learning_rate": 3.1867358490390285e-05, "loss": 4.2729, "step": 13470 }, { "epoch": 0.4114538790470373, "grad_norm": 0.3868370056152344, "learning_rate": 3.186505184560316e-05, "loss": 4.3055, "step": 13471 }, { "epoch": 0.41148442272449604, "grad_norm": 0.3826659619808197, "learning_rate": 3.1862745137605976e-05, "loss": 4.3211, "step": 13472 }, { "epoch": 0.4115149664019548, "grad_norm": 0.3701375424861908, "learning_rate": 3.186043836641997e-05, "loss": 4.3265, "step": 13473 }, { "epoch": 0.41154551007941353, "grad_norm": 0.3844135105609894, "learning_rate": 3.185813153206638e-05, "loss": 4.3031, "step": 13474 }, { "epoch": 0.41157605375687234, "grad_norm": 0.3811217248439789, "learning_rate": 3.185582463456644e-05, "loss": 4.2085, "step": 13475 }, { "epoch": 0.4116065974343311, "grad_norm": 0.3925912082195282, "learning_rate": 3.18535176739414e-05, "loss": 4.3511, "step": 13476 }, { "epoch": 0.41163714111178984, "grad_norm": 0.38978198170661926, "learning_rate": 3.185121065021251e-05, "loss": 4.2276, "step": 13477 }, { "epoch": 0.41166768478924864, "grad_norm": 0.3781844675540924, "learning_rate": 3.184890356340099e-05, "loss": 4.2954, "step": 13478 }, { "epoch": 0.4116982284667074, "grad_norm": 0.39140698313713074, "learning_rate": 3.1846596413528095e-05, "loss": 4.2711, "step": 13479 }, { "epoch": 0.41172877214416614, "grad_norm": 0.3885752558708191, "learning_rate": 3.184428920061508e-05, "loss": 4.3438, "step": 13480 }, { "epoch": 0.41175931582162495, "grad_norm": 0.3716541528701782, "learning_rate": 3.1841981924683154e-05, "loss": 4.2977, "step": 13481 }, { "epoch": 0.4117898594990837, "grad_norm": 0.3751464784145355, "learning_rate": 3.1839674585753595e-05, "loss": 4.2507, "step": 13482 }, { "epoch": 0.41182040317654245, "grad_norm": 0.3943798542022705, "learning_rate": 3.183736718384763e-05, "loss": 4.3306, "step": 13483 }, { "epoch": 0.4118509468540012, "grad_norm": 0.3870566189289093, "learning_rate": 3.183505971898651e-05, "loss": 4.3142, "step": 13484 }, { "epoch": 0.41188149053146, "grad_norm": 0.3778688609600067, "learning_rate": 3.1832752191191484e-05, "loss": 4.2714, "step": 13485 }, { "epoch": 0.41191203420891875, "grad_norm": 0.3868809938430786, "learning_rate": 3.1830444600483794e-05, "loss": 4.2277, "step": 13486 }, { "epoch": 0.4119425778863775, "grad_norm": 0.3742797076702118, "learning_rate": 3.1828136946884694e-05, "loss": 4.2934, "step": 13487 }, { "epoch": 0.4119731215638363, "grad_norm": 0.3917454779148102, "learning_rate": 3.182582923041542e-05, "loss": 4.3111, "step": 13488 }, { "epoch": 0.41200366524129506, "grad_norm": 0.3961092233657837, "learning_rate": 3.182352145109723e-05, "loss": 4.2884, "step": 13489 }, { "epoch": 0.4120342089187538, "grad_norm": 0.3894372880458832, "learning_rate": 3.1821213608951374e-05, "loss": 4.3781, "step": 13490 }, { "epoch": 0.41206475259621256, "grad_norm": 0.3849833011627197, "learning_rate": 3.181890570399909e-05, "loss": 4.3243, "step": 13491 }, { "epoch": 0.41209529627367136, "grad_norm": 0.38649898767471313, "learning_rate": 3.181659773626163e-05, "loss": 4.352, "step": 13492 }, { "epoch": 0.4121258399511301, "grad_norm": 0.38845595717430115, "learning_rate": 3.181428970576026e-05, "loss": 4.3623, "step": 13493 }, { "epoch": 0.41215638362858886, "grad_norm": 0.3868813216686249, "learning_rate": 3.181198161251622e-05, "loss": 4.3417, "step": 13494 }, { "epoch": 0.41218692730604767, "grad_norm": 0.3832434415817261, "learning_rate": 3.180967345655076e-05, "loss": 4.3919, "step": 13495 }, { "epoch": 0.4122174709835064, "grad_norm": 0.384209543466568, "learning_rate": 3.180736523788514e-05, "loss": 4.3531, "step": 13496 }, { "epoch": 0.41224801466096517, "grad_norm": 0.3860033452510834, "learning_rate": 3.1805056956540603e-05, "loss": 4.2753, "step": 13497 }, { "epoch": 0.412278558338424, "grad_norm": 0.3892919421195984, "learning_rate": 3.1802748612538406e-05, "loss": 4.422, "step": 13498 }, { "epoch": 0.4123091020158827, "grad_norm": 0.3875008523464203, "learning_rate": 3.180044020589981e-05, "loss": 4.251, "step": 13499 }, { "epoch": 0.41233964569334147, "grad_norm": 0.37987020611763, "learning_rate": 3.179813173664606e-05, "loss": 4.3429, "step": 13500 }, { "epoch": 0.4123701893708002, "grad_norm": 0.3945884704589844, "learning_rate": 3.1795823204798426e-05, "loss": 4.3453, "step": 13501 }, { "epoch": 0.412400733048259, "grad_norm": 0.39344465732574463, "learning_rate": 3.179351461037815e-05, "loss": 4.299, "step": 13502 }, { "epoch": 0.4124312767257178, "grad_norm": 0.4151705205440521, "learning_rate": 3.1791205953406484e-05, "loss": 4.3487, "step": 13503 }, { "epoch": 0.4124618204031765, "grad_norm": 0.3997652232646942, "learning_rate": 3.1788897233904694e-05, "loss": 4.3143, "step": 13504 }, { "epoch": 0.41249236408063533, "grad_norm": 0.3939313292503357, "learning_rate": 3.178658845189404e-05, "loss": 4.2765, "step": 13505 }, { "epoch": 0.4125229077580941, "grad_norm": 0.38973525166511536, "learning_rate": 3.1784279607395775e-05, "loss": 4.3017, "step": 13506 }, { "epoch": 0.41255345143555283, "grad_norm": 0.4039044976234436, "learning_rate": 3.178197070043116e-05, "loss": 4.3351, "step": 13507 }, { "epoch": 0.4125839951130116, "grad_norm": 0.3959839344024658, "learning_rate": 3.177966173102146e-05, "loss": 4.3701, "step": 13508 }, { "epoch": 0.4126145387904704, "grad_norm": 0.38065916299819946, "learning_rate": 3.177735269918792e-05, "loss": 4.2783, "step": 13509 }, { "epoch": 0.41264508246792914, "grad_norm": 0.38427501916885376, "learning_rate": 3.1775043604951816e-05, "loss": 4.3011, "step": 13510 }, { "epoch": 0.4126756261453879, "grad_norm": 0.38781729340553284, "learning_rate": 3.1772734448334405e-05, "loss": 4.3463, "step": 13511 }, { "epoch": 0.4127061698228467, "grad_norm": 0.4057108461856842, "learning_rate": 3.177042522935694e-05, "loss": 4.3884, "step": 13512 }, { "epoch": 0.41273671350030544, "grad_norm": 0.40478357672691345, "learning_rate": 3.176811594804069e-05, "loss": 4.3515, "step": 13513 }, { "epoch": 0.4127672571777642, "grad_norm": 0.3841322958469391, "learning_rate": 3.176580660440691e-05, "loss": 4.3323, "step": 13514 }, { "epoch": 0.412797800855223, "grad_norm": 0.37623727321624756, "learning_rate": 3.1763497198476876e-05, "loss": 4.3361, "step": 13515 }, { "epoch": 0.41282834453268175, "grad_norm": 0.3833290934562683, "learning_rate": 3.176118773027185e-05, "loss": 4.3403, "step": 13516 }, { "epoch": 0.4128588882101405, "grad_norm": 0.3769327402114868, "learning_rate": 3.175887819981308e-05, "loss": 4.235, "step": 13517 }, { "epoch": 0.41288943188759925, "grad_norm": 0.3944784998893738, "learning_rate": 3.1756568607121855e-05, "loss": 4.2472, "step": 13518 }, { "epoch": 0.41291997556505805, "grad_norm": 0.38408997654914856, "learning_rate": 3.175425895221943e-05, "loss": 4.3157, "step": 13519 }, { "epoch": 0.4129505192425168, "grad_norm": 0.39022988080978394, "learning_rate": 3.175194923512707e-05, "loss": 4.2105, "step": 13520 }, { "epoch": 0.41298106291997555, "grad_norm": 0.3968690037727356, "learning_rate": 3.174963945586603e-05, "loss": 4.2775, "step": 13521 }, { "epoch": 0.41301160659743436, "grad_norm": 0.3860217034816742, "learning_rate": 3.1747329614457594e-05, "loss": 4.3943, "step": 13522 }, { "epoch": 0.4130421502748931, "grad_norm": 0.3939204514026642, "learning_rate": 3.174501971092303e-05, "loss": 4.3513, "step": 13523 }, { "epoch": 0.41307269395235185, "grad_norm": 0.38301387429237366, "learning_rate": 3.17427097452836e-05, "loss": 4.3086, "step": 13524 }, { "epoch": 0.4131032376298106, "grad_norm": 0.3815016448497772, "learning_rate": 3.174039971756057e-05, "loss": 4.2843, "step": 13525 }, { "epoch": 0.4131337813072694, "grad_norm": 0.3858807384967804, "learning_rate": 3.173808962777522e-05, "loss": 4.3387, "step": 13526 }, { "epoch": 0.41316432498472816, "grad_norm": 0.3815732002258301, "learning_rate": 3.1735779475948814e-05, "loss": 4.1789, "step": 13527 }, { "epoch": 0.4131948686621869, "grad_norm": 0.38715076446533203, "learning_rate": 3.173346926210262e-05, "loss": 4.3314, "step": 13528 }, { "epoch": 0.4132254123396457, "grad_norm": 0.38308802247047424, "learning_rate": 3.1731158986257914e-05, "loss": 4.3821, "step": 13529 }, { "epoch": 0.41325595601710446, "grad_norm": 0.3979214131832123, "learning_rate": 3.172884864843597e-05, "loss": 4.276, "step": 13530 }, { "epoch": 0.4132864996945632, "grad_norm": 0.3950504660606384, "learning_rate": 3.172653824865805e-05, "loss": 4.3034, "step": 13531 }, { "epoch": 0.41331704337202196, "grad_norm": 0.3907206356525421, "learning_rate": 3.172422778694544e-05, "loss": 4.342, "step": 13532 }, { "epoch": 0.41334758704948077, "grad_norm": 0.37554529309272766, "learning_rate": 3.1721917263319394e-05, "loss": 4.3335, "step": 13533 }, { "epoch": 0.4133781307269395, "grad_norm": 0.3876136541366577, "learning_rate": 3.1719606677801216e-05, "loss": 4.2474, "step": 13534 }, { "epoch": 0.41340867440439827, "grad_norm": 0.37599003314971924, "learning_rate": 3.171729603041217e-05, "loss": 4.2234, "step": 13535 }, { "epoch": 0.4134392180818571, "grad_norm": 0.3899640142917633, "learning_rate": 3.1714985321173504e-05, "loss": 4.3212, "step": 13536 }, { "epoch": 0.4134697617593158, "grad_norm": 0.3827003240585327, "learning_rate": 3.1712674550106524e-05, "loss": 4.3354, "step": 13537 }, { "epoch": 0.4135003054367746, "grad_norm": 0.41385769844055176, "learning_rate": 3.1710363717232506e-05, "loss": 4.4141, "step": 13538 }, { "epoch": 0.4135308491142334, "grad_norm": 0.3900138735771179, "learning_rate": 3.170805282257271e-05, "loss": 4.3678, "step": 13539 }, { "epoch": 0.41356139279169213, "grad_norm": 0.38187772035598755, "learning_rate": 3.1705741866148423e-05, "loss": 4.4317, "step": 13540 }, { "epoch": 0.4135919364691509, "grad_norm": 0.37915632128715515, "learning_rate": 3.1703430847980934e-05, "loss": 4.3918, "step": 13541 }, { "epoch": 0.41362248014660963, "grad_norm": 0.3830949366092682, "learning_rate": 3.17011197680915e-05, "loss": 4.2645, "step": 13542 }, { "epoch": 0.41365302382406843, "grad_norm": 0.3946843445301056, "learning_rate": 3.169880862650141e-05, "loss": 4.3408, "step": 13543 }, { "epoch": 0.4136835675015272, "grad_norm": 0.39239105582237244, "learning_rate": 3.1696497423231954e-05, "loss": 4.3029, "step": 13544 }, { "epoch": 0.41371411117898593, "grad_norm": 0.37753328680992126, "learning_rate": 3.1694186158304394e-05, "loss": 4.3135, "step": 13545 }, { "epoch": 0.41374465485644474, "grad_norm": 0.38581109046936035, "learning_rate": 3.169187483174002e-05, "loss": 4.306, "step": 13546 }, { "epoch": 0.4137751985339035, "grad_norm": 0.385684996843338, "learning_rate": 3.168956344356012e-05, "loss": 4.3219, "step": 13547 }, { "epoch": 0.41380574221136224, "grad_norm": 0.4026761054992676, "learning_rate": 3.168725199378597e-05, "loss": 4.3323, "step": 13548 }, { "epoch": 0.413836285888821, "grad_norm": 0.38402771949768066, "learning_rate": 3.168494048243885e-05, "loss": 4.3221, "step": 13549 }, { "epoch": 0.4138668295662798, "grad_norm": 0.37728554010391235, "learning_rate": 3.1682628909540046e-05, "loss": 4.2608, "step": 13550 }, { "epoch": 0.41389737324373854, "grad_norm": 0.442151814699173, "learning_rate": 3.168031727511084e-05, "loss": 4.2562, "step": 13551 }, { "epoch": 0.4139279169211973, "grad_norm": 0.4001148045063019, "learning_rate": 3.167800557917252e-05, "loss": 4.377, "step": 13552 }, { "epoch": 0.4139584605986561, "grad_norm": 0.38564467430114746, "learning_rate": 3.1675693821746364e-05, "loss": 4.3274, "step": 13553 }, { "epoch": 0.41398900427611485, "grad_norm": 0.3851485550403595, "learning_rate": 3.167338200285367e-05, "loss": 4.3003, "step": 13554 }, { "epoch": 0.4140195479535736, "grad_norm": 0.371077299118042, "learning_rate": 3.167107012251572e-05, "loss": 4.2129, "step": 13555 }, { "epoch": 0.4140500916310324, "grad_norm": 0.39072665572166443, "learning_rate": 3.166875818075379e-05, "loss": 4.2881, "step": 13556 }, { "epoch": 0.41408063530849115, "grad_norm": 0.38512206077575684, "learning_rate": 3.166644617758918e-05, "loss": 4.3395, "step": 13557 }, { "epoch": 0.4141111789859499, "grad_norm": 0.3822222948074341, "learning_rate": 3.166413411304317e-05, "loss": 4.3449, "step": 13558 }, { "epoch": 0.41414172266340865, "grad_norm": 0.36751341819763184, "learning_rate": 3.1661821987137055e-05, "loss": 4.3199, "step": 13559 }, { "epoch": 0.41417226634086746, "grad_norm": 0.37711602449417114, "learning_rate": 3.16595097998921e-05, "loss": 4.298, "step": 13560 }, { "epoch": 0.4142028100183262, "grad_norm": 0.3758266270160675, "learning_rate": 3.1657197551329636e-05, "loss": 4.2558, "step": 13561 }, { "epoch": 0.41423335369578496, "grad_norm": 0.39497509598731995, "learning_rate": 3.165488524147092e-05, "loss": 4.2862, "step": 13562 }, { "epoch": 0.41426389737324376, "grad_norm": 0.3849687874317169, "learning_rate": 3.165257287033726e-05, "loss": 4.3277, "step": 13563 }, { "epoch": 0.4142944410507025, "grad_norm": 0.38206663727760315, "learning_rate": 3.1650260437949944e-05, "loss": 4.1844, "step": 13564 }, { "epoch": 0.41432498472816126, "grad_norm": 0.38431012630462646, "learning_rate": 3.1647947944330254e-05, "loss": 4.2979, "step": 13565 }, { "epoch": 0.41435552840562, "grad_norm": 0.37304532527923584, "learning_rate": 3.16456353894995e-05, "loss": 4.388, "step": 13566 }, { "epoch": 0.4143860720830788, "grad_norm": 0.3871828615665436, "learning_rate": 3.164332277347895e-05, "loss": 4.3284, "step": 13567 }, { "epoch": 0.41441661576053757, "grad_norm": 0.3783979117870331, "learning_rate": 3.164101009628992e-05, "loss": 4.3692, "step": 13568 }, { "epoch": 0.4144471594379963, "grad_norm": 0.36735042929649353, "learning_rate": 3.1638697357953695e-05, "loss": 4.3371, "step": 13569 }, { "epoch": 0.4144777031154551, "grad_norm": 0.38458317518234253, "learning_rate": 3.1636384558491564e-05, "loss": 4.278, "step": 13570 }, { "epoch": 0.41450824679291387, "grad_norm": 0.3754407465457916, "learning_rate": 3.163407169792483e-05, "loss": 4.2641, "step": 13571 }, { "epoch": 0.4145387904703726, "grad_norm": 0.3857097029685974, "learning_rate": 3.163175877627479e-05, "loss": 4.3465, "step": 13572 }, { "epoch": 0.4145693341478314, "grad_norm": 0.3762682378292084, "learning_rate": 3.162944579356274e-05, "loss": 4.3428, "step": 13573 }, { "epoch": 0.4145998778252902, "grad_norm": 0.3940015733242035, "learning_rate": 3.162713274980997e-05, "loss": 4.3317, "step": 13574 }, { "epoch": 0.4146304215027489, "grad_norm": 0.3864805996417999, "learning_rate": 3.162481964503778e-05, "loss": 4.3067, "step": 13575 }, { "epoch": 0.4146609651802077, "grad_norm": 0.39014002680778503, "learning_rate": 3.162250647926748e-05, "loss": 4.2551, "step": 13576 }, { "epoch": 0.4146915088576665, "grad_norm": 0.3839021325111389, "learning_rate": 3.162019325252034e-05, "loss": 4.274, "step": 13577 }, { "epoch": 0.41472205253512523, "grad_norm": 0.3784005343914032, "learning_rate": 3.1617879964817687e-05, "loss": 4.3234, "step": 13578 }, { "epoch": 0.414752596212584, "grad_norm": 0.38744425773620605, "learning_rate": 3.1615566616180815e-05, "loss": 4.3458, "step": 13579 }, { "epoch": 0.4147831398900428, "grad_norm": 0.3798242211341858, "learning_rate": 3.161325320663101e-05, "loss": 4.3135, "step": 13580 }, { "epoch": 0.41481368356750153, "grad_norm": 0.38259121775627136, "learning_rate": 3.161093973618959e-05, "loss": 4.3435, "step": 13581 }, { "epoch": 0.4148442272449603, "grad_norm": 0.38006770610809326, "learning_rate": 3.160862620487785e-05, "loss": 4.2602, "step": 13582 }, { "epoch": 0.41487477092241903, "grad_norm": 0.3855353891849518, "learning_rate": 3.160631261271709e-05, "loss": 4.3934, "step": 13583 }, { "epoch": 0.41490531459987784, "grad_norm": 0.3901466429233551, "learning_rate": 3.1603998959728606e-05, "loss": 4.3008, "step": 13584 }, { "epoch": 0.4149358582773366, "grad_norm": 0.37861743569374084, "learning_rate": 3.160168524593371e-05, "loss": 4.376, "step": 13585 }, { "epoch": 0.41496640195479534, "grad_norm": 0.3797716796398163, "learning_rate": 3.1599371471353705e-05, "loss": 4.3708, "step": 13586 }, { "epoch": 0.41499694563225414, "grad_norm": 0.38428258895874023, "learning_rate": 3.159705763600989e-05, "loss": 4.2795, "step": 13587 }, { "epoch": 0.4150274893097129, "grad_norm": 0.3843246400356293, "learning_rate": 3.159474373992358e-05, "loss": 4.3092, "step": 13588 }, { "epoch": 0.41505803298717164, "grad_norm": 0.37480199337005615, "learning_rate": 3.159242978311608e-05, "loss": 4.3537, "step": 13589 }, { "epoch": 0.41508857666463045, "grad_norm": 0.37237468361854553, "learning_rate": 3.1590115765608675e-05, "loss": 4.1965, "step": 13590 }, { "epoch": 0.4151191203420892, "grad_norm": 0.3891874849796295, "learning_rate": 3.158780168742269e-05, "loss": 4.1909, "step": 13591 }, { "epoch": 0.41514966401954795, "grad_norm": 0.37768423557281494, "learning_rate": 3.1585487548579434e-05, "loss": 4.338, "step": 13592 }, { "epoch": 0.4151802076970067, "grad_norm": 0.37225019931793213, "learning_rate": 3.15831733491002e-05, "loss": 4.3243, "step": 13593 }, { "epoch": 0.4152107513744655, "grad_norm": 0.3781239688396454, "learning_rate": 3.158085908900631e-05, "loss": 4.2906, "step": 13594 }, { "epoch": 0.41524129505192425, "grad_norm": 0.38121581077575684, "learning_rate": 3.157854476831906e-05, "loss": 4.3694, "step": 13595 }, { "epoch": 0.415271838729383, "grad_norm": 0.3863382041454315, "learning_rate": 3.157623038705978e-05, "loss": 4.3143, "step": 13596 }, { "epoch": 0.4153023824068418, "grad_norm": 0.391151487827301, "learning_rate": 3.157391594524975e-05, "loss": 4.3648, "step": 13597 }, { "epoch": 0.41533292608430056, "grad_norm": 0.44642379879951477, "learning_rate": 3.1571601442910306e-05, "loss": 4.2945, "step": 13598 }, { "epoch": 0.4153634697617593, "grad_norm": 0.38367170095443726, "learning_rate": 3.156928688006275e-05, "loss": 4.2843, "step": 13599 }, { "epoch": 0.41539401343921806, "grad_norm": 0.37401852011680603, "learning_rate": 3.156697225672839e-05, "loss": 4.3001, "step": 13600 }, { "epoch": 0.41542455711667686, "grad_norm": 0.3838059604167938, "learning_rate": 3.1564657572928534e-05, "loss": 4.3757, "step": 13601 }, { "epoch": 0.4154551007941356, "grad_norm": 0.38886088132858276, "learning_rate": 3.15623428286845e-05, "loss": 4.2158, "step": 13602 }, { "epoch": 0.41548564447159436, "grad_norm": 0.37203267216682434, "learning_rate": 3.1560028024017605e-05, "loss": 4.2904, "step": 13603 }, { "epoch": 0.41551618814905317, "grad_norm": 0.3789270222187042, "learning_rate": 3.155771315894917e-05, "loss": 4.2885, "step": 13604 }, { "epoch": 0.4155467318265119, "grad_norm": 0.39364495873451233, "learning_rate": 3.155539823350049e-05, "loss": 4.3616, "step": 13605 }, { "epoch": 0.41557727550397067, "grad_norm": 0.37329769134521484, "learning_rate": 3.1553083247692886e-05, "loss": 4.4024, "step": 13606 }, { "epoch": 0.4156078191814294, "grad_norm": 0.3946811258792877, "learning_rate": 3.155076820154768e-05, "loss": 4.2949, "step": 13607 }, { "epoch": 0.4156383628588882, "grad_norm": 0.38081640005111694, "learning_rate": 3.1548453095086166e-05, "loss": 4.3056, "step": 13608 }, { "epoch": 0.41566890653634697, "grad_norm": 0.3885517716407776, "learning_rate": 3.1546137928329686e-05, "loss": 4.3863, "step": 13609 }, { "epoch": 0.4156994502138057, "grad_norm": 0.38589152693748474, "learning_rate": 3.154382270129956e-05, "loss": 4.3151, "step": 13610 }, { "epoch": 0.4157299938912645, "grad_norm": 0.38765430450439453, "learning_rate": 3.154150741401708e-05, "loss": 4.2333, "step": 13611 }, { "epoch": 0.4157605375687233, "grad_norm": 0.39031660556793213, "learning_rate": 3.1539192066503595e-05, "loss": 4.3854, "step": 13612 }, { "epoch": 0.415791081246182, "grad_norm": 0.37356939911842346, "learning_rate": 3.153687665878039e-05, "loss": 4.2588, "step": 13613 }, { "epoch": 0.41582162492364083, "grad_norm": 0.3735477328300476, "learning_rate": 3.1534561190868806e-05, "loss": 4.2383, "step": 13614 }, { "epoch": 0.4158521686010996, "grad_norm": 0.38872477412223816, "learning_rate": 3.153224566279016e-05, "loss": 4.3274, "step": 13615 }, { "epoch": 0.41588271227855833, "grad_norm": 0.3864476978778839, "learning_rate": 3.152993007456577e-05, "loss": 4.2696, "step": 13616 }, { "epoch": 0.4159132559560171, "grad_norm": 0.3910544812679291, "learning_rate": 3.152761442621695e-05, "loss": 4.3017, "step": 13617 }, { "epoch": 0.4159437996334759, "grad_norm": 0.39557385444641113, "learning_rate": 3.152529871776503e-05, "loss": 4.3312, "step": 13618 }, { "epoch": 0.41597434331093464, "grad_norm": 0.3885238766670227, "learning_rate": 3.152298294923133e-05, "loss": 4.2942, "step": 13619 }, { "epoch": 0.4160048869883934, "grad_norm": 0.38788723945617676, "learning_rate": 3.152066712063718e-05, "loss": 4.3383, "step": 13620 }, { "epoch": 0.4160354306658522, "grad_norm": 0.3979015052318573, "learning_rate": 3.151835123200388e-05, "loss": 4.1753, "step": 13621 }, { "epoch": 0.41606597434331094, "grad_norm": 0.38436365127563477, "learning_rate": 3.1516035283352785e-05, "loss": 4.3185, "step": 13622 }, { "epoch": 0.4160965180207697, "grad_norm": 0.39092323184013367, "learning_rate": 3.1513719274705194e-05, "loss": 4.2707, "step": 13623 }, { "epoch": 0.41612706169822844, "grad_norm": 0.38125723600387573, "learning_rate": 3.1511403206082445e-05, "loss": 4.299, "step": 13624 }, { "epoch": 0.41615760537568725, "grad_norm": 0.39636340737342834, "learning_rate": 3.150908707750585e-05, "loss": 4.3406, "step": 13625 }, { "epoch": 0.416188149053146, "grad_norm": 0.398738831281662, "learning_rate": 3.150677088899675e-05, "loss": 4.4461, "step": 13626 }, { "epoch": 0.41621869273060474, "grad_norm": 0.38331469893455505, "learning_rate": 3.150445464057647e-05, "loss": 4.2871, "step": 13627 }, { "epoch": 0.41624923640806355, "grad_norm": 0.38794952630996704, "learning_rate": 3.150213833226633e-05, "loss": 4.3249, "step": 13628 }, { "epoch": 0.4162797800855223, "grad_norm": 0.37689393758773804, "learning_rate": 3.149982196408765e-05, "loss": 4.3253, "step": 13629 }, { "epoch": 0.41631032376298105, "grad_norm": 0.39607587456703186, "learning_rate": 3.149750553606178e-05, "loss": 4.2918, "step": 13630 }, { "epoch": 0.41634086744043985, "grad_norm": 0.3795020878314972, "learning_rate": 3.1495189048210025e-05, "loss": 4.418, "step": 13631 }, { "epoch": 0.4163714111178986, "grad_norm": 0.5627872943878174, "learning_rate": 3.149287250055373e-05, "loss": 4.2889, "step": 13632 }, { "epoch": 0.41640195479535735, "grad_norm": 0.3812587857246399, "learning_rate": 3.149055589311421e-05, "loss": 4.351, "step": 13633 }, { "epoch": 0.4164324984728161, "grad_norm": 0.3760678768157959, "learning_rate": 3.1488239225912816e-05, "loss": 4.3321, "step": 13634 }, { "epoch": 0.4164630421502749, "grad_norm": 0.3994765281677246, "learning_rate": 3.148592249897087e-05, "loss": 4.3372, "step": 13635 }, { "epoch": 0.41649358582773366, "grad_norm": 0.3777006268501282, "learning_rate": 3.148360571230969e-05, "loss": 4.2943, "step": 13636 }, { "epoch": 0.4165241295051924, "grad_norm": 0.3833478093147278, "learning_rate": 3.148128886595063e-05, "loss": 4.3414, "step": 13637 }, { "epoch": 0.4165546731826512, "grad_norm": 0.3769228160381317, "learning_rate": 3.1478971959915004e-05, "loss": 4.2873, "step": 13638 }, { "epoch": 0.41658521686010996, "grad_norm": 0.37998804450035095, "learning_rate": 3.147665499422415e-05, "loss": 4.2962, "step": 13639 }, { "epoch": 0.4166157605375687, "grad_norm": 0.38931360840797424, "learning_rate": 3.147433796889941e-05, "loss": 4.3573, "step": 13640 }, { "epoch": 0.41664630421502746, "grad_norm": 0.3919069468975067, "learning_rate": 3.1472020883962114e-05, "loss": 4.2175, "step": 13641 }, { "epoch": 0.41667684789248627, "grad_norm": 0.4550771713256836, "learning_rate": 3.146970373943358e-05, "loss": 4.3521, "step": 13642 }, { "epoch": 0.416707391569945, "grad_norm": 0.3817208409309387, "learning_rate": 3.146738653533516e-05, "loss": 4.2881, "step": 13643 }, { "epoch": 0.41673793524740377, "grad_norm": 0.40206602215766907, "learning_rate": 3.146506927168821e-05, "loss": 4.2302, "step": 13644 }, { "epoch": 0.4167684789248626, "grad_norm": 0.41699668765068054, "learning_rate": 3.146275194851402e-05, "loss": 4.2409, "step": 13645 }, { "epoch": 0.4167990226023213, "grad_norm": 0.37264010310173035, "learning_rate": 3.1460434565833954e-05, "loss": 4.347, "step": 13646 }, { "epoch": 0.4168295662797801, "grad_norm": 0.38049057126045227, "learning_rate": 3.145811712366935e-05, "loss": 4.3357, "step": 13647 }, { "epoch": 0.4168601099572389, "grad_norm": 0.3796240985393524, "learning_rate": 3.145579962204153e-05, "loss": 4.2692, "step": 13648 }, { "epoch": 0.4168906536346976, "grad_norm": 0.3819185793399811, "learning_rate": 3.1453482060971854e-05, "loss": 4.218, "step": 13649 }, { "epoch": 0.4169211973121564, "grad_norm": 0.3793279528617859, "learning_rate": 3.145116444048165e-05, "loss": 4.2878, "step": 13650 }, { "epoch": 0.4169517409896151, "grad_norm": 0.375271737575531, "learning_rate": 3.144884676059226e-05, "loss": 4.2873, "step": 13651 }, { "epoch": 0.41698228466707393, "grad_norm": 0.3978530764579773, "learning_rate": 3.144652902132502e-05, "loss": 4.3237, "step": 13652 }, { "epoch": 0.4170128283445327, "grad_norm": 0.38547223806381226, "learning_rate": 3.144421122270127e-05, "loss": 4.3214, "step": 13653 }, { "epoch": 0.41704337202199143, "grad_norm": 0.3812310993671417, "learning_rate": 3.144189336474236e-05, "loss": 4.2121, "step": 13654 }, { "epoch": 0.41707391569945024, "grad_norm": 0.37316563725471497, "learning_rate": 3.143957544746962e-05, "loss": 4.3381, "step": 13655 }, { "epoch": 0.417104459376909, "grad_norm": 0.37470391392707825, "learning_rate": 3.1437257470904396e-05, "loss": 4.3545, "step": 13656 }, { "epoch": 0.41713500305436774, "grad_norm": 0.38913607597351074, "learning_rate": 3.143493943506804e-05, "loss": 4.2851, "step": 13657 }, { "epoch": 0.4171655467318265, "grad_norm": 0.39087799191474915, "learning_rate": 3.143262133998188e-05, "loss": 4.3595, "step": 13658 }, { "epoch": 0.4171960904092853, "grad_norm": 0.3922009766101837, "learning_rate": 3.1430303185667275e-05, "loss": 4.3543, "step": 13659 }, { "epoch": 0.41722663408674404, "grad_norm": 0.3833576738834381, "learning_rate": 3.142798497214556e-05, "loss": 4.2516, "step": 13660 }, { "epoch": 0.4172571777642028, "grad_norm": 0.37098804116249084, "learning_rate": 3.1425666699438086e-05, "loss": 4.2887, "step": 13661 }, { "epoch": 0.4172877214416616, "grad_norm": 0.3770352900028229, "learning_rate": 3.1423348367566186e-05, "loss": 4.2876, "step": 13662 }, { "epoch": 0.41731826511912035, "grad_norm": 0.3827498257160187, "learning_rate": 3.142102997655122e-05, "loss": 4.3135, "step": 13663 }, { "epoch": 0.4173488087965791, "grad_norm": 0.38291728496551514, "learning_rate": 3.141871152641453e-05, "loss": 4.3445, "step": 13664 }, { "epoch": 0.4173793524740379, "grad_norm": 0.3742574155330658, "learning_rate": 3.1416393017177456e-05, "loss": 4.2951, "step": 13665 }, { "epoch": 0.41740989615149665, "grad_norm": 0.38434913754463196, "learning_rate": 3.141407444886136e-05, "loss": 4.2762, "step": 13666 }, { "epoch": 0.4174404398289554, "grad_norm": 0.37724965810775757, "learning_rate": 3.141175582148759e-05, "loss": 4.2519, "step": 13667 }, { "epoch": 0.41747098350641415, "grad_norm": 0.38506779074668884, "learning_rate": 3.140943713507749e-05, "loss": 4.3186, "step": 13668 }, { "epoch": 0.41750152718387296, "grad_norm": 0.38660553097724915, "learning_rate": 3.140711838965239e-05, "loss": 4.3685, "step": 13669 }, { "epoch": 0.4175320708613317, "grad_norm": 0.37817490100860596, "learning_rate": 3.140479958523366e-05, "loss": 4.3182, "step": 13670 }, { "epoch": 0.41756261453879046, "grad_norm": 0.3865169286727905, "learning_rate": 3.140248072184265e-05, "loss": 4.298, "step": 13671 }, { "epoch": 0.41759315821624926, "grad_norm": 0.4100791811943054, "learning_rate": 3.14001617995007e-05, "loss": 4.2827, "step": 13672 }, { "epoch": 0.417623701893708, "grad_norm": 0.3857673108577728, "learning_rate": 3.1397842818229186e-05, "loss": 4.2715, "step": 13673 }, { "epoch": 0.41765424557116676, "grad_norm": 0.39238712191581726, "learning_rate": 3.1395523778049436e-05, "loss": 4.3935, "step": 13674 }, { "epoch": 0.4176847892486255, "grad_norm": 0.38801640272140503, "learning_rate": 3.139320467898281e-05, "loss": 4.3668, "step": 13675 }, { "epoch": 0.4177153329260843, "grad_norm": 0.37111231684684753, "learning_rate": 3.139088552105066e-05, "loss": 4.3149, "step": 13676 }, { "epoch": 0.41774587660354306, "grad_norm": 0.38021543622016907, "learning_rate": 3.1388566304274347e-05, "loss": 4.1826, "step": 13677 }, { "epoch": 0.4177764202810018, "grad_norm": 0.3884824216365814, "learning_rate": 3.138624702867522e-05, "loss": 4.3467, "step": 13678 }, { "epoch": 0.4178069639584606, "grad_norm": 0.3881435692310333, "learning_rate": 3.1383927694274624e-05, "loss": 4.2467, "step": 13679 }, { "epoch": 0.41783750763591937, "grad_norm": 0.3758385479450226, "learning_rate": 3.138160830109392e-05, "loss": 4.3149, "step": 13680 }, { "epoch": 0.4178680513133781, "grad_norm": 0.38817480206489563, "learning_rate": 3.137928884915448e-05, "loss": 4.3065, "step": 13681 }, { "epoch": 0.41789859499083687, "grad_norm": 0.37768319249153137, "learning_rate": 3.137696933847765e-05, "loss": 4.162, "step": 13682 }, { "epoch": 0.4179291386682957, "grad_norm": 0.3938417434692383, "learning_rate": 3.137464976908477e-05, "loss": 4.2956, "step": 13683 }, { "epoch": 0.4179596823457544, "grad_norm": 0.39907196164131165, "learning_rate": 3.1372330140997226e-05, "loss": 4.2782, "step": 13684 }, { "epoch": 0.4179902260232132, "grad_norm": 0.38966476917266846, "learning_rate": 3.137001045423635e-05, "loss": 4.2787, "step": 13685 }, { "epoch": 0.418020769700672, "grad_norm": 0.3866126537322998, "learning_rate": 3.136769070882352e-05, "loss": 4.3045, "step": 13686 }, { "epoch": 0.41805131337813073, "grad_norm": 0.3792222738265991, "learning_rate": 3.136537090478008e-05, "loss": 4.3089, "step": 13687 }, { "epoch": 0.4180818570555895, "grad_norm": 0.39959701895713806, "learning_rate": 3.136305104212741e-05, "loss": 4.2949, "step": 13688 }, { "epoch": 0.4181124007330483, "grad_norm": 0.3760717213153839, "learning_rate": 3.1360731120886846e-05, "loss": 4.4092, "step": 13689 }, { "epoch": 0.41814294441050703, "grad_norm": 0.382624089717865, "learning_rate": 3.1358411141079766e-05, "loss": 4.3542, "step": 13690 }, { "epoch": 0.4181734880879658, "grad_norm": 0.38976043462753296, "learning_rate": 3.135609110272753e-05, "loss": 4.3059, "step": 13691 }, { "epoch": 0.41820403176542453, "grad_norm": 0.38025450706481934, "learning_rate": 3.135377100585149e-05, "loss": 4.2272, "step": 13692 }, { "epoch": 0.41823457544288334, "grad_norm": 0.39112037420272827, "learning_rate": 3.135145085047301e-05, "loss": 4.3085, "step": 13693 }, { "epoch": 0.4182651191203421, "grad_norm": 0.389594167470932, "learning_rate": 3.134913063661346e-05, "loss": 4.2554, "step": 13694 }, { "epoch": 0.41829566279780084, "grad_norm": 0.3918443024158478, "learning_rate": 3.13468103642942e-05, "loss": 4.326, "step": 13695 }, { "epoch": 0.41832620647525964, "grad_norm": 0.3727697432041168, "learning_rate": 3.1344490033536586e-05, "loss": 4.3022, "step": 13696 }, { "epoch": 0.4183567501527184, "grad_norm": 0.38616037368774414, "learning_rate": 3.1342169644362e-05, "loss": 4.3599, "step": 13697 }, { "epoch": 0.41838729383017714, "grad_norm": 0.3872659504413605, "learning_rate": 3.133984919679179e-05, "loss": 4.3797, "step": 13698 }, { "epoch": 0.4184178375076359, "grad_norm": 0.39233312010765076, "learning_rate": 3.133752869084734e-05, "loss": 4.3461, "step": 13699 }, { "epoch": 0.4184483811850947, "grad_norm": 0.3866831958293915, "learning_rate": 3.1335208126549995e-05, "loss": 4.3026, "step": 13700 }, { "epoch": 0.41847892486255345, "grad_norm": 0.3797352910041809, "learning_rate": 3.133288750392114e-05, "loss": 4.3113, "step": 13701 }, { "epoch": 0.4185094685400122, "grad_norm": 0.3879055380821228, "learning_rate": 3.133056682298213e-05, "loss": 4.3364, "step": 13702 }, { "epoch": 0.418540012217471, "grad_norm": 0.3834758698940277, "learning_rate": 3.132824608375433e-05, "loss": 4.2773, "step": 13703 }, { "epoch": 0.41857055589492975, "grad_norm": 0.3789663016796112, "learning_rate": 3.132592528625912e-05, "loss": 4.2182, "step": 13704 }, { "epoch": 0.4186010995723885, "grad_norm": 0.3817206025123596, "learning_rate": 3.132360443051787e-05, "loss": 4.3393, "step": 13705 }, { "epoch": 0.4186316432498473, "grad_norm": 0.3948310911655426, "learning_rate": 3.132128351655193e-05, "loss": 4.3439, "step": 13706 }, { "epoch": 0.41866218692730606, "grad_norm": 0.4020053446292877, "learning_rate": 3.1318962544382694e-05, "loss": 4.2419, "step": 13707 }, { "epoch": 0.4186927306047648, "grad_norm": 0.3723263442516327, "learning_rate": 3.1316641514031515e-05, "loss": 4.3255, "step": 13708 }, { "epoch": 0.41872327428222356, "grad_norm": 0.37622755765914917, "learning_rate": 3.1314320425519775e-05, "loss": 4.2849, "step": 13709 }, { "epoch": 0.41875381795968236, "grad_norm": 0.3736218512058258, "learning_rate": 3.1311999278868825e-05, "loss": 4.1827, "step": 13710 }, { "epoch": 0.4187843616371411, "grad_norm": 0.3779703974723816, "learning_rate": 3.1309678074100064e-05, "loss": 4.2429, "step": 13711 }, { "epoch": 0.41881490531459986, "grad_norm": 0.3752433955669403, "learning_rate": 3.130735681123486e-05, "loss": 4.3473, "step": 13712 }, { "epoch": 0.41884544899205867, "grad_norm": 0.3829043507575989, "learning_rate": 3.130503549029457e-05, "loss": 4.3204, "step": 13713 }, { "epoch": 0.4188759926695174, "grad_norm": 0.3780815005302429, "learning_rate": 3.1302714111300576e-05, "loss": 4.3338, "step": 13714 }, { "epoch": 0.41890653634697617, "grad_norm": 0.3815411329269409, "learning_rate": 3.130039267427425e-05, "loss": 4.3043, "step": 13715 }, { "epoch": 0.4189370800244349, "grad_norm": 0.390633225440979, "learning_rate": 3.1298071179236974e-05, "loss": 4.2728, "step": 13716 }, { "epoch": 0.4189676237018937, "grad_norm": 0.3807487487792969, "learning_rate": 3.1295749626210116e-05, "loss": 4.3522, "step": 13717 }, { "epoch": 0.41899816737935247, "grad_norm": 0.38575997948646545, "learning_rate": 3.1293428015215054e-05, "loss": 4.2861, "step": 13718 }, { "epoch": 0.4190287110568112, "grad_norm": 0.41998979449272156, "learning_rate": 3.1291106346273167e-05, "loss": 4.296, "step": 13719 }, { "epoch": 0.41905925473427, "grad_norm": 0.3835280239582062, "learning_rate": 3.1288784619405827e-05, "loss": 4.2194, "step": 13720 }, { "epoch": 0.4190897984117288, "grad_norm": 0.38444072008132935, "learning_rate": 3.128646283463442e-05, "loss": 4.3133, "step": 13721 }, { "epoch": 0.4191203420891875, "grad_norm": 0.38732677698135376, "learning_rate": 3.128414099198031e-05, "loss": 4.1752, "step": 13722 }, { "epoch": 0.41915088576664633, "grad_norm": 0.3843168318271637, "learning_rate": 3.128181909146489e-05, "loss": 4.3018, "step": 13723 }, { "epoch": 0.4191814294441051, "grad_norm": 0.37941625714302063, "learning_rate": 3.127949713310952e-05, "loss": 4.3452, "step": 13724 }, { "epoch": 0.41921197312156383, "grad_norm": 0.38244807720184326, "learning_rate": 3.1277175116935606e-05, "loss": 4.3391, "step": 13725 }, { "epoch": 0.4192425167990226, "grad_norm": 0.38091665506362915, "learning_rate": 3.1274853042964505e-05, "loss": 4.242, "step": 13726 }, { "epoch": 0.4192730604764814, "grad_norm": 0.382799357175827, "learning_rate": 3.12725309112176e-05, "loss": 4.3587, "step": 13727 }, { "epoch": 0.41930360415394013, "grad_norm": 0.375006765127182, "learning_rate": 3.1270208721716286e-05, "loss": 4.2647, "step": 13728 }, { "epoch": 0.4193341478313989, "grad_norm": 0.3813117742538452, "learning_rate": 3.126788647448194e-05, "loss": 4.2672, "step": 13729 }, { "epoch": 0.4193646915088577, "grad_norm": 0.38973093032836914, "learning_rate": 3.126556416953593e-05, "loss": 4.3155, "step": 13730 }, { "epoch": 0.41939523518631644, "grad_norm": 0.3779304325580597, "learning_rate": 3.126324180689966e-05, "loss": 4.2819, "step": 13731 }, { "epoch": 0.4194257788637752, "grad_norm": 0.38267406821250916, "learning_rate": 3.12609193865945e-05, "loss": 4.2992, "step": 13732 }, { "epoch": 0.41945632254123394, "grad_norm": 0.3767436742782593, "learning_rate": 3.1258596908641836e-05, "loss": 4.2696, "step": 13733 }, { "epoch": 0.41948686621869274, "grad_norm": 0.37989476323127747, "learning_rate": 3.125627437306304e-05, "loss": 4.3384, "step": 13734 }, { "epoch": 0.4195174098961515, "grad_norm": 0.39326199889183044, "learning_rate": 3.1253951779879527e-05, "loss": 4.3025, "step": 13735 }, { "epoch": 0.41954795357361024, "grad_norm": 0.37742647528648376, "learning_rate": 3.125162912911266e-05, "loss": 4.2081, "step": 13736 }, { "epoch": 0.41957849725106905, "grad_norm": 0.3927241563796997, "learning_rate": 3.1249306420783826e-05, "loss": 4.3813, "step": 13737 }, { "epoch": 0.4196090409285278, "grad_norm": 0.3745974600315094, "learning_rate": 3.124698365491441e-05, "loss": 4.3026, "step": 13738 }, { "epoch": 0.41963958460598655, "grad_norm": 0.3816806375980377, "learning_rate": 3.1244660831525813e-05, "loss": 4.2981, "step": 13739 }, { "epoch": 0.41967012828344535, "grad_norm": 0.39375248551368713, "learning_rate": 3.124233795063941e-05, "loss": 4.2926, "step": 13740 }, { "epoch": 0.4197006719609041, "grad_norm": 0.37966907024383545, "learning_rate": 3.1240015012276584e-05, "loss": 4.1978, "step": 13741 }, { "epoch": 0.41973121563836285, "grad_norm": 0.38977164030075073, "learning_rate": 3.1237692016458744e-05, "loss": 4.2679, "step": 13742 }, { "epoch": 0.4197617593158216, "grad_norm": 0.3924221694469452, "learning_rate": 3.123536896320726e-05, "loss": 4.2308, "step": 13743 }, { "epoch": 0.4197923029932804, "grad_norm": 0.396333247423172, "learning_rate": 3.123304585254352e-05, "loss": 4.2895, "step": 13744 }, { "epoch": 0.41982284667073916, "grad_norm": 0.39061209559440613, "learning_rate": 3.1230722684488937e-05, "loss": 4.3562, "step": 13745 }, { "epoch": 0.4198533903481979, "grad_norm": 0.381736159324646, "learning_rate": 3.1228399459064886e-05, "loss": 4.2799, "step": 13746 }, { "epoch": 0.4198839340256567, "grad_norm": 0.3962095379829407, "learning_rate": 3.122607617629275e-05, "loss": 4.3964, "step": 13747 }, { "epoch": 0.41991447770311546, "grad_norm": 0.3982436954975128, "learning_rate": 3.1223752836193934e-05, "loss": 4.4249, "step": 13748 }, { "epoch": 0.4199450213805742, "grad_norm": 0.3903752565383911, "learning_rate": 3.122142943878982e-05, "loss": 4.3923, "step": 13749 }, { "epoch": 0.41997556505803296, "grad_norm": 0.3865857720375061, "learning_rate": 3.121910598410181e-05, "loss": 4.3165, "step": 13750 }, { "epoch": 0.42000610873549177, "grad_norm": 0.40116778016090393, "learning_rate": 3.1216782472151296e-05, "loss": 4.3287, "step": 13751 }, { "epoch": 0.4200366524129505, "grad_norm": 0.3847326934337616, "learning_rate": 3.121445890295966e-05, "loss": 4.2294, "step": 13752 }, { "epoch": 0.42006719609040927, "grad_norm": 0.38943052291870117, "learning_rate": 3.1212135276548324e-05, "loss": 4.2765, "step": 13753 }, { "epoch": 0.4200977397678681, "grad_norm": 0.3829839527606964, "learning_rate": 3.120981159293865e-05, "loss": 4.3589, "step": 13754 }, { "epoch": 0.4201282834453268, "grad_norm": 0.3736971318721771, "learning_rate": 3.1207487852152055e-05, "loss": 4.2609, "step": 13755 }, { "epoch": 0.42015882712278557, "grad_norm": 0.38518673181533813, "learning_rate": 3.1205164054209924e-05, "loss": 4.2723, "step": 13756 }, { "epoch": 0.4201893708002443, "grad_norm": 0.39115825295448303, "learning_rate": 3.120284019913366e-05, "loss": 4.3197, "step": 13757 }, { "epoch": 0.4202199144777031, "grad_norm": 0.3893696963787079, "learning_rate": 3.120051628694465e-05, "loss": 4.3226, "step": 13758 }, { "epoch": 0.4202504581551619, "grad_norm": 0.37579968571662903, "learning_rate": 3.1198192317664305e-05, "loss": 4.3428, "step": 13759 }, { "epoch": 0.4202810018326206, "grad_norm": 0.3875128924846649, "learning_rate": 3.119586829131402e-05, "loss": 4.2786, "step": 13760 }, { "epoch": 0.42031154551007943, "grad_norm": 0.3837607204914093, "learning_rate": 3.119354420791518e-05, "loss": 4.3394, "step": 13761 }, { "epoch": 0.4203420891875382, "grad_norm": 0.3993918299674988, "learning_rate": 3.11912200674892e-05, "loss": 4.3148, "step": 13762 }, { "epoch": 0.42037263286499693, "grad_norm": 0.40109044313430786, "learning_rate": 3.118889587005748e-05, "loss": 4.2668, "step": 13763 }, { "epoch": 0.42040317654245574, "grad_norm": 0.3757227063179016, "learning_rate": 3.11865716156414e-05, "loss": 4.3022, "step": 13764 }, { "epoch": 0.4204337202199145, "grad_norm": 0.3973754346370697, "learning_rate": 3.118424730426238e-05, "loss": 4.3247, "step": 13765 }, { "epoch": 0.42046426389737324, "grad_norm": 0.38442814350128174, "learning_rate": 3.118192293594182e-05, "loss": 4.3382, "step": 13766 }, { "epoch": 0.420494807574832, "grad_norm": 0.37924724817276, "learning_rate": 3.117959851070111e-05, "loss": 4.3621, "step": 13767 }, { "epoch": 0.4205253512522908, "grad_norm": 0.3873542547225952, "learning_rate": 3.1177274028561666e-05, "loss": 4.3523, "step": 13768 }, { "epoch": 0.42055589492974954, "grad_norm": 0.38532865047454834, "learning_rate": 3.117494948954489e-05, "loss": 4.1661, "step": 13769 }, { "epoch": 0.4205864386072083, "grad_norm": 0.3723655045032501, "learning_rate": 3.1172624893672166e-05, "loss": 4.4087, "step": 13770 }, { "epoch": 0.4206169822846671, "grad_norm": 0.3823406398296356, "learning_rate": 3.117030024096491e-05, "loss": 4.3614, "step": 13771 }, { "epoch": 0.42064752596212585, "grad_norm": 0.7097539901733398, "learning_rate": 3.116797553144453e-05, "loss": 4.3931, "step": 13772 }, { "epoch": 0.4206780696395846, "grad_norm": 0.38445526361465454, "learning_rate": 3.116565076513243e-05, "loss": 4.394, "step": 13773 }, { "epoch": 0.42070861331704335, "grad_norm": 0.3904259502887726, "learning_rate": 3.116332594205002e-05, "loss": 4.3515, "step": 13774 }, { "epoch": 0.42073915699450215, "grad_norm": 0.39887988567352295, "learning_rate": 3.116100106221869e-05, "loss": 4.2993, "step": 13775 }, { "epoch": 0.4207697006719609, "grad_norm": 0.37913069128990173, "learning_rate": 3.1158676125659856e-05, "loss": 4.3717, "step": 13776 }, { "epoch": 0.42080024434941965, "grad_norm": 0.4766010344028473, "learning_rate": 3.1156351132394934e-05, "loss": 4.3716, "step": 13777 }, { "epoch": 0.42083078802687846, "grad_norm": 0.40097805857658386, "learning_rate": 3.1154026082445306e-05, "loss": 4.342, "step": 13778 }, { "epoch": 0.4208613317043372, "grad_norm": 0.39946669340133667, "learning_rate": 3.1151700975832406e-05, "loss": 4.3942, "step": 13779 }, { "epoch": 0.42089187538179595, "grad_norm": 0.40144363045692444, "learning_rate": 3.1149375812577634e-05, "loss": 4.238, "step": 13780 }, { "epoch": 0.42092241905925476, "grad_norm": 0.37701258063316345, "learning_rate": 3.114705059270239e-05, "loss": 4.314, "step": 13781 }, { "epoch": 0.4209529627367135, "grad_norm": 0.3857269883155823, "learning_rate": 3.11447253162281e-05, "loss": 4.2317, "step": 13782 }, { "epoch": 0.42098350641417226, "grad_norm": 0.396210640668869, "learning_rate": 3.114239998317616e-05, "loss": 4.3016, "step": 13783 }, { "epoch": 0.421014050091631, "grad_norm": 0.3798621892929077, "learning_rate": 3.114007459356798e-05, "loss": 4.3003, "step": 13784 }, { "epoch": 0.4210445937690898, "grad_norm": 0.39307069778442383, "learning_rate": 3.1137749147424986e-05, "loss": 4.2273, "step": 13785 }, { "epoch": 0.42107513744654856, "grad_norm": 0.3737768530845642, "learning_rate": 3.113542364476858e-05, "loss": 4.189, "step": 13786 }, { "epoch": 0.4211056811240073, "grad_norm": 0.3904006779193878, "learning_rate": 3.113309808562016e-05, "loss": 4.35, "step": 13787 }, { "epoch": 0.4211362248014661, "grad_norm": 0.3873990476131439, "learning_rate": 3.1130772470001154e-05, "loss": 4.2949, "step": 13788 }, { "epoch": 0.42116676847892487, "grad_norm": 0.37422502040863037, "learning_rate": 3.1128446797932986e-05, "loss": 4.2403, "step": 13789 }, { "epoch": 0.4211973121563836, "grad_norm": 0.3848423659801483, "learning_rate": 3.1126121069437055e-05, "loss": 4.2911, "step": 13790 }, { "epoch": 0.42122785583384237, "grad_norm": 0.3702174127101898, "learning_rate": 3.1123795284534774e-05, "loss": 4.2833, "step": 13791 }, { "epoch": 0.4212583995113012, "grad_norm": 0.3843317925930023, "learning_rate": 3.112146944324756e-05, "loss": 4.2785, "step": 13792 }, { "epoch": 0.4212889431887599, "grad_norm": 0.3867861330509186, "learning_rate": 3.1119143545596834e-05, "loss": 4.3443, "step": 13793 }, { "epoch": 0.4213194868662187, "grad_norm": 0.3840070962905884, "learning_rate": 3.111681759160401e-05, "loss": 4.2704, "step": 13794 }, { "epoch": 0.4213500305436775, "grad_norm": 0.38501593470573425, "learning_rate": 3.111449158129049e-05, "loss": 4.3365, "step": 13795 }, { "epoch": 0.42138057422113623, "grad_norm": 0.37794360518455505, "learning_rate": 3.111216551467771e-05, "loss": 4.3182, "step": 13796 }, { "epoch": 0.421411117898595, "grad_norm": 0.37285172939300537, "learning_rate": 3.110983939178708e-05, "loss": 4.3606, "step": 13797 }, { "epoch": 0.4214416615760538, "grad_norm": 0.40802332758903503, "learning_rate": 3.110751321264001e-05, "loss": 4.2316, "step": 13798 }, { "epoch": 0.42147220525351253, "grad_norm": 0.3831760585308075, "learning_rate": 3.110518697725793e-05, "loss": 4.2778, "step": 13799 }, { "epoch": 0.4215027489309713, "grad_norm": 0.37784984707832336, "learning_rate": 3.110286068566227e-05, "loss": 4.3757, "step": 13800 }, { "epoch": 0.42153329260843003, "grad_norm": 0.3918974995613098, "learning_rate": 3.1100534337874413e-05, "loss": 4.3286, "step": 13801 }, { "epoch": 0.42156383628588884, "grad_norm": 0.39075303077697754, "learning_rate": 3.10982079339158e-05, "loss": 4.3173, "step": 13802 }, { "epoch": 0.4215943799633476, "grad_norm": 0.3933880031108856, "learning_rate": 3.1095881473807865e-05, "loss": 4.263, "step": 13803 }, { "epoch": 0.42162492364080634, "grad_norm": 0.3815034329891205, "learning_rate": 3.1093554957572005e-05, "loss": 4.2825, "step": 13804 }, { "epoch": 0.42165546731826514, "grad_norm": 0.38252896070480347, "learning_rate": 3.109122838522965e-05, "loss": 4.2215, "step": 13805 }, { "epoch": 0.4216860109957239, "grad_norm": 0.3984101116657257, "learning_rate": 3.108890175680223e-05, "loss": 4.3217, "step": 13806 }, { "epoch": 0.42171655467318264, "grad_norm": 0.37775373458862305, "learning_rate": 3.1086575072311155e-05, "loss": 4.3621, "step": 13807 }, { "epoch": 0.4217470983506414, "grad_norm": 0.3915367126464844, "learning_rate": 3.108424833177786e-05, "loss": 4.3308, "step": 13808 }, { "epoch": 0.4217776420281002, "grad_norm": 0.37064144015312195, "learning_rate": 3.1081921535223764e-05, "loss": 4.3084, "step": 13809 }, { "epoch": 0.42180818570555895, "grad_norm": 0.38949722051620483, "learning_rate": 3.1079594682670287e-05, "loss": 4.3955, "step": 13810 }, { "epoch": 0.4218387293830177, "grad_norm": 0.3927614092826843, "learning_rate": 3.1077267774138855e-05, "loss": 4.2692, "step": 13811 }, { "epoch": 0.4218692730604765, "grad_norm": 0.39234063029289246, "learning_rate": 3.107494080965089e-05, "loss": 4.3624, "step": 13812 }, { "epoch": 0.42189981673793525, "grad_norm": 0.3839914798736572, "learning_rate": 3.107261378922782e-05, "loss": 4.2578, "step": 13813 }, { "epoch": 0.421930360415394, "grad_norm": 0.3832736909389496, "learning_rate": 3.1070286712891085e-05, "loss": 4.2793, "step": 13814 }, { "epoch": 0.4219609040928528, "grad_norm": 0.3802121877670288, "learning_rate": 3.106795958066209e-05, "loss": 4.2617, "step": 13815 }, { "epoch": 0.42199144777031156, "grad_norm": 0.38455960154533386, "learning_rate": 3.1065632392562275e-05, "loss": 4.2691, "step": 13816 }, { "epoch": 0.4220219914477703, "grad_norm": 0.37190622091293335, "learning_rate": 3.106330514861306e-05, "loss": 4.2148, "step": 13817 }, { "epoch": 0.42205253512522906, "grad_norm": 0.3890424072742462, "learning_rate": 3.1060977848835884e-05, "loss": 4.3043, "step": 13818 }, { "epoch": 0.42208307880268786, "grad_norm": 0.37870463728904724, "learning_rate": 3.105865049325216e-05, "loss": 4.3957, "step": 13819 }, { "epoch": 0.4221136224801466, "grad_norm": 0.38520941138267517, "learning_rate": 3.1056323081883325e-05, "loss": 4.3254, "step": 13820 }, { "epoch": 0.42214416615760536, "grad_norm": 0.3920426070690155, "learning_rate": 3.1053995614750815e-05, "loss": 4.3941, "step": 13821 }, { "epoch": 0.42217470983506417, "grad_norm": 0.3811448812484741, "learning_rate": 3.105166809187604e-05, "loss": 4.358, "step": 13822 }, { "epoch": 0.4222052535125229, "grad_norm": 0.3816964030265808, "learning_rate": 3.1049340513280476e-05, "loss": 4.2577, "step": 13823 }, { "epoch": 0.42223579718998167, "grad_norm": 0.3952347934246063, "learning_rate": 3.1047012878985506e-05, "loss": 4.3494, "step": 13824 }, { "epoch": 0.4222663408674404, "grad_norm": 0.38631969690322876, "learning_rate": 3.104468518901258e-05, "loss": 4.4073, "step": 13825 }, { "epoch": 0.4222968845448992, "grad_norm": 0.3990066349506378, "learning_rate": 3.1042357443383125e-05, "loss": 4.3831, "step": 13826 }, { "epoch": 0.42232742822235797, "grad_norm": 0.3706313371658325, "learning_rate": 3.104002964211858e-05, "loss": 4.2886, "step": 13827 }, { "epoch": 0.4223579718998167, "grad_norm": 0.3836044669151306, "learning_rate": 3.103770178524039e-05, "loss": 4.3365, "step": 13828 }, { "epoch": 0.4223885155772755, "grad_norm": 0.37956202030181885, "learning_rate": 3.103537387276996e-05, "loss": 4.3097, "step": 13829 }, { "epoch": 0.4224190592547343, "grad_norm": 0.3896401822566986, "learning_rate": 3.103304590472874e-05, "loss": 4.3042, "step": 13830 }, { "epoch": 0.422449602932193, "grad_norm": 0.37902113795280457, "learning_rate": 3.1030717881138174e-05, "loss": 4.2926, "step": 13831 }, { "epoch": 0.4224801466096518, "grad_norm": 0.38226640224456787, "learning_rate": 3.1028389802019684e-05, "loss": 4.2859, "step": 13832 }, { "epoch": 0.4225106902871106, "grad_norm": 0.38046029210090637, "learning_rate": 3.1026061667394706e-05, "loss": 4.2747, "step": 13833 }, { "epoch": 0.42254123396456933, "grad_norm": 0.38986432552337646, "learning_rate": 3.1023733477284685e-05, "loss": 4.3469, "step": 13834 }, { "epoch": 0.4225717776420281, "grad_norm": 0.3873967230319977, "learning_rate": 3.102140523171105e-05, "loss": 4.3897, "step": 13835 }, { "epoch": 0.4226023213194869, "grad_norm": 0.390354722738266, "learning_rate": 3.1019076930695235e-05, "loss": 4.1683, "step": 13836 }, { "epoch": 0.42263286499694563, "grad_norm": 0.391538143157959, "learning_rate": 3.1016748574258694e-05, "loss": 4.3861, "step": 13837 }, { "epoch": 0.4226634086744044, "grad_norm": 0.3985884189605713, "learning_rate": 3.101442016242285e-05, "loss": 4.2919, "step": 13838 }, { "epoch": 0.4226939523518632, "grad_norm": 0.3857533931732178, "learning_rate": 3.101209169520915e-05, "loss": 4.264, "step": 13839 }, { "epoch": 0.42272449602932194, "grad_norm": 0.3918190896511078, "learning_rate": 3.100976317263903e-05, "loss": 4.3507, "step": 13840 }, { "epoch": 0.4227550397067807, "grad_norm": 0.3731010854244232, "learning_rate": 3.100743459473393e-05, "loss": 4.3784, "step": 13841 }, { "epoch": 0.42278558338423944, "grad_norm": 0.3829050064086914, "learning_rate": 3.10051059615153e-05, "loss": 4.3318, "step": 13842 }, { "epoch": 0.42281612706169824, "grad_norm": 0.388029009103775, "learning_rate": 3.100277727300455e-05, "loss": 4.2963, "step": 13843 }, { "epoch": 0.422846670739157, "grad_norm": 0.40044674277305603, "learning_rate": 3.100044852922316e-05, "loss": 4.3494, "step": 13844 }, { "epoch": 0.42287721441661574, "grad_norm": 0.3922882080078125, "learning_rate": 3.0998119730192554e-05, "loss": 4.245, "step": 13845 }, { "epoch": 0.42290775809407455, "grad_norm": 0.3885088562965393, "learning_rate": 3.099579087593417e-05, "loss": 4.3402, "step": 13846 }, { "epoch": 0.4229383017715333, "grad_norm": 0.3823850154876709, "learning_rate": 3.0993461966469466e-05, "loss": 4.3145, "step": 13847 }, { "epoch": 0.42296884544899205, "grad_norm": 0.40640026330947876, "learning_rate": 3.099113300181987e-05, "loss": 4.3913, "step": 13848 }, { "epoch": 0.4229993891264508, "grad_norm": 0.3821096122264862, "learning_rate": 3.098880398200683e-05, "loss": 4.3472, "step": 13849 }, { "epoch": 0.4230299328039096, "grad_norm": 0.37719324231147766, "learning_rate": 3.098647490705179e-05, "loss": 4.3443, "step": 13850 }, { "epoch": 0.42306047648136835, "grad_norm": 0.38996419310569763, "learning_rate": 3.098414577697621e-05, "loss": 4.3138, "step": 13851 }, { "epoch": 0.4230910201588271, "grad_norm": 0.3788265883922577, "learning_rate": 3.0981816591801516e-05, "loss": 4.2233, "step": 13852 }, { "epoch": 0.4231215638362859, "grad_norm": 0.38378211855888367, "learning_rate": 3.0979487351549154e-05, "loss": 4.3177, "step": 13853 }, { "epoch": 0.42315210751374466, "grad_norm": 0.38264015316963196, "learning_rate": 3.0977158056240586e-05, "loss": 4.373, "step": 13854 }, { "epoch": 0.4231826511912034, "grad_norm": 0.3912403881549835, "learning_rate": 3.097482870589725e-05, "loss": 4.2887, "step": 13855 }, { "epoch": 0.4232131948686622, "grad_norm": 0.3926481306552887, "learning_rate": 3.097249930054059e-05, "loss": 4.2659, "step": 13856 }, { "epoch": 0.42324373854612096, "grad_norm": 0.3802621364593506, "learning_rate": 3.0970169840192064e-05, "loss": 4.4436, "step": 13857 }, { "epoch": 0.4232742822235797, "grad_norm": 0.37621867656707764, "learning_rate": 3.096784032487312e-05, "loss": 4.3395, "step": 13858 }, { "epoch": 0.42330482590103846, "grad_norm": 0.3789106011390686, "learning_rate": 3.096551075460519e-05, "loss": 4.2448, "step": 13859 }, { "epoch": 0.42333536957849727, "grad_norm": 0.38921621441841125, "learning_rate": 3.096318112940974e-05, "loss": 4.2268, "step": 13860 }, { "epoch": 0.423365913255956, "grad_norm": 0.38076522946357727, "learning_rate": 3.096085144930821e-05, "loss": 4.3985, "step": 13861 }, { "epoch": 0.42339645693341477, "grad_norm": 0.3915345072746277, "learning_rate": 3.095852171432206e-05, "loss": 4.303, "step": 13862 }, { "epoch": 0.42342700061087357, "grad_norm": 0.3810555636882782, "learning_rate": 3.095619192447274e-05, "loss": 4.3305, "step": 13863 }, { "epoch": 0.4234575442883323, "grad_norm": 0.38735732436180115, "learning_rate": 3.095386207978169e-05, "loss": 4.3033, "step": 13864 }, { "epoch": 0.42348808796579107, "grad_norm": 0.39106929302215576, "learning_rate": 3.095153218027038e-05, "loss": 4.2767, "step": 13865 }, { "epoch": 0.4235186316432498, "grad_norm": 0.38606584072113037, "learning_rate": 3.094920222596025e-05, "loss": 4.3052, "step": 13866 }, { "epoch": 0.4235491753207086, "grad_norm": 0.3923223316669464, "learning_rate": 3.0946872216872754e-05, "loss": 4.3679, "step": 13867 }, { "epoch": 0.4235797189981674, "grad_norm": 0.3915416896343231, "learning_rate": 3.0944542153029346e-05, "loss": 4.2881, "step": 13868 }, { "epoch": 0.4236102626756261, "grad_norm": 0.3776828944683075, "learning_rate": 3.094221203445149e-05, "loss": 4.3761, "step": 13869 }, { "epoch": 0.42364080635308493, "grad_norm": 0.374859094619751, "learning_rate": 3.093988186116063e-05, "loss": 4.2441, "step": 13870 }, { "epoch": 0.4236713500305437, "grad_norm": 0.37899768352508545, "learning_rate": 3.093755163317822e-05, "loss": 4.1782, "step": 13871 }, { "epoch": 0.42370189370800243, "grad_norm": 0.40005460381507874, "learning_rate": 3.0935221350525726e-05, "loss": 4.2745, "step": 13872 }, { "epoch": 0.42373243738546124, "grad_norm": 0.3830447196960449, "learning_rate": 3.093289101322459e-05, "loss": 4.3372, "step": 13873 }, { "epoch": 0.42376298106292, "grad_norm": 0.3767755627632141, "learning_rate": 3.093056062129628e-05, "loss": 4.3043, "step": 13874 }, { "epoch": 0.42379352474037874, "grad_norm": 0.37164661288261414, "learning_rate": 3.092823017476225e-05, "loss": 4.2722, "step": 13875 }, { "epoch": 0.4238240684178375, "grad_norm": 0.3832831382751465, "learning_rate": 3.092589967364395e-05, "loss": 4.2967, "step": 13876 }, { "epoch": 0.4238546120952963, "grad_norm": 0.38565337657928467, "learning_rate": 3.0923569117962855e-05, "loss": 4.3868, "step": 13877 }, { "epoch": 0.42388515577275504, "grad_norm": 0.37421751022338867, "learning_rate": 3.092123850774041e-05, "loss": 4.329, "step": 13878 }, { "epoch": 0.4239156994502138, "grad_norm": 0.3807212710380554, "learning_rate": 3.091890784299808e-05, "loss": 4.3407, "step": 13879 }, { "epoch": 0.4239462431276726, "grad_norm": 0.4003508687019348, "learning_rate": 3.091657712375731e-05, "loss": 4.3179, "step": 13880 }, { "epoch": 0.42397678680513134, "grad_norm": 0.3845762312412262, "learning_rate": 3.0914246350039586e-05, "loss": 4.3901, "step": 13881 }, { "epoch": 0.4240073304825901, "grad_norm": 0.382194846868515, "learning_rate": 3.0911915521866356e-05, "loss": 4.3197, "step": 13882 }, { "epoch": 0.42403787416004884, "grad_norm": 0.37879306077957153, "learning_rate": 3.090958463925907e-05, "loss": 4.3302, "step": 13883 }, { "epoch": 0.42406841783750765, "grad_norm": 0.382333368062973, "learning_rate": 3.09072537022392e-05, "loss": 4.2812, "step": 13884 }, { "epoch": 0.4240989615149664, "grad_norm": 0.39168575406074524, "learning_rate": 3.090492271082821e-05, "loss": 4.2948, "step": 13885 }, { "epoch": 0.42412950519242515, "grad_norm": 0.3842875361442566, "learning_rate": 3.0902591665047566e-05, "loss": 4.2253, "step": 13886 }, { "epoch": 0.42416004886988395, "grad_norm": 0.3844941258430481, "learning_rate": 3.090026056491872e-05, "loss": 4.2768, "step": 13887 }, { "epoch": 0.4241905925473427, "grad_norm": 0.38253307342529297, "learning_rate": 3.089792941046315e-05, "loss": 4.3167, "step": 13888 }, { "epoch": 0.42422113622480145, "grad_norm": 0.3778994083404541, "learning_rate": 3.08955982017023e-05, "loss": 4.2159, "step": 13889 }, { "epoch": 0.42425167990226026, "grad_norm": 0.38429656624794006, "learning_rate": 3.089326693865765e-05, "loss": 4.2827, "step": 13890 }, { "epoch": 0.424282223579719, "grad_norm": 0.3936421871185303, "learning_rate": 3.089093562135066e-05, "loss": 4.3387, "step": 13891 }, { "epoch": 0.42431276725717776, "grad_norm": 0.3681725263595581, "learning_rate": 3.088860424980281e-05, "loss": 4.3906, "step": 13892 }, { "epoch": 0.4243433109346365, "grad_norm": 0.38510075211524963, "learning_rate": 3.088627282403554e-05, "loss": 4.3317, "step": 13893 }, { "epoch": 0.4243738546120953, "grad_norm": 0.3858751952648163, "learning_rate": 3.0883941344070336e-05, "loss": 4.3191, "step": 13894 }, { "epoch": 0.42440439828955406, "grad_norm": 0.3828544318675995, "learning_rate": 3.088160980992865e-05, "loss": 4.3403, "step": 13895 }, { "epoch": 0.4244349419670128, "grad_norm": 0.3812112510204315, "learning_rate": 3.0879278221631965e-05, "loss": 4.3819, "step": 13896 }, { "epoch": 0.4244654856444716, "grad_norm": 0.4132207930088043, "learning_rate": 3.087694657920174e-05, "loss": 4.3091, "step": 13897 }, { "epoch": 0.42449602932193037, "grad_norm": 0.38963302969932556, "learning_rate": 3.087461488265945e-05, "loss": 4.331, "step": 13898 }, { "epoch": 0.4245265729993891, "grad_norm": 0.3821425437927246, "learning_rate": 3.087228313202655e-05, "loss": 4.2218, "step": 13899 }, { "epoch": 0.42455711667684787, "grad_norm": 0.37357479333877563, "learning_rate": 3.086995132732453e-05, "loss": 4.2691, "step": 13900 }, { "epoch": 0.4245876603543067, "grad_norm": 0.3860384225845337, "learning_rate": 3.0867619468574846e-05, "loss": 4.2906, "step": 13901 }, { "epoch": 0.4246182040317654, "grad_norm": 0.3818204700946808, "learning_rate": 3.086528755579898e-05, "loss": 4.3518, "step": 13902 }, { "epoch": 0.4246487477092242, "grad_norm": 0.39024636149406433, "learning_rate": 3.086295558901839e-05, "loss": 4.3236, "step": 13903 }, { "epoch": 0.424679291386683, "grad_norm": 0.39495986700057983, "learning_rate": 3.0860623568254553e-05, "loss": 4.294, "step": 13904 }, { "epoch": 0.4247098350641417, "grad_norm": 0.39176931977272034, "learning_rate": 3.085829149352894e-05, "loss": 4.3044, "step": 13905 }, { "epoch": 0.4247403787416005, "grad_norm": 0.3790483772754669, "learning_rate": 3.085595936486303e-05, "loss": 4.2778, "step": 13906 }, { "epoch": 0.4247709224190592, "grad_norm": 0.38047441840171814, "learning_rate": 3.085362718227829e-05, "loss": 4.252, "step": 13907 }, { "epoch": 0.42480146609651803, "grad_norm": 0.3763880729675293, "learning_rate": 3.085129494579619e-05, "loss": 4.3313, "step": 13908 }, { "epoch": 0.4248320097739768, "grad_norm": 0.38402897119522095, "learning_rate": 3.084896265543821e-05, "loss": 4.323, "step": 13909 }, { "epoch": 0.42486255345143553, "grad_norm": 0.4682365953922272, "learning_rate": 3.084663031122583e-05, "loss": 4.3384, "step": 13910 }, { "epoch": 0.42489309712889434, "grad_norm": 0.377053827047348, "learning_rate": 3.084429791318051e-05, "loss": 4.3767, "step": 13911 }, { "epoch": 0.4249236408063531, "grad_norm": 0.4020705223083496, "learning_rate": 3.084196546132375e-05, "loss": 4.2587, "step": 13912 }, { "epoch": 0.42495418448381184, "grad_norm": 0.3776569366455078, "learning_rate": 3.0839632955676994e-05, "loss": 4.2732, "step": 13913 }, { "epoch": 0.42498472816127064, "grad_norm": 0.40108397603034973, "learning_rate": 3.0837300396261735e-05, "loss": 4.3307, "step": 13914 }, { "epoch": 0.4250152718387294, "grad_norm": 0.3743003308773041, "learning_rate": 3.083496778309946e-05, "loss": 4.3432, "step": 13915 }, { "epoch": 0.42504581551618814, "grad_norm": 0.3824383318424225, "learning_rate": 3.0832635116211636e-05, "loss": 4.213, "step": 13916 }, { "epoch": 0.4250763591936469, "grad_norm": 0.3908652067184448, "learning_rate": 3.0830302395619736e-05, "loss": 4.3643, "step": 13917 }, { "epoch": 0.4251069028711057, "grad_norm": 0.39929690957069397, "learning_rate": 3.0827969621345246e-05, "loss": 4.3778, "step": 13918 }, { "epoch": 0.42513744654856445, "grad_norm": 0.3794640600681305, "learning_rate": 3.0825636793409646e-05, "loss": 4.1941, "step": 13919 }, { "epoch": 0.4251679902260232, "grad_norm": 0.3847818970680237, "learning_rate": 3.082330391183441e-05, "loss": 4.3529, "step": 13920 }, { "epoch": 0.425198533903482, "grad_norm": 0.3815288245677948, "learning_rate": 3.0820970976641016e-05, "loss": 4.2709, "step": 13921 }, { "epoch": 0.42522907758094075, "grad_norm": 0.369049072265625, "learning_rate": 3.081863798785096e-05, "loss": 4.3349, "step": 13922 }, { "epoch": 0.4252596212583995, "grad_norm": 0.38715893030166626, "learning_rate": 3.0816304945485704e-05, "loss": 4.1992, "step": 13923 }, { "epoch": 0.42529016493585825, "grad_norm": 0.38707926869392395, "learning_rate": 3.081397184956674e-05, "loss": 4.263, "step": 13924 }, { "epoch": 0.42532070861331706, "grad_norm": 0.39175552129745483, "learning_rate": 3.0811638700115556e-05, "loss": 4.3861, "step": 13925 }, { "epoch": 0.4253512522907758, "grad_norm": 0.3894132375717163, "learning_rate": 3.080930549715361e-05, "loss": 4.3976, "step": 13926 }, { "epoch": 0.42538179596823456, "grad_norm": 0.3867655396461487, "learning_rate": 3.080697224070241e-05, "loss": 4.2511, "step": 13927 }, { "epoch": 0.42541233964569336, "grad_norm": 0.3818444311618805, "learning_rate": 3.080463893078343e-05, "loss": 4.288, "step": 13928 }, { "epoch": 0.4254428833231521, "grad_norm": 0.38418588042259216, "learning_rate": 3.080230556741816e-05, "loss": 4.3709, "step": 13929 }, { "epoch": 0.42547342700061086, "grad_norm": 0.3888913094997406, "learning_rate": 3.079997215062808e-05, "loss": 4.2711, "step": 13930 }, { "epoch": 0.42550397067806967, "grad_norm": 0.37975794076919556, "learning_rate": 3.079763868043466e-05, "loss": 4.275, "step": 13931 }, { "epoch": 0.4255345143555284, "grad_norm": 0.3874461054801941, "learning_rate": 3.079530515685941e-05, "loss": 4.323, "step": 13932 }, { "epoch": 0.42556505803298716, "grad_norm": 0.40355050563812256, "learning_rate": 3.079297157992381e-05, "loss": 4.2183, "step": 13933 }, { "epoch": 0.4255956017104459, "grad_norm": 0.3996969163417816, "learning_rate": 3.079063794964934e-05, "loss": 4.4, "step": 13934 }, { "epoch": 0.4256261453879047, "grad_norm": 0.38647180795669556, "learning_rate": 3.078830426605749e-05, "loss": 4.2063, "step": 13935 }, { "epoch": 0.42565668906536347, "grad_norm": 0.38922441005706787, "learning_rate": 3.078597052916974e-05, "loss": 4.252, "step": 13936 }, { "epoch": 0.4256872327428222, "grad_norm": 0.37843045592308044, "learning_rate": 3.078363673900759e-05, "loss": 4.2713, "step": 13937 }, { "epoch": 0.425717776420281, "grad_norm": 0.37267783284187317, "learning_rate": 3.0781302895592514e-05, "loss": 4.3638, "step": 13938 }, { "epoch": 0.4257483200977398, "grad_norm": 0.37124112248420715, "learning_rate": 3.077896899894602e-05, "loss": 4.2034, "step": 13939 }, { "epoch": 0.4257788637751985, "grad_norm": 0.38036924600601196, "learning_rate": 3.0776635049089586e-05, "loss": 4.329, "step": 13940 }, { "epoch": 0.4258094074526573, "grad_norm": 0.38629594445228577, "learning_rate": 3.07743010460447e-05, "loss": 4.3389, "step": 13941 }, { "epoch": 0.4258399511301161, "grad_norm": 0.3753962516784668, "learning_rate": 3.077196698983286e-05, "loss": 4.3588, "step": 13942 }, { "epoch": 0.42587049480757483, "grad_norm": 0.38408613204956055, "learning_rate": 3.076963288047555e-05, "loss": 4.2789, "step": 13943 }, { "epoch": 0.4259010384850336, "grad_norm": 0.3898811638355255, "learning_rate": 3.076729871799426e-05, "loss": 4.2992, "step": 13944 }, { "epoch": 0.4259315821624924, "grad_norm": 0.381216436624527, "learning_rate": 3.076496450241048e-05, "loss": 4.2861, "step": 13945 }, { "epoch": 0.42596212583995113, "grad_norm": 0.37792903184890747, "learning_rate": 3.076263023374572e-05, "loss": 4.2013, "step": 13946 }, { "epoch": 0.4259926695174099, "grad_norm": 0.37311941385269165, "learning_rate": 3.076029591202145e-05, "loss": 4.2716, "step": 13947 }, { "epoch": 0.4260232131948687, "grad_norm": 0.38527771830558777, "learning_rate": 3.075796153725918e-05, "loss": 4.28, "step": 13948 }, { "epoch": 0.42605375687232744, "grad_norm": 0.3781599700450897, "learning_rate": 3.0755627109480406e-05, "loss": 4.2866, "step": 13949 }, { "epoch": 0.4260843005497862, "grad_norm": 0.3797016441822052, "learning_rate": 3.07532926287066e-05, "loss": 4.3264, "step": 13950 }, { "epoch": 0.42611484422724494, "grad_norm": 0.378251314163208, "learning_rate": 3.075095809495928e-05, "loss": 4.3725, "step": 13951 }, { "epoch": 0.42614538790470374, "grad_norm": 0.3812756836414337, "learning_rate": 3.0748623508259926e-05, "loss": 4.3711, "step": 13952 }, { "epoch": 0.4261759315821625, "grad_norm": 0.3901796340942383, "learning_rate": 3.074628886863004e-05, "loss": 4.27, "step": 13953 }, { "epoch": 0.42620647525962124, "grad_norm": 0.3735169768333435, "learning_rate": 3.074395417609112e-05, "loss": 4.3057, "step": 13954 }, { "epoch": 0.42623701893708005, "grad_norm": 0.37973055243492126, "learning_rate": 3.074161943066466e-05, "loss": 4.3395, "step": 13955 }, { "epoch": 0.4262675626145388, "grad_norm": 0.36915192008018494, "learning_rate": 3.073928463237217e-05, "loss": 4.2835, "step": 13956 }, { "epoch": 0.42629810629199755, "grad_norm": 0.38198205828666687, "learning_rate": 3.073694978123512e-05, "loss": 4.3426, "step": 13957 }, { "epoch": 0.4263286499694563, "grad_norm": 0.3749842941761017, "learning_rate": 3.0734614877275026e-05, "loss": 4.3541, "step": 13958 }, { "epoch": 0.4263591936469151, "grad_norm": 0.37603330612182617, "learning_rate": 3.073227992051339e-05, "loss": 4.3187, "step": 13959 }, { "epoch": 0.42638973732437385, "grad_norm": 0.38651415705680847, "learning_rate": 3.0729944910971696e-05, "loss": 4.2127, "step": 13960 }, { "epoch": 0.4264202810018326, "grad_norm": 0.38163843750953674, "learning_rate": 3.072760984867146e-05, "loss": 4.3572, "step": 13961 }, { "epoch": 0.4264508246792914, "grad_norm": 0.38637039065361023, "learning_rate": 3.0725274733634166e-05, "loss": 4.3016, "step": 13962 }, { "epoch": 0.42648136835675016, "grad_norm": 0.37552350759506226, "learning_rate": 3.0722939565881337e-05, "loss": 4.2484, "step": 13963 }, { "epoch": 0.4265119120342089, "grad_norm": 0.4034390151500702, "learning_rate": 3.072060434543446e-05, "loss": 4.2534, "step": 13964 }, { "epoch": 0.4265424557116677, "grad_norm": 0.38458216190338135, "learning_rate": 3.0718269072315033e-05, "loss": 4.351, "step": 13965 }, { "epoch": 0.42657299938912646, "grad_norm": 0.3763895034790039, "learning_rate": 3.071593374654456e-05, "loss": 4.2561, "step": 13966 }, { "epoch": 0.4266035430665852, "grad_norm": 0.38429713249206543, "learning_rate": 3.071359836814455e-05, "loss": 4.3291, "step": 13967 }, { "epoch": 0.42663408674404396, "grad_norm": 0.39596402645111084, "learning_rate": 3.0711262937136505e-05, "loss": 4.3324, "step": 13968 }, { "epoch": 0.42666463042150277, "grad_norm": 0.39373087882995605, "learning_rate": 3.0708927453541915e-05, "loss": 4.2343, "step": 13969 }, { "epoch": 0.4266951740989615, "grad_norm": 0.377252995967865, "learning_rate": 3.0706591917382304e-05, "loss": 4.2994, "step": 13970 }, { "epoch": 0.42672571777642027, "grad_norm": 0.3868178129196167, "learning_rate": 3.0704256328679165e-05, "loss": 4.3, "step": 13971 }, { "epoch": 0.42675626145387907, "grad_norm": 0.3915315270423889, "learning_rate": 3.0701920687454006e-05, "loss": 4.2717, "step": 13972 }, { "epoch": 0.4267868051313378, "grad_norm": 0.388344943523407, "learning_rate": 3.069958499372833e-05, "loss": 4.2354, "step": 13973 }, { "epoch": 0.42681734880879657, "grad_norm": 0.3875374495983124, "learning_rate": 3.069724924752365e-05, "loss": 4.3273, "step": 13974 }, { "epoch": 0.4268478924862553, "grad_norm": 0.3877227306365967, "learning_rate": 3.069491344886146e-05, "loss": 4.2956, "step": 13975 }, { "epoch": 0.4268784361637141, "grad_norm": 0.39525946974754333, "learning_rate": 3.0692577597763276e-05, "loss": 4.2984, "step": 13976 }, { "epoch": 0.4269089798411729, "grad_norm": 0.43468669056892395, "learning_rate": 3.06902416942506e-05, "loss": 4.3066, "step": 13977 }, { "epoch": 0.4269395235186316, "grad_norm": 0.3883778750896454, "learning_rate": 3.068790573834495e-05, "loss": 4.313, "step": 13978 }, { "epoch": 0.42697006719609043, "grad_norm": 0.37542983889579773, "learning_rate": 3.068556973006782e-05, "loss": 4.3031, "step": 13979 }, { "epoch": 0.4270006108735492, "grad_norm": 0.3886047899723053, "learning_rate": 3.0683233669440735e-05, "loss": 4.2765, "step": 13980 }, { "epoch": 0.42703115455100793, "grad_norm": 0.3800324499607086, "learning_rate": 3.068089755648519e-05, "loss": 4.3057, "step": 13981 }, { "epoch": 0.42706169822846674, "grad_norm": 0.3863528370857239, "learning_rate": 3.067856139122269e-05, "loss": 4.4427, "step": 13982 }, { "epoch": 0.4270922419059255, "grad_norm": 0.39567264914512634, "learning_rate": 3.067622517367477e-05, "loss": 4.2956, "step": 13983 }, { "epoch": 0.42712278558338423, "grad_norm": 0.3901180922985077, "learning_rate": 3.067388890386293e-05, "loss": 4.2168, "step": 13984 }, { "epoch": 0.427153329260843, "grad_norm": 0.3911009728908539, "learning_rate": 3.067155258180867e-05, "loss": 4.3548, "step": 13985 }, { "epoch": 0.4271838729383018, "grad_norm": 0.39926597476005554, "learning_rate": 3.06692162075335e-05, "loss": 4.3416, "step": 13986 }, { "epoch": 0.42721441661576054, "grad_norm": 0.3881482779979706, "learning_rate": 3.066687978105895e-05, "loss": 4.3371, "step": 13987 }, { "epoch": 0.4272449602932193, "grad_norm": 0.39050793647766113, "learning_rate": 3.066454330240654e-05, "loss": 4.4186, "step": 13988 }, { "epoch": 0.4272755039706781, "grad_norm": 0.38290271162986755, "learning_rate": 3.066220677159775e-05, "loss": 4.4008, "step": 13989 }, { "epoch": 0.42730604764813684, "grad_norm": 0.37547552585601807, "learning_rate": 3.065987018865411e-05, "loss": 4.3024, "step": 13990 }, { "epoch": 0.4273365913255956, "grad_norm": 0.3863029181957245, "learning_rate": 3.0657533553597146e-05, "loss": 4.3405, "step": 13991 }, { "epoch": 0.42736713500305434, "grad_norm": 0.38514652848243713, "learning_rate": 3.065519686644835e-05, "loss": 4.4039, "step": 13992 }, { "epoch": 0.42739767868051315, "grad_norm": 0.3863082826137543, "learning_rate": 3.065286012722926e-05, "loss": 4.3916, "step": 13993 }, { "epoch": 0.4274282223579719, "grad_norm": 0.38818076252937317, "learning_rate": 3.0650523335961365e-05, "loss": 4.3235, "step": 13994 }, { "epoch": 0.42745876603543065, "grad_norm": 0.3912605941295624, "learning_rate": 3.064818649266621e-05, "loss": 4.3555, "step": 13995 }, { "epoch": 0.42748930971288945, "grad_norm": 0.376414030790329, "learning_rate": 3.0645849597365295e-05, "loss": 4.3221, "step": 13996 }, { "epoch": 0.4275198533903482, "grad_norm": 0.3921084702014923, "learning_rate": 3.064351265008013e-05, "loss": 4.2398, "step": 13997 }, { "epoch": 0.42755039706780695, "grad_norm": 0.36844730377197266, "learning_rate": 3.064117565083226e-05, "loss": 4.296, "step": 13998 }, { "epoch": 0.4275809407452657, "grad_norm": 0.39044785499572754, "learning_rate": 3.063883859964318e-05, "loss": 4.3179, "step": 13999 }, { "epoch": 0.4276114844227245, "grad_norm": 0.3832925260066986, "learning_rate": 3.063650149653441e-05, "loss": 4.3074, "step": 14000 }, { "epoch": 0.42764202810018326, "grad_norm": 0.3876400291919708, "learning_rate": 3.0634164341527466e-05, "loss": 4.3299, "step": 14001 }, { "epoch": 0.427672571777642, "grad_norm": 0.38686296343803406, "learning_rate": 3.0631827134643884e-05, "loss": 4.2873, "step": 14002 }, { "epoch": 0.4277031154551008, "grad_norm": 0.3899146318435669, "learning_rate": 3.062948987590517e-05, "loss": 4.1588, "step": 14003 }, { "epoch": 0.42773365913255956, "grad_norm": 0.3754314184188843, "learning_rate": 3.062715256533285e-05, "loss": 4.3398, "step": 14004 }, { "epoch": 0.4277642028100183, "grad_norm": 0.38118597865104675, "learning_rate": 3.062481520294844e-05, "loss": 4.3611, "step": 14005 }, { "epoch": 0.4277947464874771, "grad_norm": 0.3920620083808899, "learning_rate": 3.062247778877347e-05, "loss": 4.2345, "step": 14006 }, { "epoch": 0.42782529016493587, "grad_norm": 0.3996249735355377, "learning_rate": 3.062014032282945e-05, "loss": 4.2013, "step": 14007 }, { "epoch": 0.4278558338423946, "grad_norm": 0.3808094263076782, "learning_rate": 3.0617802805137914e-05, "loss": 4.2237, "step": 14008 }, { "epoch": 0.42788637751985337, "grad_norm": 0.3806957006454468, "learning_rate": 3.0615465235720375e-05, "loss": 4.3952, "step": 14009 }, { "epoch": 0.4279169211973122, "grad_norm": 0.3868758976459503, "learning_rate": 3.061312761459836e-05, "loss": 4.2886, "step": 14010 }, { "epoch": 0.4279474648747709, "grad_norm": 0.4014315903186798, "learning_rate": 3.06107899417934e-05, "loss": 4.249, "step": 14011 }, { "epoch": 0.42797800855222967, "grad_norm": 0.3823293149471283, "learning_rate": 3.060845221732701e-05, "loss": 4.3152, "step": 14012 }, { "epoch": 0.4280085522296885, "grad_norm": 0.3951377272605896, "learning_rate": 3.060611444122071e-05, "loss": 4.2954, "step": 14013 }, { "epoch": 0.4280390959071472, "grad_norm": 0.5204219222068787, "learning_rate": 3.060377661349604e-05, "loss": 4.2225, "step": 14014 }, { "epoch": 0.428069639584606, "grad_norm": 0.40478071570396423, "learning_rate": 3.060143873417451e-05, "loss": 4.2926, "step": 14015 }, { "epoch": 0.4281001832620647, "grad_norm": 0.3846745491027832, "learning_rate": 3.059910080327766e-05, "loss": 4.2841, "step": 14016 }, { "epoch": 0.42813072693952353, "grad_norm": 0.38637441396713257, "learning_rate": 3.0596762820827e-05, "loss": 4.2914, "step": 14017 }, { "epoch": 0.4281612706169823, "grad_norm": 0.38861775398254395, "learning_rate": 3.059442478684408e-05, "loss": 4.311, "step": 14018 }, { "epoch": 0.42819181429444103, "grad_norm": 0.3906726837158203, "learning_rate": 3.0592086701350405e-05, "loss": 4.3057, "step": 14019 }, { "epoch": 0.42822235797189984, "grad_norm": 0.38560888171195984, "learning_rate": 3.058974856436752e-05, "loss": 4.2765, "step": 14020 }, { "epoch": 0.4282529016493586, "grad_norm": 0.3863850235939026, "learning_rate": 3.058741037591695e-05, "loss": 4.2993, "step": 14021 }, { "epoch": 0.42828344532681734, "grad_norm": 0.37949392199516296, "learning_rate": 3.058507213602021e-05, "loss": 4.1953, "step": 14022 }, { "epoch": 0.42831398900427614, "grad_norm": 0.3771493136882782, "learning_rate": 3.0582733844698834e-05, "loss": 4.3496, "step": 14023 }, { "epoch": 0.4283445326817349, "grad_norm": 0.37846869230270386, "learning_rate": 3.0580395501974367e-05, "loss": 4.3384, "step": 14024 }, { "epoch": 0.42837507635919364, "grad_norm": 0.39403843879699707, "learning_rate": 3.057805710786833e-05, "loss": 4.225, "step": 14025 }, { "epoch": 0.4284056200366524, "grad_norm": 0.3749949336051941, "learning_rate": 3.057571866240225e-05, "loss": 4.243, "step": 14026 }, { "epoch": 0.4284361637141112, "grad_norm": 0.39032992720603943, "learning_rate": 3.0573380165597665e-05, "loss": 4.3434, "step": 14027 }, { "epoch": 0.42846670739156995, "grad_norm": 0.39097511768341064, "learning_rate": 3.05710416174761e-05, "loss": 4.3092, "step": 14028 }, { "epoch": 0.4284972510690287, "grad_norm": 0.3807232677936554, "learning_rate": 3.0568703018059094e-05, "loss": 4.3418, "step": 14029 }, { "epoch": 0.4285277947464875, "grad_norm": 0.3843756914138794, "learning_rate": 3.056636436736817e-05, "loss": 4.3495, "step": 14030 }, { "epoch": 0.42855833842394625, "grad_norm": 0.37295103073120117, "learning_rate": 3.056402566542487e-05, "loss": 4.2883, "step": 14031 }, { "epoch": 0.428588882101405, "grad_norm": 0.39516615867614746, "learning_rate": 3.056168691225073e-05, "loss": 4.2705, "step": 14032 }, { "epoch": 0.42861942577886375, "grad_norm": 0.6891725063323975, "learning_rate": 3.0559348107867276e-05, "loss": 4.2874, "step": 14033 }, { "epoch": 0.42864996945632255, "grad_norm": 0.39125773310661316, "learning_rate": 3.0557009252296045e-05, "loss": 4.3449, "step": 14034 }, { "epoch": 0.4286805131337813, "grad_norm": 0.3888074457645416, "learning_rate": 3.0554670345558575e-05, "loss": 4.2732, "step": 14035 }, { "epoch": 0.42871105681124005, "grad_norm": 0.40281838178634644, "learning_rate": 3.055233138767639e-05, "loss": 4.2564, "step": 14036 }, { "epoch": 0.42874160048869886, "grad_norm": 0.4041851758956909, "learning_rate": 3.054999237867104e-05, "loss": 4.3584, "step": 14037 }, { "epoch": 0.4287721441661576, "grad_norm": 0.388894647359848, "learning_rate": 3.0547653318564054e-05, "loss": 4.2039, "step": 14038 }, { "epoch": 0.42880268784361636, "grad_norm": 0.3951820135116577, "learning_rate": 3.054531420737698e-05, "loss": 4.3022, "step": 14039 }, { "epoch": 0.42883323152107516, "grad_norm": 0.38504931330680847, "learning_rate": 3.054297504513134e-05, "loss": 4.2885, "step": 14040 }, { "epoch": 0.4288637751985339, "grad_norm": 0.3883126974105835, "learning_rate": 3.054063583184869e-05, "loss": 4.2823, "step": 14041 }, { "epoch": 0.42889431887599266, "grad_norm": 0.368168443441391, "learning_rate": 3.053829656755054e-05, "loss": 4.3834, "step": 14042 }, { "epoch": 0.4289248625534514, "grad_norm": 0.3808623254299164, "learning_rate": 3.053595725225846e-05, "loss": 4.3307, "step": 14043 }, { "epoch": 0.4289554062309102, "grad_norm": 0.3897000849246979, "learning_rate": 3.053361788599397e-05, "loss": 4.3057, "step": 14044 }, { "epoch": 0.42898594990836897, "grad_norm": 0.3827228546142578, "learning_rate": 3.053127846877861e-05, "loss": 4.3227, "step": 14045 }, { "epoch": 0.4290164935858277, "grad_norm": 0.3906480371952057, "learning_rate": 3.052893900063394e-05, "loss": 4.3223, "step": 14046 }, { "epoch": 0.4290470372632865, "grad_norm": 0.3803005814552307, "learning_rate": 3.052659948158146e-05, "loss": 4.3101, "step": 14047 }, { "epoch": 0.4290775809407453, "grad_norm": 0.37907102704048157, "learning_rate": 3.052425991164276e-05, "loss": 4.3665, "step": 14048 }, { "epoch": 0.429108124618204, "grad_norm": 0.38035067915916443, "learning_rate": 3.052192029083936e-05, "loss": 4.2858, "step": 14049 }, { "epoch": 0.4291386682956628, "grad_norm": 0.3905554711818695, "learning_rate": 3.051958061919279e-05, "loss": 4.3639, "step": 14050 }, { "epoch": 0.4291692119731216, "grad_norm": 0.3784732520580292, "learning_rate": 3.0517240896724602e-05, "loss": 4.2891, "step": 14051 }, { "epoch": 0.42919975565058033, "grad_norm": 0.3886611759662628, "learning_rate": 3.0514901123456347e-05, "loss": 4.2488, "step": 14052 }, { "epoch": 0.4292302993280391, "grad_norm": 0.37896728515625, "learning_rate": 3.051256129940956e-05, "loss": 4.3673, "step": 14053 }, { "epoch": 0.4292608430054979, "grad_norm": 0.38253337144851685, "learning_rate": 3.0510221424605784e-05, "loss": 4.3648, "step": 14054 }, { "epoch": 0.42929138668295663, "grad_norm": 0.39600521326065063, "learning_rate": 3.0507881499066572e-05, "loss": 4.368, "step": 14055 }, { "epoch": 0.4293219303604154, "grad_norm": 0.3852419853210449, "learning_rate": 3.0505541522813458e-05, "loss": 4.3466, "step": 14056 }, { "epoch": 0.4293524740378742, "grad_norm": 0.3766823709011078, "learning_rate": 3.0503201495867994e-05, "loss": 4.2991, "step": 14057 }, { "epoch": 0.42938301771533294, "grad_norm": 0.37718018889427185, "learning_rate": 3.0500861418251725e-05, "loss": 4.248, "step": 14058 }, { "epoch": 0.4294135613927917, "grad_norm": 0.40659502148628235, "learning_rate": 3.04985212899862e-05, "loss": 4.3304, "step": 14059 }, { "epoch": 0.42944410507025044, "grad_norm": 0.39519160985946655, "learning_rate": 3.0496181111092958e-05, "loss": 4.2106, "step": 14060 }, { "epoch": 0.42947464874770924, "grad_norm": 0.38532552123069763, "learning_rate": 3.0493840881593544e-05, "loss": 4.2959, "step": 14061 }, { "epoch": 0.429505192425168, "grad_norm": 0.3770405352115631, "learning_rate": 3.0491500601509522e-05, "loss": 4.2919, "step": 14062 }, { "epoch": 0.42953573610262674, "grad_norm": 0.3873133957386017, "learning_rate": 3.0489160270862427e-05, "loss": 4.2927, "step": 14063 }, { "epoch": 0.42956627978008555, "grad_norm": 0.37614551186561584, "learning_rate": 3.0486819889673805e-05, "loss": 4.2917, "step": 14064 }, { "epoch": 0.4295968234575443, "grad_norm": 0.3829363286495209, "learning_rate": 3.048447945796522e-05, "loss": 4.2765, "step": 14065 }, { "epoch": 0.42962736713500305, "grad_norm": 0.3792252242565155, "learning_rate": 3.0482138975758223e-05, "loss": 4.382, "step": 14066 }, { "epoch": 0.4296579108124618, "grad_norm": 0.37529900670051575, "learning_rate": 3.0479798443074343e-05, "loss": 4.308, "step": 14067 }, { "epoch": 0.4296884544899206, "grad_norm": 0.3773537278175354, "learning_rate": 3.0477457859935133e-05, "loss": 4.3703, "step": 14068 }, { "epoch": 0.42971899816737935, "grad_norm": 0.38144123554229736, "learning_rate": 3.047511722636216e-05, "loss": 4.316, "step": 14069 }, { "epoch": 0.4297495418448381, "grad_norm": 0.38206589221954346, "learning_rate": 3.047277654237697e-05, "loss": 4.2949, "step": 14070 }, { "epoch": 0.4297800855222969, "grad_norm": 0.3977736830711365, "learning_rate": 3.04704358080011e-05, "loss": 4.2791, "step": 14071 }, { "epoch": 0.42981062919975566, "grad_norm": 0.39157775044441223, "learning_rate": 3.0468095023256127e-05, "loss": 4.373, "step": 14072 }, { "epoch": 0.4298411728772144, "grad_norm": 0.379555881023407, "learning_rate": 3.0465754188163592e-05, "loss": 4.3865, "step": 14073 }, { "epoch": 0.42987171655467316, "grad_norm": 0.3890276253223419, "learning_rate": 3.0463413302745048e-05, "loss": 4.2914, "step": 14074 }, { "epoch": 0.42990226023213196, "grad_norm": 0.3770025670528412, "learning_rate": 3.0461072367022048e-05, "loss": 4.3508, "step": 14075 }, { "epoch": 0.4299328039095907, "grad_norm": 0.373028427362442, "learning_rate": 3.0458731381016143e-05, "loss": 4.3075, "step": 14076 }, { "epoch": 0.42996334758704946, "grad_norm": 0.37617218494415283, "learning_rate": 3.0456390344748896e-05, "loss": 4.3922, "step": 14077 }, { "epoch": 0.42999389126450827, "grad_norm": 0.384449303150177, "learning_rate": 3.045404925824185e-05, "loss": 4.2458, "step": 14078 }, { "epoch": 0.430024434941967, "grad_norm": 0.38314762711524963, "learning_rate": 3.0451708121516577e-05, "loss": 4.322, "step": 14079 }, { "epoch": 0.43005497861942577, "grad_norm": 0.3832378089427948, "learning_rate": 3.044936693459462e-05, "loss": 4.4181, "step": 14080 }, { "epoch": 0.43008552229688457, "grad_norm": 0.38177862763404846, "learning_rate": 3.0447025697497544e-05, "loss": 4.3021, "step": 14081 }, { "epoch": 0.4301160659743433, "grad_norm": 0.3975023627281189, "learning_rate": 3.04446844102469e-05, "loss": 4.3007, "step": 14082 }, { "epoch": 0.43014660965180207, "grad_norm": 0.3821839988231659, "learning_rate": 3.0442343072864243e-05, "loss": 4.263, "step": 14083 }, { "epoch": 0.4301771533292608, "grad_norm": 0.3831779658794403, "learning_rate": 3.044000168537114e-05, "loss": 4.4142, "step": 14084 }, { "epoch": 0.4302076970067196, "grad_norm": 0.3768845200538635, "learning_rate": 3.0437660247789133e-05, "loss": 4.297, "step": 14085 }, { "epoch": 0.4302382406841784, "grad_norm": 0.3861580789089203, "learning_rate": 3.0435318760139807e-05, "loss": 4.3156, "step": 14086 }, { "epoch": 0.4302687843616371, "grad_norm": 0.3840194344520569, "learning_rate": 3.0432977222444705e-05, "loss": 4.3127, "step": 14087 }, { "epoch": 0.43029932803909593, "grad_norm": 0.3870672285556793, "learning_rate": 3.043063563472538e-05, "loss": 4.3316, "step": 14088 }, { "epoch": 0.4303298717165547, "grad_norm": 0.37561923265457153, "learning_rate": 3.042829399700341e-05, "loss": 4.3025, "step": 14089 }, { "epoch": 0.43036041539401343, "grad_norm": 0.384327232837677, "learning_rate": 3.0425952309300344e-05, "loss": 4.2463, "step": 14090 }, { "epoch": 0.4303909590714722, "grad_norm": 0.3824513256549835, "learning_rate": 3.042361057163774e-05, "loss": 4.3419, "step": 14091 }, { "epoch": 0.430421502748931, "grad_norm": 0.3880193829536438, "learning_rate": 3.0421268784037164e-05, "loss": 4.2878, "step": 14092 }, { "epoch": 0.43045204642638973, "grad_norm": 0.38203927874565125, "learning_rate": 3.041892694652018e-05, "loss": 4.4168, "step": 14093 }, { "epoch": 0.4304825901038485, "grad_norm": 0.3776055574417114, "learning_rate": 3.041658505910836e-05, "loss": 4.3448, "step": 14094 }, { "epoch": 0.4305131337813073, "grad_norm": 0.39427706599235535, "learning_rate": 3.0414243121823245e-05, "loss": 4.2252, "step": 14095 }, { "epoch": 0.43054367745876604, "grad_norm": 0.3915638029575348, "learning_rate": 3.041190113468641e-05, "loss": 4.2696, "step": 14096 }, { "epoch": 0.4305742211362248, "grad_norm": 0.3786102533340454, "learning_rate": 3.0409559097719425e-05, "loss": 4.2571, "step": 14097 }, { "epoch": 0.4306047648136836, "grad_norm": 0.3800763487815857, "learning_rate": 3.0407217010943844e-05, "loss": 4.3149, "step": 14098 }, { "epoch": 0.43063530849114234, "grad_norm": 0.3848700523376465, "learning_rate": 3.040487487438124e-05, "loss": 4.3045, "step": 14099 }, { "epoch": 0.4306658521686011, "grad_norm": 0.3720387816429138, "learning_rate": 3.040253268805317e-05, "loss": 4.2662, "step": 14100 }, { "epoch": 0.43069639584605984, "grad_norm": 0.39269500970840454, "learning_rate": 3.040019045198121e-05, "loss": 4.2737, "step": 14101 }, { "epoch": 0.43072693952351865, "grad_norm": 0.3910750150680542, "learning_rate": 3.039784816618691e-05, "loss": 4.3908, "step": 14102 }, { "epoch": 0.4307574832009774, "grad_norm": 0.38084909319877625, "learning_rate": 3.039550583069185e-05, "loss": 4.3214, "step": 14103 }, { "epoch": 0.43078802687843615, "grad_norm": 0.39731359481811523, "learning_rate": 3.0393163445517597e-05, "loss": 4.3491, "step": 14104 }, { "epoch": 0.43081857055589495, "grad_norm": 0.38169777393341064, "learning_rate": 3.0390821010685715e-05, "loss": 4.2546, "step": 14105 }, { "epoch": 0.4308491142333537, "grad_norm": 0.4672852158546448, "learning_rate": 3.0388478526217774e-05, "loss": 4.2716, "step": 14106 }, { "epoch": 0.43087965791081245, "grad_norm": 0.3887544572353363, "learning_rate": 3.0386135992135335e-05, "loss": 4.3255, "step": 14107 }, { "epoch": 0.4309102015882712, "grad_norm": 0.3979381024837494, "learning_rate": 3.0383793408459975e-05, "loss": 4.2776, "step": 14108 }, { "epoch": 0.43094074526573, "grad_norm": 0.3871852457523346, "learning_rate": 3.038145077521326e-05, "loss": 4.2222, "step": 14109 }, { "epoch": 0.43097128894318876, "grad_norm": 0.3815964162349701, "learning_rate": 3.0379108092416763e-05, "loss": 4.2676, "step": 14110 }, { "epoch": 0.4310018326206475, "grad_norm": 0.3834735155105591, "learning_rate": 3.037676536009205e-05, "loss": 4.2793, "step": 14111 }, { "epoch": 0.4310323762981063, "grad_norm": 0.38892653584480286, "learning_rate": 3.0374422578260698e-05, "loss": 4.3296, "step": 14112 }, { "epoch": 0.43106291997556506, "grad_norm": 0.4038643538951874, "learning_rate": 3.037207974694427e-05, "loss": 4.2983, "step": 14113 }, { "epoch": 0.4310934636530238, "grad_norm": 0.3837074935436249, "learning_rate": 3.0369736866164345e-05, "loss": 4.2744, "step": 14114 }, { "epoch": 0.4311240073304826, "grad_norm": 0.3832768201828003, "learning_rate": 3.036739393594249e-05, "loss": 4.3294, "step": 14115 }, { "epoch": 0.43115455100794137, "grad_norm": 0.3769247531890869, "learning_rate": 3.0365050956300277e-05, "loss": 4.2737, "step": 14116 }, { "epoch": 0.4311850946854001, "grad_norm": 0.3837258219718933, "learning_rate": 3.0362707927259282e-05, "loss": 4.34, "step": 14117 }, { "epoch": 0.43121563836285887, "grad_norm": 0.38249292969703674, "learning_rate": 3.0360364848841085e-05, "loss": 4.3166, "step": 14118 }, { "epoch": 0.43124618204031767, "grad_norm": 0.38353416323661804, "learning_rate": 3.0358021721067243e-05, "loss": 4.3042, "step": 14119 }, { "epoch": 0.4312767257177764, "grad_norm": 0.7584260106086731, "learning_rate": 3.0355678543959342e-05, "loss": 4.3937, "step": 14120 }, { "epoch": 0.43130726939523517, "grad_norm": 0.3778648376464844, "learning_rate": 3.0353335317538966e-05, "loss": 4.3188, "step": 14121 }, { "epoch": 0.431337813072694, "grad_norm": 0.37833380699157715, "learning_rate": 3.0350992041827665e-05, "loss": 4.1671, "step": 14122 }, { "epoch": 0.4313683567501527, "grad_norm": 0.38174203038215637, "learning_rate": 3.034864871684704e-05, "loss": 4.4289, "step": 14123 }, { "epoch": 0.4313989004276115, "grad_norm": 0.387837290763855, "learning_rate": 3.034630534261865e-05, "loss": 4.3015, "step": 14124 }, { "epoch": 0.4314294441050702, "grad_norm": 0.3742102086544037, "learning_rate": 3.0343961919164077e-05, "loss": 4.2916, "step": 14125 }, { "epoch": 0.43145998778252903, "grad_norm": 0.3848930895328522, "learning_rate": 3.03416184465049e-05, "loss": 4.338, "step": 14126 }, { "epoch": 0.4314905314599878, "grad_norm": 0.47977617383003235, "learning_rate": 3.03392749246627e-05, "loss": 4.2353, "step": 14127 }, { "epoch": 0.43152107513744653, "grad_norm": 0.3969901204109192, "learning_rate": 3.0336931353659043e-05, "loss": 4.3479, "step": 14128 }, { "epoch": 0.43155161881490534, "grad_norm": 0.3906799852848053, "learning_rate": 3.0334587733515523e-05, "loss": 4.1724, "step": 14129 }, { "epoch": 0.4315821624923641, "grad_norm": 0.38136646151542664, "learning_rate": 3.0332244064253708e-05, "loss": 4.2713, "step": 14130 }, { "epoch": 0.43161270616982284, "grad_norm": 0.391166090965271, "learning_rate": 3.032990034589518e-05, "loss": 4.2784, "step": 14131 }, { "epoch": 0.43164324984728164, "grad_norm": 0.3716135323047638, "learning_rate": 3.0327556578461514e-05, "loss": 4.301, "step": 14132 }, { "epoch": 0.4316737935247404, "grad_norm": 0.37839555740356445, "learning_rate": 3.0325212761974304e-05, "loss": 4.2954, "step": 14133 }, { "epoch": 0.43170433720219914, "grad_norm": 0.40969809889793396, "learning_rate": 3.0322868896455114e-05, "loss": 4.3262, "step": 14134 }, { "epoch": 0.4317348808796579, "grad_norm": 0.38117241859436035, "learning_rate": 3.032052498192554e-05, "loss": 4.2845, "step": 14135 }, { "epoch": 0.4317654245571167, "grad_norm": 0.3814343214035034, "learning_rate": 3.0318181018407156e-05, "loss": 4.3393, "step": 14136 }, { "epoch": 0.43179596823457544, "grad_norm": 0.39053794741630554, "learning_rate": 3.0315837005921543e-05, "loss": 4.265, "step": 14137 }, { "epoch": 0.4318265119120342, "grad_norm": 0.37890464067459106, "learning_rate": 3.031349294449029e-05, "loss": 4.3442, "step": 14138 }, { "epoch": 0.431857055589493, "grad_norm": 0.3771737217903137, "learning_rate": 3.0311148834134966e-05, "loss": 4.3172, "step": 14139 }, { "epoch": 0.43188759926695175, "grad_norm": 0.3795565366744995, "learning_rate": 3.030880467487717e-05, "loss": 4.3033, "step": 14140 }, { "epoch": 0.4319181429444105, "grad_norm": 0.3802701234817505, "learning_rate": 3.0306460466738484e-05, "loss": 4.2995, "step": 14141 }, { "epoch": 0.43194868662186925, "grad_norm": 0.3864487409591675, "learning_rate": 3.0304116209740486e-05, "loss": 4.3651, "step": 14142 }, { "epoch": 0.43197923029932805, "grad_norm": 0.3806382417678833, "learning_rate": 3.030177190390475e-05, "loss": 4.3814, "step": 14143 }, { "epoch": 0.4320097739767868, "grad_norm": 0.39278095960617065, "learning_rate": 3.0299427549252894e-05, "loss": 4.3312, "step": 14144 }, { "epoch": 0.43204031765424555, "grad_norm": 0.3678450286388397, "learning_rate": 3.0297083145806478e-05, "loss": 4.3399, "step": 14145 }, { "epoch": 0.43207086133170436, "grad_norm": 0.3831479549407959, "learning_rate": 3.029473869358708e-05, "loss": 4.309, "step": 14146 }, { "epoch": 0.4321014050091631, "grad_norm": 0.3839645981788635, "learning_rate": 3.0292394192616314e-05, "loss": 4.3075, "step": 14147 }, { "epoch": 0.43213194868662186, "grad_norm": 0.4024273753166199, "learning_rate": 3.029004964291575e-05, "loss": 4.3027, "step": 14148 }, { "epoch": 0.4321624923640806, "grad_norm": 0.5745331048965454, "learning_rate": 3.0287705044506985e-05, "loss": 4.3498, "step": 14149 }, { "epoch": 0.4321930360415394, "grad_norm": 0.3762778341770172, "learning_rate": 3.028536039741159e-05, "loss": 4.2999, "step": 14150 }, { "epoch": 0.43222357971899816, "grad_norm": 0.3818497955799103, "learning_rate": 3.0283015701651172e-05, "loss": 4.354, "step": 14151 }, { "epoch": 0.4322541233964569, "grad_norm": 0.3861100375652313, "learning_rate": 3.028067095724731e-05, "loss": 4.3254, "step": 14152 }, { "epoch": 0.4322846670739157, "grad_norm": 0.3807598352432251, "learning_rate": 3.0278326164221598e-05, "loss": 4.2962, "step": 14153 }, { "epoch": 0.43231521075137447, "grad_norm": 0.389813631772995, "learning_rate": 3.027598132259562e-05, "loss": 4.3221, "step": 14154 }, { "epoch": 0.4323457544288332, "grad_norm": 0.3807912766933441, "learning_rate": 3.0273636432390973e-05, "loss": 4.3549, "step": 14155 }, { "epoch": 0.432376298106292, "grad_norm": 0.3876188099384308, "learning_rate": 3.0271291493629238e-05, "loss": 4.2765, "step": 14156 }, { "epoch": 0.4324068417837508, "grad_norm": 0.3933549225330353, "learning_rate": 3.0268946506332013e-05, "loss": 4.3507, "step": 14157 }, { "epoch": 0.4324373854612095, "grad_norm": 0.3903305232524872, "learning_rate": 3.0266601470520895e-05, "loss": 4.361, "step": 14158 }, { "epoch": 0.43246792913866827, "grad_norm": 0.3767036497592926, "learning_rate": 3.0264256386217466e-05, "loss": 4.3279, "step": 14159 }, { "epoch": 0.4324984728161271, "grad_norm": 1.4308825731277466, "learning_rate": 3.026191125344332e-05, "loss": 4.3374, "step": 14160 }, { "epoch": 0.4325290164935858, "grad_norm": 0.3849949538707733, "learning_rate": 3.025956607222006e-05, "loss": 4.2576, "step": 14161 }, { "epoch": 0.4325595601710446, "grad_norm": 0.3795109987258911, "learning_rate": 3.025722084256926e-05, "loss": 4.3521, "step": 14162 }, { "epoch": 0.4325901038485034, "grad_norm": 0.374760240316391, "learning_rate": 3.0254875564512523e-05, "loss": 4.3259, "step": 14163 }, { "epoch": 0.43262064752596213, "grad_norm": 0.38789522647857666, "learning_rate": 3.0252530238071452e-05, "loss": 4.2033, "step": 14164 }, { "epoch": 0.4326511912034209, "grad_norm": 0.3828284740447998, "learning_rate": 3.0250184863267635e-05, "loss": 4.3428, "step": 14165 }, { "epoch": 0.43268173488087963, "grad_norm": 0.38025686144828796, "learning_rate": 3.0247839440122665e-05, "loss": 4.2984, "step": 14166 }, { "epoch": 0.43271227855833844, "grad_norm": 0.37881723046302795, "learning_rate": 3.024549396865814e-05, "loss": 4.2649, "step": 14167 }, { "epoch": 0.4327428222357972, "grad_norm": 0.38836267590522766, "learning_rate": 3.0243148448895654e-05, "loss": 4.3412, "step": 14168 }, { "epoch": 0.43277336591325594, "grad_norm": 0.3879839777946472, "learning_rate": 3.0240802880856805e-05, "loss": 4.2854, "step": 14169 }, { "epoch": 0.43280390959071474, "grad_norm": 0.3809541165828705, "learning_rate": 3.023845726456318e-05, "loss": 4.2797, "step": 14170 }, { "epoch": 0.4328344532681735, "grad_norm": 0.38108882308006287, "learning_rate": 3.02361116000364e-05, "loss": 4.3051, "step": 14171 }, { "epoch": 0.43286499694563224, "grad_norm": 0.3867647349834442, "learning_rate": 3.0233765887298037e-05, "loss": 4.2284, "step": 14172 }, { "epoch": 0.43289554062309105, "grad_norm": 0.38543960452079773, "learning_rate": 3.0231420126369704e-05, "loss": 4.2838, "step": 14173 }, { "epoch": 0.4329260843005498, "grad_norm": 0.3860372006893158, "learning_rate": 3.0229074317273e-05, "loss": 4.3196, "step": 14174 }, { "epoch": 0.43295662797800855, "grad_norm": 0.3911256492137909, "learning_rate": 3.022672846002952e-05, "loss": 4.2267, "step": 14175 }, { "epoch": 0.4329871716554673, "grad_norm": 0.3952762186527252, "learning_rate": 3.022438255466087e-05, "loss": 4.253, "step": 14176 }, { "epoch": 0.4330177153329261, "grad_norm": 0.39388516545295715, "learning_rate": 3.022203660118863e-05, "loss": 4.4356, "step": 14177 }, { "epoch": 0.43304825901038485, "grad_norm": 0.3890818953514099, "learning_rate": 3.021969059963442e-05, "loss": 4.206, "step": 14178 }, { "epoch": 0.4330788026878436, "grad_norm": 0.392151415348053, "learning_rate": 3.021734455001983e-05, "loss": 4.3875, "step": 14179 }, { "epoch": 0.4331093463653024, "grad_norm": 0.38269519805908203, "learning_rate": 3.0214998452366472e-05, "loss": 4.336, "step": 14180 }, { "epoch": 0.43313989004276116, "grad_norm": 0.4022584855556488, "learning_rate": 3.0212652306695944e-05, "loss": 4.246, "step": 14181 }, { "epoch": 0.4331704337202199, "grad_norm": 0.37911251187324524, "learning_rate": 3.021030611302984e-05, "loss": 4.3168, "step": 14182 }, { "epoch": 0.43320097739767865, "grad_norm": 0.3777305483818054, "learning_rate": 3.0207959871389773e-05, "loss": 4.3328, "step": 14183 }, { "epoch": 0.43323152107513746, "grad_norm": 0.3839610517024994, "learning_rate": 3.0205613581797343e-05, "loss": 4.3456, "step": 14184 }, { "epoch": 0.4332620647525962, "grad_norm": 0.3873338997364044, "learning_rate": 3.0203267244274154e-05, "loss": 4.3283, "step": 14185 }, { "epoch": 0.43329260843005496, "grad_norm": 0.39554163813591003, "learning_rate": 3.0200920858841802e-05, "loss": 4.2999, "step": 14186 }, { "epoch": 0.43332315210751376, "grad_norm": 0.4534603953361511, "learning_rate": 3.0198574425521897e-05, "loss": 4.3287, "step": 14187 }, { "epoch": 0.4333536957849725, "grad_norm": 0.37902551889419556, "learning_rate": 3.0196227944336048e-05, "loss": 4.2442, "step": 14188 }, { "epoch": 0.43338423946243126, "grad_norm": 0.39397698640823364, "learning_rate": 3.019388141530586e-05, "loss": 4.3297, "step": 14189 }, { "epoch": 0.43341478313989007, "grad_norm": 0.3938535451889038, "learning_rate": 3.0191534838452927e-05, "loss": 4.2961, "step": 14190 }, { "epoch": 0.4334453268173488, "grad_norm": 0.3762097656726837, "learning_rate": 3.018918821379887e-05, "loss": 4.3405, "step": 14191 }, { "epoch": 0.43347587049480757, "grad_norm": 0.3819213807582855, "learning_rate": 3.0186841541365285e-05, "loss": 4.3318, "step": 14192 }, { "epoch": 0.4335064141722663, "grad_norm": 0.37912923097610474, "learning_rate": 3.0184494821173786e-05, "loss": 4.3016, "step": 14193 }, { "epoch": 0.4335369578497251, "grad_norm": 0.3929584324359894, "learning_rate": 3.0182148053245973e-05, "loss": 4.3917, "step": 14194 }, { "epoch": 0.4335675015271839, "grad_norm": 0.3735678791999817, "learning_rate": 3.0179801237603467e-05, "loss": 4.3069, "step": 14195 }, { "epoch": 0.4335980452046426, "grad_norm": 0.38225460052490234, "learning_rate": 3.017745437426786e-05, "loss": 4.2743, "step": 14196 }, { "epoch": 0.43362858888210143, "grad_norm": 0.39680245518684387, "learning_rate": 3.0175107463260765e-05, "loss": 4.3686, "step": 14197 }, { "epoch": 0.4336591325595602, "grad_norm": 0.3899089992046356, "learning_rate": 3.0172760504603802e-05, "loss": 4.3305, "step": 14198 }, { "epoch": 0.43368967623701893, "grad_norm": 0.3819870948791504, "learning_rate": 3.0170413498318584e-05, "loss": 4.3307, "step": 14199 }, { "epoch": 0.4337202199144777, "grad_norm": 0.3817079961299896, "learning_rate": 3.0168066444426702e-05, "loss": 4.3341, "step": 14200 }, { "epoch": 0.4337507635919365, "grad_norm": 0.3858918249607086, "learning_rate": 3.0165719342949766e-05, "loss": 4.3141, "step": 14201 }, { "epoch": 0.43378130726939523, "grad_norm": 0.3856894373893738, "learning_rate": 3.01633721939094e-05, "loss": 4.3646, "step": 14202 }, { "epoch": 0.433811850946854, "grad_norm": 0.3825288712978363, "learning_rate": 3.0161024997327214e-05, "loss": 4.2451, "step": 14203 }, { "epoch": 0.4338423946243128, "grad_norm": 0.3839851915836334, "learning_rate": 3.0158677753224818e-05, "loss": 4.3053, "step": 14204 }, { "epoch": 0.43387293830177154, "grad_norm": 0.3870033323764801, "learning_rate": 3.0156330461623822e-05, "loss": 4.4171, "step": 14205 }, { "epoch": 0.4339034819792303, "grad_norm": 0.37999624013900757, "learning_rate": 3.0153983122545843e-05, "loss": 4.2668, "step": 14206 }, { "epoch": 0.4339340256566891, "grad_norm": 0.3854997158050537, "learning_rate": 3.015163573601249e-05, "loss": 4.3363, "step": 14207 }, { "epoch": 0.43396456933414784, "grad_norm": 0.3956494629383087, "learning_rate": 3.0149288302045376e-05, "loss": 4.3346, "step": 14208 }, { "epoch": 0.4339951130116066, "grad_norm": 0.37256014347076416, "learning_rate": 3.014694082066612e-05, "loss": 4.3698, "step": 14209 }, { "epoch": 0.43402565668906534, "grad_norm": 0.38262662291526794, "learning_rate": 3.0144593291896332e-05, "loss": 4.3384, "step": 14210 }, { "epoch": 0.43405620036652415, "grad_norm": 0.37481585144996643, "learning_rate": 3.0142245715757627e-05, "loss": 4.3143, "step": 14211 }, { "epoch": 0.4340867440439829, "grad_norm": 0.3992418646812439, "learning_rate": 3.0139898092271623e-05, "loss": 4.3572, "step": 14212 }, { "epoch": 0.43411728772144165, "grad_norm": 0.37707120180130005, "learning_rate": 3.0137550421459936e-05, "loss": 4.2481, "step": 14213 }, { "epoch": 0.43414783139890045, "grad_norm": 0.38739946484565735, "learning_rate": 3.0135202703344183e-05, "loss": 4.3332, "step": 14214 }, { "epoch": 0.4341783750763592, "grad_norm": 0.3790908455848694, "learning_rate": 3.0132854937945974e-05, "loss": 4.2681, "step": 14215 }, { "epoch": 0.43420891875381795, "grad_norm": 0.4061118960380554, "learning_rate": 3.013050712528693e-05, "loss": 4.3665, "step": 14216 }, { "epoch": 0.4342394624312767, "grad_norm": 0.375957727432251, "learning_rate": 3.012815926538868e-05, "loss": 4.3131, "step": 14217 }, { "epoch": 0.4342700061087355, "grad_norm": 0.3926050364971161, "learning_rate": 3.0125811358272814e-05, "loss": 4.3309, "step": 14218 }, { "epoch": 0.43430054978619426, "grad_norm": 0.37279632687568665, "learning_rate": 3.012346340396098e-05, "loss": 4.3244, "step": 14219 }, { "epoch": 0.434331093463653, "grad_norm": 0.38011157512664795, "learning_rate": 3.0121115402474776e-05, "loss": 4.3083, "step": 14220 }, { "epoch": 0.4343616371411118, "grad_norm": 0.383870005607605, "learning_rate": 3.011876735383583e-05, "loss": 4.2396, "step": 14221 }, { "epoch": 0.43439218081857056, "grad_norm": 0.3800070285797119, "learning_rate": 3.011641925806577e-05, "loss": 4.3442, "step": 14222 }, { "epoch": 0.4344227244960293, "grad_norm": 0.3942297399044037, "learning_rate": 3.0114071115186206e-05, "loss": 4.3656, "step": 14223 }, { "epoch": 0.43445326817348806, "grad_norm": 0.3767910599708557, "learning_rate": 3.0111722925218756e-05, "loss": 4.3307, "step": 14224 }, { "epoch": 0.43448381185094687, "grad_norm": 0.37098634243011475, "learning_rate": 3.010937468818504e-05, "loss": 4.3128, "step": 14225 }, { "epoch": 0.4345143555284056, "grad_norm": 0.38603124022483826, "learning_rate": 3.0107026404106686e-05, "loss": 4.2415, "step": 14226 }, { "epoch": 0.43454489920586437, "grad_norm": 0.3762354850769043, "learning_rate": 3.0104678073005322e-05, "loss": 4.2981, "step": 14227 }, { "epoch": 0.43457544288332317, "grad_norm": 0.38912487030029297, "learning_rate": 3.0102329694902548e-05, "loss": 4.3465, "step": 14228 }, { "epoch": 0.4346059865607819, "grad_norm": 0.3776863217353821, "learning_rate": 3.009998126982001e-05, "loss": 4.313, "step": 14229 }, { "epoch": 0.43463653023824067, "grad_norm": 0.3816862404346466, "learning_rate": 3.0097632797779325e-05, "loss": 4.3116, "step": 14230 }, { "epoch": 0.4346670739156995, "grad_norm": 0.37866052985191345, "learning_rate": 3.0095284278802117e-05, "loss": 4.3825, "step": 14231 }, { "epoch": 0.4346976175931582, "grad_norm": 0.38049378991127014, "learning_rate": 3.0092935712909997e-05, "loss": 4.3439, "step": 14232 }, { "epoch": 0.434728161270617, "grad_norm": 0.3857736885547638, "learning_rate": 3.0090587100124608e-05, "loss": 4.2629, "step": 14233 }, { "epoch": 0.4347587049480757, "grad_norm": 0.3821689784526825, "learning_rate": 3.008823844046756e-05, "loss": 4.3113, "step": 14234 }, { "epoch": 0.43478924862553453, "grad_norm": 0.39164024591445923, "learning_rate": 3.0085889733960482e-05, "loss": 4.3126, "step": 14235 }, { "epoch": 0.4348197923029933, "grad_norm": 0.3791157305240631, "learning_rate": 3.008354098062501e-05, "loss": 4.2877, "step": 14236 }, { "epoch": 0.43485033598045203, "grad_norm": 0.37714052200317383, "learning_rate": 3.008119218048276e-05, "loss": 4.3125, "step": 14237 }, { "epoch": 0.43488087965791083, "grad_norm": 0.3719627261161804, "learning_rate": 3.0078843333555363e-05, "loss": 4.2318, "step": 14238 }, { "epoch": 0.4349114233353696, "grad_norm": 0.3923046290874481, "learning_rate": 3.007649443986444e-05, "loss": 4.2569, "step": 14239 }, { "epoch": 0.43494196701282833, "grad_norm": 0.37479984760284424, "learning_rate": 3.0074145499431626e-05, "loss": 4.2967, "step": 14240 }, { "epoch": 0.4349725106902871, "grad_norm": 0.3794528841972351, "learning_rate": 3.0071796512278545e-05, "loss": 4.3551, "step": 14241 }, { "epoch": 0.4350030543677459, "grad_norm": 0.3845604658126831, "learning_rate": 3.006944747842682e-05, "loss": 4.2831, "step": 14242 }, { "epoch": 0.43503359804520464, "grad_norm": 0.3798423707485199, "learning_rate": 3.006709839789809e-05, "loss": 4.2665, "step": 14243 }, { "epoch": 0.4350641417226634, "grad_norm": 0.3820132613182068, "learning_rate": 3.006474927071398e-05, "loss": 4.3475, "step": 14244 }, { "epoch": 0.4350946854001222, "grad_norm": 0.3922760784626007, "learning_rate": 3.006240009689612e-05, "loss": 4.2923, "step": 14245 }, { "epoch": 0.43512522907758094, "grad_norm": 0.38827481865882874, "learning_rate": 3.006005087646614e-05, "loss": 4.3791, "step": 14246 }, { "epoch": 0.4351557727550397, "grad_norm": 0.38274428248405457, "learning_rate": 3.0057701609445672e-05, "loss": 4.3074, "step": 14247 }, { "epoch": 0.4351863164324985, "grad_norm": 0.39721402525901794, "learning_rate": 3.0055352295856336e-05, "loss": 4.312, "step": 14248 }, { "epoch": 0.43521686010995725, "grad_norm": 0.3924868404865265, "learning_rate": 3.0053002935719778e-05, "loss": 4.3152, "step": 14249 }, { "epoch": 0.435247403787416, "grad_norm": 0.38260719180107117, "learning_rate": 3.0050653529057627e-05, "loss": 4.3722, "step": 14250 }, { "epoch": 0.43527794746487475, "grad_norm": 0.37548908591270447, "learning_rate": 3.004830407589151e-05, "loss": 4.3431, "step": 14251 }, { "epoch": 0.43530849114233355, "grad_norm": 0.3971134424209595, "learning_rate": 3.0045954576243057e-05, "loss": 4.2251, "step": 14252 }, { "epoch": 0.4353390348197923, "grad_norm": 0.38708585500717163, "learning_rate": 3.004360503013391e-05, "loss": 4.3305, "step": 14253 }, { "epoch": 0.43536957849725105, "grad_norm": 0.3803652822971344, "learning_rate": 3.00412554375857e-05, "loss": 4.3284, "step": 14254 }, { "epoch": 0.43540012217470986, "grad_norm": 0.3773247003555298, "learning_rate": 3.0038905798620052e-05, "loss": 4.2552, "step": 14255 }, { "epoch": 0.4354306658521686, "grad_norm": 0.37998512387275696, "learning_rate": 3.0036556113258618e-05, "loss": 4.317, "step": 14256 }, { "epoch": 0.43546120952962736, "grad_norm": 0.384561687707901, "learning_rate": 3.0034206381523017e-05, "loss": 4.3173, "step": 14257 }, { "epoch": 0.4354917532070861, "grad_norm": 0.372938871383667, "learning_rate": 3.0031856603434894e-05, "loss": 4.2783, "step": 14258 }, { "epoch": 0.4355222968845449, "grad_norm": 0.3812418580055237, "learning_rate": 3.002950677901587e-05, "loss": 4.2369, "step": 14259 }, { "epoch": 0.43555284056200366, "grad_norm": 0.39031705260276794, "learning_rate": 3.0027156908287598e-05, "loss": 4.2878, "step": 14260 }, { "epoch": 0.4355833842394624, "grad_norm": 0.3802827298641205, "learning_rate": 3.0024806991271705e-05, "loss": 4.3058, "step": 14261 }, { "epoch": 0.4356139279169212, "grad_norm": 0.37951451539993286, "learning_rate": 3.0022457027989836e-05, "loss": 4.1828, "step": 14262 }, { "epoch": 0.43564447159437997, "grad_norm": 0.3840811848640442, "learning_rate": 3.0020107018463617e-05, "loss": 4.3028, "step": 14263 }, { "epoch": 0.4356750152718387, "grad_norm": 0.387908011674881, "learning_rate": 3.0017756962714695e-05, "loss": 4.3824, "step": 14264 }, { "epoch": 0.4357055589492975, "grad_norm": 0.3935838043689728, "learning_rate": 3.00154068607647e-05, "loss": 4.3573, "step": 14265 }, { "epoch": 0.43573610262675627, "grad_norm": 0.3920755982398987, "learning_rate": 3.001305671263528e-05, "loss": 4.32, "step": 14266 }, { "epoch": 0.435766646304215, "grad_norm": 0.385323166847229, "learning_rate": 3.001070651834807e-05, "loss": 4.3499, "step": 14267 }, { "epoch": 0.43579718998167377, "grad_norm": 0.38055911660194397, "learning_rate": 3.0008356277924705e-05, "loss": 4.3236, "step": 14268 }, { "epoch": 0.4358277336591326, "grad_norm": 0.38488849997520447, "learning_rate": 3.000600599138683e-05, "loss": 4.3042, "step": 14269 }, { "epoch": 0.4358582773365913, "grad_norm": 0.3898400366306305, "learning_rate": 3.0003655658756092e-05, "loss": 4.3693, "step": 14270 }, { "epoch": 0.4358888210140501, "grad_norm": 0.39255401492118835, "learning_rate": 3.0001305280054114e-05, "loss": 4.3677, "step": 14271 }, { "epoch": 0.4359193646915089, "grad_norm": 0.41746726632118225, "learning_rate": 2.9998954855302543e-05, "loss": 4.4958, "step": 14272 }, { "epoch": 0.43594990836896763, "grad_norm": 0.38586676120758057, "learning_rate": 2.9996604384523032e-05, "loss": 4.1341, "step": 14273 }, { "epoch": 0.4359804520464264, "grad_norm": 0.3914085030555725, "learning_rate": 2.9994253867737214e-05, "loss": 4.2349, "step": 14274 }, { "epoch": 0.43601099572388513, "grad_norm": 0.39598754048347473, "learning_rate": 2.9991903304966733e-05, "loss": 4.3645, "step": 14275 }, { "epoch": 0.43604153940134394, "grad_norm": 0.38085320591926575, "learning_rate": 2.998955269623323e-05, "loss": 4.2913, "step": 14276 }, { "epoch": 0.4360720830788027, "grad_norm": 0.385222852230072, "learning_rate": 2.998720204155836e-05, "loss": 4.3845, "step": 14277 }, { "epoch": 0.43610262675626144, "grad_norm": 0.38321083784103394, "learning_rate": 2.998485134096375e-05, "loss": 4.261, "step": 14278 }, { "epoch": 0.43613317043372024, "grad_norm": 0.3718295395374298, "learning_rate": 2.9982500594471043e-05, "loss": 4.3022, "step": 14279 }, { "epoch": 0.436163714111179, "grad_norm": 0.3873947560787201, "learning_rate": 2.9980149802101897e-05, "loss": 4.2717, "step": 14280 }, { "epoch": 0.43619425778863774, "grad_norm": 0.39896202087402344, "learning_rate": 2.997779896387795e-05, "loss": 4.4168, "step": 14281 }, { "epoch": 0.43622480146609655, "grad_norm": 0.37831029295921326, "learning_rate": 2.9975448079820843e-05, "loss": 4.2682, "step": 14282 }, { "epoch": 0.4362553451435553, "grad_norm": 0.3938165605068207, "learning_rate": 2.997309714995224e-05, "loss": 4.2772, "step": 14283 }, { "epoch": 0.43628588882101405, "grad_norm": 0.3814534544944763, "learning_rate": 2.9970746174293773e-05, "loss": 4.3145, "step": 14284 }, { "epoch": 0.4363164324984728, "grad_norm": 0.38643956184387207, "learning_rate": 2.9968395152867084e-05, "loss": 4.3994, "step": 14285 }, { "epoch": 0.4363469761759316, "grad_norm": 0.3885301351547241, "learning_rate": 2.996604408569383e-05, "loss": 4.1482, "step": 14286 }, { "epoch": 0.43637751985339035, "grad_norm": 0.39657121896743774, "learning_rate": 2.9963692972795653e-05, "loss": 4.3624, "step": 14287 }, { "epoch": 0.4364080635308491, "grad_norm": 0.3876112699508667, "learning_rate": 2.9961341814194204e-05, "loss": 4.3164, "step": 14288 }, { "epoch": 0.4364386072083079, "grad_norm": 0.3864431381225586, "learning_rate": 2.9958990609911124e-05, "loss": 4.3707, "step": 14289 }, { "epoch": 0.43646915088576665, "grad_norm": 0.38692325353622437, "learning_rate": 2.9956639359968075e-05, "loss": 4.3299, "step": 14290 }, { "epoch": 0.4364996945632254, "grad_norm": 0.3875015676021576, "learning_rate": 2.9954288064386697e-05, "loss": 4.3813, "step": 14291 }, { "epoch": 0.43653023824068415, "grad_norm": 0.385242760181427, "learning_rate": 2.9951936723188645e-05, "loss": 4.291, "step": 14292 }, { "epoch": 0.43656078191814296, "grad_norm": 0.3845162093639374, "learning_rate": 2.9949585336395565e-05, "loss": 4.3062, "step": 14293 }, { "epoch": 0.4365913255956017, "grad_norm": 0.38172611594200134, "learning_rate": 2.9947233904029104e-05, "loss": 4.2886, "step": 14294 }, { "epoch": 0.43662186927306046, "grad_norm": 0.39096173644065857, "learning_rate": 2.994488242611092e-05, "loss": 4.2746, "step": 14295 }, { "epoch": 0.43665241295051926, "grad_norm": 0.3838535249233246, "learning_rate": 2.994253090266265e-05, "loss": 4.2782, "step": 14296 }, { "epoch": 0.436682956627978, "grad_norm": 0.38148900866508484, "learning_rate": 2.994017933370597e-05, "loss": 4.3017, "step": 14297 }, { "epoch": 0.43671350030543676, "grad_norm": 0.3847475051879883, "learning_rate": 2.9937827719262517e-05, "loss": 4.3384, "step": 14298 }, { "epoch": 0.4367440439828955, "grad_norm": 0.3842836320400238, "learning_rate": 2.9935476059353946e-05, "loss": 4.3766, "step": 14299 }, { "epoch": 0.4367745876603543, "grad_norm": 0.38242611289024353, "learning_rate": 2.9933124354001908e-05, "loss": 4.3302, "step": 14300 }, { "epoch": 0.43680513133781307, "grad_norm": 0.37732478976249695, "learning_rate": 2.993077260322805e-05, "loss": 4.3109, "step": 14301 }, { "epoch": 0.4368356750152718, "grad_norm": 0.3841398060321808, "learning_rate": 2.9928420807054047e-05, "loss": 4.3723, "step": 14302 }, { "epoch": 0.4368662186927306, "grad_norm": 0.37089377641677856, "learning_rate": 2.9926068965501524e-05, "loss": 4.3257, "step": 14303 }, { "epoch": 0.4368967623701894, "grad_norm": 0.38781455159187317, "learning_rate": 2.992371707859216e-05, "loss": 4.2865, "step": 14304 }, { "epoch": 0.4369273060476481, "grad_norm": 0.38836976885795593, "learning_rate": 2.99213651463476e-05, "loss": 4.3777, "step": 14305 }, { "epoch": 0.43695784972510693, "grad_norm": 0.386522501707077, "learning_rate": 2.99190131687895e-05, "loss": 4.3603, "step": 14306 }, { "epoch": 0.4369883934025657, "grad_norm": 0.3872449994087219, "learning_rate": 2.9916661145939522e-05, "loss": 4.2968, "step": 14307 }, { "epoch": 0.4370189370800244, "grad_norm": 0.3867502808570862, "learning_rate": 2.9914309077819313e-05, "loss": 4.3215, "step": 14308 }, { "epoch": 0.4370494807574832, "grad_norm": 0.38880810141563416, "learning_rate": 2.991195696445054e-05, "loss": 4.2601, "step": 14309 }, { "epoch": 0.437080024434942, "grad_norm": 0.3912285268306732, "learning_rate": 2.9909604805854847e-05, "loss": 4.3736, "step": 14310 }, { "epoch": 0.43711056811240073, "grad_norm": 0.40198183059692383, "learning_rate": 2.9907252602053898e-05, "loss": 4.3016, "step": 14311 }, { "epoch": 0.4371411117898595, "grad_norm": 0.38208770751953125, "learning_rate": 2.9904900353069356e-05, "loss": 4.2208, "step": 14312 }, { "epoch": 0.4371716554673183, "grad_norm": 0.3848706781864166, "learning_rate": 2.9902548058922863e-05, "loss": 4.3346, "step": 14313 }, { "epoch": 0.43720219914477704, "grad_norm": 0.38450920581817627, "learning_rate": 2.9900195719636097e-05, "loss": 4.29, "step": 14314 }, { "epoch": 0.4372327428222358, "grad_norm": 0.3832378387451172, "learning_rate": 2.9897843335230712e-05, "loss": 4.3268, "step": 14315 }, { "epoch": 0.43726328649969454, "grad_norm": 0.3816003203392029, "learning_rate": 2.9895490905728364e-05, "loss": 4.3456, "step": 14316 }, { "epoch": 0.43729383017715334, "grad_norm": 0.3953912556171417, "learning_rate": 2.9893138431150715e-05, "loss": 4.3168, "step": 14317 }, { "epoch": 0.4373243738546121, "grad_norm": 0.4007188081741333, "learning_rate": 2.9890785911519426e-05, "loss": 4.3198, "step": 14318 }, { "epoch": 0.43735491753207084, "grad_norm": 0.3834872245788574, "learning_rate": 2.988843334685615e-05, "loss": 4.3155, "step": 14319 }, { "epoch": 0.43738546120952965, "grad_norm": 0.4032477140426636, "learning_rate": 2.9886080737182552e-05, "loss": 4.3322, "step": 14320 }, { "epoch": 0.4374160048869884, "grad_norm": 0.3864821195602417, "learning_rate": 2.9883728082520308e-05, "loss": 4.2805, "step": 14321 }, { "epoch": 0.43744654856444715, "grad_norm": 0.3856598138809204, "learning_rate": 2.9881375382891062e-05, "loss": 4.356, "step": 14322 }, { "epoch": 0.43747709224190595, "grad_norm": 0.38886937499046326, "learning_rate": 2.987902263831649e-05, "loss": 4.3202, "step": 14323 }, { "epoch": 0.4375076359193647, "grad_norm": 0.38641873002052307, "learning_rate": 2.987666984881824e-05, "loss": 4.2847, "step": 14324 }, { "epoch": 0.43753817959682345, "grad_norm": 0.37768709659576416, "learning_rate": 2.9874317014417984e-05, "loss": 4.2711, "step": 14325 }, { "epoch": 0.4375687232742822, "grad_norm": 0.3815462589263916, "learning_rate": 2.987196413513739e-05, "loss": 4.2956, "step": 14326 }, { "epoch": 0.437599266951741, "grad_norm": 0.3956815004348755, "learning_rate": 2.9869611210998112e-05, "loss": 4.3106, "step": 14327 }, { "epoch": 0.43762981062919976, "grad_norm": 0.38897332549095154, "learning_rate": 2.9867258242021822e-05, "loss": 4.2535, "step": 14328 }, { "epoch": 0.4376603543066585, "grad_norm": 0.3874507248401642, "learning_rate": 2.9864905228230185e-05, "loss": 4.3505, "step": 14329 }, { "epoch": 0.4376908979841173, "grad_norm": 0.38203802704811096, "learning_rate": 2.9862552169644853e-05, "loss": 4.3522, "step": 14330 }, { "epoch": 0.43772144166157606, "grad_norm": 0.3873300552368164, "learning_rate": 2.9860199066287514e-05, "loss": 4.2846, "step": 14331 }, { "epoch": 0.4377519853390348, "grad_norm": 0.38189128041267395, "learning_rate": 2.985784591817983e-05, "loss": 4.2839, "step": 14332 }, { "epoch": 0.43778252901649356, "grad_norm": 0.3862111568450928, "learning_rate": 2.9855492725343455e-05, "loss": 4.3172, "step": 14333 }, { "epoch": 0.43781307269395237, "grad_norm": 0.38605496287345886, "learning_rate": 2.985313948780005e-05, "loss": 4.3326, "step": 14334 }, { "epoch": 0.4378436163714111, "grad_norm": 0.38514745235443115, "learning_rate": 2.985078620557131e-05, "loss": 4.3373, "step": 14335 }, { "epoch": 0.43787416004886986, "grad_norm": 0.3976721465587616, "learning_rate": 2.9848432878678882e-05, "loss": 4.2614, "step": 14336 }, { "epoch": 0.43790470372632867, "grad_norm": 0.37962380051612854, "learning_rate": 2.984607950714443e-05, "loss": 4.2908, "step": 14337 }, { "epoch": 0.4379352474037874, "grad_norm": 0.3846023976802826, "learning_rate": 2.984372609098965e-05, "loss": 4.2709, "step": 14338 }, { "epoch": 0.43796579108124617, "grad_norm": 0.388233482837677, "learning_rate": 2.984137263023618e-05, "loss": 4.239, "step": 14339 }, { "epoch": 0.437996334758705, "grad_norm": 0.38946518301963806, "learning_rate": 2.983901912490571e-05, "loss": 4.2859, "step": 14340 }, { "epoch": 0.4380268784361637, "grad_norm": 0.3854917585849762, "learning_rate": 2.9836665575019906e-05, "loss": 4.3058, "step": 14341 }, { "epoch": 0.4380574221136225, "grad_norm": 0.39066174626350403, "learning_rate": 2.9834311980600428e-05, "loss": 4.3663, "step": 14342 }, { "epoch": 0.4380879657910812, "grad_norm": 0.3810885548591614, "learning_rate": 2.9831958341668957e-05, "loss": 4.3406, "step": 14343 }, { "epoch": 0.43811850946854003, "grad_norm": 0.39093849062919617, "learning_rate": 2.9829604658247156e-05, "loss": 4.2337, "step": 14344 }, { "epoch": 0.4381490531459988, "grad_norm": 0.3898583650588989, "learning_rate": 2.9827250930356708e-05, "loss": 4.3099, "step": 14345 }, { "epoch": 0.43817959682345753, "grad_norm": 0.3886493444442749, "learning_rate": 2.9824897158019277e-05, "loss": 4.2246, "step": 14346 }, { "epoch": 0.43821014050091633, "grad_norm": 0.3875582218170166, "learning_rate": 2.9822543341256536e-05, "loss": 4.2855, "step": 14347 }, { "epoch": 0.4382406841783751, "grad_norm": 0.3902140259742737, "learning_rate": 2.9820189480090166e-05, "loss": 4.3296, "step": 14348 }, { "epoch": 0.43827122785583383, "grad_norm": 0.39998653531074524, "learning_rate": 2.9817835574541825e-05, "loss": 4.2443, "step": 14349 }, { "epoch": 0.4383017715332926, "grad_norm": 0.387549489736557, "learning_rate": 2.9815481624633203e-05, "loss": 4.3373, "step": 14350 }, { "epoch": 0.4383323152107514, "grad_norm": 0.3762202560901642, "learning_rate": 2.981312763038595e-05, "loss": 4.3404, "step": 14351 }, { "epoch": 0.43836285888821014, "grad_norm": 0.3813802897930145, "learning_rate": 2.9810773591821766e-05, "loss": 4.2475, "step": 14352 }, { "epoch": 0.4383934025656689, "grad_norm": 0.3984343707561493, "learning_rate": 2.980841950896232e-05, "loss": 4.3385, "step": 14353 }, { "epoch": 0.4384239462431277, "grad_norm": 0.39504092931747437, "learning_rate": 2.9806065381829273e-05, "loss": 4.3068, "step": 14354 }, { "epoch": 0.43845448992058644, "grad_norm": 0.37752506136894226, "learning_rate": 2.9803711210444323e-05, "loss": 4.3624, "step": 14355 }, { "epoch": 0.4384850335980452, "grad_norm": 0.38463833928108215, "learning_rate": 2.9801356994829133e-05, "loss": 4.3257, "step": 14356 }, { "epoch": 0.438515577275504, "grad_norm": 0.38086068630218506, "learning_rate": 2.9799002735005372e-05, "loss": 4.3269, "step": 14357 }, { "epoch": 0.43854612095296275, "grad_norm": 0.401130348443985, "learning_rate": 2.9796648430994728e-05, "loss": 4.3898, "step": 14358 }, { "epoch": 0.4385766646304215, "grad_norm": 0.3909042775630951, "learning_rate": 2.979429408281888e-05, "loss": 4.229, "step": 14359 }, { "epoch": 0.43860720830788025, "grad_norm": 0.3919336795806885, "learning_rate": 2.97919396904995e-05, "loss": 4.2798, "step": 14360 }, { "epoch": 0.43863775198533905, "grad_norm": 0.3934287428855896, "learning_rate": 2.9789585254058262e-05, "loss": 4.3337, "step": 14361 }, { "epoch": 0.4386682956627978, "grad_norm": 0.4054754078388214, "learning_rate": 2.9787230773516854e-05, "loss": 4.2948, "step": 14362 }, { "epoch": 0.43869883934025655, "grad_norm": 0.4007316827774048, "learning_rate": 2.9784876248896953e-05, "loss": 4.3365, "step": 14363 }, { "epoch": 0.43872938301771536, "grad_norm": 0.3841380178928375, "learning_rate": 2.9782521680220233e-05, "loss": 4.324, "step": 14364 }, { "epoch": 0.4387599266951741, "grad_norm": 0.3892294466495514, "learning_rate": 2.978016706750838e-05, "loss": 4.1814, "step": 14365 }, { "epoch": 0.43879047037263286, "grad_norm": 0.39223530888557434, "learning_rate": 2.9777812410783072e-05, "loss": 4.3259, "step": 14366 }, { "epoch": 0.4388210140500916, "grad_norm": 0.3900808095932007, "learning_rate": 2.9775457710065984e-05, "loss": 4.2554, "step": 14367 }, { "epoch": 0.4388515577275504, "grad_norm": 0.3937569558620453, "learning_rate": 2.97731029653788e-05, "loss": 4.3527, "step": 14368 }, { "epoch": 0.43888210140500916, "grad_norm": 0.3779461979866028, "learning_rate": 2.9770748176743207e-05, "loss": 4.2057, "step": 14369 }, { "epoch": 0.4389126450824679, "grad_norm": 0.3941808044910431, "learning_rate": 2.9768393344180883e-05, "loss": 4.3651, "step": 14370 }, { "epoch": 0.4389431887599267, "grad_norm": 0.38299089670181274, "learning_rate": 2.9766038467713514e-05, "loss": 4.2743, "step": 14371 }, { "epoch": 0.43897373243738547, "grad_norm": 0.3894725739955902, "learning_rate": 2.9763683547362775e-05, "loss": 4.2974, "step": 14372 }, { "epoch": 0.4390042761148442, "grad_norm": 0.38482630252838135, "learning_rate": 2.976132858315035e-05, "loss": 4.2655, "step": 14373 }, { "epoch": 0.43903481979230297, "grad_norm": 0.386345237493515, "learning_rate": 2.9758973575097926e-05, "loss": 4.3878, "step": 14374 }, { "epoch": 0.43906536346976177, "grad_norm": 0.3883284330368042, "learning_rate": 2.975661852322718e-05, "loss": 4.3338, "step": 14375 }, { "epoch": 0.4390959071472205, "grad_norm": 0.39105740189552307, "learning_rate": 2.975426342755981e-05, "loss": 4.3501, "step": 14376 }, { "epoch": 0.43912645082467927, "grad_norm": 0.3945144712924957, "learning_rate": 2.9751908288117485e-05, "loss": 4.1625, "step": 14377 }, { "epoch": 0.4391569945021381, "grad_norm": 0.37893348932266235, "learning_rate": 2.9749553104921902e-05, "loss": 4.278, "step": 14378 }, { "epoch": 0.4391875381795968, "grad_norm": 0.38270869851112366, "learning_rate": 2.9747197877994743e-05, "loss": 4.3448, "step": 14379 }, { "epoch": 0.4392180818570556, "grad_norm": 0.3915739059448242, "learning_rate": 2.9744842607357692e-05, "loss": 4.2901, "step": 14380 }, { "epoch": 0.4392486255345144, "grad_norm": 0.39446011185646057, "learning_rate": 2.9742487293032427e-05, "loss": 4.2926, "step": 14381 }, { "epoch": 0.43927916921197313, "grad_norm": 0.38818874955177307, "learning_rate": 2.9740131935040648e-05, "loss": 4.3293, "step": 14382 }, { "epoch": 0.4393097128894319, "grad_norm": 0.3842620551586151, "learning_rate": 2.9737776533404043e-05, "loss": 4.305, "step": 14383 }, { "epoch": 0.43934025656689063, "grad_norm": 0.38370898365974426, "learning_rate": 2.973542108814429e-05, "loss": 4.3751, "step": 14384 }, { "epoch": 0.43937080024434944, "grad_norm": 0.37282103300094604, "learning_rate": 2.9733065599283074e-05, "loss": 4.3639, "step": 14385 }, { "epoch": 0.4394013439218082, "grad_norm": 0.3891200125217438, "learning_rate": 2.9730710066842098e-05, "loss": 4.2734, "step": 14386 }, { "epoch": 0.43943188759926693, "grad_norm": 0.3900661766529083, "learning_rate": 2.9728354490843046e-05, "loss": 4.3642, "step": 14387 }, { "epoch": 0.43946243127672574, "grad_norm": 0.40216657519340515, "learning_rate": 2.972599887130759e-05, "loss": 4.305, "step": 14388 }, { "epoch": 0.4394929749541845, "grad_norm": 0.3936566114425659, "learning_rate": 2.972364320825744e-05, "loss": 4.3764, "step": 14389 }, { "epoch": 0.43952351863164324, "grad_norm": 0.3898802697658539, "learning_rate": 2.9721287501714278e-05, "loss": 4.3485, "step": 14390 }, { "epoch": 0.439554062309102, "grad_norm": 0.37635338306427, "learning_rate": 2.9718931751699798e-05, "loss": 4.3677, "step": 14391 }, { "epoch": 0.4395846059865608, "grad_norm": 0.38873979449272156, "learning_rate": 2.9716575958235676e-05, "loss": 4.3431, "step": 14392 }, { "epoch": 0.43961514966401954, "grad_norm": 0.3806302547454834, "learning_rate": 2.971422012134362e-05, "loss": 4.3167, "step": 14393 }, { "epoch": 0.4396456933414783, "grad_norm": 0.37475255131721497, "learning_rate": 2.9711864241045317e-05, "loss": 4.2571, "step": 14394 }, { "epoch": 0.4396762370189371, "grad_norm": 0.3744322955608368, "learning_rate": 2.9709508317362462e-05, "loss": 4.3024, "step": 14395 }, { "epoch": 0.43970678069639585, "grad_norm": 0.3762321174144745, "learning_rate": 2.9707152350316735e-05, "loss": 4.392, "step": 14396 }, { "epoch": 0.4397373243738546, "grad_norm": 0.3946516513824463, "learning_rate": 2.9704796339929842e-05, "loss": 4.3725, "step": 14397 }, { "epoch": 0.4397678680513134, "grad_norm": 0.4064357876777649, "learning_rate": 2.970244028622346e-05, "loss": 4.2863, "step": 14398 }, { "epoch": 0.43979841172877215, "grad_norm": 0.3810965120792389, "learning_rate": 2.97000841892193e-05, "loss": 4.3371, "step": 14399 }, { "epoch": 0.4398289554062309, "grad_norm": 0.3902789056301117, "learning_rate": 2.9697728048939048e-05, "loss": 4.3244, "step": 14400 }, { "epoch": 0.43985949908368965, "grad_norm": 0.3773987591266632, "learning_rate": 2.96953718654044e-05, "loss": 4.307, "step": 14401 }, { "epoch": 0.43989004276114846, "grad_norm": 0.3840439021587372, "learning_rate": 2.9693015638637044e-05, "loss": 4.2759, "step": 14402 }, { "epoch": 0.4399205864386072, "grad_norm": 0.3751482367515564, "learning_rate": 2.969065936865869e-05, "loss": 4.3553, "step": 14403 }, { "epoch": 0.43995113011606596, "grad_norm": 0.38339245319366455, "learning_rate": 2.968830305549102e-05, "loss": 4.3157, "step": 14404 }, { "epoch": 0.43998167379352476, "grad_norm": 0.39270639419555664, "learning_rate": 2.968594669915572e-05, "loss": 4.3025, "step": 14405 }, { "epoch": 0.4400122174709835, "grad_norm": 0.47754979133605957, "learning_rate": 2.968359029967451e-05, "loss": 4.4114, "step": 14406 }, { "epoch": 0.44004276114844226, "grad_norm": 0.38730648159980774, "learning_rate": 2.9681233857069078e-05, "loss": 4.2424, "step": 14407 }, { "epoch": 0.440073304825901, "grad_norm": 0.3862006664276123, "learning_rate": 2.967887737136112e-05, "loss": 4.2841, "step": 14408 }, { "epoch": 0.4401038485033598, "grad_norm": 0.3853468894958496, "learning_rate": 2.967652084257232e-05, "loss": 4.2306, "step": 14409 }, { "epoch": 0.44013439218081857, "grad_norm": 0.38186657428741455, "learning_rate": 2.9674164270724404e-05, "loss": 4.2998, "step": 14410 }, { "epoch": 0.4401649358582773, "grad_norm": 0.3797885775566101, "learning_rate": 2.9671807655839053e-05, "loss": 4.2671, "step": 14411 }, { "epoch": 0.4401954795357361, "grad_norm": 0.38865888118743896, "learning_rate": 2.9669450997937953e-05, "loss": 4.3555, "step": 14412 }, { "epoch": 0.4402260232131949, "grad_norm": 0.37478795647621155, "learning_rate": 2.966709429704283e-05, "loss": 4.3973, "step": 14413 }, { "epoch": 0.4402565668906536, "grad_norm": 0.3838731646537781, "learning_rate": 2.9664737553175363e-05, "loss": 4.3907, "step": 14414 }, { "epoch": 0.4402871105681124, "grad_norm": 0.3860989212989807, "learning_rate": 2.9662380766357255e-05, "loss": 4.3344, "step": 14415 }, { "epoch": 0.4403176542455712, "grad_norm": 0.38377851247787476, "learning_rate": 2.9660023936610222e-05, "loss": 4.3253, "step": 14416 }, { "epoch": 0.4403481979230299, "grad_norm": 0.40879979729652405, "learning_rate": 2.9657667063955946e-05, "loss": 4.3083, "step": 14417 }, { "epoch": 0.4403787416004887, "grad_norm": 0.3893192708492279, "learning_rate": 2.965531014841614e-05, "loss": 4.3262, "step": 14418 }, { "epoch": 0.4404092852779475, "grad_norm": 0.4030761420726776, "learning_rate": 2.9652953190012496e-05, "loss": 4.3079, "step": 14419 }, { "epoch": 0.44043982895540623, "grad_norm": 0.3822970390319824, "learning_rate": 2.9650596188766716e-05, "loss": 4.4034, "step": 14420 }, { "epoch": 0.440470372632865, "grad_norm": 0.3854112923145294, "learning_rate": 2.9648239144700514e-05, "loss": 4.3086, "step": 14421 }, { "epoch": 0.4405009163103238, "grad_norm": 0.3842936158180237, "learning_rate": 2.9645882057835573e-05, "loss": 4.3522, "step": 14422 }, { "epoch": 0.44053145998778254, "grad_norm": 0.37586909532546997, "learning_rate": 2.9643524928193615e-05, "loss": 4.2698, "step": 14423 }, { "epoch": 0.4405620036652413, "grad_norm": 0.3937770426273346, "learning_rate": 2.9641167755796335e-05, "loss": 4.3261, "step": 14424 }, { "epoch": 0.44059254734270004, "grad_norm": 0.3926417827606201, "learning_rate": 2.963881054066544e-05, "loss": 4.217, "step": 14425 }, { "epoch": 0.44062309102015884, "grad_norm": 0.38570407032966614, "learning_rate": 2.963645328282263e-05, "loss": 4.2303, "step": 14426 }, { "epoch": 0.4406536346976176, "grad_norm": 0.3836571276187897, "learning_rate": 2.9634095982289605e-05, "loss": 4.3515, "step": 14427 }, { "epoch": 0.44068417837507634, "grad_norm": 0.3873315453529358, "learning_rate": 2.963173863908808e-05, "loss": 4.3442, "step": 14428 }, { "epoch": 0.44071472205253515, "grad_norm": 0.38935157656669617, "learning_rate": 2.962938125323975e-05, "loss": 4.2782, "step": 14429 }, { "epoch": 0.4407452657299939, "grad_norm": 0.3908008933067322, "learning_rate": 2.9627023824766337e-05, "loss": 4.3278, "step": 14430 }, { "epoch": 0.44077580940745265, "grad_norm": 0.38996076583862305, "learning_rate": 2.962466635368953e-05, "loss": 4.2726, "step": 14431 }, { "epoch": 0.44080635308491145, "grad_norm": 0.400929719209671, "learning_rate": 2.962230884003104e-05, "loss": 4.2696, "step": 14432 }, { "epoch": 0.4408368967623702, "grad_norm": 0.39365673065185547, "learning_rate": 2.9619951283812586e-05, "loss": 4.3436, "step": 14433 }, { "epoch": 0.44086744043982895, "grad_norm": 0.37415507435798645, "learning_rate": 2.961759368505586e-05, "loss": 4.2556, "step": 14434 }, { "epoch": 0.4408979841172877, "grad_norm": 0.3787188231945038, "learning_rate": 2.9615236043782573e-05, "loss": 4.3477, "step": 14435 }, { "epoch": 0.4409285277947465, "grad_norm": 0.394092321395874, "learning_rate": 2.961287836001443e-05, "loss": 4.3446, "step": 14436 }, { "epoch": 0.44095907147220526, "grad_norm": 0.399172306060791, "learning_rate": 2.9610520633773153e-05, "loss": 4.2949, "step": 14437 }, { "epoch": 0.440989615149664, "grad_norm": 0.38145866990089417, "learning_rate": 2.9608162865080436e-05, "loss": 4.2441, "step": 14438 }, { "epoch": 0.4410201588271228, "grad_norm": 0.38476234674453735, "learning_rate": 2.9605805053957995e-05, "loss": 4.3162, "step": 14439 }, { "epoch": 0.44105070250458156, "grad_norm": 0.37988147139549255, "learning_rate": 2.9603447200427542e-05, "loss": 4.2856, "step": 14440 }, { "epoch": 0.4410812461820403, "grad_norm": 0.38677534461021423, "learning_rate": 2.960108930451078e-05, "loss": 4.3037, "step": 14441 }, { "epoch": 0.44111178985949906, "grad_norm": 0.3815670907497406, "learning_rate": 2.9598731366229436e-05, "loss": 4.3582, "step": 14442 }, { "epoch": 0.44114233353695786, "grad_norm": 0.38258621096611023, "learning_rate": 2.9596373385605193e-05, "loss": 4.1623, "step": 14443 }, { "epoch": 0.4411728772144166, "grad_norm": 0.3788168132305145, "learning_rate": 2.959401536265978e-05, "loss": 4.3132, "step": 14444 }, { "epoch": 0.44120342089187536, "grad_norm": 0.4104132354259491, "learning_rate": 2.959165729741491e-05, "loss": 4.3486, "step": 14445 }, { "epoch": 0.44123396456933417, "grad_norm": 0.3962785601615906, "learning_rate": 2.9589299189892283e-05, "loss": 4.2503, "step": 14446 }, { "epoch": 0.4412645082467929, "grad_norm": 0.3841494917869568, "learning_rate": 2.9586941040113625e-05, "loss": 4.2992, "step": 14447 }, { "epoch": 0.44129505192425167, "grad_norm": 0.3771495521068573, "learning_rate": 2.9584582848100638e-05, "loss": 4.3169, "step": 14448 }, { "epoch": 0.4413255956017104, "grad_norm": 0.38341400027275085, "learning_rate": 2.958222461387504e-05, "loss": 4.2692, "step": 14449 }, { "epoch": 0.4413561392791692, "grad_norm": 0.4166509211063385, "learning_rate": 2.957986633745855e-05, "loss": 4.3651, "step": 14450 }, { "epoch": 0.441386682956628, "grad_norm": 0.3882277309894562, "learning_rate": 2.9577508018872874e-05, "loss": 4.3206, "step": 14451 }, { "epoch": 0.4414172266340867, "grad_norm": 0.3774434030056, "learning_rate": 2.957514965813973e-05, "loss": 4.4202, "step": 14452 }, { "epoch": 0.44144777031154553, "grad_norm": 0.38825979828834534, "learning_rate": 2.9572791255280824e-05, "loss": 4.3814, "step": 14453 }, { "epoch": 0.4414783139890043, "grad_norm": 0.385449081659317, "learning_rate": 2.957043281031788e-05, "loss": 4.3238, "step": 14454 }, { "epoch": 0.44150885766646303, "grad_norm": 0.3823411464691162, "learning_rate": 2.956807432327261e-05, "loss": 4.3841, "step": 14455 }, { "epoch": 0.44153940134392183, "grad_norm": 0.3806200623512268, "learning_rate": 2.9565715794166733e-05, "loss": 4.3247, "step": 14456 }, { "epoch": 0.4415699450213806, "grad_norm": 0.38536566495895386, "learning_rate": 2.956335722302197e-05, "loss": 4.3322, "step": 14457 }, { "epoch": 0.44160048869883933, "grad_norm": 0.3767777383327484, "learning_rate": 2.9560998609860024e-05, "loss": 4.3348, "step": 14458 }, { "epoch": 0.4416310323762981, "grad_norm": 0.38178566098213196, "learning_rate": 2.955863995470262e-05, "loss": 4.3098, "step": 14459 }, { "epoch": 0.4416615760537569, "grad_norm": 0.37317338585853577, "learning_rate": 2.9556281257571466e-05, "loss": 4.2837, "step": 14460 }, { "epoch": 0.44169211973121564, "grad_norm": 0.3773370385169983, "learning_rate": 2.9553922518488297e-05, "loss": 4.3435, "step": 14461 }, { "epoch": 0.4417226634086744, "grad_norm": 0.3753505051136017, "learning_rate": 2.9551563737474818e-05, "loss": 4.2659, "step": 14462 }, { "epoch": 0.4417532070861332, "grad_norm": 0.3837992250919342, "learning_rate": 2.954920491455275e-05, "loss": 4.2831, "step": 14463 }, { "epoch": 0.44178375076359194, "grad_norm": 0.37328317761421204, "learning_rate": 2.954684604974382e-05, "loss": 4.3046, "step": 14464 }, { "epoch": 0.4418142944410507, "grad_norm": 0.39499950408935547, "learning_rate": 2.9544487143069742e-05, "loss": 4.383, "step": 14465 }, { "epoch": 0.44184483811850944, "grad_norm": 0.3913106322288513, "learning_rate": 2.9542128194552232e-05, "loss": 4.3259, "step": 14466 }, { "epoch": 0.44187538179596825, "grad_norm": 0.37822553515434265, "learning_rate": 2.953976920421301e-05, "loss": 4.3276, "step": 14467 }, { "epoch": 0.441905925473427, "grad_norm": 0.3768053650856018, "learning_rate": 2.9537410172073798e-05, "loss": 4.3714, "step": 14468 }, { "epoch": 0.44193646915088575, "grad_norm": 0.3903639018535614, "learning_rate": 2.953505109815632e-05, "loss": 4.324, "step": 14469 }, { "epoch": 0.44196701282834455, "grad_norm": 0.38664427399635315, "learning_rate": 2.9532691982482285e-05, "loss": 4.2844, "step": 14470 }, { "epoch": 0.4419975565058033, "grad_norm": 0.39938315749168396, "learning_rate": 2.9530332825073437e-05, "loss": 4.287, "step": 14471 }, { "epoch": 0.44202810018326205, "grad_norm": 0.38152357935905457, "learning_rate": 2.9527973625951482e-05, "loss": 4.3379, "step": 14472 }, { "epoch": 0.44205864386072086, "grad_norm": 0.3839380443096161, "learning_rate": 2.9525614385138145e-05, "loss": 4.2783, "step": 14473 }, { "epoch": 0.4420891875381796, "grad_norm": 0.39303523302078247, "learning_rate": 2.952325510265515e-05, "loss": 4.2947, "step": 14474 }, { "epoch": 0.44211973121563836, "grad_norm": 0.39080357551574707, "learning_rate": 2.952089577852422e-05, "loss": 4.3009, "step": 14475 }, { "epoch": 0.4421502748930971, "grad_norm": 0.3789012134075165, "learning_rate": 2.9518536412767077e-05, "loss": 4.3486, "step": 14476 }, { "epoch": 0.4421808185705559, "grad_norm": 0.3847172260284424, "learning_rate": 2.9516177005405443e-05, "loss": 4.3333, "step": 14477 }, { "epoch": 0.44221136224801466, "grad_norm": 0.3776858150959015, "learning_rate": 2.9513817556461054e-05, "loss": 4.3028, "step": 14478 }, { "epoch": 0.4422419059254734, "grad_norm": 0.3910532295703888, "learning_rate": 2.9511458065955622e-05, "loss": 4.3223, "step": 14479 }, { "epoch": 0.4422724496029322, "grad_norm": 0.3821597993373871, "learning_rate": 2.9509098533910874e-05, "loss": 4.3297, "step": 14480 }, { "epoch": 0.44230299328039097, "grad_norm": 0.38893988728523254, "learning_rate": 2.950673896034854e-05, "loss": 4.2784, "step": 14481 }, { "epoch": 0.4423335369578497, "grad_norm": 0.3770535886287689, "learning_rate": 2.950437934529034e-05, "loss": 4.2708, "step": 14482 }, { "epoch": 0.44236408063530847, "grad_norm": 0.38232970237731934, "learning_rate": 2.950201968875801e-05, "loss": 4.2152, "step": 14483 }, { "epoch": 0.44239462431276727, "grad_norm": 0.38356050848960876, "learning_rate": 2.949965999077326e-05, "loss": 4.3582, "step": 14484 }, { "epoch": 0.442425167990226, "grad_norm": 0.37332433462142944, "learning_rate": 2.949730025135783e-05, "loss": 4.2503, "step": 14485 }, { "epoch": 0.44245571166768477, "grad_norm": 0.37322038412094116, "learning_rate": 2.949494047053345e-05, "loss": 4.2852, "step": 14486 }, { "epoch": 0.4424862553451436, "grad_norm": 0.38226601481437683, "learning_rate": 2.949258064832183e-05, "loss": 4.2805, "step": 14487 }, { "epoch": 0.4425167990226023, "grad_norm": 0.3880964517593384, "learning_rate": 2.9490220784744725e-05, "loss": 4.2349, "step": 14488 }, { "epoch": 0.4425473427000611, "grad_norm": 0.3826215863227844, "learning_rate": 2.9487860879823842e-05, "loss": 4.347, "step": 14489 }, { "epoch": 0.4425778863775199, "grad_norm": 0.38740432262420654, "learning_rate": 2.948550093358091e-05, "loss": 4.2903, "step": 14490 }, { "epoch": 0.44260843005497863, "grad_norm": 0.38033005595207214, "learning_rate": 2.948314094603768e-05, "loss": 4.3493, "step": 14491 }, { "epoch": 0.4426389737324374, "grad_norm": 0.3854575455188751, "learning_rate": 2.9480780917215857e-05, "loss": 4.2992, "step": 14492 }, { "epoch": 0.44266951740989613, "grad_norm": 0.38409310579299927, "learning_rate": 2.9478420847137177e-05, "loss": 4.3524, "step": 14493 }, { "epoch": 0.44270006108735493, "grad_norm": 0.3738134205341339, "learning_rate": 2.9476060735823374e-05, "loss": 4.3616, "step": 14494 }, { "epoch": 0.4427306047648137, "grad_norm": 0.3798021078109741, "learning_rate": 2.9473700583296183e-05, "loss": 4.2913, "step": 14495 }, { "epoch": 0.44276114844227243, "grad_norm": 0.38965898752212524, "learning_rate": 2.947134038957733e-05, "loss": 4.3116, "step": 14496 }, { "epoch": 0.44279169211973124, "grad_norm": 0.3905829191207886, "learning_rate": 2.9468980154688546e-05, "loss": 4.2068, "step": 14497 }, { "epoch": 0.44282223579719, "grad_norm": 0.3933236002922058, "learning_rate": 2.9466619878651568e-05, "loss": 4.3264, "step": 14498 }, { "epoch": 0.44285277947464874, "grad_norm": 0.3997544050216675, "learning_rate": 2.946425956148812e-05, "loss": 4.2681, "step": 14499 }, { "epoch": 0.4428833231521075, "grad_norm": 0.39144694805145264, "learning_rate": 2.9461899203219945e-05, "loss": 4.3265, "step": 14500 }, { "epoch": 0.4429138668295663, "grad_norm": 0.3787602484226227, "learning_rate": 2.9459538803868757e-05, "loss": 4.2779, "step": 14501 }, { "epoch": 0.44294441050702504, "grad_norm": 0.3859218955039978, "learning_rate": 2.945717836345631e-05, "loss": 4.3063, "step": 14502 }, { "epoch": 0.4429749541844838, "grad_norm": 0.3954382538795471, "learning_rate": 2.9454817882004333e-05, "loss": 4.3269, "step": 14503 }, { "epoch": 0.4430054978619426, "grad_norm": 0.3862473666667938, "learning_rate": 2.9452457359534558e-05, "loss": 4.3872, "step": 14504 }, { "epoch": 0.44303604153940135, "grad_norm": 0.37603384256362915, "learning_rate": 2.9450096796068717e-05, "loss": 4.4164, "step": 14505 }, { "epoch": 0.4430665852168601, "grad_norm": 0.3980030119419098, "learning_rate": 2.9447736191628544e-05, "loss": 4.395, "step": 14506 }, { "epoch": 0.4430971288943189, "grad_norm": 0.4074828326702118, "learning_rate": 2.9445375546235775e-05, "loss": 4.3477, "step": 14507 }, { "epoch": 0.44312767257177765, "grad_norm": 0.3976598381996155, "learning_rate": 2.944301485991215e-05, "loss": 4.3322, "step": 14508 }, { "epoch": 0.4431582162492364, "grad_norm": 0.3864496648311615, "learning_rate": 2.944065413267941e-05, "loss": 4.3574, "step": 14509 }, { "epoch": 0.44318875992669515, "grad_norm": 0.39277195930480957, "learning_rate": 2.943829336455927e-05, "loss": 4.2712, "step": 14510 }, { "epoch": 0.44321930360415396, "grad_norm": 0.38744351267814636, "learning_rate": 2.9435932555573485e-05, "loss": 4.2596, "step": 14511 }, { "epoch": 0.4432498472816127, "grad_norm": 0.39352336525917053, "learning_rate": 2.9433571705743802e-05, "loss": 4.3834, "step": 14512 }, { "epoch": 0.44328039095907146, "grad_norm": 0.38754546642303467, "learning_rate": 2.9431210815091936e-05, "loss": 4.3397, "step": 14513 }, { "epoch": 0.44331093463653026, "grad_norm": 0.37752366065979004, "learning_rate": 2.942884988363963e-05, "loss": 4.224, "step": 14514 }, { "epoch": 0.443341478313989, "grad_norm": 0.3994010090827942, "learning_rate": 2.9426488911408628e-05, "loss": 4.3715, "step": 14515 }, { "epoch": 0.44337202199144776, "grad_norm": 0.3823346793651581, "learning_rate": 2.9424127898420666e-05, "loss": 4.1694, "step": 14516 }, { "epoch": 0.4434025656689065, "grad_norm": 0.3998677134513855, "learning_rate": 2.942176684469749e-05, "loss": 4.3536, "step": 14517 }, { "epoch": 0.4434331093463653, "grad_norm": 0.3817569315433502, "learning_rate": 2.9419405750260824e-05, "loss": 4.3124, "step": 14518 }, { "epoch": 0.44346365302382407, "grad_norm": 0.38503941893577576, "learning_rate": 2.9417044615132423e-05, "loss": 4.2463, "step": 14519 }, { "epoch": 0.4434941967012828, "grad_norm": 0.3846110999584198, "learning_rate": 2.9414683439334023e-05, "loss": 4.2203, "step": 14520 }, { "epoch": 0.4435247403787416, "grad_norm": 0.38159629702568054, "learning_rate": 2.9412322222887355e-05, "loss": 4.3254, "step": 14521 }, { "epoch": 0.44355528405620037, "grad_norm": 0.38843005895614624, "learning_rate": 2.9409960965814175e-05, "loss": 4.2968, "step": 14522 }, { "epoch": 0.4435858277336591, "grad_norm": 0.38241851329803467, "learning_rate": 2.9407599668136214e-05, "loss": 4.4129, "step": 14523 }, { "epoch": 0.44361637141111787, "grad_norm": 0.3878648281097412, "learning_rate": 2.9405238329875218e-05, "loss": 4.3785, "step": 14524 }, { "epoch": 0.4436469150885767, "grad_norm": 0.38012078404426575, "learning_rate": 2.9402876951052927e-05, "loss": 4.3171, "step": 14525 }, { "epoch": 0.4436774587660354, "grad_norm": 0.3878045678138733, "learning_rate": 2.940051553169108e-05, "loss": 4.4069, "step": 14526 }, { "epoch": 0.4437080024434942, "grad_norm": 0.37353190779685974, "learning_rate": 2.939815407181143e-05, "loss": 4.3019, "step": 14527 }, { "epoch": 0.443738546120953, "grad_norm": 0.3911096453666687, "learning_rate": 2.9395792571435716e-05, "loss": 4.3068, "step": 14528 }, { "epoch": 0.44376908979841173, "grad_norm": 0.3929727077484131, "learning_rate": 2.9393431030585672e-05, "loss": 4.2462, "step": 14529 }, { "epoch": 0.4437996334758705, "grad_norm": 0.38445279002189636, "learning_rate": 2.939106944928306e-05, "loss": 4.2816, "step": 14530 }, { "epoch": 0.4438301771533293, "grad_norm": 0.3941662907600403, "learning_rate": 2.9388707827549598e-05, "loss": 4.4066, "step": 14531 }, { "epoch": 0.44386072083078804, "grad_norm": 0.38079607486724854, "learning_rate": 2.938634616540706e-05, "loss": 4.2816, "step": 14532 }, { "epoch": 0.4438912645082468, "grad_norm": 0.3852478563785553, "learning_rate": 2.9383984462877175e-05, "loss": 4.2854, "step": 14533 }, { "epoch": 0.44392180818570554, "grad_norm": 0.39304277300834656, "learning_rate": 2.9381622719981688e-05, "loss": 4.2466, "step": 14534 }, { "epoch": 0.44395235186316434, "grad_norm": 0.3801390528678894, "learning_rate": 2.9379260936742355e-05, "loss": 4.3621, "step": 14535 }, { "epoch": 0.4439828955406231, "grad_norm": 0.38997313380241394, "learning_rate": 2.9376899113180905e-05, "loss": 4.4238, "step": 14536 }, { "epoch": 0.44401343921808184, "grad_norm": 0.39082521200180054, "learning_rate": 2.9374537249319102e-05, "loss": 4.3868, "step": 14537 }, { "epoch": 0.44404398289554065, "grad_norm": 0.3930679261684418, "learning_rate": 2.9372175345178677e-05, "loss": 4.4084, "step": 14538 }, { "epoch": 0.4440745265729994, "grad_norm": 0.37451109290122986, "learning_rate": 2.9369813400781395e-05, "loss": 4.3663, "step": 14539 }, { "epoch": 0.44410507025045814, "grad_norm": 0.38475242257118225, "learning_rate": 2.936745141614899e-05, "loss": 4.337, "step": 14540 }, { "epoch": 0.4441356139279169, "grad_norm": 0.39134252071380615, "learning_rate": 2.9365089391303212e-05, "loss": 4.2238, "step": 14541 }, { "epoch": 0.4441661576053757, "grad_norm": 0.38152021169662476, "learning_rate": 2.936272732626581e-05, "loss": 4.2719, "step": 14542 }, { "epoch": 0.44419670128283445, "grad_norm": 0.3928355872631073, "learning_rate": 2.9360365221058545e-05, "loss": 4.316, "step": 14543 }, { "epoch": 0.4442272449602932, "grad_norm": 0.38510656356811523, "learning_rate": 2.935800307570315e-05, "loss": 4.2975, "step": 14544 }, { "epoch": 0.444257788637752, "grad_norm": 0.393049418926239, "learning_rate": 2.9355640890221375e-05, "loss": 4.2568, "step": 14545 }, { "epoch": 0.44428833231521075, "grad_norm": 0.3807300925254822, "learning_rate": 2.9353278664634982e-05, "loss": 4.3161, "step": 14546 }, { "epoch": 0.4443188759926695, "grad_norm": 0.38868942856788635, "learning_rate": 2.9350916398965712e-05, "loss": 4.3365, "step": 14547 }, { "epoch": 0.4443494196701283, "grad_norm": 0.3870193660259247, "learning_rate": 2.9348554093235308e-05, "loss": 4.3644, "step": 14548 }, { "epoch": 0.44437996334758706, "grad_norm": 0.38398945331573486, "learning_rate": 2.934619174746554e-05, "loss": 4.2946, "step": 14549 }, { "epoch": 0.4444105070250458, "grad_norm": 0.3907892107963562, "learning_rate": 2.9343829361678153e-05, "loss": 4.2602, "step": 14550 }, { "epoch": 0.44444105070250456, "grad_norm": 0.38611072301864624, "learning_rate": 2.934146693589489e-05, "loss": 4.2908, "step": 14551 }, { "epoch": 0.44447159437996336, "grad_norm": 0.40660399198532104, "learning_rate": 2.9339104470137512e-05, "loss": 4.2112, "step": 14552 }, { "epoch": 0.4445021380574221, "grad_norm": 0.3832838237285614, "learning_rate": 2.9336741964427772e-05, "loss": 4.2621, "step": 14553 }, { "epoch": 0.44453268173488086, "grad_norm": 0.40102773904800415, "learning_rate": 2.933437941878741e-05, "loss": 4.2658, "step": 14554 }, { "epoch": 0.44456322541233967, "grad_norm": 0.38982075452804565, "learning_rate": 2.933201683323819e-05, "loss": 4.295, "step": 14555 }, { "epoch": 0.4445937690897984, "grad_norm": 0.38623735308647156, "learning_rate": 2.9329654207801867e-05, "loss": 4.2384, "step": 14556 }, { "epoch": 0.44462431276725717, "grad_norm": 0.39355459809303284, "learning_rate": 2.932729154250019e-05, "loss": 4.2641, "step": 14557 }, { "epoch": 0.4446548564447159, "grad_norm": 0.3855038583278656, "learning_rate": 2.932492883735492e-05, "loss": 4.2774, "step": 14558 }, { "epoch": 0.4446854001221747, "grad_norm": 0.3961496353149414, "learning_rate": 2.9322566092387804e-05, "loss": 4.3026, "step": 14559 }, { "epoch": 0.4447159437996335, "grad_norm": 0.40782734751701355, "learning_rate": 2.9320203307620597e-05, "loss": 4.3401, "step": 14560 }, { "epoch": 0.4447464874770922, "grad_norm": 0.39467939734458923, "learning_rate": 2.9317840483075055e-05, "loss": 4.3568, "step": 14561 }, { "epoch": 0.44477703115455103, "grad_norm": 0.38843590021133423, "learning_rate": 2.9315477618772934e-05, "loss": 4.2469, "step": 14562 }, { "epoch": 0.4448075748320098, "grad_norm": 0.3839637041091919, "learning_rate": 2.9313114714736e-05, "loss": 4.3766, "step": 14563 }, { "epoch": 0.4448381185094685, "grad_norm": 0.3847813904285431, "learning_rate": 2.9310751770985994e-05, "loss": 4.2468, "step": 14564 }, { "epoch": 0.44486866218692733, "grad_norm": 0.39479097723960876, "learning_rate": 2.9308388787544684e-05, "loss": 4.3469, "step": 14565 }, { "epoch": 0.4448992058643861, "grad_norm": 0.3919220268726349, "learning_rate": 2.930602576443382e-05, "loss": 4.3798, "step": 14566 }, { "epoch": 0.44492974954184483, "grad_norm": 0.37430670857429504, "learning_rate": 2.9303662701675173e-05, "loss": 4.3559, "step": 14567 }, { "epoch": 0.4449602932193036, "grad_norm": 0.3816460072994232, "learning_rate": 2.930129959929048e-05, "loss": 4.2372, "step": 14568 }, { "epoch": 0.4449908368967624, "grad_norm": 0.38917332887649536, "learning_rate": 2.929893645730151e-05, "loss": 4.2661, "step": 14569 }, { "epoch": 0.44502138057422114, "grad_norm": 0.3804875612258911, "learning_rate": 2.9296573275730027e-05, "loss": 4.2857, "step": 14570 }, { "epoch": 0.4450519242516799, "grad_norm": 0.3870532214641571, "learning_rate": 2.929421005459778e-05, "loss": 4.3237, "step": 14571 }, { "epoch": 0.4450824679291387, "grad_norm": 0.3900739550590515, "learning_rate": 2.9291846793926535e-05, "loss": 4.363, "step": 14572 }, { "epoch": 0.44511301160659744, "grad_norm": 0.3905746042728424, "learning_rate": 2.928948349373805e-05, "loss": 4.2758, "step": 14573 }, { "epoch": 0.4451435552840562, "grad_norm": 0.3839187026023865, "learning_rate": 2.9287120154054088e-05, "loss": 4.3472, "step": 14574 }, { "epoch": 0.44517409896151494, "grad_norm": 0.3804219365119934, "learning_rate": 2.928475677489641e-05, "loss": 4.2853, "step": 14575 }, { "epoch": 0.44520464263897375, "grad_norm": 0.40941402316093445, "learning_rate": 2.9282393356286764e-05, "loss": 4.3953, "step": 14576 }, { "epoch": 0.4452351863164325, "grad_norm": 0.38898712396621704, "learning_rate": 2.9280029898246924e-05, "loss": 4.2615, "step": 14577 }, { "epoch": 0.44526572999389125, "grad_norm": 0.37621667981147766, "learning_rate": 2.9277666400798653e-05, "loss": 4.3783, "step": 14578 }, { "epoch": 0.44529627367135005, "grad_norm": 0.39565712213516235, "learning_rate": 2.92753028639637e-05, "loss": 4.321, "step": 14579 }, { "epoch": 0.4453268173488088, "grad_norm": 0.3820638060569763, "learning_rate": 2.9272939287763834e-05, "loss": 4.3624, "step": 14580 }, { "epoch": 0.44535736102626755, "grad_norm": 0.40069857239723206, "learning_rate": 2.927057567222083e-05, "loss": 4.1856, "step": 14581 }, { "epoch": 0.44538790470372636, "grad_norm": 0.38528627157211304, "learning_rate": 2.9268212017356432e-05, "loss": 4.2662, "step": 14582 }, { "epoch": 0.4454184483811851, "grad_norm": 0.3783540427684784, "learning_rate": 2.9265848323192412e-05, "loss": 4.2617, "step": 14583 }, { "epoch": 0.44544899205864386, "grad_norm": 0.3744894862174988, "learning_rate": 2.926348458975054e-05, "loss": 4.2694, "step": 14584 }, { "epoch": 0.4454795357361026, "grad_norm": 0.3811143636703491, "learning_rate": 2.9261120817052567e-05, "loss": 4.2927, "step": 14585 }, { "epoch": 0.4455100794135614, "grad_norm": 0.3893281817436218, "learning_rate": 2.9258757005120264e-05, "loss": 4.3104, "step": 14586 }, { "epoch": 0.44554062309102016, "grad_norm": 0.38858044147491455, "learning_rate": 2.925639315397539e-05, "loss": 4.3016, "step": 14587 }, { "epoch": 0.4455711667684789, "grad_norm": 0.386735200881958, "learning_rate": 2.9254029263639727e-05, "loss": 4.3954, "step": 14588 }, { "epoch": 0.4456017104459377, "grad_norm": 0.38892415165901184, "learning_rate": 2.925166533413502e-05, "loss": 4.3237, "step": 14589 }, { "epoch": 0.44563225412339647, "grad_norm": 0.39687296748161316, "learning_rate": 2.9249301365483056e-05, "loss": 4.3737, "step": 14590 }, { "epoch": 0.4456627978008552, "grad_norm": 0.38012662529945374, "learning_rate": 2.9246937357705585e-05, "loss": 4.2806, "step": 14591 }, { "epoch": 0.44569334147831396, "grad_norm": 0.38792890310287476, "learning_rate": 2.9244573310824375e-05, "loss": 4.3158, "step": 14592 }, { "epoch": 0.44572388515577277, "grad_norm": 0.37688973546028137, "learning_rate": 2.9242209224861193e-05, "loss": 4.2564, "step": 14593 }, { "epoch": 0.4457544288332315, "grad_norm": 0.38047245144844055, "learning_rate": 2.9239845099837816e-05, "loss": 4.2789, "step": 14594 }, { "epoch": 0.44578497251069027, "grad_norm": 0.3804279863834381, "learning_rate": 2.9237480935776e-05, "loss": 4.3057, "step": 14595 }, { "epoch": 0.4458155161881491, "grad_norm": 0.3876477777957916, "learning_rate": 2.9235116732697514e-05, "loss": 4.2827, "step": 14596 }, { "epoch": 0.4458460598656078, "grad_norm": 0.3901061713695526, "learning_rate": 2.9232752490624144e-05, "loss": 4.3275, "step": 14597 }, { "epoch": 0.4458766035430666, "grad_norm": 0.38967904448509216, "learning_rate": 2.9230388209577643e-05, "loss": 4.2311, "step": 14598 }, { "epoch": 0.4459071472205253, "grad_norm": 0.39830923080444336, "learning_rate": 2.922802388957978e-05, "loss": 4.2392, "step": 14599 }, { "epoch": 0.44593769089798413, "grad_norm": 0.3845422863960266, "learning_rate": 2.9225659530652323e-05, "loss": 4.2832, "step": 14600 }, { "epoch": 0.4459682345754429, "grad_norm": 0.38638076186180115, "learning_rate": 2.9223295132817048e-05, "loss": 4.2813, "step": 14601 }, { "epoch": 0.44599877825290163, "grad_norm": 0.3906075656414032, "learning_rate": 2.9220930696095727e-05, "loss": 4.3319, "step": 14602 }, { "epoch": 0.44602932193036043, "grad_norm": 0.3791385293006897, "learning_rate": 2.921856622051012e-05, "loss": 4.2944, "step": 14603 }, { "epoch": 0.4460598656078192, "grad_norm": 0.37972986698150635, "learning_rate": 2.921620170608201e-05, "loss": 4.3033, "step": 14604 }, { "epoch": 0.44609040928527793, "grad_norm": 0.3777501583099365, "learning_rate": 2.9213837152833163e-05, "loss": 4.3577, "step": 14605 }, { "epoch": 0.44612095296273674, "grad_norm": 0.38457340002059937, "learning_rate": 2.9211472560785352e-05, "loss": 4.3466, "step": 14606 }, { "epoch": 0.4461514966401955, "grad_norm": 0.39056771993637085, "learning_rate": 2.9209107929960343e-05, "loss": 4.3007, "step": 14607 }, { "epoch": 0.44618204031765424, "grad_norm": 0.3872213065624237, "learning_rate": 2.920674326037992e-05, "loss": 4.3314, "step": 14608 }, { "epoch": 0.446212583995113, "grad_norm": 0.37832972407341003, "learning_rate": 2.9204378552065847e-05, "loss": 4.3369, "step": 14609 }, { "epoch": 0.4462431276725718, "grad_norm": 0.38184210658073425, "learning_rate": 2.920201380503989e-05, "loss": 4.3424, "step": 14610 }, { "epoch": 0.44627367135003054, "grad_norm": 0.3842697739601135, "learning_rate": 2.919964901932384e-05, "loss": 4.3398, "step": 14611 }, { "epoch": 0.4463042150274893, "grad_norm": 0.3864482641220093, "learning_rate": 2.919728419493946e-05, "loss": 4.3084, "step": 14612 }, { "epoch": 0.4463347587049481, "grad_norm": 0.38108697533607483, "learning_rate": 2.919491933190853e-05, "loss": 4.3189, "step": 14613 }, { "epoch": 0.44636530238240685, "grad_norm": 0.38007351756095886, "learning_rate": 2.9192554430252818e-05, "loss": 4.2439, "step": 14614 }, { "epoch": 0.4463958460598656, "grad_norm": 0.37674006819725037, "learning_rate": 2.9190189489994103e-05, "loss": 4.2704, "step": 14615 }, { "epoch": 0.44642638973732435, "grad_norm": 0.40127837657928467, "learning_rate": 2.918782451115416e-05, "loss": 4.2688, "step": 14616 }, { "epoch": 0.44645693341478315, "grad_norm": 0.39389073848724365, "learning_rate": 2.9185459493754758e-05, "loss": 4.3006, "step": 14617 }, { "epoch": 0.4464874770922419, "grad_norm": 0.383780837059021, "learning_rate": 2.9183094437817682e-05, "loss": 4.2932, "step": 14618 }, { "epoch": 0.44651802076970065, "grad_norm": 0.38676074147224426, "learning_rate": 2.9180729343364703e-05, "loss": 4.3268, "step": 14619 }, { "epoch": 0.44654856444715946, "grad_norm": 0.3768909275531769, "learning_rate": 2.9178364210417597e-05, "loss": 4.3242, "step": 14620 }, { "epoch": 0.4465791081246182, "grad_norm": 0.3803040683269501, "learning_rate": 2.9175999038998146e-05, "loss": 4.3792, "step": 14621 }, { "epoch": 0.44660965180207696, "grad_norm": 0.39396584033966064, "learning_rate": 2.917363382912814e-05, "loss": 4.3536, "step": 14622 }, { "epoch": 0.44664019547953576, "grad_norm": 0.3797570466995239, "learning_rate": 2.917126858082932e-05, "loss": 4.3507, "step": 14623 }, { "epoch": 0.4466707391569945, "grad_norm": 0.38920167088508606, "learning_rate": 2.9168903294123496e-05, "loss": 4.309, "step": 14624 }, { "epoch": 0.44670128283445326, "grad_norm": 0.3959050476551056, "learning_rate": 2.916653796903243e-05, "loss": 4.2877, "step": 14625 }, { "epoch": 0.446731826511912, "grad_norm": 0.39190196990966797, "learning_rate": 2.916417260557791e-05, "loss": 4.3247, "step": 14626 }, { "epoch": 0.4467623701893708, "grad_norm": 0.3840619623661041, "learning_rate": 2.916180720378171e-05, "loss": 4.238, "step": 14627 }, { "epoch": 0.44679291386682957, "grad_norm": 0.38703250885009766, "learning_rate": 2.9159441763665613e-05, "loss": 4.2363, "step": 14628 }, { "epoch": 0.4468234575442883, "grad_norm": 0.3816911578178406, "learning_rate": 2.91570762852514e-05, "loss": 4.2956, "step": 14629 }, { "epoch": 0.4468540012217471, "grad_norm": 0.38840046525001526, "learning_rate": 2.9154710768560845e-05, "loss": 4.3488, "step": 14630 }, { "epoch": 0.44688454489920587, "grad_norm": 0.42093175649642944, "learning_rate": 2.9152345213615734e-05, "loss": 4.4009, "step": 14631 }, { "epoch": 0.4469150885766646, "grad_norm": 0.37248510122299194, "learning_rate": 2.9149979620437844e-05, "loss": 4.3575, "step": 14632 }, { "epoch": 0.44694563225412337, "grad_norm": 0.3856857717037201, "learning_rate": 2.9147613989048962e-05, "loss": 4.3863, "step": 14633 }, { "epoch": 0.4469761759315822, "grad_norm": 0.3821426033973694, "learning_rate": 2.914524831947085e-05, "loss": 4.3334, "step": 14634 }, { "epoch": 0.4470067196090409, "grad_norm": 0.3861895203590393, "learning_rate": 2.914288261172532e-05, "loss": 4.289, "step": 14635 }, { "epoch": 0.4470372632864997, "grad_norm": 0.383497416973114, "learning_rate": 2.9140516865834138e-05, "loss": 4.2365, "step": 14636 }, { "epoch": 0.4470678069639585, "grad_norm": 0.38606899976730347, "learning_rate": 2.9138151081819087e-05, "loss": 4.3341, "step": 14637 }, { "epoch": 0.44709835064141723, "grad_norm": 0.3890208899974823, "learning_rate": 2.9135785259701954e-05, "loss": 4.3141, "step": 14638 }, { "epoch": 0.447128894318876, "grad_norm": 0.38826996088027954, "learning_rate": 2.9133419399504513e-05, "loss": 4.3519, "step": 14639 }, { "epoch": 0.4471594379963348, "grad_norm": 0.38894036412239075, "learning_rate": 2.9131053501248556e-05, "loss": 4.3341, "step": 14640 }, { "epoch": 0.44718998167379354, "grad_norm": 0.3811645209789276, "learning_rate": 2.912868756495587e-05, "loss": 4.3062, "step": 14641 }, { "epoch": 0.4472205253512523, "grad_norm": 0.3751193583011627, "learning_rate": 2.912632159064823e-05, "loss": 4.4143, "step": 14642 }, { "epoch": 0.44725106902871103, "grad_norm": 0.38132208585739136, "learning_rate": 2.9123955578347433e-05, "loss": 4.3084, "step": 14643 }, { "epoch": 0.44728161270616984, "grad_norm": 0.37987327575683594, "learning_rate": 2.9121589528075243e-05, "loss": 4.3924, "step": 14644 }, { "epoch": 0.4473121563836286, "grad_norm": 0.39003318548202515, "learning_rate": 2.9119223439853476e-05, "loss": 4.3384, "step": 14645 }, { "epoch": 0.44734270006108734, "grad_norm": 0.3968065679073334, "learning_rate": 2.9116857313703895e-05, "loss": 4.4125, "step": 14646 }, { "epoch": 0.44737324373854614, "grad_norm": 0.3951306939125061, "learning_rate": 2.9114491149648288e-05, "loss": 4.2926, "step": 14647 }, { "epoch": 0.4474037874160049, "grad_norm": 0.40304693579673767, "learning_rate": 2.9112124947708445e-05, "loss": 4.1928, "step": 14648 }, { "epoch": 0.44743433109346364, "grad_norm": 0.37825924158096313, "learning_rate": 2.9109758707906155e-05, "loss": 4.3491, "step": 14649 }, { "epoch": 0.4474648747709224, "grad_norm": 0.3939613401889801, "learning_rate": 2.910739243026321e-05, "loss": 4.297, "step": 14650 }, { "epoch": 0.4474954184483812, "grad_norm": 0.4001748859882355, "learning_rate": 2.9105026114801375e-05, "loss": 4.2709, "step": 14651 }, { "epoch": 0.44752596212583995, "grad_norm": 0.4316863417625427, "learning_rate": 2.9102659761542467e-05, "loss": 4.1941, "step": 14652 }, { "epoch": 0.4475565058032987, "grad_norm": 0.38841184973716736, "learning_rate": 2.9100293370508265e-05, "loss": 4.3698, "step": 14653 }, { "epoch": 0.4475870494807575, "grad_norm": 0.3845135271549225, "learning_rate": 2.9097926941720544e-05, "loss": 4.3052, "step": 14654 }, { "epoch": 0.44761759315821625, "grad_norm": 0.39461013674736023, "learning_rate": 2.9095560475201106e-05, "loss": 4.2488, "step": 14655 }, { "epoch": 0.447648136835675, "grad_norm": 0.37883180379867554, "learning_rate": 2.909319397097174e-05, "loss": 4.3499, "step": 14656 }, { "epoch": 0.4476786805131338, "grad_norm": 0.39141741394996643, "learning_rate": 2.9090827429054222e-05, "loss": 4.3697, "step": 14657 }, { "epoch": 0.44770922419059256, "grad_norm": 0.37593936920166016, "learning_rate": 2.908846084947036e-05, "loss": 4.3318, "step": 14658 }, { "epoch": 0.4477397678680513, "grad_norm": 0.3775630593299866, "learning_rate": 2.908609423224194e-05, "loss": 4.3082, "step": 14659 }, { "epoch": 0.44777031154551006, "grad_norm": 0.3906317353248596, "learning_rate": 2.9083727577390747e-05, "loss": 4.3348, "step": 14660 }, { "epoch": 0.44780085522296886, "grad_norm": 0.3814108967781067, "learning_rate": 2.9081360884938576e-05, "loss": 4.2911, "step": 14661 }, { "epoch": 0.4478313989004276, "grad_norm": 0.3908194303512573, "learning_rate": 2.9078994154907212e-05, "loss": 4.2507, "step": 14662 }, { "epoch": 0.44786194257788636, "grad_norm": 0.3925630450248718, "learning_rate": 2.9076627387318462e-05, "loss": 4.1977, "step": 14663 }, { "epoch": 0.44789248625534517, "grad_norm": 0.39252787828445435, "learning_rate": 2.907426058219409e-05, "loss": 4.3498, "step": 14664 }, { "epoch": 0.4479230299328039, "grad_norm": 0.3869829773902893, "learning_rate": 2.907189373955592e-05, "loss": 4.2686, "step": 14665 }, { "epoch": 0.44795357361026267, "grad_norm": 0.3960753083229065, "learning_rate": 2.9069526859425728e-05, "loss": 4.2782, "step": 14666 }, { "epoch": 0.4479841172877214, "grad_norm": 0.37624049186706543, "learning_rate": 2.9067159941825312e-05, "loss": 4.3131, "step": 14667 }, { "epoch": 0.4480146609651802, "grad_norm": 0.3882335424423218, "learning_rate": 2.9064792986776458e-05, "loss": 4.3773, "step": 14668 }, { "epoch": 0.448045204642639, "grad_norm": 0.3928911089897156, "learning_rate": 2.906242599430097e-05, "loss": 4.2889, "step": 14669 }, { "epoch": 0.4480757483200977, "grad_norm": 0.38211727142333984, "learning_rate": 2.9060058964420633e-05, "loss": 4.1943, "step": 14670 }, { "epoch": 0.4481062919975565, "grad_norm": 0.38208961486816406, "learning_rate": 2.9057691897157247e-05, "loss": 4.3235, "step": 14671 }, { "epoch": 0.4481368356750153, "grad_norm": 0.3988231122493744, "learning_rate": 2.90553247925326e-05, "loss": 4.2952, "step": 14672 }, { "epoch": 0.448167379352474, "grad_norm": 0.3887113928794861, "learning_rate": 2.90529576505685e-05, "loss": 4.3226, "step": 14673 }, { "epoch": 0.4481979230299328, "grad_norm": 0.4195030927658081, "learning_rate": 2.905059047128674e-05, "loss": 4.3627, "step": 14674 }, { "epoch": 0.4482284667073916, "grad_norm": 0.4165918231010437, "learning_rate": 2.9048223254709096e-05, "loss": 4.2372, "step": 14675 }, { "epoch": 0.44825901038485033, "grad_norm": 0.37345054745674133, "learning_rate": 2.9045856000857386e-05, "loss": 4.3293, "step": 14676 }, { "epoch": 0.4482895540623091, "grad_norm": 0.37918370962142944, "learning_rate": 2.9043488709753407e-05, "loss": 4.2253, "step": 14677 }, { "epoch": 0.4483200977397679, "grad_norm": 0.3835892081260681, "learning_rate": 2.904112138141894e-05, "loss": 4.333, "step": 14678 }, { "epoch": 0.44835064141722664, "grad_norm": 0.37960219383239746, "learning_rate": 2.9038754015875798e-05, "loss": 4.3148, "step": 14679 }, { "epoch": 0.4483811850946854, "grad_norm": 0.3816164433956146, "learning_rate": 2.903638661314576e-05, "loss": 4.1805, "step": 14680 }, { "epoch": 0.4484117287721442, "grad_norm": 0.39584317803382874, "learning_rate": 2.9034019173250644e-05, "loss": 4.2099, "step": 14681 }, { "epoch": 0.44844227244960294, "grad_norm": 0.3855009377002716, "learning_rate": 2.9031651696212237e-05, "loss": 4.217, "step": 14682 }, { "epoch": 0.4484728161270617, "grad_norm": 0.38952112197875977, "learning_rate": 2.902928418205234e-05, "loss": 4.3527, "step": 14683 }, { "epoch": 0.44850335980452044, "grad_norm": 0.3789049983024597, "learning_rate": 2.902691663079275e-05, "loss": 4.3172, "step": 14684 }, { "epoch": 0.44853390348197925, "grad_norm": 0.38153818249702454, "learning_rate": 2.9024549042455274e-05, "loss": 4.2396, "step": 14685 }, { "epoch": 0.448564447159438, "grad_norm": 0.40712037682533264, "learning_rate": 2.90221814170617e-05, "loss": 4.2861, "step": 14686 }, { "epoch": 0.44859499083689675, "grad_norm": 0.38102731108665466, "learning_rate": 2.9019813754633835e-05, "loss": 4.3523, "step": 14687 }, { "epoch": 0.44862553451435555, "grad_norm": 0.38059353828430176, "learning_rate": 2.9017446055193477e-05, "loss": 4.3112, "step": 14688 }, { "epoch": 0.4486560781918143, "grad_norm": 0.37630051374435425, "learning_rate": 2.9015078318762428e-05, "loss": 4.3388, "step": 14689 }, { "epoch": 0.44868662186927305, "grad_norm": 0.3803614675998688, "learning_rate": 2.9012710545362487e-05, "loss": 4.3485, "step": 14690 }, { "epoch": 0.4487171655467318, "grad_norm": 0.41686928272247314, "learning_rate": 2.901034273501546e-05, "loss": 4.3396, "step": 14691 }, { "epoch": 0.4487477092241906, "grad_norm": 0.39226555824279785, "learning_rate": 2.900797488774315e-05, "loss": 4.2812, "step": 14692 }, { "epoch": 0.44877825290164935, "grad_norm": 0.39399564266204834, "learning_rate": 2.900560700356735e-05, "loss": 4.2603, "step": 14693 }, { "epoch": 0.4488087965791081, "grad_norm": 0.3806304931640625, "learning_rate": 2.9003239082509863e-05, "loss": 4.3978, "step": 14694 }, { "epoch": 0.4488393402565669, "grad_norm": 0.37736889719963074, "learning_rate": 2.9000871124592498e-05, "loss": 4.1865, "step": 14695 }, { "epoch": 0.44886988393402566, "grad_norm": 0.38726145029067993, "learning_rate": 2.8998503129837058e-05, "loss": 4.3377, "step": 14696 }, { "epoch": 0.4489004276114844, "grad_norm": 0.3787125051021576, "learning_rate": 2.8996135098265343e-05, "loss": 4.2865, "step": 14697 }, { "epoch": 0.4489309712889432, "grad_norm": 0.38199350237846375, "learning_rate": 2.8993767029899148e-05, "loss": 4.2903, "step": 14698 }, { "epoch": 0.44896151496640196, "grad_norm": 0.3896169364452362, "learning_rate": 2.89913989247603e-05, "loss": 4.2962, "step": 14699 }, { "epoch": 0.4489920586438607, "grad_norm": 0.3837083876132965, "learning_rate": 2.898903078287059e-05, "loss": 4.3084, "step": 14700 }, { "epoch": 0.44902260232131946, "grad_norm": 0.37811484932899475, "learning_rate": 2.8986662604251818e-05, "loss": 4.259, "step": 14701 }, { "epoch": 0.44905314599877827, "grad_norm": 0.38824784755706787, "learning_rate": 2.8984294388925793e-05, "loss": 4.25, "step": 14702 }, { "epoch": 0.449083689676237, "grad_norm": 0.3812613785266876, "learning_rate": 2.8981926136914316e-05, "loss": 4.2675, "step": 14703 }, { "epoch": 0.44911423335369577, "grad_norm": 0.3834095895290375, "learning_rate": 2.897955784823921e-05, "loss": 4.3019, "step": 14704 }, { "epoch": 0.4491447770311546, "grad_norm": 0.38926786184310913, "learning_rate": 2.8977189522922255e-05, "loss": 4.22, "step": 14705 }, { "epoch": 0.4491753207086133, "grad_norm": 0.37960198521614075, "learning_rate": 2.8974821160985276e-05, "loss": 4.2896, "step": 14706 }, { "epoch": 0.4492058643860721, "grad_norm": 0.395659476518631, "learning_rate": 2.897245276245008e-05, "loss": 4.2865, "step": 14707 }, { "epoch": 0.4492364080635308, "grad_norm": 0.3823782205581665, "learning_rate": 2.897008432733847e-05, "loss": 4.3276, "step": 14708 }, { "epoch": 0.44926695174098963, "grad_norm": 0.3846006393432617, "learning_rate": 2.8967715855672244e-05, "loss": 4.3116, "step": 14709 }, { "epoch": 0.4492974954184484, "grad_norm": 0.3843406140804291, "learning_rate": 2.8965347347473227e-05, "loss": 4.3003, "step": 14710 }, { "epoch": 0.44932803909590713, "grad_norm": 0.37563374638557434, "learning_rate": 2.8962978802763214e-05, "loss": 4.279, "step": 14711 }, { "epoch": 0.44935858277336593, "grad_norm": 0.3977336585521698, "learning_rate": 2.896061022156401e-05, "loss": 4.3079, "step": 14712 }, { "epoch": 0.4493891264508247, "grad_norm": 0.38042792677879333, "learning_rate": 2.895824160389744e-05, "loss": 4.2956, "step": 14713 }, { "epoch": 0.44941967012828343, "grad_norm": 0.3846603333950043, "learning_rate": 2.8955872949785306e-05, "loss": 4.2899, "step": 14714 }, { "epoch": 0.44945021380574224, "grad_norm": 0.38522017002105713, "learning_rate": 2.8953504259249413e-05, "loss": 4.3006, "step": 14715 }, { "epoch": 0.449480757483201, "grad_norm": 0.3938196301460266, "learning_rate": 2.8951135532311575e-05, "loss": 4.2427, "step": 14716 }, { "epoch": 0.44951130116065974, "grad_norm": 0.3703390955924988, "learning_rate": 2.8948766768993603e-05, "loss": 4.3516, "step": 14717 }, { "epoch": 0.4495418448381185, "grad_norm": 0.39205053448677063, "learning_rate": 2.89463979693173e-05, "loss": 4.2506, "step": 14718 }, { "epoch": 0.4495723885155773, "grad_norm": 0.3973920941352844, "learning_rate": 2.894402913330448e-05, "loss": 4.2574, "step": 14719 }, { "epoch": 0.44960293219303604, "grad_norm": 0.38340166211128235, "learning_rate": 2.894166026097696e-05, "loss": 4.3849, "step": 14720 }, { "epoch": 0.4496334758704948, "grad_norm": 0.3836410939693451, "learning_rate": 2.8939291352356546e-05, "loss": 4.3842, "step": 14721 }, { "epoch": 0.4496640195479536, "grad_norm": 0.37983378767967224, "learning_rate": 2.893692240746505e-05, "loss": 4.2991, "step": 14722 }, { "epoch": 0.44969456322541235, "grad_norm": 0.3877679705619812, "learning_rate": 2.893455342632429e-05, "loss": 4.3051, "step": 14723 }, { "epoch": 0.4497251069028711, "grad_norm": 0.3923773169517517, "learning_rate": 2.893218440895607e-05, "loss": 4.3455, "step": 14724 }, { "epoch": 0.44975565058032985, "grad_norm": 0.4006877839565277, "learning_rate": 2.892981535538221e-05, "loss": 4.3403, "step": 14725 }, { "epoch": 0.44978619425778865, "grad_norm": 0.38660287857055664, "learning_rate": 2.8927446265624514e-05, "loss": 4.164, "step": 14726 }, { "epoch": 0.4498167379352474, "grad_norm": 0.3763723373413086, "learning_rate": 2.8925077139704802e-05, "loss": 4.3441, "step": 14727 }, { "epoch": 0.44984728161270615, "grad_norm": 0.39589449763298035, "learning_rate": 2.892270797764489e-05, "loss": 4.2801, "step": 14728 }, { "epoch": 0.44987782529016496, "grad_norm": 0.3862796127796173, "learning_rate": 2.892033877946658e-05, "loss": 4.2268, "step": 14729 }, { "epoch": 0.4499083689676237, "grad_norm": 0.39065179228782654, "learning_rate": 2.8917969545191705e-05, "loss": 4.3052, "step": 14730 }, { "epoch": 0.44993891264508246, "grad_norm": 0.39371371269226074, "learning_rate": 2.891560027484207e-05, "loss": 4.2325, "step": 14731 }, { "epoch": 0.44996945632254126, "grad_norm": 0.39930957555770874, "learning_rate": 2.8913230968439486e-05, "loss": 4.3218, "step": 14732 }, { "epoch": 0.45, "grad_norm": 0.3798272907733917, "learning_rate": 2.8910861626005776e-05, "loss": 4.3258, "step": 14733 }, { "epoch": 0.45003054367745876, "grad_norm": 0.3818298578262329, "learning_rate": 2.8908492247562747e-05, "loss": 4.2907, "step": 14734 }, { "epoch": 0.4500610873549175, "grad_norm": 0.3862065374851227, "learning_rate": 2.8906122833132226e-05, "loss": 4.2851, "step": 14735 }, { "epoch": 0.4500916310323763, "grad_norm": 0.40307408571243286, "learning_rate": 2.8903753382736016e-05, "loss": 4.2796, "step": 14736 }, { "epoch": 0.45012217470983507, "grad_norm": 0.3928047716617584, "learning_rate": 2.890138389639595e-05, "loss": 4.3113, "step": 14737 }, { "epoch": 0.4501527183872938, "grad_norm": 0.3868253827095032, "learning_rate": 2.889901437413383e-05, "loss": 4.3332, "step": 14738 }, { "epoch": 0.4501832620647526, "grad_norm": 0.3815174102783203, "learning_rate": 2.8896644815971484e-05, "loss": 4.2909, "step": 14739 }, { "epoch": 0.45021380574221137, "grad_norm": 0.3887244462966919, "learning_rate": 2.8894275221930727e-05, "loss": 4.3637, "step": 14740 }, { "epoch": 0.4502443494196701, "grad_norm": 0.3964240550994873, "learning_rate": 2.8891905592033374e-05, "loss": 4.2643, "step": 14741 }, { "epoch": 0.45027489309712887, "grad_norm": 0.38144057989120483, "learning_rate": 2.888953592630125e-05, "loss": 4.2938, "step": 14742 }, { "epoch": 0.4503054367745877, "grad_norm": 0.3825279474258423, "learning_rate": 2.8887166224756158e-05, "loss": 4.3199, "step": 14743 }, { "epoch": 0.4503359804520464, "grad_norm": 0.39055654406547546, "learning_rate": 2.8884796487419937e-05, "loss": 4.3817, "step": 14744 }, { "epoch": 0.4503665241295052, "grad_norm": 0.3868863880634308, "learning_rate": 2.888242671431439e-05, "loss": 4.3245, "step": 14745 }, { "epoch": 0.450397067806964, "grad_norm": 0.39190614223480225, "learning_rate": 2.888005690546135e-05, "loss": 4.319, "step": 14746 }, { "epoch": 0.45042761148442273, "grad_norm": 0.38138800859451294, "learning_rate": 2.887768706088263e-05, "loss": 4.4619, "step": 14747 }, { "epoch": 0.4504581551618815, "grad_norm": 0.39935916662216187, "learning_rate": 2.8875317180600053e-05, "loss": 4.271, "step": 14748 }, { "epoch": 0.45048869883934023, "grad_norm": 0.38163676857948303, "learning_rate": 2.8872947264635435e-05, "loss": 4.2643, "step": 14749 }, { "epoch": 0.45051924251679903, "grad_norm": 0.391338974237442, "learning_rate": 2.88705773130106e-05, "loss": 4.2933, "step": 14750 }, { "epoch": 0.4505497861942578, "grad_norm": 0.39565446972846985, "learning_rate": 2.8868207325747372e-05, "loss": 4.443, "step": 14751 }, { "epoch": 0.45058032987171653, "grad_norm": 0.39626234769821167, "learning_rate": 2.8865837302867566e-05, "loss": 4.3149, "step": 14752 }, { "epoch": 0.45061087354917534, "grad_norm": 0.3843268156051636, "learning_rate": 2.8863467244393006e-05, "loss": 4.3619, "step": 14753 }, { "epoch": 0.4506414172266341, "grad_norm": 0.38760027289390564, "learning_rate": 2.8861097150345528e-05, "loss": 4.3312, "step": 14754 }, { "epoch": 0.45067196090409284, "grad_norm": 0.389740526676178, "learning_rate": 2.885872702074694e-05, "loss": 4.3038, "step": 14755 }, { "epoch": 0.45070250458155164, "grad_norm": 0.39523541927337646, "learning_rate": 2.885635685561906e-05, "loss": 4.4116, "step": 14756 }, { "epoch": 0.4507330482590104, "grad_norm": 0.3926963806152344, "learning_rate": 2.8853986654983727e-05, "loss": 4.3196, "step": 14757 }, { "epoch": 0.45076359193646914, "grad_norm": 0.39963969588279724, "learning_rate": 2.885161641886276e-05, "loss": 4.3741, "step": 14758 }, { "epoch": 0.4507941356139279, "grad_norm": 0.3935772776603699, "learning_rate": 2.8849246147277976e-05, "loss": 4.3159, "step": 14759 }, { "epoch": 0.4508246792913867, "grad_norm": 0.39400631189346313, "learning_rate": 2.8846875840251196e-05, "loss": 4.2498, "step": 14760 }, { "epoch": 0.45085522296884545, "grad_norm": 0.38292431831359863, "learning_rate": 2.8844505497804263e-05, "loss": 4.2918, "step": 14761 }, { "epoch": 0.4508857666463042, "grad_norm": 0.37933892011642456, "learning_rate": 2.884213511995899e-05, "loss": 4.3236, "step": 14762 }, { "epoch": 0.450916310323763, "grad_norm": 0.4009173512458801, "learning_rate": 2.8839764706737206e-05, "loss": 4.1706, "step": 14763 }, { "epoch": 0.45094685400122175, "grad_norm": 0.40239378809928894, "learning_rate": 2.8837394258160734e-05, "loss": 4.263, "step": 14764 }, { "epoch": 0.4509773976786805, "grad_norm": 0.3945867419242859, "learning_rate": 2.883502377425139e-05, "loss": 4.2989, "step": 14765 }, { "epoch": 0.45100794135613925, "grad_norm": 0.38891637325286865, "learning_rate": 2.8832653255031023e-05, "loss": 4.2946, "step": 14766 }, { "epoch": 0.45103848503359806, "grad_norm": 0.38160157203674316, "learning_rate": 2.8830282700521433e-05, "loss": 4.3882, "step": 14767 }, { "epoch": 0.4510690287110568, "grad_norm": 0.39751026034355164, "learning_rate": 2.882791211074447e-05, "loss": 4.3481, "step": 14768 }, { "epoch": 0.45109957238851556, "grad_norm": 0.38190189003944397, "learning_rate": 2.8825541485721952e-05, "loss": 4.2772, "step": 14769 }, { "epoch": 0.45113011606597436, "grad_norm": 0.38206174969673157, "learning_rate": 2.8823170825475705e-05, "loss": 4.3146, "step": 14770 }, { "epoch": 0.4511606597434331, "grad_norm": 0.377435564994812, "learning_rate": 2.882080013002756e-05, "loss": 4.3235, "step": 14771 }, { "epoch": 0.45119120342089186, "grad_norm": 0.39484697580337524, "learning_rate": 2.8818429399399343e-05, "loss": 4.2343, "step": 14772 }, { "epoch": 0.45122174709835067, "grad_norm": 0.39242202043533325, "learning_rate": 2.8816058633612874e-05, "loss": 4.4021, "step": 14773 }, { "epoch": 0.4512522907758094, "grad_norm": 0.3881279528141022, "learning_rate": 2.8813687832690006e-05, "loss": 4.2953, "step": 14774 }, { "epoch": 0.45128283445326817, "grad_norm": 0.3771745562553406, "learning_rate": 2.881131699665255e-05, "loss": 4.3459, "step": 14775 }, { "epoch": 0.4513133781307269, "grad_norm": 0.3964027166366577, "learning_rate": 2.8808946125522335e-05, "loss": 4.3884, "step": 14776 }, { "epoch": 0.4513439218081857, "grad_norm": 0.39815691113471985, "learning_rate": 2.8806575219321185e-05, "loss": 4.2699, "step": 14777 }, { "epoch": 0.45137446548564447, "grad_norm": 0.3862990140914917, "learning_rate": 2.880420427807096e-05, "loss": 4.4264, "step": 14778 }, { "epoch": 0.4514050091631032, "grad_norm": 0.3842766582965851, "learning_rate": 2.880183330179346e-05, "loss": 4.376, "step": 14779 }, { "epoch": 0.451435552840562, "grad_norm": 0.379669189453125, "learning_rate": 2.8799462290510526e-05, "loss": 4.2532, "step": 14780 }, { "epoch": 0.4514660965180208, "grad_norm": 0.3814789950847626, "learning_rate": 2.879709124424399e-05, "loss": 4.3221, "step": 14781 }, { "epoch": 0.4514966401954795, "grad_norm": 0.38643038272857666, "learning_rate": 2.879472016301568e-05, "loss": 4.3598, "step": 14782 }, { "epoch": 0.4515271838729383, "grad_norm": 0.3967834711074829, "learning_rate": 2.8792349046847433e-05, "loss": 4.3696, "step": 14783 }, { "epoch": 0.4515577275503971, "grad_norm": 0.38223031163215637, "learning_rate": 2.8789977895761076e-05, "loss": 4.1535, "step": 14784 }, { "epoch": 0.45158827122785583, "grad_norm": 0.3831888437271118, "learning_rate": 2.8787606709778446e-05, "loss": 4.3659, "step": 14785 }, { "epoch": 0.4516188149053146, "grad_norm": 0.38523247838020325, "learning_rate": 2.8785235488921375e-05, "loss": 4.307, "step": 14786 }, { "epoch": 0.4516493585827734, "grad_norm": 0.3943220376968384, "learning_rate": 2.8782864233211698e-05, "loss": 4.3535, "step": 14787 }, { "epoch": 0.45167990226023214, "grad_norm": 0.3897576928138733, "learning_rate": 2.878049294267124e-05, "loss": 4.2865, "step": 14788 }, { "epoch": 0.4517104459376909, "grad_norm": 0.37723514437675476, "learning_rate": 2.877812161732184e-05, "loss": 4.2596, "step": 14789 }, { "epoch": 0.4517409896151497, "grad_norm": 0.3921814262866974, "learning_rate": 2.877575025718533e-05, "loss": 4.2749, "step": 14790 }, { "epoch": 0.45177153329260844, "grad_norm": 0.3807203471660614, "learning_rate": 2.877337886228355e-05, "loss": 4.2752, "step": 14791 }, { "epoch": 0.4518020769700672, "grad_norm": 0.3896438777446747, "learning_rate": 2.877100743263833e-05, "loss": 4.2673, "step": 14792 }, { "epoch": 0.45183262064752594, "grad_norm": 0.38835880160331726, "learning_rate": 2.8768635968271507e-05, "loss": 4.3296, "step": 14793 }, { "epoch": 0.45186316432498475, "grad_norm": 0.38784778118133545, "learning_rate": 2.8766264469204913e-05, "loss": 4.2876, "step": 14794 }, { "epoch": 0.4518937080024435, "grad_norm": 0.38805335760116577, "learning_rate": 2.8763892935460384e-05, "loss": 4.2342, "step": 14795 }, { "epoch": 0.45192425167990224, "grad_norm": 0.3886060118675232, "learning_rate": 2.8761521367059756e-05, "loss": 4.4144, "step": 14796 }, { "epoch": 0.45195479535736105, "grad_norm": 0.3933168947696686, "learning_rate": 2.8759149764024868e-05, "loss": 4.1778, "step": 14797 }, { "epoch": 0.4519853390348198, "grad_norm": 0.3855568766593933, "learning_rate": 2.875677812637756e-05, "loss": 4.2974, "step": 14798 }, { "epoch": 0.45201588271227855, "grad_norm": 0.3773159086704254, "learning_rate": 2.875440645413966e-05, "loss": 4.2543, "step": 14799 }, { "epoch": 0.4520464263897373, "grad_norm": 0.36976537108421326, "learning_rate": 2.8752034747333014e-05, "loss": 4.2831, "step": 14800 }, { "epoch": 0.4520769700671961, "grad_norm": 0.38525789976119995, "learning_rate": 2.874966300597945e-05, "loss": 4.2314, "step": 14801 }, { "epoch": 0.45210751374465485, "grad_norm": 0.3845961391925812, "learning_rate": 2.8747291230100814e-05, "loss": 4.2405, "step": 14802 }, { "epoch": 0.4521380574221136, "grad_norm": 0.3871965706348419, "learning_rate": 2.8744919419718942e-05, "loss": 4.2704, "step": 14803 }, { "epoch": 0.4521686010995724, "grad_norm": 0.38425299525260925, "learning_rate": 2.874254757485566e-05, "loss": 4.2464, "step": 14804 }, { "epoch": 0.45219914477703116, "grad_norm": 0.3847423195838928, "learning_rate": 2.8740175695532832e-05, "loss": 4.2952, "step": 14805 }, { "epoch": 0.4522296884544899, "grad_norm": 0.3818005919456482, "learning_rate": 2.8737803781772277e-05, "loss": 4.417, "step": 14806 }, { "epoch": 0.4522602321319487, "grad_norm": 0.3958181142807007, "learning_rate": 2.8735431833595838e-05, "loss": 4.2841, "step": 14807 }, { "epoch": 0.45229077580940746, "grad_norm": 0.38032957911491394, "learning_rate": 2.873305985102536e-05, "loss": 4.3754, "step": 14808 }, { "epoch": 0.4523213194868662, "grad_norm": 0.3872130811214447, "learning_rate": 2.8730687834082688e-05, "loss": 4.2517, "step": 14809 }, { "epoch": 0.45235186316432496, "grad_norm": 0.3855743706226349, "learning_rate": 2.8728315782789654e-05, "loss": 4.3537, "step": 14810 }, { "epoch": 0.45238240684178377, "grad_norm": 0.39611098170280457, "learning_rate": 2.872594369716809e-05, "loss": 4.3444, "step": 14811 }, { "epoch": 0.4524129505192425, "grad_norm": 0.3870587646961212, "learning_rate": 2.8723571577239856e-05, "loss": 4.3832, "step": 14812 }, { "epoch": 0.45244349419670127, "grad_norm": 0.3804739713668823, "learning_rate": 2.872119942302678e-05, "loss": 4.2537, "step": 14813 }, { "epoch": 0.4524740378741601, "grad_norm": 0.37914881110191345, "learning_rate": 2.8718827234550705e-05, "loss": 4.2767, "step": 14814 }, { "epoch": 0.4525045815516188, "grad_norm": 0.3877333104610443, "learning_rate": 2.8716455011833476e-05, "loss": 4.2758, "step": 14815 }, { "epoch": 0.4525351252290776, "grad_norm": 0.37254199385643005, "learning_rate": 2.8714082754896936e-05, "loss": 4.2854, "step": 14816 }, { "epoch": 0.4525656689065363, "grad_norm": 0.3826271593570709, "learning_rate": 2.871171046376293e-05, "loss": 4.3283, "step": 14817 }, { "epoch": 0.45259621258399513, "grad_norm": 0.38999906182289124, "learning_rate": 2.8709338138453295e-05, "loss": 4.3006, "step": 14818 }, { "epoch": 0.4526267562614539, "grad_norm": 0.38297128677368164, "learning_rate": 2.870696577898988e-05, "loss": 4.2875, "step": 14819 }, { "epoch": 0.4526572999389126, "grad_norm": 0.4085253179073334, "learning_rate": 2.8704593385394523e-05, "loss": 4.3012, "step": 14820 }, { "epoch": 0.45268784361637143, "grad_norm": 0.3943745195865631, "learning_rate": 2.8702220957689063e-05, "loss": 4.3477, "step": 14821 }, { "epoch": 0.4527183872938302, "grad_norm": 0.393066942691803, "learning_rate": 2.8699848495895358e-05, "loss": 4.3659, "step": 14822 }, { "epoch": 0.45274893097128893, "grad_norm": 0.39947402477264404, "learning_rate": 2.8697476000035245e-05, "loss": 4.236, "step": 14823 }, { "epoch": 0.4527794746487477, "grad_norm": 0.38184794783592224, "learning_rate": 2.8695103470130568e-05, "loss": 4.2619, "step": 14824 }, { "epoch": 0.4528100183262065, "grad_norm": 0.3751050531864166, "learning_rate": 2.8692730906203175e-05, "loss": 4.3074, "step": 14825 }, { "epoch": 0.45284056200366524, "grad_norm": 0.38535192608833313, "learning_rate": 2.869035830827491e-05, "loss": 4.3451, "step": 14826 }, { "epoch": 0.452871105681124, "grad_norm": 0.38751736283302307, "learning_rate": 2.868798567636762e-05, "loss": 4.2981, "step": 14827 }, { "epoch": 0.4529016493585828, "grad_norm": 0.39258649945259094, "learning_rate": 2.868561301050314e-05, "loss": 4.3049, "step": 14828 }, { "epoch": 0.45293219303604154, "grad_norm": 0.3924144208431244, "learning_rate": 2.868324031070334e-05, "loss": 4.267, "step": 14829 }, { "epoch": 0.4529627367135003, "grad_norm": 0.39070823788642883, "learning_rate": 2.8680867576990046e-05, "loss": 4.2837, "step": 14830 }, { "epoch": 0.4529932803909591, "grad_norm": 0.40588614344596863, "learning_rate": 2.8678494809385108e-05, "loss": 4.2632, "step": 14831 }, { "epoch": 0.45302382406841785, "grad_norm": 0.39312276244163513, "learning_rate": 2.8676122007910385e-05, "loss": 4.2737, "step": 14832 }, { "epoch": 0.4530543677458766, "grad_norm": 0.39505136013031006, "learning_rate": 2.8673749172587717e-05, "loss": 4.3508, "step": 14833 }, { "epoch": 0.45308491142333535, "grad_norm": 0.3857828676700592, "learning_rate": 2.8671376303438947e-05, "loss": 4.2787, "step": 14834 }, { "epoch": 0.45311545510079415, "grad_norm": 0.380140095949173, "learning_rate": 2.8669003400485923e-05, "loss": 4.3223, "step": 14835 }, { "epoch": 0.4531459987782529, "grad_norm": 0.3924762010574341, "learning_rate": 2.8666630463750504e-05, "loss": 4.3808, "step": 14836 }, { "epoch": 0.45317654245571165, "grad_norm": 0.3839065432548523, "learning_rate": 2.866425749325453e-05, "loss": 4.3665, "step": 14837 }, { "epoch": 0.45320708613317046, "grad_norm": 0.3955730199813843, "learning_rate": 2.8661884489019853e-05, "loss": 4.3647, "step": 14838 }, { "epoch": 0.4532376298106292, "grad_norm": 0.3871324360370636, "learning_rate": 2.8659511451068327e-05, "loss": 4.4019, "step": 14839 }, { "epoch": 0.45326817348808796, "grad_norm": 0.37851810455322266, "learning_rate": 2.86571383794218e-05, "loss": 4.2809, "step": 14840 }, { "epoch": 0.4532987171655467, "grad_norm": 0.3747524917125702, "learning_rate": 2.8654765274102115e-05, "loss": 4.2859, "step": 14841 }, { "epoch": 0.4533292608430055, "grad_norm": 0.3853223919868469, "learning_rate": 2.865239213513113e-05, "loss": 4.3107, "step": 14842 }, { "epoch": 0.45335980452046426, "grad_norm": 0.39864251017570496, "learning_rate": 2.8650018962530688e-05, "loss": 4.3001, "step": 14843 }, { "epoch": 0.453390348197923, "grad_norm": 0.3870830833911896, "learning_rate": 2.864764575632265e-05, "loss": 4.2663, "step": 14844 }, { "epoch": 0.4534208918753818, "grad_norm": 0.3780018091201782, "learning_rate": 2.8645272516528855e-05, "loss": 4.3045, "step": 14845 }, { "epoch": 0.45345143555284056, "grad_norm": 0.38278329372406006, "learning_rate": 2.8642899243171162e-05, "loss": 4.2868, "step": 14846 }, { "epoch": 0.4534819792302993, "grad_norm": 0.38334813714027405, "learning_rate": 2.864052593627143e-05, "loss": 4.3126, "step": 14847 }, { "epoch": 0.4535125229077581, "grad_norm": 0.379914253950119, "learning_rate": 2.86381525958515e-05, "loss": 4.2083, "step": 14848 }, { "epoch": 0.45354306658521687, "grad_norm": 0.3840716481208801, "learning_rate": 2.8635779221933234e-05, "loss": 4.3308, "step": 14849 }, { "epoch": 0.4535736102626756, "grad_norm": 0.3845156133174896, "learning_rate": 2.8633405814538473e-05, "loss": 4.2214, "step": 14850 }, { "epoch": 0.45360415394013437, "grad_norm": 0.3872481882572174, "learning_rate": 2.863103237368908e-05, "loss": 4.3089, "step": 14851 }, { "epoch": 0.4536346976175932, "grad_norm": 0.3816046714782715, "learning_rate": 2.8628658899406896e-05, "loss": 4.3098, "step": 14852 }, { "epoch": 0.4536652412950519, "grad_norm": 0.3987073004245758, "learning_rate": 2.862628539171379e-05, "loss": 4.1735, "step": 14853 }, { "epoch": 0.4536957849725107, "grad_norm": 0.38861289620399475, "learning_rate": 2.8623911850631613e-05, "loss": 4.2906, "step": 14854 }, { "epoch": 0.4537263286499695, "grad_norm": 0.371189147233963, "learning_rate": 2.8621538276182215e-05, "loss": 4.2816, "step": 14855 }, { "epoch": 0.45375687232742823, "grad_norm": 0.38053733110427856, "learning_rate": 2.8619164668387455e-05, "loss": 4.2543, "step": 14856 }, { "epoch": 0.453787416004887, "grad_norm": 0.3910219371318817, "learning_rate": 2.861679102726918e-05, "loss": 4.2914, "step": 14857 }, { "epoch": 0.45381795968234573, "grad_norm": 0.4026857018470764, "learning_rate": 2.8614417352849255e-05, "loss": 4.3332, "step": 14858 }, { "epoch": 0.45384850335980453, "grad_norm": 0.39503341913223267, "learning_rate": 2.8612043645149523e-05, "loss": 4.2271, "step": 14859 }, { "epoch": 0.4538790470372633, "grad_norm": 0.4018316864967346, "learning_rate": 2.8609669904191855e-05, "loss": 4.3623, "step": 14860 }, { "epoch": 0.45390959071472203, "grad_norm": 0.3894203007221222, "learning_rate": 2.8607296129998096e-05, "loss": 4.2946, "step": 14861 }, { "epoch": 0.45394013439218084, "grad_norm": 0.39169302582740784, "learning_rate": 2.8604922322590104e-05, "loss": 4.2706, "step": 14862 }, { "epoch": 0.4539706780696396, "grad_norm": 0.3808830976486206, "learning_rate": 2.8602548481989744e-05, "loss": 4.378, "step": 14863 }, { "epoch": 0.45400122174709834, "grad_norm": 0.3855568468570709, "learning_rate": 2.8600174608218872e-05, "loss": 4.3302, "step": 14864 }, { "epoch": 0.45403176542455714, "grad_norm": 0.36949825286865234, "learning_rate": 2.859780070129934e-05, "loss": 4.3462, "step": 14865 }, { "epoch": 0.4540623091020159, "grad_norm": 0.3901948928833008, "learning_rate": 2.8595426761253e-05, "loss": 4.3257, "step": 14866 }, { "epoch": 0.45409285277947464, "grad_norm": 0.39257821440696716, "learning_rate": 2.8593052788101725e-05, "loss": 4.3701, "step": 14867 }, { "epoch": 0.4541233964569334, "grad_norm": 0.38044849038124084, "learning_rate": 2.8590678781867362e-05, "loss": 4.2046, "step": 14868 }, { "epoch": 0.4541539401343922, "grad_norm": 0.3896430730819702, "learning_rate": 2.858830474257177e-05, "loss": 4.363, "step": 14869 }, { "epoch": 0.45418448381185095, "grad_norm": 0.3852013647556305, "learning_rate": 2.8585930670236814e-05, "loss": 4.2617, "step": 14870 }, { "epoch": 0.4542150274893097, "grad_norm": 0.4016956686973572, "learning_rate": 2.858355656488435e-05, "loss": 4.2616, "step": 14871 }, { "epoch": 0.4542455711667685, "grad_norm": 0.3914945721626282, "learning_rate": 2.8581182426536242e-05, "loss": 4.3458, "step": 14872 }, { "epoch": 0.45427611484422725, "grad_norm": 0.38248011469841003, "learning_rate": 2.8578808255214344e-05, "loss": 4.2764, "step": 14873 }, { "epoch": 0.454306658521686, "grad_norm": 0.37830406427383423, "learning_rate": 2.857643405094052e-05, "loss": 4.3388, "step": 14874 }, { "epoch": 0.45433720219914475, "grad_norm": 0.3886124789714813, "learning_rate": 2.8574059813736627e-05, "loss": 4.3375, "step": 14875 }, { "epoch": 0.45436774587660356, "grad_norm": 0.3889982998371124, "learning_rate": 2.857168554362452e-05, "loss": 4.3746, "step": 14876 }, { "epoch": 0.4543982895540623, "grad_norm": 0.3894447386264801, "learning_rate": 2.856931124062608e-05, "loss": 4.3654, "step": 14877 }, { "epoch": 0.45442883323152106, "grad_norm": 0.3841383159160614, "learning_rate": 2.8566936904763153e-05, "loss": 4.3323, "step": 14878 }, { "epoch": 0.45445937690897986, "grad_norm": 0.3781279921531677, "learning_rate": 2.8564562536057605e-05, "loss": 4.3347, "step": 14879 }, { "epoch": 0.4544899205864386, "grad_norm": 0.37704020738601685, "learning_rate": 2.856218813453129e-05, "loss": 4.2446, "step": 14880 }, { "epoch": 0.45452046426389736, "grad_norm": 0.3818495571613312, "learning_rate": 2.8559813700206084e-05, "loss": 4.3461, "step": 14881 }, { "epoch": 0.45455100794135617, "grad_norm": 0.38422325253486633, "learning_rate": 2.855743923310384e-05, "loss": 4.3416, "step": 14882 }, { "epoch": 0.4545815516188149, "grad_norm": 0.38158169388771057, "learning_rate": 2.8555064733246422e-05, "loss": 4.3776, "step": 14883 }, { "epoch": 0.45461209529627367, "grad_norm": 0.3829350471496582, "learning_rate": 2.8552690200655696e-05, "loss": 4.2171, "step": 14884 }, { "epoch": 0.4546426389737324, "grad_norm": 0.37911859154701233, "learning_rate": 2.855031563535353e-05, "loss": 4.3378, "step": 14885 }, { "epoch": 0.4546731826511912, "grad_norm": 0.40182656049728394, "learning_rate": 2.8547941037361777e-05, "loss": 4.4119, "step": 14886 }, { "epoch": 0.45470372632864997, "grad_norm": 0.3830614984035492, "learning_rate": 2.8545566406702307e-05, "loss": 4.3516, "step": 14887 }, { "epoch": 0.4547342700061087, "grad_norm": 0.3760080635547638, "learning_rate": 2.8543191743396992e-05, "loss": 4.256, "step": 14888 }, { "epoch": 0.4547648136835675, "grad_norm": 0.3757303059101105, "learning_rate": 2.8540817047467682e-05, "loss": 4.3311, "step": 14889 }, { "epoch": 0.4547953573610263, "grad_norm": 0.39110052585601807, "learning_rate": 2.853844231893625e-05, "loss": 4.2768, "step": 14890 }, { "epoch": 0.454825901038485, "grad_norm": 0.3872992992401123, "learning_rate": 2.8536067557824558e-05, "loss": 4.3724, "step": 14891 }, { "epoch": 0.4548564447159438, "grad_norm": 0.390563040971756, "learning_rate": 2.853369276415448e-05, "loss": 4.3247, "step": 14892 }, { "epoch": 0.4548869883934026, "grad_norm": 0.37629345059394836, "learning_rate": 2.8531317937947866e-05, "loss": 4.17, "step": 14893 }, { "epoch": 0.45491753207086133, "grad_norm": 0.38941195607185364, "learning_rate": 2.85289430792266e-05, "loss": 4.3625, "step": 14894 }, { "epoch": 0.4549480757483201, "grad_norm": 0.38513749837875366, "learning_rate": 2.8526568188012537e-05, "loss": 4.3597, "step": 14895 }, { "epoch": 0.4549786194257789, "grad_norm": 0.38573572039604187, "learning_rate": 2.8524193264327552e-05, "loss": 4.2966, "step": 14896 }, { "epoch": 0.45500916310323763, "grad_norm": 0.41453906893730164, "learning_rate": 2.8521818308193505e-05, "loss": 4.2988, "step": 14897 }, { "epoch": 0.4550397067806964, "grad_norm": 0.39678868651390076, "learning_rate": 2.8519443319632268e-05, "loss": 4.2012, "step": 14898 }, { "epoch": 0.45507025045815513, "grad_norm": 0.4058111906051636, "learning_rate": 2.8517068298665705e-05, "loss": 4.374, "step": 14899 }, { "epoch": 0.45510079413561394, "grad_norm": 0.389708548784256, "learning_rate": 2.8514693245315684e-05, "loss": 4.2374, "step": 14900 }, { "epoch": 0.4551313378130727, "grad_norm": 0.3935122489929199, "learning_rate": 2.8512318159604074e-05, "loss": 4.2977, "step": 14901 }, { "epoch": 0.45516188149053144, "grad_norm": 0.3858497142791748, "learning_rate": 2.850994304155275e-05, "loss": 4.4051, "step": 14902 }, { "epoch": 0.45519242516799024, "grad_norm": 0.3866609036922455, "learning_rate": 2.850756789118357e-05, "loss": 4.3856, "step": 14903 }, { "epoch": 0.455222968845449, "grad_norm": 0.38345062732696533, "learning_rate": 2.850519270851842e-05, "loss": 4.3084, "step": 14904 }, { "epoch": 0.45525351252290774, "grad_norm": 0.3828510046005249, "learning_rate": 2.8502817493579147e-05, "loss": 4.2853, "step": 14905 }, { "epoch": 0.45528405620036655, "grad_norm": 0.3986893892288208, "learning_rate": 2.8500442246387638e-05, "loss": 4.3089, "step": 14906 }, { "epoch": 0.4553145998778253, "grad_norm": 0.38336998224258423, "learning_rate": 2.8498066966965753e-05, "loss": 4.3574, "step": 14907 }, { "epoch": 0.45534514355528405, "grad_norm": 0.378842294216156, "learning_rate": 2.8495691655335372e-05, "loss": 4.2732, "step": 14908 }, { "epoch": 0.4553756872327428, "grad_norm": 0.391599178314209, "learning_rate": 2.849331631151836e-05, "loss": 4.3801, "step": 14909 }, { "epoch": 0.4554062309102016, "grad_norm": 0.3908233940601349, "learning_rate": 2.8490940935536582e-05, "loss": 4.3032, "step": 14910 }, { "epoch": 0.45543677458766035, "grad_norm": 0.3892083764076233, "learning_rate": 2.8488565527411927e-05, "loss": 4.3601, "step": 14911 }, { "epoch": 0.4554673182651191, "grad_norm": 0.38770097494125366, "learning_rate": 2.8486190087166254e-05, "loss": 4.3508, "step": 14912 }, { "epoch": 0.4554978619425779, "grad_norm": 0.37705087661743164, "learning_rate": 2.8483814614821424e-05, "loss": 4.3645, "step": 14913 }, { "epoch": 0.45552840562003666, "grad_norm": 0.38789650797843933, "learning_rate": 2.848143911039933e-05, "loss": 4.4195, "step": 14914 }, { "epoch": 0.4555589492974954, "grad_norm": 0.38526207208633423, "learning_rate": 2.847906357392184e-05, "loss": 4.2994, "step": 14915 }, { "epoch": 0.45558949297495416, "grad_norm": 0.3835034966468811, "learning_rate": 2.8476688005410818e-05, "loss": 4.2195, "step": 14916 }, { "epoch": 0.45562003665241296, "grad_norm": 0.383524626493454, "learning_rate": 2.8474312404888138e-05, "loss": 4.245, "step": 14917 }, { "epoch": 0.4556505803298717, "grad_norm": 0.3941507041454315, "learning_rate": 2.8471936772375686e-05, "loss": 4.2835, "step": 14918 }, { "epoch": 0.45568112400733046, "grad_norm": 0.3734118640422821, "learning_rate": 2.846956110789532e-05, "loss": 4.3651, "step": 14919 }, { "epoch": 0.45571166768478927, "grad_norm": 0.3749829828739166, "learning_rate": 2.8467185411468927e-05, "loss": 4.2962, "step": 14920 }, { "epoch": 0.455742211362248, "grad_norm": 0.3811282813549042, "learning_rate": 2.846480968311837e-05, "loss": 4.2531, "step": 14921 }, { "epoch": 0.45577275503970677, "grad_norm": 0.37937605381011963, "learning_rate": 2.8462433922865534e-05, "loss": 4.3748, "step": 14922 }, { "epoch": 0.4558032987171656, "grad_norm": 0.3786633014678955, "learning_rate": 2.8460058130732282e-05, "loss": 4.3332, "step": 14923 }, { "epoch": 0.4558338423946243, "grad_norm": 0.38336461782455444, "learning_rate": 2.84576823067405e-05, "loss": 4.3474, "step": 14924 }, { "epoch": 0.45586438607208307, "grad_norm": 0.3880491256713867, "learning_rate": 2.8455306450912062e-05, "loss": 4.3103, "step": 14925 }, { "epoch": 0.4558949297495418, "grad_norm": 0.3823351263999939, "learning_rate": 2.8452930563268838e-05, "loss": 4.3041, "step": 14926 }, { "epoch": 0.4559254734270006, "grad_norm": 0.37971723079681396, "learning_rate": 2.8450554643832707e-05, "loss": 4.2212, "step": 14927 }, { "epoch": 0.4559560171044594, "grad_norm": 0.39736685156822205, "learning_rate": 2.844817869262555e-05, "loss": 4.1878, "step": 14928 }, { "epoch": 0.4559865607819181, "grad_norm": 0.3879859745502472, "learning_rate": 2.8445802709669235e-05, "loss": 4.3137, "step": 14929 }, { "epoch": 0.45601710445937693, "grad_norm": 0.3783985376358032, "learning_rate": 2.844342669498563e-05, "loss": 4.3082, "step": 14930 }, { "epoch": 0.4560476481368357, "grad_norm": 0.38989511132240295, "learning_rate": 2.844105064859664e-05, "loss": 4.3012, "step": 14931 }, { "epoch": 0.45607819181429443, "grad_norm": 0.3885418176651001, "learning_rate": 2.8438674570524125e-05, "loss": 4.3064, "step": 14932 }, { "epoch": 0.4561087354917532, "grad_norm": 0.3835259675979614, "learning_rate": 2.8436298460789967e-05, "loss": 4.2772, "step": 14933 }, { "epoch": 0.456139279169212, "grad_norm": 0.38284415006637573, "learning_rate": 2.843392231941604e-05, "loss": 4.3184, "step": 14934 }, { "epoch": 0.45616982284667074, "grad_norm": 0.39066755771636963, "learning_rate": 2.8431546146424227e-05, "loss": 4.2688, "step": 14935 }, { "epoch": 0.4562003665241295, "grad_norm": 0.3899736702442169, "learning_rate": 2.8429169941836402e-05, "loss": 4.3046, "step": 14936 }, { "epoch": 0.4562309102015883, "grad_norm": 0.38541457056999207, "learning_rate": 2.8426793705674442e-05, "loss": 4.2272, "step": 14937 }, { "epoch": 0.45626145387904704, "grad_norm": 0.3849914073944092, "learning_rate": 2.8424417437960237e-05, "loss": 4.2858, "step": 14938 }, { "epoch": 0.4562919975565058, "grad_norm": 0.38555577397346497, "learning_rate": 2.8422041138715654e-05, "loss": 4.2855, "step": 14939 }, { "epoch": 0.4563225412339646, "grad_norm": 0.3999738097190857, "learning_rate": 2.841966480796258e-05, "loss": 4.2268, "step": 14940 }, { "epoch": 0.45635308491142335, "grad_norm": 0.37363165616989136, "learning_rate": 2.8417288445722896e-05, "loss": 4.2453, "step": 14941 }, { "epoch": 0.4563836285888821, "grad_norm": 0.38420212268829346, "learning_rate": 2.8414912052018483e-05, "loss": 4.4116, "step": 14942 }, { "epoch": 0.45641417226634085, "grad_norm": 0.3867620825767517, "learning_rate": 2.8412535626871224e-05, "loss": 4.2574, "step": 14943 }, { "epoch": 0.45644471594379965, "grad_norm": 0.40132829546928406, "learning_rate": 2.841015917030298e-05, "loss": 4.4105, "step": 14944 }, { "epoch": 0.4564752596212584, "grad_norm": 0.3737622797489166, "learning_rate": 2.840778268233566e-05, "loss": 4.2791, "step": 14945 }, { "epoch": 0.45650580329871715, "grad_norm": 0.38762366771698, "learning_rate": 2.840540616299113e-05, "loss": 4.2039, "step": 14946 }, { "epoch": 0.45653634697617596, "grad_norm": 0.39912188053131104, "learning_rate": 2.8403029612291266e-05, "loss": 4.314, "step": 14947 }, { "epoch": 0.4565668906536347, "grad_norm": 0.3873155117034912, "learning_rate": 2.840065303025796e-05, "loss": 4.3937, "step": 14948 }, { "epoch": 0.45659743433109345, "grad_norm": 0.3887428343296051, "learning_rate": 2.83982764169131e-05, "loss": 4.3309, "step": 14949 }, { "epoch": 0.4566279780085522, "grad_norm": 0.3835853338241577, "learning_rate": 2.839589977227856e-05, "loss": 4.3055, "step": 14950 }, { "epoch": 0.456658521686011, "grad_norm": 0.3854837119579315, "learning_rate": 2.839352309637623e-05, "loss": 4.2772, "step": 14951 }, { "epoch": 0.45668906536346976, "grad_norm": 0.38565120100975037, "learning_rate": 2.839114638922798e-05, "loss": 4.2704, "step": 14952 }, { "epoch": 0.4567196090409285, "grad_norm": 0.38553178310394287, "learning_rate": 2.8388769650855706e-05, "loss": 4.3312, "step": 14953 }, { "epoch": 0.4567501527183873, "grad_norm": 0.38633298873901367, "learning_rate": 2.8386392881281282e-05, "loss": 4.3022, "step": 14954 }, { "epoch": 0.45678069639584606, "grad_norm": 0.3955056965351105, "learning_rate": 2.8384016080526597e-05, "loss": 4.3327, "step": 14955 }, { "epoch": 0.4568112400733048, "grad_norm": 0.38344141840934753, "learning_rate": 2.8381639248613544e-05, "loss": 4.3341, "step": 14956 }, { "epoch": 0.4568417837507636, "grad_norm": 0.38067638874053955, "learning_rate": 2.8379262385563997e-05, "loss": 4.3474, "step": 14957 }, { "epoch": 0.45687232742822237, "grad_norm": 0.40069058537483215, "learning_rate": 2.837688549139984e-05, "loss": 4.3146, "step": 14958 }, { "epoch": 0.4569028711056811, "grad_norm": 0.37802764773368835, "learning_rate": 2.837450856614297e-05, "loss": 4.2932, "step": 14959 }, { "epoch": 0.45693341478313987, "grad_norm": 0.3774207830429077, "learning_rate": 2.8372131609815262e-05, "loss": 4.3189, "step": 14960 }, { "epoch": 0.4569639584605987, "grad_norm": 0.3816092610359192, "learning_rate": 2.8369754622438595e-05, "loss": 4.3179, "step": 14961 }, { "epoch": 0.4569945021380574, "grad_norm": 0.3749909996986389, "learning_rate": 2.8367377604034874e-05, "loss": 4.3137, "step": 14962 }, { "epoch": 0.4570250458155162, "grad_norm": 0.3803751766681671, "learning_rate": 2.8365000554625976e-05, "loss": 4.3281, "step": 14963 }, { "epoch": 0.457055589492975, "grad_norm": 0.38682517409324646, "learning_rate": 2.836262347423378e-05, "loss": 4.3582, "step": 14964 }, { "epoch": 0.45708613317043373, "grad_norm": 0.4002637267112732, "learning_rate": 2.8360246362880183e-05, "loss": 4.2942, "step": 14965 }, { "epoch": 0.4571166768478925, "grad_norm": 0.3929264545440674, "learning_rate": 2.8357869220587078e-05, "loss": 4.3598, "step": 14966 }, { "epoch": 0.45714722052535123, "grad_norm": 0.3819757103919983, "learning_rate": 2.8355492047376343e-05, "loss": 4.307, "step": 14967 }, { "epoch": 0.45717776420281003, "grad_norm": 0.3895776867866516, "learning_rate": 2.835311484326986e-05, "loss": 4.2017, "step": 14968 }, { "epoch": 0.4572083078802688, "grad_norm": 0.39801427721977234, "learning_rate": 2.835073760828953e-05, "loss": 4.355, "step": 14969 }, { "epoch": 0.45723885155772753, "grad_norm": 0.396908700466156, "learning_rate": 2.8348360342457235e-05, "loss": 4.3422, "step": 14970 }, { "epoch": 0.45726939523518634, "grad_norm": 0.3872062861919403, "learning_rate": 2.834598304579486e-05, "loss": 4.2501, "step": 14971 }, { "epoch": 0.4572999389126451, "grad_norm": 0.38230612874031067, "learning_rate": 2.8343605718324307e-05, "loss": 4.2702, "step": 14972 }, { "epoch": 0.45733048259010384, "grad_norm": 0.389212429523468, "learning_rate": 2.8341228360067457e-05, "loss": 4.2761, "step": 14973 }, { "epoch": 0.4573610262675626, "grad_norm": 0.39645230770111084, "learning_rate": 2.8338850971046195e-05, "loss": 4.3886, "step": 14974 }, { "epoch": 0.4573915699450214, "grad_norm": 0.4040549397468567, "learning_rate": 2.8336473551282417e-05, "loss": 4.223, "step": 14975 }, { "epoch": 0.45742211362248014, "grad_norm": 0.3837782144546509, "learning_rate": 2.8334096100798014e-05, "loss": 4.2739, "step": 14976 }, { "epoch": 0.4574526572999389, "grad_norm": 0.37357038259506226, "learning_rate": 2.833171861961487e-05, "loss": 4.2879, "step": 14977 }, { "epoch": 0.4574832009773977, "grad_norm": 0.3749956488609314, "learning_rate": 2.8329341107754875e-05, "loss": 4.3003, "step": 14978 }, { "epoch": 0.45751374465485645, "grad_norm": 0.38749921321868896, "learning_rate": 2.8326963565239933e-05, "loss": 4.3023, "step": 14979 }, { "epoch": 0.4575442883323152, "grad_norm": 0.3798281252384186, "learning_rate": 2.832458599209193e-05, "loss": 4.4097, "step": 14980 }, { "epoch": 0.457574832009774, "grad_norm": 0.37974730134010315, "learning_rate": 2.832220838833275e-05, "loss": 4.3651, "step": 14981 }, { "epoch": 0.45760537568723275, "grad_norm": 0.38936904072761536, "learning_rate": 2.8319830753984282e-05, "loss": 4.2847, "step": 14982 }, { "epoch": 0.4576359193646915, "grad_norm": 0.3874126672744751, "learning_rate": 2.8317453089068434e-05, "loss": 4.3234, "step": 14983 }, { "epoch": 0.45766646304215025, "grad_norm": 0.3832302987575531, "learning_rate": 2.8315075393607087e-05, "loss": 4.2861, "step": 14984 }, { "epoch": 0.45769700671960906, "grad_norm": 0.38897424936294556, "learning_rate": 2.8312697667622136e-05, "loss": 4.3169, "step": 14985 }, { "epoch": 0.4577275503970678, "grad_norm": 0.3827497363090515, "learning_rate": 2.8310319911135473e-05, "loss": 4.273, "step": 14986 }, { "epoch": 0.45775809407452656, "grad_norm": 0.38841089606285095, "learning_rate": 2.8307942124168994e-05, "loss": 4.322, "step": 14987 }, { "epoch": 0.45778863775198536, "grad_norm": 0.4234461188316345, "learning_rate": 2.8305564306744593e-05, "loss": 4.3949, "step": 14988 }, { "epoch": 0.4578191814294441, "grad_norm": 0.3824537992477417, "learning_rate": 2.8303186458884167e-05, "loss": 4.2506, "step": 14989 }, { "epoch": 0.45784972510690286, "grad_norm": 0.3794635236263275, "learning_rate": 2.8300808580609593e-05, "loss": 4.2542, "step": 14990 }, { "epoch": 0.4578802687843616, "grad_norm": 0.3807017207145691, "learning_rate": 2.829843067194279e-05, "loss": 4.3389, "step": 14991 }, { "epoch": 0.4579108124618204, "grad_norm": 0.3783511519432068, "learning_rate": 2.8296052732905626e-05, "loss": 4.2973, "step": 14992 }, { "epoch": 0.45794135613927917, "grad_norm": 0.37795528769493103, "learning_rate": 2.8293674763520017e-05, "loss": 4.3072, "step": 14993 }, { "epoch": 0.4579718998167379, "grad_norm": 0.3868345320224762, "learning_rate": 2.829129676380785e-05, "loss": 4.2141, "step": 14994 }, { "epoch": 0.4580024434941967, "grad_norm": 0.40078839659690857, "learning_rate": 2.828891873379102e-05, "loss": 4.3266, "step": 14995 }, { "epoch": 0.45803298717165547, "grad_norm": 0.3851265013217926, "learning_rate": 2.8286540673491425e-05, "loss": 4.2876, "step": 14996 }, { "epoch": 0.4580635308491142, "grad_norm": 0.3840343654155731, "learning_rate": 2.8284162582930963e-05, "loss": 4.3795, "step": 14997 }, { "epoch": 0.458094074526573, "grad_norm": 0.3715974986553192, "learning_rate": 2.8281784462131527e-05, "loss": 4.2855, "step": 14998 }, { "epoch": 0.4581246182040318, "grad_norm": 0.39671099185943604, "learning_rate": 2.8279406311115014e-05, "loss": 4.3089, "step": 14999 }, { "epoch": 0.4581551618814905, "grad_norm": 0.38246163725852966, "learning_rate": 2.827702812990332e-05, "loss": 4.382, "step": 15000 }, { "epoch": 0.4581857055589493, "grad_norm": 0.38577261567115784, "learning_rate": 2.8274649918518346e-05, "loss": 4.3012, "step": 15001 }, { "epoch": 0.4582162492364081, "grad_norm": 0.37595540285110474, "learning_rate": 2.827227167698198e-05, "loss": 4.3616, "step": 15002 }, { "epoch": 0.45824679291386683, "grad_norm": 0.3835258185863495, "learning_rate": 2.8269893405316134e-05, "loss": 4.2914, "step": 15003 }, { "epoch": 0.4582773365913256, "grad_norm": 0.38472554087638855, "learning_rate": 2.826751510354269e-05, "loss": 4.3793, "step": 15004 }, { "epoch": 0.4583078802687844, "grad_norm": 0.37886136770248413, "learning_rate": 2.8265136771683566e-05, "loss": 4.2857, "step": 15005 }, { "epoch": 0.45833842394624313, "grad_norm": 0.39413750171661377, "learning_rate": 2.8262758409760636e-05, "loss": 4.2698, "step": 15006 }, { "epoch": 0.4583689676237019, "grad_norm": 0.38671955466270447, "learning_rate": 2.8260380017795823e-05, "loss": 4.2464, "step": 15007 }, { "epoch": 0.45839951130116063, "grad_norm": 0.3892291188240051, "learning_rate": 2.8258001595811007e-05, "loss": 4.3456, "step": 15008 }, { "epoch": 0.45843005497861944, "grad_norm": 0.3849923610687256, "learning_rate": 2.8255623143828092e-05, "loss": 4.2376, "step": 15009 }, { "epoch": 0.4584605986560782, "grad_norm": 0.4062742590904236, "learning_rate": 2.825324466186899e-05, "loss": 4.3488, "step": 15010 }, { "epoch": 0.45849114233353694, "grad_norm": 0.3949456512928009, "learning_rate": 2.825086614995559e-05, "loss": 4.3388, "step": 15011 }, { "epoch": 0.45852168601099574, "grad_norm": 0.3995009958744049, "learning_rate": 2.824848760810979e-05, "loss": 4.3111, "step": 15012 }, { "epoch": 0.4585522296884545, "grad_norm": 0.392088919878006, "learning_rate": 2.8246109036353497e-05, "loss": 4.2766, "step": 15013 }, { "epoch": 0.45858277336591324, "grad_norm": 0.39675042033195496, "learning_rate": 2.824373043470861e-05, "loss": 4.2952, "step": 15014 }, { "epoch": 0.45861331704337205, "grad_norm": 0.38368088006973267, "learning_rate": 2.8241351803197023e-05, "loss": 4.2584, "step": 15015 }, { "epoch": 0.4586438607208308, "grad_norm": 0.38079652190208435, "learning_rate": 2.8238973141840652e-05, "loss": 4.2795, "step": 15016 }, { "epoch": 0.45867440439828955, "grad_norm": 0.3933253288269043, "learning_rate": 2.8236594450661386e-05, "loss": 4.2571, "step": 15017 }, { "epoch": 0.4587049480757483, "grad_norm": 0.37791678309440613, "learning_rate": 2.8234215729681136e-05, "loss": 4.3752, "step": 15018 }, { "epoch": 0.4587354917532071, "grad_norm": 0.3818773329257965, "learning_rate": 2.8231836978921782e-05, "loss": 4.2584, "step": 15019 }, { "epoch": 0.45876603543066585, "grad_norm": 0.3993239104747772, "learning_rate": 2.8229458198405257e-05, "loss": 4.3234, "step": 15020 }, { "epoch": 0.4587965791081246, "grad_norm": 0.3842713236808777, "learning_rate": 2.8227079388153453e-05, "loss": 4.2494, "step": 15021 }, { "epoch": 0.4588271227855834, "grad_norm": 0.3839675486087799, "learning_rate": 2.8224700548188266e-05, "loss": 4.3606, "step": 15022 }, { "epoch": 0.45885766646304216, "grad_norm": 0.38681402802467346, "learning_rate": 2.82223216785316e-05, "loss": 4.3512, "step": 15023 }, { "epoch": 0.4588882101405009, "grad_norm": 0.3870103359222412, "learning_rate": 2.8219942779205367e-05, "loss": 4.2627, "step": 15024 }, { "epoch": 0.45891875381795966, "grad_norm": 0.39469340443611145, "learning_rate": 2.821756385023146e-05, "loss": 4.3172, "step": 15025 }, { "epoch": 0.45894929749541846, "grad_norm": 0.4017728269100189, "learning_rate": 2.8215184891631787e-05, "loss": 4.2647, "step": 15026 }, { "epoch": 0.4589798411728772, "grad_norm": 0.37808361649513245, "learning_rate": 2.8212805903428258e-05, "loss": 4.3079, "step": 15027 }, { "epoch": 0.45901038485033596, "grad_norm": 0.38142213225364685, "learning_rate": 2.821042688564277e-05, "loss": 4.2927, "step": 15028 }, { "epoch": 0.45904092852779477, "grad_norm": 0.37337031960487366, "learning_rate": 2.8208047838297236e-05, "loss": 4.2481, "step": 15029 }, { "epoch": 0.4590714722052535, "grad_norm": 0.3851308524608612, "learning_rate": 2.8205668761413555e-05, "loss": 4.3154, "step": 15030 }, { "epoch": 0.45910201588271227, "grad_norm": 0.39485234022140503, "learning_rate": 2.8203289655013632e-05, "loss": 4.3475, "step": 15031 }, { "epoch": 0.45913255956017107, "grad_norm": 0.3987090289592743, "learning_rate": 2.820091051911937e-05, "loss": 4.3177, "step": 15032 }, { "epoch": 0.4591631032376298, "grad_norm": 0.40445587038993835, "learning_rate": 2.8198531353752684e-05, "loss": 4.1582, "step": 15033 }, { "epoch": 0.45919364691508857, "grad_norm": 0.3933645188808441, "learning_rate": 2.8196152158935475e-05, "loss": 4.2955, "step": 15034 }, { "epoch": 0.4592241905925473, "grad_norm": 0.3886786699295044, "learning_rate": 2.819377293468965e-05, "loss": 4.299, "step": 15035 }, { "epoch": 0.4592547342700061, "grad_norm": 0.3949982523918152, "learning_rate": 2.8191393681037116e-05, "loss": 4.3357, "step": 15036 }, { "epoch": 0.4592852779474649, "grad_norm": 0.3709859848022461, "learning_rate": 2.818901439799978e-05, "loss": 4.4094, "step": 15037 }, { "epoch": 0.4593158216249236, "grad_norm": 0.38028484582901, "learning_rate": 2.8186635085599545e-05, "loss": 4.266, "step": 15038 }, { "epoch": 0.45934636530238243, "grad_norm": 0.38597631454467773, "learning_rate": 2.8184255743858318e-05, "loss": 4.2438, "step": 15039 }, { "epoch": 0.4593769089798412, "grad_norm": 0.38815778493881226, "learning_rate": 2.818187637279802e-05, "loss": 4.3246, "step": 15040 }, { "epoch": 0.45940745265729993, "grad_norm": 0.3698059916496277, "learning_rate": 2.817949697244055e-05, "loss": 4.3, "step": 15041 }, { "epoch": 0.4594379963347587, "grad_norm": 0.375566303730011, "learning_rate": 2.817711754280781e-05, "loss": 4.3069, "step": 15042 }, { "epoch": 0.4594685400122175, "grad_norm": 0.39436590671539307, "learning_rate": 2.817473808392172e-05, "loss": 4.3753, "step": 15043 }, { "epoch": 0.45949908368967624, "grad_norm": 0.38619962334632874, "learning_rate": 2.8172358595804188e-05, "loss": 4.0947, "step": 15044 }, { "epoch": 0.459529627367135, "grad_norm": 0.3892161250114441, "learning_rate": 2.8169979078477117e-05, "loss": 4.267, "step": 15045 }, { "epoch": 0.4595601710445938, "grad_norm": 0.3952939510345459, "learning_rate": 2.8167599531962412e-05, "loss": 4.2973, "step": 15046 }, { "epoch": 0.45959071472205254, "grad_norm": 0.39611056447029114, "learning_rate": 2.8165219956281998e-05, "loss": 4.2473, "step": 15047 }, { "epoch": 0.4596212583995113, "grad_norm": 0.39583900570869446, "learning_rate": 2.8162840351457768e-05, "loss": 4.2992, "step": 15048 }, { "epoch": 0.45965180207697004, "grad_norm": 0.3870404064655304, "learning_rate": 2.8160460717511648e-05, "loss": 4.3436, "step": 15049 }, { "epoch": 0.45968234575442884, "grad_norm": 0.3679991662502289, "learning_rate": 2.8158081054465535e-05, "loss": 4.3348, "step": 15050 }, { "epoch": 0.4597128894318876, "grad_norm": 0.3958812952041626, "learning_rate": 2.8155701362341354e-05, "loss": 4.2764, "step": 15051 }, { "epoch": 0.45974343310934634, "grad_norm": 0.38896870613098145, "learning_rate": 2.8153321641161e-05, "loss": 4.236, "step": 15052 }, { "epoch": 0.45977397678680515, "grad_norm": 0.3907927870750427, "learning_rate": 2.8150941890946402e-05, "loss": 4.3403, "step": 15053 }, { "epoch": 0.4598045204642639, "grad_norm": 0.3869878053665161, "learning_rate": 2.8148562111719458e-05, "loss": 4.2636, "step": 15054 }, { "epoch": 0.45983506414172265, "grad_norm": 0.3796008825302124, "learning_rate": 2.814618230350208e-05, "loss": 4.3864, "step": 15055 }, { "epoch": 0.45986560781918145, "grad_norm": 0.3849284052848816, "learning_rate": 2.8143802466316183e-05, "loss": 4.3093, "step": 15056 }, { "epoch": 0.4598961514966402, "grad_norm": 0.37703192234039307, "learning_rate": 2.8141422600183682e-05, "loss": 4.345, "step": 15057 }, { "epoch": 0.45992669517409895, "grad_norm": 0.38554221391677856, "learning_rate": 2.813904270512649e-05, "loss": 4.2408, "step": 15058 }, { "epoch": 0.4599572388515577, "grad_norm": 0.3858998119831085, "learning_rate": 2.8136662781166517e-05, "loss": 4.3431, "step": 15059 }, { "epoch": 0.4599877825290165, "grad_norm": 0.37537306547164917, "learning_rate": 2.8134282828325683e-05, "loss": 4.3033, "step": 15060 }, { "epoch": 0.46001832620647526, "grad_norm": 0.3782043159008026, "learning_rate": 2.8131902846625887e-05, "loss": 4.3174, "step": 15061 }, { "epoch": 0.460048869883934, "grad_norm": 0.3760753870010376, "learning_rate": 2.8129522836089057e-05, "loss": 4.3204, "step": 15062 }, { "epoch": 0.4600794135613928, "grad_norm": 0.39799901843070984, "learning_rate": 2.8127142796737095e-05, "loss": 4.314, "step": 15063 }, { "epoch": 0.46010995723885156, "grad_norm": 0.3918987810611725, "learning_rate": 2.8124762728591925e-05, "loss": 4.2415, "step": 15064 }, { "epoch": 0.4601405009163103, "grad_norm": 0.3826400637626648, "learning_rate": 2.8122382631675455e-05, "loss": 4.3579, "step": 15065 }, { "epoch": 0.46017104459376906, "grad_norm": 0.3787987232208252, "learning_rate": 2.8120002506009606e-05, "loss": 4.3212, "step": 15066 }, { "epoch": 0.46020158827122787, "grad_norm": 0.3855896592140198, "learning_rate": 2.8117622351616292e-05, "loss": 4.371, "step": 15067 }, { "epoch": 0.4602321319486866, "grad_norm": 0.3879561424255371, "learning_rate": 2.8115242168517425e-05, "loss": 4.3453, "step": 15068 }, { "epoch": 0.46026267562614537, "grad_norm": 0.38283416628837585, "learning_rate": 2.811286195673492e-05, "loss": 4.2898, "step": 15069 }, { "epoch": 0.4602932193036042, "grad_norm": 0.38902127742767334, "learning_rate": 2.8110481716290687e-05, "loss": 4.3233, "step": 15070 }, { "epoch": 0.4603237629810629, "grad_norm": 0.3839239478111267, "learning_rate": 2.810810144720666e-05, "loss": 4.1572, "step": 15071 }, { "epoch": 0.4603543066585217, "grad_norm": 0.3979319632053375, "learning_rate": 2.8105721149504742e-05, "loss": 4.1912, "step": 15072 }, { "epoch": 0.4603848503359805, "grad_norm": 0.3848041892051697, "learning_rate": 2.8103340823206847e-05, "loss": 4.2759, "step": 15073 }, { "epoch": 0.4604153940134392, "grad_norm": 0.3987838625907898, "learning_rate": 2.8100960468334903e-05, "loss": 4.2835, "step": 15074 }, { "epoch": 0.460445937690898, "grad_norm": 0.3886563777923584, "learning_rate": 2.8098580084910826e-05, "loss": 4.2162, "step": 15075 }, { "epoch": 0.4604764813683567, "grad_norm": 0.3918026387691498, "learning_rate": 2.809619967295653e-05, "loss": 4.3715, "step": 15076 }, { "epoch": 0.46050702504581553, "grad_norm": 0.3856097161769867, "learning_rate": 2.809381923249392e-05, "loss": 4.3437, "step": 15077 }, { "epoch": 0.4605375687232743, "grad_norm": 0.3976520001888275, "learning_rate": 2.8091438763544932e-05, "loss": 4.2943, "step": 15078 }, { "epoch": 0.46056811240073303, "grad_norm": 0.38708409667015076, "learning_rate": 2.808905826613148e-05, "loss": 4.3923, "step": 15079 }, { "epoch": 0.46059865607819184, "grad_norm": 0.3804764151573181, "learning_rate": 2.8086677740275473e-05, "loss": 4.3222, "step": 15080 }, { "epoch": 0.4606291997556506, "grad_norm": 0.395908921957016, "learning_rate": 2.8084297185998843e-05, "loss": 4.2244, "step": 15081 }, { "epoch": 0.46065974343310934, "grad_norm": 0.37423068284988403, "learning_rate": 2.80819166033235e-05, "loss": 4.3541, "step": 15082 }, { "epoch": 0.4606902871105681, "grad_norm": 0.39535728096961975, "learning_rate": 2.8079535992271373e-05, "loss": 4.3517, "step": 15083 }, { "epoch": 0.4607208307880269, "grad_norm": 0.37739306688308716, "learning_rate": 2.807715535286437e-05, "loss": 4.3672, "step": 15084 }, { "epoch": 0.46075137446548564, "grad_norm": 0.3796534240245819, "learning_rate": 2.8074774685124415e-05, "loss": 4.3309, "step": 15085 }, { "epoch": 0.4607819181429444, "grad_norm": 0.384432315826416, "learning_rate": 2.807239398907343e-05, "loss": 4.3366, "step": 15086 }, { "epoch": 0.4608124618204032, "grad_norm": 0.3961769640445709, "learning_rate": 2.807001326473333e-05, "loss": 4.2923, "step": 15087 }, { "epoch": 0.46084300549786195, "grad_norm": 0.38277995586395264, "learning_rate": 2.806763251212604e-05, "loss": 4.2656, "step": 15088 }, { "epoch": 0.4608735491753207, "grad_norm": 0.3958064019680023, "learning_rate": 2.8065251731273484e-05, "loss": 4.2253, "step": 15089 }, { "epoch": 0.4609040928527795, "grad_norm": 0.3934191167354584, "learning_rate": 2.806287092219758e-05, "loss": 4.2717, "step": 15090 }, { "epoch": 0.46093463653023825, "grad_norm": 0.3818977177143097, "learning_rate": 2.806049008492025e-05, "loss": 4.3494, "step": 15091 }, { "epoch": 0.460965180207697, "grad_norm": 0.3878364562988281, "learning_rate": 2.8058109219463414e-05, "loss": 4.083, "step": 15092 }, { "epoch": 0.46099572388515575, "grad_norm": 0.38581332564353943, "learning_rate": 2.805572832584899e-05, "loss": 4.3285, "step": 15093 }, { "epoch": 0.46102626756261456, "grad_norm": 0.38189560174942017, "learning_rate": 2.80533474040989e-05, "loss": 4.354, "step": 15094 }, { "epoch": 0.4610568112400733, "grad_norm": 0.3771619200706482, "learning_rate": 2.805096645423508e-05, "loss": 4.3187, "step": 15095 }, { "epoch": 0.46108735491753206, "grad_norm": 0.40104883909225464, "learning_rate": 2.8048585476279437e-05, "loss": 4.3154, "step": 15096 }, { "epoch": 0.46111789859499086, "grad_norm": 0.39359644055366516, "learning_rate": 2.8046204470253895e-05, "loss": 4.3123, "step": 15097 }, { "epoch": 0.4611484422724496, "grad_norm": 0.4021340608596802, "learning_rate": 2.8043823436180396e-05, "loss": 4.2759, "step": 15098 }, { "epoch": 0.46117898594990836, "grad_norm": 0.3878012001514435, "learning_rate": 2.8041442374080846e-05, "loss": 4.3528, "step": 15099 }, { "epoch": 0.4612095296273671, "grad_norm": 0.3865509331226349, "learning_rate": 2.8039061283977168e-05, "loss": 4.3794, "step": 15100 }, { "epoch": 0.4612400733048259, "grad_norm": 0.3955272436141968, "learning_rate": 2.8036680165891288e-05, "loss": 4.3411, "step": 15101 }, { "epoch": 0.46127061698228466, "grad_norm": 0.40593641996383667, "learning_rate": 2.803429901984514e-05, "loss": 4.3286, "step": 15102 }, { "epoch": 0.4613011606597434, "grad_norm": 0.39292654395103455, "learning_rate": 2.8031917845860635e-05, "loss": 4.2732, "step": 15103 }, { "epoch": 0.4613317043372022, "grad_norm": 0.3909320831298828, "learning_rate": 2.8029536643959697e-05, "loss": 4.304, "step": 15104 }, { "epoch": 0.46136224801466097, "grad_norm": 0.38363540172576904, "learning_rate": 2.802715541416427e-05, "loss": 4.3217, "step": 15105 }, { "epoch": 0.4613927916921197, "grad_norm": 0.3920879364013672, "learning_rate": 2.8024774156496264e-05, "loss": 4.3494, "step": 15106 }, { "epoch": 0.4614233353695785, "grad_norm": 0.3999933898448944, "learning_rate": 2.8022392870977602e-05, "loss": 4.3727, "step": 15107 }, { "epoch": 0.4614538790470373, "grad_norm": 0.3940039873123169, "learning_rate": 2.8020011557630222e-05, "loss": 4.178, "step": 15108 }, { "epoch": 0.461484422724496, "grad_norm": 0.3810461461544037, "learning_rate": 2.8017630216476044e-05, "loss": 4.3315, "step": 15109 }, { "epoch": 0.4615149664019548, "grad_norm": 0.389159232378006, "learning_rate": 2.8015248847536983e-05, "loss": 4.2335, "step": 15110 }, { "epoch": 0.4615455100794136, "grad_norm": 1.0718860626220703, "learning_rate": 2.8012867450834977e-05, "loss": 4.2709, "step": 15111 }, { "epoch": 0.46157605375687233, "grad_norm": 0.3899949789047241, "learning_rate": 2.8010486026391958e-05, "loss": 4.2381, "step": 15112 }, { "epoch": 0.4616065974343311, "grad_norm": 0.39609482884407043, "learning_rate": 2.8008104574229844e-05, "loss": 4.3819, "step": 15113 }, { "epoch": 0.4616371411117899, "grad_norm": 0.396730899810791, "learning_rate": 2.8005723094370568e-05, "loss": 4.3831, "step": 15114 }, { "epoch": 0.46166768478924863, "grad_norm": 0.38996389508247375, "learning_rate": 2.8003341586836053e-05, "loss": 4.2175, "step": 15115 }, { "epoch": 0.4616982284667074, "grad_norm": 0.40056881308555603, "learning_rate": 2.8000960051648223e-05, "loss": 4.3429, "step": 15116 }, { "epoch": 0.46172877214416613, "grad_norm": 0.3918344974517822, "learning_rate": 2.7998578488829012e-05, "loss": 4.2436, "step": 15117 }, { "epoch": 0.46175931582162494, "grad_norm": 0.3898109793663025, "learning_rate": 2.7996196898400346e-05, "loss": 4.344, "step": 15118 }, { "epoch": 0.4617898594990837, "grad_norm": 0.38678833842277527, "learning_rate": 2.7993815280384156e-05, "loss": 4.3737, "step": 15119 }, { "epoch": 0.46182040317654244, "grad_norm": 0.38914555311203003, "learning_rate": 2.7991433634802372e-05, "loss": 4.2462, "step": 15120 }, { "epoch": 0.46185094685400124, "grad_norm": 0.38868528604507446, "learning_rate": 2.7989051961676914e-05, "loss": 4.2844, "step": 15121 }, { "epoch": 0.46188149053146, "grad_norm": 0.39540770649909973, "learning_rate": 2.798667026102973e-05, "loss": 4.2558, "step": 15122 }, { "epoch": 0.46191203420891874, "grad_norm": 0.3950958847999573, "learning_rate": 2.798428853288273e-05, "loss": 4.27, "step": 15123 }, { "epoch": 0.4619425778863775, "grad_norm": 0.3820394277572632, "learning_rate": 2.7981906777257856e-05, "loss": 4.3009, "step": 15124 }, { "epoch": 0.4619731215638363, "grad_norm": 0.39168021082878113, "learning_rate": 2.7979524994177018e-05, "loss": 4.27, "step": 15125 }, { "epoch": 0.46200366524129505, "grad_norm": 0.3914065957069397, "learning_rate": 2.7977143183662175e-05, "loss": 4.38, "step": 15126 }, { "epoch": 0.4620342089187538, "grad_norm": 0.38430628180503845, "learning_rate": 2.797476134573524e-05, "loss": 4.2334, "step": 15127 }, { "epoch": 0.4620647525962126, "grad_norm": 0.4025280475616455, "learning_rate": 2.7972379480418144e-05, "loss": 4.2882, "step": 15128 }, { "epoch": 0.46209529627367135, "grad_norm": 0.3783382475376129, "learning_rate": 2.7969997587732828e-05, "loss": 4.2463, "step": 15129 }, { "epoch": 0.4621258399511301, "grad_norm": 0.3841410279273987, "learning_rate": 2.796761566770122e-05, "loss": 4.2672, "step": 15130 }, { "epoch": 0.4621563836285889, "grad_norm": 0.38704243302345276, "learning_rate": 2.796523372034524e-05, "loss": 4.3465, "step": 15131 }, { "epoch": 0.46218692730604766, "grad_norm": 0.3908962905406952, "learning_rate": 2.7962851745686836e-05, "loss": 4.2662, "step": 15132 }, { "epoch": 0.4622174709835064, "grad_norm": 0.3929438889026642, "learning_rate": 2.796046974374793e-05, "loss": 4.3252, "step": 15133 }, { "epoch": 0.46224801466096516, "grad_norm": 0.3920724391937256, "learning_rate": 2.7958087714550456e-05, "loss": 4.2517, "step": 15134 }, { "epoch": 0.46227855833842396, "grad_norm": 0.3800930678844452, "learning_rate": 2.7955705658116344e-05, "loss": 4.2935, "step": 15135 }, { "epoch": 0.4623091020158827, "grad_norm": 0.3857598602771759, "learning_rate": 2.795332357446753e-05, "loss": 4.3051, "step": 15136 }, { "epoch": 0.46233964569334146, "grad_norm": 0.39083436131477356, "learning_rate": 2.7950941463625956e-05, "loss": 4.3885, "step": 15137 }, { "epoch": 0.46237018937080027, "grad_norm": 0.3847818076610565, "learning_rate": 2.7948559325613542e-05, "loss": 4.3237, "step": 15138 }, { "epoch": 0.462400733048259, "grad_norm": 0.38645121455192566, "learning_rate": 2.7946177160452232e-05, "loss": 4.3546, "step": 15139 }, { "epoch": 0.46243127672571777, "grad_norm": 0.3708156645298004, "learning_rate": 2.794379496816395e-05, "loss": 4.2925, "step": 15140 }, { "epoch": 0.4624618204031765, "grad_norm": 0.3870747685432434, "learning_rate": 2.794141274877063e-05, "loss": 4.2985, "step": 15141 }, { "epoch": 0.4624923640806353, "grad_norm": 0.3782426714897156, "learning_rate": 2.793903050229421e-05, "loss": 4.2534, "step": 15142 }, { "epoch": 0.46252290775809407, "grad_norm": 0.39317595958709717, "learning_rate": 2.793664822875663e-05, "loss": 4.3493, "step": 15143 }, { "epoch": 0.4625534514355528, "grad_norm": 0.39249157905578613, "learning_rate": 2.793426592817982e-05, "loss": 4.339, "step": 15144 }, { "epoch": 0.4625839951130116, "grad_norm": 0.38619494438171387, "learning_rate": 2.7931883600585712e-05, "loss": 4.2409, "step": 15145 }, { "epoch": 0.4626145387904704, "grad_norm": 0.3845440149307251, "learning_rate": 2.7929501245996247e-05, "loss": 4.2633, "step": 15146 }, { "epoch": 0.4626450824679291, "grad_norm": 0.3956603407859802, "learning_rate": 2.792711886443336e-05, "loss": 4.3356, "step": 15147 }, { "epoch": 0.46267562614538793, "grad_norm": 0.39752620458602905, "learning_rate": 2.7924736455918976e-05, "loss": 4.2664, "step": 15148 }, { "epoch": 0.4627061698228467, "grad_norm": 0.3794271945953369, "learning_rate": 2.7922354020475046e-05, "loss": 4.2784, "step": 15149 }, { "epoch": 0.46273671350030543, "grad_norm": 0.3810443580150604, "learning_rate": 2.7919971558123498e-05, "loss": 4.2399, "step": 15150 }, { "epoch": 0.4627672571777642, "grad_norm": 0.38846129179000854, "learning_rate": 2.7917589068886274e-05, "loss": 4.2975, "step": 15151 }, { "epoch": 0.462797800855223, "grad_norm": 0.3910019099712372, "learning_rate": 2.79152065527853e-05, "loss": 4.2974, "step": 15152 }, { "epoch": 0.46282834453268173, "grad_norm": 0.3921000063419342, "learning_rate": 2.7912824009842527e-05, "loss": 4.2726, "step": 15153 }, { "epoch": 0.4628588882101405, "grad_norm": 0.3847578763961792, "learning_rate": 2.7910441440079886e-05, "loss": 4.2844, "step": 15154 }, { "epoch": 0.4628894318875993, "grad_norm": 0.3892609775066376, "learning_rate": 2.790805884351931e-05, "loss": 4.3143, "step": 15155 }, { "epoch": 0.46291997556505804, "grad_norm": 0.3938538730144501, "learning_rate": 2.7905676220182742e-05, "loss": 4.2257, "step": 15156 }, { "epoch": 0.4629505192425168, "grad_norm": 0.37594643235206604, "learning_rate": 2.7903293570092122e-05, "loss": 4.3502, "step": 15157 }, { "epoch": 0.46298106291997554, "grad_norm": 0.3818259537220001, "learning_rate": 2.7900910893269382e-05, "loss": 4.3531, "step": 15158 }, { "epoch": 0.46301160659743434, "grad_norm": 0.3807727098464966, "learning_rate": 2.789852818973646e-05, "loss": 4.2738, "step": 15159 }, { "epoch": 0.4630421502748931, "grad_norm": 0.38510599732398987, "learning_rate": 2.789614545951531e-05, "loss": 4.3593, "step": 15160 }, { "epoch": 0.46307269395235184, "grad_norm": 0.3708555996417999, "learning_rate": 2.7893762702627853e-05, "loss": 4.3143, "step": 15161 }, { "epoch": 0.46310323762981065, "grad_norm": 0.3912312090396881, "learning_rate": 2.7891379919096038e-05, "loss": 4.3284, "step": 15162 }, { "epoch": 0.4631337813072694, "grad_norm": 0.37453794479370117, "learning_rate": 2.78889971089418e-05, "loss": 4.2452, "step": 15163 }, { "epoch": 0.46316432498472815, "grad_norm": 0.38475745916366577, "learning_rate": 2.7886614272187078e-05, "loss": 4.3195, "step": 15164 }, { "epoch": 0.46319486866218695, "grad_norm": 0.3766292333602905, "learning_rate": 2.7884231408853813e-05, "loss": 4.3061, "step": 15165 }, { "epoch": 0.4632254123396457, "grad_norm": 0.38518843054771423, "learning_rate": 2.788184851896395e-05, "loss": 4.2749, "step": 15166 }, { "epoch": 0.46325595601710445, "grad_norm": 0.39096781611442566, "learning_rate": 2.7879465602539422e-05, "loss": 4.2408, "step": 15167 }, { "epoch": 0.4632864996945632, "grad_norm": 0.39034637808799744, "learning_rate": 2.7877082659602183e-05, "loss": 4.234, "step": 15168 }, { "epoch": 0.463317043372022, "grad_norm": 0.3862096071243286, "learning_rate": 2.7874699690174155e-05, "loss": 4.2833, "step": 15169 }, { "epoch": 0.46334758704948076, "grad_norm": 0.3901599645614624, "learning_rate": 2.7872316694277295e-05, "loss": 4.317, "step": 15170 }, { "epoch": 0.4633781307269395, "grad_norm": 0.39380592107772827, "learning_rate": 2.786993367193354e-05, "loss": 4.2758, "step": 15171 }, { "epoch": 0.4634086744043983, "grad_norm": 0.3882925510406494, "learning_rate": 2.7867550623164816e-05, "loss": 4.3608, "step": 15172 }, { "epoch": 0.46343921808185706, "grad_norm": 0.38528764247894287, "learning_rate": 2.7865167547993093e-05, "loss": 4.2051, "step": 15173 }, { "epoch": 0.4634697617593158, "grad_norm": 0.3876763880252838, "learning_rate": 2.78627844464403e-05, "loss": 4.2975, "step": 15174 }, { "epoch": 0.46350030543677456, "grad_norm": 0.3870311379432678, "learning_rate": 2.7860401318528374e-05, "loss": 4.351, "step": 15175 }, { "epoch": 0.46353084911423337, "grad_norm": 0.4002728760242462, "learning_rate": 2.7858018164279254e-05, "loss": 4.3793, "step": 15176 }, { "epoch": 0.4635613927916921, "grad_norm": 0.39304959774017334, "learning_rate": 2.7855634983714908e-05, "loss": 4.2375, "step": 15177 }, { "epoch": 0.46359193646915087, "grad_norm": 0.3853696584701538, "learning_rate": 2.785325177685726e-05, "loss": 4.2684, "step": 15178 }, { "epoch": 0.4636224801466097, "grad_norm": 0.3809547424316406, "learning_rate": 2.7850868543728244e-05, "loss": 4.4238, "step": 15179 }, { "epoch": 0.4636530238240684, "grad_norm": 0.37744367122650146, "learning_rate": 2.784848528434982e-05, "loss": 4.2535, "step": 15180 }, { "epoch": 0.46368356750152717, "grad_norm": 0.38840094208717346, "learning_rate": 2.7846101998743928e-05, "loss": 4.2676, "step": 15181 }, { "epoch": 0.463714111178986, "grad_norm": 0.3924511671066284, "learning_rate": 2.7843718686932514e-05, "loss": 4.276, "step": 15182 }, { "epoch": 0.4637446548564447, "grad_norm": 0.38615912199020386, "learning_rate": 2.7841335348937513e-05, "loss": 4.2026, "step": 15183 }, { "epoch": 0.4637751985339035, "grad_norm": 0.38126763701438904, "learning_rate": 2.7838951984780886e-05, "loss": 4.2361, "step": 15184 }, { "epoch": 0.4638057422113622, "grad_norm": 0.384329229593277, "learning_rate": 2.7836568594484568e-05, "loss": 4.321, "step": 15185 }, { "epoch": 0.46383628588882103, "grad_norm": 0.376310259103775, "learning_rate": 2.7834185178070497e-05, "loss": 4.216, "step": 15186 }, { "epoch": 0.4638668295662798, "grad_norm": 0.40188685059547424, "learning_rate": 2.7831801735560636e-05, "loss": 4.3984, "step": 15187 }, { "epoch": 0.46389737324373853, "grad_norm": 0.39262062311172485, "learning_rate": 2.7829418266976915e-05, "loss": 4.2277, "step": 15188 }, { "epoch": 0.46392791692119734, "grad_norm": 0.38595911860466003, "learning_rate": 2.7827034772341283e-05, "loss": 4.1745, "step": 15189 }, { "epoch": 0.4639584605986561, "grad_norm": 0.39000406861305237, "learning_rate": 2.782465125167569e-05, "loss": 4.2371, "step": 15190 }, { "epoch": 0.46398900427611484, "grad_norm": 0.38677603006362915, "learning_rate": 2.7822267705002082e-05, "loss": 4.2085, "step": 15191 }, { "epoch": 0.4640195479535736, "grad_norm": 0.39596325159072876, "learning_rate": 2.78198841323424e-05, "loss": 4.385, "step": 15192 }, { "epoch": 0.4640500916310324, "grad_norm": 0.3819620907306671, "learning_rate": 2.78175005337186e-05, "loss": 4.2673, "step": 15193 }, { "epoch": 0.46408063530849114, "grad_norm": 0.38111796975135803, "learning_rate": 2.7815116909152624e-05, "loss": 4.3244, "step": 15194 }, { "epoch": 0.4641111789859499, "grad_norm": 0.37742769718170166, "learning_rate": 2.781273325866642e-05, "loss": 4.2986, "step": 15195 }, { "epoch": 0.4641417226634087, "grad_norm": 0.38607120513916016, "learning_rate": 2.7810349582281925e-05, "loss": 4.3189, "step": 15196 }, { "epoch": 0.46417226634086745, "grad_norm": 0.3779662847518921, "learning_rate": 2.7807965880021102e-05, "loss": 4.2255, "step": 15197 }, { "epoch": 0.4642028100183262, "grad_norm": 0.3790712356567383, "learning_rate": 2.7805582151905897e-05, "loss": 4.305, "step": 15198 }, { "epoch": 0.46423335369578494, "grad_norm": 0.3711593449115753, "learning_rate": 2.7803198397958254e-05, "loss": 4.2659, "step": 15199 }, { "epoch": 0.46426389737324375, "grad_norm": 0.3901118040084839, "learning_rate": 2.780081461820012e-05, "loss": 4.3018, "step": 15200 }, { "epoch": 0.4642944410507025, "grad_norm": 0.3730587363243103, "learning_rate": 2.779843081265345e-05, "loss": 4.2759, "step": 15201 }, { "epoch": 0.46432498472816125, "grad_norm": 0.3842100203037262, "learning_rate": 2.7796046981340184e-05, "loss": 4.3269, "step": 15202 }, { "epoch": 0.46435552840562005, "grad_norm": 0.39410707354545593, "learning_rate": 2.779366312428227e-05, "loss": 4.3309, "step": 15203 }, { "epoch": 0.4643860720830788, "grad_norm": 0.3800823390483856, "learning_rate": 2.7791279241501672e-05, "loss": 4.2151, "step": 15204 }, { "epoch": 0.46441661576053755, "grad_norm": 0.38526004552841187, "learning_rate": 2.778889533302033e-05, "loss": 4.3772, "step": 15205 }, { "epoch": 0.46444715943799636, "grad_norm": 0.38140228390693665, "learning_rate": 2.7786511398860194e-05, "loss": 4.3908, "step": 15206 }, { "epoch": 0.4644777031154551, "grad_norm": 0.3779473900794983, "learning_rate": 2.7784127439043212e-05, "loss": 4.279, "step": 15207 }, { "epoch": 0.46450824679291386, "grad_norm": 0.39129313826560974, "learning_rate": 2.778174345359134e-05, "loss": 4.2008, "step": 15208 }, { "epoch": 0.4645387904703726, "grad_norm": 0.39221906661987305, "learning_rate": 2.777935944252653e-05, "loss": 4.3117, "step": 15209 }, { "epoch": 0.4645693341478314, "grad_norm": 0.38841357827186584, "learning_rate": 2.777697540587072e-05, "loss": 4.2205, "step": 15210 }, { "epoch": 0.46459987782529016, "grad_norm": 0.3944137692451477, "learning_rate": 2.7774591343645877e-05, "loss": 4.3216, "step": 15211 }, { "epoch": 0.4646304215027489, "grad_norm": 0.38094255328178406, "learning_rate": 2.7772207255873943e-05, "loss": 4.3786, "step": 15212 }, { "epoch": 0.4646609651802077, "grad_norm": 0.3844081461429596, "learning_rate": 2.7769823142576868e-05, "loss": 4.2476, "step": 15213 }, { "epoch": 0.46469150885766647, "grad_norm": 0.3950464427471161, "learning_rate": 2.7767439003776606e-05, "loss": 4.344, "step": 15214 }, { "epoch": 0.4647220525351252, "grad_norm": 0.3852338492870331, "learning_rate": 2.776505483949512e-05, "loss": 4.3616, "step": 15215 }, { "epoch": 0.46475259621258397, "grad_norm": 0.392776757478714, "learning_rate": 2.7762670649754348e-05, "loss": 4.3442, "step": 15216 }, { "epoch": 0.4647831398900428, "grad_norm": 0.3931408226490021, "learning_rate": 2.7760286434576245e-05, "loss": 4.3475, "step": 15217 }, { "epoch": 0.4648136835675015, "grad_norm": 0.4085142910480499, "learning_rate": 2.7757902193982765e-05, "loss": 4.3081, "step": 15218 }, { "epoch": 0.4648442272449603, "grad_norm": 0.38992413878440857, "learning_rate": 2.775551792799586e-05, "loss": 4.2817, "step": 15219 }, { "epoch": 0.4648747709224191, "grad_norm": 0.3841494023799896, "learning_rate": 2.7753133636637485e-05, "loss": 4.2766, "step": 15220 }, { "epoch": 0.46490531459987783, "grad_norm": 0.3926953971385956, "learning_rate": 2.775074931992959e-05, "loss": 4.3038, "step": 15221 }, { "epoch": 0.4649358582773366, "grad_norm": 0.3842199742794037, "learning_rate": 2.7748364977894142e-05, "loss": 4.341, "step": 15222 }, { "epoch": 0.4649664019547954, "grad_norm": 0.4051361083984375, "learning_rate": 2.774598061055308e-05, "loss": 4.1936, "step": 15223 }, { "epoch": 0.46499694563225413, "grad_norm": 0.39007699489593506, "learning_rate": 2.7743596217928362e-05, "loss": 4.2714, "step": 15224 }, { "epoch": 0.4650274893097129, "grad_norm": 0.37872961163520813, "learning_rate": 2.7741211800041943e-05, "loss": 4.3336, "step": 15225 }, { "epoch": 0.46505803298717163, "grad_norm": 0.3825146555900574, "learning_rate": 2.773882735691578e-05, "loss": 4.3027, "step": 15226 }, { "epoch": 0.46508857666463044, "grad_norm": 0.38913628458976746, "learning_rate": 2.7736442888571818e-05, "loss": 4.2582, "step": 15227 }, { "epoch": 0.4651191203420892, "grad_norm": 0.39914843440055847, "learning_rate": 2.7734058395032024e-05, "loss": 4.2643, "step": 15228 }, { "epoch": 0.46514966401954794, "grad_norm": 0.39079469442367554, "learning_rate": 2.7731673876318353e-05, "loss": 4.3086, "step": 15229 }, { "epoch": 0.46518020769700674, "grad_norm": 0.3861512839794159, "learning_rate": 2.7729289332452746e-05, "loss": 4.2706, "step": 15230 }, { "epoch": 0.4652107513744655, "grad_norm": 0.38725951313972473, "learning_rate": 2.772690476345718e-05, "loss": 4.3334, "step": 15231 }, { "epoch": 0.46524129505192424, "grad_norm": 0.3913716673851013, "learning_rate": 2.7724520169353596e-05, "loss": 4.2407, "step": 15232 }, { "epoch": 0.465271838729383, "grad_norm": 0.39360255002975464, "learning_rate": 2.772213555016395e-05, "loss": 4.2124, "step": 15233 }, { "epoch": 0.4653023824068418, "grad_norm": 0.3994910418987274, "learning_rate": 2.771975090591021e-05, "loss": 4.3192, "step": 15234 }, { "epoch": 0.46533292608430055, "grad_norm": 0.3964556157588959, "learning_rate": 2.7717366236614317e-05, "loss": 4.2241, "step": 15235 }, { "epoch": 0.4653634697617593, "grad_norm": 0.38639774918556213, "learning_rate": 2.771498154229824e-05, "loss": 4.3097, "step": 15236 }, { "epoch": 0.4653940134392181, "grad_norm": 0.39815860986709595, "learning_rate": 2.771259682298393e-05, "loss": 4.299, "step": 15237 }, { "epoch": 0.46542455711667685, "grad_norm": 0.3916257619857788, "learning_rate": 2.7710212078693342e-05, "loss": 4.2755, "step": 15238 }, { "epoch": 0.4654551007941356, "grad_norm": 0.39220455288887024, "learning_rate": 2.7707827309448447e-05, "loss": 4.2373, "step": 15239 }, { "epoch": 0.4654856444715944, "grad_norm": 0.3770388066768646, "learning_rate": 2.770544251527119e-05, "loss": 4.2347, "step": 15240 }, { "epoch": 0.46551618814905316, "grad_norm": 0.3853488564491272, "learning_rate": 2.7703057696183537e-05, "loss": 4.3874, "step": 15241 }, { "epoch": 0.4655467318265119, "grad_norm": 0.37316974997520447, "learning_rate": 2.770067285220744e-05, "loss": 4.2866, "step": 15242 }, { "epoch": 0.46557727550397066, "grad_norm": 0.38577473163604736, "learning_rate": 2.7698287983364858e-05, "loss": 4.1869, "step": 15243 }, { "epoch": 0.46560781918142946, "grad_norm": 0.37949666380882263, "learning_rate": 2.7695903089677745e-05, "loss": 4.3142, "step": 15244 }, { "epoch": 0.4656383628588882, "grad_norm": 0.379169762134552, "learning_rate": 2.769351817116807e-05, "loss": 4.2584, "step": 15245 }, { "epoch": 0.46566890653634696, "grad_norm": 0.39251089096069336, "learning_rate": 2.7691133227857792e-05, "loss": 4.2432, "step": 15246 }, { "epoch": 0.46569945021380577, "grad_norm": 0.4014255106449127, "learning_rate": 2.7688748259768867e-05, "loss": 4.3066, "step": 15247 }, { "epoch": 0.4657299938912645, "grad_norm": 0.378735214471817, "learning_rate": 2.7686363266923255e-05, "loss": 4.2782, "step": 15248 }, { "epoch": 0.46576053756872327, "grad_norm": 0.39137664437294006, "learning_rate": 2.7683978249342913e-05, "loss": 4.2958, "step": 15249 }, { "epoch": 0.465791081246182, "grad_norm": 0.38793572783470154, "learning_rate": 2.76815932070498e-05, "loss": 4.2671, "step": 15250 }, { "epoch": 0.4658216249236408, "grad_norm": 0.3809603750705719, "learning_rate": 2.7679208140065876e-05, "loss": 4.3015, "step": 15251 }, { "epoch": 0.46585216860109957, "grad_norm": 0.37141478061676025, "learning_rate": 2.7676823048413115e-05, "loss": 4.3066, "step": 15252 }, { "epoch": 0.4658827122785583, "grad_norm": 0.3910270631313324, "learning_rate": 2.7674437932113468e-05, "loss": 4.336, "step": 15253 }, { "epoch": 0.4659132559560171, "grad_norm": 0.3920544981956482, "learning_rate": 2.7672052791188886e-05, "loss": 4.3777, "step": 15254 }, { "epoch": 0.4659437996334759, "grad_norm": 0.3732364773750305, "learning_rate": 2.766966762566135e-05, "loss": 4.2547, "step": 15255 }, { "epoch": 0.4659743433109346, "grad_norm": 0.3886166214942932, "learning_rate": 2.766728243555281e-05, "loss": 4.363, "step": 15256 }, { "epoch": 0.46600488698839343, "grad_norm": 0.39290517568588257, "learning_rate": 2.7664897220885222e-05, "loss": 4.3561, "step": 15257 }, { "epoch": 0.4660354306658522, "grad_norm": 0.37697452306747437, "learning_rate": 2.7662511981680562e-05, "loss": 4.2953, "step": 15258 }, { "epoch": 0.46606597434331093, "grad_norm": 0.38650816679000854, "learning_rate": 2.7660126717960787e-05, "loss": 4.3046, "step": 15259 }, { "epoch": 0.4660965180207697, "grad_norm": 0.391120046377182, "learning_rate": 2.765774142974785e-05, "loss": 4.4251, "step": 15260 }, { "epoch": 0.4661270616982285, "grad_norm": 0.3899230659008026, "learning_rate": 2.7655356117063723e-05, "loss": 4.3168, "step": 15261 }, { "epoch": 0.46615760537568723, "grad_norm": 0.38049817085266113, "learning_rate": 2.765297077993037e-05, "loss": 4.2305, "step": 15262 }, { "epoch": 0.466188149053146, "grad_norm": 0.39041465520858765, "learning_rate": 2.765058541836975e-05, "loss": 4.3025, "step": 15263 }, { "epoch": 0.4662186927306048, "grad_norm": 0.3937635123729706, "learning_rate": 2.7648200032403832e-05, "loss": 4.3302, "step": 15264 }, { "epoch": 0.46624923640806354, "grad_norm": 0.40349340438842773, "learning_rate": 2.7645814622054573e-05, "loss": 4.3224, "step": 15265 }, { "epoch": 0.4662797800855223, "grad_norm": 0.3985079228878021, "learning_rate": 2.7643429187343935e-05, "loss": 4.3201, "step": 15266 }, { "epoch": 0.46631032376298104, "grad_norm": 0.37725695967674255, "learning_rate": 2.7641043728293886e-05, "loss": 4.381, "step": 15267 }, { "epoch": 0.46634086744043984, "grad_norm": 0.3740220367908478, "learning_rate": 2.7638658244926385e-05, "loss": 4.288, "step": 15268 }, { "epoch": 0.4663714111178986, "grad_norm": 0.4019829034805298, "learning_rate": 2.7636272737263408e-05, "loss": 4.3277, "step": 15269 }, { "epoch": 0.46640195479535734, "grad_norm": 0.39471858739852905, "learning_rate": 2.763388720532691e-05, "loss": 4.2064, "step": 15270 }, { "epoch": 0.46643249847281615, "grad_norm": 0.3854384422302246, "learning_rate": 2.763150164913886e-05, "loss": 4.2717, "step": 15271 }, { "epoch": 0.4664630421502749, "grad_norm": 0.389084130525589, "learning_rate": 2.7629116068721216e-05, "loss": 4.1319, "step": 15272 }, { "epoch": 0.46649358582773365, "grad_norm": 0.3830702602863312, "learning_rate": 2.762673046409596e-05, "loss": 4.3158, "step": 15273 }, { "epoch": 0.4665241295051924, "grad_norm": 0.3829413056373596, "learning_rate": 2.7624344835285037e-05, "loss": 4.2485, "step": 15274 }, { "epoch": 0.4665546731826512, "grad_norm": 0.38758885860443115, "learning_rate": 2.762195918231042e-05, "loss": 4.3495, "step": 15275 }, { "epoch": 0.46658521686010995, "grad_norm": 0.3895930051803589, "learning_rate": 2.761957350519408e-05, "loss": 4.3321, "step": 15276 }, { "epoch": 0.4666157605375687, "grad_norm": 0.3863026201725006, "learning_rate": 2.761718780395798e-05, "loss": 4.2352, "step": 15277 }, { "epoch": 0.4666463042150275, "grad_norm": 0.3938261866569519, "learning_rate": 2.7614802078624086e-05, "loss": 4.2166, "step": 15278 }, { "epoch": 0.46667684789248626, "grad_norm": 0.3840535283088684, "learning_rate": 2.7612416329214365e-05, "loss": 4.3455, "step": 15279 }, { "epoch": 0.466707391569945, "grad_norm": 0.39660030603408813, "learning_rate": 2.761003055575079e-05, "loss": 4.3623, "step": 15280 }, { "epoch": 0.4667379352474038, "grad_norm": 0.3875378966331482, "learning_rate": 2.760764475825531e-05, "loss": 4.2656, "step": 15281 }, { "epoch": 0.46676847892486256, "grad_norm": 0.39734023809432983, "learning_rate": 2.7605258936749904e-05, "loss": 4.3615, "step": 15282 }, { "epoch": 0.4667990226023213, "grad_norm": 0.40882575511932373, "learning_rate": 2.7602873091256547e-05, "loss": 4.3772, "step": 15283 }, { "epoch": 0.46682956627978006, "grad_norm": 0.3914942443370819, "learning_rate": 2.76004872217972e-05, "loss": 4.3523, "step": 15284 }, { "epoch": 0.46686010995723887, "grad_norm": 0.3962928056716919, "learning_rate": 2.7598101328393822e-05, "loss": 4.2953, "step": 15285 }, { "epoch": 0.4668906536346976, "grad_norm": 0.39194396138191223, "learning_rate": 2.7595715411068395e-05, "loss": 4.2279, "step": 15286 }, { "epoch": 0.46692119731215637, "grad_norm": 0.3896026313304901, "learning_rate": 2.759332946984289e-05, "loss": 4.3271, "step": 15287 }, { "epoch": 0.46695174098961517, "grad_norm": 0.39452841877937317, "learning_rate": 2.7590943504739247e-05, "loss": 4.4131, "step": 15288 }, { "epoch": 0.4669822846670739, "grad_norm": 0.39497342705726624, "learning_rate": 2.7588557515779467e-05, "loss": 4.2562, "step": 15289 }, { "epoch": 0.46701282834453267, "grad_norm": 0.38636451959609985, "learning_rate": 2.758617150298551e-05, "loss": 4.3666, "step": 15290 }, { "epoch": 0.4670433720219914, "grad_norm": 0.39028096199035645, "learning_rate": 2.758378546637934e-05, "loss": 4.3193, "step": 15291 }, { "epoch": 0.4670739156994502, "grad_norm": 0.4001135528087616, "learning_rate": 2.7581399405982923e-05, "loss": 4.309, "step": 15292 }, { "epoch": 0.467104459376909, "grad_norm": 0.3805288076400757, "learning_rate": 2.7579013321818236e-05, "loss": 4.3355, "step": 15293 }, { "epoch": 0.4671350030543677, "grad_norm": 0.38950249552726746, "learning_rate": 2.757662721390725e-05, "loss": 4.2852, "step": 15294 }, { "epoch": 0.46716554673182653, "grad_norm": 0.4104808270931244, "learning_rate": 2.7574241082271934e-05, "loss": 4.2138, "step": 15295 }, { "epoch": 0.4671960904092853, "grad_norm": 0.39670300483703613, "learning_rate": 2.757185492693426e-05, "loss": 4.2589, "step": 15296 }, { "epoch": 0.46722663408674403, "grad_norm": 0.3823201358318329, "learning_rate": 2.7569468747916188e-05, "loss": 4.2859, "step": 15297 }, { "epoch": 0.46725717776420284, "grad_norm": 0.40361642837524414, "learning_rate": 2.75670825452397e-05, "loss": 4.2552, "step": 15298 }, { "epoch": 0.4672877214416616, "grad_norm": 0.382588267326355, "learning_rate": 2.756469631892676e-05, "loss": 4.2302, "step": 15299 }, { "epoch": 0.46731826511912034, "grad_norm": 0.4106360077857971, "learning_rate": 2.7562310068999347e-05, "loss": 4.3354, "step": 15300 }, { "epoch": 0.4673488087965791, "grad_norm": 0.3872615098953247, "learning_rate": 2.7559923795479425e-05, "loss": 4.207, "step": 15301 }, { "epoch": 0.4673793524740379, "grad_norm": 0.3930322229862213, "learning_rate": 2.7557537498388968e-05, "loss": 4.2746, "step": 15302 }, { "epoch": 0.46740989615149664, "grad_norm": 0.3923473060131073, "learning_rate": 2.7555151177749948e-05, "loss": 4.323, "step": 15303 }, { "epoch": 0.4674404398289554, "grad_norm": 0.38886019587516785, "learning_rate": 2.7552764833584344e-05, "loss": 4.2964, "step": 15304 }, { "epoch": 0.4674709835064142, "grad_norm": 0.3817739486694336, "learning_rate": 2.7550378465914108e-05, "loss": 4.3209, "step": 15305 }, { "epoch": 0.46750152718387294, "grad_norm": 0.377573698759079, "learning_rate": 2.7547992074761238e-05, "loss": 4.3813, "step": 15306 }, { "epoch": 0.4675320708613317, "grad_norm": 0.3820054829120636, "learning_rate": 2.754560566014769e-05, "loss": 4.3231, "step": 15307 }, { "epoch": 0.46756261453879044, "grad_norm": 0.4014400839805603, "learning_rate": 2.7543219222095447e-05, "loss": 4.2697, "step": 15308 }, { "epoch": 0.46759315821624925, "grad_norm": 0.38492682576179504, "learning_rate": 2.7540832760626466e-05, "loss": 4.3426, "step": 15309 }, { "epoch": 0.467623701893708, "grad_norm": 0.3860595226287842, "learning_rate": 2.7538446275762743e-05, "loss": 4.3266, "step": 15310 }, { "epoch": 0.46765424557116675, "grad_norm": 0.38875430822372437, "learning_rate": 2.7536059767526234e-05, "loss": 4.181, "step": 15311 }, { "epoch": 0.46768478924862555, "grad_norm": 0.39122065901756287, "learning_rate": 2.7533673235938916e-05, "loss": 4.2364, "step": 15312 }, { "epoch": 0.4677153329260843, "grad_norm": 0.40525293350219727, "learning_rate": 2.7531286681022774e-05, "loss": 4.1824, "step": 15313 }, { "epoch": 0.46774587660354305, "grad_norm": 0.38863489031791687, "learning_rate": 2.752890010279977e-05, "loss": 4.2875, "step": 15314 }, { "epoch": 0.46777642028100186, "grad_norm": 0.37698832154273987, "learning_rate": 2.752651350129188e-05, "loss": 4.3125, "step": 15315 }, { "epoch": 0.4678069639584606, "grad_norm": 0.3927778899669647, "learning_rate": 2.7524126876521082e-05, "loss": 4.3254, "step": 15316 }, { "epoch": 0.46783750763591936, "grad_norm": 0.37232550978660583, "learning_rate": 2.752174022850935e-05, "loss": 4.2451, "step": 15317 }, { "epoch": 0.4678680513133781, "grad_norm": 0.3786885738372803, "learning_rate": 2.7519353557278664e-05, "loss": 4.3686, "step": 15318 }, { "epoch": 0.4678985949908369, "grad_norm": 0.3882094919681549, "learning_rate": 2.7516966862850994e-05, "loss": 4.2305, "step": 15319 }, { "epoch": 0.46792913866829566, "grad_norm": 0.38258641958236694, "learning_rate": 2.7514580145248313e-05, "loss": 4.284, "step": 15320 }, { "epoch": 0.4679596823457544, "grad_norm": 0.384644091129303, "learning_rate": 2.7512193404492603e-05, "loss": 4.3594, "step": 15321 }, { "epoch": 0.4679902260232132, "grad_norm": 0.3914014399051666, "learning_rate": 2.750980664060583e-05, "loss": 4.2649, "step": 15322 }, { "epoch": 0.46802076970067197, "grad_norm": 0.41333863139152527, "learning_rate": 2.7507419853609977e-05, "loss": 4.3518, "step": 15323 }, { "epoch": 0.4680513133781307, "grad_norm": 0.39572498202323914, "learning_rate": 2.750503304352703e-05, "loss": 4.3103, "step": 15324 }, { "epoch": 0.46808185705558947, "grad_norm": 0.3850650191307068, "learning_rate": 2.7502646210378948e-05, "loss": 4.2856, "step": 15325 }, { "epoch": 0.4681124007330483, "grad_norm": 0.39330023527145386, "learning_rate": 2.7500259354187717e-05, "loss": 4.3797, "step": 15326 }, { "epoch": 0.468142944410507, "grad_norm": 0.4005063772201538, "learning_rate": 2.7497872474975317e-05, "loss": 4.2811, "step": 15327 }, { "epoch": 0.4681734880879658, "grad_norm": 0.38312461972236633, "learning_rate": 2.749548557276372e-05, "loss": 4.3325, "step": 15328 }, { "epoch": 0.4682040317654246, "grad_norm": 0.38913780450820923, "learning_rate": 2.7493098647574893e-05, "loss": 4.2221, "step": 15329 }, { "epoch": 0.4682345754428833, "grad_norm": 0.3832651376724243, "learning_rate": 2.7490711699430833e-05, "loss": 4.2976, "step": 15330 }, { "epoch": 0.4682651191203421, "grad_norm": 0.38336485624313354, "learning_rate": 2.748832472835351e-05, "loss": 4.3315, "step": 15331 }, { "epoch": 0.4682956627978009, "grad_norm": 0.3946143090724945, "learning_rate": 2.74859377343649e-05, "loss": 4.2653, "step": 15332 }, { "epoch": 0.46832620647525963, "grad_norm": 0.3882099390029907, "learning_rate": 2.748355071748699e-05, "loss": 4.4102, "step": 15333 }, { "epoch": 0.4683567501527184, "grad_norm": 0.374711811542511, "learning_rate": 2.7481163677741743e-05, "loss": 4.2505, "step": 15334 }, { "epoch": 0.46838729383017713, "grad_norm": 0.3866264820098877, "learning_rate": 2.7478776615151152e-05, "loss": 4.2297, "step": 15335 }, { "epoch": 0.46841783750763594, "grad_norm": 0.3864223062992096, "learning_rate": 2.7476389529737183e-05, "loss": 4.314, "step": 15336 }, { "epoch": 0.4684483811850947, "grad_norm": 0.39791300892829895, "learning_rate": 2.7474002421521833e-05, "loss": 4.2788, "step": 15337 }, { "epoch": 0.46847892486255344, "grad_norm": 0.38557565212249756, "learning_rate": 2.7471615290527064e-05, "loss": 4.4094, "step": 15338 }, { "epoch": 0.46850946854001224, "grad_norm": 0.3893681764602661, "learning_rate": 2.746922813677486e-05, "loss": 4.3269, "step": 15339 }, { "epoch": 0.468540012217471, "grad_norm": 0.38133299350738525, "learning_rate": 2.7466840960287204e-05, "loss": 4.3034, "step": 15340 }, { "epoch": 0.46857055589492974, "grad_norm": 0.3720304071903229, "learning_rate": 2.746445376108608e-05, "loss": 4.3134, "step": 15341 }, { "epoch": 0.4686010995723885, "grad_norm": 0.38491445779800415, "learning_rate": 2.7462066539193466e-05, "loss": 4.3287, "step": 15342 }, { "epoch": 0.4686316432498473, "grad_norm": 0.3918474018573761, "learning_rate": 2.745967929463133e-05, "loss": 4.2435, "step": 15343 }, { "epoch": 0.46866218692730605, "grad_norm": 0.38436001539230347, "learning_rate": 2.7457292027421665e-05, "loss": 4.2601, "step": 15344 }, { "epoch": 0.4686927306047648, "grad_norm": 0.39352354407310486, "learning_rate": 2.7454904737586453e-05, "loss": 4.3291, "step": 15345 }, { "epoch": 0.4687232742822236, "grad_norm": 0.3882274925708771, "learning_rate": 2.745251742514766e-05, "loss": 4.2751, "step": 15346 }, { "epoch": 0.46875381795968235, "grad_norm": 0.3787047863006592, "learning_rate": 2.745013009012729e-05, "loss": 4.2775, "step": 15347 }, { "epoch": 0.4687843616371411, "grad_norm": 0.38300278782844543, "learning_rate": 2.744774273254731e-05, "loss": 4.2934, "step": 15348 }, { "epoch": 0.46881490531459985, "grad_norm": 0.3977711796760559, "learning_rate": 2.74453553524297e-05, "loss": 4.3559, "step": 15349 }, { "epoch": 0.46884544899205866, "grad_norm": 0.39894500374794006, "learning_rate": 2.744296794979645e-05, "loss": 4.3971, "step": 15350 }, { "epoch": 0.4688759926695174, "grad_norm": 0.38187602162361145, "learning_rate": 2.744058052466954e-05, "loss": 4.2711, "step": 15351 }, { "epoch": 0.46890653634697615, "grad_norm": 0.3740142285823822, "learning_rate": 2.7438193077070944e-05, "loss": 4.2538, "step": 15352 }, { "epoch": 0.46893708002443496, "grad_norm": 0.3874094784259796, "learning_rate": 2.743580560702265e-05, "loss": 4.3043, "step": 15353 }, { "epoch": 0.4689676237018937, "grad_norm": 0.3828514516353607, "learning_rate": 2.743341811454665e-05, "loss": 4.227, "step": 15354 }, { "epoch": 0.46899816737935246, "grad_norm": 0.40221092104911804, "learning_rate": 2.7431030599664914e-05, "loss": 4.26, "step": 15355 }, { "epoch": 0.46902871105681126, "grad_norm": 0.38144323229789734, "learning_rate": 2.7428643062399428e-05, "loss": 4.3259, "step": 15356 }, { "epoch": 0.46905925473427, "grad_norm": 0.400060772895813, "learning_rate": 2.742625550277218e-05, "loss": 4.3883, "step": 15357 }, { "epoch": 0.46908979841172876, "grad_norm": 0.39572975039482117, "learning_rate": 2.7423867920805146e-05, "loss": 4.3434, "step": 15358 }, { "epoch": 0.4691203420891875, "grad_norm": 0.37737736105918884, "learning_rate": 2.7421480316520316e-05, "loss": 4.2939, "step": 15359 }, { "epoch": 0.4691508857666463, "grad_norm": 0.39175179600715637, "learning_rate": 2.7419092689939667e-05, "loss": 4.3392, "step": 15360 }, { "epoch": 0.46918142944410507, "grad_norm": 0.40386512875556946, "learning_rate": 2.7416705041085196e-05, "loss": 4.2833, "step": 15361 }, { "epoch": 0.4692119731215638, "grad_norm": 0.39096081256866455, "learning_rate": 2.741431736997887e-05, "loss": 4.241, "step": 15362 }, { "epoch": 0.4692425167990226, "grad_norm": 0.4014291763305664, "learning_rate": 2.7411929676642685e-05, "loss": 4.2824, "step": 15363 }, { "epoch": 0.4692730604764814, "grad_norm": 0.38239842653274536, "learning_rate": 2.7409541961098627e-05, "loss": 4.2449, "step": 15364 }, { "epoch": 0.4693036041539401, "grad_norm": 0.39266589283943176, "learning_rate": 2.740715422336868e-05, "loss": 4.3413, "step": 15365 }, { "epoch": 0.4693341478313989, "grad_norm": 0.405536413192749, "learning_rate": 2.740476646347483e-05, "loss": 4.2372, "step": 15366 }, { "epoch": 0.4693646915088577, "grad_norm": 0.414205402135849, "learning_rate": 2.7402378681439046e-05, "loss": 4.3114, "step": 15367 }, { "epoch": 0.46939523518631643, "grad_norm": 0.4001108705997467, "learning_rate": 2.739999087728333e-05, "loss": 4.2741, "step": 15368 }, { "epoch": 0.4694257788637752, "grad_norm": 0.3970058858394623, "learning_rate": 2.7397603051029668e-05, "loss": 4.214, "step": 15369 }, { "epoch": 0.469456322541234, "grad_norm": 0.3917933404445648, "learning_rate": 2.7395215202700035e-05, "loss": 4.359, "step": 15370 }, { "epoch": 0.46948686621869273, "grad_norm": 0.3822968900203705, "learning_rate": 2.739282733231643e-05, "loss": 4.3214, "step": 15371 }, { "epoch": 0.4695174098961515, "grad_norm": 0.39262574911117554, "learning_rate": 2.7390439439900833e-05, "loss": 4.2893, "step": 15372 }, { "epoch": 0.4695479535736103, "grad_norm": 0.3926610052585602, "learning_rate": 2.7388051525475234e-05, "loss": 4.2337, "step": 15373 }, { "epoch": 0.46957849725106904, "grad_norm": 0.3902330994606018, "learning_rate": 2.7385663589061613e-05, "loss": 4.4086, "step": 15374 }, { "epoch": 0.4696090409285278, "grad_norm": 0.37871524691581726, "learning_rate": 2.738327563068196e-05, "loss": 4.2772, "step": 15375 }, { "epoch": 0.46963958460598654, "grad_norm": 0.39489027857780457, "learning_rate": 2.738088765035827e-05, "loss": 4.2733, "step": 15376 }, { "epoch": 0.46967012828344534, "grad_norm": 0.3741994798183441, "learning_rate": 2.7378499648112504e-05, "loss": 4.3307, "step": 15377 }, { "epoch": 0.4697006719609041, "grad_norm": 0.3865486681461334, "learning_rate": 2.737611162396669e-05, "loss": 4.2788, "step": 15378 }, { "epoch": 0.46973121563836284, "grad_norm": 0.3897157311439514, "learning_rate": 2.7373723577942782e-05, "loss": 4.3647, "step": 15379 }, { "epoch": 0.46976175931582165, "grad_norm": 0.3881392776966095, "learning_rate": 2.737133551006279e-05, "loss": 4.3195, "step": 15380 }, { "epoch": 0.4697923029932804, "grad_norm": 0.4047125279903412, "learning_rate": 2.7368947420348686e-05, "loss": 4.3006, "step": 15381 }, { "epoch": 0.46982284667073915, "grad_norm": 0.39055290818214417, "learning_rate": 2.736655930882247e-05, "loss": 4.2957, "step": 15382 }, { "epoch": 0.4698533903481979, "grad_norm": 0.39133310317993164, "learning_rate": 2.736417117550612e-05, "loss": 4.3287, "step": 15383 }, { "epoch": 0.4698839340256567, "grad_norm": 0.3813512623310089, "learning_rate": 2.736178302042163e-05, "loss": 4.2687, "step": 15384 }, { "epoch": 0.46991447770311545, "grad_norm": 0.37701210379600525, "learning_rate": 2.735939484359099e-05, "loss": 4.2977, "step": 15385 }, { "epoch": 0.4699450213805742, "grad_norm": 0.3940443992614746, "learning_rate": 2.7357006645036198e-05, "loss": 4.3063, "step": 15386 }, { "epoch": 0.469975565058033, "grad_norm": 0.3889250159263611, "learning_rate": 2.735461842477922e-05, "loss": 4.22, "step": 15387 }, { "epoch": 0.47000610873549176, "grad_norm": 0.3978298306465149, "learning_rate": 2.7352230182842074e-05, "loss": 4.3502, "step": 15388 }, { "epoch": 0.4700366524129505, "grad_norm": 0.3867162764072418, "learning_rate": 2.7349841919246727e-05, "loss": 4.3149, "step": 15389 }, { "epoch": 0.4700671960904093, "grad_norm": 0.3831612169742584, "learning_rate": 2.7347453634015176e-05, "loss": 4.3049, "step": 15390 }, { "epoch": 0.47009773976786806, "grad_norm": 0.38356074690818787, "learning_rate": 2.7345065327169418e-05, "loss": 4.3123, "step": 15391 }, { "epoch": 0.4701282834453268, "grad_norm": 0.38731706142425537, "learning_rate": 2.734267699873143e-05, "loss": 4.2601, "step": 15392 }, { "epoch": 0.47015882712278556, "grad_norm": 0.3913838863372803, "learning_rate": 2.7340288648723215e-05, "loss": 4.3926, "step": 15393 }, { "epoch": 0.47018937080024437, "grad_norm": 0.40331313014030457, "learning_rate": 2.7337900277166756e-05, "loss": 4.3368, "step": 15394 }, { "epoch": 0.4702199144777031, "grad_norm": 0.3858858644962311, "learning_rate": 2.733551188408405e-05, "loss": 4.3558, "step": 15395 }, { "epoch": 0.47025045815516187, "grad_norm": 0.3853982388973236, "learning_rate": 2.7333123469497092e-05, "loss": 4.3151, "step": 15396 }, { "epoch": 0.47028100183262067, "grad_norm": 0.382623553276062, "learning_rate": 2.7330735033427855e-05, "loss": 4.2792, "step": 15397 }, { "epoch": 0.4703115455100794, "grad_norm": 0.4090956151485443, "learning_rate": 2.732834657589835e-05, "loss": 4.2546, "step": 15398 }, { "epoch": 0.47034208918753817, "grad_norm": 0.39056840538978577, "learning_rate": 2.7325958096930558e-05, "loss": 4.3734, "step": 15399 }, { "epoch": 0.4703726328649969, "grad_norm": 0.3955168128013611, "learning_rate": 2.732356959654648e-05, "loss": 4.2696, "step": 15400 }, { "epoch": 0.4704031765424557, "grad_norm": 0.3977935016155243, "learning_rate": 2.7321181074768086e-05, "loss": 4.2301, "step": 15401 }, { "epoch": 0.4704337202199145, "grad_norm": 0.4023224115371704, "learning_rate": 2.7318792531617398e-05, "loss": 4.2678, "step": 15402 }, { "epoch": 0.4704642638973732, "grad_norm": 0.38832393288612366, "learning_rate": 2.7316403967116395e-05, "loss": 4.2935, "step": 15403 }, { "epoch": 0.47049480757483203, "grad_norm": 0.3962940275669098, "learning_rate": 2.7314015381287067e-05, "loss": 4.3374, "step": 15404 }, { "epoch": 0.4705253512522908, "grad_norm": 0.38713890314102173, "learning_rate": 2.7311626774151406e-05, "loss": 4.347, "step": 15405 }, { "epoch": 0.47055589492974953, "grad_norm": 0.38335278630256653, "learning_rate": 2.7309238145731415e-05, "loss": 4.3319, "step": 15406 }, { "epoch": 0.47058643860720833, "grad_norm": 0.40126386284828186, "learning_rate": 2.7306849496049075e-05, "loss": 4.3246, "step": 15407 }, { "epoch": 0.4706169822846671, "grad_norm": 0.43414413928985596, "learning_rate": 2.7304460825126388e-05, "loss": 4.2623, "step": 15408 }, { "epoch": 0.47064752596212583, "grad_norm": 0.39660972356796265, "learning_rate": 2.7302072132985346e-05, "loss": 4.3556, "step": 15409 }, { "epoch": 0.4706780696395846, "grad_norm": 0.37915146350860596, "learning_rate": 2.729968341964794e-05, "loss": 4.2845, "step": 15410 }, { "epoch": 0.4707086133170434, "grad_norm": 0.38307899236679077, "learning_rate": 2.729729468513617e-05, "loss": 4.37, "step": 15411 }, { "epoch": 0.47073915699450214, "grad_norm": 0.38449355959892273, "learning_rate": 2.7294905929472027e-05, "loss": 4.3457, "step": 15412 }, { "epoch": 0.4707697006719609, "grad_norm": 0.37424835562705994, "learning_rate": 2.7292517152677506e-05, "loss": 4.2526, "step": 15413 }, { "epoch": 0.4708002443494197, "grad_norm": 0.38389289379119873, "learning_rate": 2.729012835477459e-05, "loss": 4.3112, "step": 15414 }, { "epoch": 0.47083078802687844, "grad_norm": 0.377576619386673, "learning_rate": 2.7287739535785297e-05, "loss": 4.3489, "step": 15415 }, { "epoch": 0.4708613317043372, "grad_norm": 0.40363165736198425, "learning_rate": 2.7285350695731604e-05, "loss": 4.3339, "step": 15416 }, { "epoch": 0.47089187538179594, "grad_norm": 0.38977739214897156, "learning_rate": 2.728296183463552e-05, "loss": 4.229, "step": 15417 }, { "epoch": 0.47092241905925475, "grad_norm": 0.39613500237464905, "learning_rate": 2.7280572952519016e-05, "loss": 4.2878, "step": 15418 }, { "epoch": 0.4709529627367135, "grad_norm": 0.3874720633029938, "learning_rate": 2.727818404940412e-05, "loss": 4.2815, "step": 15419 }, { "epoch": 0.47098350641417225, "grad_norm": 0.38838130235671997, "learning_rate": 2.7275795125312812e-05, "loss": 4.289, "step": 15420 }, { "epoch": 0.47101405009163105, "grad_norm": 0.4064881205558777, "learning_rate": 2.7273406180267082e-05, "loss": 4.3939, "step": 15421 }, { "epoch": 0.4710445937690898, "grad_norm": 0.37734413146972656, "learning_rate": 2.727101721428893e-05, "loss": 4.2597, "step": 15422 }, { "epoch": 0.47107513744654855, "grad_norm": 0.3838198184967041, "learning_rate": 2.7268628227400362e-05, "loss": 4.2638, "step": 15423 }, { "epoch": 0.4711056811240073, "grad_norm": 0.3931935727596283, "learning_rate": 2.7266239219623365e-05, "loss": 4.4251, "step": 15424 }, { "epoch": 0.4711362248014661, "grad_norm": 0.40471556782722473, "learning_rate": 2.7263850190979934e-05, "loss": 4.2544, "step": 15425 }, { "epoch": 0.47116676847892486, "grad_norm": 0.385456919670105, "learning_rate": 2.7261461141492073e-05, "loss": 4.3771, "step": 15426 }, { "epoch": 0.4711973121563836, "grad_norm": 0.3769247233867645, "learning_rate": 2.725907207118178e-05, "loss": 4.3821, "step": 15427 }, { "epoch": 0.4712278558338424, "grad_norm": 0.3987937867641449, "learning_rate": 2.7256682980071042e-05, "loss": 4.3041, "step": 15428 }, { "epoch": 0.47125839951130116, "grad_norm": 0.3956918716430664, "learning_rate": 2.7254293868181868e-05, "loss": 4.3235, "step": 15429 }, { "epoch": 0.4712889431887599, "grad_norm": 0.3868308961391449, "learning_rate": 2.7251904735536256e-05, "loss": 4.2376, "step": 15430 }, { "epoch": 0.4713194868662187, "grad_norm": 0.4018137454986572, "learning_rate": 2.724951558215619e-05, "loss": 4.3041, "step": 15431 }, { "epoch": 0.47135003054367747, "grad_norm": 0.3851713240146637, "learning_rate": 2.724712640806368e-05, "loss": 4.3123, "step": 15432 }, { "epoch": 0.4713805742211362, "grad_norm": 0.38530775904655457, "learning_rate": 2.7244737213280726e-05, "loss": 4.2483, "step": 15433 }, { "epoch": 0.47141111789859497, "grad_norm": 0.38874292373657227, "learning_rate": 2.7242347997829322e-05, "loss": 4.2171, "step": 15434 }, { "epoch": 0.47144166157605377, "grad_norm": 0.400020569562912, "learning_rate": 2.723995876173146e-05, "loss": 4.2145, "step": 15435 }, { "epoch": 0.4714722052535125, "grad_norm": 0.3844239413738251, "learning_rate": 2.7237569505009154e-05, "loss": 4.3178, "step": 15436 }, { "epoch": 0.47150274893097127, "grad_norm": 0.37693920731544495, "learning_rate": 2.7235180227684393e-05, "loss": 4.3364, "step": 15437 }, { "epoch": 0.4715332926084301, "grad_norm": 0.3889898657798767, "learning_rate": 2.7232790929779173e-05, "loss": 4.3294, "step": 15438 }, { "epoch": 0.4715638362858888, "grad_norm": 0.37848296761512756, "learning_rate": 2.7230401611315505e-05, "loss": 4.2683, "step": 15439 }, { "epoch": 0.4715943799633476, "grad_norm": 0.38336989283561707, "learning_rate": 2.7228012272315377e-05, "loss": 4.3455, "step": 15440 }, { "epoch": 0.4716249236408063, "grad_norm": 0.38989248871803284, "learning_rate": 2.7225622912800803e-05, "loss": 4.1935, "step": 15441 }, { "epoch": 0.47165546731826513, "grad_norm": 0.3872600793838501, "learning_rate": 2.7223233532793767e-05, "loss": 4.3061, "step": 15442 }, { "epoch": 0.4716860109957239, "grad_norm": 0.3818664848804474, "learning_rate": 2.7220844132316286e-05, "loss": 4.2609, "step": 15443 }, { "epoch": 0.47171655467318263, "grad_norm": 0.3939589560031891, "learning_rate": 2.7218454711390346e-05, "loss": 4.335, "step": 15444 }, { "epoch": 0.47174709835064144, "grad_norm": 0.3813198208808899, "learning_rate": 2.7216065270037945e-05, "loss": 4.2293, "step": 15445 }, { "epoch": 0.4717776420281002, "grad_norm": 0.38916563987731934, "learning_rate": 2.7213675808281103e-05, "loss": 4.3523, "step": 15446 }, { "epoch": 0.47180818570555894, "grad_norm": 0.3882119655609131, "learning_rate": 2.7211286326141806e-05, "loss": 4.2772, "step": 15447 }, { "epoch": 0.47183872938301774, "grad_norm": 0.38596317172050476, "learning_rate": 2.720889682364205e-05, "loss": 4.2909, "step": 15448 }, { "epoch": 0.4718692730604765, "grad_norm": 0.3885057270526886, "learning_rate": 2.7206507300803856e-05, "loss": 4.3643, "step": 15449 }, { "epoch": 0.47189981673793524, "grad_norm": 0.391389936208725, "learning_rate": 2.7204117757649212e-05, "loss": 4.2754, "step": 15450 }, { "epoch": 0.471930360415394, "grad_norm": 0.37326908111572266, "learning_rate": 2.7201728194200122e-05, "loss": 4.2937, "step": 15451 }, { "epoch": 0.4719609040928528, "grad_norm": 0.38994038105010986, "learning_rate": 2.7199338610478593e-05, "loss": 4.2858, "step": 15452 }, { "epoch": 0.47199144777031155, "grad_norm": 0.3895456790924072, "learning_rate": 2.7196949006506617e-05, "loss": 4.3874, "step": 15453 }, { "epoch": 0.4720219914477703, "grad_norm": 0.38815838098526, "learning_rate": 2.7194559382306207e-05, "loss": 4.2648, "step": 15454 }, { "epoch": 0.4720525351252291, "grad_norm": 0.39044395089149475, "learning_rate": 2.7192169737899354e-05, "loss": 4.3549, "step": 15455 }, { "epoch": 0.47208307880268785, "grad_norm": 0.389947772026062, "learning_rate": 2.718978007330807e-05, "loss": 4.2011, "step": 15456 }, { "epoch": 0.4721136224801466, "grad_norm": 0.3841250538825989, "learning_rate": 2.7187390388554358e-05, "loss": 4.3675, "step": 15457 }, { "epoch": 0.47214416615760535, "grad_norm": 0.41025352478027344, "learning_rate": 2.7185000683660212e-05, "loss": 4.2443, "step": 15458 }, { "epoch": 0.47217470983506415, "grad_norm": 0.3787362277507782, "learning_rate": 2.7182610958647648e-05, "loss": 4.3043, "step": 15459 }, { "epoch": 0.4722052535125229, "grad_norm": 0.3913891017436981, "learning_rate": 2.7180221213538658e-05, "loss": 4.3232, "step": 15460 }, { "epoch": 0.47223579718998165, "grad_norm": 0.3937297463417053, "learning_rate": 2.717783144835525e-05, "loss": 4.3163, "step": 15461 }, { "epoch": 0.47226634086744046, "grad_norm": 0.38396650552749634, "learning_rate": 2.7175441663119427e-05, "loss": 4.3143, "step": 15462 }, { "epoch": 0.4722968845448992, "grad_norm": 0.4061334431171417, "learning_rate": 2.71730518578532e-05, "loss": 4.2643, "step": 15463 }, { "epoch": 0.47232742822235796, "grad_norm": 0.3868253827095032, "learning_rate": 2.7170662032578564e-05, "loss": 4.3494, "step": 15464 }, { "epoch": 0.47235797189981676, "grad_norm": 0.38692042231559753, "learning_rate": 2.7168272187317523e-05, "loss": 4.2018, "step": 15465 }, { "epoch": 0.4723885155772755, "grad_norm": 0.3939061462879181, "learning_rate": 2.7165882322092096e-05, "loss": 4.2292, "step": 15466 }, { "epoch": 0.47241905925473426, "grad_norm": 0.3908020257949829, "learning_rate": 2.716349243692427e-05, "loss": 4.2941, "step": 15467 }, { "epoch": 0.472449602932193, "grad_norm": 0.3849680721759796, "learning_rate": 2.716110253183606e-05, "loss": 4.3144, "step": 15468 }, { "epoch": 0.4724801466096518, "grad_norm": 0.3960183262825012, "learning_rate": 2.7158712606849458e-05, "loss": 4.2362, "step": 15469 }, { "epoch": 0.47251069028711057, "grad_norm": 0.3925436735153198, "learning_rate": 2.7156322661986487e-05, "loss": 4.3228, "step": 15470 }, { "epoch": 0.4725412339645693, "grad_norm": 0.3775775730609894, "learning_rate": 2.7153932697269142e-05, "loss": 4.2955, "step": 15471 }, { "epoch": 0.4725717776420281, "grad_norm": 0.3888151943683624, "learning_rate": 2.715154271271943e-05, "loss": 4.3204, "step": 15472 }, { "epoch": 0.4726023213194869, "grad_norm": 0.38359779119491577, "learning_rate": 2.714915270835936e-05, "loss": 4.2483, "step": 15473 }, { "epoch": 0.4726328649969456, "grad_norm": 0.3913812041282654, "learning_rate": 2.7146762684210936e-05, "loss": 4.378, "step": 15474 }, { "epoch": 0.4726634086744044, "grad_norm": 0.39925792813301086, "learning_rate": 2.7144372640296173e-05, "loss": 4.2569, "step": 15475 }, { "epoch": 0.4726939523518632, "grad_norm": 0.38618943095207214, "learning_rate": 2.7141982576637055e-05, "loss": 4.321, "step": 15476 }, { "epoch": 0.47272449602932193, "grad_norm": 0.3825010359287262, "learning_rate": 2.7139592493255605e-05, "loss": 4.2904, "step": 15477 }, { "epoch": 0.4727550397067807, "grad_norm": 0.38672935962677, "learning_rate": 2.7137202390173832e-05, "loss": 4.287, "step": 15478 }, { "epoch": 0.4727855833842395, "grad_norm": 0.38616102933883667, "learning_rate": 2.7134812267413735e-05, "loss": 4.3321, "step": 15479 }, { "epoch": 0.47281612706169823, "grad_norm": 0.3877542018890381, "learning_rate": 2.713242212499732e-05, "loss": 4.3165, "step": 15480 }, { "epoch": 0.472846670739157, "grad_norm": 0.4040052890777588, "learning_rate": 2.7130031962946605e-05, "loss": 4.3326, "step": 15481 }, { "epoch": 0.4728772144166158, "grad_norm": 0.3914877772331238, "learning_rate": 2.7127641781283587e-05, "loss": 4.3082, "step": 15482 }, { "epoch": 0.47290775809407454, "grad_norm": 0.38072720170021057, "learning_rate": 2.712525158003028e-05, "loss": 4.2589, "step": 15483 }, { "epoch": 0.4729383017715333, "grad_norm": 0.38071897625923157, "learning_rate": 2.7122861359208683e-05, "loss": 4.3254, "step": 15484 }, { "epoch": 0.47296884544899204, "grad_norm": 0.4004189074039459, "learning_rate": 2.712047111884082e-05, "loss": 4.3724, "step": 15485 }, { "epoch": 0.47299938912645084, "grad_norm": 0.3788623809814453, "learning_rate": 2.7118080858948674e-05, "loss": 4.2204, "step": 15486 }, { "epoch": 0.4730299328039096, "grad_norm": 0.38802623748779297, "learning_rate": 2.7115690579554282e-05, "loss": 4.3195, "step": 15487 }, { "epoch": 0.47306047648136834, "grad_norm": 0.3765488564968109, "learning_rate": 2.711330028067963e-05, "loss": 4.3284, "step": 15488 }, { "epoch": 0.47309102015882715, "grad_norm": 0.38468271493911743, "learning_rate": 2.711090996234674e-05, "loss": 4.2442, "step": 15489 }, { "epoch": 0.4731215638362859, "grad_norm": 0.3832690715789795, "learning_rate": 2.710851962457762e-05, "loss": 4.3214, "step": 15490 }, { "epoch": 0.47315210751374465, "grad_norm": 0.3859536945819855, "learning_rate": 2.7106129267394275e-05, "loss": 4.2993, "step": 15491 }, { "epoch": 0.4731826511912034, "grad_norm": 0.38516247272491455, "learning_rate": 2.7103738890818713e-05, "loss": 4.2491, "step": 15492 }, { "epoch": 0.4732131948686622, "grad_norm": 0.38951095938682556, "learning_rate": 2.710134849487294e-05, "loss": 4.1244, "step": 15493 }, { "epoch": 0.47324373854612095, "grad_norm": 0.3819129765033722, "learning_rate": 2.709895807957898e-05, "loss": 4.3265, "step": 15494 }, { "epoch": 0.4732742822235797, "grad_norm": 0.3816624581813812, "learning_rate": 2.7096567644958832e-05, "loss": 4.3313, "step": 15495 }, { "epoch": 0.4733048259010385, "grad_norm": 0.38996967673301697, "learning_rate": 2.7094177191034498e-05, "loss": 4.2983, "step": 15496 }, { "epoch": 0.47333536957849726, "grad_norm": 0.3864108622074127, "learning_rate": 2.7091786717828004e-05, "loss": 4.3387, "step": 15497 }, { "epoch": 0.473365913255956, "grad_norm": 0.38772279024124146, "learning_rate": 2.7089396225361363e-05, "loss": 4.339, "step": 15498 }, { "epoch": 0.47339645693341476, "grad_norm": 0.38965079188346863, "learning_rate": 2.708700571365657e-05, "loss": 4.2955, "step": 15499 }, { "epoch": 0.47342700061087356, "grad_norm": 0.39335235953330994, "learning_rate": 2.708461518273564e-05, "loss": 4.1261, "step": 15500 }, { "epoch": 0.4734575442883323, "grad_norm": 0.397013396024704, "learning_rate": 2.7082224632620586e-05, "loss": 4.3389, "step": 15501 }, { "epoch": 0.47348808796579106, "grad_norm": 0.3789501488208771, "learning_rate": 2.707983406333342e-05, "loss": 4.2483, "step": 15502 }, { "epoch": 0.47351863164324987, "grad_norm": 0.39196982979774475, "learning_rate": 2.7077443474896154e-05, "loss": 4.2656, "step": 15503 }, { "epoch": 0.4735491753207086, "grad_norm": 0.38279038667678833, "learning_rate": 2.7075052867330797e-05, "loss": 4.3349, "step": 15504 }, { "epoch": 0.47357971899816736, "grad_norm": 0.39147835969924927, "learning_rate": 2.7072662240659362e-05, "loss": 4.2708, "step": 15505 }, { "epoch": 0.47361026267562617, "grad_norm": 0.38991910219192505, "learning_rate": 2.707027159490386e-05, "loss": 4.2521, "step": 15506 }, { "epoch": 0.4736408063530849, "grad_norm": 0.39505884051322937, "learning_rate": 2.7067880930086304e-05, "loss": 4.2681, "step": 15507 }, { "epoch": 0.47367135003054367, "grad_norm": 0.4030229151248932, "learning_rate": 2.7065490246228703e-05, "loss": 4.2801, "step": 15508 }, { "epoch": 0.4737018937080024, "grad_norm": 0.39282798767089844, "learning_rate": 2.7063099543353078e-05, "loss": 4.3238, "step": 15509 }, { "epoch": 0.4737324373854612, "grad_norm": 0.37937164306640625, "learning_rate": 2.7060708821481418e-05, "loss": 4.3375, "step": 15510 }, { "epoch": 0.47376298106292, "grad_norm": 0.39694783091545105, "learning_rate": 2.7058318080635765e-05, "loss": 4.2972, "step": 15511 }, { "epoch": 0.4737935247403787, "grad_norm": 0.38958609104156494, "learning_rate": 2.705592732083812e-05, "loss": 4.2947, "step": 15512 }, { "epoch": 0.47382406841783753, "grad_norm": 0.4013870656490326, "learning_rate": 2.705353654211049e-05, "loss": 4.371, "step": 15513 }, { "epoch": 0.4738546120952963, "grad_norm": 0.39199939370155334, "learning_rate": 2.70511457444749e-05, "loss": 4.2859, "step": 15514 }, { "epoch": 0.47388515577275503, "grad_norm": 0.38155853748321533, "learning_rate": 2.704875492795335e-05, "loss": 4.3386, "step": 15515 }, { "epoch": 0.4739156994502138, "grad_norm": 0.3912283480167389, "learning_rate": 2.7046364092567868e-05, "loss": 4.2905, "step": 15516 }, { "epoch": 0.4739462431276726, "grad_norm": 0.3949959874153137, "learning_rate": 2.7043973238340448e-05, "loss": 4.359, "step": 15517 }, { "epoch": 0.47397678680513133, "grad_norm": 0.3917850852012634, "learning_rate": 2.7041582365293122e-05, "loss": 4.2765, "step": 15518 }, { "epoch": 0.4740073304825901, "grad_norm": 0.397634357213974, "learning_rate": 2.70391914734479e-05, "loss": 4.2768, "step": 15519 }, { "epoch": 0.4740378741600489, "grad_norm": 0.3800916373729706, "learning_rate": 2.7036800562826785e-05, "loss": 4.3299, "step": 15520 }, { "epoch": 0.47406841783750764, "grad_norm": 0.40178319811820984, "learning_rate": 2.7034409633451812e-05, "loss": 4.3172, "step": 15521 }, { "epoch": 0.4740989615149664, "grad_norm": 0.38920858502388, "learning_rate": 2.703201868534498e-05, "loss": 4.3378, "step": 15522 }, { "epoch": 0.4741295051924252, "grad_norm": 0.3941243886947632, "learning_rate": 2.7029627718528295e-05, "loss": 4.262, "step": 15523 }, { "epoch": 0.47416004886988394, "grad_norm": 0.3942502737045288, "learning_rate": 2.7027236733023796e-05, "loss": 4.3092, "step": 15524 }, { "epoch": 0.4741905925473427, "grad_norm": 0.37925899028778076, "learning_rate": 2.7024845728853483e-05, "loss": 4.3062, "step": 15525 }, { "epoch": 0.47422113622480144, "grad_norm": 0.3815804719924927, "learning_rate": 2.702245470603938e-05, "loss": 4.3469, "step": 15526 }, { "epoch": 0.47425167990226025, "grad_norm": 0.38606345653533936, "learning_rate": 2.7020063664603485e-05, "loss": 4.3272, "step": 15527 }, { "epoch": 0.474282223579719, "grad_norm": 0.39443257451057434, "learning_rate": 2.701767260456783e-05, "loss": 4.3275, "step": 15528 }, { "epoch": 0.47431276725717775, "grad_norm": 0.3759077787399292, "learning_rate": 2.701528152595443e-05, "loss": 4.2997, "step": 15529 }, { "epoch": 0.47434331093463655, "grad_norm": 0.397128701210022, "learning_rate": 2.7012890428785292e-05, "loss": 4.2608, "step": 15530 }, { "epoch": 0.4743738546120953, "grad_norm": 0.39490073919296265, "learning_rate": 2.7010499313082445e-05, "loss": 4.2741, "step": 15531 }, { "epoch": 0.47440439828955405, "grad_norm": 0.37940308451652527, "learning_rate": 2.700810817886789e-05, "loss": 4.2776, "step": 15532 }, { "epoch": 0.4744349419670128, "grad_norm": 0.4001573622226715, "learning_rate": 2.7005717026163653e-05, "loss": 4.3393, "step": 15533 }, { "epoch": 0.4744654856444716, "grad_norm": 0.3878155052661896, "learning_rate": 2.7003325854991745e-05, "loss": 4.3174, "step": 15534 }, { "epoch": 0.47449602932193036, "grad_norm": 0.38326749205589294, "learning_rate": 2.700093466537419e-05, "loss": 4.2838, "step": 15535 }, { "epoch": 0.4745265729993891, "grad_norm": 0.3790401518344879, "learning_rate": 2.6998543457332997e-05, "loss": 4.3688, "step": 15536 }, { "epoch": 0.4745571166768479, "grad_norm": 0.40571606159210205, "learning_rate": 2.6996152230890186e-05, "loss": 4.3329, "step": 15537 }, { "epoch": 0.47458766035430666, "grad_norm": 0.4069914221763611, "learning_rate": 2.6993760986067784e-05, "loss": 4.2726, "step": 15538 }, { "epoch": 0.4746182040317654, "grad_norm": 0.4090891182422638, "learning_rate": 2.6991369722887793e-05, "loss": 4.2101, "step": 15539 }, { "epoch": 0.4746487477092242, "grad_norm": 0.38161906599998474, "learning_rate": 2.698897844137223e-05, "loss": 4.3093, "step": 15540 }, { "epoch": 0.47467929138668297, "grad_norm": 0.3887346386909485, "learning_rate": 2.698658714154313e-05, "loss": 4.2932, "step": 15541 }, { "epoch": 0.4747098350641417, "grad_norm": 0.3871590495109558, "learning_rate": 2.6984195823422498e-05, "loss": 4.3107, "step": 15542 }, { "epoch": 0.47474037874160047, "grad_norm": 0.39954978227615356, "learning_rate": 2.6981804487032358e-05, "loss": 4.237, "step": 15543 }, { "epoch": 0.47477092241905927, "grad_norm": 0.38482069969177246, "learning_rate": 2.697941313239472e-05, "loss": 4.2661, "step": 15544 }, { "epoch": 0.474801466096518, "grad_norm": 0.38768795132637024, "learning_rate": 2.697702175953161e-05, "loss": 4.2979, "step": 15545 }, { "epoch": 0.47483200977397677, "grad_norm": 0.3886266052722931, "learning_rate": 2.6974630368465047e-05, "loss": 4.236, "step": 15546 }, { "epoch": 0.4748625534514356, "grad_norm": 0.3977222740650177, "learning_rate": 2.697223895921704e-05, "loss": 4.3191, "step": 15547 }, { "epoch": 0.4748930971288943, "grad_norm": 0.3827020227909088, "learning_rate": 2.6969847531809618e-05, "loss": 4.3079, "step": 15548 }, { "epoch": 0.4749236408063531, "grad_norm": 0.3848542869091034, "learning_rate": 2.69674560862648e-05, "loss": 4.291, "step": 15549 }, { "epoch": 0.4749541844838118, "grad_norm": 0.3872586488723755, "learning_rate": 2.6965064622604597e-05, "loss": 4.3658, "step": 15550 }, { "epoch": 0.47498472816127063, "grad_norm": 0.38348388671875, "learning_rate": 2.696267314085103e-05, "loss": 4.3156, "step": 15551 }, { "epoch": 0.4750152718387294, "grad_norm": 0.4173945486545563, "learning_rate": 2.696028164102613e-05, "loss": 4.3173, "step": 15552 }, { "epoch": 0.47504581551618813, "grad_norm": 0.3815901279449463, "learning_rate": 2.695789012315192e-05, "loss": 4.2877, "step": 15553 }, { "epoch": 0.47507635919364694, "grad_norm": 0.3815825879573822, "learning_rate": 2.695549858725039e-05, "loss": 4.3452, "step": 15554 }, { "epoch": 0.4751069028711057, "grad_norm": 0.3926045000553131, "learning_rate": 2.6953107033343584e-05, "loss": 4.4127, "step": 15555 }, { "epoch": 0.47513744654856443, "grad_norm": 0.39139899611473083, "learning_rate": 2.6950715461453525e-05, "loss": 4.2874, "step": 15556 }, { "epoch": 0.47516799022602324, "grad_norm": 0.3865451216697693, "learning_rate": 2.694832387160221e-05, "loss": 4.3856, "step": 15557 }, { "epoch": 0.475198533903482, "grad_norm": 0.376904159784317, "learning_rate": 2.6945932263811684e-05, "loss": 4.2963, "step": 15558 }, { "epoch": 0.47522907758094074, "grad_norm": 0.3902612626552582, "learning_rate": 2.6943540638103963e-05, "loss": 4.2812, "step": 15559 }, { "epoch": 0.4752596212583995, "grad_norm": 0.3848382234573364, "learning_rate": 2.6941148994501065e-05, "loss": 4.3379, "step": 15560 }, { "epoch": 0.4752901649358583, "grad_norm": 0.39400410652160645, "learning_rate": 2.6938757333025006e-05, "loss": 4.2606, "step": 15561 }, { "epoch": 0.47532070861331704, "grad_norm": 0.404809832572937, "learning_rate": 2.6936365653697815e-05, "loss": 4.241, "step": 15562 }, { "epoch": 0.4753512522907758, "grad_norm": 0.39928457140922546, "learning_rate": 2.693397395654151e-05, "loss": 4.3201, "step": 15563 }, { "epoch": 0.4753817959682346, "grad_norm": 0.4052833020687103, "learning_rate": 2.6931582241578102e-05, "loss": 4.279, "step": 15564 }, { "epoch": 0.47541233964569335, "grad_norm": 0.39736485481262207, "learning_rate": 2.692919050882963e-05, "loss": 4.3341, "step": 15565 }, { "epoch": 0.4754428833231521, "grad_norm": 0.3940850496292114, "learning_rate": 2.692679875831811e-05, "loss": 4.3625, "step": 15566 }, { "epoch": 0.47547342700061085, "grad_norm": 0.3959352374076843, "learning_rate": 2.6924406990065566e-05, "loss": 4.263, "step": 15567 }, { "epoch": 0.47550397067806965, "grad_norm": 0.40131598711013794, "learning_rate": 2.6922015204094013e-05, "loss": 4.3609, "step": 15568 }, { "epoch": 0.4755345143555284, "grad_norm": 0.3883446753025055, "learning_rate": 2.691962340042548e-05, "loss": 4.3774, "step": 15569 }, { "epoch": 0.47556505803298715, "grad_norm": 0.3832762837409973, "learning_rate": 2.691723157908199e-05, "loss": 4.3313, "step": 15570 }, { "epoch": 0.47559560171044596, "grad_norm": 0.38391923904418945, "learning_rate": 2.6914839740085556e-05, "loss": 4.2778, "step": 15571 }, { "epoch": 0.4756261453879047, "grad_norm": 0.39636826515197754, "learning_rate": 2.6912447883458215e-05, "loss": 4.3426, "step": 15572 }, { "epoch": 0.47565668906536346, "grad_norm": 0.38718652725219727, "learning_rate": 2.6910056009221978e-05, "loss": 4.3224, "step": 15573 }, { "epoch": 0.47568723274282226, "grad_norm": 0.4179268181324005, "learning_rate": 2.6907664117398866e-05, "loss": 4.3613, "step": 15574 }, { "epoch": 0.475717776420281, "grad_norm": 0.39333662390708923, "learning_rate": 2.6905272208010924e-05, "loss": 4.2912, "step": 15575 }, { "epoch": 0.47574832009773976, "grad_norm": 0.42382678389549255, "learning_rate": 2.690288028108016e-05, "loss": 4.1706, "step": 15576 }, { "epoch": 0.4757788637751985, "grad_norm": 0.40099120140075684, "learning_rate": 2.6900488336628598e-05, "loss": 4.2139, "step": 15577 }, { "epoch": 0.4758094074526573, "grad_norm": 0.39247044920921326, "learning_rate": 2.689809637467825e-05, "loss": 4.3154, "step": 15578 }, { "epoch": 0.47583995113011607, "grad_norm": 0.382975310087204, "learning_rate": 2.6895704395251165e-05, "loss": 4.2699, "step": 15579 }, { "epoch": 0.4758704948075748, "grad_norm": 0.3798666298389435, "learning_rate": 2.689331239836935e-05, "loss": 4.2721, "step": 15580 }, { "epoch": 0.4759010384850336, "grad_norm": 0.3964419662952423, "learning_rate": 2.6890920384054837e-05, "loss": 4.3727, "step": 15581 }, { "epoch": 0.4759315821624924, "grad_norm": 0.39554864168167114, "learning_rate": 2.6888528352329645e-05, "loss": 4.3553, "step": 15582 }, { "epoch": 0.4759621258399511, "grad_norm": 0.3880835771560669, "learning_rate": 2.6886136303215808e-05, "loss": 4.3168, "step": 15583 }, { "epoch": 0.47599266951740987, "grad_norm": 0.3721582591533661, "learning_rate": 2.6883744236735343e-05, "loss": 4.2668, "step": 15584 }, { "epoch": 0.4760232131948687, "grad_norm": 0.39173561334609985, "learning_rate": 2.6881352152910272e-05, "loss": 4.3561, "step": 15585 }, { "epoch": 0.4760537568723274, "grad_norm": 0.39703992009162903, "learning_rate": 2.6878960051762626e-05, "loss": 4.2249, "step": 15586 }, { "epoch": 0.4760843005497862, "grad_norm": 0.3902808427810669, "learning_rate": 2.687656793331443e-05, "loss": 4.3069, "step": 15587 }, { "epoch": 0.476114844227245, "grad_norm": 0.38447651267051697, "learning_rate": 2.6874175797587703e-05, "loss": 4.2824, "step": 15588 }, { "epoch": 0.47614538790470373, "grad_norm": 0.3851999044418335, "learning_rate": 2.6871783644604476e-05, "loss": 4.2029, "step": 15589 }, { "epoch": 0.4761759315821625, "grad_norm": 0.381794810295105, "learning_rate": 2.6869391474386778e-05, "loss": 4.1776, "step": 15590 }, { "epoch": 0.47620647525962123, "grad_norm": 0.38308948278427124, "learning_rate": 2.6866999286956635e-05, "loss": 4.2707, "step": 15591 }, { "epoch": 0.47623701893708004, "grad_norm": 0.397891640663147, "learning_rate": 2.6864607082336067e-05, "loss": 4.2096, "step": 15592 }, { "epoch": 0.4762675626145388, "grad_norm": 0.39105769991874695, "learning_rate": 2.6862214860547104e-05, "loss": 4.3641, "step": 15593 }, { "epoch": 0.47629810629199754, "grad_norm": 0.38375115394592285, "learning_rate": 2.6859822621611768e-05, "loss": 4.2746, "step": 15594 }, { "epoch": 0.47632864996945634, "grad_norm": 0.38310834765434265, "learning_rate": 2.6857430365552088e-05, "loss": 4.321, "step": 15595 }, { "epoch": 0.4763591936469151, "grad_norm": 0.3876238465309143, "learning_rate": 2.6855038092390095e-05, "loss": 4.3362, "step": 15596 }, { "epoch": 0.47638973732437384, "grad_norm": 0.38926172256469727, "learning_rate": 2.6852645802147815e-05, "loss": 4.366, "step": 15597 }, { "epoch": 0.47642028100183265, "grad_norm": 0.38606661558151245, "learning_rate": 2.685025349484726e-05, "loss": 4.3094, "step": 15598 }, { "epoch": 0.4764508246792914, "grad_norm": 0.3824097514152527, "learning_rate": 2.6847861170510484e-05, "loss": 4.2168, "step": 15599 }, { "epoch": 0.47648136835675015, "grad_norm": 0.39534521102905273, "learning_rate": 2.6845468829159497e-05, "loss": 4.2812, "step": 15600 }, { "epoch": 0.4765119120342089, "grad_norm": 0.38917869329452515, "learning_rate": 2.684307647081633e-05, "loss": 4.248, "step": 15601 }, { "epoch": 0.4765424557116677, "grad_norm": 0.38674840331077576, "learning_rate": 2.6840684095503004e-05, "loss": 4.3026, "step": 15602 }, { "epoch": 0.47657299938912645, "grad_norm": 0.38781729340553284, "learning_rate": 2.6838291703241558e-05, "loss": 4.1702, "step": 15603 }, { "epoch": 0.4766035430665852, "grad_norm": 0.3873932957649231, "learning_rate": 2.683589929405402e-05, "loss": 4.3305, "step": 15604 }, { "epoch": 0.476634086744044, "grad_norm": 0.3831876218318939, "learning_rate": 2.68335068679624e-05, "loss": 4.4043, "step": 15605 }, { "epoch": 0.47666463042150276, "grad_norm": 0.3908107578754425, "learning_rate": 2.6831114424988745e-05, "loss": 4.3578, "step": 15606 }, { "epoch": 0.4766951740989615, "grad_norm": 0.3980928659439087, "learning_rate": 2.6828721965155084e-05, "loss": 4.3755, "step": 15607 }, { "epoch": 0.47672571777642025, "grad_norm": 0.3919324278831482, "learning_rate": 2.6826329488483444e-05, "loss": 4.3678, "step": 15608 }, { "epoch": 0.47675626145387906, "grad_norm": 0.40497177839279175, "learning_rate": 2.6823936994995835e-05, "loss": 4.2132, "step": 15609 }, { "epoch": 0.4767868051313378, "grad_norm": 0.3831247389316559, "learning_rate": 2.6821544484714307e-05, "loss": 4.3241, "step": 15610 }, { "epoch": 0.47681734880879656, "grad_norm": 0.38967034220695496, "learning_rate": 2.6819151957660883e-05, "loss": 4.372, "step": 15611 }, { "epoch": 0.47684789248625536, "grad_norm": 0.38845664262771606, "learning_rate": 2.6816759413857582e-05, "loss": 4.2952, "step": 15612 }, { "epoch": 0.4768784361637141, "grad_norm": 0.38738593459129333, "learning_rate": 2.6814366853326455e-05, "loss": 4.3108, "step": 15613 }, { "epoch": 0.47690897984117286, "grad_norm": 0.38619163632392883, "learning_rate": 2.6811974276089517e-05, "loss": 4.326, "step": 15614 }, { "epoch": 0.47693952351863167, "grad_norm": 0.3887642025947571, "learning_rate": 2.68095816821688e-05, "loss": 4.3429, "step": 15615 }, { "epoch": 0.4769700671960904, "grad_norm": 0.3823460042476654, "learning_rate": 2.6807189071586335e-05, "loss": 4.3401, "step": 15616 }, { "epoch": 0.47700061087354917, "grad_norm": 0.39349210262298584, "learning_rate": 2.680479644436415e-05, "loss": 4.3131, "step": 15617 }, { "epoch": 0.4770311545510079, "grad_norm": 0.3873763382434845, "learning_rate": 2.680240380052428e-05, "loss": 4.2404, "step": 15618 }, { "epoch": 0.4770616982284667, "grad_norm": 0.39481303095817566, "learning_rate": 2.6800011140088737e-05, "loss": 4.2567, "step": 15619 }, { "epoch": 0.4770922419059255, "grad_norm": 0.44600966572761536, "learning_rate": 2.679761846307958e-05, "loss": 4.3626, "step": 15620 }, { "epoch": 0.4771227855833842, "grad_norm": 0.37842902541160583, "learning_rate": 2.6795225769518823e-05, "loss": 4.3315, "step": 15621 }, { "epoch": 0.47715332926084303, "grad_norm": 0.40550553798675537, "learning_rate": 2.679283305942849e-05, "loss": 4.3384, "step": 15622 }, { "epoch": 0.4771838729383018, "grad_norm": 0.3868864178657532, "learning_rate": 2.6790440332830636e-05, "loss": 4.3695, "step": 15623 }, { "epoch": 0.47721441661576053, "grad_norm": 0.38350141048431396, "learning_rate": 2.6788047589747273e-05, "loss": 4.3375, "step": 15624 }, { "epoch": 0.4772449602932193, "grad_norm": 0.39208418130874634, "learning_rate": 2.6785654830200435e-05, "loss": 4.4171, "step": 15625 }, { "epoch": 0.4772755039706781, "grad_norm": 0.405414342880249, "learning_rate": 2.678326205421215e-05, "loss": 4.3009, "step": 15626 }, { "epoch": 0.47730604764813683, "grad_norm": 0.39472177624702454, "learning_rate": 2.678086926180446e-05, "loss": 4.3403, "step": 15627 }, { "epoch": 0.4773365913255956, "grad_norm": 0.3944166302680969, "learning_rate": 2.6778476452999385e-05, "loss": 4.3019, "step": 15628 }, { "epoch": 0.4773671350030544, "grad_norm": 0.37971481680870056, "learning_rate": 2.6776083627818967e-05, "loss": 4.394, "step": 15629 }, { "epoch": 0.47739767868051314, "grad_norm": 0.3966907858848572, "learning_rate": 2.6773690786285232e-05, "loss": 4.3223, "step": 15630 }, { "epoch": 0.4774282223579719, "grad_norm": 0.3852069675922394, "learning_rate": 2.6771297928420224e-05, "loss": 4.3589, "step": 15631 }, { "epoch": 0.4774587660354307, "grad_norm": 0.3806017339229584, "learning_rate": 2.6768905054245952e-05, "loss": 4.2196, "step": 15632 }, { "epoch": 0.47748930971288944, "grad_norm": 0.38999342918395996, "learning_rate": 2.6766512163784467e-05, "loss": 4.3085, "step": 15633 }, { "epoch": 0.4775198533903482, "grad_norm": 0.38509535789489746, "learning_rate": 2.6764119257057795e-05, "loss": 4.2023, "step": 15634 }, { "epoch": 0.47755039706780694, "grad_norm": 0.3918241262435913, "learning_rate": 2.6761726334087978e-05, "loss": 4.1499, "step": 15635 }, { "epoch": 0.47758094074526575, "grad_norm": 0.3854875862598419, "learning_rate": 2.6759333394897023e-05, "loss": 4.271, "step": 15636 }, { "epoch": 0.4776114844227245, "grad_norm": 0.39948347210884094, "learning_rate": 2.6756940439506996e-05, "loss": 4.255, "step": 15637 }, { "epoch": 0.47764202810018325, "grad_norm": 0.3857092261314392, "learning_rate": 2.675454746793991e-05, "loss": 4.2412, "step": 15638 }, { "epoch": 0.47767257177764205, "grad_norm": 0.3892865777015686, "learning_rate": 2.6752154480217806e-05, "loss": 4.3324, "step": 15639 }, { "epoch": 0.4777031154551008, "grad_norm": 0.37528371810913086, "learning_rate": 2.6749761476362716e-05, "loss": 4.2601, "step": 15640 }, { "epoch": 0.47773365913255955, "grad_norm": 0.3910044729709625, "learning_rate": 2.674736845639667e-05, "loss": 4.268, "step": 15641 }, { "epoch": 0.4777642028100183, "grad_norm": 0.388666570186615, "learning_rate": 2.6744975420341707e-05, "loss": 4.3657, "step": 15642 }, { "epoch": 0.4777947464874771, "grad_norm": 0.3874560296535492, "learning_rate": 2.674258236821985e-05, "loss": 4.2959, "step": 15643 }, { "epoch": 0.47782529016493586, "grad_norm": 0.39195242524147034, "learning_rate": 2.6740189300053143e-05, "loss": 4.3902, "step": 15644 }, { "epoch": 0.4778558338423946, "grad_norm": 0.38947588205337524, "learning_rate": 2.6737796215863625e-05, "loss": 4.3122, "step": 15645 }, { "epoch": 0.4778863775198534, "grad_norm": 0.3946269750595093, "learning_rate": 2.673540311567332e-05, "loss": 4.3696, "step": 15646 }, { "epoch": 0.47791692119731216, "grad_norm": 0.3850143849849701, "learning_rate": 2.6733009999504266e-05, "loss": 4.263, "step": 15647 }, { "epoch": 0.4779474648747709, "grad_norm": 0.3912556767463684, "learning_rate": 2.67306168673785e-05, "loss": 4.2905, "step": 15648 }, { "epoch": 0.4779780085522297, "grad_norm": 0.39299747347831726, "learning_rate": 2.672822371931805e-05, "loss": 4.2674, "step": 15649 }, { "epoch": 0.47800855222968847, "grad_norm": 0.3839244544506073, "learning_rate": 2.672583055534496e-05, "loss": 4.3579, "step": 15650 }, { "epoch": 0.4780390959071472, "grad_norm": 0.39218825101852417, "learning_rate": 2.672343737548126e-05, "loss": 4.3215, "step": 15651 }, { "epoch": 0.47806963958460597, "grad_norm": 0.38939204812049866, "learning_rate": 2.6721044179748988e-05, "loss": 4.3081, "step": 15652 }, { "epoch": 0.47810018326206477, "grad_norm": 0.38737043738365173, "learning_rate": 2.6718650968170167e-05, "loss": 4.1265, "step": 15653 }, { "epoch": 0.4781307269395235, "grad_norm": 0.38641053438186646, "learning_rate": 2.671625774076686e-05, "loss": 4.311, "step": 15654 }, { "epoch": 0.47816127061698227, "grad_norm": 0.38433244824409485, "learning_rate": 2.6713864497561075e-05, "loss": 4.3099, "step": 15655 }, { "epoch": 0.4781918142944411, "grad_norm": 0.39318129420280457, "learning_rate": 2.671147123857486e-05, "loss": 4.2804, "step": 15656 }, { "epoch": 0.4782223579718998, "grad_norm": 0.39211907982826233, "learning_rate": 2.6709077963830248e-05, "loss": 4.36, "step": 15657 }, { "epoch": 0.4782529016493586, "grad_norm": 0.40072038769721985, "learning_rate": 2.670668467334928e-05, "loss": 4.3904, "step": 15658 }, { "epoch": 0.4782834453268173, "grad_norm": 0.38899368047714233, "learning_rate": 2.6704291367153983e-05, "loss": 4.3719, "step": 15659 }, { "epoch": 0.47831398900427613, "grad_norm": 0.38221997022628784, "learning_rate": 2.67018980452664e-05, "loss": 4.3047, "step": 15660 }, { "epoch": 0.4783445326817349, "grad_norm": 0.38765010237693787, "learning_rate": 2.6699504707708565e-05, "loss": 4.3524, "step": 15661 }, { "epoch": 0.47837507635919363, "grad_norm": 0.3847431242465973, "learning_rate": 2.6697111354502525e-05, "loss": 4.2992, "step": 15662 }, { "epoch": 0.47840562003665243, "grad_norm": 0.39696842432022095, "learning_rate": 2.6694717985670303e-05, "loss": 4.3383, "step": 15663 }, { "epoch": 0.4784361637141112, "grad_norm": 0.3876287639141083, "learning_rate": 2.6692324601233948e-05, "loss": 4.2166, "step": 15664 }, { "epoch": 0.47846670739156993, "grad_norm": 0.38648316264152527, "learning_rate": 2.6689931201215484e-05, "loss": 4.3054, "step": 15665 }, { "epoch": 0.4784972510690287, "grad_norm": 0.3911687731742859, "learning_rate": 2.6687537785636953e-05, "loss": 4.3405, "step": 15666 }, { "epoch": 0.4785277947464875, "grad_norm": 0.3844218850135803, "learning_rate": 2.6685144354520392e-05, "loss": 4.2526, "step": 15667 }, { "epoch": 0.47855833842394624, "grad_norm": 0.3812675178050995, "learning_rate": 2.6682750907887844e-05, "loss": 4.2753, "step": 15668 }, { "epoch": 0.478588882101405, "grad_norm": 0.3880389928817749, "learning_rate": 2.6680357445761346e-05, "loss": 4.3068, "step": 15669 }, { "epoch": 0.4786194257788638, "grad_norm": 0.3992959260940552, "learning_rate": 2.6677963968162934e-05, "loss": 4.2993, "step": 15670 }, { "epoch": 0.47864996945632254, "grad_norm": 0.3892126977443695, "learning_rate": 2.667557047511464e-05, "loss": 4.3784, "step": 15671 }, { "epoch": 0.4786805131337813, "grad_norm": 0.3889261782169342, "learning_rate": 2.6673176966638507e-05, "loss": 4.2724, "step": 15672 }, { "epoch": 0.4787110568112401, "grad_norm": 0.39356324076652527, "learning_rate": 2.667078344275657e-05, "loss": 4.2437, "step": 15673 }, { "epoch": 0.47874160048869885, "grad_norm": 0.40697991847991943, "learning_rate": 2.6668389903490875e-05, "loss": 4.3412, "step": 15674 }, { "epoch": 0.4787721441661576, "grad_norm": 0.38823792338371277, "learning_rate": 2.6665996348863463e-05, "loss": 4.307, "step": 15675 }, { "epoch": 0.47880268784361635, "grad_norm": 0.4044148623943329, "learning_rate": 2.666360277889636e-05, "loss": 4.3419, "step": 15676 }, { "epoch": 0.47883323152107515, "grad_norm": 0.3828543722629547, "learning_rate": 2.666120919361161e-05, "loss": 4.216, "step": 15677 }, { "epoch": 0.4788637751985339, "grad_norm": 0.3911689519882202, "learning_rate": 2.6658815593031257e-05, "loss": 4.2973, "step": 15678 }, { "epoch": 0.47889431887599265, "grad_norm": 0.38610121607780457, "learning_rate": 2.6656421977177332e-05, "loss": 4.3338, "step": 15679 }, { "epoch": 0.47892486255345146, "grad_norm": 0.39831721782684326, "learning_rate": 2.6654028346071874e-05, "loss": 4.4024, "step": 15680 }, { "epoch": 0.4789554062309102, "grad_norm": 0.3939116597175598, "learning_rate": 2.6651634699736934e-05, "loss": 4.3641, "step": 15681 }, { "epoch": 0.47898594990836896, "grad_norm": 0.388051837682724, "learning_rate": 2.6649241038194543e-05, "loss": 4.2873, "step": 15682 }, { "epoch": 0.4790164935858277, "grad_norm": 0.38655808568000793, "learning_rate": 2.6646847361466742e-05, "loss": 4.3029, "step": 15683 }, { "epoch": 0.4790470372632865, "grad_norm": 0.39371800422668457, "learning_rate": 2.6644453669575564e-05, "loss": 4.2877, "step": 15684 }, { "epoch": 0.47907758094074526, "grad_norm": 0.3946990668773651, "learning_rate": 2.6642059962543066e-05, "loss": 4.3234, "step": 15685 }, { "epoch": 0.479108124618204, "grad_norm": 0.396481990814209, "learning_rate": 2.6639666240391276e-05, "loss": 4.3317, "step": 15686 }, { "epoch": 0.4791386682956628, "grad_norm": 0.38146403431892395, "learning_rate": 2.6637272503142226e-05, "loss": 4.2803, "step": 15687 }, { "epoch": 0.47916921197312157, "grad_norm": 0.39335912466049194, "learning_rate": 2.6634878750817978e-05, "loss": 4.3756, "step": 15688 }, { "epoch": 0.4791997556505803, "grad_norm": 0.3934195041656494, "learning_rate": 2.6632484983440552e-05, "loss": 4.2335, "step": 15689 }, { "epoch": 0.4792302993280391, "grad_norm": 0.38065698742866516, "learning_rate": 2.6630091201031997e-05, "loss": 4.2632, "step": 15690 }, { "epoch": 0.47926084300549787, "grad_norm": 0.39162585139274597, "learning_rate": 2.662769740361436e-05, "loss": 4.2392, "step": 15691 }, { "epoch": 0.4792913866829566, "grad_norm": 0.40431979298591614, "learning_rate": 2.662530359120967e-05, "loss": 4.2286, "step": 15692 }, { "epoch": 0.47932193036041537, "grad_norm": 0.39861974120140076, "learning_rate": 2.662290976383998e-05, "loss": 4.2709, "step": 15693 }, { "epoch": 0.4793524740378742, "grad_norm": 0.38238829374313354, "learning_rate": 2.6620515921527328e-05, "loss": 4.2902, "step": 15694 }, { "epoch": 0.4793830177153329, "grad_norm": 0.3809928297996521, "learning_rate": 2.661812206429375e-05, "loss": 4.2919, "step": 15695 }, { "epoch": 0.4794135613927917, "grad_norm": 0.3795211613178253, "learning_rate": 2.661572819216129e-05, "loss": 4.2605, "step": 15696 }, { "epoch": 0.4794441050702505, "grad_norm": 0.38790133595466614, "learning_rate": 2.6613334305151982e-05, "loss": 4.3018, "step": 15697 }, { "epoch": 0.47947464874770923, "grad_norm": 0.39500513672828674, "learning_rate": 2.6610940403287883e-05, "loss": 4.3704, "step": 15698 }, { "epoch": 0.479505192425168, "grad_norm": 0.3878181576728821, "learning_rate": 2.660854648659103e-05, "loss": 4.3097, "step": 15699 }, { "epoch": 0.47953573610262673, "grad_norm": 0.4059065282344818, "learning_rate": 2.6606152555083457e-05, "loss": 4.3281, "step": 15700 }, { "epoch": 0.47956627978008554, "grad_norm": 0.3857516050338745, "learning_rate": 2.6603758608787217e-05, "loss": 4.3523, "step": 15701 }, { "epoch": 0.4795968234575443, "grad_norm": 0.4031066298484802, "learning_rate": 2.660136464772434e-05, "loss": 4.317, "step": 15702 }, { "epoch": 0.47962736713500304, "grad_norm": 0.3918074071407318, "learning_rate": 2.6598970671916883e-05, "loss": 4.3015, "step": 15703 }, { "epoch": 0.47965791081246184, "grad_norm": 0.3882724940776825, "learning_rate": 2.659657668138687e-05, "loss": 4.3487, "step": 15704 }, { "epoch": 0.4796884544899206, "grad_norm": 0.38441208004951477, "learning_rate": 2.6594182676156364e-05, "loss": 4.3471, "step": 15705 }, { "epoch": 0.47971899816737934, "grad_norm": 0.4021814465522766, "learning_rate": 2.6591788656247398e-05, "loss": 4.3361, "step": 15706 }, { "epoch": 0.47974954184483815, "grad_norm": 0.39227017760276794, "learning_rate": 2.6589394621682007e-05, "loss": 4.2735, "step": 15707 }, { "epoch": 0.4797800855222969, "grad_norm": 0.403475821018219, "learning_rate": 2.6587000572482252e-05, "loss": 4.3311, "step": 15708 }, { "epoch": 0.47981062919975564, "grad_norm": 0.3921351134777069, "learning_rate": 2.658460650867017e-05, "loss": 4.2625, "step": 15709 }, { "epoch": 0.4798411728772144, "grad_norm": 0.3910568058490753, "learning_rate": 2.6582212430267794e-05, "loss": 4.3076, "step": 15710 }, { "epoch": 0.4798717165546732, "grad_norm": 0.3958647847175598, "learning_rate": 2.6579818337297168e-05, "loss": 4.2414, "step": 15711 }, { "epoch": 0.47990226023213195, "grad_norm": 0.374677449464798, "learning_rate": 2.657742422978035e-05, "loss": 4.3059, "step": 15712 }, { "epoch": 0.4799328039095907, "grad_norm": 0.38642996549606323, "learning_rate": 2.657503010773938e-05, "loss": 4.3038, "step": 15713 }, { "epoch": 0.4799633475870495, "grad_norm": 0.3874208331108093, "learning_rate": 2.6572635971196284e-05, "loss": 4.3268, "step": 15714 }, { "epoch": 0.47999389126450825, "grad_norm": 0.3981529772281647, "learning_rate": 2.6570241820173137e-05, "loss": 4.2718, "step": 15715 }, { "epoch": 0.480024434941967, "grad_norm": 0.3860712945461273, "learning_rate": 2.6567847654691957e-05, "loss": 4.2873, "step": 15716 }, { "epoch": 0.48005497861942575, "grad_norm": 0.3949863910675049, "learning_rate": 2.6565453474774798e-05, "loss": 4.2176, "step": 15717 }, { "epoch": 0.48008552229688456, "grad_norm": 0.39907339215278625, "learning_rate": 2.656305928044371e-05, "loss": 4.3469, "step": 15718 }, { "epoch": 0.4801160659743433, "grad_norm": 0.38827475905418396, "learning_rate": 2.6560665071720725e-05, "loss": 4.324, "step": 15719 }, { "epoch": 0.48014660965180206, "grad_norm": 0.39614740014076233, "learning_rate": 2.6558270848627898e-05, "loss": 4.1866, "step": 15720 }, { "epoch": 0.48017715332926086, "grad_norm": 0.39969441294670105, "learning_rate": 2.6555876611187264e-05, "loss": 4.3666, "step": 15721 }, { "epoch": 0.4802076970067196, "grad_norm": 0.38795655965805054, "learning_rate": 2.6553482359420877e-05, "loss": 4.307, "step": 15722 }, { "epoch": 0.48023824068417836, "grad_norm": 0.39314955472946167, "learning_rate": 2.6551088093350784e-05, "loss": 4.343, "step": 15723 }, { "epoch": 0.48026878436163717, "grad_norm": 0.39534422755241394, "learning_rate": 2.6548693812999028e-05, "loss": 4.3235, "step": 15724 }, { "epoch": 0.4802993280390959, "grad_norm": 0.38997700810432434, "learning_rate": 2.654629951838764e-05, "loss": 4.2672, "step": 15725 }, { "epoch": 0.48032987171655467, "grad_norm": 0.3733130991458893, "learning_rate": 2.6543905209538687e-05, "loss": 4.3606, "step": 15726 }, { "epoch": 0.4803604153940134, "grad_norm": 0.38296374678611755, "learning_rate": 2.6541510886474204e-05, "loss": 4.4239, "step": 15727 }, { "epoch": 0.4803909590714722, "grad_norm": 0.38409727811813354, "learning_rate": 2.6539116549216226e-05, "loss": 4.2803, "step": 15728 }, { "epoch": 0.480421502748931, "grad_norm": 0.3976336121559143, "learning_rate": 2.6536722197786824e-05, "loss": 4.263, "step": 15729 }, { "epoch": 0.4804520464263897, "grad_norm": 0.38826143741607666, "learning_rate": 2.653432783220803e-05, "loss": 4.2944, "step": 15730 }, { "epoch": 0.48048259010384853, "grad_norm": 0.3795068860054016, "learning_rate": 2.653193345250188e-05, "loss": 4.3871, "step": 15731 }, { "epoch": 0.4805131337813073, "grad_norm": 0.3941766321659088, "learning_rate": 2.652953905869044e-05, "loss": 4.3239, "step": 15732 }, { "epoch": 0.480543677458766, "grad_norm": 0.3867645561695099, "learning_rate": 2.6527144650795748e-05, "loss": 4.1906, "step": 15733 }, { "epoch": 0.4805742211362248, "grad_norm": 0.4191056489944458, "learning_rate": 2.652475022883985e-05, "loss": 4.2971, "step": 15734 }, { "epoch": 0.4806047648136836, "grad_norm": 0.3987811505794525, "learning_rate": 2.6522355792844782e-05, "loss": 4.3695, "step": 15735 }, { "epoch": 0.48063530849114233, "grad_norm": 0.38561466336250305, "learning_rate": 2.651996134283261e-05, "loss": 4.2583, "step": 15736 }, { "epoch": 0.4806658521686011, "grad_norm": 0.3853260576725006, "learning_rate": 2.651756687882538e-05, "loss": 4.3517, "step": 15737 }, { "epoch": 0.4806963958460599, "grad_norm": 0.38930636644363403, "learning_rate": 2.651517240084512e-05, "loss": 4.2881, "step": 15738 }, { "epoch": 0.48072693952351864, "grad_norm": 0.38665470480918884, "learning_rate": 2.651277790891389e-05, "loss": 4.3221, "step": 15739 }, { "epoch": 0.4807574832009774, "grad_norm": 0.3960918188095093, "learning_rate": 2.6510383403053736e-05, "loss": 4.2623, "step": 15740 }, { "epoch": 0.48078802687843614, "grad_norm": 0.38822147250175476, "learning_rate": 2.6507988883286718e-05, "loss": 4.3495, "step": 15741 }, { "epoch": 0.48081857055589494, "grad_norm": 0.3933344781398773, "learning_rate": 2.6505594349634854e-05, "loss": 4.2635, "step": 15742 }, { "epoch": 0.4808491142333537, "grad_norm": 0.3793076276779175, "learning_rate": 2.6503199802120216e-05, "loss": 4.332, "step": 15743 }, { "epoch": 0.48087965791081244, "grad_norm": 0.38743647933006287, "learning_rate": 2.6500805240764842e-05, "loss": 4.3324, "step": 15744 }, { "epoch": 0.48091020158827125, "grad_norm": 0.386448472738266, "learning_rate": 2.6498410665590783e-05, "loss": 4.3357, "step": 15745 }, { "epoch": 0.48094074526573, "grad_norm": 0.3938511312007904, "learning_rate": 2.649601607662009e-05, "loss": 4.2699, "step": 15746 }, { "epoch": 0.48097128894318875, "grad_norm": 0.39031973481178284, "learning_rate": 2.649362147387481e-05, "loss": 4.3092, "step": 15747 }, { "epoch": 0.48100183262064755, "grad_norm": 0.38431182503700256, "learning_rate": 2.6491226857376984e-05, "loss": 4.2751, "step": 15748 }, { "epoch": 0.4810323762981063, "grad_norm": 0.3721749484539032, "learning_rate": 2.6488832227148663e-05, "loss": 4.2797, "step": 15749 }, { "epoch": 0.48106291997556505, "grad_norm": 0.38129615783691406, "learning_rate": 2.6486437583211904e-05, "loss": 4.2728, "step": 15750 }, { "epoch": 0.4810934636530238, "grad_norm": 0.3961412310600281, "learning_rate": 2.648404292558875e-05, "loss": 4.2999, "step": 15751 }, { "epoch": 0.4811240073304826, "grad_norm": 0.3829442858695984, "learning_rate": 2.6481648254301244e-05, "loss": 4.2841, "step": 15752 }, { "epoch": 0.48115455100794136, "grad_norm": 0.38477471470832825, "learning_rate": 2.647925356937144e-05, "loss": 4.3098, "step": 15753 }, { "epoch": 0.4811850946854001, "grad_norm": 0.4062829613685608, "learning_rate": 2.6476858870821396e-05, "loss": 4.2333, "step": 15754 }, { "epoch": 0.4812156383628589, "grad_norm": 0.3935621380805969, "learning_rate": 2.6474464158673144e-05, "loss": 4.2713, "step": 15755 }, { "epoch": 0.48124618204031766, "grad_norm": 0.3826406002044678, "learning_rate": 2.6472069432948753e-05, "loss": 4.3077, "step": 15756 }, { "epoch": 0.4812767257177764, "grad_norm": 0.38559356331825256, "learning_rate": 2.646967469367026e-05, "loss": 4.3535, "step": 15757 }, { "epoch": 0.48130726939523516, "grad_norm": 0.3922792375087738, "learning_rate": 2.6467279940859714e-05, "loss": 4.3819, "step": 15758 }, { "epoch": 0.48133781307269397, "grad_norm": 0.3868928551673889, "learning_rate": 2.6464885174539162e-05, "loss": 4.3297, "step": 15759 }, { "epoch": 0.4813683567501527, "grad_norm": 0.38229766488075256, "learning_rate": 2.646249039473066e-05, "loss": 4.3163, "step": 15760 }, { "epoch": 0.48139890042761146, "grad_norm": 0.38378146290779114, "learning_rate": 2.6460095601456263e-05, "loss": 4.2572, "step": 15761 }, { "epoch": 0.48142944410507027, "grad_norm": 0.3871878981590271, "learning_rate": 2.645770079473801e-05, "loss": 4.3369, "step": 15762 }, { "epoch": 0.481459987782529, "grad_norm": 0.3885989785194397, "learning_rate": 2.6455305974597953e-05, "loss": 4.296, "step": 15763 }, { "epoch": 0.48149053145998777, "grad_norm": 0.4006246030330658, "learning_rate": 2.645291114105816e-05, "loss": 4.3866, "step": 15764 }, { "epoch": 0.4815210751374466, "grad_norm": 0.393442839384079, "learning_rate": 2.6450516294140655e-05, "loss": 4.3329, "step": 15765 }, { "epoch": 0.4815516188149053, "grad_norm": 0.3969939053058624, "learning_rate": 2.6448121433867507e-05, "loss": 4.2816, "step": 15766 }, { "epoch": 0.4815821624923641, "grad_norm": 0.3864619731903076, "learning_rate": 2.644572656026076e-05, "loss": 4.3677, "step": 15767 }, { "epoch": 0.4816127061698228, "grad_norm": 0.38947340846061707, "learning_rate": 2.6443331673342458e-05, "loss": 4.3691, "step": 15768 }, { "epoch": 0.48164324984728163, "grad_norm": 0.3895092308521271, "learning_rate": 2.644093677313466e-05, "loss": 4.3113, "step": 15769 }, { "epoch": 0.4816737935247404, "grad_norm": 0.39783281087875366, "learning_rate": 2.643854185965942e-05, "loss": 4.3045, "step": 15770 }, { "epoch": 0.48170433720219913, "grad_norm": 0.39334940910339355, "learning_rate": 2.6436146932938787e-05, "loss": 4.4045, "step": 15771 }, { "epoch": 0.48173488087965793, "grad_norm": 0.38583633303642273, "learning_rate": 2.643375199299481e-05, "loss": 4.2667, "step": 15772 }, { "epoch": 0.4817654245571167, "grad_norm": 0.4054793119430542, "learning_rate": 2.643135703984954e-05, "loss": 4.1584, "step": 15773 }, { "epoch": 0.48179596823457543, "grad_norm": 0.3848208785057068, "learning_rate": 2.6428962073525038e-05, "loss": 4.297, "step": 15774 }, { "epoch": 0.4818265119120342, "grad_norm": 0.4276251494884491, "learning_rate": 2.6426567094043336e-05, "loss": 4.2551, "step": 15775 }, { "epoch": 0.481857055589493, "grad_norm": 0.3925638198852539, "learning_rate": 2.6424172101426497e-05, "loss": 4.2413, "step": 15776 }, { "epoch": 0.48188759926695174, "grad_norm": 0.3872709274291992, "learning_rate": 2.6421777095696582e-05, "loss": 4.2666, "step": 15777 }, { "epoch": 0.4819181429444105, "grad_norm": 0.38676953315734863, "learning_rate": 2.6419382076875627e-05, "loss": 4.3042, "step": 15778 }, { "epoch": 0.4819486866218693, "grad_norm": 0.40850767493247986, "learning_rate": 2.64169870449857e-05, "loss": 4.365, "step": 15779 }, { "epoch": 0.48197923029932804, "grad_norm": 0.3996534049510956, "learning_rate": 2.6414592000048837e-05, "loss": 4.3982, "step": 15780 }, { "epoch": 0.4820097739767868, "grad_norm": 0.4007033109664917, "learning_rate": 2.6412196942087096e-05, "loss": 4.3225, "step": 15781 }, { "epoch": 0.4820403176542456, "grad_norm": 0.4020521342754364, "learning_rate": 2.6409801871122536e-05, "loss": 4.3048, "step": 15782 }, { "epoch": 0.48207086133170435, "grad_norm": 0.39264872670173645, "learning_rate": 2.6407406787177202e-05, "loss": 4.3065, "step": 15783 }, { "epoch": 0.4821014050091631, "grad_norm": 0.39122262597084045, "learning_rate": 2.6405011690273158e-05, "loss": 4.3327, "step": 15784 }, { "epoch": 0.48213194868662185, "grad_norm": 0.40159446001052856, "learning_rate": 2.6402616580432445e-05, "loss": 4.2075, "step": 15785 }, { "epoch": 0.48216249236408065, "grad_norm": 0.39651334285736084, "learning_rate": 2.6400221457677115e-05, "loss": 4.3074, "step": 15786 }, { "epoch": 0.4821930360415394, "grad_norm": 0.3896469175815582, "learning_rate": 2.639782632202923e-05, "loss": 4.3347, "step": 15787 }, { "epoch": 0.48222357971899815, "grad_norm": 0.38593587279319763, "learning_rate": 2.6395431173510843e-05, "loss": 4.3337, "step": 15788 }, { "epoch": 0.48225412339645696, "grad_norm": 0.38558587431907654, "learning_rate": 2.6393036012143994e-05, "loss": 4.2861, "step": 15789 }, { "epoch": 0.4822846670739157, "grad_norm": 0.4038049280643463, "learning_rate": 2.639064083795076e-05, "loss": 4.2317, "step": 15790 }, { "epoch": 0.48231521075137446, "grad_norm": 0.3886116147041321, "learning_rate": 2.638824565095317e-05, "loss": 4.281, "step": 15791 }, { "epoch": 0.4823457544288332, "grad_norm": 0.3981621563434601, "learning_rate": 2.6385850451173293e-05, "loss": 4.25, "step": 15792 }, { "epoch": 0.482376298106292, "grad_norm": 0.3999040424823761, "learning_rate": 2.6383455238633175e-05, "loss": 4.3172, "step": 15793 }, { "epoch": 0.48240684178375076, "grad_norm": 0.3871753215789795, "learning_rate": 2.6381060013354875e-05, "loss": 4.2559, "step": 15794 }, { "epoch": 0.4824373854612095, "grad_norm": 0.3845551013946533, "learning_rate": 2.6378664775360445e-05, "loss": 4.248, "step": 15795 }, { "epoch": 0.4824679291386683, "grad_norm": 0.3938505947589874, "learning_rate": 2.6376269524671942e-05, "loss": 4.3523, "step": 15796 }, { "epoch": 0.48249847281612707, "grad_norm": 0.38252246379852295, "learning_rate": 2.637387426131142e-05, "loss": 4.2614, "step": 15797 }, { "epoch": 0.4825290164935858, "grad_norm": 0.39163848757743835, "learning_rate": 2.6371478985300928e-05, "loss": 4.2951, "step": 15798 }, { "epoch": 0.4825595601710446, "grad_norm": 0.4017673432826996, "learning_rate": 2.6369083696662517e-05, "loss": 4.3154, "step": 15799 }, { "epoch": 0.48259010384850337, "grad_norm": 0.39005449414253235, "learning_rate": 2.6366688395418253e-05, "loss": 4.2889, "step": 15800 }, { "epoch": 0.4826206475259621, "grad_norm": 0.3917616605758667, "learning_rate": 2.636429308159019e-05, "loss": 4.3592, "step": 15801 }, { "epoch": 0.48265119120342087, "grad_norm": 0.38030701875686646, "learning_rate": 2.636189775520038e-05, "loss": 4.2759, "step": 15802 }, { "epoch": 0.4826817348808797, "grad_norm": 0.38365355134010315, "learning_rate": 2.6359502416270875e-05, "loss": 4.2495, "step": 15803 }, { "epoch": 0.4827122785583384, "grad_norm": 0.39036035537719727, "learning_rate": 2.6357107064823734e-05, "loss": 4.2523, "step": 15804 }, { "epoch": 0.4827428222357972, "grad_norm": 0.3784176707267761, "learning_rate": 2.6354711700881007e-05, "loss": 4.269, "step": 15805 }, { "epoch": 0.482773365913256, "grad_norm": 0.3887310326099396, "learning_rate": 2.6352316324464755e-05, "loss": 4.3259, "step": 15806 }, { "epoch": 0.48280390959071473, "grad_norm": 0.40533247590065, "learning_rate": 2.6349920935597026e-05, "loss": 4.3703, "step": 15807 }, { "epoch": 0.4828344532681735, "grad_norm": 0.3834344744682312, "learning_rate": 2.634752553429989e-05, "loss": 4.2382, "step": 15808 }, { "epoch": 0.48286499694563223, "grad_norm": 0.39331358671188354, "learning_rate": 2.634513012059539e-05, "loss": 4.2924, "step": 15809 }, { "epoch": 0.48289554062309104, "grad_norm": 0.395253449678421, "learning_rate": 2.6342734694505577e-05, "loss": 4.3387, "step": 15810 }, { "epoch": 0.4829260843005498, "grad_norm": 0.3792397975921631, "learning_rate": 2.6340339256052533e-05, "loss": 4.2786, "step": 15811 }, { "epoch": 0.48295662797800853, "grad_norm": 0.38980740308761597, "learning_rate": 2.6337943805258287e-05, "loss": 4.2302, "step": 15812 }, { "epoch": 0.48298717165546734, "grad_norm": 0.39358481764793396, "learning_rate": 2.6335548342144895e-05, "loss": 4.2114, "step": 15813 }, { "epoch": 0.4830177153329261, "grad_norm": 0.3860015869140625, "learning_rate": 2.6333152866734435e-05, "loss": 4.3387, "step": 15814 }, { "epoch": 0.48304825901038484, "grad_norm": 0.3978155255317688, "learning_rate": 2.633075737904895e-05, "loss": 4.2251, "step": 15815 }, { "epoch": 0.4830788026878436, "grad_norm": 0.38639864325523376, "learning_rate": 2.6328361879110492e-05, "loss": 4.3216, "step": 15816 }, { "epoch": 0.4831093463653024, "grad_norm": 0.39857468008995056, "learning_rate": 2.632596636694112e-05, "loss": 4.3473, "step": 15817 }, { "epoch": 0.48313989004276114, "grad_norm": 0.4075590968132019, "learning_rate": 2.63235708425629e-05, "loss": 4.3043, "step": 15818 }, { "epoch": 0.4831704337202199, "grad_norm": 0.3924999535083771, "learning_rate": 2.6321175305997892e-05, "loss": 4.2487, "step": 15819 }, { "epoch": 0.4832009773976787, "grad_norm": 0.38886314630508423, "learning_rate": 2.631877975726813e-05, "loss": 4.212, "step": 15820 }, { "epoch": 0.48323152107513745, "grad_norm": 0.3815409541130066, "learning_rate": 2.631638419639569e-05, "loss": 4.3035, "step": 15821 }, { "epoch": 0.4832620647525962, "grad_norm": 0.3971709609031677, "learning_rate": 2.6313988623402625e-05, "loss": 4.2541, "step": 15822 }, { "epoch": 0.483292608430055, "grad_norm": 0.393653005361557, "learning_rate": 2.6311593038310983e-05, "loss": 4.2301, "step": 15823 }, { "epoch": 0.48332315210751375, "grad_norm": 0.38267478346824646, "learning_rate": 2.6309197441142837e-05, "loss": 4.3567, "step": 15824 }, { "epoch": 0.4833536957849725, "grad_norm": 0.3887999951839447, "learning_rate": 2.6306801831920236e-05, "loss": 4.2946, "step": 15825 }, { "epoch": 0.48338423946243125, "grad_norm": 0.418409526348114, "learning_rate": 2.630440621066524e-05, "loss": 4.2588, "step": 15826 }, { "epoch": 0.48341478313989006, "grad_norm": 0.3986903429031372, "learning_rate": 2.6302010577399904e-05, "loss": 4.3311, "step": 15827 }, { "epoch": 0.4834453268173488, "grad_norm": 0.39171266555786133, "learning_rate": 2.6299614932146287e-05, "loss": 4.3084, "step": 15828 }, { "epoch": 0.48347587049480756, "grad_norm": 0.38818928599357605, "learning_rate": 2.629721927492645e-05, "loss": 4.3003, "step": 15829 }, { "epoch": 0.48350641417226636, "grad_norm": 0.3910899758338928, "learning_rate": 2.6294823605762437e-05, "loss": 4.1749, "step": 15830 }, { "epoch": 0.4835369578497251, "grad_norm": 0.38023990392684937, "learning_rate": 2.6292427924676327e-05, "loss": 4.2538, "step": 15831 }, { "epoch": 0.48356750152718386, "grad_norm": 0.37542417645454407, "learning_rate": 2.629003223169017e-05, "loss": 4.2427, "step": 15832 }, { "epoch": 0.4835980452046426, "grad_norm": 0.3827176094055176, "learning_rate": 2.628763652682602e-05, "loss": 4.3809, "step": 15833 }, { "epoch": 0.4836285888821014, "grad_norm": 0.38905200362205505, "learning_rate": 2.628524081010594e-05, "loss": 4.2536, "step": 15834 }, { "epoch": 0.48365913255956017, "grad_norm": 0.3960115313529968, "learning_rate": 2.6282845081551988e-05, "loss": 4.338, "step": 15835 }, { "epoch": 0.4836896762370189, "grad_norm": 0.39474382996559143, "learning_rate": 2.628044934118622e-05, "loss": 4.2848, "step": 15836 }, { "epoch": 0.4837202199144777, "grad_norm": 0.39420831203460693, "learning_rate": 2.627805358903069e-05, "loss": 4.2547, "step": 15837 }, { "epoch": 0.4837507635919365, "grad_norm": 0.398847371339798, "learning_rate": 2.6275657825107468e-05, "loss": 4.3544, "step": 15838 }, { "epoch": 0.4837813072693952, "grad_norm": 0.38332927227020264, "learning_rate": 2.6273262049438614e-05, "loss": 4.2733, "step": 15839 }, { "epoch": 0.483811850946854, "grad_norm": 0.40408313274383545, "learning_rate": 2.6270866262046173e-05, "loss": 4.3867, "step": 15840 }, { "epoch": 0.4838423946243128, "grad_norm": 0.3868478834629059, "learning_rate": 2.6268470462952216e-05, "loss": 4.2763, "step": 15841 }, { "epoch": 0.4838729383017715, "grad_norm": 0.38261541724205017, "learning_rate": 2.6266074652178803e-05, "loss": 4.2716, "step": 15842 }, { "epoch": 0.4839034819792303, "grad_norm": 0.3826061487197876, "learning_rate": 2.6263678829747994e-05, "loss": 4.2835, "step": 15843 }, { "epoch": 0.4839340256566891, "grad_norm": 0.3869379758834839, "learning_rate": 2.6261282995681835e-05, "loss": 4.3912, "step": 15844 }, { "epoch": 0.48396456933414783, "grad_norm": 0.3961101770401001, "learning_rate": 2.6258887150002398e-05, "loss": 4.2755, "step": 15845 }, { "epoch": 0.4839951130116066, "grad_norm": 0.3993239998817444, "learning_rate": 2.6256491292731738e-05, "loss": 4.3529, "step": 15846 }, { "epoch": 0.4840256566890654, "grad_norm": 0.4027218520641327, "learning_rate": 2.6254095423891915e-05, "loss": 4.3294, "step": 15847 }, { "epoch": 0.48405620036652414, "grad_norm": 0.3910938501358032, "learning_rate": 2.625169954350499e-05, "loss": 4.3193, "step": 15848 }, { "epoch": 0.4840867440439829, "grad_norm": 0.3948068916797638, "learning_rate": 2.624930365159303e-05, "loss": 4.4265, "step": 15849 }, { "epoch": 0.48411728772144164, "grad_norm": 0.38800546526908875, "learning_rate": 2.624690774817809e-05, "loss": 4.3559, "step": 15850 }, { "epoch": 0.48414783139890044, "grad_norm": 0.3877224028110504, "learning_rate": 2.6244511833282227e-05, "loss": 4.2693, "step": 15851 }, { "epoch": 0.4841783750763592, "grad_norm": 0.40500688552856445, "learning_rate": 2.6242115906927506e-05, "loss": 4.2932, "step": 15852 }, { "epoch": 0.48420891875381794, "grad_norm": 0.388295978307724, "learning_rate": 2.623971996913598e-05, "loss": 4.3724, "step": 15853 }, { "epoch": 0.48423946243127675, "grad_norm": 0.3896363079547882, "learning_rate": 2.6237324019929716e-05, "loss": 4.2481, "step": 15854 }, { "epoch": 0.4842700061087355, "grad_norm": 0.40167295932769775, "learning_rate": 2.623492805933077e-05, "loss": 4.3246, "step": 15855 }, { "epoch": 0.48430054978619425, "grad_norm": 0.40031906962394714, "learning_rate": 2.623253208736121e-05, "loss": 4.3928, "step": 15856 }, { "epoch": 0.48433109346365305, "grad_norm": 0.38369762897491455, "learning_rate": 2.6230136104043097e-05, "loss": 4.2398, "step": 15857 }, { "epoch": 0.4843616371411118, "grad_norm": 0.39282330870628357, "learning_rate": 2.6227740109398485e-05, "loss": 4.3251, "step": 15858 }, { "epoch": 0.48439218081857055, "grad_norm": 0.38414284586906433, "learning_rate": 2.6225344103449447e-05, "loss": 4.3963, "step": 15859 }, { "epoch": 0.4844227244960293, "grad_norm": 0.39159342646598816, "learning_rate": 2.6222948086218024e-05, "loss": 4.232, "step": 15860 }, { "epoch": 0.4844532681734881, "grad_norm": 0.3856854736804962, "learning_rate": 2.6220552057726288e-05, "loss": 4.3507, "step": 15861 }, { "epoch": 0.48448381185094685, "grad_norm": 0.386250764131546, "learning_rate": 2.6218156017996308e-05, "loss": 4.3328, "step": 15862 }, { "epoch": 0.4845143555284056, "grad_norm": 0.38545072078704834, "learning_rate": 2.6215759967050142e-05, "loss": 4.3787, "step": 15863 }, { "epoch": 0.4845448992058644, "grad_norm": 0.38267800211906433, "learning_rate": 2.621336390490984e-05, "loss": 4.2889, "step": 15864 }, { "epoch": 0.48457544288332316, "grad_norm": 0.3846484422683716, "learning_rate": 2.6210967831597476e-05, "loss": 4.4146, "step": 15865 }, { "epoch": 0.4846059865607819, "grad_norm": 0.39851364493370056, "learning_rate": 2.6208571747135114e-05, "loss": 4.3993, "step": 15866 }, { "epoch": 0.48463653023824066, "grad_norm": 0.37898674607276917, "learning_rate": 2.6206175651544805e-05, "loss": 4.2757, "step": 15867 }, { "epoch": 0.48466707391569946, "grad_norm": 0.38118696212768555, "learning_rate": 2.6203779544848618e-05, "loss": 4.1883, "step": 15868 }, { "epoch": 0.4846976175931582, "grad_norm": 0.39662790298461914, "learning_rate": 2.6201383427068614e-05, "loss": 4.3578, "step": 15869 }, { "epoch": 0.48472816127061696, "grad_norm": 0.39401867985725403, "learning_rate": 2.6198987298226855e-05, "loss": 4.2865, "step": 15870 }, { "epoch": 0.48475870494807577, "grad_norm": 0.4031031131744385, "learning_rate": 2.61965911583454e-05, "loss": 4.2973, "step": 15871 }, { "epoch": 0.4847892486255345, "grad_norm": 0.3963000774383545, "learning_rate": 2.619419500744632e-05, "loss": 4.2489, "step": 15872 }, { "epoch": 0.48481979230299327, "grad_norm": 0.38702818751335144, "learning_rate": 2.6191798845551673e-05, "loss": 4.2207, "step": 15873 }, { "epoch": 0.4848503359804521, "grad_norm": 0.39885565638542175, "learning_rate": 2.6189402672683517e-05, "loss": 4.3734, "step": 15874 }, { "epoch": 0.4848808796579108, "grad_norm": 0.38782766461372375, "learning_rate": 2.6187006488863925e-05, "loss": 4.2545, "step": 15875 }, { "epoch": 0.4849114233353696, "grad_norm": 0.38169610500335693, "learning_rate": 2.6184610294114953e-05, "loss": 4.2794, "step": 15876 }, { "epoch": 0.4849419670128283, "grad_norm": 0.37456128001213074, "learning_rate": 2.6182214088458663e-05, "loss": 4.2686, "step": 15877 }, { "epoch": 0.48497251069028713, "grad_norm": 0.37900957465171814, "learning_rate": 2.617981787191711e-05, "loss": 4.2207, "step": 15878 }, { "epoch": 0.4850030543677459, "grad_norm": 0.3985987603664398, "learning_rate": 2.617742164451238e-05, "loss": 4.3293, "step": 15879 }, { "epoch": 0.48503359804520463, "grad_norm": 0.3891179859638214, "learning_rate": 2.6175025406266517e-05, "loss": 4.2868, "step": 15880 }, { "epoch": 0.48506414172266343, "grad_norm": 0.3892133831977844, "learning_rate": 2.61726291572016e-05, "loss": 4.3157, "step": 15881 }, { "epoch": 0.4850946854001222, "grad_norm": 0.39166298508644104, "learning_rate": 2.6170232897339674e-05, "loss": 4.2465, "step": 15882 }, { "epoch": 0.48512522907758093, "grad_norm": 0.3938060998916626, "learning_rate": 2.6167836626702817e-05, "loss": 4.3091, "step": 15883 }, { "epoch": 0.4851557727550397, "grad_norm": 0.38719576597213745, "learning_rate": 2.616544034531309e-05, "loss": 4.2935, "step": 15884 }, { "epoch": 0.4851863164324985, "grad_norm": 0.37818244099617004, "learning_rate": 2.6163044053192548e-05, "loss": 4.3277, "step": 15885 }, { "epoch": 0.48521686010995724, "grad_norm": 0.38463887572288513, "learning_rate": 2.6160647750363266e-05, "loss": 4.1929, "step": 15886 }, { "epoch": 0.485247403787416, "grad_norm": 0.403477281332016, "learning_rate": 2.6158251436847298e-05, "loss": 4.2555, "step": 15887 }, { "epoch": 0.4852779474648748, "grad_norm": 0.3848246932029724, "learning_rate": 2.6155855112666717e-05, "loss": 4.18, "step": 15888 }, { "epoch": 0.48530849114233354, "grad_norm": 0.3958118259906769, "learning_rate": 2.6153458777843587e-05, "loss": 4.2887, "step": 15889 }, { "epoch": 0.4853390348197923, "grad_norm": 0.39323750138282776, "learning_rate": 2.615106243239997e-05, "loss": 4.2404, "step": 15890 }, { "epoch": 0.48536957849725104, "grad_norm": 0.3914062976837158, "learning_rate": 2.6148666076357926e-05, "loss": 4.324, "step": 15891 }, { "epoch": 0.48540012217470985, "grad_norm": 0.37849074602127075, "learning_rate": 2.6146269709739514e-05, "loss": 4.2878, "step": 15892 }, { "epoch": 0.4854306658521686, "grad_norm": 0.382380872964859, "learning_rate": 2.6143873332566814e-05, "loss": 4.3121, "step": 15893 }, { "epoch": 0.48546120952962735, "grad_norm": 0.382408082485199, "learning_rate": 2.6141476944861893e-05, "loss": 4.2732, "step": 15894 }, { "epoch": 0.48549175320708615, "grad_norm": 0.392577588558197, "learning_rate": 2.6139080546646794e-05, "loss": 4.2006, "step": 15895 }, { "epoch": 0.4855222968845449, "grad_norm": 0.3770793676376343, "learning_rate": 2.61366841379436e-05, "loss": 4.202, "step": 15896 }, { "epoch": 0.48555284056200365, "grad_norm": 0.3795618414878845, "learning_rate": 2.613428771877437e-05, "loss": 4.3159, "step": 15897 }, { "epoch": 0.48558338423946246, "grad_norm": 0.3937879800796509, "learning_rate": 2.6131891289161177e-05, "loss": 4.3266, "step": 15898 }, { "epoch": 0.4856139279169212, "grad_norm": 0.38260579109191895, "learning_rate": 2.612949484912607e-05, "loss": 4.27, "step": 15899 }, { "epoch": 0.48564447159437996, "grad_norm": 0.39840227365493774, "learning_rate": 2.6127098398691124e-05, "loss": 4.2164, "step": 15900 }, { "epoch": 0.4856750152718387, "grad_norm": 0.375318706035614, "learning_rate": 2.612470193787841e-05, "loss": 4.0938, "step": 15901 }, { "epoch": 0.4857055589492975, "grad_norm": 0.392834335565567, "learning_rate": 2.612230546670998e-05, "loss": 4.2856, "step": 15902 }, { "epoch": 0.48573610262675626, "grad_norm": 0.3946104943752289, "learning_rate": 2.611990898520791e-05, "loss": 4.3453, "step": 15903 }, { "epoch": 0.485766646304215, "grad_norm": 0.3995651304721832, "learning_rate": 2.6117512493394257e-05, "loss": 4.2931, "step": 15904 }, { "epoch": 0.4857971899816738, "grad_norm": 0.38565003871917725, "learning_rate": 2.61151159912911e-05, "loss": 4.384, "step": 15905 }, { "epoch": 0.48582773365913257, "grad_norm": 0.3972911834716797, "learning_rate": 2.6112719478920496e-05, "loss": 4.2958, "step": 15906 }, { "epoch": 0.4858582773365913, "grad_norm": 0.3915752172470093, "learning_rate": 2.6110322956304507e-05, "loss": 4.3755, "step": 15907 }, { "epoch": 0.48588882101405007, "grad_norm": 0.40135911107063293, "learning_rate": 2.6107926423465207e-05, "loss": 4.2586, "step": 15908 }, { "epoch": 0.48591936469150887, "grad_norm": 0.3903084695339203, "learning_rate": 2.610552988042465e-05, "loss": 4.3434, "step": 15909 }, { "epoch": 0.4859499083689676, "grad_norm": 0.3916318118572235, "learning_rate": 2.6103133327204922e-05, "loss": 4.2996, "step": 15910 }, { "epoch": 0.48598045204642637, "grad_norm": 0.38247737288475037, "learning_rate": 2.610073676382807e-05, "loss": 4.2764, "step": 15911 }, { "epoch": 0.4860109957238852, "grad_norm": 0.4067234694957733, "learning_rate": 2.6098340190316174e-05, "loss": 4.3255, "step": 15912 }, { "epoch": 0.4860415394013439, "grad_norm": 0.3986644744873047, "learning_rate": 2.60959436066913e-05, "loss": 4.3285, "step": 15913 }, { "epoch": 0.4860720830788027, "grad_norm": 0.3926362097263336, "learning_rate": 2.60935470129755e-05, "loss": 4.3651, "step": 15914 }, { "epoch": 0.4861026267562615, "grad_norm": 0.39972540736198425, "learning_rate": 2.609115040919085e-05, "loss": 4.1991, "step": 15915 }, { "epoch": 0.48613317043372023, "grad_norm": 0.4060819447040558, "learning_rate": 2.6088753795359423e-05, "loss": 4.2444, "step": 15916 }, { "epoch": 0.486163714111179, "grad_norm": 0.40347859263420105, "learning_rate": 2.6086357171503278e-05, "loss": 4.2986, "step": 15917 }, { "epoch": 0.48619425778863773, "grad_norm": 0.38557761907577515, "learning_rate": 2.6083960537644487e-05, "loss": 4.3377, "step": 15918 }, { "epoch": 0.48622480146609653, "grad_norm": 0.395388126373291, "learning_rate": 2.6081563893805107e-05, "loss": 4.3415, "step": 15919 }, { "epoch": 0.4862553451435553, "grad_norm": 0.378134548664093, "learning_rate": 2.6079167240007218e-05, "loss": 4.2791, "step": 15920 }, { "epoch": 0.48628588882101403, "grad_norm": 0.39436694979667664, "learning_rate": 2.6076770576272884e-05, "loss": 4.4062, "step": 15921 }, { "epoch": 0.48631643249847284, "grad_norm": 0.3897186517715454, "learning_rate": 2.6074373902624162e-05, "loss": 4.3213, "step": 15922 }, { "epoch": 0.4863469761759316, "grad_norm": 0.3926737606525421, "learning_rate": 2.607197721908313e-05, "loss": 4.3119, "step": 15923 }, { "epoch": 0.48637751985339034, "grad_norm": 0.3945448100566864, "learning_rate": 2.6069580525671856e-05, "loss": 4.3482, "step": 15924 }, { "epoch": 0.4864080635308491, "grad_norm": 0.4008771479129791, "learning_rate": 2.60671838224124e-05, "loss": 4.233, "step": 15925 }, { "epoch": 0.4864386072083079, "grad_norm": 0.37372735142707825, "learning_rate": 2.6064787109326833e-05, "loss": 4.245, "step": 15926 }, { "epoch": 0.48646915088576664, "grad_norm": 0.3901346027851105, "learning_rate": 2.6062390386437226e-05, "loss": 4.3122, "step": 15927 }, { "epoch": 0.4864996945632254, "grad_norm": 0.3938959240913391, "learning_rate": 2.6059993653765645e-05, "loss": 4.2899, "step": 15928 }, { "epoch": 0.4865302382406842, "grad_norm": 0.3961642384529114, "learning_rate": 2.6057596911334158e-05, "loss": 4.3185, "step": 15929 }, { "epoch": 0.48656078191814295, "grad_norm": 0.38430625200271606, "learning_rate": 2.6055200159164834e-05, "loss": 4.3603, "step": 15930 }, { "epoch": 0.4865913255956017, "grad_norm": 0.3827570080757141, "learning_rate": 2.6052803397279734e-05, "loss": 4.2916, "step": 15931 }, { "epoch": 0.4866218692730605, "grad_norm": 0.4106009602546692, "learning_rate": 2.605040662570093e-05, "loss": 4.1797, "step": 15932 }, { "epoch": 0.48665241295051925, "grad_norm": 0.39206066727638245, "learning_rate": 2.60480098444505e-05, "loss": 4.3009, "step": 15933 }, { "epoch": 0.486682956627978, "grad_norm": 0.3851000666618347, "learning_rate": 2.60456130535505e-05, "loss": 4.3378, "step": 15934 }, { "epoch": 0.48671350030543675, "grad_norm": 0.38480833172798157, "learning_rate": 2.6043216253023007e-05, "loss": 4.1962, "step": 15935 }, { "epoch": 0.48674404398289556, "grad_norm": 0.38187935948371887, "learning_rate": 2.6040819442890084e-05, "loss": 4.3132, "step": 15936 }, { "epoch": 0.4867745876603543, "grad_norm": 0.38338780403137207, "learning_rate": 2.6038422623173803e-05, "loss": 4.3618, "step": 15937 }, { "epoch": 0.48680513133781306, "grad_norm": 0.3964729607105255, "learning_rate": 2.6036025793896224e-05, "loss": 4.2601, "step": 15938 }, { "epoch": 0.48683567501527186, "grad_norm": 0.38926342129707336, "learning_rate": 2.6033628955079424e-05, "loss": 4.3507, "step": 15939 }, { "epoch": 0.4868662186927306, "grad_norm": 0.3808174133300781, "learning_rate": 2.6031232106745474e-05, "loss": 4.2714, "step": 15940 }, { "epoch": 0.48689676237018936, "grad_norm": 0.387043833732605, "learning_rate": 2.6028835248916444e-05, "loss": 4.2895, "step": 15941 }, { "epoch": 0.4869273060476481, "grad_norm": 0.38542482256889343, "learning_rate": 2.6026438381614393e-05, "loss": 4.1919, "step": 15942 }, { "epoch": 0.4869578497251069, "grad_norm": 0.40018540620803833, "learning_rate": 2.602404150486139e-05, "loss": 4.2836, "step": 15943 }, { "epoch": 0.48698839340256567, "grad_norm": 0.3875785171985626, "learning_rate": 2.6021644618679524e-05, "loss": 4.3323, "step": 15944 }, { "epoch": 0.4870189370800244, "grad_norm": 0.40076348185539246, "learning_rate": 2.601924772309085e-05, "loss": 4.3161, "step": 15945 }, { "epoch": 0.4870494807574832, "grad_norm": 0.388068288564682, "learning_rate": 2.6016850818117426e-05, "loss": 4.3592, "step": 15946 }, { "epoch": 0.48708002443494197, "grad_norm": 0.3996310830116272, "learning_rate": 2.6014453903781344e-05, "loss": 4.213, "step": 15947 }, { "epoch": 0.4871105681124007, "grad_norm": 0.39813581109046936, "learning_rate": 2.601205698010466e-05, "loss": 4.3379, "step": 15948 }, { "epoch": 0.4871411117898595, "grad_norm": 0.4003552794456482, "learning_rate": 2.600966004710944e-05, "loss": 4.2779, "step": 15949 }, { "epoch": 0.4871716554673183, "grad_norm": 0.3796999454498291, "learning_rate": 2.600726310481777e-05, "loss": 4.3223, "step": 15950 }, { "epoch": 0.487202199144777, "grad_norm": 0.38433322310447693, "learning_rate": 2.6004866153251712e-05, "loss": 4.2758, "step": 15951 }, { "epoch": 0.4872327428222358, "grad_norm": 0.3942186236381531, "learning_rate": 2.600246919243333e-05, "loss": 4.0895, "step": 15952 }, { "epoch": 0.4872632864996946, "grad_norm": 0.3992813527584076, "learning_rate": 2.6000072222384704e-05, "loss": 4.3395, "step": 15953 }, { "epoch": 0.48729383017715333, "grad_norm": 0.38542038202285767, "learning_rate": 2.599767524312789e-05, "loss": 4.3031, "step": 15954 }, { "epoch": 0.4873243738546121, "grad_norm": 0.3945067822933197, "learning_rate": 2.5995278254684974e-05, "loss": 4.3264, "step": 15955 }, { "epoch": 0.4873549175320709, "grad_norm": 0.38785409927368164, "learning_rate": 2.599288125707801e-05, "loss": 4.2842, "step": 15956 }, { "epoch": 0.48738546120952964, "grad_norm": 0.3896844983100891, "learning_rate": 2.599048425032909e-05, "loss": 4.3387, "step": 15957 }, { "epoch": 0.4874160048869884, "grad_norm": 0.3896774351596832, "learning_rate": 2.598808723446027e-05, "loss": 4.3675, "step": 15958 }, { "epoch": 0.48744654856444714, "grad_norm": 0.39050254225730896, "learning_rate": 2.598569020949362e-05, "loss": 4.2623, "step": 15959 }, { "epoch": 0.48747709224190594, "grad_norm": 0.3834158778190613, "learning_rate": 2.5983293175451213e-05, "loss": 4.214, "step": 15960 }, { "epoch": 0.4875076359193647, "grad_norm": 0.3968638777732849, "learning_rate": 2.598089613235512e-05, "loss": 4.3304, "step": 15961 }, { "epoch": 0.48753817959682344, "grad_norm": 0.39405572414398193, "learning_rate": 2.5978499080227413e-05, "loss": 4.2665, "step": 15962 }, { "epoch": 0.48756872327428225, "grad_norm": 0.38748446106910706, "learning_rate": 2.597610201909016e-05, "loss": 4.2709, "step": 15963 }, { "epoch": 0.487599266951741, "grad_norm": 0.39105188846588135, "learning_rate": 2.5973704948965434e-05, "loss": 4.4054, "step": 15964 }, { "epoch": 0.48762981062919974, "grad_norm": 0.38824164867401123, "learning_rate": 2.5971307869875304e-05, "loss": 4.2115, "step": 15965 }, { "epoch": 0.4876603543066585, "grad_norm": 0.39554858207702637, "learning_rate": 2.5968910781841848e-05, "loss": 4.2097, "step": 15966 }, { "epoch": 0.4876908979841173, "grad_norm": 0.38864246010780334, "learning_rate": 2.5966513684887133e-05, "loss": 4.2861, "step": 15967 }, { "epoch": 0.48772144166157605, "grad_norm": 0.39235809445381165, "learning_rate": 2.5964116579033232e-05, "loss": 4.3501, "step": 15968 }, { "epoch": 0.4877519853390348, "grad_norm": 0.4007333815097809, "learning_rate": 2.596171946430221e-05, "loss": 4.2022, "step": 15969 }, { "epoch": 0.4877825290164936, "grad_norm": 0.3906804323196411, "learning_rate": 2.5959322340716134e-05, "loss": 4.3274, "step": 15970 }, { "epoch": 0.48781307269395235, "grad_norm": 0.37972527742385864, "learning_rate": 2.5956925208297095e-05, "loss": 4.2145, "step": 15971 }, { "epoch": 0.4878436163714111, "grad_norm": 0.41662538051605225, "learning_rate": 2.5954528067067147e-05, "loss": 4.2562, "step": 15972 }, { "epoch": 0.4878741600488699, "grad_norm": 0.3872329592704773, "learning_rate": 2.5952130917048366e-05, "loss": 4.2898, "step": 15973 }, { "epoch": 0.48790470372632866, "grad_norm": 0.392756849527359, "learning_rate": 2.5949733758262834e-05, "loss": 4.2662, "step": 15974 }, { "epoch": 0.4879352474037874, "grad_norm": 0.391649454832077, "learning_rate": 2.5947336590732612e-05, "loss": 4.3777, "step": 15975 }, { "epoch": 0.48796579108124616, "grad_norm": 0.3923949599266052, "learning_rate": 2.5944939414479784e-05, "loss": 4.2992, "step": 15976 }, { "epoch": 0.48799633475870496, "grad_norm": 0.3898491859436035, "learning_rate": 2.5942542229526402e-05, "loss": 4.2705, "step": 15977 }, { "epoch": 0.4880268784361637, "grad_norm": 0.38874006271362305, "learning_rate": 2.5940145035894548e-05, "loss": 4.2443, "step": 15978 }, { "epoch": 0.48805742211362246, "grad_norm": 0.3864116072654724, "learning_rate": 2.5937747833606302e-05, "loss": 4.3461, "step": 15979 }, { "epoch": 0.48808796579108127, "grad_norm": 0.3848252594470978, "learning_rate": 2.5935350622683724e-05, "loss": 4.3008, "step": 15980 }, { "epoch": 0.48811850946854, "grad_norm": 0.3824065923690796, "learning_rate": 2.593295340314889e-05, "loss": 4.2502, "step": 15981 }, { "epoch": 0.48814905314599877, "grad_norm": 0.3913211226463318, "learning_rate": 2.5930556175023883e-05, "loss": 4.3662, "step": 15982 }, { "epoch": 0.4881795968234575, "grad_norm": 0.3884502053260803, "learning_rate": 2.592815893833076e-05, "loss": 4.2506, "step": 15983 }, { "epoch": 0.4882101405009163, "grad_norm": 0.39344075322151184, "learning_rate": 2.5925761693091606e-05, "loss": 4.2613, "step": 15984 }, { "epoch": 0.4882406841783751, "grad_norm": 0.39725586771965027, "learning_rate": 2.5923364439328486e-05, "loss": 4.3354, "step": 15985 }, { "epoch": 0.4882712278558338, "grad_norm": 0.39218205213546753, "learning_rate": 2.5920967177063477e-05, "loss": 4.2973, "step": 15986 }, { "epoch": 0.48830177153329263, "grad_norm": 0.3821961581707001, "learning_rate": 2.591856990631864e-05, "loss": 4.2995, "step": 15987 }, { "epoch": 0.4883323152107514, "grad_norm": 0.3812190592288971, "learning_rate": 2.5916172627116063e-05, "loss": 4.2007, "step": 15988 }, { "epoch": 0.4883628588882101, "grad_norm": 0.39381638169288635, "learning_rate": 2.591377533947782e-05, "loss": 4.3256, "step": 15989 }, { "epoch": 0.48839340256566893, "grad_norm": 0.3834885060787201, "learning_rate": 2.591137804342597e-05, "loss": 4.3067, "step": 15990 }, { "epoch": 0.4884239462431277, "grad_norm": 0.383449524641037, "learning_rate": 2.5908980738982596e-05, "loss": 4.3155, "step": 15991 }, { "epoch": 0.48845448992058643, "grad_norm": 0.3967417776584625, "learning_rate": 2.5906583426169774e-05, "loss": 4.2922, "step": 15992 }, { "epoch": 0.4884850335980452, "grad_norm": 0.3955584764480591, "learning_rate": 2.5904186105009565e-05, "loss": 4.3047, "step": 15993 }, { "epoch": 0.488515577275504, "grad_norm": 0.379637211561203, "learning_rate": 2.590178877552405e-05, "loss": 4.2753, "step": 15994 }, { "epoch": 0.48854612095296274, "grad_norm": 0.3886014223098755, "learning_rate": 2.5899391437735304e-05, "loss": 4.3162, "step": 15995 }, { "epoch": 0.4885766646304215, "grad_norm": 0.3858553171157837, "learning_rate": 2.58969940916654e-05, "loss": 4.2135, "step": 15996 }, { "epoch": 0.4886072083078803, "grad_norm": 0.40378355979919434, "learning_rate": 2.58945967373364e-05, "loss": 4.274, "step": 15997 }, { "epoch": 0.48863775198533904, "grad_norm": 0.3930398225784302, "learning_rate": 2.5892199374770398e-05, "loss": 4.2758, "step": 15998 }, { "epoch": 0.4886682956627978, "grad_norm": 0.3896864354610443, "learning_rate": 2.5889802003989467e-05, "loss": 4.2939, "step": 15999 }, { "epoch": 0.48869883934025654, "grad_norm": 0.3897542357444763, "learning_rate": 2.588740462501566e-05, "loss": 4.3496, "step": 16000 }, { "epoch": 0.48872938301771535, "grad_norm": 0.39468511939048767, "learning_rate": 2.5885007237871056e-05, "loss": 4.1402, "step": 16001 }, { "epoch": 0.4887599266951741, "grad_norm": 0.4006657004356384, "learning_rate": 2.5882609842577743e-05, "loss": 4.2407, "step": 16002 }, { "epoch": 0.48879047037263285, "grad_norm": 0.3908592164516449, "learning_rate": 2.588021243915779e-05, "loss": 4.3825, "step": 16003 }, { "epoch": 0.48882101405009165, "grad_norm": 0.38270822167396545, "learning_rate": 2.5877815027633263e-05, "loss": 4.3589, "step": 16004 }, { "epoch": 0.4888515577275504, "grad_norm": 0.3979649245738983, "learning_rate": 2.5875417608026243e-05, "loss": 4.1795, "step": 16005 }, { "epoch": 0.48888210140500915, "grad_norm": 0.3869796693325043, "learning_rate": 2.5873020180358803e-05, "loss": 4.3903, "step": 16006 }, { "epoch": 0.48891264508246796, "grad_norm": 0.3836507499217987, "learning_rate": 2.5870622744653023e-05, "loss": 4.2544, "step": 16007 }, { "epoch": 0.4889431887599267, "grad_norm": 0.39903655648231506, "learning_rate": 2.5868225300930964e-05, "loss": 4.3114, "step": 16008 }, { "epoch": 0.48897373243738546, "grad_norm": 0.3953005075454712, "learning_rate": 2.5865827849214714e-05, "loss": 4.2718, "step": 16009 }, { "epoch": 0.4890042761148442, "grad_norm": 0.3788735568523407, "learning_rate": 2.5863430389526345e-05, "loss": 4.3049, "step": 16010 }, { "epoch": 0.489034819792303, "grad_norm": 0.37816956639289856, "learning_rate": 2.586103292188791e-05, "loss": 4.1713, "step": 16011 }, { "epoch": 0.48906536346976176, "grad_norm": 0.388506144285202, "learning_rate": 2.585863544632152e-05, "loss": 4.2496, "step": 16012 }, { "epoch": 0.4890959071472205, "grad_norm": 0.4036479890346527, "learning_rate": 2.585623796284923e-05, "loss": 4.2803, "step": 16013 }, { "epoch": 0.4891264508246793, "grad_norm": 0.40421515703201294, "learning_rate": 2.5853840471493113e-05, "loss": 4.3846, "step": 16014 }, { "epoch": 0.48915699450213806, "grad_norm": 0.3885968327522278, "learning_rate": 2.585144297227525e-05, "loss": 4.2099, "step": 16015 }, { "epoch": 0.4891875381795968, "grad_norm": 0.38700467348098755, "learning_rate": 2.5849045465217714e-05, "loss": 4.2705, "step": 16016 }, { "epoch": 0.48921808185705556, "grad_norm": 0.38111141324043274, "learning_rate": 2.5846647950342577e-05, "loss": 4.3476, "step": 16017 }, { "epoch": 0.48924862553451437, "grad_norm": 0.38960641622543335, "learning_rate": 2.584425042767191e-05, "loss": 4.2605, "step": 16018 }, { "epoch": 0.4892791692119731, "grad_norm": 0.39450526237487793, "learning_rate": 2.5841852897227807e-05, "loss": 4.3373, "step": 16019 }, { "epoch": 0.48930971288943187, "grad_norm": 0.3853648900985718, "learning_rate": 2.5839455359032332e-05, "loss": 4.3369, "step": 16020 }, { "epoch": 0.4893402565668907, "grad_norm": 0.3956124186515808, "learning_rate": 2.5837057813107553e-05, "loss": 4.3605, "step": 16021 }, { "epoch": 0.4893708002443494, "grad_norm": 0.3922726511955261, "learning_rate": 2.5834660259475556e-05, "loss": 4.4098, "step": 16022 }, { "epoch": 0.4894013439218082, "grad_norm": 0.37888285517692566, "learning_rate": 2.5832262698158415e-05, "loss": 4.2579, "step": 16023 }, { "epoch": 0.489431887599267, "grad_norm": 0.37854355573654175, "learning_rate": 2.58298651291782e-05, "loss": 4.3042, "step": 16024 }, { "epoch": 0.48946243127672573, "grad_norm": 0.3833889067173004, "learning_rate": 2.582746755255699e-05, "loss": 4.3192, "step": 16025 }, { "epoch": 0.4894929749541845, "grad_norm": 0.38952526450157166, "learning_rate": 2.582506996831686e-05, "loss": 4.2851, "step": 16026 }, { "epoch": 0.48952351863164323, "grad_norm": 0.39376381039619446, "learning_rate": 2.582267237647989e-05, "loss": 4.3309, "step": 16027 }, { "epoch": 0.48955406230910203, "grad_norm": 0.38584810495376587, "learning_rate": 2.5820274777068144e-05, "loss": 4.2746, "step": 16028 }, { "epoch": 0.4895846059865608, "grad_norm": 0.39203426241874695, "learning_rate": 2.5817877170103717e-05, "loss": 4.2525, "step": 16029 }, { "epoch": 0.48961514966401953, "grad_norm": 0.3861096203327179, "learning_rate": 2.581547955560867e-05, "loss": 4.271, "step": 16030 }, { "epoch": 0.48964569334147834, "grad_norm": 0.40537574887275696, "learning_rate": 2.581308193360508e-05, "loss": 4.3671, "step": 16031 }, { "epoch": 0.4896762370189371, "grad_norm": 0.3956652879714966, "learning_rate": 2.5810684304115036e-05, "loss": 4.3952, "step": 16032 }, { "epoch": 0.48970678069639584, "grad_norm": 0.3918974995613098, "learning_rate": 2.5808286667160598e-05, "loss": 4.3178, "step": 16033 }, { "epoch": 0.4897373243738546, "grad_norm": 0.3932233154773712, "learning_rate": 2.580588902276385e-05, "loss": 4.2933, "step": 16034 }, { "epoch": 0.4897678680513134, "grad_norm": 0.3938693106174469, "learning_rate": 2.5803491370946864e-05, "loss": 4.3181, "step": 16035 }, { "epoch": 0.48979841172877214, "grad_norm": 0.3892609179019928, "learning_rate": 2.5801093711731726e-05, "loss": 4.2371, "step": 16036 }, { "epoch": 0.4898289554062309, "grad_norm": 0.40161633491516113, "learning_rate": 2.5798696045140503e-05, "loss": 4.3089, "step": 16037 }, { "epoch": 0.4898594990836897, "grad_norm": 0.3820105493068695, "learning_rate": 2.5796298371195276e-05, "loss": 4.3519, "step": 16038 }, { "epoch": 0.48989004276114845, "grad_norm": 0.4115186631679535, "learning_rate": 2.579390068991812e-05, "loss": 4.2403, "step": 16039 }, { "epoch": 0.4899205864386072, "grad_norm": 0.38681885600090027, "learning_rate": 2.579150300133112e-05, "loss": 4.2219, "step": 16040 }, { "epoch": 0.48995113011606595, "grad_norm": 0.3749080300331116, "learning_rate": 2.5789105305456334e-05, "loss": 4.2836, "step": 16041 }, { "epoch": 0.48998167379352475, "grad_norm": 0.3907417953014374, "learning_rate": 2.5786707602315846e-05, "loss": 4.191, "step": 16042 }, { "epoch": 0.4900122174709835, "grad_norm": 0.3963867127895355, "learning_rate": 2.5784309891931746e-05, "loss": 4.2736, "step": 16043 }, { "epoch": 0.49004276114844225, "grad_norm": 0.38151514530181885, "learning_rate": 2.57819121743261e-05, "loss": 4.2357, "step": 16044 }, { "epoch": 0.49007330482590106, "grad_norm": 0.37737837433815, "learning_rate": 2.5779514449520986e-05, "loss": 4.2975, "step": 16045 }, { "epoch": 0.4901038485033598, "grad_norm": 0.4124820828437805, "learning_rate": 2.5777116717538484e-05, "loss": 4.2185, "step": 16046 }, { "epoch": 0.49013439218081856, "grad_norm": 0.38091960549354553, "learning_rate": 2.5774718978400668e-05, "loss": 4.2708, "step": 16047 }, { "epoch": 0.49016493585827736, "grad_norm": 0.39886319637298584, "learning_rate": 2.577232123212961e-05, "loss": 4.1761, "step": 16048 }, { "epoch": 0.4901954795357361, "grad_norm": 0.38608986139297485, "learning_rate": 2.5769923478747398e-05, "loss": 4.2812, "step": 16049 }, { "epoch": 0.49022602321319486, "grad_norm": 0.40091651678085327, "learning_rate": 2.5767525718276104e-05, "loss": 4.2999, "step": 16050 }, { "epoch": 0.4902565668906536, "grad_norm": 0.39903339743614197, "learning_rate": 2.5765127950737805e-05, "loss": 4.243, "step": 16051 }, { "epoch": 0.4902871105681124, "grad_norm": 0.3983730673789978, "learning_rate": 2.5762730176154574e-05, "loss": 4.3787, "step": 16052 }, { "epoch": 0.49031765424557117, "grad_norm": 0.3893379867076874, "learning_rate": 2.5760332394548508e-05, "loss": 4.2723, "step": 16053 }, { "epoch": 0.4903481979230299, "grad_norm": 0.3822668194770813, "learning_rate": 2.575793460594167e-05, "loss": 4.31, "step": 16054 }, { "epoch": 0.4903787416004887, "grad_norm": 0.3898661434650421, "learning_rate": 2.5755536810356122e-05, "loss": 4.311, "step": 16055 }, { "epoch": 0.49040928527794747, "grad_norm": 0.39733248949050903, "learning_rate": 2.5753139007813976e-05, "loss": 4.276, "step": 16056 }, { "epoch": 0.4904398289554062, "grad_norm": 0.40372028946876526, "learning_rate": 2.575074119833728e-05, "loss": 4.2988, "step": 16057 }, { "epoch": 0.49047037263286497, "grad_norm": 0.3982817530632019, "learning_rate": 2.574834338194813e-05, "loss": 4.3446, "step": 16058 }, { "epoch": 0.4905009163103238, "grad_norm": 0.3740566670894623, "learning_rate": 2.5745945558668593e-05, "loss": 4.2377, "step": 16059 }, { "epoch": 0.4905314599877825, "grad_norm": 0.38569915294647217, "learning_rate": 2.5743547728520756e-05, "loss": 4.2785, "step": 16060 }, { "epoch": 0.4905620036652413, "grad_norm": 0.3915630280971527, "learning_rate": 2.574114989152669e-05, "loss": 4.3632, "step": 16061 }, { "epoch": 0.4905925473427001, "grad_norm": 0.38776999711990356, "learning_rate": 2.573875204770848e-05, "loss": 4.3708, "step": 16062 }, { "epoch": 0.49062309102015883, "grad_norm": 0.38768085837364197, "learning_rate": 2.5736354197088196e-05, "loss": 4.2635, "step": 16063 }, { "epoch": 0.4906536346976176, "grad_norm": 0.3922637104988098, "learning_rate": 2.573395633968792e-05, "loss": 4.272, "step": 16064 }, { "epoch": 0.4906841783750764, "grad_norm": 0.3985861539840698, "learning_rate": 2.5731558475529732e-05, "loss": 4.2845, "step": 16065 }, { "epoch": 0.49071472205253513, "grad_norm": 0.39606669545173645, "learning_rate": 2.572916060463571e-05, "loss": 4.3012, "step": 16066 }, { "epoch": 0.4907452657299939, "grad_norm": 0.39342623949050903, "learning_rate": 2.572676272702793e-05, "loss": 4.4221, "step": 16067 }, { "epoch": 0.49077580940745263, "grad_norm": 0.3842727243900299, "learning_rate": 2.572436484272847e-05, "loss": 4.305, "step": 16068 }, { "epoch": 0.49080635308491144, "grad_norm": 0.38643965125083923, "learning_rate": 2.572196695175942e-05, "loss": 4.2276, "step": 16069 }, { "epoch": 0.4908368967623702, "grad_norm": 0.40552839636802673, "learning_rate": 2.571956905414284e-05, "loss": 4.3344, "step": 16070 }, { "epoch": 0.49086744043982894, "grad_norm": 0.39636310935020447, "learning_rate": 2.571717114990082e-05, "loss": 4.1658, "step": 16071 }, { "epoch": 0.49089798411728774, "grad_norm": 0.4016808867454529, "learning_rate": 2.5714773239055435e-05, "loss": 4.3817, "step": 16072 }, { "epoch": 0.4909285277947465, "grad_norm": 0.38690462708473206, "learning_rate": 2.5712375321628764e-05, "loss": 4.2766, "step": 16073 }, { "epoch": 0.49095907147220524, "grad_norm": 0.3850012421607971, "learning_rate": 2.5709977397642893e-05, "loss": 4.2604, "step": 16074 }, { "epoch": 0.490989615149664, "grad_norm": 0.3825615346431732, "learning_rate": 2.570757946711989e-05, "loss": 4.3338, "step": 16075 }, { "epoch": 0.4910201588271228, "grad_norm": 0.3823314607143402, "learning_rate": 2.5705181530081835e-05, "loss": 4.312, "step": 16076 }, { "epoch": 0.49105070250458155, "grad_norm": 0.40048667788505554, "learning_rate": 2.570278358655082e-05, "loss": 4.2632, "step": 16077 }, { "epoch": 0.4910812461820403, "grad_norm": 0.3995671272277832, "learning_rate": 2.5700385636548917e-05, "loss": 4.342, "step": 16078 }, { "epoch": 0.4911117898594991, "grad_norm": 0.38456565141677856, "learning_rate": 2.5697987680098194e-05, "loss": 4.2754, "step": 16079 }, { "epoch": 0.49114233353695785, "grad_norm": 0.3915993273258209, "learning_rate": 2.569558971722075e-05, "loss": 4.2339, "step": 16080 }, { "epoch": 0.4911728772144166, "grad_norm": 0.3885776400566101, "learning_rate": 2.5693191747938643e-05, "loss": 4.2203, "step": 16081 }, { "epoch": 0.4912034208918754, "grad_norm": 0.39367473125457764, "learning_rate": 2.5690793772273964e-05, "loss": 4.2932, "step": 16082 }, { "epoch": 0.49123396456933416, "grad_norm": 0.3968450129032135, "learning_rate": 2.56883957902488e-05, "loss": 4.2493, "step": 16083 }, { "epoch": 0.4912645082467929, "grad_norm": 0.39277273416519165, "learning_rate": 2.5685997801885213e-05, "loss": 4.2808, "step": 16084 }, { "epoch": 0.49129505192425166, "grad_norm": 0.38799402117729187, "learning_rate": 2.56835998072053e-05, "loss": 4.3346, "step": 16085 }, { "epoch": 0.49132559560171046, "grad_norm": 0.3911082446575165, "learning_rate": 2.5681201806231126e-05, "loss": 4.2507, "step": 16086 }, { "epoch": 0.4913561392791692, "grad_norm": 0.3887661099433899, "learning_rate": 2.567880379898478e-05, "loss": 4.3915, "step": 16087 }, { "epoch": 0.49138668295662796, "grad_norm": 0.3839905858039856, "learning_rate": 2.567640578548834e-05, "loss": 4.3266, "step": 16088 }, { "epoch": 0.49141722663408677, "grad_norm": 0.404180109500885, "learning_rate": 2.5674007765763874e-05, "loss": 4.3463, "step": 16089 }, { "epoch": 0.4914477703115455, "grad_norm": 0.410638689994812, "learning_rate": 2.567160973983348e-05, "loss": 4.3485, "step": 16090 }, { "epoch": 0.49147831398900427, "grad_norm": 0.39267387986183167, "learning_rate": 2.566921170771923e-05, "loss": 4.3428, "step": 16091 }, { "epoch": 0.491508857666463, "grad_norm": 0.39008793234825134, "learning_rate": 2.5666813669443208e-05, "loss": 4.3518, "step": 16092 }, { "epoch": 0.4915394013439218, "grad_norm": 0.3914043605327606, "learning_rate": 2.5664415625027484e-05, "loss": 4.2998, "step": 16093 }, { "epoch": 0.49156994502138057, "grad_norm": 0.38810995221138, "learning_rate": 2.5662017574494146e-05, "loss": 4.3355, "step": 16094 }, { "epoch": 0.4916004886988393, "grad_norm": 0.39502862095832825, "learning_rate": 2.5659619517865267e-05, "loss": 4.3343, "step": 16095 }, { "epoch": 0.4916310323762981, "grad_norm": 0.38444653153419495, "learning_rate": 2.5657221455162932e-05, "loss": 4.2649, "step": 16096 }, { "epoch": 0.4916615760537569, "grad_norm": 0.3913748860359192, "learning_rate": 2.5654823386409227e-05, "loss": 4.3395, "step": 16097 }, { "epoch": 0.4916921197312156, "grad_norm": 0.3873664140701294, "learning_rate": 2.565242531162622e-05, "loss": 4.3472, "step": 16098 }, { "epoch": 0.49172266340867443, "grad_norm": 0.40412476658821106, "learning_rate": 2.5650027230835998e-05, "loss": 4.2697, "step": 16099 }, { "epoch": 0.4917532070861332, "grad_norm": 0.3881978392601013, "learning_rate": 2.5647629144060654e-05, "loss": 4.1418, "step": 16100 }, { "epoch": 0.49178375076359193, "grad_norm": 0.3855860233306885, "learning_rate": 2.5645231051322242e-05, "loss": 4.2744, "step": 16101 }, { "epoch": 0.4918142944410507, "grad_norm": 0.39244887232780457, "learning_rate": 2.5642832952642864e-05, "loss": 4.3099, "step": 16102 }, { "epoch": 0.4918448381185095, "grad_norm": 0.3946436643600464, "learning_rate": 2.5640434848044588e-05, "loss": 4.2745, "step": 16103 }, { "epoch": 0.49187538179596824, "grad_norm": 0.39321425557136536, "learning_rate": 2.5638036737549496e-05, "loss": 4.2605, "step": 16104 }, { "epoch": 0.491905925473427, "grad_norm": 0.3979871869087219, "learning_rate": 2.5635638621179675e-05, "loss": 4.3836, "step": 16105 }, { "epoch": 0.4919364691508858, "grad_norm": 0.38537177443504333, "learning_rate": 2.5633240498957202e-05, "loss": 4.2775, "step": 16106 }, { "epoch": 0.49196701282834454, "grad_norm": 0.3962664306163788, "learning_rate": 2.5630842370904157e-05, "loss": 4.32, "step": 16107 }, { "epoch": 0.4919975565058033, "grad_norm": 0.3981199860572815, "learning_rate": 2.5628444237042625e-05, "loss": 4.3131, "step": 16108 }, { "epoch": 0.49202810018326204, "grad_norm": 0.38567599654197693, "learning_rate": 2.5626046097394692e-05, "loss": 4.3629, "step": 16109 }, { "epoch": 0.49205864386072085, "grad_norm": 0.4005308747291565, "learning_rate": 2.5623647951982415e-05, "loss": 4.3964, "step": 16110 }, { "epoch": 0.4920891875381796, "grad_norm": 0.3884539008140564, "learning_rate": 2.5621249800827895e-05, "loss": 4.2613, "step": 16111 }, { "epoch": 0.49211973121563835, "grad_norm": 0.3947955071926117, "learning_rate": 2.5618851643953212e-05, "loss": 4.2816, "step": 16112 }, { "epoch": 0.49215027489309715, "grad_norm": 0.3961299955844879, "learning_rate": 2.5616453481380438e-05, "loss": 4.3108, "step": 16113 }, { "epoch": 0.4921808185705559, "grad_norm": 0.38507145643234253, "learning_rate": 2.5614055313131668e-05, "loss": 4.3075, "step": 16114 }, { "epoch": 0.49221136224801465, "grad_norm": 0.4075354039669037, "learning_rate": 2.5611657139228974e-05, "loss": 4.2775, "step": 16115 }, { "epoch": 0.4922419059254734, "grad_norm": 0.3971467614173889, "learning_rate": 2.5609258959694432e-05, "loss": 4.3546, "step": 16116 }, { "epoch": 0.4922724496029322, "grad_norm": 0.40560752153396606, "learning_rate": 2.5606860774550133e-05, "loss": 4.3768, "step": 16117 }, { "epoch": 0.49230299328039095, "grad_norm": 0.39334532618522644, "learning_rate": 2.5604462583818155e-05, "loss": 4.3272, "step": 16118 }, { "epoch": 0.4923335369578497, "grad_norm": 0.38861167430877686, "learning_rate": 2.560206438752058e-05, "loss": 4.2684, "step": 16119 }, { "epoch": 0.4923640806353085, "grad_norm": 0.4015675485134125, "learning_rate": 2.5599666185679483e-05, "loss": 4.3283, "step": 16120 }, { "epoch": 0.49239462431276726, "grad_norm": 0.38900721073150635, "learning_rate": 2.5597267978316958e-05, "loss": 4.3455, "step": 16121 }, { "epoch": 0.492425167990226, "grad_norm": 0.39499133825302124, "learning_rate": 2.5594869765455075e-05, "loss": 4.279, "step": 16122 }, { "epoch": 0.4924557116676848, "grad_norm": 0.3902948200702667, "learning_rate": 2.5592471547115924e-05, "loss": 4.267, "step": 16123 }, { "epoch": 0.49248625534514356, "grad_norm": 0.37471020221710205, "learning_rate": 2.5590073323321584e-05, "loss": 4.3021, "step": 16124 }, { "epoch": 0.4925167990226023, "grad_norm": 0.386272668838501, "learning_rate": 2.5587675094094133e-05, "loss": 4.3069, "step": 16125 }, { "epoch": 0.49254734270006106, "grad_norm": 0.37741464376449585, "learning_rate": 2.558527685945566e-05, "loss": 4.222, "step": 16126 }, { "epoch": 0.49257788637751987, "grad_norm": 0.3942352831363678, "learning_rate": 2.558287861942823e-05, "loss": 4.2302, "step": 16127 }, { "epoch": 0.4926084300549786, "grad_norm": 0.4042290151119232, "learning_rate": 2.5580480374033943e-05, "loss": 4.2335, "step": 16128 }, { "epoch": 0.49263897373243737, "grad_norm": 0.3907926082611084, "learning_rate": 2.5578082123294877e-05, "loss": 4.1812, "step": 16129 }, { "epoch": 0.4926695174098962, "grad_norm": 0.41483330726623535, "learning_rate": 2.5575683867233107e-05, "loss": 4.2598, "step": 16130 }, { "epoch": 0.4927000610873549, "grad_norm": 0.3881678283214569, "learning_rate": 2.5573285605870724e-05, "loss": 4.2669, "step": 16131 }, { "epoch": 0.4927306047648137, "grad_norm": 0.3852941393852234, "learning_rate": 2.557088733922981e-05, "loss": 4.3268, "step": 16132 }, { "epoch": 0.4927611484422724, "grad_norm": 0.39115244150161743, "learning_rate": 2.5568489067332442e-05, "loss": 4.2681, "step": 16133 }, { "epoch": 0.49279169211973123, "grad_norm": 0.39821383357048035, "learning_rate": 2.556609079020069e-05, "loss": 4.3177, "step": 16134 }, { "epoch": 0.49282223579719, "grad_norm": 0.39070677757263184, "learning_rate": 2.556369250785666e-05, "loss": 4.2966, "step": 16135 }, { "epoch": 0.49285277947464873, "grad_norm": 0.3955436944961548, "learning_rate": 2.5561294220322423e-05, "loss": 4.3324, "step": 16136 }, { "epoch": 0.49288332315210753, "grad_norm": 0.39372074604034424, "learning_rate": 2.555889592762005e-05, "loss": 4.1507, "step": 16137 }, { "epoch": 0.4929138668295663, "grad_norm": 0.3889455497264862, "learning_rate": 2.5556497629771646e-05, "loss": 4.2375, "step": 16138 }, { "epoch": 0.49294441050702503, "grad_norm": 0.3906959891319275, "learning_rate": 2.5554099326799284e-05, "loss": 4.3421, "step": 16139 }, { "epoch": 0.49297495418448384, "grad_norm": 0.3802785575389862, "learning_rate": 2.555170101872504e-05, "loss": 4.2414, "step": 16140 }, { "epoch": 0.4930054978619426, "grad_norm": 0.3841666579246521, "learning_rate": 2.5549302705571003e-05, "loss": 4.3991, "step": 16141 }, { "epoch": 0.49303604153940134, "grad_norm": 0.39589476585388184, "learning_rate": 2.5546904387359255e-05, "loss": 4.2107, "step": 16142 }, { "epoch": 0.4930665852168601, "grad_norm": 0.3901351988315582, "learning_rate": 2.5544506064111872e-05, "loss": 4.3599, "step": 16143 }, { "epoch": 0.4930971288943189, "grad_norm": 0.38883623480796814, "learning_rate": 2.5542107735850938e-05, "loss": 4.2513, "step": 16144 }, { "epoch": 0.49312767257177764, "grad_norm": 0.38382601737976074, "learning_rate": 2.5539709402598548e-05, "loss": 4.3357, "step": 16145 }, { "epoch": 0.4931582162492364, "grad_norm": 0.38707152009010315, "learning_rate": 2.5537311064376778e-05, "loss": 4.2926, "step": 16146 }, { "epoch": 0.4931887599266952, "grad_norm": 0.39183807373046875, "learning_rate": 2.5534912721207705e-05, "loss": 4.2791, "step": 16147 }, { "epoch": 0.49321930360415395, "grad_norm": 0.3968293070793152, "learning_rate": 2.5532514373113414e-05, "loss": 4.2152, "step": 16148 }, { "epoch": 0.4932498472816127, "grad_norm": 0.39917871356010437, "learning_rate": 2.553011602011599e-05, "loss": 4.2374, "step": 16149 }, { "epoch": 0.49328039095907145, "grad_norm": 0.4026024341583252, "learning_rate": 2.552771766223752e-05, "loss": 4.3813, "step": 16150 }, { "epoch": 0.49331093463653025, "grad_norm": 0.3863508105278015, "learning_rate": 2.5525319299500072e-05, "loss": 4.256, "step": 16151 }, { "epoch": 0.493341478313989, "grad_norm": 0.4002722501754761, "learning_rate": 2.5522920931925748e-05, "loss": 4.1901, "step": 16152 }, { "epoch": 0.49337202199144775, "grad_norm": 0.38623109459877014, "learning_rate": 2.552052255953662e-05, "loss": 4.3671, "step": 16153 }, { "epoch": 0.49340256566890656, "grad_norm": 0.3884779214859009, "learning_rate": 2.5518124182354763e-05, "loss": 4.3178, "step": 16154 }, { "epoch": 0.4934331093463653, "grad_norm": 0.39954856038093567, "learning_rate": 2.551572580040229e-05, "loss": 4.2418, "step": 16155 }, { "epoch": 0.49346365302382406, "grad_norm": 0.3924081027507782, "learning_rate": 2.5513327413701255e-05, "loss": 4.3178, "step": 16156 }, { "epoch": 0.49349419670128286, "grad_norm": 0.4016454815864563, "learning_rate": 2.5510929022273744e-05, "loss": 4.2754, "step": 16157 }, { "epoch": 0.4935247403787416, "grad_norm": 0.38298407196998596, "learning_rate": 2.5508530626141852e-05, "loss": 4.2553, "step": 16158 }, { "epoch": 0.49355528405620036, "grad_norm": 0.3917005658149719, "learning_rate": 2.550613222532766e-05, "loss": 4.3377, "step": 16159 }, { "epoch": 0.4935858277336591, "grad_norm": 0.38871362805366516, "learning_rate": 2.5503733819853247e-05, "loss": 4.3894, "step": 16160 }, { "epoch": 0.4936163714111179, "grad_norm": 0.38935792446136475, "learning_rate": 2.550133540974069e-05, "loss": 4.3057, "step": 16161 }, { "epoch": 0.49364691508857667, "grad_norm": 0.38753965497016907, "learning_rate": 2.549893699501209e-05, "loss": 4.3608, "step": 16162 }, { "epoch": 0.4936774587660354, "grad_norm": 0.38173985481262207, "learning_rate": 2.5496538575689517e-05, "loss": 4.205, "step": 16163 }, { "epoch": 0.4937080024434942, "grad_norm": 0.3971697986125946, "learning_rate": 2.549414015179506e-05, "loss": 4.4174, "step": 16164 }, { "epoch": 0.49373854612095297, "grad_norm": 0.396869957447052, "learning_rate": 2.54917417233508e-05, "loss": 4.3692, "step": 16165 }, { "epoch": 0.4937690897984117, "grad_norm": 0.4081462025642395, "learning_rate": 2.548934329037882e-05, "loss": 4.2052, "step": 16166 }, { "epoch": 0.49379963347587047, "grad_norm": 0.39462772011756897, "learning_rate": 2.54869448529012e-05, "loss": 4.2931, "step": 16167 }, { "epoch": 0.4938301771533293, "grad_norm": 0.3927592933177948, "learning_rate": 2.548454641094003e-05, "loss": 4.2324, "step": 16168 }, { "epoch": 0.493860720830788, "grad_norm": 0.38593584299087524, "learning_rate": 2.54821479645174e-05, "loss": 4.2839, "step": 16169 }, { "epoch": 0.4938912645082468, "grad_norm": 0.3934244215488434, "learning_rate": 2.5479749513655375e-05, "loss": 4.1672, "step": 16170 }, { "epoch": 0.4939218081857056, "grad_norm": 0.39593514800071716, "learning_rate": 2.5477351058376058e-05, "loss": 4.2818, "step": 16171 }, { "epoch": 0.49395235186316433, "grad_norm": 0.398598849773407, "learning_rate": 2.5474952598701523e-05, "loss": 4.2609, "step": 16172 }, { "epoch": 0.4939828955406231, "grad_norm": 0.39195695519447327, "learning_rate": 2.547255413465386e-05, "loss": 4.3511, "step": 16173 }, { "epoch": 0.4940134392180819, "grad_norm": 0.41086703538894653, "learning_rate": 2.5470155666255136e-05, "loss": 4.3256, "step": 16174 }, { "epoch": 0.49404398289554063, "grad_norm": 0.3872976005077362, "learning_rate": 2.546775719352745e-05, "loss": 4.2367, "step": 16175 }, { "epoch": 0.4940745265729994, "grad_norm": 0.3929809033870697, "learning_rate": 2.546535871649289e-05, "loss": 4.3302, "step": 16176 }, { "epoch": 0.49410507025045813, "grad_norm": 0.39102473855018616, "learning_rate": 2.5462960235173528e-05, "loss": 4.2725, "step": 16177 }, { "epoch": 0.49413561392791694, "grad_norm": 0.3924257755279541, "learning_rate": 2.5460561749591454e-05, "loss": 4.3343, "step": 16178 }, { "epoch": 0.4941661576053757, "grad_norm": 0.3945361375808716, "learning_rate": 2.5458163259768754e-05, "loss": 4.3421, "step": 16179 }, { "epoch": 0.49419670128283444, "grad_norm": 0.40053486824035645, "learning_rate": 2.5455764765727508e-05, "loss": 4.2398, "step": 16180 }, { "epoch": 0.49422724496029324, "grad_norm": 0.396614134311676, "learning_rate": 2.54533662674898e-05, "loss": 4.3131, "step": 16181 }, { "epoch": 0.494257788637752, "grad_norm": 0.4054681956768036, "learning_rate": 2.5450967765077716e-05, "loss": 4.2654, "step": 16182 }, { "epoch": 0.49428833231521074, "grad_norm": 0.39276427030563354, "learning_rate": 2.5448569258513338e-05, "loss": 4.2836, "step": 16183 }, { "epoch": 0.4943188759926695, "grad_norm": 0.3808285593986511, "learning_rate": 2.5446170747818753e-05, "loss": 4.3087, "step": 16184 }, { "epoch": 0.4943494196701283, "grad_norm": 0.393034964799881, "learning_rate": 2.5443772233016045e-05, "loss": 4.3387, "step": 16185 }, { "epoch": 0.49437996334758705, "grad_norm": 0.38414517045021057, "learning_rate": 2.5441373714127297e-05, "loss": 4.2871, "step": 16186 }, { "epoch": 0.4944105070250458, "grad_norm": 0.38135793805122375, "learning_rate": 2.54389751911746e-05, "loss": 4.2442, "step": 16187 }, { "epoch": 0.4944410507025046, "grad_norm": 0.3992220163345337, "learning_rate": 2.5436576664180022e-05, "loss": 4.2817, "step": 16188 }, { "epoch": 0.49447159437996335, "grad_norm": 0.3937143087387085, "learning_rate": 2.543417813316567e-05, "loss": 4.3355, "step": 16189 }, { "epoch": 0.4945021380574221, "grad_norm": 0.38699010014533997, "learning_rate": 2.543177959815361e-05, "loss": 4.3605, "step": 16190 }, { "epoch": 0.49453268173488085, "grad_norm": 0.388213187456131, "learning_rate": 2.5429381059165935e-05, "loss": 4.2881, "step": 16191 }, { "epoch": 0.49456322541233966, "grad_norm": 0.3936226963996887, "learning_rate": 2.5426982516224724e-05, "loss": 4.2276, "step": 16192 }, { "epoch": 0.4945937690897984, "grad_norm": 0.3834105432033539, "learning_rate": 2.542458396935207e-05, "loss": 4.3316, "step": 16193 }, { "epoch": 0.49462431276725716, "grad_norm": 0.40366649627685547, "learning_rate": 2.5422185418570056e-05, "loss": 4.2544, "step": 16194 }, { "epoch": 0.49465485644471596, "grad_norm": 0.39182424545288086, "learning_rate": 2.5419786863900756e-05, "loss": 4.3049, "step": 16195 }, { "epoch": 0.4946854001221747, "grad_norm": 0.3907063901424408, "learning_rate": 2.541738830536627e-05, "loss": 4.3302, "step": 16196 }, { "epoch": 0.49471594379963346, "grad_norm": 0.3961330056190491, "learning_rate": 2.541498974298867e-05, "loss": 4.2941, "step": 16197 }, { "epoch": 0.49474648747709227, "grad_norm": 0.399985134601593, "learning_rate": 2.5412591176790047e-05, "loss": 4.3037, "step": 16198 }, { "epoch": 0.494777031154551, "grad_norm": 0.39414018392562866, "learning_rate": 2.5410192606792483e-05, "loss": 4.305, "step": 16199 }, { "epoch": 0.49480757483200977, "grad_norm": 0.3877989649772644, "learning_rate": 2.5407794033018067e-05, "loss": 4.31, "step": 16200 }, { "epoch": 0.4948381185094685, "grad_norm": 0.39517638087272644, "learning_rate": 2.5405395455488883e-05, "loss": 4.2484, "step": 16201 }, { "epoch": 0.4948686621869273, "grad_norm": 0.3921125829219818, "learning_rate": 2.5402996874227014e-05, "loss": 4.2841, "step": 16202 }, { "epoch": 0.49489920586438607, "grad_norm": 0.40049296617507935, "learning_rate": 2.5400598289254545e-05, "loss": 4.2997, "step": 16203 }, { "epoch": 0.4949297495418448, "grad_norm": 0.40838369727134705, "learning_rate": 2.5398199700593565e-05, "loss": 4.2986, "step": 16204 }, { "epoch": 0.4949602932193036, "grad_norm": 0.4046509563922882, "learning_rate": 2.539580110826615e-05, "loss": 4.2901, "step": 16205 }, { "epoch": 0.4949908368967624, "grad_norm": 0.3950464129447937, "learning_rate": 2.539340251229439e-05, "loss": 4.2611, "step": 16206 }, { "epoch": 0.4950213805742211, "grad_norm": 0.40974366664886475, "learning_rate": 2.539100391270038e-05, "loss": 4.259, "step": 16207 }, { "epoch": 0.4950519242516799, "grad_norm": 0.3914492428302765, "learning_rate": 2.5388605309506184e-05, "loss": 4.3604, "step": 16208 }, { "epoch": 0.4950824679291387, "grad_norm": 0.38987401127815247, "learning_rate": 2.53862067027339e-05, "loss": 4.3782, "step": 16209 }, { "epoch": 0.49511301160659743, "grad_norm": 0.38721102476119995, "learning_rate": 2.5383808092405624e-05, "loss": 4.3041, "step": 16210 }, { "epoch": 0.4951435552840562, "grad_norm": 0.40356671810150146, "learning_rate": 2.538140947854343e-05, "loss": 4.2894, "step": 16211 }, { "epoch": 0.495174098961515, "grad_norm": 0.39973053336143494, "learning_rate": 2.5379010861169388e-05, "loss": 4.2812, "step": 16212 }, { "epoch": 0.49520464263897374, "grad_norm": 0.4005984961986542, "learning_rate": 2.53766122403056e-05, "loss": 4.3575, "step": 16213 }, { "epoch": 0.4952351863164325, "grad_norm": 0.4135389029979706, "learning_rate": 2.5374213615974164e-05, "loss": 4.2885, "step": 16214 }, { "epoch": 0.4952657299938913, "grad_norm": 0.40301480889320374, "learning_rate": 2.5371814988197136e-05, "loss": 4.2734, "step": 16215 }, { "epoch": 0.49529627367135004, "grad_norm": 0.39981380105018616, "learning_rate": 2.5369416356996623e-05, "loss": 4.2683, "step": 16216 }, { "epoch": 0.4953268173488088, "grad_norm": 0.4036186635494232, "learning_rate": 2.5367017722394705e-05, "loss": 4.1369, "step": 16217 }, { "epoch": 0.49535736102626754, "grad_norm": 0.39611580967903137, "learning_rate": 2.536461908441346e-05, "loss": 4.336, "step": 16218 }, { "epoch": 0.49538790470372635, "grad_norm": 0.39601173996925354, "learning_rate": 2.5362220443074987e-05, "loss": 4.3717, "step": 16219 }, { "epoch": 0.4954184483811851, "grad_norm": 0.40631043910980225, "learning_rate": 2.5359821798401362e-05, "loss": 4.3281, "step": 16220 }, { "epoch": 0.49544899205864384, "grad_norm": 0.4065723717212677, "learning_rate": 2.5357423150414673e-05, "loss": 4.3213, "step": 16221 }, { "epoch": 0.49547953573610265, "grad_norm": 0.3907836973667145, "learning_rate": 2.5355024499137e-05, "loss": 4.3081, "step": 16222 }, { "epoch": 0.4955100794135614, "grad_norm": 0.39493879675865173, "learning_rate": 2.535262584459044e-05, "loss": 4.358, "step": 16223 }, { "epoch": 0.49554062309102015, "grad_norm": 0.39471596479415894, "learning_rate": 2.5350227186797064e-05, "loss": 4.2642, "step": 16224 }, { "epoch": 0.4955711667684789, "grad_norm": 0.399341881275177, "learning_rate": 2.5347828525778976e-05, "loss": 4.3704, "step": 16225 }, { "epoch": 0.4956017104459377, "grad_norm": 0.39153021574020386, "learning_rate": 2.534542986155825e-05, "loss": 4.3036, "step": 16226 }, { "epoch": 0.49563225412339645, "grad_norm": 0.3970685601234436, "learning_rate": 2.5343031194156973e-05, "loss": 4.3799, "step": 16227 }, { "epoch": 0.4956627978008552, "grad_norm": 0.39959725737571716, "learning_rate": 2.5340632523597228e-05, "loss": 4.3049, "step": 16228 }, { "epoch": 0.495693341478314, "grad_norm": 0.40078485012054443, "learning_rate": 2.5338233849901104e-05, "loss": 4.3021, "step": 16229 }, { "epoch": 0.49572388515577276, "grad_norm": 0.39350759983062744, "learning_rate": 2.5335835173090693e-05, "loss": 4.2761, "step": 16230 }, { "epoch": 0.4957544288332315, "grad_norm": 0.3966679871082306, "learning_rate": 2.5333436493188073e-05, "loss": 4.2944, "step": 16231 }, { "epoch": 0.4957849725106903, "grad_norm": 0.3968333601951599, "learning_rate": 2.5331037810215325e-05, "loss": 4.3313, "step": 16232 }, { "epoch": 0.49581551618814906, "grad_norm": 0.4005744457244873, "learning_rate": 2.5328639124194553e-05, "loss": 4.3261, "step": 16233 }, { "epoch": 0.4958460598656078, "grad_norm": 0.39369550347328186, "learning_rate": 2.5326240435147826e-05, "loss": 4.3206, "step": 16234 }, { "epoch": 0.49587660354306656, "grad_norm": 0.39758428931236267, "learning_rate": 2.5323841743097236e-05, "loss": 4.3171, "step": 16235 }, { "epoch": 0.49590714722052537, "grad_norm": 0.4025009572505951, "learning_rate": 2.5321443048064863e-05, "loss": 4.2338, "step": 16236 }, { "epoch": 0.4959376908979841, "grad_norm": 0.410427451133728, "learning_rate": 2.5319044350072808e-05, "loss": 4.169, "step": 16237 }, { "epoch": 0.49596823457544287, "grad_norm": 0.390866756439209, "learning_rate": 2.531664564914314e-05, "loss": 4.2877, "step": 16238 }, { "epoch": 0.4959987782529017, "grad_norm": 0.38579443097114563, "learning_rate": 2.5314246945297952e-05, "loss": 4.3367, "step": 16239 }, { "epoch": 0.4960293219303604, "grad_norm": 0.3897685706615448, "learning_rate": 2.5311848238559337e-05, "loss": 4.2653, "step": 16240 }, { "epoch": 0.4960598656078192, "grad_norm": 0.38441571593284607, "learning_rate": 2.530944952894937e-05, "loss": 4.3198, "step": 16241 }, { "epoch": 0.4960904092852779, "grad_norm": 0.3983882963657379, "learning_rate": 2.5307050816490152e-05, "loss": 4.278, "step": 16242 }, { "epoch": 0.4961209529627367, "grad_norm": 0.39686521887779236, "learning_rate": 2.5304652101203748e-05, "loss": 4.3265, "step": 16243 }, { "epoch": 0.4961514966401955, "grad_norm": 0.3933878540992737, "learning_rate": 2.530225338311226e-05, "loss": 4.2961, "step": 16244 }, { "epoch": 0.4961820403176542, "grad_norm": 0.3819285035133362, "learning_rate": 2.529985466223777e-05, "loss": 4.2772, "step": 16245 }, { "epoch": 0.49621258399511303, "grad_norm": 0.38403162360191345, "learning_rate": 2.529745593860236e-05, "loss": 4.3625, "step": 16246 }, { "epoch": 0.4962431276725718, "grad_norm": 0.3833772540092468, "learning_rate": 2.5295057212228123e-05, "loss": 4.2778, "step": 16247 }, { "epoch": 0.49627367135003053, "grad_norm": 0.38403403759002686, "learning_rate": 2.5292658483137145e-05, "loss": 4.2659, "step": 16248 }, { "epoch": 0.49630421502748934, "grad_norm": 0.38526391983032227, "learning_rate": 2.5290259751351508e-05, "loss": 4.1164, "step": 16249 }, { "epoch": 0.4963347587049481, "grad_norm": 0.3865146040916443, "learning_rate": 2.52878610168933e-05, "loss": 4.306, "step": 16250 }, { "epoch": 0.49636530238240684, "grad_norm": 0.3975764811038971, "learning_rate": 2.5285462279784605e-05, "loss": 4.3391, "step": 16251 }, { "epoch": 0.4963958460598656, "grad_norm": 0.40544721484184265, "learning_rate": 2.528306354004752e-05, "loss": 4.2314, "step": 16252 }, { "epoch": 0.4964263897373244, "grad_norm": 0.3903459906578064, "learning_rate": 2.528066479770411e-05, "loss": 4.2747, "step": 16253 }, { "epoch": 0.49645693341478314, "grad_norm": 0.3882940113544464, "learning_rate": 2.5278266052776484e-05, "loss": 4.3176, "step": 16254 }, { "epoch": 0.4964874770922419, "grad_norm": 0.3993445634841919, "learning_rate": 2.527586730528672e-05, "loss": 4.2754, "step": 16255 }, { "epoch": 0.4965180207697007, "grad_norm": 0.3927234709262848, "learning_rate": 2.52734685552569e-05, "loss": 4.3185, "step": 16256 }, { "epoch": 0.49654856444715945, "grad_norm": 0.39459776878356934, "learning_rate": 2.5271069802709117e-05, "loss": 4.2874, "step": 16257 }, { "epoch": 0.4965791081246182, "grad_norm": 0.3851073980331421, "learning_rate": 2.526867104766546e-05, "loss": 4.2901, "step": 16258 }, { "epoch": 0.49660965180207695, "grad_norm": 0.3931562304496765, "learning_rate": 2.5266272290148e-05, "loss": 4.3127, "step": 16259 }, { "epoch": 0.49664019547953575, "grad_norm": 0.39660006761550903, "learning_rate": 2.526387353017884e-05, "loss": 4.2759, "step": 16260 }, { "epoch": 0.4966707391569945, "grad_norm": 0.40512439608573914, "learning_rate": 2.5261474767780056e-05, "loss": 4.2, "step": 16261 }, { "epoch": 0.49670128283445325, "grad_norm": 0.3985084891319275, "learning_rate": 2.5259076002973747e-05, "loss": 4.2858, "step": 16262 }, { "epoch": 0.49673182651191206, "grad_norm": 0.3928777873516083, "learning_rate": 2.5256677235781984e-05, "loss": 4.1986, "step": 16263 }, { "epoch": 0.4967623701893708, "grad_norm": 0.39070987701416016, "learning_rate": 2.5254278466226866e-05, "loss": 4.3476, "step": 16264 }, { "epoch": 0.49679291386682956, "grad_norm": 0.39836809039115906, "learning_rate": 2.525187969433048e-05, "loss": 4.3169, "step": 16265 }, { "epoch": 0.4968234575442883, "grad_norm": 0.3965975344181061, "learning_rate": 2.524948092011491e-05, "loss": 4.2838, "step": 16266 }, { "epoch": 0.4968540012217471, "grad_norm": 0.39102277159690857, "learning_rate": 2.5247082143602224e-05, "loss": 4.2705, "step": 16267 }, { "epoch": 0.49688454489920586, "grad_norm": 0.3886418044567108, "learning_rate": 2.5244683364814542e-05, "loss": 4.3955, "step": 16268 }, { "epoch": 0.4969150885766646, "grad_norm": 0.39040470123291016, "learning_rate": 2.5242284583773928e-05, "loss": 4.3473, "step": 16269 }, { "epoch": 0.4969456322541234, "grad_norm": 0.3917366862297058, "learning_rate": 2.523988580050247e-05, "loss": 4.2628, "step": 16270 }, { "epoch": 0.49697617593158216, "grad_norm": 0.4014611840248108, "learning_rate": 2.5237487015022266e-05, "loss": 4.3509, "step": 16271 }, { "epoch": 0.4970067196090409, "grad_norm": 0.3848678469657898, "learning_rate": 2.5235088227355395e-05, "loss": 4.3263, "step": 16272 }, { "epoch": 0.4970372632864997, "grad_norm": 0.3796590268611908, "learning_rate": 2.5232689437523955e-05, "loss": 4.2374, "step": 16273 }, { "epoch": 0.49706780696395847, "grad_norm": 0.39443889260292053, "learning_rate": 2.5230290645550014e-05, "loss": 4.4164, "step": 16274 }, { "epoch": 0.4970983506414172, "grad_norm": 0.381660133600235, "learning_rate": 2.522789185145567e-05, "loss": 4.2939, "step": 16275 }, { "epoch": 0.49712889431887597, "grad_norm": 0.38813433051109314, "learning_rate": 2.522549305526301e-05, "loss": 4.2451, "step": 16276 }, { "epoch": 0.4971594379963348, "grad_norm": 0.3882502019405365, "learning_rate": 2.522309425699412e-05, "loss": 4.3038, "step": 16277 }, { "epoch": 0.4971899816737935, "grad_norm": 0.39704084396362305, "learning_rate": 2.5220695456671085e-05, "loss": 4.2066, "step": 16278 }, { "epoch": 0.4972205253512523, "grad_norm": 0.3912200927734375, "learning_rate": 2.5218296654315992e-05, "loss": 4.2863, "step": 16279 }, { "epoch": 0.4972510690287111, "grad_norm": 0.3936383128166199, "learning_rate": 2.5215897849950937e-05, "loss": 4.3422, "step": 16280 }, { "epoch": 0.49728161270616983, "grad_norm": 0.3943866491317749, "learning_rate": 2.5213499043597994e-05, "loss": 4.2841, "step": 16281 }, { "epoch": 0.4973121563836286, "grad_norm": 0.40183743834495544, "learning_rate": 2.5211100235279257e-05, "loss": 4.3216, "step": 16282 }, { "epoch": 0.49734270006108733, "grad_norm": 0.3892087936401367, "learning_rate": 2.5208701425016807e-05, "loss": 4.3096, "step": 16283 }, { "epoch": 0.49737324373854613, "grad_norm": 0.38853099942207336, "learning_rate": 2.5206302612832737e-05, "loss": 4.2653, "step": 16284 }, { "epoch": 0.4974037874160049, "grad_norm": 0.3980344831943512, "learning_rate": 2.5203903798749134e-05, "loss": 4.3758, "step": 16285 }, { "epoch": 0.49743433109346363, "grad_norm": 0.4013378620147705, "learning_rate": 2.5201504982788087e-05, "loss": 4.2731, "step": 16286 }, { "epoch": 0.49746487477092244, "grad_norm": 0.3977729380130768, "learning_rate": 2.519910616497167e-05, "loss": 4.2257, "step": 16287 }, { "epoch": 0.4974954184483812, "grad_norm": 0.38557490706443787, "learning_rate": 2.5196707345321995e-05, "loss": 4.2887, "step": 16288 }, { "epoch": 0.49752596212583994, "grad_norm": 0.3906026780605316, "learning_rate": 2.5194308523861125e-05, "loss": 4.2908, "step": 16289 }, { "epoch": 0.49755650580329874, "grad_norm": 0.3900163769721985, "learning_rate": 2.5191909700611156e-05, "loss": 4.2093, "step": 16290 }, { "epoch": 0.4975870494807575, "grad_norm": 0.3820274770259857, "learning_rate": 2.518951087559418e-05, "loss": 4.2207, "step": 16291 }, { "epoch": 0.49761759315821624, "grad_norm": 0.40238887071609497, "learning_rate": 2.5187112048832277e-05, "loss": 4.2627, "step": 16292 }, { "epoch": 0.497648136835675, "grad_norm": 0.3983149826526642, "learning_rate": 2.518471322034754e-05, "loss": 4.3518, "step": 16293 }, { "epoch": 0.4976786805131338, "grad_norm": 0.4135679006576538, "learning_rate": 2.5182314390162047e-05, "loss": 4.3364, "step": 16294 }, { "epoch": 0.49770922419059255, "grad_norm": 0.4035440981388092, "learning_rate": 2.51799155582979e-05, "loss": 4.3524, "step": 16295 }, { "epoch": 0.4977397678680513, "grad_norm": 0.4033554792404175, "learning_rate": 2.5177516724777173e-05, "loss": 4.3991, "step": 16296 }, { "epoch": 0.4977703115455101, "grad_norm": 0.39398902654647827, "learning_rate": 2.5175117889621962e-05, "loss": 4.2749, "step": 16297 }, { "epoch": 0.49780085522296885, "grad_norm": 0.42069247364997864, "learning_rate": 2.517271905285435e-05, "loss": 4.3408, "step": 16298 }, { "epoch": 0.4978313989004276, "grad_norm": 0.3909655213356018, "learning_rate": 2.5170320214496423e-05, "loss": 4.2338, "step": 16299 }, { "epoch": 0.49786194257788635, "grad_norm": 0.39961323142051697, "learning_rate": 2.516792137457027e-05, "loss": 4.3583, "step": 16300 }, { "epoch": 0.49789248625534516, "grad_norm": 0.38434794545173645, "learning_rate": 2.5165522533097975e-05, "loss": 4.3298, "step": 16301 }, { "epoch": 0.4979230299328039, "grad_norm": 0.3897586762905121, "learning_rate": 2.516312369010163e-05, "loss": 4.2102, "step": 16302 }, { "epoch": 0.49795357361026266, "grad_norm": 0.41830840706825256, "learning_rate": 2.516072484560333e-05, "loss": 4.2663, "step": 16303 }, { "epoch": 0.49798411728772146, "grad_norm": 0.3898344933986664, "learning_rate": 2.5158325999625148e-05, "loss": 4.3839, "step": 16304 }, { "epoch": 0.4980146609651802, "grad_norm": 0.3962806761264801, "learning_rate": 2.5155927152189172e-05, "loss": 4.1992, "step": 16305 }, { "epoch": 0.49804520464263896, "grad_norm": 0.3887242376804352, "learning_rate": 2.5153528303317503e-05, "loss": 4.3333, "step": 16306 }, { "epoch": 0.49807574832009777, "grad_norm": 0.3895359933376312, "learning_rate": 2.5151129453032214e-05, "loss": 4.2448, "step": 16307 }, { "epoch": 0.4981062919975565, "grad_norm": 0.3831447660923004, "learning_rate": 2.5148730601355402e-05, "loss": 4.3416, "step": 16308 }, { "epoch": 0.49813683567501527, "grad_norm": 0.38712525367736816, "learning_rate": 2.5146331748309148e-05, "loss": 4.4056, "step": 16309 }, { "epoch": 0.498167379352474, "grad_norm": 0.4040777087211609, "learning_rate": 2.5143932893915546e-05, "loss": 4.2452, "step": 16310 }, { "epoch": 0.4981979230299328, "grad_norm": 0.39067527651786804, "learning_rate": 2.514153403819668e-05, "loss": 4.2613, "step": 16311 }, { "epoch": 0.49822846670739157, "grad_norm": 0.3953768014907837, "learning_rate": 2.5139135181174632e-05, "loss": 4.3676, "step": 16312 }, { "epoch": 0.4982590103848503, "grad_norm": 0.38170507550239563, "learning_rate": 2.51367363228715e-05, "loss": 4.2724, "step": 16313 }, { "epoch": 0.4982895540623091, "grad_norm": 0.3814541697502136, "learning_rate": 2.513433746330936e-05, "loss": 4.2921, "step": 16314 }, { "epoch": 0.4983200977397679, "grad_norm": 0.3961137533187866, "learning_rate": 2.5131938602510314e-05, "loss": 4.2435, "step": 16315 }, { "epoch": 0.4983506414172266, "grad_norm": 0.38845574855804443, "learning_rate": 2.5129539740496437e-05, "loss": 4.3294, "step": 16316 }, { "epoch": 0.4983811850946854, "grad_norm": 0.3912668824195862, "learning_rate": 2.5127140877289823e-05, "loss": 4.2118, "step": 16317 }, { "epoch": 0.4984117287721442, "grad_norm": 0.40530022978782654, "learning_rate": 2.512474201291255e-05, "loss": 4.219, "step": 16318 }, { "epoch": 0.49844227244960293, "grad_norm": 0.4375171363353729, "learning_rate": 2.5122343147386724e-05, "loss": 4.3423, "step": 16319 }, { "epoch": 0.4984728161270617, "grad_norm": 0.3963235914707184, "learning_rate": 2.511994428073442e-05, "loss": 4.285, "step": 16320 }, { "epoch": 0.4985033598045205, "grad_norm": 0.4279894530773163, "learning_rate": 2.511754541297772e-05, "loss": 4.2498, "step": 16321 }, { "epoch": 0.49853390348197923, "grad_norm": 0.39722058176994324, "learning_rate": 2.5115146544138728e-05, "loss": 4.3633, "step": 16322 }, { "epoch": 0.498564447159438, "grad_norm": 0.3977246880531311, "learning_rate": 2.5112747674239516e-05, "loss": 4.3578, "step": 16323 }, { "epoch": 0.4985949908368968, "grad_norm": 0.3963385820388794, "learning_rate": 2.5110348803302175e-05, "loss": 4.3664, "step": 16324 }, { "epoch": 0.49862553451435554, "grad_norm": 0.3931380808353424, "learning_rate": 2.5107949931348807e-05, "loss": 4.3163, "step": 16325 }, { "epoch": 0.4986560781918143, "grad_norm": 0.3990595042705536, "learning_rate": 2.5105551058401483e-05, "loss": 4.2314, "step": 16326 }, { "epoch": 0.49868662186927304, "grad_norm": 0.39886146783828735, "learning_rate": 2.510315218448229e-05, "loss": 4.2715, "step": 16327 }, { "epoch": 0.49871716554673184, "grad_norm": 0.39618512988090515, "learning_rate": 2.5100753309613334e-05, "loss": 4.3476, "step": 16328 }, { "epoch": 0.4987477092241906, "grad_norm": 0.3931339681148529, "learning_rate": 2.5098354433816683e-05, "loss": 4.2718, "step": 16329 }, { "epoch": 0.49877825290164934, "grad_norm": 0.4092642068862915, "learning_rate": 2.5095955557114435e-05, "loss": 4.4145, "step": 16330 }, { "epoch": 0.49880879657910815, "grad_norm": 0.39272743463516235, "learning_rate": 2.5093556679528668e-05, "loss": 4.2832, "step": 16331 }, { "epoch": 0.4988393402565669, "grad_norm": 0.3959715664386749, "learning_rate": 2.509115780108148e-05, "loss": 4.308, "step": 16332 }, { "epoch": 0.49886988393402565, "grad_norm": 0.3950578272342682, "learning_rate": 2.5088758921794963e-05, "loss": 4.321, "step": 16333 }, { "epoch": 0.4989004276114844, "grad_norm": 0.395413339138031, "learning_rate": 2.5086360041691187e-05, "loss": 4.2552, "step": 16334 }, { "epoch": 0.4989309712889432, "grad_norm": 0.39390817284584045, "learning_rate": 2.5083961160792257e-05, "loss": 4.2917, "step": 16335 }, { "epoch": 0.49896151496640195, "grad_norm": 0.39718523621559143, "learning_rate": 2.5081562279120253e-05, "loss": 4.2605, "step": 16336 }, { "epoch": 0.4989920586438607, "grad_norm": 0.39034155011177063, "learning_rate": 2.507916339669726e-05, "loss": 4.352, "step": 16337 }, { "epoch": 0.4990226023213195, "grad_norm": 0.38533899188041687, "learning_rate": 2.5076764513545364e-05, "loss": 4.301, "step": 16338 }, { "epoch": 0.49905314599877826, "grad_norm": 0.3793961703777313, "learning_rate": 2.5074365629686664e-05, "loss": 4.2993, "step": 16339 }, { "epoch": 0.499083689676237, "grad_norm": 0.4012499451637268, "learning_rate": 2.507196674514324e-05, "loss": 4.3967, "step": 16340 }, { "epoch": 0.49911423335369576, "grad_norm": 0.3855135142803192, "learning_rate": 2.5069567859937184e-05, "loss": 4.31, "step": 16341 }, { "epoch": 0.49914477703115456, "grad_norm": 0.3931320309638977, "learning_rate": 2.506716897409057e-05, "loss": 4.2892, "step": 16342 }, { "epoch": 0.4991753207086133, "grad_norm": 0.3835207223892212, "learning_rate": 2.506477008762551e-05, "loss": 4.2708, "step": 16343 }, { "epoch": 0.49920586438607206, "grad_norm": 0.3903816342353821, "learning_rate": 2.5062371200564076e-05, "loss": 4.3439, "step": 16344 }, { "epoch": 0.49923640806353087, "grad_norm": 0.38224852085113525, "learning_rate": 2.5059972312928354e-05, "loss": 4.3345, "step": 16345 }, { "epoch": 0.4992669517409896, "grad_norm": 0.3979294002056122, "learning_rate": 2.5057573424740438e-05, "loss": 4.3654, "step": 16346 }, { "epoch": 0.49929749541844837, "grad_norm": 0.39547228813171387, "learning_rate": 2.5055174536022414e-05, "loss": 4.2379, "step": 16347 }, { "epoch": 0.4993280390959072, "grad_norm": 0.3989923298358917, "learning_rate": 2.505277564679636e-05, "loss": 4.3006, "step": 16348 }, { "epoch": 0.4993585827733659, "grad_norm": 0.4026157557964325, "learning_rate": 2.505037675708439e-05, "loss": 4.2705, "step": 16349 }, { "epoch": 0.49938912645082467, "grad_norm": 0.39307835698127747, "learning_rate": 2.5047977866908567e-05, "loss": 4.1691, "step": 16350 }, { "epoch": 0.4994196701282834, "grad_norm": 0.38310492038726807, "learning_rate": 2.504557897629099e-05, "loss": 4.3166, "step": 16351 }, { "epoch": 0.4994502138057422, "grad_norm": 0.39901992678642273, "learning_rate": 2.5043180085253744e-05, "loss": 4.2771, "step": 16352 }, { "epoch": 0.499480757483201, "grad_norm": 0.3834623396396637, "learning_rate": 2.5040781193818913e-05, "loss": 4.379, "step": 16353 }, { "epoch": 0.4995113011606597, "grad_norm": 0.3885561525821686, "learning_rate": 2.5038382302008596e-05, "loss": 4.3268, "step": 16354 }, { "epoch": 0.49954184483811853, "grad_norm": 0.39249780774116516, "learning_rate": 2.503598340984486e-05, "loss": 4.2498, "step": 16355 }, { "epoch": 0.4995723885155773, "grad_norm": 0.40019840002059937, "learning_rate": 2.5033584517349818e-05, "loss": 4.3545, "step": 16356 }, { "epoch": 0.49960293219303603, "grad_norm": 0.4018455743789673, "learning_rate": 2.5031185624545538e-05, "loss": 4.2982, "step": 16357 }, { "epoch": 0.4996334758704948, "grad_norm": 0.39469438791275024, "learning_rate": 2.5028786731454124e-05, "loss": 4.2864, "step": 16358 }, { "epoch": 0.4996640195479536, "grad_norm": 0.3955739140510559, "learning_rate": 2.5026387838097654e-05, "loss": 4.2923, "step": 16359 }, { "epoch": 0.49969456322541234, "grad_norm": 0.3975728452205658, "learning_rate": 2.5023988944498216e-05, "loss": 4.24, "step": 16360 }, { "epoch": 0.4997251069028711, "grad_norm": 0.39444559812545776, "learning_rate": 2.5021590050677897e-05, "loss": 4.3338, "step": 16361 }, { "epoch": 0.4997556505803299, "grad_norm": 0.390758216381073, "learning_rate": 2.5019191156658782e-05, "loss": 4.256, "step": 16362 }, { "epoch": 0.49978619425778864, "grad_norm": 0.39176145195961, "learning_rate": 2.5016792262462973e-05, "loss": 4.0926, "step": 16363 }, { "epoch": 0.4998167379352474, "grad_norm": 0.3873123526573181, "learning_rate": 2.501439336811255e-05, "loss": 4.3436, "step": 16364 }, { "epoch": 0.4998472816127062, "grad_norm": 0.40656864643096924, "learning_rate": 2.5011994473629596e-05, "loss": 4.2306, "step": 16365 }, { "epoch": 0.49987782529016495, "grad_norm": 0.38004764914512634, "learning_rate": 2.500959557903621e-05, "loss": 4.2257, "step": 16366 }, { "epoch": 0.4999083689676237, "grad_norm": 0.3987904489040375, "learning_rate": 2.500719668435447e-05, "loss": 4.288, "step": 16367 }, { "epoch": 0.49993891264508244, "grad_norm": 0.3873579800128937, "learning_rate": 2.500479778960646e-05, "loss": 4.3117, "step": 16368 }, { "epoch": 0.49996945632254125, "grad_norm": 0.4005345106124878, "learning_rate": 2.5002398894814273e-05, "loss": 4.3753, "step": 16369 }, { "epoch": 0.5, "grad_norm": 0.4038325548171997, "learning_rate": 2.5e-05, "loss": 4.2874, "step": 16370 }, { "epoch": 0.5000305436774588, "grad_norm": 0.3903076648712158, "learning_rate": 2.499760110518573e-05, "loss": 4.3387, "step": 16371 }, { "epoch": 0.5000610873549175, "grad_norm": 0.39815405011177063, "learning_rate": 2.499520221039355e-05, "loss": 4.2863, "step": 16372 }, { "epoch": 0.5000916310323763, "grad_norm": 0.4060390293598175, "learning_rate": 2.499280331564554e-05, "loss": 4.1325, "step": 16373 }, { "epoch": 0.5001221747098351, "grad_norm": 0.3848831355571747, "learning_rate": 2.49904044209638e-05, "loss": 4.2846, "step": 16374 }, { "epoch": 0.5001527183872938, "grad_norm": 0.387584388256073, "learning_rate": 2.4988005526370413e-05, "loss": 4.3359, "step": 16375 }, { "epoch": 0.5001832620647526, "grad_norm": 0.4040386378765106, "learning_rate": 2.4985606631887453e-05, "loss": 4.3049, "step": 16376 }, { "epoch": 0.5002138057422114, "grad_norm": 0.3994768559932709, "learning_rate": 2.4983207737537023e-05, "loss": 4.2355, "step": 16377 }, { "epoch": 0.5002443494196701, "grad_norm": 0.3952573239803314, "learning_rate": 2.498080884334122e-05, "loss": 4.3525, "step": 16378 }, { "epoch": 0.5002748930971289, "grad_norm": 0.404073566198349, "learning_rate": 2.4978409949322105e-05, "loss": 4.3538, "step": 16379 }, { "epoch": 0.5003054367745876, "grad_norm": 0.3837433159351349, "learning_rate": 2.4976011055501796e-05, "loss": 4.2774, "step": 16380 }, { "epoch": 0.5003359804520464, "grad_norm": 0.3899146020412445, "learning_rate": 2.4973612161902356e-05, "loss": 4.3232, "step": 16381 }, { "epoch": 0.5003665241295052, "grad_norm": 0.3811289370059967, "learning_rate": 2.497121326854588e-05, "loss": 4.2711, "step": 16382 }, { "epoch": 0.5003970678069639, "grad_norm": 0.39311152696609497, "learning_rate": 2.4968814375454468e-05, "loss": 4.2479, "step": 16383 }, { "epoch": 0.5004276114844227, "grad_norm": 0.3947369158267975, "learning_rate": 2.496641548265019e-05, "loss": 4.2672, "step": 16384 }, { "epoch": 0.5004581551618815, "grad_norm": 0.3794077932834625, "learning_rate": 2.496401659015514e-05, "loss": 4.2729, "step": 16385 }, { "epoch": 0.5004886988393402, "grad_norm": 0.3940161466598511, "learning_rate": 2.496161769799142e-05, "loss": 4.2511, "step": 16386 }, { "epoch": 0.500519242516799, "grad_norm": 0.38809704780578613, "learning_rate": 2.4959218806181093e-05, "loss": 4.2361, "step": 16387 }, { "epoch": 0.5005497861942578, "grad_norm": 0.39218002557754517, "learning_rate": 2.495681991474626e-05, "loss": 4.3111, "step": 16388 }, { "epoch": 0.5005803298717165, "grad_norm": 0.3891999125480652, "learning_rate": 2.4954421023709015e-05, "loss": 4.3174, "step": 16389 }, { "epoch": 0.5006108735491753, "grad_norm": 0.3865351378917694, "learning_rate": 2.495202213309144e-05, "loss": 4.2609, "step": 16390 }, { "epoch": 0.5006414172266341, "grad_norm": 0.3985934257507324, "learning_rate": 2.4949623242915614e-05, "loss": 4.2432, "step": 16391 }, { "epoch": 0.5006719609040928, "grad_norm": 0.4016825258731842, "learning_rate": 2.494722435320364e-05, "loss": 4.2569, "step": 16392 }, { "epoch": 0.5007025045815516, "grad_norm": 0.39239534735679626, "learning_rate": 2.494482546397759e-05, "loss": 4.2842, "step": 16393 }, { "epoch": 0.5007330482590104, "grad_norm": 0.3996763527393341, "learning_rate": 2.4942426575259565e-05, "loss": 4.2757, "step": 16394 }, { "epoch": 0.5007635919364691, "grad_norm": 0.4061809778213501, "learning_rate": 2.4940027687071655e-05, "loss": 4.2848, "step": 16395 }, { "epoch": 0.5007941356139279, "grad_norm": 0.40799811482429504, "learning_rate": 2.4937628799435926e-05, "loss": 4.2406, "step": 16396 }, { "epoch": 0.5008246792913866, "grad_norm": 0.3906305432319641, "learning_rate": 2.4935229912374496e-05, "loss": 4.3467, "step": 16397 }, { "epoch": 0.5008552229688454, "grad_norm": 0.39399126172065735, "learning_rate": 2.4932831025909434e-05, "loss": 4.2814, "step": 16398 }, { "epoch": 0.5008857666463042, "grad_norm": 0.40811261534690857, "learning_rate": 2.4930432140062822e-05, "loss": 4.3093, "step": 16399 }, { "epoch": 0.5009163103237629, "grad_norm": 0.4038730561733246, "learning_rate": 2.4928033254856774e-05, "loss": 4.3218, "step": 16400 }, { "epoch": 0.5009468540012217, "grad_norm": 0.3938544690608978, "learning_rate": 2.4925634370313342e-05, "loss": 4.3452, "step": 16401 }, { "epoch": 0.5009773976786805, "grad_norm": 0.3845721483230591, "learning_rate": 2.4923235486454638e-05, "loss": 4.3484, "step": 16402 }, { "epoch": 0.5010079413561392, "grad_norm": 0.38618242740631104, "learning_rate": 2.4920836603302753e-05, "loss": 4.3371, "step": 16403 }, { "epoch": 0.501038485033598, "grad_norm": 0.39483359456062317, "learning_rate": 2.4918437720879756e-05, "loss": 4.3684, "step": 16404 }, { "epoch": 0.5010690287110569, "grad_norm": 0.390168696641922, "learning_rate": 2.491603883920775e-05, "loss": 4.3459, "step": 16405 }, { "epoch": 0.5010995723885155, "grad_norm": 0.38769546151161194, "learning_rate": 2.4913639958308816e-05, "loss": 4.2421, "step": 16406 }, { "epoch": 0.5011301160659744, "grad_norm": 0.40764328837394714, "learning_rate": 2.4911241078205043e-05, "loss": 4.2727, "step": 16407 }, { "epoch": 0.5011606597434332, "grad_norm": 0.3901675045490265, "learning_rate": 2.4908842198918518e-05, "loss": 4.4052, "step": 16408 }, { "epoch": 0.5011912034208919, "grad_norm": 0.5034430623054504, "learning_rate": 2.4906443320471338e-05, "loss": 4.393, "step": 16409 }, { "epoch": 0.5012217470983507, "grad_norm": 0.38575974106788635, "learning_rate": 2.490404444288557e-05, "loss": 4.2865, "step": 16410 }, { "epoch": 0.5012522907758095, "grad_norm": 0.38245880603790283, "learning_rate": 2.4901645566183316e-05, "loss": 4.3046, "step": 16411 }, { "epoch": 0.5012828344532682, "grad_norm": 0.39101749658584595, "learning_rate": 2.489924669038667e-05, "loss": 4.3538, "step": 16412 }, { "epoch": 0.501313378130727, "grad_norm": 0.3934672176837921, "learning_rate": 2.489684781551771e-05, "loss": 4.2866, "step": 16413 }, { "epoch": 0.5013439218081857, "grad_norm": 0.39866313338279724, "learning_rate": 2.4894448941598526e-05, "loss": 4.2976, "step": 16414 }, { "epoch": 0.5013744654856445, "grad_norm": 0.38957637548446655, "learning_rate": 2.4892050068651202e-05, "loss": 4.268, "step": 16415 }, { "epoch": 0.5014050091631033, "grad_norm": 0.400167316198349, "learning_rate": 2.488965119669782e-05, "loss": 4.2049, "step": 16416 }, { "epoch": 0.501435552840562, "grad_norm": 0.40247657895088196, "learning_rate": 2.4887252325760493e-05, "loss": 4.3046, "step": 16417 }, { "epoch": 0.5014660965180208, "grad_norm": 0.3946249783039093, "learning_rate": 2.4884853455861278e-05, "loss": 4.3514, "step": 16418 }, { "epoch": 0.5014966401954796, "grad_norm": 0.387821227312088, "learning_rate": 2.4882454587022278e-05, "loss": 4.3515, "step": 16419 }, { "epoch": 0.5015271838729383, "grad_norm": 0.39411935210227966, "learning_rate": 2.488005571926559e-05, "loss": 4.3087, "step": 16420 }, { "epoch": 0.5015577275503971, "grad_norm": 0.38051703572273254, "learning_rate": 2.4877656852613282e-05, "loss": 4.1142, "step": 16421 }, { "epoch": 0.5015882712278559, "grad_norm": 0.39085710048675537, "learning_rate": 2.4875257987087448e-05, "loss": 4.306, "step": 16422 }, { "epoch": 0.5016188149053146, "grad_norm": 0.3925432860851288, "learning_rate": 2.4872859122710186e-05, "loss": 4.2043, "step": 16423 }, { "epoch": 0.5016493585827734, "grad_norm": 0.39292001724243164, "learning_rate": 2.4870460259503565e-05, "loss": 4.3534, "step": 16424 }, { "epoch": 0.5016799022602322, "grad_norm": 0.3958616554737091, "learning_rate": 2.4868061397489685e-05, "loss": 4.2228, "step": 16425 }, { "epoch": 0.5017104459376909, "grad_norm": 0.39020130038261414, "learning_rate": 2.4865662536690644e-05, "loss": 4.3255, "step": 16426 }, { "epoch": 0.5017409896151497, "grad_norm": 0.405443012714386, "learning_rate": 2.4863263677128504e-05, "loss": 4.297, "step": 16427 }, { "epoch": 0.5017715332926085, "grad_norm": 0.4094003438949585, "learning_rate": 2.486086481882537e-05, "loss": 4.1571, "step": 16428 }, { "epoch": 0.5018020769700672, "grad_norm": 0.3965490162372589, "learning_rate": 2.4858465961803327e-05, "loss": 4.3716, "step": 16429 }, { "epoch": 0.501832620647526, "grad_norm": 0.4128081798553467, "learning_rate": 2.485606710608446e-05, "loss": 4.2917, "step": 16430 }, { "epoch": 0.5018631643249847, "grad_norm": 0.39419257640838623, "learning_rate": 2.485366825169086e-05, "loss": 4.2155, "step": 16431 }, { "epoch": 0.5018937080024435, "grad_norm": 0.383914977312088, "learning_rate": 2.4851269398644607e-05, "loss": 4.3458, "step": 16432 }, { "epoch": 0.5019242516799023, "grad_norm": 0.39111438393592834, "learning_rate": 2.484887054696779e-05, "loss": 4.282, "step": 16433 }, { "epoch": 0.501954795357361, "grad_norm": 0.3922477662563324, "learning_rate": 2.4846471696682506e-05, "loss": 4.3393, "step": 16434 }, { "epoch": 0.5019853390348198, "grad_norm": 0.3987692594528198, "learning_rate": 2.484407284781083e-05, "loss": 4.3186, "step": 16435 }, { "epoch": 0.5020158827122786, "grad_norm": 0.3874969184398651, "learning_rate": 2.4841674000374858e-05, "loss": 4.3189, "step": 16436 }, { "epoch": 0.5020464263897373, "grad_norm": 0.387112557888031, "learning_rate": 2.4839275154396677e-05, "loss": 4.389, "step": 16437 }, { "epoch": 0.5020769700671961, "grad_norm": 0.39434918761253357, "learning_rate": 2.483687630989837e-05, "loss": 4.3157, "step": 16438 }, { "epoch": 0.5021075137446549, "grad_norm": 0.38889434933662415, "learning_rate": 2.4834477466902024e-05, "loss": 4.3147, "step": 16439 }, { "epoch": 0.5021380574221136, "grad_norm": 0.3942722678184509, "learning_rate": 2.483207862542974e-05, "loss": 4.277, "step": 16440 }, { "epoch": 0.5021686010995724, "grad_norm": 0.3847815692424774, "learning_rate": 2.4829679785503586e-05, "loss": 4.3452, "step": 16441 }, { "epoch": 0.5021991447770312, "grad_norm": 0.39061644673347473, "learning_rate": 2.4827280947145652e-05, "loss": 4.2419, "step": 16442 }, { "epoch": 0.5022296884544899, "grad_norm": 0.3844122290611267, "learning_rate": 2.4824882110378043e-05, "loss": 4.239, "step": 16443 }, { "epoch": 0.5022602321319487, "grad_norm": 0.38417336344718933, "learning_rate": 2.4822483275222833e-05, "loss": 4.2832, "step": 16444 }, { "epoch": 0.5022907758094075, "grad_norm": 0.3916752338409424, "learning_rate": 2.48200844417021e-05, "loss": 4.3001, "step": 16445 }, { "epoch": 0.5023213194868662, "grad_norm": 0.3802902400493622, "learning_rate": 2.4817685609837955e-05, "loss": 4.2633, "step": 16446 }, { "epoch": 0.502351863164325, "grad_norm": 0.3895072042942047, "learning_rate": 2.4815286779652463e-05, "loss": 4.1915, "step": 16447 }, { "epoch": 0.5023824068417837, "grad_norm": 0.3930206596851349, "learning_rate": 2.4812887951167732e-05, "loss": 4.3483, "step": 16448 }, { "epoch": 0.5024129505192425, "grad_norm": 0.39535441994667053, "learning_rate": 2.4810489124405825e-05, "loss": 4.3354, "step": 16449 }, { "epoch": 0.5024434941967013, "grad_norm": 0.3967461884021759, "learning_rate": 2.4808090299388843e-05, "loss": 4.1637, "step": 16450 }, { "epoch": 0.50247403787416, "grad_norm": 0.38953208923339844, "learning_rate": 2.480569147613888e-05, "loss": 4.345, "step": 16451 }, { "epoch": 0.5025045815516188, "grad_norm": 0.40401214361190796, "learning_rate": 2.4803292654678008e-05, "loss": 4.332, "step": 16452 }, { "epoch": 0.5025351252290776, "grad_norm": 0.398670494556427, "learning_rate": 2.480089383502833e-05, "loss": 4.2496, "step": 16453 }, { "epoch": 0.5025656689065363, "grad_norm": 0.3933417499065399, "learning_rate": 2.4798495017211926e-05, "loss": 4.3354, "step": 16454 }, { "epoch": 0.5025962125839951, "grad_norm": 0.39712846279144287, "learning_rate": 2.479609620125087e-05, "loss": 4.3442, "step": 16455 }, { "epoch": 0.5026267562614539, "grad_norm": 0.39342889189720154, "learning_rate": 2.4793697387167266e-05, "loss": 4.2874, "step": 16456 }, { "epoch": 0.5026572999389126, "grad_norm": 0.41640955209732056, "learning_rate": 2.4791298574983202e-05, "loss": 4.2651, "step": 16457 }, { "epoch": 0.5026878436163714, "grad_norm": 0.3996852934360504, "learning_rate": 2.4788899764720752e-05, "loss": 4.3064, "step": 16458 }, { "epoch": 0.5027183872938302, "grad_norm": 0.39763760566711426, "learning_rate": 2.4786500956402015e-05, "loss": 4.3606, "step": 16459 }, { "epoch": 0.5027489309712889, "grad_norm": 0.40041518211364746, "learning_rate": 2.4784102150049072e-05, "loss": 4.2413, "step": 16460 }, { "epoch": 0.5027794746487477, "grad_norm": 0.40382057428359985, "learning_rate": 2.4781703345684014e-05, "loss": 4.31, "step": 16461 }, { "epoch": 0.5028100183262064, "grad_norm": 0.39875274896621704, "learning_rate": 2.4779304543328928e-05, "loss": 4.2856, "step": 16462 }, { "epoch": 0.5028405620036652, "grad_norm": 0.40547341108322144, "learning_rate": 2.4776905743005887e-05, "loss": 4.3279, "step": 16463 }, { "epoch": 0.502871105681124, "grad_norm": 0.3816928565502167, "learning_rate": 2.4774506944736993e-05, "loss": 4.171, "step": 16464 }, { "epoch": 0.5029016493585827, "grad_norm": 0.39189380407333374, "learning_rate": 2.477210814854434e-05, "loss": 4.2804, "step": 16465 }, { "epoch": 0.5029321930360415, "grad_norm": 0.3975089192390442, "learning_rate": 2.4769709354449992e-05, "loss": 4.316, "step": 16466 }, { "epoch": 0.5029627367135003, "grad_norm": 0.39330416917800903, "learning_rate": 2.4767310562476054e-05, "loss": 4.3487, "step": 16467 }, { "epoch": 0.502993280390959, "grad_norm": 0.39919957518577576, "learning_rate": 2.4764911772644607e-05, "loss": 4.3458, "step": 16468 }, { "epoch": 0.5030238240684178, "grad_norm": 0.38686397671699524, "learning_rate": 2.4762512984977736e-05, "loss": 4.2533, "step": 16469 }, { "epoch": 0.5030543677458766, "grad_norm": 0.4053928554058075, "learning_rate": 2.4760114199497532e-05, "loss": 4.2233, "step": 16470 }, { "epoch": 0.5030849114233353, "grad_norm": 0.3936421871185303, "learning_rate": 2.4757715416226084e-05, "loss": 4.3684, "step": 16471 }, { "epoch": 0.5031154551007941, "grad_norm": 0.40482765436172485, "learning_rate": 2.4755316635185467e-05, "loss": 4.2945, "step": 16472 }, { "epoch": 0.503145998778253, "grad_norm": 0.3850998878479004, "learning_rate": 2.4752917856397772e-05, "loss": 4.4064, "step": 16473 }, { "epoch": 0.5031765424557116, "grad_norm": 0.4012029469013214, "learning_rate": 2.4750519079885105e-05, "loss": 4.2575, "step": 16474 }, { "epoch": 0.5032070861331704, "grad_norm": 0.39825817942619324, "learning_rate": 2.4748120305669524e-05, "loss": 4.3303, "step": 16475 }, { "epoch": 0.5032376298106293, "grad_norm": 0.38608020544052124, "learning_rate": 2.4745721533773133e-05, "loss": 4.3063, "step": 16476 }, { "epoch": 0.5032681734880879, "grad_norm": 0.39542531967163086, "learning_rate": 2.4743322764218022e-05, "loss": 4.3529, "step": 16477 }, { "epoch": 0.5032987171655467, "grad_norm": 0.39481672644615173, "learning_rate": 2.4740923997026258e-05, "loss": 4.3103, "step": 16478 }, { "epoch": 0.5033292608430054, "grad_norm": 0.40735605359077454, "learning_rate": 2.4738525232219953e-05, "loss": 4.2962, "step": 16479 }, { "epoch": 0.5033598045204642, "grad_norm": 0.39287635684013367, "learning_rate": 2.4736126469821166e-05, "loss": 4.2327, "step": 16480 }, { "epoch": 0.503390348197923, "grad_norm": 0.39722850918769836, "learning_rate": 2.4733727709852e-05, "loss": 4.3526, "step": 16481 }, { "epoch": 0.5034208918753817, "grad_norm": 0.3882203996181488, "learning_rate": 2.4731328952334553e-05, "loss": 4.2646, "step": 16482 }, { "epoch": 0.5034514355528406, "grad_norm": 0.38632187247276306, "learning_rate": 2.4728930197290885e-05, "loss": 4.2321, "step": 16483 }, { "epoch": 0.5034819792302994, "grad_norm": 0.3940429985523224, "learning_rate": 2.4726531444743105e-05, "loss": 4.2781, "step": 16484 }, { "epoch": 0.503512522907758, "grad_norm": 0.4055195450782776, "learning_rate": 2.4724132694713293e-05, "loss": 4.3087, "step": 16485 }, { "epoch": 0.5035430665852169, "grad_norm": 0.383611798286438, "learning_rate": 2.4721733947223522e-05, "loss": 4.255, "step": 16486 }, { "epoch": 0.5035736102626757, "grad_norm": 0.39167216420173645, "learning_rate": 2.471933520229589e-05, "loss": 4.3434, "step": 16487 }, { "epoch": 0.5036041539401344, "grad_norm": 0.38950833678245544, "learning_rate": 2.4716936459952496e-05, "loss": 4.2789, "step": 16488 }, { "epoch": 0.5036346976175932, "grad_norm": 0.38428646326065063, "learning_rate": 2.4714537720215398e-05, "loss": 4.3011, "step": 16489 }, { "epoch": 0.503665241295052, "grad_norm": 0.4071025252342224, "learning_rate": 2.4712138983106707e-05, "loss": 4.3191, "step": 16490 }, { "epoch": 0.5036957849725107, "grad_norm": 0.40740543603897095, "learning_rate": 2.47097402486485e-05, "loss": 4.2791, "step": 16491 }, { "epoch": 0.5037263286499695, "grad_norm": 0.38132810592651367, "learning_rate": 2.470734151686286e-05, "loss": 4.2266, "step": 16492 }, { "epoch": 0.5037568723274283, "grad_norm": 0.3901231288909912, "learning_rate": 2.470494278777188e-05, "loss": 4.3524, "step": 16493 }, { "epoch": 0.503787416004887, "grad_norm": 0.4073294401168823, "learning_rate": 2.4702544061397647e-05, "loss": 4.2737, "step": 16494 }, { "epoch": 0.5038179596823458, "grad_norm": 0.3884488046169281, "learning_rate": 2.4700145337762235e-05, "loss": 4.3317, "step": 16495 }, { "epoch": 0.5038485033598045, "grad_norm": 0.3995975852012634, "learning_rate": 2.469774661688775e-05, "loss": 4.2192, "step": 16496 }, { "epoch": 0.5038790470372633, "grad_norm": 0.3872223198413849, "learning_rate": 2.4695347898796258e-05, "loss": 4.2643, "step": 16497 }, { "epoch": 0.5039095907147221, "grad_norm": 0.4012219309806824, "learning_rate": 2.4692949183509853e-05, "loss": 4.2152, "step": 16498 }, { "epoch": 0.5039401343921808, "grad_norm": 0.3996519148349762, "learning_rate": 2.469055047105063e-05, "loss": 4.2126, "step": 16499 }, { "epoch": 0.5039706780696396, "grad_norm": 0.4053725302219391, "learning_rate": 2.468815176144067e-05, "loss": 4.3044, "step": 16500 }, { "epoch": 0.5040012217470984, "grad_norm": 0.38081756234169006, "learning_rate": 2.468575305470205e-05, "loss": 4.3565, "step": 16501 }, { "epoch": 0.5040317654245571, "grad_norm": 0.3914535641670227, "learning_rate": 2.4683354350856872e-05, "loss": 4.2928, "step": 16502 }, { "epoch": 0.5040623091020159, "grad_norm": 0.40025487542152405, "learning_rate": 2.46809556499272e-05, "loss": 4.2724, "step": 16503 }, { "epoch": 0.5040928527794747, "grad_norm": 0.40178611874580383, "learning_rate": 2.4678556951935136e-05, "loss": 4.2902, "step": 16504 }, { "epoch": 0.5041233964569334, "grad_norm": 0.41288697719573975, "learning_rate": 2.4676158256902773e-05, "loss": 4.3122, "step": 16505 }, { "epoch": 0.5041539401343922, "grad_norm": 0.3931586742401123, "learning_rate": 2.4673759564852176e-05, "loss": 4.2653, "step": 16506 }, { "epoch": 0.504184483811851, "grad_norm": 0.39235159754753113, "learning_rate": 2.4671360875805453e-05, "loss": 4.3385, "step": 16507 }, { "epoch": 0.5042150274893097, "grad_norm": 0.39524489641189575, "learning_rate": 2.466896218978468e-05, "loss": 4.2903, "step": 16508 }, { "epoch": 0.5042455711667685, "grad_norm": 0.387419730424881, "learning_rate": 2.4666563506811936e-05, "loss": 4.2633, "step": 16509 }, { "epoch": 0.5042761148442273, "grad_norm": 0.39591777324676514, "learning_rate": 2.466416482690931e-05, "loss": 4.2778, "step": 16510 }, { "epoch": 0.504306658521686, "grad_norm": 0.39633113145828247, "learning_rate": 2.46617661500989e-05, "loss": 4.3015, "step": 16511 }, { "epoch": 0.5043372021991448, "grad_norm": 0.408617228269577, "learning_rate": 2.4659367476402774e-05, "loss": 4.2986, "step": 16512 }, { "epoch": 0.5043677458766035, "grad_norm": 0.4038684070110321, "learning_rate": 2.4656968805843036e-05, "loss": 4.1742, "step": 16513 }, { "epoch": 0.5043982895540623, "grad_norm": 0.4008390009403229, "learning_rate": 2.4654570138441756e-05, "loss": 4.282, "step": 16514 }, { "epoch": 0.5044288332315211, "grad_norm": 0.3985770046710968, "learning_rate": 2.465217147422103e-05, "loss": 4.2924, "step": 16515 }, { "epoch": 0.5044593769089798, "grad_norm": 0.40416860580444336, "learning_rate": 2.464977281320294e-05, "loss": 4.3023, "step": 16516 }, { "epoch": 0.5044899205864386, "grad_norm": 0.40335744619369507, "learning_rate": 2.464737415540957e-05, "loss": 4.2988, "step": 16517 }, { "epoch": 0.5045204642638974, "grad_norm": 0.40576308965682983, "learning_rate": 2.4644975500863003e-05, "loss": 4.3958, "step": 16518 }, { "epoch": 0.5045510079413561, "grad_norm": 0.39619874954223633, "learning_rate": 2.464257684958534e-05, "loss": 4.3212, "step": 16519 }, { "epoch": 0.5045815516188149, "grad_norm": 0.3860657215118408, "learning_rate": 2.4640178201598644e-05, "loss": 4.3054, "step": 16520 }, { "epoch": 0.5046120952962737, "grad_norm": 0.40438905358314514, "learning_rate": 2.4637779556925016e-05, "loss": 4.2595, "step": 16521 }, { "epoch": 0.5046426389737324, "grad_norm": 0.3870641589164734, "learning_rate": 2.4635380915586542e-05, "loss": 4.4055, "step": 16522 }, { "epoch": 0.5046731826511912, "grad_norm": 0.3995385468006134, "learning_rate": 2.46329822776053e-05, "loss": 4.3392, "step": 16523 }, { "epoch": 0.50470372632865, "grad_norm": 0.39389434456825256, "learning_rate": 2.4630583643003376e-05, "loss": 4.3232, "step": 16524 }, { "epoch": 0.5047342700061087, "grad_norm": 0.3874051570892334, "learning_rate": 2.462818501180287e-05, "loss": 4.298, "step": 16525 }, { "epoch": 0.5047648136835675, "grad_norm": 0.39061954617500305, "learning_rate": 2.4625786384025845e-05, "loss": 4.3615, "step": 16526 }, { "epoch": 0.5047953573610263, "grad_norm": 0.3805510699748993, "learning_rate": 2.4623387759694394e-05, "loss": 4.3111, "step": 16527 }, { "epoch": 0.504825901038485, "grad_norm": 0.4043945074081421, "learning_rate": 2.4620989138830618e-05, "loss": 4.2245, "step": 16528 }, { "epoch": 0.5048564447159438, "grad_norm": 0.39889001846313477, "learning_rate": 2.461859052145658e-05, "loss": 4.2595, "step": 16529 }, { "epoch": 0.5048869883934025, "grad_norm": 0.386116087436676, "learning_rate": 2.4616191907594385e-05, "loss": 4.2002, "step": 16530 }, { "epoch": 0.5049175320708613, "grad_norm": 0.39200231432914734, "learning_rate": 2.4613793297266103e-05, "loss": 4.3224, "step": 16531 }, { "epoch": 0.5049480757483201, "grad_norm": 0.3811894357204437, "learning_rate": 2.4611394690493818e-05, "loss": 4.3339, "step": 16532 }, { "epoch": 0.5049786194257788, "grad_norm": 0.3954848349094391, "learning_rate": 2.4608996087299634e-05, "loss": 4.2435, "step": 16533 }, { "epoch": 0.5050091631032376, "grad_norm": 0.40371814370155334, "learning_rate": 2.4606597487705614e-05, "loss": 4.3559, "step": 16534 }, { "epoch": 0.5050397067806964, "grad_norm": 0.4005235731601715, "learning_rate": 2.4604198891733853e-05, "loss": 4.3096, "step": 16535 }, { "epoch": 0.5050702504581551, "grad_norm": 0.3878074884414673, "learning_rate": 2.4601800299406447e-05, "loss": 4.2511, "step": 16536 }, { "epoch": 0.5051007941356139, "grad_norm": 0.3831508159637451, "learning_rate": 2.459940171074546e-05, "loss": 4.2908, "step": 16537 }, { "epoch": 0.5051313378130727, "grad_norm": 0.3956459164619446, "learning_rate": 2.459700312577299e-05, "loss": 4.2233, "step": 16538 }, { "epoch": 0.5051618814905314, "grad_norm": 0.39836299419403076, "learning_rate": 2.459460454451112e-05, "loss": 4.2558, "step": 16539 }, { "epoch": 0.5051924251679902, "grad_norm": 0.40036994218826294, "learning_rate": 2.459220596698194e-05, "loss": 4.1728, "step": 16540 }, { "epoch": 0.505222968845449, "grad_norm": 0.38229531049728394, "learning_rate": 2.4589807393207516e-05, "loss": 4.259, "step": 16541 }, { "epoch": 0.5052535125229077, "grad_norm": 0.3938654661178589, "learning_rate": 2.4587408823209962e-05, "loss": 4.3291, "step": 16542 }, { "epoch": 0.5052840562003665, "grad_norm": 0.39425429701805115, "learning_rate": 2.4585010257011334e-05, "loss": 4.3465, "step": 16543 }, { "epoch": 0.5053145998778253, "grad_norm": 0.3901579976081848, "learning_rate": 2.458261169463373e-05, "loss": 4.2564, "step": 16544 }, { "epoch": 0.505345143555284, "grad_norm": 0.3943187892436981, "learning_rate": 2.458021313609925e-05, "loss": 4.2776, "step": 16545 }, { "epoch": 0.5053756872327428, "grad_norm": 0.3858257532119751, "learning_rate": 2.4577814581429953e-05, "loss": 4.303, "step": 16546 }, { "epoch": 0.5054062309102015, "grad_norm": 0.40518462657928467, "learning_rate": 2.4575416030647935e-05, "loss": 4.3485, "step": 16547 }, { "epoch": 0.5054367745876603, "grad_norm": 0.3889579176902771, "learning_rate": 2.457301748377528e-05, "loss": 4.3506, "step": 16548 }, { "epoch": 0.5054673182651191, "grad_norm": 0.39757388830184937, "learning_rate": 2.457061894083407e-05, "loss": 4.2142, "step": 16549 }, { "epoch": 0.5054978619425778, "grad_norm": 0.38982918858528137, "learning_rate": 2.45682204018464e-05, "loss": 4.2725, "step": 16550 }, { "epoch": 0.5055284056200366, "grad_norm": 0.3862990736961365, "learning_rate": 2.4565821866834337e-05, "loss": 4.3481, "step": 16551 }, { "epoch": 0.5055589492974955, "grad_norm": 0.3944605886936188, "learning_rate": 2.4563423335819973e-05, "loss": 4.2159, "step": 16552 }, { "epoch": 0.5055894929749541, "grad_norm": 0.39446714520454407, "learning_rate": 2.456102480882541e-05, "loss": 4.2799, "step": 16553 }, { "epoch": 0.505620036652413, "grad_norm": 0.3842567801475525, "learning_rate": 2.4558626285872712e-05, "loss": 4.1725, "step": 16554 }, { "epoch": 0.5056505803298718, "grad_norm": 0.3875161111354828, "learning_rate": 2.4556227766983957e-05, "loss": 4.163, "step": 16555 }, { "epoch": 0.5056811240073305, "grad_norm": 0.39119914174079895, "learning_rate": 2.4553829252181256e-05, "loss": 4.3085, "step": 16556 }, { "epoch": 0.5057116676847893, "grad_norm": 0.40234068036079407, "learning_rate": 2.4551430741486668e-05, "loss": 4.2359, "step": 16557 }, { "epoch": 0.5057422113622481, "grad_norm": 0.3997771143913269, "learning_rate": 2.4549032234922286e-05, "loss": 4.3199, "step": 16558 }, { "epoch": 0.5057727550397068, "grad_norm": 0.4029655158519745, "learning_rate": 2.454663373251021e-05, "loss": 4.2896, "step": 16559 }, { "epoch": 0.5058032987171656, "grad_norm": 0.384340763092041, "learning_rate": 2.4544235234272498e-05, "loss": 4.2654, "step": 16560 }, { "epoch": 0.5058338423946244, "grad_norm": 0.39109504222869873, "learning_rate": 2.454183674023125e-05, "loss": 4.3111, "step": 16561 }, { "epoch": 0.5058643860720831, "grad_norm": 0.38408163189888, "learning_rate": 2.453943825040855e-05, "loss": 4.287, "step": 16562 }, { "epoch": 0.5058949297495419, "grad_norm": 0.3890446424484253, "learning_rate": 2.4537039764826474e-05, "loss": 4.344, "step": 16563 }, { "epoch": 0.5059254734270006, "grad_norm": 0.4170498251914978, "learning_rate": 2.453464128350712e-05, "loss": 4.3774, "step": 16564 }, { "epoch": 0.5059560171044594, "grad_norm": 0.3902972340583801, "learning_rate": 2.453224280647255e-05, "loss": 4.3535, "step": 16565 }, { "epoch": 0.5059865607819182, "grad_norm": 0.3894410729408264, "learning_rate": 2.4529844333744866e-05, "loss": 4.3284, "step": 16566 }, { "epoch": 0.5060171044593769, "grad_norm": 0.4014415740966797, "learning_rate": 2.4527445865346153e-05, "loss": 4.3001, "step": 16567 }, { "epoch": 0.5060476481368357, "grad_norm": 0.397614985704422, "learning_rate": 2.4525047401298483e-05, "loss": 4.2707, "step": 16568 }, { "epoch": 0.5060781918142945, "grad_norm": 0.39453884959220886, "learning_rate": 2.4522648941623945e-05, "loss": 4.2858, "step": 16569 }, { "epoch": 0.5061087354917532, "grad_norm": 0.39327386021614075, "learning_rate": 2.4520250486344627e-05, "loss": 4.2489, "step": 16570 }, { "epoch": 0.506139279169212, "grad_norm": 0.40854647755622864, "learning_rate": 2.4517852035482606e-05, "loss": 4.3111, "step": 16571 }, { "epoch": 0.5061698228466708, "grad_norm": 0.4108431339263916, "learning_rate": 2.4515453589059967e-05, "loss": 4.2829, "step": 16572 }, { "epoch": 0.5062003665241295, "grad_norm": 0.39427319169044495, "learning_rate": 2.4513055147098806e-05, "loss": 4.2006, "step": 16573 }, { "epoch": 0.5062309102015883, "grad_norm": 0.416795015335083, "learning_rate": 2.451065670962119e-05, "loss": 4.2539, "step": 16574 }, { "epoch": 0.5062614538790471, "grad_norm": 0.41383877396583557, "learning_rate": 2.4508258276649203e-05, "loss": 4.2935, "step": 16575 }, { "epoch": 0.5062919975565058, "grad_norm": 0.3848644196987152, "learning_rate": 2.450585984820495e-05, "loss": 4.3344, "step": 16576 }, { "epoch": 0.5063225412339646, "grad_norm": 0.3971449136734009, "learning_rate": 2.450346142431049e-05, "loss": 4.2862, "step": 16577 }, { "epoch": 0.5063530849114234, "grad_norm": 0.3999771475791931, "learning_rate": 2.4501063004987913e-05, "loss": 4.2681, "step": 16578 }, { "epoch": 0.5063836285888821, "grad_norm": 0.38128378987312317, "learning_rate": 2.4498664590259315e-05, "loss": 4.3456, "step": 16579 }, { "epoch": 0.5064141722663409, "grad_norm": 0.3958710730075836, "learning_rate": 2.449626618014676e-05, "loss": 4.2809, "step": 16580 }, { "epoch": 0.5064447159437996, "grad_norm": 0.40304723381996155, "learning_rate": 2.449386777467235e-05, "loss": 4.383, "step": 16581 }, { "epoch": 0.5064752596212584, "grad_norm": 0.4021213948726654, "learning_rate": 2.4491469373858153e-05, "loss": 4.3037, "step": 16582 }, { "epoch": 0.5065058032987172, "grad_norm": 0.4016588032245636, "learning_rate": 2.4489070977726255e-05, "loss": 4.3686, "step": 16583 }, { "epoch": 0.5065363469761759, "grad_norm": 0.39452654123306274, "learning_rate": 2.4486672586298758e-05, "loss": 4.2849, "step": 16584 }, { "epoch": 0.5065668906536347, "grad_norm": 0.40232181549072266, "learning_rate": 2.4484274199597718e-05, "loss": 4.2793, "step": 16585 }, { "epoch": 0.5065974343310935, "grad_norm": 0.38455668091773987, "learning_rate": 2.4481875817645232e-05, "loss": 4.2394, "step": 16586 }, { "epoch": 0.5066279780085522, "grad_norm": 0.3881787061691284, "learning_rate": 2.4479477440463393e-05, "loss": 4.309, "step": 16587 }, { "epoch": 0.506658521686011, "grad_norm": 0.39992398023605347, "learning_rate": 2.447707906807426e-05, "loss": 4.338, "step": 16588 }, { "epoch": 0.5066890653634698, "grad_norm": 0.4017115533351898, "learning_rate": 2.4474680700499927e-05, "loss": 4.3616, "step": 16589 }, { "epoch": 0.5067196090409285, "grad_norm": 0.39811646938323975, "learning_rate": 2.4472282337762492e-05, "loss": 4.3044, "step": 16590 }, { "epoch": 0.5067501527183873, "grad_norm": 0.39270123839378357, "learning_rate": 2.446988397988401e-05, "loss": 4.2715, "step": 16591 }, { "epoch": 0.5067806963958461, "grad_norm": 0.4097326397895813, "learning_rate": 2.446748562688659e-05, "loss": 4.3455, "step": 16592 }, { "epoch": 0.5068112400733048, "grad_norm": 0.3857720196247101, "learning_rate": 2.44650872787923e-05, "loss": 4.2778, "step": 16593 }, { "epoch": 0.5068417837507636, "grad_norm": 0.38522854447364807, "learning_rate": 2.4462688935623228e-05, "loss": 4.2627, "step": 16594 }, { "epoch": 0.5068723274282224, "grad_norm": 0.3952409029006958, "learning_rate": 2.446029059740145e-05, "loss": 4.3296, "step": 16595 }, { "epoch": 0.5069028711056811, "grad_norm": 0.38951411843299866, "learning_rate": 2.4457892264149064e-05, "loss": 4.2555, "step": 16596 }, { "epoch": 0.5069334147831399, "grad_norm": 0.3954443335533142, "learning_rate": 2.445549393588813e-05, "loss": 4.3633, "step": 16597 }, { "epoch": 0.5069639584605986, "grad_norm": 0.3939392864704132, "learning_rate": 2.4453095612640754e-05, "loss": 4.2941, "step": 16598 }, { "epoch": 0.5069945021380574, "grad_norm": 0.3846375048160553, "learning_rate": 2.4450697294429e-05, "loss": 4.304, "step": 16599 }, { "epoch": 0.5070250458155162, "grad_norm": 0.38917988538742065, "learning_rate": 2.4448298981274963e-05, "loss": 4.2971, "step": 16600 }, { "epoch": 0.5070555894929749, "grad_norm": 0.3836996853351593, "learning_rate": 2.444590067320072e-05, "loss": 4.3075, "step": 16601 }, { "epoch": 0.5070861331704337, "grad_norm": 0.39770519733428955, "learning_rate": 2.4443502370228356e-05, "loss": 4.2906, "step": 16602 }, { "epoch": 0.5071166768478925, "grad_norm": 0.3874382972717285, "learning_rate": 2.4441104072379948e-05, "loss": 4.3954, "step": 16603 }, { "epoch": 0.5071472205253512, "grad_norm": 0.38594383001327515, "learning_rate": 2.443870577967759e-05, "loss": 4.2457, "step": 16604 }, { "epoch": 0.50717776420281, "grad_norm": 0.38404542207717896, "learning_rate": 2.4436307492143345e-05, "loss": 4.1533, "step": 16605 }, { "epoch": 0.5072083078802688, "grad_norm": 0.38811302185058594, "learning_rate": 2.443390920979931e-05, "loss": 4.3524, "step": 16606 }, { "epoch": 0.5072388515577275, "grad_norm": 0.392626017332077, "learning_rate": 2.443151093266757e-05, "loss": 4.2678, "step": 16607 }, { "epoch": 0.5072693952351863, "grad_norm": 0.4015207290649414, "learning_rate": 2.442911266077019e-05, "loss": 4.3011, "step": 16608 }, { "epoch": 0.5072999389126451, "grad_norm": 0.3970275819301605, "learning_rate": 2.4426714394129275e-05, "loss": 4.3419, "step": 16609 }, { "epoch": 0.5073304825901038, "grad_norm": 0.3863662779331207, "learning_rate": 2.4424316132766898e-05, "loss": 4.2803, "step": 16610 }, { "epoch": 0.5073610262675626, "grad_norm": 0.3876722455024719, "learning_rate": 2.442191787670513e-05, "loss": 4.2277, "step": 16611 }, { "epoch": 0.5073915699450213, "grad_norm": 0.3833913505077362, "learning_rate": 2.4419519625966067e-05, "loss": 4.3148, "step": 16612 }, { "epoch": 0.5074221136224801, "grad_norm": 0.41194048523902893, "learning_rate": 2.4417121380571776e-05, "loss": 4.2787, "step": 16613 }, { "epoch": 0.5074526572999389, "grad_norm": 0.3835042119026184, "learning_rate": 2.441472314054435e-05, "loss": 4.3234, "step": 16614 }, { "epoch": 0.5074832009773976, "grad_norm": 0.4049800932407379, "learning_rate": 2.4412324905905876e-05, "loss": 4.3423, "step": 16615 }, { "epoch": 0.5075137446548564, "grad_norm": 0.3952866792678833, "learning_rate": 2.4409926676678422e-05, "loss": 4.231, "step": 16616 }, { "epoch": 0.5075442883323152, "grad_norm": 0.38225263357162476, "learning_rate": 2.4407528452884078e-05, "loss": 4.3089, "step": 16617 }, { "epoch": 0.5075748320097739, "grad_norm": 0.3849438726902008, "learning_rate": 2.440513023454493e-05, "loss": 4.2658, "step": 16618 }, { "epoch": 0.5076053756872327, "grad_norm": 0.387726753950119, "learning_rate": 2.4402732021683048e-05, "loss": 4.3397, "step": 16619 }, { "epoch": 0.5076359193646915, "grad_norm": 0.38713738322257996, "learning_rate": 2.4400333814320516e-05, "loss": 4.3262, "step": 16620 }, { "epoch": 0.5076664630421502, "grad_norm": 0.40323665738105774, "learning_rate": 2.439793561247943e-05, "loss": 4.2168, "step": 16621 }, { "epoch": 0.507697006719609, "grad_norm": 0.3868129253387451, "learning_rate": 2.4395537416181848e-05, "loss": 4.2, "step": 16622 }, { "epoch": 0.5077275503970679, "grad_norm": 0.4017769992351532, "learning_rate": 2.4393139225449872e-05, "loss": 4.2554, "step": 16623 }, { "epoch": 0.5077580940745265, "grad_norm": 0.3930133581161499, "learning_rate": 2.4390741040305574e-05, "loss": 4.3552, "step": 16624 }, { "epoch": 0.5077886377519854, "grad_norm": 0.3806200623512268, "learning_rate": 2.4388342860771035e-05, "loss": 4.3323, "step": 16625 }, { "epoch": 0.5078191814294442, "grad_norm": 0.3954963982105255, "learning_rate": 2.4385944686868334e-05, "loss": 4.3189, "step": 16626 }, { "epoch": 0.5078497251069028, "grad_norm": 0.398040771484375, "learning_rate": 2.4383546518619565e-05, "loss": 4.2906, "step": 16627 }, { "epoch": 0.5078802687843617, "grad_norm": 0.39490726590156555, "learning_rate": 2.4381148356046793e-05, "loss": 4.3057, "step": 16628 }, { "epoch": 0.5079108124618203, "grad_norm": 0.3936992287635803, "learning_rate": 2.4378750199172114e-05, "loss": 4.2235, "step": 16629 }, { "epoch": 0.5079413561392792, "grad_norm": 0.3897957503795624, "learning_rate": 2.437635204801759e-05, "loss": 4.1784, "step": 16630 }, { "epoch": 0.507971899816738, "grad_norm": 0.4008060693740845, "learning_rate": 2.4373953902605314e-05, "loss": 4.3561, "step": 16631 }, { "epoch": 0.5080024434941967, "grad_norm": 0.3863193988800049, "learning_rate": 2.437155576295738e-05, "loss": 4.3709, "step": 16632 }, { "epoch": 0.5080329871716555, "grad_norm": 0.38881003856658936, "learning_rate": 2.436915762909585e-05, "loss": 4.2814, "step": 16633 }, { "epoch": 0.5080635308491143, "grad_norm": 0.3913125991821289, "learning_rate": 2.43667595010428e-05, "loss": 4.2598, "step": 16634 }, { "epoch": 0.508094074526573, "grad_norm": 0.5102542042732239, "learning_rate": 2.4364361378820334e-05, "loss": 4.2481, "step": 16635 }, { "epoch": 0.5081246182040318, "grad_norm": 0.38280966877937317, "learning_rate": 2.4361963262450506e-05, "loss": 4.3058, "step": 16636 }, { "epoch": 0.5081551618814906, "grad_norm": 0.3879993259906769, "learning_rate": 2.4359565151955414e-05, "loss": 4.281, "step": 16637 }, { "epoch": 0.5081857055589493, "grad_norm": 0.38284191489219666, "learning_rate": 2.4357167047357145e-05, "loss": 4.2378, "step": 16638 }, { "epoch": 0.5082162492364081, "grad_norm": 0.38883155584335327, "learning_rate": 2.435476894867776e-05, "loss": 4.3133, "step": 16639 }, { "epoch": 0.5082467929138669, "grad_norm": 0.3952130377292633, "learning_rate": 2.4352370855939352e-05, "loss": 4.3409, "step": 16640 }, { "epoch": 0.5082773365913256, "grad_norm": 0.3990316689014435, "learning_rate": 2.4349972769164005e-05, "loss": 4.2765, "step": 16641 }, { "epoch": 0.5083078802687844, "grad_norm": 0.4007558226585388, "learning_rate": 2.4347574688373782e-05, "loss": 4.2874, "step": 16642 }, { "epoch": 0.5083384239462432, "grad_norm": 0.4014708697795868, "learning_rate": 2.434517661359077e-05, "loss": 4.2208, "step": 16643 }, { "epoch": 0.5083689676237019, "grad_norm": 0.4244024157524109, "learning_rate": 2.4342778544837074e-05, "loss": 4.3053, "step": 16644 }, { "epoch": 0.5083995113011607, "grad_norm": 0.40681782364845276, "learning_rate": 2.4340380482134735e-05, "loss": 4.3278, "step": 16645 }, { "epoch": 0.5084300549786194, "grad_norm": 0.38833171129226685, "learning_rate": 2.4337982425505867e-05, "loss": 4.3054, "step": 16646 }, { "epoch": 0.5084605986560782, "grad_norm": 0.38520270586013794, "learning_rate": 2.433558437497252e-05, "loss": 4.3535, "step": 16647 }, { "epoch": 0.508491142333537, "grad_norm": 0.4051803946495056, "learning_rate": 2.43331863305568e-05, "loss": 4.1435, "step": 16648 }, { "epoch": 0.5085216860109957, "grad_norm": 0.4097146987915039, "learning_rate": 2.4330788292280775e-05, "loss": 4.2674, "step": 16649 }, { "epoch": 0.5085522296884545, "grad_norm": 0.3813908100128174, "learning_rate": 2.4328390260166524e-05, "loss": 4.1618, "step": 16650 }, { "epoch": 0.5085827733659133, "grad_norm": 0.3906807601451874, "learning_rate": 2.4325992234236125e-05, "loss": 4.2262, "step": 16651 }, { "epoch": 0.508613317043372, "grad_norm": 0.3980856239795685, "learning_rate": 2.4323594214511672e-05, "loss": 4.3686, "step": 16652 }, { "epoch": 0.5086438607208308, "grad_norm": 0.38274332880973816, "learning_rate": 2.4321196201015226e-05, "loss": 4.3494, "step": 16653 }, { "epoch": 0.5086744043982896, "grad_norm": 0.3946852385997772, "learning_rate": 2.4318798193768873e-05, "loss": 4.2945, "step": 16654 }, { "epoch": 0.5087049480757483, "grad_norm": 0.3899881839752197, "learning_rate": 2.4316400192794707e-05, "loss": 4.313, "step": 16655 }, { "epoch": 0.5087354917532071, "grad_norm": 0.40368807315826416, "learning_rate": 2.431400219811479e-05, "loss": 4.3664, "step": 16656 }, { "epoch": 0.5087660354306659, "grad_norm": 0.39475005865097046, "learning_rate": 2.4311604209751203e-05, "loss": 4.299, "step": 16657 }, { "epoch": 0.5087965791081246, "grad_norm": 0.3835216164588928, "learning_rate": 2.4309206227726042e-05, "loss": 4.2835, "step": 16658 }, { "epoch": 0.5088271227855834, "grad_norm": 0.39523354172706604, "learning_rate": 2.4306808252061363e-05, "loss": 4.2536, "step": 16659 }, { "epoch": 0.5088576664630422, "grad_norm": 0.3959640562534332, "learning_rate": 2.4304410282779254e-05, "loss": 4.255, "step": 16660 }, { "epoch": 0.5088882101405009, "grad_norm": 0.40070098638534546, "learning_rate": 2.430201231990181e-05, "loss": 4.3679, "step": 16661 }, { "epoch": 0.5089187538179597, "grad_norm": 0.39532044529914856, "learning_rate": 2.429961436345109e-05, "loss": 4.3325, "step": 16662 }, { "epoch": 0.5089492974954184, "grad_norm": 0.3939477205276489, "learning_rate": 2.4297216413449188e-05, "loss": 4.2937, "step": 16663 }, { "epoch": 0.5089798411728772, "grad_norm": 0.38817235827445984, "learning_rate": 2.429481846991817e-05, "loss": 4.2741, "step": 16664 }, { "epoch": 0.509010384850336, "grad_norm": 0.3972647786140442, "learning_rate": 2.4292420532880116e-05, "loss": 4.2527, "step": 16665 }, { "epoch": 0.5090409285277947, "grad_norm": 0.3930419087409973, "learning_rate": 2.429002260235712e-05, "loss": 4.2956, "step": 16666 }, { "epoch": 0.5090714722052535, "grad_norm": 0.40816763043403625, "learning_rate": 2.428762467837124e-05, "loss": 4.3263, "step": 16667 }, { "epoch": 0.5091020158827123, "grad_norm": 0.4062563478946686, "learning_rate": 2.4285226760944568e-05, "loss": 4.2574, "step": 16668 }, { "epoch": 0.509132559560171, "grad_norm": 0.3948878049850464, "learning_rate": 2.428282885009919e-05, "loss": 4.3468, "step": 16669 }, { "epoch": 0.5091631032376298, "grad_norm": 0.3929347097873688, "learning_rate": 2.4280430945857166e-05, "loss": 4.3501, "step": 16670 }, { "epoch": 0.5091936469150886, "grad_norm": 0.3994848430156708, "learning_rate": 2.427803304824059e-05, "loss": 4.4044, "step": 16671 }, { "epoch": 0.5092241905925473, "grad_norm": 0.3991519808769226, "learning_rate": 2.4275635157271532e-05, "loss": 4.2771, "step": 16672 }, { "epoch": 0.5092547342700061, "grad_norm": 0.38805627822875977, "learning_rate": 2.4273237272972076e-05, "loss": 4.3229, "step": 16673 }, { "epoch": 0.5092852779474649, "grad_norm": 0.39724200963974, "learning_rate": 2.427083939536429e-05, "loss": 4.2702, "step": 16674 }, { "epoch": 0.5093158216249236, "grad_norm": 0.3861120343208313, "learning_rate": 2.4268441524470277e-05, "loss": 4.2979, "step": 16675 }, { "epoch": 0.5093463653023824, "grad_norm": 0.3908320963382721, "learning_rate": 2.426604366031208e-05, "loss": 4.3119, "step": 16676 }, { "epoch": 0.5093769089798412, "grad_norm": 0.3845028281211853, "learning_rate": 2.4263645802911803e-05, "loss": 4.2401, "step": 16677 }, { "epoch": 0.5094074526572999, "grad_norm": 0.39952120184898376, "learning_rate": 2.426124795229153e-05, "loss": 4.2629, "step": 16678 }, { "epoch": 0.5094379963347587, "grad_norm": 0.3989907205104828, "learning_rate": 2.4258850108473315e-05, "loss": 4.2217, "step": 16679 }, { "epoch": 0.5094685400122174, "grad_norm": 0.40219244360923767, "learning_rate": 2.4256452271479253e-05, "loss": 4.3313, "step": 16680 }, { "epoch": 0.5094990836896762, "grad_norm": 0.3928655982017517, "learning_rate": 2.4254054441331412e-05, "loss": 4.4207, "step": 16681 }, { "epoch": 0.509529627367135, "grad_norm": 0.3917246162891388, "learning_rate": 2.4251656618051874e-05, "loss": 4.2527, "step": 16682 }, { "epoch": 0.5095601710445937, "grad_norm": 0.39249369502067566, "learning_rate": 2.424925880166273e-05, "loss": 4.2473, "step": 16683 }, { "epoch": 0.5095907147220525, "grad_norm": 0.37881094217300415, "learning_rate": 2.4246860992186033e-05, "loss": 4.3682, "step": 16684 }, { "epoch": 0.5096212583995113, "grad_norm": 0.39214181900024414, "learning_rate": 2.4244463189643874e-05, "loss": 4.2771, "step": 16685 }, { "epoch": 0.50965180207697, "grad_norm": 0.4009851813316345, "learning_rate": 2.4242065394058342e-05, "loss": 4.3121, "step": 16686 }, { "epoch": 0.5096823457544288, "grad_norm": 0.39523157477378845, "learning_rate": 2.4239667605451498e-05, "loss": 4.3264, "step": 16687 }, { "epoch": 0.5097128894318876, "grad_norm": 0.39915257692337036, "learning_rate": 2.423726982384542e-05, "loss": 4.3546, "step": 16688 }, { "epoch": 0.5097434331093463, "grad_norm": 0.39195510745048523, "learning_rate": 2.4234872049262204e-05, "loss": 4.285, "step": 16689 }, { "epoch": 0.5097739767868051, "grad_norm": 0.3869314193725586, "learning_rate": 2.42324742817239e-05, "loss": 4.2064, "step": 16690 }, { "epoch": 0.5098045204642639, "grad_norm": 0.39210250973701477, "learning_rate": 2.4230076521252605e-05, "loss": 4.277, "step": 16691 }, { "epoch": 0.5098350641417226, "grad_norm": 0.3998558521270752, "learning_rate": 2.4227678767870395e-05, "loss": 4.3659, "step": 16692 }, { "epoch": 0.5098656078191814, "grad_norm": 0.4044615626335144, "learning_rate": 2.4225281021599338e-05, "loss": 4.2147, "step": 16693 }, { "epoch": 0.5098961514966402, "grad_norm": 0.4084634780883789, "learning_rate": 2.4222883282461522e-05, "loss": 4.2492, "step": 16694 }, { "epoch": 0.5099266951740989, "grad_norm": 0.39500460028648376, "learning_rate": 2.422048555047902e-05, "loss": 4.3488, "step": 16695 }, { "epoch": 0.5099572388515577, "grad_norm": 0.3928202986717224, "learning_rate": 2.4218087825673906e-05, "loss": 4.3103, "step": 16696 }, { "epoch": 0.5099877825290164, "grad_norm": 0.4092996418476105, "learning_rate": 2.4215690108068263e-05, "loss": 4.3105, "step": 16697 }, { "epoch": 0.5100183262064752, "grad_norm": 0.39554113149642944, "learning_rate": 2.4213292397684156e-05, "loss": 4.2492, "step": 16698 }, { "epoch": 0.510048869883934, "grad_norm": 0.39222437143325806, "learning_rate": 2.421089469454367e-05, "loss": 4.3218, "step": 16699 }, { "epoch": 0.5100794135613927, "grad_norm": 0.4113781750202179, "learning_rate": 2.4208496998668893e-05, "loss": 4.2448, "step": 16700 }, { "epoch": 0.5101099572388516, "grad_norm": 0.40498995780944824, "learning_rate": 2.4206099310081885e-05, "loss": 4.352, "step": 16701 }, { "epoch": 0.5101405009163104, "grad_norm": 0.4063013792037964, "learning_rate": 2.420370162880473e-05, "loss": 4.2912, "step": 16702 }, { "epoch": 0.510171044593769, "grad_norm": 0.3953460156917572, "learning_rate": 2.42013039548595e-05, "loss": 4.2911, "step": 16703 }, { "epoch": 0.5102015882712279, "grad_norm": 0.39143019914627075, "learning_rate": 2.419890628826828e-05, "loss": 4.1889, "step": 16704 }, { "epoch": 0.5102321319486867, "grad_norm": 0.38994506001472473, "learning_rate": 2.4196508629053135e-05, "loss": 4.304, "step": 16705 }, { "epoch": 0.5102626756261454, "grad_norm": 0.4032163918018341, "learning_rate": 2.419411097723616e-05, "loss": 4.2805, "step": 16706 }, { "epoch": 0.5102932193036042, "grad_norm": 0.3951120376586914, "learning_rate": 2.4191713332839404e-05, "loss": 4.2645, "step": 16707 }, { "epoch": 0.510323762981063, "grad_norm": 0.3970176875591278, "learning_rate": 2.4189315695884966e-05, "loss": 4.3214, "step": 16708 }, { "epoch": 0.5103543066585217, "grad_norm": 0.3880331516265869, "learning_rate": 2.418691806639492e-05, "loss": 4.3364, "step": 16709 }, { "epoch": 0.5103848503359805, "grad_norm": 0.39594200253486633, "learning_rate": 2.4184520444391336e-05, "loss": 4.3211, "step": 16710 }, { "epoch": 0.5104153940134393, "grad_norm": 0.3855641782283783, "learning_rate": 2.4182122829896285e-05, "loss": 4.2859, "step": 16711 }, { "epoch": 0.510445937690898, "grad_norm": 0.3901093900203705, "learning_rate": 2.417972522293186e-05, "loss": 4.2828, "step": 16712 }, { "epoch": 0.5104764813683568, "grad_norm": 0.3931598961353302, "learning_rate": 2.4177327623520116e-05, "loss": 4.2609, "step": 16713 }, { "epoch": 0.5105070250458155, "grad_norm": 0.40850889682769775, "learning_rate": 2.4174930031683152e-05, "loss": 4.3441, "step": 16714 }, { "epoch": 0.5105375687232743, "grad_norm": 0.39029133319854736, "learning_rate": 2.4172532447443017e-05, "loss": 4.2892, "step": 16715 }, { "epoch": 0.5105681124007331, "grad_norm": 0.3909622132778168, "learning_rate": 2.4170134870821804e-05, "loss": 4.2717, "step": 16716 }, { "epoch": 0.5105986560781918, "grad_norm": 0.39661040902137756, "learning_rate": 2.4167737301841594e-05, "loss": 4.2959, "step": 16717 }, { "epoch": 0.5106291997556506, "grad_norm": 0.397329181432724, "learning_rate": 2.4165339740524447e-05, "loss": 4.2904, "step": 16718 }, { "epoch": 0.5106597434331094, "grad_norm": 0.38733020424842834, "learning_rate": 2.416294218689245e-05, "loss": 4.2859, "step": 16719 }, { "epoch": 0.5106902871105681, "grad_norm": 0.3925689160823822, "learning_rate": 2.416054464096768e-05, "loss": 4.3472, "step": 16720 }, { "epoch": 0.5107208307880269, "grad_norm": 0.4021136462688446, "learning_rate": 2.41581471027722e-05, "loss": 4.2552, "step": 16721 }, { "epoch": 0.5107513744654857, "grad_norm": 0.38526830077171326, "learning_rate": 2.4155749572328084e-05, "loss": 4.2532, "step": 16722 }, { "epoch": 0.5107819181429444, "grad_norm": 0.40060630440711975, "learning_rate": 2.4153352049657432e-05, "loss": 4.2909, "step": 16723 }, { "epoch": 0.5108124618204032, "grad_norm": 0.3904705345630646, "learning_rate": 2.4150954534782295e-05, "loss": 4.1757, "step": 16724 }, { "epoch": 0.510843005497862, "grad_norm": 0.3844291865825653, "learning_rate": 2.4148557027724754e-05, "loss": 4.2864, "step": 16725 }, { "epoch": 0.5108735491753207, "grad_norm": 0.3886110484600067, "learning_rate": 2.4146159528506892e-05, "loss": 4.3277, "step": 16726 }, { "epoch": 0.5109040928527795, "grad_norm": 0.3862251043319702, "learning_rate": 2.4143762037150777e-05, "loss": 4.3224, "step": 16727 }, { "epoch": 0.5109346365302383, "grad_norm": 0.39570319652557373, "learning_rate": 2.4141364553678482e-05, "loss": 4.2763, "step": 16728 }, { "epoch": 0.510965180207697, "grad_norm": 0.4039923846721649, "learning_rate": 2.413896707811209e-05, "loss": 4.2695, "step": 16729 }, { "epoch": 0.5109957238851558, "grad_norm": 0.387467622756958, "learning_rate": 2.4136569610473664e-05, "loss": 4.2998, "step": 16730 }, { "epoch": 0.5110262675626145, "grad_norm": 0.40610209107398987, "learning_rate": 2.4134172150785295e-05, "loss": 4.2829, "step": 16731 }, { "epoch": 0.5110568112400733, "grad_norm": 0.39255285263061523, "learning_rate": 2.4131774699069038e-05, "loss": 4.2493, "step": 16732 }, { "epoch": 0.5110873549175321, "grad_norm": 0.3955683708190918, "learning_rate": 2.4129377255346983e-05, "loss": 4.3027, "step": 16733 }, { "epoch": 0.5111178985949908, "grad_norm": 0.3919079601764679, "learning_rate": 2.41269798196412e-05, "loss": 4.3514, "step": 16734 }, { "epoch": 0.5111484422724496, "grad_norm": 0.3980446755886078, "learning_rate": 2.4124582391973763e-05, "loss": 4.2289, "step": 16735 }, { "epoch": 0.5111789859499084, "grad_norm": 0.39972952008247375, "learning_rate": 2.412218497236674e-05, "loss": 4.3134, "step": 16736 }, { "epoch": 0.5112095296273671, "grad_norm": 0.37610962986946106, "learning_rate": 2.4119787560842222e-05, "loss": 4.1408, "step": 16737 }, { "epoch": 0.5112400733048259, "grad_norm": 0.3909541368484497, "learning_rate": 2.411739015742226e-05, "loss": 4.1971, "step": 16738 }, { "epoch": 0.5112706169822847, "grad_norm": 0.40068283677101135, "learning_rate": 2.411499276212894e-05, "loss": 4.2763, "step": 16739 }, { "epoch": 0.5113011606597434, "grad_norm": 0.40458643436431885, "learning_rate": 2.4112595374984352e-05, "loss": 4.314, "step": 16740 }, { "epoch": 0.5113317043372022, "grad_norm": 0.40211501717567444, "learning_rate": 2.4110197996010542e-05, "loss": 4.2752, "step": 16741 }, { "epoch": 0.511362248014661, "grad_norm": 0.3921259939670563, "learning_rate": 2.4107800625229597e-05, "loss": 4.2985, "step": 16742 }, { "epoch": 0.5113927916921197, "grad_norm": 0.3964706361293793, "learning_rate": 2.4105403262663602e-05, "loss": 4.3214, "step": 16743 }, { "epoch": 0.5114233353695785, "grad_norm": 0.39885956048965454, "learning_rate": 2.410300590833461e-05, "loss": 4.2384, "step": 16744 }, { "epoch": 0.5114538790470373, "grad_norm": 0.3947899341583252, "learning_rate": 2.4100608562264698e-05, "loss": 4.2154, "step": 16745 }, { "epoch": 0.511484422724496, "grad_norm": 0.3896682560443878, "learning_rate": 2.4098211224475958e-05, "loss": 4.3445, "step": 16746 }, { "epoch": 0.5115149664019548, "grad_norm": 0.3879489302635193, "learning_rate": 2.409581389499044e-05, "loss": 4.388, "step": 16747 }, { "epoch": 0.5115455100794135, "grad_norm": 0.38356146216392517, "learning_rate": 2.409341657383024e-05, "loss": 4.3375, "step": 16748 }, { "epoch": 0.5115760537568723, "grad_norm": 0.3957943618297577, "learning_rate": 2.409101926101741e-05, "loss": 4.2163, "step": 16749 }, { "epoch": 0.5116065974343311, "grad_norm": 0.39437952637672424, "learning_rate": 2.4088621956574036e-05, "loss": 4.2571, "step": 16750 }, { "epoch": 0.5116371411117898, "grad_norm": 0.3892040252685547, "learning_rate": 2.4086224660522193e-05, "loss": 4.334, "step": 16751 }, { "epoch": 0.5116676847892486, "grad_norm": 0.40587756037712097, "learning_rate": 2.408382737288394e-05, "loss": 4.2791, "step": 16752 }, { "epoch": 0.5116982284667074, "grad_norm": 0.39189377427101135, "learning_rate": 2.408143009368136e-05, "loss": 4.2741, "step": 16753 }, { "epoch": 0.5117287721441661, "grad_norm": 0.3895176947116852, "learning_rate": 2.4079032822936536e-05, "loss": 4.2492, "step": 16754 }, { "epoch": 0.5117593158216249, "grad_norm": 0.3899196684360504, "learning_rate": 2.407663556067152e-05, "loss": 4.2596, "step": 16755 }, { "epoch": 0.5117898594990837, "grad_norm": 0.39367154240608215, "learning_rate": 2.4074238306908393e-05, "loss": 4.3272, "step": 16756 }, { "epoch": 0.5118204031765424, "grad_norm": 0.394193559885025, "learning_rate": 2.407184106166924e-05, "loss": 4.2326, "step": 16757 }, { "epoch": 0.5118509468540012, "grad_norm": 0.38982459902763367, "learning_rate": 2.4069443824976123e-05, "loss": 4.2038, "step": 16758 }, { "epoch": 0.51188149053146, "grad_norm": 0.38674700260162354, "learning_rate": 2.4067046596851105e-05, "loss": 4.3123, "step": 16759 }, { "epoch": 0.5119120342089187, "grad_norm": 0.4018951654434204, "learning_rate": 2.4064649377316285e-05, "loss": 4.2581, "step": 16760 }, { "epoch": 0.5119425778863775, "grad_norm": 0.3946934640407562, "learning_rate": 2.4062252166393704e-05, "loss": 4.2619, "step": 16761 }, { "epoch": 0.5119731215638362, "grad_norm": 0.39436599612236023, "learning_rate": 2.405985496410546e-05, "loss": 4.313, "step": 16762 }, { "epoch": 0.512003665241295, "grad_norm": 0.3811963200569153, "learning_rate": 2.4057457770473607e-05, "loss": 4.2875, "step": 16763 }, { "epoch": 0.5120342089187538, "grad_norm": 0.392844557762146, "learning_rate": 2.4055060585520222e-05, "loss": 4.2956, "step": 16764 }, { "epoch": 0.5120647525962125, "grad_norm": 0.3790076673030853, "learning_rate": 2.4052663409267394e-05, "loss": 4.2937, "step": 16765 }, { "epoch": 0.5120952962736713, "grad_norm": 0.3965660035610199, "learning_rate": 2.4050266241737172e-05, "loss": 4.3275, "step": 16766 }, { "epoch": 0.5121258399511301, "grad_norm": 0.403117299079895, "learning_rate": 2.4047869082951633e-05, "loss": 4.3107, "step": 16767 }, { "epoch": 0.5121563836285888, "grad_norm": 0.39260298013687134, "learning_rate": 2.4045471932932862e-05, "loss": 4.3671, "step": 16768 }, { "epoch": 0.5121869273060476, "grad_norm": 0.3842645287513733, "learning_rate": 2.4043074791702914e-05, "loss": 4.3182, "step": 16769 }, { "epoch": 0.5122174709835065, "grad_norm": 0.39273801445961, "learning_rate": 2.4040677659283868e-05, "loss": 4.2315, "step": 16770 }, { "epoch": 0.5122480146609651, "grad_norm": 0.3950859606266022, "learning_rate": 2.4038280535697804e-05, "loss": 4.285, "step": 16771 }, { "epoch": 0.512278558338424, "grad_norm": 0.39385896921157837, "learning_rate": 2.4035883420966777e-05, "loss": 4.2872, "step": 16772 }, { "epoch": 0.5123091020158828, "grad_norm": 0.4122019112110138, "learning_rate": 2.4033486315112873e-05, "loss": 4.3443, "step": 16773 }, { "epoch": 0.5123396456933415, "grad_norm": 0.3896559476852417, "learning_rate": 2.4031089218158158e-05, "loss": 4.2371, "step": 16774 }, { "epoch": 0.5123701893708003, "grad_norm": 0.40355098247528076, "learning_rate": 2.40286921301247e-05, "loss": 4.249, "step": 16775 }, { "epoch": 0.5124007330482591, "grad_norm": 0.3977544903755188, "learning_rate": 2.4026295051034565e-05, "loss": 4.2724, "step": 16776 }, { "epoch": 0.5124312767257178, "grad_norm": 0.4008345901966095, "learning_rate": 2.402389798090985e-05, "loss": 4.3009, "step": 16777 }, { "epoch": 0.5124618204031766, "grad_norm": 0.3871117830276489, "learning_rate": 2.402150091977259e-05, "loss": 4.2979, "step": 16778 }, { "epoch": 0.5124923640806353, "grad_norm": 0.3961469829082489, "learning_rate": 2.401910386764489e-05, "loss": 4.2782, "step": 16779 }, { "epoch": 0.5125229077580941, "grad_norm": 0.38183629512786865, "learning_rate": 2.4016706824548793e-05, "loss": 4.3003, "step": 16780 }, { "epoch": 0.5125534514355529, "grad_norm": 0.3963654041290283, "learning_rate": 2.4014309790506386e-05, "loss": 4.2833, "step": 16781 }, { "epoch": 0.5125839951130116, "grad_norm": 0.3909192383289337, "learning_rate": 2.4011912765539737e-05, "loss": 4.3909, "step": 16782 }, { "epoch": 0.5126145387904704, "grad_norm": 0.4002465307712555, "learning_rate": 2.4009515749670917e-05, "loss": 4.2712, "step": 16783 }, { "epoch": 0.5126450824679292, "grad_norm": 0.3905017673969269, "learning_rate": 2.4007118742921985e-05, "loss": 4.216, "step": 16784 }, { "epoch": 0.5126756261453879, "grad_norm": 0.39428067207336426, "learning_rate": 2.4004721745315036e-05, "loss": 4.1508, "step": 16785 }, { "epoch": 0.5127061698228467, "grad_norm": 0.4002215564250946, "learning_rate": 2.4002324756872112e-05, "loss": 4.291, "step": 16786 }, { "epoch": 0.5127367135003055, "grad_norm": 0.38419201970100403, "learning_rate": 2.3999927777615298e-05, "loss": 4.2442, "step": 16787 }, { "epoch": 0.5127672571777642, "grad_norm": 0.4035014808177948, "learning_rate": 2.3997530807566678e-05, "loss": 4.3393, "step": 16788 }, { "epoch": 0.512797800855223, "grad_norm": 0.3879338204860687, "learning_rate": 2.3995133846748297e-05, "loss": 4.2386, "step": 16789 }, { "epoch": 0.5128283445326818, "grad_norm": 0.3933236598968506, "learning_rate": 2.399273689518223e-05, "loss": 4.2839, "step": 16790 }, { "epoch": 0.5128588882101405, "grad_norm": 0.3981400430202484, "learning_rate": 2.3990339952890564e-05, "loss": 4.3018, "step": 16791 }, { "epoch": 0.5128894318875993, "grad_norm": 0.3923989534378052, "learning_rate": 2.3987943019895346e-05, "loss": 4.3537, "step": 16792 }, { "epoch": 0.5129199755650581, "grad_norm": 0.4033251702785492, "learning_rate": 2.398554609621866e-05, "loss": 4.2751, "step": 16793 }, { "epoch": 0.5129505192425168, "grad_norm": 0.3918102979660034, "learning_rate": 2.3983149181882577e-05, "loss": 4.3434, "step": 16794 }, { "epoch": 0.5129810629199756, "grad_norm": 0.3842962384223938, "learning_rate": 2.3980752276909156e-05, "loss": 4.175, "step": 16795 }, { "epoch": 0.5130116065974343, "grad_norm": 0.39685487747192383, "learning_rate": 2.3978355381320485e-05, "loss": 4.3234, "step": 16796 }, { "epoch": 0.5130421502748931, "grad_norm": 0.39372801780700684, "learning_rate": 2.3975958495138612e-05, "loss": 4.345, "step": 16797 }, { "epoch": 0.5130726939523519, "grad_norm": 0.4012880325317383, "learning_rate": 2.3973561618385612e-05, "loss": 4.1754, "step": 16798 }, { "epoch": 0.5131032376298106, "grad_norm": 0.39574477076530457, "learning_rate": 2.397116475108357e-05, "loss": 4.2945, "step": 16799 }, { "epoch": 0.5131337813072694, "grad_norm": 0.39791563153266907, "learning_rate": 2.396876789325453e-05, "loss": 4.3347, "step": 16800 }, { "epoch": 0.5131643249847282, "grad_norm": 0.4089561104774475, "learning_rate": 2.3966371044920575e-05, "loss": 4.195, "step": 16801 }, { "epoch": 0.5131948686621869, "grad_norm": 0.3946491777896881, "learning_rate": 2.3963974206103786e-05, "loss": 4.2753, "step": 16802 }, { "epoch": 0.5132254123396457, "grad_norm": 0.3994293212890625, "learning_rate": 2.3961577376826206e-05, "loss": 4.3284, "step": 16803 }, { "epoch": 0.5132559560171045, "grad_norm": 0.3910483121871948, "learning_rate": 2.3959180557109922e-05, "loss": 4.1808, "step": 16804 }, { "epoch": 0.5132864996945632, "grad_norm": 0.39018359780311584, "learning_rate": 2.3956783746977e-05, "loss": 4.3358, "step": 16805 }, { "epoch": 0.513317043372022, "grad_norm": 0.38595908880233765, "learning_rate": 2.3954386946449503e-05, "loss": 4.1926, "step": 16806 }, { "epoch": 0.5133475870494808, "grad_norm": 0.40194734930992126, "learning_rate": 2.39519901555495e-05, "loss": 4.2186, "step": 16807 }, { "epoch": 0.5133781307269395, "grad_norm": 0.39669665694236755, "learning_rate": 2.394959337429907e-05, "loss": 4.2245, "step": 16808 }, { "epoch": 0.5134086744043983, "grad_norm": 0.39920806884765625, "learning_rate": 2.3947196602720272e-05, "loss": 4.3396, "step": 16809 }, { "epoch": 0.5134392180818571, "grad_norm": 0.4033339321613312, "learning_rate": 2.394479984083517e-05, "loss": 4.341, "step": 16810 }, { "epoch": 0.5134697617593158, "grad_norm": 0.40941551327705383, "learning_rate": 2.3942403088665848e-05, "loss": 4.1411, "step": 16811 }, { "epoch": 0.5135003054367746, "grad_norm": 0.3927787244319916, "learning_rate": 2.394000634623436e-05, "loss": 4.2407, "step": 16812 }, { "epoch": 0.5135308491142333, "grad_norm": 0.3833625912666321, "learning_rate": 2.393760961356278e-05, "loss": 4.3142, "step": 16813 }, { "epoch": 0.5135613927916921, "grad_norm": 0.3886118233203888, "learning_rate": 2.3935212890673173e-05, "loss": 4.2645, "step": 16814 }, { "epoch": 0.5135919364691509, "grad_norm": 0.39252492785453796, "learning_rate": 2.3932816177587606e-05, "loss": 4.3157, "step": 16815 }, { "epoch": 0.5136224801466096, "grad_norm": 0.41815996170043945, "learning_rate": 2.3930419474328156e-05, "loss": 4.2886, "step": 16816 }, { "epoch": 0.5136530238240684, "grad_norm": 0.3991340398788452, "learning_rate": 2.3928022780916875e-05, "loss": 4.252, "step": 16817 }, { "epoch": 0.5136835675015272, "grad_norm": 0.3986581563949585, "learning_rate": 2.392562609737584e-05, "loss": 4.3306, "step": 16818 }, { "epoch": 0.5137141111789859, "grad_norm": 0.40592917799949646, "learning_rate": 2.3923229423727128e-05, "loss": 4.3642, "step": 16819 }, { "epoch": 0.5137446548564447, "grad_norm": 0.3872142732143402, "learning_rate": 2.392083275999279e-05, "loss": 4.2293, "step": 16820 }, { "epoch": 0.5137751985339035, "grad_norm": 0.39529040455818176, "learning_rate": 2.3918436106194895e-05, "loss": 4.3797, "step": 16821 }, { "epoch": 0.5138057422113622, "grad_norm": 0.3937298357486725, "learning_rate": 2.3916039462355526e-05, "loss": 4.2783, "step": 16822 }, { "epoch": 0.513836285888821, "grad_norm": 0.4010869860649109, "learning_rate": 2.3913642828496728e-05, "loss": 4.2373, "step": 16823 }, { "epoch": 0.5138668295662798, "grad_norm": 0.39221736788749695, "learning_rate": 2.3911246204640576e-05, "loss": 4.3299, "step": 16824 }, { "epoch": 0.5138973732437385, "grad_norm": 0.40014249086380005, "learning_rate": 2.3908849590809155e-05, "loss": 4.2756, "step": 16825 }, { "epoch": 0.5139279169211973, "grad_norm": 0.3971664011478424, "learning_rate": 2.3906452987024506e-05, "loss": 4.3646, "step": 16826 }, { "epoch": 0.5139584605986561, "grad_norm": 0.38776445388793945, "learning_rate": 2.390405639330871e-05, "loss": 4.2685, "step": 16827 }, { "epoch": 0.5139890042761148, "grad_norm": 0.3930489420890808, "learning_rate": 2.390165980968383e-05, "loss": 4.3186, "step": 16828 }, { "epoch": 0.5140195479535736, "grad_norm": 0.3860373795032501, "learning_rate": 2.3899263236171934e-05, "loss": 4.2971, "step": 16829 }, { "epoch": 0.5140500916310323, "grad_norm": 0.39089757204055786, "learning_rate": 2.3896866672795094e-05, "loss": 4.2561, "step": 16830 }, { "epoch": 0.5140806353084911, "grad_norm": 0.4121697247028351, "learning_rate": 2.3894470119575354e-05, "loss": 4.3775, "step": 16831 }, { "epoch": 0.5141111789859499, "grad_norm": 0.39427268505096436, "learning_rate": 2.3892073576534802e-05, "loss": 4.2463, "step": 16832 }, { "epoch": 0.5141417226634086, "grad_norm": 0.3850007653236389, "learning_rate": 2.3889677043695506e-05, "loss": 4.326, "step": 16833 }, { "epoch": 0.5141722663408674, "grad_norm": 0.4003082811832428, "learning_rate": 2.3887280521079513e-05, "loss": 4.31, "step": 16834 }, { "epoch": 0.5142028100183262, "grad_norm": 0.39256784319877625, "learning_rate": 2.3884884008708907e-05, "loss": 4.37, "step": 16835 }, { "epoch": 0.5142333536957849, "grad_norm": 0.39348623156547546, "learning_rate": 2.3882487506605745e-05, "loss": 4.3411, "step": 16836 }, { "epoch": 0.5142638973732437, "grad_norm": 0.39525729417800903, "learning_rate": 2.38800910147921e-05, "loss": 4.3148, "step": 16837 }, { "epoch": 0.5142944410507025, "grad_norm": 0.3993961215019226, "learning_rate": 2.3877694533290023e-05, "loss": 4.2744, "step": 16838 }, { "epoch": 0.5143249847281612, "grad_norm": 0.3890596628189087, "learning_rate": 2.3875298062121602e-05, "loss": 4.324, "step": 16839 }, { "epoch": 0.51435552840562, "grad_norm": 0.39721012115478516, "learning_rate": 2.3872901601308878e-05, "loss": 4.2564, "step": 16840 }, { "epoch": 0.5143860720830788, "grad_norm": 0.40916112065315247, "learning_rate": 2.387050515087393e-05, "loss": 4.233, "step": 16841 }, { "epoch": 0.5144166157605375, "grad_norm": 0.39432790875434875, "learning_rate": 2.3868108710838833e-05, "loss": 4.2711, "step": 16842 }, { "epoch": 0.5144471594379963, "grad_norm": 0.3864205479621887, "learning_rate": 2.3865712281225632e-05, "loss": 4.2632, "step": 16843 }, { "epoch": 0.5144777031154552, "grad_norm": 0.3929330110549927, "learning_rate": 2.38633158620564e-05, "loss": 4.2585, "step": 16844 }, { "epoch": 0.5145082467929138, "grad_norm": 0.4058994948863983, "learning_rate": 2.3860919453353215e-05, "loss": 4.3336, "step": 16845 }, { "epoch": 0.5145387904703727, "grad_norm": 0.39826419949531555, "learning_rate": 2.3858523055138116e-05, "loss": 4.3007, "step": 16846 }, { "epoch": 0.5145693341478313, "grad_norm": 0.3986304998397827, "learning_rate": 2.3856126667433192e-05, "loss": 4.3427, "step": 16847 }, { "epoch": 0.5145998778252902, "grad_norm": 0.4033719301223755, "learning_rate": 2.385373029026049e-05, "loss": 4.2783, "step": 16848 }, { "epoch": 0.514630421502749, "grad_norm": 0.384441077709198, "learning_rate": 2.3851333923642083e-05, "loss": 4.2773, "step": 16849 }, { "epoch": 0.5146609651802077, "grad_norm": 0.38235610723495483, "learning_rate": 2.3848937567600043e-05, "loss": 4.2848, "step": 16850 }, { "epoch": 0.5146915088576665, "grad_norm": 0.4127671718597412, "learning_rate": 2.3846541222156418e-05, "loss": 4.3983, "step": 16851 }, { "epoch": 0.5147220525351253, "grad_norm": 0.39296969771385193, "learning_rate": 2.3844144887333285e-05, "loss": 4.2338, "step": 16852 }, { "epoch": 0.514752596212584, "grad_norm": 0.39403265714645386, "learning_rate": 2.384174856315271e-05, "loss": 4.3038, "step": 16853 }, { "epoch": 0.5147831398900428, "grad_norm": 0.38970711827278137, "learning_rate": 2.3839352249636743e-05, "loss": 4.2914, "step": 16854 }, { "epoch": 0.5148136835675016, "grad_norm": 0.39218491315841675, "learning_rate": 2.3836955946807454e-05, "loss": 4.3125, "step": 16855 }, { "epoch": 0.5148442272449603, "grad_norm": 0.4091689884662628, "learning_rate": 2.3834559654686922e-05, "loss": 4.221, "step": 16856 }, { "epoch": 0.5148747709224191, "grad_norm": 0.3922315835952759, "learning_rate": 2.3832163373297185e-05, "loss": 4.2307, "step": 16857 }, { "epoch": 0.5149053145998779, "grad_norm": 0.38907578587532043, "learning_rate": 2.382976710266033e-05, "loss": 4.2938, "step": 16858 }, { "epoch": 0.5149358582773366, "grad_norm": 0.39486679434776306, "learning_rate": 2.382737084279841e-05, "loss": 4.3728, "step": 16859 }, { "epoch": 0.5149664019547954, "grad_norm": 0.38875052332878113, "learning_rate": 2.3824974593733486e-05, "loss": 4.2553, "step": 16860 }, { "epoch": 0.5149969456322542, "grad_norm": 0.3837661147117615, "learning_rate": 2.382257835548762e-05, "loss": 4.3066, "step": 16861 }, { "epoch": 0.5150274893097129, "grad_norm": 0.39575257897377014, "learning_rate": 2.3820182128082895e-05, "loss": 4.3296, "step": 16862 }, { "epoch": 0.5150580329871717, "grad_norm": 0.40079593658447266, "learning_rate": 2.3817785911541347e-05, "loss": 4.2827, "step": 16863 }, { "epoch": 0.5150885766646304, "grad_norm": 0.38945117592811584, "learning_rate": 2.381538970588506e-05, "loss": 4.2236, "step": 16864 }, { "epoch": 0.5151191203420892, "grad_norm": 0.40033331513404846, "learning_rate": 2.381299351113608e-05, "loss": 4.3211, "step": 16865 }, { "epoch": 0.515149664019548, "grad_norm": 0.4070702791213989, "learning_rate": 2.381059732731648e-05, "loss": 4.2782, "step": 16866 }, { "epoch": 0.5151802076970067, "grad_norm": 0.39555028080940247, "learning_rate": 2.3808201154448333e-05, "loss": 4.2622, "step": 16867 }, { "epoch": 0.5152107513744655, "grad_norm": 0.40028810501098633, "learning_rate": 2.3805804992553688e-05, "loss": 4.3913, "step": 16868 }, { "epoch": 0.5152412950519243, "grad_norm": 0.3873225450515747, "learning_rate": 2.38034088416546e-05, "loss": 4.3074, "step": 16869 }, { "epoch": 0.515271838729383, "grad_norm": 0.3895944356918335, "learning_rate": 2.3801012701773154e-05, "loss": 4.1807, "step": 16870 }, { "epoch": 0.5153023824068418, "grad_norm": 0.3977919816970825, "learning_rate": 2.379861657293139e-05, "loss": 4.3174, "step": 16871 }, { "epoch": 0.5153329260843006, "grad_norm": 0.38853180408477783, "learning_rate": 2.379622045515138e-05, "loss": 4.1531, "step": 16872 }, { "epoch": 0.5153634697617593, "grad_norm": 0.40449219942092896, "learning_rate": 2.37938243484552e-05, "loss": 4.328, "step": 16873 }, { "epoch": 0.5153940134392181, "grad_norm": 0.3895971477031708, "learning_rate": 2.379142825286489e-05, "loss": 4.2529, "step": 16874 }, { "epoch": 0.5154245571166769, "grad_norm": 0.39833641052246094, "learning_rate": 2.3789032168402526e-05, "loss": 4.318, "step": 16875 }, { "epoch": 0.5154551007941356, "grad_norm": 0.39154165983200073, "learning_rate": 2.378663609509017e-05, "loss": 4.2234, "step": 16876 }, { "epoch": 0.5154856444715944, "grad_norm": 0.39467498660087585, "learning_rate": 2.3784240032949867e-05, "loss": 4.3467, "step": 16877 }, { "epoch": 0.5155161881490532, "grad_norm": 0.3907918334007263, "learning_rate": 2.3781843982003694e-05, "loss": 4.3107, "step": 16878 }, { "epoch": 0.5155467318265119, "grad_norm": 0.38615408539772034, "learning_rate": 2.3779447942273718e-05, "loss": 4.1756, "step": 16879 }, { "epoch": 0.5155772755039707, "grad_norm": 0.3959985673427582, "learning_rate": 2.3777051913781982e-05, "loss": 4.3005, "step": 16880 }, { "epoch": 0.5156078191814294, "grad_norm": 0.3958488702774048, "learning_rate": 2.377465589655057e-05, "loss": 4.2657, "step": 16881 }, { "epoch": 0.5156383628588882, "grad_norm": 0.39626097679138184, "learning_rate": 2.3772259890601517e-05, "loss": 4.2784, "step": 16882 }, { "epoch": 0.515668906536347, "grad_norm": 0.3873476982116699, "learning_rate": 2.3769863895956906e-05, "loss": 4.2558, "step": 16883 }, { "epoch": 0.5156994502138057, "grad_norm": 0.393900066614151, "learning_rate": 2.3767467912638795e-05, "loss": 4.0836, "step": 16884 }, { "epoch": 0.5157299938912645, "grad_norm": 0.3850999176502228, "learning_rate": 2.3765071940669236e-05, "loss": 4.2542, "step": 16885 }, { "epoch": 0.5157605375687233, "grad_norm": 0.3905242681503296, "learning_rate": 2.3762675980070287e-05, "loss": 4.3089, "step": 16886 }, { "epoch": 0.515791081246182, "grad_norm": 0.3953069746494293, "learning_rate": 2.376028003086403e-05, "loss": 4.2731, "step": 16887 }, { "epoch": 0.5158216249236408, "grad_norm": 0.4005531668663025, "learning_rate": 2.3757884093072503e-05, "loss": 4.2605, "step": 16888 }, { "epoch": 0.5158521686010996, "grad_norm": 0.3831935524940491, "learning_rate": 2.3755488166717772e-05, "loss": 4.2879, "step": 16889 }, { "epoch": 0.5158827122785583, "grad_norm": 0.3843670189380646, "learning_rate": 2.3753092251821915e-05, "loss": 4.359, "step": 16890 }, { "epoch": 0.5159132559560171, "grad_norm": 0.39167001843452454, "learning_rate": 2.3750696348406974e-05, "loss": 4.295, "step": 16891 }, { "epoch": 0.5159437996334759, "grad_norm": 0.38892173767089844, "learning_rate": 2.3748300456495004e-05, "loss": 4.3144, "step": 16892 }, { "epoch": 0.5159743433109346, "grad_norm": 0.38703152537345886, "learning_rate": 2.374590457610809e-05, "loss": 4.3064, "step": 16893 }, { "epoch": 0.5160048869883934, "grad_norm": 0.40604352951049805, "learning_rate": 2.3743508707268268e-05, "loss": 4.3266, "step": 16894 }, { "epoch": 0.5160354306658522, "grad_norm": 0.3782370090484619, "learning_rate": 2.37411128499976e-05, "loss": 4.2894, "step": 16895 }, { "epoch": 0.5160659743433109, "grad_norm": 0.38029882311820984, "learning_rate": 2.3738717004318174e-05, "loss": 4.3767, "step": 16896 }, { "epoch": 0.5160965180207697, "grad_norm": 0.3932530879974365, "learning_rate": 2.373632117025201e-05, "loss": 4.2369, "step": 16897 }, { "epoch": 0.5161270616982284, "grad_norm": 0.39317938685417175, "learning_rate": 2.37339253478212e-05, "loss": 4.2304, "step": 16898 }, { "epoch": 0.5161576053756872, "grad_norm": 0.3988128900527954, "learning_rate": 2.373152953704779e-05, "loss": 4.3524, "step": 16899 }, { "epoch": 0.516188149053146, "grad_norm": 0.3918786644935608, "learning_rate": 2.372913373795383e-05, "loss": 4.1663, "step": 16900 }, { "epoch": 0.5162186927306047, "grad_norm": 0.3934394121170044, "learning_rate": 2.37267379505614e-05, "loss": 4.294, "step": 16901 }, { "epoch": 0.5162492364080635, "grad_norm": 0.39642277359962463, "learning_rate": 2.3724342174892535e-05, "loss": 4.2122, "step": 16902 }, { "epoch": 0.5162797800855223, "grad_norm": 0.3987198770046234, "learning_rate": 2.372194641096931e-05, "loss": 4.3008, "step": 16903 }, { "epoch": 0.516310323762981, "grad_norm": 0.3905619978904724, "learning_rate": 2.3719550658813792e-05, "loss": 4.2472, "step": 16904 }, { "epoch": 0.5163408674404398, "grad_norm": 0.3966327905654907, "learning_rate": 2.371715491844802e-05, "loss": 4.2285, "step": 16905 }, { "epoch": 0.5163714111178986, "grad_norm": 0.4010481536388397, "learning_rate": 2.3714759189894063e-05, "loss": 4.2687, "step": 16906 }, { "epoch": 0.5164019547953573, "grad_norm": 0.40386152267456055, "learning_rate": 2.371236347317399e-05, "loss": 4.2361, "step": 16907 }, { "epoch": 0.5164324984728161, "grad_norm": 0.40653344988822937, "learning_rate": 2.370996776830984e-05, "loss": 4.2977, "step": 16908 }, { "epoch": 0.5164630421502749, "grad_norm": 0.38927343487739563, "learning_rate": 2.3707572075323672e-05, "loss": 4.267, "step": 16909 }, { "epoch": 0.5164935858277336, "grad_norm": 0.3977777659893036, "learning_rate": 2.3705176394237566e-05, "loss": 4.2862, "step": 16910 }, { "epoch": 0.5165241295051924, "grad_norm": 0.40396732091903687, "learning_rate": 2.3702780725073557e-05, "loss": 4.3287, "step": 16911 }, { "epoch": 0.5165546731826511, "grad_norm": 0.40262505412101746, "learning_rate": 2.3700385067853726e-05, "loss": 4.2713, "step": 16912 }, { "epoch": 0.5165852168601099, "grad_norm": 0.40035194158554077, "learning_rate": 2.36979894226001e-05, "loss": 4.1617, "step": 16913 }, { "epoch": 0.5166157605375687, "grad_norm": 0.4095413386821747, "learning_rate": 2.3695593789334765e-05, "loss": 4.2801, "step": 16914 }, { "epoch": 0.5166463042150274, "grad_norm": 0.3938795030117035, "learning_rate": 2.369319816807977e-05, "loss": 4.2375, "step": 16915 }, { "epoch": 0.5166768478924862, "grad_norm": 0.3891791105270386, "learning_rate": 2.369080255885717e-05, "loss": 4.3407, "step": 16916 }, { "epoch": 0.516707391569945, "grad_norm": 0.38683903217315674, "learning_rate": 2.368840696168902e-05, "loss": 4.2278, "step": 16917 }, { "epoch": 0.5167379352474037, "grad_norm": 0.39888623356819153, "learning_rate": 2.3686011376597387e-05, "loss": 4.3062, "step": 16918 }, { "epoch": 0.5167684789248626, "grad_norm": 0.3994083106517792, "learning_rate": 2.3683615803604317e-05, "loss": 4.1386, "step": 16919 }, { "epoch": 0.5167990226023214, "grad_norm": 0.39262908697128296, "learning_rate": 2.368122024273187e-05, "loss": 4.3571, "step": 16920 }, { "epoch": 0.51682956627978, "grad_norm": 0.3983030915260315, "learning_rate": 2.367882469400212e-05, "loss": 4.2605, "step": 16921 }, { "epoch": 0.5168601099572389, "grad_norm": 0.40427932143211365, "learning_rate": 2.3676429157437104e-05, "loss": 4.406, "step": 16922 }, { "epoch": 0.5168906536346977, "grad_norm": 0.3923923373222351, "learning_rate": 2.367403363305888e-05, "loss": 4.2994, "step": 16923 }, { "epoch": 0.5169211973121564, "grad_norm": 0.4079344868659973, "learning_rate": 2.367163812088952e-05, "loss": 4.2231, "step": 16924 }, { "epoch": 0.5169517409896152, "grad_norm": 0.38785049319267273, "learning_rate": 2.366924262095106e-05, "loss": 4.3641, "step": 16925 }, { "epoch": 0.516982284667074, "grad_norm": 0.4153934121131897, "learning_rate": 2.3666847133265568e-05, "loss": 4.3768, "step": 16926 }, { "epoch": 0.5170128283445327, "grad_norm": 0.39878907799720764, "learning_rate": 2.366445165785511e-05, "loss": 4.2859, "step": 16927 }, { "epoch": 0.5170433720219915, "grad_norm": 0.398585706949234, "learning_rate": 2.3662056194741722e-05, "loss": 4.235, "step": 16928 }, { "epoch": 0.5170739156994502, "grad_norm": 0.39310744404792786, "learning_rate": 2.3659660743947483e-05, "loss": 4.2391, "step": 16929 }, { "epoch": 0.517104459376909, "grad_norm": 0.3920597732067108, "learning_rate": 2.365726530549443e-05, "loss": 4.3157, "step": 16930 }, { "epoch": 0.5171350030543678, "grad_norm": 0.3934909701347351, "learning_rate": 2.3654869879404617e-05, "loss": 4.3399, "step": 16931 }, { "epoch": 0.5171655467318265, "grad_norm": 0.3926798403263092, "learning_rate": 2.3652474465700124e-05, "loss": 4.1401, "step": 16932 }, { "epoch": 0.5171960904092853, "grad_norm": 0.38840237259864807, "learning_rate": 2.3650079064402976e-05, "loss": 4.304, "step": 16933 }, { "epoch": 0.5172266340867441, "grad_norm": 0.38885173201560974, "learning_rate": 2.3647683675535248e-05, "loss": 4.3068, "step": 16934 }, { "epoch": 0.5172571777642028, "grad_norm": 0.38347265124320984, "learning_rate": 2.3645288299119002e-05, "loss": 4.2539, "step": 16935 }, { "epoch": 0.5172877214416616, "grad_norm": 0.4009738266468048, "learning_rate": 2.364289293517627e-05, "loss": 4.2877, "step": 16936 }, { "epoch": 0.5173182651191204, "grad_norm": 0.4211263656616211, "learning_rate": 2.364049758372913e-05, "loss": 4.3233, "step": 16937 }, { "epoch": 0.5173488087965791, "grad_norm": 0.3852934241294861, "learning_rate": 2.3638102244799625e-05, "loss": 4.2136, "step": 16938 }, { "epoch": 0.5173793524740379, "grad_norm": 0.39310622215270996, "learning_rate": 2.3635706918409813e-05, "loss": 4.1434, "step": 16939 }, { "epoch": 0.5174098961514967, "grad_norm": 0.4221212565898895, "learning_rate": 2.3633311604581743e-05, "loss": 4.3013, "step": 16940 }, { "epoch": 0.5174404398289554, "grad_norm": 0.39721477031707764, "learning_rate": 2.363091630333749e-05, "loss": 4.4242, "step": 16941 }, { "epoch": 0.5174709835064142, "grad_norm": 0.39397236704826355, "learning_rate": 2.3628521014699078e-05, "loss": 4.2563, "step": 16942 }, { "epoch": 0.517501527183873, "grad_norm": 0.40103670954704285, "learning_rate": 2.3626125738688583e-05, "loss": 4.3282, "step": 16943 }, { "epoch": 0.5175320708613317, "grad_norm": 0.39948517084121704, "learning_rate": 2.3623730475328064e-05, "loss": 4.2059, "step": 16944 }, { "epoch": 0.5175626145387905, "grad_norm": 0.40616145730018616, "learning_rate": 2.362133522463956e-05, "loss": 4.3095, "step": 16945 }, { "epoch": 0.5175931582162492, "grad_norm": 0.4075354039669037, "learning_rate": 2.361893998664513e-05, "loss": 4.2975, "step": 16946 }, { "epoch": 0.517623701893708, "grad_norm": 0.39351800084114075, "learning_rate": 2.3616544761366834e-05, "loss": 4.2908, "step": 16947 }, { "epoch": 0.5176542455711668, "grad_norm": 0.3944564461708069, "learning_rate": 2.361414954882671e-05, "loss": 4.2634, "step": 16948 }, { "epoch": 0.5176847892486255, "grad_norm": 0.40127548575401306, "learning_rate": 2.361175434904684e-05, "loss": 4.2437, "step": 16949 }, { "epoch": 0.5177153329260843, "grad_norm": 0.4082801640033722, "learning_rate": 2.360935916204925e-05, "loss": 4.3439, "step": 16950 }, { "epoch": 0.5177458766035431, "grad_norm": 0.3997398912906647, "learning_rate": 2.3606963987856e-05, "loss": 4.3471, "step": 16951 }, { "epoch": 0.5177764202810018, "grad_norm": 0.3876469135284424, "learning_rate": 2.3604568826489166e-05, "loss": 4.2343, "step": 16952 }, { "epoch": 0.5178069639584606, "grad_norm": 0.3921712338924408, "learning_rate": 2.3602173677970777e-05, "loss": 4.2917, "step": 16953 }, { "epoch": 0.5178375076359194, "grad_norm": 0.38131898641586304, "learning_rate": 2.3599778542322887e-05, "loss": 4.2364, "step": 16954 }, { "epoch": 0.5178680513133781, "grad_norm": 0.40926629304885864, "learning_rate": 2.3597383419567568e-05, "loss": 4.2176, "step": 16955 }, { "epoch": 0.5178985949908369, "grad_norm": 0.4032144546508789, "learning_rate": 2.3594988309726848e-05, "loss": 4.375, "step": 16956 }, { "epoch": 0.5179291386682957, "grad_norm": 0.3902854919433594, "learning_rate": 2.3592593212822794e-05, "loss": 4.2658, "step": 16957 }, { "epoch": 0.5179596823457544, "grad_norm": 0.41202449798583984, "learning_rate": 2.359019812887747e-05, "loss": 4.2886, "step": 16958 }, { "epoch": 0.5179902260232132, "grad_norm": 0.39500537514686584, "learning_rate": 2.3587803057912906e-05, "loss": 4.2697, "step": 16959 }, { "epoch": 0.518020769700672, "grad_norm": 0.3963448703289032, "learning_rate": 2.358540799995117e-05, "loss": 4.3041, "step": 16960 }, { "epoch": 0.5180513133781307, "grad_norm": 0.4016719162464142, "learning_rate": 2.3583012955014307e-05, "loss": 4.2866, "step": 16961 }, { "epoch": 0.5180818570555895, "grad_norm": 0.3947698175907135, "learning_rate": 2.3580617923124376e-05, "loss": 4.3138, "step": 16962 }, { "epoch": 0.5181124007330482, "grad_norm": 0.3934115171432495, "learning_rate": 2.357822290430343e-05, "loss": 4.2861, "step": 16963 }, { "epoch": 0.518142944410507, "grad_norm": 0.41074809432029724, "learning_rate": 2.357582789857351e-05, "loss": 4.305, "step": 16964 }, { "epoch": 0.5181734880879658, "grad_norm": 0.3914755582809448, "learning_rate": 2.357343290595667e-05, "loss": 4.2831, "step": 16965 }, { "epoch": 0.5182040317654245, "grad_norm": 0.39646098017692566, "learning_rate": 2.3571037926474974e-05, "loss": 4.3273, "step": 16966 }, { "epoch": 0.5182345754428833, "grad_norm": 0.3988714814186096, "learning_rate": 2.3568642960150462e-05, "loss": 4.2425, "step": 16967 }, { "epoch": 0.5182651191203421, "grad_norm": 0.4085433781147003, "learning_rate": 2.3566248007005192e-05, "loss": 4.2568, "step": 16968 }, { "epoch": 0.5182956627978008, "grad_norm": 0.4021753668785095, "learning_rate": 2.3563853067061216e-05, "loss": 4.2589, "step": 16969 }, { "epoch": 0.5183262064752596, "grad_norm": 0.40127700567245483, "learning_rate": 2.3561458140340582e-05, "loss": 4.2229, "step": 16970 }, { "epoch": 0.5183567501527184, "grad_norm": 0.3957216441631317, "learning_rate": 2.355906322686534e-05, "loss": 4.3059, "step": 16971 }, { "epoch": 0.5183872938301771, "grad_norm": 0.4012468159198761, "learning_rate": 2.3556668326657548e-05, "loss": 4.3732, "step": 16972 }, { "epoch": 0.5184178375076359, "grad_norm": 0.40454813838005066, "learning_rate": 2.355427343973925e-05, "loss": 4.2758, "step": 16973 }, { "epoch": 0.5184483811850947, "grad_norm": 0.3955692648887634, "learning_rate": 2.3551878566132492e-05, "loss": 4.2387, "step": 16974 }, { "epoch": 0.5184789248625534, "grad_norm": 0.39201414585113525, "learning_rate": 2.3549483705859347e-05, "loss": 4.2859, "step": 16975 }, { "epoch": 0.5185094685400122, "grad_norm": 0.39012786746025085, "learning_rate": 2.354708885894184e-05, "loss": 4.3362, "step": 16976 }, { "epoch": 0.518540012217471, "grad_norm": 0.4008357524871826, "learning_rate": 2.3544694025402042e-05, "loss": 4.2168, "step": 16977 }, { "epoch": 0.5185705558949297, "grad_norm": 0.3986007571220398, "learning_rate": 2.3542299205261996e-05, "loss": 4.195, "step": 16978 }, { "epoch": 0.5186010995723885, "grad_norm": 0.3887597620487213, "learning_rate": 2.3539904398543742e-05, "loss": 4.196, "step": 16979 }, { "epoch": 0.5186316432498472, "grad_norm": 0.39782077074050903, "learning_rate": 2.353750960526935e-05, "loss": 4.1704, "step": 16980 }, { "epoch": 0.518662186927306, "grad_norm": 0.403121680021286, "learning_rate": 2.3535114825460844e-05, "loss": 4.3405, "step": 16981 }, { "epoch": 0.5186927306047648, "grad_norm": 0.39495447278022766, "learning_rate": 2.353272005914029e-05, "loss": 4.3243, "step": 16982 }, { "epoch": 0.5187232742822235, "grad_norm": 0.4071181118488312, "learning_rate": 2.3530325306329752e-05, "loss": 4.2751, "step": 16983 }, { "epoch": 0.5187538179596823, "grad_norm": 0.4065418541431427, "learning_rate": 2.3527930567051252e-05, "loss": 4.3953, "step": 16984 }, { "epoch": 0.5187843616371411, "grad_norm": 0.3925236463546753, "learning_rate": 2.3525535841326855e-05, "loss": 4.1594, "step": 16985 }, { "epoch": 0.5188149053145998, "grad_norm": 0.38996121287345886, "learning_rate": 2.3523141129178614e-05, "loss": 4.3306, "step": 16986 }, { "epoch": 0.5188454489920586, "grad_norm": 0.3829202651977539, "learning_rate": 2.352074643062856e-05, "loss": 4.325, "step": 16987 }, { "epoch": 0.5188759926695174, "grad_norm": 0.38505497574806213, "learning_rate": 2.3518351745698758e-05, "loss": 4.2354, "step": 16988 }, { "epoch": 0.5189065363469761, "grad_norm": 0.4020123779773712, "learning_rate": 2.3515957074411264e-05, "loss": 4.2209, "step": 16989 }, { "epoch": 0.518937080024435, "grad_norm": 0.40379443764686584, "learning_rate": 2.3513562416788102e-05, "loss": 4.2516, "step": 16990 }, { "epoch": 0.5189676237018938, "grad_norm": 0.38587045669555664, "learning_rate": 2.3511167772851343e-05, "loss": 4.3432, "step": 16991 }, { "epoch": 0.5189981673793524, "grad_norm": 0.3881511688232422, "learning_rate": 2.3508773142623025e-05, "loss": 4.2056, "step": 16992 }, { "epoch": 0.5190287110568113, "grad_norm": 0.40980657935142517, "learning_rate": 2.35063785261252e-05, "loss": 4.2338, "step": 16993 }, { "epoch": 0.5190592547342701, "grad_norm": 0.40154725313186646, "learning_rate": 2.350398392337991e-05, "loss": 4.3372, "step": 16994 }, { "epoch": 0.5190897984117288, "grad_norm": 0.38712388277053833, "learning_rate": 2.3501589334409223e-05, "loss": 4.3094, "step": 16995 }, { "epoch": 0.5191203420891876, "grad_norm": 0.40826234221458435, "learning_rate": 2.349919475923516e-05, "loss": 4.2419, "step": 16996 }, { "epoch": 0.5191508857666463, "grad_norm": 0.399758517742157, "learning_rate": 2.3496800197879797e-05, "loss": 4.2797, "step": 16997 }, { "epoch": 0.5191814294441051, "grad_norm": 0.39809224009513855, "learning_rate": 2.3494405650365155e-05, "loss": 4.2732, "step": 16998 }, { "epoch": 0.5192119731215639, "grad_norm": 0.3959900438785553, "learning_rate": 2.3492011116713288e-05, "loss": 4.2759, "step": 16999 }, { "epoch": 0.5192425167990226, "grad_norm": 0.39465567469596863, "learning_rate": 2.3489616596946266e-05, "loss": 4.3129, "step": 17000 }, { "epoch": 0.5192730604764814, "grad_norm": 0.40422937273979187, "learning_rate": 2.3487222091086116e-05, "loss": 4.2363, "step": 17001 }, { "epoch": 0.5193036041539402, "grad_norm": 0.401166170835495, "learning_rate": 2.3484827599154884e-05, "loss": 4.3, "step": 17002 }, { "epoch": 0.5193341478313989, "grad_norm": 0.40027883648872375, "learning_rate": 2.3482433121174634e-05, "loss": 4.2753, "step": 17003 }, { "epoch": 0.5193646915088577, "grad_norm": 0.387844979763031, "learning_rate": 2.348003865716739e-05, "loss": 4.2209, "step": 17004 }, { "epoch": 0.5193952351863165, "grad_norm": 0.39035260677337646, "learning_rate": 2.3477644207155217e-05, "loss": 4.2747, "step": 17005 }, { "epoch": 0.5194257788637752, "grad_norm": 0.40656694769859314, "learning_rate": 2.3475249771160163e-05, "loss": 4.3957, "step": 17006 }, { "epoch": 0.519456322541234, "grad_norm": 0.3986187279224396, "learning_rate": 2.3472855349204258e-05, "loss": 4.282, "step": 17007 }, { "epoch": 0.5194868662186928, "grad_norm": 0.3991183340549469, "learning_rate": 2.3470460941309563e-05, "loss": 4.279, "step": 17008 }, { "epoch": 0.5195174098961515, "grad_norm": 0.3910673260688782, "learning_rate": 2.3468066547498126e-05, "loss": 4.197, "step": 17009 }, { "epoch": 0.5195479535736103, "grad_norm": 0.39883118867874146, "learning_rate": 2.346567216779198e-05, "loss": 4.3616, "step": 17010 }, { "epoch": 0.5195784972510691, "grad_norm": 0.39367806911468506, "learning_rate": 2.3463277802213178e-05, "loss": 4.2124, "step": 17011 }, { "epoch": 0.5196090409285278, "grad_norm": 0.402817040681839, "learning_rate": 2.3460883450783777e-05, "loss": 4.2534, "step": 17012 }, { "epoch": 0.5196395846059866, "grad_norm": 0.399275004863739, "learning_rate": 2.3458489113525802e-05, "loss": 4.326, "step": 17013 }, { "epoch": 0.5196701282834453, "grad_norm": 0.4055754542350769, "learning_rate": 2.3456094790461325e-05, "loss": 4.3076, "step": 17014 }, { "epoch": 0.5197006719609041, "grad_norm": 0.39346879720687866, "learning_rate": 2.345370048161236e-05, "loss": 4.3641, "step": 17015 }, { "epoch": 0.5197312156383629, "grad_norm": 0.3871077597141266, "learning_rate": 2.345130618700098e-05, "loss": 4.2986, "step": 17016 }, { "epoch": 0.5197617593158216, "grad_norm": 0.38857823610305786, "learning_rate": 2.3448911906649225e-05, "loss": 4.3264, "step": 17017 }, { "epoch": 0.5197923029932804, "grad_norm": 0.3992884159088135, "learning_rate": 2.3446517640579125e-05, "loss": 4.4047, "step": 17018 }, { "epoch": 0.5198228466707392, "grad_norm": 0.40373942255973816, "learning_rate": 2.3444123388812735e-05, "loss": 4.35, "step": 17019 }, { "epoch": 0.5198533903481979, "grad_norm": 0.4101135730743408, "learning_rate": 2.344172915137211e-05, "loss": 4.2719, "step": 17020 }, { "epoch": 0.5198839340256567, "grad_norm": 0.38929176330566406, "learning_rate": 2.343933492827928e-05, "loss": 4.2576, "step": 17021 }, { "epoch": 0.5199144777031155, "grad_norm": 0.38204365968704224, "learning_rate": 2.343694071955629e-05, "loss": 4.3194, "step": 17022 }, { "epoch": 0.5199450213805742, "grad_norm": 0.393543541431427, "learning_rate": 2.3434546525225205e-05, "loss": 4.3565, "step": 17023 }, { "epoch": 0.519975565058033, "grad_norm": 0.3993774354457855, "learning_rate": 2.343215234530805e-05, "loss": 4.157, "step": 17024 }, { "epoch": 0.5200061087354918, "grad_norm": 0.3920222222805023, "learning_rate": 2.3429758179826866e-05, "loss": 4.2403, "step": 17025 }, { "epoch": 0.5200366524129505, "grad_norm": 0.3963533937931061, "learning_rate": 2.3427364028803718e-05, "loss": 4.351, "step": 17026 }, { "epoch": 0.5200671960904093, "grad_norm": 0.3930045962333679, "learning_rate": 2.342496989226063e-05, "loss": 4.3282, "step": 17027 }, { "epoch": 0.5200977397678681, "grad_norm": 0.40600496530532837, "learning_rate": 2.342257577021965e-05, "loss": 4.2665, "step": 17028 }, { "epoch": 0.5201282834453268, "grad_norm": 0.4156474173069, "learning_rate": 2.3420181662702838e-05, "loss": 4.317, "step": 17029 }, { "epoch": 0.5201588271227856, "grad_norm": 0.3934885561466217, "learning_rate": 2.3417787569732215e-05, "loss": 4.2578, "step": 17030 }, { "epoch": 0.5201893708002443, "grad_norm": 0.391811341047287, "learning_rate": 2.3415393491329847e-05, "loss": 4.2267, "step": 17031 }, { "epoch": 0.5202199144777031, "grad_norm": 0.39005574584007263, "learning_rate": 2.3412999427517757e-05, "loss": 4.2734, "step": 17032 }, { "epoch": 0.5202504581551619, "grad_norm": 0.39150333404541016, "learning_rate": 2.3410605378317992e-05, "loss": 4.285, "step": 17033 }, { "epoch": 0.5202810018326206, "grad_norm": 0.3982454538345337, "learning_rate": 2.3408211343752615e-05, "loss": 4.279, "step": 17034 }, { "epoch": 0.5203115455100794, "grad_norm": 0.3981057405471802, "learning_rate": 2.3405817323843642e-05, "loss": 4.2486, "step": 17035 }, { "epoch": 0.5203420891875382, "grad_norm": 0.3886571228504181, "learning_rate": 2.340342331861313e-05, "loss": 4.3102, "step": 17036 }, { "epoch": 0.5203726328649969, "grad_norm": 0.39777639508247375, "learning_rate": 2.340102932808313e-05, "loss": 4.2025, "step": 17037 }, { "epoch": 0.5204031765424557, "grad_norm": 0.39782828092575073, "learning_rate": 2.3398635352275662e-05, "loss": 4.2629, "step": 17038 }, { "epoch": 0.5204337202199145, "grad_norm": 0.3998251259326935, "learning_rate": 2.3396241391212792e-05, "loss": 4.3317, "step": 17039 }, { "epoch": 0.5204642638973732, "grad_norm": 0.4063655138015747, "learning_rate": 2.3393847444916552e-05, "loss": 4.3342, "step": 17040 }, { "epoch": 0.520494807574832, "grad_norm": 0.3929362893104553, "learning_rate": 2.339145351340898e-05, "loss": 4.4046, "step": 17041 }, { "epoch": 0.5205253512522908, "grad_norm": 0.38283252716064453, "learning_rate": 2.3389059596712116e-05, "loss": 4.2467, "step": 17042 }, { "epoch": 0.5205558949297495, "grad_norm": 0.3927852213382721, "learning_rate": 2.3386665694848023e-05, "loss": 4.3496, "step": 17043 }, { "epoch": 0.5205864386072083, "grad_norm": 0.3853228986263275, "learning_rate": 2.3384271807838717e-05, "loss": 4.207, "step": 17044 }, { "epoch": 0.5206169822846671, "grad_norm": 0.39184892177581787, "learning_rate": 2.338187793570625e-05, "loss": 4.2673, "step": 17045 }, { "epoch": 0.5206475259621258, "grad_norm": 0.4005049467086792, "learning_rate": 2.3379484078472678e-05, "loss": 4.2246, "step": 17046 }, { "epoch": 0.5206780696395846, "grad_norm": 0.39989203214645386, "learning_rate": 2.3377090236160022e-05, "loss": 4.2833, "step": 17047 }, { "epoch": 0.5207086133170433, "grad_norm": 0.4069465696811676, "learning_rate": 2.3374696408790332e-05, "loss": 4.2999, "step": 17048 }, { "epoch": 0.5207391569945021, "grad_norm": 0.39404165744781494, "learning_rate": 2.3372302596385648e-05, "loss": 4.2218, "step": 17049 }, { "epoch": 0.5207697006719609, "grad_norm": 0.39437901973724365, "learning_rate": 2.3369908798968005e-05, "loss": 4.2312, "step": 17050 }, { "epoch": 0.5208002443494196, "grad_norm": 0.39819958806037903, "learning_rate": 2.3367515016559457e-05, "loss": 4.3586, "step": 17051 }, { "epoch": 0.5208307880268784, "grad_norm": 0.40646854043006897, "learning_rate": 2.336512124918203e-05, "loss": 4.2421, "step": 17052 }, { "epoch": 0.5208613317043372, "grad_norm": 0.4004811942577362, "learning_rate": 2.3362727496857773e-05, "loss": 4.2787, "step": 17053 }, { "epoch": 0.5208918753817959, "grad_norm": 0.3955535590648651, "learning_rate": 2.3360333759608736e-05, "loss": 4.2893, "step": 17054 }, { "epoch": 0.5209224190592547, "grad_norm": 0.4034290015697479, "learning_rate": 2.3357940037456944e-05, "loss": 4.3008, "step": 17055 }, { "epoch": 0.5209529627367135, "grad_norm": 0.3951907455921173, "learning_rate": 2.3355546330424435e-05, "loss": 4.2258, "step": 17056 }, { "epoch": 0.5209835064141722, "grad_norm": 0.39514774084091187, "learning_rate": 2.3353152638533267e-05, "loss": 4.276, "step": 17057 }, { "epoch": 0.521014050091631, "grad_norm": 0.3886739909648895, "learning_rate": 2.3350758961805463e-05, "loss": 4.3549, "step": 17058 }, { "epoch": 0.5210445937690898, "grad_norm": 0.40272969007492065, "learning_rate": 2.3348365300263065e-05, "loss": 4.2937, "step": 17059 }, { "epoch": 0.5210751374465485, "grad_norm": 0.39699748158454895, "learning_rate": 2.3345971653928128e-05, "loss": 4.3043, "step": 17060 }, { "epoch": 0.5211056811240073, "grad_norm": 0.39039146900177, "learning_rate": 2.334357802282267e-05, "loss": 4.2697, "step": 17061 }, { "epoch": 0.521136224801466, "grad_norm": 0.4001983106136322, "learning_rate": 2.3341184406968756e-05, "loss": 4.1851, "step": 17062 }, { "epoch": 0.5211667684789248, "grad_norm": 0.39395150542259216, "learning_rate": 2.33387908063884e-05, "loss": 4.1369, "step": 17063 }, { "epoch": 0.5211973121563837, "grad_norm": 0.3921845555305481, "learning_rate": 2.3336397221103644e-05, "loss": 4.2979, "step": 17064 }, { "epoch": 0.5212278558338423, "grad_norm": 0.4070073962211609, "learning_rate": 2.333400365113655e-05, "loss": 4.3289, "step": 17065 }, { "epoch": 0.5212583995113012, "grad_norm": 0.40567153692245483, "learning_rate": 2.3331610096509128e-05, "loss": 4.2817, "step": 17066 }, { "epoch": 0.52128894318876, "grad_norm": 0.4064812660217285, "learning_rate": 2.3329216557243427e-05, "loss": 4.3134, "step": 17067 }, { "epoch": 0.5213194868662187, "grad_norm": 0.3930458724498749, "learning_rate": 2.3326823033361502e-05, "loss": 4.3184, "step": 17068 }, { "epoch": 0.5213500305436775, "grad_norm": 0.394859254360199, "learning_rate": 2.3324429524885368e-05, "loss": 4.3692, "step": 17069 }, { "epoch": 0.5213805742211363, "grad_norm": 0.393574059009552, "learning_rate": 2.3322036031837075e-05, "loss": 4.2775, "step": 17070 }, { "epoch": 0.521411117898595, "grad_norm": 0.3987980782985687, "learning_rate": 2.331964255423866e-05, "loss": 4.3175, "step": 17071 }, { "epoch": 0.5214416615760538, "grad_norm": 0.3943885862827301, "learning_rate": 2.3317249092112158e-05, "loss": 4.17, "step": 17072 }, { "epoch": 0.5214722052535126, "grad_norm": 0.39365631341934204, "learning_rate": 2.3314855645479607e-05, "loss": 4.3514, "step": 17073 }, { "epoch": 0.5215027489309713, "grad_norm": 0.3980093002319336, "learning_rate": 2.3312462214363056e-05, "loss": 4.2926, "step": 17074 }, { "epoch": 0.5215332926084301, "grad_norm": 0.40270569920539856, "learning_rate": 2.3310068798784522e-05, "loss": 4.2627, "step": 17075 }, { "epoch": 0.5215638362858889, "grad_norm": 0.39951691031455994, "learning_rate": 2.3307675398766054e-05, "loss": 4.2102, "step": 17076 }, { "epoch": 0.5215943799633476, "grad_norm": 0.39408209919929504, "learning_rate": 2.33052820143297e-05, "loss": 4.3545, "step": 17077 }, { "epoch": 0.5216249236408064, "grad_norm": 0.3898397386074066, "learning_rate": 2.3302888645497477e-05, "loss": 4.3055, "step": 17078 }, { "epoch": 0.5216554673182651, "grad_norm": 0.3863654136657715, "learning_rate": 2.3300495292291437e-05, "loss": 4.2171, "step": 17079 }, { "epoch": 0.5216860109957239, "grad_norm": 0.39478135108947754, "learning_rate": 2.3298101954733606e-05, "loss": 4.2616, "step": 17080 }, { "epoch": 0.5217165546731827, "grad_norm": 0.3984929919242859, "learning_rate": 2.329570863284602e-05, "loss": 4.3527, "step": 17081 }, { "epoch": 0.5217470983506414, "grad_norm": 0.4072570502758026, "learning_rate": 2.329331532665073e-05, "loss": 4.261, "step": 17082 }, { "epoch": 0.5217776420281002, "grad_norm": 0.4089201092720032, "learning_rate": 2.3290922036169758e-05, "loss": 4.2238, "step": 17083 }, { "epoch": 0.521808185705559, "grad_norm": 0.3922775983810425, "learning_rate": 2.3288528761425142e-05, "loss": 4.2733, "step": 17084 }, { "epoch": 0.5218387293830177, "grad_norm": 0.4066953659057617, "learning_rate": 2.3286135502438934e-05, "loss": 4.3543, "step": 17085 }, { "epoch": 0.5218692730604765, "grad_norm": 0.3854396939277649, "learning_rate": 2.3283742259233146e-05, "loss": 4.2263, "step": 17086 }, { "epoch": 0.5218998167379353, "grad_norm": 0.3973906636238098, "learning_rate": 2.328134903182983e-05, "loss": 4.2808, "step": 17087 }, { "epoch": 0.521930360415394, "grad_norm": 0.39682433009147644, "learning_rate": 2.3278955820251025e-05, "loss": 4.301, "step": 17088 }, { "epoch": 0.5219609040928528, "grad_norm": 0.39088207483291626, "learning_rate": 2.3276562624518743e-05, "loss": 4.2677, "step": 17089 }, { "epoch": 0.5219914477703116, "grad_norm": 0.38699227571487427, "learning_rate": 2.3274169444655038e-05, "loss": 4.2473, "step": 17090 }, { "epoch": 0.5220219914477703, "grad_norm": 0.3963116407394409, "learning_rate": 2.3271776280681956e-05, "loss": 4.2209, "step": 17091 }, { "epoch": 0.5220525351252291, "grad_norm": 0.39653414487838745, "learning_rate": 2.32693831326215e-05, "loss": 4.3101, "step": 17092 }, { "epoch": 0.5220830788026879, "grad_norm": 0.3966410458087921, "learning_rate": 2.3266990000495737e-05, "loss": 4.3095, "step": 17093 }, { "epoch": 0.5221136224801466, "grad_norm": 0.3951604962348938, "learning_rate": 2.3264596884326683e-05, "loss": 4.3931, "step": 17094 }, { "epoch": 0.5221441661576054, "grad_norm": 0.38904714584350586, "learning_rate": 2.326220378413638e-05, "loss": 4.2753, "step": 17095 }, { "epoch": 0.5221747098350641, "grad_norm": 0.3987729549407959, "learning_rate": 2.3259810699946866e-05, "loss": 4.2858, "step": 17096 }, { "epoch": 0.5222052535125229, "grad_norm": 0.3941957652568817, "learning_rate": 2.3257417631780156e-05, "loss": 4.2722, "step": 17097 }, { "epoch": 0.5222357971899817, "grad_norm": 0.39803770184516907, "learning_rate": 2.3255024579658303e-05, "loss": 4.2851, "step": 17098 }, { "epoch": 0.5222663408674404, "grad_norm": 0.3957825005054474, "learning_rate": 2.3252631543603343e-05, "loss": 4.3455, "step": 17099 }, { "epoch": 0.5222968845448992, "grad_norm": 0.3954923450946808, "learning_rate": 2.325023852363729e-05, "loss": 4.2654, "step": 17100 }, { "epoch": 0.522327428222358, "grad_norm": 0.41143420338630676, "learning_rate": 2.32478455197822e-05, "loss": 4.2257, "step": 17101 }, { "epoch": 0.5223579718998167, "grad_norm": 0.40542080998420715, "learning_rate": 2.3245452532060095e-05, "loss": 4.3063, "step": 17102 }, { "epoch": 0.5223885155772755, "grad_norm": 0.39029213786125183, "learning_rate": 2.3243059560493006e-05, "loss": 4.2584, "step": 17103 }, { "epoch": 0.5224190592547343, "grad_norm": 0.401745080947876, "learning_rate": 2.3240666605102973e-05, "loss": 4.3176, "step": 17104 }, { "epoch": 0.522449602932193, "grad_norm": 0.3951036334037781, "learning_rate": 2.3238273665912035e-05, "loss": 4.2588, "step": 17105 }, { "epoch": 0.5224801466096518, "grad_norm": 0.4010821282863617, "learning_rate": 2.3235880742942208e-05, "loss": 4.2555, "step": 17106 }, { "epoch": 0.5225106902871106, "grad_norm": 0.40176287293434143, "learning_rate": 2.3233487836215535e-05, "loss": 4.3117, "step": 17107 }, { "epoch": 0.5225412339645693, "grad_norm": 0.3953820466995239, "learning_rate": 2.3231094945754053e-05, "loss": 4.2664, "step": 17108 }, { "epoch": 0.5225717776420281, "grad_norm": 0.39402639865875244, "learning_rate": 2.3228702071579782e-05, "loss": 4.3467, "step": 17109 }, { "epoch": 0.5226023213194869, "grad_norm": 0.4141523838043213, "learning_rate": 2.3226309213714767e-05, "loss": 4.3487, "step": 17110 }, { "epoch": 0.5226328649969456, "grad_norm": 0.40111926198005676, "learning_rate": 2.322391637218104e-05, "loss": 4.249, "step": 17111 }, { "epoch": 0.5226634086744044, "grad_norm": 0.41139060258865356, "learning_rate": 2.3221523547000617e-05, "loss": 4.255, "step": 17112 }, { "epoch": 0.5226939523518631, "grad_norm": 0.4063100814819336, "learning_rate": 2.3219130738195554e-05, "loss": 4.265, "step": 17113 }, { "epoch": 0.5227244960293219, "grad_norm": 0.39371323585510254, "learning_rate": 2.321673794578786e-05, "loss": 4.2786, "step": 17114 }, { "epoch": 0.5227550397067807, "grad_norm": 0.39490628242492676, "learning_rate": 2.3214345169799574e-05, "loss": 4.3138, "step": 17115 }, { "epoch": 0.5227855833842394, "grad_norm": 0.39573320746421814, "learning_rate": 2.321195241025274e-05, "loss": 4.191, "step": 17116 }, { "epoch": 0.5228161270616982, "grad_norm": 0.4000847637653351, "learning_rate": 2.320955966716937e-05, "loss": 4.2438, "step": 17117 }, { "epoch": 0.522846670739157, "grad_norm": 0.3895086348056793, "learning_rate": 2.3207166940571508e-05, "loss": 4.3525, "step": 17118 }, { "epoch": 0.5228772144166157, "grad_norm": 0.41065922379493713, "learning_rate": 2.3204774230481193e-05, "loss": 4.3129, "step": 17119 }, { "epoch": 0.5229077580940745, "grad_norm": 0.3836015462875366, "learning_rate": 2.3202381536920427e-05, "loss": 4.2822, "step": 17120 }, { "epoch": 0.5229383017715333, "grad_norm": 0.3988349735736847, "learning_rate": 2.3199988859911262e-05, "loss": 4.2856, "step": 17121 }, { "epoch": 0.522968845448992, "grad_norm": 0.3908029794692993, "learning_rate": 2.3197596199475736e-05, "loss": 4.2292, "step": 17122 }, { "epoch": 0.5229993891264508, "grad_norm": 0.391384482383728, "learning_rate": 2.3195203555635856e-05, "loss": 4.2764, "step": 17123 }, { "epoch": 0.5230299328039096, "grad_norm": 0.39215511083602905, "learning_rate": 2.319281092841367e-05, "loss": 4.3859, "step": 17124 }, { "epoch": 0.5230604764813683, "grad_norm": 0.3871902823448181, "learning_rate": 2.3190418317831207e-05, "loss": 4.2458, "step": 17125 }, { "epoch": 0.5230910201588271, "grad_norm": 0.4021033048629761, "learning_rate": 2.318802572391049e-05, "loss": 4.3574, "step": 17126 }, { "epoch": 0.5231215638362859, "grad_norm": 0.40019768476486206, "learning_rate": 2.3185633146673547e-05, "loss": 4.2511, "step": 17127 }, { "epoch": 0.5231521075137446, "grad_norm": 0.39373403787612915, "learning_rate": 2.318324058614242e-05, "loss": 4.2007, "step": 17128 }, { "epoch": 0.5231826511912034, "grad_norm": 0.42614564299583435, "learning_rate": 2.3180848042339123e-05, "loss": 4.257, "step": 17129 }, { "epoch": 0.5232131948686621, "grad_norm": 0.4359264075756073, "learning_rate": 2.3178455515285706e-05, "loss": 4.2689, "step": 17130 }, { "epoch": 0.5232437385461209, "grad_norm": 0.4005795419216156, "learning_rate": 2.317606300500417e-05, "loss": 4.2333, "step": 17131 }, { "epoch": 0.5232742822235797, "grad_norm": 0.4068372845649719, "learning_rate": 2.3173670511516566e-05, "loss": 4.126, "step": 17132 }, { "epoch": 0.5233048259010384, "grad_norm": 0.3964928388595581, "learning_rate": 2.3171278034844922e-05, "loss": 4.3052, "step": 17133 }, { "epoch": 0.5233353695784972, "grad_norm": 0.39073753356933594, "learning_rate": 2.316888557501126e-05, "loss": 4.2343, "step": 17134 }, { "epoch": 0.523365913255956, "grad_norm": 0.4051881432533264, "learning_rate": 2.31664931320376e-05, "loss": 4.246, "step": 17135 }, { "epoch": 0.5233964569334147, "grad_norm": 0.4389544129371643, "learning_rate": 2.3164100705945997e-05, "loss": 4.3201, "step": 17136 }, { "epoch": 0.5234270006108735, "grad_norm": 0.3897213339805603, "learning_rate": 2.3161708296758448e-05, "loss": 4.2335, "step": 17137 }, { "epoch": 0.5234575442883324, "grad_norm": 0.4035385251045227, "learning_rate": 2.3159315904496995e-05, "loss": 4.3044, "step": 17138 }, { "epoch": 0.523488087965791, "grad_norm": 0.3934761583805084, "learning_rate": 2.315692352918368e-05, "loss": 4.3724, "step": 17139 }, { "epoch": 0.5235186316432499, "grad_norm": 0.40387478470802307, "learning_rate": 2.3154531170840506e-05, "loss": 4.3213, "step": 17140 }, { "epoch": 0.5235491753207087, "grad_norm": 0.3966476321220398, "learning_rate": 2.3152138829489518e-05, "loss": 4.2162, "step": 17141 }, { "epoch": 0.5235797189981674, "grad_norm": 0.40278398990631104, "learning_rate": 2.3149746505152742e-05, "loss": 4.2614, "step": 17142 }, { "epoch": 0.5236102626756262, "grad_norm": 0.40028876066207886, "learning_rate": 2.314735419785219e-05, "loss": 4.2689, "step": 17143 }, { "epoch": 0.523640806353085, "grad_norm": 0.3899601399898529, "learning_rate": 2.3144961907609904e-05, "loss": 4.2967, "step": 17144 }, { "epoch": 0.5236713500305437, "grad_norm": 0.38812658190727234, "learning_rate": 2.3142569634447918e-05, "loss": 4.341, "step": 17145 }, { "epoch": 0.5237018937080025, "grad_norm": 0.4000588357448578, "learning_rate": 2.3140177378388235e-05, "loss": 4.2855, "step": 17146 }, { "epoch": 0.5237324373854612, "grad_norm": 0.39406174421310425, "learning_rate": 2.3137785139452905e-05, "loss": 4.3483, "step": 17147 }, { "epoch": 0.52376298106292, "grad_norm": 0.3966740071773529, "learning_rate": 2.313539291766394e-05, "loss": 4.3088, "step": 17148 }, { "epoch": 0.5237935247403788, "grad_norm": 0.3947462737560272, "learning_rate": 2.313300071304337e-05, "loss": 4.3294, "step": 17149 }, { "epoch": 0.5238240684178375, "grad_norm": 0.38884633779525757, "learning_rate": 2.3130608525613228e-05, "loss": 4.2533, "step": 17150 }, { "epoch": 0.5238546120952963, "grad_norm": 0.41885676980018616, "learning_rate": 2.3128216355395526e-05, "loss": 4.3336, "step": 17151 }, { "epoch": 0.5238851557727551, "grad_norm": 0.39544686675071716, "learning_rate": 2.31258242024123e-05, "loss": 4.2323, "step": 17152 }, { "epoch": 0.5239156994502138, "grad_norm": 0.3940523564815521, "learning_rate": 2.3123432066685583e-05, "loss": 4.2818, "step": 17153 }, { "epoch": 0.5239462431276726, "grad_norm": 0.3874437212944031, "learning_rate": 2.312103994823738e-05, "loss": 4.2021, "step": 17154 }, { "epoch": 0.5239767868051314, "grad_norm": 0.395117849111557, "learning_rate": 2.311864784708973e-05, "loss": 4.3238, "step": 17155 }, { "epoch": 0.5240073304825901, "grad_norm": 0.4034319818019867, "learning_rate": 2.3116255763264666e-05, "loss": 4.2131, "step": 17156 }, { "epoch": 0.5240378741600489, "grad_norm": 0.3909439444541931, "learning_rate": 2.3113863696784198e-05, "loss": 4.3483, "step": 17157 }, { "epoch": 0.5240684178375077, "grad_norm": 0.39418119192123413, "learning_rate": 2.311147164767035e-05, "loss": 4.1639, "step": 17158 }, { "epoch": 0.5240989615149664, "grad_norm": 0.3914026618003845, "learning_rate": 2.310907961594517e-05, "loss": 4.219, "step": 17159 }, { "epoch": 0.5241295051924252, "grad_norm": 0.3989231288433075, "learning_rate": 2.310668760163065e-05, "loss": 4.3413, "step": 17160 }, { "epoch": 0.524160048869884, "grad_norm": 0.40483057498931885, "learning_rate": 2.3104295604748834e-05, "loss": 4.3717, "step": 17161 }, { "epoch": 0.5241905925473427, "grad_norm": 0.3866084814071655, "learning_rate": 2.3101903625321753e-05, "loss": 4.2857, "step": 17162 }, { "epoch": 0.5242211362248015, "grad_norm": 0.3875280022621155, "learning_rate": 2.3099511663371408e-05, "loss": 4.293, "step": 17163 }, { "epoch": 0.5242516799022602, "grad_norm": 0.39381495118141174, "learning_rate": 2.3097119718919852e-05, "loss": 4.3687, "step": 17164 }, { "epoch": 0.524282223579719, "grad_norm": 0.38798990845680237, "learning_rate": 2.3094727791989082e-05, "loss": 4.2783, "step": 17165 }, { "epoch": 0.5243127672571778, "grad_norm": 0.3987607955932617, "learning_rate": 2.3092335882601133e-05, "loss": 4.3232, "step": 17166 }, { "epoch": 0.5243433109346365, "grad_norm": 0.3872123658657074, "learning_rate": 2.3089943990778035e-05, "loss": 4.2858, "step": 17167 }, { "epoch": 0.5243738546120953, "grad_norm": 0.3962055444717407, "learning_rate": 2.3087552116541794e-05, "loss": 4.3278, "step": 17168 }, { "epoch": 0.5244043982895541, "grad_norm": 0.39633724093437195, "learning_rate": 2.3085160259914446e-05, "loss": 4.2372, "step": 17169 }, { "epoch": 0.5244349419670128, "grad_norm": 0.38961297273635864, "learning_rate": 2.308276842091802e-05, "loss": 4.2783, "step": 17170 }, { "epoch": 0.5244654856444716, "grad_norm": 0.4047028720378876, "learning_rate": 2.3080376599574523e-05, "loss": 4.3292, "step": 17171 }, { "epoch": 0.5244960293219304, "grad_norm": 0.4097861349582672, "learning_rate": 2.3077984795905992e-05, "loss": 4.3462, "step": 17172 }, { "epoch": 0.5245265729993891, "grad_norm": 0.3940255045890808, "learning_rate": 2.3075593009934447e-05, "loss": 4.2826, "step": 17173 }, { "epoch": 0.5245571166768479, "grad_norm": 0.4013235569000244, "learning_rate": 2.3073201241681892e-05, "loss": 4.1331, "step": 17174 }, { "epoch": 0.5245876603543067, "grad_norm": 0.39631187915802, "learning_rate": 2.307080949117037e-05, "loss": 4.3196, "step": 17175 }, { "epoch": 0.5246182040317654, "grad_norm": 0.40312716364860535, "learning_rate": 2.3068417758421904e-05, "loss": 4.259, "step": 17176 }, { "epoch": 0.5246487477092242, "grad_norm": 0.4052020013332367, "learning_rate": 2.30660260434585e-05, "loss": 4.3211, "step": 17177 }, { "epoch": 0.524679291386683, "grad_norm": 0.3922213912010193, "learning_rate": 2.3063634346302184e-05, "loss": 4.2936, "step": 17178 }, { "epoch": 0.5247098350641417, "grad_norm": 0.3864261209964752, "learning_rate": 2.3061242666974997e-05, "loss": 4.2973, "step": 17179 }, { "epoch": 0.5247403787416005, "grad_norm": 0.3908592164516449, "learning_rate": 2.305885100549894e-05, "loss": 4.3278, "step": 17180 }, { "epoch": 0.5247709224190592, "grad_norm": 0.3908024728298187, "learning_rate": 2.305645936189604e-05, "loss": 4.2436, "step": 17181 }, { "epoch": 0.524801466096518, "grad_norm": 0.3944041430950165, "learning_rate": 2.3054067736188318e-05, "loss": 4.3563, "step": 17182 }, { "epoch": 0.5248320097739768, "grad_norm": 0.3908618092536926, "learning_rate": 2.305167612839779e-05, "loss": 4.3348, "step": 17183 }, { "epoch": 0.5248625534514355, "grad_norm": 0.3903408348560333, "learning_rate": 2.3049284538546488e-05, "loss": 4.1806, "step": 17184 }, { "epoch": 0.5248930971288943, "grad_norm": 0.39576980471611023, "learning_rate": 2.3046892966656418e-05, "loss": 4.1397, "step": 17185 }, { "epoch": 0.5249236408063531, "grad_norm": 0.39588698744773865, "learning_rate": 2.304450141274961e-05, "loss": 4.2243, "step": 17186 }, { "epoch": 0.5249541844838118, "grad_norm": 0.4006788432598114, "learning_rate": 2.3042109876848096e-05, "loss": 4.332, "step": 17187 }, { "epoch": 0.5249847281612706, "grad_norm": 0.39031702280044556, "learning_rate": 2.3039718358973872e-05, "loss": 4.3708, "step": 17188 }, { "epoch": 0.5250152718387294, "grad_norm": 0.3921090364456177, "learning_rate": 2.3037326859148966e-05, "loss": 4.1763, "step": 17189 }, { "epoch": 0.5250458155161881, "grad_norm": 0.3920438587665558, "learning_rate": 2.3034935377395416e-05, "loss": 4.248, "step": 17190 }, { "epoch": 0.5250763591936469, "grad_norm": 0.39777281880378723, "learning_rate": 2.3032543913735207e-05, "loss": 4.3332, "step": 17191 }, { "epoch": 0.5251069028711057, "grad_norm": 0.400465190410614, "learning_rate": 2.3030152468190384e-05, "loss": 4.3416, "step": 17192 }, { "epoch": 0.5251374465485644, "grad_norm": 0.4014144241809845, "learning_rate": 2.302776104078297e-05, "loss": 4.203, "step": 17193 }, { "epoch": 0.5251679902260232, "grad_norm": 0.4014131426811218, "learning_rate": 2.302536963153496e-05, "loss": 4.2483, "step": 17194 }, { "epoch": 0.525198533903482, "grad_norm": 0.41798993945121765, "learning_rate": 2.3022978240468394e-05, "loss": 4.2193, "step": 17195 }, { "epoch": 0.5252290775809407, "grad_norm": 0.39953166246414185, "learning_rate": 2.3020586867605283e-05, "loss": 4.3653, "step": 17196 }, { "epoch": 0.5252596212583995, "grad_norm": 0.3959800899028778, "learning_rate": 2.301819551296765e-05, "loss": 4.2749, "step": 17197 }, { "epoch": 0.5252901649358582, "grad_norm": 0.4027783274650574, "learning_rate": 2.3015804176577515e-05, "loss": 4.2139, "step": 17198 }, { "epoch": 0.525320708613317, "grad_norm": 0.4087359309196472, "learning_rate": 2.3013412858456876e-05, "loss": 4.2657, "step": 17199 }, { "epoch": 0.5253512522907758, "grad_norm": 0.38810843229293823, "learning_rate": 2.3011021558627768e-05, "loss": 4.2647, "step": 17200 }, { "epoch": 0.5253817959682345, "grad_norm": 0.3939962685108185, "learning_rate": 2.300863027711222e-05, "loss": 4.3285, "step": 17201 }, { "epoch": 0.5254123396456933, "grad_norm": 0.38786253333091736, "learning_rate": 2.3006239013932225e-05, "loss": 4.2474, "step": 17202 }, { "epoch": 0.5254428833231521, "grad_norm": 0.3942965865135193, "learning_rate": 2.3003847769109816e-05, "loss": 4.2669, "step": 17203 }, { "epoch": 0.5254734270006108, "grad_norm": 0.3864176273345947, "learning_rate": 2.300145654266701e-05, "loss": 4.3094, "step": 17204 }, { "epoch": 0.5255039706780696, "grad_norm": 0.40093186497688293, "learning_rate": 2.299906533462582e-05, "loss": 4.309, "step": 17205 }, { "epoch": 0.5255345143555284, "grad_norm": 0.40359026193618774, "learning_rate": 2.2996674145008258e-05, "loss": 4.3222, "step": 17206 }, { "epoch": 0.5255650580329871, "grad_norm": 0.39797094464302063, "learning_rate": 2.2994282973836356e-05, "loss": 4.3545, "step": 17207 }, { "epoch": 0.525595601710446, "grad_norm": 0.3979036211967468, "learning_rate": 2.2991891821132114e-05, "loss": 4.275, "step": 17208 }, { "epoch": 0.5256261453879048, "grad_norm": 0.38834047317504883, "learning_rate": 2.2989500686917558e-05, "loss": 4.1435, "step": 17209 }, { "epoch": 0.5256566890653634, "grad_norm": 0.40532466769218445, "learning_rate": 2.298710957121471e-05, "loss": 4.2593, "step": 17210 }, { "epoch": 0.5256872327428223, "grad_norm": 0.3981987535953522, "learning_rate": 2.2984718474045573e-05, "loss": 4.2708, "step": 17211 }, { "epoch": 0.525717776420281, "grad_norm": 0.4034743010997772, "learning_rate": 2.2982327395432174e-05, "loss": 4.2982, "step": 17212 }, { "epoch": 0.5257483200977398, "grad_norm": 0.40294328331947327, "learning_rate": 2.297993633539652e-05, "loss": 4.2824, "step": 17213 }, { "epoch": 0.5257788637751986, "grad_norm": 0.3903157413005829, "learning_rate": 2.2977545293960627e-05, "loss": 4.3159, "step": 17214 }, { "epoch": 0.5258094074526573, "grad_norm": 0.38586121797561646, "learning_rate": 2.2975154271146526e-05, "loss": 4.3806, "step": 17215 }, { "epoch": 0.5258399511301161, "grad_norm": 0.4034113883972168, "learning_rate": 2.297276326697621e-05, "loss": 4.1518, "step": 17216 }, { "epoch": 0.5258704948075749, "grad_norm": 0.3944297432899475, "learning_rate": 2.2970372281471704e-05, "loss": 4.3176, "step": 17217 }, { "epoch": 0.5259010384850336, "grad_norm": 0.39265674352645874, "learning_rate": 2.2967981314655036e-05, "loss": 4.3612, "step": 17218 }, { "epoch": 0.5259315821624924, "grad_norm": 0.3921995759010315, "learning_rate": 2.2965590366548194e-05, "loss": 4.3379, "step": 17219 }, { "epoch": 0.5259621258399512, "grad_norm": 0.40163472294807434, "learning_rate": 2.2963199437173218e-05, "loss": 4.2796, "step": 17220 }, { "epoch": 0.5259926695174099, "grad_norm": 0.3991311192512512, "learning_rate": 2.2960808526552113e-05, "loss": 4.2801, "step": 17221 }, { "epoch": 0.5260232131948687, "grad_norm": 0.4030067026615143, "learning_rate": 2.2958417634706883e-05, "loss": 4.2511, "step": 17222 }, { "epoch": 0.5260537568723275, "grad_norm": 0.38554489612579346, "learning_rate": 2.295602676165955e-05, "loss": 4.277, "step": 17223 }, { "epoch": 0.5260843005497862, "grad_norm": 0.4010355770587921, "learning_rate": 2.2953635907432145e-05, "loss": 4.247, "step": 17224 }, { "epoch": 0.526114844227245, "grad_norm": 0.3971039652824402, "learning_rate": 2.2951245072046652e-05, "loss": 4.2001, "step": 17225 }, { "epoch": 0.5261453879047038, "grad_norm": 0.3979131281375885, "learning_rate": 2.2948854255525107e-05, "loss": 4.3286, "step": 17226 }, { "epoch": 0.5261759315821625, "grad_norm": 0.38976016640663147, "learning_rate": 2.294646345788951e-05, "loss": 4.3427, "step": 17227 }, { "epoch": 0.5262064752596213, "grad_norm": 0.3931601345539093, "learning_rate": 2.2944072679161886e-05, "loss": 4.3628, "step": 17228 }, { "epoch": 0.52623701893708, "grad_norm": 0.39306145906448364, "learning_rate": 2.2941681919364244e-05, "loss": 4.3159, "step": 17229 }, { "epoch": 0.5262675626145388, "grad_norm": 0.39461249113082886, "learning_rate": 2.2939291178518585e-05, "loss": 4.3125, "step": 17230 }, { "epoch": 0.5262981062919976, "grad_norm": 0.4086866080760956, "learning_rate": 2.293690045664693e-05, "loss": 4.3139, "step": 17231 }, { "epoch": 0.5263286499694563, "grad_norm": 0.4063190519809723, "learning_rate": 2.2934509753771306e-05, "loss": 4.2968, "step": 17232 }, { "epoch": 0.5263591936469151, "grad_norm": 0.391179621219635, "learning_rate": 2.2932119069913702e-05, "loss": 4.2851, "step": 17233 }, { "epoch": 0.5263897373243739, "grad_norm": 0.384371817111969, "learning_rate": 2.2929728405096145e-05, "loss": 4.1981, "step": 17234 }, { "epoch": 0.5264202810018326, "grad_norm": 0.38777756690979004, "learning_rate": 2.2927337759340644e-05, "loss": 4.2464, "step": 17235 }, { "epoch": 0.5264508246792914, "grad_norm": 0.4110466539859772, "learning_rate": 2.2924947132669212e-05, "loss": 4.2071, "step": 17236 }, { "epoch": 0.5264813683567502, "grad_norm": 0.4025261104106903, "learning_rate": 2.2922556525103848e-05, "loss": 4.2557, "step": 17237 }, { "epoch": 0.5265119120342089, "grad_norm": 0.3980015218257904, "learning_rate": 2.292016593666659e-05, "loss": 4.3031, "step": 17238 }, { "epoch": 0.5265424557116677, "grad_norm": 0.38740482926368713, "learning_rate": 2.2917775367379417e-05, "loss": 4.3357, "step": 17239 }, { "epoch": 0.5265729993891265, "grad_norm": 0.3859798312187195, "learning_rate": 2.291538481726436e-05, "loss": 4.2615, "step": 17240 }, { "epoch": 0.5266035430665852, "grad_norm": 0.4057469666004181, "learning_rate": 2.291299428634344e-05, "loss": 4.3836, "step": 17241 }, { "epoch": 0.526634086744044, "grad_norm": 0.3910676836967468, "learning_rate": 2.2910603774638643e-05, "loss": 4.2338, "step": 17242 }, { "epoch": 0.5266646304215028, "grad_norm": 0.39305147528648376, "learning_rate": 2.2908213282171995e-05, "loss": 4.2549, "step": 17243 }, { "epoch": 0.5266951740989615, "grad_norm": 0.39457687735557556, "learning_rate": 2.2905822808965508e-05, "loss": 4.3403, "step": 17244 }, { "epoch": 0.5267257177764203, "grad_norm": 0.3988508880138397, "learning_rate": 2.2903432355041177e-05, "loss": 4.287, "step": 17245 }, { "epoch": 0.526756261453879, "grad_norm": 0.4215378761291504, "learning_rate": 2.2901041920421032e-05, "loss": 4.2815, "step": 17246 }, { "epoch": 0.5267868051313378, "grad_norm": 0.39090514183044434, "learning_rate": 2.2898651505127066e-05, "loss": 4.2591, "step": 17247 }, { "epoch": 0.5268173488087966, "grad_norm": 0.3985687792301178, "learning_rate": 2.289626110918129e-05, "loss": 4.2809, "step": 17248 }, { "epoch": 0.5268478924862553, "grad_norm": 0.39593198895454407, "learning_rate": 2.2893870732605734e-05, "loss": 4.2838, "step": 17249 }, { "epoch": 0.5268784361637141, "grad_norm": 0.4093213379383087, "learning_rate": 2.2891480375422385e-05, "loss": 4.1735, "step": 17250 }, { "epoch": 0.5269089798411729, "grad_norm": 0.39549943804740906, "learning_rate": 2.288909003765326e-05, "loss": 4.2793, "step": 17251 }, { "epoch": 0.5269395235186316, "grad_norm": 0.4020281136035919, "learning_rate": 2.2886699719320375e-05, "loss": 4.3362, "step": 17252 }, { "epoch": 0.5269700671960904, "grad_norm": 0.4027918875217438, "learning_rate": 2.2884309420445727e-05, "loss": 4.2362, "step": 17253 }, { "epoch": 0.5270006108735492, "grad_norm": 0.4083658754825592, "learning_rate": 2.2881919141051322e-05, "loss": 4.2858, "step": 17254 }, { "epoch": 0.5270311545510079, "grad_norm": 0.3961414396762848, "learning_rate": 2.2879528881159193e-05, "loss": 4.2443, "step": 17255 }, { "epoch": 0.5270616982284667, "grad_norm": 0.40944918990135193, "learning_rate": 2.287713864079132e-05, "loss": 4.3221, "step": 17256 }, { "epoch": 0.5270922419059255, "grad_norm": 0.4016384184360504, "learning_rate": 2.2874748419969727e-05, "loss": 4.2565, "step": 17257 }, { "epoch": 0.5271227855833842, "grad_norm": 0.41103336215019226, "learning_rate": 2.287235821871642e-05, "loss": 4.3993, "step": 17258 }, { "epoch": 0.527153329260843, "grad_norm": 0.40473294258117676, "learning_rate": 2.28699680370534e-05, "loss": 4.2317, "step": 17259 }, { "epoch": 0.5271838729383018, "grad_norm": 0.4010947644710541, "learning_rate": 2.286757787500268e-05, "loss": 4.2996, "step": 17260 }, { "epoch": 0.5272144166157605, "grad_norm": 0.39854544401168823, "learning_rate": 2.2865187732586274e-05, "loss": 4.3064, "step": 17261 }, { "epoch": 0.5272449602932193, "grad_norm": 0.40411514043807983, "learning_rate": 2.2862797609826174e-05, "loss": 4.2647, "step": 17262 }, { "epoch": 0.527275503970678, "grad_norm": 0.3943064510822296, "learning_rate": 2.28604075067444e-05, "loss": 4.2865, "step": 17263 }, { "epoch": 0.5273060476481368, "grad_norm": 0.3990679681301117, "learning_rate": 2.285801742336295e-05, "loss": 4.29, "step": 17264 }, { "epoch": 0.5273365913255956, "grad_norm": 0.40994977951049805, "learning_rate": 2.2855627359703833e-05, "loss": 4.2488, "step": 17265 }, { "epoch": 0.5273671350030543, "grad_norm": 0.39023715257644653, "learning_rate": 2.285323731578907e-05, "loss": 4.2642, "step": 17266 }, { "epoch": 0.5273976786805131, "grad_norm": 0.3999473750591278, "learning_rate": 2.2850847291640644e-05, "loss": 4.3144, "step": 17267 }, { "epoch": 0.5274282223579719, "grad_norm": 0.3923684060573578, "learning_rate": 2.284845728728057e-05, "loss": 4.2828, "step": 17268 }, { "epoch": 0.5274587660354306, "grad_norm": 0.3848441243171692, "learning_rate": 2.2846067302730867e-05, "loss": 4.2763, "step": 17269 }, { "epoch": 0.5274893097128894, "grad_norm": 0.40229400992393494, "learning_rate": 2.284367733801352e-05, "loss": 4.2457, "step": 17270 }, { "epoch": 0.5275198533903482, "grad_norm": 0.3950638175010681, "learning_rate": 2.284128739315054e-05, "loss": 4.2599, "step": 17271 }, { "epoch": 0.5275503970678069, "grad_norm": 0.4113307595252991, "learning_rate": 2.2838897468163954e-05, "loss": 4.3079, "step": 17272 }, { "epoch": 0.5275809407452657, "grad_norm": 0.399495393037796, "learning_rate": 2.2836507563075736e-05, "loss": 4.2441, "step": 17273 }, { "epoch": 0.5276114844227245, "grad_norm": 0.3970144987106323, "learning_rate": 2.283411767790791e-05, "loss": 4.1851, "step": 17274 }, { "epoch": 0.5276420281001832, "grad_norm": 0.3980907201766968, "learning_rate": 2.2831727812682482e-05, "loss": 4.3092, "step": 17275 }, { "epoch": 0.527672571777642, "grad_norm": 0.4066966772079468, "learning_rate": 2.282933796742144e-05, "loss": 4.2942, "step": 17276 }, { "epoch": 0.5277031154551008, "grad_norm": 0.4116334021091461, "learning_rate": 2.28269481421468e-05, "loss": 4.3108, "step": 17277 }, { "epoch": 0.5277336591325595, "grad_norm": 0.3844373822212219, "learning_rate": 2.282455833688058e-05, "loss": 4.3118, "step": 17278 }, { "epoch": 0.5277642028100183, "grad_norm": 0.39616331458091736, "learning_rate": 2.282216855164475e-05, "loss": 4.2965, "step": 17279 }, { "epoch": 0.527794746487477, "grad_norm": 0.4147299528121948, "learning_rate": 2.281977878646135e-05, "loss": 4.3471, "step": 17280 }, { "epoch": 0.5278252901649358, "grad_norm": 0.3905905783176422, "learning_rate": 2.2817389041352358e-05, "loss": 4.2833, "step": 17281 }, { "epoch": 0.5278558338423947, "grad_norm": 0.3960477411746979, "learning_rate": 2.281499931633979e-05, "loss": 4.2704, "step": 17282 }, { "epoch": 0.5278863775198533, "grad_norm": 0.3949703276157379, "learning_rate": 2.2812609611445658e-05, "loss": 4.3425, "step": 17283 }, { "epoch": 0.5279169211973122, "grad_norm": 0.39010798931121826, "learning_rate": 2.2810219926691936e-05, "loss": 4.3727, "step": 17284 }, { "epoch": 0.527947464874771, "grad_norm": 0.40075376629829407, "learning_rate": 2.2807830262100648e-05, "loss": 4.2638, "step": 17285 }, { "epoch": 0.5279780085522296, "grad_norm": 0.40509313344955444, "learning_rate": 2.2805440617693806e-05, "loss": 4.2695, "step": 17286 }, { "epoch": 0.5280085522296885, "grad_norm": 0.3991883099079132, "learning_rate": 2.2803050993493386e-05, "loss": 4.2356, "step": 17287 }, { "epoch": 0.5280390959071473, "grad_norm": 0.4021025002002716, "learning_rate": 2.2800661389521406e-05, "loss": 4.2978, "step": 17288 }, { "epoch": 0.528069639584606, "grad_norm": 0.3993586599826813, "learning_rate": 2.279827180579988e-05, "loss": 4.3624, "step": 17289 }, { "epoch": 0.5281001832620648, "grad_norm": 0.40285706520080566, "learning_rate": 2.2795882242350794e-05, "loss": 4.2995, "step": 17290 }, { "epoch": 0.5281307269395236, "grad_norm": 0.38789835572242737, "learning_rate": 2.2793492699196146e-05, "loss": 4.2361, "step": 17291 }, { "epoch": 0.5281612706169823, "grad_norm": 0.41489648818969727, "learning_rate": 2.2791103176357953e-05, "loss": 4.2838, "step": 17292 }, { "epoch": 0.5281918142944411, "grad_norm": 0.4071250855922699, "learning_rate": 2.2788713673858203e-05, "loss": 4.3258, "step": 17293 }, { "epoch": 0.5282223579718999, "grad_norm": 0.385270893573761, "learning_rate": 2.27863241917189e-05, "loss": 4.3065, "step": 17294 }, { "epoch": 0.5282529016493586, "grad_norm": 0.3924577832221985, "learning_rate": 2.2783934729962057e-05, "loss": 4.3385, "step": 17295 }, { "epoch": 0.5282834453268174, "grad_norm": 0.38993141055107117, "learning_rate": 2.278154528860966e-05, "loss": 4.2906, "step": 17296 }, { "epoch": 0.5283139890042761, "grad_norm": 0.38192346692085266, "learning_rate": 2.2779155867683726e-05, "loss": 4.3494, "step": 17297 }, { "epoch": 0.5283445326817349, "grad_norm": 0.39663735032081604, "learning_rate": 2.277676646720624e-05, "loss": 4.2936, "step": 17298 }, { "epoch": 0.5283750763591937, "grad_norm": 0.4089413583278656, "learning_rate": 2.2774377087199203e-05, "loss": 4.3921, "step": 17299 }, { "epoch": 0.5284056200366524, "grad_norm": 0.3890983760356903, "learning_rate": 2.277198772768463e-05, "loss": 4.317, "step": 17300 }, { "epoch": 0.5284361637141112, "grad_norm": 0.4095730483531952, "learning_rate": 2.27695983886845e-05, "loss": 4.3, "step": 17301 }, { "epoch": 0.52846670739157, "grad_norm": 0.38885998725891113, "learning_rate": 2.2767209070220826e-05, "loss": 4.3042, "step": 17302 }, { "epoch": 0.5284972510690287, "grad_norm": 0.390924334526062, "learning_rate": 2.2764819772315617e-05, "loss": 4.3168, "step": 17303 }, { "epoch": 0.5285277947464875, "grad_norm": 0.4097631871700287, "learning_rate": 2.276243049499085e-05, "loss": 4.3681, "step": 17304 }, { "epoch": 0.5285583384239463, "grad_norm": 0.40533068776130676, "learning_rate": 2.2760041238268543e-05, "loss": 4.2691, "step": 17305 }, { "epoch": 0.528588882101405, "grad_norm": 0.39972123503685, "learning_rate": 2.2757652002170687e-05, "loss": 4.2286, "step": 17306 }, { "epoch": 0.5286194257788638, "grad_norm": 0.402877539396286, "learning_rate": 2.275526278671928e-05, "loss": 4.3635, "step": 17307 }, { "epoch": 0.5286499694563226, "grad_norm": 0.3988335430622101, "learning_rate": 2.275287359193632e-05, "loss": 4.2758, "step": 17308 }, { "epoch": 0.5286805131337813, "grad_norm": 0.39418765902519226, "learning_rate": 2.2750484417843817e-05, "loss": 4.3718, "step": 17309 }, { "epoch": 0.5287110568112401, "grad_norm": 0.3868429660797119, "learning_rate": 2.274809526446375e-05, "loss": 4.2159, "step": 17310 }, { "epoch": 0.5287416004886989, "grad_norm": 0.41231265664100647, "learning_rate": 2.2745706131818128e-05, "loss": 4.2713, "step": 17311 }, { "epoch": 0.5287721441661576, "grad_norm": 0.401430606842041, "learning_rate": 2.274331701992896e-05, "loss": 4.4477, "step": 17312 }, { "epoch": 0.5288026878436164, "grad_norm": 0.3981861174106598, "learning_rate": 2.274092792881823e-05, "loss": 4.2573, "step": 17313 }, { "epoch": 0.5288332315210751, "grad_norm": 0.3913121521472931, "learning_rate": 2.2738538858507936e-05, "loss": 4.3193, "step": 17314 }, { "epoch": 0.5288637751985339, "grad_norm": 0.39058953523635864, "learning_rate": 2.2736149809020075e-05, "loss": 4.3039, "step": 17315 }, { "epoch": 0.5288943188759927, "grad_norm": 0.40605849027633667, "learning_rate": 2.273376078037664e-05, "loss": 4.2907, "step": 17316 }, { "epoch": 0.5289248625534514, "grad_norm": 0.4004141390323639, "learning_rate": 2.273137177259965e-05, "loss": 4.2507, "step": 17317 }, { "epoch": 0.5289554062309102, "grad_norm": 0.38324809074401855, "learning_rate": 2.2728982785711075e-05, "loss": 4.3693, "step": 17318 }, { "epoch": 0.528985949908369, "grad_norm": 0.3900691866874695, "learning_rate": 2.272659381973292e-05, "loss": 4.2315, "step": 17319 }, { "epoch": 0.5290164935858277, "grad_norm": 0.3893962502479553, "learning_rate": 2.27242048746872e-05, "loss": 4.3277, "step": 17320 }, { "epoch": 0.5290470372632865, "grad_norm": 0.3936118185520172, "learning_rate": 2.272181595059589e-05, "loss": 4.3472, "step": 17321 }, { "epoch": 0.5290775809407453, "grad_norm": 0.3949021100997925, "learning_rate": 2.2719427047480983e-05, "loss": 4.2939, "step": 17322 }, { "epoch": 0.529108124618204, "grad_norm": 0.389765202999115, "learning_rate": 2.2717038165364494e-05, "loss": 4.2056, "step": 17323 }, { "epoch": 0.5291386682956628, "grad_norm": 0.38680991530418396, "learning_rate": 2.27146493042684e-05, "loss": 4.297, "step": 17324 }, { "epoch": 0.5291692119731216, "grad_norm": 0.4006824195384979, "learning_rate": 2.2712260464214702e-05, "loss": 4.29, "step": 17325 }, { "epoch": 0.5291997556505803, "grad_norm": 0.398555189371109, "learning_rate": 2.270987164522541e-05, "loss": 4.2337, "step": 17326 }, { "epoch": 0.5292302993280391, "grad_norm": 0.39377835392951965, "learning_rate": 2.27074828473225e-05, "loss": 4.3248, "step": 17327 }, { "epoch": 0.5292608430054979, "grad_norm": 0.39248186349868774, "learning_rate": 2.2705094070527976e-05, "loss": 4.3075, "step": 17328 }, { "epoch": 0.5292913866829566, "grad_norm": 0.3887282907962799, "learning_rate": 2.2702705314863833e-05, "loss": 4.3403, "step": 17329 }, { "epoch": 0.5293219303604154, "grad_norm": 0.3939334750175476, "learning_rate": 2.270031658035206e-05, "loss": 4.3549, "step": 17330 }, { "epoch": 0.5293524740378741, "grad_norm": 0.38451337814331055, "learning_rate": 2.2697927867014663e-05, "loss": 4.2732, "step": 17331 }, { "epoch": 0.5293830177153329, "grad_norm": 0.39742937684059143, "learning_rate": 2.2695539174873618e-05, "loss": 4.3124, "step": 17332 }, { "epoch": 0.5294135613927917, "grad_norm": 0.4379645586013794, "learning_rate": 2.2693150503950927e-05, "loss": 4.2679, "step": 17333 }, { "epoch": 0.5294441050702504, "grad_norm": 0.39575284719467163, "learning_rate": 2.2690761854268597e-05, "loss": 4.2406, "step": 17334 }, { "epoch": 0.5294746487477092, "grad_norm": 0.3968692719936371, "learning_rate": 2.2688373225848597e-05, "loss": 4.1758, "step": 17335 }, { "epoch": 0.529505192425168, "grad_norm": 0.4104986786842346, "learning_rate": 2.2685984618712942e-05, "loss": 4.3526, "step": 17336 }, { "epoch": 0.5295357361026267, "grad_norm": 0.40007007122039795, "learning_rate": 2.2683596032883615e-05, "loss": 4.22, "step": 17337 }, { "epoch": 0.5295662797800855, "grad_norm": 0.3950786292552948, "learning_rate": 2.2681207468382608e-05, "loss": 4.2074, "step": 17338 }, { "epoch": 0.5295968234575443, "grad_norm": 0.3990030586719513, "learning_rate": 2.2678818925231913e-05, "loss": 4.3268, "step": 17339 }, { "epoch": 0.529627367135003, "grad_norm": 0.3916895389556885, "learning_rate": 2.2676430403453533e-05, "loss": 4.2609, "step": 17340 }, { "epoch": 0.5296579108124618, "grad_norm": 0.4053928554058075, "learning_rate": 2.2674041903069444e-05, "loss": 4.3417, "step": 17341 }, { "epoch": 0.5296884544899206, "grad_norm": 0.3871797025203705, "learning_rate": 2.2671653424101648e-05, "loss": 4.3275, "step": 17342 }, { "epoch": 0.5297189981673793, "grad_norm": 0.3906733989715576, "learning_rate": 2.2669264966572147e-05, "loss": 4.2351, "step": 17343 }, { "epoch": 0.5297495418448381, "grad_norm": 0.39837849140167236, "learning_rate": 2.2666876530502917e-05, "loss": 4.2818, "step": 17344 }, { "epoch": 0.5297800855222969, "grad_norm": 0.41371583938598633, "learning_rate": 2.2664488115915947e-05, "loss": 4.3609, "step": 17345 }, { "epoch": 0.5298106291997556, "grad_norm": 0.40596529841423035, "learning_rate": 2.266209972283325e-05, "loss": 4.2791, "step": 17346 }, { "epoch": 0.5298411728772144, "grad_norm": 0.3924832344055176, "learning_rate": 2.2659711351276787e-05, "loss": 4.3286, "step": 17347 }, { "epoch": 0.5298717165546731, "grad_norm": 0.40781980752944946, "learning_rate": 2.2657323001268578e-05, "loss": 4.2233, "step": 17348 }, { "epoch": 0.5299022602321319, "grad_norm": 0.38412538170814514, "learning_rate": 2.265493467283059e-05, "loss": 4.308, "step": 17349 }, { "epoch": 0.5299328039095907, "grad_norm": 0.4020765423774719, "learning_rate": 2.2652546365984826e-05, "loss": 4.2878, "step": 17350 }, { "epoch": 0.5299633475870494, "grad_norm": 0.4051748216152191, "learning_rate": 2.2650158080753282e-05, "loss": 4.2739, "step": 17351 }, { "epoch": 0.5299938912645082, "grad_norm": 0.4017631411552429, "learning_rate": 2.264776981715793e-05, "loss": 4.2778, "step": 17352 }, { "epoch": 0.530024434941967, "grad_norm": 0.39548930525779724, "learning_rate": 2.2645381575220782e-05, "loss": 4.2851, "step": 17353 }, { "epoch": 0.5300549786194257, "grad_norm": 0.4059699773788452, "learning_rate": 2.2642993354963814e-05, "loss": 4.2634, "step": 17354 }, { "epoch": 0.5300855222968845, "grad_norm": 0.40365567803382874, "learning_rate": 2.2640605156409013e-05, "loss": 4.336, "step": 17355 }, { "epoch": 0.5301160659743434, "grad_norm": 0.4138631820678711, "learning_rate": 2.263821697957837e-05, "loss": 4.2395, "step": 17356 }, { "epoch": 0.530146609651802, "grad_norm": 0.39125388860702515, "learning_rate": 2.263582882449389e-05, "loss": 4.2923, "step": 17357 }, { "epoch": 0.5301771533292609, "grad_norm": 0.40476447343826294, "learning_rate": 2.263344069117754e-05, "loss": 4.273, "step": 17358 }, { "epoch": 0.5302076970067197, "grad_norm": 0.4012939929962158, "learning_rate": 2.2631052579651317e-05, "loss": 4.2787, "step": 17359 }, { "epoch": 0.5302382406841784, "grad_norm": 0.3805723190307617, "learning_rate": 2.2628664489937217e-05, "loss": 4.2624, "step": 17360 }, { "epoch": 0.5302687843616372, "grad_norm": 0.3932909667491913, "learning_rate": 2.262627642205722e-05, "loss": 4.3055, "step": 17361 }, { "epoch": 0.5302993280390959, "grad_norm": 0.39818286895751953, "learning_rate": 2.2623888376033324e-05, "loss": 4.281, "step": 17362 }, { "epoch": 0.5303298717165547, "grad_norm": 0.41640034317970276, "learning_rate": 2.26215003518875e-05, "loss": 4.1505, "step": 17363 }, { "epoch": 0.5303604153940135, "grad_norm": 0.4024260640144348, "learning_rate": 2.261911234964174e-05, "loss": 4.2255, "step": 17364 }, { "epoch": 0.5303909590714722, "grad_norm": 0.4136187732219696, "learning_rate": 2.2616724369318053e-05, "loss": 4.3296, "step": 17365 }, { "epoch": 0.530421502748931, "grad_norm": 0.40749385952949524, "learning_rate": 2.2614336410938393e-05, "loss": 4.3057, "step": 17366 }, { "epoch": 0.5304520464263898, "grad_norm": 0.4032258987426758, "learning_rate": 2.2611948474524775e-05, "loss": 4.3083, "step": 17367 }, { "epoch": 0.5304825901038485, "grad_norm": 0.40204867720603943, "learning_rate": 2.2609560560099176e-05, "loss": 4.2447, "step": 17368 }, { "epoch": 0.5305131337813073, "grad_norm": 0.3962036669254303, "learning_rate": 2.2607172667683576e-05, "loss": 4.3431, "step": 17369 }, { "epoch": 0.5305436774587661, "grad_norm": 0.40622419118881226, "learning_rate": 2.2604784797299967e-05, "loss": 4.2495, "step": 17370 }, { "epoch": 0.5305742211362248, "grad_norm": 0.40102946758270264, "learning_rate": 2.2602396948970345e-05, "loss": 4.2987, "step": 17371 }, { "epoch": 0.5306047648136836, "grad_norm": 0.39599740505218506, "learning_rate": 2.2600009122716675e-05, "loss": 4.3377, "step": 17372 }, { "epoch": 0.5306353084911424, "grad_norm": 0.4039570987224579, "learning_rate": 2.2597621318560956e-05, "loss": 4.3327, "step": 17373 }, { "epoch": 0.5306658521686011, "grad_norm": 0.3975801169872284, "learning_rate": 2.2595233536525184e-05, "loss": 4.255, "step": 17374 }, { "epoch": 0.5306963958460599, "grad_norm": 0.4078766703605652, "learning_rate": 2.259284577663132e-05, "loss": 4.274, "step": 17375 }, { "epoch": 0.5307269395235187, "grad_norm": 0.3990611433982849, "learning_rate": 2.2590458038901372e-05, "loss": 4.2868, "step": 17376 }, { "epoch": 0.5307574832009774, "grad_norm": 0.3982560336589813, "learning_rate": 2.2588070323357317e-05, "loss": 4.1957, "step": 17377 }, { "epoch": 0.5307880268784362, "grad_norm": 0.3960031270980835, "learning_rate": 2.258568263002113e-05, "loss": 4.2697, "step": 17378 }, { "epoch": 0.5308185705558949, "grad_norm": 0.39631354808807373, "learning_rate": 2.258329495891482e-05, "loss": 4.2719, "step": 17379 }, { "epoch": 0.5308491142333537, "grad_norm": 0.4053654372692108, "learning_rate": 2.258090731006034e-05, "loss": 4.2025, "step": 17380 }, { "epoch": 0.5308796579108125, "grad_norm": 0.4015188217163086, "learning_rate": 2.2578519683479687e-05, "loss": 4.2128, "step": 17381 }, { "epoch": 0.5309102015882712, "grad_norm": 0.3862977623939514, "learning_rate": 2.2576132079194863e-05, "loss": 4.2308, "step": 17382 }, { "epoch": 0.53094074526573, "grad_norm": 0.406272292137146, "learning_rate": 2.257374449722783e-05, "loss": 4.2825, "step": 17383 }, { "epoch": 0.5309712889431888, "grad_norm": 0.4020388424396515, "learning_rate": 2.2571356937600578e-05, "loss": 4.2316, "step": 17384 }, { "epoch": 0.5310018326206475, "grad_norm": 0.40065693855285645, "learning_rate": 2.2568969400335098e-05, "loss": 4.3184, "step": 17385 }, { "epoch": 0.5310323762981063, "grad_norm": 0.4010711908340454, "learning_rate": 2.256658188545336e-05, "loss": 4.2666, "step": 17386 }, { "epoch": 0.5310629199755651, "grad_norm": 0.4060738980770111, "learning_rate": 2.2564194392977348e-05, "loss": 4.2476, "step": 17387 }, { "epoch": 0.5310934636530238, "grad_norm": 0.402124285697937, "learning_rate": 2.2561806922929062e-05, "loss": 4.2498, "step": 17388 }, { "epoch": 0.5311240073304826, "grad_norm": 0.3884003758430481, "learning_rate": 2.2559419475330466e-05, "loss": 4.2738, "step": 17389 }, { "epoch": 0.5311545510079414, "grad_norm": 0.39272329211235046, "learning_rate": 2.2557032050203553e-05, "loss": 4.3568, "step": 17390 }, { "epoch": 0.5311850946854001, "grad_norm": 0.39028990268707275, "learning_rate": 2.25546446475703e-05, "loss": 4.2593, "step": 17391 }, { "epoch": 0.5312156383628589, "grad_norm": 0.392545610666275, "learning_rate": 2.2552257267452696e-05, "loss": 4.3482, "step": 17392 }, { "epoch": 0.5312461820403177, "grad_norm": 0.3935648202896118, "learning_rate": 2.254986990987271e-05, "loss": 4.2687, "step": 17393 }, { "epoch": 0.5312767257177764, "grad_norm": 0.4025449752807617, "learning_rate": 2.254748257485234e-05, "loss": 4.3226, "step": 17394 }, { "epoch": 0.5313072693952352, "grad_norm": 0.39421477913856506, "learning_rate": 2.254509526241355e-05, "loss": 4.2613, "step": 17395 }, { "epoch": 0.5313378130726939, "grad_norm": 0.39427340030670166, "learning_rate": 2.2542707972578344e-05, "loss": 4.2691, "step": 17396 }, { "epoch": 0.5313683567501527, "grad_norm": 0.40441474318504333, "learning_rate": 2.2540320705368675e-05, "loss": 4.3054, "step": 17397 }, { "epoch": 0.5313989004276115, "grad_norm": 0.40636587142944336, "learning_rate": 2.2537933460806537e-05, "loss": 4.2512, "step": 17398 }, { "epoch": 0.5314294441050702, "grad_norm": 0.4013751745223999, "learning_rate": 2.2535546238913924e-05, "loss": 4.3148, "step": 17399 }, { "epoch": 0.531459987782529, "grad_norm": 0.3987697958946228, "learning_rate": 2.2533159039712802e-05, "loss": 4.327, "step": 17400 }, { "epoch": 0.5314905314599878, "grad_norm": 0.40730971097946167, "learning_rate": 2.2530771863225143e-05, "loss": 4.2682, "step": 17401 }, { "epoch": 0.5315210751374465, "grad_norm": 0.3990730047225952, "learning_rate": 2.2528384709472946e-05, "loss": 4.2773, "step": 17402 }, { "epoch": 0.5315516188149053, "grad_norm": 0.3902263343334198, "learning_rate": 2.2525997578478176e-05, "loss": 4.2816, "step": 17403 }, { "epoch": 0.5315821624923641, "grad_norm": 0.41139695048332214, "learning_rate": 2.2523610470262812e-05, "loss": 4.3525, "step": 17404 }, { "epoch": 0.5316127061698228, "grad_norm": 0.4087548851966858, "learning_rate": 2.2521223384848854e-05, "loss": 4.3284, "step": 17405 }, { "epoch": 0.5316432498472816, "grad_norm": 0.39578527212142944, "learning_rate": 2.251883632225826e-05, "loss": 4.3198, "step": 17406 }, { "epoch": 0.5316737935247404, "grad_norm": 0.39926761388778687, "learning_rate": 2.2516449282513017e-05, "loss": 4.314, "step": 17407 }, { "epoch": 0.5317043372021991, "grad_norm": 0.39260637760162354, "learning_rate": 2.2514062265635107e-05, "loss": 4.3331, "step": 17408 }, { "epoch": 0.5317348808796579, "grad_norm": 0.39990732073783875, "learning_rate": 2.2511675271646493e-05, "loss": 4.2517, "step": 17409 }, { "epoch": 0.5317654245571167, "grad_norm": 0.40531063079833984, "learning_rate": 2.250928830056917e-05, "loss": 4.2119, "step": 17410 }, { "epoch": 0.5317959682345754, "grad_norm": 0.40190961956977844, "learning_rate": 2.2506901352425113e-05, "loss": 4.3545, "step": 17411 }, { "epoch": 0.5318265119120342, "grad_norm": 0.402173787355423, "learning_rate": 2.250451442723629e-05, "loss": 4.1359, "step": 17412 }, { "epoch": 0.5318570555894929, "grad_norm": 0.39060235023498535, "learning_rate": 2.2502127525024695e-05, "loss": 4.3163, "step": 17413 }, { "epoch": 0.5318875992669517, "grad_norm": 0.39898085594177246, "learning_rate": 2.249974064581229e-05, "loss": 4.2804, "step": 17414 }, { "epoch": 0.5319181429444105, "grad_norm": 0.40244966745376587, "learning_rate": 2.2497353789621055e-05, "loss": 4.2979, "step": 17415 }, { "epoch": 0.5319486866218692, "grad_norm": 0.3937089443206787, "learning_rate": 2.249496695647298e-05, "loss": 4.2352, "step": 17416 }, { "epoch": 0.531979230299328, "grad_norm": 0.3901645541191101, "learning_rate": 2.2492580146390025e-05, "loss": 4.3196, "step": 17417 }, { "epoch": 0.5320097739767868, "grad_norm": 0.38987070322036743, "learning_rate": 2.249019335939417e-05, "loss": 4.2707, "step": 17418 }, { "epoch": 0.5320403176542455, "grad_norm": 0.39526253938674927, "learning_rate": 2.248780659550741e-05, "loss": 4.3174, "step": 17419 }, { "epoch": 0.5320708613317043, "grad_norm": 0.40310126543045044, "learning_rate": 2.248541985475169e-05, "loss": 4.2814, "step": 17420 }, { "epoch": 0.5321014050091631, "grad_norm": 0.39744094014167786, "learning_rate": 2.2483033137149008e-05, "loss": 4.2706, "step": 17421 }, { "epoch": 0.5321319486866218, "grad_norm": 0.38686805963516235, "learning_rate": 2.248064644272134e-05, "loss": 4.276, "step": 17422 }, { "epoch": 0.5321624923640806, "grad_norm": 0.4066472053527832, "learning_rate": 2.2478259771490652e-05, "loss": 4.3742, "step": 17423 }, { "epoch": 0.5321930360415394, "grad_norm": 0.42217570543289185, "learning_rate": 2.247587312347892e-05, "loss": 4.2573, "step": 17424 }, { "epoch": 0.5322235797189981, "grad_norm": 0.4032348692417145, "learning_rate": 2.2473486498708126e-05, "loss": 4.294, "step": 17425 }, { "epoch": 0.532254123396457, "grad_norm": 0.40022265911102295, "learning_rate": 2.2471099897200235e-05, "loss": 4.2619, "step": 17426 }, { "epoch": 0.5322846670739158, "grad_norm": 0.3924105763435364, "learning_rate": 2.246871331897723e-05, "loss": 4.3473, "step": 17427 }, { "epoch": 0.5323152107513744, "grad_norm": 0.38937216997146606, "learning_rate": 2.246632676406109e-05, "loss": 4.2424, "step": 17428 }, { "epoch": 0.5323457544288333, "grad_norm": 0.3867984414100647, "learning_rate": 2.246394023247377e-05, "loss": 4.2712, "step": 17429 }, { "epoch": 0.532376298106292, "grad_norm": 0.40150779485702515, "learning_rate": 2.2461553724237266e-05, "loss": 4.3534, "step": 17430 }, { "epoch": 0.5324068417837508, "grad_norm": 0.4030921161174774, "learning_rate": 2.245916723937354e-05, "loss": 4.18, "step": 17431 }, { "epoch": 0.5324373854612096, "grad_norm": 0.3944793939590454, "learning_rate": 2.2456780777904562e-05, "loss": 4.2724, "step": 17432 }, { "epoch": 0.5324679291386683, "grad_norm": 0.4054536819458008, "learning_rate": 2.2454394339852322e-05, "loss": 4.3015, "step": 17433 }, { "epoch": 0.532498472816127, "grad_norm": 0.41223034262657166, "learning_rate": 2.2452007925238768e-05, "loss": 4.2867, "step": 17434 }, { "epoch": 0.5325290164935859, "grad_norm": 0.386561781167984, "learning_rate": 2.244962153408589e-05, "loss": 4.1771, "step": 17435 }, { "epoch": 0.5325595601710446, "grad_norm": 0.40312620997428894, "learning_rate": 2.244723516641567e-05, "loss": 4.3489, "step": 17436 }, { "epoch": 0.5325901038485034, "grad_norm": 0.39881041646003723, "learning_rate": 2.2444848822250054e-05, "loss": 4.3054, "step": 17437 }, { "epoch": 0.5326206475259622, "grad_norm": 0.39908286929130554, "learning_rate": 2.2442462501611038e-05, "loss": 4.3431, "step": 17438 }, { "epoch": 0.5326511912034209, "grad_norm": 0.39631760120391846, "learning_rate": 2.2440076204520584e-05, "loss": 4.3031, "step": 17439 }, { "epoch": 0.5326817348808797, "grad_norm": 0.3989723026752472, "learning_rate": 2.2437689931000662e-05, "loss": 4.3398, "step": 17440 }, { "epoch": 0.5327122785583385, "grad_norm": 0.41405197978019714, "learning_rate": 2.243530368107324e-05, "loss": 4.3638, "step": 17441 }, { "epoch": 0.5327428222357972, "grad_norm": 0.3940064609050751, "learning_rate": 2.2432917454760307e-05, "loss": 4.3365, "step": 17442 }, { "epoch": 0.532773365913256, "grad_norm": 0.4155278205871582, "learning_rate": 2.2430531252083815e-05, "loss": 4.3246, "step": 17443 }, { "epoch": 0.5328039095907148, "grad_norm": 0.4019154906272888, "learning_rate": 2.242814507306574e-05, "loss": 4.3777, "step": 17444 }, { "epoch": 0.5328344532681735, "grad_norm": 0.405964732170105, "learning_rate": 2.242575891772807e-05, "loss": 4.3649, "step": 17445 }, { "epoch": 0.5328649969456323, "grad_norm": 0.40686771273612976, "learning_rate": 2.242337278609275e-05, "loss": 4.3395, "step": 17446 }, { "epoch": 0.532895540623091, "grad_norm": 0.39762330055236816, "learning_rate": 2.2420986678181767e-05, "loss": 4.3035, "step": 17447 }, { "epoch": 0.5329260843005498, "grad_norm": 0.3964112401008606, "learning_rate": 2.2418600594017083e-05, "loss": 4.2629, "step": 17448 }, { "epoch": 0.5329566279780086, "grad_norm": 0.39911386370658875, "learning_rate": 2.2416214533620666e-05, "loss": 4.324, "step": 17449 }, { "epoch": 0.5329871716554673, "grad_norm": 0.39374420046806335, "learning_rate": 2.2413828497014504e-05, "loss": 4.2625, "step": 17450 }, { "epoch": 0.5330177153329261, "grad_norm": 0.3957955539226532, "learning_rate": 2.2411442484220535e-05, "loss": 4.3006, "step": 17451 }, { "epoch": 0.5330482590103849, "grad_norm": 0.40013161301612854, "learning_rate": 2.240905649526075e-05, "loss": 4.3181, "step": 17452 }, { "epoch": 0.5330788026878436, "grad_norm": 0.39518842101097107, "learning_rate": 2.2406670530157127e-05, "loss": 4.3099, "step": 17453 }, { "epoch": 0.5331093463653024, "grad_norm": 0.4003431797027588, "learning_rate": 2.240428458893161e-05, "loss": 4.3139, "step": 17454 }, { "epoch": 0.5331398900427612, "grad_norm": 0.4323251247406006, "learning_rate": 2.240189867160618e-05, "loss": 4.2447, "step": 17455 }, { "epoch": 0.5331704337202199, "grad_norm": 0.4017029404640198, "learning_rate": 2.2399512778202814e-05, "loss": 4.3425, "step": 17456 }, { "epoch": 0.5332009773976787, "grad_norm": 0.39257359504699707, "learning_rate": 2.239712690874346e-05, "loss": 4.3182, "step": 17457 }, { "epoch": 0.5332315210751375, "grad_norm": 0.39069345593452454, "learning_rate": 2.2394741063250095e-05, "loss": 4.3265, "step": 17458 }, { "epoch": 0.5332620647525962, "grad_norm": 0.41317734122276306, "learning_rate": 2.23923552417447e-05, "loss": 4.2689, "step": 17459 }, { "epoch": 0.533292608430055, "grad_norm": 0.3921692669391632, "learning_rate": 2.238996944424922e-05, "loss": 4.2894, "step": 17460 }, { "epoch": 0.5333231521075138, "grad_norm": 0.40742284059524536, "learning_rate": 2.2387583670785637e-05, "loss": 4.3763, "step": 17461 }, { "epoch": 0.5333536957849725, "grad_norm": 0.4060111343860626, "learning_rate": 2.238519792137592e-05, "loss": 4.2671, "step": 17462 }, { "epoch": 0.5333842394624313, "grad_norm": 0.38697052001953125, "learning_rate": 2.2382812196042026e-05, "loss": 4.3113, "step": 17463 }, { "epoch": 0.53341478313989, "grad_norm": 0.3994543254375458, "learning_rate": 2.2380426494805936e-05, "loss": 4.1865, "step": 17464 }, { "epoch": 0.5334453268173488, "grad_norm": 0.40054649114608765, "learning_rate": 2.237804081768959e-05, "loss": 4.3005, "step": 17465 }, { "epoch": 0.5334758704948076, "grad_norm": 0.4043289124965668, "learning_rate": 2.237565516471497e-05, "loss": 4.2551, "step": 17466 }, { "epoch": 0.5335064141722663, "grad_norm": 0.39114779233932495, "learning_rate": 2.2373269535904054e-05, "loss": 4.3429, "step": 17467 }, { "epoch": 0.5335369578497251, "grad_norm": 0.40027493238449097, "learning_rate": 2.2370883931278786e-05, "loss": 4.3006, "step": 17468 }, { "epoch": 0.5335675015271839, "grad_norm": 0.40152618288993835, "learning_rate": 2.2368498350861147e-05, "loss": 4.2489, "step": 17469 }, { "epoch": 0.5335980452046426, "grad_norm": 0.40515705943107605, "learning_rate": 2.2366112794673093e-05, "loss": 4.3338, "step": 17470 }, { "epoch": 0.5336285888821014, "grad_norm": 0.39934787154197693, "learning_rate": 2.23637272627366e-05, "loss": 4.3004, "step": 17471 }, { "epoch": 0.5336591325595602, "grad_norm": 0.40448957681655884, "learning_rate": 2.2361341755073614e-05, "loss": 4.3127, "step": 17472 }, { "epoch": 0.5336896762370189, "grad_norm": 0.39614853262901306, "learning_rate": 2.2358956271706123e-05, "loss": 4.1953, "step": 17473 }, { "epoch": 0.5337202199144777, "grad_norm": 0.4167099893093109, "learning_rate": 2.235657081265607e-05, "loss": 4.3081, "step": 17474 }, { "epoch": 0.5337507635919365, "grad_norm": 0.4035815894603729, "learning_rate": 2.235418537794543e-05, "loss": 4.2819, "step": 17475 }, { "epoch": 0.5337813072693952, "grad_norm": 0.39696255326271057, "learning_rate": 2.2351799967596174e-05, "loss": 4.306, "step": 17476 }, { "epoch": 0.533811850946854, "grad_norm": 0.4145742654800415, "learning_rate": 2.2349414581630252e-05, "loss": 4.301, "step": 17477 }, { "epoch": 0.5338423946243128, "grad_norm": 0.3967048227787018, "learning_rate": 2.234702922006963e-05, "loss": 4.3273, "step": 17478 }, { "epoch": 0.5338729383017715, "grad_norm": 0.41015905141830444, "learning_rate": 2.2344643882936282e-05, "loss": 4.2134, "step": 17479 }, { "epoch": 0.5339034819792303, "grad_norm": 0.4086320400238037, "learning_rate": 2.2342258570252155e-05, "loss": 4.318, "step": 17480 }, { "epoch": 0.533934025656689, "grad_norm": 0.39444243907928467, "learning_rate": 2.2339873282039226e-05, "loss": 4.3185, "step": 17481 }, { "epoch": 0.5339645693341478, "grad_norm": 0.39159199595451355, "learning_rate": 2.233748801831944e-05, "loss": 4.2074, "step": 17482 }, { "epoch": 0.5339951130116066, "grad_norm": 0.40950807929039, "learning_rate": 2.2335102779114774e-05, "loss": 4.0988, "step": 17483 }, { "epoch": 0.5340256566890653, "grad_norm": 0.4088072180747986, "learning_rate": 2.23327175644472e-05, "loss": 4.1468, "step": 17484 }, { "epoch": 0.5340562003665241, "grad_norm": 0.3967943489551544, "learning_rate": 2.233033237433865e-05, "loss": 4.3074, "step": 17485 }, { "epoch": 0.5340867440439829, "grad_norm": 0.4113112986087799, "learning_rate": 2.2327947208811113e-05, "loss": 4.2613, "step": 17486 }, { "epoch": 0.5341172877214416, "grad_norm": 0.3935881555080414, "learning_rate": 2.2325562067886548e-05, "loss": 4.3165, "step": 17487 }, { "epoch": 0.5341478313989004, "grad_norm": 0.39983445405960083, "learning_rate": 2.232317695158689e-05, "loss": 4.2914, "step": 17488 }, { "epoch": 0.5341783750763592, "grad_norm": 0.4013211131095886, "learning_rate": 2.232079185993412e-05, "loss": 4.2283, "step": 17489 }, { "epoch": 0.5342089187538179, "grad_norm": 0.39540717005729675, "learning_rate": 2.2318406792950208e-05, "loss": 4.3384, "step": 17490 }, { "epoch": 0.5342394624312767, "grad_norm": 0.3963264524936676, "learning_rate": 2.2316021750657097e-05, "loss": 4.341, "step": 17491 }, { "epoch": 0.5342700061087355, "grad_norm": 0.38584887981414795, "learning_rate": 2.2313636733076754e-05, "loss": 4.2176, "step": 17492 }, { "epoch": 0.5343005497861942, "grad_norm": 0.391279011964798, "learning_rate": 2.231125174023114e-05, "loss": 4.1781, "step": 17493 }, { "epoch": 0.534331093463653, "grad_norm": 0.39540916681289673, "learning_rate": 2.230886677214221e-05, "loss": 4.2898, "step": 17494 }, { "epoch": 0.5343616371411118, "grad_norm": 0.3950141370296478, "learning_rate": 2.230648182883193e-05, "loss": 4.3159, "step": 17495 }, { "epoch": 0.5343921808185705, "grad_norm": 0.3936106264591217, "learning_rate": 2.230409691032226e-05, "loss": 4.2981, "step": 17496 }, { "epoch": 0.5344227244960293, "grad_norm": 0.39845144748687744, "learning_rate": 2.230171201663515e-05, "loss": 4.2508, "step": 17497 }, { "epoch": 0.534453268173488, "grad_norm": 0.3957536220550537, "learning_rate": 2.2299327147792574e-05, "loss": 4.2667, "step": 17498 }, { "epoch": 0.5344838118509468, "grad_norm": 0.3876585364341736, "learning_rate": 2.229694230381647e-05, "loss": 4.2523, "step": 17499 }, { "epoch": 0.5345143555284056, "grad_norm": 0.3991587162017822, "learning_rate": 2.2294557484728815e-05, "loss": 4.2092, "step": 17500 }, { "epoch": 0.5345448992058643, "grad_norm": 0.4109421670436859, "learning_rate": 2.229217269055156e-05, "loss": 4.3427, "step": 17501 }, { "epoch": 0.5345754428833231, "grad_norm": 0.3960173428058624, "learning_rate": 2.228978792130666e-05, "loss": 4.2826, "step": 17502 }, { "epoch": 0.534605986560782, "grad_norm": 0.4047790467739105, "learning_rate": 2.2287403177016074e-05, "loss": 4.2699, "step": 17503 }, { "epoch": 0.5346365302382406, "grad_norm": 0.393288254737854, "learning_rate": 2.228501845770177e-05, "loss": 4.2427, "step": 17504 }, { "epoch": 0.5346670739156995, "grad_norm": 0.3866714537143707, "learning_rate": 2.228263376338569e-05, "loss": 4.2679, "step": 17505 }, { "epoch": 0.5346976175931583, "grad_norm": 0.39342230558395386, "learning_rate": 2.2280249094089793e-05, "loss": 4.3373, "step": 17506 }, { "epoch": 0.534728161270617, "grad_norm": 0.4011106789112091, "learning_rate": 2.2277864449836054e-05, "loss": 4.2555, "step": 17507 }, { "epoch": 0.5347587049480758, "grad_norm": 0.39710649847984314, "learning_rate": 2.2275479830646407e-05, "loss": 4.3603, "step": 17508 }, { "epoch": 0.5347892486255346, "grad_norm": 0.4031154215335846, "learning_rate": 2.2273095236542822e-05, "loss": 4.2893, "step": 17509 }, { "epoch": 0.5348197923029933, "grad_norm": 0.3942774534225464, "learning_rate": 2.227071066754726e-05, "loss": 4.2837, "step": 17510 }, { "epoch": 0.5348503359804521, "grad_norm": 0.3915327489376068, "learning_rate": 2.2268326123681653e-05, "loss": 4.2493, "step": 17511 }, { "epoch": 0.5348808796579108, "grad_norm": 0.40388745069503784, "learning_rate": 2.2265941604967985e-05, "loss": 4.2456, "step": 17512 }, { "epoch": 0.5349114233353696, "grad_norm": 0.3993578255176544, "learning_rate": 2.2263557111428184e-05, "loss": 4.3798, "step": 17513 }, { "epoch": 0.5349419670128284, "grad_norm": 0.3952264189720154, "learning_rate": 2.2261172643084225e-05, "loss": 4.231, "step": 17514 }, { "epoch": 0.5349725106902871, "grad_norm": 0.394510954618454, "learning_rate": 2.2258788199958067e-05, "loss": 4.1257, "step": 17515 }, { "epoch": 0.5350030543677459, "grad_norm": 0.41313278675079346, "learning_rate": 2.225640378207164e-05, "loss": 4.1998, "step": 17516 }, { "epoch": 0.5350335980452047, "grad_norm": 0.3969813883304596, "learning_rate": 2.2254019389446924e-05, "loss": 4.4104, "step": 17517 }, { "epoch": 0.5350641417226634, "grad_norm": 0.40890800952911377, "learning_rate": 2.2251635022105867e-05, "loss": 4.2527, "step": 17518 }, { "epoch": 0.5350946854001222, "grad_norm": 0.39635851979255676, "learning_rate": 2.224925068007041e-05, "loss": 4.2305, "step": 17519 }, { "epoch": 0.535125229077581, "grad_norm": 0.40289488434791565, "learning_rate": 2.2246866363362517e-05, "loss": 4.35, "step": 17520 }, { "epoch": 0.5351557727550397, "grad_norm": 0.3890317678451538, "learning_rate": 2.224448207200415e-05, "loss": 4.2426, "step": 17521 }, { "epoch": 0.5351863164324985, "grad_norm": 0.4067089855670929, "learning_rate": 2.2242097806017244e-05, "loss": 4.4025, "step": 17522 }, { "epoch": 0.5352168601099573, "grad_norm": 0.4150392711162567, "learning_rate": 2.2239713565423764e-05, "loss": 4.3529, "step": 17523 }, { "epoch": 0.535247403787416, "grad_norm": 0.4059336483478546, "learning_rate": 2.223732935024566e-05, "loss": 4.2827, "step": 17524 }, { "epoch": 0.5352779474648748, "grad_norm": 0.391118586063385, "learning_rate": 2.223494516050489e-05, "loss": 4.227, "step": 17525 }, { "epoch": 0.5353084911423336, "grad_norm": 0.40267106890678406, "learning_rate": 2.2232560996223393e-05, "loss": 4.3187, "step": 17526 }, { "epoch": 0.5353390348197923, "grad_norm": 0.3947095274925232, "learning_rate": 2.223017685742314e-05, "loss": 4.2763, "step": 17527 }, { "epoch": 0.5353695784972511, "grad_norm": 0.3986029624938965, "learning_rate": 2.2227792744126063e-05, "loss": 4.3231, "step": 17528 }, { "epoch": 0.5354001221747098, "grad_norm": 0.4010148048400879, "learning_rate": 2.2225408656354133e-05, "loss": 4.3238, "step": 17529 }, { "epoch": 0.5354306658521686, "grad_norm": 0.4135085344314575, "learning_rate": 2.222302459412928e-05, "loss": 4.3408, "step": 17530 }, { "epoch": 0.5354612095296274, "grad_norm": 0.4034806191921234, "learning_rate": 2.2220640557473472e-05, "loss": 4.2728, "step": 17531 }, { "epoch": 0.5354917532070861, "grad_norm": 0.40922802686691284, "learning_rate": 2.2218256546408666e-05, "loss": 4.2033, "step": 17532 }, { "epoch": 0.5355222968845449, "grad_norm": 0.3978569507598877, "learning_rate": 2.2215872560956794e-05, "loss": 4.2642, "step": 17533 }, { "epoch": 0.5355528405620037, "grad_norm": 0.3955713212490082, "learning_rate": 2.221348860113981e-05, "loss": 4.3097, "step": 17534 }, { "epoch": 0.5355833842394624, "grad_norm": 0.3951985836029053, "learning_rate": 2.2211104666979678e-05, "loss": 4.2945, "step": 17535 }, { "epoch": 0.5356139279169212, "grad_norm": 0.3950061798095703, "learning_rate": 2.2208720758498334e-05, "loss": 4.2726, "step": 17536 }, { "epoch": 0.53564447159438, "grad_norm": 0.39413389563560486, "learning_rate": 2.2206336875717724e-05, "loss": 4.3478, "step": 17537 }, { "epoch": 0.5356750152718387, "grad_norm": 0.40993350744247437, "learning_rate": 2.2203953018659825e-05, "loss": 4.3342, "step": 17538 }, { "epoch": 0.5357055589492975, "grad_norm": 0.4008277356624603, "learning_rate": 2.2201569187346557e-05, "loss": 4.3327, "step": 17539 }, { "epoch": 0.5357361026267563, "grad_norm": 0.40389442443847656, "learning_rate": 2.2199185381799882e-05, "loss": 4.3181, "step": 17540 }, { "epoch": 0.535766646304215, "grad_norm": 0.3983864188194275, "learning_rate": 2.2196801602041756e-05, "loss": 4.2823, "step": 17541 }, { "epoch": 0.5357971899816738, "grad_norm": 0.40650877356529236, "learning_rate": 2.2194417848094105e-05, "loss": 4.2163, "step": 17542 }, { "epoch": 0.5358277336591326, "grad_norm": 0.3991272449493408, "learning_rate": 2.2192034119978897e-05, "loss": 4.2163, "step": 17543 }, { "epoch": 0.5358582773365913, "grad_norm": 0.399191677570343, "learning_rate": 2.218965041771808e-05, "loss": 4.2213, "step": 17544 }, { "epoch": 0.5358888210140501, "grad_norm": 0.4004049003124237, "learning_rate": 2.2187266741333587e-05, "loss": 4.2725, "step": 17545 }, { "epoch": 0.5359193646915088, "grad_norm": 0.4087423086166382, "learning_rate": 2.218488309084739e-05, "loss": 4.2932, "step": 17546 }, { "epoch": 0.5359499083689676, "grad_norm": 0.4088171422481537, "learning_rate": 2.2182499466281406e-05, "loss": 4.3041, "step": 17547 }, { "epoch": 0.5359804520464264, "grad_norm": 0.4051668643951416, "learning_rate": 2.2180115867657606e-05, "loss": 4.3035, "step": 17548 }, { "epoch": 0.5360109957238851, "grad_norm": 0.3819052278995514, "learning_rate": 2.2177732294997927e-05, "loss": 4.2727, "step": 17549 }, { "epoch": 0.5360415394013439, "grad_norm": 0.39050987362861633, "learning_rate": 2.2175348748324317e-05, "loss": 4.28, "step": 17550 }, { "epoch": 0.5360720830788027, "grad_norm": 0.3864195644855499, "learning_rate": 2.217296522765872e-05, "loss": 4.2472, "step": 17551 }, { "epoch": 0.5361026267562614, "grad_norm": 0.38789257407188416, "learning_rate": 2.2170581733023097e-05, "loss": 4.2259, "step": 17552 }, { "epoch": 0.5361331704337202, "grad_norm": 0.4007605314254761, "learning_rate": 2.2168198264439373e-05, "loss": 4.3309, "step": 17553 }, { "epoch": 0.536163714111179, "grad_norm": 0.38545840978622437, "learning_rate": 2.2165814821929498e-05, "loss": 4.3167, "step": 17554 }, { "epoch": 0.5361942577886377, "grad_norm": 0.38873589038848877, "learning_rate": 2.2163431405515438e-05, "loss": 4.3244, "step": 17555 }, { "epoch": 0.5362248014660965, "grad_norm": 0.3967600166797638, "learning_rate": 2.216104801521912e-05, "loss": 4.3252, "step": 17556 }, { "epoch": 0.5362553451435553, "grad_norm": 0.39752471446990967, "learning_rate": 2.2158664651062483e-05, "loss": 4.3092, "step": 17557 }, { "epoch": 0.536285888821014, "grad_norm": 0.402739018201828, "learning_rate": 2.2156281313067495e-05, "loss": 4.1992, "step": 17558 }, { "epoch": 0.5363164324984728, "grad_norm": 0.4007534980773926, "learning_rate": 2.2153898001256075e-05, "loss": 4.234, "step": 17559 }, { "epoch": 0.5363469761759316, "grad_norm": 0.391216516494751, "learning_rate": 2.215151471565018e-05, "loss": 4.2071, "step": 17560 }, { "epoch": 0.5363775198533903, "grad_norm": 0.40672993659973145, "learning_rate": 2.2149131456271762e-05, "loss": 4.2901, "step": 17561 }, { "epoch": 0.5364080635308491, "grad_norm": 0.39215272665023804, "learning_rate": 2.214674822314275e-05, "loss": 4.2675, "step": 17562 }, { "epoch": 0.5364386072083078, "grad_norm": 0.3923547863960266, "learning_rate": 2.21443650162851e-05, "loss": 4.2143, "step": 17563 }, { "epoch": 0.5364691508857666, "grad_norm": 0.39410391449928284, "learning_rate": 2.2141981835720748e-05, "loss": 4.2429, "step": 17564 }, { "epoch": 0.5364996945632254, "grad_norm": 0.4159872233867645, "learning_rate": 2.2139598681471632e-05, "loss": 4.4062, "step": 17565 }, { "epoch": 0.5365302382406841, "grad_norm": 0.3944370448589325, "learning_rate": 2.2137215553559714e-05, "loss": 4.2199, "step": 17566 }, { "epoch": 0.5365607819181429, "grad_norm": 0.39969050884246826, "learning_rate": 2.2134832452006912e-05, "loss": 4.2491, "step": 17567 }, { "epoch": 0.5365913255956017, "grad_norm": 0.39790400862693787, "learning_rate": 2.213244937683518e-05, "loss": 4.3318, "step": 17568 }, { "epoch": 0.5366218692730604, "grad_norm": 0.3934984505176544, "learning_rate": 2.2130066328066473e-05, "loss": 4.3618, "step": 17569 }, { "epoch": 0.5366524129505192, "grad_norm": 0.3948898911476135, "learning_rate": 2.212768330572271e-05, "loss": 4.2593, "step": 17570 }, { "epoch": 0.536682956627978, "grad_norm": 0.40687504410743713, "learning_rate": 2.2125300309825848e-05, "loss": 4.3271, "step": 17571 }, { "epoch": 0.5367135003054367, "grad_norm": 0.40276092290878296, "learning_rate": 2.2122917340397826e-05, "loss": 4.2396, "step": 17572 }, { "epoch": 0.5367440439828955, "grad_norm": 0.3885403275489807, "learning_rate": 2.212053439746058e-05, "loss": 4.3601, "step": 17573 }, { "epoch": 0.5367745876603544, "grad_norm": 0.39946046471595764, "learning_rate": 2.2118151481036052e-05, "loss": 4.2654, "step": 17574 }, { "epoch": 0.536805131337813, "grad_norm": 0.3935021758079529, "learning_rate": 2.2115768591146193e-05, "loss": 4.3624, "step": 17575 }, { "epoch": 0.5368356750152719, "grad_norm": 0.39827072620391846, "learning_rate": 2.2113385727812927e-05, "loss": 4.2767, "step": 17576 }, { "epoch": 0.5368662186927307, "grad_norm": 0.38658562302589417, "learning_rate": 2.2111002891058204e-05, "loss": 4.2673, "step": 17577 }, { "epoch": 0.5368967623701894, "grad_norm": 0.40147629380226135, "learning_rate": 2.2108620080903967e-05, "loss": 4.2942, "step": 17578 }, { "epoch": 0.5369273060476482, "grad_norm": 0.39586690068244934, "learning_rate": 2.2106237297372153e-05, "loss": 4.2484, "step": 17579 }, { "epoch": 0.5369578497251069, "grad_norm": 0.40540796518325806, "learning_rate": 2.2103854540484698e-05, "loss": 4.2966, "step": 17580 }, { "epoch": 0.5369883934025657, "grad_norm": 0.4082675278186798, "learning_rate": 2.2101471810263544e-05, "loss": 4.3097, "step": 17581 }, { "epoch": 0.5370189370800245, "grad_norm": 0.38904914259910583, "learning_rate": 2.2099089106730623e-05, "loss": 4.1687, "step": 17582 }, { "epoch": 0.5370494807574832, "grad_norm": 0.40016794204711914, "learning_rate": 2.209670642990789e-05, "loss": 4.3124, "step": 17583 }, { "epoch": 0.537080024434942, "grad_norm": 0.4066368043422699, "learning_rate": 2.2094323779817263e-05, "loss": 4.3207, "step": 17584 }, { "epoch": 0.5371105681124008, "grad_norm": 0.4070887267589569, "learning_rate": 2.209194115648069e-05, "loss": 4.2023, "step": 17585 }, { "epoch": 0.5371411117898595, "grad_norm": 0.4047764241695404, "learning_rate": 2.2089558559920123e-05, "loss": 4.2616, "step": 17586 }, { "epoch": 0.5371716554673183, "grad_norm": 0.39435794949531555, "learning_rate": 2.2087175990157482e-05, "loss": 4.2469, "step": 17587 }, { "epoch": 0.5372021991447771, "grad_norm": 0.40189602971076965, "learning_rate": 2.2084793447214704e-05, "loss": 4.3185, "step": 17588 }, { "epoch": 0.5372327428222358, "grad_norm": 0.40889304876327515, "learning_rate": 2.208241093111374e-05, "loss": 4.2523, "step": 17589 }, { "epoch": 0.5372632864996946, "grad_norm": 0.39663341641426086, "learning_rate": 2.2080028441876508e-05, "loss": 4.319, "step": 17590 }, { "epoch": 0.5372938301771534, "grad_norm": 0.40302741527557373, "learning_rate": 2.2077645979524956e-05, "loss": 4.3595, "step": 17591 }, { "epoch": 0.5373243738546121, "grad_norm": 0.39727485179901123, "learning_rate": 2.2075263544081033e-05, "loss": 4.2221, "step": 17592 }, { "epoch": 0.5373549175320709, "grad_norm": 0.39239272475242615, "learning_rate": 2.207288113556665e-05, "loss": 4.2977, "step": 17593 }, { "epoch": 0.5373854612095297, "grad_norm": 0.4050658643245697, "learning_rate": 2.207049875400376e-05, "loss": 4.2899, "step": 17594 }, { "epoch": 0.5374160048869884, "grad_norm": 0.39609313011169434, "learning_rate": 2.2068116399414294e-05, "loss": 4.1882, "step": 17595 }, { "epoch": 0.5374465485644472, "grad_norm": 0.39957642555236816, "learning_rate": 2.206573407182019e-05, "loss": 4.2609, "step": 17596 }, { "epoch": 0.5374770922419059, "grad_norm": 0.4056844413280487, "learning_rate": 2.2063351771243382e-05, "loss": 4.2895, "step": 17597 }, { "epoch": 0.5375076359193647, "grad_norm": 0.4040898382663727, "learning_rate": 2.2060969497705795e-05, "loss": 4.4415, "step": 17598 }, { "epoch": 0.5375381795968235, "grad_norm": 0.3954162001609802, "learning_rate": 2.2058587251229373e-05, "loss": 4.2905, "step": 17599 }, { "epoch": 0.5375687232742822, "grad_norm": 0.3990013003349304, "learning_rate": 2.2056205031836063e-05, "loss": 4.3665, "step": 17600 }, { "epoch": 0.537599266951741, "grad_norm": 0.40563860535621643, "learning_rate": 2.2053822839547774e-05, "loss": 4.2969, "step": 17601 }, { "epoch": 0.5376298106291998, "grad_norm": 0.4072929322719574, "learning_rate": 2.205144067438646e-05, "loss": 4.2236, "step": 17602 }, { "epoch": 0.5376603543066585, "grad_norm": 0.39762523770332336, "learning_rate": 2.204905853637405e-05, "loss": 4.2136, "step": 17603 }, { "epoch": 0.5376908979841173, "grad_norm": 0.40021833777427673, "learning_rate": 2.204667642553247e-05, "loss": 4.24, "step": 17604 }, { "epoch": 0.5377214416615761, "grad_norm": 0.4000873267650604, "learning_rate": 2.2044294341883655e-05, "loss": 4.2511, "step": 17605 }, { "epoch": 0.5377519853390348, "grad_norm": 0.3936825096607208, "learning_rate": 2.2041912285449554e-05, "loss": 4.3665, "step": 17606 }, { "epoch": 0.5377825290164936, "grad_norm": 0.3990184962749481, "learning_rate": 2.2039530256252075e-05, "loss": 4.2721, "step": 17607 }, { "epoch": 0.5378130726939524, "grad_norm": 0.4175666272640228, "learning_rate": 2.2037148254313163e-05, "loss": 4.3247, "step": 17608 }, { "epoch": 0.5378436163714111, "grad_norm": 0.3921147882938385, "learning_rate": 2.2034766279654763e-05, "loss": 4.2425, "step": 17609 }, { "epoch": 0.5378741600488699, "grad_norm": 0.3952483534812927, "learning_rate": 2.203238433229879e-05, "loss": 4.2379, "step": 17610 }, { "epoch": 0.5379047037263287, "grad_norm": 0.38773414492607117, "learning_rate": 2.2030002412267174e-05, "loss": 4.2655, "step": 17611 }, { "epoch": 0.5379352474037874, "grad_norm": 0.39842888712882996, "learning_rate": 2.202762051958186e-05, "loss": 4.2389, "step": 17612 }, { "epoch": 0.5379657910812462, "grad_norm": 0.40307867527008057, "learning_rate": 2.2025238654264767e-05, "loss": 4.0996, "step": 17613 }, { "epoch": 0.5379963347587049, "grad_norm": 0.40091848373413086, "learning_rate": 2.2022856816337837e-05, "loss": 4.255, "step": 17614 }, { "epoch": 0.5380268784361637, "grad_norm": 0.39766064286231995, "learning_rate": 2.2020475005822984e-05, "loss": 4.3592, "step": 17615 }, { "epoch": 0.5380574221136225, "grad_norm": 0.3994275629520416, "learning_rate": 2.2018093222742153e-05, "loss": 4.1717, "step": 17616 }, { "epoch": 0.5380879657910812, "grad_norm": 0.3972587585449219, "learning_rate": 2.201571146711728e-05, "loss": 4.2713, "step": 17617 }, { "epoch": 0.53811850946854, "grad_norm": 0.40044862031936646, "learning_rate": 2.2013329738970277e-05, "loss": 4.2738, "step": 17618 }, { "epoch": 0.5381490531459988, "grad_norm": 0.40577128529548645, "learning_rate": 2.2010948038323085e-05, "loss": 4.3525, "step": 17619 }, { "epoch": 0.5381795968234575, "grad_norm": 0.4042204022407532, "learning_rate": 2.200856636519764e-05, "loss": 4.3123, "step": 17620 }, { "epoch": 0.5382101405009163, "grad_norm": 0.41045841574668884, "learning_rate": 2.2006184719615847e-05, "loss": 4.338, "step": 17621 }, { "epoch": 0.5382406841783751, "grad_norm": 0.39662131667137146, "learning_rate": 2.2003803101599653e-05, "loss": 4.3127, "step": 17622 }, { "epoch": 0.5382712278558338, "grad_norm": 0.40364590287208557, "learning_rate": 2.2001421511170997e-05, "loss": 4.3029, "step": 17623 }, { "epoch": 0.5383017715332926, "grad_norm": 0.39031124114990234, "learning_rate": 2.1999039948351783e-05, "loss": 4.3543, "step": 17624 }, { "epoch": 0.5383323152107514, "grad_norm": 0.3864196240901947, "learning_rate": 2.1996658413163956e-05, "loss": 4.2147, "step": 17625 }, { "epoch": 0.5383628588882101, "grad_norm": 0.4043090045452118, "learning_rate": 2.1994276905629438e-05, "loss": 4.3335, "step": 17626 }, { "epoch": 0.5383934025656689, "grad_norm": 0.4021712839603424, "learning_rate": 2.199189542577016e-05, "loss": 4.2848, "step": 17627 }, { "epoch": 0.5384239462431277, "grad_norm": 0.39421090483665466, "learning_rate": 2.198951397360804e-05, "loss": 4.3205, "step": 17628 }, { "epoch": 0.5384544899205864, "grad_norm": 0.39085352420806885, "learning_rate": 2.1987132549165025e-05, "loss": 4.2671, "step": 17629 }, { "epoch": 0.5384850335980452, "grad_norm": 0.39999571442604065, "learning_rate": 2.198475115246302e-05, "loss": 4.3258, "step": 17630 }, { "epoch": 0.5385155772755039, "grad_norm": 0.40607187151908875, "learning_rate": 2.1982369783523972e-05, "loss": 4.3542, "step": 17631 }, { "epoch": 0.5385461209529627, "grad_norm": 0.40332990884780884, "learning_rate": 2.197998844236978e-05, "loss": 4.4109, "step": 17632 }, { "epoch": 0.5385766646304215, "grad_norm": 0.397681325674057, "learning_rate": 2.19776071290224e-05, "loss": 4.299, "step": 17633 }, { "epoch": 0.5386072083078802, "grad_norm": 0.40203842520713806, "learning_rate": 2.197522584350374e-05, "loss": 4.2974, "step": 17634 }, { "epoch": 0.538637751985339, "grad_norm": 0.397827684879303, "learning_rate": 2.1972844585835736e-05, "loss": 4.1967, "step": 17635 }, { "epoch": 0.5386682956627978, "grad_norm": 0.38649725914001465, "learning_rate": 2.19704633560403e-05, "loss": 4.2174, "step": 17636 }, { "epoch": 0.5386988393402565, "grad_norm": 0.40474364161491394, "learning_rate": 2.1968082154139378e-05, "loss": 4.2838, "step": 17637 }, { "epoch": 0.5387293830177153, "grad_norm": 0.3993789255619049, "learning_rate": 2.196570098015487e-05, "loss": 4.2637, "step": 17638 }, { "epoch": 0.5387599266951741, "grad_norm": 0.39929574728012085, "learning_rate": 2.196331983410871e-05, "loss": 4.3223, "step": 17639 }, { "epoch": 0.5387904703726328, "grad_norm": 0.39952561259269714, "learning_rate": 2.196093871602284e-05, "loss": 4.2303, "step": 17640 }, { "epoch": 0.5388210140500916, "grad_norm": 0.402424693107605, "learning_rate": 2.195855762591916e-05, "loss": 4.3247, "step": 17641 }, { "epoch": 0.5388515577275504, "grad_norm": 0.40593722462654114, "learning_rate": 2.1956176563819607e-05, "loss": 4.287, "step": 17642 }, { "epoch": 0.5388821014050091, "grad_norm": 0.3938712775707245, "learning_rate": 2.195379552974611e-05, "loss": 4.285, "step": 17643 }, { "epoch": 0.538912645082468, "grad_norm": 0.38961702585220337, "learning_rate": 2.195141452372057e-05, "loss": 4.2552, "step": 17644 }, { "epoch": 0.5389431887599268, "grad_norm": 0.39476755261421204, "learning_rate": 2.1949033545764924e-05, "loss": 4.2887, "step": 17645 }, { "epoch": 0.5389737324373854, "grad_norm": 0.39791423082351685, "learning_rate": 2.194665259590111e-05, "loss": 4.2652, "step": 17646 }, { "epoch": 0.5390042761148442, "grad_norm": 0.40448901057243347, "learning_rate": 2.194427167415102e-05, "loss": 4.3021, "step": 17647 }, { "epoch": 0.5390348197923029, "grad_norm": 0.40244728326797485, "learning_rate": 2.19418907805366e-05, "loss": 4.3105, "step": 17648 }, { "epoch": 0.5390653634697617, "grad_norm": 0.39478856325149536, "learning_rate": 2.1939509915079756e-05, "loss": 4.2252, "step": 17649 }, { "epoch": 0.5390959071472206, "grad_norm": 0.3999432921409607, "learning_rate": 2.1937129077802422e-05, "loss": 4.2747, "step": 17650 }, { "epoch": 0.5391264508246792, "grad_norm": 0.4017772376537323, "learning_rate": 2.1934748268726525e-05, "loss": 4.2947, "step": 17651 }, { "epoch": 0.539156994502138, "grad_norm": 0.38876718282699585, "learning_rate": 2.1932367487873962e-05, "loss": 4.2822, "step": 17652 }, { "epoch": 0.5391875381795969, "grad_norm": 0.3991703689098358, "learning_rate": 2.1929986735266672e-05, "loss": 4.299, "step": 17653 }, { "epoch": 0.5392180818570556, "grad_norm": 0.4067111313343048, "learning_rate": 2.192760601092658e-05, "loss": 4.2974, "step": 17654 }, { "epoch": 0.5392486255345144, "grad_norm": 0.3866025507450104, "learning_rate": 2.1925225314875587e-05, "loss": 4.293, "step": 17655 }, { "epoch": 0.5392791692119732, "grad_norm": 0.39949604868888855, "learning_rate": 2.1922844647135638e-05, "loss": 4.2289, "step": 17656 }, { "epoch": 0.5393097128894319, "grad_norm": 0.39776337146759033, "learning_rate": 2.1920464007728633e-05, "loss": 4.3383, "step": 17657 }, { "epoch": 0.5393402565668907, "grad_norm": 0.3953717350959778, "learning_rate": 2.1918083396676503e-05, "loss": 4.258, "step": 17658 }, { "epoch": 0.5393708002443495, "grad_norm": 0.39245566725730896, "learning_rate": 2.1915702814001156e-05, "loss": 4.2791, "step": 17659 }, { "epoch": 0.5394013439218082, "grad_norm": 0.3941556513309479, "learning_rate": 2.1913322259724533e-05, "loss": 4.3336, "step": 17660 }, { "epoch": 0.539431887599267, "grad_norm": 0.39774221181869507, "learning_rate": 2.1910941733868525e-05, "loss": 4.2389, "step": 17661 }, { "epoch": 0.5394624312767257, "grad_norm": 0.3997329771518707, "learning_rate": 2.1908561236455077e-05, "loss": 4.3119, "step": 17662 }, { "epoch": 0.5394929749541845, "grad_norm": 0.4061392545700073, "learning_rate": 2.1906180767506083e-05, "loss": 4.2806, "step": 17663 }, { "epoch": 0.5395235186316433, "grad_norm": 0.409270316362381, "learning_rate": 2.190380032704348e-05, "loss": 4.3095, "step": 17664 }, { "epoch": 0.539554062309102, "grad_norm": 0.390144407749176, "learning_rate": 2.1901419915089184e-05, "loss": 4.1907, "step": 17665 }, { "epoch": 0.5395846059865608, "grad_norm": 0.39157503843307495, "learning_rate": 2.1899039531665103e-05, "loss": 4.3124, "step": 17666 }, { "epoch": 0.5396151496640196, "grad_norm": 0.39306923747062683, "learning_rate": 2.189665917679315e-05, "loss": 4.2679, "step": 17667 }, { "epoch": 0.5396456933414783, "grad_norm": 0.39698413014411926, "learning_rate": 2.189427885049527e-05, "loss": 4.2703, "step": 17668 }, { "epoch": 0.5396762370189371, "grad_norm": 0.40316110849380493, "learning_rate": 2.1891898552793347e-05, "loss": 4.2626, "step": 17669 }, { "epoch": 0.5397067806963959, "grad_norm": 0.4016358256340027, "learning_rate": 2.1889518283709312e-05, "loss": 4.307, "step": 17670 }, { "epoch": 0.5397373243738546, "grad_norm": 0.39753732085227966, "learning_rate": 2.1887138043265094e-05, "loss": 4.3265, "step": 17671 }, { "epoch": 0.5397678680513134, "grad_norm": 0.3989063799381256, "learning_rate": 2.1884757831482584e-05, "loss": 4.3612, "step": 17672 }, { "epoch": 0.5397984117287722, "grad_norm": 0.39424601197242737, "learning_rate": 2.1882377648383714e-05, "loss": 4.2577, "step": 17673 }, { "epoch": 0.5398289554062309, "grad_norm": 0.40066593885421753, "learning_rate": 2.1879997493990403e-05, "loss": 4.2835, "step": 17674 }, { "epoch": 0.5398594990836897, "grad_norm": 0.39531898498535156, "learning_rate": 2.1877617368324547e-05, "loss": 4.3047, "step": 17675 }, { "epoch": 0.5398900427611485, "grad_norm": 0.40199804306030273, "learning_rate": 2.1875237271408077e-05, "loss": 4.3122, "step": 17676 }, { "epoch": 0.5399205864386072, "grad_norm": 0.3971390724182129, "learning_rate": 2.1872857203262914e-05, "loss": 4.3277, "step": 17677 }, { "epoch": 0.539951130116066, "grad_norm": 0.3966670632362366, "learning_rate": 2.1870477163910952e-05, "loss": 4.2715, "step": 17678 }, { "epoch": 0.5399816737935247, "grad_norm": 0.4071638882160187, "learning_rate": 2.1868097153374123e-05, "loss": 4.224, "step": 17679 }, { "epoch": 0.5400122174709835, "grad_norm": 0.40104618668556213, "learning_rate": 2.1865717171674327e-05, "loss": 4.2694, "step": 17680 }, { "epoch": 0.5400427611484423, "grad_norm": 0.40551531314849854, "learning_rate": 2.1863337218833485e-05, "loss": 4.222, "step": 17681 }, { "epoch": 0.540073304825901, "grad_norm": 0.4026091992855072, "learning_rate": 2.1860957294873513e-05, "loss": 4.222, "step": 17682 }, { "epoch": 0.5401038485033598, "grad_norm": 0.3919178247451782, "learning_rate": 2.185857739981632e-05, "loss": 4.1808, "step": 17683 }, { "epoch": 0.5401343921808186, "grad_norm": 0.41086241602897644, "learning_rate": 2.185619753368382e-05, "loss": 4.3213, "step": 17684 }, { "epoch": 0.5401649358582773, "grad_norm": 0.4110238552093506, "learning_rate": 2.185381769649793e-05, "loss": 4.2693, "step": 17685 }, { "epoch": 0.5401954795357361, "grad_norm": 0.40068021416664124, "learning_rate": 2.185143788828055e-05, "loss": 4.296, "step": 17686 }, { "epoch": 0.5402260232131949, "grad_norm": 0.3884764015674591, "learning_rate": 2.18490581090536e-05, "loss": 4.2544, "step": 17687 }, { "epoch": 0.5402565668906536, "grad_norm": 0.40417158603668213, "learning_rate": 2.1846678358839e-05, "loss": 4.3197, "step": 17688 }, { "epoch": 0.5402871105681124, "grad_norm": 0.40268296003341675, "learning_rate": 2.1844298637658652e-05, "loss": 4.3077, "step": 17689 }, { "epoch": 0.5403176542455712, "grad_norm": 0.4003271758556366, "learning_rate": 2.184191894553446e-05, "loss": 4.3181, "step": 17690 }, { "epoch": 0.5403481979230299, "grad_norm": 0.39676013588905334, "learning_rate": 2.183953928248836e-05, "loss": 4.3042, "step": 17691 }, { "epoch": 0.5403787416004887, "grad_norm": 0.39861544966697693, "learning_rate": 2.1837159648542234e-05, "loss": 4.2895, "step": 17692 }, { "epoch": 0.5404092852779475, "grad_norm": 0.4005342125892639, "learning_rate": 2.1834780043718005e-05, "loss": 4.3853, "step": 17693 }, { "epoch": 0.5404398289554062, "grad_norm": 0.4080963134765625, "learning_rate": 2.183240046803759e-05, "loss": 4.2937, "step": 17694 }, { "epoch": 0.540470372632865, "grad_norm": 0.39159074425697327, "learning_rate": 2.1830020921522885e-05, "loss": 4.2184, "step": 17695 }, { "epoch": 0.5405009163103237, "grad_norm": 0.395297646522522, "learning_rate": 2.182764140419582e-05, "loss": 4.3395, "step": 17696 }, { "epoch": 0.5405314599877825, "grad_norm": 0.40394312143325806, "learning_rate": 2.1825261916078288e-05, "loss": 4.2459, "step": 17697 }, { "epoch": 0.5405620036652413, "grad_norm": 0.42049697041511536, "learning_rate": 2.182288245719219e-05, "loss": 4.271, "step": 17698 }, { "epoch": 0.5405925473427, "grad_norm": 0.40139687061309814, "learning_rate": 2.1820503027559464e-05, "loss": 4.3707, "step": 17699 }, { "epoch": 0.5406230910201588, "grad_norm": 0.39935269951820374, "learning_rate": 2.1818123627201985e-05, "loss": 4.2789, "step": 17700 }, { "epoch": 0.5406536346976176, "grad_norm": 0.4056501090526581, "learning_rate": 2.1815744256141678e-05, "loss": 4.2384, "step": 17701 }, { "epoch": 0.5406841783750763, "grad_norm": 0.4103955924510956, "learning_rate": 2.1813364914400468e-05, "loss": 4.3925, "step": 17702 }, { "epoch": 0.5407147220525351, "grad_norm": 0.3984735906124115, "learning_rate": 2.1810985602000228e-05, "loss": 4.2232, "step": 17703 }, { "epoch": 0.5407452657299939, "grad_norm": 0.39461538195610046, "learning_rate": 2.180860631896289e-05, "loss": 4.2125, "step": 17704 }, { "epoch": 0.5407758094074526, "grad_norm": 0.40025702118873596, "learning_rate": 2.1806227065310355e-05, "loss": 4.2652, "step": 17705 }, { "epoch": 0.5408063530849114, "grad_norm": 0.4145715832710266, "learning_rate": 2.180384784106453e-05, "loss": 4.1676, "step": 17706 }, { "epoch": 0.5408368967623702, "grad_norm": 0.3960014283657074, "learning_rate": 2.1801468646247318e-05, "loss": 4.3226, "step": 17707 }, { "epoch": 0.5408674404398289, "grad_norm": 0.3985217213630676, "learning_rate": 2.1799089480880634e-05, "loss": 4.1991, "step": 17708 }, { "epoch": 0.5408979841172877, "grad_norm": 0.4065625071525574, "learning_rate": 2.1796710344986374e-05, "loss": 4.2527, "step": 17709 }, { "epoch": 0.5409285277947465, "grad_norm": 0.404002845287323, "learning_rate": 2.1794331238586447e-05, "loss": 4.3103, "step": 17710 }, { "epoch": 0.5409590714722052, "grad_norm": 0.3984246253967285, "learning_rate": 2.179195216170277e-05, "loss": 4.2707, "step": 17711 }, { "epoch": 0.540989615149664, "grad_norm": 0.40291330218315125, "learning_rate": 2.1789573114357236e-05, "loss": 4.2585, "step": 17712 }, { "epoch": 0.5410201588271227, "grad_norm": 0.3857273757457733, "learning_rate": 2.1787194096571748e-05, "loss": 4.291, "step": 17713 }, { "epoch": 0.5410507025045815, "grad_norm": 0.4011026620864868, "learning_rate": 2.1784815108368216e-05, "loss": 4.295, "step": 17714 }, { "epoch": 0.5410812461820403, "grad_norm": 0.3926413357257843, "learning_rate": 2.1782436149768546e-05, "loss": 4.2924, "step": 17715 }, { "epoch": 0.541111789859499, "grad_norm": 0.4005396068096161, "learning_rate": 2.1780057220794646e-05, "loss": 4.4146, "step": 17716 }, { "epoch": 0.5411423335369578, "grad_norm": 0.4021865129470825, "learning_rate": 2.1777678321468404e-05, "loss": 4.2946, "step": 17717 }, { "epoch": 0.5411728772144166, "grad_norm": 0.4052032232284546, "learning_rate": 2.1775299451811737e-05, "loss": 4.3772, "step": 17718 }, { "epoch": 0.5412034208918753, "grad_norm": 0.40048936009407043, "learning_rate": 2.1772920611846553e-05, "loss": 4.3474, "step": 17719 }, { "epoch": 0.5412339645693341, "grad_norm": 0.4019205868244171, "learning_rate": 2.1770541801594746e-05, "loss": 4.3419, "step": 17720 }, { "epoch": 0.541264508246793, "grad_norm": 0.38965100049972534, "learning_rate": 2.1768163021078213e-05, "loss": 4.3199, "step": 17721 }, { "epoch": 0.5412950519242516, "grad_norm": 0.41322529315948486, "learning_rate": 2.176578427031888e-05, "loss": 4.3434, "step": 17722 }, { "epoch": 0.5413255956017105, "grad_norm": 0.38435888290405273, "learning_rate": 2.176340554933862e-05, "loss": 4.2903, "step": 17723 }, { "epoch": 0.5413561392791693, "grad_norm": 0.39738592505455017, "learning_rate": 2.176102685815935e-05, "loss": 4.2369, "step": 17724 }, { "epoch": 0.541386682956628, "grad_norm": 0.4153304696083069, "learning_rate": 2.175864819680298e-05, "loss": 4.3482, "step": 17725 }, { "epoch": 0.5414172266340868, "grad_norm": 0.3995625078678131, "learning_rate": 2.1756269565291394e-05, "loss": 4.3143, "step": 17726 }, { "epoch": 0.5414477703115456, "grad_norm": 0.39559152722358704, "learning_rate": 2.1753890963646505e-05, "loss": 4.2904, "step": 17727 }, { "epoch": 0.5414783139890043, "grad_norm": 0.39484313130378723, "learning_rate": 2.1751512391890214e-05, "loss": 4.1884, "step": 17728 }, { "epoch": 0.5415088576664631, "grad_norm": 0.39902064204216003, "learning_rate": 2.174913385004442e-05, "loss": 4.2763, "step": 17729 }, { "epoch": 0.5415394013439218, "grad_norm": 0.39763203263282776, "learning_rate": 2.174675533813102e-05, "loss": 4.2834, "step": 17730 }, { "epoch": 0.5415699450213806, "grad_norm": 0.40657687187194824, "learning_rate": 2.174437685617191e-05, "loss": 4.2355, "step": 17731 }, { "epoch": 0.5416004886988394, "grad_norm": 0.41165655851364136, "learning_rate": 2.1741998404188995e-05, "loss": 4.4026, "step": 17732 }, { "epoch": 0.5416310323762981, "grad_norm": 0.3927052319049835, "learning_rate": 2.173961998220419e-05, "loss": 4.3243, "step": 17733 }, { "epoch": 0.5416615760537569, "grad_norm": 0.39920854568481445, "learning_rate": 2.1737241590239366e-05, "loss": 4.3756, "step": 17734 }, { "epoch": 0.5416921197312157, "grad_norm": 0.4113107919692993, "learning_rate": 2.1734863228316443e-05, "loss": 4.2039, "step": 17735 }, { "epoch": 0.5417226634086744, "grad_norm": 0.39222851395606995, "learning_rate": 2.173248489645731e-05, "loss": 4.2927, "step": 17736 }, { "epoch": 0.5417532070861332, "grad_norm": 0.39795225858688354, "learning_rate": 2.1730106594683875e-05, "loss": 4.2104, "step": 17737 }, { "epoch": 0.541783750763592, "grad_norm": 0.4042458236217499, "learning_rate": 2.1727728323018022e-05, "loss": 4.3101, "step": 17738 }, { "epoch": 0.5418142944410507, "grad_norm": 0.3953306972980499, "learning_rate": 2.1725350081481663e-05, "loss": 4.249, "step": 17739 }, { "epoch": 0.5418448381185095, "grad_norm": 0.4000888466835022, "learning_rate": 2.172297187009668e-05, "loss": 4.3352, "step": 17740 }, { "epoch": 0.5418753817959683, "grad_norm": 0.3966306447982788, "learning_rate": 2.1720593688884985e-05, "loss": 4.3031, "step": 17741 }, { "epoch": 0.541905925473427, "grad_norm": 0.4103957712650299, "learning_rate": 2.171821553786848e-05, "loss": 4.2622, "step": 17742 }, { "epoch": 0.5419364691508858, "grad_norm": 0.3971138000488281, "learning_rate": 2.171583741706904e-05, "loss": 4.2819, "step": 17743 }, { "epoch": 0.5419670128283446, "grad_norm": 0.39240166544914246, "learning_rate": 2.1713459326508574e-05, "loss": 4.2601, "step": 17744 }, { "epoch": 0.5419975565058033, "grad_norm": 0.3932826519012451, "learning_rate": 2.1711081266208985e-05, "loss": 4.3367, "step": 17745 }, { "epoch": 0.5420281001832621, "grad_norm": 0.3980084955692291, "learning_rate": 2.170870323619215e-05, "loss": 4.327, "step": 17746 }, { "epoch": 0.5420586438607208, "grad_norm": 0.3970754146575928, "learning_rate": 2.1706325236479992e-05, "loss": 4.28, "step": 17747 }, { "epoch": 0.5420891875381796, "grad_norm": 0.3987519145011902, "learning_rate": 2.170394726709438e-05, "loss": 4.2834, "step": 17748 }, { "epoch": 0.5421197312156384, "grad_norm": 0.395993709564209, "learning_rate": 2.1701569328057217e-05, "loss": 4.2823, "step": 17749 }, { "epoch": 0.5421502748930971, "grad_norm": 0.4055258631706238, "learning_rate": 2.1699191419390413e-05, "loss": 4.1976, "step": 17750 }, { "epoch": 0.5421808185705559, "grad_norm": 0.4035756289958954, "learning_rate": 2.169681354111584e-05, "loss": 4.3198, "step": 17751 }, { "epoch": 0.5422113622480147, "grad_norm": 0.3997751772403717, "learning_rate": 2.169443569325541e-05, "loss": 4.1918, "step": 17752 }, { "epoch": 0.5422419059254734, "grad_norm": 0.396454781293869, "learning_rate": 2.169205787583101e-05, "loss": 4.3658, "step": 17753 }, { "epoch": 0.5422724496029322, "grad_norm": 0.39314010739326477, "learning_rate": 2.168968008886453e-05, "loss": 4.3557, "step": 17754 }, { "epoch": 0.542302993280391, "grad_norm": 0.399286687374115, "learning_rate": 2.1687302332377867e-05, "loss": 4.3053, "step": 17755 }, { "epoch": 0.5423335369578497, "grad_norm": 0.39319321513175964, "learning_rate": 2.168492460639292e-05, "loss": 4.31, "step": 17756 }, { "epoch": 0.5423640806353085, "grad_norm": 0.4058838486671448, "learning_rate": 2.168254691093157e-05, "loss": 4.2137, "step": 17757 }, { "epoch": 0.5423946243127673, "grad_norm": 0.40619054436683655, "learning_rate": 2.168016924601572e-05, "loss": 4.3401, "step": 17758 }, { "epoch": 0.542425167990226, "grad_norm": 0.39166259765625, "learning_rate": 2.1677791611667258e-05, "loss": 4.2591, "step": 17759 }, { "epoch": 0.5424557116676848, "grad_norm": 0.3970774710178375, "learning_rate": 2.167541400790808e-05, "loss": 4.2844, "step": 17760 }, { "epoch": 0.5424862553451436, "grad_norm": 0.39776819944381714, "learning_rate": 2.1673036434760066e-05, "loss": 4.2557, "step": 17761 }, { "epoch": 0.5425167990226023, "grad_norm": 0.3969067633152008, "learning_rate": 2.1670658892245127e-05, "loss": 4.2519, "step": 17762 }, { "epoch": 0.5425473427000611, "grad_norm": 0.4044017791748047, "learning_rate": 2.1668281380385134e-05, "loss": 4.4362, "step": 17763 }, { "epoch": 0.5425778863775198, "grad_norm": 0.395017147064209, "learning_rate": 2.1665903899201998e-05, "loss": 4.3028, "step": 17764 }, { "epoch": 0.5426084300549786, "grad_norm": 0.4026811420917511, "learning_rate": 2.1663526448717586e-05, "loss": 4.2683, "step": 17765 }, { "epoch": 0.5426389737324374, "grad_norm": 0.39862221479415894, "learning_rate": 2.1661149028953808e-05, "loss": 4.2986, "step": 17766 }, { "epoch": 0.5426695174098961, "grad_norm": 0.4135335683822632, "learning_rate": 2.1658771639932552e-05, "loss": 4.2988, "step": 17767 }, { "epoch": 0.5427000610873549, "grad_norm": 0.39833250641822815, "learning_rate": 2.16563942816757e-05, "loss": 4.2162, "step": 17768 }, { "epoch": 0.5427306047648137, "grad_norm": 0.3995916545391083, "learning_rate": 2.1654016954205136e-05, "loss": 4.2972, "step": 17769 }, { "epoch": 0.5427611484422724, "grad_norm": 0.40774253010749817, "learning_rate": 2.1651639657542774e-05, "loss": 4.292, "step": 17770 }, { "epoch": 0.5427916921197312, "grad_norm": 0.3970165252685547, "learning_rate": 2.1649262391710473e-05, "loss": 4.263, "step": 17771 }, { "epoch": 0.54282223579719, "grad_norm": 0.3973940312862396, "learning_rate": 2.1646885156730142e-05, "loss": 4.2596, "step": 17772 }, { "epoch": 0.5428527794746487, "grad_norm": 0.39976999163627625, "learning_rate": 2.1644507952623666e-05, "loss": 4.2248, "step": 17773 }, { "epoch": 0.5428833231521075, "grad_norm": 0.4006308913230896, "learning_rate": 2.1642130779412924e-05, "loss": 4.2681, "step": 17774 }, { "epoch": 0.5429138668295663, "grad_norm": 0.40763863921165466, "learning_rate": 2.1639753637119813e-05, "loss": 4.375, "step": 17775 }, { "epoch": 0.542944410507025, "grad_norm": 0.411094069480896, "learning_rate": 2.163737652576623e-05, "loss": 4.3442, "step": 17776 }, { "epoch": 0.5429749541844838, "grad_norm": 0.3990481197834015, "learning_rate": 2.1634999445374033e-05, "loss": 4.3231, "step": 17777 }, { "epoch": 0.5430054978619426, "grad_norm": 0.4126923680305481, "learning_rate": 2.1632622395965128e-05, "loss": 4.346, "step": 17778 }, { "epoch": 0.5430360415394013, "grad_norm": 0.39270517230033875, "learning_rate": 2.1630245377561407e-05, "loss": 4.3894, "step": 17779 }, { "epoch": 0.5430665852168601, "grad_norm": 0.40301838517189026, "learning_rate": 2.1627868390184747e-05, "loss": 4.1906, "step": 17780 }, { "epoch": 0.5430971288943188, "grad_norm": 0.3946962058544159, "learning_rate": 2.1625491433857042e-05, "loss": 4.3293, "step": 17781 }, { "epoch": 0.5431276725717776, "grad_norm": 0.39260363578796387, "learning_rate": 2.1623114508600162e-05, "loss": 4.1867, "step": 17782 }, { "epoch": 0.5431582162492364, "grad_norm": 0.395193874835968, "learning_rate": 2.162073761443601e-05, "loss": 4.3725, "step": 17783 }, { "epoch": 0.5431887599266951, "grad_norm": 0.3967553973197937, "learning_rate": 2.1618360751386468e-05, "loss": 4.1651, "step": 17784 }, { "epoch": 0.5432193036041539, "grad_norm": 0.40111687779426575, "learning_rate": 2.1615983919473405e-05, "loss": 4.2833, "step": 17785 }, { "epoch": 0.5432498472816127, "grad_norm": 0.4073619246482849, "learning_rate": 2.161360711871872e-05, "loss": 4.2256, "step": 17786 }, { "epoch": 0.5432803909590714, "grad_norm": 0.3919562101364136, "learning_rate": 2.1611230349144307e-05, "loss": 4.2357, "step": 17787 }, { "epoch": 0.5433109346365302, "grad_norm": 0.3958987593650818, "learning_rate": 2.1608853610772026e-05, "loss": 4.251, "step": 17788 }, { "epoch": 0.543341478313989, "grad_norm": 0.3995066285133362, "learning_rate": 2.160647690362378e-05, "loss": 4.336, "step": 17789 }, { "epoch": 0.5433720219914477, "grad_norm": 0.3916167616844177, "learning_rate": 2.1604100227721442e-05, "loss": 4.2835, "step": 17790 }, { "epoch": 0.5434025656689065, "grad_norm": 0.41388657689094543, "learning_rate": 2.1601723583086906e-05, "loss": 4.0957, "step": 17791 }, { "epoch": 0.5434331093463654, "grad_norm": 0.40482422709465027, "learning_rate": 2.159934696974204e-05, "loss": 4.2928, "step": 17792 }, { "epoch": 0.543463653023824, "grad_norm": 0.40639540553092957, "learning_rate": 2.1596970387708743e-05, "loss": 4.3263, "step": 17793 }, { "epoch": 0.5434941967012829, "grad_norm": 0.3960679769515991, "learning_rate": 2.159459383700888e-05, "loss": 4.2329, "step": 17794 }, { "epoch": 0.5435247403787417, "grad_norm": 0.40482255816459656, "learning_rate": 2.159221731766434e-05, "loss": 4.2636, "step": 17795 }, { "epoch": 0.5435552840562003, "grad_norm": 0.40551993250846863, "learning_rate": 2.1589840829697023e-05, "loss": 4.2684, "step": 17796 }, { "epoch": 0.5435858277336592, "grad_norm": 0.3969292938709259, "learning_rate": 2.1587464373128782e-05, "loss": 4.2686, "step": 17797 }, { "epoch": 0.5436163714111178, "grad_norm": 0.403535932302475, "learning_rate": 2.1585087947981523e-05, "loss": 4.2801, "step": 17798 }, { "epoch": 0.5436469150885767, "grad_norm": 0.3968461751937866, "learning_rate": 2.1582711554277106e-05, "loss": 4.3245, "step": 17799 }, { "epoch": 0.5436774587660355, "grad_norm": 0.39967551827430725, "learning_rate": 2.1580335192037422e-05, "loss": 4.3004, "step": 17800 }, { "epoch": 0.5437080024434942, "grad_norm": 0.39710384607315063, "learning_rate": 2.1577958861284352e-05, "loss": 4.2395, "step": 17801 }, { "epoch": 0.543738546120953, "grad_norm": 0.4030826687812805, "learning_rate": 2.157558256203977e-05, "loss": 4.3701, "step": 17802 }, { "epoch": 0.5437690897984118, "grad_norm": 0.3927137553691864, "learning_rate": 2.157320629432556e-05, "loss": 4.3318, "step": 17803 }, { "epoch": 0.5437996334758705, "grad_norm": 0.4074222147464752, "learning_rate": 2.157083005816361e-05, "loss": 4.2892, "step": 17804 }, { "epoch": 0.5438301771533293, "grad_norm": 0.3988654613494873, "learning_rate": 2.156845385357578e-05, "loss": 4.2958, "step": 17805 }, { "epoch": 0.5438607208307881, "grad_norm": 0.41929298639297485, "learning_rate": 2.1566077680583967e-05, "loss": 4.1724, "step": 17806 }, { "epoch": 0.5438912645082468, "grad_norm": 0.3922084867954254, "learning_rate": 2.1563701539210042e-05, "loss": 4.2512, "step": 17807 }, { "epoch": 0.5439218081857056, "grad_norm": 0.39632630348205566, "learning_rate": 2.156132542947588e-05, "loss": 4.3639, "step": 17808 }, { "epoch": 0.5439523518631644, "grad_norm": 0.3954261541366577, "learning_rate": 2.155894935140336e-05, "loss": 4.1871, "step": 17809 }, { "epoch": 0.5439828955406231, "grad_norm": 0.39846423268318176, "learning_rate": 2.155657330501437e-05, "loss": 4.2537, "step": 17810 }, { "epoch": 0.5440134392180819, "grad_norm": 0.3987862169742584, "learning_rate": 2.1554197290330774e-05, "loss": 4.2438, "step": 17811 }, { "epoch": 0.5440439828955406, "grad_norm": 0.3952085077762604, "learning_rate": 2.1551821307374463e-05, "loss": 4.2724, "step": 17812 }, { "epoch": 0.5440745265729994, "grad_norm": 0.3995920717716217, "learning_rate": 2.1549445356167295e-05, "loss": 4.2632, "step": 17813 }, { "epoch": 0.5441050702504582, "grad_norm": 0.41882166266441345, "learning_rate": 2.1547069436731168e-05, "loss": 4.334, "step": 17814 }, { "epoch": 0.5441356139279169, "grad_norm": 0.39889487624168396, "learning_rate": 2.1544693549087947e-05, "loss": 4.2706, "step": 17815 }, { "epoch": 0.5441661576053757, "grad_norm": 0.40899044275283813, "learning_rate": 2.1542317693259505e-05, "loss": 4.2589, "step": 17816 }, { "epoch": 0.5441967012828345, "grad_norm": 0.39802661538124084, "learning_rate": 2.1539941869267717e-05, "loss": 4.3682, "step": 17817 }, { "epoch": 0.5442272449602932, "grad_norm": 0.39338478446006775, "learning_rate": 2.1537566077134478e-05, "loss": 4.2673, "step": 17818 }, { "epoch": 0.544257788637752, "grad_norm": 0.4028678238391876, "learning_rate": 2.1535190316881635e-05, "loss": 4.2332, "step": 17819 }, { "epoch": 0.5442883323152108, "grad_norm": 0.4101259708404541, "learning_rate": 2.1532814588531075e-05, "loss": 4.2234, "step": 17820 }, { "epoch": 0.5443188759926695, "grad_norm": 0.3985699713230133, "learning_rate": 2.1530438892104685e-05, "loss": 4.3334, "step": 17821 }, { "epoch": 0.5443494196701283, "grad_norm": 0.3979792594909668, "learning_rate": 2.1528063227624323e-05, "loss": 4.2437, "step": 17822 }, { "epoch": 0.5443799633475871, "grad_norm": 0.3984043300151825, "learning_rate": 2.152568759511186e-05, "loss": 4.2704, "step": 17823 }, { "epoch": 0.5444105070250458, "grad_norm": 0.3999180793762207, "learning_rate": 2.1523311994589195e-05, "loss": 4.3502, "step": 17824 }, { "epoch": 0.5444410507025046, "grad_norm": 0.4039277732372284, "learning_rate": 2.1520936426078167e-05, "loss": 4.284, "step": 17825 }, { "epoch": 0.5444715943799634, "grad_norm": 0.40403011441230774, "learning_rate": 2.151856088960067e-05, "loss": 4.325, "step": 17826 }, { "epoch": 0.5445021380574221, "grad_norm": 0.39892926812171936, "learning_rate": 2.151618538517858e-05, "loss": 4.3705, "step": 17827 }, { "epoch": 0.5445326817348809, "grad_norm": 0.41563645005226135, "learning_rate": 2.1513809912833755e-05, "loss": 4.2721, "step": 17828 }, { "epoch": 0.5445632254123396, "grad_norm": 0.40330633521080017, "learning_rate": 2.1511434472588082e-05, "loss": 4.2211, "step": 17829 }, { "epoch": 0.5445937690897984, "grad_norm": 0.39988818764686584, "learning_rate": 2.1509059064463424e-05, "loss": 4.3267, "step": 17830 }, { "epoch": 0.5446243127672572, "grad_norm": 0.3995557427406311, "learning_rate": 2.1506683688481646e-05, "loss": 4.262, "step": 17831 }, { "epoch": 0.5446548564447159, "grad_norm": 0.40001168847084045, "learning_rate": 2.150430834466464e-05, "loss": 4.3422, "step": 17832 }, { "epoch": 0.5446854001221747, "grad_norm": 0.3970082700252533, "learning_rate": 2.1501933033034253e-05, "loss": 4.3398, "step": 17833 }, { "epoch": 0.5447159437996335, "grad_norm": 0.39326712489128113, "learning_rate": 2.1499557753612364e-05, "loss": 4.3404, "step": 17834 }, { "epoch": 0.5447464874770922, "grad_norm": 0.41129299998283386, "learning_rate": 2.149718250642086e-05, "loss": 4.309, "step": 17835 }, { "epoch": 0.544777031154551, "grad_norm": 0.393475741147995, "learning_rate": 2.149480729148159e-05, "loss": 4.3118, "step": 17836 }, { "epoch": 0.5448075748320098, "grad_norm": 0.4023958146572113, "learning_rate": 2.149243210881643e-05, "loss": 4.3357, "step": 17837 }, { "epoch": 0.5448381185094685, "grad_norm": 0.39700502157211304, "learning_rate": 2.1490056958447256e-05, "loss": 4.2214, "step": 17838 }, { "epoch": 0.5448686621869273, "grad_norm": 0.3962412178516388, "learning_rate": 2.1487681840395928e-05, "loss": 4.3753, "step": 17839 }, { "epoch": 0.5448992058643861, "grad_norm": 0.39784058928489685, "learning_rate": 2.148530675468432e-05, "loss": 4.3088, "step": 17840 }, { "epoch": 0.5449297495418448, "grad_norm": 0.39700847864151, "learning_rate": 2.1482931701334304e-05, "loss": 4.3268, "step": 17841 }, { "epoch": 0.5449602932193036, "grad_norm": 0.4020911455154419, "learning_rate": 2.1480556680367734e-05, "loss": 4.1288, "step": 17842 }, { "epoch": 0.5449908368967624, "grad_norm": 0.4008094370365143, "learning_rate": 2.1478181691806494e-05, "loss": 4.2548, "step": 17843 }, { "epoch": 0.5450213805742211, "grad_norm": 0.39946773648262024, "learning_rate": 2.1475806735672453e-05, "loss": 4.3255, "step": 17844 }, { "epoch": 0.5450519242516799, "grad_norm": 0.39568719267845154, "learning_rate": 2.1473431811987465e-05, "loss": 4.3058, "step": 17845 }, { "epoch": 0.5450824679291386, "grad_norm": 0.38947793841362, "learning_rate": 2.1471056920773404e-05, "loss": 4.2844, "step": 17846 }, { "epoch": 0.5451130116065974, "grad_norm": 0.4013616740703583, "learning_rate": 2.146868206205214e-05, "loss": 4.2926, "step": 17847 }, { "epoch": 0.5451435552840562, "grad_norm": 0.39218732714653015, "learning_rate": 2.1466307235845527e-05, "loss": 4.2579, "step": 17848 }, { "epoch": 0.5451740989615149, "grad_norm": 0.3969977796077728, "learning_rate": 2.146393244217545e-05, "loss": 4.2747, "step": 17849 }, { "epoch": 0.5452046426389737, "grad_norm": 0.41465407609939575, "learning_rate": 2.1461557681063757e-05, "loss": 4.3318, "step": 17850 }, { "epoch": 0.5452351863164325, "grad_norm": 0.4055708944797516, "learning_rate": 2.145918295253232e-05, "loss": 4.3113, "step": 17851 }, { "epoch": 0.5452657299938912, "grad_norm": 0.3918266296386719, "learning_rate": 2.1456808256603017e-05, "loss": 4.2387, "step": 17852 }, { "epoch": 0.54529627367135, "grad_norm": 0.3957691192626953, "learning_rate": 2.1454433593297695e-05, "loss": 4.3217, "step": 17853 }, { "epoch": 0.5453268173488088, "grad_norm": 0.3907942473888397, "learning_rate": 2.1452058962638226e-05, "loss": 4.2828, "step": 17854 }, { "epoch": 0.5453573610262675, "grad_norm": 0.3879343569278717, "learning_rate": 2.144968436464648e-05, "loss": 4.2694, "step": 17855 }, { "epoch": 0.5453879047037263, "grad_norm": 0.41232141852378845, "learning_rate": 2.1447309799344306e-05, "loss": 4.2758, "step": 17856 }, { "epoch": 0.5454184483811851, "grad_norm": 0.4036828279495239, "learning_rate": 2.1444935266753577e-05, "loss": 4.3479, "step": 17857 }, { "epoch": 0.5454489920586438, "grad_norm": 0.40527233481407166, "learning_rate": 2.144256076689617e-05, "loss": 4.2682, "step": 17858 }, { "epoch": 0.5454795357361026, "grad_norm": 0.3982768654823303, "learning_rate": 2.1440186299793922e-05, "loss": 4.245, "step": 17859 }, { "epoch": 0.5455100794135614, "grad_norm": 0.39982151985168457, "learning_rate": 2.1437811865468714e-05, "loss": 4.2157, "step": 17860 }, { "epoch": 0.5455406230910201, "grad_norm": 0.4071528911590576, "learning_rate": 2.1435437463942404e-05, "loss": 4.2664, "step": 17861 }, { "epoch": 0.5455711667684789, "grad_norm": 0.4027228057384491, "learning_rate": 2.1433063095236856e-05, "loss": 4.2801, "step": 17862 }, { "epoch": 0.5456017104459376, "grad_norm": 0.4061543941497803, "learning_rate": 2.1430688759373933e-05, "loss": 4.2315, "step": 17863 }, { "epoch": 0.5456322541233964, "grad_norm": 0.39849647879600525, "learning_rate": 2.1428314456375485e-05, "loss": 4.2803, "step": 17864 }, { "epoch": 0.5456627978008552, "grad_norm": 0.41639479994773865, "learning_rate": 2.142594018626338e-05, "loss": 4.3853, "step": 17865 }, { "epoch": 0.5456933414783139, "grad_norm": 0.40051987767219543, "learning_rate": 2.1423565949059492e-05, "loss": 4.3204, "step": 17866 }, { "epoch": 0.5457238851557727, "grad_norm": 0.4087503254413605, "learning_rate": 2.1421191744785662e-05, "loss": 4.352, "step": 17867 }, { "epoch": 0.5457544288332316, "grad_norm": 0.4090481996536255, "learning_rate": 2.1418817573463764e-05, "loss": 4.2072, "step": 17868 }, { "epoch": 0.5457849725106902, "grad_norm": 0.4037148952484131, "learning_rate": 2.1416443435115656e-05, "loss": 4.2294, "step": 17869 }, { "epoch": 0.545815516188149, "grad_norm": 0.40014106035232544, "learning_rate": 2.141406932976319e-05, "loss": 4.3727, "step": 17870 }, { "epoch": 0.5458460598656079, "grad_norm": 0.4018325209617615, "learning_rate": 2.1411695257428234e-05, "loss": 4.2788, "step": 17871 }, { "epoch": 0.5458766035430666, "grad_norm": 0.4027743339538574, "learning_rate": 2.140932121813265e-05, "loss": 4.2818, "step": 17872 }, { "epoch": 0.5459071472205254, "grad_norm": 0.4019080102443695, "learning_rate": 2.140694721189828e-05, "loss": 4.209, "step": 17873 }, { "epoch": 0.5459376908979842, "grad_norm": 0.40320369601249695, "learning_rate": 2.1404573238747e-05, "loss": 4.2802, "step": 17874 }, { "epoch": 0.5459682345754429, "grad_norm": 0.4021894335746765, "learning_rate": 2.140219929870067e-05, "loss": 4.2562, "step": 17875 }, { "epoch": 0.5459987782529017, "grad_norm": 0.41070085763931274, "learning_rate": 2.1399825391781137e-05, "loss": 4.1213, "step": 17876 }, { "epoch": 0.5460293219303605, "grad_norm": 0.40351590514183044, "learning_rate": 2.1397451518010252e-05, "loss": 4.2673, "step": 17877 }, { "epoch": 0.5460598656078192, "grad_norm": 0.4007019102573395, "learning_rate": 2.13950776774099e-05, "loss": 4.3201, "step": 17878 }, { "epoch": 0.546090409285278, "grad_norm": 0.39843443036079407, "learning_rate": 2.139270387000191e-05, "loss": 4.2919, "step": 17879 }, { "epoch": 0.5461209529627367, "grad_norm": 0.42503923177719116, "learning_rate": 2.1390330095808157e-05, "loss": 4.3572, "step": 17880 }, { "epoch": 0.5461514966401955, "grad_norm": 0.40507498383522034, "learning_rate": 2.1387956354850483e-05, "loss": 4.3311, "step": 17881 }, { "epoch": 0.5461820403176543, "grad_norm": 0.3966383635997772, "learning_rate": 2.138558264715075e-05, "loss": 4.3443, "step": 17882 }, { "epoch": 0.546212583995113, "grad_norm": 0.39477676153182983, "learning_rate": 2.1383208972730828e-05, "loss": 4.3013, "step": 17883 }, { "epoch": 0.5462431276725718, "grad_norm": 0.3916115164756775, "learning_rate": 2.1380835331612555e-05, "loss": 4.0872, "step": 17884 }, { "epoch": 0.5462736713500306, "grad_norm": 0.395486444234848, "learning_rate": 2.1378461723817787e-05, "loss": 4.3322, "step": 17885 }, { "epoch": 0.5463042150274893, "grad_norm": 0.40252161026000977, "learning_rate": 2.1376088149368396e-05, "loss": 4.3007, "step": 17886 }, { "epoch": 0.5463347587049481, "grad_norm": 0.41208571195602417, "learning_rate": 2.1373714608286215e-05, "loss": 4.27, "step": 17887 }, { "epoch": 0.5463653023824069, "grad_norm": 0.39960089325904846, "learning_rate": 2.1371341100593103e-05, "loss": 4.1756, "step": 17888 }, { "epoch": 0.5463958460598656, "grad_norm": 0.5881655216217041, "learning_rate": 2.136896762631093e-05, "loss": 4.1938, "step": 17889 }, { "epoch": 0.5464263897373244, "grad_norm": 0.40432947874069214, "learning_rate": 2.1366594185461533e-05, "loss": 4.2627, "step": 17890 }, { "epoch": 0.5464569334147832, "grad_norm": 0.3983272910118103, "learning_rate": 2.1364220778066775e-05, "loss": 4.3024, "step": 17891 }, { "epoch": 0.5464874770922419, "grad_norm": 0.397175133228302, "learning_rate": 2.1361847404148504e-05, "loss": 4.202, "step": 17892 }, { "epoch": 0.5465180207697007, "grad_norm": 0.40298548340797424, "learning_rate": 2.1359474063728574e-05, "loss": 4.3634, "step": 17893 }, { "epoch": 0.5465485644471595, "grad_norm": 0.3915930986404419, "learning_rate": 2.1357100756828833e-05, "loss": 4.286, "step": 17894 }, { "epoch": 0.5465791081246182, "grad_norm": 0.39979860186576843, "learning_rate": 2.135472748347115e-05, "loss": 4.3231, "step": 17895 }, { "epoch": 0.546609651802077, "grad_norm": 0.40404728055000305, "learning_rate": 2.135235424367736e-05, "loss": 4.3384, "step": 17896 }, { "epoch": 0.5466401954795357, "grad_norm": 0.4016813337802887, "learning_rate": 2.134998103746932e-05, "loss": 4.2846, "step": 17897 }, { "epoch": 0.5466707391569945, "grad_norm": 0.40509799122810364, "learning_rate": 2.134760786486888e-05, "loss": 4.2152, "step": 17898 }, { "epoch": 0.5467012828344533, "grad_norm": 0.39649590849876404, "learning_rate": 2.134523472589789e-05, "loss": 4.2923, "step": 17899 }, { "epoch": 0.546731826511912, "grad_norm": 0.39813825488090515, "learning_rate": 2.134286162057821e-05, "loss": 4.2038, "step": 17900 }, { "epoch": 0.5467623701893708, "grad_norm": 0.4132900834083557, "learning_rate": 2.134048854893168e-05, "loss": 4.3003, "step": 17901 }, { "epoch": 0.5467929138668296, "grad_norm": 0.3920799791812897, "learning_rate": 2.1338115510980143e-05, "loss": 4.2707, "step": 17902 }, { "epoch": 0.5468234575442883, "grad_norm": 0.40430641174316406, "learning_rate": 2.1335742506745475e-05, "loss": 4.2589, "step": 17903 }, { "epoch": 0.5468540012217471, "grad_norm": 0.4009625017642975, "learning_rate": 2.1333369536249505e-05, "loss": 4.316, "step": 17904 }, { "epoch": 0.5468845448992059, "grad_norm": 0.4023456573486328, "learning_rate": 2.133099659951408e-05, "loss": 4.3435, "step": 17905 }, { "epoch": 0.5469150885766646, "grad_norm": 0.39836689829826355, "learning_rate": 2.1328623696561065e-05, "loss": 4.205, "step": 17906 }, { "epoch": 0.5469456322541234, "grad_norm": 0.3990590274333954, "learning_rate": 2.1326250827412292e-05, "loss": 4.2723, "step": 17907 }, { "epoch": 0.5469761759315822, "grad_norm": 0.4136354923248291, "learning_rate": 2.1323877992089618e-05, "loss": 4.4059, "step": 17908 }, { "epoch": 0.5470067196090409, "grad_norm": 0.4070485830307007, "learning_rate": 2.1321505190614898e-05, "loss": 4.2945, "step": 17909 }, { "epoch": 0.5470372632864997, "grad_norm": 0.4000381529331207, "learning_rate": 2.131913242300996e-05, "loss": 4.3805, "step": 17910 }, { "epoch": 0.5470678069639585, "grad_norm": 0.3999421298503876, "learning_rate": 2.1316759689296663e-05, "loss": 4.2059, "step": 17911 }, { "epoch": 0.5470983506414172, "grad_norm": 0.40537410974502563, "learning_rate": 2.131438698949686e-05, "loss": 4.2216, "step": 17912 }, { "epoch": 0.547128894318876, "grad_norm": 0.3876737058162689, "learning_rate": 2.1312014323632384e-05, "loss": 4.3265, "step": 17913 }, { "epoch": 0.5471594379963347, "grad_norm": 0.3979793190956116, "learning_rate": 2.1309641691725098e-05, "loss": 4.2993, "step": 17914 }, { "epoch": 0.5471899816737935, "grad_norm": 0.40294843912124634, "learning_rate": 2.1307269093796827e-05, "loss": 4.3276, "step": 17915 }, { "epoch": 0.5472205253512523, "grad_norm": 0.4091850221157074, "learning_rate": 2.1304896529869435e-05, "loss": 4.3081, "step": 17916 }, { "epoch": 0.547251069028711, "grad_norm": 0.417411744594574, "learning_rate": 2.1302523999964767e-05, "loss": 4.3569, "step": 17917 }, { "epoch": 0.5472816127061698, "grad_norm": 0.4210120439529419, "learning_rate": 2.1300151504104648e-05, "loss": 4.3459, "step": 17918 }, { "epoch": 0.5473121563836286, "grad_norm": 0.3944048583507538, "learning_rate": 2.129777904231094e-05, "loss": 4.2415, "step": 17919 }, { "epoch": 0.5473427000610873, "grad_norm": 0.40010443329811096, "learning_rate": 2.129540661460549e-05, "loss": 4.3421, "step": 17920 }, { "epoch": 0.5473732437385461, "grad_norm": 0.4000413417816162, "learning_rate": 2.1293034221010128e-05, "loss": 4.2697, "step": 17921 }, { "epoch": 0.5474037874160049, "grad_norm": 0.40136563777923584, "learning_rate": 2.1290661861546704e-05, "loss": 4.254, "step": 17922 }, { "epoch": 0.5474343310934636, "grad_norm": 0.4066993296146393, "learning_rate": 2.1288289536237074e-05, "loss": 4.3891, "step": 17923 }, { "epoch": 0.5474648747709224, "grad_norm": 0.4013901948928833, "learning_rate": 2.1285917245103067e-05, "loss": 4.3236, "step": 17924 }, { "epoch": 0.5474954184483812, "grad_norm": 0.3991108238697052, "learning_rate": 2.1283544988166523e-05, "loss": 4.2807, "step": 17925 }, { "epoch": 0.5475259621258399, "grad_norm": 0.40207603573799133, "learning_rate": 2.1281172765449304e-05, "loss": 4.2515, "step": 17926 }, { "epoch": 0.5475565058032987, "grad_norm": 0.4045592248439789, "learning_rate": 2.1278800576973226e-05, "loss": 4.2617, "step": 17927 }, { "epoch": 0.5475870494807575, "grad_norm": 0.40597763657569885, "learning_rate": 2.1276428422760146e-05, "loss": 4.2663, "step": 17928 }, { "epoch": 0.5476175931582162, "grad_norm": 0.39601194858551025, "learning_rate": 2.1274056302831914e-05, "loss": 4.3338, "step": 17929 }, { "epoch": 0.547648136835675, "grad_norm": 0.3991471230983734, "learning_rate": 2.127168421721035e-05, "loss": 4.3224, "step": 17930 }, { "epoch": 0.5476786805131337, "grad_norm": 0.39566731452941895, "learning_rate": 2.1269312165917318e-05, "loss": 4.2001, "step": 17931 }, { "epoch": 0.5477092241905925, "grad_norm": 0.4065060615539551, "learning_rate": 2.126694014897464e-05, "loss": 4.2669, "step": 17932 }, { "epoch": 0.5477397678680513, "grad_norm": 0.40230703353881836, "learning_rate": 2.126456816640416e-05, "loss": 4.3454, "step": 17933 }, { "epoch": 0.54777031154551, "grad_norm": 0.401239812374115, "learning_rate": 2.1262196218227732e-05, "loss": 4.3343, "step": 17934 }, { "epoch": 0.5478008552229688, "grad_norm": 0.40697550773620605, "learning_rate": 2.1259824304467174e-05, "loss": 4.3521, "step": 17935 }, { "epoch": 0.5478313989004276, "grad_norm": 0.4144934415817261, "learning_rate": 2.1257452425144335e-05, "loss": 4.3288, "step": 17936 }, { "epoch": 0.5478619425778863, "grad_norm": 0.4118089973926544, "learning_rate": 2.125508058028107e-05, "loss": 4.3759, "step": 17937 }, { "epoch": 0.5478924862553451, "grad_norm": 0.41100582480430603, "learning_rate": 2.1252708769899192e-05, "loss": 4.2135, "step": 17938 }, { "epoch": 0.547923029932804, "grad_norm": 0.42305707931518555, "learning_rate": 2.1250336994020554e-05, "loss": 4.1886, "step": 17939 }, { "epoch": 0.5479535736102626, "grad_norm": 0.3977496325969696, "learning_rate": 2.1247965252667e-05, "loss": 4.289, "step": 17940 }, { "epoch": 0.5479841172877215, "grad_norm": 0.41326212882995605, "learning_rate": 2.1245593545860347e-05, "loss": 4.3089, "step": 17941 }, { "epoch": 0.5480146609651803, "grad_norm": 0.4096650779247284, "learning_rate": 2.1243221873622444e-05, "loss": 4.2911, "step": 17942 }, { "epoch": 0.548045204642639, "grad_norm": 0.40689897537231445, "learning_rate": 2.1240850235975138e-05, "loss": 4.3534, "step": 17943 }, { "epoch": 0.5480757483200978, "grad_norm": 0.406673789024353, "learning_rate": 2.1238478632940247e-05, "loss": 4.3285, "step": 17944 }, { "epoch": 0.5481062919975566, "grad_norm": 0.39394181966781616, "learning_rate": 2.123610706453962e-05, "loss": 4.3201, "step": 17945 }, { "epoch": 0.5481368356750153, "grad_norm": 0.40042901039123535, "learning_rate": 2.1233735530795096e-05, "loss": 4.2859, "step": 17946 }, { "epoch": 0.5481673793524741, "grad_norm": 0.3975382447242737, "learning_rate": 2.1231364031728502e-05, "loss": 4.189, "step": 17947 }, { "epoch": 0.5481979230299328, "grad_norm": 0.4070843458175659, "learning_rate": 2.1228992567361676e-05, "loss": 4.2372, "step": 17948 }, { "epoch": 0.5482284667073916, "grad_norm": 0.41001269221305847, "learning_rate": 2.1226621137716456e-05, "loss": 4.2937, "step": 17949 }, { "epoch": 0.5482590103848504, "grad_norm": 0.3905497193336487, "learning_rate": 2.1224249742814674e-05, "loss": 4.2576, "step": 17950 }, { "epoch": 0.5482895540623091, "grad_norm": 0.4100095331668854, "learning_rate": 2.122187838267817e-05, "loss": 4.2028, "step": 17951 }, { "epoch": 0.5483200977397679, "grad_norm": 0.3963164985179901, "learning_rate": 2.1219507057328767e-05, "loss": 4.3444, "step": 17952 }, { "epoch": 0.5483506414172267, "grad_norm": 0.3955681324005127, "learning_rate": 2.1217135766788305e-05, "loss": 4.2784, "step": 17953 }, { "epoch": 0.5483811850946854, "grad_norm": 0.3961940407752991, "learning_rate": 2.1214764511078627e-05, "loss": 4.295, "step": 17954 }, { "epoch": 0.5484117287721442, "grad_norm": 0.39603403210639954, "learning_rate": 2.1212393290221556e-05, "loss": 4.2128, "step": 17955 }, { "epoch": 0.548442272449603, "grad_norm": 0.39743027091026306, "learning_rate": 2.1210022104238926e-05, "loss": 4.182, "step": 17956 }, { "epoch": 0.5484728161270617, "grad_norm": 0.39744964241981506, "learning_rate": 2.1207650953152576e-05, "loss": 4.3221, "step": 17957 }, { "epoch": 0.5485033598045205, "grad_norm": 0.39272022247314453, "learning_rate": 2.1205279836984322e-05, "loss": 4.3178, "step": 17958 }, { "epoch": 0.5485339034819793, "grad_norm": 0.40883082151412964, "learning_rate": 2.120290875575601e-05, "loss": 4.3248, "step": 17959 }, { "epoch": 0.548564447159438, "grad_norm": 0.4023451507091522, "learning_rate": 2.1200537709489483e-05, "loss": 4.4528, "step": 17960 }, { "epoch": 0.5485949908368968, "grad_norm": 0.402480810880661, "learning_rate": 2.1198166698206545e-05, "loss": 4.2802, "step": 17961 }, { "epoch": 0.5486255345143555, "grad_norm": 0.4063194990158081, "learning_rate": 2.119579572192905e-05, "loss": 4.2806, "step": 17962 }, { "epoch": 0.5486560781918143, "grad_norm": 0.40773871541023254, "learning_rate": 2.1193424780678817e-05, "loss": 4.1804, "step": 17963 }, { "epoch": 0.5486866218692731, "grad_norm": 0.40098121762275696, "learning_rate": 2.1191053874477675e-05, "loss": 4.3514, "step": 17964 }, { "epoch": 0.5487171655467318, "grad_norm": 0.4168302118778229, "learning_rate": 2.1188683003347463e-05, "loss": 4.2461, "step": 17965 }, { "epoch": 0.5487477092241906, "grad_norm": 0.40324825048446655, "learning_rate": 2.118631216731e-05, "loss": 4.2817, "step": 17966 }, { "epoch": 0.5487782529016494, "grad_norm": 0.3993174135684967, "learning_rate": 2.118394136638712e-05, "loss": 4.2652, "step": 17967 }, { "epoch": 0.5488087965791081, "grad_norm": 0.4055582880973816, "learning_rate": 2.118157060060067e-05, "loss": 4.2432, "step": 17968 }, { "epoch": 0.5488393402565669, "grad_norm": 0.4039788544178009, "learning_rate": 2.1179199869972445e-05, "loss": 4.2775, "step": 17969 }, { "epoch": 0.5488698839340257, "grad_norm": 0.400054007768631, "learning_rate": 2.11768291745243e-05, "loss": 4.245, "step": 17970 }, { "epoch": 0.5489004276114844, "grad_norm": 0.40531888604164124, "learning_rate": 2.1174458514278057e-05, "loss": 4.2705, "step": 17971 }, { "epoch": 0.5489309712889432, "grad_norm": 0.4026396870613098, "learning_rate": 2.117208788925554e-05, "loss": 4.3859, "step": 17972 }, { "epoch": 0.548961514966402, "grad_norm": 0.40246039628982544, "learning_rate": 2.1169717299478566e-05, "loss": 4.3095, "step": 17973 }, { "epoch": 0.5489920586438607, "grad_norm": 0.3976525366306305, "learning_rate": 2.116734674496899e-05, "loss": 4.2705, "step": 17974 }, { "epoch": 0.5490226023213195, "grad_norm": 0.39779189229011536, "learning_rate": 2.116497622574861e-05, "loss": 4.2552, "step": 17975 }, { "epoch": 0.5490531459987783, "grad_norm": 0.40809640288352966, "learning_rate": 2.1162605741839268e-05, "loss": 4.3173, "step": 17976 }, { "epoch": 0.549083689676237, "grad_norm": 0.4094543755054474, "learning_rate": 2.11602352932628e-05, "loss": 4.2837, "step": 17977 }, { "epoch": 0.5491142333536958, "grad_norm": 0.39289581775665283, "learning_rate": 2.1157864880041016e-05, "loss": 4.2989, "step": 17978 }, { "epoch": 0.5491447770311545, "grad_norm": 0.40407392382621765, "learning_rate": 2.115549450219574e-05, "loss": 4.348, "step": 17979 }, { "epoch": 0.5491753207086133, "grad_norm": 0.39987891912460327, "learning_rate": 2.1153124159748806e-05, "loss": 4.3153, "step": 17980 }, { "epoch": 0.5492058643860721, "grad_norm": 0.39252951741218567, "learning_rate": 2.1150753852722026e-05, "loss": 4.2969, "step": 17981 }, { "epoch": 0.5492364080635308, "grad_norm": 0.39957529306411743, "learning_rate": 2.1148383581137253e-05, "loss": 4.2592, "step": 17982 }, { "epoch": 0.5492669517409896, "grad_norm": 0.40189552307128906, "learning_rate": 2.1146013345016275e-05, "loss": 4.3004, "step": 17983 }, { "epoch": 0.5492974954184484, "grad_norm": 0.39638471603393555, "learning_rate": 2.1143643144380936e-05, "loss": 4.149, "step": 17984 }, { "epoch": 0.5493280390959071, "grad_norm": 0.3955856263637543, "learning_rate": 2.114127297925307e-05, "loss": 4.318, "step": 17985 }, { "epoch": 0.5493585827733659, "grad_norm": 0.40177446603775024, "learning_rate": 2.113890284965448e-05, "loss": 4.2345, "step": 17986 }, { "epoch": 0.5493891264508247, "grad_norm": 0.4086393415927887, "learning_rate": 2.113653275560699e-05, "loss": 4.2958, "step": 17987 }, { "epoch": 0.5494196701282834, "grad_norm": 0.4023808538913727, "learning_rate": 2.1134162697132443e-05, "loss": 4.296, "step": 17988 }, { "epoch": 0.5494502138057422, "grad_norm": 0.4018838405609131, "learning_rate": 2.1131792674252637e-05, "loss": 4.319, "step": 17989 }, { "epoch": 0.549480757483201, "grad_norm": 0.4015491008758545, "learning_rate": 2.1129422686989404e-05, "loss": 4.1647, "step": 17990 }, { "epoch": 0.5495113011606597, "grad_norm": 0.39893537759780884, "learning_rate": 2.1127052735364574e-05, "loss": 4.3379, "step": 17991 }, { "epoch": 0.5495418448381185, "grad_norm": 0.39620885252952576, "learning_rate": 2.1124682819399956e-05, "loss": 4.257, "step": 17992 }, { "epoch": 0.5495723885155773, "grad_norm": 0.40168535709381104, "learning_rate": 2.1122312939117374e-05, "loss": 4.2745, "step": 17993 }, { "epoch": 0.549602932193036, "grad_norm": 0.40370112657546997, "learning_rate": 2.1119943094538654e-05, "loss": 4.3303, "step": 17994 }, { "epoch": 0.5496334758704948, "grad_norm": 0.394690603017807, "learning_rate": 2.1117573285685614e-05, "loss": 4.2972, "step": 17995 }, { "epoch": 0.5496640195479535, "grad_norm": 0.40118828415870667, "learning_rate": 2.111520351258008e-05, "loss": 4.2478, "step": 17996 }, { "epoch": 0.5496945632254123, "grad_norm": 0.40368348360061646, "learning_rate": 2.1112833775243848e-05, "loss": 4.3217, "step": 17997 }, { "epoch": 0.5497251069028711, "grad_norm": 0.4067794680595398, "learning_rate": 2.1110464073698757e-05, "loss": 4.2722, "step": 17998 }, { "epoch": 0.5497556505803298, "grad_norm": 0.4097255766391754, "learning_rate": 2.1108094407966635e-05, "loss": 4.2773, "step": 17999 }, { "epoch": 0.5497861942577886, "grad_norm": 0.41674351692199707, "learning_rate": 2.110572477806928e-05, "loss": 4.3558, "step": 18000 }, { "epoch": 0.5498167379352474, "grad_norm": 0.40823301672935486, "learning_rate": 2.1103355184028518e-05, "loss": 4.2622, "step": 18001 }, { "epoch": 0.5498472816127061, "grad_norm": 0.40092888474464417, "learning_rate": 2.1100985625866172e-05, "loss": 4.2787, "step": 18002 }, { "epoch": 0.5498778252901649, "grad_norm": 0.39608246088027954, "learning_rate": 2.1098616103604058e-05, "loss": 4.258, "step": 18003 }, { "epoch": 0.5499083689676237, "grad_norm": 0.3994726240634918, "learning_rate": 2.109624661726398e-05, "loss": 4.2909, "step": 18004 }, { "epoch": 0.5499389126450824, "grad_norm": 0.40430521965026855, "learning_rate": 2.1093877166867783e-05, "loss": 4.3396, "step": 18005 }, { "epoch": 0.5499694563225412, "grad_norm": 0.4002358913421631, "learning_rate": 2.1091507752437255e-05, "loss": 4.3425, "step": 18006 }, { "epoch": 0.55, "grad_norm": 0.4011009633541107, "learning_rate": 2.1089138373994223e-05, "loss": 4.3334, "step": 18007 }, { "epoch": 0.5500305436774587, "grad_norm": 0.4137163758277893, "learning_rate": 2.108676903156052e-05, "loss": 4.2753, "step": 18008 }, { "epoch": 0.5500610873549175, "grad_norm": 0.3972877562046051, "learning_rate": 2.108439972515794e-05, "loss": 4.2289, "step": 18009 }, { "epoch": 0.5500916310323763, "grad_norm": 0.40101224184036255, "learning_rate": 2.1082030454808294e-05, "loss": 4.3153, "step": 18010 }, { "epoch": 0.550122174709835, "grad_norm": 0.3935271203517914, "learning_rate": 2.1079661220533424e-05, "loss": 4.3549, "step": 18011 }, { "epoch": 0.5501527183872938, "grad_norm": 0.39755868911743164, "learning_rate": 2.1077292022355118e-05, "loss": 4.2662, "step": 18012 }, { "epoch": 0.5501832620647525, "grad_norm": 0.40902432799339294, "learning_rate": 2.107492286029521e-05, "loss": 4.3208, "step": 18013 }, { "epoch": 0.5502138057422113, "grad_norm": 0.3973546326160431, "learning_rate": 2.1072553734375495e-05, "loss": 4.4057, "step": 18014 }, { "epoch": 0.5502443494196702, "grad_norm": 0.4010879695415497, "learning_rate": 2.1070184644617795e-05, "loss": 4.3277, "step": 18015 }, { "epoch": 0.5502748930971288, "grad_norm": 0.4148920774459839, "learning_rate": 2.1067815591043937e-05, "loss": 4.3267, "step": 18016 }, { "epoch": 0.5503054367745877, "grad_norm": 0.40238460898399353, "learning_rate": 2.1065446573675716e-05, "loss": 4.2823, "step": 18017 }, { "epoch": 0.5503359804520465, "grad_norm": 0.4006001353263855, "learning_rate": 2.106307759253495e-05, "loss": 4.2754, "step": 18018 }, { "epoch": 0.5503665241295052, "grad_norm": 0.40106186270713806, "learning_rate": 2.1060708647643467e-05, "loss": 4.2796, "step": 18019 }, { "epoch": 0.550397067806964, "grad_norm": 0.41707438230514526, "learning_rate": 2.1058339739023048e-05, "loss": 4.3382, "step": 18020 }, { "epoch": 0.5504276114844228, "grad_norm": 0.41047340631484985, "learning_rate": 2.105597086669552e-05, "loss": 4.2845, "step": 18021 }, { "epoch": 0.5504581551618815, "grad_norm": 0.4062484800815582, "learning_rate": 2.105360203068271e-05, "loss": 4.2401, "step": 18022 }, { "epoch": 0.5504886988393403, "grad_norm": 0.41204971075057983, "learning_rate": 2.1051233231006406e-05, "loss": 4.2702, "step": 18023 }, { "epoch": 0.5505192425167991, "grad_norm": 0.4038454592227936, "learning_rate": 2.1048864467688428e-05, "loss": 4.2892, "step": 18024 }, { "epoch": 0.5505497861942578, "grad_norm": 0.4154101610183716, "learning_rate": 2.104649574075059e-05, "loss": 4.2926, "step": 18025 }, { "epoch": 0.5505803298717166, "grad_norm": 0.39552804827690125, "learning_rate": 2.10441270502147e-05, "loss": 4.2878, "step": 18026 }, { "epoch": 0.5506108735491754, "grad_norm": 0.40690574049949646, "learning_rate": 2.1041758396102558e-05, "loss": 4.3163, "step": 18027 }, { "epoch": 0.5506414172266341, "grad_norm": 0.4100548326969147, "learning_rate": 2.103938977843599e-05, "loss": 4.3563, "step": 18028 }, { "epoch": 0.5506719609040929, "grad_norm": 0.4001668095588684, "learning_rate": 2.103702119723679e-05, "loss": 4.2117, "step": 18029 }, { "epoch": 0.5507025045815516, "grad_norm": 0.418489545583725, "learning_rate": 2.1034652652526785e-05, "loss": 4.3853, "step": 18030 }, { "epoch": 0.5507330482590104, "grad_norm": 0.4109768867492676, "learning_rate": 2.1032284144327758e-05, "loss": 4.3439, "step": 18031 }, { "epoch": 0.5507635919364692, "grad_norm": 0.39833298325538635, "learning_rate": 2.1029915672661533e-05, "loss": 4.2431, "step": 18032 }, { "epoch": 0.5507941356139279, "grad_norm": 0.39926499128341675, "learning_rate": 2.1027547237549926e-05, "loss": 4.3529, "step": 18033 }, { "epoch": 0.5508246792913867, "grad_norm": 0.41791805624961853, "learning_rate": 2.1025178839014726e-05, "loss": 4.2341, "step": 18034 }, { "epoch": 0.5508552229688455, "grad_norm": 0.4104960858821869, "learning_rate": 2.1022810477077744e-05, "loss": 4.2855, "step": 18035 }, { "epoch": 0.5508857666463042, "grad_norm": 0.4040725827217102, "learning_rate": 2.1020442151760804e-05, "loss": 4.3227, "step": 18036 }, { "epoch": 0.550916310323763, "grad_norm": 0.39748573303222656, "learning_rate": 2.1018073863085686e-05, "loss": 4.3469, "step": 18037 }, { "epoch": 0.5509468540012218, "grad_norm": 0.4111361503601074, "learning_rate": 2.101570561107421e-05, "loss": 4.2348, "step": 18038 }, { "epoch": 0.5509773976786805, "grad_norm": 0.3992607295513153, "learning_rate": 2.101333739574819e-05, "loss": 4.3076, "step": 18039 }, { "epoch": 0.5510079413561393, "grad_norm": 0.405992329120636, "learning_rate": 2.1010969217129416e-05, "loss": 4.2795, "step": 18040 }, { "epoch": 0.5510384850335981, "grad_norm": 0.4126213490962982, "learning_rate": 2.10086010752397e-05, "loss": 4.2122, "step": 18041 }, { "epoch": 0.5510690287110568, "grad_norm": 0.4091879725456238, "learning_rate": 2.1006232970100854e-05, "loss": 4.322, "step": 18042 }, { "epoch": 0.5510995723885156, "grad_norm": 0.4106013774871826, "learning_rate": 2.1003864901734666e-05, "loss": 4.263, "step": 18043 }, { "epoch": 0.5511301160659744, "grad_norm": 0.40630966424942017, "learning_rate": 2.100149687016294e-05, "loss": 4.3314, "step": 18044 }, { "epoch": 0.5511606597434331, "grad_norm": 0.40403392910957336, "learning_rate": 2.0999128875407508e-05, "loss": 4.2719, "step": 18045 }, { "epoch": 0.5511912034208919, "grad_norm": 0.4191429615020752, "learning_rate": 2.099676091749014e-05, "loss": 4.233, "step": 18046 }, { "epoch": 0.5512217470983506, "grad_norm": 0.4038875997066498, "learning_rate": 2.099439299643266e-05, "loss": 4.3606, "step": 18047 }, { "epoch": 0.5512522907758094, "grad_norm": 0.41554194688796997, "learning_rate": 2.0992025112256856e-05, "loss": 4.2243, "step": 18048 }, { "epoch": 0.5512828344532682, "grad_norm": 0.4014471769332886, "learning_rate": 2.0989657264984543e-05, "loss": 4.1587, "step": 18049 }, { "epoch": 0.5513133781307269, "grad_norm": 0.4148299992084503, "learning_rate": 2.0987289454637523e-05, "loss": 4.353, "step": 18050 }, { "epoch": 0.5513439218081857, "grad_norm": 0.40620264410972595, "learning_rate": 2.0984921681237578e-05, "loss": 4.3135, "step": 18051 }, { "epoch": 0.5513744654856445, "grad_norm": 0.4162881076335907, "learning_rate": 2.0982553944806526e-05, "loss": 4.4552, "step": 18052 }, { "epoch": 0.5514050091631032, "grad_norm": 0.40455833077430725, "learning_rate": 2.0980186245366174e-05, "loss": 4.314, "step": 18053 }, { "epoch": 0.551435552840562, "grad_norm": 0.41010603308677673, "learning_rate": 2.0977818582938307e-05, "loss": 4.3001, "step": 18054 }, { "epoch": 0.5514660965180208, "grad_norm": 0.40155452489852905, "learning_rate": 2.097545095754473e-05, "loss": 4.2984, "step": 18055 }, { "epoch": 0.5514966401954795, "grad_norm": 0.4102075695991516, "learning_rate": 2.0973083369207256e-05, "loss": 4.235, "step": 18056 }, { "epoch": 0.5515271838729383, "grad_norm": 0.4015978276729584, "learning_rate": 2.0970715817947665e-05, "loss": 4.311, "step": 18057 }, { "epoch": 0.5515577275503971, "grad_norm": 0.4046516716480255, "learning_rate": 2.0968348303787765e-05, "loss": 4.2989, "step": 18058 }, { "epoch": 0.5515882712278558, "grad_norm": 0.39917153120040894, "learning_rate": 2.0965980826749365e-05, "loss": 4.2065, "step": 18059 }, { "epoch": 0.5516188149053146, "grad_norm": 0.397367000579834, "learning_rate": 2.096361338685424e-05, "loss": 4.3435, "step": 18060 }, { "epoch": 0.5516493585827734, "grad_norm": 0.4031406342983246, "learning_rate": 2.0961245984124205e-05, "loss": 4.277, "step": 18061 }, { "epoch": 0.5516799022602321, "grad_norm": 0.42326250672340393, "learning_rate": 2.0958878618581067e-05, "loss": 4.2956, "step": 18062 }, { "epoch": 0.5517104459376909, "grad_norm": 0.3936004638671875, "learning_rate": 2.0956511290246595e-05, "loss": 4.2132, "step": 18063 }, { "epoch": 0.5517409896151496, "grad_norm": 0.39825937151908875, "learning_rate": 2.0954143999142617e-05, "loss": 4.3045, "step": 18064 }, { "epoch": 0.5517715332926084, "grad_norm": 0.3946278691291809, "learning_rate": 2.095177674529091e-05, "loss": 4.2415, "step": 18065 }, { "epoch": 0.5518020769700672, "grad_norm": 0.3977227509021759, "learning_rate": 2.0949409528713267e-05, "loss": 4.2354, "step": 18066 }, { "epoch": 0.5518326206475259, "grad_norm": 0.3997592031955719, "learning_rate": 2.094704234943151e-05, "loss": 4.2684, "step": 18067 }, { "epoch": 0.5518631643249847, "grad_norm": 0.40194210410118103, "learning_rate": 2.0944675207467403e-05, "loss": 4.2759, "step": 18068 }, { "epoch": 0.5518937080024435, "grad_norm": 0.3977118134498596, "learning_rate": 2.0942308102842756e-05, "loss": 4.2885, "step": 18069 }, { "epoch": 0.5519242516799022, "grad_norm": 0.40424904227256775, "learning_rate": 2.0939941035579376e-05, "loss": 4.2935, "step": 18070 }, { "epoch": 0.551954795357361, "grad_norm": 0.4096849858760834, "learning_rate": 2.0937574005699037e-05, "loss": 4.3426, "step": 18071 }, { "epoch": 0.5519853390348198, "grad_norm": 0.40535274147987366, "learning_rate": 2.0935207013223545e-05, "loss": 4.241, "step": 18072 }, { "epoch": 0.5520158827122785, "grad_norm": 0.4056932032108307, "learning_rate": 2.09328400581747e-05, "loss": 4.2761, "step": 18073 }, { "epoch": 0.5520464263897373, "grad_norm": 0.3915324807167053, "learning_rate": 2.0930473140574277e-05, "loss": 4.2259, "step": 18074 }, { "epoch": 0.5520769700671961, "grad_norm": 0.40097498893737793, "learning_rate": 2.092810626044408e-05, "loss": 4.3037, "step": 18075 }, { "epoch": 0.5521075137446548, "grad_norm": 0.4156084954738617, "learning_rate": 2.092573941780591e-05, "loss": 4.294, "step": 18076 }, { "epoch": 0.5521380574221136, "grad_norm": 0.40460991859436035, "learning_rate": 2.0923372612681547e-05, "loss": 4.3411, "step": 18077 }, { "epoch": 0.5521686010995724, "grad_norm": 0.39520788192749023, "learning_rate": 2.0921005845092783e-05, "loss": 4.2443, "step": 18078 }, { "epoch": 0.5521991447770311, "grad_norm": 0.40801170468330383, "learning_rate": 2.0918639115061426e-05, "loss": 4.3836, "step": 18079 }, { "epoch": 0.5522296884544899, "grad_norm": 0.39373064041137695, "learning_rate": 2.0916272422609256e-05, "loss": 4.3325, "step": 18080 }, { "epoch": 0.5522602321319486, "grad_norm": 0.4108075797557831, "learning_rate": 2.0913905767758067e-05, "loss": 4.2992, "step": 18081 }, { "epoch": 0.5522907758094074, "grad_norm": 0.40414753556251526, "learning_rate": 2.0911539150529645e-05, "loss": 4.2086, "step": 18082 }, { "epoch": 0.5523213194868662, "grad_norm": 0.3960482180118561, "learning_rate": 2.0909172570945777e-05, "loss": 4.2224, "step": 18083 }, { "epoch": 0.5523518631643249, "grad_norm": 0.40333113074302673, "learning_rate": 2.0906806029028274e-05, "loss": 4.3596, "step": 18084 }, { "epoch": 0.5523824068417837, "grad_norm": 0.4117567837238312, "learning_rate": 2.09044395247989e-05, "loss": 4.2951, "step": 18085 }, { "epoch": 0.5524129505192426, "grad_norm": 0.38804891705513, "learning_rate": 2.0902073058279455e-05, "loss": 4.3596, "step": 18086 }, { "epoch": 0.5524434941967012, "grad_norm": 0.3975244462490082, "learning_rate": 2.0899706629491744e-05, "loss": 4.2753, "step": 18087 }, { "epoch": 0.55247403787416, "grad_norm": 0.4070165753364563, "learning_rate": 2.0897340238457535e-05, "loss": 4.2712, "step": 18088 }, { "epoch": 0.5525045815516189, "grad_norm": 0.40863296389579773, "learning_rate": 2.089497388519862e-05, "loss": 4.2549, "step": 18089 }, { "epoch": 0.5525351252290776, "grad_norm": 0.38916921615600586, "learning_rate": 2.0892607569736806e-05, "loss": 4.2358, "step": 18090 }, { "epoch": 0.5525656689065364, "grad_norm": 0.40427365899086, "learning_rate": 2.0890241292093848e-05, "loss": 4.415, "step": 18091 }, { "epoch": 0.5525962125839952, "grad_norm": 0.403505802154541, "learning_rate": 2.0887875052291557e-05, "loss": 4.1855, "step": 18092 }, { "epoch": 0.5526267562614539, "grad_norm": 0.4025377631187439, "learning_rate": 2.088550885035172e-05, "loss": 4.3369, "step": 18093 }, { "epoch": 0.5526572999389127, "grad_norm": 0.4122251868247986, "learning_rate": 2.0883142686296108e-05, "loss": 4.3604, "step": 18094 }, { "epoch": 0.5526878436163715, "grad_norm": 0.4136887490749359, "learning_rate": 2.088077656014653e-05, "loss": 4.3174, "step": 18095 }, { "epoch": 0.5527183872938302, "grad_norm": 0.3981240391731262, "learning_rate": 2.087841047192476e-05, "loss": 4.2961, "step": 18096 }, { "epoch": 0.552748930971289, "grad_norm": 0.41332849860191345, "learning_rate": 2.0876044421652573e-05, "loss": 4.3073, "step": 18097 }, { "epoch": 0.5527794746487477, "grad_norm": 0.40013518929481506, "learning_rate": 2.087367840935178e-05, "loss": 4.2648, "step": 18098 }, { "epoch": 0.5528100183262065, "grad_norm": 0.4036632180213928, "learning_rate": 2.0871312435044135e-05, "loss": 4.3099, "step": 18099 }, { "epoch": 0.5528405620036653, "grad_norm": 0.4148487448692322, "learning_rate": 2.0868946498751443e-05, "loss": 4.2625, "step": 18100 }, { "epoch": 0.552871105681124, "grad_norm": 0.40283599495887756, "learning_rate": 2.0866580600495493e-05, "loss": 4.2474, "step": 18101 }, { "epoch": 0.5529016493585828, "grad_norm": 0.4000115394592285, "learning_rate": 2.0864214740298055e-05, "loss": 4.2933, "step": 18102 }, { "epoch": 0.5529321930360416, "grad_norm": 0.40034207701683044, "learning_rate": 2.0861848918180918e-05, "loss": 4.2729, "step": 18103 }, { "epoch": 0.5529627367135003, "grad_norm": 0.40058866143226624, "learning_rate": 2.0859483134165868e-05, "loss": 4.2981, "step": 18104 }, { "epoch": 0.5529932803909591, "grad_norm": 0.4041898846626282, "learning_rate": 2.0857117388274686e-05, "loss": 4.3126, "step": 18105 }, { "epoch": 0.5530238240684179, "grad_norm": 0.4092489182949066, "learning_rate": 2.0854751680529148e-05, "loss": 4.3444, "step": 18106 }, { "epoch": 0.5530543677458766, "grad_norm": 0.41292667388916016, "learning_rate": 2.0852386010951054e-05, "loss": 4.2086, "step": 18107 }, { "epoch": 0.5530849114233354, "grad_norm": 0.4059184789657593, "learning_rate": 2.0850020379562162e-05, "loss": 4.3206, "step": 18108 }, { "epoch": 0.5531154551007942, "grad_norm": 0.40966883301734924, "learning_rate": 2.0847654786384268e-05, "loss": 4.3386, "step": 18109 }, { "epoch": 0.5531459987782529, "grad_norm": 0.4170601963996887, "learning_rate": 2.084528923143916e-05, "loss": 4.2855, "step": 18110 }, { "epoch": 0.5531765424557117, "grad_norm": 0.3925948739051819, "learning_rate": 2.0842923714748606e-05, "loss": 4.2274, "step": 18111 }, { "epoch": 0.5532070861331705, "grad_norm": 0.40709394216537476, "learning_rate": 2.0840558236334386e-05, "loss": 4.1724, "step": 18112 }, { "epoch": 0.5532376298106292, "grad_norm": 0.3986020088195801, "learning_rate": 2.0838192796218297e-05, "loss": 4.2779, "step": 18113 }, { "epoch": 0.553268173488088, "grad_norm": 0.4188045859336853, "learning_rate": 2.0835827394422093e-05, "loss": 4.3449, "step": 18114 }, { "epoch": 0.5532987171655467, "grad_norm": 0.40249910950660706, "learning_rate": 2.0833462030967578e-05, "loss": 4.2188, "step": 18115 }, { "epoch": 0.5533292608430055, "grad_norm": 0.41169053316116333, "learning_rate": 2.0831096705876513e-05, "loss": 4.2162, "step": 18116 }, { "epoch": 0.5533598045204643, "grad_norm": 0.3977378308773041, "learning_rate": 2.082873141917068e-05, "loss": 4.3018, "step": 18117 }, { "epoch": 0.553390348197923, "grad_norm": 0.4069487750530243, "learning_rate": 2.0826366170871877e-05, "loss": 4.2272, "step": 18118 }, { "epoch": 0.5534208918753818, "grad_norm": 0.4115804135799408, "learning_rate": 2.0824000961001856e-05, "loss": 4.2964, "step": 18119 }, { "epoch": 0.5534514355528406, "grad_norm": 0.3954985737800598, "learning_rate": 2.0821635789582402e-05, "loss": 4.2455, "step": 18120 }, { "epoch": 0.5534819792302993, "grad_norm": 0.39687579870224, "learning_rate": 2.0819270656635306e-05, "loss": 4.192, "step": 18121 }, { "epoch": 0.5535125229077581, "grad_norm": 0.3983050584793091, "learning_rate": 2.0816905562182324e-05, "loss": 4.337, "step": 18122 }, { "epoch": 0.5535430665852169, "grad_norm": 0.40551215410232544, "learning_rate": 2.0814540506245245e-05, "loss": 4.305, "step": 18123 }, { "epoch": 0.5535736102626756, "grad_norm": 0.4048663079738617, "learning_rate": 2.081217548884585e-05, "loss": 4.2823, "step": 18124 }, { "epoch": 0.5536041539401344, "grad_norm": 0.4028575122356415, "learning_rate": 2.08098105100059e-05, "loss": 4.2601, "step": 18125 }, { "epoch": 0.5536346976175932, "grad_norm": 0.4099375307559967, "learning_rate": 2.0807445569747184e-05, "loss": 4.2726, "step": 18126 }, { "epoch": 0.5536652412950519, "grad_norm": 0.412504643201828, "learning_rate": 2.0805080668091474e-05, "loss": 4.174, "step": 18127 }, { "epoch": 0.5536957849725107, "grad_norm": 0.4002184569835663, "learning_rate": 2.0802715805060545e-05, "loss": 4.2534, "step": 18128 }, { "epoch": 0.5537263286499694, "grad_norm": 0.40457239747047424, "learning_rate": 2.080035098067617e-05, "loss": 4.2074, "step": 18129 }, { "epoch": 0.5537568723274282, "grad_norm": 0.410815954208374, "learning_rate": 2.0797986194960115e-05, "loss": 4.2063, "step": 18130 }, { "epoch": 0.553787416004887, "grad_norm": 0.41358909010887146, "learning_rate": 2.0795621447934162e-05, "loss": 4.3212, "step": 18131 }, { "epoch": 0.5538179596823457, "grad_norm": 0.40963980555534363, "learning_rate": 2.0793256739620092e-05, "loss": 4.2809, "step": 18132 }, { "epoch": 0.5538485033598045, "grad_norm": 0.4140871465206146, "learning_rate": 2.079089207003966e-05, "loss": 4.2683, "step": 18133 }, { "epoch": 0.5538790470372633, "grad_norm": 0.40569040179252625, "learning_rate": 2.0788527439214657e-05, "loss": 4.2813, "step": 18134 }, { "epoch": 0.553909590714722, "grad_norm": 0.4009630084037781, "learning_rate": 2.0786162847166843e-05, "loss": 4.3712, "step": 18135 }, { "epoch": 0.5539401343921808, "grad_norm": 0.40386489033699036, "learning_rate": 2.0783798293917997e-05, "loss": 4.3566, "step": 18136 }, { "epoch": 0.5539706780696396, "grad_norm": 0.3983607590198517, "learning_rate": 2.078143377948988e-05, "loss": 4.1719, "step": 18137 }, { "epoch": 0.5540012217470983, "grad_norm": 0.40130650997161865, "learning_rate": 2.0779069303904286e-05, "loss": 4.3149, "step": 18138 }, { "epoch": 0.5540317654245571, "grad_norm": 0.40021640062332153, "learning_rate": 2.0776704867182954e-05, "loss": 4.2423, "step": 18139 }, { "epoch": 0.5540623091020159, "grad_norm": 0.3973793685436249, "learning_rate": 2.077434046934768e-05, "loss": 4.2621, "step": 18140 }, { "epoch": 0.5540928527794746, "grad_norm": 0.40387511253356934, "learning_rate": 2.0771976110420233e-05, "loss": 4.2613, "step": 18141 }, { "epoch": 0.5541233964569334, "grad_norm": 0.4073854982852936, "learning_rate": 2.076961179042236e-05, "loss": 4.289, "step": 18142 }, { "epoch": 0.5541539401343922, "grad_norm": 0.3971288204193115, "learning_rate": 2.076724750937586e-05, "loss": 4.2362, "step": 18143 }, { "epoch": 0.5541844838118509, "grad_norm": 0.3890162706375122, "learning_rate": 2.076488326730249e-05, "loss": 4.3259, "step": 18144 }, { "epoch": 0.5542150274893097, "grad_norm": 0.40295520424842834, "learning_rate": 2.0762519064224005e-05, "loss": 4.3257, "step": 18145 }, { "epoch": 0.5542455711667684, "grad_norm": 0.41597771644592285, "learning_rate": 2.07601549001622e-05, "loss": 4.2324, "step": 18146 }, { "epoch": 0.5542761148442272, "grad_norm": 0.3955451548099518, "learning_rate": 2.0757790775138812e-05, "loss": 4.3169, "step": 18147 }, { "epoch": 0.554306658521686, "grad_norm": 0.4080725908279419, "learning_rate": 2.075542668917563e-05, "loss": 4.2572, "step": 18148 }, { "epoch": 0.5543372021991447, "grad_norm": 0.40305963158607483, "learning_rate": 2.0753062642294427e-05, "loss": 4.38, "step": 18149 }, { "epoch": 0.5543677458766035, "grad_norm": 0.40231096744537354, "learning_rate": 2.075069863451695e-05, "loss": 4.1128, "step": 18150 }, { "epoch": 0.5543982895540623, "grad_norm": 0.41525301337242126, "learning_rate": 2.074833466586498e-05, "loss": 4.4005, "step": 18151 }, { "epoch": 0.554428833231521, "grad_norm": 0.39954254031181335, "learning_rate": 2.0745970736360282e-05, "loss": 4.3744, "step": 18152 }, { "epoch": 0.5544593769089798, "grad_norm": 0.407136470079422, "learning_rate": 2.074360684602461e-05, "loss": 4.2263, "step": 18153 }, { "epoch": 0.5544899205864386, "grad_norm": 0.40658339858055115, "learning_rate": 2.0741242994879738e-05, "loss": 4.2679, "step": 18154 }, { "epoch": 0.5545204642638973, "grad_norm": 0.40640100836753845, "learning_rate": 2.0738879182947443e-05, "loss": 4.3125, "step": 18155 }, { "epoch": 0.5545510079413561, "grad_norm": 0.40242308378219604, "learning_rate": 2.0736515410249466e-05, "loss": 4.3685, "step": 18156 }, { "epoch": 0.554581551618815, "grad_norm": 0.40345779061317444, "learning_rate": 2.073415167680759e-05, "loss": 4.2861, "step": 18157 }, { "epoch": 0.5546120952962736, "grad_norm": 0.40353620052337646, "learning_rate": 2.073178798264357e-05, "loss": 4.2804, "step": 18158 }, { "epoch": 0.5546426389737324, "grad_norm": 0.40076062083244324, "learning_rate": 2.072942432777918e-05, "loss": 4.2933, "step": 18159 }, { "epoch": 0.5546731826511913, "grad_norm": 0.40635883808135986, "learning_rate": 2.0727060712236162e-05, "loss": 4.2923, "step": 18160 }, { "epoch": 0.55470372632865, "grad_norm": 0.40154996514320374, "learning_rate": 2.0724697136036307e-05, "loss": 4.3117, "step": 18161 }, { "epoch": 0.5547342700061088, "grad_norm": 0.41545650362968445, "learning_rate": 2.0722333599201356e-05, "loss": 4.358, "step": 18162 }, { "epoch": 0.5547648136835674, "grad_norm": 0.40217912197113037, "learning_rate": 2.0719970101753085e-05, "loss": 4.1866, "step": 18163 }, { "epoch": 0.5547953573610263, "grad_norm": 0.3998216986656189, "learning_rate": 2.071760664371324e-05, "loss": 4.2754, "step": 18164 }, { "epoch": 0.5548259010384851, "grad_norm": 0.40947824716567993, "learning_rate": 2.0715243225103592e-05, "loss": 4.3373, "step": 18165 }, { "epoch": 0.5548564447159438, "grad_norm": 0.40585634112358093, "learning_rate": 2.0712879845945915e-05, "loss": 4.356, "step": 18166 }, { "epoch": 0.5548869883934026, "grad_norm": 0.3971901535987854, "learning_rate": 2.0710516506261955e-05, "loss": 4.1036, "step": 18167 }, { "epoch": 0.5549175320708614, "grad_norm": 0.405470609664917, "learning_rate": 2.0708153206073467e-05, "loss": 4.3423, "step": 18168 }, { "epoch": 0.5549480757483201, "grad_norm": 0.4142991602420807, "learning_rate": 2.0705789945402225e-05, "loss": 4.397, "step": 18169 }, { "epoch": 0.5549786194257789, "grad_norm": 0.40024158358573914, "learning_rate": 2.070342672426998e-05, "loss": 4.2951, "step": 18170 }, { "epoch": 0.5550091631032377, "grad_norm": 0.3992362916469574, "learning_rate": 2.0701063542698488e-05, "loss": 4.2611, "step": 18171 }, { "epoch": 0.5550397067806964, "grad_norm": 0.4015386700630188, "learning_rate": 2.0698700400709528e-05, "loss": 4.2117, "step": 18172 }, { "epoch": 0.5550702504581552, "grad_norm": 0.4054650664329529, "learning_rate": 2.0696337298324833e-05, "loss": 4.2838, "step": 18173 }, { "epoch": 0.555100794135614, "grad_norm": 0.392117977142334, "learning_rate": 2.069397423556618e-05, "loss": 4.3117, "step": 18174 }, { "epoch": 0.5551313378130727, "grad_norm": 0.42371609807014465, "learning_rate": 2.0691611212455325e-05, "loss": 4.3195, "step": 18175 }, { "epoch": 0.5551618814905315, "grad_norm": 0.397475004196167, "learning_rate": 2.068924822901401e-05, "loss": 4.2469, "step": 18176 }, { "epoch": 0.5551924251679903, "grad_norm": 0.405475378036499, "learning_rate": 2.0686885285264002e-05, "loss": 4.346, "step": 18177 }, { "epoch": 0.555222968845449, "grad_norm": 0.3942578136920929, "learning_rate": 2.068452238122707e-05, "loss": 4.2363, "step": 18178 }, { "epoch": 0.5552535125229078, "grad_norm": 0.41901692748069763, "learning_rate": 2.0682159516924947e-05, "loss": 4.3371, "step": 18179 }, { "epoch": 0.5552840562003665, "grad_norm": 0.3954559564590454, "learning_rate": 2.0679796692379416e-05, "loss": 4.3122, "step": 18180 }, { "epoch": 0.5553145998778253, "grad_norm": 0.41931620240211487, "learning_rate": 2.0677433907612205e-05, "loss": 4.2521, "step": 18181 }, { "epoch": 0.5553451435552841, "grad_norm": 0.41053828597068787, "learning_rate": 2.0675071162645087e-05, "loss": 4.2673, "step": 18182 }, { "epoch": 0.5553756872327428, "grad_norm": 0.4161873757839203, "learning_rate": 2.0672708457499816e-05, "loss": 4.3124, "step": 18183 }, { "epoch": 0.5554062309102016, "grad_norm": 0.42150071263313293, "learning_rate": 2.0670345792198136e-05, "loss": 4.3695, "step": 18184 }, { "epoch": 0.5554367745876604, "grad_norm": 0.4169604182243347, "learning_rate": 2.066798316676181e-05, "loss": 4.2268, "step": 18185 }, { "epoch": 0.5554673182651191, "grad_norm": 0.3961184620857239, "learning_rate": 2.0665620581212598e-05, "loss": 4.277, "step": 18186 }, { "epoch": 0.5554978619425779, "grad_norm": 0.4008199870586395, "learning_rate": 2.0663258035572237e-05, "loss": 4.3291, "step": 18187 }, { "epoch": 0.5555284056200367, "grad_norm": 0.40697431564331055, "learning_rate": 2.0660895529862487e-05, "loss": 4.2994, "step": 18188 }, { "epoch": 0.5555589492974954, "grad_norm": 0.40662091970443726, "learning_rate": 2.0658533064105113e-05, "loss": 4.2788, "step": 18189 }, { "epoch": 0.5555894929749542, "grad_norm": 0.406699001789093, "learning_rate": 2.0656170638321852e-05, "loss": 4.3529, "step": 18190 }, { "epoch": 0.555620036652413, "grad_norm": 0.4035905599594116, "learning_rate": 2.0653808252534458e-05, "loss": 4.1961, "step": 18191 }, { "epoch": 0.5556505803298717, "grad_norm": 0.4107079803943634, "learning_rate": 2.0651445906764698e-05, "loss": 4.3212, "step": 18192 }, { "epoch": 0.5556811240073305, "grad_norm": 0.4035865366458893, "learning_rate": 2.0649083601034297e-05, "loss": 4.2831, "step": 18193 }, { "epoch": 0.5557116676847893, "grad_norm": 0.4080837368965149, "learning_rate": 2.064672133536502e-05, "loss": 4.3428, "step": 18194 }, { "epoch": 0.555742211362248, "grad_norm": 0.4163829982280731, "learning_rate": 2.064435910977863e-05, "loss": 4.1689, "step": 18195 }, { "epoch": 0.5557727550397068, "grad_norm": 0.41220077872276306, "learning_rate": 2.0641996924296856e-05, "loss": 4.2359, "step": 18196 }, { "epoch": 0.5558032987171655, "grad_norm": 0.39819419384002686, "learning_rate": 2.0639634778941467e-05, "loss": 4.2431, "step": 18197 }, { "epoch": 0.5558338423946243, "grad_norm": 0.3983999192714691, "learning_rate": 2.0637272673734194e-05, "loss": 4.2716, "step": 18198 }, { "epoch": 0.5558643860720831, "grad_norm": 0.3960113525390625, "learning_rate": 2.063491060869679e-05, "loss": 4.1955, "step": 18199 }, { "epoch": 0.5558949297495418, "grad_norm": 0.40384620428085327, "learning_rate": 2.0632548583851026e-05, "loss": 4.2404, "step": 18200 }, { "epoch": 0.5559254734270006, "grad_norm": 0.4077132046222687, "learning_rate": 2.0630186599218615e-05, "loss": 4.223, "step": 18201 }, { "epoch": 0.5559560171044594, "grad_norm": 0.40617403388023376, "learning_rate": 2.0627824654821322e-05, "loss": 4.2472, "step": 18202 }, { "epoch": 0.5559865607819181, "grad_norm": 0.4130571782588959, "learning_rate": 2.062546275068091e-05, "loss": 4.1517, "step": 18203 }, { "epoch": 0.5560171044593769, "grad_norm": 0.41699856519699097, "learning_rate": 2.06231008868191e-05, "loss": 4.3211, "step": 18204 }, { "epoch": 0.5560476481368357, "grad_norm": 0.40940114855766296, "learning_rate": 2.0620739063257654e-05, "loss": 4.2023, "step": 18205 }, { "epoch": 0.5560781918142944, "grad_norm": 0.40205755829811096, "learning_rate": 2.061837728001832e-05, "loss": 4.2829, "step": 18206 }, { "epoch": 0.5561087354917532, "grad_norm": 0.4343961477279663, "learning_rate": 2.061601553712283e-05, "loss": 4.2234, "step": 18207 }, { "epoch": 0.556139279169212, "grad_norm": 0.41080090403556824, "learning_rate": 2.061365383459294e-05, "loss": 4.2253, "step": 18208 }, { "epoch": 0.5561698228466707, "grad_norm": 0.4152996838092804, "learning_rate": 2.0611292172450404e-05, "loss": 4.1833, "step": 18209 }, { "epoch": 0.5562003665241295, "grad_norm": 0.4020151197910309, "learning_rate": 2.0608930550716947e-05, "loss": 4.2144, "step": 18210 }, { "epoch": 0.5562309102015883, "grad_norm": 0.4066010117530823, "learning_rate": 2.0606568969414323e-05, "loss": 4.306, "step": 18211 }, { "epoch": 0.556261453879047, "grad_norm": 0.3915579915046692, "learning_rate": 2.0604207428564293e-05, "loss": 4.2875, "step": 18212 }, { "epoch": 0.5562919975565058, "grad_norm": 0.3935665488243103, "learning_rate": 2.0601845928188573e-05, "loss": 4.295, "step": 18213 }, { "epoch": 0.5563225412339645, "grad_norm": 0.4069826602935791, "learning_rate": 2.0599484468308922e-05, "loss": 4.3116, "step": 18214 }, { "epoch": 0.5563530849114233, "grad_norm": 0.401039183139801, "learning_rate": 2.0597123048947082e-05, "loss": 4.3389, "step": 18215 }, { "epoch": 0.5563836285888821, "grad_norm": 0.41841378808021545, "learning_rate": 2.0594761670124785e-05, "loss": 4.3052, "step": 18216 }, { "epoch": 0.5564141722663408, "grad_norm": 0.39797887206077576, "learning_rate": 2.0592400331863795e-05, "loss": 4.2232, "step": 18217 }, { "epoch": 0.5564447159437996, "grad_norm": 0.40776246786117554, "learning_rate": 2.059003903418583e-05, "loss": 4.3318, "step": 18218 }, { "epoch": 0.5564752596212584, "grad_norm": 0.412219762802124, "learning_rate": 2.0587677777112644e-05, "loss": 4.314, "step": 18219 }, { "epoch": 0.5565058032987171, "grad_norm": 0.4088142216205597, "learning_rate": 2.0585316560665986e-05, "loss": 4.3674, "step": 18220 }, { "epoch": 0.5565363469761759, "grad_norm": 0.39762628078460693, "learning_rate": 2.0582955384867583e-05, "loss": 4.3542, "step": 18221 }, { "epoch": 0.5565668906536347, "grad_norm": 0.39631885290145874, "learning_rate": 2.0580594249739178e-05, "loss": 4.29, "step": 18222 }, { "epoch": 0.5565974343310934, "grad_norm": 0.41723155975341797, "learning_rate": 2.057823315530252e-05, "loss": 4.1505, "step": 18223 }, { "epoch": 0.5566279780085522, "grad_norm": 0.4022293984889984, "learning_rate": 2.0575872101579336e-05, "loss": 4.221, "step": 18224 }, { "epoch": 0.556658521686011, "grad_norm": 0.4088364541530609, "learning_rate": 2.057351108859137e-05, "loss": 4.3298, "step": 18225 }, { "epoch": 0.5566890653634697, "grad_norm": 0.40974119305610657, "learning_rate": 2.0571150116360376e-05, "loss": 4.3331, "step": 18226 }, { "epoch": 0.5567196090409285, "grad_norm": 0.41769513487815857, "learning_rate": 2.056878918490807e-05, "loss": 4.2864, "step": 18227 }, { "epoch": 0.5567501527183873, "grad_norm": 0.3975972533226013, "learning_rate": 2.05664282942562e-05, "loss": 4.3205, "step": 18228 }, { "epoch": 0.556780696395846, "grad_norm": 0.40371862053871155, "learning_rate": 2.0564067444426517e-05, "loss": 4.3351, "step": 18229 }, { "epoch": 0.5568112400733048, "grad_norm": 0.4011894762516022, "learning_rate": 2.0561706635440732e-05, "loss": 4.3183, "step": 18230 }, { "epoch": 0.5568417837507635, "grad_norm": 0.40924450755119324, "learning_rate": 2.0559345867320607e-05, "loss": 4.2828, "step": 18231 }, { "epoch": 0.5568723274282223, "grad_norm": 0.4067070186138153, "learning_rate": 2.0556985140087857e-05, "loss": 4.2709, "step": 18232 }, { "epoch": 0.5569028711056812, "grad_norm": 0.4038390815258026, "learning_rate": 2.0554624453764227e-05, "loss": 4.2929, "step": 18233 }, { "epoch": 0.5569334147831398, "grad_norm": 0.40252959728240967, "learning_rate": 2.055226380837147e-05, "loss": 4.2524, "step": 18234 }, { "epoch": 0.5569639584605987, "grad_norm": 0.4077681601047516, "learning_rate": 2.0549903203931293e-05, "loss": 4.3728, "step": 18235 }, { "epoch": 0.5569945021380575, "grad_norm": 0.3976309895515442, "learning_rate": 2.054754264046545e-05, "loss": 4.3321, "step": 18236 }, { "epoch": 0.5570250458155162, "grad_norm": 0.41133469343185425, "learning_rate": 2.054518211799567e-05, "loss": 4.2005, "step": 18237 }, { "epoch": 0.557055589492975, "grad_norm": 0.4005463719367981, "learning_rate": 2.0542821636543695e-05, "loss": 4.221, "step": 18238 }, { "epoch": 0.5570861331704338, "grad_norm": 0.4088764786720276, "learning_rate": 2.0540461196131242e-05, "loss": 4.3331, "step": 18239 }, { "epoch": 0.5571166768478925, "grad_norm": 0.3937077820301056, "learning_rate": 2.0538100796780067e-05, "loss": 4.2989, "step": 18240 }, { "epoch": 0.5571472205253513, "grad_norm": 0.40333089232444763, "learning_rate": 2.0535740438511884e-05, "loss": 4.2736, "step": 18241 }, { "epoch": 0.5571777642028101, "grad_norm": 0.4095554053783417, "learning_rate": 2.053338012134843e-05, "loss": 4.3176, "step": 18242 }, { "epoch": 0.5572083078802688, "grad_norm": 0.4100833535194397, "learning_rate": 2.0531019845311457e-05, "loss": 4.3216, "step": 18243 }, { "epoch": 0.5572388515577276, "grad_norm": 0.40543368458747864, "learning_rate": 2.0528659610422672e-05, "loss": 4.3246, "step": 18244 }, { "epoch": 0.5572693952351864, "grad_norm": 0.40240827202796936, "learning_rate": 2.0526299416703816e-05, "loss": 4.1699, "step": 18245 }, { "epoch": 0.5572999389126451, "grad_norm": 0.4133923053741455, "learning_rate": 2.0523939264176632e-05, "loss": 4.3231, "step": 18246 }, { "epoch": 0.5573304825901039, "grad_norm": 0.41199952363967896, "learning_rate": 2.0521579152862826e-05, "loss": 4.2212, "step": 18247 }, { "epoch": 0.5573610262675626, "grad_norm": 0.4101250171661377, "learning_rate": 2.0519219082784156e-05, "loss": 4.4236, "step": 18248 }, { "epoch": 0.5573915699450214, "grad_norm": 0.41693490743637085, "learning_rate": 2.051685905396233e-05, "loss": 4.2611, "step": 18249 }, { "epoch": 0.5574221136224802, "grad_norm": 0.412370502948761, "learning_rate": 2.0514499066419084e-05, "loss": 4.238, "step": 18250 }, { "epoch": 0.5574526572999389, "grad_norm": 0.41109538078308105, "learning_rate": 2.0512139120176167e-05, "loss": 4.243, "step": 18251 }, { "epoch": 0.5574832009773977, "grad_norm": 0.40590253472328186, "learning_rate": 2.0509779215255277e-05, "loss": 4.321, "step": 18252 }, { "epoch": 0.5575137446548565, "grad_norm": 0.4167027473449707, "learning_rate": 2.050741935167817e-05, "loss": 4.305, "step": 18253 }, { "epoch": 0.5575442883323152, "grad_norm": 0.39674773812294006, "learning_rate": 2.0505059529466562e-05, "loss": 4.3546, "step": 18254 }, { "epoch": 0.557574832009774, "grad_norm": 0.39772462844848633, "learning_rate": 2.0502699748642173e-05, "loss": 4.222, "step": 18255 }, { "epoch": 0.5576053756872328, "grad_norm": 0.39553529024124146, "learning_rate": 2.0500340009226744e-05, "loss": 4.1883, "step": 18256 }, { "epoch": 0.5576359193646915, "grad_norm": 0.3916482627391815, "learning_rate": 2.0497980311242004e-05, "loss": 4.3129, "step": 18257 }, { "epoch": 0.5576664630421503, "grad_norm": 0.4106144905090332, "learning_rate": 2.0495620654709663e-05, "loss": 4.2321, "step": 18258 }, { "epoch": 0.5576970067196091, "grad_norm": 0.40922340750694275, "learning_rate": 2.0493261039651468e-05, "loss": 4.3094, "step": 18259 }, { "epoch": 0.5577275503970678, "grad_norm": 0.4199635982513428, "learning_rate": 2.0490901466089132e-05, "loss": 4.2866, "step": 18260 }, { "epoch": 0.5577580940745266, "grad_norm": 0.3987356126308441, "learning_rate": 2.0488541934044387e-05, "loss": 4.3432, "step": 18261 }, { "epoch": 0.5577886377519854, "grad_norm": 0.40135523676872253, "learning_rate": 2.0486182443538948e-05, "loss": 4.3044, "step": 18262 }, { "epoch": 0.5578191814294441, "grad_norm": 0.4232235550880432, "learning_rate": 2.048382299459456e-05, "loss": 4.2325, "step": 18263 }, { "epoch": 0.5578497251069029, "grad_norm": 0.42456501722335815, "learning_rate": 2.0481463587232925e-05, "loss": 4.2368, "step": 18264 }, { "epoch": 0.5578802687843616, "grad_norm": 0.4148890972137451, "learning_rate": 2.0479104221475788e-05, "loss": 4.3745, "step": 18265 }, { "epoch": 0.5579108124618204, "grad_norm": 0.40409940481185913, "learning_rate": 2.0476744897344855e-05, "loss": 4.2357, "step": 18266 }, { "epoch": 0.5579413561392792, "grad_norm": 0.404208242893219, "learning_rate": 2.047438561486186e-05, "loss": 4.2899, "step": 18267 }, { "epoch": 0.5579718998167379, "grad_norm": 0.4024861752986908, "learning_rate": 2.0472026374048524e-05, "loss": 4.351, "step": 18268 }, { "epoch": 0.5580024434941967, "grad_norm": 0.4001862108707428, "learning_rate": 2.046966717492657e-05, "loss": 4.2388, "step": 18269 }, { "epoch": 0.5580329871716555, "grad_norm": 0.4069063663482666, "learning_rate": 2.046730801751771e-05, "loss": 4.334, "step": 18270 }, { "epoch": 0.5580635308491142, "grad_norm": 0.4092971086502075, "learning_rate": 2.0464948901843693e-05, "loss": 4.3969, "step": 18271 }, { "epoch": 0.558094074526573, "grad_norm": 0.4138419032096863, "learning_rate": 2.046258982792621e-05, "loss": 4.2609, "step": 18272 }, { "epoch": 0.5581246182040318, "grad_norm": 3.009706497192383, "learning_rate": 2.0460230795786993e-05, "loss": 4.2602, "step": 18273 }, { "epoch": 0.5581551618814905, "grad_norm": 0.40752044320106506, "learning_rate": 2.0457871805447777e-05, "loss": 4.25, "step": 18274 }, { "epoch": 0.5581857055589493, "grad_norm": 0.40364518761634827, "learning_rate": 2.0455512856930263e-05, "loss": 4.2055, "step": 18275 }, { "epoch": 0.5582162492364081, "grad_norm": 0.4027591943740845, "learning_rate": 2.0453153950256178e-05, "loss": 4.248, "step": 18276 }, { "epoch": 0.5582467929138668, "grad_norm": 0.39740920066833496, "learning_rate": 2.045079508544725e-05, "loss": 4.2706, "step": 18277 }, { "epoch": 0.5582773365913256, "grad_norm": 0.4020118713378906, "learning_rate": 2.0448436262525184e-05, "loss": 4.194, "step": 18278 }, { "epoch": 0.5583078802687843, "grad_norm": 0.40271487832069397, "learning_rate": 2.0446077481511713e-05, "loss": 4.348, "step": 18279 }, { "epoch": 0.5583384239462431, "grad_norm": 0.40948015451431274, "learning_rate": 2.0443718742428537e-05, "loss": 4.1659, "step": 18280 }, { "epoch": 0.5583689676237019, "grad_norm": 0.4087790250778198, "learning_rate": 2.0441360045297385e-05, "loss": 4.1995, "step": 18281 }, { "epoch": 0.5583995113011606, "grad_norm": 0.4102829694747925, "learning_rate": 2.043900139013999e-05, "loss": 4.3104, "step": 18282 }, { "epoch": 0.5584300549786194, "grad_norm": 0.4100954234600067, "learning_rate": 2.043664277697804e-05, "loss": 4.2262, "step": 18283 }, { "epoch": 0.5584605986560782, "grad_norm": 0.4142984449863434, "learning_rate": 2.0434284205833266e-05, "loss": 4.2928, "step": 18284 }, { "epoch": 0.5584911423335369, "grad_norm": 0.39928755164146423, "learning_rate": 2.0431925676727397e-05, "loss": 4.2973, "step": 18285 }, { "epoch": 0.5585216860109957, "grad_norm": 0.40903130173683167, "learning_rate": 2.0429567189682124e-05, "loss": 4.2618, "step": 18286 }, { "epoch": 0.5585522296884545, "grad_norm": 0.4196850061416626, "learning_rate": 2.042720874471918e-05, "loss": 4.2201, "step": 18287 }, { "epoch": 0.5585827733659132, "grad_norm": 0.4135900139808655, "learning_rate": 2.0424850341860283e-05, "loss": 4.2467, "step": 18288 }, { "epoch": 0.558613317043372, "grad_norm": 0.40374651551246643, "learning_rate": 2.0422491981127128e-05, "loss": 4.2482, "step": 18289 }, { "epoch": 0.5586438607208308, "grad_norm": 0.39958685636520386, "learning_rate": 2.042013366254145e-05, "loss": 4.3268, "step": 18290 }, { "epoch": 0.5586744043982895, "grad_norm": 0.40853020548820496, "learning_rate": 2.041777538612496e-05, "loss": 4.3471, "step": 18291 }, { "epoch": 0.5587049480757483, "grad_norm": 0.4116208255290985, "learning_rate": 2.0415417151899365e-05, "loss": 4.1627, "step": 18292 }, { "epoch": 0.5587354917532071, "grad_norm": 0.4056163430213928, "learning_rate": 2.0413058959886377e-05, "loss": 4.3392, "step": 18293 }, { "epoch": 0.5587660354306658, "grad_norm": 0.40398508310317993, "learning_rate": 2.0410700810107726e-05, "loss": 4.2394, "step": 18294 }, { "epoch": 0.5587965791081246, "grad_norm": 0.39688053727149963, "learning_rate": 2.0408342702585096e-05, "loss": 4.3437, "step": 18295 }, { "epoch": 0.5588271227855833, "grad_norm": 0.409731924533844, "learning_rate": 2.040598463734023e-05, "loss": 4.2934, "step": 18296 }, { "epoch": 0.5588576664630421, "grad_norm": 0.4033215641975403, "learning_rate": 2.0403626614394813e-05, "loss": 4.3754, "step": 18297 }, { "epoch": 0.5588882101405009, "grad_norm": 0.4122712314128876, "learning_rate": 2.040126863377057e-05, "loss": 4.2734, "step": 18298 }, { "epoch": 0.5589187538179596, "grad_norm": 0.43150198459625244, "learning_rate": 2.0398910695489225e-05, "loss": 4.3412, "step": 18299 }, { "epoch": 0.5589492974954184, "grad_norm": 0.40393978357315063, "learning_rate": 2.0396552799572464e-05, "loss": 4.2579, "step": 18300 }, { "epoch": 0.5589798411728772, "grad_norm": 0.4067365527153015, "learning_rate": 2.0394194946042007e-05, "loss": 4.2617, "step": 18301 }, { "epoch": 0.5590103848503359, "grad_norm": 0.39862117171287537, "learning_rate": 2.0391837134919573e-05, "loss": 4.3374, "step": 18302 }, { "epoch": 0.5590409285277947, "grad_norm": 0.39744582772254944, "learning_rate": 2.0389479366226856e-05, "loss": 4.2577, "step": 18303 }, { "epoch": 0.5590714722052536, "grad_norm": 0.4059101939201355, "learning_rate": 2.038712163998557e-05, "loss": 4.3111, "step": 18304 }, { "epoch": 0.5591020158827122, "grad_norm": 0.4049159586429596, "learning_rate": 2.0384763956217436e-05, "loss": 4.3421, "step": 18305 }, { "epoch": 0.559132559560171, "grad_norm": 0.41025233268737793, "learning_rate": 2.0382406314944146e-05, "loss": 4.2452, "step": 18306 }, { "epoch": 0.5591631032376299, "grad_norm": 0.4066869020462036, "learning_rate": 2.038004871618742e-05, "loss": 4.3108, "step": 18307 }, { "epoch": 0.5591936469150885, "grad_norm": 0.39845022559165955, "learning_rate": 2.0377691159968964e-05, "loss": 4.2819, "step": 18308 }, { "epoch": 0.5592241905925474, "grad_norm": 0.41168200969696045, "learning_rate": 2.0375333646310474e-05, "loss": 4.1734, "step": 18309 }, { "epoch": 0.5592547342700062, "grad_norm": 0.4100383520126343, "learning_rate": 2.0372976175233665e-05, "loss": 4.3521, "step": 18310 }, { "epoch": 0.5592852779474649, "grad_norm": 0.39917847514152527, "learning_rate": 2.0370618746760252e-05, "loss": 4.3386, "step": 18311 }, { "epoch": 0.5593158216249237, "grad_norm": 0.4012482464313507, "learning_rate": 2.0368261360911926e-05, "loss": 4.3368, "step": 18312 }, { "epoch": 0.5593463653023824, "grad_norm": 0.4017755389213562, "learning_rate": 2.0365904017710404e-05, "loss": 4.2455, "step": 18313 }, { "epoch": 0.5593769089798412, "grad_norm": 0.40603047609329224, "learning_rate": 2.0363546717177377e-05, "loss": 4.2601, "step": 18314 }, { "epoch": 0.5594074526573, "grad_norm": 0.39880889654159546, "learning_rate": 2.0361189459334567e-05, "loss": 4.206, "step": 18315 }, { "epoch": 0.5594379963347587, "grad_norm": 0.40280580520629883, "learning_rate": 2.0358832244203678e-05, "loss": 4.2545, "step": 18316 }, { "epoch": 0.5594685400122175, "grad_norm": 0.398990660905838, "learning_rate": 2.035647507180639e-05, "loss": 4.2715, "step": 18317 }, { "epoch": 0.5594990836896763, "grad_norm": 0.39626145362854004, "learning_rate": 2.0354117942164426e-05, "loss": 4.3157, "step": 18318 }, { "epoch": 0.559529627367135, "grad_norm": 0.39384523034095764, "learning_rate": 2.03517608552995e-05, "loss": 4.1808, "step": 18319 }, { "epoch": 0.5595601710445938, "grad_norm": 0.3985455632209778, "learning_rate": 2.0349403811233286e-05, "loss": 4.2799, "step": 18320 }, { "epoch": 0.5595907147220526, "grad_norm": 0.42332592606544495, "learning_rate": 2.0347046809987507e-05, "loss": 4.1795, "step": 18321 }, { "epoch": 0.5596212583995113, "grad_norm": 0.4148714244365692, "learning_rate": 2.034468985158387e-05, "loss": 4.1853, "step": 18322 }, { "epoch": 0.5596518020769701, "grad_norm": 0.39663365483283997, "learning_rate": 2.034233293604406e-05, "loss": 4.2003, "step": 18323 }, { "epoch": 0.5596823457544289, "grad_norm": 0.400460809469223, "learning_rate": 2.033997606338978e-05, "loss": 4.3154, "step": 18324 }, { "epoch": 0.5597128894318876, "grad_norm": 0.40633493661880493, "learning_rate": 2.0337619233642748e-05, "loss": 4.1497, "step": 18325 }, { "epoch": 0.5597434331093464, "grad_norm": 0.4056271016597748, "learning_rate": 2.0335262446824643e-05, "loss": 4.3133, "step": 18326 }, { "epoch": 0.5597739767868052, "grad_norm": 0.40504589676856995, "learning_rate": 2.0332905702957173e-05, "loss": 4.2827, "step": 18327 }, { "epoch": 0.5598045204642639, "grad_norm": 0.4018038213253021, "learning_rate": 2.0330549002062053e-05, "loss": 4.3443, "step": 18328 }, { "epoch": 0.5598350641417227, "grad_norm": 0.4112304747104645, "learning_rate": 2.0328192344160956e-05, "loss": 4.3485, "step": 18329 }, { "epoch": 0.5598656078191814, "grad_norm": 0.3968660235404968, "learning_rate": 2.0325835729275605e-05, "loss": 4.2312, "step": 18330 }, { "epoch": 0.5598961514966402, "grad_norm": 0.3980157673358917, "learning_rate": 2.0323479157427682e-05, "loss": 4.2955, "step": 18331 }, { "epoch": 0.559926695174099, "grad_norm": 0.39616531133651733, "learning_rate": 2.032112262863889e-05, "loss": 4.2685, "step": 18332 }, { "epoch": 0.5599572388515577, "grad_norm": 0.41053226590156555, "learning_rate": 2.0318766142930934e-05, "loss": 4.2611, "step": 18333 }, { "epoch": 0.5599877825290165, "grad_norm": 0.3973124921321869, "learning_rate": 2.0316409700325494e-05, "loss": 4.3096, "step": 18334 }, { "epoch": 0.5600183262064753, "grad_norm": 0.41323667764663696, "learning_rate": 2.031405330084428e-05, "loss": 4.2769, "step": 18335 }, { "epoch": 0.560048869883934, "grad_norm": 0.41732969880104065, "learning_rate": 2.0311696944508997e-05, "loss": 4.2848, "step": 18336 }, { "epoch": 0.5600794135613928, "grad_norm": 0.40786832571029663, "learning_rate": 2.0309340631341318e-05, "loss": 4.2752, "step": 18337 }, { "epoch": 0.5601099572388516, "grad_norm": 0.39782142639160156, "learning_rate": 2.0306984361362958e-05, "loss": 4.2509, "step": 18338 }, { "epoch": 0.5601405009163103, "grad_norm": 0.3949338495731354, "learning_rate": 2.030462813459561e-05, "loss": 4.2505, "step": 18339 }, { "epoch": 0.5601710445937691, "grad_norm": 0.40723517537117004, "learning_rate": 2.0302271951060954e-05, "loss": 4.0921, "step": 18340 }, { "epoch": 0.5602015882712279, "grad_norm": 0.41805171966552734, "learning_rate": 2.0299915810780702e-05, "loss": 4.32, "step": 18341 }, { "epoch": 0.5602321319486866, "grad_norm": 0.41067972779273987, "learning_rate": 2.0297559713776546e-05, "loss": 4.2731, "step": 18342 }, { "epoch": 0.5602626756261454, "grad_norm": 0.39964860677719116, "learning_rate": 2.0295203660070167e-05, "loss": 4.3425, "step": 18343 }, { "epoch": 0.5602932193036042, "grad_norm": 0.3995191752910614, "learning_rate": 2.0292847649683264e-05, "loss": 4.2147, "step": 18344 }, { "epoch": 0.5603237629810629, "grad_norm": 0.40566426515579224, "learning_rate": 2.0290491682637547e-05, "loss": 4.2653, "step": 18345 }, { "epoch": 0.5603543066585217, "grad_norm": 0.39820608496665955, "learning_rate": 2.0288135758954686e-05, "loss": 4.3175, "step": 18346 }, { "epoch": 0.5603848503359804, "grad_norm": 0.41133344173431396, "learning_rate": 2.0285779878656384e-05, "loss": 4.3923, "step": 18347 }, { "epoch": 0.5604153940134392, "grad_norm": 0.4180194139480591, "learning_rate": 2.028342404176433e-05, "loss": 4.3281, "step": 18348 }, { "epoch": 0.560445937690898, "grad_norm": 0.40056943893432617, "learning_rate": 2.028106824830021e-05, "loss": 4.1973, "step": 18349 }, { "epoch": 0.5604764813683567, "grad_norm": 0.39609280228614807, "learning_rate": 2.027871249828573e-05, "loss": 4.2558, "step": 18350 }, { "epoch": 0.5605070250458155, "grad_norm": 0.39886561036109924, "learning_rate": 2.0276356791742564e-05, "loss": 4.352, "step": 18351 }, { "epoch": 0.5605375687232743, "grad_norm": 0.4089384973049164, "learning_rate": 2.027400112869241e-05, "loss": 4.3521, "step": 18352 }, { "epoch": 0.560568112400733, "grad_norm": 0.4169572591781616, "learning_rate": 2.0271645509156967e-05, "loss": 4.2796, "step": 18353 }, { "epoch": 0.5605986560781918, "grad_norm": 0.40292173624038696, "learning_rate": 2.0269289933157908e-05, "loss": 4.3116, "step": 18354 }, { "epoch": 0.5606291997556506, "grad_norm": 0.4119732081890106, "learning_rate": 2.0266934400716925e-05, "loss": 4.2563, "step": 18355 }, { "epoch": 0.5606597434331093, "grad_norm": 0.4103682339191437, "learning_rate": 2.026457891185572e-05, "loss": 4.3696, "step": 18356 }, { "epoch": 0.5606902871105681, "grad_norm": 0.4113123416900635, "learning_rate": 2.0262223466595963e-05, "loss": 4.2095, "step": 18357 }, { "epoch": 0.5607208307880269, "grad_norm": 0.4118817448616028, "learning_rate": 2.0259868064959348e-05, "loss": 4.2723, "step": 18358 }, { "epoch": 0.5607513744654856, "grad_norm": 0.3957030475139618, "learning_rate": 2.025751270696758e-05, "loss": 4.2691, "step": 18359 }, { "epoch": 0.5607819181429444, "grad_norm": 0.4115174412727356, "learning_rate": 2.0255157392642317e-05, "loss": 4.3142, "step": 18360 }, { "epoch": 0.5608124618204032, "grad_norm": 0.3980451822280884, "learning_rate": 2.0252802122005263e-05, "loss": 4.2234, "step": 18361 }, { "epoch": 0.5608430054978619, "grad_norm": 0.41442686319351196, "learning_rate": 2.02504468950781e-05, "loss": 4.1302, "step": 18362 }, { "epoch": 0.5608735491753207, "grad_norm": 0.39334696531295776, "learning_rate": 2.024809171188252e-05, "loss": 4.3324, "step": 18363 }, { "epoch": 0.5609040928527794, "grad_norm": 0.3966802656650543, "learning_rate": 2.0245736572440204e-05, "loss": 4.1548, "step": 18364 }, { "epoch": 0.5609346365302382, "grad_norm": 0.4021555483341217, "learning_rate": 2.0243381476772828e-05, "loss": 4.2772, "step": 18365 }, { "epoch": 0.560965180207697, "grad_norm": 0.3947821855545044, "learning_rate": 2.0241026424902083e-05, "loss": 4.3142, "step": 18366 }, { "epoch": 0.5609957238851557, "grad_norm": 0.4004049301147461, "learning_rate": 2.0238671416849664e-05, "loss": 4.1248, "step": 18367 }, { "epoch": 0.5610262675626145, "grad_norm": 0.39628127217292786, "learning_rate": 2.0236316452637234e-05, "loss": 4.2427, "step": 18368 }, { "epoch": 0.5610568112400733, "grad_norm": 0.4002668857574463, "learning_rate": 2.0233961532286495e-05, "loss": 4.2746, "step": 18369 }, { "epoch": 0.561087354917532, "grad_norm": 0.41106951236724854, "learning_rate": 2.0231606655819123e-05, "loss": 4.2374, "step": 18370 }, { "epoch": 0.5611178985949908, "grad_norm": 0.3996765613555908, "learning_rate": 2.0229251823256796e-05, "loss": 4.2527, "step": 18371 }, { "epoch": 0.5611484422724496, "grad_norm": 0.4080483615398407, "learning_rate": 2.0226897034621197e-05, "loss": 4.2301, "step": 18372 }, { "epoch": 0.5611789859499083, "grad_norm": 0.4054116904735565, "learning_rate": 2.0224542289934022e-05, "loss": 4.3887, "step": 18373 }, { "epoch": 0.5612095296273671, "grad_norm": 0.40808919072151184, "learning_rate": 2.0222187589216933e-05, "loss": 4.2611, "step": 18374 }, { "epoch": 0.561240073304826, "grad_norm": 0.39693501591682434, "learning_rate": 2.021983293249162e-05, "loss": 4.2611, "step": 18375 }, { "epoch": 0.5612706169822846, "grad_norm": 0.40351319313049316, "learning_rate": 2.021747831977977e-05, "loss": 4.309, "step": 18376 }, { "epoch": 0.5613011606597434, "grad_norm": 0.40168818831443787, "learning_rate": 2.0215123751103056e-05, "loss": 4.3208, "step": 18377 }, { "epoch": 0.5613317043372023, "grad_norm": 0.3986504375934601, "learning_rate": 2.0212769226483148e-05, "loss": 4.2139, "step": 18378 }, { "epoch": 0.561362248014661, "grad_norm": 0.3973727822303772, "learning_rate": 2.0210414745941744e-05, "loss": 4.2025, "step": 18379 }, { "epoch": 0.5613927916921198, "grad_norm": 0.4060591757297516, "learning_rate": 2.0208060309500507e-05, "loss": 4.268, "step": 18380 }, { "epoch": 0.5614233353695784, "grad_norm": 0.40917620062828064, "learning_rate": 2.0205705917181132e-05, "loss": 4.2635, "step": 18381 }, { "epoch": 0.5614538790470373, "grad_norm": 0.40761837363243103, "learning_rate": 2.0203351569005275e-05, "loss": 4.2467, "step": 18382 }, { "epoch": 0.5614844227244961, "grad_norm": 0.4083675146102905, "learning_rate": 2.0200997264994627e-05, "loss": 4.2554, "step": 18383 }, { "epoch": 0.5615149664019548, "grad_norm": 0.41259047389030457, "learning_rate": 2.019864300517088e-05, "loss": 4.2279, "step": 18384 }, { "epoch": 0.5615455100794136, "grad_norm": 0.40886908769607544, "learning_rate": 2.019628878955568e-05, "loss": 4.1708, "step": 18385 }, { "epoch": 0.5615760537568724, "grad_norm": 0.41248247027397156, "learning_rate": 2.0193934618170723e-05, "loss": 4.3274, "step": 18386 }, { "epoch": 0.5616065974343311, "grad_norm": 0.41762015223503113, "learning_rate": 2.019158049103769e-05, "loss": 4.2367, "step": 18387 }, { "epoch": 0.5616371411117899, "grad_norm": 0.4056018888950348, "learning_rate": 2.0189226408178236e-05, "loss": 4.3002, "step": 18388 }, { "epoch": 0.5616676847892487, "grad_norm": 0.40290141105651855, "learning_rate": 2.018687236961405e-05, "loss": 4.2435, "step": 18389 }, { "epoch": 0.5616982284667074, "grad_norm": 0.4068973660469055, "learning_rate": 2.0184518375366813e-05, "loss": 4.3152, "step": 18390 }, { "epoch": 0.5617287721441662, "grad_norm": 0.4307534396648407, "learning_rate": 2.0182164425458178e-05, "loss": 4.193, "step": 18391 }, { "epoch": 0.561759315821625, "grad_norm": 0.4316895604133606, "learning_rate": 2.0179810519909843e-05, "loss": 4.2467, "step": 18392 }, { "epoch": 0.5617898594990837, "grad_norm": 0.40863969922065735, "learning_rate": 2.0177456658743467e-05, "loss": 4.2744, "step": 18393 }, { "epoch": 0.5618204031765425, "grad_norm": 0.40481752157211304, "learning_rate": 2.017510284198073e-05, "loss": 4.2147, "step": 18394 }, { "epoch": 0.5618509468540013, "grad_norm": 0.39363035559654236, "learning_rate": 2.0172749069643294e-05, "loss": 4.2248, "step": 18395 }, { "epoch": 0.56188149053146, "grad_norm": 0.4102550446987152, "learning_rate": 2.017039534175285e-05, "loss": 4.2207, "step": 18396 }, { "epoch": 0.5619120342089188, "grad_norm": 0.40644964575767517, "learning_rate": 2.0168041658331045e-05, "loss": 4.2335, "step": 18397 }, { "epoch": 0.5619425778863775, "grad_norm": 0.4008929431438446, "learning_rate": 2.016568801939958e-05, "loss": 4.297, "step": 18398 }, { "epoch": 0.5619731215638363, "grad_norm": 0.4127717614173889, "learning_rate": 2.0163334424980103e-05, "loss": 4.3137, "step": 18399 }, { "epoch": 0.5620036652412951, "grad_norm": 0.40282076597213745, "learning_rate": 2.0160980875094292e-05, "loss": 4.3578, "step": 18400 }, { "epoch": 0.5620342089187538, "grad_norm": 0.40977543592453003, "learning_rate": 2.015862736976382e-05, "loss": 4.2397, "step": 18401 }, { "epoch": 0.5620647525962126, "grad_norm": 0.423041969537735, "learning_rate": 2.015627390901036e-05, "loss": 4.32, "step": 18402 }, { "epoch": 0.5620952962736714, "grad_norm": 0.4001908302307129, "learning_rate": 2.0153920492855565e-05, "loss": 4.2351, "step": 18403 }, { "epoch": 0.5621258399511301, "grad_norm": 0.40988782048225403, "learning_rate": 2.015156712132113e-05, "loss": 4.3295, "step": 18404 }, { "epoch": 0.5621563836285889, "grad_norm": 0.4047658145427704, "learning_rate": 2.0149213794428694e-05, "loss": 4.2507, "step": 18405 }, { "epoch": 0.5621869273060477, "grad_norm": 0.4005791246891022, "learning_rate": 2.0146860512199948e-05, "loss": 4.2903, "step": 18406 }, { "epoch": 0.5622174709835064, "grad_norm": 0.3982382118701935, "learning_rate": 2.0144507274656558e-05, "loss": 4.2107, "step": 18407 }, { "epoch": 0.5622480146609652, "grad_norm": 0.40387600660324097, "learning_rate": 2.0142154081820173e-05, "loss": 4.2895, "step": 18408 }, { "epoch": 0.562278558338424, "grad_norm": 0.4196506142616272, "learning_rate": 2.013980093371248e-05, "loss": 4.2814, "step": 18409 }, { "epoch": 0.5623091020158827, "grad_norm": 0.41435909271240234, "learning_rate": 2.013744783035515e-05, "loss": 4.3006, "step": 18410 }, { "epoch": 0.5623396456933415, "grad_norm": 0.4049944281578064, "learning_rate": 2.013509477176982e-05, "loss": 4.3413, "step": 18411 }, { "epoch": 0.5623701893708003, "grad_norm": 0.4067923426628113, "learning_rate": 2.013274175797818e-05, "loss": 4.3644, "step": 18412 }, { "epoch": 0.562400733048259, "grad_norm": 0.40447381138801575, "learning_rate": 2.0130388789001893e-05, "loss": 4.2854, "step": 18413 }, { "epoch": 0.5624312767257178, "grad_norm": 0.4200936257839203, "learning_rate": 2.0128035864862615e-05, "loss": 4.2543, "step": 18414 }, { "epoch": 0.5624618204031765, "grad_norm": 0.4084419012069702, "learning_rate": 2.012568298558202e-05, "loss": 4.3514, "step": 18415 }, { "epoch": 0.5624923640806353, "grad_norm": 0.41662415862083435, "learning_rate": 2.0123330151181767e-05, "loss": 4.2773, "step": 18416 }, { "epoch": 0.5625229077580941, "grad_norm": 0.4066928029060364, "learning_rate": 2.012097736168352e-05, "loss": 4.1618, "step": 18417 }, { "epoch": 0.5625534514355528, "grad_norm": 0.40934768319129944, "learning_rate": 2.0118624617108947e-05, "loss": 4.2055, "step": 18418 }, { "epoch": 0.5625839951130116, "grad_norm": 0.4038417935371399, "learning_rate": 2.0116271917479698e-05, "loss": 4.3052, "step": 18419 }, { "epoch": 0.5626145387904704, "grad_norm": 0.41499805450439453, "learning_rate": 2.0113919262817443e-05, "loss": 4.3034, "step": 18420 }, { "epoch": 0.5626450824679291, "grad_norm": 0.3986659646034241, "learning_rate": 2.011156665314386e-05, "loss": 4.3026, "step": 18421 }, { "epoch": 0.5626756261453879, "grad_norm": 0.4142310917377472, "learning_rate": 2.0109214088480583e-05, "loss": 4.1944, "step": 18422 }, { "epoch": 0.5627061698228467, "grad_norm": 0.4166299104690552, "learning_rate": 2.010686156884929e-05, "loss": 4.3493, "step": 18423 }, { "epoch": 0.5627367135003054, "grad_norm": 0.40976619720458984, "learning_rate": 2.010450909427164e-05, "loss": 4.2144, "step": 18424 }, { "epoch": 0.5627672571777642, "grad_norm": 0.4146591126918793, "learning_rate": 2.0102156664769294e-05, "loss": 4.2235, "step": 18425 }, { "epoch": 0.562797800855223, "grad_norm": 0.4080324172973633, "learning_rate": 2.0099804280363902e-05, "loss": 4.2713, "step": 18426 }, { "epoch": 0.5628283445326817, "grad_norm": 0.41192662715911865, "learning_rate": 2.0097451941077143e-05, "loss": 4.2677, "step": 18427 }, { "epoch": 0.5628588882101405, "grad_norm": 0.4116693437099457, "learning_rate": 2.0095099646930654e-05, "loss": 4.3399, "step": 18428 }, { "epoch": 0.5628894318875992, "grad_norm": 0.4274929463863373, "learning_rate": 2.0092747397946114e-05, "loss": 4.3567, "step": 18429 }, { "epoch": 0.562919975565058, "grad_norm": 0.4065336287021637, "learning_rate": 2.0090395194145162e-05, "loss": 4.1661, "step": 18430 }, { "epoch": 0.5629505192425168, "grad_norm": 0.4061581790447235, "learning_rate": 2.0088043035549464e-05, "loss": 4.2445, "step": 18431 }, { "epoch": 0.5629810629199755, "grad_norm": 0.4084659814834595, "learning_rate": 2.0085690922180693e-05, "loss": 4.3005, "step": 18432 }, { "epoch": 0.5630116065974343, "grad_norm": 0.40867719054222107, "learning_rate": 2.0083338854060483e-05, "loss": 4.3016, "step": 18433 }, { "epoch": 0.5630421502748931, "grad_norm": 0.41036391258239746, "learning_rate": 2.0080986831210495e-05, "loss": 4.1445, "step": 18434 }, { "epoch": 0.5630726939523518, "grad_norm": 0.4274502992630005, "learning_rate": 2.0078634853652406e-05, "loss": 4.2931, "step": 18435 }, { "epoch": 0.5631032376298106, "grad_norm": 0.40197381377220154, "learning_rate": 2.0076282921407844e-05, "loss": 4.3239, "step": 18436 }, { "epoch": 0.5631337813072694, "grad_norm": 0.4057323634624481, "learning_rate": 2.0073931034498475e-05, "loss": 4.3538, "step": 18437 }, { "epoch": 0.5631643249847281, "grad_norm": 0.41252708435058594, "learning_rate": 2.0071579192945966e-05, "loss": 4.3212, "step": 18438 }, { "epoch": 0.5631948686621869, "grad_norm": 0.41034698486328125, "learning_rate": 2.0069227396771952e-05, "loss": 4.2969, "step": 18439 }, { "epoch": 0.5632254123396457, "grad_norm": 0.4191092252731323, "learning_rate": 2.00668756459981e-05, "loss": 4.3232, "step": 18440 }, { "epoch": 0.5632559560171044, "grad_norm": 0.4103803038597107, "learning_rate": 2.0064523940646067e-05, "loss": 4.2071, "step": 18441 }, { "epoch": 0.5632864996945632, "grad_norm": 0.42710161209106445, "learning_rate": 2.006217228073749e-05, "loss": 4.3256, "step": 18442 }, { "epoch": 0.563317043372022, "grad_norm": 0.4072459936141968, "learning_rate": 2.0059820666294028e-05, "loss": 4.2466, "step": 18443 }, { "epoch": 0.5633475870494807, "grad_norm": 0.41299140453338623, "learning_rate": 2.005746909733735e-05, "loss": 4.1929, "step": 18444 }, { "epoch": 0.5633781307269395, "grad_norm": 0.4155232310295105, "learning_rate": 2.0055117573889088e-05, "loss": 4.2394, "step": 18445 }, { "epoch": 0.5634086744043982, "grad_norm": 0.4130275249481201, "learning_rate": 2.0052766095970906e-05, "loss": 4.3324, "step": 18446 }, { "epoch": 0.563439218081857, "grad_norm": 0.4077603220939636, "learning_rate": 2.005041466360444e-05, "loss": 4.2653, "step": 18447 }, { "epoch": 0.5634697617593158, "grad_norm": 0.4096280634403229, "learning_rate": 2.004806327681136e-05, "loss": 4.3261, "step": 18448 }, { "epoch": 0.5635003054367745, "grad_norm": 0.4088045060634613, "learning_rate": 2.004571193561331e-05, "loss": 4.251, "step": 18449 }, { "epoch": 0.5635308491142333, "grad_norm": 0.39872851967811584, "learning_rate": 2.0043360640031928e-05, "loss": 4.3303, "step": 18450 }, { "epoch": 0.5635613927916922, "grad_norm": 0.40918946266174316, "learning_rate": 2.0041009390088872e-05, "loss": 4.294, "step": 18451 }, { "epoch": 0.5635919364691508, "grad_norm": 0.39414307475090027, "learning_rate": 2.00386581858058e-05, "loss": 4.2376, "step": 18452 }, { "epoch": 0.5636224801466097, "grad_norm": 0.4032468795776367, "learning_rate": 2.0036307027204353e-05, "loss": 4.2279, "step": 18453 }, { "epoch": 0.5636530238240685, "grad_norm": 0.40831905603408813, "learning_rate": 2.003395591430617e-05, "loss": 4.279, "step": 18454 }, { "epoch": 0.5636835675015271, "grad_norm": 0.40294378995895386, "learning_rate": 2.003160484713292e-05, "loss": 4.1069, "step": 18455 }, { "epoch": 0.563714111178986, "grad_norm": 0.40319302678108215, "learning_rate": 2.0029253825706236e-05, "loss": 4.1818, "step": 18456 }, { "epoch": 0.5637446548564448, "grad_norm": 0.40478432178497314, "learning_rate": 2.002690285004776e-05, "loss": 4.2685, "step": 18457 }, { "epoch": 0.5637751985339035, "grad_norm": 0.42435726523399353, "learning_rate": 2.002455192017916e-05, "loss": 4.2974, "step": 18458 }, { "epoch": 0.5638057422113623, "grad_norm": 0.4004998207092285, "learning_rate": 2.0022201036122054e-05, "loss": 4.1564, "step": 18459 }, { "epoch": 0.5638362858888211, "grad_norm": 0.39732855558395386, "learning_rate": 2.0019850197898106e-05, "loss": 4.2476, "step": 18460 }, { "epoch": 0.5638668295662798, "grad_norm": 0.4037957787513733, "learning_rate": 2.0017499405528963e-05, "loss": 4.3019, "step": 18461 }, { "epoch": 0.5638973732437386, "grad_norm": 0.42052146792411804, "learning_rate": 2.001514865903626e-05, "loss": 4.1938, "step": 18462 }, { "epoch": 0.5639279169211973, "grad_norm": 0.3957054018974304, "learning_rate": 2.0012797958441654e-05, "loss": 4.3186, "step": 18463 }, { "epoch": 0.5639584605986561, "grad_norm": 0.4224432110786438, "learning_rate": 2.0010447303766773e-05, "loss": 4.2414, "step": 18464 }, { "epoch": 0.5639890042761149, "grad_norm": 0.40673550963401794, "learning_rate": 2.000809669503327e-05, "loss": 4.1968, "step": 18465 }, { "epoch": 0.5640195479535736, "grad_norm": 0.4058692753314972, "learning_rate": 2.0005746132262795e-05, "loss": 4.3535, "step": 18466 }, { "epoch": 0.5640500916310324, "grad_norm": 0.40084993839263916, "learning_rate": 2.000339561547697e-05, "loss": 4.2335, "step": 18467 }, { "epoch": 0.5640806353084912, "grad_norm": 0.4040408134460449, "learning_rate": 2.0001045144697456e-05, "loss": 4.1395, "step": 18468 }, { "epoch": 0.5641111789859499, "grad_norm": 0.41215261816978455, "learning_rate": 1.9998694719945898e-05, "loss": 4.2771, "step": 18469 }, { "epoch": 0.5641417226634087, "grad_norm": 0.40716612339019775, "learning_rate": 1.9996344341243917e-05, "loss": 4.2717, "step": 18470 }, { "epoch": 0.5641722663408675, "grad_norm": 0.42032966017723083, "learning_rate": 1.9993994008613172e-05, "loss": 4.3542, "step": 18471 }, { "epoch": 0.5642028100183262, "grad_norm": 0.41029438376426697, "learning_rate": 1.9991643722075297e-05, "loss": 4.1607, "step": 18472 }, { "epoch": 0.564233353695785, "grad_norm": 0.39887356758117676, "learning_rate": 1.998929348165194e-05, "loss": 4.3145, "step": 18473 }, { "epoch": 0.5642638973732438, "grad_norm": 0.4068220555782318, "learning_rate": 1.998694328736472e-05, "loss": 4.3623, "step": 18474 }, { "epoch": 0.5642944410507025, "grad_norm": 0.41158759593963623, "learning_rate": 1.9984593139235306e-05, "loss": 4.1788, "step": 18475 }, { "epoch": 0.5643249847281613, "grad_norm": 0.40883320569992065, "learning_rate": 1.9982243037285307e-05, "loss": 4.2591, "step": 18476 }, { "epoch": 0.5643555284056201, "grad_norm": 0.42085516452789307, "learning_rate": 1.997989298153638e-05, "loss": 4.2369, "step": 18477 }, { "epoch": 0.5643860720830788, "grad_norm": 0.4171455204486847, "learning_rate": 1.9977542972010173e-05, "loss": 4.355, "step": 18478 }, { "epoch": 0.5644166157605376, "grad_norm": 0.4053919315338135, "learning_rate": 1.9975193008728297e-05, "loss": 4.3122, "step": 18479 }, { "epoch": 0.5644471594379963, "grad_norm": 0.40571099519729614, "learning_rate": 1.9972843091712408e-05, "loss": 4.2496, "step": 18480 }, { "epoch": 0.5644777031154551, "grad_norm": 0.39404061436653137, "learning_rate": 1.997049322098414e-05, "loss": 4.2697, "step": 18481 }, { "epoch": 0.5645082467929139, "grad_norm": 0.4113111197948456, "learning_rate": 1.9968143396565116e-05, "loss": 4.2719, "step": 18482 }, { "epoch": 0.5645387904703726, "grad_norm": 0.39957526326179504, "learning_rate": 1.9965793618476995e-05, "loss": 4.2608, "step": 18483 }, { "epoch": 0.5645693341478314, "grad_norm": 0.39436039328575134, "learning_rate": 1.9963443886741388e-05, "loss": 4.2944, "step": 18484 }, { "epoch": 0.5645998778252902, "grad_norm": 0.4093289077281952, "learning_rate": 1.9961094201379943e-05, "loss": 4.3191, "step": 18485 }, { "epoch": 0.5646304215027489, "grad_norm": 0.40483400225639343, "learning_rate": 1.9958744562414308e-05, "loss": 4.2978, "step": 18486 }, { "epoch": 0.5646609651802077, "grad_norm": 0.39845412969589233, "learning_rate": 1.9956394969866095e-05, "loss": 4.3823, "step": 18487 }, { "epoch": 0.5646915088576665, "grad_norm": 0.4007343053817749, "learning_rate": 1.9954045423756945e-05, "loss": 4.2949, "step": 18488 }, { "epoch": 0.5647220525351252, "grad_norm": 0.3955763280391693, "learning_rate": 1.99516959241085e-05, "loss": 4.3285, "step": 18489 }, { "epoch": 0.564752596212584, "grad_norm": 0.4053416848182678, "learning_rate": 1.994934647094238e-05, "loss": 4.3391, "step": 18490 }, { "epoch": 0.5647831398900428, "grad_norm": 0.3987317383289337, "learning_rate": 1.994699706428022e-05, "loss": 4.3189, "step": 18491 }, { "epoch": 0.5648136835675015, "grad_norm": 0.4060051143169403, "learning_rate": 1.994464770414367e-05, "loss": 4.3097, "step": 18492 }, { "epoch": 0.5648442272449603, "grad_norm": 0.400985449552536, "learning_rate": 1.9942298390554334e-05, "loss": 4.3265, "step": 18493 }, { "epoch": 0.5648747709224191, "grad_norm": 0.4073285758495331, "learning_rate": 1.9939949123533863e-05, "loss": 4.2825, "step": 18494 }, { "epoch": 0.5649053145998778, "grad_norm": 0.4092347323894501, "learning_rate": 1.9937599903103883e-05, "loss": 4.2192, "step": 18495 }, { "epoch": 0.5649358582773366, "grad_norm": 0.4039839506149292, "learning_rate": 1.9935250729286025e-05, "loss": 4.1948, "step": 18496 }, { "epoch": 0.5649664019547953, "grad_norm": 0.40895795822143555, "learning_rate": 1.993290160210192e-05, "loss": 4.3648, "step": 18497 }, { "epoch": 0.5649969456322541, "grad_norm": 0.39998114109039307, "learning_rate": 1.9930552521573186e-05, "loss": 4.2924, "step": 18498 }, { "epoch": 0.5650274893097129, "grad_norm": 0.40223461389541626, "learning_rate": 1.992820348772146e-05, "loss": 4.3034, "step": 18499 }, { "epoch": 0.5650580329871716, "grad_norm": 0.4138909578323364, "learning_rate": 1.9925854500568387e-05, "loss": 4.2961, "step": 18500 }, { "epoch": 0.5650885766646304, "grad_norm": 0.3943306505680084, "learning_rate": 1.9923505560135563e-05, "loss": 4.3345, "step": 18501 }, { "epoch": 0.5651191203420892, "grad_norm": 0.40721893310546875, "learning_rate": 1.9921156666444647e-05, "loss": 4.188, "step": 18502 }, { "epoch": 0.5651496640195479, "grad_norm": 0.4129241704940796, "learning_rate": 1.9918807819517247e-05, "loss": 4.2972, "step": 18503 }, { "epoch": 0.5651802076970067, "grad_norm": 0.40274354815483093, "learning_rate": 1.9916459019374997e-05, "loss": 4.2915, "step": 18504 }, { "epoch": 0.5652107513744655, "grad_norm": 0.3996383249759674, "learning_rate": 1.9914110266039513e-05, "loss": 4.2669, "step": 18505 }, { "epoch": 0.5652412950519242, "grad_norm": 0.39999818801879883, "learning_rate": 1.991176155953245e-05, "loss": 4.3142, "step": 18506 }, { "epoch": 0.565271838729383, "grad_norm": 0.4078276455402374, "learning_rate": 1.9909412899875398e-05, "loss": 4.2739, "step": 18507 }, { "epoch": 0.5653023824068418, "grad_norm": 0.4041635990142822, "learning_rate": 1.9907064287090002e-05, "loss": 4.3753, "step": 18508 }, { "epoch": 0.5653329260843005, "grad_norm": 0.40139836072921753, "learning_rate": 1.9904715721197892e-05, "loss": 4.2995, "step": 18509 }, { "epoch": 0.5653634697617593, "grad_norm": 0.403434693813324, "learning_rate": 1.9902367202220677e-05, "loss": 4.3188, "step": 18510 }, { "epoch": 0.5653940134392181, "grad_norm": 0.3997526466846466, "learning_rate": 1.9900018730179987e-05, "loss": 4.3106, "step": 18511 }, { "epoch": 0.5654245571166768, "grad_norm": 0.40821024775505066, "learning_rate": 1.9897670305097455e-05, "loss": 4.3271, "step": 18512 }, { "epoch": 0.5654551007941356, "grad_norm": 0.40588903427124023, "learning_rate": 1.9895321926994687e-05, "loss": 4.3667, "step": 18513 }, { "epoch": 0.5654856444715943, "grad_norm": 0.41659680008888245, "learning_rate": 1.9892973595893323e-05, "loss": 4.3055, "step": 18514 }, { "epoch": 0.5655161881490531, "grad_norm": 0.40032243728637695, "learning_rate": 1.9890625311814967e-05, "loss": 4.1933, "step": 18515 }, { "epoch": 0.5655467318265119, "grad_norm": 0.42244914174079895, "learning_rate": 1.9888277074781254e-05, "loss": 4.2335, "step": 18516 }, { "epoch": 0.5655772755039706, "grad_norm": 0.40259239077568054, "learning_rate": 1.9885928884813807e-05, "loss": 4.3781, "step": 18517 }, { "epoch": 0.5656078191814294, "grad_norm": 0.4208872616291046, "learning_rate": 1.9883580741934237e-05, "loss": 4.3923, "step": 18518 }, { "epoch": 0.5656383628588882, "grad_norm": 0.41001126170158386, "learning_rate": 1.988123264616417e-05, "loss": 4.2457, "step": 18519 }, { "epoch": 0.5656689065363469, "grad_norm": 0.413845032453537, "learning_rate": 1.9878884597525234e-05, "loss": 4.2056, "step": 18520 }, { "epoch": 0.5656994502138057, "grad_norm": 0.4225864112377167, "learning_rate": 1.9876536596039027e-05, "loss": 4.2656, "step": 18521 }, { "epoch": 0.5657299938912645, "grad_norm": 0.4042171537876129, "learning_rate": 1.9874188641727185e-05, "loss": 4.3061, "step": 18522 }, { "epoch": 0.5657605375687232, "grad_norm": 0.39897090196609497, "learning_rate": 1.9871840734611334e-05, "loss": 4.2491, "step": 18523 }, { "epoch": 0.565791081246182, "grad_norm": 0.41564881801605225, "learning_rate": 1.986949287471307e-05, "loss": 4.246, "step": 18524 }, { "epoch": 0.5658216249236409, "grad_norm": 0.4087013006210327, "learning_rate": 1.9867145062054028e-05, "loss": 4.3786, "step": 18525 }, { "epoch": 0.5658521686010995, "grad_norm": 0.39918264746665955, "learning_rate": 1.9864797296655822e-05, "loss": 4.3609, "step": 18526 }, { "epoch": 0.5658827122785584, "grad_norm": 0.4201332926750183, "learning_rate": 1.986244957854007e-05, "loss": 4.2832, "step": 18527 }, { "epoch": 0.5659132559560172, "grad_norm": 0.4147801101207733, "learning_rate": 1.9860101907728376e-05, "loss": 4.1836, "step": 18528 }, { "epoch": 0.5659437996334759, "grad_norm": 0.4040261507034302, "learning_rate": 1.985775428424238e-05, "loss": 4.2545, "step": 18529 }, { "epoch": 0.5659743433109347, "grad_norm": 0.40232083201408386, "learning_rate": 1.985540670810367e-05, "loss": 4.2524, "step": 18530 }, { "epoch": 0.5660048869883934, "grad_norm": 0.4060232639312744, "learning_rate": 1.985305917933389e-05, "loss": 4.2805, "step": 18531 }, { "epoch": 0.5660354306658522, "grad_norm": 0.4047696590423584, "learning_rate": 1.9850711697954626e-05, "loss": 4.3745, "step": 18532 }, { "epoch": 0.566065974343311, "grad_norm": 0.40087929368019104, "learning_rate": 1.9848364263987518e-05, "loss": 4.3448, "step": 18533 }, { "epoch": 0.5660965180207697, "grad_norm": 0.4019812345504761, "learning_rate": 1.9846016877454166e-05, "loss": 4.2717, "step": 18534 }, { "epoch": 0.5661270616982285, "grad_norm": 0.40314412117004395, "learning_rate": 1.9843669538376184e-05, "loss": 4.274, "step": 18535 }, { "epoch": 0.5661576053756873, "grad_norm": 0.4042361378669739, "learning_rate": 1.9841322246775185e-05, "loss": 4.3026, "step": 18536 }, { "epoch": 0.566188149053146, "grad_norm": 0.3987964689731598, "learning_rate": 1.9838975002672795e-05, "loss": 4.2665, "step": 18537 }, { "epoch": 0.5662186927306048, "grad_norm": 0.44964665174484253, "learning_rate": 1.9836627806090603e-05, "loss": 4.1491, "step": 18538 }, { "epoch": 0.5662492364080636, "grad_norm": 0.411469966173172, "learning_rate": 1.9834280657050236e-05, "loss": 4.2435, "step": 18539 }, { "epoch": 0.5662797800855223, "grad_norm": 0.4057430326938629, "learning_rate": 1.983193355557331e-05, "loss": 4.3531, "step": 18540 }, { "epoch": 0.5663103237629811, "grad_norm": 0.4017626941204071, "learning_rate": 1.9829586501681425e-05, "loss": 4.2527, "step": 18541 }, { "epoch": 0.5663408674404399, "grad_norm": 0.3950585424900055, "learning_rate": 1.9827239495396193e-05, "loss": 4.2456, "step": 18542 }, { "epoch": 0.5663714111178986, "grad_norm": 0.4007292687892914, "learning_rate": 1.9824892536739238e-05, "loss": 4.3678, "step": 18543 }, { "epoch": 0.5664019547953574, "grad_norm": 0.39325618743896484, "learning_rate": 1.9822545625732144e-05, "loss": 4.2447, "step": 18544 }, { "epoch": 0.5664324984728162, "grad_norm": 0.40807175636291504, "learning_rate": 1.9820198762396536e-05, "loss": 4.296, "step": 18545 }, { "epoch": 0.5664630421502749, "grad_norm": 0.4137038588523865, "learning_rate": 1.9817851946754033e-05, "loss": 4.2719, "step": 18546 }, { "epoch": 0.5664935858277337, "grad_norm": 0.40886494517326355, "learning_rate": 1.9815505178826216e-05, "loss": 4.3024, "step": 18547 }, { "epoch": 0.5665241295051924, "grad_norm": 0.40189820528030396, "learning_rate": 1.9813158458634724e-05, "loss": 4.267, "step": 18548 }, { "epoch": 0.5665546731826512, "grad_norm": 0.41431406140327454, "learning_rate": 1.9810811786201135e-05, "loss": 4.3867, "step": 18549 }, { "epoch": 0.56658521686011, "grad_norm": 0.4318939745426178, "learning_rate": 1.9808465161547075e-05, "loss": 4.1398, "step": 18550 }, { "epoch": 0.5666157605375687, "grad_norm": 0.3978431224822998, "learning_rate": 1.9806118584694154e-05, "loss": 4.232, "step": 18551 }, { "epoch": 0.5666463042150275, "grad_norm": 0.4103338420391083, "learning_rate": 1.9803772055663958e-05, "loss": 4.2029, "step": 18552 }, { "epoch": 0.5666768478924863, "grad_norm": 0.4057474732398987, "learning_rate": 1.9801425574478106e-05, "loss": 4.2488, "step": 18553 }, { "epoch": 0.566707391569945, "grad_norm": 0.3988485336303711, "learning_rate": 1.9799079141158207e-05, "loss": 4.2524, "step": 18554 }, { "epoch": 0.5667379352474038, "grad_norm": 0.40215086936950684, "learning_rate": 1.9796732755725856e-05, "loss": 4.069, "step": 18555 }, { "epoch": 0.5667684789248626, "grad_norm": 0.41195544600486755, "learning_rate": 1.9794386418202663e-05, "loss": 4.1891, "step": 18556 }, { "epoch": 0.5667990226023213, "grad_norm": 0.41796794533729553, "learning_rate": 1.9792040128610232e-05, "loss": 4.2877, "step": 18557 }, { "epoch": 0.5668295662797801, "grad_norm": 0.394106924533844, "learning_rate": 1.9789693886970163e-05, "loss": 4.2743, "step": 18558 }, { "epoch": 0.5668601099572389, "grad_norm": 0.4086756706237793, "learning_rate": 1.9787347693304058e-05, "loss": 4.361, "step": 18559 }, { "epoch": 0.5668906536346976, "grad_norm": 0.4098148047924042, "learning_rate": 1.9785001547633533e-05, "loss": 4.3366, "step": 18560 }, { "epoch": 0.5669211973121564, "grad_norm": 0.4174616038799286, "learning_rate": 1.978265544998017e-05, "loss": 4.2188, "step": 18561 }, { "epoch": 0.5669517409896152, "grad_norm": 0.41252198815345764, "learning_rate": 1.978030940036558e-05, "loss": 4.2154, "step": 18562 }, { "epoch": 0.5669822846670739, "grad_norm": 0.41652023792266846, "learning_rate": 1.9777963398811377e-05, "loss": 4.2647, "step": 18563 }, { "epoch": 0.5670128283445327, "grad_norm": 0.4087757170200348, "learning_rate": 1.9775617445339136e-05, "loss": 4.2942, "step": 18564 }, { "epoch": 0.5670433720219914, "grad_norm": 0.4144354462623596, "learning_rate": 1.9773271539970487e-05, "loss": 4.2853, "step": 18565 }, { "epoch": 0.5670739156994502, "grad_norm": 0.4180101156234741, "learning_rate": 1.9770925682727003e-05, "loss": 4.2597, "step": 18566 }, { "epoch": 0.567104459376909, "grad_norm": 0.4209989309310913, "learning_rate": 1.9768579873630295e-05, "loss": 4.3415, "step": 18567 }, { "epoch": 0.5671350030543677, "grad_norm": 0.39547932147979736, "learning_rate": 1.976623411270197e-05, "loss": 4.315, "step": 18568 }, { "epoch": 0.5671655467318265, "grad_norm": 0.40460190176963806, "learning_rate": 1.976388839996361e-05, "loss": 4.2606, "step": 18569 }, { "epoch": 0.5671960904092853, "grad_norm": 0.4081195592880249, "learning_rate": 1.9761542735436816e-05, "loss": 4.433, "step": 18570 }, { "epoch": 0.567226634086744, "grad_norm": 0.41260024905204773, "learning_rate": 1.9759197119143208e-05, "loss": 4.264, "step": 18571 }, { "epoch": 0.5672571777642028, "grad_norm": 0.39839547872543335, "learning_rate": 1.9756851551104352e-05, "loss": 4.262, "step": 18572 }, { "epoch": 0.5672877214416616, "grad_norm": 0.41486769914627075, "learning_rate": 1.9754506031341867e-05, "loss": 4.272, "step": 18573 }, { "epoch": 0.5673182651191203, "grad_norm": 0.41065457463264465, "learning_rate": 1.9752160559877348e-05, "loss": 4.2904, "step": 18574 }, { "epoch": 0.5673488087965791, "grad_norm": 0.4064982831478119, "learning_rate": 1.974981513673237e-05, "loss": 4.2416, "step": 18575 }, { "epoch": 0.5673793524740379, "grad_norm": 0.4072554409503937, "learning_rate": 1.974746976192855e-05, "loss": 4.1939, "step": 18576 }, { "epoch": 0.5674098961514966, "grad_norm": 0.40437307953834534, "learning_rate": 1.9745124435487483e-05, "loss": 4.3184, "step": 18577 }, { "epoch": 0.5674404398289554, "grad_norm": 0.41037681698799133, "learning_rate": 1.9742779157430746e-05, "loss": 4.2865, "step": 18578 }, { "epoch": 0.5674709835064141, "grad_norm": 0.40782254934310913, "learning_rate": 1.9740433927779956e-05, "loss": 4.2821, "step": 18579 }, { "epoch": 0.5675015271838729, "grad_norm": 0.4184117019176483, "learning_rate": 1.9738088746556687e-05, "loss": 4.3, "step": 18580 }, { "epoch": 0.5675320708613317, "grad_norm": 0.4139685034751892, "learning_rate": 1.973574361378254e-05, "loss": 4.3142, "step": 18581 }, { "epoch": 0.5675626145387904, "grad_norm": 0.4267510771751404, "learning_rate": 1.973339852947911e-05, "loss": 4.3376, "step": 18582 }, { "epoch": 0.5675931582162492, "grad_norm": 0.4324631989002228, "learning_rate": 1.973105349366799e-05, "loss": 4.2777, "step": 18583 }, { "epoch": 0.567623701893708, "grad_norm": 0.401124507188797, "learning_rate": 1.9728708506370765e-05, "loss": 4.3165, "step": 18584 }, { "epoch": 0.5676542455711667, "grad_norm": 0.431474506855011, "learning_rate": 1.9726363567609036e-05, "loss": 4.3407, "step": 18585 }, { "epoch": 0.5676847892486255, "grad_norm": 0.4293960630893707, "learning_rate": 1.9724018677404383e-05, "loss": 4.2617, "step": 18586 }, { "epoch": 0.5677153329260843, "grad_norm": 0.4119535982608795, "learning_rate": 1.97216738357784e-05, "loss": 4.2731, "step": 18587 }, { "epoch": 0.567745876603543, "grad_norm": 0.4048275649547577, "learning_rate": 1.9719329042752692e-05, "loss": 4.4049, "step": 18588 }, { "epoch": 0.5677764202810018, "grad_norm": 0.4122851490974426, "learning_rate": 1.9716984298348833e-05, "loss": 4.2863, "step": 18589 }, { "epoch": 0.5678069639584606, "grad_norm": 0.40021705627441406, "learning_rate": 1.971463960258841e-05, "loss": 4.2643, "step": 18590 }, { "epoch": 0.5678375076359193, "grad_norm": 0.42156901955604553, "learning_rate": 1.9712294955493027e-05, "loss": 4.3258, "step": 18591 }, { "epoch": 0.5678680513133781, "grad_norm": 0.40108686685562134, "learning_rate": 1.970995035708425e-05, "loss": 4.2491, "step": 18592 }, { "epoch": 0.567898594990837, "grad_norm": 0.41392770409584045, "learning_rate": 1.9707605807383682e-05, "loss": 4.2378, "step": 18593 }, { "epoch": 0.5679291386682956, "grad_norm": 0.4061761200428009, "learning_rate": 1.970526130641292e-05, "loss": 4.3183, "step": 18594 }, { "epoch": 0.5679596823457544, "grad_norm": 0.4016978144645691, "learning_rate": 1.970291685419353e-05, "loss": 4.2879, "step": 18595 }, { "epoch": 0.5679902260232131, "grad_norm": 0.40599164366722107, "learning_rate": 1.970057245074712e-05, "loss": 4.2436, "step": 18596 }, { "epoch": 0.568020769700672, "grad_norm": 0.41037824749946594, "learning_rate": 1.9698228096095255e-05, "loss": 4.3348, "step": 18597 }, { "epoch": 0.5680513133781308, "grad_norm": 0.411508172750473, "learning_rate": 1.9695883790259523e-05, "loss": 4.2259, "step": 18598 }, { "epoch": 0.5680818570555894, "grad_norm": 0.3928549885749817, "learning_rate": 1.969353953326153e-05, "loss": 4.308, "step": 18599 }, { "epoch": 0.5681124007330483, "grad_norm": 0.40757349133491516, "learning_rate": 1.9691195325122835e-05, "loss": 4.2913, "step": 18600 }, { "epoch": 0.5681429444105071, "grad_norm": 0.40065905451774597, "learning_rate": 1.9688851165865033e-05, "loss": 4.2646, "step": 18601 }, { "epoch": 0.5681734880879658, "grad_norm": 0.4018748700618744, "learning_rate": 1.9686507055509723e-05, "loss": 4.2079, "step": 18602 }, { "epoch": 0.5682040317654246, "grad_norm": 0.41153666377067566, "learning_rate": 1.968416299407846e-05, "loss": 4.3585, "step": 18603 }, { "epoch": 0.5682345754428834, "grad_norm": 0.3980960547924042, "learning_rate": 1.9681818981592846e-05, "loss": 4.1843, "step": 18604 }, { "epoch": 0.568265119120342, "grad_norm": 0.41380998492240906, "learning_rate": 1.9679475018074465e-05, "loss": 4.123, "step": 18605 }, { "epoch": 0.5682956627978009, "grad_norm": 0.41792619228363037, "learning_rate": 1.967713110354489e-05, "loss": 4.2468, "step": 18606 }, { "epoch": 0.5683262064752597, "grad_norm": 0.40624168515205383, "learning_rate": 1.96747872380257e-05, "loss": 4.3654, "step": 18607 }, { "epoch": 0.5683567501527184, "grad_norm": 0.4201704263687134, "learning_rate": 1.967244342153849e-05, "loss": 4.3309, "step": 18608 }, { "epoch": 0.5683872938301772, "grad_norm": 0.3927011489868164, "learning_rate": 1.9670099654104826e-05, "loss": 4.2806, "step": 18609 }, { "epoch": 0.568417837507636, "grad_norm": 0.40951183438301086, "learning_rate": 1.9667755935746294e-05, "loss": 4.3226, "step": 18610 }, { "epoch": 0.5684483811850947, "grad_norm": 0.4085061550140381, "learning_rate": 1.9665412266484483e-05, "loss": 4.271, "step": 18611 }, { "epoch": 0.5684789248625535, "grad_norm": 0.39929598569869995, "learning_rate": 1.966306864634096e-05, "loss": 4.243, "step": 18612 }, { "epoch": 0.5685094685400122, "grad_norm": 0.42178624868392944, "learning_rate": 1.966072507533731e-05, "loss": 4.3212, "step": 18613 }, { "epoch": 0.568540012217471, "grad_norm": 0.4042128324508667, "learning_rate": 1.9658381553495105e-05, "loss": 4.2889, "step": 18614 }, { "epoch": 0.5685705558949298, "grad_norm": 0.4098977744579315, "learning_rate": 1.9656038080835925e-05, "loss": 4.3553, "step": 18615 }, { "epoch": 0.5686010995723885, "grad_norm": 0.39744171500205994, "learning_rate": 1.965369465738136e-05, "loss": 4.3319, "step": 18616 }, { "epoch": 0.5686316432498473, "grad_norm": 0.42821043729782104, "learning_rate": 1.965135128315297e-05, "loss": 4.3619, "step": 18617 }, { "epoch": 0.5686621869273061, "grad_norm": 0.4042018949985504, "learning_rate": 1.9649007958172334e-05, "loss": 4.2594, "step": 18618 }, { "epoch": 0.5686927306047648, "grad_norm": 0.4034062922000885, "learning_rate": 1.9646664682461047e-05, "loss": 4.3623, "step": 18619 }, { "epoch": 0.5687232742822236, "grad_norm": 0.40591564774513245, "learning_rate": 1.9644321456040664e-05, "loss": 4.3009, "step": 18620 }, { "epoch": 0.5687538179596824, "grad_norm": 0.4203260838985443, "learning_rate": 1.964197827893276e-05, "loss": 4.2825, "step": 18621 }, { "epoch": 0.5687843616371411, "grad_norm": 0.41661059856414795, "learning_rate": 1.9639635151158928e-05, "loss": 4.3368, "step": 18622 }, { "epoch": 0.5688149053145999, "grad_norm": 0.4096837341785431, "learning_rate": 1.963729207274072e-05, "loss": 4.2625, "step": 18623 }, { "epoch": 0.5688454489920587, "grad_norm": 0.4064236879348755, "learning_rate": 1.9634949043699725e-05, "loss": 4.2479, "step": 18624 }, { "epoch": 0.5688759926695174, "grad_norm": 0.41388577222824097, "learning_rate": 1.963260606405752e-05, "loss": 4.2896, "step": 18625 }, { "epoch": 0.5689065363469762, "grad_norm": 0.41095975041389465, "learning_rate": 1.9630263133835657e-05, "loss": 4.3139, "step": 18626 }, { "epoch": 0.568937080024435, "grad_norm": 0.4027508795261383, "learning_rate": 1.962792025305573e-05, "loss": 4.2666, "step": 18627 }, { "epoch": 0.5689676237018937, "grad_norm": 0.4110487699508667, "learning_rate": 1.9625577421739305e-05, "loss": 4.3371, "step": 18628 }, { "epoch": 0.5689981673793525, "grad_norm": 0.40832459926605225, "learning_rate": 1.9623234639907952e-05, "loss": 4.2768, "step": 18629 }, { "epoch": 0.5690287110568112, "grad_norm": 0.4055747389793396, "learning_rate": 1.9620891907583246e-05, "loss": 4.31, "step": 18630 }, { "epoch": 0.56905925473427, "grad_norm": 0.40171101689338684, "learning_rate": 1.9618549224786745e-05, "loss": 4.2671, "step": 18631 }, { "epoch": 0.5690897984117288, "grad_norm": 0.3997366726398468, "learning_rate": 1.9616206591540028e-05, "loss": 4.314, "step": 18632 }, { "epoch": 0.5691203420891875, "grad_norm": 0.4054766893386841, "learning_rate": 1.9613864007864674e-05, "loss": 4.2309, "step": 18633 }, { "epoch": 0.5691508857666463, "grad_norm": 0.4110518991947174, "learning_rate": 1.9611521473782232e-05, "loss": 4.3509, "step": 18634 }, { "epoch": 0.5691814294441051, "grad_norm": 0.40999507904052734, "learning_rate": 1.960917898931429e-05, "loss": 4.2788, "step": 18635 }, { "epoch": 0.5692119731215638, "grad_norm": 0.4096200168132782, "learning_rate": 1.960683655448241e-05, "loss": 4.1924, "step": 18636 }, { "epoch": 0.5692425167990226, "grad_norm": 0.39856812357902527, "learning_rate": 1.9604494169308156e-05, "loss": 4.2453, "step": 18637 }, { "epoch": 0.5692730604764814, "grad_norm": 0.3980196714401245, "learning_rate": 1.9602151833813093e-05, "loss": 4.341, "step": 18638 }, { "epoch": 0.5693036041539401, "grad_norm": 0.40434494614601135, "learning_rate": 1.9599809548018804e-05, "loss": 4.2009, "step": 18639 }, { "epoch": 0.5693341478313989, "grad_norm": 0.41942012310028076, "learning_rate": 1.9597467311946832e-05, "loss": 4.252, "step": 18640 }, { "epoch": 0.5693646915088577, "grad_norm": 0.4118083119392395, "learning_rate": 1.959512512561876e-05, "loss": 4.3389, "step": 18641 }, { "epoch": 0.5693952351863164, "grad_norm": 0.40778860449790955, "learning_rate": 1.959278298905616e-05, "loss": 4.2156, "step": 18642 }, { "epoch": 0.5694257788637752, "grad_norm": 0.40850013494491577, "learning_rate": 1.9590440902280584e-05, "loss": 4.22, "step": 18643 }, { "epoch": 0.569456322541234, "grad_norm": 0.4017121493816376, "learning_rate": 1.958809886531359e-05, "loss": 4.3626, "step": 18644 }, { "epoch": 0.5694868662186927, "grad_norm": 0.39925897121429443, "learning_rate": 1.9585756878176764e-05, "loss": 4.0758, "step": 18645 }, { "epoch": 0.5695174098961515, "grad_norm": 0.40798264741897583, "learning_rate": 1.958341494089165e-05, "loss": 4.2285, "step": 18646 }, { "epoch": 0.5695479535736102, "grad_norm": 0.41799426078796387, "learning_rate": 1.9581073053479825e-05, "loss": 4.3763, "step": 18647 }, { "epoch": 0.569578497251069, "grad_norm": 0.41525280475616455, "learning_rate": 1.957873121596284e-05, "loss": 4.275, "step": 18648 }, { "epoch": 0.5696090409285278, "grad_norm": 0.4037061631679535, "learning_rate": 1.9576389428362262e-05, "loss": 4.2343, "step": 18649 }, { "epoch": 0.5696395846059865, "grad_norm": 0.4043390452861786, "learning_rate": 1.9574047690699672e-05, "loss": 4.2825, "step": 18650 }, { "epoch": 0.5696701282834453, "grad_norm": 0.4041483998298645, "learning_rate": 1.9571706002996597e-05, "loss": 4.3117, "step": 18651 }, { "epoch": 0.5697006719609041, "grad_norm": 0.4030652940273285, "learning_rate": 1.956936436527462e-05, "loss": 4.335, "step": 18652 }, { "epoch": 0.5697312156383628, "grad_norm": 0.4038642346858978, "learning_rate": 1.9567022777555308e-05, "loss": 4.2555, "step": 18653 }, { "epoch": 0.5697617593158216, "grad_norm": 0.4172120690345764, "learning_rate": 1.95646812398602e-05, "loss": 4.2521, "step": 18654 }, { "epoch": 0.5697923029932804, "grad_norm": 0.404077410697937, "learning_rate": 1.9562339752210862e-05, "loss": 4.2489, "step": 18655 }, { "epoch": 0.5698228466707391, "grad_norm": 0.3990996479988098, "learning_rate": 1.955999831462887e-05, "loss": 4.2224, "step": 18656 }, { "epoch": 0.5698533903481979, "grad_norm": 0.400882363319397, "learning_rate": 1.9557656927135763e-05, "loss": 4.2529, "step": 18657 }, { "epoch": 0.5698839340256567, "grad_norm": 0.40321019291877747, "learning_rate": 1.955531558975311e-05, "loss": 4.2518, "step": 18658 }, { "epoch": 0.5699144777031154, "grad_norm": 0.4080426096916199, "learning_rate": 1.9552974302502465e-05, "loss": 4.26, "step": 18659 }, { "epoch": 0.5699450213805742, "grad_norm": 0.41626495122909546, "learning_rate": 1.9550633065405386e-05, "loss": 4.298, "step": 18660 }, { "epoch": 0.569975565058033, "grad_norm": 0.4111883044242859, "learning_rate": 1.9548291878483425e-05, "loss": 4.2493, "step": 18661 }, { "epoch": 0.5700061087354917, "grad_norm": 0.411371111869812, "learning_rate": 1.9545950741758155e-05, "loss": 4.2877, "step": 18662 }, { "epoch": 0.5700366524129505, "grad_norm": 0.39656496047973633, "learning_rate": 1.954360965525111e-05, "loss": 4.2259, "step": 18663 }, { "epoch": 0.5700671960904092, "grad_norm": 0.41347190737724304, "learning_rate": 1.9541268618983866e-05, "loss": 4.262, "step": 18664 }, { "epoch": 0.570097739767868, "grad_norm": 0.4047081470489502, "learning_rate": 1.953892763297796e-05, "loss": 4.1894, "step": 18665 }, { "epoch": 0.5701282834453268, "grad_norm": 0.3973439335823059, "learning_rate": 1.9536586697254958e-05, "loss": 4.2428, "step": 18666 }, { "epoch": 0.5701588271227855, "grad_norm": 0.4083559811115265, "learning_rate": 1.9534245811836414e-05, "loss": 4.2761, "step": 18667 }, { "epoch": 0.5701893708002443, "grad_norm": 0.41527247428894043, "learning_rate": 1.9531904976743876e-05, "loss": 4.201, "step": 18668 }, { "epoch": 0.5702199144777031, "grad_norm": 0.4082687199115753, "learning_rate": 1.9529564191998895e-05, "loss": 4.3669, "step": 18669 }, { "epoch": 0.5702504581551618, "grad_norm": 0.4186480641365051, "learning_rate": 1.9527223457623043e-05, "loss": 4.238, "step": 18670 }, { "epoch": 0.5702810018326206, "grad_norm": 0.4054604470729828, "learning_rate": 1.9524882773637845e-05, "loss": 4.2812, "step": 18671 }, { "epoch": 0.5703115455100795, "grad_norm": 0.4137834310531616, "learning_rate": 1.9522542140064866e-05, "loss": 4.3084, "step": 18672 }, { "epoch": 0.5703420891875381, "grad_norm": 0.41538381576538086, "learning_rate": 1.952020155692567e-05, "loss": 4.2386, "step": 18673 }, { "epoch": 0.570372632864997, "grad_norm": 0.4033186137676239, "learning_rate": 1.9517861024241786e-05, "loss": 4.2745, "step": 18674 }, { "epoch": 0.5704031765424558, "grad_norm": 0.4197094440460205, "learning_rate": 1.9515520542034775e-05, "loss": 4.1895, "step": 18675 }, { "epoch": 0.5704337202199145, "grad_norm": 0.41631847620010376, "learning_rate": 1.9513180110326197e-05, "loss": 4.2823, "step": 18676 }, { "epoch": 0.5704642638973733, "grad_norm": 0.4085993766784668, "learning_rate": 1.951083972913758e-05, "loss": 4.1519, "step": 18677 }, { "epoch": 0.5704948075748321, "grad_norm": 0.40901073813438416, "learning_rate": 1.950849939849048e-05, "loss": 4.3016, "step": 18678 }, { "epoch": 0.5705253512522908, "grad_norm": 0.4113316833972931, "learning_rate": 1.9506159118406462e-05, "loss": 4.3496, "step": 18679 }, { "epoch": 0.5705558949297496, "grad_norm": 0.42249876260757446, "learning_rate": 1.9503818888907048e-05, "loss": 4.3064, "step": 18680 }, { "epoch": 0.5705864386072083, "grad_norm": 0.41285303235054016, "learning_rate": 1.9501478710013814e-05, "loss": 4.383, "step": 18681 }, { "epoch": 0.5706169822846671, "grad_norm": 0.4004957675933838, "learning_rate": 1.949913858174828e-05, "loss": 4.3291, "step": 18682 }, { "epoch": 0.5706475259621259, "grad_norm": 0.401711106300354, "learning_rate": 1.949679850413201e-05, "loss": 4.3098, "step": 18683 }, { "epoch": 0.5706780696395846, "grad_norm": 0.3927970826625824, "learning_rate": 1.9494458477186554e-05, "loss": 4.1837, "step": 18684 }, { "epoch": 0.5707086133170434, "grad_norm": 0.40106189250946045, "learning_rate": 1.9492118500933437e-05, "loss": 4.2786, "step": 18685 }, { "epoch": 0.5707391569945022, "grad_norm": 0.40353628993034363, "learning_rate": 1.948977857539422e-05, "loss": 4.3849, "step": 18686 }, { "epoch": 0.5707697006719609, "grad_norm": 0.4172646403312683, "learning_rate": 1.948743870059045e-05, "loss": 4.2608, "step": 18687 }, { "epoch": 0.5708002443494197, "grad_norm": 0.4046993553638458, "learning_rate": 1.948509887654366e-05, "loss": 4.327, "step": 18688 }, { "epoch": 0.5708307880268785, "grad_norm": 0.4097272753715515, "learning_rate": 1.94827591032754e-05, "loss": 4.2971, "step": 18689 }, { "epoch": 0.5708613317043372, "grad_norm": 0.42064645886421204, "learning_rate": 1.948041938080722e-05, "loss": 4.3718, "step": 18690 }, { "epoch": 0.570891875381796, "grad_norm": 0.4120575487613678, "learning_rate": 1.947807970916065e-05, "loss": 4.2753, "step": 18691 }, { "epoch": 0.5709224190592548, "grad_norm": 0.4183921813964844, "learning_rate": 1.947574008835724e-05, "loss": 4.3023, "step": 18692 }, { "epoch": 0.5709529627367135, "grad_norm": 0.4309093654155731, "learning_rate": 1.947340051841854e-05, "loss": 4.242, "step": 18693 }, { "epoch": 0.5709835064141723, "grad_norm": 0.42462262511253357, "learning_rate": 1.947106099936607e-05, "loss": 4.3164, "step": 18694 }, { "epoch": 0.5710140500916311, "grad_norm": 0.4010990560054779, "learning_rate": 1.9468721531221385e-05, "loss": 4.2972, "step": 18695 }, { "epoch": 0.5710445937690898, "grad_norm": 0.4093201756477356, "learning_rate": 1.9466382114006038e-05, "loss": 4.3259, "step": 18696 }, { "epoch": 0.5710751374465486, "grad_norm": 0.41229304671287537, "learning_rate": 1.9464042747741543e-05, "loss": 4.3152, "step": 18697 }, { "epoch": 0.5711056811240073, "grad_norm": 0.4046492874622345, "learning_rate": 1.9461703432449465e-05, "loss": 4.2956, "step": 18698 }, { "epoch": 0.5711362248014661, "grad_norm": 0.4217342138290405, "learning_rate": 1.9459364168151324e-05, "loss": 4.2684, "step": 18699 }, { "epoch": 0.5711667684789249, "grad_norm": 0.4156203269958496, "learning_rate": 1.945702495486866e-05, "loss": 4.3252, "step": 18700 }, { "epoch": 0.5711973121563836, "grad_norm": 0.40335792303085327, "learning_rate": 1.9454685792623028e-05, "loss": 4.2844, "step": 18701 }, { "epoch": 0.5712278558338424, "grad_norm": 0.39609968662261963, "learning_rate": 1.9452346681435945e-05, "loss": 4.2839, "step": 18702 }, { "epoch": 0.5712583995113012, "grad_norm": 0.39847052097320557, "learning_rate": 1.9450007621328958e-05, "loss": 4.269, "step": 18703 }, { "epoch": 0.5712889431887599, "grad_norm": 0.39764708280563354, "learning_rate": 1.9447668612323617e-05, "loss": 4.3323, "step": 18704 }, { "epoch": 0.5713194868662187, "grad_norm": 0.40214574337005615, "learning_rate": 1.9445329654441434e-05, "loss": 4.3238, "step": 18705 }, { "epoch": 0.5713500305436775, "grad_norm": 0.4000249207019806, "learning_rate": 1.944299074770396e-05, "loss": 4.3087, "step": 18706 }, { "epoch": 0.5713805742211362, "grad_norm": 0.40230268239974976, "learning_rate": 1.944065189213274e-05, "loss": 4.3166, "step": 18707 }, { "epoch": 0.571411117898595, "grad_norm": 0.406185507774353, "learning_rate": 1.9438313087749278e-05, "loss": 4.2162, "step": 18708 }, { "epoch": 0.5714416615760538, "grad_norm": 0.4037574529647827, "learning_rate": 1.943597433457513e-05, "loss": 4.2801, "step": 18709 }, { "epoch": 0.5714722052535125, "grad_norm": 0.4093983769416809, "learning_rate": 1.9433635632631834e-05, "loss": 4.3071, "step": 18710 }, { "epoch": 0.5715027489309713, "grad_norm": 0.41318395733833313, "learning_rate": 1.9431296981940912e-05, "loss": 4.2322, "step": 18711 }, { "epoch": 0.5715332926084301, "grad_norm": 0.402256041765213, "learning_rate": 1.9428958382523902e-05, "loss": 4.4522, "step": 18712 }, { "epoch": 0.5715638362858888, "grad_norm": 0.4081309735774994, "learning_rate": 1.9426619834402337e-05, "loss": 4.2757, "step": 18713 }, { "epoch": 0.5715943799633476, "grad_norm": 0.40463849902153015, "learning_rate": 1.9424281337597752e-05, "loss": 4.1762, "step": 18714 }, { "epoch": 0.5716249236408063, "grad_norm": 0.4063279330730438, "learning_rate": 1.942194289213167e-05, "loss": 4.3382, "step": 18715 }, { "epoch": 0.5716554673182651, "grad_norm": 0.4135722815990448, "learning_rate": 1.9419604498025636e-05, "loss": 4.1529, "step": 18716 }, { "epoch": 0.5716860109957239, "grad_norm": 0.4078684151172638, "learning_rate": 1.941726615530116e-05, "loss": 4.2663, "step": 18717 }, { "epoch": 0.5717165546731826, "grad_norm": 0.4063945412635803, "learning_rate": 1.94149278639798e-05, "loss": 4.3085, "step": 18718 }, { "epoch": 0.5717470983506414, "grad_norm": 0.41095271706581116, "learning_rate": 1.941258962408306e-05, "loss": 4.254, "step": 18719 }, { "epoch": 0.5717776420281002, "grad_norm": 0.4124815762042999, "learning_rate": 1.9410251435632476e-05, "loss": 4.2399, "step": 18720 }, { "epoch": 0.5718081857055589, "grad_norm": 0.40705808997154236, "learning_rate": 1.9407913298649597e-05, "loss": 4.2682, "step": 18721 }, { "epoch": 0.5718387293830177, "grad_norm": 0.4018859565258026, "learning_rate": 1.9405575213155927e-05, "loss": 4.3626, "step": 18722 }, { "epoch": 0.5718692730604765, "grad_norm": 0.3953850567340851, "learning_rate": 1.9403237179172997e-05, "loss": 4.2604, "step": 18723 }, { "epoch": 0.5718998167379352, "grad_norm": 0.4052194356918335, "learning_rate": 1.9400899196722348e-05, "loss": 4.3123, "step": 18724 }, { "epoch": 0.571930360415394, "grad_norm": 0.42098328471183777, "learning_rate": 1.9398561265825493e-05, "loss": 4.2738, "step": 18725 }, { "epoch": 0.5719609040928528, "grad_norm": 0.40651795268058777, "learning_rate": 1.939622338650396e-05, "loss": 4.2967, "step": 18726 }, { "epoch": 0.5719914477703115, "grad_norm": 0.40545424818992615, "learning_rate": 1.9393885558779297e-05, "loss": 4.3455, "step": 18727 }, { "epoch": 0.5720219914477703, "grad_norm": 0.41443753242492676, "learning_rate": 1.9391547782672996e-05, "loss": 4.336, "step": 18728 }, { "epoch": 0.572052535125229, "grad_norm": 0.4011746942996979, "learning_rate": 1.9389210058206608e-05, "loss": 4.3296, "step": 18729 }, { "epoch": 0.5720830788026878, "grad_norm": 0.40257808566093445, "learning_rate": 1.9386872385401643e-05, "loss": 4.2695, "step": 18730 }, { "epoch": 0.5721136224801466, "grad_norm": 0.425727516412735, "learning_rate": 1.9384534764279628e-05, "loss": 4.3275, "step": 18731 }, { "epoch": 0.5721441661576053, "grad_norm": 0.4050522446632385, "learning_rate": 1.9382197194862095e-05, "loss": 4.3502, "step": 18732 }, { "epoch": 0.5721747098350641, "grad_norm": 0.401309609413147, "learning_rate": 1.9379859677170554e-05, "loss": 4.2284, "step": 18733 }, { "epoch": 0.5722052535125229, "grad_norm": 0.40382641553878784, "learning_rate": 1.9377522211226533e-05, "loss": 4.2568, "step": 18734 }, { "epoch": 0.5722357971899816, "grad_norm": 0.40944185853004456, "learning_rate": 1.9375184797051566e-05, "loss": 4.2579, "step": 18735 }, { "epoch": 0.5722663408674404, "grad_norm": 0.4032996892929077, "learning_rate": 1.9372847434667155e-05, "loss": 4.3596, "step": 18736 }, { "epoch": 0.5722968845448992, "grad_norm": 0.41655346751213074, "learning_rate": 1.9370510124094834e-05, "loss": 4.2554, "step": 18737 }, { "epoch": 0.5723274282223579, "grad_norm": 0.4154263436794281, "learning_rate": 1.9368172865356122e-05, "loss": 4.3273, "step": 18738 }, { "epoch": 0.5723579718998167, "grad_norm": 0.4127860367298126, "learning_rate": 1.9365835658472537e-05, "loss": 4.3312, "step": 18739 }, { "epoch": 0.5723885155772755, "grad_norm": 0.4055713713169098, "learning_rate": 1.9363498503465596e-05, "loss": 4.3456, "step": 18740 }, { "epoch": 0.5724190592547342, "grad_norm": 0.41785281896591187, "learning_rate": 1.9361161400356835e-05, "loss": 4.2906, "step": 18741 }, { "epoch": 0.572449602932193, "grad_norm": 0.4065609574317932, "learning_rate": 1.9358824349167744e-05, "loss": 4.282, "step": 18742 }, { "epoch": 0.5724801466096519, "grad_norm": 0.41392603516578674, "learning_rate": 1.9356487349919862e-05, "loss": 4.3302, "step": 18743 }, { "epoch": 0.5725106902871105, "grad_norm": 0.4112754762172699, "learning_rate": 1.9354150402634714e-05, "loss": 4.3473, "step": 18744 }, { "epoch": 0.5725412339645694, "grad_norm": 0.41786015033721924, "learning_rate": 1.9351813507333798e-05, "loss": 4.2911, "step": 18745 }, { "epoch": 0.572571777642028, "grad_norm": 0.39421921968460083, "learning_rate": 1.9349476664038637e-05, "loss": 4.2739, "step": 18746 }, { "epoch": 0.5726023213194869, "grad_norm": 0.40615078806877136, "learning_rate": 1.9347139872770755e-05, "loss": 4.2744, "step": 18747 }, { "epoch": 0.5726328649969457, "grad_norm": 0.40425905585289, "learning_rate": 1.9344803133551654e-05, "loss": 4.3216, "step": 18748 }, { "epoch": 0.5726634086744044, "grad_norm": 0.42508020997047424, "learning_rate": 1.9342466446402867e-05, "loss": 4.3664, "step": 18749 }, { "epoch": 0.5726939523518632, "grad_norm": 0.41375353932380676, "learning_rate": 1.934012981134589e-05, "loss": 4.3299, "step": 18750 }, { "epoch": 0.572724496029322, "grad_norm": 0.40014466643333435, "learning_rate": 1.9337793228402252e-05, "loss": 4.2753, "step": 18751 }, { "epoch": 0.5727550397067807, "grad_norm": 0.43621549010276794, "learning_rate": 1.933545669759347e-05, "loss": 4.3421, "step": 18752 }, { "epoch": 0.5727855833842395, "grad_norm": 0.40764039754867554, "learning_rate": 1.9333120218941047e-05, "loss": 4.2736, "step": 18753 }, { "epoch": 0.5728161270616983, "grad_norm": 0.4048648774623871, "learning_rate": 1.9330783792466493e-05, "loss": 4.2357, "step": 18754 }, { "epoch": 0.572846670739157, "grad_norm": 0.42347684502601624, "learning_rate": 1.932844741819134e-05, "loss": 4.2706, "step": 18755 }, { "epoch": 0.5728772144166158, "grad_norm": 0.4112595319747925, "learning_rate": 1.932611109613708e-05, "loss": 4.2808, "step": 18756 }, { "epoch": 0.5729077580940746, "grad_norm": 0.4121232330799103, "learning_rate": 1.9323774826325226e-05, "loss": 4.2644, "step": 18757 }, { "epoch": 0.5729383017715333, "grad_norm": 0.3998022675514221, "learning_rate": 1.932143860877731e-05, "loss": 4.3591, "step": 18758 }, { "epoch": 0.5729688454489921, "grad_norm": 0.41270124912261963, "learning_rate": 1.9319102443514818e-05, "loss": 4.3529, "step": 18759 }, { "epoch": 0.5729993891264509, "grad_norm": 0.4034897983074188, "learning_rate": 1.931676633055927e-05, "loss": 4.3158, "step": 18760 }, { "epoch": 0.5730299328039096, "grad_norm": 0.40399911999702454, "learning_rate": 1.9314430269932183e-05, "loss": 4.3326, "step": 18761 }, { "epoch": 0.5730604764813684, "grad_norm": 0.3990517258644104, "learning_rate": 1.9312094261655055e-05, "loss": 4.3084, "step": 18762 }, { "epoch": 0.5730910201588271, "grad_norm": 0.4178944230079651, "learning_rate": 1.9309758305749408e-05, "loss": 4.3507, "step": 18763 }, { "epoch": 0.5731215638362859, "grad_norm": 0.4118480980396271, "learning_rate": 1.9307422402236734e-05, "loss": 4.2319, "step": 18764 }, { "epoch": 0.5731521075137447, "grad_norm": 0.4034946858882904, "learning_rate": 1.9305086551138546e-05, "loss": 4.3167, "step": 18765 }, { "epoch": 0.5731826511912034, "grad_norm": 0.4017924964427948, "learning_rate": 1.9302750752476363e-05, "loss": 4.3872, "step": 18766 }, { "epoch": 0.5732131948686622, "grad_norm": 0.40264248847961426, "learning_rate": 1.9300415006271676e-05, "loss": 4.3214, "step": 18767 }, { "epoch": 0.573243738546121, "grad_norm": 0.4185369610786438, "learning_rate": 1.9298079312546e-05, "loss": 4.2834, "step": 18768 }, { "epoch": 0.5732742822235797, "grad_norm": 0.4208921194076538, "learning_rate": 1.929574367132084e-05, "loss": 4.2716, "step": 18769 }, { "epoch": 0.5733048259010385, "grad_norm": 0.4117700457572937, "learning_rate": 1.9293408082617702e-05, "loss": 4.3073, "step": 18770 }, { "epoch": 0.5733353695784973, "grad_norm": 0.4001065194606781, "learning_rate": 1.9291072546458084e-05, "loss": 4.3288, "step": 18771 }, { "epoch": 0.573365913255956, "grad_norm": 0.4162059724330902, "learning_rate": 1.9288737062863507e-05, "loss": 4.2284, "step": 18772 }, { "epoch": 0.5733964569334148, "grad_norm": 0.41298866271972656, "learning_rate": 1.9286401631855457e-05, "loss": 4.3153, "step": 18773 }, { "epoch": 0.5734270006108736, "grad_norm": 0.4092593193054199, "learning_rate": 1.928406625345544e-05, "loss": 4.2471, "step": 18774 }, { "epoch": 0.5734575442883323, "grad_norm": 0.41032591462135315, "learning_rate": 1.9281730927684976e-05, "loss": 4.3339, "step": 18775 }, { "epoch": 0.5734880879657911, "grad_norm": 0.4115365743637085, "learning_rate": 1.927939565456555e-05, "loss": 4.1554, "step": 18776 }, { "epoch": 0.5735186316432499, "grad_norm": 0.4037311375141144, "learning_rate": 1.9277060434118666e-05, "loss": 4.149, "step": 18777 }, { "epoch": 0.5735491753207086, "grad_norm": 0.4098159074783325, "learning_rate": 1.9274725266365836e-05, "loss": 4.3055, "step": 18778 }, { "epoch": 0.5735797189981674, "grad_norm": 0.40406811237335205, "learning_rate": 1.9272390151328546e-05, "loss": 4.2908, "step": 18779 }, { "epoch": 0.5736102626756261, "grad_norm": 0.4148555099964142, "learning_rate": 1.9270055089028317e-05, "loss": 4.2892, "step": 18780 }, { "epoch": 0.5736408063530849, "grad_norm": 0.4059417247772217, "learning_rate": 1.9267720079486622e-05, "loss": 4.2937, "step": 18781 }, { "epoch": 0.5736713500305437, "grad_norm": 0.41839367151260376, "learning_rate": 1.9265385122724977e-05, "loss": 4.2518, "step": 18782 }, { "epoch": 0.5737018937080024, "grad_norm": 0.405333548784256, "learning_rate": 1.9263050218764892e-05, "loss": 4.2975, "step": 18783 }, { "epoch": 0.5737324373854612, "grad_norm": 0.4048703610897064, "learning_rate": 1.926071536762784e-05, "loss": 4.3179, "step": 18784 }, { "epoch": 0.57376298106292, "grad_norm": 0.4376685321331024, "learning_rate": 1.925838056933534e-05, "loss": 4.1943, "step": 18785 }, { "epoch": 0.5737935247403787, "grad_norm": 0.4082486927509308, "learning_rate": 1.9256045823908887e-05, "loss": 4.1864, "step": 18786 }, { "epoch": 0.5738240684178375, "grad_norm": 0.4098513126373291, "learning_rate": 1.925371113136996e-05, "loss": 4.2675, "step": 18787 }, { "epoch": 0.5738546120952963, "grad_norm": 0.40574777126312256, "learning_rate": 1.9251376491740076e-05, "loss": 4.2844, "step": 18788 }, { "epoch": 0.573885155772755, "grad_norm": 0.3956936001777649, "learning_rate": 1.9249041905040725e-05, "loss": 4.2383, "step": 18789 }, { "epoch": 0.5739156994502138, "grad_norm": 0.4071781039237976, "learning_rate": 1.9246707371293398e-05, "loss": 4.2294, "step": 18790 }, { "epoch": 0.5739462431276726, "grad_norm": 0.4181385338306427, "learning_rate": 1.9244372890519604e-05, "loss": 4.2218, "step": 18791 }, { "epoch": 0.5739767868051313, "grad_norm": 0.4217166006565094, "learning_rate": 1.9242038462740818e-05, "loss": 4.3014, "step": 18792 }, { "epoch": 0.5740073304825901, "grad_norm": 0.4072813093662262, "learning_rate": 1.923970408797855e-05, "loss": 4.2773, "step": 18793 }, { "epoch": 0.5740378741600489, "grad_norm": 0.41140246391296387, "learning_rate": 1.9237369766254283e-05, "loss": 4.2396, "step": 18794 }, { "epoch": 0.5740684178375076, "grad_norm": 0.40153968334198, "learning_rate": 1.9235035497589522e-05, "loss": 4.2523, "step": 18795 }, { "epoch": 0.5740989615149664, "grad_norm": 0.4105651378631592, "learning_rate": 1.9232701282005748e-05, "loss": 4.2573, "step": 18796 }, { "epoch": 0.5741295051924251, "grad_norm": 0.40792229771614075, "learning_rate": 1.9230367119524465e-05, "loss": 4.2491, "step": 18797 }, { "epoch": 0.5741600488698839, "grad_norm": 0.42406925559043884, "learning_rate": 1.922803301016715e-05, "loss": 4.3294, "step": 18798 }, { "epoch": 0.5741905925473427, "grad_norm": 0.4399218261241913, "learning_rate": 1.9225698953955308e-05, "loss": 4.3394, "step": 18799 }, { "epoch": 0.5742211362248014, "grad_norm": 0.40977370738983154, "learning_rate": 1.9223364950910423e-05, "loss": 4.3162, "step": 18800 }, { "epoch": 0.5742516799022602, "grad_norm": 0.4129740297794342, "learning_rate": 1.9221031001053986e-05, "loss": 4.24, "step": 18801 }, { "epoch": 0.574282223579719, "grad_norm": 0.4090502858161926, "learning_rate": 1.9218697104407485e-05, "loss": 4.2486, "step": 18802 }, { "epoch": 0.5743127672571777, "grad_norm": 0.40416595339775085, "learning_rate": 1.921636326099242e-05, "loss": 4.2758, "step": 18803 }, { "epoch": 0.5743433109346365, "grad_norm": 0.41114938259124756, "learning_rate": 1.9214029470830266e-05, "loss": 4.2006, "step": 18804 }, { "epoch": 0.5743738546120953, "grad_norm": 0.4130377173423767, "learning_rate": 1.9211695733942513e-05, "loss": 4.2271, "step": 18805 }, { "epoch": 0.574404398289554, "grad_norm": 0.41489070653915405, "learning_rate": 1.920936205035067e-05, "loss": 4.1769, "step": 18806 }, { "epoch": 0.5744349419670128, "grad_norm": 0.4139387011528015, "learning_rate": 1.920702842007619e-05, "loss": 4.3181, "step": 18807 }, { "epoch": 0.5744654856444716, "grad_norm": 0.4088250398635864, "learning_rate": 1.9204694843140586e-05, "loss": 4.3629, "step": 18808 }, { "epoch": 0.5744960293219303, "grad_norm": 0.42045164108276367, "learning_rate": 1.9202361319565342e-05, "loss": 4.3792, "step": 18809 }, { "epoch": 0.5745265729993891, "grad_norm": 0.4212080240249634, "learning_rate": 1.920002784937193e-05, "loss": 4.2771, "step": 18810 }, { "epoch": 0.574557116676848, "grad_norm": 0.4035055935382843, "learning_rate": 1.919769443258184e-05, "loss": 4.254, "step": 18811 }, { "epoch": 0.5745876603543066, "grad_norm": 0.40921327471733093, "learning_rate": 1.919536106921657e-05, "loss": 4.2845, "step": 18812 }, { "epoch": 0.5746182040317654, "grad_norm": 0.40613067150115967, "learning_rate": 1.9193027759297588e-05, "loss": 4.215, "step": 18813 }, { "epoch": 0.5746487477092241, "grad_norm": 0.4118572175502777, "learning_rate": 1.9190694502846397e-05, "loss": 4.3111, "step": 18814 }, { "epoch": 0.5746792913866829, "grad_norm": 0.4176383316516876, "learning_rate": 1.9188361299884457e-05, "loss": 4.1455, "step": 18815 }, { "epoch": 0.5747098350641417, "grad_norm": 0.42027273774147034, "learning_rate": 1.9186028150433267e-05, "loss": 4.1934, "step": 18816 }, { "epoch": 0.5747403787416004, "grad_norm": 0.41070881485939026, "learning_rate": 1.918369505451431e-05, "loss": 4.2821, "step": 18817 }, { "epoch": 0.5747709224190592, "grad_norm": 0.40487557649612427, "learning_rate": 1.918136201214905e-05, "loss": 4.1696, "step": 18818 }, { "epoch": 0.574801466096518, "grad_norm": 0.40264618396759033, "learning_rate": 1.9179029023358983e-05, "loss": 4.3081, "step": 18819 }, { "epoch": 0.5748320097739767, "grad_norm": 0.42019936442375183, "learning_rate": 1.91766960881656e-05, "loss": 4.2986, "step": 18820 }, { "epoch": 0.5748625534514356, "grad_norm": 0.4152611792087555, "learning_rate": 1.917436320659036e-05, "loss": 4.2767, "step": 18821 }, { "epoch": 0.5748930971288944, "grad_norm": 0.40201616287231445, "learning_rate": 1.917203037865476e-05, "loss": 4.2285, "step": 18822 }, { "epoch": 0.574923640806353, "grad_norm": 0.4268544614315033, "learning_rate": 1.9169697604380267e-05, "loss": 4.274, "step": 18823 }, { "epoch": 0.5749541844838119, "grad_norm": 0.4097439646720886, "learning_rate": 1.916736488378837e-05, "loss": 4.2539, "step": 18824 }, { "epoch": 0.5749847281612707, "grad_norm": 0.4183792173862457, "learning_rate": 1.916503221690054e-05, "loss": 4.3147, "step": 18825 }, { "epoch": 0.5750152718387294, "grad_norm": 0.41148024797439575, "learning_rate": 1.9162699603738267e-05, "loss": 4.281, "step": 18826 }, { "epoch": 0.5750458155161882, "grad_norm": 0.4086368978023529, "learning_rate": 1.9160367044323008e-05, "loss": 4.3125, "step": 18827 }, { "epoch": 0.575076359193647, "grad_norm": 0.40642404556274414, "learning_rate": 1.9158034538676252e-05, "loss": 4.2928, "step": 18828 }, { "epoch": 0.5751069028711057, "grad_norm": 0.401019811630249, "learning_rate": 1.9155702086819487e-05, "loss": 4.2607, "step": 18829 }, { "epoch": 0.5751374465485645, "grad_norm": 0.4176531732082367, "learning_rate": 1.915336968877417e-05, "loss": 4.3046, "step": 18830 }, { "epoch": 0.5751679902260232, "grad_norm": 0.4280518591403961, "learning_rate": 1.9151037344561793e-05, "loss": 4.2145, "step": 18831 }, { "epoch": 0.575198533903482, "grad_norm": 0.4064413011074066, "learning_rate": 1.9148705054203816e-05, "loss": 4.1224, "step": 18832 }, { "epoch": 0.5752290775809408, "grad_norm": 0.4135831594467163, "learning_rate": 1.9146372817721718e-05, "loss": 4.1465, "step": 18833 }, { "epoch": 0.5752596212583995, "grad_norm": 0.4108319878578186, "learning_rate": 1.914404063513698e-05, "loss": 4.2634, "step": 18834 }, { "epoch": 0.5752901649358583, "grad_norm": 0.4165457487106323, "learning_rate": 1.9141708506471064e-05, "loss": 4.2342, "step": 18835 }, { "epoch": 0.5753207086133171, "grad_norm": 0.409016877412796, "learning_rate": 1.913937643174545e-05, "loss": 4.2496, "step": 18836 }, { "epoch": 0.5753512522907758, "grad_norm": 0.41714757680892944, "learning_rate": 1.913704441098162e-05, "loss": 4.2495, "step": 18837 }, { "epoch": 0.5753817959682346, "grad_norm": 0.4100281894207001, "learning_rate": 1.9134712444201026e-05, "loss": 4.359, "step": 18838 }, { "epoch": 0.5754123396456934, "grad_norm": 0.40373948216438293, "learning_rate": 1.9132380531425153e-05, "loss": 4.2798, "step": 18839 }, { "epoch": 0.5754428833231521, "grad_norm": 0.40719306468963623, "learning_rate": 1.9130048672675477e-05, "loss": 4.3066, "step": 18840 }, { "epoch": 0.5754734270006109, "grad_norm": 0.41477876901626587, "learning_rate": 1.9127716867973452e-05, "loss": 4.3153, "step": 18841 }, { "epoch": 0.5755039706780697, "grad_norm": 0.41941770911216736, "learning_rate": 1.9125385117340556e-05, "loss": 4.2886, "step": 18842 }, { "epoch": 0.5755345143555284, "grad_norm": 0.41893285512924194, "learning_rate": 1.912305342079827e-05, "loss": 4.3204, "step": 18843 }, { "epoch": 0.5755650580329872, "grad_norm": 0.40842241048812866, "learning_rate": 1.912072177836804e-05, "loss": 4.363, "step": 18844 }, { "epoch": 0.575595601710446, "grad_norm": 0.422360360622406, "learning_rate": 1.9118390190071357e-05, "loss": 4.2826, "step": 18845 }, { "epoch": 0.5756261453879047, "grad_norm": 0.3970910310745239, "learning_rate": 1.9116058655929677e-05, "loss": 4.2768, "step": 18846 }, { "epoch": 0.5756566890653635, "grad_norm": 0.4015195965766907, "learning_rate": 1.9113727175964468e-05, "loss": 4.3926, "step": 18847 }, { "epoch": 0.5756872327428222, "grad_norm": 0.4081462323665619, "learning_rate": 1.9111395750197204e-05, "loss": 4.3806, "step": 18848 }, { "epoch": 0.575717776420281, "grad_norm": 0.4075891673564911, "learning_rate": 1.910906437864934e-05, "loss": 4.3182, "step": 18849 }, { "epoch": 0.5757483200977398, "grad_norm": 0.4128127098083496, "learning_rate": 1.910673306134235e-05, "loss": 4.2892, "step": 18850 }, { "epoch": 0.5757788637751985, "grad_norm": 0.39654049277305603, "learning_rate": 1.910440179829771e-05, "loss": 4.3324, "step": 18851 }, { "epoch": 0.5758094074526573, "grad_norm": 0.42327478528022766, "learning_rate": 1.910207058953686e-05, "loss": 4.2982, "step": 18852 }, { "epoch": 0.5758399511301161, "grad_norm": 0.40901923179626465, "learning_rate": 1.9099739435081275e-05, "loss": 4.3037, "step": 18853 }, { "epoch": 0.5758704948075748, "grad_norm": 0.3998510241508484, "learning_rate": 1.909740833495244e-05, "loss": 4.2475, "step": 18854 }, { "epoch": 0.5759010384850336, "grad_norm": 0.4086066782474518, "learning_rate": 1.9095077289171793e-05, "loss": 4.3089, "step": 18855 }, { "epoch": 0.5759315821624924, "grad_norm": 0.40707895159721375, "learning_rate": 1.9092746297760802e-05, "loss": 4.2623, "step": 18856 }, { "epoch": 0.5759621258399511, "grad_norm": 0.40040841698646545, "learning_rate": 1.9090415360740945e-05, "loss": 4.1303, "step": 18857 }, { "epoch": 0.5759926695174099, "grad_norm": 0.41308197379112244, "learning_rate": 1.9088084478133657e-05, "loss": 4.2734, "step": 18858 }, { "epoch": 0.5760232131948687, "grad_norm": 0.4024352431297302, "learning_rate": 1.9085753649960413e-05, "loss": 4.1887, "step": 18859 }, { "epoch": 0.5760537568723274, "grad_norm": 0.42172643542289734, "learning_rate": 1.9083422876242693e-05, "loss": 4.3284, "step": 18860 }, { "epoch": 0.5760843005497862, "grad_norm": 0.3997439444065094, "learning_rate": 1.9081092157001925e-05, "loss": 4.2837, "step": 18861 }, { "epoch": 0.576114844227245, "grad_norm": 0.40040817856788635, "learning_rate": 1.9078761492259595e-05, "loss": 4.3011, "step": 18862 }, { "epoch": 0.5761453879047037, "grad_norm": 0.41141289472579956, "learning_rate": 1.9076430882037154e-05, "loss": 4.257, "step": 18863 }, { "epoch": 0.5761759315821625, "grad_norm": 0.41326525807380676, "learning_rate": 1.907410032635605e-05, "loss": 4.3354, "step": 18864 }, { "epoch": 0.5762064752596212, "grad_norm": 0.4025871753692627, "learning_rate": 1.907176982523776e-05, "loss": 4.2452, "step": 18865 }, { "epoch": 0.57623701893708, "grad_norm": 0.41394445300102234, "learning_rate": 1.9069439378703725e-05, "loss": 4.3124, "step": 18866 }, { "epoch": 0.5762675626145388, "grad_norm": 0.4119683802127838, "learning_rate": 1.9067108986775407e-05, "loss": 4.3115, "step": 18867 }, { "epoch": 0.5762981062919975, "grad_norm": 0.40753477811813354, "learning_rate": 1.9064778649474283e-05, "loss": 4.3223, "step": 18868 }, { "epoch": 0.5763286499694563, "grad_norm": 0.40637874603271484, "learning_rate": 1.906244836682178e-05, "loss": 4.3013, "step": 18869 }, { "epoch": 0.5763591936469151, "grad_norm": 0.393679678440094, "learning_rate": 1.9060118138839373e-05, "loss": 4.2911, "step": 18870 }, { "epoch": 0.5763897373243738, "grad_norm": 0.39813897013664246, "learning_rate": 1.9057787965548513e-05, "loss": 4.3645, "step": 18871 }, { "epoch": 0.5764202810018326, "grad_norm": 0.41032373905181885, "learning_rate": 1.9055457846970653e-05, "loss": 4.2577, "step": 18872 }, { "epoch": 0.5764508246792914, "grad_norm": 0.4184574782848358, "learning_rate": 1.9053127783127245e-05, "loss": 4.2215, "step": 18873 }, { "epoch": 0.5764813683567501, "grad_norm": 0.4099454879760742, "learning_rate": 1.9050797774039757e-05, "loss": 4.3493, "step": 18874 }, { "epoch": 0.5765119120342089, "grad_norm": 0.4007128179073334, "learning_rate": 1.9048467819729625e-05, "loss": 4.2414, "step": 18875 }, { "epoch": 0.5765424557116677, "grad_norm": 0.40993478894233704, "learning_rate": 1.9046137920218303e-05, "loss": 4.3238, "step": 18876 }, { "epoch": 0.5765729993891264, "grad_norm": 0.4250096082687378, "learning_rate": 1.904380807552727e-05, "loss": 4.3228, "step": 18877 }, { "epoch": 0.5766035430665852, "grad_norm": 0.4075644612312317, "learning_rate": 1.9041478285677945e-05, "loss": 4.2582, "step": 18878 }, { "epoch": 0.5766340867440439, "grad_norm": 0.40980690717697144, "learning_rate": 1.90391485506918e-05, "loss": 4.2079, "step": 18879 }, { "epoch": 0.5766646304215027, "grad_norm": 0.398053377866745, "learning_rate": 1.903681887059027e-05, "loss": 4.2127, "step": 18880 }, { "epoch": 0.5766951740989615, "grad_norm": 0.4214755892753601, "learning_rate": 1.903448924539482e-05, "loss": 4.27, "step": 18881 }, { "epoch": 0.5767257177764202, "grad_norm": 0.408891499042511, "learning_rate": 1.9032159675126897e-05, "loss": 4.2791, "step": 18882 }, { "epoch": 0.576756261453879, "grad_norm": 0.41605812311172485, "learning_rate": 1.902983015980794e-05, "loss": 4.3796, "step": 18883 }, { "epoch": 0.5767868051313378, "grad_norm": 0.4036093056201935, "learning_rate": 1.9027500699459408e-05, "loss": 4.2169, "step": 18884 }, { "epoch": 0.5768173488087965, "grad_norm": 0.412811279296875, "learning_rate": 1.9025171294102758e-05, "loss": 4.2849, "step": 18885 }, { "epoch": 0.5768478924862553, "grad_norm": 0.4110613763332367, "learning_rate": 1.902284194375942e-05, "loss": 4.2433, "step": 18886 }, { "epoch": 0.5768784361637141, "grad_norm": 0.42210862040519714, "learning_rate": 1.9020512648450848e-05, "loss": 4.2526, "step": 18887 }, { "epoch": 0.5769089798411728, "grad_norm": 0.4198777377605438, "learning_rate": 1.9018183408198496e-05, "loss": 4.3445, "step": 18888 }, { "epoch": 0.5769395235186316, "grad_norm": 0.40858763456344604, "learning_rate": 1.9015854223023798e-05, "loss": 4.2369, "step": 18889 }, { "epoch": 0.5769700671960905, "grad_norm": 0.40837082266807556, "learning_rate": 1.9013525092948207e-05, "loss": 4.161, "step": 18890 }, { "epoch": 0.5770006108735491, "grad_norm": 0.4214780032634735, "learning_rate": 1.9011196017993176e-05, "loss": 4.2658, "step": 18891 }, { "epoch": 0.577031154551008, "grad_norm": 0.411300927400589, "learning_rate": 1.9008866998180136e-05, "loss": 4.2318, "step": 18892 }, { "epoch": 0.5770616982284668, "grad_norm": 0.40732237696647644, "learning_rate": 1.900653803353054e-05, "loss": 4.3148, "step": 18893 }, { "epoch": 0.5770922419059255, "grad_norm": 0.40088707208633423, "learning_rate": 1.9004209124065832e-05, "loss": 4.3011, "step": 18894 }, { "epoch": 0.5771227855833843, "grad_norm": 0.4174115061759949, "learning_rate": 1.900188026980745e-05, "loss": 4.3531, "step": 18895 }, { "epoch": 0.577153329260843, "grad_norm": 0.4195736050605774, "learning_rate": 1.899955147077685e-05, "loss": 4.2078, "step": 18896 }, { "epoch": 0.5771838729383018, "grad_norm": 0.41472047567367554, "learning_rate": 1.899722272699545e-05, "loss": 4.3924, "step": 18897 }, { "epoch": 0.5772144166157606, "grad_norm": 0.3945538401603699, "learning_rate": 1.8994894038484712e-05, "loss": 4.2378, "step": 18898 }, { "epoch": 0.5772449602932193, "grad_norm": 0.39578521251678467, "learning_rate": 1.8992565405266077e-05, "loss": 4.2263, "step": 18899 }, { "epoch": 0.5772755039706781, "grad_norm": 0.4131461977958679, "learning_rate": 1.8990236827360975e-05, "loss": 4.3069, "step": 18900 }, { "epoch": 0.5773060476481369, "grad_norm": 0.4146427512168884, "learning_rate": 1.8987908304790854e-05, "loss": 4.2717, "step": 18901 }, { "epoch": 0.5773365913255956, "grad_norm": 0.41886746883392334, "learning_rate": 1.8985579837577155e-05, "loss": 4.3029, "step": 18902 }, { "epoch": 0.5773671350030544, "grad_norm": 0.40747231245040894, "learning_rate": 1.8983251425741315e-05, "loss": 4.3305, "step": 18903 }, { "epoch": 0.5773976786805132, "grad_norm": 0.4054637551307678, "learning_rate": 1.8980923069304764e-05, "loss": 4.2278, "step": 18904 }, { "epoch": 0.5774282223579719, "grad_norm": 0.4088361859321594, "learning_rate": 1.897859476828896e-05, "loss": 4.1893, "step": 18905 }, { "epoch": 0.5774587660354307, "grad_norm": 0.4076113998889923, "learning_rate": 1.897626652271532e-05, "loss": 4.3602, "step": 18906 }, { "epoch": 0.5774893097128895, "grad_norm": 0.4076698422431946, "learning_rate": 1.8973938332605293e-05, "loss": 4.3415, "step": 18907 }, { "epoch": 0.5775198533903482, "grad_norm": 0.4020911157131195, "learning_rate": 1.8971610197980325e-05, "loss": 4.3323, "step": 18908 }, { "epoch": 0.577550397067807, "grad_norm": 0.3947901129722595, "learning_rate": 1.8969282118861835e-05, "loss": 4.173, "step": 18909 }, { "epoch": 0.5775809407452658, "grad_norm": 0.4128442704677582, "learning_rate": 1.8966954095271258e-05, "loss": 4.3377, "step": 18910 }, { "epoch": 0.5776114844227245, "grad_norm": 0.3922027051448822, "learning_rate": 1.896462612723005e-05, "loss": 4.2601, "step": 18911 }, { "epoch": 0.5776420281001833, "grad_norm": 0.41246500611305237, "learning_rate": 1.896229821475962e-05, "loss": 4.2688, "step": 18912 }, { "epoch": 0.577672571777642, "grad_norm": 0.401201456785202, "learning_rate": 1.8959970357881428e-05, "loss": 4.2163, "step": 18913 }, { "epoch": 0.5777031154551008, "grad_norm": 0.4116602838039398, "learning_rate": 1.895764255661688e-05, "loss": 4.2169, "step": 18914 }, { "epoch": 0.5777336591325596, "grad_norm": 0.39867696166038513, "learning_rate": 1.8955314810987422e-05, "loss": 4.2686, "step": 18915 }, { "epoch": 0.5777642028100183, "grad_norm": 0.39605605602264404, "learning_rate": 1.8952987121014504e-05, "loss": 4.3009, "step": 18916 }, { "epoch": 0.5777947464874771, "grad_norm": 0.3983018398284912, "learning_rate": 1.8950659486719534e-05, "loss": 4.2829, "step": 18917 }, { "epoch": 0.5778252901649359, "grad_norm": 0.40428921580314636, "learning_rate": 1.894833190812395e-05, "loss": 4.2522, "step": 18918 }, { "epoch": 0.5778558338423946, "grad_norm": 0.39890721440315247, "learning_rate": 1.8946004385249198e-05, "loss": 4.3635, "step": 18919 }, { "epoch": 0.5778863775198534, "grad_norm": 0.4263395071029663, "learning_rate": 1.894367691811668e-05, "loss": 4.195, "step": 18920 }, { "epoch": 0.5779169211973122, "grad_norm": 0.40794259309768677, "learning_rate": 1.8941349506747847e-05, "loss": 4.1579, "step": 18921 }, { "epoch": 0.5779474648747709, "grad_norm": 0.4010288715362549, "learning_rate": 1.8939022151164132e-05, "loss": 4.2637, "step": 18922 }, { "epoch": 0.5779780085522297, "grad_norm": 0.4074702560901642, "learning_rate": 1.8936694851386945e-05, "loss": 4.3085, "step": 18923 }, { "epoch": 0.5780085522296885, "grad_norm": 0.4125251770019531, "learning_rate": 1.8934367607437734e-05, "loss": 4.174, "step": 18924 }, { "epoch": 0.5780390959071472, "grad_norm": 0.3995441496372223, "learning_rate": 1.8932040419337918e-05, "loss": 4.3169, "step": 18925 }, { "epoch": 0.578069639584606, "grad_norm": 0.40937602519989014, "learning_rate": 1.8929713287108924e-05, "loss": 4.3564, "step": 18926 }, { "epoch": 0.5781001832620648, "grad_norm": 0.4276959300041199, "learning_rate": 1.8927386210772178e-05, "loss": 4.1131, "step": 18927 }, { "epoch": 0.5781307269395235, "grad_norm": 0.4048537015914917, "learning_rate": 1.892505919034912e-05, "loss": 4.2124, "step": 18928 }, { "epoch": 0.5781612706169823, "grad_norm": 0.40047916769981384, "learning_rate": 1.8922732225861154e-05, "loss": 4.2921, "step": 18929 }, { "epoch": 0.578191814294441, "grad_norm": 0.4025689959526062, "learning_rate": 1.8920405317329726e-05, "loss": 4.285, "step": 18930 }, { "epoch": 0.5782223579718998, "grad_norm": 0.428516149520874, "learning_rate": 1.8918078464776242e-05, "loss": 4.3805, "step": 18931 }, { "epoch": 0.5782529016493586, "grad_norm": 0.413015216588974, "learning_rate": 1.8915751668222143e-05, "loss": 4.1512, "step": 18932 }, { "epoch": 0.5782834453268173, "grad_norm": 0.4152609407901764, "learning_rate": 1.8913424927688847e-05, "loss": 4.2017, "step": 18933 }, { "epoch": 0.5783139890042761, "grad_norm": 0.4064081311225891, "learning_rate": 1.891109824319778e-05, "loss": 4.3073, "step": 18934 }, { "epoch": 0.5783445326817349, "grad_norm": 0.41316282749176025, "learning_rate": 1.890877161477035e-05, "loss": 4.3053, "step": 18935 }, { "epoch": 0.5783750763591936, "grad_norm": 0.4146432876586914, "learning_rate": 1.8906445042428005e-05, "loss": 4.2902, "step": 18936 }, { "epoch": 0.5784056200366524, "grad_norm": 0.4043525755405426, "learning_rate": 1.8904118526192144e-05, "loss": 4.3028, "step": 18937 }, { "epoch": 0.5784361637141112, "grad_norm": 0.4157094359397888, "learning_rate": 1.8901792066084197e-05, "loss": 4.2426, "step": 18938 }, { "epoch": 0.5784667073915699, "grad_norm": 0.4130510091781616, "learning_rate": 1.8899465662125596e-05, "loss": 4.2498, "step": 18939 }, { "epoch": 0.5784972510690287, "grad_norm": 0.42442116141319275, "learning_rate": 1.889713931433774e-05, "loss": 4.2847, "step": 18940 }, { "epoch": 0.5785277947464875, "grad_norm": 0.4150886833667755, "learning_rate": 1.889481302274207e-05, "loss": 4.2693, "step": 18941 }, { "epoch": 0.5785583384239462, "grad_norm": 0.4204821288585663, "learning_rate": 1.8892486787359995e-05, "loss": 4.2395, "step": 18942 }, { "epoch": 0.578588882101405, "grad_norm": 0.4152848720550537, "learning_rate": 1.8890160608212924e-05, "loss": 4.3157, "step": 18943 }, { "epoch": 0.5786194257788638, "grad_norm": 0.40426284074783325, "learning_rate": 1.888783448532229e-05, "loss": 4.2793, "step": 18944 }, { "epoch": 0.5786499694563225, "grad_norm": 0.4092729091644287, "learning_rate": 1.8885508418709517e-05, "loss": 4.1468, "step": 18945 }, { "epoch": 0.5786805131337813, "grad_norm": 0.41387736797332764, "learning_rate": 1.8883182408395997e-05, "loss": 4.2549, "step": 18946 }, { "epoch": 0.57871105681124, "grad_norm": 0.4136117100715637, "learning_rate": 1.888085645440317e-05, "loss": 4.3296, "step": 18947 }, { "epoch": 0.5787416004886988, "grad_norm": 0.41018980741500854, "learning_rate": 1.887853055675244e-05, "loss": 4.3089, "step": 18948 }, { "epoch": 0.5787721441661576, "grad_norm": 0.40644893050193787, "learning_rate": 1.8876204715465232e-05, "loss": 4.3478, "step": 18949 }, { "epoch": 0.5788026878436163, "grad_norm": 0.40529343485832214, "learning_rate": 1.8873878930562958e-05, "loss": 4.2641, "step": 18950 }, { "epoch": 0.5788332315210751, "grad_norm": 0.41171693801879883, "learning_rate": 1.887155320206702e-05, "loss": 4.2016, "step": 18951 }, { "epoch": 0.5788637751985339, "grad_norm": 0.41026800870895386, "learning_rate": 1.886922752999884e-05, "loss": 4.2936, "step": 18952 }, { "epoch": 0.5788943188759926, "grad_norm": 0.4080231785774231, "learning_rate": 1.886690191437985e-05, "loss": 4.266, "step": 18953 }, { "epoch": 0.5789248625534514, "grad_norm": 0.4029797315597534, "learning_rate": 1.8864576355231435e-05, "loss": 4.2638, "step": 18954 }, { "epoch": 0.5789554062309102, "grad_norm": 0.4129504859447479, "learning_rate": 1.8862250852575023e-05, "loss": 4.3584, "step": 18955 }, { "epoch": 0.5789859499083689, "grad_norm": 0.4287678301334381, "learning_rate": 1.8859925406432026e-05, "loss": 4.2928, "step": 18956 }, { "epoch": 0.5790164935858277, "grad_norm": 0.40338048338890076, "learning_rate": 1.885760001682385e-05, "loss": 4.2117, "step": 18957 }, { "epoch": 0.5790470372632865, "grad_norm": 0.4139944314956665, "learning_rate": 1.8855274683771905e-05, "loss": 4.2393, "step": 18958 }, { "epoch": 0.5790775809407452, "grad_norm": 0.41318267583847046, "learning_rate": 1.8852949407297617e-05, "loss": 4.2864, "step": 18959 }, { "epoch": 0.579108124618204, "grad_norm": 0.4127398729324341, "learning_rate": 1.885062418742237e-05, "loss": 4.3202, "step": 18960 }, { "epoch": 0.5791386682956629, "grad_norm": 0.41393864154815674, "learning_rate": 1.8848299024167593e-05, "loss": 4.2026, "step": 18961 }, { "epoch": 0.5791692119731215, "grad_norm": 0.4026590585708618, "learning_rate": 1.8845973917554696e-05, "loss": 4.3441, "step": 18962 }, { "epoch": 0.5791997556505804, "grad_norm": 0.4119780957698822, "learning_rate": 1.8843648867605075e-05, "loss": 4.2173, "step": 18963 }, { "epoch": 0.579230299328039, "grad_norm": 0.409589022397995, "learning_rate": 1.884132387434015e-05, "loss": 4.3336, "step": 18964 }, { "epoch": 0.5792608430054978, "grad_norm": 0.40300461649894714, "learning_rate": 1.8838998937781318e-05, "loss": 4.3318, "step": 18965 }, { "epoch": 0.5792913866829567, "grad_norm": 0.4029216468334198, "learning_rate": 1.8836674057949987e-05, "loss": 4.32, "step": 18966 }, { "epoch": 0.5793219303604153, "grad_norm": 0.4028205871582031, "learning_rate": 1.8834349234867577e-05, "loss": 4.2784, "step": 18967 }, { "epoch": 0.5793524740378742, "grad_norm": 0.41041305661201477, "learning_rate": 1.8832024468555473e-05, "loss": 4.2537, "step": 18968 }, { "epoch": 0.579383017715333, "grad_norm": 0.40602245926856995, "learning_rate": 1.8829699759035092e-05, "loss": 4.3412, "step": 18969 }, { "epoch": 0.5794135613927917, "grad_norm": 0.41497161984443665, "learning_rate": 1.8827375106327846e-05, "loss": 4.2079, "step": 18970 }, { "epoch": 0.5794441050702505, "grad_norm": 0.40754127502441406, "learning_rate": 1.8825050510455122e-05, "loss": 4.2919, "step": 18971 }, { "epoch": 0.5794746487477093, "grad_norm": 0.407291442155838, "learning_rate": 1.8822725971438337e-05, "loss": 4.3149, "step": 18972 }, { "epoch": 0.579505192425168, "grad_norm": 0.4138685464859009, "learning_rate": 1.88204014892989e-05, "loss": 4.3266, "step": 18973 }, { "epoch": 0.5795357361026268, "grad_norm": 0.4130098521709442, "learning_rate": 1.8818077064058187e-05, "loss": 4.2594, "step": 18974 }, { "epoch": 0.5795662797800856, "grad_norm": 0.41219156980514526, "learning_rate": 1.881575269573762e-05, "loss": 4.1464, "step": 18975 }, { "epoch": 0.5795968234575443, "grad_norm": 0.41883477568626404, "learning_rate": 1.8813428384358606e-05, "loss": 4.2994, "step": 18976 }, { "epoch": 0.5796273671350031, "grad_norm": 0.42201176285743713, "learning_rate": 1.881110412994253e-05, "loss": 4.3111, "step": 18977 }, { "epoch": 0.5796579108124619, "grad_norm": 0.41629573702812195, "learning_rate": 1.8808779932510794e-05, "loss": 4.2927, "step": 18978 }, { "epoch": 0.5796884544899206, "grad_norm": 0.4159570038318634, "learning_rate": 1.880645579208482e-05, "loss": 4.2533, "step": 18979 }, { "epoch": 0.5797189981673794, "grad_norm": 0.4043563902378082, "learning_rate": 1.880413170868599e-05, "loss": 4.2583, "step": 18980 }, { "epoch": 0.5797495418448381, "grad_norm": 0.4121628403663635, "learning_rate": 1.8801807682335698e-05, "loss": 4.3593, "step": 18981 }, { "epoch": 0.5797800855222969, "grad_norm": 0.42068806290626526, "learning_rate": 1.8799483713055356e-05, "loss": 4.3711, "step": 18982 }, { "epoch": 0.5798106291997557, "grad_norm": 0.41277655959129333, "learning_rate": 1.8797159800866346e-05, "loss": 4.2793, "step": 18983 }, { "epoch": 0.5798411728772144, "grad_norm": 0.41036325693130493, "learning_rate": 1.8794835945790085e-05, "loss": 4.2003, "step": 18984 }, { "epoch": 0.5798717165546732, "grad_norm": 0.40432295203208923, "learning_rate": 1.879251214784795e-05, "loss": 4.2009, "step": 18985 }, { "epoch": 0.579902260232132, "grad_norm": 0.4194100797176361, "learning_rate": 1.879018840706135e-05, "loss": 4.2224, "step": 18986 }, { "epoch": 0.5799328039095907, "grad_norm": 0.41272467374801636, "learning_rate": 1.8787864723451686e-05, "loss": 4.2972, "step": 18987 }, { "epoch": 0.5799633475870495, "grad_norm": 0.4056428372859955, "learning_rate": 1.878554109704034e-05, "loss": 4.3206, "step": 18988 }, { "epoch": 0.5799938912645083, "grad_norm": 0.4118229150772095, "learning_rate": 1.8783217527848706e-05, "loss": 4.296, "step": 18989 }, { "epoch": 0.580024434941967, "grad_norm": 0.40345776081085205, "learning_rate": 1.8780894015898197e-05, "loss": 4.3261, "step": 18990 }, { "epoch": 0.5800549786194258, "grad_norm": 0.4227825999259949, "learning_rate": 1.8778570561210185e-05, "loss": 4.3752, "step": 18991 }, { "epoch": 0.5800855222968846, "grad_norm": 0.40070217847824097, "learning_rate": 1.8776247163806072e-05, "loss": 4.3068, "step": 18992 }, { "epoch": 0.5801160659743433, "grad_norm": 0.4148021340370178, "learning_rate": 1.877392382370726e-05, "loss": 4.2535, "step": 18993 }, { "epoch": 0.5801466096518021, "grad_norm": 0.41759300231933594, "learning_rate": 1.8771600540935123e-05, "loss": 4.3473, "step": 18994 }, { "epoch": 0.5801771533292609, "grad_norm": 0.4076758325099945, "learning_rate": 1.8769277315511066e-05, "loss": 4.2185, "step": 18995 }, { "epoch": 0.5802076970067196, "grad_norm": 0.4138885736465454, "learning_rate": 1.8766954147456482e-05, "loss": 4.3111, "step": 18996 }, { "epoch": 0.5802382406841784, "grad_norm": 0.4281485080718994, "learning_rate": 1.8764631036792748e-05, "loss": 4.3218, "step": 18997 }, { "epoch": 0.5802687843616371, "grad_norm": 0.40946608781814575, "learning_rate": 1.8762307983541272e-05, "loss": 4.2819, "step": 18998 }, { "epoch": 0.5802993280390959, "grad_norm": 0.4211723804473877, "learning_rate": 1.8759984987723422e-05, "loss": 4.3429, "step": 18999 }, { "epoch": 0.5803298717165547, "grad_norm": 0.41713976860046387, "learning_rate": 1.8757662049360595e-05, "loss": 4.2824, "step": 19000 }, { "epoch": 0.5803604153940134, "grad_norm": 0.41840413212776184, "learning_rate": 1.87553391684742e-05, "loss": 4.2891, "step": 19001 }, { "epoch": 0.5803909590714722, "grad_norm": 0.409612238407135, "learning_rate": 1.8753016345085595e-05, "loss": 4.2497, "step": 19002 }, { "epoch": 0.580421502748931, "grad_norm": 0.42122015357017517, "learning_rate": 1.8750693579216184e-05, "loss": 4.3403, "step": 19003 }, { "epoch": 0.5804520464263897, "grad_norm": 0.4047461748123169, "learning_rate": 1.874837087088735e-05, "loss": 4.2527, "step": 19004 }, { "epoch": 0.5804825901038485, "grad_norm": 0.3999994099140167, "learning_rate": 1.8746048220120483e-05, "loss": 4.2076, "step": 19005 }, { "epoch": 0.5805131337813073, "grad_norm": 0.4092850387096405, "learning_rate": 1.8743725626936955e-05, "loss": 4.269, "step": 19006 }, { "epoch": 0.580543677458766, "grad_norm": 0.41280484199523926, "learning_rate": 1.8741403091358176e-05, "loss": 4.2381, "step": 19007 }, { "epoch": 0.5805742211362248, "grad_norm": 0.42599940299987793, "learning_rate": 1.8739080613405506e-05, "loss": 4.2888, "step": 19008 }, { "epoch": 0.5806047648136836, "grad_norm": 0.4146268963813782, "learning_rate": 1.873675819310034e-05, "loss": 4.2898, "step": 19009 }, { "epoch": 0.5806353084911423, "grad_norm": 0.40254998207092285, "learning_rate": 1.873443583046407e-05, "loss": 4.3266, "step": 19010 }, { "epoch": 0.5806658521686011, "grad_norm": 0.4194299578666687, "learning_rate": 1.8732113525518067e-05, "loss": 4.2418, "step": 19011 }, { "epoch": 0.5806963958460599, "grad_norm": 0.42179563641548157, "learning_rate": 1.8729791278283713e-05, "loss": 4.254, "step": 19012 }, { "epoch": 0.5807269395235186, "grad_norm": 0.4249163568019867, "learning_rate": 1.87274690887824e-05, "loss": 4.3125, "step": 19013 }, { "epoch": 0.5807574832009774, "grad_norm": 0.43120241165161133, "learning_rate": 1.87251469570355e-05, "loss": 4.3225, "step": 19014 }, { "epoch": 0.5807880268784361, "grad_norm": 0.4097975194454193, "learning_rate": 1.8722824883064406e-05, "loss": 4.359, "step": 19015 }, { "epoch": 0.5808185705558949, "grad_norm": 0.42894861102104187, "learning_rate": 1.8720502866890483e-05, "loss": 4.2761, "step": 19016 }, { "epoch": 0.5808491142333537, "grad_norm": 0.4110569357872009, "learning_rate": 1.8718180908535117e-05, "loss": 4.3018, "step": 19017 }, { "epoch": 0.5808796579108124, "grad_norm": 0.41725656390190125, "learning_rate": 1.8715859008019697e-05, "loss": 4.3276, "step": 19018 }, { "epoch": 0.5809102015882712, "grad_norm": 0.4115001857280731, "learning_rate": 1.8713537165365593e-05, "loss": 4.2931, "step": 19019 }, { "epoch": 0.58094074526573, "grad_norm": 0.40844810009002686, "learning_rate": 1.8711215380594176e-05, "loss": 4.1963, "step": 19020 }, { "epoch": 0.5809712889431887, "grad_norm": 0.4175020754337311, "learning_rate": 1.8708893653726843e-05, "loss": 4.3434, "step": 19021 }, { "epoch": 0.5810018326206475, "grad_norm": 0.41400769352912903, "learning_rate": 1.870657198478495e-05, "loss": 4.2652, "step": 19022 }, { "epoch": 0.5810323762981063, "grad_norm": 0.4170360267162323, "learning_rate": 1.8704250373789883e-05, "loss": 4.3631, "step": 19023 }, { "epoch": 0.581062919975565, "grad_norm": 0.42266327142715454, "learning_rate": 1.8701928820763038e-05, "loss": 4.2204, "step": 19024 }, { "epoch": 0.5810934636530238, "grad_norm": 0.4263538718223572, "learning_rate": 1.8699607325725753e-05, "loss": 4.2438, "step": 19025 }, { "epoch": 0.5811240073304826, "grad_norm": 0.40986305475234985, "learning_rate": 1.8697285888699433e-05, "loss": 4.2625, "step": 19026 }, { "epoch": 0.5811545510079413, "grad_norm": 0.4146375358104706, "learning_rate": 1.8694964509705442e-05, "loss": 4.2144, "step": 19027 }, { "epoch": 0.5811850946854001, "grad_norm": 0.41801995038986206, "learning_rate": 1.8692643188765154e-05, "loss": 4.285, "step": 19028 }, { "epoch": 0.5812156383628588, "grad_norm": 0.41545507311820984, "learning_rate": 1.8690321925899945e-05, "loss": 4.2705, "step": 19029 }, { "epoch": 0.5812461820403176, "grad_norm": 0.40829068422317505, "learning_rate": 1.868800072113118e-05, "loss": 4.3569, "step": 19030 }, { "epoch": 0.5812767257177764, "grad_norm": 0.4110178053379059, "learning_rate": 1.8685679574480238e-05, "loss": 4.1907, "step": 19031 }, { "epoch": 0.5813072693952351, "grad_norm": 0.4120244085788727, "learning_rate": 1.8683358485968497e-05, "loss": 4.272, "step": 19032 }, { "epoch": 0.5813378130726939, "grad_norm": 0.4161643981933594, "learning_rate": 1.8681037455617315e-05, "loss": 4.3221, "step": 19033 }, { "epoch": 0.5813683567501527, "grad_norm": 0.4155626595020294, "learning_rate": 1.867871648344807e-05, "loss": 4.3252, "step": 19034 }, { "epoch": 0.5813989004276114, "grad_norm": 0.41845059394836426, "learning_rate": 1.867639556948214e-05, "loss": 4.3532, "step": 19035 }, { "epoch": 0.5814294441050702, "grad_norm": 0.41070014238357544, "learning_rate": 1.8674074713740885e-05, "loss": 4.2358, "step": 19036 }, { "epoch": 0.581459987782529, "grad_norm": 0.4159228801727295, "learning_rate": 1.867175391624567e-05, "loss": 4.2592, "step": 19037 }, { "epoch": 0.5814905314599877, "grad_norm": 0.4253068268299103, "learning_rate": 1.866943317701788e-05, "loss": 4.37, "step": 19038 }, { "epoch": 0.5815210751374466, "grad_norm": 0.4063524007797241, "learning_rate": 1.8667112496078865e-05, "loss": 4.2762, "step": 19039 }, { "epoch": 0.5815516188149054, "grad_norm": 0.41210323572158813, "learning_rate": 1.866479187345e-05, "loss": 4.3227, "step": 19040 }, { "epoch": 0.581582162492364, "grad_norm": 0.40979546308517456, "learning_rate": 1.8662471309152664e-05, "loss": 4.3632, "step": 19041 }, { "epoch": 0.5816127061698229, "grad_norm": 0.4066770076751709, "learning_rate": 1.866015080320821e-05, "loss": 4.3111, "step": 19042 }, { "epoch": 0.5816432498472817, "grad_norm": 0.4217503070831299, "learning_rate": 1.8657830355638e-05, "loss": 4.2556, "step": 19043 }, { "epoch": 0.5816737935247404, "grad_norm": 0.4041259288787842, "learning_rate": 1.8655509966463416e-05, "loss": 4.3578, "step": 19044 }, { "epoch": 0.5817043372021992, "grad_norm": 0.41013723611831665, "learning_rate": 1.8653189635705806e-05, "loss": 4.2149, "step": 19045 }, { "epoch": 0.5817348808796579, "grad_norm": 0.42411112785339355, "learning_rate": 1.8650869363386553e-05, "loss": 4.2919, "step": 19046 }, { "epoch": 0.5817654245571167, "grad_norm": 0.4054730236530304, "learning_rate": 1.8648549149526994e-05, "loss": 4.2346, "step": 19047 }, { "epoch": 0.5817959682345755, "grad_norm": 0.4123680293560028, "learning_rate": 1.8646228994148514e-05, "loss": 4.2809, "step": 19048 }, { "epoch": 0.5818265119120342, "grad_norm": 0.41136422753334045, "learning_rate": 1.864390889727248e-05, "loss": 4.3465, "step": 19049 }, { "epoch": 0.581857055589493, "grad_norm": 0.43283963203430176, "learning_rate": 1.8641588858920233e-05, "loss": 4.2683, "step": 19050 }, { "epoch": 0.5818875992669518, "grad_norm": 0.4034237563610077, "learning_rate": 1.8639268879113153e-05, "loss": 4.2602, "step": 19051 }, { "epoch": 0.5819181429444105, "grad_norm": 0.4158223867416382, "learning_rate": 1.86369489578726e-05, "loss": 4.2124, "step": 19052 }, { "epoch": 0.5819486866218693, "grad_norm": 0.41865256428718567, "learning_rate": 1.863462909521992e-05, "loss": 4.2992, "step": 19053 }, { "epoch": 0.5819792302993281, "grad_norm": 0.4183656573295593, "learning_rate": 1.8632309291176482e-05, "loss": 4.2094, "step": 19054 }, { "epoch": 0.5820097739767868, "grad_norm": 0.4106634259223938, "learning_rate": 1.8629989545763653e-05, "loss": 4.3045, "step": 19055 }, { "epoch": 0.5820403176542456, "grad_norm": 0.4099826216697693, "learning_rate": 1.862766985900278e-05, "loss": 4.2637, "step": 19056 }, { "epoch": 0.5820708613317044, "grad_norm": 0.41891273856163025, "learning_rate": 1.862535023091523e-05, "loss": 4.362, "step": 19057 }, { "epoch": 0.5821014050091631, "grad_norm": 0.41532039642333984, "learning_rate": 1.8623030661522357e-05, "loss": 4.2295, "step": 19058 }, { "epoch": 0.5821319486866219, "grad_norm": 0.41279131174087524, "learning_rate": 1.8620711150845522e-05, "loss": 4.3207, "step": 19059 }, { "epoch": 0.5821624923640807, "grad_norm": 0.4161830544471741, "learning_rate": 1.8618391698906075e-05, "loss": 4.3057, "step": 19060 }, { "epoch": 0.5821930360415394, "grad_norm": 0.41895031929016113, "learning_rate": 1.8616072305725385e-05, "loss": 4.3367, "step": 19061 }, { "epoch": 0.5822235797189982, "grad_norm": 0.4131419360637665, "learning_rate": 1.861375297132479e-05, "loss": 4.3123, "step": 19062 }, { "epoch": 0.5822541233964569, "grad_norm": 0.40774020552635193, "learning_rate": 1.861143369572566e-05, "loss": 4.3698, "step": 19063 }, { "epoch": 0.5822846670739157, "grad_norm": 0.4145958423614502, "learning_rate": 1.860911447894934e-05, "loss": 4.34, "step": 19064 }, { "epoch": 0.5823152107513745, "grad_norm": 0.418244332075119, "learning_rate": 1.8606795321017195e-05, "loss": 4.3691, "step": 19065 }, { "epoch": 0.5823457544288332, "grad_norm": 0.41693589091300964, "learning_rate": 1.8604476221950566e-05, "loss": 4.3073, "step": 19066 }, { "epoch": 0.582376298106292, "grad_norm": 0.42274051904678345, "learning_rate": 1.860215718177082e-05, "loss": 4.3885, "step": 19067 }, { "epoch": 0.5824068417837508, "grad_norm": 0.4131426513195038, "learning_rate": 1.8599838200499294e-05, "loss": 4.259, "step": 19068 }, { "epoch": 0.5824373854612095, "grad_norm": 0.4107687175273895, "learning_rate": 1.859751927815736e-05, "loss": 4.3171, "step": 19069 }, { "epoch": 0.5824679291386683, "grad_norm": 0.4118354022502899, "learning_rate": 1.8595200414766347e-05, "loss": 4.3173, "step": 19070 }, { "epoch": 0.5824984728161271, "grad_norm": 0.3942270278930664, "learning_rate": 1.8592881610347612e-05, "loss": 4.2127, "step": 19071 }, { "epoch": 0.5825290164935858, "grad_norm": 0.40855225920677185, "learning_rate": 1.8590562864922524e-05, "loss": 4.2535, "step": 19072 }, { "epoch": 0.5825595601710446, "grad_norm": 0.4106553792953491, "learning_rate": 1.858824417851241e-05, "loss": 4.2598, "step": 19073 }, { "epoch": 0.5825901038485034, "grad_norm": 0.4260832965373993, "learning_rate": 1.8585925551138632e-05, "loss": 4.2728, "step": 19074 }, { "epoch": 0.5826206475259621, "grad_norm": 0.41006308794021606, "learning_rate": 1.8583606982822543e-05, "loss": 4.2573, "step": 19075 }, { "epoch": 0.5826511912034209, "grad_norm": 0.4148522615432739, "learning_rate": 1.8581288473585474e-05, "loss": 4.3316, "step": 19076 }, { "epoch": 0.5826817348808797, "grad_norm": 0.42061755061149597, "learning_rate": 1.8578970023448776e-05, "loss": 4.2213, "step": 19077 }, { "epoch": 0.5827122785583384, "grad_norm": 0.41240301728248596, "learning_rate": 1.8576651632433817e-05, "loss": 4.2959, "step": 19078 }, { "epoch": 0.5827428222357972, "grad_norm": 0.4110184907913208, "learning_rate": 1.857433330056192e-05, "loss": 4.3085, "step": 19079 }, { "epoch": 0.5827733659132559, "grad_norm": 0.40659111738204956, "learning_rate": 1.8572015027854447e-05, "loss": 4.2151, "step": 19080 }, { "epoch": 0.5828039095907147, "grad_norm": 0.41056105494499207, "learning_rate": 1.8569696814332727e-05, "loss": 4.3081, "step": 19081 }, { "epoch": 0.5828344532681735, "grad_norm": 0.4079778492450714, "learning_rate": 1.856737866001812e-05, "loss": 4.2669, "step": 19082 }, { "epoch": 0.5828649969456322, "grad_norm": 0.41329944133758545, "learning_rate": 1.8565060564931972e-05, "loss": 4.2839, "step": 19083 }, { "epoch": 0.582895540623091, "grad_norm": 0.42169615626335144, "learning_rate": 1.856274252909561e-05, "loss": 4.3083, "step": 19084 }, { "epoch": 0.5829260843005498, "grad_norm": 0.4250231087207794, "learning_rate": 1.8560424552530384e-05, "loss": 4.3219, "step": 19085 }, { "epoch": 0.5829566279780085, "grad_norm": 0.41079679131507874, "learning_rate": 1.855810663525765e-05, "loss": 4.296, "step": 19086 }, { "epoch": 0.5829871716554673, "grad_norm": 0.41785863041877747, "learning_rate": 1.8555788777298734e-05, "loss": 4.2587, "step": 19087 }, { "epoch": 0.5830177153329261, "grad_norm": 0.4027552604675293, "learning_rate": 1.8553470978674982e-05, "loss": 4.2847, "step": 19088 }, { "epoch": 0.5830482590103848, "grad_norm": 0.4175674617290497, "learning_rate": 1.8551153239407745e-05, "loss": 4.286, "step": 19089 }, { "epoch": 0.5830788026878436, "grad_norm": 0.4165140986442566, "learning_rate": 1.854883555951835e-05, "loss": 4.2861, "step": 19090 }, { "epoch": 0.5831093463653024, "grad_norm": 0.40061259269714355, "learning_rate": 1.8546517939028145e-05, "loss": 4.2557, "step": 19091 }, { "epoch": 0.5831398900427611, "grad_norm": 0.4112897217273712, "learning_rate": 1.854420037795847e-05, "loss": 4.3558, "step": 19092 }, { "epoch": 0.5831704337202199, "grad_norm": 0.42031994462013245, "learning_rate": 1.854188287633066e-05, "loss": 4.3397, "step": 19093 }, { "epoch": 0.5832009773976787, "grad_norm": 0.40372949838638306, "learning_rate": 1.8539565434166045e-05, "loss": 4.3421, "step": 19094 }, { "epoch": 0.5832315210751374, "grad_norm": 0.40782803297042847, "learning_rate": 1.853724805148599e-05, "loss": 4.1914, "step": 19095 }, { "epoch": 0.5832620647525962, "grad_norm": 0.4118858873844147, "learning_rate": 1.85349307283118e-05, "loss": 4.2351, "step": 19096 }, { "epoch": 0.5832926084300549, "grad_norm": 0.40903282165527344, "learning_rate": 1.8532613464664838e-05, "loss": 4.2895, "step": 19097 }, { "epoch": 0.5833231521075137, "grad_norm": 0.4021926522254944, "learning_rate": 1.8530296260566427e-05, "loss": 4.2514, "step": 19098 }, { "epoch": 0.5833536957849725, "grad_norm": 0.39694729447364807, "learning_rate": 1.85279791160379e-05, "loss": 4.3484, "step": 19099 }, { "epoch": 0.5833842394624312, "grad_norm": 0.42038509249687195, "learning_rate": 1.8525662031100597e-05, "loss": 4.2364, "step": 19100 }, { "epoch": 0.58341478313989, "grad_norm": 0.4099312722682953, "learning_rate": 1.8523345005775852e-05, "loss": 4.2372, "step": 19101 }, { "epoch": 0.5834453268173488, "grad_norm": 0.4123348593711853, "learning_rate": 1.8521028040085e-05, "loss": 4.2668, "step": 19102 }, { "epoch": 0.5834758704948075, "grad_norm": 0.41634684801101685, "learning_rate": 1.851871113404938e-05, "loss": 4.2932, "step": 19103 }, { "epoch": 0.5835064141722663, "grad_norm": 0.3956868648529053, "learning_rate": 1.8516394287690307e-05, "loss": 4.3137, "step": 19104 }, { "epoch": 0.5835369578497251, "grad_norm": 0.4137938320636749, "learning_rate": 1.8514077501029136e-05, "loss": 4.3231, "step": 19105 }, { "epoch": 0.5835675015271838, "grad_norm": 0.41219741106033325, "learning_rate": 1.8511760774087193e-05, "loss": 4.3158, "step": 19106 }, { "epoch": 0.5835980452046426, "grad_norm": 0.41576749086380005, "learning_rate": 1.850944410688579e-05, "loss": 4.3369, "step": 19107 }, { "epoch": 0.5836285888821015, "grad_norm": 0.40381401777267456, "learning_rate": 1.8507127499446274e-05, "loss": 4.2491, "step": 19108 }, { "epoch": 0.5836591325595601, "grad_norm": 0.40879470109939575, "learning_rate": 1.8504810951789984e-05, "loss": 4.2947, "step": 19109 }, { "epoch": 0.583689676237019, "grad_norm": 0.4209616184234619, "learning_rate": 1.850249446393823e-05, "loss": 4.3061, "step": 19110 }, { "epoch": 0.5837202199144778, "grad_norm": 0.44500428438186646, "learning_rate": 1.8500178035912346e-05, "loss": 4.2727, "step": 19111 }, { "epoch": 0.5837507635919365, "grad_norm": 0.41804224252700806, "learning_rate": 1.8497861667733678e-05, "loss": 4.2657, "step": 19112 }, { "epoch": 0.5837813072693953, "grad_norm": 0.42318597435951233, "learning_rate": 1.849554535942354e-05, "loss": 4.1887, "step": 19113 }, { "epoch": 0.583811850946854, "grad_norm": 0.4092322289943695, "learning_rate": 1.849322911100325e-05, "loss": 4.2786, "step": 19114 }, { "epoch": 0.5838423946243128, "grad_norm": 0.4078111946582794, "learning_rate": 1.8490912922494153e-05, "loss": 4.3095, "step": 19115 }, { "epoch": 0.5838729383017716, "grad_norm": 0.41819262504577637, "learning_rate": 1.848859679391756e-05, "loss": 4.2812, "step": 19116 }, { "epoch": 0.5839034819792303, "grad_norm": 0.4045258164405823, "learning_rate": 1.8486280725294812e-05, "loss": 4.309, "step": 19117 }, { "epoch": 0.5839340256566891, "grad_norm": 0.4094124138355255, "learning_rate": 1.8483964716647224e-05, "loss": 4.277, "step": 19118 }, { "epoch": 0.5839645693341479, "grad_norm": 0.4266737997531891, "learning_rate": 1.8481648767996114e-05, "loss": 4.2667, "step": 19119 }, { "epoch": 0.5839951130116066, "grad_norm": 0.40894877910614014, "learning_rate": 1.8479332879362828e-05, "loss": 4.2942, "step": 19120 }, { "epoch": 0.5840256566890654, "grad_norm": 0.4089193046092987, "learning_rate": 1.8477017050768674e-05, "loss": 4.234, "step": 19121 }, { "epoch": 0.5840562003665242, "grad_norm": 0.410518079996109, "learning_rate": 1.847470128223497e-05, "loss": 4.1257, "step": 19122 }, { "epoch": 0.5840867440439829, "grad_norm": 0.4228353202342987, "learning_rate": 1.8472385573783058e-05, "loss": 4.1946, "step": 19123 }, { "epoch": 0.5841172877214417, "grad_norm": 0.4127574563026428, "learning_rate": 1.847006992543424e-05, "loss": 4.2826, "step": 19124 }, { "epoch": 0.5841478313989005, "grad_norm": 0.40621718764305115, "learning_rate": 1.846775433720984e-05, "loss": 4.3603, "step": 19125 }, { "epoch": 0.5841783750763592, "grad_norm": 0.41287723183631897, "learning_rate": 1.84654388091312e-05, "loss": 4.2699, "step": 19126 }, { "epoch": 0.584208918753818, "grad_norm": 0.40604230761528015, "learning_rate": 1.8463123341219612e-05, "loss": 4.2743, "step": 19127 }, { "epoch": 0.5842394624312768, "grad_norm": 0.4029260277748108, "learning_rate": 1.8460807933496414e-05, "loss": 4.274, "step": 19128 }, { "epoch": 0.5842700061087355, "grad_norm": 0.41265416145324707, "learning_rate": 1.8458492585982923e-05, "loss": 4.1854, "step": 19129 }, { "epoch": 0.5843005497861943, "grad_norm": 0.407115638256073, "learning_rate": 1.8456177298700445e-05, "loss": 4.2857, "step": 19130 }, { "epoch": 0.584331093463653, "grad_norm": 0.4282996952533722, "learning_rate": 1.845386207167032e-05, "loss": 4.3801, "step": 19131 }, { "epoch": 0.5843616371411118, "grad_norm": 0.40389326214790344, "learning_rate": 1.845154690491384e-05, "loss": 4.3424, "step": 19132 }, { "epoch": 0.5843921808185706, "grad_norm": 0.4191890358924866, "learning_rate": 1.8449231798452332e-05, "loss": 4.282, "step": 19133 }, { "epoch": 0.5844227244960293, "grad_norm": 0.4080604314804077, "learning_rate": 1.8446916752307127e-05, "loss": 4.3314, "step": 19134 }, { "epoch": 0.5844532681734881, "grad_norm": 0.4070560336112976, "learning_rate": 1.844460176649952e-05, "loss": 4.2591, "step": 19135 }, { "epoch": 0.5844838118509469, "grad_norm": 0.4043203592300415, "learning_rate": 1.8442286841050838e-05, "loss": 4.2955, "step": 19136 }, { "epoch": 0.5845143555284056, "grad_norm": 0.43436989188194275, "learning_rate": 1.8439971975982394e-05, "loss": 4.3231, "step": 19137 }, { "epoch": 0.5845448992058644, "grad_norm": 0.40363356471061707, "learning_rate": 1.8437657171315504e-05, "loss": 4.2707, "step": 19138 }, { "epoch": 0.5845754428833232, "grad_norm": 0.4162013530731201, "learning_rate": 1.843534242707147e-05, "loss": 4.258, "step": 19139 }, { "epoch": 0.5846059865607819, "grad_norm": 0.41324537992477417, "learning_rate": 1.8433027743271623e-05, "loss": 4.1751, "step": 19140 }, { "epoch": 0.5846365302382407, "grad_norm": 0.42523878812789917, "learning_rate": 1.8430713119937255e-05, "loss": 4.3044, "step": 19141 }, { "epoch": 0.5846670739156995, "grad_norm": 0.4035435914993286, "learning_rate": 1.842839855708969e-05, "loss": 4.3615, "step": 19142 }, { "epoch": 0.5846976175931582, "grad_norm": 0.41847315430641174, "learning_rate": 1.8426084054750247e-05, "loss": 4.2894, "step": 19143 }, { "epoch": 0.584728161270617, "grad_norm": 0.41103512048721313, "learning_rate": 1.8423769612940227e-05, "loss": 4.2551, "step": 19144 }, { "epoch": 0.5847587049480758, "grad_norm": 0.4008012115955353, "learning_rate": 1.8421455231680933e-05, "loss": 4.2196, "step": 19145 }, { "epoch": 0.5847892486255345, "grad_norm": 0.4202156364917755, "learning_rate": 1.8419140910993697e-05, "loss": 4.3185, "step": 19146 }, { "epoch": 0.5848197923029933, "grad_norm": 0.4096069037914276, "learning_rate": 1.84168266508998e-05, "loss": 4.3438, "step": 19147 }, { "epoch": 0.584850335980452, "grad_norm": 0.43219199776649475, "learning_rate": 1.8414512451420576e-05, "loss": 4.2329, "step": 19148 }, { "epoch": 0.5848808796579108, "grad_norm": 0.4122687876224518, "learning_rate": 1.841219831257731e-05, "loss": 4.2269, "step": 19149 }, { "epoch": 0.5849114233353696, "grad_norm": 0.41841253638267517, "learning_rate": 1.8409884234391324e-05, "loss": 4.3485, "step": 19150 }, { "epoch": 0.5849419670128283, "grad_norm": 0.4102758765220642, "learning_rate": 1.8407570216883932e-05, "loss": 4.3625, "step": 19151 }, { "epoch": 0.5849725106902871, "grad_norm": 0.41560831665992737, "learning_rate": 1.8405256260076426e-05, "loss": 4.2922, "step": 19152 }, { "epoch": 0.5850030543677459, "grad_norm": 0.4040425419807434, "learning_rate": 1.840294236399011e-05, "loss": 4.1448, "step": 19153 }, { "epoch": 0.5850335980452046, "grad_norm": 0.4088931381702423, "learning_rate": 1.8400628528646305e-05, "loss": 4.3432, "step": 19154 }, { "epoch": 0.5850641417226634, "grad_norm": 0.40975743532180786, "learning_rate": 1.8398314754066295e-05, "loss": 4.1619, "step": 19155 }, { "epoch": 0.5850946854001222, "grad_norm": 0.43035992980003357, "learning_rate": 1.83960010402714e-05, "loss": 4.2675, "step": 19156 }, { "epoch": 0.5851252290775809, "grad_norm": 0.41363850235939026, "learning_rate": 1.8393687387282922e-05, "loss": 4.3672, "step": 19157 }, { "epoch": 0.5851557727550397, "grad_norm": 0.40699684619903564, "learning_rate": 1.8391373795122158e-05, "loss": 4.2838, "step": 19158 }, { "epoch": 0.5851863164324985, "grad_norm": 0.4235721230506897, "learning_rate": 1.8389060263810414e-05, "loss": 4.2285, "step": 19159 }, { "epoch": 0.5852168601099572, "grad_norm": 0.39866217970848083, "learning_rate": 1.8386746793368992e-05, "loss": 4.2221, "step": 19160 }, { "epoch": 0.585247403787416, "grad_norm": 0.4098477363586426, "learning_rate": 1.8384433383819194e-05, "loss": 4.312, "step": 19161 }, { "epoch": 0.5852779474648748, "grad_norm": 0.4210176467895508, "learning_rate": 1.838212003518231e-05, "loss": 4.2748, "step": 19162 }, { "epoch": 0.5853084911423335, "grad_norm": 0.4101846516132355, "learning_rate": 1.8379806747479664e-05, "loss": 4.2591, "step": 19163 }, { "epoch": 0.5853390348197923, "grad_norm": 0.4089871346950531, "learning_rate": 1.837749352073253e-05, "loss": 4.2724, "step": 19164 }, { "epoch": 0.585369578497251, "grad_norm": 0.4288085401058197, "learning_rate": 1.837518035496223e-05, "loss": 4.2567, "step": 19165 }, { "epoch": 0.5854001221747098, "grad_norm": 0.40920543670654297, "learning_rate": 1.8372867250190034e-05, "loss": 4.3426, "step": 19166 }, { "epoch": 0.5854306658521686, "grad_norm": 0.4190155863761902, "learning_rate": 1.8370554206437268e-05, "loss": 4.2474, "step": 19167 }, { "epoch": 0.5854612095296273, "grad_norm": 0.42012661695480347, "learning_rate": 1.8368241223725213e-05, "loss": 4.2169, "step": 19168 }, { "epoch": 0.5854917532070861, "grad_norm": 0.4159410893917084, "learning_rate": 1.8365928302075174e-05, "loss": 4.2648, "step": 19169 }, { "epoch": 0.5855222968845449, "grad_norm": 0.40531986951828003, "learning_rate": 1.836361544150844e-05, "loss": 4.2815, "step": 19170 }, { "epoch": 0.5855528405620036, "grad_norm": 0.4044361114501953, "learning_rate": 1.8361302642046317e-05, "loss": 4.357, "step": 19171 }, { "epoch": 0.5855833842394624, "grad_norm": 0.4136351943016052, "learning_rate": 1.8358989903710088e-05, "loss": 4.1812, "step": 19172 }, { "epoch": 0.5856139279169212, "grad_norm": 0.4134538173675537, "learning_rate": 1.8356677226521052e-05, "loss": 4.2631, "step": 19173 }, { "epoch": 0.5856444715943799, "grad_norm": 0.41754892468452454, "learning_rate": 1.8354364610500514e-05, "loss": 4.1903, "step": 19174 }, { "epoch": 0.5856750152718387, "grad_norm": 0.4145892560482025, "learning_rate": 1.8352052055669752e-05, "loss": 4.24, "step": 19175 }, { "epoch": 0.5857055589492975, "grad_norm": 0.42521554231643677, "learning_rate": 1.8349739562050062e-05, "loss": 4.3438, "step": 19176 }, { "epoch": 0.5857361026267562, "grad_norm": 0.4132545590400696, "learning_rate": 1.8347427129662747e-05, "loss": 4.2373, "step": 19177 }, { "epoch": 0.585766646304215, "grad_norm": 0.42665669322013855, "learning_rate": 1.834511475852908e-05, "loss": 4.2127, "step": 19178 }, { "epoch": 0.5857971899816737, "grad_norm": 0.4105542302131653, "learning_rate": 1.8342802448670376e-05, "loss": 4.2985, "step": 19179 }, { "epoch": 0.5858277336591325, "grad_norm": 0.4087473452091217, "learning_rate": 1.8340490200107903e-05, "loss": 4.2668, "step": 19180 }, { "epoch": 0.5858582773365913, "grad_norm": 0.43692314624786377, "learning_rate": 1.8338178012862954e-05, "loss": 4.3155, "step": 19181 }, { "epoch": 0.58588882101405, "grad_norm": 0.40708422660827637, "learning_rate": 1.8335865886956845e-05, "loss": 4.3077, "step": 19182 }, { "epoch": 0.5859193646915088, "grad_norm": 0.4295409321784973, "learning_rate": 1.8333553822410826e-05, "loss": 4.2106, "step": 19183 }, { "epoch": 0.5859499083689677, "grad_norm": 0.4066582918167114, "learning_rate": 1.8331241819246215e-05, "loss": 4.3201, "step": 19184 }, { "epoch": 0.5859804520464263, "grad_norm": 0.4272352159023285, "learning_rate": 1.8328929877484293e-05, "loss": 4.2477, "step": 19185 }, { "epoch": 0.5860109957238852, "grad_norm": 0.4171171188354492, "learning_rate": 1.8326617997146333e-05, "loss": 4.1163, "step": 19186 }, { "epoch": 0.586041539401344, "grad_norm": 0.43143099546432495, "learning_rate": 1.832430617825363e-05, "loss": 4.1832, "step": 19187 }, { "epoch": 0.5860720830788027, "grad_norm": 0.4266033470630646, "learning_rate": 1.8321994420827488e-05, "loss": 4.3166, "step": 19188 }, { "epoch": 0.5861026267562615, "grad_norm": 0.4177812933921814, "learning_rate": 1.8319682724889164e-05, "loss": 4.2838, "step": 19189 }, { "epoch": 0.5861331704337203, "grad_norm": 0.41783788800239563, "learning_rate": 1.831737109045996e-05, "loss": 4.1293, "step": 19190 }, { "epoch": 0.586163714111179, "grad_norm": 0.4127238690853119, "learning_rate": 1.8315059517561157e-05, "loss": 4.293, "step": 19191 }, { "epoch": 0.5861942577886378, "grad_norm": 0.4116778075695038, "learning_rate": 1.8312748006214037e-05, "loss": 4.3317, "step": 19192 }, { "epoch": 0.5862248014660966, "grad_norm": 0.40635946393013, "learning_rate": 1.8310436556439882e-05, "loss": 4.3108, "step": 19193 }, { "epoch": 0.5862553451435553, "grad_norm": 0.4161338210105896, "learning_rate": 1.8308125168259985e-05, "loss": 4.3569, "step": 19194 }, { "epoch": 0.5862858888210141, "grad_norm": 0.41576629877090454, "learning_rate": 1.830581384169561e-05, "loss": 4.2438, "step": 19195 }, { "epoch": 0.5863164324984728, "grad_norm": 0.41419240832328796, "learning_rate": 1.8303502576768062e-05, "loss": 4.282, "step": 19196 }, { "epoch": 0.5863469761759316, "grad_norm": 0.4124029576778412, "learning_rate": 1.8301191373498594e-05, "loss": 4.2578, "step": 19197 }, { "epoch": 0.5863775198533904, "grad_norm": 0.4278981387615204, "learning_rate": 1.8298880231908504e-05, "loss": 4.3813, "step": 19198 }, { "epoch": 0.5864080635308491, "grad_norm": 0.4176560640335083, "learning_rate": 1.829656915201908e-05, "loss": 4.3365, "step": 19199 }, { "epoch": 0.5864386072083079, "grad_norm": 0.427245557308197, "learning_rate": 1.8294258133851582e-05, "loss": 4.2955, "step": 19200 }, { "epoch": 0.5864691508857667, "grad_norm": 0.4025323987007141, "learning_rate": 1.8291947177427292e-05, "loss": 4.2606, "step": 19201 }, { "epoch": 0.5864996945632254, "grad_norm": 0.4221898317337036, "learning_rate": 1.828963628276751e-05, "loss": 4.217, "step": 19202 }, { "epoch": 0.5865302382406842, "grad_norm": 0.46695369482040405, "learning_rate": 1.8287325449893478e-05, "loss": 4.3512, "step": 19203 }, { "epoch": 0.586560781918143, "grad_norm": 0.41578352451324463, "learning_rate": 1.8285014678826495e-05, "loss": 4.2491, "step": 19204 }, { "epoch": 0.5865913255956017, "grad_norm": 0.42656370997428894, "learning_rate": 1.8282703969587846e-05, "loss": 4.1966, "step": 19205 }, { "epoch": 0.5866218692730605, "grad_norm": 0.4105704426765442, "learning_rate": 1.8280393322198786e-05, "loss": 4.2677, "step": 19206 }, { "epoch": 0.5866524129505193, "grad_norm": 0.407953143119812, "learning_rate": 1.82780827366806e-05, "loss": 4.3138, "step": 19207 }, { "epoch": 0.586682956627978, "grad_norm": 0.41184425354003906, "learning_rate": 1.8275772213054572e-05, "loss": 4.3613, "step": 19208 }, { "epoch": 0.5867135003054368, "grad_norm": 0.4034995436668396, "learning_rate": 1.827346175134196e-05, "loss": 4.3144, "step": 19209 }, { "epoch": 0.5867440439828956, "grad_norm": 0.5980051159858704, "learning_rate": 1.8271151351564035e-05, "loss": 4.1882, "step": 19210 }, { "epoch": 0.5867745876603543, "grad_norm": 0.409106969833374, "learning_rate": 1.8268841013742096e-05, "loss": 4.1993, "step": 19211 }, { "epoch": 0.5868051313378131, "grad_norm": 0.41956478357315063, "learning_rate": 1.8266530737897384e-05, "loss": 4.3483, "step": 19212 }, { "epoch": 0.5868356750152718, "grad_norm": 0.4332074820995331, "learning_rate": 1.8264220524051195e-05, "loss": 4.2839, "step": 19213 }, { "epoch": 0.5868662186927306, "grad_norm": 0.4219987988471985, "learning_rate": 1.8261910372224783e-05, "loss": 4.2911, "step": 19214 }, { "epoch": 0.5868967623701894, "grad_norm": 0.41873133182525635, "learning_rate": 1.8259600282439434e-05, "loss": 4.1291, "step": 19215 }, { "epoch": 0.5869273060476481, "grad_norm": 0.40864524245262146, "learning_rate": 1.8257290254716412e-05, "loss": 4.2523, "step": 19216 }, { "epoch": 0.5869578497251069, "grad_norm": 0.40632590651512146, "learning_rate": 1.825498028907698e-05, "loss": 4.1537, "step": 19217 }, { "epoch": 0.5869883934025657, "grad_norm": 0.413859486579895, "learning_rate": 1.8252670385542408e-05, "loss": 4.3266, "step": 19218 }, { "epoch": 0.5870189370800244, "grad_norm": 0.40535593032836914, "learning_rate": 1.825036054413398e-05, "loss": 4.2781, "step": 19219 }, { "epoch": 0.5870494807574832, "grad_norm": 0.421853244304657, "learning_rate": 1.8248050764872942e-05, "loss": 4.3277, "step": 19220 }, { "epoch": 0.587080024434942, "grad_norm": 0.41775503754615784, "learning_rate": 1.8245741047780572e-05, "loss": 4.1283, "step": 19221 }, { "epoch": 0.5871105681124007, "grad_norm": 0.43139147758483887, "learning_rate": 1.824343139287815e-05, "loss": 4.2757, "step": 19222 }, { "epoch": 0.5871411117898595, "grad_norm": 0.41827207803726196, "learning_rate": 1.824112180018692e-05, "loss": 4.2011, "step": 19223 }, { "epoch": 0.5871716554673183, "grad_norm": 0.4279731810092926, "learning_rate": 1.8238812269728157e-05, "loss": 4.3094, "step": 19224 }, { "epoch": 0.587202199144777, "grad_norm": 0.42387494444847107, "learning_rate": 1.823650280152313e-05, "loss": 4.2719, "step": 19225 }, { "epoch": 0.5872327428222358, "grad_norm": 0.41624897718429565, "learning_rate": 1.823419339559309e-05, "loss": 4.2339, "step": 19226 }, { "epoch": 0.5872632864996946, "grad_norm": 0.40611064434051514, "learning_rate": 1.8231884051959315e-05, "loss": 4.199, "step": 19227 }, { "epoch": 0.5872938301771533, "grad_norm": 0.40845030546188354, "learning_rate": 1.8229574770643072e-05, "loss": 4.284, "step": 19228 }, { "epoch": 0.5873243738546121, "grad_norm": 0.4191302955150604, "learning_rate": 1.82272655516656e-05, "loss": 4.256, "step": 19229 }, { "epoch": 0.5873549175320708, "grad_norm": 0.41614192724227905, "learning_rate": 1.8224956395048186e-05, "loss": 4.187, "step": 19230 }, { "epoch": 0.5873854612095296, "grad_norm": 0.4151588976383209, "learning_rate": 1.8222647300812085e-05, "loss": 4.3067, "step": 19231 }, { "epoch": 0.5874160048869884, "grad_norm": 0.415814608335495, "learning_rate": 1.8220338268978544e-05, "loss": 4.4133, "step": 19232 }, { "epoch": 0.5874465485644471, "grad_norm": 0.4154393672943115, "learning_rate": 1.8218029299568845e-05, "loss": 4.272, "step": 19233 }, { "epoch": 0.5874770922419059, "grad_norm": 0.4078424572944641, "learning_rate": 1.8215720392604227e-05, "loss": 4.2219, "step": 19234 }, { "epoch": 0.5875076359193647, "grad_norm": 0.4279220700263977, "learning_rate": 1.821341154810596e-05, "loss": 4.2922, "step": 19235 }, { "epoch": 0.5875381795968234, "grad_norm": 0.402710884809494, "learning_rate": 1.821110276609531e-05, "loss": 4.2846, "step": 19236 }, { "epoch": 0.5875687232742822, "grad_norm": 0.4119054079055786, "learning_rate": 1.8208794046593522e-05, "loss": 4.1751, "step": 19237 }, { "epoch": 0.587599266951741, "grad_norm": 0.41666021943092346, "learning_rate": 1.8206485389621862e-05, "loss": 4.2663, "step": 19238 }, { "epoch": 0.5876298106291997, "grad_norm": 0.4127439558506012, "learning_rate": 1.8204176795201587e-05, "loss": 4.3315, "step": 19239 }, { "epoch": 0.5876603543066585, "grad_norm": 0.40716516971588135, "learning_rate": 1.8201868263353943e-05, "loss": 4.3046, "step": 19240 }, { "epoch": 0.5876908979841173, "grad_norm": 0.4195431172847748, "learning_rate": 1.819955979410019e-05, "loss": 4.2257, "step": 19241 }, { "epoch": 0.587721441661576, "grad_norm": 0.4180912971496582, "learning_rate": 1.81972513874616e-05, "loss": 4.2564, "step": 19242 }, { "epoch": 0.5877519853390348, "grad_norm": 0.4116857349872589, "learning_rate": 1.81949430434594e-05, "loss": 4.3016, "step": 19243 }, { "epoch": 0.5877825290164936, "grad_norm": 0.4090951085090637, "learning_rate": 1.8192634762114864e-05, "loss": 4.2501, "step": 19244 }, { "epoch": 0.5878130726939523, "grad_norm": 0.4294307231903076, "learning_rate": 1.8190326543449243e-05, "loss": 4.2618, "step": 19245 }, { "epoch": 0.5878436163714111, "grad_norm": 0.41454604268074036, "learning_rate": 1.8188018387483785e-05, "loss": 4.1993, "step": 19246 }, { "epoch": 0.5878741600488698, "grad_norm": 0.4180777668952942, "learning_rate": 1.8185710294239746e-05, "loss": 4.2305, "step": 19247 }, { "epoch": 0.5879047037263286, "grad_norm": 0.41927453875541687, "learning_rate": 1.8183402263738374e-05, "loss": 4.2975, "step": 19248 }, { "epoch": 0.5879352474037874, "grad_norm": 0.410563588142395, "learning_rate": 1.8181094296000916e-05, "loss": 4.2525, "step": 19249 }, { "epoch": 0.5879657910812461, "grad_norm": 0.40370973944664, "learning_rate": 1.817878639104864e-05, "loss": 4.2947, "step": 19250 }, { "epoch": 0.5879963347587049, "grad_norm": 0.4128369688987732, "learning_rate": 1.8176478548902775e-05, "loss": 4.2166, "step": 19251 }, { "epoch": 0.5880268784361637, "grad_norm": 0.42891255021095276, "learning_rate": 1.8174170769584582e-05, "loss": 4.3588, "step": 19252 }, { "epoch": 0.5880574221136224, "grad_norm": 0.4163552224636078, "learning_rate": 1.8171863053115312e-05, "loss": 4.2838, "step": 19253 }, { "epoch": 0.5880879657910812, "grad_norm": 0.40839484333992004, "learning_rate": 1.8169555399516208e-05, "loss": 4.1457, "step": 19254 }, { "epoch": 0.58811850946854, "grad_norm": 0.41024133563041687, "learning_rate": 1.816724780880852e-05, "loss": 4.2243, "step": 19255 }, { "epoch": 0.5881490531459987, "grad_norm": 0.41062527894973755, "learning_rate": 1.81649402810135e-05, "loss": 4.2802, "step": 19256 }, { "epoch": 0.5881795968234576, "grad_norm": 0.4123936891555786, "learning_rate": 1.8162632816152374e-05, "loss": 4.3027, "step": 19257 }, { "epoch": 0.5882101405009164, "grad_norm": 0.4044981300830841, "learning_rate": 1.816032541424641e-05, "loss": 4.2671, "step": 19258 }, { "epoch": 0.588240684178375, "grad_norm": 0.41556715965270996, "learning_rate": 1.8158018075316852e-05, "loss": 4.302, "step": 19259 }, { "epoch": 0.5882712278558339, "grad_norm": 0.41315749287605286, "learning_rate": 1.8155710799384932e-05, "loss": 4.2703, "step": 19260 }, { "epoch": 0.5883017715332927, "grad_norm": 0.4091978669166565, "learning_rate": 1.8153403586471907e-05, "loss": 4.3145, "step": 19261 }, { "epoch": 0.5883323152107514, "grad_norm": 0.40734708309173584, "learning_rate": 1.8151096436599018e-05, "loss": 4.2532, "step": 19262 }, { "epoch": 0.5883628588882102, "grad_norm": 0.41494664549827576, "learning_rate": 1.81487893497875e-05, "loss": 4.3652, "step": 19263 }, { "epoch": 0.5883934025656689, "grad_norm": 0.4264282286167145, "learning_rate": 1.8146482326058605e-05, "loss": 4.2013, "step": 19264 }, { "epoch": 0.5884239462431277, "grad_norm": 0.43128928542137146, "learning_rate": 1.8144175365433564e-05, "loss": 4.3238, "step": 19265 }, { "epoch": 0.5884544899205865, "grad_norm": 0.41498783230781555, "learning_rate": 1.8141868467933627e-05, "loss": 4.2885, "step": 19266 }, { "epoch": 0.5884850335980452, "grad_norm": 0.4087356626987457, "learning_rate": 1.813956163358004e-05, "loss": 4.2835, "step": 19267 }, { "epoch": 0.588515577275504, "grad_norm": 0.4144023656845093, "learning_rate": 1.8137254862394026e-05, "loss": 4.2758, "step": 19268 }, { "epoch": 0.5885461209529628, "grad_norm": 0.417470782995224, "learning_rate": 1.8134948154396843e-05, "loss": 4.4032, "step": 19269 }, { "epoch": 0.5885766646304215, "grad_norm": 0.4086393117904663, "learning_rate": 1.813264150960972e-05, "loss": 4.2913, "step": 19270 }, { "epoch": 0.5886072083078803, "grad_norm": 0.4102211892604828, "learning_rate": 1.81303349280539e-05, "loss": 4.1879, "step": 19271 }, { "epoch": 0.5886377519853391, "grad_norm": 0.4196188747882843, "learning_rate": 1.8128028409750613e-05, "loss": 4.2566, "step": 19272 }, { "epoch": 0.5886682956627978, "grad_norm": 0.41358333826065063, "learning_rate": 1.812572195472111e-05, "loss": 4.1592, "step": 19273 }, { "epoch": 0.5886988393402566, "grad_norm": 0.40552592277526855, "learning_rate": 1.8123415562986606e-05, "loss": 4.2065, "step": 19274 }, { "epoch": 0.5887293830177154, "grad_norm": 0.41991105675697327, "learning_rate": 1.8121109234568356e-05, "loss": 4.2075, "step": 19275 }, { "epoch": 0.5887599266951741, "grad_norm": 0.41678598523139954, "learning_rate": 1.8118802969487598e-05, "loss": 4.283, "step": 19276 }, { "epoch": 0.5887904703726329, "grad_norm": 0.4350072741508484, "learning_rate": 1.8116496767765555e-05, "loss": 4.2982, "step": 19277 }, { "epoch": 0.5888210140500917, "grad_norm": 0.41845136880874634, "learning_rate": 1.8114190629423457e-05, "loss": 4.3351, "step": 19278 }, { "epoch": 0.5888515577275504, "grad_norm": 0.42917144298553467, "learning_rate": 1.811188455448256e-05, "loss": 4.3444, "step": 19279 }, { "epoch": 0.5888821014050092, "grad_norm": 0.4245784878730774, "learning_rate": 1.8109578542964074e-05, "loss": 4.235, "step": 19280 }, { "epoch": 0.5889126450824679, "grad_norm": 0.4187563955783844, "learning_rate": 1.8107272594889245e-05, "loss": 4.2599, "step": 19281 }, { "epoch": 0.5889431887599267, "grad_norm": 0.41928350925445557, "learning_rate": 1.81049667102793e-05, "loss": 4.2736, "step": 19282 }, { "epoch": 0.5889737324373855, "grad_norm": 0.4209982454776764, "learning_rate": 1.8102660889155465e-05, "loss": 4.3089, "step": 19283 }, { "epoch": 0.5890042761148442, "grad_norm": 0.42928069829940796, "learning_rate": 1.8100355131538986e-05, "loss": 4.2761, "step": 19284 }, { "epoch": 0.589034819792303, "grad_norm": 0.41020482778549194, "learning_rate": 1.8098049437451086e-05, "loss": 4.2983, "step": 19285 }, { "epoch": 0.5890653634697618, "grad_norm": 0.4091692268848419, "learning_rate": 1.8095743806912986e-05, "loss": 4.295, "step": 19286 }, { "epoch": 0.5890959071472205, "grad_norm": 0.41993382573127747, "learning_rate": 1.809343823994593e-05, "loss": 4.2755, "step": 19287 }, { "epoch": 0.5891264508246793, "grad_norm": 0.41008174419403076, "learning_rate": 1.809113273657113e-05, "loss": 4.3326, "step": 19288 }, { "epoch": 0.5891569945021381, "grad_norm": 0.4077414572238922, "learning_rate": 1.8088827296809827e-05, "loss": 4.1211, "step": 19289 }, { "epoch": 0.5891875381795968, "grad_norm": 0.4218113124370575, "learning_rate": 1.8086521920683253e-05, "loss": 4.0928, "step": 19290 }, { "epoch": 0.5892180818570556, "grad_norm": 0.41010570526123047, "learning_rate": 1.8084216608212613e-05, "loss": 4.2524, "step": 19291 }, { "epoch": 0.5892486255345144, "grad_norm": 0.41978684067726135, "learning_rate": 1.8081911359419153e-05, "loss": 4.2939, "step": 19292 }, { "epoch": 0.5892791692119731, "grad_norm": 0.4108317792415619, "learning_rate": 1.8079606174324092e-05, "loss": 4.1992, "step": 19293 }, { "epoch": 0.5893097128894319, "grad_norm": 0.4027242362499237, "learning_rate": 1.807730105294866e-05, "loss": 4.2308, "step": 19294 }, { "epoch": 0.5893402565668907, "grad_norm": 0.42344072461128235, "learning_rate": 1.8074995995314066e-05, "loss": 4.2612, "step": 19295 }, { "epoch": 0.5893708002443494, "grad_norm": 0.4137101471424103, "learning_rate": 1.8072691001441555e-05, "loss": 4.261, "step": 19296 }, { "epoch": 0.5894013439218082, "grad_norm": 0.43153852224349976, "learning_rate": 1.8070386071352328e-05, "loss": 4.2582, "step": 19297 }, { "epoch": 0.5894318875992669, "grad_norm": 0.4255433678627014, "learning_rate": 1.8068081205067634e-05, "loss": 4.1678, "step": 19298 }, { "epoch": 0.5894624312767257, "grad_norm": 0.4049045145511627, "learning_rate": 1.8065776402608665e-05, "loss": 4.2685, "step": 19299 }, { "epoch": 0.5894929749541845, "grad_norm": 0.4033341407775879, "learning_rate": 1.8063471663996667e-05, "loss": 4.3761, "step": 19300 }, { "epoch": 0.5895235186316432, "grad_norm": 0.41713348031044006, "learning_rate": 1.8061166989252848e-05, "loss": 4.2353, "step": 19301 }, { "epoch": 0.589554062309102, "grad_norm": 0.41443318128585815, "learning_rate": 1.8058862378398437e-05, "loss": 4.3193, "step": 19302 }, { "epoch": 0.5895846059865608, "grad_norm": 0.41729381680488586, "learning_rate": 1.805655783145464e-05, "loss": 4.3155, "step": 19303 }, { "epoch": 0.5896151496640195, "grad_norm": 0.41084539890289307, "learning_rate": 1.8054253348442696e-05, "loss": 4.3549, "step": 19304 }, { "epoch": 0.5896456933414783, "grad_norm": 0.4102024435997009, "learning_rate": 1.8051948929383805e-05, "loss": 4.3493, "step": 19305 }, { "epoch": 0.5896762370189371, "grad_norm": 0.430543452501297, "learning_rate": 1.804964457429919e-05, "loss": 4.1748, "step": 19306 }, { "epoch": 0.5897067806963958, "grad_norm": 0.4098289906978607, "learning_rate": 1.804734028321008e-05, "loss": 4.2622, "step": 19307 }, { "epoch": 0.5897373243738546, "grad_norm": 0.4138297438621521, "learning_rate": 1.8045036056137677e-05, "loss": 4.3304, "step": 19308 }, { "epoch": 0.5897678680513134, "grad_norm": 0.4231466054916382, "learning_rate": 1.8042731893103205e-05, "loss": 4.277, "step": 19309 }, { "epoch": 0.5897984117287721, "grad_norm": 0.4093301594257355, "learning_rate": 1.8040427794127877e-05, "loss": 4.2526, "step": 19310 }, { "epoch": 0.5898289554062309, "grad_norm": 0.437028706073761, "learning_rate": 1.8038123759232906e-05, "loss": 4.2097, "step": 19311 }, { "epoch": 0.5898594990836897, "grad_norm": 0.413120299577713, "learning_rate": 1.8035819788439507e-05, "loss": 4.1873, "step": 19312 }, { "epoch": 0.5898900427611484, "grad_norm": 0.41960299015045166, "learning_rate": 1.8033515881768908e-05, "loss": 4.3322, "step": 19313 }, { "epoch": 0.5899205864386072, "grad_norm": 0.4077020585536957, "learning_rate": 1.8031212039242295e-05, "loss": 4.3163, "step": 19314 }, { "epoch": 0.5899511301160659, "grad_norm": 0.4140762984752655, "learning_rate": 1.802890826088091e-05, "loss": 4.3526, "step": 19315 }, { "epoch": 0.5899816737935247, "grad_norm": 0.4237990975379944, "learning_rate": 1.8026604546705942e-05, "loss": 4.2985, "step": 19316 }, { "epoch": 0.5900122174709835, "grad_norm": 0.4197373390197754, "learning_rate": 1.8024300896738612e-05, "loss": 4.2214, "step": 19317 }, { "epoch": 0.5900427611484422, "grad_norm": 0.418352872133255, "learning_rate": 1.8021997311000137e-05, "loss": 4.2479, "step": 19318 }, { "epoch": 0.590073304825901, "grad_norm": 0.4228028655052185, "learning_rate": 1.801969378951171e-05, "loss": 4.2547, "step": 19319 }, { "epoch": 0.5901038485033598, "grad_norm": 0.42344343662261963, "learning_rate": 1.8017390332294553e-05, "loss": 4.2137, "step": 19320 }, { "epoch": 0.5901343921808185, "grad_norm": 0.4217512309551239, "learning_rate": 1.8015086939369884e-05, "loss": 4.3254, "step": 19321 }, { "epoch": 0.5901649358582773, "grad_norm": 0.4168541431427002, "learning_rate": 1.801278361075889e-05, "loss": 4.362, "step": 19322 }, { "epoch": 0.5901954795357361, "grad_norm": 0.41751208901405334, "learning_rate": 1.8010480346482793e-05, "loss": 4.1977, "step": 19323 }, { "epoch": 0.5902260232131948, "grad_norm": 0.40980446338653564, "learning_rate": 1.8008177146562797e-05, "loss": 4.2296, "step": 19324 }, { "epoch": 0.5902565668906536, "grad_norm": 0.42059969902038574, "learning_rate": 1.8005874011020107e-05, "loss": 4.3127, "step": 19325 }, { "epoch": 0.5902871105681124, "grad_norm": 0.41672077775001526, "learning_rate": 1.800357093987593e-05, "loss": 4.2867, "step": 19326 }, { "epoch": 0.5903176542455711, "grad_norm": 0.4197723865509033, "learning_rate": 1.8001267933151485e-05, "loss": 4.214, "step": 19327 }, { "epoch": 0.59034819792303, "grad_norm": 0.4214729070663452, "learning_rate": 1.7998964990867947e-05, "loss": 4.273, "step": 19328 }, { "epoch": 0.5903787416004886, "grad_norm": 0.4072055518627167, "learning_rate": 1.799666211304655e-05, "loss": 4.3751, "step": 19329 }, { "epoch": 0.5904092852779474, "grad_norm": 0.4085993766784668, "learning_rate": 1.799435929970848e-05, "loss": 4.287, "step": 19330 }, { "epoch": 0.5904398289554063, "grad_norm": 0.41221728920936584, "learning_rate": 1.799205655087494e-05, "loss": 4.2454, "step": 19331 }, { "epoch": 0.590470372632865, "grad_norm": 0.4094404876232147, "learning_rate": 1.7989753866567157e-05, "loss": 4.3661, "step": 19332 }, { "epoch": 0.5905009163103238, "grad_norm": 0.42096975445747375, "learning_rate": 1.79874512468063e-05, "loss": 4.2103, "step": 19333 }, { "epoch": 0.5905314599877826, "grad_norm": 0.4324139654636383, "learning_rate": 1.7985148691613585e-05, "loss": 4.2392, "step": 19334 }, { "epoch": 0.5905620036652413, "grad_norm": 0.4185613989830017, "learning_rate": 1.798284620101022e-05, "loss": 4.2111, "step": 19335 }, { "epoch": 0.5905925473427001, "grad_norm": 0.4086952209472656, "learning_rate": 1.7980543775017392e-05, "loss": 4.2618, "step": 19336 }, { "epoch": 0.5906230910201589, "grad_norm": 0.41338035464286804, "learning_rate": 1.7978241413656304e-05, "loss": 4.3001, "step": 19337 }, { "epoch": 0.5906536346976176, "grad_norm": 0.4122822880744934, "learning_rate": 1.7975939116948167e-05, "loss": 4.2691, "step": 19338 }, { "epoch": 0.5906841783750764, "grad_norm": 0.4072543978691101, "learning_rate": 1.7973636884914163e-05, "loss": 4.2715, "step": 19339 }, { "epoch": 0.5907147220525352, "grad_norm": 0.41344738006591797, "learning_rate": 1.79713347175755e-05, "loss": 4.3345, "step": 19340 }, { "epoch": 0.5907452657299939, "grad_norm": 0.414750337600708, "learning_rate": 1.7969032614953375e-05, "loss": 4.3098, "step": 19341 }, { "epoch": 0.5907758094074527, "grad_norm": 0.41446810960769653, "learning_rate": 1.7966730577068975e-05, "loss": 4.3848, "step": 19342 }, { "epoch": 0.5908063530849115, "grad_norm": 0.4035835862159729, "learning_rate": 1.7964428603943497e-05, "loss": 4.2289, "step": 19343 }, { "epoch": 0.5908368967623702, "grad_norm": 0.40969279408454895, "learning_rate": 1.7962126695598157e-05, "loss": 4.3247, "step": 19344 }, { "epoch": 0.590867440439829, "grad_norm": 0.4156499207019806, "learning_rate": 1.7959824852054124e-05, "loss": 4.2792, "step": 19345 }, { "epoch": 0.5908979841172877, "grad_norm": 0.41486746072769165, "learning_rate": 1.7957523073332618e-05, "loss": 4.2348, "step": 19346 }, { "epoch": 0.5909285277947465, "grad_norm": 0.4283270835876465, "learning_rate": 1.79552213594548e-05, "loss": 4.2936, "step": 19347 }, { "epoch": 0.5909590714722053, "grad_norm": 0.4077829122543335, "learning_rate": 1.795291971044189e-05, "loss": 4.3242, "step": 19348 }, { "epoch": 0.590989615149664, "grad_norm": 0.41286706924438477, "learning_rate": 1.7950618126315076e-05, "loss": 4.286, "step": 19349 }, { "epoch": 0.5910201588271228, "grad_norm": 0.40961548686027527, "learning_rate": 1.7948316607095533e-05, "loss": 4.2959, "step": 19350 }, { "epoch": 0.5910507025045816, "grad_norm": 0.4141198396682739, "learning_rate": 1.7946015152804468e-05, "loss": 4.3909, "step": 19351 }, { "epoch": 0.5910812461820403, "grad_norm": 0.4206382930278778, "learning_rate": 1.7943713763463075e-05, "loss": 4.3105, "step": 19352 }, { "epoch": 0.5911117898594991, "grad_norm": 0.4180923104286194, "learning_rate": 1.7941412439092532e-05, "loss": 4.1643, "step": 19353 }, { "epoch": 0.5911423335369579, "grad_norm": 0.4028664231300354, "learning_rate": 1.793911117971403e-05, "loss": 4.2604, "step": 19354 }, { "epoch": 0.5911728772144166, "grad_norm": 0.4086323380470276, "learning_rate": 1.7936809985348774e-05, "loss": 4.3426, "step": 19355 }, { "epoch": 0.5912034208918754, "grad_norm": 0.42741039395332336, "learning_rate": 1.7934508856017935e-05, "loss": 4.2448, "step": 19356 }, { "epoch": 0.5912339645693342, "grad_norm": 0.41881102323532104, "learning_rate": 1.79322077917427e-05, "loss": 4.2301, "step": 19357 }, { "epoch": 0.5912645082467929, "grad_norm": 0.4206870198249817, "learning_rate": 1.7929906792544272e-05, "loss": 4.3231, "step": 19358 }, { "epoch": 0.5912950519242517, "grad_norm": 0.4133823812007904, "learning_rate": 1.7927605858443814e-05, "loss": 4.2021, "step": 19359 }, { "epoch": 0.5913255956017105, "grad_norm": 0.42575523257255554, "learning_rate": 1.7925304989462527e-05, "loss": 4.29, "step": 19360 }, { "epoch": 0.5913561392791692, "grad_norm": 0.43134981393814087, "learning_rate": 1.7923004185621607e-05, "loss": 4.2956, "step": 19361 }, { "epoch": 0.591386682956628, "grad_norm": 0.4164954721927643, "learning_rate": 1.792070344694221e-05, "loss": 4.3062, "step": 19362 }, { "epoch": 0.5914172266340867, "grad_norm": 0.4310621917247772, "learning_rate": 1.7918402773445554e-05, "loss": 4.3077, "step": 19363 }, { "epoch": 0.5914477703115455, "grad_norm": 0.4169144332408905, "learning_rate": 1.7916102165152795e-05, "loss": 4.3285, "step": 19364 }, { "epoch": 0.5914783139890043, "grad_norm": 0.42689940333366394, "learning_rate": 1.791380162208512e-05, "loss": 4.4161, "step": 19365 }, { "epoch": 0.591508857666463, "grad_norm": 0.4271848499774933, "learning_rate": 1.791150114426373e-05, "loss": 4.2563, "step": 19366 }, { "epoch": 0.5915394013439218, "grad_norm": 0.4132046401500702, "learning_rate": 1.7909200731709782e-05, "loss": 4.2384, "step": 19367 }, { "epoch": 0.5915699450213806, "grad_norm": 0.4177311658859253, "learning_rate": 1.790690038444447e-05, "loss": 4.2224, "step": 19368 }, { "epoch": 0.5916004886988393, "grad_norm": 0.41257014870643616, "learning_rate": 1.790460010248898e-05, "loss": 4.3125, "step": 19369 }, { "epoch": 0.5916310323762981, "grad_norm": 0.4093189537525177, "learning_rate": 1.7902299885864475e-05, "loss": 4.2322, "step": 19370 }, { "epoch": 0.5916615760537569, "grad_norm": 0.42093542218208313, "learning_rate": 1.7899999734592155e-05, "loss": 4.1908, "step": 19371 }, { "epoch": 0.5916921197312156, "grad_norm": 0.4030461013317108, "learning_rate": 1.7897699648693187e-05, "loss": 4.2905, "step": 19372 }, { "epoch": 0.5917226634086744, "grad_norm": 0.40436047315597534, "learning_rate": 1.789539962818874e-05, "loss": 4.2367, "step": 19373 }, { "epoch": 0.5917532070861332, "grad_norm": 0.4292541444301605, "learning_rate": 1.7893099673100004e-05, "loss": 4.2994, "step": 19374 }, { "epoch": 0.5917837507635919, "grad_norm": 0.4227309226989746, "learning_rate": 1.7890799783448165e-05, "loss": 4.3494, "step": 19375 }, { "epoch": 0.5918142944410507, "grad_norm": 0.4073423445224762, "learning_rate": 1.7888499959254374e-05, "loss": 4.3124, "step": 19376 }, { "epoch": 0.5918448381185095, "grad_norm": 0.4201998710632324, "learning_rate": 1.7886200200539822e-05, "loss": 4.316, "step": 19377 }, { "epoch": 0.5918753817959682, "grad_norm": 0.42165493965148926, "learning_rate": 1.788390050732569e-05, "loss": 4.3366, "step": 19378 }, { "epoch": 0.591905925473427, "grad_norm": 0.41774696111679077, "learning_rate": 1.7881600879633143e-05, "loss": 4.2248, "step": 19379 }, { "epoch": 0.5919364691508857, "grad_norm": 0.4081386923789978, "learning_rate": 1.7879301317483354e-05, "loss": 4.2071, "step": 19380 }, { "epoch": 0.5919670128283445, "grad_norm": 0.4104406535625458, "learning_rate": 1.78770018208975e-05, "loss": 4.3108, "step": 19381 }, { "epoch": 0.5919975565058033, "grad_norm": 0.41606518626213074, "learning_rate": 1.7874702389896746e-05, "loss": 4.2447, "step": 19382 }, { "epoch": 0.592028100183262, "grad_norm": 0.41799396276474, "learning_rate": 1.787240302450228e-05, "loss": 4.3966, "step": 19383 }, { "epoch": 0.5920586438607208, "grad_norm": 0.42909595370292664, "learning_rate": 1.787010372473526e-05, "loss": 4.2026, "step": 19384 }, { "epoch": 0.5920891875381796, "grad_norm": 0.4305063486099243, "learning_rate": 1.7867804490616855e-05, "loss": 4.2656, "step": 19385 }, { "epoch": 0.5921197312156383, "grad_norm": 0.40743643045425415, "learning_rate": 1.7865505322168254e-05, "loss": 4.3057, "step": 19386 }, { "epoch": 0.5921502748930971, "grad_norm": 0.4193486273288727, "learning_rate": 1.7863206219410605e-05, "loss": 4.3346, "step": 19387 }, { "epoch": 0.5921808185705559, "grad_norm": 0.414275586605072, "learning_rate": 1.7860907182365082e-05, "loss": 4.3076, "step": 19388 }, { "epoch": 0.5922113622480146, "grad_norm": 0.41576340794563293, "learning_rate": 1.7858608211052872e-05, "loss": 4.2804, "step": 19389 }, { "epoch": 0.5922419059254734, "grad_norm": 0.41823890805244446, "learning_rate": 1.7856309305495113e-05, "loss": 4.1744, "step": 19390 }, { "epoch": 0.5922724496029322, "grad_norm": 0.4130680561065674, "learning_rate": 1.7854010465712988e-05, "loss": 4.1771, "step": 19391 }, { "epoch": 0.5923029932803909, "grad_norm": 0.41342100501060486, "learning_rate": 1.7851711691727675e-05, "loss": 4.2547, "step": 19392 }, { "epoch": 0.5923335369578497, "grad_norm": 0.41445547342300415, "learning_rate": 1.7849412983560315e-05, "loss": 4.1431, "step": 19393 }, { "epoch": 0.5923640806353085, "grad_norm": 0.40538138151168823, "learning_rate": 1.784711434123209e-05, "loss": 4.2409, "step": 19394 }, { "epoch": 0.5923946243127672, "grad_norm": 0.4168015420436859, "learning_rate": 1.784481576476417e-05, "loss": 4.2636, "step": 19395 }, { "epoch": 0.592425167990226, "grad_norm": 0.4085123538970947, "learning_rate": 1.7842517254177698e-05, "loss": 4.256, "step": 19396 }, { "epoch": 0.5924557116676847, "grad_norm": 0.4151148498058319, "learning_rate": 1.784021880949386e-05, "loss": 4.2289, "step": 19397 }, { "epoch": 0.5924862553451435, "grad_norm": 0.407452791929245, "learning_rate": 1.78379204307338e-05, "loss": 4.3022, "step": 19398 }, { "epoch": 0.5925167990226023, "grad_norm": 0.4144078195095062, "learning_rate": 1.7835622117918685e-05, "loss": 4.2504, "step": 19399 }, { "epoch": 0.592547342700061, "grad_norm": 0.4177333414554596, "learning_rate": 1.7833323871069696e-05, "loss": 4.3151, "step": 19400 }, { "epoch": 0.5925778863775198, "grad_norm": 0.40901318192481995, "learning_rate": 1.7831025690207963e-05, "loss": 4.3395, "step": 19401 }, { "epoch": 0.5926084300549787, "grad_norm": 0.4107382297515869, "learning_rate": 1.782872757535467e-05, "loss": 4.2773, "step": 19402 }, { "epoch": 0.5926389737324373, "grad_norm": 0.4129318594932556, "learning_rate": 1.782642952653097e-05, "loss": 4.1543, "step": 19403 }, { "epoch": 0.5926695174098962, "grad_norm": 0.43615084886550903, "learning_rate": 1.782413154375802e-05, "loss": 4.3168, "step": 19404 }, { "epoch": 0.592700061087355, "grad_norm": 0.40750113129615784, "learning_rate": 1.7821833627056976e-05, "loss": 4.2411, "step": 19405 }, { "epoch": 0.5927306047648137, "grad_norm": 0.4108969569206238, "learning_rate": 1.7819535776449014e-05, "loss": 4.3433, "step": 19406 }, { "epoch": 0.5927611484422725, "grad_norm": 0.41082707047462463, "learning_rate": 1.7817237991955264e-05, "loss": 4.291, "step": 19407 }, { "epoch": 0.5927916921197313, "grad_norm": 0.4252144694328308, "learning_rate": 1.7814940273596898e-05, "loss": 4.2715, "step": 19408 }, { "epoch": 0.59282223579719, "grad_norm": 0.41516685485839844, "learning_rate": 1.781264262139508e-05, "loss": 4.3436, "step": 19409 }, { "epoch": 0.5928527794746488, "grad_norm": 0.4117773175239563, "learning_rate": 1.7810345035370955e-05, "loss": 4.2909, "step": 19410 }, { "epoch": 0.5928833231521076, "grad_norm": 0.41606801748275757, "learning_rate": 1.7808047515545673e-05, "loss": 4.2515, "step": 19411 }, { "epoch": 0.5929138668295663, "grad_norm": 0.42613330483436584, "learning_rate": 1.78057500619404e-05, "loss": 4.2299, "step": 19412 }, { "epoch": 0.5929444105070251, "grad_norm": 0.4232316017150879, "learning_rate": 1.7803452674576282e-05, "loss": 4.2491, "step": 19413 }, { "epoch": 0.5929749541844838, "grad_norm": 0.417898952960968, "learning_rate": 1.7801155353474484e-05, "loss": 4.3068, "step": 19414 }, { "epoch": 0.5930054978619426, "grad_norm": 0.4088732600212097, "learning_rate": 1.779885809865614e-05, "loss": 4.3426, "step": 19415 }, { "epoch": 0.5930360415394014, "grad_norm": 0.423431396484375, "learning_rate": 1.779656091014241e-05, "loss": 4.266, "step": 19416 }, { "epoch": 0.5930665852168601, "grad_norm": 0.41132158041000366, "learning_rate": 1.7794263787954458e-05, "loss": 4.307, "step": 19417 }, { "epoch": 0.5930971288943189, "grad_norm": 0.4118538796901703, "learning_rate": 1.7791966732113414e-05, "loss": 4.2505, "step": 19418 }, { "epoch": 0.5931276725717777, "grad_norm": 0.41130000352859497, "learning_rate": 1.7789669742640445e-05, "loss": 4.2459, "step": 19419 }, { "epoch": 0.5931582162492364, "grad_norm": 0.4217052757740021, "learning_rate": 1.7787372819556698e-05, "loss": 4.3437, "step": 19420 }, { "epoch": 0.5931887599266952, "grad_norm": 0.41124820709228516, "learning_rate": 1.778507596288331e-05, "loss": 4.2558, "step": 19421 }, { "epoch": 0.593219303604154, "grad_norm": 0.4153750240802765, "learning_rate": 1.778277917264143e-05, "loss": 4.3117, "step": 19422 }, { "epoch": 0.5932498472816127, "grad_norm": 0.41680797934532166, "learning_rate": 1.778048244885223e-05, "loss": 4.1671, "step": 19423 }, { "epoch": 0.5932803909590715, "grad_norm": 0.42667654156684875, "learning_rate": 1.7778185791536827e-05, "loss": 4.2963, "step": 19424 }, { "epoch": 0.5933109346365303, "grad_norm": 0.4064270853996277, "learning_rate": 1.7775889200716383e-05, "loss": 4.3068, "step": 19425 }, { "epoch": 0.593341478313989, "grad_norm": 0.4204716384410858, "learning_rate": 1.7773592676412045e-05, "loss": 4.347, "step": 19426 }, { "epoch": 0.5933720219914478, "grad_norm": 0.4109514653682709, "learning_rate": 1.7771296218644956e-05, "loss": 4.2475, "step": 19427 }, { "epoch": 0.5934025656689066, "grad_norm": 0.4234694838523865, "learning_rate": 1.776899982743625e-05, "loss": 4.1941, "step": 19428 }, { "epoch": 0.5934331093463653, "grad_norm": 0.41519367694854736, "learning_rate": 1.7766703502807094e-05, "loss": 4.3149, "step": 19429 }, { "epoch": 0.5934636530238241, "grad_norm": 0.4167728126049042, "learning_rate": 1.7764407244778608e-05, "loss": 4.3033, "step": 19430 }, { "epoch": 0.5934941967012828, "grad_norm": 0.42624273896217346, "learning_rate": 1.7762111053371953e-05, "loss": 4.3111, "step": 19431 }, { "epoch": 0.5935247403787416, "grad_norm": 0.4120386242866516, "learning_rate": 1.7759814928608255e-05, "loss": 4.3415, "step": 19432 }, { "epoch": 0.5935552840562004, "grad_norm": 0.4028065800666809, "learning_rate": 1.7757518870508665e-05, "loss": 4.2307, "step": 19433 }, { "epoch": 0.5935858277336591, "grad_norm": 0.4149778187274933, "learning_rate": 1.7755222879094323e-05, "loss": 4.3056, "step": 19434 }, { "epoch": 0.5936163714111179, "grad_norm": 0.4222392141819, "learning_rate": 1.7752926954386372e-05, "loss": 4.2229, "step": 19435 }, { "epoch": 0.5936469150885767, "grad_norm": 0.41513675451278687, "learning_rate": 1.775063109640594e-05, "loss": 4.2382, "step": 19436 }, { "epoch": 0.5936774587660354, "grad_norm": 0.40573906898498535, "learning_rate": 1.7748335305174187e-05, "loss": 4.2417, "step": 19437 }, { "epoch": 0.5937080024434942, "grad_norm": 0.4079432487487793, "learning_rate": 1.774603958071223e-05, "loss": 4.3204, "step": 19438 }, { "epoch": 0.593738546120953, "grad_norm": 0.4213533103466034, "learning_rate": 1.774374392304121e-05, "loss": 4.2368, "step": 19439 }, { "epoch": 0.5937690897984117, "grad_norm": 0.4336179494857788, "learning_rate": 1.774144833218229e-05, "loss": 4.3354, "step": 19440 }, { "epoch": 0.5937996334758705, "grad_norm": 0.4105556607246399, "learning_rate": 1.7739152808156574e-05, "loss": 4.2363, "step": 19441 }, { "epoch": 0.5938301771533293, "grad_norm": 0.4100397825241089, "learning_rate": 1.7736857350985214e-05, "loss": 4.2333, "step": 19442 }, { "epoch": 0.593860720830788, "grad_norm": 0.405224084854126, "learning_rate": 1.7734561960689347e-05, "loss": 4.2059, "step": 19443 }, { "epoch": 0.5938912645082468, "grad_norm": 0.43889278173446655, "learning_rate": 1.7732266637290097e-05, "loss": 4.3228, "step": 19444 }, { "epoch": 0.5939218081857056, "grad_norm": 0.41070979833602905, "learning_rate": 1.7729971380808604e-05, "loss": 4.2293, "step": 19445 }, { "epoch": 0.5939523518631643, "grad_norm": 0.40277132391929626, "learning_rate": 1.7727676191266007e-05, "loss": 4.2164, "step": 19446 }, { "epoch": 0.5939828955406231, "grad_norm": 0.4168623387813568, "learning_rate": 1.7725381068683428e-05, "loss": 4.2656, "step": 19447 }, { "epoch": 0.5940134392180818, "grad_norm": 0.406474769115448, "learning_rate": 1.772308601308202e-05, "loss": 4.3151, "step": 19448 }, { "epoch": 0.5940439828955406, "grad_norm": 0.4217151403427124, "learning_rate": 1.7720791024482884e-05, "loss": 4.2487, "step": 19449 }, { "epoch": 0.5940745265729994, "grad_norm": 0.4184712767601013, "learning_rate": 1.7718496102907177e-05, "loss": 4.3372, "step": 19450 }, { "epoch": 0.5941050702504581, "grad_norm": 0.42646074295043945, "learning_rate": 1.7716201248376024e-05, "loss": 4.1935, "step": 19451 }, { "epoch": 0.5941356139279169, "grad_norm": 0.41502469778060913, "learning_rate": 1.771390646091054e-05, "loss": 4.268, "step": 19452 }, { "epoch": 0.5941661576053757, "grad_norm": 0.42002665996551514, "learning_rate": 1.7711611740531864e-05, "loss": 4.3322, "step": 19453 }, { "epoch": 0.5941967012828344, "grad_norm": 0.41168463230133057, "learning_rate": 1.770931708726114e-05, "loss": 4.2712, "step": 19454 }, { "epoch": 0.5942272449602932, "grad_norm": 0.41006311774253845, "learning_rate": 1.770702250111947e-05, "loss": 4.2667, "step": 19455 }, { "epoch": 0.594257788637752, "grad_norm": 0.42166173458099365, "learning_rate": 1.7704727982128e-05, "loss": 4.2602, "step": 19456 }, { "epoch": 0.5942883323152107, "grad_norm": 0.411660760641098, "learning_rate": 1.770243353030785e-05, "loss": 4.2625, "step": 19457 }, { "epoch": 0.5943188759926695, "grad_norm": 0.4205770194530487, "learning_rate": 1.7700139145680143e-05, "loss": 4.3439, "step": 19458 }, { "epoch": 0.5943494196701283, "grad_norm": 0.4156044125556946, "learning_rate": 1.7697844828266006e-05, "loss": 4.3299, "step": 19459 }, { "epoch": 0.594379963347587, "grad_norm": 0.40331533551216125, "learning_rate": 1.7695550578086577e-05, "loss": 4.2121, "step": 19460 }, { "epoch": 0.5944105070250458, "grad_norm": 0.41628074645996094, "learning_rate": 1.7693256395162956e-05, "loss": 4.3489, "step": 19461 }, { "epoch": 0.5944410507025046, "grad_norm": 0.4215211868286133, "learning_rate": 1.769096227951628e-05, "loss": 4.345, "step": 19462 }, { "epoch": 0.5944715943799633, "grad_norm": 0.4211028516292572, "learning_rate": 1.7688668231167686e-05, "loss": 4.2555, "step": 19463 }, { "epoch": 0.5945021380574221, "grad_norm": 0.41352131962776184, "learning_rate": 1.768637425013827e-05, "loss": 4.3135, "step": 19464 }, { "epoch": 0.5945326817348808, "grad_norm": 0.417233943939209, "learning_rate": 1.768408033644918e-05, "loss": 4.2213, "step": 19465 }, { "epoch": 0.5945632254123396, "grad_norm": 0.4286036193370819, "learning_rate": 1.7681786490121516e-05, "loss": 4.3936, "step": 19466 }, { "epoch": 0.5945937690897984, "grad_norm": 0.4136054813861847, "learning_rate": 1.76794927111764e-05, "loss": 4.3213, "step": 19467 }, { "epoch": 0.5946243127672571, "grad_norm": 0.4293716549873352, "learning_rate": 1.767719899963497e-05, "loss": 4.3136, "step": 19468 }, { "epoch": 0.5946548564447159, "grad_norm": 0.41772255301475525, "learning_rate": 1.7674905355518325e-05, "loss": 4.3479, "step": 19469 }, { "epoch": 0.5946854001221747, "grad_norm": 0.4164806604385376, "learning_rate": 1.7672611778847592e-05, "loss": 4.2329, "step": 19470 }, { "epoch": 0.5947159437996334, "grad_norm": 0.4110364019870758, "learning_rate": 1.76703182696439e-05, "loss": 4.2731, "step": 19471 }, { "epoch": 0.5947464874770922, "grad_norm": 0.4148796796798706, "learning_rate": 1.766802482792835e-05, "loss": 4.2295, "step": 19472 }, { "epoch": 0.594777031154551, "grad_norm": 0.4036722481250763, "learning_rate": 1.7665731453722062e-05, "loss": 4.3291, "step": 19473 }, { "epoch": 0.5948075748320097, "grad_norm": 0.43008285760879517, "learning_rate": 1.766343814704616e-05, "loss": 4.2688, "step": 19474 }, { "epoch": 0.5948381185094685, "grad_norm": 0.4178261458873749, "learning_rate": 1.7661144907921755e-05, "loss": 4.2441, "step": 19475 }, { "epoch": 0.5948686621869274, "grad_norm": 0.4150526225566864, "learning_rate": 1.7658851736369957e-05, "loss": 4.2413, "step": 19476 }, { "epoch": 0.594899205864386, "grad_norm": 0.4177497923374176, "learning_rate": 1.7656558632411893e-05, "loss": 4.3268, "step": 19477 }, { "epoch": 0.5949297495418449, "grad_norm": 0.3968607485294342, "learning_rate": 1.765426559606866e-05, "loss": 4.3398, "step": 19478 }, { "epoch": 0.5949602932193035, "grad_norm": 0.41245096921920776, "learning_rate": 1.7651972627361393e-05, "loss": 4.2097, "step": 19479 }, { "epoch": 0.5949908368967624, "grad_norm": 0.4170399308204651, "learning_rate": 1.764967972631118e-05, "loss": 4.1341, "step": 19480 }, { "epoch": 0.5950213805742212, "grad_norm": 0.42715680599212646, "learning_rate": 1.7647386892939153e-05, "loss": 4.1434, "step": 19481 }, { "epoch": 0.5950519242516799, "grad_norm": 0.421644389629364, "learning_rate": 1.7645094127266418e-05, "loss": 4.2964, "step": 19482 }, { "epoch": 0.5950824679291387, "grad_norm": 0.4237774908542633, "learning_rate": 1.764280142931407e-05, "loss": 4.2768, "step": 19483 }, { "epoch": 0.5951130116065975, "grad_norm": 0.412990927696228, "learning_rate": 1.7640508799103236e-05, "loss": 4.3148, "step": 19484 }, { "epoch": 0.5951435552840562, "grad_norm": 0.41288623213768005, "learning_rate": 1.763821623665503e-05, "loss": 4.2524, "step": 19485 }, { "epoch": 0.595174098961515, "grad_norm": 0.4108606278896332, "learning_rate": 1.7635923741990543e-05, "loss": 4.312, "step": 19486 }, { "epoch": 0.5952046426389738, "grad_norm": 0.4324086606502533, "learning_rate": 1.763363131513089e-05, "loss": 4.2552, "step": 19487 }, { "epoch": 0.5952351863164325, "grad_norm": 0.4106403589248657, "learning_rate": 1.7631338956097193e-05, "loss": 4.2468, "step": 19488 }, { "epoch": 0.5952657299938913, "grad_norm": 0.41507628560066223, "learning_rate": 1.7629046664910543e-05, "loss": 4.2912, "step": 19489 }, { "epoch": 0.5952962736713501, "grad_norm": 0.4130965769290924, "learning_rate": 1.762675444159204e-05, "loss": 4.1881, "step": 19490 }, { "epoch": 0.5953268173488088, "grad_norm": 0.4014265537261963, "learning_rate": 1.7624462286162817e-05, "loss": 4.2837, "step": 19491 }, { "epoch": 0.5953573610262676, "grad_norm": 0.41297876834869385, "learning_rate": 1.7622170198643944e-05, "loss": 4.2906, "step": 19492 }, { "epoch": 0.5953879047037264, "grad_norm": 0.42400306463241577, "learning_rate": 1.7619878179056548e-05, "loss": 4.3232, "step": 19493 }, { "epoch": 0.5954184483811851, "grad_norm": 0.42164334654808044, "learning_rate": 1.761758622742174e-05, "loss": 4.3015, "step": 19494 }, { "epoch": 0.5954489920586439, "grad_norm": 0.41494086384773254, "learning_rate": 1.7615294343760598e-05, "loss": 4.2933, "step": 19495 }, { "epoch": 0.5954795357361026, "grad_norm": 0.41161438822746277, "learning_rate": 1.7613002528094246e-05, "loss": 4.2551, "step": 19496 }, { "epoch": 0.5955100794135614, "grad_norm": 0.40953177213668823, "learning_rate": 1.761071078044378e-05, "loss": 4.3464, "step": 19497 }, { "epoch": 0.5955406230910202, "grad_norm": 0.4169476330280304, "learning_rate": 1.7608419100830288e-05, "loss": 4.3447, "step": 19498 }, { "epoch": 0.5955711667684789, "grad_norm": 0.41501033306121826, "learning_rate": 1.7606127489274892e-05, "loss": 4.196, "step": 19499 }, { "epoch": 0.5956017104459377, "grad_norm": 0.4132348597049713, "learning_rate": 1.7603835945798674e-05, "loss": 4.2304, "step": 19500 }, { "epoch": 0.5956322541233965, "grad_norm": 0.41239362955093384, "learning_rate": 1.7601544470422737e-05, "loss": 4.2924, "step": 19501 }, { "epoch": 0.5956627978008552, "grad_norm": 0.41372448205947876, "learning_rate": 1.7599253063168198e-05, "loss": 4.2407, "step": 19502 }, { "epoch": 0.595693341478314, "grad_norm": 0.4095982611179352, "learning_rate": 1.759696172405613e-05, "loss": 4.3388, "step": 19503 }, { "epoch": 0.5957238851557728, "grad_norm": 0.4080451428890228, "learning_rate": 1.7594670453107648e-05, "loss": 4.3166, "step": 19504 }, { "epoch": 0.5957544288332315, "grad_norm": 0.4160013794898987, "learning_rate": 1.7592379250343847e-05, "loss": 4.3378, "step": 19505 }, { "epoch": 0.5957849725106903, "grad_norm": 0.4001513421535492, "learning_rate": 1.759008811578581e-05, "loss": 4.2564, "step": 19506 }, { "epoch": 0.5958155161881491, "grad_norm": 0.41177067160606384, "learning_rate": 1.7587797049454635e-05, "loss": 4.2887, "step": 19507 }, { "epoch": 0.5958460598656078, "grad_norm": 0.4188779890537262, "learning_rate": 1.758550605137144e-05, "loss": 4.2946, "step": 19508 }, { "epoch": 0.5958766035430666, "grad_norm": 0.41700777411460876, "learning_rate": 1.758321512155729e-05, "loss": 4.3136, "step": 19509 }, { "epoch": 0.5959071472205254, "grad_norm": 0.41416335105895996, "learning_rate": 1.7580924260033293e-05, "loss": 4.1827, "step": 19510 }, { "epoch": 0.5959376908979841, "grad_norm": 0.41903412342071533, "learning_rate": 1.757863346682055e-05, "loss": 4.2631, "step": 19511 }, { "epoch": 0.5959682345754429, "grad_norm": 0.4113200008869171, "learning_rate": 1.757634274194014e-05, "loss": 4.2396, "step": 19512 }, { "epoch": 0.5959987782529016, "grad_norm": 0.41592374444007874, "learning_rate": 1.7574052085413163e-05, "loss": 4.1959, "step": 19513 }, { "epoch": 0.5960293219303604, "grad_norm": 0.41011086106300354, "learning_rate": 1.7571761497260704e-05, "loss": 4.2582, "step": 19514 }, { "epoch": 0.5960598656078192, "grad_norm": 0.41247448325157166, "learning_rate": 1.7569470977503848e-05, "loss": 4.2063, "step": 19515 }, { "epoch": 0.5960904092852779, "grad_norm": 0.4165780544281006, "learning_rate": 1.7567180526163703e-05, "loss": 4.2469, "step": 19516 }, { "epoch": 0.5961209529627367, "grad_norm": 0.40901675820350647, "learning_rate": 1.7564890143261343e-05, "loss": 4.2051, "step": 19517 }, { "epoch": 0.5961514966401955, "grad_norm": 0.41668450832366943, "learning_rate": 1.7562599828817857e-05, "loss": 4.241, "step": 19518 }, { "epoch": 0.5961820403176542, "grad_norm": 0.4194188117980957, "learning_rate": 1.7560309582854352e-05, "loss": 4.3081, "step": 19519 }, { "epoch": 0.596212583995113, "grad_norm": 0.42244160175323486, "learning_rate": 1.7558019405391895e-05, "loss": 4.2346, "step": 19520 }, { "epoch": 0.5962431276725718, "grad_norm": 0.41150546073913574, "learning_rate": 1.7555729296451575e-05, "loss": 4.235, "step": 19521 }, { "epoch": 0.5962736713500305, "grad_norm": 0.4089278280735016, "learning_rate": 1.7553439256054493e-05, "loss": 4.2152, "step": 19522 }, { "epoch": 0.5963042150274893, "grad_norm": 0.4260617792606354, "learning_rate": 1.7551149284221715e-05, "loss": 4.2573, "step": 19523 }, { "epoch": 0.5963347587049481, "grad_norm": 0.4136294424533844, "learning_rate": 1.7548859380974337e-05, "loss": 4.2933, "step": 19524 }, { "epoch": 0.5963653023824068, "grad_norm": 0.40940970182418823, "learning_rate": 1.754656954633345e-05, "loss": 4.2463, "step": 19525 }, { "epoch": 0.5963958460598656, "grad_norm": 0.4121306240558624, "learning_rate": 1.7544279780320117e-05, "loss": 4.2826, "step": 19526 }, { "epoch": 0.5964263897373244, "grad_norm": 0.4138147532939911, "learning_rate": 1.754199008295544e-05, "loss": 4.3373, "step": 19527 }, { "epoch": 0.5964569334147831, "grad_norm": 0.41900384426116943, "learning_rate": 1.7539700454260497e-05, "loss": 4.3131, "step": 19528 }, { "epoch": 0.5964874770922419, "grad_norm": 0.41343796253204346, "learning_rate": 1.753741089425637e-05, "loss": 4.2092, "step": 19529 }, { "epoch": 0.5965180207697006, "grad_norm": 0.4081043601036072, "learning_rate": 1.7535121402964132e-05, "loss": 4.3136, "step": 19530 }, { "epoch": 0.5965485644471594, "grad_norm": 0.425040602684021, "learning_rate": 1.753283198040487e-05, "loss": 4.366, "step": 19531 }, { "epoch": 0.5965791081246182, "grad_norm": 0.4307349622249603, "learning_rate": 1.753054262659966e-05, "loss": 4.3173, "step": 19532 }, { "epoch": 0.5966096518020769, "grad_norm": 0.4118160009384155, "learning_rate": 1.752825334156959e-05, "loss": 4.2709, "step": 19533 }, { "epoch": 0.5966401954795357, "grad_norm": 0.416614294052124, "learning_rate": 1.752596412533573e-05, "loss": 4.3037, "step": 19534 }, { "epoch": 0.5966707391569945, "grad_norm": 0.4089375436306, "learning_rate": 1.752367497791916e-05, "loss": 4.1891, "step": 19535 }, { "epoch": 0.5967012828344532, "grad_norm": 0.4205523729324341, "learning_rate": 1.7521385899340966e-05, "loss": 4.3048, "step": 19536 }, { "epoch": 0.596731826511912, "grad_norm": 0.41368094086647034, "learning_rate": 1.751909688962221e-05, "loss": 4.1939, "step": 19537 }, { "epoch": 0.5967623701893708, "grad_norm": 0.4097531735897064, "learning_rate": 1.751680794878397e-05, "loss": 4.2895, "step": 19538 }, { "epoch": 0.5967929138668295, "grad_norm": 0.4121223986148834, "learning_rate": 1.751451907684734e-05, "loss": 4.1821, "step": 19539 }, { "epoch": 0.5968234575442883, "grad_norm": 0.4227229952812195, "learning_rate": 1.7512230273833372e-05, "loss": 4.3222, "step": 19540 }, { "epoch": 0.5968540012217471, "grad_norm": 0.41774582862854004, "learning_rate": 1.750994153976315e-05, "loss": 4.2886, "step": 19541 }, { "epoch": 0.5968845448992058, "grad_norm": 0.42165735363960266, "learning_rate": 1.7507652874657755e-05, "loss": 4.3308, "step": 19542 }, { "epoch": 0.5969150885766646, "grad_norm": 0.42169907689094543, "learning_rate": 1.7505364278538248e-05, "loss": 4.3726, "step": 19543 }, { "epoch": 0.5969456322541234, "grad_norm": 0.4275985360145569, "learning_rate": 1.75030757514257e-05, "loss": 4.2999, "step": 19544 }, { "epoch": 0.5969761759315821, "grad_norm": 0.4180491864681244, "learning_rate": 1.75007872933412e-05, "loss": 4.3026, "step": 19545 }, { "epoch": 0.597006719609041, "grad_norm": 0.4152076542377472, "learning_rate": 1.7498498904305795e-05, "loss": 4.3437, "step": 19546 }, { "epoch": 0.5970372632864996, "grad_norm": 0.4123433232307434, "learning_rate": 1.7496210584340577e-05, "loss": 4.2188, "step": 19547 }, { "epoch": 0.5970678069639584, "grad_norm": 0.4176740348339081, "learning_rate": 1.7493922333466597e-05, "loss": 4.349, "step": 19548 }, { "epoch": 0.5970983506414173, "grad_norm": 0.4187074601650238, "learning_rate": 1.7491634151704932e-05, "loss": 4.2717, "step": 19549 }, { "epoch": 0.597128894318876, "grad_norm": 0.4106564223766327, "learning_rate": 1.7489346039076663e-05, "loss": 4.3276, "step": 19550 }, { "epoch": 0.5971594379963348, "grad_norm": 0.4097903072834015, "learning_rate": 1.748705799560284e-05, "loss": 4.2598, "step": 19551 }, { "epoch": 0.5971899816737936, "grad_norm": 0.4248608350753784, "learning_rate": 1.7484770021304536e-05, "loss": 4.2248, "step": 19552 }, { "epoch": 0.5972205253512523, "grad_norm": 0.415096640586853, "learning_rate": 1.748248211620283e-05, "loss": 4.2836, "step": 19553 }, { "epoch": 0.5972510690287111, "grad_norm": 0.414457768201828, "learning_rate": 1.7480194280318763e-05, "loss": 4.3456, "step": 19554 }, { "epoch": 0.5972816127061699, "grad_norm": 0.42489275336265564, "learning_rate": 1.7477906513673407e-05, "loss": 4.291, "step": 19555 }, { "epoch": 0.5973121563836286, "grad_norm": 0.4207597076892853, "learning_rate": 1.7475618816287852e-05, "loss": 4.2246, "step": 19556 }, { "epoch": 0.5973427000610874, "grad_norm": 0.41341906785964966, "learning_rate": 1.747333118818313e-05, "loss": 4.2222, "step": 19557 }, { "epoch": 0.5973732437385462, "grad_norm": 0.4094640910625458, "learning_rate": 1.7471043629380324e-05, "loss": 4.2276, "step": 19558 }, { "epoch": 0.5974037874160049, "grad_norm": 0.4102701246738434, "learning_rate": 1.746875613990049e-05, "loss": 4.1238, "step": 19559 }, { "epoch": 0.5974343310934637, "grad_norm": 0.4147556722164154, "learning_rate": 1.746646871976469e-05, "loss": 4.2838, "step": 19560 }, { "epoch": 0.5974648747709225, "grad_norm": 0.4170129895210266, "learning_rate": 1.7464181368993982e-05, "loss": 4.351, "step": 19561 }, { "epoch": 0.5974954184483812, "grad_norm": 0.423079252243042, "learning_rate": 1.7461894087609438e-05, "loss": 4.3095, "step": 19562 }, { "epoch": 0.59752596212584, "grad_norm": 0.4071657657623291, "learning_rate": 1.74596068756321e-05, "loss": 4.277, "step": 19563 }, { "epoch": 0.5975565058032987, "grad_norm": 0.4159005880355835, "learning_rate": 1.7457319733083053e-05, "loss": 4.0954, "step": 19564 }, { "epoch": 0.5975870494807575, "grad_norm": 0.41710492968559265, "learning_rate": 1.7455032659983328e-05, "loss": 4.3051, "step": 19565 }, { "epoch": 0.5976175931582163, "grad_norm": 0.41712647676467896, "learning_rate": 1.7452745656354002e-05, "loss": 4.2082, "step": 19566 }, { "epoch": 0.597648136835675, "grad_norm": 0.4097483158111572, "learning_rate": 1.7450458722216127e-05, "loss": 4.2946, "step": 19567 }, { "epoch": 0.5976786805131338, "grad_norm": 0.4075736999511719, "learning_rate": 1.7448171857590763e-05, "loss": 4.352, "step": 19568 }, { "epoch": 0.5977092241905926, "grad_norm": 0.4200708270072937, "learning_rate": 1.7445885062498954e-05, "loss": 4.2471, "step": 19569 }, { "epoch": 0.5977397678680513, "grad_norm": 0.4163135886192322, "learning_rate": 1.7443598336961776e-05, "loss": 4.2929, "step": 19570 }, { "epoch": 0.5977703115455101, "grad_norm": 0.4186095595359802, "learning_rate": 1.7441311681000265e-05, "loss": 4.3038, "step": 19571 }, { "epoch": 0.5978008552229689, "grad_norm": 0.4032991826534271, "learning_rate": 1.7439025094635483e-05, "loss": 4.2739, "step": 19572 }, { "epoch": 0.5978313989004276, "grad_norm": 0.4175022542476654, "learning_rate": 1.7436738577888495e-05, "loss": 4.2937, "step": 19573 }, { "epoch": 0.5978619425778864, "grad_norm": 0.41650664806365967, "learning_rate": 1.743445213078033e-05, "loss": 4.2852, "step": 19574 }, { "epoch": 0.5978924862553452, "grad_norm": 0.415242999792099, "learning_rate": 1.7432165753332065e-05, "loss": 4.2453, "step": 19575 }, { "epoch": 0.5979230299328039, "grad_norm": 0.4147113263607025, "learning_rate": 1.7429879445564744e-05, "loss": 4.3044, "step": 19576 }, { "epoch": 0.5979535736102627, "grad_norm": 0.4111514389514923, "learning_rate": 1.7427593207499406e-05, "loss": 4.3093, "step": 19577 }, { "epoch": 0.5979841172877215, "grad_norm": 0.40936851501464844, "learning_rate": 1.7425307039157106e-05, "loss": 4.2592, "step": 19578 }, { "epoch": 0.5980146609651802, "grad_norm": 0.4175778031349182, "learning_rate": 1.7423020940558914e-05, "loss": 4.2553, "step": 19579 }, { "epoch": 0.598045204642639, "grad_norm": 0.40947121381759644, "learning_rate": 1.742073491172585e-05, "loss": 4.3068, "step": 19580 }, { "epoch": 0.5980757483200977, "grad_norm": 0.4133935868740082, "learning_rate": 1.7418448952678986e-05, "loss": 4.3745, "step": 19581 }, { "epoch": 0.5981062919975565, "grad_norm": 0.41117730736732483, "learning_rate": 1.7416163063439352e-05, "loss": 4.2444, "step": 19582 }, { "epoch": 0.5981368356750153, "grad_norm": 0.47217124700546265, "learning_rate": 1.741387724402801e-05, "loss": 4.2463, "step": 19583 }, { "epoch": 0.598167379352474, "grad_norm": 0.41743919253349304, "learning_rate": 1.7411591494466006e-05, "loss": 4.3334, "step": 19584 }, { "epoch": 0.5981979230299328, "grad_norm": 0.4302535951137543, "learning_rate": 1.7409305814774368e-05, "loss": 4.3051, "step": 19585 }, { "epoch": 0.5982284667073916, "grad_norm": 0.4244992733001709, "learning_rate": 1.7407020204974156e-05, "loss": 4.2165, "step": 19586 }, { "epoch": 0.5982590103848503, "grad_norm": 0.40790459513664246, "learning_rate": 1.7404734665086424e-05, "loss": 4.3032, "step": 19587 }, { "epoch": 0.5982895540623091, "grad_norm": 0.41068750619888306, "learning_rate": 1.740244919513219e-05, "loss": 4.217, "step": 19588 }, { "epoch": 0.5983200977397679, "grad_norm": 0.40599727630615234, "learning_rate": 1.7400163795132523e-05, "loss": 4.2479, "step": 19589 }, { "epoch": 0.5983506414172266, "grad_norm": 0.41556450724601746, "learning_rate": 1.7397878465108456e-05, "loss": 4.2621, "step": 19590 }, { "epoch": 0.5983811850946854, "grad_norm": 0.4092918932437897, "learning_rate": 1.739559320508103e-05, "loss": 4.2733, "step": 19591 }, { "epoch": 0.5984117287721442, "grad_norm": 0.41922786831855774, "learning_rate": 1.7393308015071278e-05, "loss": 4.2308, "step": 19592 }, { "epoch": 0.5984422724496029, "grad_norm": 0.40937891602516174, "learning_rate": 1.739102289510026e-05, "loss": 4.3044, "step": 19593 }, { "epoch": 0.5984728161270617, "grad_norm": 0.41555267572402954, "learning_rate": 1.7388737845189e-05, "loss": 4.31, "step": 19594 }, { "epoch": 0.5985033598045205, "grad_norm": 0.41084542870521545, "learning_rate": 1.7386452865358545e-05, "loss": 4.3869, "step": 19595 }, { "epoch": 0.5985339034819792, "grad_norm": 0.41123729944229126, "learning_rate": 1.738416795562994e-05, "loss": 4.1797, "step": 19596 }, { "epoch": 0.598564447159438, "grad_norm": 0.41406306624412537, "learning_rate": 1.7381883116024205e-05, "loss": 4.2862, "step": 19597 }, { "epoch": 0.5985949908368967, "grad_norm": 0.42845597863197327, "learning_rate": 1.7379598346562402e-05, "loss": 4.3087, "step": 19598 }, { "epoch": 0.5986255345143555, "grad_norm": 0.42201995849609375, "learning_rate": 1.737731364726555e-05, "loss": 4.1874, "step": 19599 }, { "epoch": 0.5986560781918143, "grad_norm": 0.4206920862197876, "learning_rate": 1.7375029018154686e-05, "loss": 4.2453, "step": 19600 }, { "epoch": 0.598686621869273, "grad_norm": 0.42279186844825745, "learning_rate": 1.7372744459250857e-05, "loss": 4.1178, "step": 19601 }, { "epoch": 0.5987171655467318, "grad_norm": 0.40593743324279785, "learning_rate": 1.737045997057508e-05, "loss": 4.2346, "step": 19602 }, { "epoch": 0.5987477092241906, "grad_norm": 0.4084257185459137, "learning_rate": 1.7368175552148407e-05, "loss": 4.2571, "step": 19603 }, { "epoch": 0.5987782529016493, "grad_norm": 0.41435396671295166, "learning_rate": 1.7365891203991874e-05, "loss": 4.1807, "step": 19604 }, { "epoch": 0.5988087965791081, "grad_norm": 0.41604337096214294, "learning_rate": 1.7363606926126493e-05, "loss": 4.1573, "step": 19605 }, { "epoch": 0.5988393402565669, "grad_norm": 0.4050212502479553, "learning_rate": 1.7361322718573316e-05, "loss": 4.2703, "step": 19606 }, { "epoch": 0.5988698839340256, "grad_norm": 0.4158697724342346, "learning_rate": 1.735903858135337e-05, "loss": 4.3596, "step": 19607 }, { "epoch": 0.5989004276114844, "grad_norm": 0.41464754939079285, "learning_rate": 1.7356754514487677e-05, "loss": 4.2983, "step": 19608 }, { "epoch": 0.5989309712889432, "grad_norm": 0.415538489818573, "learning_rate": 1.7354470517997276e-05, "loss": 4.3256, "step": 19609 }, { "epoch": 0.5989615149664019, "grad_norm": 0.41387084126472473, "learning_rate": 1.7352186591903206e-05, "loss": 4.1961, "step": 19610 }, { "epoch": 0.5989920586438607, "grad_norm": 0.42785388231277466, "learning_rate": 1.7349902736226476e-05, "loss": 4.2232, "step": 19611 }, { "epoch": 0.5990226023213195, "grad_norm": 0.41953015327453613, "learning_rate": 1.7347618950988128e-05, "loss": 4.2768, "step": 19612 }, { "epoch": 0.5990531459987782, "grad_norm": 0.4185953736305237, "learning_rate": 1.734533523620919e-05, "loss": 4.2844, "step": 19613 }, { "epoch": 0.599083689676237, "grad_norm": 0.4174289107322693, "learning_rate": 1.7343051591910682e-05, "loss": 4.2418, "step": 19614 }, { "epoch": 0.5991142333536957, "grad_norm": 0.41957396268844604, "learning_rate": 1.734076801811364e-05, "loss": 4.2364, "step": 19615 }, { "epoch": 0.5991447770311545, "grad_norm": 0.42991042137145996, "learning_rate": 1.7338484514839076e-05, "loss": 4.3102, "step": 19616 }, { "epoch": 0.5991753207086133, "grad_norm": 0.42130327224731445, "learning_rate": 1.7336201082108024e-05, "loss": 4.2326, "step": 19617 }, { "epoch": 0.599205864386072, "grad_norm": 0.42572224140167236, "learning_rate": 1.733391771994152e-05, "loss": 4.2271, "step": 19618 }, { "epoch": 0.5992364080635308, "grad_norm": 0.40682360529899597, "learning_rate": 1.7331634428360565e-05, "loss": 4.3641, "step": 19619 }, { "epoch": 0.5992669517409897, "grad_norm": 0.4112112820148468, "learning_rate": 1.7329351207386195e-05, "loss": 4.2671, "step": 19620 }, { "epoch": 0.5992974954184483, "grad_norm": 0.41642582416534424, "learning_rate": 1.7327068057039447e-05, "loss": 4.2895, "step": 19621 }, { "epoch": 0.5993280390959072, "grad_norm": 0.4129098355770111, "learning_rate": 1.732478497734132e-05, "loss": 4.246, "step": 19622 }, { "epoch": 0.599358582773366, "grad_norm": 0.40512239933013916, "learning_rate": 1.7322501968312837e-05, "loss": 4.25, "step": 19623 }, { "epoch": 0.5993891264508246, "grad_norm": 0.4220920503139496, "learning_rate": 1.732021902997504e-05, "loss": 4.2639, "step": 19624 }, { "epoch": 0.5994196701282835, "grad_norm": 0.4214065968990326, "learning_rate": 1.731793616234892e-05, "loss": 4.2423, "step": 19625 }, { "epoch": 0.5994502138057423, "grad_norm": 0.40804681181907654, "learning_rate": 1.7315653365455515e-05, "loss": 4.2582, "step": 19626 }, { "epoch": 0.599480757483201, "grad_norm": 0.4050791263580322, "learning_rate": 1.7313370639315848e-05, "loss": 4.2061, "step": 19627 }, { "epoch": 0.5995113011606598, "grad_norm": 0.411510169506073, "learning_rate": 1.7311087983950923e-05, "loss": 4.2964, "step": 19628 }, { "epoch": 0.5995418448381185, "grad_norm": 0.41258224844932556, "learning_rate": 1.7308805399381774e-05, "loss": 4.2568, "step": 19629 }, { "epoch": 0.5995723885155773, "grad_norm": 0.4276440739631653, "learning_rate": 1.7306522885629397e-05, "loss": 4.2472, "step": 19630 }, { "epoch": 0.5996029321930361, "grad_norm": 0.4250119924545288, "learning_rate": 1.730424044271482e-05, "loss": 4.3135, "step": 19631 }, { "epoch": 0.5996334758704948, "grad_norm": 0.40911734104156494, "learning_rate": 1.7301958070659065e-05, "loss": 4.2951, "step": 19632 }, { "epoch": 0.5996640195479536, "grad_norm": 0.4167598783969879, "learning_rate": 1.7299675769483132e-05, "loss": 4.2662, "step": 19633 }, { "epoch": 0.5996945632254124, "grad_norm": 0.4202461838722229, "learning_rate": 1.7297393539208044e-05, "loss": 4.2755, "step": 19634 }, { "epoch": 0.5997251069028711, "grad_norm": 0.43020135164260864, "learning_rate": 1.7295111379854822e-05, "loss": 4.2917, "step": 19635 }, { "epoch": 0.5997556505803299, "grad_norm": 0.4199417531490326, "learning_rate": 1.729282929144446e-05, "loss": 4.2481, "step": 19636 }, { "epoch": 0.5997861942577887, "grad_norm": 0.41251125931739807, "learning_rate": 1.729054727399799e-05, "loss": 4.2457, "step": 19637 }, { "epoch": 0.5998167379352474, "grad_norm": 0.4230957627296448, "learning_rate": 1.7288265327536412e-05, "loss": 4.2454, "step": 19638 }, { "epoch": 0.5998472816127062, "grad_norm": 0.40864938497543335, "learning_rate": 1.7285983452080742e-05, "loss": 4.3194, "step": 19639 }, { "epoch": 0.599877825290165, "grad_norm": 0.41677072644233704, "learning_rate": 1.7283701647651984e-05, "loss": 4.2984, "step": 19640 }, { "epoch": 0.5999083689676237, "grad_norm": 0.41302257776260376, "learning_rate": 1.728141991427116e-05, "loss": 4.3565, "step": 19641 }, { "epoch": 0.5999389126450825, "grad_norm": 0.42297521233558655, "learning_rate": 1.7279138251959263e-05, "loss": 4.287, "step": 19642 }, { "epoch": 0.5999694563225413, "grad_norm": 0.4139910638332367, "learning_rate": 1.727685666073731e-05, "loss": 4.2446, "step": 19643 }, { "epoch": 0.6, "grad_norm": 0.42089611291885376, "learning_rate": 1.7274575140626318e-05, "loss": 4.2409, "step": 19644 }, { "epoch": 0.6000305436774588, "grad_norm": 0.42414242029190063, "learning_rate": 1.727229369164728e-05, "loss": 4.2731, "step": 19645 }, { "epoch": 0.6000610873549175, "grad_norm": 0.4100324213504791, "learning_rate": 1.7270012313821206e-05, "loss": 4.3162, "step": 19646 }, { "epoch": 0.6000916310323763, "grad_norm": 0.4154488742351532, "learning_rate": 1.7267731007169103e-05, "loss": 4.2563, "step": 19647 }, { "epoch": 0.6001221747098351, "grad_norm": 0.4264897108078003, "learning_rate": 1.7265449771711972e-05, "loss": 4.1571, "step": 19648 }, { "epoch": 0.6001527183872938, "grad_norm": 0.4245768189430237, "learning_rate": 1.726316860747083e-05, "loss": 4.253, "step": 19649 }, { "epoch": 0.6001832620647526, "grad_norm": 0.42340731620788574, "learning_rate": 1.7260887514466667e-05, "loss": 4.3198, "step": 19650 }, { "epoch": 0.6002138057422114, "grad_norm": 0.4287507236003876, "learning_rate": 1.7258606492720486e-05, "loss": 4.2576, "step": 19651 }, { "epoch": 0.6002443494196701, "grad_norm": 0.4271126985549927, "learning_rate": 1.725632554225331e-05, "loss": 4.2491, "step": 19652 }, { "epoch": 0.6002748930971289, "grad_norm": 0.42189696431159973, "learning_rate": 1.7254044663086117e-05, "loss": 4.3104, "step": 19653 }, { "epoch": 0.6003054367745877, "grad_norm": 0.4134884178638458, "learning_rate": 1.7251763855239916e-05, "loss": 4.3266, "step": 19654 }, { "epoch": 0.6003359804520464, "grad_norm": 0.4100598096847534, "learning_rate": 1.7249483118735715e-05, "loss": 4.2998, "step": 19655 }, { "epoch": 0.6003665241295052, "grad_norm": 0.41000351309776306, "learning_rate": 1.72472024535945e-05, "loss": 4.2288, "step": 19656 }, { "epoch": 0.600397067806964, "grad_norm": 0.4225384593009949, "learning_rate": 1.7244921859837282e-05, "loss": 4.3177, "step": 19657 }, { "epoch": 0.6004276114844227, "grad_norm": 0.4095531404018402, "learning_rate": 1.724264133748506e-05, "loss": 4.2794, "step": 19658 }, { "epoch": 0.6004581551618815, "grad_norm": 0.4137973189353943, "learning_rate": 1.724036088655882e-05, "loss": 4.193, "step": 19659 }, { "epoch": 0.6004886988393403, "grad_norm": 0.4218757748603821, "learning_rate": 1.723808050707957e-05, "loss": 4.3159, "step": 19660 }, { "epoch": 0.600519242516799, "grad_norm": 0.40808141231536865, "learning_rate": 1.723580019906831e-05, "loss": 4.1733, "step": 19661 }, { "epoch": 0.6005497861942578, "grad_norm": 0.41658687591552734, "learning_rate": 1.723351996254602e-05, "loss": 4.2195, "step": 19662 }, { "epoch": 0.6005803298717165, "grad_norm": 0.4157029986381531, "learning_rate": 1.7231239797533716e-05, "loss": 4.2001, "step": 19663 }, { "epoch": 0.6006108735491753, "grad_norm": 0.4187282919883728, "learning_rate": 1.722895970405237e-05, "loss": 4.2155, "step": 19664 }, { "epoch": 0.6006414172266341, "grad_norm": 0.42749688029289246, "learning_rate": 1.7226679682122986e-05, "loss": 4.3885, "step": 19665 }, { "epoch": 0.6006719609040928, "grad_norm": 0.41462209820747375, "learning_rate": 1.722439973176657e-05, "loss": 4.3005, "step": 19666 }, { "epoch": 0.6007025045815516, "grad_norm": 0.4228743314743042, "learning_rate": 1.7222119853004097e-05, "loss": 4.2654, "step": 19667 }, { "epoch": 0.6007330482590104, "grad_norm": 0.41238170862197876, "learning_rate": 1.7219840045856568e-05, "loss": 4.2543, "step": 19668 }, { "epoch": 0.6007635919364691, "grad_norm": 0.4089946746826172, "learning_rate": 1.7217560310344967e-05, "loss": 4.209, "step": 19669 }, { "epoch": 0.6007941356139279, "grad_norm": 0.41894444823265076, "learning_rate": 1.7215280646490294e-05, "loss": 4.1208, "step": 19670 }, { "epoch": 0.6008246792913867, "grad_norm": 0.41865938901901245, "learning_rate": 1.7213001054313533e-05, "loss": 4.2242, "step": 19671 }, { "epoch": 0.6008552229688454, "grad_norm": 0.4168911278247833, "learning_rate": 1.7210721533835676e-05, "loss": 4.3061, "step": 19672 }, { "epoch": 0.6008857666463042, "grad_norm": 0.4189281463623047, "learning_rate": 1.7208442085077708e-05, "loss": 4.1891, "step": 19673 }, { "epoch": 0.600916310323763, "grad_norm": 0.4102969467639923, "learning_rate": 1.7206162708060618e-05, "loss": 4.2896, "step": 19674 }, { "epoch": 0.6009468540012217, "grad_norm": 0.4158555269241333, "learning_rate": 1.7203883402805403e-05, "loss": 4.2573, "step": 19675 }, { "epoch": 0.6009773976786805, "grad_norm": 0.4314243495464325, "learning_rate": 1.7201604169333042e-05, "loss": 4.2379, "step": 19676 }, { "epoch": 0.6010079413561393, "grad_norm": 0.41136738657951355, "learning_rate": 1.719932500766451e-05, "loss": 4.2936, "step": 19677 }, { "epoch": 0.601038485033598, "grad_norm": 0.4237667918205261, "learning_rate": 1.719704591782082e-05, "loss": 4.2885, "step": 19678 }, { "epoch": 0.6010690287110568, "grad_norm": 0.4185526371002197, "learning_rate": 1.7194766899822924e-05, "loss": 4.2891, "step": 19679 }, { "epoch": 0.6010995723885155, "grad_norm": 0.4207238554954529, "learning_rate": 1.7192487953691837e-05, "loss": 4.2069, "step": 19680 }, { "epoch": 0.6011301160659743, "grad_norm": 0.4112640619277954, "learning_rate": 1.7190209079448514e-05, "loss": 4.274, "step": 19681 }, { "epoch": 0.6011606597434331, "grad_norm": 0.428075909614563, "learning_rate": 1.718793027711395e-05, "loss": 4.3389, "step": 19682 }, { "epoch": 0.6011912034208918, "grad_norm": 0.4141707420349121, "learning_rate": 1.7185651546709142e-05, "loss": 4.2718, "step": 19683 }, { "epoch": 0.6012217470983506, "grad_norm": 0.40898892283439636, "learning_rate": 1.7183372888255045e-05, "loss": 4.2428, "step": 19684 }, { "epoch": 0.6012522907758094, "grad_norm": 0.4221579432487488, "learning_rate": 1.718109430177266e-05, "loss": 4.3176, "step": 19685 }, { "epoch": 0.6012828344532681, "grad_norm": 0.4249706566333771, "learning_rate": 1.7178815787282965e-05, "loss": 4.3482, "step": 19686 }, { "epoch": 0.6013133781307269, "grad_norm": 0.42198535799980164, "learning_rate": 1.7176537344806925e-05, "loss": 4.3127, "step": 19687 }, { "epoch": 0.6013439218081857, "grad_norm": 0.4132598638534546, "learning_rate": 1.7174258974365527e-05, "loss": 4.2012, "step": 19688 }, { "epoch": 0.6013744654856444, "grad_norm": 0.4420413672924042, "learning_rate": 1.717198067597976e-05, "loss": 4.205, "step": 19689 }, { "epoch": 0.6014050091631032, "grad_norm": 0.4280628263950348, "learning_rate": 1.7169702449670582e-05, "loss": 4.291, "step": 19690 }, { "epoch": 0.601435552840562, "grad_norm": 0.42447516322135925, "learning_rate": 1.7167424295458983e-05, "loss": 4.2607, "step": 19691 }, { "epoch": 0.6014660965180207, "grad_norm": 0.41226643323898315, "learning_rate": 1.7165146213365938e-05, "loss": 4.3258, "step": 19692 }, { "epoch": 0.6014966401954795, "grad_norm": 0.41558337211608887, "learning_rate": 1.7162868203412418e-05, "loss": 4.264, "step": 19693 }, { "epoch": 0.6015271838729384, "grad_norm": 0.42389044165611267, "learning_rate": 1.7160590265619397e-05, "loss": 4.2192, "step": 19694 }, { "epoch": 0.601557727550397, "grad_norm": 0.41772863268852234, "learning_rate": 1.7158312400007858e-05, "loss": 4.2646, "step": 19695 }, { "epoch": 0.6015882712278559, "grad_norm": 0.4112403988838196, "learning_rate": 1.7156034606598765e-05, "loss": 4.2274, "step": 19696 }, { "epoch": 0.6016188149053145, "grad_norm": 0.42560458183288574, "learning_rate": 1.71537568854131e-05, "loss": 4.3054, "step": 19697 }, { "epoch": 0.6016493585827734, "grad_norm": 0.40883728861808777, "learning_rate": 1.7151479236471818e-05, "loss": 4.2437, "step": 19698 }, { "epoch": 0.6016799022602322, "grad_norm": 0.4138837158679962, "learning_rate": 1.714920165979591e-05, "loss": 4.2023, "step": 19699 }, { "epoch": 0.6017104459376909, "grad_norm": 0.41451090574264526, "learning_rate": 1.714692415540634e-05, "loss": 4.2677, "step": 19700 }, { "epoch": 0.6017409896151497, "grad_norm": 0.42048829793930054, "learning_rate": 1.7144646723324074e-05, "loss": 4.2412, "step": 19701 }, { "epoch": 0.6017715332926085, "grad_norm": 0.42872506380081177, "learning_rate": 1.714236936357008e-05, "loss": 4.2695, "step": 19702 }, { "epoch": 0.6018020769700672, "grad_norm": 0.42439013719558716, "learning_rate": 1.7140092076165342e-05, "loss": 4.2371, "step": 19703 }, { "epoch": 0.601832620647526, "grad_norm": 0.42000848054885864, "learning_rate": 1.7137814861130807e-05, "loss": 4.4155, "step": 19704 }, { "epoch": 0.6018631643249848, "grad_norm": 0.41652098298072815, "learning_rate": 1.7135537718487454e-05, "loss": 4.3329, "step": 19705 }, { "epoch": 0.6018937080024435, "grad_norm": 0.41977331042289734, "learning_rate": 1.7133260648256254e-05, "loss": 4.2521, "step": 19706 }, { "epoch": 0.6019242516799023, "grad_norm": 0.41309812664985657, "learning_rate": 1.7130983650458165e-05, "loss": 4.3009, "step": 19707 }, { "epoch": 0.6019547953573611, "grad_norm": 0.44788557291030884, "learning_rate": 1.7128706725114156e-05, "loss": 4.3205, "step": 19708 }, { "epoch": 0.6019853390348198, "grad_norm": 0.4296742081642151, "learning_rate": 1.7126429872245197e-05, "loss": 4.2978, "step": 19709 }, { "epoch": 0.6020158827122786, "grad_norm": 0.41804373264312744, "learning_rate": 1.7124153091872235e-05, "loss": 4.3263, "step": 19710 }, { "epoch": 0.6020464263897374, "grad_norm": 0.4296393096446991, "learning_rate": 1.712187638401625e-05, "loss": 4.2492, "step": 19711 }, { "epoch": 0.6020769700671961, "grad_norm": 0.43271195888519287, "learning_rate": 1.7119599748698207e-05, "loss": 4.2904, "step": 19712 }, { "epoch": 0.6021075137446549, "grad_norm": 0.4175255298614502, "learning_rate": 1.711732318593905e-05, "loss": 4.3029, "step": 19713 }, { "epoch": 0.6021380574221136, "grad_norm": 0.42090845108032227, "learning_rate": 1.7115046695759758e-05, "loss": 4.2851, "step": 19714 }, { "epoch": 0.6021686010995724, "grad_norm": 0.4348422884941101, "learning_rate": 1.7112770278181278e-05, "loss": 4.281, "step": 19715 }, { "epoch": 0.6021991447770312, "grad_norm": 0.4360603988170624, "learning_rate": 1.7110493933224583e-05, "loss": 4.2739, "step": 19716 }, { "epoch": 0.6022296884544899, "grad_norm": 0.4099327325820923, "learning_rate": 1.7108217660910633e-05, "loss": 4.1927, "step": 19717 }, { "epoch": 0.6022602321319487, "grad_norm": 0.41383787989616394, "learning_rate": 1.7105941461260367e-05, "loss": 4.2505, "step": 19718 }, { "epoch": 0.6022907758094075, "grad_norm": 0.4300900995731354, "learning_rate": 1.710366533429476e-05, "loss": 4.2183, "step": 19719 }, { "epoch": 0.6023213194868662, "grad_norm": 0.4182938039302826, "learning_rate": 1.7101389280034773e-05, "loss": 4.3522, "step": 19720 }, { "epoch": 0.602351863164325, "grad_norm": 0.42197027802467346, "learning_rate": 1.709911329850135e-05, "loss": 4.2396, "step": 19721 }, { "epoch": 0.6023824068417838, "grad_norm": 0.40945178270339966, "learning_rate": 1.7096837389715454e-05, "loss": 4.3375, "step": 19722 }, { "epoch": 0.6024129505192425, "grad_norm": 0.4165823459625244, "learning_rate": 1.7094561553698042e-05, "loss": 4.2335, "step": 19723 }, { "epoch": 0.6024434941967013, "grad_norm": 0.426016241312027, "learning_rate": 1.7092285790470067e-05, "loss": 4.2216, "step": 19724 }, { "epoch": 0.6024740378741601, "grad_norm": 0.42012059688568115, "learning_rate": 1.7090010100052475e-05, "loss": 4.1704, "step": 19725 }, { "epoch": 0.6025045815516188, "grad_norm": 0.40955913066864014, "learning_rate": 1.708773448246624e-05, "loss": 4.2492, "step": 19726 }, { "epoch": 0.6025351252290776, "grad_norm": 0.4107974171638489, "learning_rate": 1.7085458937732286e-05, "loss": 4.2546, "step": 19727 }, { "epoch": 0.6025656689065364, "grad_norm": 0.41968730092048645, "learning_rate": 1.708318346587159e-05, "loss": 4.3296, "step": 19728 }, { "epoch": 0.6025962125839951, "grad_norm": 0.4240012466907501, "learning_rate": 1.7080908066905092e-05, "loss": 4.2396, "step": 19729 }, { "epoch": 0.6026267562614539, "grad_norm": 0.41951414942741394, "learning_rate": 1.7078632740853746e-05, "loss": 4.2739, "step": 19730 }, { "epoch": 0.6026572999389126, "grad_norm": 0.41562867164611816, "learning_rate": 1.7076357487738505e-05, "loss": 4.1764, "step": 19731 }, { "epoch": 0.6026878436163714, "grad_norm": 0.4235726594924927, "learning_rate": 1.7074082307580313e-05, "loss": 4.3426, "step": 19732 }, { "epoch": 0.6027183872938302, "grad_norm": 0.42524856328964233, "learning_rate": 1.7071807200400115e-05, "loss": 4.2615, "step": 19733 }, { "epoch": 0.6027489309712889, "grad_norm": 0.40785515308380127, "learning_rate": 1.706953216621887e-05, "loss": 4.2248, "step": 19734 }, { "epoch": 0.6027794746487477, "grad_norm": 0.427812397480011, "learning_rate": 1.7067257205057512e-05, "loss": 4.1865, "step": 19735 }, { "epoch": 0.6028100183262065, "grad_norm": 0.415260910987854, "learning_rate": 1.7064982316937002e-05, "loss": 4.2561, "step": 19736 }, { "epoch": 0.6028405620036652, "grad_norm": 0.4423210918903351, "learning_rate": 1.7062707501878284e-05, "loss": 4.2834, "step": 19737 }, { "epoch": 0.602871105681124, "grad_norm": 0.41990926861763, "learning_rate": 1.7060432759902288e-05, "loss": 4.2212, "step": 19738 }, { "epoch": 0.6029016493585828, "grad_norm": 0.4197322428226471, "learning_rate": 1.7058158091029974e-05, "loss": 4.2992, "step": 19739 }, { "epoch": 0.6029321930360415, "grad_norm": 0.41733771562576294, "learning_rate": 1.7055883495282286e-05, "loss": 4.3447, "step": 19740 }, { "epoch": 0.6029627367135003, "grad_norm": 0.41924476623535156, "learning_rate": 1.705360897268016e-05, "loss": 4.201, "step": 19741 }, { "epoch": 0.6029932803909591, "grad_norm": 0.4182184338569641, "learning_rate": 1.7051334523244537e-05, "loss": 4.2789, "step": 19742 }, { "epoch": 0.6030238240684178, "grad_norm": 0.42298081517219543, "learning_rate": 1.7049060146996374e-05, "loss": 4.2581, "step": 19743 }, { "epoch": 0.6030543677458766, "grad_norm": 0.4241239130496979, "learning_rate": 1.704678584395659e-05, "loss": 4.3529, "step": 19744 }, { "epoch": 0.6030849114233354, "grad_norm": 0.42369797825813293, "learning_rate": 1.7044511614146147e-05, "loss": 4.3165, "step": 19745 }, { "epoch": 0.6031154551007941, "grad_norm": 0.41551652550697327, "learning_rate": 1.7042237457585974e-05, "loss": 4.4097, "step": 19746 }, { "epoch": 0.6031459987782529, "grad_norm": 0.4211517870426178, "learning_rate": 1.7039963374297014e-05, "loss": 4.2997, "step": 19747 }, { "epoch": 0.6031765424557116, "grad_norm": 0.43507152795791626, "learning_rate": 1.70376893643002e-05, "loss": 4.2578, "step": 19748 }, { "epoch": 0.6032070861331704, "grad_norm": 0.4173317551612854, "learning_rate": 1.7035415427616476e-05, "loss": 4.272, "step": 19749 }, { "epoch": 0.6032376298106292, "grad_norm": 0.4256918132305145, "learning_rate": 1.7033141564266773e-05, "loss": 4.3177, "step": 19750 }, { "epoch": 0.6032681734880879, "grad_norm": 0.4180830419063568, "learning_rate": 1.703086777427204e-05, "loss": 4.3391, "step": 19751 }, { "epoch": 0.6032987171655467, "grad_norm": 0.4161113202571869, "learning_rate": 1.7028594057653198e-05, "loss": 4.2669, "step": 19752 }, { "epoch": 0.6033292608430055, "grad_norm": 0.41005536913871765, "learning_rate": 1.7026320414431186e-05, "loss": 4.2384, "step": 19753 }, { "epoch": 0.6033598045204642, "grad_norm": 0.4187007546424866, "learning_rate": 1.7024046844626954e-05, "loss": 4.3666, "step": 19754 }, { "epoch": 0.603390348197923, "grad_norm": 0.42739206552505493, "learning_rate": 1.7021773348261418e-05, "loss": 4.3295, "step": 19755 }, { "epoch": 0.6034208918753818, "grad_norm": 0.42006850242614746, "learning_rate": 1.7019499925355508e-05, "loss": 4.2895, "step": 19756 }, { "epoch": 0.6034514355528405, "grad_norm": 0.4128940999507904, "learning_rate": 1.7017226575930178e-05, "loss": 4.2767, "step": 19757 }, { "epoch": 0.6034819792302993, "grad_norm": 0.41482844948768616, "learning_rate": 1.7014953300006338e-05, "loss": 4.2785, "step": 19758 }, { "epoch": 0.6035125229077581, "grad_norm": 0.42203038930892944, "learning_rate": 1.7012680097604927e-05, "loss": 4.2312, "step": 19759 }, { "epoch": 0.6035430665852168, "grad_norm": 0.4298105239868164, "learning_rate": 1.7010406968746888e-05, "loss": 4.2608, "step": 19760 }, { "epoch": 0.6035736102626756, "grad_norm": 0.40798419713974, "learning_rate": 1.7008133913453128e-05, "loss": 4.2973, "step": 19761 }, { "epoch": 0.6036041539401344, "grad_norm": 0.41516751050949097, "learning_rate": 1.7005860931744597e-05, "loss": 4.2446, "step": 19762 }, { "epoch": 0.6036346976175931, "grad_norm": 0.44778528809547424, "learning_rate": 1.7003588023642216e-05, "loss": 4.3653, "step": 19763 }, { "epoch": 0.603665241295052, "grad_norm": 0.4271847903728485, "learning_rate": 1.7001315189166906e-05, "loss": 4.3004, "step": 19764 }, { "epoch": 0.6036957849725106, "grad_norm": 0.4138881266117096, "learning_rate": 1.6999042428339607e-05, "loss": 4.2966, "step": 19765 }, { "epoch": 0.6037263286499694, "grad_norm": 0.42009446024894714, "learning_rate": 1.6996769741181223e-05, "loss": 4.2555, "step": 19766 }, { "epoch": 0.6037568723274283, "grad_norm": 0.4180087149143219, "learning_rate": 1.69944971277127e-05, "loss": 4.3038, "step": 19767 }, { "epoch": 0.603787416004887, "grad_norm": 0.4187307059764862, "learning_rate": 1.699222458795497e-05, "loss": 4.3404, "step": 19768 }, { "epoch": 0.6038179596823458, "grad_norm": 0.42066270112991333, "learning_rate": 1.6989952121928933e-05, "loss": 4.307, "step": 19769 }, { "epoch": 0.6038485033598046, "grad_norm": 0.42347440123558044, "learning_rate": 1.6987679729655525e-05, "loss": 4.2262, "step": 19770 }, { "epoch": 0.6038790470372633, "grad_norm": 0.41743889451026917, "learning_rate": 1.6985407411155675e-05, "loss": 4.2425, "step": 19771 }, { "epoch": 0.603909590714722, "grad_norm": 0.411663293838501, "learning_rate": 1.69831351664503e-05, "loss": 4.3508, "step": 19772 }, { "epoch": 0.6039401343921809, "grad_norm": 0.41688650846481323, "learning_rate": 1.6980862995560315e-05, "loss": 4.2939, "step": 19773 }, { "epoch": 0.6039706780696396, "grad_norm": 0.41224992275238037, "learning_rate": 1.6978590898506658e-05, "loss": 4.1972, "step": 19774 }, { "epoch": 0.6040012217470984, "grad_norm": 0.4197900593280792, "learning_rate": 1.6976318875310225e-05, "loss": 4.2971, "step": 19775 }, { "epoch": 0.6040317654245572, "grad_norm": 0.43070754408836365, "learning_rate": 1.6974046925991956e-05, "loss": 4.2147, "step": 19776 }, { "epoch": 0.6040623091020159, "grad_norm": 0.4174697697162628, "learning_rate": 1.697177505057277e-05, "loss": 4.2752, "step": 19777 }, { "epoch": 0.6040928527794747, "grad_norm": 0.421159565448761, "learning_rate": 1.6969503249073578e-05, "loss": 4.1588, "step": 19778 }, { "epoch": 0.6041233964569335, "grad_norm": 0.43193763494491577, "learning_rate": 1.6967231521515286e-05, "loss": 4.33, "step": 19779 }, { "epoch": 0.6041539401343922, "grad_norm": 0.41417616605758667, "learning_rate": 1.6964959867918837e-05, "loss": 4.2978, "step": 19780 }, { "epoch": 0.604184483811851, "grad_norm": 0.4118664562702179, "learning_rate": 1.6962688288305123e-05, "loss": 4.1726, "step": 19781 }, { "epoch": 0.6042150274893097, "grad_norm": 0.4181888699531555, "learning_rate": 1.696041678269508e-05, "loss": 4.2966, "step": 19782 }, { "epoch": 0.6042455711667685, "grad_norm": 0.40931445360183716, "learning_rate": 1.6958145351109606e-05, "loss": 4.2281, "step": 19783 }, { "epoch": 0.6042761148442273, "grad_norm": 0.4491273760795593, "learning_rate": 1.695587399356962e-05, "loss": 4.259, "step": 19784 }, { "epoch": 0.604306658521686, "grad_norm": 0.43143129348754883, "learning_rate": 1.695360271009605e-05, "loss": 4.2155, "step": 19785 }, { "epoch": 0.6043372021991448, "grad_norm": 0.4329475164413452, "learning_rate": 1.6951331500709787e-05, "loss": 4.2347, "step": 19786 }, { "epoch": 0.6043677458766036, "grad_norm": 0.42961958050727844, "learning_rate": 1.6949060365431756e-05, "loss": 4.2214, "step": 19787 }, { "epoch": 0.6043982895540623, "grad_norm": 0.4140598773956299, "learning_rate": 1.694678930428287e-05, "loss": 4.2684, "step": 19788 }, { "epoch": 0.6044288332315211, "grad_norm": 0.4147438406944275, "learning_rate": 1.6944518317284023e-05, "loss": 4.2833, "step": 19789 }, { "epoch": 0.6044593769089799, "grad_norm": 0.42469748854637146, "learning_rate": 1.6942247404456146e-05, "loss": 4.2988, "step": 19790 }, { "epoch": 0.6044899205864386, "grad_norm": 0.40944814682006836, "learning_rate": 1.693997656582014e-05, "loss": 4.2652, "step": 19791 }, { "epoch": 0.6045204642638974, "grad_norm": 0.4409770667552948, "learning_rate": 1.6937705801396915e-05, "loss": 4.2027, "step": 19792 }, { "epoch": 0.6045510079413562, "grad_norm": 0.4353369474411011, "learning_rate": 1.6935435111207375e-05, "loss": 4.2752, "step": 19793 }, { "epoch": 0.6045815516188149, "grad_norm": 0.42434194684028625, "learning_rate": 1.6933164495272433e-05, "loss": 4.2925, "step": 19794 }, { "epoch": 0.6046120952962737, "grad_norm": 0.4118460714817047, "learning_rate": 1.693089395361299e-05, "loss": 4.2476, "step": 19795 }, { "epoch": 0.6046426389737324, "grad_norm": 0.43361812829971313, "learning_rate": 1.6928623486249965e-05, "loss": 4.307, "step": 19796 }, { "epoch": 0.6046731826511912, "grad_norm": 0.42487621307373047, "learning_rate": 1.692635309320424e-05, "loss": 4.3288, "step": 19797 }, { "epoch": 0.60470372632865, "grad_norm": 0.4317246675491333, "learning_rate": 1.6924082774496736e-05, "loss": 4.2937, "step": 19798 }, { "epoch": 0.6047342700061087, "grad_norm": 0.4296594262123108, "learning_rate": 1.692181253014836e-05, "loss": 4.2121, "step": 19799 }, { "epoch": 0.6047648136835675, "grad_norm": 0.41449418663978577, "learning_rate": 1.6919542360180003e-05, "loss": 4.3074, "step": 19800 }, { "epoch": 0.6047953573610263, "grad_norm": 0.42625612020492554, "learning_rate": 1.6917272264612576e-05, "loss": 4.2354, "step": 19801 }, { "epoch": 0.604825901038485, "grad_norm": 0.42546015977859497, "learning_rate": 1.691500224346698e-05, "loss": 4.2725, "step": 19802 }, { "epoch": 0.6048564447159438, "grad_norm": 0.4204031825065613, "learning_rate": 1.6912732296764118e-05, "loss": 4.2431, "step": 19803 }, { "epoch": 0.6048869883934026, "grad_norm": 0.411216139793396, "learning_rate": 1.691046242452488e-05, "loss": 4.2506, "step": 19804 }, { "epoch": 0.6049175320708613, "grad_norm": 0.41001445055007935, "learning_rate": 1.6908192626770188e-05, "loss": 4.2843, "step": 19805 }, { "epoch": 0.6049480757483201, "grad_norm": 0.42095792293548584, "learning_rate": 1.690592290352091e-05, "loss": 4.1938, "step": 19806 }, { "epoch": 0.6049786194257789, "grad_norm": 0.42041337490081787, "learning_rate": 1.6903653254797963e-05, "loss": 4.2772, "step": 19807 }, { "epoch": 0.6050091631032376, "grad_norm": 0.41066551208496094, "learning_rate": 1.6901383680622256e-05, "loss": 4.2465, "step": 19808 }, { "epoch": 0.6050397067806964, "grad_norm": 0.4141598045825958, "learning_rate": 1.6899114181014668e-05, "loss": 4.2301, "step": 19809 }, { "epoch": 0.6050702504581552, "grad_norm": 0.42026886343955994, "learning_rate": 1.6896844755996093e-05, "loss": 4.2949, "step": 19810 }, { "epoch": 0.6051007941356139, "grad_norm": 0.42022770643234253, "learning_rate": 1.689457540558745e-05, "loss": 4.2588, "step": 19811 }, { "epoch": 0.6051313378130727, "grad_norm": 0.4201277792453766, "learning_rate": 1.6892306129809606e-05, "loss": 4.3029, "step": 19812 }, { "epoch": 0.6051618814905314, "grad_norm": 0.41942018270492554, "learning_rate": 1.6890036928683472e-05, "loss": 4.2914, "step": 19813 }, { "epoch": 0.6051924251679902, "grad_norm": 0.4332962930202484, "learning_rate": 1.6887767802229937e-05, "loss": 4.2961, "step": 19814 }, { "epoch": 0.605222968845449, "grad_norm": 0.4123258888721466, "learning_rate": 1.6885498750469888e-05, "loss": 4.2998, "step": 19815 }, { "epoch": 0.6052535125229077, "grad_norm": 0.4200344681739807, "learning_rate": 1.6883229773424236e-05, "loss": 4.2631, "step": 19816 }, { "epoch": 0.6052840562003665, "grad_norm": 0.41761189699172974, "learning_rate": 1.6880960871113854e-05, "loss": 4.3056, "step": 19817 }, { "epoch": 0.6053145998778253, "grad_norm": 0.4068767726421356, "learning_rate": 1.687869204355964e-05, "loss": 4.2635, "step": 19818 }, { "epoch": 0.605345143555284, "grad_norm": 0.41445356607437134, "learning_rate": 1.6876423290782494e-05, "loss": 4.2449, "step": 19819 }, { "epoch": 0.6053756872327428, "grad_norm": 0.42677730321884155, "learning_rate": 1.687415461280328e-05, "loss": 4.3293, "step": 19820 }, { "epoch": 0.6054062309102016, "grad_norm": 0.41761693358421326, "learning_rate": 1.6871886009642906e-05, "loss": 4.3394, "step": 19821 }, { "epoch": 0.6054367745876603, "grad_norm": 0.42241600155830383, "learning_rate": 1.6869617481322263e-05, "loss": 4.2288, "step": 19822 }, { "epoch": 0.6054673182651191, "grad_norm": 0.4203411340713501, "learning_rate": 1.6867349027862228e-05, "loss": 4.1983, "step": 19823 }, { "epoch": 0.6054978619425779, "grad_norm": 0.42117178440093994, "learning_rate": 1.6865080649283694e-05, "loss": 4.2766, "step": 19824 }, { "epoch": 0.6055284056200366, "grad_norm": 0.42027992010116577, "learning_rate": 1.6862812345607542e-05, "loss": 4.3413, "step": 19825 }, { "epoch": 0.6055589492974954, "grad_norm": 0.4141625165939331, "learning_rate": 1.6860544116854666e-05, "loss": 4.294, "step": 19826 }, { "epoch": 0.6055894929749542, "grad_norm": 0.4184727966785431, "learning_rate": 1.6858275963045933e-05, "loss": 4.3708, "step": 19827 }, { "epoch": 0.6056200366524129, "grad_norm": 0.42514368891716003, "learning_rate": 1.6856007884202256e-05, "loss": 4.2473, "step": 19828 }, { "epoch": 0.6056505803298717, "grad_norm": 0.4213060438632965, "learning_rate": 1.6853739880344487e-05, "loss": 4.2953, "step": 19829 }, { "epoch": 0.6056811240073304, "grad_norm": 0.4208658039569855, "learning_rate": 1.6851471951493536e-05, "loss": 4.2819, "step": 19830 }, { "epoch": 0.6057116676847892, "grad_norm": 0.4224928021430969, "learning_rate": 1.6849204097670263e-05, "loss": 4.3385, "step": 19831 }, { "epoch": 0.605742211362248, "grad_norm": 0.422457218170166, "learning_rate": 1.6846936318895563e-05, "loss": 4.3105, "step": 19832 }, { "epoch": 0.6057727550397067, "grad_norm": 0.4313477873802185, "learning_rate": 1.6844668615190313e-05, "loss": 4.3134, "step": 19833 }, { "epoch": 0.6058032987171655, "grad_norm": 0.41299888491630554, "learning_rate": 1.6842400986575388e-05, "loss": 4.2646, "step": 19834 }, { "epoch": 0.6058338423946243, "grad_norm": 0.43197113275527954, "learning_rate": 1.684013343307167e-05, "loss": 4.2596, "step": 19835 }, { "epoch": 0.605864386072083, "grad_norm": 0.4193957448005676, "learning_rate": 1.6837865954700048e-05, "loss": 4.3013, "step": 19836 }, { "epoch": 0.6058949297495418, "grad_norm": 0.41384434700012207, "learning_rate": 1.683559855148138e-05, "loss": 4.2789, "step": 19837 }, { "epoch": 0.6059254734270006, "grad_norm": 0.4165976345539093, "learning_rate": 1.6833331223436556e-05, "loss": 4.2172, "step": 19838 }, { "epoch": 0.6059560171044593, "grad_norm": 0.417244553565979, "learning_rate": 1.683106397058646e-05, "loss": 4.1786, "step": 19839 }, { "epoch": 0.6059865607819181, "grad_norm": 0.408399373292923, "learning_rate": 1.6828796792951943e-05, "loss": 4.2265, "step": 19840 }, { "epoch": 0.606017104459377, "grad_norm": 0.42877405881881714, "learning_rate": 1.6826529690553905e-05, "loss": 4.3328, "step": 19841 }, { "epoch": 0.6060476481368356, "grad_norm": 0.41144442558288574, "learning_rate": 1.6824262663413216e-05, "loss": 4.2578, "step": 19842 }, { "epoch": 0.6060781918142945, "grad_norm": 0.428641140460968, "learning_rate": 1.682199571155073e-05, "loss": 4.3239, "step": 19843 }, { "epoch": 0.6061087354917533, "grad_norm": 0.43067026138305664, "learning_rate": 1.6819728834987337e-05, "loss": 4.3241, "step": 19844 }, { "epoch": 0.606139279169212, "grad_norm": 0.41928866505622864, "learning_rate": 1.6817462033743918e-05, "loss": 4.3157, "step": 19845 }, { "epoch": 0.6061698228466708, "grad_norm": 0.42628103494644165, "learning_rate": 1.681519530784132e-05, "loss": 4.2312, "step": 19846 }, { "epoch": 0.6062003665241295, "grad_norm": 0.43683022260665894, "learning_rate": 1.6812928657300436e-05, "loss": 4.2251, "step": 19847 }, { "epoch": 0.6062309102015883, "grad_norm": 0.44157400727272034, "learning_rate": 1.681066208214212e-05, "loss": 4.2145, "step": 19848 }, { "epoch": 0.6062614538790471, "grad_norm": 0.41966569423675537, "learning_rate": 1.6808395582387253e-05, "loss": 4.3182, "step": 19849 }, { "epoch": 0.6062919975565058, "grad_norm": 0.42060211300849915, "learning_rate": 1.6806129158056708e-05, "loss": 4.3072, "step": 19850 }, { "epoch": 0.6063225412339646, "grad_norm": 0.41319194436073303, "learning_rate": 1.680386280917133e-05, "loss": 4.3066, "step": 19851 }, { "epoch": 0.6063530849114234, "grad_norm": 0.4278911352157593, "learning_rate": 1.6801596535752003e-05, "loss": 4.3151, "step": 19852 }, { "epoch": 0.6063836285888821, "grad_norm": 0.428956001996994, "learning_rate": 1.67993303378196e-05, "loss": 4.3214, "step": 19853 }, { "epoch": 0.6064141722663409, "grad_norm": 0.408648818731308, "learning_rate": 1.6797064215394973e-05, "loss": 4.249, "step": 19854 }, { "epoch": 0.6064447159437997, "grad_norm": 0.42211011052131653, "learning_rate": 1.6794798168498995e-05, "loss": 4.2371, "step": 19855 }, { "epoch": 0.6064752596212584, "grad_norm": 0.4089406430721283, "learning_rate": 1.6792532197152532e-05, "loss": 4.2465, "step": 19856 }, { "epoch": 0.6065058032987172, "grad_norm": 0.42548996210098267, "learning_rate": 1.679026630137644e-05, "loss": 4.3177, "step": 19857 }, { "epoch": 0.606536346976176, "grad_norm": 0.4116481840610504, "learning_rate": 1.6788000481191583e-05, "loss": 4.2424, "step": 19858 }, { "epoch": 0.6065668906536347, "grad_norm": 0.4134538471698761, "learning_rate": 1.6785734736618846e-05, "loss": 4.3578, "step": 19859 }, { "epoch": 0.6065974343310935, "grad_norm": 0.42792946100234985, "learning_rate": 1.6783469067679052e-05, "loss": 4.2906, "step": 19860 }, { "epoch": 0.6066279780085523, "grad_norm": 0.4213765859603882, "learning_rate": 1.678120347439309e-05, "loss": 4.2996, "step": 19861 }, { "epoch": 0.606658521686011, "grad_norm": 0.43024200201034546, "learning_rate": 1.677893795678182e-05, "loss": 4.2793, "step": 19862 }, { "epoch": 0.6066890653634698, "grad_norm": 0.4148522615432739, "learning_rate": 1.677667251486609e-05, "loss": 4.2644, "step": 19863 }, { "epoch": 0.6067196090409285, "grad_norm": 0.4212040901184082, "learning_rate": 1.6774407148666767e-05, "loss": 4.2622, "step": 19864 }, { "epoch": 0.6067501527183873, "grad_norm": 0.4283951222896576, "learning_rate": 1.6772141858204706e-05, "loss": 4.2434, "step": 19865 }, { "epoch": 0.6067806963958461, "grad_norm": 0.417447954416275, "learning_rate": 1.6769876643500753e-05, "loss": 4.2469, "step": 19866 }, { "epoch": 0.6068112400733048, "grad_norm": 0.40993019938468933, "learning_rate": 1.6767611504575797e-05, "loss": 4.1921, "step": 19867 }, { "epoch": 0.6068417837507636, "grad_norm": 0.4218437969684601, "learning_rate": 1.6765346441450658e-05, "loss": 4.3234, "step": 19868 }, { "epoch": 0.6068723274282224, "grad_norm": 0.4138750433921814, "learning_rate": 1.6763081454146212e-05, "loss": 4.176, "step": 19869 }, { "epoch": 0.6069028711056811, "grad_norm": 0.40711715817451477, "learning_rate": 1.6760816542683317e-05, "loss": 4.1957, "step": 19870 }, { "epoch": 0.6069334147831399, "grad_norm": 0.4239448010921478, "learning_rate": 1.6758551707082815e-05, "loss": 4.2632, "step": 19871 }, { "epoch": 0.6069639584605987, "grad_norm": 0.4121412932872772, "learning_rate": 1.6756286947365564e-05, "loss": 4.179, "step": 19872 }, { "epoch": 0.6069945021380574, "grad_norm": 0.42745184898376465, "learning_rate": 1.6754022263552427e-05, "loss": 4.2961, "step": 19873 }, { "epoch": 0.6070250458155162, "grad_norm": 0.4158641993999481, "learning_rate": 1.6751757655664234e-05, "loss": 4.2836, "step": 19874 }, { "epoch": 0.607055589492975, "grad_norm": 0.419392853975296, "learning_rate": 1.6749493123721847e-05, "loss": 4.3498, "step": 19875 }, { "epoch": 0.6070861331704337, "grad_norm": 0.40540894865989685, "learning_rate": 1.6747228667746133e-05, "loss": 4.2205, "step": 19876 }, { "epoch": 0.6071166768478925, "grad_norm": 0.42078691720962524, "learning_rate": 1.674496428775792e-05, "loss": 4.2873, "step": 19877 }, { "epoch": 0.6071472205253513, "grad_norm": 0.42299923300743103, "learning_rate": 1.6742699983778064e-05, "loss": 4.3255, "step": 19878 }, { "epoch": 0.60717776420281, "grad_norm": 0.41276103258132935, "learning_rate": 1.674043575582742e-05, "loss": 4.2842, "step": 19879 }, { "epoch": 0.6072083078802688, "grad_norm": 0.4119579493999481, "learning_rate": 1.6738171603926827e-05, "loss": 4.2689, "step": 19880 }, { "epoch": 0.6072388515577275, "grad_norm": 0.41531848907470703, "learning_rate": 1.6735907528097137e-05, "loss": 4.2934, "step": 19881 }, { "epoch": 0.6072693952351863, "grad_norm": 0.4199812114238739, "learning_rate": 1.6733643528359192e-05, "loss": 4.2677, "step": 19882 }, { "epoch": 0.6072999389126451, "grad_norm": 0.4154888093471527, "learning_rate": 1.6731379604733843e-05, "loss": 4.2577, "step": 19883 }, { "epoch": 0.6073304825901038, "grad_norm": 0.4287946820259094, "learning_rate": 1.672911575724194e-05, "loss": 4.2129, "step": 19884 }, { "epoch": 0.6073610262675626, "grad_norm": 0.42174142599105835, "learning_rate": 1.672685198590431e-05, "loss": 4.2386, "step": 19885 }, { "epoch": 0.6073915699450214, "grad_norm": 0.42481526732444763, "learning_rate": 1.672458829074181e-05, "loss": 4.3004, "step": 19886 }, { "epoch": 0.6074221136224801, "grad_norm": 0.41713958978652954, "learning_rate": 1.6722324671775284e-05, "loss": 4.2147, "step": 19887 }, { "epoch": 0.6074526572999389, "grad_norm": 0.416330486536026, "learning_rate": 1.672006112902557e-05, "loss": 4.326, "step": 19888 }, { "epoch": 0.6074832009773977, "grad_norm": 0.410311758518219, "learning_rate": 1.6717797662513507e-05, "loss": 4.3173, "step": 19889 }, { "epoch": 0.6075137446548564, "grad_norm": 0.4373311698436737, "learning_rate": 1.6715534272259946e-05, "loss": 4.225, "step": 19890 }, { "epoch": 0.6075442883323152, "grad_norm": 0.42410242557525635, "learning_rate": 1.6713270958285717e-05, "loss": 4.1615, "step": 19891 }, { "epoch": 0.607574832009774, "grad_norm": 0.4122481048107147, "learning_rate": 1.6711007720611656e-05, "loss": 4.3212, "step": 19892 }, { "epoch": 0.6076053756872327, "grad_norm": 0.4276754856109619, "learning_rate": 1.670874455925862e-05, "loss": 4.226, "step": 19893 }, { "epoch": 0.6076359193646915, "grad_norm": 0.41989362239837646, "learning_rate": 1.6706481474247426e-05, "loss": 4.2273, "step": 19894 }, { "epoch": 0.6076664630421503, "grad_norm": 0.4146403968334198, "learning_rate": 1.6704218465598925e-05, "loss": 4.2975, "step": 19895 }, { "epoch": 0.607697006719609, "grad_norm": 0.422052800655365, "learning_rate": 1.6701955533333957e-05, "loss": 4.1713, "step": 19896 }, { "epoch": 0.6077275503970678, "grad_norm": 0.422149658203125, "learning_rate": 1.669969267747334e-05, "loss": 4.2665, "step": 19897 }, { "epoch": 0.6077580940745265, "grad_norm": 0.4217558801174164, "learning_rate": 1.669742989803793e-05, "loss": 4.3501, "step": 19898 }, { "epoch": 0.6077886377519853, "grad_norm": 0.4205314815044403, "learning_rate": 1.6695167195048546e-05, "loss": 4.1818, "step": 19899 }, { "epoch": 0.6078191814294441, "grad_norm": 0.4226907193660736, "learning_rate": 1.669290456852602e-05, "loss": 4.2921, "step": 19900 }, { "epoch": 0.6078497251069028, "grad_norm": 0.4214646816253662, "learning_rate": 1.669064201849121e-05, "loss": 4.2207, "step": 19901 }, { "epoch": 0.6078802687843616, "grad_norm": 0.41616934537887573, "learning_rate": 1.6688379544964915e-05, "loss": 4.2842, "step": 19902 }, { "epoch": 0.6079108124618204, "grad_norm": 0.41617390513420105, "learning_rate": 1.6686117147967988e-05, "loss": 4.2797, "step": 19903 }, { "epoch": 0.6079413561392791, "grad_norm": 0.4046090245246887, "learning_rate": 1.668385482752126e-05, "loss": 4.2733, "step": 19904 }, { "epoch": 0.6079718998167379, "grad_norm": 0.43712085485458374, "learning_rate": 1.6681592583645553e-05, "loss": 4.2433, "step": 19905 }, { "epoch": 0.6080024434941967, "grad_norm": 0.41814911365509033, "learning_rate": 1.6679330416361695e-05, "loss": 4.1233, "step": 19906 }, { "epoch": 0.6080329871716554, "grad_norm": 0.4242136478424072, "learning_rate": 1.667706832569053e-05, "loss": 4.3122, "step": 19907 }, { "epoch": 0.6080635308491142, "grad_norm": 0.4142349064350128, "learning_rate": 1.667480631165287e-05, "loss": 4.1828, "step": 19908 }, { "epoch": 0.608094074526573, "grad_norm": 0.41546159982681274, "learning_rate": 1.6672544374269545e-05, "loss": 4.3189, "step": 19909 }, { "epoch": 0.6081246182040317, "grad_norm": 0.41717445850372314, "learning_rate": 1.6670282513561395e-05, "loss": 4.2574, "step": 19910 }, { "epoch": 0.6081551618814905, "grad_norm": 0.4188929498195648, "learning_rate": 1.6668020729549232e-05, "loss": 4.266, "step": 19911 }, { "epoch": 0.6081857055589494, "grad_norm": 0.4227185547351837, "learning_rate": 1.6665759022253883e-05, "loss": 4.2937, "step": 19912 }, { "epoch": 0.608216249236408, "grad_norm": 0.42189157009124756, "learning_rate": 1.6663497391696182e-05, "loss": 4.2469, "step": 19913 }, { "epoch": 0.6082467929138669, "grad_norm": 0.4121049642562866, "learning_rate": 1.666123583789694e-05, "loss": 4.3078, "step": 19914 }, { "epoch": 0.6082773365913255, "grad_norm": 0.41762837767601013, "learning_rate": 1.6658974360876998e-05, "loss": 4.3257, "step": 19915 }, { "epoch": 0.6083078802687844, "grad_norm": 0.4335074722766876, "learning_rate": 1.6656712960657158e-05, "loss": 4.3065, "step": 19916 }, { "epoch": 0.6083384239462432, "grad_norm": 0.4127328097820282, "learning_rate": 1.6654451637258245e-05, "loss": 4.2474, "step": 19917 }, { "epoch": 0.6083689676237019, "grad_norm": 0.41939881443977356, "learning_rate": 1.66521903907011e-05, "loss": 4.2645, "step": 19918 }, { "epoch": 0.6083995113011607, "grad_norm": 0.41983118653297424, "learning_rate": 1.6649929221006526e-05, "loss": 4.2993, "step": 19919 }, { "epoch": 0.6084300549786195, "grad_norm": 0.4264201521873474, "learning_rate": 1.6647668128195342e-05, "loss": 4.318, "step": 19920 }, { "epoch": 0.6084605986560782, "grad_norm": 0.41661307215690613, "learning_rate": 1.664540711228838e-05, "loss": 4.3042, "step": 19921 }, { "epoch": 0.608491142333537, "grad_norm": 0.42635011672973633, "learning_rate": 1.6643146173306447e-05, "loss": 4.2719, "step": 19922 }, { "epoch": 0.6085216860109958, "grad_norm": 0.4244064688682556, "learning_rate": 1.6640885311270355e-05, "loss": 4.2963, "step": 19923 }, { "epoch": 0.6085522296884545, "grad_norm": 0.42078298330307007, "learning_rate": 1.6638624526200945e-05, "loss": 4.3343, "step": 19924 }, { "epoch": 0.6085827733659133, "grad_norm": 0.4335343539714813, "learning_rate": 1.6636363818119004e-05, "loss": 4.2608, "step": 19925 }, { "epoch": 0.6086133170433721, "grad_norm": 0.4238768219947815, "learning_rate": 1.6634103187045368e-05, "loss": 4.2972, "step": 19926 }, { "epoch": 0.6086438607208308, "grad_norm": 0.42804306745529175, "learning_rate": 1.6631842633000848e-05, "loss": 4.2203, "step": 19927 }, { "epoch": 0.6086744043982896, "grad_norm": 0.41527506709098816, "learning_rate": 1.6629582156006255e-05, "loss": 4.3113, "step": 19928 }, { "epoch": 0.6087049480757484, "grad_norm": 0.43106552958488464, "learning_rate": 1.6627321756082395e-05, "loss": 4.2861, "step": 19929 }, { "epoch": 0.6087354917532071, "grad_norm": 0.4178798794746399, "learning_rate": 1.66250614332501e-05, "loss": 4.2968, "step": 19930 }, { "epoch": 0.6087660354306659, "grad_norm": 0.41872185468673706, "learning_rate": 1.662280118753016e-05, "loss": 4.2304, "step": 19931 }, { "epoch": 0.6087965791081246, "grad_norm": 0.4268074929714203, "learning_rate": 1.6620541018943407e-05, "loss": 4.2274, "step": 19932 }, { "epoch": 0.6088271227855834, "grad_norm": 0.41948822140693665, "learning_rate": 1.661828092751063e-05, "loss": 4.19, "step": 19933 }, { "epoch": 0.6088576664630422, "grad_norm": 0.4186643064022064, "learning_rate": 1.6616020913252654e-05, "loss": 4.355, "step": 19934 }, { "epoch": 0.6088882101405009, "grad_norm": 0.4134465157985687, "learning_rate": 1.6613760976190287e-05, "loss": 4.2642, "step": 19935 }, { "epoch": 0.6089187538179597, "grad_norm": 0.42947399616241455, "learning_rate": 1.6611501116344337e-05, "loss": 4.2344, "step": 19936 }, { "epoch": 0.6089492974954185, "grad_norm": 0.41487938165664673, "learning_rate": 1.6609241333735598e-05, "loss": 4.1575, "step": 19937 }, { "epoch": 0.6089798411728772, "grad_norm": 0.4284798502922058, "learning_rate": 1.66069816283849e-05, "loss": 4.309, "step": 19938 }, { "epoch": 0.609010384850336, "grad_norm": 0.41726428270339966, "learning_rate": 1.6604722000313027e-05, "loss": 4.3237, "step": 19939 }, { "epoch": 0.6090409285277948, "grad_norm": 0.42382436990737915, "learning_rate": 1.6602462449540797e-05, "loss": 4.2867, "step": 19940 }, { "epoch": 0.6090714722052535, "grad_norm": 0.4174746870994568, "learning_rate": 1.660020297608902e-05, "loss": 4.2388, "step": 19941 }, { "epoch": 0.6091020158827123, "grad_norm": 0.4331396520137787, "learning_rate": 1.6597943579978492e-05, "loss": 4.3703, "step": 19942 }, { "epoch": 0.6091325595601711, "grad_norm": 0.42115819454193115, "learning_rate": 1.659568426123001e-05, "loss": 4.251, "step": 19943 }, { "epoch": 0.6091631032376298, "grad_norm": 0.41307854652404785, "learning_rate": 1.6593425019864394e-05, "loss": 4.2904, "step": 19944 }, { "epoch": 0.6091936469150886, "grad_norm": 0.42136985063552856, "learning_rate": 1.6591165855902425e-05, "loss": 4.0711, "step": 19945 }, { "epoch": 0.6092241905925473, "grad_norm": 0.4175446331501007, "learning_rate": 1.6588906769364925e-05, "loss": 4.2977, "step": 19946 }, { "epoch": 0.6092547342700061, "grad_norm": 0.42414334416389465, "learning_rate": 1.6586647760272677e-05, "loss": 4.1913, "step": 19947 }, { "epoch": 0.6092852779474649, "grad_norm": 0.41472965478897095, "learning_rate": 1.658438882864649e-05, "loss": 4.2191, "step": 19948 }, { "epoch": 0.6093158216249236, "grad_norm": 0.43842417001724243, "learning_rate": 1.658212997450717e-05, "loss": 4.2078, "step": 19949 }, { "epoch": 0.6093463653023824, "grad_norm": 0.4202609062194824, "learning_rate": 1.6579871197875497e-05, "loss": 4.3012, "step": 19950 }, { "epoch": 0.6093769089798412, "grad_norm": 0.428703248500824, "learning_rate": 1.6577612498772283e-05, "loss": 4.2849, "step": 19951 }, { "epoch": 0.6094074526572999, "grad_norm": 0.4567168653011322, "learning_rate": 1.657535387721833e-05, "loss": 4.3113, "step": 19952 }, { "epoch": 0.6094379963347587, "grad_norm": 0.4155616760253906, "learning_rate": 1.6573095333234412e-05, "loss": 4.3111, "step": 19953 }, { "epoch": 0.6094685400122175, "grad_norm": 0.4322052001953125, "learning_rate": 1.6570836866841337e-05, "loss": 4.226, "step": 19954 }, { "epoch": 0.6094990836896762, "grad_norm": 0.43207916617393494, "learning_rate": 1.6568578478059916e-05, "loss": 4.1838, "step": 19955 }, { "epoch": 0.609529627367135, "grad_norm": 0.4315933287143707, "learning_rate": 1.6566320166910914e-05, "loss": 4.1778, "step": 19956 }, { "epoch": 0.6095601710445938, "grad_norm": 0.4286060035228729, "learning_rate": 1.6564061933415142e-05, "loss": 4.3449, "step": 19957 }, { "epoch": 0.6095907147220525, "grad_norm": 0.40771976113319397, "learning_rate": 1.6561803777593392e-05, "loss": 4.2084, "step": 19958 }, { "epoch": 0.6096212583995113, "grad_norm": 0.43124836683273315, "learning_rate": 1.6559545699466455e-05, "loss": 4.2484, "step": 19959 }, { "epoch": 0.6096518020769701, "grad_norm": 0.42327165603637695, "learning_rate": 1.655728769905511e-05, "loss": 4.2667, "step": 19960 }, { "epoch": 0.6096823457544288, "grad_norm": 0.43208324909210205, "learning_rate": 1.655502977638017e-05, "loss": 4.2323, "step": 19961 }, { "epoch": 0.6097128894318876, "grad_norm": 0.4208800494670868, "learning_rate": 1.655277193146241e-05, "loss": 4.1183, "step": 19962 }, { "epoch": 0.6097434331093463, "grad_norm": 0.41529178619384766, "learning_rate": 1.655051416432262e-05, "loss": 4.2672, "step": 19963 }, { "epoch": 0.6097739767868051, "grad_norm": 0.4291607737541199, "learning_rate": 1.6548256474981587e-05, "loss": 4.2709, "step": 19964 }, { "epoch": 0.6098045204642639, "grad_norm": 0.42176875472068787, "learning_rate": 1.6545998863460106e-05, "loss": 4.3234, "step": 19965 }, { "epoch": 0.6098350641417226, "grad_norm": 0.42947980761528015, "learning_rate": 1.654374132977896e-05, "loss": 4.2907, "step": 19966 }, { "epoch": 0.6098656078191814, "grad_norm": 0.42356768250465393, "learning_rate": 1.6541483873958936e-05, "loss": 4.1842, "step": 19967 }, { "epoch": 0.6098961514966402, "grad_norm": 0.4160880744457245, "learning_rate": 1.6539226496020817e-05, "loss": 4.2442, "step": 19968 }, { "epoch": 0.6099266951740989, "grad_norm": 0.4223646819591522, "learning_rate": 1.6536969195985392e-05, "loss": 4.247, "step": 19969 }, { "epoch": 0.6099572388515577, "grad_norm": 0.42401018738746643, "learning_rate": 1.6534711973873437e-05, "loss": 4.2149, "step": 19970 }, { "epoch": 0.6099877825290165, "grad_norm": 0.418768048286438, "learning_rate": 1.653245482970574e-05, "loss": 4.2819, "step": 19971 }, { "epoch": 0.6100183262064752, "grad_norm": 0.4313458204269409, "learning_rate": 1.6530197763503096e-05, "loss": 4.2926, "step": 19972 }, { "epoch": 0.610048869883934, "grad_norm": 0.4142274260520935, "learning_rate": 1.652794077528627e-05, "loss": 4.229, "step": 19973 }, { "epoch": 0.6100794135613928, "grad_norm": 0.43072789907455444, "learning_rate": 1.6525683865076047e-05, "loss": 4.2627, "step": 19974 }, { "epoch": 0.6101099572388515, "grad_norm": 0.42816999554634094, "learning_rate": 1.6523427032893222e-05, "loss": 4.313, "step": 19975 }, { "epoch": 0.6101405009163103, "grad_norm": 0.43346962332725525, "learning_rate": 1.6521170278758548e-05, "loss": 4.376, "step": 19976 }, { "epoch": 0.6101710445937691, "grad_norm": 0.4237440526485443, "learning_rate": 1.6518913602692817e-05, "loss": 4.2628, "step": 19977 }, { "epoch": 0.6102015882712278, "grad_norm": 0.4234876334667206, "learning_rate": 1.6516657004716825e-05, "loss": 4.2493, "step": 19978 }, { "epoch": 0.6102321319486866, "grad_norm": 0.4263756275177002, "learning_rate": 1.6514400484851318e-05, "loss": 4.2842, "step": 19979 }, { "epoch": 0.6102626756261453, "grad_norm": 0.4364109933376312, "learning_rate": 1.6512144043117102e-05, "loss": 4.3335, "step": 19980 }, { "epoch": 0.6102932193036041, "grad_norm": 0.4268800616264343, "learning_rate": 1.6509887679534923e-05, "loss": 4.2322, "step": 19981 }, { "epoch": 0.610323762981063, "grad_norm": 0.4154852628707886, "learning_rate": 1.6507631394125588e-05, "loss": 4.2912, "step": 19982 }, { "epoch": 0.6103543066585216, "grad_norm": 0.41389790177345276, "learning_rate": 1.6505375186909856e-05, "loss": 4.3261, "step": 19983 }, { "epoch": 0.6103848503359804, "grad_norm": 0.4219915568828583, "learning_rate": 1.6503119057908495e-05, "loss": 4.2735, "step": 19984 }, { "epoch": 0.6104153940134392, "grad_norm": 0.42830783128738403, "learning_rate": 1.6500863007142282e-05, "loss": 4.2834, "step": 19985 }, { "epoch": 0.6104459376908979, "grad_norm": 0.4228881299495697, "learning_rate": 1.6498607034632007e-05, "loss": 4.232, "step": 19986 }, { "epoch": 0.6104764813683567, "grad_norm": 0.4198465943336487, "learning_rate": 1.6496351140398418e-05, "loss": 4.2483, "step": 19987 }, { "epoch": 0.6105070250458156, "grad_norm": 0.4185536503791809, "learning_rate": 1.64940953244623e-05, "loss": 4.2829, "step": 19988 }, { "epoch": 0.6105375687232742, "grad_norm": 0.42407140135765076, "learning_rate": 1.649183958684442e-05, "loss": 4.3005, "step": 19989 }, { "epoch": 0.610568112400733, "grad_norm": 0.4275609850883484, "learning_rate": 1.6489583927565546e-05, "loss": 4.2698, "step": 19990 }, { "epoch": 0.6105986560781919, "grad_norm": 0.4349468946456909, "learning_rate": 1.6487328346646442e-05, "loss": 4.3102, "step": 19991 }, { "epoch": 0.6106291997556506, "grad_norm": 0.4230678677558899, "learning_rate": 1.6485072844107898e-05, "loss": 4.2978, "step": 19992 }, { "epoch": 0.6106597434331094, "grad_norm": 0.4214548170566559, "learning_rate": 1.648281741997065e-05, "loss": 4.2639, "step": 19993 }, { "epoch": 0.6106902871105682, "grad_norm": 0.40423938632011414, "learning_rate": 1.6480562074255484e-05, "loss": 4.3167, "step": 19994 }, { "epoch": 0.6107208307880269, "grad_norm": 0.447986364364624, "learning_rate": 1.6478306806983174e-05, "loss": 4.2443, "step": 19995 }, { "epoch": 0.6107513744654857, "grad_norm": 0.41773778200149536, "learning_rate": 1.6476051618174466e-05, "loss": 4.3011, "step": 19996 }, { "epoch": 0.6107819181429444, "grad_norm": 0.43031951785087585, "learning_rate": 1.647379650785014e-05, "loss": 4.1789, "step": 19997 }, { "epoch": 0.6108124618204032, "grad_norm": 0.41633376479148865, "learning_rate": 1.647154147603095e-05, "loss": 4.2822, "step": 19998 }, { "epoch": 0.610843005497862, "grad_norm": 0.4168541133403778, "learning_rate": 1.646928652273766e-05, "loss": 4.3356, "step": 19999 }, { "epoch": 0.6108735491753207, "grad_norm": 0.42393311858177185, "learning_rate": 1.6467031647991038e-05, "loss": 4.3072, "step": 20000 }, { "epoch": 0.6109040928527795, "grad_norm": 0.43172207474708557, "learning_rate": 1.646477685181184e-05, "loss": 4.3642, "step": 20001 }, { "epoch": 0.6109346365302383, "grad_norm": 0.4095096290111542, "learning_rate": 1.6462522134220824e-05, "loss": 4.2687, "step": 20002 }, { "epoch": 0.610965180207697, "grad_norm": 0.42440417408943176, "learning_rate": 1.646026749523877e-05, "loss": 4.2581, "step": 20003 }, { "epoch": 0.6109957238851558, "grad_norm": 0.4282965660095215, "learning_rate": 1.6458012934886412e-05, "loss": 4.1917, "step": 20004 }, { "epoch": 0.6110262675626146, "grad_norm": 0.4236031770706177, "learning_rate": 1.645575845318453e-05, "loss": 4.3485, "step": 20005 }, { "epoch": 0.6110568112400733, "grad_norm": 0.4170015752315521, "learning_rate": 1.6453504050153873e-05, "loss": 4.2939, "step": 20006 }, { "epoch": 0.6110873549175321, "grad_norm": 0.43170106410980225, "learning_rate": 1.6451249725815194e-05, "loss": 4.3559, "step": 20007 }, { "epoch": 0.6111178985949909, "grad_norm": 0.4193147122859955, "learning_rate": 1.644899548018925e-05, "loss": 4.3889, "step": 20008 }, { "epoch": 0.6111484422724496, "grad_norm": 0.4117017388343811, "learning_rate": 1.644674131329681e-05, "loss": 4.2311, "step": 20009 }, { "epoch": 0.6111789859499084, "grad_norm": 0.4258511960506439, "learning_rate": 1.6444487225158612e-05, "loss": 4.3136, "step": 20010 }, { "epoch": 0.6112095296273672, "grad_norm": 0.4208127558231354, "learning_rate": 1.6442233215795423e-05, "loss": 4.1864, "step": 20011 }, { "epoch": 0.6112400733048259, "grad_norm": 0.4199236035346985, "learning_rate": 1.6439979285227995e-05, "loss": 4.2245, "step": 20012 }, { "epoch": 0.6112706169822847, "grad_norm": 0.4062110185623169, "learning_rate": 1.6437725433477075e-05, "loss": 4.3476, "step": 20013 }, { "epoch": 0.6113011606597434, "grad_norm": 0.41603854298591614, "learning_rate": 1.6435471660563424e-05, "loss": 4.2042, "step": 20014 }, { "epoch": 0.6113317043372022, "grad_norm": 0.4268389940261841, "learning_rate": 1.6433217966507785e-05, "loss": 4.2888, "step": 20015 }, { "epoch": 0.611362248014661, "grad_norm": 0.4264819025993347, "learning_rate": 1.6430964351330907e-05, "loss": 4.3433, "step": 20016 }, { "epoch": 0.6113927916921197, "grad_norm": 0.4193324148654938, "learning_rate": 1.6428710815053562e-05, "loss": 4.2614, "step": 20017 }, { "epoch": 0.6114233353695785, "grad_norm": 0.4210345149040222, "learning_rate": 1.642645735769647e-05, "loss": 4.2639, "step": 20018 }, { "epoch": 0.6114538790470373, "grad_norm": 0.4152240455150604, "learning_rate": 1.642420397928039e-05, "loss": 4.2268, "step": 20019 }, { "epoch": 0.611484422724496, "grad_norm": 0.4243243336677551, "learning_rate": 1.642195067982609e-05, "loss": 4.2379, "step": 20020 }, { "epoch": 0.6115149664019548, "grad_norm": 0.41749507188796997, "learning_rate": 1.641969745935429e-05, "loss": 4.2812, "step": 20021 }, { "epoch": 0.6115455100794136, "grad_norm": 0.4204152822494507, "learning_rate": 1.6417444317885743e-05, "loss": 4.2969, "step": 20022 }, { "epoch": 0.6115760537568723, "grad_norm": 0.4216260313987732, "learning_rate": 1.641519125544121e-05, "loss": 4.2997, "step": 20023 }, { "epoch": 0.6116065974343311, "grad_norm": 0.4246405363082886, "learning_rate": 1.6412938272041413e-05, "loss": 4.244, "step": 20024 }, { "epoch": 0.6116371411117899, "grad_norm": 0.4245218336582184, "learning_rate": 1.641068536770711e-05, "loss": 4.2239, "step": 20025 }, { "epoch": 0.6116676847892486, "grad_norm": 0.42966505885124207, "learning_rate": 1.640843254245905e-05, "loss": 4.2949, "step": 20026 }, { "epoch": 0.6116982284667074, "grad_norm": 0.4235380291938782, "learning_rate": 1.6406179796317966e-05, "loss": 4.3191, "step": 20027 }, { "epoch": 0.6117287721441662, "grad_norm": 0.42933833599090576, "learning_rate": 1.6403927129304602e-05, "loss": 4.3482, "step": 20028 }, { "epoch": 0.6117593158216249, "grad_norm": 0.4235943555831909, "learning_rate": 1.640167454143971e-05, "loss": 4.202, "step": 20029 }, { "epoch": 0.6117898594990837, "grad_norm": 0.42649558186531067, "learning_rate": 1.6399422032744004e-05, "loss": 4.333, "step": 20030 }, { "epoch": 0.6118204031765424, "grad_norm": 0.4214315414428711, "learning_rate": 1.639716960323826e-05, "loss": 4.3164, "step": 20031 }, { "epoch": 0.6118509468540012, "grad_norm": 0.41585788130760193, "learning_rate": 1.6394917252943185e-05, "loss": 4.2433, "step": 20032 }, { "epoch": 0.61188149053146, "grad_norm": 0.42106494307518005, "learning_rate": 1.639266498187953e-05, "loss": 4.2842, "step": 20033 }, { "epoch": 0.6119120342089187, "grad_norm": 0.4279192090034485, "learning_rate": 1.6390412790068045e-05, "loss": 4.1832, "step": 20034 }, { "epoch": 0.6119425778863775, "grad_norm": 0.4258825182914734, "learning_rate": 1.6388160677529448e-05, "loss": 4.1579, "step": 20035 }, { "epoch": 0.6119731215638363, "grad_norm": 0.4149577021598816, "learning_rate": 1.6385908644284485e-05, "loss": 4.194, "step": 20036 }, { "epoch": 0.612003665241295, "grad_norm": 0.4198443591594696, "learning_rate": 1.638365669035389e-05, "loss": 4.3226, "step": 20037 }, { "epoch": 0.6120342089187538, "grad_norm": 0.42609623074531555, "learning_rate": 1.63814048157584e-05, "loss": 4.2845, "step": 20038 }, { "epoch": 0.6120647525962126, "grad_norm": 0.42216381430625916, "learning_rate": 1.6379153020518738e-05, "loss": 4.2918, "step": 20039 }, { "epoch": 0.6120952962736713, "grad_norm": 0.42742660641670227, "learning_rate": 1.6376901304655662e-05, "loss": 4.264, "step": 20040 }, { "epoch": 0.6121258399511301, "grad_norm": 0.4240172803401947, "learning_rate": 1.637464966818988e-05, "loss": 4.2946, "step": 20041 }, { "epoch": 0.6121563836285889, "grad_norm": 0.41583558917045593, "learning_rate": 1.6372398111142128e-05, "loss": 4.3024, "step": 20042 }, { "epoch": 0.6121869273060476, "grad_norm": 0.41863134503364563, "learning_rate": 1.6370146633533157e-05, "loss": 4.2672, "step": 20043 }, { "epoch": 0.6122174709835064, "grad_norm": 0.42272284626960754, "learning_rate": 1.6367895235383672e-05, "loss": 4.3233, "step": 20044 }, { "epoch": 0.6122480146609652, "grad_norm": 0.41668280959129333, "learning_rate": 1.6365643916714413e-05, "loss": 4.2689, "step": 20045 }, { "epoch": 0.6122785583384239, "grad_norm": 0.4303666949272156, "learning_rate": 1.6363392677546118e-05, "loss": 4.2492, "step": 20046 }, { "epoch": 0.6123091020158827, "grad_norm": 0.4187264144420624, "learning_rate": 1.63611415178995e-05, "loss": 4.2076, "step": 20047 }, { "epoch": 0.6123396456933414, "grad_norm": 0.42338553071022034, "learning_rate": 1.6358890437795304e-05, "loss": 4.2658, "step": 20048 }, { "epoch": 0.6123701893708002, "grad_norm": 0.41351425647735596, "learning_rate": 1.6356639437254235e-05, "loss": 4.1727, "step": 20049 }, { "epoch": 0.612400733048259, "grad_norm": 0.40564772486686707, "learning_rate": 1.635438851629703e-05, "loss": 4.2831, "step": 20050 }, { "epoch": 0.6124312767257177, "grad_norm": 0.42518672347068787, "learning_rate": 1.6352137674944425e-05, "loss": 4.3201, "step": 20051 }, { "epoch": 0.6124618204031765, "grad_norm": 0.4294830560684204, "learning_rate": 1.634988691321713e-05, "loss": 4.1978, "step": 20052 }, { "epoch": 0.6124923640806353, "grad_norm": 0.41815200448036194, "learning_rate": 1.6347636231135868e-05, "loss": 4.3288, "step": 20053 }, { "epoch": 0.612522907758094, "grad_norm": 0.42965370416641235, "learning_rate": 1.634538562872138e-05, "loss": 4.1957, "step": 20054 }, { "epoch": 0.6125534514355528, "grad_norm": 0.42248040437698364, "learning_rate": 1.6343135105994364e-05, "loss": 4.3343, "step": 20055 }, { "epoch": 0.6125839951130116, "grad_norm": 0.4365704357624054, "learning_rate": 1.6340884662975555e-05, "loss": 4.2418, "step": 20056 }, { "epoch": 0.6126145387904703, "grad_norm": 0.4218209683895111, "learning_rate": 1.6338634299685684e-05, "loss": 4.2588, "step": 20057 }, { "epoch": 0.6126450824679291, "grad_norm": 0.4152050018310547, "learning_rate": 1.633638401614545e-05, "loss": 4.285, "step": 20058 }, { "epoch": 0.612675626145388, "grad_norm": 0.41476237773895264, "learning_rate": 1.6334133812375585e-05, "loss": 4.2368, "step": 20059 }, { "epoch": 0.6127061698228466, "grad_norm": 0.42322054505348206, "learning_rate": 1.633188368839681e-05, "loss": 4.2016, "step": 20060 }, { "epoch": 0.6127367135003055, "grad_norm": 0.4213467836380005, "learning_rate": 1.6329633644229835e-05, "loss": 4.3295, "step": 20061 }, { "epoch": 0.6127672571777643, "grad_norm": 0.41827720403671265, "learning_rate": 1.6327383679895375e-05, "loss": 4.2664, "step": 20062 }, { "epoch": 0.612797800855223, "grad_norm": 0.426405131816864, "learning_rate": 1.6325133795414167e-05, "loss": 4.1759, "step": 20063 }, { "epoch": 0.6128283445326818, "grad_norm": 0.41330450773239136, "learning_rate": 1.6322883990806896e-05, "loss": 4.2948, "step": 20064 }, { "epoch": 0.6128588882101405, "grad_norm": 0.41931477189064026, "learning_rate": 1.632063426609431e-05, "loss": 4.3359, "step": 20065 }, { "epoch": 0.6128894318875993, "grad_norm": 0.4181690216064453, "learning_rate": 1.6318384621297094e-05, "loss": 4.2307, "step": 20066 }, { "epoch": 0.6129199755650581, "grad_norm": 0.4637139141559601, "learning_rate": 1.6316135056435976e-05, "loss": 4.3426, "step": 20067 }, { "epoch": 0.6129505192425168, "grad_norm": 0.4198925197124481, "learning_rate": 1.631388557153167e-05, "loss": 4.3038, "step": 20068 }, { "epoch": 0.6129810629199756, "grad_norm": 0.4162857234477997, "learning_rate": 1.631163616660489e-05, "loss": 4.2961, "step": 20069 }, { "epoch": 0.6130116065974344, "grad_norm": 0.42426973581314087, "learning_rate": 1.6309386841676333e-05, "loss": 4.3134, "step": 20070 }, { "epoch": 0.6130421502748931, "grad_norm": 0.420881986618042, "learning_rate": 1.6307137596766732e-05, "loss": 4.2708, "step": 20071 }, { "epoch": 0.6130726939523519, "grad_norm": 0.4314824044704437, "learning_rate": 1.630488843189677e-05, "loss": 4.3334, "step": 20072 }, { "epoch": 0.6131032376298107, "grad_norm": 0.4235875606536865, "learning_rate": 1.630263934708718e-05, "loss": 4.2952, "step": 20073 }, { "epoch": 0.6131337813072694, "grad_norm": 0.41637828946113586, "learning_rate": 1.6300390342358662e-05, "loss": 4.2653, "step": 20074 }, { "epoch": 0.6131643249847282, "grad_norm": 0.4145091772079468, "learning_rate": 1.629814141773192e-05, "loss": 4.2532, "step": 20075 }, { "epoch": 0.613194868662187, "grad_norm": 0.42976143956184387, "learning_rate": 1.6295892573227662e-05, "loss": 4.2288, "step": 20076 }, { "epoch": 0.6132254123396457, "grad_norm": 0.4181082248687744, "learning_rate": 1.6293643808866605e-05, "loss": 4.2494, "step": 20077 }, { "epoch": 0.6132559560171045, "grad_norm": 0.43131545186042786, "learning_rate": 1.6291395124669434e-05, "loss": 4.3039, "step": 20078 }, { "epoch": 0.6132864996945633, "grad_norm": 0.4170653820037842, "learning_rate": 1.6289146520656867e-05, "loss": 4.2294, "step": 20079 }, { "epoch": 0.613317043372022, "grad_norm": 0.4169030785560608, "learning_rate": 1.628689799684962e-05, "loss": 4.2793, "step": 20080 }, { "epoch": 0.6133475870494808, "grad_norm": 0.4272659122943878, "learning_rate": 1.628464955326837e-05, "loss": 4.3413, "step": 20081 }, { "epoch": 0.6133781307269395, "grad_norm": 0.42892777919769287, "learning_rate": 1.628240118993384e-05, "loss": 4.2484, "step": 20082 }, { "epoch": 0.6134086744043983, "grad_norm": 0.41195371747016907, "learning_rate": 1.628015290686672e-05, "loss": 4.1316, "step": 20083 }, { "epoch": 0.6134392180818571, "grad_norm": 0.4311881363391876, "learning_rate": 1.6277904704087714e-05, "loss": 4.0256, "step": 20084 }, { "epoch": 0.6134697617593158, "grad_norm": 0.41659384965896606, "learning_rate": 1.6275656581617532e-05, "loss": 4.3221, "step": 20085 }, { "epoch": 0.6135003054367746, "grad_norm": 0.41597768664360046, "learning_rate": 1.6273408539476857e-05, "loss": 4.2667, "step": 20086 }, { "epoch": 0.6135308491142334, "grad_norm": 0.42990216612815857, "learning_rate": 1.6271160577686395e-05, "loss": 4.343, "step": 20087 }, { "epoch": 0.6135613927916921, "grad_norm": 0.4263720214366913, "learning_rate": 1.6268912696266855e-05, "loss": 4.298, "step": 20088 }, { "epoch": 0.6135919364691509, "grad_norm": 0.42294585704803467, "learning_rate": 1.6266664895238913e-05, "loss": 4.3925, "step": 20089 }, { "epoch": 0.6136224801466097, "grad_norm": 0.41761380434036255, "learning_rate": 1.6264417174623285e-05, "loss": 4.2402, "step": 20090 }, { "epoch": 0.6136530238240684, "grad_norm": 0.4256206154823303, "learning_rate": 1.6262169534440663e-05, "loss": 4.1771, "step": 20091 }, { "epoch": 0.6136835675015272, "grad_norm": 0.42279258370399475, "learning_rate": 1.6259921974711733e-05, "loss": 4.3003, "step": 20092 }, { "epoch": 0.613714111178986, "grad_norm": 0.4291408658027649, "learning_rate": 1.625767449545719e-05, "loss": 4.2776, "step": 20093 }, { "epoch": 0.6137446548564447, "grad_norm": 0.42535048723220825, "learning_rate": 1.6255427096697746e-05, "loss": 4.3521, "step": 20094 }, { "epoch": 0.6137751985339035, "grad_norm": 0.4365043640136719, "learning_rate": 1.6253179778454068e-05, "loss": 4.1388, "step": 20095 }, { "epoch": 0.6138057422113622, "grad_norm": 0.43247178196907043, "learning_rate": 1.625093254074688e-05, "loss": 4.2166, "step": 20096 }, { "epoch": 0.613836285888821, "grad_norm": 0.42533576488494873, "learning_rate": 1.6248685383596832e-05, "loss": 4.2211, "step": 20097 }, { "epoch": 0.6138668295662798, "grad_norm": 0.41878053545951843, "learning_rate": 1.6246438307024647e-05, "loss": 4.3607, "step": 20098 }, { "epoch": 0.6138973732437385, "grad_norm": 0.41426825523376465, "learning_rate": 1.6244191311051005e-05, "loss": 4.2549, "step": 20099 }, { "epoch": 0.6139279169211973, "grad_norm": 0.4259796142578125, "learning_rate": 1.6241944395696596e-05, "loss": 4.3349, "step": 20100 }, { "epoch": 0.6139584605986561, "grad_norm": 0.42523038387298584, "learning_rate": 1.6239697560982103e-05, "loss": 4.19, "step": 20101 }, { "epoch": 0.6139890042761148, "grad_norm": 0.4218809902667999, "learning_rate": 1.623745080692823e-05, "loss": 4.171, "step": 20102 }, { "epoch": 0.6140195479535736, "grad_norm": 0.428336501121521, "learning_rate": 1.6235204133555636e-05, "loss": 4.3292, "step": 20103 }, { "epoch": 0.6140500916310324, "grad_norm": 0.4223839342594147, "learning_rate": 1.623295754088503e-05, "loss": 4.2967, "step": 20104 }, { "epoch": 0.6140806353084911, "grad_norm": 0.422778844833374, "learning_rate": 1.6230711028937102e-05, "loss": 4.2248, "step": 20105 }, { "epoch": 0.6141111789859499, "grad_norm": 0.4230424761772156, "learning_rate": 1.6228464597732513e-05, "loss": 4.2151, "step": 20106 }, { "epoch": 0.6141417226634087, "grad_norm": 0.4201336205005646, "learning_rate": 1.622621824729197e-05, "loss": 4.2152, "step": 20107 }, { "epoch": 0.6141722663408674, "grad_norm": 0.43882808089256287, "learning_rate": 1.6223971977636147e-05, "loss": 4.3764, "step": 20108 }, { "epoch": 0.6142028100183262, "grad_norm": 0.4191682040691376, "learning_rate": 1.622172578878572e-05, "loss": 4.3185, "step": 20109 }, { "epoch": 0.614233353695785, "grad_norm": 0.4195726215839386, "learning_rate": 1.6219479680761374e-05, "loss": 4.2305, "step": 20110 }, { "epoch": 0.6142638973732437, "grad_norm": 0.424544095993042, "learning_rate": 1.6217233653583803e-05, "loss": 4.3084, "step": 20111 }, { "epoch": 0.6142944410507025, "grad_norm": 0.4218977391719818, "learning_rate": 1.6214987707273667e-05, "loss": 4.1795, "step": 20112 }, { "epoch": 0.6143249847281612, "grad_norm": 0.42615261673927307, "learning_rate": 1.6212741841851667e-05, "loss": 4.3152, "step": 20113 }, { "epoch": 0.61435552840562, "grad_norm": 0.42657792568206787, "learning_rate": 1.6210496057338458e-05, "loss": 4.276, "step": 20114 }, { "epoch": 0.6143860720830788, "grad_norm": 0.422518253326416, "learning_rate": 1.620825035375474e-05, "loss": 4.1864, "step": 20115 }, { "epoch": 0.6144166157605375, "grad_norm": 0.418465793132782, "learning_rate": 1.620600473112119e-05, "loss": 4.2039, "step": 20116 }, { "epoch": 0.6144471594379963, "grad_norm": 0.42046335339546204, "learning_rate": 1.6203759189458455e-05, "loss": 4.4193, "step": 20117 }, { "epoch": 0.6144777031154551, "grad_norm": 0.41676414012908936, "learning_rate": 1.620151372878724e-05, "loss": 4.2298, "step": 20118 }, { "epoch": 0.6145082467929138, "grad_norm": 0.42713746428489685, "learning_rate": 1.6199268349128222e-05, "loss": 4.2386, "step": 20119 }, { "epoch": 0.6145387904703726, "grad_norm": 0.4252661466598511, "learning_rate": 1.6197023050502053e-05, "loss": 4.1707, "step": 20120 }, { "epoch": 0.6145693341478314, "grad_norm": 0.4475409686565399, "learning_rate": 1.619477783292942e-05, "loss": 4.1637, "step": 20121 }, { "epoch": 0.6145998778252901, "grad_norm": 0.41872045397758484, "learning_rate": 1.6192532696431e-05, "loss": 4.2482, "step": 20122 }, { "epoch": 0.6146304215027489, "grad_norm": 0.4210160970687866, "learning_rate": 1.6190287641027458e-05, "loss": 4.1949, "step": 20123 }, { "epoch": 0.6146609651802077, "grad_norm": 0.430074542760849, "learning_rate": 1.618804266673946e-05, "loss": 4.3167, "step": 20124 }, { "epoch": 0.6146915088576664, "grad_norm": 0.4141797125339508, "learning_rate": 1.6185797773587698e-05, "loss": 4.2266, "step": 20125 }, { "epoch": 0.6147220525351252, "grad_norm": 0.4227760136127472, "learning_rate": 1.6183552961592816e-05, "loss": 4.2723, "step": 20126 }, { "epoch": 0.614752596212584, "grad_norm": 0.4150736629962921, "learning_rate": 1.6181308230775494e-05, "loss": 4.3883, "step": 20127 }, { "epoch": 0.6147831398900427, "grad_norm": 0.42834487557411194, "learning_rate": 1.617906358115641e-05, "loss": 4.295, "step": 20128 }, { "epoch": 0.6148136835675015, "grad_norm": 0.4259772300720215, "learning_rate": 1.6176819012756217e-05, "loss": 4.2655, "step": 20129 }, { "epoch": 0.6148442272449602, "grad_norm": 0.419213205575943, "learning_rate": 1.6174574525595597e-05, "loss": 4.3425, "step": 20130 }, { "epoch": 0.614874770922419, "grad_norm": 0.42374101281166077, "learning_rate": 1.61723301196952e-05, "loss": 4.3086, "step": 20131 }, { "epoch": 0.6149053145998779, "grad_norm": 0.42573314905166626, "learning_rate": 1.6170085795075694e-05, "loss": 4.2153, "step": 20132 }, { "epoch": 0.6149358582773365, "grad_norm": 0.4231007695198059, "learning_rate": 1.6167841551757757e-05, "loss": 4.2974, "step": 20133 }, { "epoch": 0.6149664019547953, "grad_norm": 0.4174611270427704, "learning_rate": 1.6165597389762036e-05, "loss": 4.3176, "step": 20134 }, { "epoch": 0.6149969456322542, "grad_norm": 0.4372168183326721, "learning_rate": 1.61633533091092e-05, "loss": 4.3729, "step": 20135 }, { "epoch": 0.6150274893097128, "grad_norm": 0.4249826967716217, "learning_rate": 1.6161109309819924e-05, "loss": 4.2274, "step": 20136 }, { "epoch": 0.6150580329871717, "grad_norm": 0.4296017587184906, "learning_rate": 1.615886539191485e-05, "loss": 4.2299, "step": 20137 }, { "epoch": 0.6150885766646305, "grad_norm": 0.4186043441295624, "learning_rate": 1.6156621555414653e-05, "loss": 4.2451, "step": 20138 }, { "epoch": 0.6151191203420892, "grad_norm": 0.4442298710346222, "learning_rate": 1.615437780033999e-05, "loss": 4.2936, "step": 20139 }, { "epoch": 0.615149664019548, "grad_norm": 0.4293006658554077, "learning_rate": 1.615213412671151e-05, "loss": 4.2403, "step": 20140 }, { "epoch": 0.6151802076970068, "grad_norm": 0.43667909502983093, "learning_rate": 1.6149890534549884e-05, "loss": 4.2907, "step": 20141 }, { "epoch": 0.6152107513744655, "grad_norm": 0.42483851313591003, "learning_rate": 1.614764702387577e-05, "loss": 4.3115, "step": 20142 }, { "epoch": 0.6152412950519243, "grad_norm": 0.4214646518230438, "learning_rate": 1.614540359470982e-05, "loss": 4.1873, "step": 20143 }, { "epoch": 0.6152718387293831, "grad_norm": 0.41344335675239563, "learning_rate": 1.6143160247072682e-05, "loss": 4.2886, "step": 20144 }, { "epoch": 0.6153023824068418, "grad_norm": 0.43587642908096313, "learning_rate": 1.614091698098504e-05, "loss": 4.3341, "step": 20145 }, { "epoch": 0.6153329260843006, "grad_norm": 0.4213210940361023, "learning_rate": 1.6138673796467518e-05, "loss": 4.1995, "step": 20146 }, { "epoch": 0.6153634697617593, "grad_norm": 0.42499569058418274, "learning_rate": 1.6136430693540784e-05, "loss": 4.2482, "step": 20147 }, { "epoch": 0.6153940134392181, "grad_norm": 0.43036481738090515, "learning_rate": 1.6134187672225493e-05, "loss": 4.2201, "step": 20148 }, { "epoch": 0.6154245571166769, "grad_norm": 0.4205123484134674, "learning_rate": 1.6131944732542286e-05, "loss": 4.2208, "step": 20149 }, { "epoch": 0.6154551007941356, "grad_norm": 0.4185269773006439, "learning_rate": 1.6129701874511836e-05, "loss": 4.3621, "step": 20150 }, { "epoch": 0.6154856444715944, "grad_norm": 0.417772501707077, "learning_rate": 1.6127459098154766e-05, "loss": 4.2566, "step": 20151 }, { "epoch": 0.6155161881490532, "grad_norm": 0.4248795807361603, "learning_rate": 1.612521640349175e-05, "loss": 4.2368, "step": 20152 }, { "epoch": 0.6155467318265119, "grad_norm": 0.4248339831829071, "learning_rate": 1.6122973790543436e-05, "loss": 4.2919, "step": 20153 }, { "epoch": 0.6155772755039707, "grad_norm": 0.42589160799980164, "learning_rate": 1.612073125933046e-05, "loss": 4.3154, "step": 20154 }, { "epoch": 0.6156078191814295, "grad_norm": 0.42139726877212524, "learning_rate": 1.611848880987347e-05, "loss": 4.1979, "step": 20155 }, { "epoch": 0.6156383628588882, "grad_norm": 0.4389370381832123, "learning_rate": 1.6116246442193136e-05, "loss": 4.3351, "step": 20156 }, { "epoch": 0.615668906536347, "grad_norm": 0.4393371641635895, "learning_rate": 1.6114004156310074e-05, "loss": 4.215, "step": 20157 }, { "epoch": 0.6156994502138058, "grad_norm": 0.4305470585823059, "learning_rate": 1.6111761952244946e-05, "loss": 4.2576, "step": 20158 }, { "epoch": 0.6157299938912645, "grad_norm": 0.42167791724205017, "learning_rate": 1.6109519830018408e-05, "loss": 4.2242, "step": 20159 }, { "epoch": 0.6157605375687233, "grad_norm": 0.4255753755569458, "learning_rate": 1.6107277789651078e-05, "loss": 4.2826, "step": 20160 }, { "epoch": 0.6157910812461821, "grad_norm": 0.43708646297454834, "learning_rate": 1.610503583116362e-05, "loss": 4.2157, "step": 20161 }, { "epoch": 0.6158216249236408, "grad_norm": 0.4189453721046448, "learning_rate": 1.6102793954576677e-05, "loss": 4.2766, "step": 20162 }, { "epoch": 0.6158521686010996, "grad_norm": 0.4203806221485138, "learning_rate": 1.610055215991087e-05, "loss": 4.2643, "step": 20163 }, { "epoch": 0.6158827122785583, "grad_norm": 0.4356774389743805, "learning_rate": 1.609831044718687e-05, "loss": 4.3145, "step": 20164 }, { "epoch": 0.6159132559560171, "grad_norm": 0.4278014898300171, "learning_rate": 1.609606881642529e-05, "loss": 4.2752, "step": 20165 }, { "epoch": 0.6159437996334759, "grad_norm": 0.4235706925392151, "learning_rate": 1.6093827267646784e-05, "loss": 4.2483, "step": 20166 }, { "epoch": 0.6159743433109346, "grad_norm": 0.4191134572029114, "learning_rate": 1.6091585800871995e-05, "loss": 4.2542, "step": 20167 }, { "epoch": 0.6160048869883934, "grad_norm": 0.41047239303588867, "learning_rate": 1.608934441612155e-05, "loss": 4.3122, "step": 20168 }, { "epoch": 0.6160354306658522, "grad_norm": 0.42275428771972656, "learning_rate": 1.6087103113416098e-05, "loss": 4.2894, "step": 20169 }, { "epoch": 0.6160659743433109, "grad_norm": 0.4197637438774109, "learning_rate": 1.6084861892776266e-05, "loss": 4.1952, "step": 20170 }, { "epoch": 0.6160965180207697, "grad_norm": 0.4262668192386627, "learning_rate": 1.60826207542227e-05, "loss": 4.2027, "step": 20171 }, { "epoch": 0.6161270616982285, "grad_norm": 0.4225892722606659, "learning_rate": 1.608037969777602e-05, "loss": 4.3388, "step": 20172 }, { "epoch": 0.6161576053756872, "grad_norm": 0.4203222692012787, "learning_rate": 1.6078138723456883e-05, "loss": 4.2885, "step": 20173 }, { "epoch": 0.616188149053146, "grad_norm": 0.42324092984199524, "learning_rate": 1.6075897831285898e-05, "loss": 4.2995, "step": 20174 }, { "epoch": 0.6162186927306048, "grad_norm": 0.4185411036014557, "learning_rate": 1.6073657021283706e-05, "loss": 4.2746, "step": 20175 }, { "epoch": 0.6162492364080635, "grad_norm": 0.4292079210281372, "learning_rate": 1.607141629347096e-05, "loss": 4.2369, "step": 20176 }, { "epoch": 0.6162797800855223, "grad_norm": 0.4144899845123291, "learning_rate": 1.6069175647868268e-05, "loss": 4.2783, "step": 20177 }, { "epoch": 0.6163103237629811, "grad_norm": 0.42226895689964294, "learning_rate": 1.606693508449626e-05, "loss": 4.2912, "step": 20178 }, { "epoch": 0.6163408674404398, "grad_norm": 0.43250954151153564, "learning_rate": 1.6064694603375584e-05, "loss": 4.3372, "step": 20179 }, { "epoch": 0.6163714111178986, "grad_norm": 0.4193370044231415, "learning_rate": 1.6062454204526854e-05, "loss": 4.353, "step": 20180 }, { "epoch": 0.6164019547953573, "grad_norm": 0.42852115631103516, "learning_rate": 1.6060213887970708e-05, "loss": 4.2483, "step": 20181 }, { "epoch": 0.6164324984728161, "grad_norm": 0.4354509115219116, "learning_rate": 1.605797365372776e-05, "loss": 4.3301, "step": 20182 }, { "epoch": 0.6164630421502749, "grad_norm": 0.43291518092155457, "learning_rate": 1.605573350181865e-05, "loss": 4.4021, "step": 20183 }, { "epoch": 0.6164935858277336, "grad_norm": 0.4176683723926544, "learning_rate": 1.6053493432264005e-05, "loss": 4.2359, "step": 20184 }, { "epoch": 0.6165241295051924, "grad_norm": 0.4136183261871338, "learning_rate": 1.6051253445084444e-05, "loss": 4.2116, "step": 20185 }, { "epoch": 0.6165546731826512, "grad_norm": 0.42303165793418884, "learning_rate": 1.604901354030059e-05, "loss": 4.2542, "step": 20186 }, { "epoch": 0.6165852168601099, "grad_norm": 0.4254765808582306, "learning_rate": 1.6046773717933078e-05, "loss": 4.2608, "step": 20187 }, { "epoch": 0.6166157605375687, "grad_norm": 0.42402270436286926, "learning_rate": 1.6044533978002512e-05, "loss": 4.177, "step": 20188 }, { "epoch": 0.6166463042150275, "grad_norm": 0.45532849431037903, "learning_rate": 1.6042294320529526e-05, "loss": 4.2876, "step": 20189 }, { "epoch": 0.6166768478924862, "grad_norm": 0.42986243963241577, "learning_rate": 1.6040054745534754e-05, "loss": 4.2635, "step": 20190 }, { "epoch": 0.616707391569945, "grad_norm": 0.41601094603538513, "learning_rate": 1.6037815253038796e-05, "loss": 4.2872, "step": 20191 }, { "epoch": 0.6167379352474038, "grad_norm": 0.43146824836730957, "learning_rate": 1.6035575843062285e-05, "loss": 4.2821, "step": 20192 }, { "epoch": 0.6167684789248625, "grad_norm": 0.4343413710594177, "learning_rate": 1.6033336515625834e-05, "loss": 4.213, "step": 20193 }, { "epoch": 0.6167990226023213, "grad_norm": 0.42483460903167725, "learning_rate": 1.6031097270750068e-05, "loss": 4.1539, "step": 20194 }, { "epoch": 0.6168295662797801, "grad_norm": 0.4172264635562897, "learning_rate": 1.602885810845559e-05, "loss": 4.3528, "step": 20195 }, { "epoch": 0.6168601099572388, "grad_norm": 0.4214830696582794, "learning_rate": 1.6026619028763042e-05, "loss": 4.2682, "step": 20196 }, { "epoch": 0.6168906536346976, "grad_norm": 0.43920907378196716, "learning_rate": 1.6024380031693016e-05, "loss": 4.2983, "step": 20197 }, { "epoch": 0.6169211973121563, "grad_norm": 0.43707066774368286, "learning_rate": 1.6022141117266147e-05, "loss": 4.3051, "step": 20198 }, { "epoch": 0.6169517409896151, "grad_norm": 0.4176385998725891, "learning_rate": 1.601990228550303e-05, "loss": 4.278, "step": 20199 }, { "epoch": 0.6169822846670739, "grad_norm": 0.431936651468277, "learning_rate": 1.6017663536424298e-05, "loss": 4.2182, "step": 20200 }, { "epoch": 0.6170128283445326, "grad_norm": 0.4364278018474579, "learning_rate": 1.6015424870050554e-05, "loss": 4.2769, "step": 20201 }, { "epoch": 0.6170433720219914, "grad_norm": 0.4225829243659973, "learning_rate": 1.601318628640241e-05, "loss": 4.277, "step": 20202 }, { "epoch": 0.6170739156994502, "grad_norm": 0.4207788407802582, "learning_rate": 1.601094778550048e-05, "loss": 4.3238, "step": 20203 }, { "epoch": 0.6171044593769089, "grad_norm": 0.42754775285720825, "learning_rate": 1.600870936736538e-05, "loss": 4.2781, "step": 20204 }, { "epoch": 0.6171350030543677, "grad_norm": 0.4156157076358795, "learning_rate": 1.600647103201771e-05, "loss": 4.2846, "step": 20205 }, { "epoch": 0.6171655467318266, "grad_norm": 0.42510196566581726, "learning_rate": 1.6004232779478088e-05, "loss": 4.3529, "step": 20206 }, { "epoch": 0.6171960904092852, "grad_norm": 0.4159197211265564, "learning_rate": 1.6001994609767124e-05, "loss": 4.2753, "step": 20207 }, { "epoch": 0.617226634086744, "grad_norm": 0.4237036406993866, "learning_rate": 1.599975652290542e-05, "loss": 4.2511, "step": 20208 }, { "epoch": 0.6172571777642029, "grad_norm": 0.42124417424201965, "learning_rate": 1.599751851891358e-05, "loss": 4.2888, "step": 20209 }, { "epoch": 0.6172877214416616, "grad_norm": 0.4326944351196289, "learning_rate": 1.5995280597812223e-05, "loss": 4.2586, "step": 20210 }, { "epoch": 0.6173182651191204, "grad_norm": 0.4329741299152374, "learning_rate": 1.599304275962194e-05, "loss": 4.3369, "step": 20211 }, { "epoch": 0.6173488087965792, "grad_norm": 0.4204753041267395, "learning_rate": 1.5990805004363344e-05, "loss": 4.2534, "step": 20212 }, { "epoch": 0.6173793524740379, "grad_norm": 0.4271453320980072, "learning_rate": 1.598856733205705e-05, "loss": 4.2934, "step": 20213 }, { "epoch": 0.6174098961514967, "grad_norm": 0.4288082718849182, "learning_rate": 1.5986329742723634e-05, "loss": 4.1873, "step": 20214 }, { "epoch": 0.6174404398289554, "grad_norm": 0.4308112561702728, "learning_rate": 1.5984092236383724e-05, "loss": 4.2627, "step": 20215 }, { "epoch": 0.6174709835064142, "grad_norm": 0.4182683229446411, "learning_rate": 1.5981854813057905e-05, "loss": 4.3071, "step": 20216 }, { "epoch": 0.617501527183873, "grad_norm": 0.412841796875, "learning_rate": 1.5979617472766796e-05, "loss": 4.2796, "step": 20217 }, { "epoch": 0.6175320708613317, "grad_norm": 0.4256400465965271, "learning_rate": 1.5977380215530985e-05, "loss": 4.3205, "step": 20218 }, { "epoch": 0.6175626145387905, "grad_norm": 0.4199879467487335, "learning_rate": 1.5975143041371064e-05, "loss": 4.2143, "step": 20219 }, { "epoch": 0.6175931582162493, "grad_norm": 0.4226009249687195, "learning_rate": 1.5972905950307644e-05, "loss": 4.2547, "step": 20220 }, { "epoch": 0.617623701893708, "grad_norm": 0.42234596610069275, "learning_rate": 1.5970668942361327e-05, "loss": 4.1942, "step": 20221 }, { "epoch": 0.6176542455711668, "grad_norm": 0.4229981601238251, "learning_rate": 1.5968432017552693e-05, "loss": 4.2607, "step": 20222 }, { "epoch": 0.6176847892486256, "grad_norm": 0.4299970865249634, "learning_rate": 1.5966195175902356e-05, "loss": 4.2286, "step": 20223 }, { "epoch": 0.6177153329260843, "grad_norm": 0.42498108744621277, "learning_rate": 1.5963958417430905e-05, "loss": 4.2796, "step": 20224 }, { "epoch": 0.6177458766035431, "grad_norm": 0.41877248883247375, "learning_rate": 1.5961721742158936e-05, "loss": 4.214, "step": 20225 }, { "epoch": 0.6177764202810019, "grad_norm": 0.412533164024353, "learning_rate": 1.5959485150107033e-05, "loss": 4.211, "step": 20226 }, { "epoch": 0.6178069639584606, "grad_norm": 0.42654985189437866, "learning_rate": 1.5957248641295812e-05, "loss": 4.2292, "step": 20227 }, { "epoch": 0.6178375076359194, "grad_norm": 0.42949262261390686, "learning_rate": 1.595501221574584e-05, "loss": 4.3177, "step": 20228 }, { "epoch": 0.6178680513133782, "grad_norm": 0.4243193566799164, "learning_rate": 1.595277587347772e-05, "loss": 4.2741, "step": 20229 }, { "epoch": 0.6178985949908369, "grad_norm": 0.42837220430374146, "learning_rate": 1.5950539614512055e-05, "loss": 4.2254, "step": 20230 }, { "epoch": 0.6179291386682957, "grad_norm": 0.42162129282951355, "learning_rate": 1.5948303438869423e-05, "loss": 4.2557, "step": 20231 }, { "epoch": 0.6179596823457544, "grad_norm": 0.4198239743709564, "learning_rate": 1.594606734657041e-05, "loss": 4.2103, "step": 20232 }, { "epoch": 0.6179902260232132, "grad_norm": 0.4204699397087097, "learning_rate": 1.5943831337635616e-05, "loss": 4.2449, "step": 20233 }, { "epoch": 0.618020769700672, "grad_norm": 0.43064650893211365, "learning_rate": 1.5941595412085615e-05, "loss": 4.2749, "step": 20234 }, { "epoch": 0.6180513133781307, "grad_norm": 0.4253021478652954, "learning_rate": 1.593935956994101e-05, "loss": 4.3109, "step": 20235 }, { "epoch": 0.6180818570555895, "grad_norm": 0.4377852976322174, "learning_rate": 1.593712381122237e-05, "loss": 4.3258, "step": 20236 }, { "epoch": 0.6181124007330483, "grad_norm": 0.4166874885559082, "learning_rate": 1.5934888135950292e-05, "loss": 4.2325, "step": 20237 }, { "epoch": 0.618142944410507, "grad_norm": 0.42997920513153076, "learning_rate": 1.5932652544145373e-05, "loss": 4.3436, "step": 20238 }, { "epoch": 0.6181734880879658, "grad_norm": 0.4233574867248535, "learning_rate": 1.593041703582817e-05, "loss": 4.2972, "step": 20239 }, { "epoch": 0.6182040317654246, "grad_norm": 0.4162576496601105, "learning_rate": 1.5928181611019287e-05, "loss": 4.2578, "step": 20240 }, { "epoch": 0.6182345754428833, "grad_norm": 0.4255230724811554, "learning_rate": 1.5925946269739304e-05, "loss": 4.263, "step": 20241 }, { "epoch": 0.6182651191203421, "grad_norm": 0.423805832862854, "learning_rate": 1.592371101200879e-05, "loss": 4.2895, "step": 20242 }, { "epoch": 0.6182956627978009, "grad_norm": 0.42069175839424133, "learning_rate": 1.5921475837848337e-05, "loss": 4.3236, "step": 20243 }, { "epoch": 0.6183262064752596, "grad_norm": 0.44709962606430054, "learning_rate": 1.5919240747278532e-05, "loss": 4.2239, "step": 20244 }, { "epoch": 0.6183567501527184, "grad_norm": 0.41705796122550964, "learning_rate": 1.591700574031994e-05, "loss": 4.2104, "step": 20245 }, { "epoch": 0.6183872938301771, "grad_norm": 0.4204055964946747, "learning_rate": 1.591477081699315e-05, "loss": 4.2978, "step": 20246 }, { "epoch": 0.6184178375076359, "grad_norm": 0.4186600148677826, "learning_rate": 1.5912535977318727e-05, "loss": 4.2865, "step": 20247 }, { "epoch": 0.6184483811850947, "grad_norm": 0.4205283522605896, "learning_rate": 1.5910301221317263e-05, "loss": 4.3564, "step": 20248 }, { "epoch": 0.6184789248625534, "grad_norm": 0.42178401350975037, "learning_rate": 1.5908066549009336e-05, "loss": 4.2584, "step": 20249 }, { "epoch": 0.6185094685400122, "grad_norm": 0.44364240765571594, "learning_rate": 1.5905831960415508e-05, "loss": 4.3157, "step": 20250 }, { "epoch": 0.618540012217471, "grad_norm": 0.42070272564888, "learning_rate": 1.590359745555636e-05, "loss": 4.174, "step": 20251 }, { "epoch": 0.6185705558949297, "grad_norm": 0.43817219138145447, "learning_rate": 1.590136303445247e-05, "loss": 4.2756, "step": 20252 }, { "epoch": 0.6186010995723885, "grad_norm": 0.42373126745224, "learning_rate": 1.5899128697124404e-05, "loss": 4.2453, "step": 20253 }, { "epoch": 0.6186316432498473, "grad_norm": 0.4202257990837097, "learning_rate": 1.5896894443592737e-05, "loss": 4.2497, "step": 20254 }, { "epoch": 0.618662186927306, "grad_norm": 0.41706526279449463, "learning_rate": 1.5894660273878054e-05, "loss": 4.2708, "step": 20255 }, { "epoch": 0.6186927306047648, "grad_norm": 0.4252786934375763, "learning_rate": 1.5892426188000912e-05, "loss": 4.257, "step": 20256 }, { "epoch": 0.6187232742822236, "grad_norm": 0.42340850830078125, "learning_rate": 1.589019218598188e-05, "loss": 4.283, "step": 20257 }, { "epoch": 0.6187538179596823, "grad_norm": 0.4204011559486389, "learning_rate": 1.588795826784154e-05, "loss": 4.2595, "step": 20258 }, { "epoch": 0.6187843616371411, "grad_norm": 0.42820918560028076, "learning_rate": 1.5885724433600443e-05, "loss": 4.2732, "step": 20259 }, { "epoch": 0.6188149053145999, "grad_norm": 0.41874584555625916, "learning_rate": 1.588349068327917e-05, "loss": 4.2362, "step": 20260 }, { "epoch": 0.6188454489920586, "grad_norm": 0.41446810960769653, "learning_rate": 1.5881257016898293e-05, "loss": 4.2213, "step": 20261 }, { "epoch": 0.6188759926695174, "grad_norm": 0.4333711564540863, "learning_rate": 1.5879023434478362e-05, "loss": 4.1227, "step": 20262 }, { "epoch": 0.6189065363469761, "grad_norm": 0.4193894863128662, "learning_rate": 1.5876789936039962e-05, "loss": 4.3244, "step": 20263 }, { "epoch": 0.6189370800244349, "grad_norm": 0.41615059971809387, "learning_rate": 1.5874556521603643e-05, "loss": 4.2982, "step": 20264 }, { "epoch": 0.6189676237018937, "grad_norm": 0.42085957527160645, "learning_rate": 1.587232319118997e-05, "loss": 4.2719, "step": 20265 }, { "epoch": 0.6189981673793524, "grad_norm": 0.42200446128845215, "learning_rate": 1.5870089944819515e-05, "loss": 4.2368, "step": 20266 }, { "epoch": 0.6190287110568112, "grad_norm": 0.4202564060688019, "learning_rate": 1.586785678251283e-05, "loss": 4.2981, "step": 20267 }, { "epoch": 0.61905925473427, "grad_norm": 0.4326910376548767, "learning_rate": 1.5865623704290483e-05, "loss": 4.3102, "step": 20268 }, { "epoch": 0.6190897984117287, "grad_norm": 0.4278632700443268, "learning_rate": 1.5863390710173047e-05, "loss": 4.2971, "step": 20269 }, { "epoch": 0.6191203420891875, "grad_norm": 0.42495208978652954, "learning_rate": 1.5861157800181057e-05, "loss": 4.2861, "step": 20270 }, { "epoch": 0.6191508857666463, "grad_norm": 0.42698755860328674, "learning_rate": 1.5858924974335095e-05, "loss": 4.1084, "step": 20271 }, { "epoch": 0.619181429444105, "grad_norm": 0.4311671555042267, "learning_rate": 1.585669223265571e-05, "loss": 4.2746, "step": 20272 }, { "epoch": 0.6192119731215638, "grad_norm": 0.42427751421928406, "learning_rate": 1.5854459575163452e-05, "loss": 4.0819, "step": 20273 }, { "epoch": 0.6192425167990226, "grad_norm": 0.43078160285949707, "learning_rate": 1.585222700187889e-05, "loss": 4.1492, "step": 20274 }, { "epoch": 0.6192730604764813, "grad_norm": 0.41958087682724, "learning_rate": 1.5849994512822582e-05, "loss": 4.2648, "step": 20275 }, { "epoch": 0.6193036041539401, "grad_norm": 0.42291170358657837, "learning_rate": 1.5847762108015075e-05, "loss": 4.4091, "step": 20276 }, { "epoch": 0.619334147831399, "grad_norm": 0.42885398864746094, "learning_rate": 1.5845529787476924e-05, "loss": 4.3246, "step": 20277 }, { "epoch": 0.6193646915088576, "grad_norm": 0.4237627685070038, "learning_rate": 1.5843297551228696e-05, "loss": 4.2416, "step": 20278 }, { "epoch": 0.6193952351863165, "grad_norm": 0.41977766156196594, "learning_rate": 1.5841065399290932e-05, "loss": 4.2868, "step": 20279 }, { "epoch": 0.6194257788637751, "grad_norm": 0.42242512106895447, "learning_rate": 1.5838833331684192e-05, "loss": 4.2244, "step": 20280 }, { "epoch": 0.619456322541234, "grad_norm": 0.42381665110588074, "learning_rate": 1.583660134842902e-05, "loss": 4.3033, "step": 20281 }, { "epoch": 0.6194868662186928, "grad_norm": 0.42385512590408325, "learning_rate": 1.5834369449545966e-05, "loss": 4.2832, "step": 20282 }, { "epoch": 0.6195174098961514, "grad_norm": 0.4430061876773834, "learning_rate": 1.5832137635055595e-05, "loss": 4.2809, "step": 20283 }, { "epoch": 0.6195479535736103, "grad_norm": 0.42688313126564026, "learning_rate": 1.5829905904978437e-05, "loss": 4.2237, "step": 20284 }, { "epoch": 0.6195784972510691, "grad_norm": 0.42357322573661804, "learning_rate": 1.5827674259335047e-05, "loss": 4.2994, "step": 20285 }, { "epoch": 0.6196090409285278, "grad_norm": 0.4291011691093445, "learning_rate": 1.582544269814599e-05, "loss": 4.3222, "step": 20286 }, { "epoch": 0.6196395846059866, "grad_norm": 0.42880979180336, "learning_rate": 1.5823211221431795e-05, "loss": 4.2609, "step": 20287 }, { "epoch": 0.6196701282834454, "grad_norm": 0.42135950922966003, "learning_rate": 1.5820979829213e-05, "loss": 4.3126, "step": 20288 }, { "epoch": 0.6197006719609041, "grad_norm": 0.41937580704689026, "learning_rate": 1.581874852151018e-05, "loss": 4.2866, "step": 20289 }, { "epoch": 0.6197312156383629, "grad_norm": 0.41904130578041077, "learning_rate": 1.5816517298343852e-05, "loss": 4.3179, "step": 20290 }, { "epoch": 0.6197617593158217, "grad_norm": 0.42569902539253235, "learning_rate": 1.581428615973457e-05, "loss": 4.2715, "step": 20291 }, { "epoch": 0.6197923029932804, "grad_norm": 0.42717045545578003, "learning_rate": 1.581205510570289e-05, "loss": 4.3297, "step": 20292 }, { "epoch": 0.6198228466707392, "grad_norm": 0.42426279187202454, "learning_rate": 1.580982413626933e-05, "loss": 4.2609, "step": 20293 }, { "epoch": 0.619853390348198, "grad_norm": 0.42312732338905334, "learning_rate": 1.580759325145445e-05, "loss": 4.2788, "step": 20294 }, { "epoch": 0.6198839340256567, "grad_norm": 0.4223068952560425, "learning_rate": 1.5805362451278787e-05, "loss": 4.3583, "step": 20295 }, { "epoch": 0.6199144777031155, "grad_norm": 0.4320734441280365, "learning_rate": 1.5803131735762877e-05, "loss": 4.2605, "step": 20296 }, { "epoch": 0.6199450213805742, "grad_norm": 0.434375137090683, "learning_rate": 1.5800901104927266e-05, "loss": 4.1801, "step": 20297 }, { "epoch": 0.619975565058033, "grad_norm": 0.42789122462272644, "learning_rate": 1.5798670558792477e-05, "loss": 4.2998, "step": 20298 }, { "epoch": 0.6200061087354918, "grad_norm": 0.4216354489326477, "learning_rate": 1.5796440097379064e-05, "loss": 4.3367, "step": 20299 }, { "epoch": 0.6200366524129505, "grad_norm": 0.4327588379383087, "learning_rate": 1.5794209720707568e-05, "loss": 4.3311, "step": 20300 }, { "epoch": 0.6200671960904093, "grad_norm": 0.42482462525367737, "learning_rate": 1.5791979428798503e-05, "loss": 4.2198, "step": 20301 }, { "epoch": 0.6200977397678681, "grad_norm": 0.42469877004623413, "learning_rate": 1.5789749221672425e-05, "loss": 4.3675, "step": 20302 }, { "epoch": 0.6201282834453268, "grad_norm": 0.4283198118209839, "learning_rate": 1.5787519099349863e-05, "loss": 4.2846, "step": 20303 }, { "epoch": 0.6201588271227856, "grad_norm": 0.4224816560745239, "learning_rate": 1.5785289061851345e-05, "loss": 4.2189, "step": 20304 }, { "epoch": 0.6201893708002444, "grad_norm": 0.43048226833343506, "learning_rate": 1.5783059109197406e-05, "loss": 4.3017, "step": 20305 }, { "epoch": 0.6202199144777031, "grad_norm": 0.4178590774536133, "learning_rate": 1.578082924140859e-05, "loss": 4.2445, "step": 20306 }, { "epoch": 0.6202504581551619, "grad_norm": 0.4209390878677368, "learning_rate": 1.577859945850541e-05, "loss": 4.3136, "step": 20307 }, { "epoch": 0.6202810018326207, "grad_norm": 0.4214223027229309, "learning_rate": 1.5776369760508402e-05, "loss": 4.2557, "step": 20308 }, { "epoch": 0.6203115455100794, "grad_norm": 0.42098963260650635, "learning_rate": 1.5774140147438117e-05, "loss": 4.2414, "step": 20309 }, { "epoch": 0.6203420891875382, "grad_norm": 0.42959919571876526, "learning_rate": 1.5771910619315056e-05, "loss": 4.3121, "step": 20310 }, { "epoch": 0.620372632864997, "grad_norm": 0.43906331062316895, "learning_rate": 1.5769681176159757e-05, "loss": 4.2401, "step": 20311 }, { "epoch": 0.6204031765424557, "grad_norm": 0.42960256338119507, "learning_rate": 1.5767451817992755e-05, "loss": 4.3726, "step": 20312 }, { "epoch": 0.6204337202199145, "grad_norm": 0.429985374212265, "learning_rate": 1.576522254483457e-05, "loss": 4.3683, "step": 20313 }, { "epoch": 0.6204642638973732, "grad_norm": 0.4191993772983551, "learning_rate": 1.576299335670573e-05, "loss": 4.2382, "step": 20314 }, { "epoch": 0.620494807574832, "grad_norm": 0.4269378185272217, "learning_rate": 1.576076425362675e-05, "loss": 4.3277, "step": 20315 }, { "epoch": 0.6205253512522908, "grad_norm": 0.43144339323043823, "learning_rate": 1.5758535235618173e-05, "loss": 4.2725, "step": 20316 }, { "epoch": 0.6205558949297495, "grad_norm": 0.4385301470756531, "learning_rate": 1.5756306302700512e-05, "loss": 4.2662, "step": 20317 }, { "epoch": 0.6205864386072083, "grad_norm": 0.42224547266960144, "learning_rate": 1.5754077454894293e-05, "loss": 4.2684, "step": 20318 }, { "epoch": 0.6206169822846671, "grad_norm": 0.4285850524902344, "learning_rate": 1.575184869222003e-05, "loss": 4.1856, "step": 20319 }, { "epoch": 0.6206475259621258, "grad_norm": 0.4195028841495514, "learning_rate": 1.574962001469826e-05, "loss": 4.2295, "step": 20320 }, { "epoch": 0.6206780696395846, "grad_norm": 0.4268270432949066, "learning_rate": 1.574739142234949e-05, "loss": 4.323, "step": 20321 }, { "epoch": 0.6207086133170434, "grad_norm": 0.4255701005458832, "learning_rate": 1.574516291519424e-05, "loss": 4.2432, "step": 20322 }, { "epoch": 0.6207391569945021, "grad_norm": 0.41704368591308594, "learning_rate": 1.5742934493253043e-05, "loss": 4.3378, "step": 20323 }, { "epoch": 0.6207697006719609, "grad_norm": 0.42085686326026917, "learning_rate": 1.5740706156546396e-05, "loss": 4.2158, "step": 20324 }, { "epoch": 0.6208002443494197, "grad_norm": 0.4224969148635864, "learning_rate": 1.5738477905094835e-05, "loss": 4.3468, "step": 20325 }, { "epoch": 0.6208307880268784, "grad_norm": 0.4156099855899811, "learning_rate": 1.5736249738918872e-05, "loss": 4.2974, "step": 20326 }, { "epoch": 0.6208613317043372, "grad_norm": 0.41399621963500977, "learning_rate": 1.5734021658039015e-05, "loss": 4.2018, "step": 20327 }, { "epoch": 0.620891875381796, "grad_norm": 0.4257844388484955, "learning_rate": 1.5731793662475786e-05, "loss": 4.2825, "step": 20328 }, { "epoch": 0.6209224190592547, "grad_norm": 0.4178290367126465, "learning_rate": 1.5729565752249707e-05, "loss": 4.2978, "step": 20329 }, { "epoch": 0.6209529627367135, "grad_norm": 0.4173493981361389, "learning_rate": 1.572733792738127e-05, "loss": 4.2094, "step": 20330 }, { "epoch": 0.6209835064141722, "grad_norm": 0.43077078461647034, "learning_rate": 1.5725110187891014e-05, "loss": 4.2437, "step": 20331 }, { "epoch": 0.621014050091631, "grad_norm": 0.4263695180416107, "learning_rate": 1.572288253379942e-05, "loss": 4.3122, "step": 20332 }, { "epoch": 0.6210445937690898, "grad_norm": 0.42415204644203186, "learning_rate": 1.5720654965127027e-05, "loss": 4.3099, "step": 20333 }, { "epoch": 0.6210751374465485, "grad_norm": 0.4313192069530487, "learning_rate": 1.5718427481894332e-05, "loss": 4.1851, "step": 20334 }, { "epoch": 0.6211056811240073, "grad_norm": 0.4266579747200012, "learning_rate": 1.571620008412185e-05, "loss": 4.3143, "step": 20335 }, { "epoch": 0.6211362248014661, "grad_norm": 0.4186718761920929, "learning_rate": 1.5713972771830078e-05, "loss": 4.2764, "step": 20336 }, { "epoch": 0.6211667684789248, "grad_norm": 0.4181123971939087, "learning_rate": 1.5711745545039546e-05, "loss": 4.2347, "step": 20337 }, { "epoch": 0.6211973121563836, "grad_norm": 0.41785579919815063, "learning_rate": 1.570951840377074e-05, "loss": 4.3206, "step": 20338 }, { "epoch": 0.6212278558338424, "grad_norm": 0.4284851551055908, "learning_rate": 1.5707291348044174e-05, "loss": 4.2407, "step": 20339 }, { "epoch": 0.6212583995113011, "grad_norm": 0.40974780917167664, "learning_rate": 1.5705064377880362e-05, "loss": 4.203, "step": 20340 }, { "epoch": 0.6212889431887599, "grad_norm": 0.43241509795188904, "learning_rate": 1.5702837493299797e-05, "loss": 4.3194, "step": 20341 }, { "epoch": 0.6213194868662187, "grad_norm": 0.41172483563423157, "learning_rate": 1.570061069432298e-05, "loss": 4.2611, "step": 20342 }, { "epoch": 0.6213500305436774, "grad_norm": 0.42608028650283813, "learning_rate": 1.5698383980970437e-05, "loss": 4.3192, "step": 20343 }, { "epoch": 0.6213805742211362, "grad_norm": 0.4167874753475189, "learning_rate": 1.5696157353262642e-05, "loss": 4.2763, "step": 20344 }, { "epoch": 0.621411117898595, "grad_norm": 0.4159981906414032, "learning_rate": 1.569393081122011e-05, "loss": 4.1735, "step": 20345 }, { "epoch": 0.6214416615760537, "grad_norm": 0.4248446524143219, "learning_rate": 1.5691704354863354e-05, "loss": 4.1923, "step": 20346 }, { "epoch": 0.6214722052535125, "grad_norm": 0.4297676384449005, "learning_rate": 1.568947798421285e-05, "loss": 4.2529, "step": 20347 }, { "epoch": 0.6215027489309712, "grad_norm": 0.4203876256942749, "learning_rate": 1.5687251699289118e-05, "loss": 4.1728, "step": 20348 }, { "epoch": 0.62153329260843, "grad_norm": 0.41840192675590515, "learning_rate": 1.5685025500112638e-05, "loss": 4.2908, "step": 20349 }, { "epoch": 0.6215638362858888, "grad_norm": 0.4156193435192108, "learning_rate": 1.5682799386703926e-05, "loss": 4.2762, "step": 20350 }, { "epoch": 0.6215943799633475, "grad_norm": 0.41647791862487793, "learning_rate": 1.5680573359083473e-05, "loss": 4.2486, "step": 20351 }, { "epoch": 0.6216249236408063, "grad_norm": 0.41755229234695435, "learning_rate": 1.567834741727176e-05, "loss": 4.2215, "step": 20352 }, { "epoch": 0.6216554673182652, "grad_norm": 0.42181047797203064, "learning_rate": 1.5676121561289298e-05, "loss": 4.2887, "step": 20353 }, { "epoch": 0.6216860109957238, "grad_norm": 0.42424893379211426, "learning_rate": 1.567389579115659e-05, "loss": 4.2222, "step": 20354 }, { "epoch": 0.6217165546731827, "grad_norm": 0.4411254823207855, "learning_rate": 1.5671670106894103e-05, "loss": 4.2799, "step": 20355 }, { "epoch": 0.6217470983506415, "grad_norm": 0.4182320535182953, "learning_rate": 1.566944450852236e-05, "loss": 4.264, "step": 20356 }, { "epoch": 0.6217776420281002, "grad_norm": 0.44054317474365234, "learning_rate": 1.566721899606183e-05, "loss": 4.313, "step": 20357 }, { "epoch": 0.621808185705559, "grad_norm": 0.42924773693084717, "learning_rate": 1.5664993569533015e-05, "loss": 4.1902, "step": 20358 }, { "epoch": 0.6218387293830178, "grad_norm": 0.418977290391922, "learning_rate": 1.5662768228956398e-05, "loss": 4.2367, "step": 20359 }, { "epoch": 0.6218692730604765, "grad_norm": 0.4223248064517975, "learning_rate": 1.5660542974352487e-05, "loss": 4.2941, "step": 20360 }, { "epoch": 0.6218998167379353, "grad_norm": 0.42219674587249756, "learning_rate": 1.565831780574175e-05, "loss": 4.3426, "step": 20361 }, { "epoch": 0.6219303604153941, "grad_norm": 0.4136650860309601, "learning_rate": 1.5656092723144684e-05, "loss": 4.2317, "step": 20362 }, { "epoch": 0.6219609040928528, "grad_norm": 0.4278407096862793, "learning_rate": 1.5653867726581785e-05, "loss": 4.187, "step": 20363 }, { "epoch": 0.6219914477703116, "grad_norm": 0.4246256351470947, "learning_rate": 1.565164281607352e-05, "loss": 4.2379, "step": 20364 }, { "epoch": 0.6220219914477703, "grad_norm": 0.4197361469268799, "learning_rate": 1.5649417991640394e-05, "loss": 4.2356, "step": 20365 }, { "epoch": 0.6220525351252291, "grad_norm": 0.4175150394439697, "learning_rate": 1.5647193253302884e-05, "loss": 4.2566, "step": 20366 }, { "epoch": 0.6220830788026879, "grad_norm": 0.42406439781188965, "learning_rate": 1.5644968601081467e-05, "loss": 4.1986, "step": 20367 }, { "epoch": 0.6221136224801466, "grad_norm": 0.41690903902053833, "learning_rate": 1.5642744034996642e-05, "loss": 4.2711, "step": 20368 }, { "epoch": 0.6221441661576054, "grad_norm": 0.43615296483039856, "learning_rate": 1.564051955506888e-05, "loss": 4.2608, "step": 20369 }, { "epoch": 0.6221747098350642, "grad_norm": 0.42185547947883606, "learning_rate": 1.563829516131866e-05, "loss": 4.383, "step": 20370 }, { "epoch": 0.6222052535125229, "grad_norm": 0.42676427960395813, "learning_rate": 1.5636070853766482e-05, "loss": 4.3823, "step": 20371 }, { "epoch": 0.6222357971899817, "grad_norm": 0.42848217487335205, "learning_rate": 1.5633846632432805e-05, "loss": 4.2419, "step": 20372 }, { "epoch": 0.6222663408674405, "grad_norm": 0.4055107533931732, "learning_rate": 1.563162249733812e-05, "loss": 4.2119, "step": 20373 }, { "epoch": 0.6222968845448992, "grad_norm": 0.43010008335113525, "learning_rate": 1.5629398448502913e-05, "loss": 4.3208, "step": 20374 }, { "epoch": 0.622327428222358, "grad_norm": 0.4282521605491638, "learning_rate": 1.5627174485947637e-05, "loss": 4.2244, "step": 20375 }, { "epoch": 0.6223579718998168, "grad_norm": 0.41960516571998596, "learning_rate": 1.562495060969279e-05, "loss": 4.2955, "step": 20376 }, { "epoch": 0.6223885155772755, "grad_norm": 0.42176276445388794, "learning_rate": 1.562272681975885e-05, "loss": 4.2908, "step": 20377 }, { "epoch": 0.6224190592547343, "grad_norm": 0.4205428957939148, "learning_rate": 1.5620503116166278e-05, "loss": 4.3244, "step": 20378 }, { "epoch": 0.6224496029321931, "grad_norm": 0.43496301770210266, "learning_rate": 1.5618279498935557e-05, "loss": 4.2418, "step": 20379 }, { "epoch": 0.6224801466096518, "grad_norm": 0.4248429834842682, "learning_rate": 1.5616055968087164e-05, "loss": 4.3853, "step": 20380 }, { "epoch": 0.6225106902871106, "grad_norm": 0.4271824061870575, "learning_rate": 1.5613832523641565e-05, "loss": 4.3316, "step": 20381 }, { "epoch": 0.6225412339645693, "grad_norm": 0.44480347633361816, "learning_rate": 1.5611609165619247e-05, "loss": 4.1645, "step": 20382 }, { "epoch": 0.6225717776420281, "grad_norm": 0.4196718633174896, "learning_rate": 1.5609385894040652e-05, "loss": 4.2468, "step": 20383 }, { "epoch": 0.6226023213194869, "grad_norm": 0.4197300970554352, "learning_rate": 1.5607162708926273e-05, "loss": 4.2281, "step": 20384 }, { "epoch": 0.6226328649969456, "grad_norm": 0.4283983111381531, "learning_rate": 1.5604939610296587e-05, "loss": 4.3166, "step": 20385 }, { "epoch": 0.6226634086744044, "grad_norm": 0.4368489682674408, "learning_rate": 1.5602716598172044e-05, "loss": 4.2542, "step": 20386 }, { "epoch": 0.6226939523518632, "grad_norm": 0.4334263801574707, "learning_rate": 1.560049367257312e-05, "loss": 4.176, "step": 20387 }, { "epoch": 0.6227244960293219, "grad_norm": 0.42323943972587585, "learning_rate": 1.559827083352029e-05, "loss": 4.3459, "step": 20388 }, { "epoch": 0.6227550397067807, "grad_norm": 0.4206070005893707, "learning_rate": 1.559604808103401e-05, "loss": 4.3006, "step": 20389 }, { "epoch": 0.6227855833842395, "grad_norm": 0.4181557595729828, "learning_rate": 1.559382541513475e-05, "loss": 4.2314, "step": 20390 }, { "epoch": 0.6228161270616982, "grad_norm": 0.4151463806629181, "learning_rate": 1.5591602835842982e-05, "loss": 4.2962, "step": 20391 }, { "epoch": 0.622846670739157, "grad_norm": 0.4257940351963043, "learning_rate": 1.5589380343179155e-05, "loss": 4.2383, "step": 20392 }, { "epoch": 0.6228772144166158, "grad_norm": 0.41307637095451355, "learning_rate": 1.558715793716374e-05, "loss": 4.1905, "step": 20393 }, { "epoch": 0.6229077580940745, "grad_norm": 0.43426284193992615, "learning_rate": 1.5584935617817215e-05, "loss": 4.207, "step": 20394 }, { "epoch": 0.6229383017715333, "grad_norm": 0.4228580594062805, "learning_rate": 1.5582713385160014e-05, "loss": 4.2295, "step": 20395 }, { "epoch": 0.622968845448992, "grad_norm": 0.42656219005584717, "learning_rate": 1.5580491239212624e-05, "loss": 4.3039, "step": 20396 }, { "epoch": 0.6229993891264508, "grad_norm": 0.4268149733543396, "learning_rate": 1.5578269179995492e-05, "loss": 4.1396, "step": 20397 }, { "epoch": 0.6230299328039096, "grad_norm": 0.4204046130180359, "learning_rate": 1.5576047207529072e-05, "loss": 4.1736, "step": 20398 }, { "epoch": 0.6230604764813683, "grad_norm": 0.42484650015830994, "learning_rate": 1.5573825321833846e-05, "loss": 4.2679, "step": 20399 }, { "epoch": 0.6230910201588271, "grad_norm": 0.4287087619304657, "learning_rate": 1.557160352293024e-05, "loss": 4.1505, "step": 20400 }, { "epoch": 0.6231215638362859, "grad_norm": 0.437306672334671, "learning_rate": 1.556938181083873e-05, "loss": 4.2553, "step": 20401 }, { "epoch": 0.6231521075137446, "grad_norm": 0.42909711599349976, "learning_rate": 1.5567160185579782e-05, "loss": 4.2601, "step": 20402 }, { "epoch": 0.6231826511912034, "grad_norm": 0.4349684417247772, "learning_rate": 1.5564938647173827e-05, "loss": 4.1588, "step": 20403 }, { "epoch": 0.6232131948686622, "grad_norm": 0.4256328046321869, "learning_rate": 1.556271719564134e-05, "loss": 4.1222, "step": 20404 }, { "epoch": 0.6232437385461209, "grad_norm": 0.4251222014427185, "learning_rate": 1.5560495831002775e-05, "loss": 4.2675, "step": 20405 }, { "epoch": 0.6232742822235797, "grad_norm": 0.4130258858203888, "learning_rate": 1.5558274553278566e-05, "loss": 4.3331, "step": 20406 }, { "epoch": 0.6233048259010385, "grad_norm": 0.4297840893268585, "learning_rate": 1.5556053362489176e-05, "loss": 4.3193, "step": 20407 }, { "epoch": 0.6233353695784972, "grad_norm": 0.4152376353740692, "learning_rate": 1.555383225865507e-05, "loss": 4.2764, "step": 20408 }, { "epoch": 0.623365913255956, "grad_norm": 0.44754472374916077, "learning_rate": 1.5551611241796677e-05, "loss": 4.2699, "step": 20409 }, { "epoch": 0.6233964569334148, "grad_norm": 0.42134982347488403, "learning_rate": 1.554939031193446e-05, "loss": 4.2505, "step": 20410 }, { "epoch": 0.6234270006108735, "grad_norm": 0.42177945375442505, "learning_rate": 1.554716946908887e-05, "loss": 4.2266, "step": 20411 }, { "epoch": 0.6234575442883323, "grad_norm": 0.42395681142807007, "learning_rate": 1.554494871328035e-05, "loss": 4.3725, "step": 20412 }, { "epoch": 0.623488087965791, "grad_norm": 0.42684584856033325, "learning_rate": 1.5542728044529348e-05, "loss": 4.3258, "step": 20413 }, { "epoch": 0.6235186316432498, "grad_norm": 0.42413055896759033, "learning_rate": 1.554050746285631e-05, "loss": 4.2662, "step": 20414 }, { "epoch": 0.6235491753207086, "grad_norm": 0.42437878251075745, "learning_rate": 1.553828696828168e-05, "loss": 4.2901, "step": 20415 }, { "epoch": 0.6235797189981673, "grad_norm": 0.4237339198589325, "learning_rate": 1.5536066560825914e-05, "loss": 4.1991, "step": 20416 }, { "epoch": 0.6236102626756261, "grad_norm": 0.4164661765098572, "learning_rate": 1.553384624050944e-05, "loss": 4.3362, "step": 20417 }, { "epoch": 0.6236408063530849, "grad_norm": 0.42497438192367554, "learning_rate": 1.5531626007352713e-05, "loss": 4.2823, "step": 20418 }, { "epoch": 0.6236713500305436, "grad_norm": 0.4274701178073883, "learning_rate": 1.5529405861376177e-05, "loss": 4.1533, "step": 20419 }, { "epoch": 0.6237018937080024, "grad_norm": 0.4238717257976532, "learning_rate": 1.5527185802600274e-05, "loss": 4.3365, "step": 20420 }, { "epoch": 0.6237324373854612, "grad_norm": 0.42853251099586487, "learning_rate": 1.5524965831045433e-05, "loss": 4.3271, "step": 20421 }, { "epoch": 0.6237629810629199, "grad_norm": 0.4309992492198944, "learning_rate": 1.5522745946732113e-05, "loss": 4.3745, "step": 20422 }, { "epoch": 0.6237935247403787, "grad_norm": 0.4205266535282135, "learning_rate": 1.5520526149680733e-05, "loss": 4.2585, "step": 20423 }, { "epoch": 0.6238240684178376, "grad_norm": 0.4279661774635315, "learning_rate": 1.5518306439911745e-05, "loss": 4.2512, "step": 20424 }, { "epoch": 0.6238546120952962, "grad_norm": 0.4343249499797821, "learning_rate": 1.5516086817445592e-05, "loss": 4.3073, "step": 20425 }, { "epoch": 0.623885155772755, "grad_norm": 0.4404680132865906, "learning_rate": 1.5513867282302695e-05, "loss": 4.4298, "step": 20426 }, { "epoch": 0.6239156994502139, "grad_norm": 0.4444870948791504, "learning_rate": 1.5511647834503505e-05, "loss": 4.2751, "step": 20427 }, { "epoch": 0.6239462431276726, "grad_norm": 0.4136878252029419, "learning_rate": 1.5509428474068455e-05, "loss": 4.2845, "step": 20428 }, { "epoch": 0.6239767868051314, "grad_norm": 0.43040895462036133, "learning_rate": 1.5507209201017968e-05, "loss": 4.3108, "step": 20429 }, { "epoch": 0.62400733048259, "grad_norm": 0.42712631821632385, "learning_rate": 1.5504990015372493e-05, "loss": 4.2704, "step": 20430 }, { "epoch": 0.6240378741600489, "grad_norm": 0.43198660016059875, "learning_rate": 1.5502770917152454e-05, "loss": 4.2949, "step": 20431 }, { "epoch": 0.6240684178375077, "grad_norm": 0.43517759442329407, "learning_rate": 1.550055190637828e-05, "loss": 4.3755, "step": 20432 }, { "epoch": 0.6240989615149664, "grad_norm": 0.4235628545284271, "learning_rate": 1.549833298307042e-05, "loss": 4.2015, "step": 20433 }, { "epoch": 0.6241295051924252, "grad_norm": 0.4237369894981384, "learning_rate": 1.5496114147249286e-05, "loss": 4.3022, "step": 20434 }, { "epoch": 0.624160048869884, "grad_norm": 0.44475850462913513, "learning_rate": 1.5493895398935317e-05, "loss": 4.3204, "step": 20435 }, { "epoch": 0.6241905925473427, "grad_norm": 0.4348040819168091, "learning_rate": 1.5491676738148943e-05, "loss": 4.3221, "step": 20436 }, { "epoch": 0.6242211362248015, "grad_norm": 0.42737433314323425, "learning_rate": 1.5489458164910593e-05, "loss": 4.2347, "step": 20437 }, { "epoch": 0.6242516799022603, "grad_norm": 0.43097490072250366, "learning_rate": 1.5487239679240677e-05, "loss": 4.228, "step": 20438 }, { "epoch": 0.624282223579719, "grad_norm": 0.4234485626220703, "learning_rate": 1.5485021281159657e-05, "loss": 4.1399, "step": 20439 }, { "epoch": 0.6243127672571778, "grad_norm": 0.4298597276210785, "learning_rate": 1.5482802970687922e-05, "loss": 4.3222, "step": 20440 }, { "epoch": 0.6243433109346366, "grad_norm": 0.424732506275177, "learning_rate": 1.5480584747845913e-05, "loss": 4.2665, "step": 20441 }, { "epoch": 0.6243738546120953, "grad_norm": 0.4101489186286926, "learning_rate": 1.5478366612654066e-05, "loss": 4.3453, "step": 20442 }, { "epoch": 0.6244043982895541, "grad_norm": 0.4285544157028198, "learning_rate": 1.5476148565132793e-05, "loss": 4.2672, "step": 20443 }, { "epoch": 0.6244349419670129, "grad_norm": 0.43199455738067627, "learning_rate": 1.5473930605302507e-05, "loss": 4.2517, "step": 20444 }, { "epoch": 0.6244654856444716, "grad_norm": 0.43550270795822144, "learning_rate": 1.5471712733183648e-05, "loss": 4.2484, "step": 20445 }, { "epoch": 0.6244960293219304, "grad_norm": 0.42313677072525024, "learning_rate": 1.546949494879662e-05, "loss": 4.2084, "step": 20446 }, { "epoch": 0.6245265729993891, "grad_norm": 0.4313671886920929, "learning_rate": 1.546727725216186e-05, "loss": 4.301, "step": 20447 }, { "epoch": 0.6245571166768479, "grad_norm": 0.418156236410141, "learning_rate": 1.5465059643299775e-05, "loss": 4.3186, "step": 20448 }, { "epoch": 0.6245876603543067, "grad_norm": 0.41860726475715637, "learning_rate": 1.5462842122230787e-05, "loss": 4.3636, "step": 20449 }, { "epoch": 0.6246182040317654, "grad_norm": 0.43999162316322327, "learning_rate": 1.5460624688975323e-05, "loss": 4.3307, "step": 20450 }, { "epoch": 0.6246487477092242, "grad_norm": 0.435992956161499, "learning_rate": 1.545840734355379e-05, "loss": 4.2781, "step": 20451 }, { "epoch": 0.624679291386683, "grad_norm": 0.42577314376831055, "learning_rate": 1.54561900859866e-05, "loss": 4.2302, "step": 20452 }, { "epoch": 0.6247098350641417, "grad_norm": 0.42232269048690796, "learning_rate": 1.5453972916294182e-05, "loss": 4.252, "step": 20453 }, { "epoch": 0.6247403787416005, "grad_norm": 0.43330708146095276, "learning_rate": 1.5451755834496934e-05, "loss": 4.2305, "step": 20454 }, { "epoch": 0.6247709224190593, "grad_norm": 0.4333122670650482, "learning_rate": 1.5449538840615283e-05, "loss": 4.2225, "step": 20455 }, { "epoch": 0.624801466096518, "grad_norm": 0.42561444640159607, "learning_rate": 1.5447321934669644e-05, "loss": 4.1943, "step": 20456 }, { "epoch": 0.6248320097739768, "grad_norm": 0.4428400993347168, "learning_rate": 1.5445105116680417e-05, "loss": 4.3213, "step": 20457 }, { "epoch": 0.6248625534514356, "grad_norm": 0.42516303062438965, "learning_rate": 1.5442888386668024e-05, "loss": 4.317, "step": 20458 }, { "epoch": 0.6248930971288943, "grad_norm": 0.42318814992904663, "learning_rate": 1.5440671744652868e-05, "loss": 4.2991, "step": 20459 }, { "epoch": 0.6249236408063531, "grad_norm": 0.42855125665664673, "learning_rate": 1.5438455190655365e-05, "loss": 4.295, "step": 20460 }, { "epoch": 0.6249541844838119, "grad_norm": 0.4654834568500519, "learning_rate": 1.5436238724695918e-05, "loss": 4.1786, "step": 20461 }, { "epoch": 0.6249847281612706, "grad_norm": 0.43741604685783386, "learning_rate": 1.5434022346794945e-05, "loss": 4.2937, "step": 20462 }, { "epoch": 0.6250152718387294, "grad_norm": 0.42260000109672546, "learning_rate": 1.543180605697284e-05, "loss": 4.2562, "step": 20463 }, { "epoch": 0.6250458155161881, "grad_norm": 0.41435205936431885, "learning_rate": 1.5429589855250023e-05, "loss": 4.2873, "step": 20464 }, { "epoch": 0.6250763591936469, "grad_norm": 0.4162319600582123, "learning_rate": 1.5427373741646884e-05, "loss": 4.2177, "step": 20465 }, { "epoch": 0.6251069028711057, "grad_norm": 0.446382075548172, "learning_rate": 1.542515771618384e-05, "loss": 4.2275, "step": 20466 }, { "epoch": 0.6251374465485644, "grad_norm": 0.43159037828445435, "learning_rate": 1.5422941778881296e-05, "loss": 4.3307, "step": 20467 }, { "epoch": 0.6251679902260232, "grad_norm": 0.43343761563301086, "learning_rate": 1.5420725929759648e-05, "loss": 4.3196, "step": 20468 }, { "epoch": 0.625198533903482, "grad_norm": 0.43355026841163635, "learning_rate": 1.5418510168839296e-05, "loss": 4.2746, "step": 20469 }, { "epoch": 0.6252290775809407, "grad_norm": 0.42635712027549744, "learning_rate": 1.541629449614066e-05, "loss": 4.2291, "step": 20470 }, { "epoch": 0.6252596212583995, "grad_norm": 0.42737945914268494, "learning_rate": 1.5414078911684114e-05, "loss": 4.1564, "step": 20471 }, { "epoch": 0.6252901649358583, "grad_norm": 0.42674311995506287, "learning_rate": 1.5411863415490074e-05, "loss": 4.3051, "step": 20472 }, { "epoch": 0.625320708613317, "grad_norm": 0.432319700717926, "learning_rate": 1.5409648007578946e-05, "loss": 4.3145, "step": 20473 }, { "epoch": 0.6253512522907758, "grad_norm": 0.43256083130836487, "learning_rate": 1.5407432687971112e-05, "loss": 4.2033, "step": 20474 }, { "epoch": 0.6253817959682346, "grad_norm": 0.4235641658306122, "learning_rate": 1.540521745668698e-05, "loss": 4.3191, "step": 20475 }, { "epoch": 0.6254123396456933, "grad_norm": 0.4388376772403717, "learning_rate": 1.5403002313746957e-05, "loss": 4.2626, "step": 20476 }, { "epoch": 0.6254428833231521, "grad_norm": 0.4441100060939789, "learning_rate": 1.5400787259171405e-05, "loss": 4.2853, "step": 20477 }, { "epoch": 0.6254734270006109, "grad_norm": 0.4425044059753418, "learning_rate": 1.5398572292980747e-05, "loss": 4.2505, "step": 20478 }, { "epoch": 0.6255039706780696, "grad_norm": 0.4327234923839569, "learning_rate": 1.5396357415195377e-05, "loss": 4.2496, "step": 20479 }, { "epoch": 0.6255345143555284, "grad_norm": 0.423209011554718, "learning_rate": 1.5394142625835674e-05, "loss": 4.2117, "step": 20480 }, { "epoch": 0.6255650580329871, "grad_norm": 0.4302835166454315, "learning_rate": 1.5391927924922046e-05, "loss": 4.1901, "step": 20481 }, { "epoch": 0.6255956017104459, "grad_norm": 0.42531394958496094, "learning_rate": 1.538971331247487e-05, "loss": 4.302, "step": 20482 }, { "epoch": 0.6256261453879047, "grad_norm": 0.43408116698265076, "learning_rate": 1.5387498788514547e-05, "loss": 4.2772, "step": 20483 }, { "epoch": 0.6256566890653634, "grad_norm": 0.43001505732536316, "learning_rate": 1.5385284353061475e-05, "loss": 4.3176, "step": 20484 }, { "epoch": 0.6256872327428222, "grad_norm": 0.4313301742076874, "learning_rate": 1.5383070006136018e-05, "loss": 4.2521, "step": 20485 }, { "epoch": 0.625717776420281, "grad_norm": 0.42447420954704285, "learning_rate": 1.5380855747758582e-05, "loss": 4.3216, "step": 20486 }, { "epoch": 0.6257483200977397, "grad_norm": 0.4406334161758423, "learning_rate": 1.5378641577949565e-05, "loss": 4.2473, "step": 20487 }, { "epoch": 0.6257788637751985, "grad_norm": 0.4329853355884552, "learning_rate": 1.5376427496729327e-05, "loss": 4.228, "step": 20488 }, { "epoch": 0.6258094074526573, "grad_norm": 0.43862584233283997, "learning_rate": 1.537421350411828e-05, "loss": 4.2888, "step": 20489 }, { "epoch": 0.625839951130116, "grad_norm": 0.41471925377845764, "learning_rate": 1.5371999600136794e-05, "loss": 4.2843, "step": 20490 }, { "epoch": 0.6258704948075748, "grad_norm": 0.4212028980255127, "learning_rate": 1.536978578480526e-05, "loss": 4.3094, "step": 20491 }, { "epoch": 0.6259010384850336, "grad_norm": 0.42969825863838196, "learning_rate": 1.5367572058144053e-05, "loss": 4.3026, "step": 20492 }, { "epoch": 0.6259315821624923, "grad_norm": 0.4282734990119934, "learning_rate": 1.5365358420173576e-05, "loss": 4.3175, "step": 20493 }, { "epoch": 0.6259621258399511, "grad_norm": 0.4298694133758545, "learning_rate": 1.5363144870914183e-05, "loss": 4.2103, "step": 20494 }, { "epoch": 0.62599266951741, "grad_norm": 0.41836288571357727, "learning_rate": 1.5360931410386272e-05, "loss": 4.2383, "step": 20495 }, { "epoch": 0.6260232131948686, "grad_norm": 0.4278787076473236, "learning_rate": 1.535871803861023e-05, "loss": 4.2862, "step": 20496 }, { "epoch": 0.6260537568723274, "grad_norm": 0.45124557614326477, "learning_rate": 1.5356504755606422e-05, "loss": 4.3148, "step": 20497 }, { "epoch": 0.6260843005497861, "grad_norm": 0.4284174144268036, "learning_rate": 1.5354291561395238e-05, "loss": 4.3388, "step": 20498 }, { "epoch": 0.626114844227245, "grad_norm": 0.4341849982738495, "learning_rate": 1.5352078455997048e-05, "loss": 4.2589, "step": 20499 }, { "epoch": 0.6261453879047038, "grad_norm": 0.4300820827484131, "learning_rate": 1.5349865439432227e-05, "loss": 4.2864, "step": 20500 }, { "epoch": 0.6261759315821624, "grad_norm": 0.4237051010131836, "learning_rate": 1.534765251172117e-05, "loss": 4.2822, "step": 20501 }, { "epoch": 0.6262064752596213, "grad_norm": 0.42433297634124756, "learning_rate": 1.5345439672884227e-05, "loss": 4.3205, "step": 20502 }, { "epoch": 0.6262370189370801, "grad_norm": 0.4285863935947418, "learning_rate": 1.5343226922941784e-05, "loss": 4.2933, "step": 20503 }, { "epoch": 0.6262675626145388, "grad_norm": 0.4206720292568207, "learning_rate": 1.534101426191422e-05, "loss": 4.2761, "step": 20504 }, { "epoch": 0.6262981062919976, "grad_norm": 0.4371737241744995, "learning_rate": 1.5338801689821903e-05, "loss": 4.1533, "step": 20505 }, { "epoch": 0.6263286499694564, "grad_norm": 0.42486771941185, "learning_rate": 1.533658920668521e-05, "loss": 4.2093, "step": 20506 }, { "epoch": 0.6263591936469151, "grad_norm": 0.4253760576248169, "learning_rate": 1.5334376812524508e-05, "loss": 4.3482, "step": 20507 }, { "epoch": 0.6263897373243739, "grad_norm": 0.4287201762199402, "learning_rate": 1.5332164507360162e-05, "loss": 4.236, "step": 20508 }, { "epoch": 0.6264202810018327, "grad_norm": 0.42440065741539, "learning_rate": 1.5329952291212546e-05, "loss": 4.2492, "step": 20509 }, { "epoch": 0.6264508246792914, "grad_norm": 0.43819910287857056, "learning_rate": 1.5327740164102044e-05, "loss": 4.2887, "step": 20510 }, { "epoch": 0.6264813683567502, "grad_norm": 0.4308643937110901, "learning_rate": 1.5325528126049e-05, "loss": 4.2272, "step": 20511 }, { "epoch": 0.626511912034209, "grad_norm": 0.4271983504295349, "learning_rate": 1.53233161770738e-05, "loss": 4.2948, "step": 20512 }, { "epoch": 0.6265424557116677, "grad_norm": 0.4378211796283722, "learning_rate": 1.53211043171968e-05, "loss": 4.218, "step": 20513 }, { "epoch": 0.6265729993891265, "grad_norm": 0.432984858751297, "learning_rate": 1.5318892546438367e-05, "loss": 4.2644, "step": 20514 }, { "epoch": 0.6266035430665852, "grad_norm": 0.4227244257926941, "learning_rate": 1.5316680864818878e-05, "loss": 4.1805, "step": 20515 }, { "epoch": 0.626634086744044, "grad_norm": 0.41362765431404114, "learning_rate": 1.5314469272358673e-05, "loss": 4.187, "step": 20516 }, { "epoch": 0.6266646304215028, "grad_norm": 0.43228647112846375, "learning_rate": 1.531225776907813e-05, "loss": 4.2774, "step": 20517 }, { "epoch": 0.6266951740989615, "grad_norm": 0.4300098717212677, "learning_rate": 1.531004635499762e-05, "loss": 4.2663, "step": 20518 }, { "epoch": 0.6267257177764203, "grad_norm": 0.43891414999961853, "learning_rate": 1.5307835030137488e-05, "loss": 4.222, "step": 20519 }, { "epoch": 0.6267562614538791, "grad_norm": 0.43770456314086914, "learning_rate": 1.53056237945181e-05, "loss": 4.2339, "step": 20520 }, { "epoch": 0.6267868051313378, "grad_norm": 0.4355297088623047, "learning_rate": 1.5303412648159833e-05, "loss": 4.2923, "step": 20521 }, { "epoch": 0.6268173488087966, "grad_norm": 0.42034727334976196, "learning_rate": 1.530120159108302e-05, "loss": 4.3015, "step": 20522 }, { "epoch": 0.6268478924862554, "grad_norm": 0.438189834356308, "learning_rate": 1.5298990623308025e-05, "loss": 4.245, "step": 20523 }, { "epoch": 0.6268784361637141, "grad_norm": 0.42624035477638245, "learning_rate": 1.529677974485523e-05, "loss": 4.1463, "step": 20524 }, { "epoch": 0.6269089798411729, "grad_norm": 0.42280465364456177, "learning_rate": 1.5294568955744954e-05, "loss": 4.3408, "step": 20525 }, { "epoch": 0.6269395235186317, "grad_norm": 0.4279245138168335, "learning_rate": 1.5292358255997573e-05, "loss": 4.241, "step": 20526 }, { "epoch": 0.6269700671960904, "grad_norm": 0.4335055947303772, "learning_rate": 1.5290147645633452e-05, "loss": 4.292, "step": 20527 }, { "epoch": 0.6270006108735492, "grad_norm": 0.4219020903110504, "learning_rate": 1.5287937124672924e-05, "loss": 4.2629, "step": 20528 }, { "epoch": 0.627031154551008, "grad_norm": 0.43939676880836487, "learning_rate": 1.5285726693136357e-05, "loss": 4.2482, "step": 20529 }, { "epoch": 0.6270616982284667, "grad_norm": 0.41922539472579956, "learning_rate": 1.52835163510441e-05, "loss": 4.2735, "step": 20530 }, { "epoch": 0.6270922419059255, "grad_norm": 0.42535337805747986, "learning_rate": 1.52813060984165e-05, "loss": 4.2237, "step": 20531 }, { "epoch": 0.6271227855833842, "grad_norm": 0.43808773159980774, "learning_rate": 1.527909593527392e-05, "loss": 4.2608, "step": 20532 }, { "epoch": 0.627153329260843, "grad_norm": 0.4332878589630127, "learning_rate": 1.527688586163669e-05, "loss": 4.2027, "step": 20533 }, { "epoch": 0.6271838729383018, "grad_norm": 0.42725440859794617, "learning_rate": 1.5274675877525174e-05, "loss": 4.3113, "step": 20534 }, { "epoch": 0.6272144166157605, "grad_norm": 0.42450618743896484, "learning_rate": 1.5272465982959727e-05, "loss": 4.3366, "step": 20535 }, { "epoch": 0.6272449602932193, "grad_norm": 0.4278339743614197, "learning_rate": 1.5270256177960675e-05, "loss": 4.3119, "step": 20536 }, { "epoch": 0.6272755039706781, "grad_norm": 0.4312021732330322, "learning_rate": 1.526804646254838e-05, "loss": 4.323, "step": 20537 }, { "epoch": 0.6273060476481368, "grad_norm": 0.42673882842063904, "learning_rate": 1.5265836836743195e-05, "loss": 4.3414, "step": 20538 }, { "epoch": 0.6273365913255956, "grad_norm": 0.4246896505355835, "learning_rate": 1.526362730056544e-05, "loss": 4.2727, "step": 20539 }, { "epoch": 0.6273671350030544, "grad_norm": 0.4255083501338959, "learning_rate": 1.526141785403548e-05, "loss": 4.3122, "step": 20540 }, { "epoch": 0.6273976786805131, "grad_norm": 0.4260079860687256, "learning_rate": 1.525920849717366e-05, "loss": 4.1909, "step": 20541 }, { "epoch": 0.6274282223579719, "grad_norm": 0.42149636149406433, "learning_rate": 1.5256999230000305e-05, "loss": 4.2963, "step": 20542 }, { "epoch": 0.6274587660354307, "grad_norm": 0.41633912920951843, "learning_rate": 1.5254790052535766e-05, "loss": 4.2176, "step": 20543 }, { "epoch": 0.6274893097128894, "grad_norm": 0.4325919449329376, "learning_rate": 1.52525809648004e-05, "loss": 4.3244, "step": 20544 }, { "epoch": 0.6275198533903482, "grad_norm": 0.42494258284568787, "learning_rate": 1.5250371966814525e-05, "loss": 4.2585, "step": 20545 }, { "epoch": 0.6275503970678069, "grad_norm": 0.43046313524246216, "learning_rate": 1.5248163058598486e-05, "loss": 4.2629, "step": 20546 }, { "epoch": 0.6275809407452657, "grad_norm": 0.4202335476875305, "learning_rate": 1.5245954240172628e-05, "loss": 4.2458, "step": 20547 }, { "epoch": 0.6276114844227245, "grad_norm": 0.4232257902622223, "learning_rate": 1.5243745511557276e-05, "loss": 4.2385, "step": 20548 }, { "epoch": 0.6276420281001832, "grad_norm": 0.432014524936676, "learning_rate": 1.5241536872772786e-05, "loss": 4.1939, "step": 20549 }, { "epoch": 0.627672571777642, "grad_norm": 0.4297126829624176, "learning_rate": 1.5239328323839474e-05, "loss": 4.2682, "step": 20550 }, { "epoch": 0.6277031154551008, "grad_norm": 0.42485329508781433, "learning_rate": 1.5237119864777683e-05, "loss": 4.2304, "step": 20551 }, { "epoch": 0.6277336591325595, "grad_norm": 0.42811575531959534, "learning_rate": 1.5234911495607762e-05, "loss": 4.3814, "step": 20552 }, { "epoch": 0.6277642028100183, "grad_norm": 0.4230957329273224, "learning_rate": 1.5232703216350025e-05, "loss": 4.305, "step": 20553 }, { "epoch": 0.6277947464874771, "grad_norm": 0.4166720509529114, "learning_rate": 1.5230495027024805e-05, "loss": 4.3116, "step": 20554 }, { "epoch": 0.6278252901649358, "grad_norm": 0.4284593164920807, "learning_rate": 1.5228286927652452e-05, "loss": 4.2907, "step": 20555 }, { "epoch": 0.6278558338423946, "grad_norm": 0.4649564325809479, "learning_rate": 1.5226078918253273e-05, "loss": 4.2999, "step": 20556 }, { "epoch": 0.6278863775198534, "grad_norm": 0.4400310814380646, "learning_rate": 1.522387099884761e-05, "loss": 4.1915, "step": 20557 }, { "epoch": 0.6279169211973121, "grad_norm": 0.42945173382759094, "learning_rate": 1.5221663169455808e-05, "loss": 4.3774, "step": 20558 }, { "epoch": 0.6279474648747709, "grad_norm": 0.4341476559638977, "learning_rate": 1.5219455430098168e-05, "loss": 4.2178, "step": 20559 }, { "epoch": 0.6279780085522297, "grad_norm": 0.4337448477745056, "learning_rate": 1.5217247780795036e-05, "loss": 4.2984, "step": 20560 }, { "epoch": 0.6280085522296884, "grad_norm": 0.4223020076751709, "learning_rate": 1.521504022156674e-05, "loss": 4.3044, "step": 20561 }, { "epoch": 0.6280390959071472, "grad_norm": 0.43309327960014343, "learning_rate": 1.5212832752433587e-05, "loss": 4.1797, "step": 20562 }, { "epoch": 0.6280696395846059, "grad_norm": 0.4142926037311554, "learning_rate": 1.5210625373415926e-05, "loss": 4.257, "step": 20563 }, { "epoch": 0.6281001832620647, "grad_norm": 0.42744705080986023, "learning_rate": 1.520841808453406e-05, "loss": 4.2655, "step": 20564 }, { "epoch": 0.6281307269395235, "grad_norm": 0.4203033745288849, "learning_rate": 1.5206210885808322e-05, "loss": 4.3092, "step": 20565 }, { "epoch": 0.6281612706169822, "grad_norm": 0.4242802560329437, "learning_rate": 1.5204003777259046e-05, "loss": 4.3473, "step": 20566 }, { "epoch": 0.628191814294441, "grad_norm": 0.4155353903770447, "learning_rate": 1.5201796758906536e-05, "loss": 4.2543, "step": 20567 }, { "epoch": 0.6282223579718998, "grad_norm": 0.43726328015327454, "learning_rate": 1.5199589830771125e-05, "loss": 4.3265, "step": 20568 }, { "epoch": 0.6282529016493585, "grad_norm": 0.4309946894645691, "learning_rate": 1.5197382992873127e-05, "loss": 4.3128, "step": 20569 }, { "epoch": 0.6282834453268173, "grad_norm": 0.42216259241104126, "learning_rate": 1.5195176245232868e-05, "loss": 4.1953, "step": 20570 }, { "epoch": 0.6283139890042762, "grad_norm": 0.4246034026145935, "learning_rate": 1.5192969587870654e-05, "loss": 4.2557, "step": 20571 }, { "epoch": 0.6283445326817348, "grad_norm": 0.43086814880371094, "learning_rate": 1.5190763020806825e-05, "loss": 4.3146, "step": 20572 }, { "epoch": 0.6283750763591937, "grad_norm": 0.4132668972015381, "learning_rate": 1.5188556544061671e-05, "loss": 4.143, "step": 20573 }, { "epoch": 0.6284056200366525, "grad_norm": 0.4299916625022888, "learning_rate": 1.518635015765552e-05, "loss": 4.2344, "step": 20574 }, { "epoch": 0.6284361637141112, "grad_norm": 0.4222824275493622, "learning_rate": 1.5184143861608702e-05, "loss": 4.3337, "step": 20575 }, { "epoch": 0.62846670739157, "grad_norm": 0.4249652922153473, "learning_rate": 1.5181937655941514e-05, "loss": 4.2851, "step": 20576 }, { "epoch": 0.6284972510690288, "grad_norm": 0.4078172445297241, "learning_rate": 1.5179731540674266e-05, "loss": 4.2536, "step": 20577 }, { "epoch": 0.6285277947464875, "grad_norm": 0.42739251255989075, "learning_rate": 1.517752551582729e-05, "loss": 4.2418, "step": 20578 }, { "epoch": 0.6285583384239463, "grad_norm": 0.4326584041118622, "learning_rate": 1.5175319581420876e-05, "loss": 4.2559, "step": 20579 }, { "epoch": 0.628588882101405, "grad_norm": 0.42825862765312195, "learning_rate": 1.5173113737475359e-05, "loss": 4.2961, "step": 20580 }, { "epoch": 0.6286194257788638, "grad_norm": 0.4266921579837799, "learning_rate": 1.5170907984011024e-05, "loss": 4.2524, "step": 20581 }, { "epoch": 0.6286499694563226, "grad_norm": 0.4294019043445587, "learning_rate": 1.5168702321048192e-05, "loss": 4.2593, "step": 20582 }, { "epoch": 0.6286805131337813, "grad_norm": 0.4353732168674469, "learning_rate": 1.5166496748607184e-05, "loss": 4.384, "step": 20583 }, { "epoch": 0.6287110568112401, "grad_norm": 0.428931325674057, "learning_rate": 1.5164291266708287e-05, "loss": 4.2262, "step": 20584 }, { "epoch": 0.6287416004886989, "grad_norm": 0.4232137203216553, "learning_rate": 1.5162085875371821e-05, "loss": 4.2697, "step": 20585 }, { "epoch": 0.6287721441661576, "grad_norm": 0.4468746781349182, "learning_rate": 1.515988057461809e-05, "loss": 4.1688, "step": 20586 }, { "epoch": 0.6288026878436164, "grad_norm": 0.4340914189815521, "learning_rate": 1.5157675364467393e-05, "loss": 4.2402, "step": 20587 }, { "epoch": 0.6288332315210752, "grad_norm": 0.4233216941356659, "learning_rate": 1.515547024494004e-05, "loss": 4.2766, "step": 20588 }, { "epoch": 0.6288637751985339, "grad_norm": 0.4248301386833191, "learning_rate": 1.515326521605634e-05, "loss": 4.2184, "step": 20589 }, { "epoch": 0.6288943188759927, "grad_norm": 0.4414061903953552, "learning_rate": 1.5151060277836582e-05, "loss": 4.256, "step": 20590 }, { "epoch": 0.6289248625534515, "grad_norm": 0.4244893193244934, "learning_rate": 1.5148855430301079e-05, "loss": 4.3407, "step": 20591 }, { "epoch": 0.6289554062309102, "grad_norm": 0.42447343468666077, "learning_rate": 1.5146650673470132e-05, "loss": 4.2776, "step": 20592 }, { "epoch": 0.628985949908369, "grad_norm": 0.4201352894306183, "learning_rate": 1.5144446007364038e-05, "loss": 4.2769, "step": 20593 }, { "epoch": 0.6290164935858278, "grad_norm": 0.43924540281295776, "learning_rate": 1.514224143200309e-05, "loss": 4.2764, "step": 20594 }, { "epoch": 0.6290470372632865, "grad_norm": 0.43213820457458496, "learning_rate": 1.5140036947407604e-05, "loss": 4.2709, "step": 20595 }, { "epoch": 0.6290775809407453, "grad_norm": 0.43140852451324463, "learning_rate": 1.5137832553597858e-05, "loss": 4.2785, "step": 20596 }, { "epoch": 0.629108124618204, "grad_norm": 0.4329405725002289, "learning_rate": 1.5135628250594167e-05, "loss": 4.2754, "step": 20597 }, { "epoch": 0.6291386682956628, "grad_norm": 0.4183530807495117, "learning_rate": 1.513342403841681e-05, "loss": 4.2206, "step": 20598 }, { "epoch": 0.6291692119731216, "grad_norm": 0.4276011288166046, "learning_rate": 1.5131219917086093e-05, "loss": 4.1964, "step": 20599 }, { "epoch": 0.6291997556505803, "grad_norm": 0.4242086410522461, "learning_rate": 1.5129015886622311e-05, "loss": 4.2839, "step": 20600 }, { "epoch": 0.6292302993280391, "grad_norm": 0.41669216752052307, "learning_rate": 1.5126811947045755e-05, "loss": 4.3418, "step": 20601 }, { "epoch": 0.6292608430054979, "grad_norm": 0.4368862211704254, "learning_rate": 1.5124608098376711e-05, "loss": 4.3206, "step": 20602 }, { "epoch": 0.6292913866829566, "grad_norm": 0.4270285665988922, "learning_rate": 1.5122404340635488e-05, "loss": 4.2375, "step": 20603 }, { "epoch": 0.6293219303604154, "grad_norm": 0.4282672703266144, "learning_rate": 1.5120200673842358e-05, "loss": 4.1483, "step": 20604 }, { "epoch": 0.6293524740378742, "grad_norm": 0.41795849800109863, "learning_rate": 1.511799709801762e-05, "loss": 4.2962, "step": 20605 }, { "epoch": 0.6293830177153329, "grad_norm": 0.4228827953338623, "learning_rate": 1.5115793613181573e-05, "loss": 4.3093, "step": 20606 }, { "epoch": 0.6294135613927917, "grad_norm": 0.4446878731250763, "learning_rate": 1.5113590219354484e-05, "loss": 4.3258, "step": 20607 }, { "epoch": 0.6294441050702505, "grad_norm": 0.43008488416671753, "learning_rate": 1.5111386916556664e-05, "loss": 4.3355, "step": 20608 }, { "epoch": 0.6294746487477092, "grad_norm": 0.42983561754226685, "learning_rate": 1.5109183704808388e-05, "loss": 4.3538, "step": 20609 }, { "epoch": 0.629505192425168, "grad_norm": 0.4239710867404938, "learning_rate": 1.5106980584129934e-05, "loss": 4.3542, "step": 20610 }, { "epoch": 0.6295357361026268, "grad_norm": 0.43145596981048584, "learning_rate": 1.51047775545416e-05, "loss": 4.2731, "step": 20611 }, { "epoch": 0.6295662797800855, "grad_norm": 0.42964163422584534, "learning_rate": 1.510257461606367e-05, "loss": 4.2425, "step": 20612 }, { "epoch": 0.6295968234575443, "grad_norm": 0.41930294036865234, "learning_rate": 1.510037176871642e-05, "loss": 4.2377, "step": 20613 }, { "epoch": 0.629627367135003, "grad_norm": 0.4240611493587494, "learning_rate": 1.5098169012520144e-05, "loss": 4.3297, "step": 20614 }, { "epoch": 0.6296579108124618, "grad_norm": 0.4400244355201721, "learning_rate": 1.5095966347495109e-05, "loss": 4.3608, "step": 20615 }, { "epoch": 0.6296884544899206, "grad_norm": 0.4210905134677887, "learning_rate": 1.5093763773661606e-05, "loss": 4.2206, "step": 20616 }, { "epoch": 0.6297189981673793, "grad_norm": 0.4413932263851166, "learning_rate": 1.509156129103992e-05, "loss": 4.215, "step": 20617 }, { "epoch": 0.6297495418448381, "grad_norm": 0.43902668356895447, "learning_rate": 1.5089358899650315e-05, "loss": 4.3723, "step": 20618 }, { "epoch": 0.6297800855222969, "grad_norm": 0.43866804242134094, "learning_rate": 1.5087156599513077e-05, "loss": 4.3373, "step": 20619 }, { "epoch": 0.6298106291997556, "grad_norm": 0.4265997111797333, "learning_rate": 1.5084954390648495e-05, "loss": 4.2465, "step": 20620 }, { "epoch": 0.6298411728772144, "grad_norm": 0.42632198333740234, "learning_rate": 1.5082752273076828e-05, "loss": 4.2078, "step": 20621 }, { "epoch": 0.6298717165546732, "grad_norm": 0.42177683115005493, "learning_rate": 1.508055024681836e-05, "loss": 4.3112, "step": 20622 }, { "epoch": 0.6299022602321319, "grad_norm": 0.41734635829925537, "learning_rate": 1.507834831189337e-05, "loss": 4.3099, "step": 20623 }, { "epoch": 0.6299328039095907, "grad_norm": 0.43399569392204285, "learning_rate": 1.5076146468322125e-05, "loss": 4.3466, "step": 20624 }, { "epoch": 0.6299633475870495, "grad_norm": 0.4302365183830261, "learning_rate": 1.50739447161249e-05, "loss": 4.3167, "step": 20625 }, { "epoch": 0.6299938912645082, "grad_norm": 0.4266853630542755, "learning_rate": 1.5071743055321978e-05, "loss": 4.2116, "step": 20626 }, { "epoch": 0.630024434941967, "grad_norm": 0.43447986245155334, "learning_rate": 1.506954148593361e-05, "loss": 4.2702, "step": 20627 }, { "epoch": 0.6300549786194258, "grad_norm": 0.43084415793418884, "learning_rate": 1.5067340007980082e-05, "loss": 4.3204, "step": 20628 }, { "epoch": 0.6300855222968845, "grad_norm": 0.4288300573825836, "learning_rate": 1.5065138621481673e-05, "loss": 4.2945, "step": 20629 }, { "epoch": 0.6301160659743433, "grad_norm": 0.43095964193344116, "learning_rate": 1.5062937326458626e-05, "loss": 4.2037, "step": 20630 }, { "epoch": 0.630146609651802, "grad_norm": 0.42165955901145935, "learning_rate": 1.5060736122931238e-05, "loss": 4.2877, "step": 20631 }, { "epoch": 0.6301771533292608, "grad_norm": 0.42790329456329346, "learning_rate": 1.5058535010919755e-05, "loss": 4.2744, "step": 20632 }, { "epoch": 0.6302076970067196, "grad_norm": 0.4397054612636566, "learning_rate": 1.5056333990444448e-05, "loss": 4.3115, "step": 20633 }, { "epoch": 0.6302382406841783, "grad_norm": 0.4265710413455963, "learning_rate": 1.50541330615256e-05, "loss": 4.332, "step": 20634 }, { "epoch": 0.6302687843616371, "grad_norm": 0.42923951148986816, "learning_rate": 1.5051932224183446e-05, "loss": 4.1986, "step": 20635 }, { "epoch": 0.6302993280390959, "grad_norm": 0.42998629808425903, "learning_rate": 1.504973147843827e-05, "loss": 4.2783, "step": 20636 }, { "epoch": 0.6303298717165546, "grad_norm": 0.4156526029109955, "learning_rate": 1.5047530824310341e-05, "loss": 4.2106, "step": 20637 }, { "epoch": 0.6303604153940134, "grad_norm": 0.43017280101776123, "learning_rate": 1.5045330261819907e-05, "loss": 4.2899, "step": 20638 }, { "epoch": 0.6303909590714722, "grad_norm": 0.4325011372566223, "learning_rate": 1.5043129790987236e-05, "loss": 4.3303, "step": 20639 }, { "epoch": 0.6304215027489309, "grad_norm": 0.42187991738319397, "learning_rate": 1.5040929411832594e-05, "loss": 4.2557, "step": 20640 }, { "epoch": 0.6304520464263897, "grad_norm": 0.4345906674861908, "learning_rate": 1.5038729124376227e-05, "loss": 4.346, "step": 20641 }, { "epoch": 0.6304825901038486, "grad_norm": 0.42778369784355164, "learning_rate": 1.50365289286384e-05, "loss": 4.1837, "step": 20642 }, { "epoch": 0.6305131337813072, "grad_norm": 0.435932457447052, "learning_rate": 1.5034328824639388e-05, "loss": 4.3082, "step": 20643 }, { "epoch": 0.630543677458766, "grad_norm": 0.43367037177085876, "learning_rate": 1.5032128812399421e-05, "loss": 4.3008, "step": 20644 }, { "epoch": 0.6305742211362249, "grad_norm": 0.43574655055999756, "learning_rate": 1.5029928891938771e-05, "loss": 4.1442, "step": 20645 }, { "epoch": 0.6306047648136835, "grad_norm": 0.42974212765693665, "learning_rate": 1.5027729063277699e-05, "loss": 4.3229, "step": 20646 }, { "epoch": 0.6306353084911424, "grad_norm": 0.4273315966129303, "learning_rate": 1.502552932643645e-05, "loss": 4.283, "step": 20647 }, { "epoch": 0.630665852168601, "grad_norm": 0.4299751818180084, "learning_rate": 1.5023329681435284e-05, "loss": 4.2956, "step": 20648 }, { "epoch": 0.6306963958460599, "grad_norm": 0.42682817578315735, "learning_rate": 1.5021130128294442e-05, "loss": 4.328, "step": 20649 }, { "epoch": 0.6307269395235187, "grad_norm": 0.4200012683868408, "learning_rate": 1.5018930667034187e-05, "loss": 4.3308, "step": 20650 }, { "epoch": 0.6307574832009774, "grad_norm": 0.43100109696388245, "learning_rate": 1.5016731297674777e-05, "loss": 4.2239, "step": 20651 }, { "epoch": 0.6307880268784362, "grad_norm": 0.42638567090034485, "learning_rate": 1.5014532020236443e-05, "loss": 4.2628, "step": 20652 }, { "epoch": 0.630818570555895, "grad_norm": 0.43596285581588745, "learning_rate": 1.5012332834739451e-05, "loss": 4.275, "step": 20653 }, { "epoch": 0.6308491142333537, "grad_norm": 0.4333532750606537, "learning_rate": 1.5010133741204055e-05, "loss": 4.3307, "step": 20654 }, { "epoch": 0.6308796579108125, "grad_norm": 0.430582731962204, "learning_rate": 1.5007934739650486e-05, "loss": 4.2735, "step": 20655 }, { "epoch": 0.6309102015882713, "grad_norm": 0.42830610275268555, "learning_rate": 1.5005735830098999e-05, "loss": 4.2127, "step": 20656 }, { "epoch": 0.63094074526573, "grad_norm": 0.4244304597377777, "learning_rate": 1.5003537012569846e-05, "loss": 4.2029, "step": 20657 }, { "epoch": 0.6309712889431888, "grad_norm": 0.43156424164772034, "learning_rate": 1.5001338287083261e-05, "loss": 4.262, "step": 20658 }, { "epoch": 0.6310018326206476, "grad_norm": 0.4299916625022888, "learning_rate": 1.4999139653659495e-05, "loss": 4.3283, "step": 20659 }, { "epoch": 0.6310323762981063, "grad_norm": 0.4266061782836914, "learning_rate": 1.4996941112318799e-05, "loss": 4.2725, "step": 20660 }, { "epoch": 0.6310629199755651, "grad_norm": 0.429598331451416, "learning_rate": 1.4994742663081402e-05, "loss": 4.2933, "step": 20661 }, { "epoch": 0.6310934636530239, "grad_norm": 0.4301218092441559, "learning_rate": 1.4992544305967557e-05, "loss": 4.2557, "step": 20662 }, { "epoch": 0.6311240073304826, "grad_norm": 0.4197080135345459, "learning_rate": 1.4990346040997508e-05, "loss": 4.1295, "step": 20663 }, { "epoch": 0.6311545510079414, "grad_norm": 0.43054965138435364, "learning_rate": 1.4988147868191476e-05, "loss": 4.2896, "step": 20664 }, { "epoch": 0.6311850946854001, "grad_norm": 0.4241558313369751, "learning_rate": 1.498594978756973e-05, "loss": 4.3337, "step": 20665 }, { "epoch": 0.6312156383628589, "grad_norm": 0.4310472309589386, "learning_rate": 1.4983751799152478e-05, "loss": 4.2337, "step": 20666 }, { "epoch": 0.6312461820403177, "grad_norm": 0.4319305717945099, "learning_rate": 1.4981553902959977e-05, "loss": 4.2715, "step": 20667 }, { "epoch": 0.6312767257177764, "grad_norm": 0.4247813820838928, "learning_rate": 1.497935609901247e-05, "loss": 4.27, "step": 20668 }, { "epoch": 0.6313072693952352, "grad_norm": 0.42294520139694214, "learning_rate": 1.497715838733017e-05, "loss": 4.1788, "step": 20669 }, { "epoch": 0.631337813072694, "grad_norm": 0.4408992528915405, "learning_rate": 1.4974960767933333e-05, "loss": 4.2894, "step": 20670 }, { "epoch": 0.6313683567501527, "grad_norm": 0.43177464604377747, "learning_rate": 1.4972763240842191e-05, "loss": 4.3124, "step": 20671 }, { "epoch": 0.6313989004276115, "grad_norm": 0.4397733509540558, "learning_rate": 1.4970565806076964e-05, "loss": 4.1993, "step": 20672 }, { "epoch": 0.6314294441050703, "grad_norm": 0.41847723722457886, "learning_rate": 1.4968368463657895e-05, "loss": 4.2253, "step": 20673 }, { "epoch": 0.631459987782529, "grad_norm": 0.42670080065727234, "learning_rate": 1.4966171213605224e-05, "loss": 4.3213, "step": 20674 }, { "epoch": 0.6314905314599878, "grad_norm": 0.4238632917404175, "learning_rate": 1.4963974055939162e-05, "loss": 4.3242, "step": 20675 }, { "epoch": 0.6315210751374466, "grad_norm": 0.4232980012893677, "learning_rate": 1.4961776990679954e-05, "loss": 4.2357, "step": 20676 }, { "epoch": 0.6315516188149053, "grad_norm": 0.43638166785240173, "learning_rate": 1.4959580017847835e-05, "loss": 4.3478, "step": 20677 }, { "epoch": 0.6315821624923641, "grad_norm": 0.4290229380130768, "learning_rate": 1.495738313746302e-05, "loss": 4.2778, "step": 20678 }, { "epoch": 0.6316127061698229, "grad_norm": 0.42646729946136475, "learning_rate": 1.4955186349545736e-05, "loss": 4.2708, "step": 20679 }, { "epoch": 0.6316432498472816, "grad_norm": 0.4350796937942505, "learning_rate": 1.4952989654116229e-05, "loss": 4.2896, "step": 20680 }, { "epoch": 0.6316737935247404, "grad_norm": 0.43319928646087646, "learning_rate": 1.49507930511947e-05, "loss": 4.349, "step": 20681 }, { "epoch": 0.6317043372021991, "grad_norm": 0.42486125230789185, "learning_rate": 1.4948596540801396e-05, "loss": 4.3228, "step": 20682 }, { "epoch": 0.6317348808796579, "grad_norm": 0.4219457805156708, "learning_rate": 1.4946400122956522e-05, "loss": 4.2875, "step": 20683 }, { "epoch": 0.6317654245571167, "grad_norm": 0.4252837300300598, "learning_rate": 1.4944203797680308e-05, "loss": 4.2365, "step": 20684 }, { "epoch": 0.6317959682345754, "grad_norm": 0.4344184994697571, "learning_rate": 1.4942007564992993e-05, "loss": 4.2756, "step": 20685 }, { "epoch": 0.6318265119120342, "grad_norm": 0.41763147711753845, "learning_rate": 1.493981142491478e-05, "loss": 4.2478, "step": 20686 }, { "epoch": 0.631857055589493, "grad_norm": 0.42179304361343384, "learning_rate": 1.4937615377465891e-05, "loss": 4.2576, "step": 20687 }, { "epoch": 0.6318875992669517, "grad_norm": 0.43164482712745667, "learning_rate": 1.493541942266656e-05, "loss": 4.3267, "step": 20688 }, { "epoch": 0.6319181429444105, "grad_norm": 0.43164047598838806, "learning_rate": 1.4933223560536988e-05, "loss": 4.1422, "step": 20689 }, { "epoch": 0.6319486866218693, "grad_norm": 0.43550869822502136, "learning_rate": 1.4931027791097402e-05, "loss": 4.1223, "step": 20690 }, { "epoch": 0.631979230299328, "grad_norm": 0.42900463938713074, "learning_rate": 1.492883211436803e-05, "loss": 4.2838, "step": 20691 }, { "epoch": 0.6320097739767868, "grad_norm": 0.44109973311424255, "learning_rate": 1.492663653036907e-05, "loss": 4.3575, "step": 20692 }, { "epoch": 0.6320403176542456, "grad_norm": 0.43798866868019104, "learning_rate": 1.4924441039120751e-05, "loss": 4.2559, "step": 20693 }, { "epoch": 0.6320708613317043, "grad_norm": 0.42213746905326843, "learning_rate": 1.4922245640643282e-05, "loss": 4.2434, "step": 20694 }, { "epoch": 0.6321014050091631, "grad_norm": 0.422502726316452, "learning_rate": 1.4920050334956881e-05, "loss": 4.3287, "step": 20695 }, { "epoch": 0.6321319486866218, "grad_norm": 0.4415550231933594, "learning_rate": 1.4917855122081764e-05, "loss": 4.2774, "step": 20696 }, { "epoch": 0.6321624923640806, "grad_norm": 0.4293172359466553, "learning_rate": 1.4915660002038126e-05, "loss": 4.1936, "step": 20697 }, { "epoch": 0.6321930360415394, "grad_norm": 0.4310956299304962, "learning_rate": 1.4913464974846192e-05, "loss": 4.1077, "step": 20698 }, { "epoch": 0.6322235797189981, "grad_norm": 0.4258755147457123, "learning_rate": 1.4911270040526185e-05, "loss": 4.3183, "step": 20699 }, { "epoch": 0.6322541233964569, "grad_norm": 0.42860886454582214, "learning_rate": 1.4909075199098288e-05, "loss": 4.2785, "step": 20700 }, { "epoch": 0.6322846670739157, "grad_norm": 0.4298258125782013, "learning_rate": 1.4906880450582734e-05, "loss": 4.2817, "step": 20701 }, { "epoch": 0.6323152107513744, "grad_norm": 0.4275090992450714, "learning_rate": 1.4904685794999717e-05, "loss": 4.3048, "step": 20702 }, { "epoch": 0.6323457544288332, "grad_norm": 0.4261130690574646, "learning_rate": 1.4902491232369447e-05, "loss": 4.2857, "step": 20703 }, { "epoch": 0.632376298106292, "grad_norm": 0.442288339138031, "learning_rate": 1.490029676271213e-05, "loss": 4.2554, "step": 20704 }, { "epoch": 0.6324068417837507, "grad_norm": 0.4279504120349884, "learning_rate": 1.4898102386047982e-05, "loss": 4.3141, "step": 20705 }, { "epoch": 0.6324373854612095, "grad_norm": 0.4210265278816223, "learning_rate": 1.489590810239719e-05, "loss": 4.2056, "step": 20706 }, { "epoch": 0.6324679291386683, "grad_norm": 0.4347792863845825, "learning_rate": 1.4893713911779966e-05, "loss": 4.2767, "step": 20707 }, { "epoch": 0.632498472816127, "grad_norm": 0.42775410413742065, "learning_rate": 1.4891519814216526e-05, "loss": 4.2465, "step": 20708 }, { "epoch": 0.6325290164935858, "grad_norm": 0.43759024143218994, "learning_rate": 1.4889325809727056e-05, "loss": 4.2843, "step": 20709 }, { "epoch": 0.6325595601710446, "grad_norm": 0.42968669533729553, "learning_rate": 1.4887131898331754e-05, "loss": 4.3306, "step": 20710 }, { "epoch": 0.6325901038485033, "grad_norm": 0.42016804218292236, "learning_rate": 1.4884938080050839e-05, "loss": 4.2944, "step": 20711 }, { "epoch": 0.6326206475259621, "grad_norm": 0.4201464056968689, "learning_rate": 1.488274435490449e-05, "loss": 4.2765, "step": 20712 }, { "epoch": 0.6326511912034208, "grad_norm": 0.44246339797973633, "learning_rate": 1.4880550722912926e-05, "loss": 4.2269, "step": 20713 }, { "epoch": 0.6326817348808796, "grad_norm": 0.4351453483104706, "learning_rate": 1.4878357184096325e-05, "loss": 4.2471, "step": 20714 }, { "epoch": 0.6327122785583384, "grad_norm": 0.4227009415626526, "learning_rate": 1.4876163738474891e-05, "loss": 4.2225, "step": 20715 }, { "epoch": 0.6327428222357971, "grad_norm": 0.42830890417099, "learning_rate": 1.4873970386068833e-05, "loss": 4.2159, "step": 20716 }, { "epoch": 0.632773365913256, "grad_norm": 0.42907822132110596, "learning_rate": 1.4871777126898328e-05, "loss": 4.1518, "step": 20717 }, { "epoch": 0.6328039095907148, "grad_norm": 0.4261125326156616, "learning_rate": 1.4869583960983582e-05, "loss": 4.149, "step": 20718 }, { "epoch": 0.6328344532681734, "grad_norm": 0.4313003122806549, "learning_rate": 1.4867390888344789e-05, "loss": 4.2696, "step": 20719 }, { "epoch": 0.6328649969456323, "grad_norm": 0.42653152346611023, "learning_rate": 1.4865197909002131e-05, "loss": 4.2532, "step": 20720 }, { "epoch": 0.6328955406230911, "grad_norm": 0.427722692489624, "learning_rate": 1.4863005022975804e-05, "loss": 4.3045, "step": 20721 }, { "epoch": 0.6329260843005498, "grad_norm": 0.42478832602500916, "learning_rate": 1.4860812230286015e-05, "loss": 4.2726, "step": 20722 }, { "epoch": 0.6329566279780086, "grad_norm": 0.4390614330768585, "learning_rate": 1.4858619530952927e-05, "loss": 4.2259, "step": 20723 }, { "epoch": 0.6329871716554674, "grad_norm": 0.4263613820075989, "learning_rate": 1.4856426924996746e-05, "loss": 4.2702, "step": 20724 }, { "epoch": 0.6330177153329261, "grad_norm": 0.4220036268234253, "learning_rate": 1.4854234412437663e-05, "loss": 4.2721, "step": 20725 }, { "epoch": 0.6330482590103849, "grad_norm": 0.4289313554763794, "learning_rate": 1.4852041993295857e-05, "loss": 4.2652, "step": 20726 }, { "epoch": 0.6330788026878437, "grad_norm": 0.44100987911224365, "learning_rate": 1.4849849667591515e-05, "loss": 4.2726, "step": 20727 }, { "epoch": 0.6331093463653024, "grad_norm": 0.4395960569381714, "learning_rate": 1.4847657435344836e-05, "loss": 4.34, "step": 20728 }, { "epoch": 0.6331398900427612, "grad_norm": 0.42267492413520813, "learning_rate": 1.4845465296575984e-05, "loss": 4.2455, "step": 20729 }, { "epoch": 0.6331704337202199, "grad_norm": 0.4297671914100647, "learning_rate": 1.4843273251305162e-05, "loss": 4.1885, "step": 20730 }, { "epoch": 0.6332009773976787, "grad_norm": 0.4269045889377594, "learning_rate": 1.4841081299552537e-05, "loss": 4.2764, "step": 20731 }, { "epoch": 0.6332315210751375, "grad_norm": 0.4383520483970642, "learning_rate": 1.4838889441338305e-05, "loss": 4.3351, "step": 20732 }, { "epoch": 0.6332620647525962, "grad_norm": 0.4350430965423584, "learning_rate": 1.4836697676682643e-05, "loss": 4.2602, "step": 20733 }, { "epoch": 0.633292608430055, "grad_norm": 0.4320831894874573, "learning_rate": 1.483450600560573e-05, "loss": 4.2861, "step": 20734 }, { "epoch": 0.6333231521075138, "grad_norm": 0.4279843866825104, "learning_rate": 1.4832314428127742e-05, "loss": 4.3223, "step": 20735 }, { "epoch": 0.6333536957849725, "grad_norm": 0.41730982065200806, "learning_rate": 1.4830122944268871e-05, "loss": 4.2975, "step": 20736 }, { "epoch": 0.6333842394624313, "grad_norm": 0.42735594511032104, "learning_rate": 1.482793155404928e-05, "loss": 4.2651, "step": 20737 }, { "epoch": 0.6334147831398901, "grad_norm": 0.4235915243625641, "learning_rate": 1.4825740257489148e-05, "loss": 4.2994, "step": 20738 }, { "epoch": 0.6334453268173488, "grad_norm": 0.41165590286254883, "learning_rate": 1.482354905460867e-05, "loss": 4.1465, "step": 20739 }, { "epoch": 0.6334758704948076, "grad_norm": 0.4243169128894806, "learning_rate": 1.4821357945428e-05, "loss": 4.2469, "step": 20740 }, { "epoch": 0.6335064141722664, "grad_norm": 0.42759764194488525, "learning_rate": 1.4819166929967321e-05, "loss": 4.1774, "step": 20741 }, { "epoch": 0.6335369578497251, "grad_norm": 0.44204580783843994, "learning_rate": 1.4816976008246816e-05, "loss": 4.2794, "step": 20742 }, { "epoch": 0.6335675015271839, "grad_norm": 0.42186930775642395, "learning_rate": 1.4814785180286636e-05, "loss": 4.2795, "step": 20743 }, { "epoch": 0.6335980452046427, "grad_norm": 0.43009305000305176, "learning_rate": 1.4812594446106967e-05, "loss": 4.2849, "step": 20744 }, { "epoch": 0.6336285888821014, "grad_norm": 0.43766334652900696, "learning_rate": 1.4810403805727988e-05, "loss": 4.226, "step": 20745 }, { "epoch": 0.6336591325595602, "grad_norm": 0.418205201625824, "learning_rate": 1.4808213259169851e-05, "loss": 4.3276, "step": 20746 }, { "epoch": 0.6336896762370189, "grad_norm": 0.43066051602363586, "learning_rate": 1.4806022806452743e-05, "loss": 4.2472, "step": 20747 }, { "epoch": 0.6337202199144777, "grad_norm": 0.4254206120967865, "learning_rate": 1.4803832447596815e-05, "loss": 4.295, "step": 20748 }, { "epoch": 0.6337507635919365, "grad_norm": 0.42644554376602173, "learning_rate": 1.4801642182622249e-05, "loss": 4.2905, "step": 20749 }, { "epoch": 0.6337813072693952, "grad_norm": 0.43600815534591675, "learning_rate": 1.4799452011549214e-05, "loss": 4.1776, "step": 20750 }, { "epoch": 0.633811850946854, "grad_norm": 0.4217502176761627, "learning_rate": 1.4797261934397855e-05, "loss": 4.2533, "step": 20751 }, { "epoch": 0.6338423946243128, "grad_norm": 0.43249019980430603, "learning_rate": 1.4795071951188354e-05, "loss": 4.2352, "step": 20752 }, { "epoch": 0.6338729383017715, "grad_norm": 0.42727962136268616, "learning_rate": 1.4792882061940883e-05, "loss": 4.3341, "step": 20753 }, { "epoch": 0.6339034819792303, "grad_norm": 0.43014582991600037, "learning_rate": 1.4790692266675583e-05, "loss": 4.2748, "step": 20754 }, { "epoch": 0.6339340256566891, "grad_norm": 0.421281635761261, "learning_rate": 1.4788502565412632e-05, "loss": 4.1785, "step": 20755 }, { "epoch": 0.6339645693341478, "grad_norm": 0.42632564902305603, "learning_rate": 1.4786312958172188e-05, "loss": 4.3603, "step": 20756 }, { "epoch": 0.6339951130116066, "grad_norm": 0.43601396679878235, "learning_rate": 1.4784123444974416e-05, "loss": 4.2529, "step": 20757 }, { "epoch": 0.6340256566890654, "grad_norm": 0.4182014763355255, "learning_rate": 1.4781934025839465e-05, "loss": 4.2414, "step": 20758 }, { "epoch": 0.6340562003665241, "grad_norm": 0.4269876182079315, "learning_rate": 1.477974470078751e-05, "loss": 4.2562, "step": 20759 }, { "epoch": 0.6340867440439829, "grad_norm": 0.43936747312545776, "learning_rate": 1.4777555469838689e-05, "loss": 4.2483, "step": 20760 }, { "epoch": 0.6341172877214417, "grad_norm": 0.4441959857940674, "learning_rate": 1.4775366333013175e-05, "loss": 4.2834, "step": 20761 }, { "epoch": 0.6341478313989004, "grad_norm": 0.4217971861362457, "learning_rate": 1.4773177290331125e-05, "loss": 4.2558, "step": 20762 }, { "epoch": 0.6341783750763592, "grad_norm": 0.4373181462287903, "learning_rate": 1.4770988341812685e-05, "loss": 4.3162, "step": 20763 }, { "epoch": 0.6342089187538179, "grad_norm": 0.42576864361763, "learning_rate": 1.4768799487478023e-05, "loss": 4.1348, "step": 20764 }, { "epoch": 0.6342394624312767, "grad_norm": 0.4187270998954773, "learning_rate": 1.4766610727347277e-05, "loss": 4.2636, "step": 20765 }, { "epoch": 0.6342700061087355, "grad_norm": 0.41927164793014526, "learning_rate": 1.4764422061440603e-05, "loss": 4.3283, "step": 20766 }, { "epoch": 0.6343005497861942, "grad_norm": 0.4316079914569855, "learning_rate": 1.4762233489778171e-05, "loss": 4.2013, "step": 20767 }, { "epoch": 0.634331093463653, "grad_norm": 0.42708566784858704, "learning_rate": 1.4760045012380106e-05, "loss": 4.2537, "step": 20768 }, { "epoch": 0.6343616371411118, "grad_norm": 0.42410022020339966, "learning_rate": 1.4757856629266573e-05, "loss": 4.3084, "step": 20769 }, { "epoch": 0.6343921808185705, "grad_norm": 0.4416881799697876, "learning_rate": 1.475566834045773e-05, "loss": 4.3302, "step": 20770 }, { "epoch": 0.6344227244960293, "grad_norm": 0.42759639024734497, "learning_rate": 1.4753480145973703e-05, "loss": 4.282, "step": 20771 }, { "epoch": 0.6344532681734881, "grad_norm": 0.4220709204673767, "learning_rate": 1.4751292045834659e-05, "loss": 4.2438, "step": 20772 }, { "epoch": 0.6344838118509468, "grad_norm": 0.4301493465900421, "learning_rate": 1.4749104040060747e-05, "loss": 4.2653, "step": 20773 }, { "epoch": 0.6345143555284056, "grad_norm": 0.43042290210723877, "learning_rate": 1.4746916128672089e-05, "loss": 4.3309, "step": 20774 }, { "epoch": 0.6345448992058644, "grad_norm": 0.42325302958488464, "learning_rate": 1.4744728311688849e-05, "loss": 4.2738, "step": 20775 }, { "epoch": 0.6345754428833231, "grad_norm": 0.42901548743247986, "learning_rate": 1.4742540589131177e-05, "loss": 4.2582, "step": 20776 }, { "epoch": 0.6346059865607819, "grad_norm": 0.4181293547153473, "learning_rate": 1.47403529610192e-05, "loss": 4.1798, "step": 20777 }, { "epoch": 0.6346365302382407, "grad_norm": 0.4205329418182373, "learning_rate": 1.4738165427373069e-05, "loss": 4.2379, "step": 20778 }, { "epoch": 0.6346670739156994, "grad_norm": 0.43150609731674194, "learning_rate": 1.4735977988212929e-05, "loss": 4.2141, "step": 20779 }, { "epoch": 0.6346976175931582, "grad_norm": 0.4317363500595093, "learning_rate": 1.4733790643558915e-05, "loss": 4.278, "step": 20780 }, { "epoch": 0.6347281612706169, "grad_norm": 0.4246579110622406, "learning_rate": 1.4731603393431176e-05, "loss": 4.2578, "step": 20781 }, { "epoch": 0.6347587049480757, "grad_norm": 0.43237772583961487, "learning_rate": 1.472941623784983e-05, "loss": 4.2461, "step": 20782 }, { "epoch": 0.6347892486255345, "grad_norm": 0.4322569668292999, "learning_rate": 1.4727229176835034e-05, "loss": 4.2739, "step": 20783 }, { "epoch": 0.6348197923029932, "grad_norm": 0.4297195374965668, "learning_rate": 1.4725042210406925e-05, "loss": 4.2856, "step": 20784 }, { "epoch": 0.634850335980452, "grad_norm": 0.4265316426753998, "learning_rate": 1.4722855338585631e-05, "loss": 4.2719, "step": 20785 }, { "epoch": 0.6348808796579108, "grad_norm": 0.4331541657447815, "learning_rate": 1.4720668561391288e-05, "loss": 4.2536, "step": 20786 }, { "epoch": 0.6349114233353695, "grad_norm": 0.4380677342414856, "learning_rate": 1.4718481878844048e-05, "loss": 4.2095, "step": 20787 }, { "epoch": 0.6349419670128283, "grad_norm": 0.42461204528808594, "learning_rate": 1.4716295290964025e-05, "loss": 4.3072, "step": 20788 }, { "epoch": 0.6349725106902872, "grad_norm": 0.42431485652923584, "learning_rate": 1.4714108797771353e-05, "loss": 4.2733, "step": 20789 }, { "epoch": 0.6350030543677458, "grad_norm": 0.42914465069770813, "learning_rate": 1.4711922399286179e-05, "loss": 4.2374, "step": 20790 }, { "epoch": 0.6350335980452047, "grad_norm": 0.41891202330589294, "learning_rate": 1.4709736095528617e-05, "loss": 4.1861, "step": 20791 }, { "epoch": 0.6350641417226635, "grad_norm": 0.4313201606273651, "learning_rate": 1.4707549886518804e-05, "loss": 4.274, "step": 20792 }, { "epoch": 0.6350946854001221, "grad_norm": 0.41663289070129395, "learning_rate": 1.470536377227688e-05, "loss": 4.2548, "step": 20793 }, { "epoch": 0.635125229077581, "grad_norm": 0.43204474449157715, "learning_rate": 1.470317775282296e-05, "loss": 4.2682, "step": 20794 }, { "epoch": 0.6351557727550398, "grad_norm": 0.43238604068756104, "learning_rate": 1.4700991828177176e-05, "loss": 4.2277, "step": 20795 }, { "epoch": 0.6351863164324985, "grad_norm": 0.43870919942855835, "learning_rate": 1.4698805998359663e-05, "loss": 4.3311, "step": 20796 }, { "epoch": 0.6352168601099573, "grad_norm": 0.42396610975265503, "learning_rate": 1.4696620263390528e-05, "loss": 4.2047, "step": 20797 }, { "epoch": 0.635247403787416, "grad_norm": 0.44254693388938904, "learning_rate": 1.4694434623289922e-05, "loss": 4.2595, "step": 20798 }, { "epoch": 0.6352779474648748, "grad_norm": 0.4217897355556488, "learning_rate": 1.469224907807794e-05, "loss": 4.2529, "step": 20799 }, { "epoch": 0.6353084911423336, "grad_norm": 0.4402235448360443, "learning_rate": 1.4690063627774722e-05, "loss": 4.2269, "step": 20800 }, { "epoch": 0.6353390348197923, "grad_norm": 0.4371456503868103, "learning_rate": 1.4687878272400399e-05, "loss": 4.3082, "step": 20801 }, { "epoch": 0.6353695784972511, "grad_norm": 0.4306822419166565, "learning_rate": 1.468569301197507e-05, "loss": 4.3616, "step": 20802 }, { "epoch": 0.6354001221747099, "grad_norm": 0.43938490748405457, "learning_rate": 1.468350784651888e-05, "loss": 4.2615, "step": 20803 }, { "epoch": 0.6354306658521686, "grad_norm": 0.4332619905471802, "learning_rate": 1.4681322776051933e-05, "loss": 4.2746, "step": 20804 }, { "epoch": 0.6354612095296274, "grad_norm": 0.43239450454711914, "learning_rate": 1.4679137800594355e-05, "loss": 4.2485, "step": 20805 }, { "epoch": 0.6354917532070862, "grad_norm": 0.43152710795402527, "learning_rate": 1.4676952920166254e-05, "loss": 4.239, "step": 20806 }, { "epoch": 0.6355222968845449, "grad_norm": 0.43498849868774414, "learning_rate": 1.4674768134787766e-05, "loss": 4.2358, "step": 20807 }, { "epoch": 0.6355528405620037, "grad_norm": 0.43025898933410645, "learning_rate": 1.4672583444478988e-05, "loss": 4.2821, "step": 20808 }, { "epoch": 0.6355833842394625, "grad_norm": 0.434956818819046, "learning_rate": 1.4670398849260041e-05, "loss": 4.2915, "step": 20809 }, { "epoch": 0.6356139279169212, "grad_norm": 0.43631938099861145, "learning_rate": 1.4668214349151055e-05, "loss": 4.2541, "step": 20810 }, { "epoch": 0.63564447159438, "grad_norm": 0.42459359765052795, "learning_rate": 1.4666029944172126e-05, "loss": 4.3602, "step": 20811 }, { "epoch": 0.6356750152718388, "grad_norm": 0.42497459053993225, "learning_rate": 1.466384563434337e-05, "loss": 4.293, "step": 20812 }, { "epoch": 0.6357055589492975, "grad_norm": 0.4386137127876282, "learning_rate": 1.4661661419684907e-05, "loss": 4.3709, "step": 20813 }, { "epoch": 0.6357361026267563, "grad_norm": 0.4333665668964386, "learning_rate": 1.4659477300216835e-05, "loss": 4.2782, "step": 20814 }, { "epoch": 0.635766646304215, "grad_norm": 0.4323093295097351, "learning_rate": 1.4657293275959282e-05, "loss": 4.2411, "step": 20815 }, { "epoch": 0.6357971899816738, "grad_norm": 0.4353082776069641, "learning_rate": 1.4655109346932338e-05, "loss": 4.2211, "step": 20816 }, { "epoch": 0.6358277336591326, "grad_norm": 0.45327502489089966, "learning_rate": 1.465292551315612e-05, "loss": 4.1905, "step": 20817 }, { "epoch": 0.6358582773365913, "grad_norm": 0.43481460213661194, "learning_rate": 1.465074177465075e-05, "loss": 4.2271, "step": 20818 }, { "epoch": 0.6358888210140501, "grad_norm": 0.4270915985107422, "learning_rate": 1.4648558131436312e-05, "loss": 4.3072, "step": 20819 }, { "epoch": 0.6359193646915089, "grad_norm": 0.4365759789943695, "learning_rate": 1.4646374583532918e-05, "loss": 4.3752, "step": 20820 }, { "epoch": 0.6359499083689676, "grad_norm": 0.4425078332424164, "learning_rate": 1.4644191130960689e-05, "loss": 4.3664, "step": 20821 }, { "epoch": 0.6359804520464264, "grad_norm": 0.4280012845993042, "learning_rate": 1.4642007773739702e-05, "loss": 4.2442, "step": 20822 }, { "epoch": 0.6360109957238852, "grad_norm": 0.43113914132118225, "learning_rate": 1.4639824511890076e-05, "loss": 4.3039, "step": 20823 }, { "epoch": 0.6360415394013439, "grad_norm": 0.43372854590415955, "learning_rate": 1.4637641345431927e-05, "loss": 4.3372, "step": 20824 }, { "epoch": 0.6360720830788027, "grad_norm": 0.43016088008880615, "learning_rate": 1.4635458274385328e-05, "loss": 4.3159, "step": 20825 }, { "epoch": 0.6361026267562615, "grad_norm": 0.43683260679244995, "learning_rate": 1.4633275298770399e-05, "loss": 4.2519, "step": 20826 }, { "epoch": 0.6361331704337202, "grad_norm": 0.4164777398109436, "learning_rate": 1.4631092418607234e-05, "loss": 4.0925, "step": 20827 }, { "epoch": 0.636163714111179, "grad_norm": 0.4345250427722931, "learning_rate": 1.4628909633915932e-05, "loss": 4.2388, "step": 20828 }, { "epoch": 0.6361942577886378, "grad_norm": 0.43391263484954834, "learning_rate": 1.462672694471659e-05, "loss": 4.3269, "step": 20829 }, { "epoch": 0.6362248014660965, "grad_norm": 0.42498913407325745, "learning_rate": 1.4624544351029312e-05, "loss": 4.2622, "step": 20830 }, { "epoch": 0.6362553451435553, "grad_norm": 0.4264145493507385, "learning_rate": 1.4622361852874184e-05, "loss": 4.2547, "step": 20831 }, { "epoch": 0.636285888821014, "grad_norm": 0.43643718957901, "learning_rate": 1.4620179450271309e-05, "loss": 4.2789, "step": 20832 }, { "epoch": 0.6363164324984728, "grad_norm": 0.42258867621421814, "learning_rate": 1.4617997143240774e-05, "loss": 4.2837, "step": 20833 }, { "epoch": 0.6363469761759316, "grad_norm": 0.4276708662509918, "learning_rate": 1.461581493180268e-05, "loss": 4.2442, "step": 20834 }, { "epoch": 0.6363775198533903, "grad_norm": 0.4306081533432007, "learning_rate": 1.4613632815977119e-05, "loss": 4.2364, "step": 20835 }, { "epoch": 0.6364080635308491, "grad_norm": 0.4196700155735016, "learning_rate": 1.4611450795784176e-05, "loss": 4.3305, "step": 20836 }, { "epoch": 0.6364386072083079, "grad_norm": 0.44682803750038147, "learning_rate": 1.4609268871243947e-05, "loss": 4.246, "step": 20837 }, { "epoch": 0.6364691508857666, "grad_norm": 0.4314630925655365, "learning_rate": 1.4607087042376527e-05, "loss": 4.2051, "step": 20838 }, { "epoch": 0.6364996945632254, "grad_norm": 0.43242138624191284, "learning_rate": 1.4604905309201993e-05, "loss": 4.2421, "step": 20839 }, { "epoch": 0.6365302382406842, "grad_norm": 0.4330613911151886, "learning_rate": 1.4602723671740442e-05, "loss": 4.2569, "step": 20840 }, { "epoch": 0.6365607819181429, "grad_norm": 0.4283473789691925, "learning_rate": 1.4600542130011968e-05, "loss": 4.1933, "step": 20841 }, { "epoch": 0.6365913255956017, "grad_norm": 0.4238740801811218, "learning_rate": 1.4598360684036643e-05, "loss": 4.2673, "step": 20842 }, { "epoch": 0.6366218692730605, "grad_norm": 0.4411593973636627, "learning_rate": 1.4596179333834558e-05, "loss": 4.1783, "step": 20843 }, { "epoch": 0.6366524129505192, "grad_norm": 0.434444785118103, "learning_rate": 1.4593998079425808e-05, "loss": 4.2253, "step": 20844 }, { "epoch": 0.636682956627978, "grad_norm": 0.4310144782066345, "learning_rate": 1.4591816920830454e-05, "loss": 4.1598, "step": 20845 }, { "epoch": 0.6367135003054367, "grad_norm": 0.43130046129226685, "learning_rate": 1.4589635858068607e-05, "loss": 4.195, "step": 20846 }, { "epoch": 0.6367440439828955, "grad_norm": 0.4277227520942688, "learning_rate": 1.4587454891160324e-05, "loss": 4.2413, "step": 20847 }, { "epoch": 0.6367745876603543, "grad_norm": 0.44082701206207275, "learning_rate": 1.4585274020125697e-05, "loss": 4.2104, "step": 20848 }, { "epoch": 0.636805131337813, "grad_norm": 0.4297252297401428, "learning_rate": 1.4583093244984819e-05, "loss": 4.3151, "step": 20849 }, { "epoch": 0.6368356750152718, "grad_norm": 0.4284893572330475, "learning_rate": 1.4580912565757743e-05, "loss": 4.2901, "step": 20850 }, { "epoch": 0.6368662186927306, "grad_norm": 0.43094125390052795, "learning_rate": 1.4578731982464567e-05, "loss": 4.1628, "step": 20851 }, { "epoch": 0.6368967623701893, "grad_norm": 0.439390629529953, "learning_rate": 1.4576551495125367e-05, "loss": 4.3311, "step": 20852 }, { "epoch": 0.6369273060476481, "grad_norm": 0.42365747690200806, "learning_rate": 1.4574371103760214e-05, "loss": 4.301, "step": 20853 }, { "epoch": 0.6369578497251069, "grad_norm": 0.4367024898529053, "learning_rate": 1.4572190808389192e-05, "loss": 4.247, "step": 20854 }, { "epoch": 0.6369883934025656, "grad_norm": 0.4320427477359772, "learning_rate": 1.4570010609032373e-05, "loss": 4.2699, "step": 20855 }, { "epoch": 0.6370189370800244, "grad_norm": 0.43403416872024536, "learning_rate": 1.4567830505709817e-05, "loss": 4.2372, "step": 20856 }, { "epoch": 0.6370494807574832, "grad_norm": 0.42222484946250916, "learning_rate": 1.456565049844161e-05, "loss": 4.2433, "step": 20857 }, { "epoch": 0.6370800244349419, "grad_norm": 0.42198610305786133, "learning_rate": 1.4563470587247836e-05, "loss": 4.1872, "step": 20858 }, { "epoch": 0.6371105681124007, "grad_norm": 0.42423874139785767, "learning_rate": 1.456129077214854e-05, "loss": 4.2035, "step": 20859 }, { "epoch": 0.6371411117898595, "grad_norm": 0.4395139813423157, "learning_rate": 1.455911105316381e-05, "loss": 4.2958, "step": 20860 }, { "epoch": 0.6371716554673182, "grad_norm": 0.43657442927360535, "learning_rate": 1.455693143031372e-05, "loss": 4.3282, "step": 20861 }, { "epoch": 0.637202199144777, "grad_norm": 0.43736764788627625, "learning_rate": 1.4554751903618325e-05, "loss": 4.3527, "step": 20862 }, { "epoch": 0.6372327428222357, "grad_norm": 0.42578303813934326, "learning_rate": 1.4552572473097708e-05, "loss": 4.2332, "step": 20863 }, { "epoch": 0.6372632864996945, "grad_norm": 0.4275452494621277, "learning_rate": 1.4550393138771918e-05, "loss": 4.2771, "step": 20864 }, { "epoch": 0.6372938301771534, "grad_norm": 0.42390644550323486, "learning_rate": 1.4548213900661029e-05, "loss": 4.2999, "step": 20865 }, { "epoch": 0.637324373854612, "grad_norm": 0.421305775642395, "learning_rate": 1.454603475878512e-05, "loss": 4.3231, "step": 20866 }, { "epoch": 0.6373549175320709, "grad_norm": 0.4391569197177887, "learning_rate": 1.4543855713164233e-05, "loss": 4.3068, "step": 20867 }, { "epoch": 0.6373854612095297, "grad_norm": 0.4376240670681, "learning_rate": 1.4541676763818446e-05, "loss": 4.2585, "step": 20868 }, { "epoch": 0.6374160048869884, "grad_norm": 0.4247013330459595, "learning_rate": 1.4539497910767825e-05, "loss": 4.2976, "step": 20869 }, { "epoch": 0.6374465485644472, "grad_norm": 0.41941848397254944, "learning_rate": 1.4537319154032426e-05, "loss": 4.293, "step": 20870 }, { "epoch": 0.637477092241906, "grad_norm": 0.42792201042175293, "learning_rate": 1.45351404936323e-05, "loss": 4.2411, "step": 20871 }, { "epoch": 0.6375076359193647, "grad_norm": 0.4364573359489441, "learning_rate": 1.453296192958752e-05, "loss": 4.2713, "step": 20872 }, { "epoch": 0.6375381795968235, "grad_norm": 0.4221683740615845, "learning_rate": 1.4530783461918137e-05, "loss": 4.2437, "step": 20873 }, { "epoch": 0.6375687232742823, "grad_norm": 0.42581966519355774, "learning_rate": 1.4528605090644211e-05, "loss": 4.2251, "step": 20874 }, { "epoch": 0.637599266951741, "grad_norm": 0.4407512843608856, "learning_rate": 1.4526426815785815e-05, "loss": 4.2799, "step": 20875 }, { "epoch": 0.6376298106291998, "grad_norm": 0.4270709455013275, "learning_rate": 1.452424863736298e-05, "loss": 4.2549, "step": 20876 }, { "epoch": 0.6376603543066586, "grad_norm": 0.44295230507850647, "learning_rate": 1.4522070555395772e-05, "loss": 4.2553, "step": 20877 }, { "epoch": 0.6376908979841173, "grad_norm": 0.427119642496109, "learning_rate": 1.4519892569904261e-05, "loss": 4.2528, "step": 20878 }, { "epoch": 0.6377214416615761, "grad_norm": 0.42999112606048584, "learning_rate": 1.4517714680908477e-05, "loss": 4.3189, "step": 20879 }, { "epoch": 0.6377519853390348, "grad_norm": 0.42953816056251526, "learning_rate": 1.4515536888428491e-05, "loss": 4.1653, "step": 20880 }, { "epoch": 0.6377825290164936, "grad_norm": 0.43578270077705383, "learning_rate": 1.4513359192484338e-05, "loss": 4.1454, "step": 20881 }, { "epoch": 0.6378130726939524, "grad_norm": 0.43739452958106995, "learning_rate": 1.4511181593096079e-05, "loss": 4.2927, "step": 20882 }, { "epoch": 0.6378436163714111, "grad_norm": 0.43246322870254517, "learning_rate": 1.4509004090283775e-05, "loss": 4.2516, "step": 20883 }, { "epoch": 0.6378741600488699, "grad_norm": 0.429997980594635, "learning_rate": 1.4506826684067453e-05, "loss": 4.114, "step": 20884 }, { "epoch": 0.6379047037263287, "grad_norm": 0.44570764899253845, "learning_rate": 1.4504649374467185e-05, "loss": 4.2599, "step": 20885 }, { "epoch": 0.6379352474037874, "grad_norm": 0.42441195249557495, "learning_rate": 1.4502472161502995e-05, "loss": 4.2536, "step": 20886 }, { "epoch": 0.6379657910812462, "grad_norm": 0.43148866295814514, "learning_rate": 1.4500295045194951e-05, "loss": 4.2772, "step": 20887 }, { "epoch": 0.637996334758705, "grad_norm": 0.4258911907672882, "learning_rate": 1.4498118025563078e-05, "loss": 4.3148, "step": 20888 }, { "epoch": 0.6380268784361637, "grad_norm": 0.4353081285953522, "learning_rate": 1.4495941102627442e-05, "loss": 4.3045, "step": 20889 }, { "epoch": 0.6380574221136225, "grad_norm": 0.4363282322883606, "learning_rate": 1.4493764276408067e-05, "loss": 4.2406, "step": 20890 }, { "epoch": 0.6380879657910813, "grad_norm": 0.427687406539917, "learning_rate": 1.449158754692501e-05, "loss": 4.2429, "step": 20891 }, { "epoch": 0.63811850946854, "grad_norm": 0.4389835596084595, "learning_rate": 1.4489410914198314e-05, "loss": 4.2276, "step": 20892 }, { "epoch": 0.6381490531459988, "grad_norm": 0.42853033542633057, "learning_rate": 1.448723437824801e-05, "loss": 4.2253, "step": 20893 }, { "epoch": 0.6381795968234576, "grad_norm": 0.4453960955142975, "learning_rate": 1.448505793909414e-05, "loss": 4.2178, "step": 20894 }, { "epoch": 0.6382101405009163, "grad_norm": 0.43799376487731934, "learning_rate": 1.448288159675676e-05, "loss": 4.249, "step": 20895 }, { "epoch": 0.6382406841783751, "grad_norm": 0.4388410747051239, "learning_rate": 1.4480705351255885e-05, "loss": 4.2469, "step": 20896 }, { "epoch": 0.6382712278558338, "grad_norm": 0.4360980987548828, "learning_rate": 1.447852920261158e-05, "loss": 4.3859, "step": 20897 }, { "epoch": 0.6383017715332926, "grad_norm": 0.4473316967487335, "learning_rate": 1.447635315084385e-05, "loss": 4.3094, "step": 20898 }, { "epoch": 0.6383323152107514, "grad_norm": 0.43535757064819336, "learning_rate": 1.447417719597275e-05, "loss": 4.2649, "step": 20899 }, { "epoch": 0.6383628588882101, "grad_norm": 0.4284830093383789, "learning_rate": 1.447200133801832e-05, "loss": 4.2781, "step": 20900 }, { "epoch": 0.6383934025656689, "grad_norm": 0.4273596704006195, "learning_rate": 1.446982557700059e-05, "loss": 4.2119, "step": 20901 }, { "epoch": 0.6384239462431277, "grad_norm": 0.4291965067386627, "learning_rate": 1.4467649912939577e-05, "loss": 4.2846, "step": 20902 }, { "epoch": 0.6384544899205864, "grad_norm": 0.4418685734272003, "learning_rate": 1.4465474345855338e-05, "loss": 4.2747, "step": 20903 }, { "epoch": 0.6384850335980452, "grad_norm": 0.4407007694244385, "learning_rate": 1.4463298875767883e-05, "loss": 4.217, "step": 20904 }, { "epoch": 0.638515577275504, "grad_norm": 0.44141754508018494, "learning_rate": 1.446112350269725e-05, "loss": 4.1445, "step": 20905 }, { "epoch": 0.6385461209529627, "grad_norm": 0.4214126467704773, "learning_rate": 1.4458948226663485e-05, "loss": 4.3155, "step": 20906 }, { "epoch": 0.6385766646304215, "grad_norm": 0.43431556224823, "learning_rate": 1.4456773047686593e-05, "loss": 4.2863, "step": 20907 }, { "epoch": 0.6386072083078803, "grad_norm": 0.4341563880443573, "learning_rate": 1.445459796578661e-05, "loss": 4.2741, "step": 20908 }, { "epoch": 0.638637751985339, "grad_norm": 0.4156809449195862, "learning_rate": 1.4452422980983577e-05, "loss": 4.3455, "step": 20909 }, { "epoch": 0.6386682956627978, "grad_norm": 0.4334651231765747, "learning_rate": 1.4450248093297497e-05, "loss": 4.2941, "step": 20910 }, { "epoch": 0.6386988393402566, "grad_norm": 0.43366485834121704, "learning_rate": 1.4448073302748411e-05, "loss": 4.2191, "step": 20911 }, { "epoch": 0.6387293830177153, "grad_norm": 0.43668392300605774, "learning_rate": 1.4445898609356345e-05, "loss": 4.3291, "step": 20912 }, { "epoch": 0.6387599266951741, "grad_norm": 0.43663424253463745, "learning_rate": 1.4443724013141307e-05, "loss": 4.2114, "step": 20913 }, { "epoch": 0.6387904703726328, "grad_norm": 0.439846396446228, "learning_rate": 1.4441549514123342e-05, "loss": 4.3368, "step": 20914 }, { "epoch": 0.6388210140500916, "grad_norm": 0.43570077419281006, "learning_rate": 1.4439375112322452e-05, "loss": 4.27, "step": 20915 }, { "epoch": 0.6388515577275504, "grad_norm": 0.4237023591995239, "learning_rate": 1.4437200807758672e-05, "loss": 4.2075, "step": 20916 }, { "epoch": 0.6388821014050091, "grad_norm": 0.4298877418041229, "learning_rate": 1.4435026600452001e-05, "loss": 4.1869, "step": 20917 }, { "epoch": 0.6389126450824679, "grad_norm": 0.4483068585395813, "learning_rate": 1.4432852490422489e-05, "loss": 4.1192, "step": 20918 }, { "epoch": 0.6389431887599267, "grad_norm": 0.4239503741264343, "learning_rate": 1.4430678477690123e-05, "loss": 4.1755, "step": 20919 }, { "epoch": 0.6389737324373854, "grad_norm": 0.44151145219802856, "learning_rate": 1.4428504562274945e-05, "loss": 4.3044, "step": 20920 }, { "epoch": 0.6390042761148442, "grad_norm": 0.42634621262550354, "learning_rate": 1.442633074419695e-05, "loss": 4.2717, "step": 20921 }, { "epoch": 0.639034819792303, "grad_norm": 0.4403544068336487, "learning_rate": 1.4424157023476164e-05, "loss": 4.1254, "step": 20922 }, { "epoch": 0.6390653634697617, "grad_norm": 0.4428805410861969, "learning_rate": 1.4421983400132617e-05, "loss": 4.2572, "step": 20923 }, { "epoch": 0.6390959071472205, "grad_norm": 0.43512576818466187, "learning_rate": 1.4419809874186291e-05, "loss": 4.2722, "step": 20924 }, { "epoch": 0.6391264508246793, "grad_norm": 0.42669299244880676, "learning_rate": 1.4417636445657218e-05, "loss": 4.2675, "step": 20925 }, { "epoch": 0.639156994502138, "grad_norm": 0.4301072955131531, "learning_rate": 1.441546311456542e-05, "loss": 4.2704, "step": 20926 }, { "epoch": 0.6391875381795968, "grad_norm": 0.44124114513397217, "learning_rate": 1.441328988093088e-05, "loss": 4.2745, "step": 20927 }, { "epoch": 0.6392180818570556, "grad_norm": 0.43837425112724304, "learning_rate": 1.4411116744773626e-05, "loss": 4.2169, "step": 20928 }, { "epoch": 0.6392486255345143, "grad_norm": 0.4328920245170593, "learning_rate": 1.4408943706113676e-05, "loss": 4.3017, "step": 20929 }, { "epoch": 0.6392791692119731, "grad_norm": 0.43556901812553406, "learning_rate": 1.4406770764971012e-05, "loss": 4.1356, "step": 20930 }, { "epoch": 0.6393097128894318, "grad_norm": 0.4259960353374481, "learning_rate": 1.440459792136567e-05, "loss": 4.2857, "step": 20931 }, { "epoch": 0.6393402565668906, "grad_norm": 0.42814549803733826, "learning_rate": 1.440242517531763e-05, "loss": 4.1832, "step": 20932 }, { "epoch": 0.6393708002443494, "grad_norm": 0.4369051158428192, "learning_rate": 1.4400252526846921e-05, "loss": 4.2144, "step": 20933 }, { "epoch": 0.6394013439218081, "grad_norm": 0.436160147190094, "learning_rate": 1.4398079975973538e-05, "loss": 4.0866, "step": 20934 }, { "epoch": 0.639431887599267, "grad_norm": 0.4194192886352539, "learning_rate": 1.4395907522717472e-05, "loss": 4.2376, "step": 20935 }, { "epoch": 0.6394624312767258, "grad_norm": 0.43268147110939026, "learning_rate": 1.439373516709874e-05, "loss": 4.247, "step": 20936 }, { "epoch": 0.6394929749541844, "grad_norm": 0.4279082417488098, "learning_rate": 1.439156290913735e-05, "loss": 4.2201, "step": 20937 }, { "epoch": 0.6395235186316433, "grad_norm": 0.43877461552619934, "learning_rate": 1.4389390748853281e-05, "loss": 4.1155, "step": 20938 }, { "epoch": 0.6395540623091021, "grad_norm": 0.4495144486427307, "learning_rate": 1.4387218686266552e-05, "loss": 4.1912, "step": 20939 }, { "epoch": 0.6395846059865608, "grad_norm": 0.4368610084056854, "learning_rate": 1.4385046721397166e-05, "loss": 4.3068, "step": 20940 }, { "epoch": 0.6396151496640196, "grad_norm": 0.42857620120048523, "learning_rate": 1.4382874854265102e-05, "loss": 4.3149, "step": 20941 }, { "epoch": 0.6396456933414784, "grad_norm": 0.4169212579727173, "learning_rate": 1.4380703084890368e-05, "loss": 4.2653, "step": 20942 }, { "epoch": 0.639676237018937, "grad_norm": 0.4280339181423187, "learning_rate": 1.4378531413292973e-05, "loss": 4.3522, "step": 20943 }, { "epoch": 0.6397067806963959, "grad_norm": 0.4302683472633362, "learning_rate": 1.4376359839492887e-05, "loss": 4.2716, "step": 20944 }, { "epoch": 0.6397373243738547, "grad_norm": 0.4391636252403259, "learning_rate": 1.4374188363510116e-05, "loss": 4.2571, "step": 20945 }, { "epoch": 0.6397678680513134, "grad_norm": 0.4278767704963684, "learning_rate": 1.4372016985364672e-05, "loss": 4.2637, "step": 20946 }, { "epoch": 0.6397984117287722, "grad_norm": 0.42403218150138855, "learning_rate": 1.4369845705076518e-05, "loss": 4.3212, "step": 20947 }, { "epoch": 0.6398289554062309, "grad_norm": 0.439017653465271, "learning_rate": 1.436767452266567e-05, "loss": 4.3139, "step": 20948 }, { "epoch": 0.6398594990836897, "grad_norm": 0.4305783212184906, "learning_rate": 1.4365503438152112e-05, "loss": 4.2963, "step": 20949 }, { "epoch": 0.6398900427611485, "grad_norm": 0.4307389557361603, "learning_rate": 1.436333245155582e-05, "loss": 4.2053, "step": 20950 }, { "epoch": 0.6399205864386072, "grad_norm": 0.44009560346603394, "learning_rate": 1.4361161562896803e-05, "loss": 4.3246, "step": 20951 }, { "epoch": 0.639951130116066, "grad_norm": 0.4371011257171631, "learning_rate": 1.4358990772195035e-05, "loss": 4.2279, "step": 20952 }, { "epoch": 0.6399816737935248, "grad_norm": 0.43077144026756287, "learning_rate": 1.4356820079470507e-05, "loss": 4.1612, "step": 20953 }, { "epoch": 0.6400122174709835, "grad_norm": 0.43566596508026123, "learning_rate": 1.435464948474322e-05, "loss": 4.2526, "step": 20954 }, { "epoch": 0.6400427611484423, "grad_norm": 0.4265750050544739, "learning_rate": 1.4352478988033138e-05, "loss": 4.2348, "step": 20955 }, { "epoch": 0.6400733048259011, "grad_norm": 0.44813668727874756, "learning_rate": 1.4350308589360257e-05, "loss": 4.2999, "step": 20956 }, { "epoch": 0.6401038485033598, "grad_norm": 0.4402742087841034, "learning_rate": 1.4348138288744573e-05, "loss": 4.2288, "step": 20957 }, { "epoch": 0.6401343921808186, "grad_norm": 0.42855125665664673, "learning_rate": 1.4345968086206042e-05, "loss": 4.1747, "step": 20958 }, { "epoch": 0.6401649358582774, "grad_norm": 0.4291336238384247, "learning_rate": 1.4343797981764662e-05, "loss": 4.2504, "step": 20959 }, { "epoch": 0.6401954795357361, "grad_norm": 0.42191746830940247, "learning_rate": 1.4341627975440422e-05, "loss": 4.251, "step": 20960 }, { "epoch": 0.6402260232131949, "grad_norm": 0.4265415072441101, "learning_rate": 1.4339458067253287e-05, "loss": 4.2977, "step": 20961 }, { "epoch": 0.6402565668906537, "grad_norm": 0.43140852451324463, "learning_rate": 1.4337288257223247e-05, "loss": 4.2745, "step": 20962 }, { "epoch": 0.6402871105681124, "grad_norm": 0.43499311804771423, "learning_rate": 1.4335118545370268e-05, "loss": 4.23, "step": 20963 }, { "epoch": 0.6403176542455712, "grad_norm": 0.42365124821662903, "learning_rate": 1.4332948931714349e-05, "loss": 4.2385, "step": 20964 }, { "epoch": 0.6403481979230299, "grad_norm": 0.4395384192466736, "learning_rate": 1.4330779416275453e-05, "loss": 4.2972, "step": 20965 }, { "epoch": 0.6403787416004887, "grad_norm": 0.4335724115371704, "learning_rate": 1.4328609999073545e-05, "loss": 4.2405, "step": 20966 }, { "epoch": 0.6404092852779475, "grad_norm": 0.43301135301589966, "learning_rate": 1.4326440680128612e-05, "loss": 4.2446, "step": 20967 }, { "epoch": 0.6404398289554062, "grad_norm": 0.4351486265659332, "learning_rate": 1.4324271459460637e-05, "loss": 4.2907, "step": 20968 }, { "epoch": 0.640470372632865, "grad_norm": 0.4192051887512207, "learning_rate": 1.4322102337089572e-05, "loss": 4.2264, "step": 20969 }, { "epoch": 0.6405009163103238, "grad_norm": 0.4396056830883026, "learning_rate": 1.4319933313035402e-05, "loss": 4.35, "step": 20970 }, { "epoch": 0.6405314599877825, "grad_norm": 0.42679110169410706, "learning_rate": 1.4317764387318108e-05, "loss": 4.381, "step": 20971 }, { "epoch": 0.6405620036652413, "grad_norm": 0.432970255613327, "learning_rate": 1.431559555995764e-05, "loss": 4.2013, "step": 20972 }, { "epoch": 0.6405925473427001, "grad_norm": 0.4255213141441345, "learning_rate": 1.4313426830973975e-05, "loss": 4.2952, "step": 20973 }, { "epoch": 0.6406230910201588, "grad_norm": 0.4363674223423004, "learning_rate": 1.4311258200387095e-05, "loss": 4.2707, "step": 20974 }, { "epoch": 0.6406536346976176, "grad_norm": 0.4317370057106018, "learning_rate": 1.4309089668216946e-05, "loss": 4.3164, "step": 20975 }, { "epoch": 0.6406841783750764, "grad_norm": 0.4362036883831024, "learning_rate": 1.4306921234483505e-05, "loss": 4.2393, "step": 20976 }, { "epoch": 0.6407147220525351, "grad_norm": 0.42102256417274475, "learning_rate": 1.4304752899206749e-05, "loss": 4.1508, "step": 20977 }, { "epoch": 0.6407452657299939, "grad_norm": 0.44688284397125244, "learning_rate": 1.4302584662406621e-05, "loss": 4.2648, "step": 20978 }, { "epoch": 0.6407758094074527, "grad_norm": 0.4299912452697754, "learning_rate": 1.4300416524103105e-05, "loss": 4.2289, "step": 20979 }, { "epoch": 0.6408063530849114, "grad_norm": 0.43970152735710144, "learning_rate": 1.4298248484316157e-05, "loss": 4.161, "step": 20980 }, { "epoch": 0.6408368967623702, "grad_norm": 0.4412551522254944, "learning_rate": 1.4296080543065729e-05, "loss": 4.3334, "step": 20981 }, { "epoch": 0.6408674404398289, "grad_norm": 0.4380338191986084, "learning_rate": 1.4293912700371798e-05, "loss": 4.2653, "step": 20982 }, { "epoch": 0.6408979841172877, "grad_norm": 0.4464479684829712, "learning_rate": 1.429174495625431e-05, "loss": 4.191, "step": 20983 }, { "epoch": 0.6409285277947465, "grad_norm": 0.44059523940086365, "learning_rate": 1.4289577310733229e-05, "loss": 4.2717, "step": 20984 }, { "epoch": 0.6409590714722052, "grad_norm": 0.43815678358078003, "learning_rate": 1.428740976382853e-05, "loss": 4.3424, "step": 20985 }, { "epoch": 0.640989615149664, "grad_norm": 0.4412875473499298, "learning_rate": 1.4285242315560144e-05, "loss": 4.2855, "step": 20986 }, { "epoch": 0.6410201588271228, "grad_norm": 0.43481025099754333, "learning_rate": 1.428307496594804e-05, "loss": 4.2886, "step": 20987 }, { "epoch": 0.6410507025045815, "grad_norm": 0.42977237701416016, "learning_rate": 1.4280907715012188e-05, "loss": 4.3085, "step": 20988 }, { "epoch": 0.6410812461820403, "grad_norm": 0.43573105335235596, "learning_rate": 1.427874056277252e-05, "loss": 4.2258, "step": 20989 }, { "epoch": 0.6411117898594991, "grad_norm": 0.4415750503540039, "learning_rate": 1.4276573509248997e-05, "loss": 4.2846, "step": 20990 }, { "epoch": 0.6411423335369578, "grad_norm": 0.4251331388950348, "learning_rate": 1.4274406554461585e-05, "loss": 4.2396, "step": 20991 }, { "epoch": 0.6411728772144166, "grad_norm": 0.43044885993003845, "learning_rate": 1.4272239698430217e-05, "loss": 4.2729, "step": 20992 }, { "epoch": 0.6412034208918754, "grad_norm": 0.4355219602584839, "learning_rate": 1.4270072941174856e-05, "loss": 4.3191, "step": 20993 }, { "epoch": 0.6412339645693341, "grad_norm": 0.4216696321964264, "learning_rate": 1.426790628271546e-05, "loss": 4.312, "step": 20994 }, { "epoch": 0.6412645082467929, "grad_norm": 0.4489155411720276, "learning_rate": 1.4265739723071969e-05, "loss": 4.3104, "step": 20995 }, { "epoch": 0.6412950519242516, "grad_norm": 0.4290701746940613, "learning_rate": 1.4263573262264317e-05, "loss": 4.1883, "step": 20996 }, { "epoch": 0.6413255956017104, "grad_norm": 0.4315647482872009, "learning_rate": 1.4261406900312482e-05, "loss": 4.3715, "step": 20997 }, { "epoch": 0.6413561392791692, "grad_norm": 0.4307608902454376, "learning_rate": 1.4259240637236381e-05, "loss": 4.3109, "step": 20998 }, { "epoch": 0.6413866829566279, "grad_norm": 0.42871609330177307, "learning_rate": 1.4257074473055987e-05, "loss": 4.2042, "step": 20999 }, { "epoch": 0.6414172266340867, "grad_norm": 0.42527568340301514, "learning_rate": 1.4254908407791217e-05, "loss": 4.2637, "step": 21000 }, { "epoch": 0.6414477703115455, "grad_norm": 0.43189698457717896, "learning_rate": 1.4252742441462035e-05, "loss": 4.2259, "step": 21001 }, { "epoch": 0.6414783139890042, "grad_norm": 0.4412490725517273, "learning_rate": 1.4250576574088387e-05, "loss": 4.2936, "step": 21002 }, { "epoch": 0.641508857666463, "grad_norm": 0.43482649326324463, "learning_rate": 1.4248410805690195e-05, "loss": 4.239, "step": 21003 }, { "epoch": 0.6415394013439218, "grad_norm": 0.42699843645095825, "learning_rate": 1.4246245136287417e-05, "loss": 4.2128, "step": 21004 }, { "epoch": 0.6415699450213805, "grad_norm": 0.43223926424980164, "learning_rate": 1.4244079565899995e-05, "loss": 4.2241, "step": 21005 }, { "epoch": 0.6416004886988393, "grad_norm": 0.43646004796028137, "learning_rate": 1.4241914094547854e-05, "loss": 4.1553, "step": 21006 }, { "epoch": 0.6416310323762981, "grad_norm": 0.4364183843135834, "learning_rate": 1.4239748722250942e-05, "loss": 4.2397, "step": 21007 }, { "epoch": 0.6416615760537568, "grad_norm": 0.4327743947505951, "learning_rate": 1.4237583449029207e-05, "loss": 4.2995, "step": 21008 }, { "epoch": 0.6416921197312156, "grad_norm": 0.44006484746932983, "learning_rate": 1.4235418274902563e-05, "loss": 4.3252, "step": 21009 }, { "epoch": 0.6417226634086745, "grad_norm": 0.431643009185791, "learning_rate": 1.4233253199890968e-05, "loss": 4.2639, "step": 21010 }, { "epoch": 0.6417532070861331, "grad_norm": 0.426366925239563, "learning_rate": 1.4231088224014343e-05, "loss": 4.2827, "step": 21011 }, { "epoch": 0.641783750763592, "grad_norm": 0.4372303783893585, "learning_rate": 1.4228923347292619e-05, "loss": 4.2286, "step": 21012 }, { "epoch": 0.6418142944410506, "grad_norm": 0.4385010898113251, "learning_rate": 1.4226758569745745e-05, "loss": 4.28, "step": 21013 }, { "epoch": 0.6418448381185095, "grad_norm": 0.4400394856929779, "learning_rate": 1.4224593891393633e-05, "loss": 4.2744, "step": 21014 }, { "epoch": 0.6418753817959683, "grad_norm": 0.45595860481262207, "learning_rate": 1.422242931225623e-05, "loss": 4.3048, "step": 21015 }, { "epoch": 0.641905925473427, "grad_norm": 0.43266505002975464, "learning_rate": 1.4220264832353466e-05, "loss": 4.1323, "step": 21016 }, { "epoch": 0.6419364691508858, "grad_norm": 0.42914292216300964, "learning_rate": 1.4218100451705258e-05, "loss": 4.377, "step": 21017 }, { "epoch": 0.6419670128283446, "grad_norm": 0.41976800560951233, "learning_rate": 1.4215936170331545e-05, "loss": 4.1877, "step": 21018 }, { "epoch": 0.6419975565058033, "grad_norm": 0.4212176501750946, "learning_rate": 1.4213771988252259e-05, "loss": 4.2826, "step": 21019 }, { "epoch": 0.6420281001832621, "grad_norm": 0.4395303726196289, "learning_rate": 1.4211607905487311e-05, "loss": 4.2577, "step": 21020 }, { "epoch": 0.6420586438607209, "grad_norm": 0.43207597732543945, "learning_rate": 1.4209443922056637e-05, "loss": 4.1788, "step": 21021 }, { "epoch": 0.6420891875381796, "grad_norm": 0.42056718468666077, "learning_rate": 1.420728003798017e-05, "loss": 4.2641, "step": 21022 }, { "epoch": 0.6421197312156384, "grad_norm": 0.43060219287872314, "learning_rate": 1.4205116253277811e-05, "loss": 4.3329, "step": 21023 }, { "epoch": 0.6421502748930972, "grad_norm": 0.42892521619796753, "learning_rate": 1.4202952567969503e-05, "loss": 4.3357, "step": 21024 }, { "epoch": 0.6421808185705559, "grad_norm": 0.432931512594223, "learning_rate": 1.420078898207517e-05, "loss": 4.242, "step": 21025 }, { "epoch": 0.6422113622480147, "grad_norm": 0.441959947347641, "learning_rate": 1.4198625495614724e-05, "loss": 4.2505, "step": 21026 }, { "epoch": 0.6422419059254735, "grad_norm": 0.44396841526031494, "learning_rate": 1.4196462108608077e-05, "loss": 4.2861, "step": 21027 }, { "epoch": 0.6422724496029322, "grad_norm": 0.4351729154586792, "learning_rate": 1.4194298821075167e-05, "loss": 4.2467, "step": 21028 }, { "epoch": 0.642302993280391, "grad_norm": 0.425542414188385, "learning_rate": 1.4192135633035894e-05, "loss": 4.2916, "step": 21029 }, { "epoch": 0.6423335369578497, "grad_norm": 0.43538618087768555, "learning_rate": 1.4189972544510197e-05, "loss": 4.2871, "step": 21030 }, { "epoch": 0.6423640806353085, "grad_norm": 0.4355488121509552, "learning_rate": 1.4187809555517967e-05, "loss": 4.3208, "step": 21031 }, { "epoch": 0.6423946243127673, "grad_norm": 0.43643316626548767, "learning_rate": 1.4185646666079138e-05, "loss": 4.2451, "step": 21032 }, { "epoch": 0.642425167990226, "grad_norm": 0.43654027581214905, "learning_rate": 1.4183483876213626e-05, "loss": 4.3411, "step": 21033 }, { "epoch": 0.6424557116676848, "grad_norm": 0.447013795375824, "learning_rate": 1.4181321185941332e-05, "loss": 4.3373, "step": 21034 }, { "epoch": 0.6424862553451436, "grad_norm": 0.4346176087856293, "learning_rate": 1.4179158595282177e-05, "loss": 4.1691, "step": 21035 }, { "epoch": 0.6425167990226023, "grad_norm": 0.4297037720680237, "learning_rate": 1.417699610425608e-05, "loss": 4.2634, "step": 21036 }, { "epoch": 0.6425473427000611, "grad_norm": 0.4371500015258789, "learning_rate": 1.4174833712882938e-05, "loss": 4.2782, "step": 21037 }, { "epoch": 0.6425778863775199, "grad_norm": 0.42916393280029297, "learning_rate": 1.4172671421182665e-05, "loss": 4.3165, "step": 21038 }, { "epoch": 0.6426084300549786, "grad_norm": 0.42911919951438904, "learning_rate": 1.4170509229175183e-05, "loss": 4.2795, "step": 21039 }, { "epoch": 0.6426389737324374, "grad_norm": 0.43398723006248474, "learning_rate": 1.416834713688038e-05, "loss": 4.2929, "step": 21040 }, { "epoch": 0.6426695174098962, "grad_norm": 0.437396377325058, "learning_rate": 1.4166185144318184e-05, "loss": 4.2623, "step": 21041 }, { "epoch": 0.6427000610873549, "grad_norm": 0.43246084451675415, "learning_rate": 1.4164023251508485e-05, "loss": 4.3031, "step": 21042 }, { "epoch": 0.6427306047648137, "grad_norm": 0.4284917414188385, "learning_rate": 1.4161861458471202e-05, "loss": 4.2705, "step": 21043 }, { "epoch": 0.6427611484422725, "grad_norm": 0.4354085624217987, "learning_rate": 1.4159699765226226e-05, "loss": 4.2005, "step": 21044 }, { "epoch": 0.6427916921197312, "grad_norm": 0.4358280599117279, "learning_rate": 1.4157538171793473e-05, "loss": 4.2933, "step": 21045 }, { "epoch": 0.64282223579719, "grad_norm": 0.42371663451194763, "learning_rate": 1.4155376678192832e-05, "loss": 4.3245, "step": 21046 }, { "epoch": 0.6428527794746487, "grad_norm": 0.42323723435401917, "learning_rate": 1.4153215284444228e-05, "loss": 4.2568, "step": 21047 }, { "epoch": 0.6428833231521075, "grad_norm": 0.42911002039909363, "learning_rate": 1.415105399056753e-05, "loss": 4.2427, "step": 21048 }, { "epoch": 0.6429138668295663, "grad_norm": 0.43669480085372925, "learning_rate": 1.4148892796582663e-05, "loss": 4.2402, "step": 21049 }, { "epoch": 0.642944410507025, "grad_norm": 0.42695295810699463, "learning_rate": 1.4146731702509525e-05, "loss": 4.2496, "step": 21050 }, { "epoch": 0.6429749541844838, "grad_norm": 0.4406731128692627, "learning_rate": 1.4144570708368002e-05, "loss": 4.1317, "step": 21051 }, { "epoch": 0.6430054978619426, "grad_norm": 0.4348336458206177, "learning_rate": 1.4142409814177996e-05, "loss": 4.255, "step": 21052 }, { "epoch": 0.6430360415394013, "grad_norm": 0.44650062918663025, "learning_rate": 1.4140249019959415e-05, "loss": 4.3329, "step": 21053 }, { "epoch": 0.6430665852168601, "grad_norm": 0.4342305064201355, "learning_rate": 1.4138088325732136e-05, "loss": 4.2686, "step": 21054 }, { "epoch": 0.6430971288943189, "grad_norm": 0.4231473207473755, "learning_rate": 1.4135927731516061e-05, "loss": 4.2792, "step": 21055 }, { "epoch": 0.6431276725717776, "grad_norm": 0.42728593945503235, "learning_rate": 1.4133767237331095e-05, "loss": 4.212, "step": 21056 }, { "epoch": 0.6431582162492364, "grad_norm": 0.4342862367630005, "learning_rate": 1.413160684319711e-05, "loss": 4.1898, "step": 21057 }, { "epoch": 0.6431887599266952, "grad_norm": 0.44126302003860474, "learning_rate": 1.4129446549134021e-05, "loss": 4.2229, "step": 21058 }, { "epoch": 0.6432193036041539, "grad_norm": 0.4350857436656952, "learning_rate": 1.4127286355161707e-05, "loss": 4.2211, "step": 21059 }, { "epoch": 0.6432498472816127, "grad_norm": 0.44403645396232605, "learning_rate": 1.4125126261300044e-05, "loss": 4.1411, "step": 21060 }, { "epoch": 0.6432803909590715, "grad_norm": 0.4376108944416046, "learning_rate": 1.4122966267568938e-05, "loss": 4.2469, "step": 21061 }, { "epoch": 0.6433109346365302, "grad_norm": 0.43198350071907043, "learning_rate": 1.4120806373988282e-05, "loss": 4.3124, "step": 21062 }, { "epoch": 0.643341478313989, "grad_norm": 0.43985438346862793, "learning_rate": 1.4118646580577949e-05, "loss": 4.314, "step": 21063 }, { "epoch": 0.6433720219914477, "grad_norm": 0.42659956216812134, "learning_rate": 1.4116486887357837e-05, "loss": 4.3175, "step": 21064 }, { "epoch": 0.6434025656689065, "grad_norm": 0.4265137016773224, "learning_rate": 1.4114327294347817e-05, "loss": 4.2633, "step": 21065 }, { "epoch": 0.6434331093463653, "grad_norm": 0.4348084330558777, "learning_rate": 1.4112167801567788e-05, "loss": 4.2118, "step": 21066 }, { "epoch": 0.643463653023824, "grad_norm": 0.4332530200481415, "learning_rate": 1.4110008409037634e-05, "loss": 4.2022, "step": 21067 }, { "epoch": 0.6434941967012828, "grad_norm": 0.4378170073032379, "learning_rate": 1.4107849116777219e-05, "loss": 4.3574, "step": 21068 }, { "epoch": 0.6435247403787416, "grad_norm": 0.44310733675956726, "learning_rate": 1.410568992480644e-05, "loss": 4.3109, "step": 21069 }, { "epoch": 0.6435552840562003, "grad_norm": 0.44647806882858276, "learning_rate": 1.4103530833145185e-05, "loss": 4.3582, "step": 21070 }, { "epoch": 0.6435858277336591, "grad_norm": 0.434533029794693, "learning_rate": 1.4101371841813316e-05, "loss": 4.1978, "step": 21071 }, { "epoch": 0.6436163714111179, "grad_norm": 0.4337749779224396, "learning_rate": 1.4099212950830726e-05, "loss": 4.3072, "step": 21072 }, { "epoch": 0.6436469150885766, "grad_norm": 0.4382791519165039, "learning_rate": 1.4097054160217276e-05, "loss": 4.1372, "step": 21073 }, { "epoch": 0.6436774587660354, "grad_norm": 0.41996923089027405, "learning_rate": 1.4094895469992869e-05, "loss": 4.2206, "step": 21074 }, { "epoch": 0.6437080024434942, "grad_norm": 0.4399844706058502, "learning_rate": 1.4092736880177355e-05, "loss": 4.1914, "step": 21075 }, { "epoch": 0.6437385461209529, "grad_norm": 0.45229843258857727, "learning_rate": 1.4090578390790629e-05, "loss": 4.3383, "step": 21076 }, { "epoch": 0.6437690897984117, "grad_norm": 0.4395165741443634, "learning_rate": 1.4088420001852548e-05, "loss": 4.2647, "step": 21077 }, { "epoch": 0.6437996334758705, "grad_norm": 0.44719457626342773, "learning_rate": 1.4086261713382992e-05, "loss": 4.3001, "step": 21078 }, { "epoch": 0.6438301771533292, "grad_norm": 0.442442923784256, "learning_rate": 1.4084103525401848e-05, "loss": 4.32, "step": 21079 }, { "epoch": 0.643860720830788, "grad_norm": 0.4349832236766815, "learning_rate": 1.4081945437928967e-05, "loss": 4.2848, "step": 21080 }, { "epoch": 0.6438912645082467, "grad_norm": 0.43772944808006287, "learning_rate": 1.4079787450984234e-05, "loss": 4.2969, "step": 21081 }, { "epoch": 0.6439218081857055, "grad_norm": 0.44156739115715027, "learning_rate": 1.4077629564587502e-05, "loss": 4.2405, "step": 21082 }, { "epoch": 0.6439523518631644, "grad_norm": 0.4371800720691681, "learning_rate": 1.4075471778758653e-05, "loss": 4.2834, "step": 21083 }, { "epoch": 0.643982895540623, "grad_norm": 0.443726509809494, "learning_rate": 1.4073314093517565e-05, "loss": 4.3685, "step": 21084 }, { "epoch": 0.6440134392180819, "grad_norm": 0.4388931393623352, "learning_rate": 1.4071156508884076e-05, "loss": 4.2031, "step": 21085 }, { "epoch": 0.6440439828955407, "grad_norm": 0.4362320005893707, "learning_rate": 1.4068999024878072e-05, "loss": 4.2476, "step": 21086 }, { "epoch": 0.6440745265729994, "grad_norm": 0.4386395215988159, "learning_rate": 1.4066841641519423e-05, "loss": 4.3103, "step": 21087 }, { "epoch": 0.6441050702504582, "grad_norm": 0.444771945476532, "learning_rate": 1.4064684358827973e-05, "loss": 4.2849, "step": 21088 }, { "epoch": 0.644135613927917, "grad_norm": 0.4458480477333069, "learning_rate": 1.4062527176823608e-05, "loss": 4.2826, "step": 21089 }, { "epoch": 0.6441661576053757, "grad_norm": 0.439208447933197, "learning_rate": 1.4060370095526177e-05, "loss": 4.3371, "step": 21090 }, { "epoch": 0.6441967012828345, "grad_norm": 0.42620715498924255, "learning_rate": 1.4058213114955538e-05, "loss": 4.2941, "step": 21091 }, { "epoch": 0.6442272449602933, "grad_norm": 0.43360239267349243, "learning_rate": 1.405605623513155e-05, "loss": 4.2505, "step": 21092 }, { "epoch": 0.644257788637752, "grad_norm": 0.4394244849681854, "learning_rate": 1.4053899456074092e-05, "loss": 4.2638, "step": 21093 }, { "epoch": 0.6442883323152108, "grad_norm": 0.4327975809574127, "learning_rate": 1.4051742777803001e-05, "loss": 4.2472, "step": 21094 }, { "epoch": 0.6443188759926696, "grad_norm": 0.4332446753978729, "learning_rate": 1.404958620033814e-05, "loss": 4.2352, "step": 21095 }, { "epoch": 0.6443494196701283, "grad_norm": 0.4403285086154938, "learning_rate": 1.4047429723699385e-05, "loss": 4.297, "step": 21096 }, { "epoch": 0.6443799633475871, "grad_norm": 0.43508023023605347, "learning_rate": 1.4045273347906559e-05, "loss": 4.2706, "step": 21097 }, { "epoch": 0.6444105070250458, "grad_norm": 0.4321177899837494, "learning_rate": 1.4043117072979548e-05, "loss": 4.3009, "step": 21098 }, { "epoch": 0.6444410507025046, "grad_norm": 0.4359356164932251, "learning_rate": 1.404096089893818e-05, "loss": 4.2652, "step": 21099 }, { "epoch": 0.6444715943799634, "grad_norm": 0.42550718784332275, "learning_rate": 1.403880482580232e-05, "loss": 4.3259, "step": 21100 }, { "epoch": 0.6445021380574221, "grad_norm": 0.42512837052345276, "learning_rate": 1.4036648853591827e-05, "loss": 4.245, "step": 21101 }, { "epoch": 0.6445326817348809, "grad_norm": 0.42437320947647095, "learning_rate": 1.4034492982326539e-05, "loss": 4.2047, "step": 21102 }, { "epoch": 0.6445632254123397, "grad_norm": 0.4179435670375824, "learning_rate": 1.4032337212026308e-05, "loss": 4.2905, "step": 21103 }, { "epoch": 0.6445937690897984, "grad_norm": 0.44330477714538574, "learning_rate": 1.4030181542711002e-05, "loss": 4.2422, "step": 21104 }, { "epoch": 0.6446243127672572, "grad_norm": 0.4247261881828308, "learning_rate": 1.402802597440045e-05, "loss": 4.268, "step": 21105 }, { "epoch": 0.644654856444716, "grad_norm": 0.4216490685939789, "learning_rate": 1.4025870507114497e-05, "loss": 4.2099, "step": 21106 }, { "epoch": 0.6446854001221747, "grad_norm": 0.4320565462112427, "learning_rate": 1.4023715140873006e-05, "loss": 4.3292, "step": 21107 }, { "epoch": 0.6447159437996335, "grad_norm": 0.43205326795578003, "learning_rate": 1.4021559875695803e-05, "loss": 4.2724, "step": 21108 }, { "epoch": 0.6447464874770923, "grad_norm": 0.43522876501083374, "learning_rate": 1.4019404711602743e-05, "loss": 4.2577, "step": 21109 }, { "epoch": 0.644777031154551, "grad_norm": 0.42374926805496216, "learning_rate": 1.4017249648613678e-05, "loss": 4.3566, "step": 21110 }, { "epoch": 0.6448075748320098, "grad_norm": 0.4293595850467682, "learning_rate": 1.4015094686748434e-05, "loss": 4.2278, "step": 21111 }, { "epoch": 0.6448381185094686, "grad_norm": 0.44071295857429504, "learning_rate": 1.4012939826026861e-05, "loss": 4.2393, "step": 21112 }, { "epoch": 0.6448686621869273, "grad_norm": 0.4284474551677704, "learning_rate": 1.401078506646881e-05, "loss": 4.2128, "step": 21113 }, { "epoch": 0.6448992058643861, "grad_norm": 0.42609769105911255, "learning_rate": 1.4008630408094101e-05, "loss": 4.3708, "step": 21114 }, { "epoch": 0.6449297495418448, "grad_norm": 0.43136319518089294, "learning_rate": 1.400647585092259e-05, "loss": 4.226, "step": 21115 }, { "epoch": 0.6449602932193036, "grad_norm": 0.4294709861278534, "learning_rate": 1.40043213949741e-05, "loss": 4.3147, "step": 21116 }, { "epoch": 0.6449908368967624, "grad_norm": 0.4324917197227478, "learning_rate": 1.400216704026848e-05, "loss": 4.3406, "step": 21117 }, { "epoch": 0.6450213805742211, "grad_norm": 0.4356519877910614, "learning_rate": 1.4000012786825567e-05, "loss": 4.2327, "step": 21118 }, { "epoch": 0.6450519242516799, "grad_norm": 0.4410383701324463, "learning_rate": 1.3997858634665188e-05, "loss": 4.2625, "step": 21119 }, { "epoch": 0.6450824679291387, "grad_norm": 0.8193965554237366, "learning_rate": 1.3995704583807184e-05, "loss": 4.2913, "step": 21120 }, { "epoch": 0.6451130116065974, "grad_norm": 0.4435451924800873, "learning_rate": 1.399355063427139e-05, "loss": 4.2179, "step": 21121 }, { "epoch": 0.6451435552840562, "grad_norm": 0.44381529092788696, "learning_rate": 1.3991396786077626e-05, "loss": 4.2396, "step": 21122 }, { "epoch": 0.645174098961515, "grad_norm": 0.43135207891464233, "learning_rate": 1.398924303924573e-05, "loss": 4.2628, "step": 21123 }, { "epoch": 0.6452046426389737, "grad_norm": 0.4294601380825043, "learning_rate": 1.3987089393795545e-05, "loss": 4.2782, "step": 21124 }, { "epoch": 0.6452351863164325, "grad_norm": 0.46458935737609863, "learning_rate": 1.3984935849746878e-05, "loss": 4.301, "step": 21125 }, { "epoch": 0.6452657299938913, "grad_norm": 0.4423114061355591, "learning_rate": 1.3982782407119571e-05, "loss": 4.3035, "step": 21126 }, { "epoch": 0.64529627367135, "grad_norm": 0.44654613733291626, "learning_rate": 1.3980629065933462e-05, "loss": 4.2313, "step": 21127 }, { "epoch": 0.6453268173488088, "grad_norm": 0.4359596371650696, "learning_rate": 1.3978475826208356e-05, "loss": 4.3153, "step": 21128 }, { "epoch": 0.6453573610262676, "grad_norm": 0.4296357035636902, "learning_rate": 1.3976322687964089e-05, "loss": 4.2257, "step": 21129 }, { "epoch": 0.6453879047037263, "grad_norm": 0.43246129155158997, "learning_rate": 1.3974169651220498e-05, "loss": 4.2928, "step": 21130 }, { "epoch": 0.6454184483811851, "grad_norm": 0.43866097927093506, "learning_rate": 1.3972016715997387e-05, "loss": 4.3707, "step": 21131 }, { "epoch": 0.6454489920586438, "grad_norm": 0.43802911043167114, "learning_rate": 1.3969863882314596e-05, "loss": 4.3556, "step": 21132 }, { "epoch": 0.6454795357361026, "grad_norm": 0.4287024438381195, "learning_rate": 1.3967711150191932e-05, "loss": 4.2887, "step": 21133 }, { "epoch": 0.6455100794135614, "grad_norm": 0.4383234679698944, "learning_rate": 1.3965558519649218e-05, "loss": 4.1668, "step": 21134 }, { "epoch": 0.6455406230910201, "grad_norm": 0.43580368161201477, "learning_rate": 1.3963405990706296e-05, "loss": 4.305, "step": 21135 }, { "epoch": 0.6455711667684789, "grad_norm": 0.42706483602523804, "learning_rate": 1.3961253563382968e-05, "loss": 4.3027, "step": 21136 }, { "epoch": 0.6456017104459377, "grad_norm": 0.4300468862056732, "learning_rate": 1.3959101237699044e-05, "loss": 4.1477, "step": 21137 }, { "epoch": 0.6456322541233964, "grad_norm": 0.43352407217025757, "learning_rate": 1.3956949013674358e-05, "loss": 4.2239, "step": 21138 }, { "epoch": 0.6456627978008552, "grad_norm": 0.43327629566192627, "learning_rate": 1.3954796891328714e-05, "loss": 4.1836, "step": 21139 }, { "epoch": 0.645693341478314, "grad_norm": 0.43320125341415405, "learning_rate": 1.3952644870681936e-05, "loss": 4.2688, "step": 21140 }, { "epoch": 0.6457238851557727, "grad_norm": 0.44398877024650574, "learning_rate": 1.395049295175384e-05, "loss": 4.2681, "step": 21141 }, { "epoch": 0.6457544288332315, "grad_norm": 0.4409175217151642, "learning_rate": 1.394834113456423e-05, "loss": 4.2429, "step": 21142 }, { "epoch": 0.6457849725106903, "grad_norm": 0.44578132033348083, "learning_rate": 1.3946189419132926e-05, "loss": 4.0775, "step": 21143 }, { "epoch": 0.645815516188149, "grad_norm": 0.4403804838657379, "learning_rate": 1.394403780547975e-05, "loss": 4.2416, "step": 21144 }, { "epoch": 0.6458460598656078, "grad_norm": 0.4450329542160034, "learning_rate": 1.3941886293624489e-05, "loss": 4.332, "step": 21145 }, { "epoch": 0.6458766035430665, "grad_norm": 0.43841227889060974, "learning_rate": 1.393973488358698e-05, "loss": 4.3006, "step": 21146 }, { "epoch": 0.6459071472205253, "grad_norm": 0.4274863004684448, "learning_rate": 1.3937583575387008e-05, "loss": 4.2981, "step": 21147 }, { "epoch": 0.6459376908979841, "grad_norm": 0.43269726634025574, "learning_rate": 1.3935432369044393e-05, "loss": 4.2876, "step": 21148 }, { "epoch": 0.6459682345754428, "grad_norm": 0.4330745041370392, "learning_rate": 1.3933281264578946e-05, "loss": 4.2238, "step": 21149 }, { "epoch": 0.6459987782529016, "grad_norm": 0.44344043731689453, "learning_rate": 1.3931130262010462e-05, "loss": 4.2921, "step": 21150 }, { "epoch": 0.6460293219303604, "grad_norm": 0.43180492520332336, "learning_rate": 1.3928979361358762e-05, "loss": 4.1932, "step": 21151 }, { "epoch": 0.6460598656078191, "grad_norm": 0.4278257489204407, "learning_rate": 1.3926828562643631e-05, "loss": 4.2768, "step": 21152 }, { "epoch": 0.646090409285278, "grad_norm": 0.4348292648792267, "learning_rate": 1.3924677865884895e-05, "loss": 4.2274, "step": 21153 }, { "epoch": 0.6461209529627367, "grad_norm": 0.44207748770713806, "learning_rate": 1.392252727110233e-05, "loss": 4.2669, "step": 21154 }, { "epoch": 0.6461514966401954, "grad_norm": 0.4377844035625458, "learning_rate": 1.3920376778315764e-05, "loss": 4.3228, "step": 21155 }, { "epoch": 0.6461820403176542, "grad_norm": 0.4238259196281433, "learning_rate": 1.3918226387544978e-05, "loss": 4.2318, "step": 21156 }, { "epoch": 0.646212583995113, "grad_norm": 0.4436475932598114, "learning_rate": 1.3916076098809778e-05, "loss": 4.3518, "step": 21157 }, { "epoch": 0.6462431276725717, "grad_norm": 0.4251596927642822, "learning_rate": 1.3913925912129971e-05, "loss": 4.302, "step": 21158 }, { "epoch": 0.6462736713500306, "grad_norm": 0.448956161737442, "learning_rate": 1.3911775827525343e-05, "loss": 4.2134, "step": 21159 }, { "epoch": 0.6463042150274894, "grad_norm": 0.43174389004707336, "learning_rate": 1.3909625845015689e-05, "loss": 4.1983, "step": 21160 }, { "epoch": 0.646334758704948, "grad_norm": 0.44998759031295776, "learning_rate": 1.3907475964620828e-05, "loss": 4.1872, "step": 21161 }, { "epoch": 0.6463653023824069, "grad_norm": 0.4346848726272583, "learning_rate": 1.3905326186360526e-05, "loss": 4.2975, "step": 21162 }, { "epoch": 0.6463958460598656, "grad_norm": 0.4548057019710541, "learning_rate": 1.3903176510254601e-05, "loss": 4.1906, "step": 21163 }, { "epoch": 0.6464263897373244, "grad_norm": 0.4449179172515869, "learning_rate": 1.3901026936322824e-05, "loss": 4.3589, "step": 21164 }, { "epoch": 0.6464569334147832, "grad_norm": 0.4270898997783661, "learning_rate": 1.3898877464585002e-05, "loss": 4.2867, "step": 21165 }, { "epoch": 0.6464874770922419, "grad_norm": 0.4374103546142578, "learning_rate": 1.3896728095060929e-05, "loss": 4.2856, "step": 21166 }, { "epoch": 0.6465180207697007, "grad_norm": 0.4344637989997864, "learning_rate": 1.3894578827770382e-05, "loss": 4.2139, "step": 21167 }, { "epoch": 0.6465485644471595, "grad_norm": 0.4381921887397766, "learning_rate": 1.389242966273317e-05, "loss": 4.2849, "step": 21168 }, { "epoch": 0.6465791081246182, "grad_norm": 0.4339566230773926, "learning_rate": 1.3890280599969063e-05, "loss": 4.2569, "step": 21169 }, { "epoch": 0.646609651802077, "grad_norm": 0.43035972118377686, "learning_rate": 1.3888131639497847e-05, "loss": 4.2152, "step": 21170 }, { "epoch": 0.6466401954795358, "grad_norm": 0.43558645248413086, "learning_rate": 1.3885982781339318e-05, "loss": 4.2177, "step": 21171 }, { "epoch": 0.6466707391569945, "grad_norm": 0.436625599861145, "learning_rate": 1.3883834025513265e-05, "loss": 4.2129, "step": 21172 }, { "epoch": 0.6467012828344533, "grad_norm": 0.4421745240688324, "learning_rate": 1.3881685372039463e-05, "loss": 4.1206, "step": 21173 }, { "epoch": 0.6467318265119121, "grad_norm": 0.438831627368927, "learning_rate": 1.3879536820937697e-05, "loss": 4.3473, "step": 21174 }, { "epoch": 0.6467623701893708, "grad_norm": 0.43969231843948364, "learning_rate": 1.3877388372227766e-05, "loss": 4.2367, "step": 21175 }, { "epoch": 0.6467929138668296, "grad_norm": 0.438094824552536, "learning_rate": 1.3875240025929425e-05, "loss": 4.2392, "step": 21176 }, { "epoch": 0.6468234575442884, "grad_norm": 0.44013258814811707, "learning_rate": 1.3873091782062469e-05, "loss": 4.247, "step": 21177 }, { "epoch": 0.6468540012217471, "grad_norm": 0.4346576929092407, "learning_rate": 1.387094364064669e-05, "loss": 4.3384, "step": 21178 }, { "epoch": 0.6468845448992059, "grad_norm": 0.5044375658035278, "learning_rate": 1.3868795601701844e-05, "loss": 4.2943, "step": 21179 }, { "epoch": 0.6469150885766646, "grad_norm": 0.42656877636909485, "learning_rate": 1.3866647665247734e-05, "loss": 4.2794, "step": 21180 }, { "epoch": 0.6469456322541234, "grad_norm": 0.42888474464416504, "learning_rate": 1.3864499831304106e-05, "loss": 4.2501, "step": 21181 }, { "epoch": 0.6469761759315822, "grad_norm": 0.4352085292339325, "learning_rate": 1.3862352099890768e-05, "loss": 4.1707, "step": 21182 }, { "epoch": 0.6470067196090409, "grad_norm": 0.4460216164588928, "learning_rate": 1.386020447102747e-05, "loss": 4.2335, "step": 21183 }, { "epoch": 0.6470372632864997, "grad_norm": 0.4273276925086975, "learning_rate": 1.3858056944734008e-05, "loss": 4.2397, "step": 21184 }, { "epoch": 0.6470678069639585, "grad_norm": 0.4420175552368164, "learning_rate": 1.385590952103013e-05, "loss": 4.243, "step": 21185 }, { "epoch": 0.6470983506414172, "grad_norm": 0.4388704001903534, "learning_rate": 1.3853762199935638e-05, "loss": 4.183, "step": 21186 }, { "epoch": 0.647128894318876, "grad_norm": 0.44135093688964844, "learning_rate": 1.3851614981470274e-05, "loss": 4.3107, "step": 21187 }, { "epoch": 0.6471594379963348, "grad_norm": 0.4364798367023468, "learning_rate": 1.3849467865653826e-05, "loss": 4.2204, "step": 21188 }, { "epoch": 0.6471899816737935, "grad_norm": 0.4497968852519989, "learning_rate": 1.3847320852506068e-05, "loss": 4.3052, "step": 21189 }, { "epoch": 0.6472205253512523, "grad_norm": 0.43956491351127625, "learning_rate": 1.3845173942046753e-05, "loss": 4.2811, "step": 21190 }, { "epoch": 0.6472510690287111, "grad_norm": 0.4299684166908264, "learning_rate": 1.3843027134295656e-05, "loss": 4.233, "step": 21191 }, { "epoch": 0.6472816127061698, "grad_norm": 0.4440910518169403, "learning_rate": 1.3840880429272554e-05, "loss": 4.2097, "step": 21192 }, { "epoch": 0.6473121563836286, "grad_norm": 0.44333627820014954, "learning_rate": 1.3838733826997193e-05, "loss": 4.2476, "step": 21193 }, { "epoch": 0.6473427000610874, "grad_norm": 0.4347141981124878, "learning_rate": 1.383658732748935e-05, "loss": 4.3099, "step": 21194 }, { "epoch": 0.6473732437385461, "grad_norm": 0.4401034116744995, "learning_rate": 1.3834440930768797e-05, "loss": 4.1846, "step": 21195 }, { "epoch": 0.6474037874160049, "grad_norm": 0.42656561732292175, "learning_rate": 1.3832294636855276e-05, "loss": 4.3044, "step": 21196 }, { "epoch": 0.6474343310934636, "grad_norm": 0.438059002161026, "learning_rate": 1.383014844576857e-05, "loss": 4.2785, "step": 21197 }, { "epoch": 0.6474648747709224, "grad_norm": 0.4357857406139374, "learning_rate": 1.3828002357528419e-05, "loss": 4.2206, "step": 21198 }, { "epoch": 0.6474954184483812, "grad_norm": 0.4444965124130249, "learning_rate": 1.3825856372154609e-05, "loss": 4.3075, "step": 21199 }, { "epoch": 0.6475259621258399, "grad_norm": 0.43521371483802795, "learning_rate": 1.382371048966688e-05, "loss": 4.2452, "step": 21200 }, { "epoch": 0.6475565058032987, "grad_norm": 0.4310136139392853, "learning_rate": 1.3821564710084985e-05, "loss": 4.1949, "step": 21201 }, { "epoch": 0.6475870494807575, "grad_norm": 0.44937247037887573, "learning_rate": 1.3819419033428693e-05, "loss": 4.2137, "step": 21202 }, { "epoch": 0.6476175931582162, "grad_norm": 0.4305424392223358, "learning_rate": 1.3817273459717767e-05, "loss": 4.2053, "step": 21203 }, { "epoch": 0.647648136835675, "grad_norm": 0.44916802644729614, "learning_rate": 1.3815127988971945e-05, "loss": 4.2326, "step": 21204 }, { "epoch": 0.6476786805131338, "grad_norm": 0.4364206790924072, "learning_rate": 1.3812982621210991e-05, "loss": 4.206, "step": 21205 }, { "epoch": 0.6477092241905925, "grad_norm": 0.4448912739753723, "learning_rate": 1.3810837356454667e-05, "loss": 4.1428, "step": 21206 }, { "epoch": 0.6477397678680513, "grad_norm": 0.4412743151187897, "learning_rate": 1.3808692194722705e-05, "loss": 4.1676, "step": 21207 }, { "epoch": 0.6477703115455101, "grad_norm": 0.4404304623603821, "learning_rate": 1.380654713603487e-05, "loss": 4.3193, "step": 21208 }, { "epoch": 0.6478008552229688, "grad_norm": 0.4290046989917755, "learning_rate": 1.380440218041092e-05, "loss": 4.269, "step": 21209 }, { "epoch": 0.6478313989004276, "grad_norm": 0.4285532236099243, "learning_rate": 1.3802257327870585e-05, "loss": 4.2083, "step": 21210 }, { "epoch": 0.6478619425778864, "grad_norm": 0.4380370080471039, "learning_rate": 1.3800112578433624e-05, "loss": 4.1791, "step": 21211 }, { "epoch": 0.6478924862553451, "grad_norm": 0.4425673186779022, "learning_rate": 1.3797967932119796e-05, "loss": 4.3737, "step": 21212 }, { "epoch": 0.6479230299328039, "grad_norm": 0.44105973839759827, "learning_rate": 1.3795823388948826e-05, "loss": 4.3281, "step": 21213 }, { "epoch": 0.6479535736102626, "grad_norm": 0.43755704164505005, "learning_rate": 1.379367894894048e-05, "loss": 4.3393, "step": 21214 }, { "epoch": 0.6479841172877214, "grad_norm": 0.43949955701828003, "learning_rate": 1.3791534612114493e-05, "loss": 4.2411, "step": 21215 }, { "epoch": 0.6480146609651802, "grad_norm": 0.43412142992019653, "learning_rate": 1.3789390378490602e-05, "loss": 4.228, "step": 21216 }, { "epoch": 0.6480452046426389, "grad_norm": 0.42443835735321045, "learning_rate": 1.3787246248088564e-05, "loss": 4.3017, "step": 21217 }, { "epoch": 0.6480757483200977, "grad_norm": 0.4375346899032593, "learning_rate": 1.3785102220928109e-05, "loss": 4.2785, "step": 21218 }, { "epoch": 0.6481062919975565, "grad_norm": 0.4458271861076355, "learning_rate": 1.3782958297028983e-05, "loss": 4.1445, "step": 21219 }, { "epoch": 0.6481368356750152, "grad_norm": 0.4383467137813568, "learning_rate": 1.3780814476410935e-05, "loss": 4.2164, "step": 21220 }, { "epoch": 0.648167379352474, "grad_norm": 0.4439735412597656, "learning_rate": 1.377867075909369e-05, "loss": 4.3024, "step": 21221 }, { "epoch": 0.6481979230299328, "grad_norm": 0.4399392604827881, "learning_rate": 1.377652714509699e-05, "loss": 4.317, "step": 21222 }, { "epoch": 0.6482284667073915, "grad_norm": 0.4341663718223572, "learning_rate": 1.3774383634440585e-05, "loss": 4.3042, "step": 21223 }, { "epoch": 0.6482590103848503, "grad_norm": 0.4457317888736725, "learning_rate": 1.3772240227144195e-05, "loss": 4.338, "step": 21224 }, { "epoch": 0.6482895540623091, "grad_norm": 0.43395107984542847, "learning_rate": 1.3770096923227557e-05, "loss": 4.2802, "step": 21225 }, { "epoch": 0.6483200977397678, "grad_norm": 0.4340900778770447, "learning_rate": 1.3767953722710424e-05, "loss": 4.24, "step": 21226 }, { "epoch": 0.6483506414172266, "grad_norm": 0.4448748528957367, "learning_rate": 1.3765810625612504e-05, "loss": 4.355, "step": 21227 }, { "epoch": 0.6483811850946855, "grad_norm": 0.4356089234352112, "learning_rate": 1.3763667631953553e-05, "loss": 4.2683, "step": 21228 }, { "epoch": 0.6484117287721441, "grad_norm": 0.443418025970459, "learning_rate": 1.3761524741753278e-05, "loss": 4.2652, "step": 21229 }, { "epoch": 0.648442272449603, "grad_norm": 0.4282909035682678, "learning_rate": 1.3759381955031436e-05, "loss": 4.2082, "step": 21230 }, { "epoch": 0.6484728161270616, "grad_norm": 0.4418359100818634, "learning_rate": 1.3757239271807746e-05, "loss": 4.3259, "step": 21231 }, { "epoch": 0.6485033598045205, "grad_norm": 0.43221360445022583, "learning_rate": 1.3755096692101921e-05, "loss": 4.2749, "step": 21232 }, { "epoch": 0.6485339034819793, "grad_norm": 0.44953447580337524, "learning_rate": 1.3752954215933702e-05, "loss": 4.2079, "step": 21233 }, { "epoch": 0.648564447159438, "grad_norm": 0.4298286437988281, "learning_rate": 1.375081184332283e-05, "loss": 4.251, "step": 21234 }, { "epoch": 0.6485949908368968, "grad_norm": 0.43898651003837585, "learning_rate": 1.3748669574289002e-05, "loss": 4.3318, "step": 21235 }, { "epoch": 0.6486255345143556, "grad_norm": 0.4412127137184143, "learning_rate": 1.3746527408851962e-05, "loss": 4.3374, "step": 21236 }, { "epoch": 0.6486560781918143, "grad_norm": 0.44602349400520325, "learning_rate": 1.3744385347031439e-05, "loss": 4.2776, "step": 21237 }, { "epoch": 0.6486866218692731, "grad_norm": 0.43901294469833374, "learning_rate": 1.3742243388847137e-05, "loss": 4.2777, "step": 21238 }, { "epoch": 0.6487171655467319, "grad_norm": 0.44270679354667664, "learning_rate": 1.3740101534318788e-05, "loss": 4.2472, "step": 21239 }, { "epoch": 0.6487477092241906, "grad_norm": 0.43377625942230225, "learning_rate": 1.3737959783466122e-05, "loss": 4.2471, "step": 21240 }, { "epoch": 0.6487782529016494, "grad_norm": 0.44580909609794617, "learning_rate": 1.3735818136308842e-05, "loss": 4.3159, "step": 21241 }, { "epoch": 0.6488087965791082, "grad_norm": 0.4678201377391815, "learning_rate": 1.3733676592866679e-05, "loss": 4.2951, "step": 21242 }, { "epoch": 0.6488393402565669, "grad_norm": 0.43911823630332947, "learning_rate": 1.3731535153159352e-05, "loss": 4.1706, "step": 21243 }, { "epoch": 0.6488698839340257, "grad_norm": 0.4308195114135742, "learning_rate": 1.3729393817206571e-05, "loss": 4.2032, "step": 21244 }, { "epoch": 0.6489004276114845, "grad_norm": 0.4429471790790558, "learning_rate": 1.372725258502806e-05, "loss": 4.3485, "step": 21245 }, { "epoch": 0.6489309712889432, "grad_norm": 0.4382035434246063, "learning_rate": 1.3725111456643533e-05, "loss": 4.2437, "step": 21246 }, { "epoch": 0.648961514966402, "grad_norm": 0.4483877122402191, "learning_rate": 1.372297043207269e-05, "loss": 4.2722, "step": 21247 }, { "epoch": 0.6489920586438607, "grad_norm": 0.4369518756866455, "learning_rate": 1.3720829511335271e-05, "loss": 4.2747, "step": 21248 }, { "epoch": 0.6490226023213195, "grad_norm": 0.4284117817878723, "learning_rate": 1.371868869445096e-05, "loss": 4.2819, "step": 21249 }, { "epoch": 0.6490531459987783, "grad_norm": 0.4372688829898834, "learning_rate": 1.3716547981439485e-05, "loss": 4.2488, "step": 21250 }, { "epoch": 0.649083689676237, "grad_norm": 0.42381101846694946, "learning_rate": 1.3714407372320562e-05, "loss": 4.2871, "step": 21251 }, { "epoch": 0.6491142333536958, "grad_norm": 0.432824969291687, "learning_rate": 1.3712266867113882e-05, "loss": 4.182, "step": 21252 }, { "epoch": 0.6491447770311546, "grad_norm": 0.4455331563949585, "learning_rate": 1.3710126465839168e-05, "loss": 4.2159, "step": 21253 }, { "epoch": 0.6491753207086133, "grad_norm": 0.42972084879875183, "learning_rate": 1.3707986168516129e-05, "loss": 4.2151, "step": 21254 }, { "epoch": 0.6492058643860721, "grad_norm": 0.44612857699394226, "learning_rate": 1.3705845975164461e-05, "loss": 4.3392, "step": 21255 }, { "epoch": 0.6492364080635309, "grad_norm": 0.44003111124038696, "learning_rate": 1.3703705885803874e-05, "loss": 4.2378, "step": 21256 }, { "epoch": 0.6492669517409896, "grad_norm": 0.42593008279800415, "learning_rate": 1.3701565900454089e-05, "loss": 4.2897, "step": 21257 }, { "epoch": 0.6492974954184484, "grad_norm": 0.43016883730888367, "learning_rate": 1.3699426019134782e-05, "loss": 4.2935, "step": 21258 }, { "epoch": 0.6493280390959072, "grad_norm": 0.42566946148872375, "learning_rate": 1.369728624186567e-05, "loss": 4.2578, "step": 21259 }, { "epoch": 0.6493585827733659, "grad_norm": 0.4500935673713684, "learning_rate": 1.3695146568666467e-05, "loss": 4.279, "step": 21260 }, { "epoch": 0.6493891264508247, "grad_norm": 0.4493837058544159, "learning_rate": 1.3693006999556863e-05, "loss": 4.2784, "step": 21261 }, { "epoch": 0.6494196701282835, "grad_norm": 0.44417712092399597, "learning_rate": 1.3690867534556543e-05, "loss": 4.3069, "step": 21262 }, { "epoch": 0.6494502138057422, "grad_norm": 0.4399315118789673, "learning_rate": 1.368872817368523e-05, "loss": 4.222, "step": 21263 }, { "epoch": 0.649480757483201, "grad_norm": 0.43795186281204224, "learning_rate": 1.3686588916962606e-05, "loss": 4.1303, "step": 21264 }, { "epoch": 0.6495113011606597, "grad_norm": 0.4344418942928314, "learning_rate": 1.368444976440838e-05, "loss": 4.3806, "step": 21265 }, { "epoch": 0.6495418448381185, "grad_norm": 0.44816333055496216, "learning_rate": 1.3682310716042238e-05, "loss": 4.2267, "step": 21266 }, { "epoch": 0.6495723885155773, "grad_norm": 0.43595078587532043, "learning_rate": 1.3680171771883876e-05, "loss": 4.2494, "step": 21267 }, { "epoch": 0.649602932193036, "grad_norm": 0.42703375220298767, "learning_rate": 1.3678032931953006e-05, "loss": 4.1556, "step": 21268 }, { "epoch": 0.6496334758704948, "grad_norm": 0.4337003529071808, "learning_rate": 1.3675894196269295e-05, "loss": 4.2437, "step": 21269 }, { "epoch": 0.6496640195479536, "grad_norm": 0.44068843126296997, "learning_rate": 1.3673755564852454e-05, "loss": 4.122, "step": 21270 }, { "epoch": 0.6496945632254123, "grad_norm": 0.4373866319656372, "learning_rate": 1.3671617037722173e-05, "loss": 4.2536, "step": 21271 }, { "epoch": 0.6497251069028711, "grad_norm": 0.4457160234451294, "learning_rate": 1.3669478614898128e-05, "loss": 4.2606, "step": 21272 }, { "epoch": 0.6497556505803299, "grad_norm": 0.42449724674224854, "learning_rate": 1.3667340296400022e-05, "loss": 4.3047, "step": 21273 }, { "epoch": 0.6497861942577886, "grad_norm": 0.45894694328308105, "learning_rate": 1.366520208224755e-05, "loss": 4.2756, "step": 21274 }, { "epoch": 0.6498167379352474, "grad_norm": 0.43397659063339233, "learning_rate": 1.366306397246038e-05, "loss": 4.2806, "step": 21275 }, { "epoch": 0.6498472816127062, "grad_norm": 0.4264613091945648, "learning_rate": 1.3660925967058219e-05, "loss": 4.2699, "step": 21276 }, { "epoch": 0.6498778252901649, "grad_norm": 0.4344651401042938, "learning_rate": 1.3658788066060732e-05, "loss": 4.2664, "step": 21277 }, { "epoch": 0.6499083689676237, "grad_norm": 0.43418052792549133, "learning_rate": 1.3656650269487626e-05, "loss": 4.1618, "step": 21278 }, { "epoch": 0.6499389126450825, "grad_norm": 0.4355841279029846, "learning_rate": 1.365451257735856e-05, "loss": 4.2658, "step": 21279 }, { "epoch": 0.6499694563225412, "grad_norm": 0.43676313757896423, "learning_rate": 1.3652374989693242e-05, "loss": 4.1967, "step": 21280 }, { "epoch": 0.65, "grad_norm": 0.4331037700176239, "learning_rate": 1.3650237506511331e-05, "loss": 4.3135, "step": 21281 }, { "epoch": 0.6500305436774587, "grad_norm": 0.4459570646286011, "learning_rate": 1.3648100127832531e-05, "loss": 4.3426, "step": 21282 }, { "epoch": 0.6500610873549175, "grad_norm": 0.43986475467681885, "learning_rate": 1.3645962853676497e-05, "loss": 4.2584, "step": 21283 }, { "epoch": 0.6500916310323763, "grad_norm": 0.4242192506790161, "learning_rate": 1.3643825684062922e-05, "loss": 4.271, "step": 21284 }, { "epoch": 0.650122174709835, "grad_norm": 0.43863824009895325, "learning_rate": 1.3641688619011494e-05, "loss": 4.1198, "step": 21285 }, { "epoch": 0.6501527183872938, "grad_norm": 0.4498697817325592, "learning_rate": 1.3639551658541865e-05, "loss": 4.2176, "step": 21286 }, { "epoch": 0.6501832620647526, "grad_norm": 0.43019193410873413, "learning_rate": 1.363741480267373e-05, "loss": 4.205, "step": 21287 }, { "epoch": 0.6502138057422113, "grad_norm": 0.4283975064754486, "learning_rate": 1.3635278051426765e-05, "loss": 4.2318, "step": 21288 }, { "epoch": 0.6502443494196701, "grad_norm": 0.4372805953025818, "learning_rate": 1.3633141404820629e-05, "loss": 4.2782, "step": 21289 }, { "epoch": 0.6502748930971289, "grad_norm": 0.4578319787979126, "learning_rate": 1.3631004862875004e-05, "loss": 4.2641, "step": 21290 }, { "epoch": 0.6503054367745876, "grad_norm": 0.4355950653553009, "learning_rate": 1.3628868425609575e-05, "loss": 4.3187, "step": 21291 }, { "epoch": 0.6503359804520464, "grad_norm": 0.4299917221069336, "learning_rate": 1.3626732093043998e-05, "loss": 4.1901, "step": 21292 }, { "epoch": 0.6503665241295052, "grad_norm": 0.4402620494365692, "learning_rate": 1.3624595865197936e-05, "loss": 4.3014, "step": 21293 }, { "epoch": 0.6503970678069639, "grad_norm": 0.4447282552719116, "learning_rate": 1.3622459742091081e-05, "loss": 4.2635, "step": 21294 }, { "epoch": 0.6504276114844227, "grad_norm": 0.4306296110153198, "learning_rate": 1.3620323723743079e-05, "loss": 4.2305, "step": 21295 }, { "epoch": 0.6504581551618815, "grad_norm": 0.4393887221813202, "learning_rate": 1.3618187810173604e-05, "loss": 4.3295, "step": 21296 }, { "epoch": 0.6504886988393402, "grad_norm": 0.4374406039714813, "learning_rate": 1.3616052001402338e-05, "loss": 4.3294, "step": 21297 }, { "epoch": 0.650519242516799, "grad_norm": 0.4428955316543579, "learning_rate": 1.3613916297448925e-05, "loss": 4.346, "step": 21298 }, { "epoch": 0.6505497861942577, "grad_norm": 0.42878440022468567, "learning_rate": 1.3611780698333048e-05, "loss": 4.2563, "step": 21299 }, { "epoch": 0.6505803298717165, "grad_norm": 0.4325643479824066, "learning_rate": 1.3609645204074351e-05, "loss": 4.2875, "step": 21300 }, { "epoch": 0.6506108735491754, "grad_norm": 0.43229374289512634, "learning_rate": 1.3607509814692507e-05, "loss": 4.3334, "step": 21301 }, { "epoch": 0.650641417226634, "grad_norm": 0.4367774426937103, "learning_rate": 1.3605374530207188e-05, "loss": 4.3132, "step": 21302 }, { "epoch": 0.6506719609040928, "grad_norm": 0.4326803982257843, "learning_rate": 1.3603239350638034e-05, "loss": 4.3094, "step": 21303 }, { "epoch": 0.6507025045815517, "grad_norm": 0.4372454881668091, "learning_rate": 1.3601104276004714e-05, "loss": 4.2464, "step": 21304 }, { "epoch": 0.6507330482590103, "grad_norm": 0.44551753997802734, "learning_rate": 1.3598969306326897e-05, "loss": 4.3659, "step": 21305 }, { "epoch": 0.6507635919364692, "grad_norm": 0.4444466531276703, "learning_rate": 1.3596834441624223e-05, "loss": 4.2966, "step": 21306 }, { "epoch": 0.650794135613928, "grad_norm": 0.42653989791870117, "learning_rate": 1.3594699681916367e-05, "loss": 4.2995, "step": 21307 }, { "epoch": 0.6508246792913867, "grad_norm": 0.4300265908241272, "learning_rate": 1.3592565027222967e-05, "loss": 4.181, "step": 21308 }, { "epoch": 0.6508552229688455, "grad_norm": 0.4324687719345093, "learning_rate": 1.3590430477563693e-05, "loss": 4.2697, "step": 21309 }, { "epoch": 0.6508857666463043, "grad_norm": 0.4343962073326111, "learning_rate": 1.3588296032958183e-05, "loss": 4.2891, "step": 21310 }, { "epoch": 0.650916310323763, "grad_norm": 0.4273720383644104, "learning_rate": 1.3586161693426108e-05, "loss": 4.1874, "step": 21311 }, { "epoch": 0.6509468540012218, "grad_norm": 0.43561887741088867, "learning_rate": 1.3584027458987103e-05, "loss": 4.2944, "step": 21312 }, { "epoch": 0.6509773976786805, "grad_norm": 0.43370601534843445, "learning_rate": 1.3581893329660832e-05, "loss": 4.1838, "step": 21313 }, { "epoch": 0.6510079413561393, "grad_norm": 0.4302336573600769, "learning_rate": 1.3579759305466935e-05, "loss": 4.2563, "step": 21314 }, { "epoch": 0.6510384850335981, "grad_norm": 0.43467020988464355, "learning_rate": 1.3577625386425064e-05, "loss": 4.1455, "step": 21315 }, { "epoch": 0.6510690287110568, "grad_norm": 0.4322792589664459, "learning_rate": 1.3575491572554876e-05, "loss": 4.2251, "step": 21316 }, { "epoch": 0.6510995723885156, "grad_norm": 0.45329317450523376, "learning_rate": 1.3573357863876008e-05, "loss": 4.324, "step": 21317 }, { "epoch": 0.6511301160659744, "grad_norm": 0.4324851334095001, "learning_rate": 1.3571224260408105e-05, "loss": 4.2969, "step": 21318 }, { "epoch": 0.6511606597434331, "grad_norm": 0.4315534830093384, "learning_rate": 1.3569090762170825e-05, "loss": 4.2318, "step": 21319 }, { "epoch": 0.6511912034208919, "grad_norm": 0.4297376573085785, "learning_rate": 1.3566957369183794e-05, "loss": 4.3016, "step": 21320 }, { "epoch": 0.6512217470983507, "grad_norm": 0.4318103492259979, "learning_rate": 1.3564824081466665e-05, "loss": 4.2585, "step": 21321 }, { "epoch": 0.6512522907758094, "grad_norm": 0.4521101713180542, "learning_rate": 1.356269089903909e-05, "loss": 4.258, "step": 21322 }, { "epoch": 0.6512828344532682, "grad_norm": 0.44107887148857117, "learning_rate": 1.3560557821920691e-05, "loss": 4.3169, "step": 21323 }, { "epoch": 0.651313378130727, "grad_norm": 0.43589967489242554, "learning_rate": 1.3558424850131127e-05, "loss": 4.2682, "step": 21324 }, { "epoch": 0.6513439218081857, "grad_norm": 0.43344834446907043, "learning_rate": 1.3556291983690029e-05, "loss": 4.1471, "step": 21325 }, { "epoch": 0.6513744654856445, "grad_norm": 0.4399707615375519, "learning_rate": 1.3554159222617024e-05, "loss": 4.3212, "step": 21326 }, { "epoch": 0.6514050091631033, "grad_norm": 0.4293361008167267, "learning_rate": 1.3552026566931758e-05, "loss": 4.311, "step": 21327 }, { "epoch": 0.651435552840562, "grad_norm": 0.4395430386066437, "learning_rate": 1.3549894016653883e-05, "loss": 4.3165, "step": 21328 }, { "epoch": 0.6514660965180208, "grad_norm": 0.47570091485977173, "learning_rate": 1.3547761571803009e-05, "loss": 4.2666, "step": 21329 }, { "epoch": 0.6514966401954795, "grad_norm": 0.4523426592350006, "learning_rate": 1.3545629232398794e-05, "loss": 4.1706, "step": 21330 }, { "epoch": 0.6515271838729383, "grad_norm": 0.4539046585559845, "learning_rate": 1.3543496998460848e-05, "loss": 4.3041, "step": 21331 }, { "epoch": 0.6515577275503971, "grad_norm": 0.42901936173439026, "learning_rate": 1.3541364870008816e-05, "loss": 4.2581, "step": 21332 }, { "epoch": 0.6515882712278558, "grad_norm": 0.4391797184944153, "learning_rate": 1.353923284706234e-05, "loss": 4.2307, "step": 21333 }, { "epoch": 0.6516188149053146, "grad_norm": 0.45204195380210876, "learning_rate": 1.3537100929641028e-05, "loss": 4.2356, "step": 21334 }, { "epoch": 0.6516493585827734, "grad_norm": 0.44261935353279114, "learning_rate": 1.353496911776452e-05, "loss": 4.2845, "step": 21335 }, { "epoch": 0.6516799022602321, "grad_norm": 0.43812379240989685, "learning_rate": 1.353283741145246e-05, "loss": 4.1944, "step": 21336 }, { "epoch": 0.6517104459376909, "grad_norm": 0.43411874771118164, "learning_rate": 1.3530705810724447e-05, "loss": 4.2104, "step": 21337 }, { "epoch": 0.6517409896151497, "grad_norm": 0.42836296558380127, "learning_rate": 1.3528574315600138e-05, "loss": 4.2761, "step": 21338 }, { "epoch": 0.6517715332926084, "grad_norm": 0.43811845779418945, "learning_rate": 1.352644292609913e-05, "loss": 4.3666, "step": 21339 }, { "epoch": 0.6518020769700672, "grad_norm": 0.4261512756347656, "learning_rate": 1.3524311642241072e-05, "loss": 4.237, "step": 21340 }, { "epoch": 0.651832620647526, "grad_norm": 0.4330686926841736, "learning_rate": 1.3522180464045565e-05, "loss": 4.2688, "step": 21341 }, { "epoch": 0.6518631643249847, "grad_norm": 0.4287276268005371, "learning_rate": 1.3520049391532257e-05, "loss": 4.2624, "step": 21342 }, { "epoch": 0.6518937080024435, "grad_norm": 0.4279739260673523, "learning_rate": 1.3517918424720743e-05, "loss": 4.2274, "step": 21343 }, { "epoch": 0.6519242516799023, "grad_norm": 0.4269879162311554, "learning_rate": 1.3515787563630661e-05, "loss": 4.2141, "step": 21344 }, { "epoch": 0.651954795357361, "grad_norm": 0.43575698137283325, "learning_rate": 1.351365680828164e-05, "loss": 4.2131, "step": 21345 }, { "epoch": 0.6519853390348198, "grad_norm": 0.43822523951530457, "learning_rate": 1.351152615869327e-05, "loss": 4.3379, "step": 21346 }, { "epoch": 0.6520158827122785, "grad_norm": 0.4436497092247009, "learning_rate": 1.3509395614885199e-05, "loss": 4.3363, "step": 21347 }, { "epoch": 0.6520464263897373, "grad_norm": 0.43610045313835144, "learning_rate": 1.3507265176877018e-05, "loss": 4.3468, "step": 21348 }, { "epoch": 0.6520769700671961, "grad_norm": 0.4396657347679138, "learning_rate": 1.3505134844688359e-05, "loss": 4.2536, "step": 21349 }, { "epoch": 0.6521075137446548, "grad_norm": 0.4437452256679535, "learning_rate": 1.3503004618338837e-05, "loss": 4.2005, "step": 21350 }, { "epoch": 0.6521380574221136, "grad_norm": 0.44576358795166016, "learning_rate": 1.350087449784806e-05, "loss": 4.2994, "step": 21351 }, { "epoch": 0.6521686010995724, "grad_norm": 0.4462438225746155, "learning_rate": 1.3498744483235643e-05, "loss": 4.2338, "step": 21352 }, { "epoch": 0.6521991447770311, "grad_norm": 0.44163742661476135, "learning_rate": 1.3496614574521205e-05, "loss": 4.2385, "step": 21353 }, { "epoch": 0.6522296884544899, "grad_norm": 0.44679349660873413, "learning_rate": 1.3494484771724341e-05, "loss": 4.2432, "step": 21354 }, { "epoch": 0.6522602321319487, "grad_norm": 0.432021826505661, "learning_rate": 1.3492355074864687e-05, "loss": 4.3146, "step": 21355 }, { "epoch": 0.6522907758094074, "grad_norm": 0.43981635570526123, "learning_rate": 1.3490225483961832e-05, "loss": 4.3105, "step": 21356 }, { "epoch": 0.6523213194868662, "grad_norm": 0.4491661489009857, "learning_rate": 1.3488095999035376e-05, "loss": 4.1928, "step": 21357 }, { "epoch": 0.652351863164325, "grad_norm": 0.4289884865283966, "learning_rate": 1.3485966620104945e-05, "loss": 4.2259, "step": 21358 }, { "epoch": 0.6523824068417837, "grad_norm": 0.4466245770454407, "learning_rate": 1.3483837347190147e-05, "loss": 4.3817, "step": 21359 }, { "epoch": 0.6524129505192425, "grad_norm": 0.4396856129169464, "learning_rate": 1.348170818031057e-05, "loss": 4.3647, "step": 21360 }, { "epoch": 0.6524434941967013, "grad_norm": 0.4431663751602173, "learning_rate": 1.3479579119485827e-05, "loss": 4.173, "step": 21361 }, { "epoch": 0.65247403787416, "grad_norm": 0.4403160810470581, "learning_rate": 1.3477450164735534e-05, "loss": 4.3017, "step": 21362 }, { "epoch": 0.6525045815516188, "grad_norm": 0.43896183371543884, "learning_rate": 1.347532131607927e-05, "loss": 4.2531, "step": 21363 }, { "epoch": 0.6525351252290775, "grad_norm": 0.4362775981426239, "learning_rate": 1.3473192573536659e-05, "loss": 4.0648, "step": 21364 }, { "epoch": 0.6525656689065363, "grad_norm": 0.44095146656036377, "learning_rate": 1.3471063937127276e-05, "loss": 4.2065, "step": 21365 }, { "epoch": 0.6525962125839951, "grad_norm": 0.4412960410118103, "learning_rate": 1.346893540687074e-05, "loss": 4.3148, "step": 21366 }, { "epoch": 0.6526267562614538, "grad_norm": 0.45062166452407837, "learning_rate": 1.3466806982786651e-05, "loss": 4.1926, "step": 21367 }, { "epoch": 0.6526572999389126, "grad_norm": 0.42941150069236755, "learning_rate": 1.3464678664894592e-05, "loss": 4.2287, "step": 21368 }, { "epoch": 0.6526878436163714, "grad_norm": 0.43052560091018677, "learning_rate": 1.3462550453214167e-05, "loss": 4.2828, "step": 21369 }, { "epoch": 0.6527183872938301, "grad_norm": 0.44647127389907837, "learning_rate": 1.3460422347764983e-05, "loss": 4.2184, "step": 21370 }, { "epoch": 0.6527489309712889, "grad_norm": 0.43617668747901917, "learning_rate": 1.3458294348566624e-05, "loss": 4.2551, "step": 21371 }, { "epoch": 0.6527794746487477, "grad_norm": 0.4252930283546448, "learning_rate": 1.3456166455638672e-05, "loss": 4.272, "step": 21372 }, { "epoch": 0.6528100183262064, "grad_norm": 0.4425393044948578, "learning_rate": 1.3454038669000741e-05, "loss": 4.2371, "step": 21373 }, { "epoch": 0.6528405620036652, "grad_norm": 0.43662264943122864, "learning_rate": 1.34519109886724e-05, "loss": 4.1867, "step": 21374 }, { "epoch": 0.652871105681124, "grad_norm": 0.42909860610961914, "learning_rate": 1.3449783414673256e-05, "loss": 4.2876, "step": 21375 }, { "epoch": 0.6529016493585827, "grad_norm": 0.43933284282684326, "learning_rate": 1.3447655947022902e-05, "loss": 4.2313, "step": 21376 }, { "epoch": 0.6529321930360416, "grad_norm": 0.45017823576927185, "learning_rate": 1.3445528585740908e-05, "loss": 4.2846, "step": 21377 }, { "epoch": 0.6529627367135004, "grad_norm": 0.432701051235199, "learning_rate": 1.3443401330846875e-05, "loss": 4.336, "step": 21378 }, { "epoch": 0.652993280390959, "grad_norm": 0.4241582751274109, "learning_rate": 1.3441274182360397e-05, "loss": 4.2515, "step": 21379 }, { "epoch": 0.6530238240684179, "grad_norm": 0.44985759258270264, "learning_rate": 1.3439147140301042e-05, "loss": 4.2535, "step": 21380 }, { "epoch": 0.6530543677458766, "grad_norm": 0.43569618463516235, "learning_rate": 1.343702020468841e-05, "loss": 4.282, "step": 21381 }, { "epoch": 0.6530849114233354, "grad_norm": 0.44456911087036133, "learning_rate": 1.3434893375542074e-05, "loss": 4.1666, "step": 21382 }, { "epoch": 0.6531154551007942, "grad_norm": 0.43912363052368164, "learning_rate": 1.3432766652881618e-05, "loss": 4.156, "step": 21383 }, { "epoch": 0.6531459987782529, "grad_norm": 0.4278964400291443, "learning_rate": 1.3430640036726633e-05, "loss": 4.2887, "step": 21384 }, { "epoch": 0.6531765424557117, "grad_norm": 0.44311612844467163, "learning_rate": 1.3428513527096686e-05, "loss": 4.314, "step": 21385 }, { "epoch": 0.6532070861331705, "grad_norm": 0.4476030170917511, "learning_rate": 1.3426387124011375e-05, "loss": 4.2841, "step": 21386 }, { "epoch": 0.6532376298106292, "grad_norm": 0.44584810733795166, "learning_rate": 1.3424260827490259e-05, "loss": 4.2055, "step": 21387 }, { "epoch": 0.653268173488088, "grad_norm": 0.42884209752082825, "learning_rate": 1.3422134637552935e-05, "loss": 4.2141, "step": 21388 }, { "epoch": 0.6532987171655468, "grad_norm": 0.4418642520904541, "learning_rate": 1.342000855421896e-05, "loss": 4.3014, "step": 21389 }, { "epoch": 0.6533292608430055, "grad_norm": 0.4322982430458069, "learning_rate": 1.3417882577507929e-05, "loss": 4.2585, "step": 21390 }, { "epoch": 0.6533598045204643, "grad_norm": 0.4431343376636505, "learning_rate": 1.3415756707439398e-05, "loss": 4.2317, "step": 21391 }, { "epoch": 0.6533903481979231, "grad_norm": 0.41708213090896606, "learning_rate": 1.3413630944032951e-05, "loss": 4.2254, "step": 21392 }, { "epoch": 0.6534208918753818, "grad_norm": 0.432271271944046, "learning_rate": 1.3411505287308174e-05, "loss": 4.3143, "step": 21393 }, { "epoch": 0.6534514355528406, "grad_norm": 0.42367276549339294, "learning_rate": 1.3409379737284613e-05, "loss": 4.2886, "step": 21394 }, { "epoch": 0.6534819792302994, "grad_norm": 0.4333040118217468, "learning_rate": 1.3407254293981853e-05, "loss": 4.2546, "step": 21395 }, { "epoch": 0.6535125229077581, "grad_norm": 0.43935319781303406, "learning_rate": 1.3405128957419472e-05, "loss": 4.2142, "step": 21396 }, { "epoch": 0.6535430665852169, "grad_norm": 0.4388595223426819, "learning_rate": 1.3403003727617023e-05, "loss": 4.3222, "step": 21397 }, { "epoch": 0.6535736102626756, "grad_norm": 0.43851733207702637, "learning_rate": 1.3400878604594088e-05, "loss": 4.3456, "step": 21398 }, { "epoch": 0.6536041539401344, "grad_norm": 0.43474048376083374, "learning_rate": 1.339875358837022e-05, "loss": 4.3502, "step": 21399 }, { "epoch": 0.6536346976175932, "grad_norm": 0.4377831220626831, "learning_rate": 1.339662867896499e-05, "loss": 4.2927, "step": 21400 }, { "epoch": 0.6536652412950519, "grad_norm": 0.44583120942115784, "learning_rate": 1.3394503876397979e-05, "loss": 4.1859, "step": 21401 }, { "epoch": 0.6536957849725107, "grad_norm": 0.42995381355285645, "learning_rate": 1.3392379180688736e-05, "loss": 4.2552, "step": 21402 }, { "epoch": 0.6537263286499695, "grad_norm": 0.4368152916431427, "learning_rate": 1.3390254591856815e-05, "loss": 4.3093, "step": 21403 }, { "epoch": 0.6537568723274282, "grad_norm": 0.44805771112442017, "learning_rate": 1.3388130109921798e-05, "loss": 4.2207, "step": 21404 }, { "epoch": 0.653787416004887, "grad_norm": 0.4350070357322693, "learning_rate": 1.338600573490323e-05, "loss": 4.2952, "step": 21405 }, { "epoch": 0.6538179596823458, "grad_norm": 0.44040417671203613, "learning_rate": 1.3383881466820678e-05, "loss": 4.1781, "step": 21406 }, { "epoch": 0.6538485033598045, "grad_norm": 0.4417301416397095, "learning_rate": 1.338175730569371e-05, "loss": 4.2607, "step": 21407 }, { "epoch": 0.6538790470372633, "grad_norm": 0.4415037930011749, "learning_rate": 1.3379633251541868e-05, "loss": 4.2432, "step": 21408 }, { "epoch": 0.6539095907147221, "grad_norm": 0.4338521361351013, "learning_rate": 1.3377509304384717e-05, "loss": 4.277, "step": 21409 }, { "epoch": 0.6539401343921808, "grad_norm": 0.4361286163330078, "learning_rate": 1.3375385464241824e-05, "loss": 4.2969, "step": 21410 }, { "epoch": 0.6539706780696396, "grad_norm": 0.4320518374443054, "learning_rate": 1.3373261731132722e-05, "loss": 4.2384, "step": 21411 }, { "epoch": 0.6540012217470984, "grad_norm": 0.44644320011138916, "learning_rate": 1.3371138105076977e-05, "loss": 4.2945, "step": 21412 }, { "epoch": 0.6540317654245571, "grad_norm": 0.43109244108200073, "learning_rate": 1.3369014586094153e-05, "loss": 4.1798, "step": 21413 }, { "epoch": 0.6540623091020159, "grad_norm": 0.4310764968395233, "learning_rate": 1.3366891174203782e-05, "loss": 4.245, "step": 21414 }, { "epoch": 0.6540928527794746, "grad_norm": 0.4439699053764343, "learning_rate": 1.3364767869425438e-05, "loss": 4.2716, "step": 21415 }, { "epoch": 0.6541233964569334, "grad_norm": 0.4762832522392273, "learning_rate": 1.3362644671778646e-05, "loss": 4.2726, "step": 21416 }, { "epoch": 0.6541539401343922, "grad_norm": 0.44004905223846436, "learning_rate": 1.3360521581282975e-05, "loss": 4.2892, "step": 21417 }, { "epoch": 0.6541844838118509, "grad_norm": 0.443976491689682, "learning_rate": 1.3358398597957961e-05, "loss": 4.2072, "step": 21418 }, { "epoch": 0.6542150274893097, "grad_norm": 0.44216692447662354, "learning_rate": 1.3356275721823164e-05, "loss": 4.2047, "step": 21419 }, { "epoch": 0.6542455711667685, "grad_norm": 0.43603360652923584, "learning_rate": 1.3354152952898114e-05, "loss": 4.2401, "step": 21420 }, { "epoch": 0.6542761148442272, "grad_norm": 0.44321030378341675, "learning_rate": 1.3352030291202372e-05, "loss": 4.2278, "step": 21421 }, { "epoch": 0.654306658521686, "grad_norm": 0.43549850583076477, "learning_rate": 1.3349907736755471e-05, "loss": 4.2873, "step": 21422 }, { "epoch": 0.6543372021991448, "grad_norm": 0.44268253445625305, "learning_rate": 1.3347785289576958e-05, "loss": 4.2915, "step": 21423 }, { "epoch": 0.6543677458766035, "grad_norm": 0.4357571601867676, "learning_rate": 1.3345662949686382e-05, "loss": 4.287, "step": 21424 }, { "epoch": 0.6543982895540623, "grad_norm": 0.43263253569602966, "learning_rate": 1.3343540717103275e-05, "loss": 4.3156, "step": 21425 }, { "epoch": 0.6544288332315211, "grad_norm": 0.4513043165206909, "learning_rate": 1.3341418591847182e-05, "loss": 4.2406, "step": 21426 }, { "epoch": 0.6544593769089798, "grad_norm": 0.43557584285736084, "learning_rate": 1.3339296573937648e-05, "loss": 4.3023, "step": 21427 }, { "epoch": 0.6544899205864386, "grad_norm": 0.464191198348999, "learning_rate": 1.33371746633942e-05, "loss": 4.1964, "step": 21428 }, { "epoch": 0.6545204642638974, "grad_norm": 0.4509983956813812, "learning_rate": 1.333505286023638e-05, "loss": 4.2604, "step": 21429 }, { "epoch": 0.6545510079413561, "grad_norm": 0.44505536556243896, "learning_rate": 1.3332931164483736e-05, "loss": 4.3187, "step": 21430 }, { "epoch": 0.6545815516188149, "grad_norm": 0.44059690833091736, "learning_rate": 1.333080957615578e-05, "loss": 4.2749, "step": 21431 }, { "epoch": 0.6546120952962736, "grad_norm": 0.44485223293304443, "learning_rate": 1.3328688095272074e-05, "loss": 4.2176, "step": 21432 }, { "epoch": 0.6546426389737324, "grad_norm": 0.4383482336997986, "learning_rate": 1.3326566721852127e-05, "loss": 4.1442, "step": 21433 }, { "epoch": 0.6546731826511912, "grad_norm": 0.44335365295410156, "learning_rate": 1.3324445455915491e-05, "loss": 4.2619, "step": 21434 }, { "epoch": 0.6547037263286499, "grad_norm": 0.45279526710510254, "learning_rate": 1.3322324297481686e-05, "loss": 4.3325, "step": 21435 }, { "epoch": 0.6547342700061087, "grad_norm": 0.4507189989089966, "learning_rate": 1.332020324657024e-05, "loss": 4.1541, "step": 21436 }, { "epoch": 0.6547648136835675, "grad_norm": 0.4473946988582611, "learning_rate": 1.3318082303200684e-05, "loss": 4.1966, "step": 21437 }, { "epoch": 0.6547953573610262, "grad_norm": 0.436139315366745, "learning_rate": 1.3315961467392566e-05, "loss": 4.2194, "step": 21438 }, { "epoch": 0.654825901038485, "grad_norm": 0.462211549282074, "learning_rate": 1.3313840739165384e-05, "loss": 4.227, "step": 21439 }, { "epoch": 0.6548564447159438, "grad_norm": 0.4526912569999695, "learning_rate": 1.331172011853868e-05, "loss": 4.3038, "step": 21440 }, { "epoch": 0.6548869883934025, "grad_norm": 0.44392314553260803, "learning_rate": 1.3309599605531986e-05, "loss": 4.2713, "step": 21441 }, { "epoch": 0.6549175320708613, "grad_norm": 0.43537527322769165, "learning_rate": 1.3307479200164812e-05, "loss": 4.2839, "step": 21442 }, { "epoch": 0.6549480757483201, "grad_norm": 0.44151490926742554, "learning_rate": 1.3305358902456688e-05, "loss": 4.234, "step": 21443 }, { "epoch": 0.6549786194257788, "grad_norm": 0.436016708612442, "learning_rate": 1.3303238712427146e-05, "loss": 4.2753, "step": 21444 }, { "epoch": 0.6550091631032376, "grad_norm": 0.4405350089073181, "learning_rate": 1.3301118630095688e-05, "loss": 4.3649, "step": 21445 }, { "epoch": 0.6550397067806965, "grad_norm": 0.4363257884979248, "learning_rate": 1.3298998655481847e-05, "loss": 4.289, "step": 21446 }, { "epoch": 0.6550702504581551, "grad_norm": 0.43479394912719727, "learning_rate": 1.3296878788605154e-05, "loss": 4.1535, "step": 21447 }, { "epoch": 0.655100794135614, "grad_norm": 0.43650317192077637, "learning_rate": 1.3294759029485115e-05, "loss": 4.2246, "step": 21448 }, { "epoch": 0.6551313378130726, "grad_norm": 0.4365602135658264, "learning_rate": 1.3292639378141236e-05, "loss": 4.29, "step": 21449 }, { "epoch": 0.6551618814905315, "grad_norm": 0.4339067041873932, "learning_rate": 1.3290519834593055e-05, "loss": 4.2601, "step": 21450 }, { "epoch": 0.6551924251679903, "grad_norm": 0.4387187063694, "learning_rate": 1.3288400398860068e-05, "loss": 4.3435, "step": 21451 }, { "epoch": 0.655222968845449, "grad_norm": 0.4372676908969879, "learning_rate": 1.328628107096181e-05, "loss": 4.2441, "step": 21452 }, { "epoch": 0.6552535125229078, "grad_norm": 0.44601306319236755, "learning_rate": 1.3284161850917776e-05, "loss": 4.259, "step": 21453 }, { "epoch": 0.6552840562003666, "grad_norm": 0.42632123827934265, "learning_rate": 1.3282042738747489e-05, "loss": 4.2856, "step": 21454 }, { "epoch": 0.6553145998778253, "grad_norm": 0.43715330958366394, "learning_rate": 1.3279923734470467e-05, "loss": 4.1799, "step": 21455 }, { "epoch": 0.6553451435552841, "grad_norm": 0.4311637282371521, "learning_rate": 1.3277804838106204e-05, "loss": 4.3082, "step": 21456 }, { "epoch": 0.6553756872327429, "grad_norm": 0.44353657960891724, "learning_rate": 1.3275686049674219e-05, "loss": 4.2102, "step": 21457 }, { "epoch": 0.6554062309102016, "grad_norm": 0.44397440552711487, "learning_rate": 1.3273567369194029e-05, "loss": 4.2645, "step": 21458 }, { "epoch": 0.6554367745876604, "grad_norm": 0.43106400966644287, "learning_rate": 1.3271448796685127e-05, "loss": 4.3141, "step": 21459 }, { "epoch": 0.6554673182651192, "grad_norm": 0.44190552830696106, "learning_rate": 1.326933033216702e-05, "loss": 4.229, "step": 21460 }, { "epoch": 0.6554978619425779, "grad_norm": 0.43517544865608215, "learning_rate": 1.3267211975659233e-05, "loss": 4.2478, "step": 21461 }, { "epoch": 0.6555284056200367, "grad_norm": 0.4436893165111542, "learning_rate": 1.326509372718125e-05, "loss": 4.2647, "step": 21462 }, { "epoch": 0.6555589492974954, "grad_norm": 0.4343273937702179, "learning_rate": 1.326297558675259e-05, "loss": 4.2371, "step": 21463 }, { "epoch": 0.6555894929749542, "grad_norm": 0.4393012225627899, "learning_rate": 1.3260857554392742e-05, "loss": 4.2661, "step": 21464 }, { "epoch": 0.655620036652413, "grad_norm": 0.43643662333488464, "learning_rate": 1.325873963012122e-05, "loss": 4.12, "step": 21465 }, { "epoch": 0.6556505803298717, "grad_norm": 0.44417130947113037, "learning_rate": 1.325662181395752e-05, "loss": 4.2492, "step": 21466 }, { "epoch": 0.6556811240073305, "grad_norm": 0.4418010115623474, "learning_rate": 1.3254504105921129e-05, "loss": 4.2663, "step": 21467 }, { "epoch": 0.6557116676847893, "grad_norm": 0.43557503819465637, "learning_rate": 1.325238650603156e-05, "loss": 4.2573, "step": 21468 }, { "epoch": 0.655742211362248, "grad_norm": 0.43571174144744873, "learning_rate": 1.325026901430832e-05, "loss": 4.2087, "step": 21469 }, { "epoch": 0.6557727550397068, "grad_norm": 0.43795865774154663, "learning_rate": 1.3248151630770883e-05, "loss": 4.3019, "step": 21470 }, { "epoch": 0.6558032987171656, "grad_norm": 0.4383411109447479, "learning_rate": 1.3246034355438753e-05, "loss": 4.3243, "step": 21471 }, { "epoch": 0.6558338423946243, "grad_norm": 0.43099427223205566, "learning_rate": 1.3243917188331442e-05, "loss": 4.2913, "step": 21472 }, { "epoch": 0.6558643860720831, "grad_norm": 0.43363189697265625, "learning_rate": 1.3241800129468418e-05, "loss": 4.275, "step": 21473 }, { "epoch": 0.6558949297495419, "grad_norm": 0.44139358401298523, "learning_rate": 1.3239683178869186e-05, "loss": 4.2483, "step": 21474 }, { "epoch": 0.6559254734270006, "grad_norm": 0.442779541015625, "learning_rate": 1.3237566336553248e-05, "loss": 4.2722, "step": 21475 }, { "epoch": 0.6559560171044594, "grad_norm": 0.4411680996417999, "learning_rate": 1.3235449602540073e-05, "loss": 4.2856, "step": 21476 }, { "epoch": 0.6559865607819182, "grad_norm": 0.4352394640445709, "learning_rate": 1.3233332976849164e-05, "loss": 4.2459, "step": 21477 }, { "epoch": 0.6560171044593769, "grad_norm": 0.43022620677948, "learning_rate": 1.3231216459500017e-05, "loss": 4.2876, "step": 21478 }, { "epoch": 0.6560476481368357, "grad_norm": 0.43866094946861267, "learning_rate": 1.32291000505121e-05, "loss": 4.1931, "step": 21479 }, { "epoch": 0.6560781918142944, "grad_norm": 0.4461245536804199, "learning_rate": 1.3226983749904925e-05, "loss": 4.2532, "step": 21480 }, { "epoch": 0.6561087354917532, "grad_norm": 0.43958327174186707, "learning_rate": 1.3224867557697959e-05, "loss": 4.2683, "step": 21481 }, { "epoch": 0.656139279169212, "grad_norm": 0.43658074736595154, "learning_rate": 1.3222751473910683e-05, "loss": 4.2667, "step": 21482 }, { "epoch": 0.6561698228466707, "grad_norm": 0.447086900472641, "learning_rate": 1.3220635498562601e-05, "loss": 4.2308, "step": 21483 }, { "epoch": 0.6562003665241295, "grad_norm": 0.4419384002685547, "learning_rate": 1.3218519631673173e-05, "loss": 4.2521, "step": 21484 }, { "epoch": 0.6562309102015883, "grad_norm": 0.4472782015800476, "learning_rate": 1.3216403873261893e-05, "loss": 4.284, "step": 21485 }, { "epoch": 0.656261453879047, "grad_norm": 0.4379054307937622, "learning_rate": 1.3214288223348248e-05, "loss": 4.3176, "step": 21486 }, { "epoch": 0.6562919975565058, "grad_norm": 0.4454466700553894, "learning_rate": 1.3212172681951707e-05, "loss": 4.2691, "step": 21487 }, { "epoch": 0.6563225412339646, "grad_norm": 0.4433867037296295, "learning_rate": 1.3210057249091747e-05, "loss": 4.2396, "step": 21488 }, { "epoch": 0.6563530849114233, "grad_norm": 0.4449737071990967, "learning_rate": 1.3207941924787865e-05, "loss": 4.1664, "step": 21489 }, { "epoch": 0.6563836285888821, "grad_norm": 0.4362492561340332, "learning_rate": 1.3205826709059513e-05, "loss": 4.3066, "step": 21490 }, { "epoch": 0.6564141722663409, "grad_norm": 0.4477207660675049, "learning_rate": 1.3203711601926177e-05, "loss": 4.3158, "step": 21491 }, { "epoch": 0.6564447159437996, "grad_norm": 0.4343065023422241, "learning_rate": 1.3201596603407345e-05, "loss": 4.3597, "step": 21492 }, { "epoch": 0.6564752596212584, "grad_norm": 0.4373162090778351, "learning_rate": 1.3199481713522472e-05, "loss": 4.301, "step": 21493 }, { "epoch": 0.6565058032987172, "grad_norm": 0.443093866109848, "learning_rate": 1.3197366932291044e-05, "loss": 4.2705, "step": 21494 }, { "epoch": 0.6565363469761759, "grad_norm": 0.44685789942741394, "learning_rate": 1.3195252259732522e-05, "loss": 4.3065, "step": 21495 }, { "epoch": 0.6565668906536347, "grad_norm": 0.4441170394420624, "learning_rate": 1.3193137695866386e-05, "loss": 4.3718, "step": 21496 }, { "epoch": 0.6565974343310934, "grad_norm": 0.42886632680892944, "learning_rate": 1.3191023240712094e-05, "loss": 4.1691, "step": 21497 }, { "epoch": 0.6566279780085522, "grad_norm": 0.4403967261314392, "learning_rate": 1.318890889428913e-05, "loss": 4.2767, "step": 21498 }, { "epoch": 0.656658521686011, "grad_norm": 0.42723548412323, "learning_rate": 1.318679465661695e-05, "loss": 4.2622, "step": 21499 }, { "epoch": 0.6566890653634697, "grad_norm": 0.43732836842536926, "learning_rate": 1.3184680527715033e-05, "loss": 4.2921, "step": 21500 }, { "epoch": 0.6567196090409285, "grad_norm": 0.4387902021408081, "learning_rate": 1.3182566507602825e-05, "loss": 4.2078, "step": 21501 }, { "epoch": 0.6567501527183873, "grad_norm": 0.4340397119522095, "learning_rate": 1.3180452596299805e-05, "loss": 4.2672, "step": 21502 }, { "epoch": 0.656780696395846, "grad_norm": 0.4253580868244171, "learning_rate": 1.3178338793825446e-05, "loss": 4.219, "step": 21503 }, { "epoch": 0.6568112400733048, "grad_norm": 0.4325118362903595, "learning_rate": 1.3176225100199188e-05, "loss": 4.2922, "step": 21504 }, { "epoch": 0.6568417837507636, "grad_norm": 0.44597986340522766, "learning_rate": 1.3174111515440507e-05, "loss": 4.2353, "step": 21505 }, { "epoch": 0.6568723274282223, "grad_norm": 0.5898609161376953, "learning_rate": 1.3171998039568866e-05, "loss": 4.2798, "step": 21506 }, { "epoch": 0.6569028711056811, "grad_norm": 0.42929691076278687, "learning_rate": 1.3169884672603717e-05, "loss": 4.284, "step": 21507 }, { "epoch": 0.6569334147831399, "grad_norm": 0.4302777051925659, "learning_rate": 1.316777141456452e-05, "loss": 4.1539, "step": 21508 }, { "epoch": 0.6569639584605986, "grad_norm": 0.43768227100372314, "learning_rate": 1.3165658265470742e-05, "loss": 4.3066, "step": 21509 }, { "epoch": 0.6569945021380574, "grad_norm": 0.45148083567619324, "learning_rate": 1.3163545225341828e-05, "loss": 4.2582, "step": 21510 }, { "epoch": 0.6570250458155162, "grad_norm": 0.4387325644493103, "learning_rate": 1.3161432294197246e-05, "loss": 4.2478, "step": 21511 }, { "epoch": 0.6570555894929749, "grad_norm": 0.4435369670391083, "learning_rate": 1.3159319472056442e-05, "loss": 4.3294, "step": 21512 }, { "epoch": 0.6570861331704337, "grad_norm": 0.4445756673812866, "learning_rate": 1.3157206758938868e-05, "loss": 4.264, "step": 21513 }, { "epoch": 0.6571166768478924, "grad_norm": 0.4351990818977356, "learning_rate": 1.3155094154863983e-05, "loss": 4.2839, "step": 21514 }, { "epoch": 0.6571472205253512, "grad_norm": 0.4343978464603424, "learning_rate": 1.3152981659851226e-05, "loss": 4.2976, "step": 21515 }, { "epoch": 0.65717776420281, "grad_norm": 0.44549036026000977, "learning_rate": 1.3150869273920064e-05, "loss": 4.3091, "step": 21516 }, { "epoch": 0.6572083078802687, "grad_norm": 0.44303861260414124, "learning_rate": 1.3148756997089948e-05, "loss": 4.278, "step": 21517 }, { "epoch": 0.6572388515577275, "grad_norm": 0.44187217950820923, "learning_rate": 1.3146644829380309e-05, "loss": 4.3025, "step": 21518 }, { "epoch": 0.6572693952351863, "grad_norm": 0.44904476404190063, "learning_rate": 1.3144532770810607e-05, "loss": 4.2037, "step": 21519 }, { "epoch": 0.657299938912645, "grad_norm": 0.4445706009864807, "learning_rate": 1.3142420821400295e-05, "loss": 4.1796, "step": 21520 }, { "epoch": 0.6573304825901038, "grad_norm": 0.4496091604232788, "learning_rate": 1.3140308981168802e-05, "loss": 4.253, "step": 21521 }, { "epoch": 0.6573610262675627, "grad_norm": 0.43979015946388245, "learning_rate": 1.3138197250135581e-05, "loss": 4.2453, "step": 21522 }, { "epoch": 0.6573915699450213, "grad_norm": 0.436181902885437, "learning_rate": 1.3136085628320089e-05, "loss": 4.2793, "step": 21523 }, { "epoch": 0.6574221136224802, "grad_norm": 0.43921083211898804, "learning_rate": 1.3133974115741745e-05, "loss": 4.3276, "step": 21524 }, { "epoch": 0.657452657299939, "grad_norm": 0.4423568546772003, "learning_rate": 1.3131862712420001e-05, "loss": 4.3068, "step": 21525 }, { "epoch": 0.6574832009773977, "grad_norm": 0.44681957364082336, "learning_rate": 1.3129751418374315e-05, "loss": 4.3223, "step": 21526 }, { "epoch": 0.6575137446548565, "grad_norm": 0.45015159249305725, "learning_rate": 1.3127640233624103e-05, "loss": 4.3316, "step": 21527 }, { "epoch": 0.6575442883323153, "grad_norm": 0.44556140899658203, "learning_rate": 1.3125529158188805e-05, "loss": 4.2368, "step": 21528 }, { "epoch": 0.657574832009774, "grad_norm": 0.43351390957832336, "learning_rate": 1.3123418192087875e-05, "loss": 4.2445, "step": 21529 }, { "epoch": 0.6576053756872328, "grad_norm": 0.44336894154548645, "learning_rate": 1.312130733534073e-05, "loss": 4.2022, "step": 21530 }, { "epoch": 0.6576359193646915, "grad_norm": 0.45140859484672546, "learning_rate": 1.3119196587966825e-05, "loss": 4.2739, "step": 21531 }, { "epoch": 0.6576664630421503, "grad_norm": 0.44101306796073914, "learning_rate": 1.3117085949985578e-05, "loss": 4.2411, "step": 21532 }, { "epoch": 0.6576970067196091, "grad_norm": 0.4360206425189972, "learning_rate": 1.3114975421416429e-05, "loss": 4.2845, "step": 21533 }, { "epoch": 0.6577275503970678, "grad_norm": 0.43377792835235596, "learning_rate": 1.311286500227882e-05, "loss": 4.2215, "step": 21534 }, { "epoch": 0.6577580940745266, "grad_norm": 0.4240417182445526, "learning_rate": 1.3110754692592167e-05, "loss": 4.2784, "step": 21535 }, { "epoch": 0.6577886377519854, "grad_norm": 0.4306793808937073, "learning_rate": 1.3108644492375907e-05, "loss": 4.1554, "step": 21536 }, { "epoch": 0.6578191814294441, "grad_norm": 0.431745320558548, "learning_rate": 1.3106534401649483e-05, "loss": 4.3012, "step": 21537 }, { "epoch": 0.6578497251069029, "grad_norm": 0.4330848157405853, "learning_rate": 1.3104424420432298e-05, "loss": 4.2216, "step": 21538 }, { "epoch": 0.6578802687843617, "grad_norm": 0.4457254111766815, "learning_rate": 1.31023145487438e-05, "loss": 4.2416, "step": 21539 }, { "epoch": 0.6579108124618204, "grad_norm": 0.44033902883529663, "learning_rate": 1.3100204786603412e-05, "loss": 4.2836, "step": 21540 }, { "epoch": 0.6579413561392792, "grad_norm": 0.44363918900489807, "learning_rate": 1.3098095134030552e-05, "loss": 4.2713, "step": 21541 }, { "epoch": 0.657971899816738, "grad_norm": 0.43724524974823, "learning_rate": 1.3095985591044658e-05, "loss": 4.2984, "step": 21542 }, { "epoch": 0.6580024434941967, "grad_norm": 0.43922269344329834, "learning_rate": 1.309387615766513e-05, "loss": 4.2282, "step": 21543 }, { "epoch": 0.6580329871716555, "grad_norm": 0.44660520553588867, "learning_rate": 1.3091766833911424e-05, "loss": 4.2731, "step": 21544 }, { "epoch": 0.6580635308491143, "grad_norm": 0.43506646156311035, "learning_rate": 1.3089657619802929e-05, "loss": 4.2311, "step": 21545 }, { "epoch": 0.658094074526573, "grad_norm": 0.4395938515663147, "learning_rate": 1.3087548515359088e-05, "loss": 4.2204, "step": 21546 }, { "epoch": 0.6581246182040318, "grad_norm": 0.4474462568759918, "learning_rate": 1.3085439520599307e-05, "loss": 4.2633, "step": 21547 }, { "epoch": 0.6581551618814905, "grad_norm": 0.43301454186439514, "learning_rate": 1.3083330635543018e-05, "loss": 4.2596, "step": 21548 }, { "epoch": 0.6581857055589493, "grad_norm": 0.4411955177783966, "learning_rate": 1.3081221860209619e-05, "loss": 4.2906, "step": 21549 }, { "epoch": 0.6582162492364081, "grad_norm": 0.44460391998291016, "learning_rate": 1.3079113194618542e-05, "loss": 4.3424, "step": 21550 }, { "epoch": 0.6582467929138668, "grad_norm": 0.4421364963054657, "learning_rate": 1.3077004638789209e-05, "loss": 4.2293, "step": 21551 }, { "epoch": 0.6582773365913256, "grad_norm": 0.43193796277046204, "learning_rate": 1.307489619274101e-05, "loss": 4.2885, "step": 21552 }, { "epoch": 0.6583078802687844, "grad_norm": 0.4397016167640686, "learning_rate": 1.307278785649338e-05, "loss": 4.3088, "step": 21553 }, { "epoch": 0.6583384239462431, "grad_norm": 0.4379785656929016, "learning_rate": 1.307067963006573e-05, "loss": 4.2301, "step": 21554 }, { "epoch": 0.6583689676237019, "grad_norm": 0.44674476981163025, "learning_rate": 1.3068571513477457e-05, "loss": 4.2892, "step": 21555 }, { "epoch": 0.6583995113011607, "grad_norm": 0.44192731380462646, "learning_rate": 1.3066463506747977e-05, "loss": 4.2345, "step": 21556 }, { "epoch": 0.6584300549786194, "grad_norm": 0.43366536498069763, "learning_rate": 1.3064355609896717e-05, "loss": 4.2866, "step": 21557 }, { "epoch": 0.6584605986560782, "grad_norm": 0.4338904619216919, "learning_rate": 1.306224782294307e-05, "loss": 4.293, "step": 21558 }, { "epoch": 0.658491142333537, "grad_norm": 0.44930723309516907, "learning_rate": 1.3060140145906436e-05, "loss": 4.1846, "step": 21559 }, { "epoch": 0.6585216860109957, "grad_norm": 0.43671098351478577, "learning_rate": 1.305803257880624e-05, "loss": 4.2684, "step": 21560 }, { "epoch": 0.6585522296884545, "grad_norm": 0.4394223690032959, "learning_rate": 1.3055925121661871e-05, "loss": 4.1983, "step": 21561 }, { "epoch": 0.6585827733659133, "grad_norm": 0.4366568922996521, "learning_rate": 1.3053817774492737e-05, "loss": 4.2696, "step": 21562 }, { "epoch": 0.658613317043372, "grad_norm": 0.44136691093444824, "learning_rate": 1.3051710537318257e-05, "loss": 4.2515, "step": 21563 }, { "epoch": 0.6586438607208308, "grad_norm": 0.4514155089855194, "learning_rate": 1.304960341015781e-05, "loss": 4.2532, "step": 21564 }, { "epoch": 0.6586744043982895, "grad_norm": 0.4404812753200531, "learning_rate": 1.3047496393030817e-05, "loss": 4.2229, "step": 21565 }, { "epoch": 0.6587049480757483, "grad_norm": 0.4375819265842438, "learning_rate": 1.3045389485956661e-05, "loss": 4.2278, "step": 21566 }, { "epoch": 0.6587354917532071, "grad_norm": 0.4437384307384491, "learning_rate": 1.3043282688954753e-05, "loss": 4.3383, "step": 21567 }, { "epoch": 0.6587660354306658, "grad_norm": 0.4237575829029083, "learning_rate": 1.3041176002044498e-05, "loss": 4.1662, "step": 21568 }, { "epoch": 0.6587965791081246, "grad_norm": 0.43125608563423157, "learning_rate": 1.303906942524527e-05, "loss": 4.3144, "step": 21569 }, { "epoch": 0.6588271227855834, "grad_norm": 0.4322090148925781, "learning_rate": 1.3036962958576487e-05, "loss": 4.2584, "step": 21570 }, { "epoch": 0.6588576664630421, "grad_norm": 0.4287354350090027, "learning_rate": 1.303485660205754e-05, "loss": 4.256, "step": 21571 }, { "epoch": 0.6588882101405009, "grad_norm": 0.8098154664039612, "learning_rate": 1.3032750355707812e-05, "loss": 4.2244, "step": 21572 }, { "epoch": 0.6589187538179597, "grad_norm": 0.4343084394931793, "learning_rate": 1.3030644219546717e-05, "loss": 4.2092, "step": 21573 }, { "epoch": 0.6589492974954184, "grad_norm": 0.4406672716140747, "learning_rate": 1.3028538193593623e-05, "loss": 4.304, "step": 21574 }, { "epoch": 0.6589798411728772, "grad_norm": 0.42995449900627136, "learning_rate": 1.3026432277867942e-05, "loss": 4.306, "step": 21575 }, { "epoch": 0.659010384850336, "grad_norm": 0.4447319507598877, "learning_rate": 1.3024326472389048e-05, "loss": 4.1541, "step": 21576 }, { "epoch": 0.6590409285277947, "grad_norm": 0.4413328170776367, "learning_rate": 1.3022220777176345e-05, "loss": 4.2453, "step": 21577 }, { "epoch": 0.6590714722052535, "grad_norm": 0.4458414316177368, "learning_rate": 1.3020115192249205e-05, "loss": 4.2268, "step": 21578 }, { "epoch": 0.6591020158827123, "grad_norm": 0.4452706575393677, "learning_rate": 1.3018009717627022e-05, "loss": 4.2706, "step": 21579 }, { "epoch": 0.659132559560171, "grad_norm": 0.4446513056755066, "learning_rate": 1.3015904353329195e-05, "loss": 4.3102, "step": 21580 }, { "epoch": 0.6591631032376298, "grad_norm": 0.4494681656360626, "learning_rate": 1.301379909937509e-05, "loss": 4.3647, "step": 21581 }, { "epoch": 0.6591936469150885, "grad_norm": 0.437556654214859, "learning_rate": 1.3011693955784104e-05, "loss": 4.218, "step": 21582 }, { "epoch": 0.6592241905925473, "grad_norm": 0.43580591678619385, "learning_rate": 1.300958892257561e-05, "loss": 4.1507, "step": 21583 }, { "epoch": 0.6592547342700061, "grad_norm": 0.44466495513916016, "learning_rate": 1.3007483999768995e-05, "loss": 4.2369, "step": 21584 }, { "epoch": 0.6592852779474648, "grad_norm": 0.43800103664398193, "learning_rate": 1.3005379187383651e-05, "loss": 4.2136, "step": 21585 }, { "epoch": 0.6593158216249236, "grad_norm": 0.42968010902404785, "learning_rate": 1.3003274485438938e-05, "loss": 4.2569, "step": 21586 }, { "epoch": 0.6593463653023824, "grad_norm": 0.4435257911682129, "learning_rate": 1.3001169893954246e-05, "loss": 4.3202, "step": 21587 }, { "epoch": 0.6593769089798411, "grad_norm": 0.4407442510128021, "learning_rate": 1.2999065412948958e-05, "loss": 4.2919, "step": 21588 }, { "epoch": 0.6594074526572999, "grad_norm": 0.43190622329711914, "learning_rate": 1.299696104244244e-05, "loss": 4.3133, "step": 21589 }, { "epoch": 0.6594379963347587, "grad_norm": 0.44024863839149475, "learning_rate": 1.2994856782454079e-05, "loss": 4.3034, "step": 21590 }, { "epoch": 0.6594685400122174, "grad_norm": 0.4374716281890869, "learning_rate": 1.2992752633003247e-05, "loss": 4.2233, "step": 21591 }, { "epoch": 0.6594990836896762, "grad_norm": 0.44306281208992004, "learning_rate": 1.29906485941093e-05, "loss": 4.3112, "step": 21592 }, { "epoch": 0.659529627367135, "grad_norm": 0.4350774884223938, "learning_rate": 1.298854466579163e-05, "loss": 4.3164, "step": 21593 }, { "epoch": 0.6595601710445937, "grad_norm": 0.4406251013278961, "learning_rate": 1.2986440848069615e-05, "loss": 4.2799, "step": 21594 }, { "epoch": 0.6595907147220526, "grad_norm": 0.4422287344932556, "learning_rate": 1.2984337140962605e-05, "loss": 4.312, "step": 21595 }, { "epoch": 0.6596212583995114, "grad_norm": 0.43944358825683594, "learning_rate": 1.2982233544489983e-05, "loss": 4.2667, "step": 21596 }, { "epoch": 0.65965180207697, "grad_norm": 0.4425075352191925, "learning_rate": 1.2980130058671125e-05, "loss": 4.2754, "step": 21597 }, { "epoch": 0.6596823457544289, "grad_norm": 0.43573275208473206, "learning_rate": 1.2978026683525376e-05, "loss": 4.2313, "step": 21598 }, { "epoch": 0.6597128894318876, "grad_norm": 0.4279424846172333, "learning_rate": 1.2975923419072127e-05, "loss": 4.2451, "step": 21599 }, { "epoch": 0.6597434331093464, "grad_norm": 0.44067317247390747, "learning_rate": 1.2973820265330727e-05, "loss": 4.3017, "step": 21600 }, { "epoch": 0.6597739767868052, "grad_norm": 0.4536212980747223, "learning_rate": 1.2971717222320546e-05, "loss": 4.2485, "step": 21601 }, { "epoch": 0.6598045204642639, "grad_norm": 0.43738263845443726, "learning_rate": 1.2969614290060958e-05, "loss": 4.3328, "step": 21602 }, { "epoch": 0.6598350641417227, "grad_norm": 0.4403706192970276, "learning_rate": 1.2967511468571309e-05, "loss": 4.2353, "step": 21603 }, { "epoch": 0.6598656078191815, "grad_norm": 0.4471595883369446, "learning_rate": 1.2965408757870973e-05, "loss": 4.2863, "step": 21604 }, { "epoch": 0.6598961514966402, "grad_norm": 0.45200562477111816, "learning_rate": 1.29633061579793e-05, "loss": 4.161, "step": 21605 }, { "epoch": 0.659926695174099, "grad_norm": 0.448567271232605, "learning_rate": 1.2961203668915664e-05, "loss": 4.2819, "step": 21606 }, { "epoch": 0.6599572388515578, "grad_norm": 0.43564584851264954, "learning_rate": 1.2959101290699407e-05, "loss": 4.2208, "step": 21607 }, { "epoch": 0.6599877825290165, "grad_norm": 0.4435165822505951, "learning_rate": 1.2956999023349904e-05, "loss": 4.232, "step": 21608 }, { "epoch": 0.6600183262064753, "grad_norm": 0.4432889521121979, "learning_rate": 1.2954896866886496e-05, "loss": 4.3224, "step": 21609 }, { "epoch": 0.6600488698839341, "grad_norm": 0.43836385011672974, "learning_rate": 1.2952794821328539e-05, "loss": 4.3011, "step": 21610 }, { "epoch": 0.6600794135613928, "grad_norm": 0.44654542207717896, "learning_rate": 1.2950692886695408e-05, "loss": 4.275, "step": 21611 }, { "epoch": 0.6601099572388516, "grad_norm": 0.4404127895832062, "learning_rate": 1.2948591063006438e-05, "loss": 4.3826, "step": 21612 }, { "epoch": 0.6601405009163103, "grad_norm": 0.4418918192386627, "learning_rate": 1.2946489350280987e-05, "loss": 4.3112, "step": 21613 }, { "epoch": 0.6601710445937691, "grad_norm": 0.447587251663208, "learning_rate": 1.2944387748538403e-05, "loss": 4.1929, "step": 21614 }, { "epoch": 0.6602015882712279, "grad_norm": 0.4425387382507324, "learning_rate": 1.2942286257798037e-05, "loss": 4.2256, "step": 21615 }, { "epoch": 0.6602321319486866, "grad_norm": 0.43076080083847046, "learning_rate": 1.2940184878079247e-05, "loss": 4.1608, "step": 21616 }, { "epoch": 0.6602626756261454, "grad_norm": 0.437343567609787, "learning_rate": 1.2938083609401372e-05, "loss": 4.2174, "step": 21617 }, { "epoch": 0.6602932193036042, "grad_norm": 0.4484369456768036, "learning_rate": 1.2935982451783759e-05, "loss": 4.3382, "step": 21618 }, { "epoch": 0.6603237629810629, "grad_norm": 0.4527128338813782, "learning_rate": 1.2933881405245768e-05, "loss": 4.3969, "step": 21619 }, { "epoch": 0.6603543066585217, "grad_norm": 0.447205126285553, "learning_rate": 1.2931780469806725e-05, "loss": 4.2486, "step": 21620 }, { "epoch": 0.6603848503359805, "grad_norm": 0.43976616859436035, "learning_rate": 1.2929679645485998e-05, "loss": 4.3065, "step": 21621 }, { "epoch": 0.6604153940134392, "grad_norm": 0.4348383843898773, "learning_rate": 1.2927578932302912e-05, "loss": 4.2254, "step": 21622 }, { "epoch": 0.660445937690898, "grad_norm": 0.4405447542667389, "learning_rate": 1.2925478330276805e-05, "loss": 4.2489, "step": 21623 }, { "epoch": 0.6604764813683568, "grad_norm": 0.4431120753288269, "learning_rate": 1.2923377839427026e-05, "loss": 4.2108, "step": 21624 }, { "epoch": 0.6605070250458155, "grad_norm": 0.433765709400177, "learning_rate": 1.292127745977293e-05, "loss": 4.3219, "step": 21625 }, { "epoch": 0.6605375687232743, "grad_norm": 0.44339361786842346, "learning_rate": 1.2919177191333828e-05, "loss": 4.2408, "step": 21626 }, { "epoch": 0.6605681124007331, "grad_norm": 0.43268653750419617, "learning_rate": 1.2917077034129078e-05, "loss": 4.3209, "step": 21627 }, { "epoch": 0.6605986560781918, "grad_norm": 0.44680920243263245, "learning_rate": 1.2914976988178018e-05, "loss": 4.2617, "step": 21628 }, { "epoch": 0.6606291997556506, "grad_norm": 0.4449014663696289, "learning_rate": 1.291287705349997e-05, "loss": 4.3712, "step": 21629 }, { "epoch": 0.6606597434331093, "grad_norm": 0.43603140115737915, "learning_rate": 1.2910777230114285e-05, "loss": 4.243, "step": 21630 }, { "epoch": 0.6606902871105681, "grad_norm": 0.44921210408210754, "learning_rate": 1.2908677518040283e-05, "loss": 4.2933, "step": 21631 }, { "epoch": 0.6607208307880269, "grad_norm": 0.4443557858467102, "learning_rate": 1.2906577917297301e-05, "loss": 4.286, "step": 21632 }, { "epoch": 0.6607513744654856, "grad_norm": 0.4323692321777344, "learning_rate": 1.2904478427904687e-05, "loss": 4.1949, "step": 21633 }, { "epoch": 0.6607819181429444, "grad_norm": 0.44173938035964966, "learning_rate": 1.2902379049881746e-05, "loss": 4.324, "step": 21634 }, { "epoch": 0.6608124618204032, "grad_norm": 0.43767231702804565, "learning_rate": 1.2900279783247826e-05, "loss": 4.2958, "step": 21635 }, { "epoch": 0.6608430054978619, "grad_norm": 0.4453837275505066, "learning_rate": 1.2898180628022258e-05, "loss": 4.2684, "step": 21636 }, { "epoch": 0.6608735491753207, "grad_norm": 0.44136252999305725, "learning_rate": 1.2896081584224361e-05, "loss": 4.256, "step": 21637 }, { "epoch": 0.6609040928527795, "grad_norm": 0.4373026192188263, "learning_rate": 1.2893982651873457e-05, "loss": 4.3113, "step": 21638 }, { "epoch": 0.6609346365302382, "grad_norm": 0.4464661478996277, "learning_rate": 1.2891883830988887e-05, "loss": 4.1643, "step": 21639 }, { "epoch": 0.660965180207697, "grad_norm": 0.4466699957847595, "learning_rate": 1.2889785121589959e-05, "loss": 4.2439, "step": 21640 }, { "epoch": 0.6609957238851558, "grad_norm": 0.4439840316772461, "learning_rate": 1.2887686523696008e-05, "loss": 4.2545, "step": 21641 }, { "epoch": 0.6610262675626145, "grad_norm": 0.42567846179008484, "learning_rate": 1.2885588037326363e-05, "loss": 4.2257, "step": 21642 }, { "epoch": 0.6610568112400733, "grad_norm": 0.43592092394828796, "learning_rate": 1.2883489662500326e-05, "loss": 4.2771, "step": 21643 }, { "epoch": 0.6610873549175321, "grad_norm": 0.44099289178848267, "learning_rate": 1.288139139923723e-05, "loss": 4.1729, "step": 21644 }, { "epoch": 0.6611178985949908, "grad_norm": 0.44660472869873047, "learning_rate": 1.2879293247556407e-05, "loss": 4.2899, "step": 21645 }, { "epoch": 0.6611484422724496, "grad_norm": 0.44161078333854675, "learning_rate": 1.287719520747715e-05, "loss": 4.2508, "step": 21646 }, { "epoch": 0.6611789859499083, "grad_norm": 0.4438224136829376, "learning_rate": 1.2875097279018799e-05, "loss": 4.3398, "step": 21647 }, { "epoch": 0.6612095296273671, "grad_norm": 0.4564880430698395, "learning_rate": 1.2872999462200652e-05, "loss": 4.2917, "step": 21648 }, { "epoch": 0.6612400733048259, "grad_norm": 0.43954113125801086, "learning_rate": 1.2870901757042036e-05, "loss": 4.2764, "step": 21649 }, { "epoch": 0.6612706169822846, "grad_norm": 0.44647952914237976, "learning_rate": 1.2868804163562271e-05, "loss": 4.2611, "step": 21650 }, { "epoch": 0.6613011606597434, "grad_norm": 0.4449508488178253, "learning_rate": 1.2866706681780654e-05, "loss": 4.2151, "step": 21651 }, { "epoch": 0.6613317043372022, "grad_norm": 0.4321031868457794, "learning_rate": 1.2864609311716519e-05, "loss": 4.3498, "step": 21652 }, { "epoch": 0.6613622480146609, "grad_norm": 0.4368959665298462, "learning_rate": 1.2862512053389153e-05, "loss": 4.1972, "step": 21653 }, { "epoch": 0.6613927916921197, "grad_norm": 0.44362953305244446, "learning_rate": 1.2860414906817891e-05, "loss": 4.3008, "step": 21654 }, { "epoch": 0.6614233353695785, "grad_norm": 0.4382346570491791, "learning_rate": 1.2858317872022018e-05, "loss": 4.1507, "step": 21655 }, { "epoch": 0.6614538790470372, "grad_norm": 0.43413418531417847, "learning_rate": 1.285622094902087e-05, "loss": 4.285, "step": 21656 }, { "epoch": 0.661484422724496, "grad_norm": 0.4443778693675995, "learning_rate": 1.2854124137833723e-05, "loss": 4.2672, "step": 21657 }, { "epoch": 0.6615149664019548, "grad_norm": 0.4448404014110565, "learning_rate": 1.2852027438479902e-05, "loss": 4.2976, "step": 21658 }, { "epoch": 0.6615455100794135, "grad_norm": 0.437092661857605, "learning_rate": 1.2849930850978722e-05, "loss": 4.2637, "step": 21659 }, { "epoch": 0.6615760537568723, "grad_norm": 0.43822774291038513, "learning_rate": 1.2847834375349466e-05, "loss": 4.2387, "step": 21660 }, { "epoch": 0.6616065974343311, "grad_norm": 0.4472495913505554, "learning_rate": 1.2845738011611446e-05, "loss": 4.2634, "step": 21661 }, { "epoch": 0.6616371411117898, "grad_norm": 0.46607303619384766, "learning_rate": 1.2843641759783975e-05, "loss": 4.2207, "step": 21662 }, { "epoch": 0.6616676847892486, "grad_norm": 0.43357670307159424, "learning_rate": 1.2841545619886333e-05, "loss": 4.2728, "step": 21663 }, { "epoch": 0.6616982284667073, "grad_norm": 0.4297065734863281, "learning_rate": 1.283944959193784e-05, "loss": 4.2063, "step": 21664 }, { "epoch": 0.6617287721441661, "grad_norm": 0.43700680136680603, "learning_rate": 1.2837353675957784e-05, "loss": 4.2498, "step": 21665 }, { "epoch": 0.661759315821625, "grad_norm": 0.4606853127479553, "learning_rate": 1.2835257871965462e-05, "loss": 4.2315, "step": 21666 }, { "epoch": 0.6617898594990836, "grad_norm": 0.4384194612503052, "learning_rate": 1.2833162179980185e-05, "loss": 4.2164, "step": 21667 }, { "epoch": 0.6618204031765424, "grad_norm": 0.4372156858444214, "learning_rate": 1.2831066600021242e-05, "loss": 4.2823, "step": 21668 }, { "epoch": 0.6618509468540013, "grad_norm": 0.43829888105392456, "learning_rate": 1.2828971132107908e-05, "loss": 4.0532, "step": 21669 }, { "epoch": 0.66188149053146, "grad_norm": 0.45636239647865295, "learning_rate": 1.2826875776259512e-05, "loss": 4.319, "step": 21670 }, { "epoch": 0.6619120342089188, "grad_norm": 0.43931615352630615, "learning_rate": 1.2824780532495317e-05, "loss": 4.2835, "step": 21671 }, { "epoch": 0.6619425778863776, "grad_norm": 0.4423951804637909, "learning_rate": 1.2822685400834628e-05, "loss": 4.2095, "step": 21672 }, { "epoch": 0.6619731215638363, "grad_norm": 0.4885840117931366, "learning_rate": 1.2820590381296743e-05, "loss": 4.2397, "step": 21673 }, { "epoch": 0.6620036652412951, "grad_norm": 0.4453308880329132, "learning_rate": 1.2818495473900938e-05, "loss": 4.3226, "step": 21674 }, { "epoch": 0.6620342089187539, "grad_norm": 0.4470888376235962, "learning_rate": 1.2816400678666507e-05, "loss": 4.1519, "step": 21675 }, { "epoch": 0.6620647525962126, "grad_norm": 0.439513236284256, "learning_rate": 1.2814305995612749e-05, "loss": 4.1857, "step": 21676 }, { "epoch": 0.6620952962736714, "grad_norm": 0.44344109296798706, "learning_rate": 1.2812211424758933e-05, "loss": 4.2139, "step": 21677 }, { "epoch": 0.6621258399511302, "grad_norm": 0.4470707178115845, "learning_rate": 1.281011696612435e-05, "loss": 4.3141, "step": 21678 }, { "epoch": 0.6621563836285889, "grad_norm": 0.4542614817619324, "learning_rate": 1.28080226197283e-05, "loss": 4.3205, "step": 21679 }, { "epoch": 0.6621869273060477, "grad_norm": 0.4463619291782379, "learning_rate": 1.280592838559004e-05, "loss": 4.302, "step": 21680 }, { "epoch": 0.6622174709835064, "grad_norm": 0.4339683949947357, "learning_rate": 1.280383426372888e-05, "loss": 4.2365, "step": 21681 }, { "epoch": 0.6622480146609652, "grad_norm": 0.42752790451049805, "learning_rate": 1.280174025416408e-05, "loss": 4.2458, "step": 21682 }, { "epoch": 0.662278558338424, "grad_norm": 0.44504985213279724, "learning_rate": 1.2799646356914935e-05, "loss": 4.2718, "step": 21683 }, { "epoch": 0.6623091020158827, "grad_norm": 0.4483395516872406, "learning_rate": 1.279755257200071e-05, "loss": 4.2699, "step": 21684 }, { "epoch": 0.6623396456933415, "grad_norm": 0.4386056065559387, "learning_rate": 1.2795458899440705e-05, "loss": 4.3028, "step": 21685 }, { "epoch": 0.6623701893708003, "grad_norm": 0.44422271847724915, "learning_rate": 1.279336533925417e-05, "loss": 4.2019, "step": 21686 }, { "epoch": 0.662400733048259, "grad_norm": 0.4300565719604492, "learning_rate": 1.279127189146041e-05, "loss": 4.2465, "step": 21687 }, { "epoch": 0.6624312767257178, "grad_norm": 0.4308333694934845, "learning_rate": 1.278917855607868e-05, "loss": 4.2288, "step": 21688 }, { "epoch": 0.6624618204031766, "grad_norm": 0.5057281851768494, "learning_rate": 1.2787085333128257e-05, "loss": 4.2773, "step": 21689 }, { "epoch": 0.6624923640806353, "grad_norm": 0.44414252042770386, "learning_rate": 1.2784992222628428e-05, "loss": 4.2204, "step": 21690 }, { "epoch": 0.6625229077580941, "grad_norm": 0.4442189037799835, "learning_rate": 1.278289922459845e-05, "loss": 4.2512, "step": 21691 }, { "epoch": 0.6625534514355529, "grad_norm": 0.4539809226989746, "learning_rate": 1.2780806339057593e-05, "loss": 4.2569, "step": 21692 }, { "epoch": 0.6625839951130116, "grad_norm": 0.4576911926269531, "learning_rate": 1.2778713566025151e-05, "loss": 4.3106, "step": 21693 }, { "epoch": 0.6626145387904704, "grad_norm": 0.4258063733577728, "learning_rate": 1.2776620905520364e-05, "loss": 4.2318, "step": 21694 }, { "epoch": 0.6626450824679292, "grad_norm": 0.4482001066207886, "learning_rate": 1.2774528357562515e-05, "loss": 4.2793, "step": 21695 }, { "epoch": 0.6626756261453879, "grad_norm": 0.4341863989830017, "learning_rate": 1.2772435922170877e-05, "loss": 4.2764, "step": 21696 }, { "epoch": 0.6627061698228467, "grad_norm": 0.435666024684906, "learning_rate": 1.2770343599364697e-05, "loss": 4.2273, "step": 21697 }, { "epoch": 0.6627367135003054, "grad_norm": 0.43561139702796936, "learning_rate": 1.2768251389163266e-05, "loss": 4.2321, "step": 21698 }, { "epoch": 0.6627672571777642, "grad_norm": 0.4411951005458832, "learning_rate": 1.2766159291585821e-05, "loss": 4.2717, "step": 21699 }, { "epoch": 0.662797800855223, "grad_norm": 0.4480993449687958, "learning_rate": 1.2764067306651645e-05, "loss": 4.2211, "step": 21700 }, { "epoch": 0.6628283445326817, "grad_norm": 0.44726112484931946, "learning_rate": 1.2761975434379997e-05, "loss": 4.2459, "step": 21701 }, { "epoch": 0.6628588882101405, "grad_norm": 0.4437250792980194, "learning_rate": 1.2759883674790119e-05, "loss": 4.2907, "step": 21702 }, { "epoch": 0.6628894318875993, "grad_norm": 0.43527501821517944, "learning_rate": 1.2757792027901289e-05, "loss": 4.3471, "step": 21703 }, { "epoch": 0.662919975565058, "grad_norm": 0.4395018219947815, "learning_rate": 1.275570049373277e-05, "loss": 4.3368, "step": 21704 }, { "epoch": 0.6629505192425168, "grad_norm": 0.4305398762226105, "learning_rate": 1.2753609072303802e-05, "loss": 4.2412, "step": 21705 }, { "epoch": 0.6629810629199756, "grad_norm": 0.43797367811203003, "learning_rate": 1.2751517763633653e-05, "loss": 4.2439, "step": 21706 }, { "epoch": 0.6630116065974343, "grad_norm": 0.4431800842285156, "learning_rate": 1.2749426567741585e-05, "loss": 4.3011, "step": 21707 }, { "epoch": 0.6630421502748931, "grad_norm": 0.4361172616481781, "learning_rate": 1.2747335484646838e-05, "loss": 4.2517, "step": 21708 }, { "epoch": 0.6630726939523519, "grad_norm": 0.4450550079345703, "learning_rate": 1.274524451436867e-05, "loss": 4.243, "step": 21709 }, { "epoch": 0.6631032376298106, "grad_norm": 0.43700528144836426, "learning_rate": 1.2743153656926348e-05, "loss": 4.2505, "step": 21710 }, { "epoch": 0.6631337813072694, "grad_norm": 0.4446488618850708, "learning_rate": 1.2741062912339103e-05, "loss": 4.3016, "step": 21711 }, { "epoch": 0.6631643249847282, "grad_norm": 0.43927979469299316, "learning_rate": 1.2738972280626194e-05, "loss": 4.3566, "step": 21712 }, { "epoch": 0.6631948686621869, "grad_norm": 0.43154484033584595, "learning_rate": 1.2736881761806879e-05, "loss": 4.2426, "step": 21713 }, { "epoch": 0.6632254123396457, "grad_norm": 0.43993350863456726, "learning_rate": 1.2734791355900402e-05, "loss": 4.2362, "step": 21714 }, { "epoch": 0.6632559560171044, "grad_norm": 0.43783414363861084, "learning_rate": 1.2732701062925995e-05, "loss": 4.2565, "step": 21715 }, { "epoch": 0.6632864996945632, "grad_norm": 0.44309312105178833, "learning_rate": 1.2730610882902926e-05, "loss": 4.295, "step": 21716 }, { "epoch": 0.663317043372022, "grad_norm": 0.4459110200405121, "learning_rate": 1.2728520815850425e-05, "loss": 4.2139, "step": 21717 }, { "epoch": 0.6633475870494807, "grad_norm": 0.4429893493652344, "learning_rate": 1.2726430861787749e-05, "loss": 4.2395, "step": 21718 }, { "epoch": 0.6633781307269395, "grad_norm": 0.4438059628009796, "learning_rate": 1.2724341020734126e-05, "loss": 4.3041, "step": 21719 }, { "epoch": 0.6634086744043983, "grad_norm": 0.438997745513916, "learning_rate": 1.2722251292708806e-05, "loss": 4.3026, "step": 21720 }, { "epoch": 0.663439218081857, "grad_norm": 0.4368843734264374, "learning_rate": 1.272016167773104e-05, "loss": 4.1885, "step": 21721 }, { "epoch": 0.6634697617593158, "grad_norm": 0.4500848650932312, "learning_rate": 1.271807217582005e-05, "loss": 4.2667, "step": 21722 }, { "epoch": 0.6635003054367746, "grad_norm": 0.4489595890045166, "learning_rate": 1.2715982786995085e-05, "loss": 4.1472, "step": 21723 }, { "epoch": 0.6635308491142333, "grad_norm": 0.44551709294319153, "learning_rate": 1.271389351127539e-05, "loss": 4.2666, "step": 21724 }, { "epoch": 0.6635613927916921, "grad_norm": 0.44315484166145325, "learning_rate": 1.2711804348680186e-05, "loss": 4.2602, "step": 21725 }, { "epoch": 0.6635919364691509, "grad_norm": 0.43806731700897217, "learning_rate": 1.270971529922872e-05, "loss": 4.2798, "step": 21726 }, { "epoch": 0.6636224801466096, "grad_norm": 0.4439290165901184, "learning_rate": 1.2707626362940228e-05, "loss": 4.327, "step": 21727 }, { "epoch": 0.6636530238240684, "grad_norm": 0.4435403347015381, "learning_rate": 1.2705537539833933e-05, "loss": 4.2488, "step": 21728 }, { "epoch": 0.6636835675015272, "grad_norm": 0.4487079381942749, "learning_rate": 1.2703448829929088e-05, "loss": 4.2709, "step": 21729 }, { "epoch": 0.6637141111789859, "grad_norm": 0.44010061025619507, "learning_rate": 1.2701360233244897e-05, "loss": 4.2227, "step": 21730 }, { "epoch": 0.6637446548564447, "grad_norm": 0.4488498270511627, "learning_rate": 1.2699271749800617e-05, "loss": 4.1967, "step": 21731 }, { "epoch": 0.6637751985339034, "grad_norm": 0.44138509035110474, "learning_rate": 1.2697183379615469e-05, "loss": 4.4099, "step": 21732 }, { "epoch": 0.6638057422113622, "grad_norm": 0.4375784993171692, "learning_rate": 1.2695095122708666e-05, "loss": 4.2972, "step": 21733 }, { "epoch": 0.663836285888821, "grad_norm": 0.4325626790523529, "learning_rate": 1.2693006979099453e-05, "loss": 4.2939, "step": 21734 }, { "epoch": 0.6638668295662797, "grad_norm": 0.44192391633987427, "learning_rate": 1.269091894880706e-05, "loss": 4.2037, "step": 21735 }, { "epoch": 0.6638973732437385, "grad_norm": 0.4355240762233734, "learning_rate": 1.2688831031850695e-05, "loss": 4.2418, "step": 21736 }, { "epoch": 0.6639279169211973, "grad_norm": 0.4487077295780182, "learning_rate": 1.2686743228249593e-05, "loss": 4.224, "step": 21737 }, { "epoch": 0.663958460598656, "grad_norm": 0.4332866668701172, "learning_rate": 1.2684655538022986e-05, "loss": 4.3293, "step": 21738 }, { "epoch": 0.6639890042761148, "grad_norm": 0.443589985370636, "learning_rate": 1.2682567961190079e-05, "loss": 4.1627, "step": 21739 }, { "epoch": 0.6640195479535737, "grad_norm": 0.4432498812675476, "learning_rate": 1.2680480497770098e-05, "loss": 4.3193, "step": 21740 }, { "epoch": 0.6640500916310323, "grad_norm": 0.447287917137146, "learning_rate": 1.267839314778228e-05, "loss": 4.2788, "step": 21741 }, { "epoch": 0.6640806353084912, "grad_norm": 0.4447721838951111, "learning_rate": 1.267630591124582e-05, "loss": 4.2744, "step": 21742 }, { "epoch": 0.66411117898595, "grad_norm": 0.4485520124435425, "learning_rate": 1.2674218788179948e-05, "loss": 4.2791, "step": 21743 }, { "epoch": 0.6641417226634087, "grad_norm": 0.4495161771774292, "learning_rate": 1.2672131778603891e-05, "loss": 4.3467, "step": 21744 }, { "epoch": 0.6641722663408675, "grad_norm": 0.4498489499092102, "learning_rate": 1.2670044882536848e-05, "loss": 4.2394, "step": 21745 }, { "epoch": 0.6642028100183263, "grad_norm": 0.43748167157173157, "learning_rate": 1.2667958099998048e-05, "loss": 4.2821, "step": 21746 }, { "epoch": 0.664233353695785, "grad_norm": 0.44186675548553467, "learning_rate": 1.2665871431006699e-05, "loss": 4.2475, "step": 21747 }, { "epoch": 0.6642638973732438, "grad_norm": 0.4550088047981262, "learning_rate": 1.2663784875582001e-05, "loss": 4.3026, "step": 21748 }, { "epoch": 0.6642944410507025, "grad_norm": 0.4401456415653229, "learning_rate": 1.2661698433743191e-05, "loss": 4.1993, "step": 21749 }, { "epoch": 0.6643249847281613, "grad_norm": 0.43583568930625916, "learning_rate": 1.2659612105509457e-05, "loss": 4.3194, "step": 21750 }, { "epoch": 0.6643555284056201, "grad_norm": 0.43711209297180176, "learning_rate": 1.2657525890900018e-05, "loss": 4.2706, "step": 21751 }, { "epoch": 0.6643860720830788, "grad_norm": 0.4641270041465759, "learning_rate": 1.2655439789934098e-05, "loss": 4.3056, "step": 21752 }, { "epoch": 0.6644166157605376, "grad_norm": 0.4527159631252289, "learning_rate": 1.2653353802630877e-05, "loss": 4.2704, "step": 21753 }, { "epoch": 0.6644471594379964, "grad_norm": 0.43525364995002747, "learning_rate": 1.2651267929009575e-05, "loss": 4.2364, "step": 21754 }, { "epoch": 0.6644777031154551, "grad_norm": 0.4385095536708832, "learning_rate": 1.2649182169089411e-05, "loss": 4.1932, "step": 21755 }, { "epoch": 0.6645082467929139, "grad_norm": 0.44983193278312683, "learning_rate": 1.2647096522889564e-05, "loss": 4.3355, "step": 21756 }, { "epoch": 0.6645387904703727, "grad_norm": 0.4482821822166443, "learning_rate": 1.2645010990429255e-05, "loss": 4.3715, "step": 21757 }, { "epoch": 0.6645693341478314, "grad_norm": 0.4447920620441437, "learning_rate": 1.2642925571727687e-05, "loss": 4.262, "step": 21758 }, { "epoch": 0.6645998778252902, "grad_norm": 0.4439249038696289, "learning_rate": 1.2640840266804049e-05, "loss": 4.2915, "step": 21759 }, { "epoch": 0.664630421502749, "grad_norm": 0.4373268485069275, "learning_rate": 1.2638755075677561e-05, "loss": 4.2186, "step": 21760 }, { "epoch": 0.6646609651802077, "grad_norm": 0.4446796476840973, "learning_rate": 1.2636669998367398e-05, "loss": 4.2524, "step": 21761 }, { "epoch": 0.6646915088576665, "grad_norm": 0.4713890254497528, "learning_rate": 1.2634585034892782e-05, "loss": 4.2441, "step": 21762 }, { "epoch": 0.6647220525351252, "grad_norm": 0.43023109436035156, "learning_rate": 1.2632500185272889e-05, "loss": 4.1882, "step": 21763 }, { "epoch": 0.664752596212584, "grad_norm": 0.44639667868614197, "learning_rate": 1.2630415449526934e-05, "loss": 4.2322, "step": 21764 }, { "epoch": 0.6647831398900428, "grad_norm": 0.44325143098831177, "learning_rate": 1.2628330827674095e-05, "loss": 4.2663, "step": 21765 }, { "epoch": 0.6648136835675015, "grad_norm": 0.4415765404701233, "learning_rate": 1.2626246319733584e-05, "loss": 4.226, "step": 21766 }, { "epoch": 0.6648442272449603, "grad_norm": 0.43381360173225403, "learning_rate": 1.2624161925724577e-05, "loss": 4.1649, "step": 21767 }, { "epoch": 0.6648747709224191, "grad_norm": 0.4492894113063812, "learning_rate": 1.2622077645666274e-05, "loss": 4.3485, "step": 21768 }, { "epoch": 0.6649053145998778, "grad_norm": 0.44673120975494385, "learning_rate": 1.2619993479577875e-05, "loss": 4.3342, "step": 21769 }, { "epoch": 0.6649358582773366, "grad_norm": 0.4479658901691437, "learning_rate": 1.2617909427478553e-05, "loss": 4.2528, "step": 21770 }, { "epoch": 0.6649664019547954, "grad_norm": 0.4435429573059082, "learning_rate": 1.26158254893875e-05, "loss": 4.2862, "step": 21771 }, { "epoch": 0.6649969456322541, "grad_norm": 0.43100425601005554, "learning_rate": 1.2613741665323926e-05, "loss": 4.1781, "step": 21772 }, { "epoch": 0.6650274893097129, "grad_norm": 0.44290322065353394, "learning_rate": 1.2611657955306988e-05, "loss": 4.3081, "step": 21773 }, { "epoch": 0.6650580329871717, "grad_norm": 0.4420301616191864, "learning_rate": 1.2609574359355884e-05, "loss": 4.2359, "step": 21774 }, { "epoch": 0.6650885766646304, "grad_norm": 0.44054803252220154, "learning_rate": 1.2607490877489808e-05, "loss": 4.2063, "step": 21775 }, { "epoch": 0.6651191203420892, "grad_norm": 0.4403954744338989, "learning_rate": 1.260540750972793e-05, "loss": 4.2591, "step": 21776 }, { "epoch": 0.665149664019548, "grad_norm": 0.4385419189929962, "learning_rate": 1.2603324256089442e-05, "loss": 4.2643, "step": 21777 }, { "epoch": 0.6651802076970067, "grad_norm": 0.4396132230758667, "learning_rate": 1.2601241116593524e-05, "loss": 4.2718, "step": 21778 }, { "epoch": 0.6652107513744655, "grad_norm": 0.44708847999572754, "learning_rate": 1.2599158091259345e-05, "loss": 4.197, "step": 21779 }, { "epoch": 0.6652412950519242, "grad_norm": 0.4415383040904999, "learning_rate": 1.25970751801061e-05, "loss": 4.2913, "step": 21780 }, { "epoch": 0.665271838729383, "grad_norm": 0.4464470148086548, "learning_rate": 1.2594992383152954e-05, "loss": 4.2147, "step": 21781 }, { "epoch": 0.6653023824068418, "grad_norm": 0.44284552335739136, "learning_rate": 1.259290970041909e-05, "loss": 4.2882, "step": 21782 }, { "epoch": 0.6653329260843005, "grad_norm": 0.44214338064193726, "learning_rate": 1.2590827131923693e-05, "loss": 4.3601, "step": 21783 }, { "epoch": 0.6653634697617593, "grad_norm": 0.453935831785202, "learning_rate": 1.2588744677685927e-05, "loss": 4.2851, "step": 21784 }, { "epoch": 0.6653940134392181, "grad_norm": 0.4562552571296692, "learning_rate": 1.2586662337724964e-05, "loss": 4.3353, "step": 21785 }, { "epoch": 0.6654245571166768, "grad_norm": 0.439135879278183, "learning_rate": 1.2584580112059996e-05, "loss": 4.3538, "step": 21786 }, { "epoch": 0.6654551007941356, "grad_norm": 0.4461939334869385, "learning_rate": 1.2582498000710169e-05, "loss": 4.3256, "step": 21787 }, { "epoch": 0.6654856444715944, "grad_norm": 0.4379241168498993, "learning_rate": 1.2580416003694672e-05, "loss": 4.2443, "step": 21788 }, { "epoch": 0.6655161881490531, "grad_norm": 0.4432680904865265, "learning_rate": 1.2578334121032678e-05, "loss": 4.3368, "step": 21789 }, { "epoch": 0.6655467318265119, "grad_norm": 0.4361809194087982, "learning_rate": 1.257625235274334e-05, "loss": 4.2543, "step": 21790 }, { "epoch": 0.6655772755039707, "grad_norm": 0.44700679183006287, "learning_rate": 1.2574170698845833e-05, "loss": 4.3439, "step": 21791 }, { "epoch": 0.6656078191814294, "grad_norm": 0.4404914379119873, "learning_rate": 1.2572089159359335e-05, "loss": 4.2818, "step": 21792 }, { "epoch": 0.6656383628588882, "grad_norm": 0.44496992230415344, "learning_rate": 1.2570007734303002e-05, "loss": 4.2599, "step": 21793 }, { "epoch": 0.665668906536347, "grad_norm": 0.4413927495479584, "learning_rate": 1.2567926423695985e-05, "loss": 4.2501, "step": 21794 }, { "epoch": 0.6656994502138057, "grad_norm": 0.4308341145515442, "learning_rate": 1.2565845227557477e-05, "loss": 4.3126, "step": 21795 }, { "epoch": 0.6657299938912645, "grad_norm": 0.4380316138267517, "learning_rate": 1.2563764145906614e-05, "loss": 4.2455, "step": 21796 }, { "epoch": 0.6657605375687232, "grad_norm": 0.44044557213783264, "learning_rate": 1.2561683178762579e-05, "loss": 4.3517, "step": 21797 }, { "epoch": 0.665791081246182, "grad_norm": 0.4438953101634979, "learning_rate": 1.255960232614451e-05, "loss": 4.283, "step": 21798 }, { "epoch": 0.6658216249236408, "grad_norm": 0.4599926173686981, "learning_rate": 1.255752158807158e-05, "loss": 4.1574, "step": 21799 }, { "epoch": 0.6658521686010995, "grad_norm": 0.4474157691001892, "learning_rate": 1.2555440964562953e-05, "loss": 4.2838, "step": 21800 }, { "epoch": 0.6658827122785583, "grad_norm": 0.44122621417045593, "learning_rate": 1.2553360455637772e-05, "loss": 4.3322, "step": 21801 }, { "epoch": 0.6659132559560171, "grad_norm": 0.439121812582016, "learning_rate": 1.2551280061315202e-05, "loss": 4.1989, "step": 21802 }, { "epoch": 0.6659437996334758, "grad_norm": 0.44665762782096863, "learning_rate": 1.2549199781614405e-05, "loss": 4.282, "step": 21803 }, { "epoch": 0.6659743433109346, "grad_norm": 0.443707138299942, "learning_rate": 1.2547119616554517e-05, "loss": 4.2694, "step": 21804 }, { "epoch": 0.6660048869883934, "grad_norm": 0.4296126961708069, "learning_rate": 1.2545039566154704e-05, "loss": 4.2986, "step": 21805 }, { "epoch": 0.6660354306658521, "grad_norm": 0.442455917596817, "learning_rate": 1.254295963043412e-05, "loss": 4.2332, "step": 21806 }, { "epoch": 0.6660659743433109, "grad_norm": 0.4382309913635254, "learning_rate": 1.2540879809411904e-05, "loss": 4.2638, "step": 21807 }, { "epoch": 0.6660965180207697, "grad_norm": 0.4512716233730316, "learning_rate": 1.2538800103107226e-05, "loss": 4.1998, "step": 21808 }, { "epoch": 0.6661270616982284, "grad_norm": 0.4464185833930969, "learning_rate": 1.2536720511539212e-05, "loss": 4.3014, "step": 21809 }, { "epoch": 0.6661576053756872, "grad_norm": 0.4350646138191223, "learning_rate": 1.2534641034727029e-05, "loss": 4.3096, "step": 21810 }, { "epoch": 0.666188149053146, "grad_norm": 0.44466260075569153, "learning_rate": 1.2532561672689802e-05, "loss": 4.2163, "step": 21811 }, { "epoch": 0.6662186927306047, "grad_norm": 0.4341558516025543, "learning_rate": 1.2530482425446705e-05, "loss": 4.2443, "step": 21812 }, { "epoch": 0.6662492364080635, "grad_norm": 0.44878655672073364, "learning_rate": 1.2528403293016855e-05, "loss": 4.299, "step": 21813 }, { "epoch": 0.6662797800855222, "grad_norm": 0.43579402565956116, "learning_rate": 1.2526324275419415e-05, "loss": 4.3356, "step": 21814 }, { "epoch": 0.666310323762981, "grad_norm": 0.4361726641654968, "learning_rate": 1.2524245372673515e-05, "loss": 4.2916, "step": 21815 }, { "epoch": 0.6663408674404399, "grad_norm": 0.4333873689174652, "learning_rate": 1.2522166584798303e-05, "loss": 4.2129, "step": 21816 }, { "epoch": 0.6663714111178985, "grad_norm": 0.4393933117389679, "learning_rate": 1.2520087911812928e-05, "loss": 4.2633, "step": 21817 }, { "epoch": 0.6664019547953574, "grad_norm": 0.4532322883605957, "learning_rate": 1.251800935373651e-05, "loss": 4.3149, "step": 21818 }, { "epoch": 0.6664324984728162, "grad_norm": 0.4416901171207428, "learning_rate": 1.2515930910588194e-05, "loss": 4.226, "step": 21819 }, { "epoch": 0.6664630421502749, "grad_norm": 0.43917569518089294, "learning_rate": 1.2513852582387135e-05, "loss": 4.3086, "step": 21820 }, { "epoch": 0.6664935858277337, "grad_norm": 0.43914029002189636, "learning_rate": 1.2511774369152444e-05, "loss": 4.236, "step": 21821 }, { "epoch": 0.6665241295051925, "grad_norm": 0.4456649124622345, "learning_rate": 1.2509696270903265e-05, "loss": 4.3033, "step": 21822 }, { "epoch": 0.6665546731826512, "grad_norm": 0.44447556138038635, "learning_rate": 1.2507618287658746e-05, "loss": 4.259, "step": 21823 }, { "epoch": 0.66658521686011, "grad_norm": 0.4440855383872986, "learning_rate": 1.2505540419438009e-05, "loss": 4.2432, "step": 21824 }, { "epoch": 0.6666157605375688, "grad_norm": 0.4544777274131775, "learning_rate": 1.2503462666260174e-05, "loss": 4.2979, "step": 21825 }, { "epoch": 0.6666463042150275, "grad_norm": 0.4502999186515808, "learning_rate": 1.2501385028144393e-05, "loss": 4.2891, "step": 21826 }, { "epoch": 0.6666768478924863, "grad_norm": 0.44208455085754395, "learning_rate": 1.2499307505109778e-05, "loss": 4.2871, "step": 21827 }, { "epoch": 0.6667073915699451, "grad_norm": 0.4424198865890503, "learning_rate": 1.2497230097175467e-05, "loss": 4.143, "step": 21828 }, { "epoch": 0.6667379352474038, "grad_norm": 0.43017178773880005, "learning_rate": 1.2495152804360593e-05, "loss": 4.2933, "step": 21829 }, { "epoch": 0.6667684789248626, "grad_norm": 0.4505442678928375, "learning_rate": 1.2493075626684269e-05, "loss": 4.2816, "step": 21830 }, { "epoch": 0.6667990226023213, "grad_norm": 0.4438903331756592, "learning_rate": 1.2490998564165638e-05, "loss": 4.3812, "step": 21831 }, { "epoch": 0.6668295662797801, "grad_norm": 0.4469562768936157, "learning_rate": 1.2488921616823804e-05, "loss": 4.1677, "step": 21832 }, { "epoch": 0.6668601099572389, "grad_norm": 0.4503742456436157, "learning_rate": 1.2486844784677901e-05, "loss": 4.2847, "step": 21833 }, { "epoch": 0.6668906536346976, "grad_norm": 0.4479029178619385, "learning_rate": 1.2484768067747063e-05, "loss": 4.2698, "step": 21834 }, { "epoch": 0.6669211973121564, "grad_norm": 0.43217480182647705, "learning_rate": 1.248269146605039e-05, "loss": 4.2544, "step": 21835 }, { "epoch": 0.6669517409896152, "grad_norm": 0.4477680027484894, "learning_rate": 1.248061497960701e-05, "loss": 4.2136, "step": 21836 }, { "epoch": 0.6669822846670739, "grad_norm": 0.45130616426467896, "learning_rate": 1.2478538608436058e-05, "loss": 4.22, "step": 21837 }, { "epoch": 0.6670128283445327, "grad_norm": 0.4495508372783661, "learning_rate": 1.2476462352556628e-05, "loss": 4.2881, "step": 21838 }, { "epoch": 0.6670433720219915, "grad_norm": 0.4440421462059021, "learning_rate": 1.2474386211987858e-05, "loss": 4.2109, "step": 21839 }, { "epoch": 0.6670739156994502, "grad_norm": 0.4481242895126343, "learning_rate": 1.2472310186748842e-05, "loss": 4.2879, "step": 21840 }, { "epoch": 0.667104459376909, "grad_norm": 0.44391506910324097, "learning_rate": 1.247023427685872e-05, "loss": 4.2902, "step": 21841 }, { "epoch": 0.6671350030543678, "grad_norm": 0.4429197907447815, "learning_rate": 1.2468158482336582e-05, "loss": 4.2001, "step": 21842 }, { "epoch": 0.6671655467318265, "grad_norm": 0.44675400853157043, "learning_rate": 1.2466082803201562e-05, "loss": 4.2775, "step": 21843 }, { "epoch": 0.6671960904092853, "grad_norm": 0.45324015617370605, "learning_rate": 1.2464007239472752e-05, "loss": 4.2099, "step": 21844 }, { "epoch": 0.6672266340867441, "grad_norm": 0.44011643528938293, "learning_rate": 1.2461931791169273e-05, "loss": 4.2023, "step": 21845 }, { "epoch": 0.6672571777642028, "grad_norm": 0.43982821702957153, "learning_rate": 1.2459856458310243e-05, "loss": 4.2379, "step": 21846 }, { "epoch": 0.6672877214416616, "grad_norm": 0.45331665873527527, "learning_rate": 1.2457781240914753e-05, "loss": 4.2013, "step": 21847 }, { "epoch": 0.6673182651191203, "grad_norm": 0.44367754459381104, "learning_rate": 1.245570613900193e-05, "loss": 4.1835, "step": 21848 }, { "epoch": 0.6673488087965791, "grad_norm": 0.4480254650115967, "learning_rate": 1.2453631152590861e-05, "loss": 4.1772, "step": 21849 }, { "epoch": 0.6673793524740379, "grad_norm": 0.42820465564727783, "learning_rate": 1.245155628170066e-05, "loss": 4.2824, "step": 21850 }, { "epoch": 0.6674098961514966, "grad_norm": 0.435566782951355, "learning_rate": 1.2449481526350442e-05, "loss": 4.3406, "step": 21851 }, { "epoch": 0.6674404398289554, "grad_norm": 0.45179325342178345, "learning_rate": 1.2447406886559291e-05, "loss": 4.288, "step": 21852 }, { "epoch": 0.6674709835064142, "grad_norm": 0.4478006064891815, "learning_rate": 1.2445332362346317e-05, "loss": 4.1856, "step": 21853 }, { "epoch": 0.6675015271838729, "grad_norm": 0.4460681080818176, "learning_rate": 1.2443257953730636e-05, "loss": 4.2302, "step": 21854 }, { "epoch": 0.6675320708613317, "grad_norm": 0.43677058815956116, "learning_rate": 1.2441183660731322e-05, "loss": 4.2624, "step": 21855 }, { "epoch": 0.6675626145387905, "grad_norm": 0.4398520886898041, "learning_rate": 1.2439109483367497e-05, "loss": 4.2324, "step": 21856 }, { "epoch": 0.6675931582162492, "grad_norm": 0.4436818063259125, "learning_rate": 1.2437035421658253e-05, "loss": 4.2826, "step": 21857 }, { "epoch": 0.667623701893708, "grad_norm": 0.44946831464767456, "learning_rate": 1.243496147562267e-05, "loss": 4.2465, "step": 21858 }, { "epoch": 0.6676542455711668, "grad_norm": 0.4547164738178253, "learning_rate": 1.2432887645279855e-05, "loss": 4.2862, "step": 21859 }, { "epoch": 0.6676847892486255, "grad_norm": 0.4402896463871002, "learning_rate": 1.2430813930648918e-05, "loss": 4.2871, "step": 21860 }, { "epoch": 0.6677153329260843, "grad_norm": 0.43154484033584595, "learning_rate": 1.242874033174893e-05, "loss": 4.2642, "step": 21861 }, { "epoch": 0.6677458766035431, "grad_norm": 0.45106828212738037, "learning_rate": 1.2426666848598992e-05, "loss": 4.276, "step": 21862 }, { "epoch": 0.6677764202810018, "grad_norm": 0.4524475038051605, "learning_rate": 1.2424593481218208e-05, "loss": 4.2383, "step": 21863 }, { "epoch": 0.6678069639584606, "grad_norm": 0.4462624192237854, "learning_rate": 1.2422520229625644e-05, "loss": 4.3011, "step": 21864 }, { "epoch": 0.6678375076359193, "grad_norm": 0.4361220896244049, "learning_rate": 1.2420447093840418e-05, "loss": 4.3124, "step": 21865 }, { "epoch": 0.6678680513133781, "grad_norm": 0.448036789894104, "learning_rate": 1.2418374073881588e-05, "loss": 4.2961, "step": 21866 }, { "epoch": 0.6678985949908369, "grad_norm": 0.44204261898994446, "learning_rate": 1.241630116976826e-05, "loss": 4.2655, "step": 21867 }, { "epoch": 0.6679291386682956, "grad_norm": 0.44408223032951355, "learning_rate": 1.2414228381519527e-05, "loss": 4.2682, "step": 21868 }, { "epoch": 0.6679596823457544, "grad_norm": 0.4433569014072418, "learning_rate": 1.2412155709154455e-05, "loss": 4.2554, "step": 21869 }, { "epoch": 0.6679902260232132, "grad_norm": 0.44485417008399963, "learning_rate": 1.2410083152692144e-05, "loss": 4.3001, "step": 21870 }, { "epoch": 0.6680207697006719, "grad_norm": 0.4442654252052307, "learning_rate": 1.2408010712151666e-05, "loss": 4.2312, "step": 21871 }, { "epoch": 0.6680513133781307, "grad_norm": 0.4438581168651581, "learning_rate": 1.2405938387552114e-05, "loss": 4.2282, "step": 21872 }, { "epoch": 0.6680818570555895, "grad_norm": 0.43829992413520813, "learning_rate": 1.240386617891255e-05, "loss": 4.2642, "step": 21873 }, { "epoch": 0.6681124007330482, "grad_norm": 0.44262346625328064, "learning_rate": 1.240179408625208e-05, "loss": 4.2997, "step": 21874 }, { "epoch": 0.668142944410507, "grad_norm": 0.4424034655094147, "learning_rate": 1.2399722109589759e-05, "loss": 4.307, "step": 21875 }, { "epoch": 0.6681734880879658, "grad_norm": 0.4449617564678192, "learning_rate": 1.2397650248944675e-05, "loss": 4.2156, "step": 21876 }, { "epoch": 0.6682040317654245, "grad_norm": 0.45389318466186523, "learning_rate": 1.2395578504335914e-05, "loss": 4.3157, "step": 21877 }, { "epoch": 0.6682345754428833, "grad_norm": 0.42992809414863586, "learning_rate": 1.2393506875782532e-05, "loss": 4.3433, "step": 21878 }, { "epoch": 0.6682651191203421, "grad_norm": 0.45702028274536133, "learning_rate": 1.2391435363303614e-05, "loss": 4.2063, "step": 21879 }, { "epoch": 0.6682956627978008, "grad_norm": 0.4553925395011902, "learning_rate": 1.2389363966918244e-05, "loss": 4.3235, "step": 21880 }, { "epoch": 0.6683262064752596, "grad_norm": 0.43685829639434814, "learning_rate": 1.2387292686645472e-05, "loss": 4.2747, "step": 21881 }, { "epoch": 0.6683567501527183, "grad_norm": 0.43913981318473816, "learning_rate": 1.2385221522504392e-05, "loss": 4.2865, "step": 21882 }, { "epoch": 0.6683872938301771, "grad_norm": 0.4515787363052368, "learning_rate": 1.2383150474514054e-05, "loss": 4.241, "step": 21883 }, { "epoch": 0.668417837507636, "grad_norm": 0.44583725929260254, "learning_rate": 1.2381079542693535e-05, "loss": 4.3044, "step": 21884 }, { "epoch": 0.6684483811850946, "grad_norm": 0.44945573806762695, "learning_rate": 1.2379008727061916e-05, "loss": 4.3505, "step": 21885 }, { "epoch": 0.6684789248625534, "grad_norm": 0.44577616453170776, "learning_rate": 1.2376938027638244e-05, "loss": 4.3246, "step": 21886 }, { "epoch": 0.6685094685400123, "grad_norm": 0.4447712004184723, "learning_rate": 1.2374867444441601e-05, "loss": 4.2012, "step": 21887 }, { "epoch": 0.668540012217471, "grad_norm": 0.44184011220932007, "learning_rate": 1.2372796977491044e-05, "loss": 4.2512, "step": 21888 }, { "epoch": 0.6685705558949298, "grad_norm": 0.4442001283168793, "learning_rate": 1.2370726626805632e-05, "loss": 4.2884, "step": 21889 }, { "epoch": 0.6686010995723886, "grad_norm": 0.45380908250808716, "learning_rate": 1.2368656392404429e-05, "loss": 4.2528, "step": 21890 }, { "epoch": 0.6686316432498473, "grad_norm": 0.44385629892349243, "learning_rate": 1.2366586274306514e-05, "loss": 4.3112, "step": 21891 }, { "epoch": 0.6686621869273061, "grad_norm": 0.4419175982475281, "learning_rate": 1.2364516272530922e-05, "loss": 4.2005, "step": 21892 }, { "epoch": 0.6686927306047649, "grad_norm": 0.46068158745765686, "learning_rate": 1.2362446387096726e-05, "loss": 4.2104, "step": 21893 }, { "epoch": 0.6687232742822236, "grad_norm": 0.4375793933868408, "learning_rate": 1.2360376618022994e-05, "loss": 4.3486, "step": 21894 }, { "epoch": 0.6687538179596824, "grad_norm": 0.4554436504840851, "learning_rate": 1.2358306965328764e-05, "loss": 4.181, "step": 21895 }, { "epoch": 0.6687843616371412, "grad_norm": 0.43378040194511414, "learning_rate": 1.23562374290331e-05, "loss": 4.2387, "step": 21896 }, { "epoch": 0.6688149053145999, "grad_norm": 0.4475177526473999, "learning_rate": 1.2354168009155071e-05, "loss": 4.2753, "step": 21897 }, { "epoch": 0.6688454489920587, "grad_norm": 0.44511669874191284, "learning_rate": 1.2352098705713705e-05, "loss": 4.2886, "step": 21898 }, { "epoch": 0.6688759926695174, "grad_norm": 0.4480319321155548, "learning_rate": 1.2350029518728082e-05, "loss": 4.2706, "step": 21899 }, { "epoch": 0.6689065363469762, "grad_norm": 0.43660420179367065, "learning_rate": 1.234796044821723e-05, "loss": 4.2261, "step": 21900 }, { "epoch": 0.668937080024435, "grad_norm": 0.4414530396461487, "learning_rate": 1.2345891494200213e-05, "loss": 4.2481, "step": 21901 }, { "epoch": 0.6689676237018937, "grad_norm": 0.4406130313873291, "learning_rate": 1.2343822656696088e-05, "loss": 4.2999, "step": 21902 }, { "epoch": 0.6689981673793525, "grad_norm": 0.4464285671710968, "learning_rate": 1.2341753935723893e-05, "loss": 4.2876, "step": 21903 }, { "epoch": 0.6690287110568113, "grad_norm": 0.43023255467414856, "learning_rate": 1.2339685331302672e-05, "loss": 4.1735, "step": 21904 }, { "epoch": 0.66905925473427, "grad_norm": 0.44440916180610657, "learning_rate": 1.2337616843451483e-05, "loss": 4.1686, "step": 21905 }, { "epoch": 0.6690897984117288, "grad_norm": 0.437584787607193, "learning_rate": 1.2335548472189359e-05, "loss": 4.2519, "step": 21906 }, { "epoch": 0.6691203420891876, "grad_norm": 0.4349323809146881, "learning_rate": 1.233348021753535e-05, "loss": 4.1868, "step": 21907 }, { "epoch": 0.6691508857666463, "grad_norm": 0.44926542043685913, "learning_rate": 1.233141207950851e-05, "loss": 4.304, "step": 21908 }, { "epoch": 0.6691814294441051, "grad_norm": 0.4513198137283325, "learning_rate": 1.2329344058127867e-05, "loss": 4.3295, "step": 21909 }, { "epoch": 0.6692119731215639, "grad_norm": 0.4338223338127136, "learning_rate": 1.2327276153412465e-05, "loss": 4.2005, "step": 21910 }, { "epoch": 0.6692425167990226, "grad_norm": 0.45338496565818787, "learning_rate": 1.2325208365381357e-05, "loss": 4.0324, "step": 21911 }, { "epoch": 0.6692730604764814, "grad_norm": 0.4584369659423828, "learning_rate": 1.2323140694053564e-05, "loss": 4.3431, "step": 21912 }, { "epoch": 0.6693036041539401, "grad_norm": 0.4586818218231201, "learning_rate": 1.2321073139448141e-05, "loss": 4.3182, "step": 21913 }, { "epoch": 0.6693341478313989, "grad_norm": 0.44628944993019104, "learning_rate": 1.2319005701584108e-05, "loss": 4.2801, "step": 21914 }, { "epoch": 0.6693646915088577, "grad_norm": 0.43791866302490234, "learning_rate": 1.2316938380480508e-05, "loss": 4.3014, "step": 21915 }, { "epoch": 0.6693952351863164, "grad_norm": 0.4398958086967468, "learning_rate": 1.2314871176156387e-05, "loss": 4.2522, "step": 21916 }, { "epoch": 0.6694257788637752, "grad_norm": 0.46458134055137634, "learning_rate": 1.2312804088630759e-05, "loss": 4.275, "step": 21917 }, { "epoch": 0.669456322541234, "grad_norm": 0.4450494349002838, "learning_rate": 1.2310737117922677e-05, "loss": 4.3403, "step": 21918 }, { "epoch": 0.6694868662186927, "grad_norm": 0.44052654504776, "learning_rate": 1.2308670264051153e-05, "loss": 4.2074, "step": 21919 }, { "epoch": 0.6695174098961515, "grad_norm": 0.4473276436328888, "learning_rate": 1.2306603527035238e-05, "loss": 4.2672, "step": 21920 }, { "epoch": 0.6695479535736103, "grad_norm": 0.4396871030330658, "learning_rate": 1.2304536906893937e-05, "loss": 4.2517, "step": 21921 }, { "epoch": 0.669578497251069, "grad_norm": 0.43761056661605835, "learning_rate": 1.2302470403646308e-05, "loss": 4.3037, "step": 21922 }, { "epoch": 0.6696090409285278, "grad_norm": 0.45031654834747314, "learning_rate": 1.2300404017311349e-05, "loss": 4.3102, "step": 21923 }, { "epoch": 0.6696395846059866, "grad_norm": 0.455427348613739, "learning_rate": 1.2298337747908098e-05, "loss": 4.3167, "step": 21924 }, { "epoch": 0.6696701282834453, "grad_norm": 0.4447261691093445, "learning_rate": 1.2296271595455593e-05, "loss": 4.2544, "step": 21925 }, { "epoch": 0.6697006719609041, "grad_norm": 0.454047292470932, "learning_rate": 1.2294205559972838e-05, "loss": 4.2498, "step": 21926 }, { "epoch": 0.6697312156383629, "grad_norm": 0.43875113129615784, "learning_rate": 1.2292139641478866e-05, "loss": 4.2538, "step": 21927 }, { "epoch": 0.6697617593158216, "grad_norm": 0.44677069783210754, "learning_rate": 1.2290073839992705e-05, "loss": 4.3259, "step": 21928 }, { "epoch": 0.6697923029932804, "grad_norm": 0.43615594506263733, "learning_rate": 1.2288008155533362e-05, "loss": 4.2778, "step": 21929 }, { "epoch": 0.6698228466707391, "grad_norm": 0.44479188323020935, "learning_rate": 1.2285942588119873e-05, "loss": 4.1746, "step": 21930 }, { "epoch": 0.6698533903481979, "grad_norm": 0.4415675401687622, "learning_rate": 1.2283877137771239e-05, "loss": 4.2602, "step": 21931 }, { "epoch": 0.6698839340256567, "grad_norm": 0.45150497555732727, "learning_rate": 1.2281811804506482e-05, "loss": 4.2909, "step": 21932 }, { "epoch": 0.6699144777031154, "grad_norm": 0.4558194577693939, "learning_rate": 1.2279746588344634e-05, "loss": 4.1927, "step": 21933 }, { "epoch": 0.6699450213805742, "grad_norm": 0.44316649436950684, "learning_rate": 1.2277681489304702e-05, "loss": 4.2698, "step": 21934 }, { "epoch": 0.669975565058033, "grad_norm": 0.445015013217926, "learning_rate": 1.2275616507405685e-05, "loss": 4.2782, "step": 21935 }, { "epoch": 0.6700061087354917, "grad_norm": 0.451369047164917, "learning_rate": 1.227355164266662e-05, "loss": 4.2262, "step": 21936 }, { "epoch": 0.6700366524129505, "grad_norm": 0.4404115080833435, "learning_rate": 1.2271486895106498e-05, "loss": 4.2276, "step": 21937 }, { "epoch": 0.6700671960904093, "grad_norm": 0.4537423253059387, "learning_rate": 1.2269422264744342e-05, "loss": 4.269, "step": 21938 }, { "epoch": 0.670097739767868, "grad_norm": 0.4410310685634613, "learning_rate": 1.2267357751599171e-05, "loss": 4.2383, "step": 21939 }, { "epoch": 0.6701282834453268, "grad_norm": 0.44028761982917786, "learning_rate": 1.2265293355689972e-05, "loss": 4.2929, "step": 21940 }, { "epoch": 0.6701588271227856, "grad_norm": 0.45038241147994995, "learning_rate": 1.2263229077035765e-05, "loss": 4.2986, "step": 21941 }, { "epoch": 0.6701893708002443, "grad_norm": 0.4354515075683594, "learning_rate": 1.2261164915655566e-05, "loss": 4.2927, "step": 21942 }, { "epoch": 0.6702199144777031, "grad_norm": 0.4478455185890198, "learning_rate": 1.225910087156836e-05, "loss": 4.3215, "step": 21943 }, { "epoch": 0.6702504581551619, "grad_norm": 0.4539986550807953, "learning_rate": 1.2257036944793165e-05, "loss": 4.2385, "step": 21944 }, { "epoch": 0.6702810018326206, "grad_norm": 0.4378114938735962, "learning_rate": 1.2254973135348994e-05, "loss": 4.2624, "step": 21945 }, { "epoch": 0.6703115455100794, "grad_norm": 0.4492722153663635, "learning_rate": 1.2252909443254825e-05, "loss": 4.3377, "step": 21946 }, { "epoch": 0.6703420891875381, "grad_norm": 0.442675918340683, "learning_rate": 1.2250845868529684e-05, "loss": 4.2534, "step": 21947 }, { "epoch": 0.6703726328649969, "grad_norm": 0.4457179307937622, "learning_rate": 1.224878241119255e-05, "loss": 4.2978, "step": 21948 }, { "epoch": 0.6704031765424557, "grad_norm": 0.4441484808921814, "learning_rate": 1.2246719071262442e-05, "loss": 4.3105, "step": 21949 }, { "epoch": 0.6704337202199144, "grad_norm": 0.4484574794769287, "learning_rate": 1.2244655848758338e-05, "loss": 4.2733, "step": 21950 }, { "epoch": 0.6704642638973732, "grad_norm": 0.4505191445350647, "learning_rate": 1.2242592743699258e-05, "loss": 4.2387, "step": 21951 }, { "epoch": 0.670494807574832, "grad_norm": 0.4584595561027527, "learning_rate": 1.2240529756104174e-05, "loss": 4.3496, "step": 21952 }, { "epoch": 0.6705253512522907, "grad_norm": 0.4470570683479309, "learning_rate": 1.2238466885992102e-05, "loss": 4.2183, "step": 21953 }, { "epoch": 0.6705558949297495, "grad_norm": 0.44058623909950256, "learning_rate": 1.223640413338202e-05, "loss": 4.2125, "step": 21954 }, { "epoch": 0.6705864386072083, "grad_norm": 0.44036152958869934, "learning_rate": 1.2234341498292926e-05, "loss": 4.2426, "step": 21955 }, { "epoch": 0.670616982284667, "grad_norm": 0.4492662250995636, "learning_rate": 1.2232278980743821e-05, "loss": 4.2407, "step": 21956 }, { "epoch": 0.6706475259621258, "grad_norm": 0.44807568192481995, "learning_rate": 1.223021658075368e-05, "loss": 4.183, "step": 21957 }, { "epoch": 0.6706780696395847, "grad_norm": 0.4466039836406708, "learning_rate": 1.2228154298341501e-05, "loss": 3.9862, "step": 21958 }, { "epoch": 0.6707086133170433, "grad_norm": 0.4491986334323883, "learning_rate": 1.2226092133526282e-05, "loss": 4.3107, "step": 21959 }, { "epoch": 0.6707391569945022, "grad_norm": 0.4480973780155182, "learning_rate": 1.222403008632699e-05, "loss": 4.2915, "step": 21960 }, { "epoch": 0.670769700671961, "grad_norm": 0.43236783146858215, "learning_rate": 1.2221968156762622e-05, "loss": 4.1795, "step": 21961 }, { "epoch": 0.6708002443494196, "grad_norm": 0.4424637258052826, "learning_rate": 1.2219906344852173e-05, "loss": 4.2643, "step": 21962 }, { "epoch": 0.6708307880268785, "grad_norm": 0.4616939127445221, "learning_rate": 1.2217844650614606e-05, "loss": 4.1028, "step": 21963 }, { "epoch": 0.6708613317043371, "grad_norm": 0.452150821685791, "learning_rate": 1.2215783074068926e-05, "loss": 4.2738, "step": 21964 }, { "epoch": 0.670891875381796, "grad_norm": 0.45594897866249084, "learning_rate": 1.2213721615234094e-05, "loss": 4.276, "step": 21965 }, { "epoch": 0.6709224190592548, "grad_norm": 0.45232337713241577, "learning_rate": 1.221166027412911e-05, "loss": 4.2712, "step": 21966 }, { "epoch": 0.6709529627367135, "grad_norm": 0.4465128183364868, "learning_rate": 1.2209599050772947e-05, "loss": 4.3266, "step": 21967 }, { "epoch": 0.6709835064141723, "grad_norm": 0.4521312713623047, "learning_rate": 1.2207537945184571e-05, "loss": 4.3585, "step": 21968 }, { "epoch": 0.6710140500916311, "grad_norm": 0.4572652578353882, "learning_rate": 1.2205476957382971e-05, "loss": 4.158, "step": 21969 }, { "epoch": 0.6710445937690898, "grad_norm": 0.43438050150871277, "learning_rate": 1.2203416087387132e-05, "loss": 4.2826, "step": 21970 }, { "epoch": 0.6710751374465486, "grad_norm": 0.43658217787742615, "learning_rate": 1.2201355335216011e-05, "loss": 4.3148, "step": 21971 }, { "epoch": 0.6711056811240074, "grad_norm": 0.44256678223609924, "learning_rate": 1.2199294700888592e-05, "loss": 4.2602, "step": 21972 }, { "epoch": 0.6711362248014661, "grad_norm": 0.4413590133190155, "learning_rate": 1.2197234184423859e-05, "loss": 4.3521, "step": 21973 }, { "epoch": 0.6711667684789249, "grad_norm": 0.43362957239151, "learning_rate": 1.219517378584076e-05, "loss": 4.2861, "step": 21974 }, { "epoch": 0.6711973121563837, "grad_norm": 0.4456942677497864, "learning_rate": 1.2193113505158282e-05, "loss": 4.2788, "step": 21975 }, { "epoch": 0.6712278558338424, "grad_norm": 0.44287988543510437, "learning_rate": 1.2191053342395404e-05, "loss": 4.3444, "step": 21976 }, { "epoch": 0.6712583995113012, "grad_norm": 0.4426783621311188, "learning_rate": 1.2188993297571072e-05, "loss": 4.1997, "step": 21977 }, { "epoch": 0.67128894318876, "grad_norm": 0.4455697238445282, "learning_rate": 1.2186933370704265e-05, "loss": 4.2433, "step": 21978 }, { "epoch": 0.6713194868662187, "grad_norm": 0.440963476896286, "learning_rate": 1.218487356181396e-05, "loss": 4.2778, "step": 21979 }, { "epoch": 0.6713500305436775, "grad_norm": 0.43460336327552795, "learning_rate": 1.2182813870919112e-05, "loss": 4.167, "step": 21980 }, { "epoch": 0.6713805742211362, "grad_norm": 0.430159330368042, "learning_rate": 1.218075429803868e-05, "loss": 4.293, "step": 21981 }, { "epoch": 0.671411117898595, "grad_norm": 0.45362815260887146, "learning_rate": 1.2178694843191644e-05, "loss": 4.3095, "step": 21982 }, { "epoch": 0.6714416615760538, "grad_norm": 0.44496336579322815, "learning_rate": 1.2176635506396944e-05, "loss": 4.3504, "step": 21983 }, { "epoch": 0.6714722052535125, "grad_norm": 0.4370768368244171, "learning_rate": 1.2174576287673564e-05, "loss": 4.2752, "step": 21984 }, { "epoch": 0.6715027489309713, "grad_norm": 0.4435734748840332, "learning_rate": 1.2172517187040447e-05, "loss": 4.2877, "step": 21985 }, { "epoch": 0.6715332926084301, "grad_norm": 0.44616207480430603, "learning_rate": 1.2170458204516557e-05, "loss": 4.2832, "step": 21986 }, { "epoch": 0.6715638362858888, "grad_norm": 0.4579845070838928, "learning_rate": 1.2168399340120865e-05, "loss": 4.2195, "step": 21987 }, { "epoch": 0.6715943799633476, "grad_norm": 0.4450795650482178, "learning_rate": 1.2166340593872308e-05, "loss": 4.3433, "step": 21988 }, { "epoch": 0.6716249236408064, "grad_norm": 0.44209009408950806, "learning_rate": 1.2164281965789853e-05, "loss": 4.2952, "step": 21989 }, { "epoch": 0.6716554673182651, "grad_norm": 0.44517025351524353, "learning_rate": 1.2162223455892463e-05, "loss": 4.1736, "step": 21990 }, { "epoch": 0.6716860109957239, "grad_norm": 0.4433179199695587, "learning_rate": 1.216016506419907e-05, "loss": 4.2673, "step": 21991 }, { "epoch": 0.6717165546731827, "grad_norm": 0.4407457411289215, "learning_rate": 1.215810679072864e-05, "loss": 4.2089, "step": 21992 }, { "epoch": 0.6717470983506414, "grad_norm": 0.4515048861503601, "learning_rate": 1.2156048635500133e-05, "loss": 4.4013, "step": 21993 }, { "epoch": 0.6717776420281002, "grad_norm": 0.4475298523902893, "learning_rate": 1.215399059853248e-05, "loss": 4.2492, "step": 21994 }, { "epoch": 0.671808185705559, "grad_norm": 0.4437271058559418, "learning_rate": 1.2151932679844651e-05, "loss": 4.2164, "step": 21995 }, { "epoch": 0.6718387293830177, "grad_norm": 0.4433665871620178, "learning_rate": 1.2149874879455575e-05, "loss": 4.2048, "step": 21996 }, { "epoch": 0.6718692730604765, "grad_norm": 0.4355505108833313, "learning_rate": 1.2147817197384215e-05, "loss": 4.2275, "step": 21997 }, { "epoch": 0.6718998167379352, "grad_norm": 0.43815067410469055, "learning_rate": 1.2145759633649511e-05, "loss": 4.1563, "step": 21998 }, { "epoch": 0.671930360415394, "grad_norm": 0.4527795910835266, "learning_rate": 1.2143702188270399e-05, "loss": 4.2469, "step": 21999 }, { "epoch": 0.6719609040928528, "grad_norm": 0.4438483417034149, "learning_rate": 1.214164486126583e-05, "loss": 4.2543, "step": 22000 }, { "epoch": 0.6719914477703115, "grad_norm": 0.44321516156196594, "learning_rate": 1.2139587652654755e-05, "loss": 4.1857, "step": 22001 }, { "epoch": 0.6720219914477703, "grad_norm": 0.4419453740119934, "learning_rate": 1.21375305624561e-05, "loss": 4.3436, "step": 22002 }, { "epoch": 0.6720525351252291, "grad_norm": 0.43995627760887146, "learning_rate": 1.2135473590688818e-05, "loss": 4.2421, "step": 22003 }, { "epoch": 0.6720830788026878, "grad_norm": 0.4524575471878052, "learning_rate": 1.2133416737371852e-05, "loss": 4.2949, "step": 22004 }, { "epoch": 0.6721136224801466, "grad_norm": 0.44247904419898987, "learning_rate": 1.2131360002524122e-05, "loss": 4.312, "step": 22005 }, { "epoch": 0.6721441661576054, "grad_norm": 0.4452088475227356, "learning_rate": 1.2129303386164581e-05, "loss": 4.2759, "step": 22006 }, { "epoch": 0.6721747098350641, "grad_norm": 0.44601526856422424, "learning_rate": 1.2127246888312168e-05, "loss": 4.2597, "step": 22007 }, { "epoch": 0.6722052535125229, "grad_norm": 0.44829681515693665, "learning_rate": 1.2125190508985801e-05, "loss": 4.2601, "step": 22008 }, { "epoch": 0.6722357971899817, "grad_norm": 0.4449951946735382, "learning_rate": 1.2123134248204427e-05, "loss": 4.2775, "step": 22009 }, { "epoch": 0.6722663408674404, "grad_norm": 0.43245425820350647, "learning_rate": 1.2121078105986986e-05, "loss": 4.2686, "step": 22010 }, { "epoch": 0.6722968845448992, "grad_norm": 0.43841826915740967, "learning_rate": 1.2119022082352388e-05, "loss": 4.3077, "step": 22011 }, { "epoch": 0.672327428222358, "grad_norm": 0.45606714487075806, "learning_rate": 1.2116966177319588e-05, "loss": 4.3012, "step": 22012 }, { "epoch": 0.6723579718998167, "grad_norm": 0.4428425133228302, "learning_rate": 1.2114910390907505e-05, "loss": 4.3503, "step": 22013 }, { "epoch": 0.6723885155772755, "grad_norm": 0.44907239079475403, "learning_rate": 1.2112854723135056e-05, "loss": 4.1656, "step": 22014 }, { "epoch": 0.6724190592547342, "grad_norm": 0.4513114392757416, "learning_rate": 1.211079917402119e-05, "loss": 4.2438, "step": 22015 }, { "epoch": 0.672449602932193, "grad_norm": 0.4556064307689667, "learning_rate": 1.2108743743584814e-05, "loss": 4.2794, "step": 22016 }, { "epoch": 0.6724801466096518, "grad_norm": 0.44461554288864136, "learning_rate": 1.210668843184486e-05, "loss": 4.3029, "step": 22017 }, { "epoch": 0.6725106902871105, "grad_norm": 0.4569113850593567, "learning_rate": 1.2104633238820265e-05, "loss": 4.2495, "step": 22018 }, { "epoch": 0.6725412339645693, "grad_norm": 0.45705127716064453, "learning_rate": 1.2102578164529934e-05, "loss": 4.2618, "step": 22019 }, { "epoch": 0.6725717776420281, "grad_norm": 0.4520547091960907, "learning_rate": 1.2100523208992795e-05, "loss": 4.301, "step": 22020 }, { "epoch": 0.6726023213194868, "grad_norm": 0.44587206840515137, "learning_rate": 1.2098468372227784e-05, "loss": 4.2003, "step": 22021 }, { "epoch": 0.6726328649969456, "grad_norm": 0.4375489354133606, "learning_rate": 1.2096413654253794e-05, "loss": 4.2527, "step": 22022 }, { "epoch": 0.6726634086744044, "grad_norm": 0.4415518343448639, "learning_rate": 1.209435905508976e-05, "loss": 4.3164, "step": 22023 }, { "epoch": 0.6726939523518631, "grad_norm": 0.4555264115333557, "learning_rate": 1.2092304574754607e-05, "loss": 4.2785, "step": 22024 }, { "epoch": 0.6727244960293219, "grad_norm": 0.4443526268005371, "learning_rate": 1.2090250213267234e-05, "loss": 4.2572, "step": 22025 }, { "epoch": 0.6727550397067807, "grad_norm": 0.4504827857017517, "learning_rate": 1.2088195970646562e-05, "loss": 4.3141, "step": 22026 }, { "epoch": 0.6727855833842394, "grad_norm": 0.45546913146972656, "learning_rate": 1.208614184691152e-05, "loss": 4.3, "step": 22027 }, { "epoch": 0.6728161270616982, "grad_norm": 0.4420785903930664, "learning_rate": 1.208408784208101e-05, "loss": 4.3722, "step": 22028 }, { "epoch": 0.672846670739157, "grad_norm": 0.4603831171989441, "learning_rate": 1.2082033956173933e-05, "loss": 4.3326, "step": 22029 }, { "epoch": 0.6728772144166157, "grad_norm": 0.43791285157203674, "learning_rate": 1.2079980189209222e-05, "loss": 4.2322, "step": 22030 }, { "epoch": 0.6729077580940745, "grad_norm": 0.451911062002182, "learning_rate": 1.2077926541205763e-05, "loss": 4.3247, "step": 22031 }, { "epoch": 0.6729383017715332, "grad_norm": 0.4497428238391876, "learning_rate": 1.2075873012182492e-05, "loss": 4.2812, "step": 22032 }, { "epoch": 0.672968845448992, "grad_norm": 0.4584067463874817, "learning_rate": 1.2073819602158294e-05, "loss": 4.2216, "step": 22033 }, { "epoch": 0.6729993891264509, "grad_norm": 0.4493548274040222, "learning_rate": 1.2071766311152084e-05, "loss": 4.1219, "step": 22034 }, { "epoch": 0.6730299328039095, "grad_norm": 0.4410942792892456, "learning_rate": 1.2069713139182776e-05, "loss": 4.2449, "step": 22035 }, { "epoch": 0.6730604764813684, "grad_norm": 0.46208277344703674, "learning_rate": 1.2067660086269259e-05, "loss": 4.2261, "step": 22036 }, { "epoch": 0.6730910201588272, "grad_norm": 0.46094122529029846, "learning_rate": 1.2065607152430444e-05, "loss": 4.2646, "step": 22037 }, { "epoch": 0.6731215638362859, "grad_norm": 0.4451128840446472, "learning_rate": 1.2063554337685243e-05, "loss": 4.3171, "step": 22038 }, { "epoch": 0.6731521075137447, "grad_norm": 0.4455035328865051, "learning_rate": 1.2061501642052542e-05, "loss": 4.304, "step": 22039 }, { "epoch": 0.6731826511912035, "grad_norm": 0.46308764815330505, "learning_rate": 1.2059449065551245e-05, "loss": 4.3328, "step": 22040 }, { "epoch": 0.6732131948686622, "grad_norm": 0.4331128001213074, "learning_rate": 1.2057396608200264e-05, "loss": 4.2113, "step": 22041 }, { "epoch": 0.673243738546121, "grad_norm": 0.44839388132095337, "learning_rate": 1.205534427001848e-05, "loss": 4.2899, "step": 22042 }, { "epoch": 0.6732742822235798, "grad_norm": 0.4529636800289154, "learning_rate": 1.2053292051024804e-05, "loss": 4.3887, "step": 22043 }, { "epoch": 0.6733048259010385, "grad_norm": 0.4555519223213196, "learning_rate": 1.2051239951238123e-05, "loss": 4.2945, "step": 22044 }, { "epoch": 0.6733353695784973, "grad_norm": 0.44431737065315247, "learning_rate": 1.2049187970677326e-05, "loss": 4.2572, "step": 22045 }, { "epoch": 0.6733659132559561, "grad_norm": 0.44708460569381714, "learning_rate": 1.2047136109361312e-05, "loss": 4.3236, "step": 22046 }, { "epoch": 0.6733964569334148, "grad_norm": 0.44589582085609436, "learning_rate": 1.2045084367308987e-05, "loss": 4.2685, "step": 22047 }, { "epoch": 0.6734270006108736, "grad_norm": 0.4578890800476074, "learning_rate": 1.204303274453922e-05, "loss": 4.3491, "step": 22048 }, { "epoch": 0.6734575442883323, "grad_norm": 0.45507699251174927, "learning_rate": 1.2040981241070923e-05, "loss": 4.3065, "step": 22049 }, { "epoch": 0.6734880879657911, "grad_norm": 0.44809821248054504, "learning_rate": 1.2038929856922965e-05, "loss": 4.3415, "step": 22050 }, { "epoch": 0.6735186316432499, "grad_norm": 0.44016289710998535, "learning_rate": 1.2036878592114245e-05, "loss": 4.2423, "step": 22051 }, { "epoch": 0.6735491753207086, "grad_norm": 0.44007307291030884, "learning_rate": 1.2034827446663657e-05, "loss": 4.1702, "step": 22052 }, { "epoch": 0.6735797189981674, "grad_norm": 0.4363603889942169, "learning_rate": 1.203277642059007e-05, "loss": 4.1827, "step": 22053 }, { "epoch": 0.6736102626756262, "grad_norm": 0.45577219128608704, "learning_rate": 1.2030725513912375e-05, "loss": 4.3195, "step": 22054 }, { "epoch": 0.6736408063530849, "grad_norm": 0.45042961835861206, "learning_rate": 1.202867472664947e-05, "loss": 4.2828, "step": 22055 }, { "epoch": 0.6736713500305437, "grad_norm": 0.44957780838012695, "learning_rate": 1.2026624058820216e-05, "loss": 4.2038, "step": 22056 }, { "epoch": 0.6737018937080025, "grad_norm": 0.4407792389392853, "learning_rate": 1.2024573510443504e-05, "loss": 4.2898, "step": 22057 }, { "epoch": 0.6737324373854612, "grad_norm": 0.4406372010707855, "learning_rate": 1.2022523081538226e-05, "loss": 4.3528, "step": 22058 }, { "epoch": 0.67376298106292, "grad_norm": 0.4507885277271271, "learning_rate": 1.2020472772123249e-05, "loss": 4.3837, "step": 22059 }, { "epoch": 0.6737935247403788, "grad_norm": 0.4475787281990051, "learning_rate": 1.2018422582217443e-05, "loss": 4.145, "step": 22060 }, { "epoch": 0.6738240684178375, "grad_norm": 0.4517005980014801, "learning_rate": 1.2016372511839705e-05, "loss": 4.3075, "step": 22061 }, { "epoch": 0.6738546120952963, "grad_norm": 0.44386547803878784, "learning_rate": 1.2014322561008892e-05, "loss": 4.1921, "step": 22062 }, { "epoch": 0.673885155772755, "grad_norm": 0.4488826096057892, "learning_rate": 1.2012272729743895e-05, "loss": 4.272, "step": 22063 }, { "epoch": 0.6739156994502138, "grad_norm": 0.4437287151813507, "learning_rate": 1.2010223018063574e-05, "loss": 4.2561, "step": 22064 }, { "epoch": 0.6739462431276726, "grad_norm": 0.44002971053123474, "learning_rate": 1.2008173425986804e-05, "loss": 4.3378, "step": 22065 }, { "epoch": 0.6739767868051313, "grad_norm": 0.45091766119003296, "learning_rate": 1.2006123953532475e-05, "loss": 4.3314, "step": 22066 }, { "epoch": 0.6740073304825901, "grad_norm": 0.4532092809677124, "learning_rate": 1.2004074600719434e-05, "loss": 4.1482, "step": 22067 }, { "epoch": 0.6740378741600489, "grad_norm": 0.4421318769454956, "learning_rate": 1.2002025367566557e-05, "loss": 4.2286, "step": 22068 }, { "epoch": 0.6740684178375076, "grad_norm": 0.4421590566635132, "learning_rate": 1.1999976254092726e-05, "loss": 4.2498, "step": 22069 }, { "epoch": 0.6740989615149664, "grad_norm": 0.45577389001846313, "learning_rate": 1.1997927260316789e-05, "loss": 4.2526, "step": 22070 }, { "epoch": 0.6741295051924252, "grad_norm": 0.44859856367111206, "learning_rate": 1.199587838625762e-05, "loss": 4.2377, "step": 22071 }, { "epoch": 0.6741600488698839, "grad_norm": 0.4484640657901764, "learning_rate": 1.1993829631934095e-05, "loss": 4.3739, "step": 22072 }, { "epoch": 0.6741905925473427, "grad_norm": 0.44042208790779114, "learning_rate": 1.1991780997365057e-05, "loss": 4.2555, "step": 22073 }, { "epoch": 0.6742211362248015, "grad_norm": 0.4384591579437256, "learning_rate": 1.1989732482569389e-05, "loss": 4.2768, "step": 22074 }, { "epoch": 0.6742516799022602, "grad_norm": 0.4389960765838623, "learning_rate": 1.1987684087565934e-05, "loss": 4.1992, "step": 22075 }, { "epoch": 0.674282223579719, "grad_norm": 0.4525173306465149, "learning_rate": 1.1985635812373572e-05, "loss": 4.2993, "step": 22076 }, { "epoch": 0.6743127672571778, "grad_norm": 0.45680326223373413, "learning_rate": 1.1983587657011142e-05, "loss": 4.2819, "step": 22077 }, { "epoch": 0.6743433109346365, "grad_norm": 0.44506120681762695, "learning_rate": 1.1981539621497523e-05, "loss": 4.2183, "step": 22078 }, { "epoch": 0.6743738546120953, "grad_norm": 0.44961225986480713, "learning_rate": 1.197949170585155e-05, "loss": 4.2342, "step": 22079 }, { "epoch": 0.674404398289554, "grad_norm": 0.44259724020957947, "learning_rate": 1.1977443910092103e-05, "loss": 4.3158, "step": 22080 }, { "epoch": 0.6744349419670128, "grad_norm": 0.43898820877075195, "learning_rate": 1.1975396234238018e-05, "loss": 4.3362, "step": 22081 }, { "epoch": 0.6744654856444716, "grad_norm": 0.4570780098438263, "learning_rate": 1.1973348678308156e-05, "loss": 4.0953, "step": 22082 }, { "epoch": 0.6744960293219303, "grad_norm": 0.4451844096183777, "learning_rate": 1.1971301242321379e-05, "loss": 4.2793, "step": 22083 }, { "epoch": 0.6745265729993891, "grad_norm": 0.4390404224395752, "learning_rate": 1.1969253926296519e-05, "loss": 4.3354, "step": 22084 }, { "epoch": 0.6745571166768479, "grad_norm": 0.45066988468170166, "learning_rate": 1.196720673025244e-05, "loss": 4.272, "step": 22085 }, { "epoch": 0.6745876603543066, "grad_norm": 0.456062376499176, "learning_rate": 1.1965159654207997e-05, "loss": 4.2336, "step": 22086 }, { "epoch": 0.6746182040317654, "grad_norm": 0.45066630840301514, "learning_rate": 1.1963112698182021e-05, "loss": 4.2501, "step": 22087 }, { "epoch": 0.6746487477092242, "grad_norm": 0.4643912613391876, "learning_rate": 1.196106586219337e-05, "loss": 4.2704, "step": 22088 }, { "epoch": 0.6746792913866829, "grad_norm": 0.44080623984336853, "learning_rate": 1.1959019146260903e-05, "loss": 4.1162, "step": 22089 }, { "epoch": 0.6747098350641417, "grad_norm": 0.4466986656188965, "learning_rate": 1.1956972550403447e-05, "loss": 4.219, "step": 22090 }, { "epoch": 0.6747403787416005, "grad_norm": 0.45287463068962097, "learning_rate": 1.1954926074639844e-05, "loss": 4.2852, "step": 22091 }, { "epoch": 0.6747709224190592, "grad_norm": 0.4457882344722748, "learning_rate": 1.1952879718988951e-05, "loss": 4.3417, "step": 22092 }, { "epoch": 0.674801466096518, "grad_norm": 0.4409711956977844, "learning_rate": 1.1950833483469592e-05, "loss": 4.2717, "step": 22093 }, { "epoch": 0.6748320097739768, "grad_norm": 0.44057953357696533, "learning_rate": 1.1948787368100623e-05, "loss": 4.1264, "step": 22094 }, { "epoch": 0.6748625534514355, "grad_norm": 0.4449407458305359, "learning_rate": 1.1946741372900886e-05, "loss": 4.2322, "step": 22095 }, { "epoch": 0.6748930971288943, "grad_norm": 0.4463712275028229, "learning_rate": 1.1944695497889203e-05, "loss": 4.1605, "step": 22096 }, { "epoch": 0.674923640806353, "grad_norm": 0.4433779716491699, "learning_rate": 1.1942649743084431e-05, "loss": 4.2292, "step": 22097 }, { "epoch": 0.6749541844838118, "grad_norm": 0.4537830650806427, "learning_rate": 1.1940604108505384e-05, "loss": 4.3699, "step": 22098 }, { "epoch": 0.6749847281612706, "grad_norm": 0.4489137828350067, "learning_rate": 1.1938558594170912e-05, "loss": 4.2894, "step": 22099 }, { "epoch": 0.6750152718387293, "grad_norm": 0.44536301493644714, "learning_rate": 1.1936513200099855e-05, "loss": 4.2854, "step": 22100 }, { "epoch": 0.6750458155161881, "grad_norm": 0.45240694284439087, "learning_rate": 1.193446792631103e-05, "loss": 4.2259, "step": 22101 }, { "epoch": 0.675076359193647, "grad_norm": 0.44907453656196594, "learning_rate": 1.1932422772823274e-05, "loss": 4.3063, "step": 22102 }, { "epoch": 0.6751069028711056, "grad_norm": 0.4573569893836975, "learning_rate": 1.193037773965543e-05, "loss": 4.2953, "step": 22103 }, { "epoch": 0.6751374465485644, "grad_norm": 0.4438124895095825, "learning_rate": 1.192833282682631e-05, "loss": 4.1706, "step": 22104 }, { "epoch": 0.6751679902260233, "grad_norm": 0.44338521361351013, "learning_rate": 1.192628803435476e-05, "loss": 4.161, "step": 22105 }, { "epoch": 0.675198533903482, "grad_norm": 0.4474702775478363, "learning_rate": 1.1924243362259587e-05, "loss": 4.3208, "step": 22106 }, { "epoch": 0.6752290775809408, "grad_norm": 0.4524361789226532, "learning_rate": 1.1922198810559638e-05, "loss": 4.3023, "step": 22107 }, { "epoch": 0.6752596212583996, "grad_norm": 0.4488283693790436, "learning_rate": 1.1920154379273717e-05, "loss": 4.166, "step": 22108 }, { "epoch": 0.6752901649358583, "grad_norm": 0.468214750289917, "learning_rate": 1.1918110068420673e-05, "loss": 4.1947, "step": 22109 }, { "epoch": 0.6753207086133171, "grad_norm": 0.44704753160476685, "learning_rate": 1.1916065878019305e-05, "loss": 4.2975, "step": 22110 }, { "epoch": 0.6753512522907759, "grad_norm": 0.4569455683231354, "learning_rate": 1.1914021808088446e-05, "loss": 4.283, "step": 22111 }, { "epoch": 0.6753817959682346, "grad_norm": 0.44591081142425537, "learning_rate": 1.1911977858646925e-05, "loss": 4.2415, "step": 22112 }, { "epoch": 0.6754123396456934, "grad_norm": 0.44409996271133423, "learning_rate": 1.1909934029713544e-05, "loss": 4.2336, "step": 22113 }, { "epoch": 0.675442883323152, "grad_norm": 0.4486781358718872, "learning_rate": 1.1907890321307138e-05, "loss": 4.2836, "step": 22114 }, { "epoch": 0.6754734270006109, "grad_norm": 0.445186972618103, "learning_rate": 1.190584673344651e-05, "loss": 4.3082, "step": 22115 }, { "epoch": 0.6755039706780697, "grad_norm": 0.45314615964889526, "learning_rate": 1.1903803266150482e-05, "loss": 4.1936, "step": 22116 }, { "epoch": 0.6755345143555284, "grad_norm": 0.4464535117149353, "learning_rate": 1.190175991943788e-05, "loss": 4.2277, "step": 22117 }, { "epoch": 0.6755650580329872, "grad_norm": 0.46477943658828735, "learning_rate": 1.18997166933275e-05, "loss": 4.2675, "step": 22118 }, { "epoch": 0.675595601710446, "grad_norm": 0.4418445825576782, "learning_rate": 1.1897673587838166e-05, "loss": 4.2079, "step": 22119 }, { "epoch": 0.6756261453879047, "grad_norm": 0.43741562962532043, "learning_rate": 1.1895630602988695e-05, "loss": 4.2445, "step": 22120 }, { "epoch": 0.6756566890653635, "grad_norm": 0.4634755849838257, "learning_rate": 1.1893587738797881e-05, "loss": 4.2286, "step": 22121 }, { "epoch": 0.6756872327428223, "grad_norm": 0.45297232270240784, "learning_rate": 1.1891544995284553e-05, "loss": 4.2554, "step": 22122 }, { "epoch": 0.675717776420281, "grad_norm": 0.45487362146377563, "learning_rate": 1.1889502372467511e-05, "loss": 4.2997, "step": 22123 }, { "epoch": 0.6757483200977398, "grad_norm": 0.4508597254753113, "learning_rate": 1.1887459870365553e-05, "loss": 4.2828, "step": 22124 }, { "epoch": 0.6757788637751986, "grad_norm": 0.43568143248558044, "learning_rate": 1.1885417488997492e-05, "loss": 4.2404, "step": 22125 }, { "epoch": 0.6758094074526573, "grad_norm": 0.4417223036289215, "learning_rate": 1.1883375228382143e-05, "loss": 4.2675, "step": 22126 }, { "epoch": 0.6758399511301161, "grad_norm": 0.44390636682510376, "learning_rate": 1.1881333088538293e-05, "loss": 4.3161, "step": 22127 }, { "epoch": 0.6758704948075749, "grad_norm": 0.44898873567581177, "learning_rate": 1.1879291069484757e-05, "loss": 4.1012, "step": 22128 }, { "epoch": 0.6759010384850336, "grad_norm": 0.4446035623550415, "learning_rate": 1.1877249171240342e-05, "loss": 4.2354, "step": 22129 }, { "epoch": 0.6759315821624924, "grad_norm": 0.4486401379108429, "learning_rate": 1.187520739382383e-05, "loss": 4.1771, "step": 22130 }, { "epoch": 0.6759621258399511, "grad_norm": 0.4522971510887146, "learning_rate": 1.1873165737254044e-05, "loss": 4.2084, "step": 22131 }, { "epoch": 0.6759926695174099, "grad_norm": 0.4453699290752411, "learning_rate": 1.187112420154976e-05, "loss": 4.1763, "step": 22132 }, { "epoch": 0.6760232131948687, "grad_norm": 0.4373874068260193, "learning_rate": 1.1869082786729785e-05, "loss": 4.3327, "step": 22133 }, { "epoch": 0.6760537568723274, "grad_norm": 0.4442560076713562, "learning_rate": 1.1867041492812924e-05, "loss": 4.1497, "step": 22134 }, { "epoch": 0.6760843005497862, "grad_norm": 0.45425042510032654, "learning_rate": 1.1865000319817956e-05, "loss": 4.2199, "step": 22135 }, { "epoch": 0.676114844227245, "grad_norm": 0.46025294065475464, "learning_rate": 1.1862959267763685e-05, "loss": 4.2939, "step": 22136 }, { "epoch": 0.6761453879047037, "grad_norm": 0.4475710988044739, "learning_rate": 1.1860918336668911e-05, "loss": 4.2485, "step": 22137 }, { "epoch": 0.6761759315821625, "grad_norm": 0.4491017460823059, "learning_rate": 1.1858877526552417e-05, "loss": 4.2648, "step": 22138 }, { "epoch": 0.6762064752596213, "grad_norm": 0.4636853039264679, "learning_rate": 1.1856836837432986e-05, "loss": 4.2293, "step": 22139 }, { "epoch": 0.67623701893708, "grad_norm": 0.45004257559776306, "learning_rate": 1.1854796269329424e-05, "loss": 4.3007, "step": 22140 }, { "epoch": 0.6762675626145388, "grad_norm": 0.4473344087600708, "learning_rate": 1.18527558222605e-05, "loss": 4.3162, "step": 22141 }, { "epoch": 0.6762981062919976, "grad_norm": 0.4387594163417816, "learning_rate": 1.1850715496245015e-05, "loss": 4.1064, "step": 22142 }, { "epoch": 0.6763286499694563, "grad_norm": 0.44699591398239136, "learning_rate": 1.1848675291301761e-05, "loss": 4.2865, "step": 22143 }, { "epoch": 0.6763591936469151, "grad_norm": 0.4416167140007019, "learning_rate": 1.1846635207449507e-05, "loss": 4.2772, "step": 22144 }, { "epoch": 0.6763897373243739, "grad_norm": 0.4542389512062073, "learning_rate": 1.1844595244707046e-05, "loss": 4.1878, "step": 22145 }, { "epoch": 0.6764202810018326, "grad_norm": 0.4563947021961212, "learning_rate": 1.184255540309317e-05, "loss": 4.3017, "step": 22146 }, { "epoch": 0.6764508246792914, "grad_norm": 0.4449830949306488, "learning_rate": 1.1840515682626641e-05, "loss": 4.2873, "step": 22147 }, { "epoch": 0.6764813683567501, "grad_norm": 0.44757118821144104, "learning_rate": 1.1838476083326261e-05, "loss": 4.2318, "step": 22148 }, { "epoch": 0.6765119120342089, "grad_norm": 0.4501773416996002, "learning_rate": 1.1836436605210788e-05, "loss": 4.1479, "step": 22149 }, { "epoch": 0.6765424557116677, "grad_norm": 0.4505711495876312, "learning_rate": 1.183439724829901e-05, "loss": 4.2646, "step": 22150 }, { "epoch": 0.6765729993891264, "grad_norm": 0.4629424214363098, "learning_rate": 1.1832358012609716e-05, "loss": 4.2785, "step": 22151 }, { "epoch": 0.6766035430665852, "grad_norm": 0.4487506151199341, "learning_rate": 1.1830318898161664e-05, "loss": 4.3039, "step": 22152 }, { "epoch": 0.676634086744044, "grad_norm": 0.44988423585891724, "learning_rate": 1.1828279904973644e-05, "loss": 4.2776, "step": 22153 }, { "epoch": 0.6766646304215027, "grad_norm": 0.43790745735168457, "learning_rate": 1.1826241033064425e-05, "loss": 4.3286, "step": 22154 }, { "epoch": 0.6766951740989615, "grad_norm": 0.45825496315956116, "learning_rate": 1.1824202282452767e-05, "loss": 4.3037, "step": 22155 }, { "epoch": 0.6767257177764203, "grad_norm": 0.4465937316417694, "learning_rate": 1.1822163653157454e-05, "loss": 4.2188, "step": 22156 }, { "epoch": 0.676756261453879, "grad_norm": 0.4467545747756958, "learning_rate": 1.1820125145197264e-05, "loss": 4.2312, "step": 22157 }, { "epoch": 0.6767868051313378, "grad_norm": 0.4499398171901703, "learning_rate": 1.1818086758590952e-05, "loss": 4.2514, "step": 22158 }, { "epoch": 0.6768173488087966, "grad_norm": 0.456349641084671, "learning_rate": 1.1816048493357291e-05, "loss": 4.3527, "step": 22159 }, { "epoch": 0.6768478924862553, "grad_norm": 0.4485487937927246, "learning_rate": 1.1814010349515055e-05, "loss": 4.283, "step": 22160 }, { "epoch": 0.6768784361637141, "grad_norm": 0.45035991072654724, "learning_rate": 1.1811972327083e-05, "loss": 4.2963, "step": 22161 }, { "epoch": 0.6769089798411729, "grad_norm": 0.45165809988975525, "learning_rate": 1.1809934426079897e-05, "loss": 4.2128, "step": 22162 }, { "epoch": 0.6769395235186316, "grad_norm": 0.44436201453208923, "learning_rate": 1.180789664652452e-05, "loss": 4.3508, "step": 22163 }, { "epoch": 0.6769700671960904, "grad_norm": 0.4514068365097046, "learning_rate": 1.180585898843561e-05, "loss": 4.2045, "step": 22164 }, { "epoch": 0.6770006108735491, "grad_norm": 0.44112175703048706, "learning_rate": 1.1803821451831948e-05, "loss": 4.2928, "step": 22165 }, { "epoch": 0.6770311545510079, "grad_norm": 0.4442959129810333, "learning_rate": 1.1801784036732277e-05, "loss": 4.2647, "step": 22166 }, { "epoch": 0.6770616982284667, "grad_norm": 0.444513738155365, "learning_rate": 1.1799746743155368e-05, "loss": 4.2483, "step": 22167 }, { "epoch": 0.6770922419059254, "grad_norm": 0.44526347517967224, "learning_rate": 1.1797709571119988e-05, "loss": 4.3297, "step": 22168 }, { "epoch": 0.6771227855833842, "grad_norm": 0.4424288868904114, "learning_rate": 1.1795672520644882e-05, "loss": 4.1109, "step": 22169 }, { "epoch": 0.677153329260843, "grad_norm": 0.4477527439594269, "learning_rate": 1.17936355917488e-05, "loss": 4.2126, "step": 22170 }, { "epoch": 0.6771838729383017, "grad_norm": 0.44696447253227234, "learning_rate": 1.1791598784450515e-05, "loss": 4.3346, "step": 22171 }, { "epoch": 0.6772144166157605, "grad_norm": 0.45195379853248596, "learning_rate": 1.1789562098768759e-05, "loss": 4.2475, "step": 22172 }, { "epoch": 0.6772449602932193, "grad_norm": 0.4386375844478607, "learning_rate": 1.17875255347223e-05, "loss": 4.2468, "step": 22173 }, { "epoch": 0.677275503970678, "grad_norm": 0.4531745910644531, "learning_rate": 1.1785489092329894e-05, "loss": 4.2679, "step": 22174 }, { "epoch": 0.6773060476481368, "grad_norm": 0.453617662191391, "learning_rate": 1.1783452771610273e-05, "loss": 4.2782, "step": 22175 }, { "epoch": 0.6773365913255956, "grad_norm": 0.44885939359664917, "learning_rate": 1.1781416572582201e-05, "loss": 4.2678, "step": 22176 }, { "epoch": 0.6773671350030543, "grad_norm": 0.4467166066169739, "learning_rate": 1.177938049526443e-05, "loss": 4.2707, "step": 22177 }, { "epoch": 0.6773976786805131, "grad_norm": 0.4411126673221588, "learning_rate": 1.1777344539675694e-05, "loss": 4.3283, "step": 22178 }, { "epoch": 0.677428222357972, "grad_norm": 0.4559294581413269, "learning_rate": 1.1775308705834743e-05, "loss": 4.362, "step": 22179 }, { "epoch": 0.6774587660354306, "grad_norm": 0.4533725082874298, "learning_rate": 1.1773272993760334e-05, "loss": 4.3714, "step": 22180 }, { "epoch": 0.6774893097128895, "grad_norm": 0.4500109553337097, "learning_rate": 1.1771237403471191e-05, "loss": 4.2969, "step": 22181 }, { "epoch": 0.6775198533903481, "grad_norm": 0.4424620270729065, "learning_rate": 1.1769201934986077e-05, "loss": 4.368, "step": 22182 }, { "epoch": 0.677550397067807, "grad_norm": 0.45467498898506165, "learning_rate": 1.1767166588323713e-05, "loss": 4.2758, "step": 22183 }, { "epoch": 0.6775809407452658, "grad_norm": 0.46435821056365967, "learning_rate": 1.176513136350286e-05, "loss": 4.3272, "step": 22184 }, { "epoch": 0.6776114844227245, "grad_norm": 0.44854697585105896, "learning_rate": 1.1763096260542235e-05, "loss": 4.188, "step": 22185 }, { "epoch": 0.6776420281001833, "grad_norm": 0.4573337733745575, "learning_rate": 1.1761061279460603e-05, "loss": 4.3895, "step": 22186 }, { "epoch": 0.6776725717776421, "grad_norm": 0.4534786641597748, "learning_rate": 1.1759026420276676e-05, "loss": 4.271, "step": 22187 }, { "epoch": 0.6777031154551008, "grad_norm": 0.47254809737205505, "learning_rate": 1.1756991683009208e-05, "loss": 4.2141, "step": 22188 }, { "epoch": 0.6777336591325596, "grad_norm": 0.45860496163368225, "learning_rate": 1.1754957067676917e-05, "loss": 4.361, "step": 22189 }, { "epoch": 0.6777642028100184, "grad_norm": 0.4471695125102997, "learning_rate": 1.1752922574298547e-05, "loss": 4.2832, "step": 22190 }, { "epoch": 0.6777947464874771, "grad_norm": 0.460842102766037, "learning_rate": 1.175088820289284e-05, "loss": 4.2137, "step": 22191 }, { "epoch": 0.6778252901649359, "grad_norm": 0.4491609036922455, "learning_rate": 1.1748853953478505e-05, "loss": 4.3121, "step": 22192 }, { "epoch": 0.6778558338423947, "grad_norm": 0.455753356218338, "learning_rate": 1.174681982607429e-05, "loss": 4.2856, "step": 22193 }, { "epoch": 0.6778863775198534, "grad_norm": 0.4492652416229248, "learning_rate": 1.1744785820698925e-05, "loss": 4.2645, "step": 22194 }, { "epoch": 0.6779169211973122, "grad_norm": 0.4456239342689514, "learning_rate": 1.1742751937371122e-05, "loss": 4.2579, "step": 22195 }, { "epoch": 0.677947464874771, "grad_norm": 0.4596019387245178, "learning_rate": 1.1740718176109619e-05, "loss": 4.2235, "step": 22196 }, { "epoch": 0.6779780085522297, "grad_norm": 0.44934144616127014, "learning_rate": 1.173868453693315e-05, "loss": 4.2053, "step": 22197 }, { "epoch": 0.6780085522296885, "grad_norm": 0.4553340971469879, "learning_rate": 1.1736651019860422e-05, "loss": 4.3246, "step": 22198 }, { "epoch": 0.6780390959071472, "grad_norm": 0.45854026079177856, "learning_rate": 1.1734617624910177e-05, "loss": 4.2049, "step": 22199 }, { "epoch": 0.678069639584606, "grad_norm": 0.4511757493019104, "learning_rate": 1.1732584352101128e-05, "loss": 4.256, "step": 22200 }, { "epoch": 0.6781001832620648, "grad_norm": 0.4434596300125122, "learning_rate": 1.1730551201451986e-05, "loss": 4.2089, "step": 22201 }, { "epoch": 0.6781307269395235, "grad_norm": 0.4450863301753998, "learning_rate": 1.1728518172981493e-05, "loss": 4.1914, "step": 22202 }, { "epoch": 0.6781612706169823, "grad_norm": 0.45096370577812195, "learning_rate": 1.1726485266708345e-05, "loss": 4.2988, "step": 22203 }, { "epoch": 0.6781918142944411, "grad_norm": 0.45071858167648315, "learning_rate": 1.1724452482651272e-05, "loss": 4.157, "step": 22204 }, { "epoch": 0.6782223579718998, "grad_norm": 0.4398270845413208, "learning_rate": 1.1722419820829e-05, "loss": 4.1942, "step": 22205 }, { "epoch": 0.6782529016493586, "grad_norm": 0.45465341210365295, "learning_rate": 1.1720387281260226e-05, "loss": 4.3049, "step": 22206 }, { "epoch": 0.6782834453268174, "grad_norm": 0.43772703409194946, "learning_rate": 1.1718354863963676e-05, "loss": 4.2567, "step": 22207 }, { "epoch": 0.6783139890042761, "grad_norm": 0.45869797468185425, "learning_rate": 1.1716322568958068e-05, "loss": 4.1942, "step": 22208 }, { "epoch": 0.6783445326817349, "grad_norm": 0.4372938275337219, "learning_rate": 1.1714290396262101e-05, "loss": 4.172, "step": 22209 }, { "epoch": 0.6783750763591937, "grad_norm": 0.4394901692867279, "learning_rate": 1.1712258345894491e-05, "loss": 4.2783, "step": 22210 }, { "epoch": 0.6784056200366524, "grad_norm": 0.4523928463459015, "learning_rate": 1.1710226417873962e-05, "loss": 4.3044, "step": 22211 }, { "epoch": 0.6784361637141112, "grad_norm": 0.45500895380973816, "learning_rate": 1.17081946122192e-05, "loss": 4.287, "step": 22212 }, { "epoch": 0.6784667073915699, "grad_norm": 0.45562341809272766, "learning_rate": 1.1706162928948934e-05, "loss": 4.2856, "step": 22213 }, { "epoch": 0.6784972510690287, "grad_norm": 0.4531252682209015, "learning_rate": 1.1704131368081852e-05, "loss": 4.3004, "step": 22214 }, { "epoch": 0.6785277947464875, "grad_norm": 0.44620898365974426, "learning_rate": 1.1702099929636678e-05, "loss": 4.258, "step": 22215 }, { "epoch": 0.6785583384239462, "grad_norm": 0.4552915096282959, "learning_rate": 1.1700068613632094e-05, "loss": 4.3528, "step": 22216 }, { "epoch": 0.678588882101405, "grad_norm": 0.4606224298477173, "learning_rate": 1.1698037420086832e-05, "loss": 4.2376, "step": 22217 }, { "epoch": 0.6786194257788638, "grad_norm": 0.4537862539291382, "learning_rate": 1.1696006349019568e-05, "loss": 4.211, "step": 22218 }, { "epoch": 0.6786499694563225, "grad_norm": 0.44137880206108093, "learning_rate": 1.169397540044902e-05, "loss": 4.1961, "step": 22219 }, { "epoch": 0.6786805131337813, "grad_norm": 0.4469358026981354, "learning_rate": 1.1691944574393873e-05, "loss": 4.3217, "step": 22220 }, { "epoch": 0.6787110568112401, "grad_norm": 0.46770694851875305, "learning_rate": 1.1689913870872837e-05, "loss": 4.3341, "step": 22221 }, { "epoch": 0.6787416004886988, "grad_norm": 0.44436731934547424, "learning_rate": 1.1687883289904614e-05, "loss": 4.193, "step": 22222 }, { "epoch": 0.6787721441661576, "grad_norm": 0.45027080178260803, "learning_rate": 1.1685852831507887e-05, "loss": 4.3188, "step": 22223 }, { "epoch": 0.6788026878436164, "grad_norm": 0.4445602297782898, "learning_rate": 1.1683822495701358e-05, "loss": 4.239, "step": 22224 }, { "epoch": 0.6788332315210751, "grad_norm": 0.44538557529449463, "learning_rate": 1.1681792282503728e-05, "loss": 4.2758, "step": 22225 }, { "epoch": 0.6788637751985339, "grad_norm": 0.45101672410964966, "learning_rate": 1.1679762191933677e-05, "loss": 4.301, "step": 22226 }, { "epoch": 0.6788943188759927, "grad_norm": 0.4497489333152771, "learning_rate": 1.1677732224009905e-05, "loss": 4.2191, "step": 22227 }, { "epoch": 0.6789248625534514, "grad_norm": 0.4509330689907074, "learning_rate": 1.167570237875111e-05, "loss": 4.2954, "step": 22228 }, { "epoch": 0.6789554062309102, "grad_norm": 0.45653578639030457, "learning_rate": 1.1673672656175966e-05, "loss": 4.3012, "step": 22229 }, { "epoch": 0.6789859499083689, "grad_norm": 0.449753999710083, "learning_rate": 1.1671643056303177e-05, "loss": 4.23, "step": 22230 }, { "epoch": 0.6790164935858277, "grad_norm": 0.44897007942199707, "learning_rate": 1.1669613579151417e-05, "loss": 4.2112, "step": 22231 }, { "epoch": 0.6790470372632865, "grad_norm": 0.4504436254501343, "learning_rate": 1.1667584224739384e-05, "loss": 4.2713, "step": 22232 }, { "epoch": 0.6790775809407452, "grad_norm": 0.44919511675834656, "learning_rate": 1.1665554993085762e-05, "loss": 4.3687, "step": 22233 }, { "epoch": 0.679108124618204, "grad_norm": 0.45759838819503784, "learning_rate": 1.1663525884209218e-05, "loss": 4.293, "step": 22234 }, { "epoch": 0.6791386682956628, "grad_norm": 0.4550197124481201, "learning_rate": 1.1661496898128449e-05, "loss": 4.308, "step": 22235 }, { "epoch": 0.6791692119731215, "grad_norm": 0.44686296582221985, "learning_rate": 1.1659468034862145e-05, "loss": 4.2082, "step": 22236 }, { "epoch": 0.6791997556505803, "grad_norm": 0.4498513340950012, "learning_rate": 1.165743929442897e-05, "loss": 4.1676, "step": 22237 }, { "epoch": 0.6792302993280391, "grad_norm": 0.4556511640548706, "learning_rate": 1.1655410676847612e-05, "loss": 4.3259, "step": 22238 }, { "epoch": 0.6792608430054978, "grad_norm": 0.43997806310653687, "learning_rate": 1.1653382182136758e-05, "loss": 4.2534, "step": 22239 }, { "epoch": 0.6792913866829566, "grad_norm": 0.45114028453826904, "learning_rate": 1.1651353810315067e-05, "loss": 4.2889, "step": 22240 }, { "epoch": 0.6793219303604154, "grad_norm": 0.44318899512290955, "learning_rate": 1.1649325561401222e-05, "loss": 4.2793, "step": 22241 }, { "epoch": 0.6793524740378741, "grad_norm": 0.43904122710227966, "learning_rate": 1.1647297435413912e-05, "loss": 4.1636, "step": 22242 }, { "epoch": 0.6793830177153329, "grad_norm": 0.45742809772491455, "learning_rate": 1.1645269432371792e-05, "loss": 4.2425, "step": 22243 }, { "epoch": 0.6794135613927917, "grad_norm": 0.4475516974925995, "learning_rate": 1.164324155229354e-05, "loss": 4.3188, "step": 22244 }, { "epoch": 0.6794441050702504, "grad_norm": 0.456106036901474, "learning_rate": 1.164121379519784e-05, "loss": 4.3545, "step": 22245 }, { "epoch": 0.6794746487477092, "grad_norm": 0.45394596457481384, "learning_rate": 1.1639186161103344e-05, "loss": 4.3407, "step": 22246 }, { "epoch": 0.6795051924251679, "grad_norm": 0.4527236819267273, "learning_rate": 1.163715865002874e-05, "loss": 4.242, "step": 22247 }, { "epoch": 0.6795357361026267, "grad_norm": 0.44333982467651367, "learning_rate": 1.1635131261992687e-05, "loss": 4.2544, "step": 22248 }, { "epoch": 0.6795662797800855, "grad_norm": 0.4349171817302704, "learning_rate": 1.1633103997013844e-05, "loss": 4.2224, "step": 22249 }, { "epoch": 0.6795968234575442, "grad_norm": 0.4394209086894989, "learning_rate": 1.1631076855110893e-05, "loss": 4.2194, "step": 22250 }, { "epoch": 0.679627367135003, "grad_norm": 0.4507175385951996, "learning_rate": 1.1629049836302484e-05, "loss": 4.2659, "step": 22251 }, { "epoch": 0.6796579108124619, "grad_norm": 0.4402818977832794, "learning_rate": 1.1627022940607285e-05, "loss": 4.3248, "step": 22252 }, { "epoch": 0.6796884544899205, "grad_norm": 0.44874534010887146, "learning_rate": 1.162499616804397e-05, "loss": 4.3126, "step": 22253 }, { "epoch": 0.6797189981673794, "grad_norm": 0.4390614330768585, "learning_rate": 1.1622969518631186e-05, "loss": 4.2279, "step": 22254 }, { "epoch": 0.6797495418448382, "grad_norm": 0.4456976652145386, "learning_rate": 1.1620942992387596e-05, "loss": 4.3622, "step": 22255 }, { "epoch": 0.6797800855222969, "grad_norm": 0.4427097737789154, "learning_rate": 1.1618916589331874e-05, "loss": 4.2328, "step": 22256 }, { "epoch": 0.6798106291997557, "grad_norm": 0.4509161114692688, "learning_rate": 1.1616890309482659e-05, "loss": 4.2159, "step": 22257 }, { "epoch": 0.6798411728772145, "grad_norm": 0.44907450675964355, "learning_rate": 1.1614864152858613e-05, "loss": 4.3085, "step": 22258 }, { "epoch": 0.6798717165546732, "grad_norm": 0.4395529627799988, "learning_rate": 1.1612838119478406e-05, "loss": 4.2915, "step": 22259 }, { "epoch": 0.679902260232132, "grad_norm": 0.47231003642082214, "learning_rate": 1.161081220936067e-05, "loss": 4.3519, "step": 22260 }, { "epoch": 0.6799328039095908, "grad_norm": 0.44245198369026184, "learning_rate": 1.1608786422524081e-05, "loss": 4.2261, "step": 22261 }, { "epoch": 0.6799633475870495, "grad_norm": 0.44569069147109985, "learning_rate": 1.160676075898727e-05, "loss": 4.2123, "step": 22262 }, { "epoch": 0.6799938912645083, "grad_norm": 0.4413110613822937, "learning_rate": 1.1604735218768908e-05, "loss": 4.2608, "step": 22263 }, { "epoch": 0.680024434941967, "grad_norm": 0.45127642154693604, "learning_rate": 1.1602709801887637e-05, "loss": 4.2518, "step": 22264 }, { "epoch": 0.6800549786194258, "grad_norm": 0.4416428208351135, "learning_rate": 1.1600684508362097e-05, "loss": 4.2539, "step": 22265 }, { "epoch": 0.6800855222968846, "grad_norm": 0.4671672284603119, "learning_rate": 1.1598659338210941e-05, "loss": 4.2265, "step": 22266 }, { "epoch": 0.6801160659743433, "grad_norm": 0.44788607954978943, "learning_rate": 1.1596634291452829e-05, "loss": 4.2651, "step": 22267 }, { "epoch": 0.6801466096518021, "grad_norm": 0.45015057921409607, "learning_rate": 1.159460936810639e-05, "loss": 4.2795, "step": 22268 }, { "epoch": 0.6801771533292609, "grad_norm": 0.44936269521713257, "learning_rate": 1.1592584568190271e-05, "loss": 4.2794, "step": 22269 }, { "epoch": 0.6802076970067196, "grad_norm": 0.4524766504764557, "learning_rate": 1.1590559891723132e-05, "loss": 4.2491, "step": 22270 }, { "epoch": 0.6802382406841784, "grad_norm": 0.44534966349601746, "learning_rate": 1.1588535338723592e-05, "loss": 4.3117, "step": 22271 }, { "epoch": 0.6802687843616372, "grad_norm": 0.45795774459838867, "learning_rate": 1.1586510909210303e-05, "loss": 4.2219, "step": 22272 }, { "epoch": 0.6802993280390959, "grad_norm": 0.4515015780925751, "learning_rate": 1.158448660320191e-05, "loss": 4.1198, "step": 22273 }, { "epoch": 0.6803298717165547, "grad_norm": 0.45261260867118835, "learning_rate": 1.158246242071704e-05, "loss": 4.412, "step": 22274 }, { "epoch": 0.6803604153940135, "grad_norm": 0.44894590973854065, "learning_rate": 1.1580438361774337e-05, "loss": 4.2214, "step": 22275 }, { "epoch": 0.6803909590714722, "grad_norm": 0.44959309697151184, "learning_rate": 1.1578414426392448e-05, "loss": 4.3075, "step": 22276 }, { "epoch": 0.680421502748931, "grad_norm": 0.45116499066352844, "learning_rate": 1.1576390614589989e-05, "loss": 4.1969, "step": 22277 }, { "epoch": 0.6804520464263898, "grad_norm": 0.4531096816062927, "learning_rate": 1.157436692638561e-05, "loss": 4.1377, "step": 22278 }, { "epoch": 0.6804825901038485, "grad_norm": 0.45650070905685425, "learning_rate": 1.1572343361797942e-05, "loss": 4.2485, "step": 22279 }, { "epoch": 0.6805131337813073, "grad_norm": 0.44545498490333557, "learning_rate": 1.15703199208456e-05, "loss": 4.301, "step": 22280 }, { "epoch": 0.680543677458766, "grad_norm": 0.4512157738208771, "learning_rate": 1.1568296603547234e-05, "loss": 4.1691, "step": 22281 }, { "epoch": 0.6805742211362248, "grad_norm": 0.4499669075012207, "learning_rate": 1.156627340992146e-05, "loss": 4.1983, "step": 22282 }, { "epoch": 0.6806047648136836, "grad_norm": 0.46140190958976746, "learning_rate": 1.1564250339986914e-05, "loss": 4.2614, "step": 22283 }, { "epoch": 0.6806353084911423, "grad_norm": 0.4478181004524231, "learning_rate": 1.1562227393762234e-05, "loss": 4.318, "step": 22284 }, { "epoch": 0.6806658521686011, "grad_norm": 0.44878825545310974, "learning_rate": 1.1560204571266026e-05, "loss": 4.2776, "step": 22285 }, { "epoch": 0.6806963958460599, "grad_norm": 0.4620125889778137, "learning_rate": 1.1558181872516923e-05, "loss": 4.2346, "step": 22286 }, { "epoch": 0.6807269395235186, "grad_norm": 0.4607437252998352, "learning_rate": 1.1556159297533561e-05, "loss": 4.325, "step": 22287 }, { "epoch": 0.6807574832009774, "grad_norm": 0.4469181001186371, "learning_rate": 1.1554136846334543e-05, "loss": 4.2973, "step": 22288 }, { "epoch": 0.6807880268784362, "grad_norm": 0.4519760310649872, "learning_rate": 1.1552114518938498e-05, "loss": 4.1602, "step": 22289 }, { "epoch": 0.6808185705558949, "grad_norm": 0.45290908217430115, "learning_rate": 1.155009231536406e-05, "loss": 4.2551, "step": 22290 }, { "epoch": 0.6808491142333537, "grad_norm": 0.44571250677108765, "learning_rate": 1.154807023562983e-05, "loss": 4.1737, "step": 22291 }, { "epoch": 0.6808796579108125, "grad_norm": 0.4528110921382904, "learning_rate": 1.1546048279754429e-05, "loss": 4.1364, "step": 22292 }, { "epoch": 0.6809102015882712, "grad_norm": 0.4475921094417572, "learning_rate": 1.1544026447756493e-05, "loss": 4.2156, "step": 22293 }, { "epoch": 0.68094074526573, "grad_norm": 0.4465691149234772, "learning_rate": 1.154200473965462e-05, "loss": 4.2884, "step": 22294 }, { "epoch": 0.6809712889431888, "grad_norm": 0.4453214108943939, "learning_rate": 1.153998315546742e-05, "loss": 4.3189, "step": 22295 }, { "epoch": 0.6810018326206475, "grad_norm": 0.44657355546951294, "learning_rate": 1.1537961695213525e-05, "loss": 4.2679, "step": 22296 }, { "epoch": 0.6810323762981063, "grad_norm": 0.4366617500782013, "learning_rate": 1.1535940358911531e-05, "loss": 4.2668, "step": 22297 }, { "epoch": 0.681062919975565, "grad_norm": 0.43754351139068604, "learning_rate": 1.1533919146580066e-05, "loss": 4.2956, "step": 22298 }, { "epoch": 0.6810934636530238, "grad_norm": 0.4400831460952759, "learning_rate": 1.153189805823772e-05, "loss": 4.2148, "step": 22299 }, { "epoch": 0.6811240073304826, "grad_norm": 0.4525356888771057, "learning_rate": 1.1529877093903113e-05, "loss": 4.2801, "step": 22300 }, { "epoch": 0.6811545510079413, "grad_norm": 0.44839271903038025, "learning_rate": 1.1527856253594863e-05, "loss": 4.3232, "step": 22301 }, { "epoch": 0.6811850946854001, "grad_norm": 0.46391627192497253, "learning_rate": 1.1525835537331559e-05, "loss": 4.2626, "step": 22302 }, { "epoch": 0.6812156383628589, "grad_norm": 0.441852331161499, "learning_rate": 1.1523814945131814e-05, "loss": 4.1999, "step": 22303 }, { "epoch": 0.6812461820403176, "grad_norm": 0.4621879756450653, "learning_rate": 1.1521794477014242e-05, "loss": 4.2793, "step": 22304 }, { "epoch": 0.6812767257177764, "grad_norm": 0.4362879693508148, "learning_rate": 1.151977413299743e-05, "loss": 4.2629, "step": 22305 }, { "epoch": 0.6813072693952352, "grad_norm": 0.4462431073188782, "learning_rate": 1.1517753913099987e-05, "loss": 4.1715, "step": 22306 }, { "epoch": 0.6813378130726939, "grad_norm": 0.4514142870903015, "learning_rate": 1.1515733817340527e-05, "loss": 4.2861, "step": 22307 }, { "epoch": 0.6813683567501527, "grad_norm": 0.44594037532806396, "learning_rate": 1.1513713845737627e-05, "loss": 4.2353, "step": 22308 }, { "epoch": 0.6813989004276115, "grad_norm": 0.4524186849594116, "learning_rate": 1.1511693998309909e-05, "loss": 4.2565, "step": 22309 }, { "epoch": 0.6814294441050702, "grad_norm": 0.4434250295162201, "learning_rate": 1.1509674275075957e-05, "loss": 4.2142, "step": 22310 }, { "epoch": 0.681459987782529, "grad_norm": 0.44095510244369507, "learning_rate": 1.1507654676054364e-05, "loss": 4.244, "step": 22311 }, { "epoch": 0.6814905314599878, "grad_norm": 0.45282572507858276, "learning_rate": 1.1505635201263728e-05, "loss": 4.2481, "step": 22312 }, { "epoch": 0.6815210751374465, "grad_norm": 0.452874094247818, "learning_rate": 1.1503615850722657e-05, "loss": 4.1878, "step": 22313 }, { "epoch": 0.6815516188149053, "grad_norm": 0.4540434181690216, "learning_rate": 1.1501596624449725e-05, "loss": 4.2552, "step": 22314 }, { "epoch": 0.681582162492364, "grad_norm": 0.4474555552005768, "learning_rate": 1.1499577522463545e-05, "loss": 4.2379, "step": 22315 }, { "epoch": 0.6816127061698228, "grad_norm": 0.442341685295105, "learning_rate": 1.1497558544782682e-05, "loss": 4.2899, "step": 22316 }, { "epoch": 0.6816432498472816, "grad_norm": 0.4589315354824066, "learning_rate": 1.1495539691425745e-05, "loss": 4.2357, "step": 22317 }, { "epoch": 0.6816737935247403, "grad_norm": 0.44467514753341675, "learning_rate": 1.1493520962411322e-05, "loss": 4.1936, "step": 22318 }, { "epoch": 0.6817043372021991, "grad_norm": 0.4487692415714264, "learning_rate": 1.1491502357757988e-05, "loss": 4.2485, "step": 22319 }, { "epoch": 0.681734880879658, "grad_norm": 0.45266327261924744, "learning_rate": 1.1489483877484338e-05, "loss": 4.3698, "step": 22320 }, { "epoch": 0.6817654245571166, "grad_norm": 0.45295169949531555, "learning_rate": 1.1487465521608968e-05, "loss": 4.3186, "step": 22321 }, { "epoch": 0.6817959682345754, "grad_norm": 0.4519616961479187, "learning_rate": 1.1485447290150437e-05, "loss": 4.2981, "step": 22322 }, { "epoch": 0.6818265119120342, "grad_norm": 0.45597460865974426, "learning_rate": 1.1483429183127343e-05, "loss": 4.2795, "step": 22323 }, { "epoch": 0.6818570555894929, "grad_norm": 0.45288217067718506, "learning_rate": 1.1481411200558272e-05, "loss": 4.1781, "step": 22324 }, { "epoch": 0.6818875992669517, "grad_norm": 0.44679734110832214, "learning_rate": 1.1479393342461804e-05, "loss": 4.2429, "step": 22325 }, { "epoch": 0.6819181429444106, "grad_norm": 0.4577798545360565, "learning_rate": 1.14773756088565e-05, "loss": 4.319, "step": 22326 }, { "epoch": 0.6819486866218692, "grad_norm": 0.443270742893219, "learning_rate": 1.1475357999760963e-05, "loss": 4.3319, "step": 22327 }, { "epoch": 0.681979230299328, "grad_norm": 0.4480389654636383, "learning_rate": 1.1473340515193748e-05, "loss": 4.286, "step": 22328 }, { "epoch": 0.6820097739767869, "grad_norm": 0.4381831884384155, "learning_rate": 1.1471323155173444e-05, "loss": 4.1793, "step": 22329 }, { "epoch": 0.6820403176542456, "grad_norm": 0.44859960675239563, "learning_rate": 1.1469305919718629e-05, "loss": 4.3072, "step": 22330 }, { "epoch": 0.6820708613317044, "grad_norm": 0.44356095790863037, "learning_rate": 1.1467288808847865e-05, "loss": 4.2802, "step": 22331 }, { "epoch": 0.682101405009163, "grad_norm": 0.45024850964546204, "learning_rate": 1.1465271822579737e-05, "loss": 4.1981, "step": 22332 }, { "epoch": 0.6821319486866219, "grad_norm": 0.45183855295181274, "learning_rate": 1.1463254960932804e-05, "loss": 4.2724, "step": 22333 }, { "epoch": 0.6821624923640807, "grad_norm": 0.4506075978279114, "learning_rate": 1.1461238223925642e-05, "loss": 4.2484, "step": 22334 }, { "epoch": 0.6821930360415394, "grad_norm": 0.45391377806663513, "learning_rate": 1.1459221611576829e-05, "loss": 4.2018, "step": 22335 }, { "epoch": 0.6822235797189982, "grad_norm": 0.4424549639225006, "learning_rate": 1.1457205123904916e-05, "loss": 4.3696, "step": 22336 }, { "epoch": 0.682254123396457, "grad_norm": 0.44939473271369934, "learning_rate": 1.1455188760928476e-05, "loss": 4.2524, "step": 22337 }, { "epoch": 0.6822846670739157, "grad_norm": 0.45274674892425537, "learning_rate": 1.1453172522666089e-05, "loss": 4.3283, "step": 22338 }, { "epoch": 0.6823152107513745, "grad_norm": 0.4478514790534973, "learning_rate": 1.1451156409136296e-05, "loss": 4.2947, "step": 22339 }, { "epoch": 0.6823457544288333, "grad_norm": 0.45222008228302, "learning_rate": 1.1449140420357684e-05, "loss": 4.3468, "step": 22340 }, { "epoch": 0.682376298106292, "grad_norm": 0.45293983817100525, "learning_rate": 1.1447124556348794e-05, "loss": 4.3342, "step": 22341 }, { "epoch": 0.6824068417837508, "grad_norm": 0.44413816928863525, "learning_rate": 1.1445108817128204e-05, "loss": 4.2251, "step": 22342 }, { "epoch": 0.6824373854612096, "grad_norm": 0.44295504689216614, "learning_rate": 1.1443093202714459e-05, "loss": 4.3262, "step": 22343 }, { "epoch": 0.6824679291386683, "grad_norm": 0.46245527267456055, "learning_rate": 1.144107771312613e-05, "loss": 4.3385, "step": 22344 }, { "epoch": 0.6824984728161271, "grad_norm": 0.4497450888156891, "learning_rate": 1.1439062348381766e-05, "loss": 4.3527, "step": 22345 }, { "epoch": 0.6825290164935859, "grad_norm": 0.44196537137031555, "learning_rate": 1.1437047108499924e-05, "loss": 4.1952, "step": 22346 }, { "epoch": 0.6825595601710446, "grad_norm": 0.44917619228363037, "learning_rate": 1.1435031993499174e-05, "loss": 4.2776, "step": 22347 }, { "epoch": 0.6825901038485034, "grad_norm": 0.4795977771282196, "learning_rate": 1.1433017003398047e-05, "loss": 4.3171, "step": 22348 }, { "epoch": 0.6826206475259621, "grad_norm": 0.4389595687389374, "learning_rate": 1.143100213821512e-05, "loss": 4.2812, "step": 22349 }, { "epoch": 0.6826511912034209, "grad_norm": 0.45041489601135254, "learning_rate": 1.1428987397968921e-05, "loss": 4.2814, "step": 22350 }, { "epoch": 0.6826817348808797, "grad_norm": 0.44813063740730286, "learning_rate": 1.1426972782678014e-05, "loss": 4.3353, "step": 22351 }, { "epoch": 0.6827122785583384, "grad_norm": 0.4568723142147064, "learning_rate": 1.1424958292360957e-05, "loss": 4.2092, "step": 22352 }, { "epoch": 0.6827428222357972, "grad_norm": 0.4529930651187897, "learning_rate": 1.1422943927036278e-05, "loss": 4.276, "step": 22353 }, { "epoch": 0.682773365913256, "grad_norm": 0.4408375024795532, "learning_rate": 1.1420929686722535e-05, "loss": 4.1532, "step": 22354 }, { "epoch": 0.6828039095907147, "grad_norm": 0.46522754430770874, "learning_rate": 1.1418915571438285e-05, "loss": 4.2726, "step": 22355 }, { "epoch": 0.6828344532681735, "grad_norm": 0.4435679316520691, "learning_rate": 1.141690158120205e-05, "loss": 4.2521, "step": 22356 }, { "epoch": 0.6828649969456323, "grad_norm": 0.44631701707839966, "learning_rate": 1.1414887716032396e-05, "loss": 4.2309, "step": 22357 }, { "epoch": 0.682895540623091, "grad_norm": 0.44644713401794434, "learning_rate": 1.1412873975947857e-05, "loss": 4.2626, "step": 22358 }, { "epoch": 0.6829260843005498, "grad_norm": 0.4441573917865753, "learning_rate": 1.1410860360966963e-05, "loss": 4.2849, "step": 22359 }, { "epoch": 0.6829566279780086, "grad_norm": 0.44956740736961365, "learning_rate": 1.1408846871108264e-05, "loss": 4.1707, "step": 22360 }, { "epoch": 0.6829871716554673, "grad_norm": 0.45091211795806885, "learning_rate": 1.140683350639031e-05, "loss": 4.2346, "step": 22361 }, { "epoch": 0.6830177153329261, "grad_norm": 0.45025330781936646, "learning_rate": 1.140482026683162e-05, "loss": 4.2835, "step": 22362 }, { "epoch": 0.6830482590103848, "grad_norm": 0.4589793384075165, "learning_rate": 1.1402807152450748e-05, "loss": 4.2611, "step": 22363 }, { "epoch": 0.6830788026878436, "grad_norm": 0.45266193151474, "learning_rate": 1.1400794163266212e-05, "loss": 4.1797, "step": 22364 }, { "epoch": 0.6831093463653024, "grad_norm": 0.45250117778778076, "learning_rate": 1.1398781299296557e-05, "loss": 4.1953, "step": 22365 }, { "epoch": 0.6831398900427611, "grad_norm": 0.45687657594680786, "learning_rate": 1.1396768560560326e-05, "loss": 4.3182, "step": 22366 }, { "epoch": 0.6831704337202199, "grad_norm": 0.4549284279346466, "learning_rate": 1.1394755947076027e-05, "loss": 4.2533, "step": 22367 }, { "epoch": 0.6832009773976787, "grad_norm": 0.45663484930992126, "learning_rate": 1.139274345886221e-05, "loss": 4.2392, "step": 22368 }, { "epoch": 0.6832315210751374, "grad_norm": 0.45612838864326477, "learning_rate": 1.1390731095937407e-05, "loss": 4.1724, "step": 22369 }, { "epoch": 0.6832620647525962, "grad_norm": 0.4534534513950348, "learning_rate": 1.1388718858320133e-05, "loss": 4.3475, "step": 22370 }, { "epoch": 0.683292608430055, "grad_norm": 0.44696250557899475, "learning_rate": 1.138670674602893e-05, "loss": 4.1844, "step": 22371 }, { "epoch": 0.6833231521075137, "grad_norm": 0.4531387984752655, "learning_rate": 1.1384694759082306e-05, "loss": 4.2363, "step": 22372 }, { "epoch": 0.6833536957849725, "grad_norm": 0.45478153228759766, "learning_rate": 1.1382682897498812e-05, "loss": 4.2699, "step": 22373 }, { "epoch": 0.6833842394624313, "grad_norm": 0.4535902440547943, "learning_rate": 1.1380671161296944e-05, "loss": 4.3052, "step": 22374 }, { "epoch": 0.68341478313989, "grad_norm": 0.45023998618125916, "learning_rate": 1.1378659550495252e-05, "loss": 4.0559, "step": 22375 }, { "epoch": 0.6834453268173488, "grad_norm": 0.4447741210460663, "learning_rate": 1.1376648065112233e-05, "loss": 4.2688, "step": 22376 }, { "epoch": 0.6834758704948076, "grad_norm": 0.470041960477829, "learning_rate": 1.1374636705166419e-05, "loss": 4.2892, "step": 22377 }, { "epoch": 0.6835064141722663, "grad_norm": 0.4522513151168823, "learning_rate": 1.1372625470676343e-05, "loss": 4.2119, "step": 22378 }, { "epoch": 0.6835369578497251, "grad_norm": 0.4483667314052582, "learning_rate": 1.1370614361660498e-05, "loss": 4.1909, "step": 22379 }, { "epoch": 0.6835675015271838, "grad_norm": 0.45547178387641907, "learning_rate": 1.1368603378137427e-05, "loss": 4.2041, "step": 22380 }, { "epoch": 0.6835980452046426, "grad_norm": 0.47493836283683777, "learning_rate": 1.1366592520125621e-05, "loss": 4.2727, "step": 22381 }, { "epoch": 0.6836285888821014, "grad_norm": 0.45027387142181396, "learning_rate": 1.1364581787643608e-05, "loss": 4.2565, "step": 22382 }, { "epoch": 0.6836591325595601, "grad_norm": 0.452901691198349, "learning_rate": 1.1362571180709911e-05, "loss": 4.2049, "step": 22383 }, { "epoch": 0.6836896762370189, "grad_norm": 0.4477255344390869, "learning_rate": 1.1360560699343024e-05, "loss": 4.2454, "step": 22384 }, { "epoch": 0.6837202199144777, "grad_norm": 0.45327049493789673, "learning_rate": 1.1358550343561464e-05, "loss": 4.2646, "step": 22385 }, { "epoch": 0.6837507635919364, "grad_norm": 0.4489918053150177, "learning_rate": 1.1356540113383757e-05, "loss": 4.3049, "step": 22386 }, { "epoch": 0.6837813072693952, "grad_norm": 0.45363473892211914, "learning_rate": 1.135453000882839e-05, "loss": 4.2365, "step": 22387 }, { "epoch": 0.683811850946854, "grad_norm": 0.4519067108631134, "learning_rate": 1.135252002991389e-05, "loss": 4.2105, "step": 22388 }, { "epoch": 0.6838423946243127, "grad_norm": 0.440956711769104, "learning_rate": 1.1350510176658757e-05, "loss": 4.2602, "step": 22389 }, { "epoch": 0.6838729383017715, "grad_norm": 0.45180976390838623, "learning_rate": 1.1348500449081485e-05, "loss": 4.2333, "step": 22390 }, { "epoch": 0.6839034819792303, "grad_norm": 0.46513232588768005, "learning_rate": 1.1346490847200587e-05, "loss": 4.1689, "step": 22391 }, { "epoch": 0.683934025656689, "grad_norm": 0.4558616578578949, "learning_rate": 1.1344481371034576e-05, "loss": 4.3113, "step": 22392 }, { "epoch": 0.6839645693341478, "grad_norm": 0.4492345452308655, "learning_rate": 1.1342472020601939e-05, "loss": 4.3012, "step": 22393 }, { "epoch": 0.6839951130116066, "grad_norm": 0.48426175117492676, "learning_rate": 1.134046279592118e-05, "loss": 4.3533, "step": 22394 }, { "epoch": 0.6840256566890653, "grad_norm": 0.4493529498577118, "learning_rate": 1.1338453697010817e-05, "loss": 4.1949, "step": 22395 }, { "epoch": 0.6840562003665241, "grad_norm": 0.44805672764778137, "learning_rate": 1.1336444723889323e-05, "loss": 4.2651, "step": 22396 }, { "epoch": 0.6840867440439828, "grad_norm": 0.45594725012779236, "learning_rate": 1.1334435876575217e-05, "loss": 4.2779, "step": 22397 }, { "epoch": 0.6841172877214416, "grad_norm": 0.4530581831932068, "learning_rate": 1.1332427155086978e-05, "loss": 4.2438, "step": 22398 }, { "epoch": 0.6841478313989005, "grad_norm": 0.4451550543308258, "learning_rate": 1.133041855944311e-05, "loss": 4.2902, "step": 22399 }, { "epoch": 0.6841783750763591, "grad_norm": 0.45289045572280884, "learning_rate": 1.1328410089662114e-05, "loss": 4.2219, "step": 22400 }, { "epoch": 0.684208918753818, "grad_norm": 0.4382557272911072, "learning_rate": 1.1326401745762466e-05, "loss": 4.226, "step": 22401 }, { "epoch": 0.6842394624312768, "grad_norm": 0.45283448696136475, "learning_rate": 1.1324393527762669e-05, "loss": 4.2563, "step": 22402 }, { "epoch": 0.6842700061087355, "grad_norm": 0.44241347908973694, "learning_rate": 1.1322385435681221e-05, "loss": 4.247, "step": 22403 }, { "epoch": 0.6843005497861943, "grad_norm": 0.44471263885498047, "learning_rate": 1.1320377469536603e-05, "loss": 4.1207, "step": 22404 }, { "epoch": 0.6843310934636531, "grad_norm": 0.44254693388938904, "learning_rate": 1.1318369629347293e-05, "loss": 4.2779, "step": 22405 }, { "epoch": 0.6843616371411118, "grad_norm": 0.45482951402664185, "learning_rate": 1.1316361915131796e-05, "loss": 4.2586, "step": 22406 }, { "epoch": 0.6843921808185706, "grad_norm": 0.4548377990722656, "learning_rate": 1.1314354326908584e-05, "loss": 4.1737, "step": 22407 }, { "epoch": 0.6844227244960294, "grad_norm": 0.45435813069343567, "learning_rate": 1.1312346864696143e-05, "loss": 4.2529, "step": 22408 }, { "epoch": 0.6844532681734881, "grad_norm": 0.4506899118423462, "learning_rate": 1.1310339528512976e-05, "loss": 4.2699, "step": 22409 }, { "epoch": 0.6844838118509469, "grad_norm": 0.4418310225009918, "learning_rate": 1.1308332318377542e-05, "loss": 4.2353, "step": 22410 }, { "epoch": 0.6845143555284057, "grad_norm": 0.4433553218841553, "learning_rate": 1.1306325234308331e-05, "loss": 4.2142, "step": 22411 }, { "epoch": 0.6845448992058644, "grad_norm": 0.45980948209762573, "learning_rate": 1.1304318276323834e-05, "loss": 4.1757, "step": 22412 }, { "epoch": 0.6845754428833232, "grad_norm": 0.4532087743282318, "learning_rate": 1.130231144444251e-05, "loss": 4.2558, "step": 22413 }, { "epoch": 0.6846059865607819, "grad_norm": 0.4492570161819458, "learning_rate": 1.1300304738682858e-05, "loss": 4.3186, "step": 22414 }, { "epoch": 0.6846365302382407, "grad_norm": 0.45656654238700867, "learning_rate": 1.129829815906333e-05, "loss": 4.2835, "step": 22415 }, { "epoch": 0.6846670739156995, "grad_norm": 0.4482048451900482, "learning_rate": 1.1296291705602422e-05, "loss": 4.1735, "step": 22416 }, { "epoch": 0.6846976175931582, "grad_norm": 0.4527125358581543, "learning_rate": 1.1294285378318606e-05, "loss": 4.2769, "step": 22417 }, { "epoch": 0.684728161270617, "grad_norm": 0.4539802074432373, "learning_rate": 1.1292279177230344e-05, "loss": 4.2391, "step": 22418 }, { "epoch": 0.6847587049480758, "grad_norm": 0.4505620300769806, "learning_rate": 1.1290273102356128e-05, "loss": 4.2373, "step": 22419 }, { "epoch": 0.6847892486255345, "grad_norm": 0.44141048192977905, "learning_rate": 1.1288267153714413e-05, "loss": 4.2844, "step": 22420 }, { "epoch": 0.6848197923029933, "grad_norm": 0.4402792751789093, "learning_rate": 1.1286261331323662e-05, "loss": 4.231, "step": 22421 }, { "epoch": 0.6848503359804521, "grad_norm": 0.4525945484638214, "learning_rate": 1.1284255635202357e-05, "loss": 4.3714, "step": 22422 }, { "epoch": 0.6848808796579108, "grad_norm": 0.4407881796360016, "learning_rate": 1.1282250065368968e-05, "loss": 4.2151, "step": 22423 }, { "epoch": 0.6849114233353696, "grad_norm": 0.4380265772342682, "learning_rate": 1.1280244621841948e-05, "loss": 4.2349, "step": 22424 }, { "epoch": 0.6849419670128284, "grad_norm": 0.461372047662735, "learning_rate": 1.127823930463977e-05, "loss": 4.2143, "step": 22425 }, { "epoch": 0.6849725106902871, "grad_norm": 0.44134819507598877, "learning_rate": 1.1276234113780906e-05, "loss": 4.2063, "step": 22426 }, { "epoch": 0.6850030543677459, "grad_norm": 0.4451918303966522, "learning_rate": 1.1274229049283803e-05, "loss": 4.3235, "step": 22427 }, { "epoch": 0.6850335980452047, "grad_norm": 0.46107229590415955, "learning_rate": 1.127222411116693e-05, "loss": 4.111, "step": 22428 }, { "epoch": 0.6850641417226634, "grad_norm": 0.45198121666908264, "learning_rate": 1.1270219299448755e-05, "loss": 4.2965, "step": 22429 }, { "epoch": 0.6850946854001222, "grad_norm": 0.452413409948349, "learning_rate": 1.1268214614147723e-05, "loss": 4.2204, "step": 22430 }, { "epoch": 0.6851252290775809, "grad_norm": 0.45541125535964966, "learning_rate": 1.1266210055282308e-05, "loss": 4.3173, "step": 22431 }, { "epoch": 0.6851557727550397, "grad_norm": 0.4471030831336975, "learning_rate": 1.126420562287095e-05, "loss": 4.2689, "step": 22432 }, { "epoch": 0.6851863164324985, "grad_norm": 0.4545775353908539, "learning_rate": 1.1262201316932112e-05, "loss": 4.2208, "step": 22433 }, { "epoch": 0.6852168601099572, "grad_norm": 0.45309269428253174, "learning_rate": 1.1260197137484257e-05, "loss": 4.338, "step": 22434 }, { "epoch": 0.685247403787416, "grad_norm": 0.4412635266780853, "learning_rate": 1.1258193084545834e-05, "loss": 4.2419, "step": 22435 }, { "epoch": 0.6852779474648748, "grad_norm": 0.4582819938659668, "learning_rate": 1.1256189158135284e-05, "loss": 4.2979, "step": 22436 }, { "epoch": 0.6853084911423335, "grad_norm": 0.45809414982795715, "learning_rate": 1.1254185358271071e-05, "loss": 4.1593, "step": 22437 }, { "epoch": 0.6853390348197923, "grad_norm": 0.44121330976486206, "learning_rate": 1.1252181684971636e-05, "loss": 4.2805, "step": 22438 }, { "epoch": 0.6853695784972511, "grad_norm": 0.44883060455322266, "learning_rate": 1.1250178138255433e-05, "loss": 4.2837, "step": 22439 }, { "epoch": 0.6854001221747098, "grad_norm": 0.46281614899635315, "learning_rate": 1.1248174718140917e-05, "loss": 4.1812, "step": 22440 }, { "epoch": 0.6854306658521686, "grad_norm": 0.4479089379310608, "learning_rate": 1.1246171424646517e-05, "loss": 4.2153, "step": 22441 }, { "epoch": 0.6854612095296274, "grad_norm": 0.44233909249305725, "learning_rate": 1.1244168257790689e-05, "loss": 4.287, "step": 22442 }, { "epoch": 0.6854917532070861, "grad_norm": 0.45703884959220886, "learning_rate": 1.1242165217591885e-05, "loss": 4.3292, "step": 22443 }, { "epoch": 0.6855222968845449, "grad_norm": 0.4581523537635803, "learning_rate": 1.1240162304068533e-05, "loss": 4.2306, "step": 22444 }, { "epoch": 0.6855528405620037, "grad_norm": 0.4612031877040863, "learning_rate": 1.1238159517239078e-05, "loss": 4.2721, "step": 22445 }, { "epoch": 0.6855833842394624, "grad_norm": 0.447733998298645, "learning_rate": 1.1236156857121974e-05, "loss": 4.2136, "step": 22446 }, { "epoch": 0.6856139279169212, "grad_norm": 0.44309574365615845, "learning_rate": 1.1234154323735641e-05, "loss": 4.2162, "step": 22447 }, { "epoch": 0.6856444715943799, "grad_norm": 0.44195881485939026, "learning_rate": 1.1232151917098538e-05, "loss": 4.2906, "step": 22448 }, { "epoch": 0.6856750152718387, "grad_norm": 0.45913684368133545, "learning_rate": 1.1230149637229078e-05, "loss": 4.3163, "step": 22449 }, { "epoch": 0.6857055589492975, "grad_norm": 0.4571821987628937, "learning_rate": 1.1228147484145724e-05, "loss": 4.1569, "step": 22450 }, { "epoch": 0.6857361026267562, "grad_norm": 0.449959933757782, "learning_rate": 1.1226145457866886e-05, "loss": 4.3179, "step": 22451 }, { "epoch": 0.685766646304215, "grad_norm": 0.4538728892803192, "learning_rate": 1.1224143558411015e-05, "loss": 4.2665, "step": 22452 }, { "epoch": 0.6857971899816738, "grad_norm": 0.4451378285884857, "learning_rate": 1.122214178579653e-05, "loss": 4.259, "step": 22453 }, { "epoch": 0.6858277336591325, "grad_norm": 0.4489266574382782, "learning_rate": 1.1220140140041879e-05, "loss": 4.2572, "step": 22454 }, { "epoch": 0.6858582773365913, "grad_norm": 0.44826409220695496, "learning_rate": 1.1218138621165475e-05, "loss": 4.1664, "step": 22455 }, { "epoch": 0.6858888210140501, "grad_norm": 0.44593799114227295, "learning_rate": 1.1216137229185752e-05, "loss": 4.166, "step": 22456 }, { "epoch": 0.6859193646915088, "grad_norm": 0.4417325258255005, "learning_rate": 1.121413596412115e-05, "loss": 4.166, "step": 22457 }, { "epoch": 0.6859499083689676, "grad_norm": 0.449933260679245, "learning_rate": 1.1212134825990078e-05, "loss": 4.2973, "step": 22458 }, { "epoch": 0.6859804520464264, "grad_norm": 0.4479832947254181, "learning_rate": 1.1210133814810968e-05, "loss": 4.3258, "step": 22459 }, { "epoch": 0.6860109957238851, "grad_norm": 0.45246636867523193, "learning_rate": 1.1208132930602257e-05, "loss": 4.2413, "step": 22460 }, { "epoch": 0.6860415394013439, "grad_norm": 0.45860007405281067, "learning_rate": 1.1206132173382347e-05, "loss": 4.2532, "step": 22461 }, { "epoch": 0.6860720830788027, "grad_norm": 0.4615461826324463, "learning_rate": 1.120413154316967e-05, "loss": 4.3031, "step": 22462 }, { "epoch": 0.6861026267562614, "grad_norm": 0.45105603337287903, "learning_rate": 1.1202131039982658e-05, "loss": 4.2552, "step": 22463 }, { "epoch": 0.6861331704337202, "grad_norm": 0.45653361082077026, "learning_rate": 1.1200130663839711e-05, "loss": 4.2129, "step": 22464 }, { "epoch": 0.6861637141111789, "grad_norm": 0.4642999768257141, "learning_rate": 1.1198130414759262e-05, "loss": 4.3185, "step": 22465 }, { "epoch": 0.6861942577886377, "grad_norm": 0.4599066972732544, "learning_rate": 1.1196130292759716e-05, "loss": 4.1211, "step": 22466 }, { "epoch": 0.6862248014660965, "grad_norm": 0.45479390025138855, "learning_rate": 1.1194130297859504e-05, "loss": 4.2259, "step": 22467 }, { "epoch": 0.6862553451435552, "grad_norm": 0.45086124539375305, "learning_rate": 1.1192130430077033e-05, "loss": 4.2566, "step": 22468 }, { "epoch": 0.686285888821014, "grad_norm": 0.4598686099052429, "learning_rate": 1.1190130689430706e-05, "loss": 4.2854, "step": 22469 }, { "epoch": 0.6863164324984729, "grad_norm": 0.45717567205429077, "learning_rate": 1.1188131075938945e-05, "loss": 4.2237, "step": 22470 }, { "epoch": 0.6863469761759315, "grad_norm": 0.46091675758361816, "learning_rate": 1.1186131589620174e-05, "loss": 4.2917, "step": 22471 }, { "epoch": 0.6863775198533903, "grad_norm": 0.4490126371383667, "learning_rate": 1.1184132230492784e-05, "loss": 4.2432, "step": 22472 }, { "epoch": 0.6864080635308492, "grad_norm": 0.4434099495410919, "learning_rate": 1.118213299857519e-05, "loss": 4.3103, "step": 22473 }, { "epoch": 0.6864386072083078, "grad_norm": 0.45609262585639954, "learning_rate": 1.1180133893885811e-05, "loss": 4.2726, "step": 22474 }, { "epoch": 0.6864691508857667, "grad_norm": 0.4689633250236511, "learning_rate": 1.1178134916443034e-05, "loss": 4.2408, "step": 22475 }, { "epoch": 0.6864996945632255, "grad_norm": 0.4653984308242798, "learning_rate": 1.1176136066265278e-05, "loss": 4.3007, "step": 22476 }, { "epoch": 0.6865302382406842, "grad_norm": 0.4473908543586731, "learning_rate": 1.1174137343370953e-05, "loss": 4.145, "step": 22477 }, { "epoch": 0.686560781918143, "grad_norm": 0.44917726516723633, "learning_rate": 1.1172138747778443e-05, "loss": 4.2411, "step": 22478 }, { "epoch": 0.6865913255956018, "grad_norm": 0.45352619886398315, "learning_rate": 1.1170140279506164e-05, "loss": 4.2997, "step": 22479 }, { "epoch": 0.6866218692730605, "grad_norm": 0.4502789080142975, "learning_rate": 1.116814193857252e-05, "loss": 4.3136, "step": 22480 }, { "epoch": 0.6866524129505193, "grad_norm": 0.4521922469139099, "learning_rate": 1.1166143724995909e-05, "loss": 4.2974, "step": 22481 }, { "epoch": 0.686682956627978, "grad_norm": 0.4573599398136139, "learning_rate": 1.1164145638794715e-05, "loss": 4.2802, "step": 22482 }, { "epoch": 0.6867135003054368, "grad_norm": 0.4452800750732422, "learning_rate": 1.1162147679987353e-05, "loss": 4.3063, "step": 22483 }, { "epoch": 0.6867440439828956, "grad_norm": 0.4603477716445923, "learning_rate": 1.1160149848592205e-05, "loss": 4.3308, "step": 22484 }, { "epoch": 0.6867745876603543, "grad_norm": 0.4624602198600769, "learning_rate": 1.1158152144627682e-05, "loss": 4.3221, "step": 22485 }, { "epoch": 0.6868051313378131, "grad_norm": 0.46956866979599, "learning_rate": 1.115615456811216e-05, "loss": 4.3187, "step": 22486 }, { "epoch": 0.6868356750152719, "grad_norm": 0.4569092392921448, "learning_rate": 1.1154157119064038e-05, "loss": 4.2649, "step": 22487 }, { "epoch": 0.6868662186927306, "grad_norm": 0.45079800486564636, "learning_rate": 1.115215979750172e-05, "loss": 4.2305, "step": 22488 }, { "epoch": 0.6868967623701894, "grad_norm": 0.4508245587348938, "learning_rate": 1.1150162603443578e-05, "loss": 4.308, "step": 22489 }, { "epoch": 0.6869273060476482, "grad_norm": 0.4420104920864105, "learning_rate": 1.1148165536908012e-05, "loss": 4.3016, "step": 22490 }, { "epoch": 0.6869578497251069, "grad_norm": 0.4643767476081848, "learning_rate": 1.1146168597913415e-05, "loss": 4.2341, "step": 22491 }, { "epoch": 0.6869883934025657, "grad_norm": 0.45313331484794617, "learning_rate": 1.1144171786478158e-05, "loss": 4.2511, "step": 22492 }, { "epoch": 0.6870189370800245, "grad_norm": 0.4562123715877533, "learning_rate": 1.1142175102620637e-05, "loss": 4.3298, "step": 22493 }, { "epoch": 0.6870494807574832, "grad_norm": 0.4535899758338928, "learning_rate": 1.114017854635924e-05, "loss": 4.3635, "step": 22494 }, { "epoch": 0.687080024434942, "grad_norm": 0.4538962244987488, "learning_rate": 1.113818211771234e-05, "loss": 4.2807, "step": 22495 }, { "epoch": 0.6871105681124008, "grad_norm": 0.4577338397502899, "learning_rate": 1.113618581669833e-05, "loss": 4.3024, "step": 22496 }, { "epoch": 0.6871411117898595, "grad_norm": 0.45094233751296997, "learning_rate": 1.113418964333558e-05, "loss": 4.2577, "step": 22497 }, { "epoch": 0.6871716554673183, "grad_norm": 0.45930951833724976, "learning_rate": 1.1132193597642479e-05, "loss": 4.1418, "step": 22498 }, { "epoch": 0.687202199144777, "grad_norm": 0.4465688467025757, "learning_rate": 1.1130197679637404e-05, "loss": 4.2094, "step": 22499 }, { "epoch": 0.6872327428222358, "grad_norm": 0.4497171640396118, "learning_rate": 1.1128201889338723e-05, "loss": 4.2788, "step": 22500 }, { "epoch": 0.6872632864996946, "grad_norm": 0.4491575360298157, "learning_rate": 1.1126206226764818e-05, "loss": 4.312, "step": 22501 }, { "epoch": 0.6872938301771533, "grad_norm": 0.45210403203964233, "learning_rate": 1.1124210691934076e-05, "loss": 4.2249, "step": 22502 }, { "epoch": 0.6873243738546121, "grad_norm": 0.452057808637619, "learning_rate": 1.1122215284864849e-05, "loss": 4.3024, "step": 22503 }, { "epoch": 0.6873549175320709, "grad_norm": 0.46546363830566406, "learning_rate": 1.1120220005575522e-05, "loss": 4.2134, "step": 22504 }, { "epoch": 0.6873854612095296, "grad_norm": 0.4531290829181671, "learning_rate": 1.1118224854084475e-05, "loss": 4.3654, "step": 22505 }, { "epoch": 0.6874160048869884, "grad_norm": 0.45130300521850586, "learning_rate": 1.1116229830410058e-05, "loss": 4.1953, "step": 22506 }, { "epoch": 0.6874465485644472, "grad_norm": 0.45910778641700745, "learning_rate": 1.1114234934570652e-05, "loss": 4.201, "step": 22507 }, { "epoch": 0.6874770922419059, "grad_norm": 0.4577278792858124, "learning_rate": 1.1112240166584636e-05, "loss": 4.2031, "step": 22508 }, { "epoch": 0.6875076359193647, "grad_norm": 0.4583202302455902, "learning_rate": 1.1110245526470352e-05, "loss": 4.2831, "step": 22509 }, { "epoch": 0.6875381795968235, "grad_norm": 0.461153119802475, "learning_rate": 1.1108251014246185e-05, "loss": 4.2443, "step": 22510 }, { "epoch": 0.6875687232742822, "grad_norm": 0.44844383001327515, "learning_rate": 1.1106256629930497e-05, "loss": 4.2935, "step": 22511 }, { "epoch": 0.687599266951741, "grad_norm": 0.47031518816947937, "learning_rate": 1.110426237354164e-05, "loss": 4.344, "step": 22512 }, { "epoch": 0.6876298106291997, "grad_norm": 0.4471265375614166, "learning_rate": 1.1102268245097994e-05, "loss": 4.2981, "step": 22513 }, { "epoch": 0.6876603543066585, "grad_norm": 0.44967004656791687, "learning_rate": 1.110027424461791e-05, "loss": 4.2907, "step": 22514 }, { "epoch": 0.6876908979841173, "grad_norm": 0.450427383184433, "learning_rate": 1.1098280372119738e-05, "loss": 4.2642, "step": 22515 }, { "epoch": 0.687721441661576, "grad_norm": 0.45425400137901306, "learning_rate": 1.1096286627621852e-05, "loss": 4.3718, "step": 22516 }, { "epoch": 0.6877519853390348, "grad_norm": 0.46080461144447327, "learning_rate": 1.1094293011142599e-05, "loss": 4.2463, "step": 22517 }, { "epoch": 0.6877825290164936, "grad_norm": 0.4652978181838989, "learning_rate": 1.1092299522700336e-05, "loss": 4.2855, "step": 22518 }, { "epoch": 0.6878130726939523, "grad_norm": 0.4573077857494354, "learning_rate": 1.1090306162313435e-05, "loss": 4.3272, "step": 22519 }, { "epoch": 0.6878436163714111, "grad_norm": 0.44872406125068665, "learning_rate": 1.1088312930000224e-05, "loss": 4.3328, "step": 22520 }, { "epoch": 0.6878741600488699, "grad_norm": 0.4529697000980377, "learning_rate": 1.108631982577907e-05, "loss": 4.1977, "step": 22521 }, { "epoch": 0.6879047037263286, "grad_norm": 0.45153507590293884, "learning_rate": 1.1084326849668334e-05, "loss": 4.271, "step": 22522 }, { "epoch": 0.6879352474037874, "grad_norm": 0.4682513177394867, "learning_rate": 1.1082334001686345e-05, "loss": 4.1883, "step": 22523 }, { "epoch": 0.6879657910812462, "grad_norm": 0.4539635479450226, "learning_rate": 1.1080341281851462e-05, "loss": 4.278, "step": 22524 }, { "epoch": 0.6879963347587049, "grad_norm": 0.45512163639068604, "learning_rate": 1.1078348690182044e-05, "loss": 4.2679, "step": 22525 }, { "epoch": 0.6880268784361637, "grad_norm": 0.4501354992389679, "learning_rate": 1.1076356226696416e-05, "loss": 4.257, "step": 22526 }, { "epoch": 0.6880574221136225, "grad_norm": 0.4483231008052826, "learning_rate": 1.1074363891412944e-05, "loss": 4.2518, "step": 22527 }, { "epoch": 0.6880879657910812, "grad_norm": 0.45179152488708496, "learning_rate": 1.1072371684349958e-05, "loss": 4.2762, "step": 22528 }, { "epoch": 0.68811850946854, "grad_norm": 0.45671895146369934, "learning_rate": 1.1070379605525813e-05, "loss": 4.3042, "step": 22529 }, { "epoch": 0.6881490531459987, "grad_norm": 0.45778778195381165, "learning_rate": 1.1068387654958848e-05, "loss": 4.2186, "step": 22530 }, { "epoch": 0.6881795968234575, "grad_norm": 0.4519447088241577, "learning_rate": 1.1066395832667386e-05, "loss": 4.3181, "step": 22531 }, { "epoch": 0.6882101405009163, "grad_norm": 0.43883344531059265, "learning_rate": 1.1064404138669788e-05, "loss": 4.2578, "step": 22532 }, { "epoch": 0.688240684178375, "grad_norm": 0.45558223128318787, "learning_rate": 1.106241257298439e-05, "loss": 4.2594, "step": 22533 }, { "epoch": 0.6882712278558338, "grad_norm": 0.4551319479942322, "learning_rate": 1.106042113562952e-05, "loss": 4.3248, "step": 22534 }, { "epoch": 0.6883017715332926, "grad_norm": 0.4466346800327301, "learning_rate": 1.1058429826623517e-05, "loss": 4.2807, "step": 22535 }, { "epoch": 0.6883323152107513, "grad_norm": 0.46547839045524597, "learning_rate": 1.105643864598473e-05, "loss": 4.2186, "step": 22536 }, { "epoch": 0.6883628588882101, "grad_norm": 0.45579400658607483, "learning_rate": 1.105444759373147e-05, "loss": 4.3019, "step": 22537 }, { "epoch": 0.6883934025656689, "grad_norm": 0.4460242688655853, "learning_rate": 1.1052456669882082e-05, "loss": 4.2122, "step": 22538 }, { "epoch": 0.6884239462431276, "grad_norm": 0.45216289162635803, "learning_rate": 1.1050465874454907e-05, "loss": 4.2918, "step": 22539 }, { "epoch": 0.6884544899205864, "grad_norm": 0.4489406645298004, "learning_rate": 1.1048475207468253e-05, "loss": 4.2726, "step": 22540 }, { "epoch": 0.6884850335980452, "grad_norm": 0.45306017994880676, "learning_rate": 1.1046484668940463e-05, "loss": 4.16, "step": 22541 }, { "epoch": 0.6885155772755039, "grad_norm": 0.4555571377277374, "learning_rate": 1.1044494258889873e-05, "loss": 4.266, "step": 22542 }, { "epoch": 0.6885461209529627, "grad_norm": 0.4660964012145996, "learning_rate": 1.104250397733479e-05, "loss": 4.2168, "step": 22543 }, { "epoch": 0.6885766646304216, "grad_norm": 0.4683650732040405, "learning_rate": 1.1040513824293556e-05, "loss": 4.2339, "step": 22544 }, { "epoch": 0.6886072083078802, "grad_norm": 0.4777982831001282, "learning_rate": 1.103852379978449e-05, "loss": 4.2075, "step": 22545 }, { "epoch": 0.688637751985339, "grad_norm": 0.4636048674583435, "learning_rate": 1.1036533903825905e-05, "loss": 4.3075, "step": 22546 }, { "epoch": 0.6886682956627977, "grad_norm": 0.45253196358680725, "learning_rate": 1.103454413643614e-05, "loss": 4.2887, "step": 22547 }, { "epoch": 0.6886988393402566, "grad_norm": 0.4563131034374237, "learning_rate": 1.1032554497633496e-05, "loss": 4.3674, "step": 22548 }, { "epoch": 0.6887293830177154, "grad_norm": 0.44933006167411804, "learning_rate": 1.1030564987436306e-05, "loss": 4.2254, "step": 22549 }, { "epoch": 0.688759926695174, "grad_norm": 0.4525240361690521, "learning_rate": 1.1028575605862899e-05, "loss": 4.2458, "step": 22550 }, { "epoch": 0.6887904703726329, "grad_norm": 0.45991551876068115, "learning_rate": 1.1026586352931567e-05, "loss": 4.3156, "step": 22551 }, { "epoch": 0.6888210140500917, "grad_norm": 0.4519025981426239, "learning_rate": 1.1024597228660638e-05, "loss": 4.2392, "step": 22552 }, { "epoch": 0.6888515577275504, "grad_norm": 0.4570424556732178, "learning_rate": 1.1022608233068438e-05, "loss": 4.2818, "step": 22553 }, { "epoch": 0.6888821014050092, "grad_norm": 0.45689699053764343, "learning_rate": 1.1020619366173262e-05, "loss": 4.2238, "step": 22554 }, { "epoch": 0.688912645082468, "grad_norm": 0.4506707489490509, "learning_rate": 1.101863062799343e-05, "loss": 4.2707, "step": 22555 }, { "epoch": 0.6889431887599267, "grad_norm": 0.4478841722011566, "learning_rate": 1.1016642018547266e-05, "loss": 4.2962, "step": 22556 }, { "epoch": 0.6889737324373855, "grad_norm": 0.4466427266597748, "learning_rate": 1.1014653537853056e-05, "loss": 4.2935, "step": 22557 }, { "epoch": 0.6890042761148443, "grad_norm": 0.44897541403770447, "learning_rate": 1.1012665185929124e-05, "loss": 4.2263, "step": 22558 }, { "epoch": 0.689034819792303, "grad_norm": 0.45473620295524597, "learning_rate": 1.1010676962793785e-05, "loss": 4.2037, "step": 22559 }, { "epoch": 0.6890653634697618, "grad_norm": 0.46284082531929016, "learning_rate": 1.1008688868465333e-05, "loss": 4.3473, "step": 22560 }, { "epoch": 0.6890959071472206, "grad_norm": 0.46013543009757996, "learning_rate": 1.100670090296207e-05, "loss": 4.2643, "step": 22561 }, { "epoch": 0.6891264508246793, "grad_norm": 0.45548906922340393, "learning_rate": 1.100471306630231e-05, "loss": 4.3321, "step": 22562 }, { "epoch": 0.6891569945021381, "grad_norm": 0.4441363513469696, "learning_rate": 1.1002725358504348e-05, "loss": 4.2461, "step": 22563 }, { "epoch": 0.6891875381795968, "grad_norm": 0.47240301966667175, "learning_rate": 1.1000737779586501e-05, "loss": 4.2656, "step": 22564 }, { "epoch": 0.6892180818570556, "grad_norm": 0.44633233547210693, "learning_rate": 1.0998750329567046e-05, "loss": 4.2524, "step": 22565 }, { "epoch": 0.6892486255345144, "grad_norm": 0.46028733253479004, "learning_rate": 1.0996763008464297e-05, "loss": 4.2889, "step": 22566 }, { "epoch": 0.6892791692119731, "grad_norm": 0.4526899456977844, "learning_rate": 1.099477581629656e-05, "loss": 4.2325, "step": 22567 }, { "epoch": 0.6893097128894319, "grad_norm": 0.44918474555015564, "learning_rate": 1.0992788753082114e-05, "loss": 4.3153, "step": 22568 }, { "epoch": 0.6893402565668907, "grad_norm": 0.4438585042953491, "learning_rate": 1.0990801818839263e-05, "loss": 4.2238, "step": 22569 }, { "epoch": 0.6893708002443494, "grad_norm": 0.45590394735336304, "learning_rate": 1.0988815013586312e-05, "loss": 4.3556, "step": 22570 }, { "epoch": 0.6894013439218082, "grad_norm": 0.45310553908348083, "learning_rate": 1.0986828337341535e-05, "loss": 4.3391, "step": 22571 }, { "epoch": 0.689431887599267, "grad_norm": 0.4453124701976776, "learning_rate": 1.0984841790123235e-05, "loss": 4.279, "step": 22572 }, { "epoch": 0.6894624312767257, "grad_norm": 0.4519931972026825, "learning_rate": 1.098285537194971e-05, "loss": 4.3025, "step": 22573 }, { "epoch": 0.6894929749541845, "grad_norm": 0.45379966497421265, "learning_rate": 1.0980869082839238e-05, "loss": 4.3024, "step": 22574 }, { "epoch": 0.6895235186316433, "grad_norm": 0.4620403051376343, "learning_rate": 1.0978882922810116e-05, "loss": 4.2186, "step": 22575 }, { "epoch": 0.689554062309102, "grad_norm": 0.44419869780540466, "learning_rate": 1.0976896891880622e-05, "loss": 4.2393, "step": 22576 }, { "epoch": 0.6895846059865608, "grad_norm": 0.44837117195129395, "learning_rate": 1.0974910990069056e-05, "loss": 4.2068, "step": 22577 }, { "epoch": 0.6896151496640196, "grad_norm": 0.46494507789611816, "learning_rate": 1.0972925217393687e-05, "loss": 4.355, "step": 22578 }, { "epoch": 0.6896456933414783, "grad_norm": 0.46182894706726074, "learning_rate": 1.0970939573872818e-05, "loss": 4.244, "step": 22579 }, { "epoch": 0.6896762370189371, "grad_norm": 0.4580952227115631, "learning_rate": 1.096895405952471e-05, "loss": 4.0906, "step": 22580 }, { "epoch": 0.6897067806963958, "grad_norm": 0.45077183842658997, "learning_rate": 1.0966968674367667e-05, "loss": 4.2982, "step": 22581 }, { "epoch": 0.6897373243738546, "grad_norm": 0.45683977007865906, "learning_rate": 1.0964983418419947e-05, "loss": 4.2632, "step": 22582 }, { "epoch": 0.6897678680513134, "grad_norm": 0.44736191630363464, "learning_rate": 1.0962998291699842e-05, "loss": 4.2913, "step": 22583 }, { "epoch": 0.6897984117287721, "grad_norm": 0.4555202126502991, "learning_rate": 1.0961013294225638e-05, "loss": 4.2559, "step": 22584 }, { "epoch": 0.6898289554062309, "grad_norm": 0.4554537236690521, "learning_rate": 1.0959028426015595e-05, "loss": 4.2723, "step": 22585 }, { "epoch": 0.6898594990836897, "grad_norm": 0.4567093253135681, "learning_rate": 1.0957043687087995e-05, "loss": 4.1786, "step": 22586 }, { "epoch": 0.6898900427611484, "grad_norm": 0.45223644375801086, "learning_rate": 1.0955059077461121e-05, "loss": 4.2716, "step": 22587 }, { "epoch": 0.6899205864386072, "grad_norm": 0.45412561297416687, "learning_rate": 1.0953074597153234e-05, "loss": 4.2579, "step": 22588 }, { "epoch": 0.689951130116066, "grad_norm": 0.45070376992225647, "learning_rate": 1.095109024618261e-05, "loss": 4.2041, "step": 22589 }, { "epoch": 0.6899816737935247, "grad_norm": 0.45501983165740967, "learning_rate": 1.094910602456753e-05, "loss": 4.3198, "step": 22590 }, { "epoch": 0.6900122174709835, "grad_norm": 0.44825318455696106, "learning_rate": 1.0947121932326254e-05, "loss": 4.2942, "step": 22591 }, { "epoch": 0.6900427611484423, "grad_norm": 0.4430406093597412, "learning_rate": 1.0945137969477046e-05, "loss": 4.2787, "step": 22592 }, { "epoch": 0.690073304825901, "grad_norm": 0.4602745473384857, "learning_rate": 1.0943154136038187e-05, "loss": 4.2774, "step": 22593 }, { "epoch": 0.6901038485033598, "grad_norm": 0.4692747890949249, "learning_rate": 1.0941170432027922e-05, "loss": 4.2169, "step": 22594 }, { "epoch": 0.6901343921808186, "grad_norm": 0.4474954605102539, "learning_rate": 1.0939186857464534e-05, "loss": 4.1976, "step": 22595 }, { "epoch": 0.6901649358582773, "grad_norm": 0.44727417826652527, "learning_rate": 1.0937203412366287e-05, "loss": 4.3061, "step": 22596 }, { "epoch": 0.6901954795357361, "grad_norm": 0.4492981731891632, "learning_rate": 1.0935220096751433e-05, "loss": 4.278, "step": 22597 }, { "epoch": 0.6902260232131948, "grad_norm": 0.44962450861930847, "learning_rate": 1.0933236910638248e-05, "loss": 4.2795, "step": 22598 }, { "epoch": 0.6902565668906536, "grad_norm": 0.44615936279296875, "learning_rate": 1.093125385404497e-05, "loss": 4.253, "step": 22599 }, { "epoch": 0.6902871105681124, "grad_norm": 0.4539259374141693, "learning_rate": 1.0929270926989876e-05, "loss": 4.265, "step": 22600 }, { "epoch": 0.6903176542455711, "grad_norm": 0.4440503418445587, "learning_rate": 1.0927288129491226e-05, "loss": 4.2512, "step": 22601 }, { "epoch": 0.6903481979230299, "grad_norm": 0.45712384581565857, "learning_rate": 1.092530546156726e-05, "loss": 4.2262, "step": 22602 }, { "epoch": 0.6903787416004887, "grad_norm": 0.45708492398262024, "learning_rate": 1.0923322923236245e-05, "loss": 4.2821, "step": 22603 }, { "epoch": 0.6904092852779474, "grad_norm": 0.45311683416366577, "learning_rate": 1.092134051451644e-05, "loss": 4.3186, "step": 22604 }, { "epoch": 0.6904398289554062, "grad_norm": 0.4485797882080078, "learning_rate": 1.0919358235426083e-05, "loss": 4.2959, "step": 22605 }, { "epoch": 0.690470372632865, "grad_norm": 0.4580337405204773, "learning_rate": 1.0917376085983444e-05, "loss": 4.3224, "step": 22606 }, { "epoch": 0.6905009163103237, "grad_norm": 0.44359612464904785, "learning_rate": 1.0915394066206756e-05, "loss": 4.2651, "step": 22607 }, { "epoch": 0.6905314599877825, "grad_norm": 0.4409966766834259, "learning_rate": 1.0913412176114285e-05, "loss": 4.2173, "step": 22608 }, { "epoch": 0.6905620036652413, "grad_norm": 0.4563532769680023, "learning_rate": 1.091143041572426e-05, "loss": 4.2957, "step": 22609 }, { "epoch": 0.6905925473427, "grad_norm": 0.4648640751838684, "learning_rate": 1.0909448785054949e-05, "loss": 4.3381, "step": 22610 }, { "epoch": 0.6906230910201588, "grad_norm": 0.45674601197242737, "learning_rate": 1.0907467284124578e-05, "loss": 4.251, "step": 22611 }, { "epoch": 0.6906536346976176, "grad_norm": 0.46855688095092773, "learning_rate": 1.0905485912951402e-05, "loss": 4.3158, "step": 22612 }, { "epoch": 0.6906841783750763, "grad_norm": 0.45339927077293396, "learning_rate": 1.0903504671553671e-05, "loss": 4.3118, "step": 22613 }, { "epoch": 0.6907147220525351, "grad_norm": 0.45970702171325684, "learning_rate": 1.0901523559949614e-05, "loss": 4.2343, "step": 22614 }, { "epoch": 0.6907452657299938, "grad_norm": 0.44798675179481506, "learning_rate": 1.0899542578157488e-05, "loss": 4.2583, "step": 22615 }, { "epoch": 0.6907758094074526, "grad_norm": 0.45234161615371704, "learning_rate": 1.0897561726195512e-05, "loss": 4.372, "step": 22616 }, { "epoch": 0.6908063530849115, "grad_norm": 0.45369040966033936, "learning_rate": 1.0895581004081937e-05, "loss": 4.2432, "step": 22617 }, { "epoch": 0.6908368967623701, "grad_norm": 0.44894251227378845, "learning_rate": 1.0893600411835005e-05, "loss": 4.2668, "step": 22618 }, { "epoch": 0.690867440439829, "grad_norm": 0.4448123574256897, "learning_rate": 1.0891619949472942e-05, "loss": 4.3199, "step": 22619 }, { "epoch": 0.6908979841172878, "grad_norm": 0.4536854028701782, "learning_rate": 1.0889639617013986e-05, "loss": 4.2725, "step": 22620 }, { "epoch": 0.6909285277947464, "grad_norm": 0.4539216160774231, "learning_rate": 1.0887659414476384e-05, "loss": 4.299, "step": 22621 }, { "epoch": 0.6909590714722053, "grad_norm": 0.4438766837120056, "learning_rate": 1.0885679341878346e-05, "loss": 4.2468, "step": 22622 }, { "epoch": 0.6909896151496641, "grad_norm": 0.4579436182975769, "learning_rate": 1.0883699399238125e-05, "loss": 4.3071, "step": 22623 }, { "epoch": 0.6910201588271228, "grad_norm": 0.4642106890678406, "learning_rate": 1.0881719586573943e-05, "loss": 4.2215, "step": 22624 }, { "epoch": 0.6910507025045816, "grad_norm": 0.4561261832714081, "learning_rate": 1.0879739903904015e-05, "loss": 4.1898, "step": 22625 }, { "epoch": 0.6910812461820404, "grad_norm": 0.4572647213935852, "learning_rate": 1.0877760351246586e-05, "loss": 4.3039, "step": 22626 }, { "epoch": 0.6911117898594991, "grad_norm": 0.45066142082214355, "learning_rate": 1.0875780928619886e-05, "loss": 4.2357, "step": 22627 }, { "epoch": 0.6911423335369579, "grad_norm": 0.4538658857345581, "learning_rate": 1.0873801636042123e-05, "loss": 4.2561, "step": 22628 }, { "epoch": 0.6911728772144167, "grad_norm": 0.45707985758781433, "learning_rate": 1.0871822473531531e-05, "loss": 4.2736, "step": 22629 }, { "epoch": 0.6912034208918754, "grad_norm": 0.44623276591300964, "learning_rate": 1.0869843441106342e-05, "loss": 4.1679, "step": 22630 }, { "epoch": 0.6912339645693342, "grad_norm": 0.4465060532093048, "learning_rate": 1.0867864538784764e-05, "loss": 4.117, "step": 22631 }, { "epoch": 0.6912645082467929, "grad_norm": 0.4534396231174469, "learning_rate": 1.086588576658503e-05, "loss": 4.1715, "step": 22632 }, { "epoch": 0.6912950519242517, "grad_norm": 0.46584171056747437, "learning_rate": 1.0863907124525341e-05, "loss": 4.2329, "step": 22633 }, { "epoch": 0.6913255956017105, "grad_norm": 0.45631346106529236, "learning_rate": 1.0861928612623931e-05, "loss": 4.3571, "step": 22634 }, { "epoch": 0.6913561392791692, "grad_norm": 0.46050602197647095, "learning_rate": 1.085995023089902e-05, "loss": 4.3314, "step": 22635 }, { "epoch": 0.691386682956628, "grad_norm": 0.4473913609981537, "learning_rate": 1.0857971979368812e-05, "loss": 4.3357, "step": 22636 }, { "epoch": 0.6914172266340868, "grad_norm": 0.45471617579460144, "learning_rate": 1.0855993858051533e-05, "loss": 4.2202, "step": 22637 }, { "epoch": 0.6914477703115455, "grad_norm": 0.4787098169326782, "learning_rate": 1.0854015866965382e-05, "loss": 4.2752, "step": 22638 }, { "epoch": 0.6914783139890043, "grad_norm": 0.4444624185562134, "learning_rate": 1.085203800612859e-05, "loss": 4.2746, "step": 22639 }, { "epoch": 0.6915088576664631, "grad_norm": 0.43885985016822815, "learning_rate": 1.0850060275559346e-05, "loss": 4.31, "step": 22640 }, { "epoch": 0.6915394013439218, "grad_norm": 0.4661809206008911, "learning_rate": 1.0848082675275883e-05, "loss": 4.2708, "step": 22641 }, { "epoch": 0.6915699450213806, "grad_norm": 0.4482782483100891, "learning_rate": 1.0846105205296392e-05, "loss": 4.3479, "step": 22642 }, { "epoch": 0.6916004886988394, "grad_norm": 0.4540477991104126, "learning_rate": 1.0844127865639087e-05, "loss": 4.1737, "step": 22643 }, { "epoch": 0.6916310323762981, "grad_norm": 0.4556243419647217, "learning_rate": 1.0842150656322184e-05, "loss": 4.2868, "step": 22644 }, { "epoch": 0.6916615760537569, "grad_norm": 0.4550873935222626, "learning_rate": 1.0840173577363869e-05, "loss": 4.3399, "step": 22645 }, { "epoch": 0.6916921197312157, "grad_norm": 0.462495893239975, "learning_rate": 1.0838196628782355e-05, "loss": 4.27, "step": 22646 }, { "epoch": 0.6917226634086744, "grad_norm": 0.4458850622177124, "learning_rate": 1.0836219810595857e-05, "loss": 4.2994, "step": 22647 }, { "epoch": 0.6917532070861332, "grad_norm": 0.46421459317207336, "learning_rate": 1.0834243122822557e-05, "loss": 4.3333, "step": 22648 }, { "epoch": 0.6917837507635919, "grad_norm": 0.44956451654434204, "learning_rate": 1.083226656548067e-05, "loss": 4.2262, "step": 22649 }, { "epoch": 0.6918142944410507, "grad_norm": 0.4632648229598999, "learning_rate": 1.0830290138588383e-05, "loss": 4.3233, "step": 22650 }, { "epoch": 0.6918448381185095, "grad_norm": 0.4550561010837555, "learning_rate": 1.0828313842163899e-05, "loss": 4.1887, "step": 22651 }, { "epoch": 0.6918753817959682, "grad_norm": 0.44464242458343506, "learning_rate": 1.0826337676225426e-05, "loss": 4.2533, "step": 22652 }, { "epoch": 0.691905925473427, "grad_norm": 0.44952133297920227, "learning_rate": 1.0824361640791139e-05, "loss": 4.2543, "step": 22653 }, { "epoch": 0.6919364691508858, "grad_norm": 0.4475139379501343, "learning_rate": 1.082238573587925e-05, "loss": 4.2234, "step": 22654 }, { "epoch": 0.6919670128283445, "grad_norm": 0.46366867423057556, "learning_rate": 1.082040996150795e-05, "loss": 4.3358, "step": 22655 }, { "epoch": 0.6919975565058033, "grad_norm": 0.44931313395500183, "learning_rate": 1.0818434317695412e-05, "loss": 4.3056, "step": 22656 }, { "epoch": 0.6920281001832621, "grad_norm": 0.45809534192085266, "learning_rate": 1.0816458804459842e-05, "loss": 4.2104, "step": 22657 }, { "epoch": 0.6920586438607208, "grad_norm": 0.451381653547287, "learning_rate": 1.0814483421819438e-05, "loss": 4.2589, "step": 22658 }, { "epoch": 0.6920891875381796, "grad_norm": 0.4509986639022827, "learning_rate": 1.0812508169792368e-05, "loss": 4.3502, "step": 22659 }, { "epoch": 0.6921197312156384, "grad_norm": 0.45694029331207275, "learning_rate": 1.0810533048396831e-05, "loss": 4.1683, "step": 22660 }, { "epoch": 0.6921502748930971, "grad_norm": 0.4560030698776245, "learning_rate": 1.0808558057651023e-05, "loss": 4.3221, "step": 22661 }, { "epoch": 0.6921808185705559, "grad_norm": 0.44934165477752686, "learning_rate": 1.0806583197573106e-05, "loss": 4.2404, "step": 22662 }, { "epoch": 0.6922113622480146, "grad_norm": 0.45436999201774597, "learning_rate": 1.0804608468181282e-05, "loss": 4.2687, "step": 22663 }, { "epoch": 0.6922419059254734, "grad_norm": 0.44811633229255676, "learning_rate": 1.0802633869493719e-05, "loss": 4.1861, "step": 22664 }, { "epoch": 0.6922724496029322, "grad_norm": 0.45096251368522644, "learning_rate": 1.0800659401528607e-05, "loss": 4.2936, "step": 22665 }, { "epoch": 0.6923029932803909, "grad_norm": 0.45527753233909607, "learning_rate": 1.0798685064304134e-05, "loss": 4.308, "step": 22666 }, { "epoch": 0.6923335369578497, "grad_norm": 0.45262110233306885, "learning_rate": 1.0796710857838457e-05, "loss": 4.237, "step": 22667 }, { "epoch": 0.6923640806353085, "grad_norm": 0.4590744078159332, "learning_rate": 1.079473678214977e-05, "loss": 4.2805, "step": 22668 }, { "epoch": 0.6923946243127672, "grad_norm": 0.4589497148990631, "learning_rate": 1.0792762837256251e-05, "loss": 4.1819, "step": 22669 }, { "epoch": 0.692425167990226, "grad_norm": 0.44602909684181213, "learning_rate": 1.079078902317607e-05, "loss": 4.2945, "step": 22670 }, { "epoch": 0.6924557116676848, "grad_norm": 0.4459098279476166, "learning_rate": 1.0788815339927392e-05, "loss": 4.1993, "step": 22671 }, { "epoch": 0.6924862553451435, "grad_norm": 0.46135786175727844, "learning_rate": 1.0786841787528404e-05, "loss": 4.3081, "step": 22672 }, { "epoch": 0.6925167990226023, "grad_norm": 0.46795448660850525, "learning_rate": 1.0784868365997265e-05, "loss": 4.2447, "step": 22673 }, { "epoch": 0.6925473427000611, "grad_norm": 0.45614495873451233, "learning_rate": 1.078289507535215e-05, "loss": 4.2529, "step": 22674 }, { "epoch": 0.6925778863775198, "grad_norm": 0.4483983516693115, "learning_rate": 1.078092191561124e-05, "loss": 4.2442, "step": 22675 }, { "epoch": 0.6926084300549786, "grad_norm": 0.45160698890686035, "learning_rate": 1.0778948886792683e-05, "loss": 4.2787, "step": 22676 }, { "epoch": 0.6926389737324374, "grad_norm": 0.45410099625587463, "learning_rate": 1.0776975988914656e-05, "loss": 4.214, "step": 22677 }, { "epoch": 0.6926695174098961, "grad_norm": 0.49219027161598206, "learning_rate": 1.0775003221995334e-05, "loss": 4.2414, "step": 22678 }, { "epoch": 0.6927000610873549, "grad_norm": 0.4502160847187042, "learning_rate": 1.0773030586052859e-05, "loss": 4.2448, "step": 22679 }, { "epoch": 0.6927306047648136, "grad_norm": 0.4653753936290741, "learning_rate": 1.0771058081105417e-05, "loss": 4.2275, "step": 22680 }, { "epoch": 0.6927611484422724, "grad_norm": 0.45114630460739136, "learning_rate": 1.076908570717115e-05, "loss": 4.3289, "step": 22681 }, { "epoch": 0.6927916921197312, "grad_norm": 0.44650688767433167, "learning_rate": 1.0767113464268228e-05, "loss": 4.2334, "step": 22682 }, { "epoch": 0.6928222357971899, "grad_norm": 0.44575443863868713, "learning_rate": 1.0765141352414817e-05, "loss": 4.3182, "step": 22683 }, { "epoch": 0.6928527794746487, "grad_norm": 0.46260708570480347, "learning_rate": 1.0763169371629062e-05, "loss": 4.2302, "step": 22684 }, { "epoch": 0.6928833231521075, "grad_norm": 0.4556620717048645, "learning_rate": 1.0761197521929134e-05, "loss": 4.2662, "step": 22685 }, { "epoch": 0.6929138668295662, "grad_norm": 0.44569703936576843, "learning_rate": 1.0759225803333173e-05, "loss": 4.2706, "step": 22686 }, { "epoch": 0.692944410507025, "grad_norm": 0.4535895586013794, "learning_rate": 1.075725421585935e-05, "loss": 4.1357, "step": 22687 }, { "epoch": 0.6929749541844838, "grad_norm": 0.46421822905540466, "learning_rate": 1.07552827595258e-05, "loss": 4.1499, "step": 22688 }, { "epoch": 0.6930054978619425, "grad_norm": 0.4588136672973633, "learning_rate": 1.0753311434350699e-05, "loss": 4.2589, "step": 22689 }, { "epoch": 0.6930360415394013, "grad_norm": 0.45476430654525757, "learning_rate": 1.0751340240352173e-05, "loss": 4.2693, "step": 22690 }, { "epoch": 0.6930665852168602, "grad_norm": 0.4592219591140747, "learning_rate": 1.0749369177548383e-05, "loss": 4.2486, "step": 22691 }, { "epoch": 0.6930971288943188, "grad_norm": 0.4585663080215454, "learning_rate": 1.0747398245957488e-05, "loss": 4.2552, "step": 22692 }, { "epoch": 0.6931276725717777, "grad_norm": 0.44638702273368835, "learning_rate": 1.0745427445597614e-05, "loss": 4.2655, "step": 22693 }, { "epoch": 0.6931582162492365, "grad_norm": 0.45737308263778687, "learning_rate": 1.0743456776486922e-05, "loss": 4.3262, "step": 22694 }, { "epoch": 0.6931887599266952, "grad_norm": 0.4547407627105713, "learning_rate": 1.0741486238643558e-05, "loss": 4.331, "step": 22695 }, { "epoch": 0.693219303604154, "grad_norm": 0.4454900920391083, "learning_rate": 1.0739515832085655e-05, "loss": 4.3212, "step": 22696 }, { "epoch": 0.6932498472816127, "grad_norm": 0.45567476749420166, "learning_rate": 1.0737545556831372e-05, "loss": 4.2318, "step": 22697 }, { "epoch": 0.6932803909590715, "grad_norm": 0.4591873288154602, "learning_rate": 1.073557541289883e-05, "loss": 4.2281, "step": 22698 }, { "epoch": 0.6933109346365303, "grad_norm": 0.46649184823036194, "learning_rate": 1.0733605400306179e-05, "loss": 4.2888, "step": 22699 }, { "epoch": 0.693341478313989, "grad_norm": 0.47133883833885193, "learning_rate": 1.0731635519071568e-05, "loss": 4.3377, "step": 22700 }, { "epoch": 0.6933720219914478, "grad_norm": 0.45567017793655396, "learning_rate": 1.0729665769213121e-05, "loss": 4.2539, "step": 22701 }, { "epoch": 0.6934025656689066, "grad_norm": 0.4648129642009735, "learning_rate": 1.0727696150748972e-05, "loss": 4.2886, "step": 22702 }, { "epoch": 0.6934331093463653, "grad_norm": 0.4623138904571533, "learning_rate": 1.0725726663697273e-05, "loss": 4.212, "step": 22703 }, { "epoch": 0.6934636530238241, "grad_norm": 0.4668419063091278, "learning_rate": 1.0723757308076138e-05, "loss": 4.239, "step": 22704 }, { "epoch": 0.6934941967012829, "grad_norm": 0.46295979619026184, "learning_rate": 1.0721788083903708e-05, "loss": 4.2022, "step": 22705 }, { "epoch": 0.6935247403787416, "grad_norm": 0.45050132274627686, "learning_rate": 1.0719818991198127e-05, "loss": 4.31, "step": 22706 }, { "epoch": 0.6935552840562004, "grad_norm": 0.45351794362068176, "learning_rate": 1.0717850029977505e-05, "loss": 4.2912, "step": 22707 }, { "epoch": 0.6935858277336592, "grad_norm": 0.4560956656932831, "learning_rate": 1.0715881200259981e-05, "loss": 4.1918, "step": 22708 }, { "epoch": 0.6936163714111179, "grad_norm": 0.45509642362594604, "learning_rate": 1.071391250206369e-05, "loss": 4.3338, "step": 22709 }, { "epoch": 0.6936469150885767, "grad_norm": 0.4501149654388428, "learning_rate": 1.0711943935406747e-05, "loss": 4.2391, "step": 22710 }, { "epoch": 0.6936774587660355, "grad_norm": 0.4556811451911926, "learning_rate": 1.0709975500307279e-05, "loss": 4.2787, "step": 22711 }, { "epoch": 0.6937080024434942, "grad_norm": 0.4505477547645569, "learning_rate": 1.0708007196783423e-05, "loss": 4.2572, "step": 22712 }, { "epoch": 0.693738546120953, "grad_norm": 0.4500192105770111, "learning_rate": 1.0706039024853284e-05, "loss": 4.2665, "step": 22713 }, { "epoch": 0.6937690897984117, "grad_norm": 0.44798335433006287, "learning_rate": 1.0704070984535003e-05, "loss": 4.2273, "step": 22714 }, { "epoch": 0.6937996334758705, "grad_norm": 0.4523986876010895, "learning_rate": 1.0702103075846681e-05, "loss": 4.2179, "step": 22715 }, { "epoch": 0.6938301771533293, "grad_norm": 0.45388171076774597, "learning_rate": 1.0700135298806458e-05, "loss": 4.2457, "step": 22716 }, { "epoch": 0.693860720830788, "grad_norm": 0.4543318748474121, "learning_rate": 1.069816765343243e-05, "loss": 4.2347, "step": 22717 }, { "epoch": 0.6938912645082468, "grad_norm": 0.4729534685611725, "learning_rate": 1.0696200139742738e-05, "loss": 4.2348, "step": 22718 }, { "epoch": 0.6939218081857056, "grad_norm": 0.4347546100616455, "learning_rate": 1.0694232757755474e-05, "loss": 4.2022, "step": 22719 }, { "epoch": 0.6939523518631643, "grad_norm": 0.4449945092201233, "learning_rate": 1.0692265507488774e-05, "loss": 4.178, "step": 22720 }, { "epoch": 0.6939828955406231, "grad_norm": 0.4608657658100128, "learning_rate": 1.0690298388960732e-05, "loss": 4.306, "step": 22721 }, { "epoch": 0.6940134392180819, "grad_norm": 0.4572378396987915, "learning_rate": 1.0688331402189469e-05, "loss": 4.314, "step": 22722 }, { "epoch": 0.6940439828955406, "grad_norm": 0.4479822516441345, "learning_rate": 1.068636454719311e-05, "loss": 4.2877, "step": 22723 }, { "epoch": 0.6940745265729994, "grad_norm": 0.4591982364654541, "learning_rate": 1.0684397823989738e-05, "loss": 4.3184, "step": 22724 }, { "epoch": 0.6941050702504582, "grad_norm": 0.46644577383995056, "learning_rate": 1.0682431232597481e-05, "loss": 4.2596, "step": 22725 }, { "epoch": 0.6941356139279169, "grad_norm": 0.46868130564689636, "learning_rate": 1.0680464773034445e-05, "loss": 4.353, "step": 22726 }, { "epoch": 0.6941661576053757, "grad_norm": 0.46635594964027405, "learning_rate": 1.0678498445318726e-05, "loss": 4.1466, "step": 22727 }, { "epoch": 0.6941967012828345, "grad_norm": 0.44649335741996765, "learning_rate": 1.0676532249468434e-05, "loss": 4.2816, "step": 22728 }, { "epoch": 0.6942272449602932, "grad_norm": 0.46004197001457214, "learning_rate": 1.0674566185501686e-05, "loss": 4.2579, "step": 22729 }, { "epoch": 0.694257788637752, "grad_norm": 0.4495900869369507, "learning_rate": 1.067260025343656e-05, "loss": 4.3044, "step": 22730 }, { "epoch": 0.6942883323152107, "grad_norm": 0.4542057514190674, "learning_rate": 1.0670634453291181e-05, "loss": 4.2525, "step": 22731 }, { "epoch": 0.6943188759926695, "grad_norm": 0.45877596735954285, "learning_rate": 1.0668668785083626e-05, "loss": 4.2961, "step": 22732 }, { "epoch": 0.6943494196701283, "grad_norm": 0.4618251323699951, "learning_rate": 1.0666703248832019e-05, "loss": 4.2264, "step": 22733 }, { "epoch": 0.694379963347587, "grad_norm": 0.4557754099369049, "learning_rate": 1.0664737844554443e-05, "loss": 4.3274, "step": 22734 }, { "epoch": 0.6944105070250458, "grad_norm": 0.4548986852169037, "learning_rate": 1.0662772572268987e-05, "loss": 4.2386, "step": 22735 }, { "epoch": 0.6944410507025046, "grad_norm": 0.45085638761520386, "learning_rate": 1.0660807431993754e-05, "loss": 4.185, "step": 22736 }, { "epoch": 0.6944715943799633, "grad_norm": 0.4543350338935852, "learning_rate": 1.0658842423746848e-05, "loss": 4.2254, "step": 22737 }, { "epoch": 0.6945021380574221, "grad_norm": 0.44732439517974854, "learning_rate": 1.0656877547546348e-05, "loss": 4.2332, "step": 22738 }, { "epoch": 0.6945326817348809, "grad_norm": 0.4567820131778717, "learning_rate": 1.0654912803410347e-05, "loss": 4.2042, "step": 22739 }, { "epoch": 0.6945632254123396, "grad_norm": 0.447374165058136, "learning_rate": 1.065294819135695e-05, "loss": 4.2858, "step": 22740 }, { "epoch": 0.6945937690897984, "grad_norm": 0.459987998008728, "learning_rate": 1.0650983711404228e-05, "loss": 4.3389, "step": 22741 }, { "epoch": 0.6946243127672572, "grad_norm": 0.4564252495765686, "learning_rate": 1.0649019363570276e-05, "loss": 4.3483, "step": 22742 }, { "epoch": 0.6946548564447159, "grad_norm": 0.4549638628959656, "learning_rate": 1.064705514787319e-05, "loss": 4.1606, "step": 22743 }, { "epoch": 0.6946854001221747, "grad_norm": 0.44929051399230957, "learning_rate": 1.0645091064331037e-05, "loss": 4.3184, "step": 22744 }, { "epoch": 0.6947159437996335, "grad_norm": 0.4463508427143097, "learning_rate": 1.064312711296191e-05, "loss": 4.2346, "step": 22745 }, { "epoch": 0.6947464874770922, "grad_norm": 0.47114238142967224, "learning_rate": 1.0641163293783904e-05, "loss": 4.3217, "step": 22746 }, { "epoch": 0.694777031154551, "grad_norm": 0.45320630073547363, "learning_rate": 1.063919960681509e-05, "loss": 4.2203, "step": 22747 }, { "epoch": 0.6948075748320097, "grad_norm": 0.4650655686855316, "learning_rate": 1.063723605207354e-05, "loss": 4.2045, "step": 22748 }, { "epoch": 0.6948381185094685, "grad_norm": 0.45936307311058044, "learning_rate": 1.063527262957735e-05, "loss": 4.229, "step": 22749 }, { "epoch": 0.6948686621869273, "grad_norm": 0.45240601897239685, "learning_rate": 1.0633309339344582e-05, "loss": 4.1375, "step": 22750 }, { "epoch": 0.694899205864386, "grad_norm": 0.4525461792945862, "learning_rate": 1.063134618139333e-05, "loss": 4.1712, "step": 22751 }, { "epoch": 0.6949297495418448, "grad_norm": 0.4503779709339142, "learning_rate": 1.0629383155741655e-05, "loss": 4.2981, "step": 22752 }, { "epoch": 0.6949602932193036, "grad_norm": 0.4564204514026642, "learning_rate": 1.0627420262407636e-05, "loss": 4.264, "step": 22753 }, { "epoch": 0.6949908368967623, "grad_norm": 0.446082204580307, "learning_rate": 1.0625457501409358e-05, "loss": 4.2113, "step": 22754 }, { "epoch": 0.6950213805742211, "grad_norm": 0.46429017186164856, "learning_rate": 1.0623494872764874e-05, "loss": 4.3066, "step": 22755 }, { "epoch": 0.6950519242516799, "grad_norm": 0.4692479074001312, "learning_rate": 1.0621532376492263e-05, "loss": 4.2357, "step": 22756 }, { "epoch": 0.6950824679291386, "grad_norm": 0.455361008644104, "learning_rate": 1.0619570012609605e-05, "loss": 4.2605, "step": 22757 }, { "epoch": 0.6951130116065974, "grad_norm": 0.47085341811180115, "learning_rate": 1.0617607781134953e-05, "loss": 4.1763, "step": 22758 }, { "epoch": 0.6951435552840562, "grad_norm": 0.4496605694293976, "learning_rate": 1.0615645682086381e-05, "loss": 4.2282, "step": 22759 }, { "epoch": 0.6951740989615149, "grad_norm": 0.4482784569263458, "learning_rate": 1.0613683715481963e-05, "loss": 4.2908, "step": 22760 }, { "epoch": 0.6952046426389737, "grad_norm": 0.4612351953983307, "learning_rate": 1.0611721881339745e-05, "loss": 4.2647, "step": 22761 }, { "epoch": 0.6952351863164326, "grad_norm": 0.46078968048095703, "learning_rate": 1.0609760179677813e-05, "loss": 4.2485, "step": 22762 }, { "epoch": 0.6952657299938912, "grad_norm": 0.45844951272010803, "learning_rate": 1.0607798610514208e-05, "loss": 4.3535, "step": 22763 }, { "epoch": 0.69529627367135, "grad_norm": 0.45963022112846375, "learning_rate": 1.0605837173867008e-05, "loss": 4.1855, "step": 22764 }, { "epoch": 0.6953268173488087, "grad_norm": 0.44669249653816223, "learning_rate": 1.0603875869754267e-05, "loss": 4.1857, "step": 22765 }, { "epoch": 0.6953573610262676, "grad_norm": 0.46802541613578796, "learning_rate": 1.0601914698194035e-05, "loss": 4.28, "step": 22766 }, { "epoch": 0.6953879047037264, "grad_norm": 0.464522123336792, "learning_rate": 1.0599953659204375e-05, "loss": 4.3777, "step": 22767 }, { "epoch": 0.695418448381185, "grad_norm": 0.46767720580101013, "learning_rate": 1.0597992752803357e-05, "loss": 4.334, "step": 22768 }, { "epoch": 0.6954489920586439, "grad_norm": 0.4716775119304657, "learning_rate": 1.0596031979009013e-05, "loss": 4.3408, "step": 22769 }, { "epoch": 0.6954795357361027, "grad_norm": 0.4925782084465027, "learning_rate": 1.0594071337839413e-05, "loss": 4.2696, "step": 22770 }, { "epoch": 0.6955100794135614, "grad_norm": 0.45372727513313293, "learning_rate": 1.0592110829312607e-05, "loss": 4.247, "step": 22771 }, { "epoch": 0.6955406230910202, "grad_norm": 0.4582664966583252, "learning_rate": 1.059015045344664e-05, "loss": 4.2245, "step": 22772 }, { "epoch": 0.695571166768479, "grad_norm": 0.45461025834083557, "learning_rate": 1.0588190210259565e-05, "loss": 4.2273, "step": 22773 }, { "epoch": 0.6956017104459377, "grad_norm": 0.4730740189552307, "learning_rate": 1.0586230099769442e-05, "loss": 4.2925, "step": 22774 }, { "epoch": 0.6956322541233965, "grad_norm": 0.45986199378967285, "learning_rate": 1.0584270121994299e-05, "loss": 4.1654, "step": 22775 }, { "epoch": 0.6956627978008553, "grad_norm": 0.46677327156066895, "learning_rate": 1.0582310276952195e-05, "loss": 4.2184, "step": 22776 }, { "epoch": 0.695693341478314, "grad_norm": 0.46292540431022644, "learning_rate": 1.0580350564661181e-05, "loss": 4.2586, "step": 22777 }, { "epoch": 0.6957238851557728, "grad_norm": 0.45276370644569397, "learning_rate": 1.0578390985139285e-05, "loss": 4.1592, "step": 22778 }, { "epoch": 0.6957544288332316, "grad_norm": 0.447833776473999, "learning_rate": 1.0576431538404566e-05, "loss": 4.2816, "step": 22779 }, { "epoch": 0.6957849725106903, "grad_norm": 0.4498077630996704, "learning_rate": 1.057447222447506e-05, "loss": 4.2154, "step": 22780 }, { "epoch": 0.6958155161881491, "grad_norm": 0.4841563105583191, "learning_rate": 1.0572513043368793e-05, "loss": 4.3494, "step": 22781 }, { "epoch": 0.6958460598656078, "grad_norm": 0.44808560609817505, "learning_rate": 1.0570553995103827e-05, "loss": 4.2625, "step": 22782 }, { "epoch": 0.6958766035430666, "grad_norm": 0.45944198966026306, "learning_rate": 1.0568595079698179e-05, "loss": 4.2378, "step": 22783 }, { "epoch": 0.6959071472205254, "grad_norm": 0.44881394505500793, "learning_rate": 1.0566636297169897e-05, "loss": 4.2265, "step": 22784 }, { "epoch": 0.6959376908979841, "grad_norm": 0.4576733708381653, "learning_rate": 1.0564677647537025e-05, "loss": 4.3218, "step": 22785 }, { "epoch": 0.6959682345754429, "grad_norm": 0.44308409094810486, "learning_rate": 1.0562719130817578e-05, "loss": 4.1475, "step": 22786 }, { "epoch": 0.6959987782529017, "grad_norm": 0.45640912652015686, "learning_rate": 1.05607607470296e-05, "loss": 4.3287, "step": 22787 }, { "epoch": 0.6960293219303604, "grad_norm": 0.4557933211326599, "learning_rate": 1.0558802496191128e-05, "loss": 4.2762, "step": 22788 }, { "epoch": 0.6960598656078192, "grad_norm": 0.45621564984321594, "learning_rate": 1.055684437832018e-05, "loss": 4.3063, "step": 22789 }, { "epoch": 0.696090409285278, "grad_norm": 0.4657212495803833, "learning_rate": 1.0554886393434791e-05, "loss": 4.2578, "step": 22790 }, { "epoch": 0.6961209529627367, "grad_norm": 0.4450451135635376, "learning_rate": 1.0552928541552998e-05, "loss": 4.2922, "step": 22791 }, { "epoch": 0.6961514966401955, "grad_norm": 0.4603678286075592, "learning_rate": 1.0550970822692812e-05, "loss": 4.2497, "step": 22792 }, { "epoch": 0.6961820403176543, "grad_norm": 0.4646070897579193, "learning_rate": 1.0549013236872273e-05, "loss": 4.299, "step": 22793 }, { "epoch": 0.696212583995113, "grad_norm": 0.4557971954345703, "learning_rate": 1.0547055784109395e-05, "loss": 4.2764, "step": 22794 }, { "epoch": 0.6962431276725718, "grad_norm": 0.4516531527042389, "learning_rate": 1.054509846442221e-05, "loss": 4.1994, "step": 22795 }, { "epoch": 0.6962736713500306, "grad_norm": 0.4418831467628479, "learning_rate": 1.0543141277828727e-05, "loss": 4.2442, "step": 22796 }, { "epoch": 0.6963042150274893, "grad_norm": 0.4544922411441803, "learning_rate": 1.0541184224346987e-05, "loss": 4.3623, "step": 22797 }, { "epoch": 0.6963347587049481, "grad_norm": 0.45369160175323486, "learning_rate": 1.0539227303994986e-05, "loss": 4.2389, "step": 22798 }, { "epoch": 0.6963653023824068, "grad_norm": 0.4542105495929718, "learning_rate": 1.0537270516790765e-05, "loss": 4.326, "step": 22799 }, { "epoch": 0.6963958460598656, "grad_norm": 0.4559042155742645, "learning_rate": 1.0535313862752321e-05, "loss": 4.2456, "step": 22800 }, { "epoch": 0.6964263897373244, "grad_norm": 0.4509340226650238, "learning_rate": 1.0533357341897679e-05, "loss": 4.1451, "step": 22801 }, { "epoch": 0.6964569334147831, "grad_norm": 0.44896769523620605, "learning_rate": 1.0531400954244864e-05, "loss": 4.1841, "step": 22802 }, { "epoch": 0.6964874770922419, "grad_norm": 0.46018415689468384, "learning_rate": 1.0529444699811868e-05, "loss": 4.2205, "step": 22803 }, { "epoch": 0.6965180207697007, "grad_norm": 0.4641273021697998, "learning_rate": 1.0527488578616718e-05, "loss": 4.2829, "step": 22804 }, { "epoch": 0.6965485644471594, "grad_norm": 0.4688418507575989, "learning_rate": 1.0525532590677428e-05, "loss": 4.3238, "step": 22805 }, { "epoch": 0.6965791081246182, "grad_norm": 0.459431916475296, "learning_rate": 1.0523576736011991e-05, "loss": 4.2714, "step": 22806 }, { "epoch": 0.696609651802077, "grad_norm": 0.4511159062385559, "learning_rate": 1.052162101463843e-05, "loss": 4.2013, "step": 22807 }, { "epoch": 0.6966401954795357, "grad_norm": 0.45229795575141907, "learning_rate": 1.0519665426574753e-05, "loss": 4.2777, "step": 22808 }, { "epoch": 0.6966707391569945, "grad_norm": 0.4547392427921295, "learning_rate": 1.0517709971838956e-05, "loss": 4.2567, "step": 22809 }, { "epoch": 0.6967012828344533, "grad_norm": 0.4672562777996063, "learning_rate": 1.0515754650449058e-05, "loss": 4.1606, "step": 22810 }, { "epoch": 0.696731826511912, "grad_norm": 0.45276057720184326, "learning_rate": 1.0513799462423055e-05, "loss": 4.2349, "step": 22811 }, { "epoch": 0.6967623701893708, "grad_norm": 0.44743719696998596, "learning_rate": 1.0511844407778937e-05, "loss": 4.294, "step": 22812 }, { "epoch": 0.6967929138668295, "grad_norm": 0.45572879910469055, "learning_rate": 1.0509889486534726e-05, "loss": 4.2881, "step": 22813 }, { "epoch": 0.6968234575442883, "grad_norm": 0.45885956287384033, "learning_rate": 1.0507934698708404e-05, "loss": 4.2677, "step": 22814 }, { "epoch": 0.6968540012217471, "grad_norm": 0.45006221532821655, "learning_rate": 1.0505980044317978e-05, "loss": 4.2654, "step": 22815 }, { "epoch": 0.6968845448992058, "grad_norm": 0.4549961984157562, "learning_rate": 1.0504025523381456e-05, "loss": 4.2227, "step": 22816 }, { "epoch": 0.6969150885766646, "grad_norm": 0.47202563285827637, "learning_rate": 1.0502071135916814e-05, "loss": 4.1716, "step": 22817 }, { "epoch": 0.6969456322541234, "grad_norm": 0.47222447395324707, "learning_rate": 1.0500116881942057e-05, "loss": 4.2642, "step": 22818 }, { "epoch": 0.6969761759315821, "grad_norm": 0.4501686990261078, "learning_rate": 1.049816276147519e-05, "loss": 4.2738, "step": 22819 }, { "epoch": 0.6970067196090409, "grad_norm": 0.46504899859428406, "learning_rate": 1.0496208774534182e-05, "loss": 4.1569, "step": 22820 }, { "epoch": 0.6970372632864997, "grad_norm": 0.4425036907196045, "learning_rate": 1.0494254921137039e-05, "loss": 4.3195, "step": 22821 }, { "epoch": 0.6970678069639584, "grad_norm": 0.45372775197029114, "learning_rate": 1.0492301201301758e-05, "loss": 4.1661, "step": 22822 }, { "epoch": 0.6970983506414172, "grad_norm": 0.45559263229370117, "learning_rate": 1.0490347615046309e-05, "loss": 4.201, "step": 22823 }, { "epoch": 0.697128894318876, "grad_norm": 0.46905282139778137, "learning_rate": 1.048839416238869e-05, "loss": 4.2574, "step": 22824 }, { "epoch": 0.6971594379963347, "grad_norm": 0.46674585342407227, "learning_rate": 1.0486440843346898e-05, "loss": 4.2871, "step": 22825 }, { "epoch": 0.6971899816737935, "grad_norm": 0.4550858736038208, "learning_rate": 1.0484487657938905e-05, "loss": 4.2842, "step": 22826 }, { "epoch": 0.6972205253512523, "grad_norm": 0.44392356276512146, "learning_rate": 1.048253460618269e-05, "loss": 4.2502, "step": 22827 }, { "epoch": 0.697251069028711, "grad_norm": 0.4722963273525238, "learning_rate": 1.048058168809625e-05, "loss": 4.2229, "step": 22828 }, { "epoch": 0.6972816127061698, "grad_norm": 0.4542422890663147, "learning_rate": 1.0478628903697552e-05, "loss": 4.281, "step": 22829 }, { "epoch": 0.6973121563836285, "grad_norm": 0.4579913318157196, "learning_rate": 1.0476676253004591e-05, "loss": 4.2305, "step": 22830 }, { "epoch": 0.6973427000610873, "grad_norm": 0.45174694061279297, "learning_rate": 1.0474723736035334e-05, "loss": 4.2755, "step": 22831 }, { "epoch": 0.6973732437385461, "grad_norm": 0.44975000619888306, "learning_rate": 1.0472771352807762e-05, "loss": 4.3056, "step": 22832 }, { "epoch": 0.6974037874160048, "grad_norm": 0.46305251121520996, "learning_rate": 1.047081910333986e-05, "loss": 4.2508, "step": 22833 }, { "epoch": 0.6974343310934636, "grad_norm": 0.47716858983039856, "learning_rate": 1.046886698764959e-05, "loss": 4.3683, "step": 22834 }, { "epoch": 0.6974648747709224, "grad_norm": 0.446892112493515, "learning_rate": 1.0466915005754929e-05, "loss": 4.2761, "step": 22835 }, { "epoch": 0.6974954184483811, "grad_norm": 0.4577455222606659, "learning_rate": 1.0464963157673868e-05, "loss": 4.2599, "step": 22836 }, { "epoch": 0.69752596212584, "grad_norm": 0.4556043744087219, "learning_rate": 1.0463011443424353e-05, "loss": 4.3024, "step": 22837 }, { "epoch": 0.6975565058032988, "grad_norm": 0.45836561918258667, "learning_rate": 1.0461059863024364e-05, "loss": 4.1664, "step": 22838 }, { "epoch": 0.6975870494807574, "grad_norm": 0.4661169648170471, "learning_rate": 1.0459108416491883e-05, "loss": 4.344, "step": 22839 }, { "epoch": 0.6976175931582163, "grad_norm": 0.46274223923683167, "learning_rate": 1.0457157103844858e-05, "loss": 4.3789, "step": 22840 }, { "epoch": 0.6976481368356751, "grad_norm": 0.4516662061214447, "learning_rate": 1.0455205925101275e-05, "loss": 4.2521, "step": 22841 }, { "epoch": 0.6976786805131338, "grad_norm": 0.4610843062400818, "learning_rate": 1.0453254880279078e-05, "loss": 4.2518, "step": 22842 }, { "epoch": 0.6977092241905926, "grad_norm": 0.4653957784175873, "learning_rate": 1.0451303969396253e-05, "loss": 4.3244, "step": 22843 }, { "epoch": 0.6977397678680514, "grad_norm": 0.46599701046943665, "learning_rate": 1.0449353192470743e-05, "loss": 4.3443, "step": 22844 }, { "epoch": 0.6977703115455101, "grad_norm": 0.46791771054267883, "learning_rate": 1.0447402549520527e-05, "loss": 4.251, "step": 22845 }, { "epoch": 0.6978008552229689, "grad_norm": 0.4504343867301941, "learning_rate": 1.044545204056355e-05, "loss": 4.2825, "step": 22846 }, { "epoch": 0.6978313989004276, "grad_norm": 0.46715641021728516, "learning_rate": 1.0443501665617789e-05, "loss": 4.3188, "step": 22847 }, { "epoch": 0.6978619425778864, "grad_norm": 0.4514692425727844, "learning_rate": 1.0441551424701182e-05, "loss": 4.2475, "step": 22848 }, { "epoch": 0.6978924862553452, "grad_norm": 0.4623212218284607, "learning_rate": 1.0439601317831699e-05, "loss": 4.1918, "step": 22849 }, { "epoch": 0.6979230299328039, "grad_norm": 0.46822938323020935, "learning_rate": 1.04376513450273e-05, "loss": 4.3156, "step": 22850 }, { "epoch": 0.6979535736102627, "grad_norm": 0.45809489488601685, "learning_rate": 1.0435701506305923e-05, "loss": 4.2324, "step": 22851 }, { "epoch": 0.6979841172877215, "grad_norm": 0.4544871747493744, "learning_rate": 1.0433751801685528e-05, "loss": 4.3057, "step": 22852 }, { "epoch": 0.6980146609651802, "grad_norm": 0.45751920342445374, "learning_rate": 1.0431802231184081e-05, "loss": 4.2899, "step": 22853 }, { "epoch": 0.698045204642639, "grad_norm": 0.454427570104599, "learning_rate": 1.0429852794819514e-05, "loss": 4.2862, "step": 22854 }, { "epoch": 0.6980757483200978, "grad_norm": 0.44961053133010864, "learning_rate": 1.042790349260978e-05, "loss": 4.2939, "step": 22855 }, { "epoch": 0.6981062919975565, "grad_norm": 0.4618109464645386, "learning_rate": 1.0425954324572843e-05, "loss": 4.3625, "step": 22856 }, { "epoch": 0.6981368356750153, "grad_norm": 0.46019870042800903, "learning_rate": 1.0424005290726638e-05, "loss": 4.2188, "step": 22857 }, { "epoch": 0.6981673793524741, "grad_norm": 0.4547751247882843, "learning_rate": 1.0422056391089099e-05, "loss": 4.2536, "step": 22858 }, { "epoch": 0.6981979230299328, "grad_norm": 0.4470670819282532, "learning_rate": 1.0420107625678191e-05, "loss": 4.2599, "step": 22859 }, { "epoch": 0.6982284667073916, "grad_norm": 0.45126599073410034, "learning_rate": 1.0418158994511839e-05, "loss": 4.1517, "step": 22860 }, { "epoch": 0.6982590103848504, "grad_norm": 0.45018112659454346, "learning_rate": 1.0416210497607998e-05, "loss": 4.2648, "step": 22861 }, { "epoch": 0.6982895540623091, "grad_norm": 0.47230610251426697, "learning_rate": 1.041426213498461e-05, "loss": 4.258, "step": 22862 }, { "epoch": 0.6983200977397679, "grad_norm": 0.45856279134750366, "learning_rate": 1.0412313906659604e-05, "loss": 4.2749, "step": 22863 }, { "epoch": 0.6983506414172266, "grad_norm": 0.4581805467605591, "learning_rate": 1.041036581265093e-05, "loss": 4.2231, "step": 22864 }, { "epoch": 0.6983811850946854, "grad_norm": 0.4617120027542114, "learning_rate": 1.0408417852976513e-05, "loss": 4.1451, "step": 22865 }, { "epoch": 0.6984117287721442, "grad_norm": 0.4467180073261261, "learning_rate": 1.0406470027654295e-05, "loss": 4.2038, "step": 22866 }, { "epoch": 0.6984422724496029, "grad_norm": 0.46572232246398926, "learning_rate": 1.0404522336702216e-05, "loss": 4.2056, "step": 22867 }, { "epoch": 0.6984728161270617, "grad_norm": 0.4557824432849884, "learning_rate": 1.04025747801382e-05, "loss": 4.2603, "step": 22868 }, { "epoch": 0.6985033598045205, "grad_norm": 0.4526784420013428, "learning_rate": 1.040062735798018e-05, "loss": 4.232, "step": 22869 }, { "epoch": 0.6985339034819792, "grad_norm": 0.4632478356361389, "learning_rate": 1.03986800702461e-05, "loss": 4.2931, "step": 22870 }, { "epoch": 0.698564447159438, "grad_norm": 0.4516502618789673, "learning_rate": 1.039673291695387e-05, "loss": 4.302, "step": 22871 }, { "epoch": 0.6985949908368968, "grad_norm": 0.4551776945590973, "learning_rate": 1.039478589812144e-05, "loss": 4.1556, "step": 22872 }, { "epoch": 0.6986255345143555, "grad_norm": 0.45602408051490784, "learning_rate": 1.0392839013766715e-05, "loss": 4.3394, "step": 22873 }, { "epoch": 0.6986560781918143, "grad_norm": 0.4564760625362396, "learning_rate": 1.039089226390764e-05, "loss": 4.3199, "step": 22874 }, { "epoch": 0.6986866218692731, "grad_norm": 0.4595808684825897, "learning_rate": 1.0388945648562121e-05, "loss": 4.255, "step": 22875 }, { "epoch": 0.6987171655467318, "grad_norm": 0.4444665014743805, "learning_rate": 1.0386999167748102e-05, "loss": 4.2802, "step": 22876 }, { "epoch": 0.6987477092241906, "grad_norm": 0.4644223749637604, "learning_rate": 1.0385052821483484e-05, "loss": 4.2077, "step": 22877 }, { "epoch": 0.6987782529016494, "grad_norm": 0.4642653167247772, "learning_rate": 1.0383106609786204e-05, "loss": 4.2481, "step": 22878 }, { "epoch": 0.6988087965791081, "grad_norm": 0.4488057792186737, "learning_rate": 1.038116053267418e-05, "loss": 4.2985, "step": 22879 }, { "epoch": 0.6988393402565669, "grad_norm": 0.46279019117355347, "learning_rate": 1.0379214590165322e-05, "loss": 4.3395, "step": 22880 }, { "epoch": 0.6988698839340256, "grad_norm": 0.45985159277915955, "learning_rate": 1.037726878227756e-05, "loss": 4.3194, "step": 22881 }, { "epoch": 0.6989004276114844, "grad_norm": 0.46547752618789673, "learning_rate": 1.0375323109028795e-05, "loss": 4.1387, "step": 22882 }, { "epoch": 0.6989309712889432, "grad_norm": 0.4664629101753235, "learning_rate": 1.0373377570436949e-05, "loss": 4.2698, "step": 22883 }, { "epoch": 0.6989615149664019, "grad_norm": 0.4571145474910736, "learning_rate": 1.0371432166519943e-05, "loss": 4.3208, "step": 22884 }, { "epoch": 0.6989920586438607, "grad_norm": 0.4502510726451874, "learning_rate": 1.0369486897295674e-05, "loss": 4.3289, "step": 22885 }, { "epoch": 0.6990226023213195, "grad_norm": 0.45623093843460083, "learning_rate": 1.0367541762782062e-05, "loss": 4.2714, "step": 22886 }, { "epoch": 0.6990531459987782, "grad_norm": 0.4479089379310608, "learning_rate": 1.0365596762997027e-05, "loss": 4.2443, "step": 22887 }, { "epoch": 0.699083689676237, "grad_norm": 0.4560113251209259, "learning_rate": 1.0363651897958453e-05, "loss": 4.3138, "step": 22888 }, { "epoch": 0.6991142333536958, "grad_norm": 0.47750183939933777, "learning_rate": 1.0361707167684275e-05, "loss": 4.3354, "step": 22889 }, { "epoch": 0.6991447770311545, "grad_norm": 0.46508169174194336, "learning_rate": 1.0359762572192385e-05, "loss": 4.3022, "step": 22890 }, { "epoch": 0.6991753207086133, "grad_norm": 0.4507010877132416, "learning_rate": 1.0357818111500678e-05, "loss": 4.2577, "step": 22891 }, { "epoch": 0.6992058643860721, "grad_norm": 0.4538446366786957, "learning_rate": 1.0355873785627068e-05, "loss": 4.2725, "step": 22892 }, { "epoch": 0.6992364080635308, "grad_norm": 0.4999224841594696, "learning_rate": 1.0353929594589465e-05, "loss": 4.3376, "step": 22893 }, { "epoch": 0.6992669517409896, "grad_norm": 0.4636268615722656, "learning_rate": 1.0351985538405757e-05, "loss": 4.2829, "step": 22894 }, { "epoch": 0.6992974954184484, "grad_norm": 0.45094069838523865, "learning_rate": 1.0350041617093844e-05, "loss": 4.2092, "step": 22895 }, { "epoch": 0.6993280390959071, "grad_norm": 0.4499596953392029, "learning_rate": 1.0348097830671644e-05, "loss": 4.212, "step": 22896 }, { "epoch": 0.6993585827733659, "grad_norm": 0.4595717489719391, "learning_rate": 1.034615417915703e-05, "loss": 4.4017, "step": 22897 }, { "epoch": 0.6993891264508246, "grad_norm": 0.4581140875816345, "learning_rate": 1.0344210662567919e-05, "loss": 4.3352, "step": 22898 }, { "epoch": 0.6994196701282834, "grad_norm": 0.45370274782180786, "learning_rate": 1.0342267280922183e-05, "loss": 4.2297, "step": 22899 }, { "epoch": 0.6994502138057422, "grad_norm": 0.44876858592033386, "learning_rate": 1.0340324034237731e-05, "loss": 4.3151, "step": 22900 }, { "epoch": 0.6994807574832009, "grad_norm": 0.4457947015762329, "learning_rate": 1.0338380922532461e-05, "loss": 4.1924, "step": 22901 }, { "epoch": 0.6995113011606597, "grad_norm": 0.46032339334487915, "learning_rate": 1.0336437945824247e-05, "loss": 4.2476, "step": 22902 }, { "epoch": 0.6995418448381185, "grad_norm": 0.46415388584136963, "learning_rate": 1.0334495104130999e-05, "loss": 4.3286, "step": 22903 }, { "epoch": 0.6995723885155772, "grad_norm": 0.4670765995979309, "learning_rate": 1.0332552397470585e-05, "loss": 4.3422, "step": 22904 }, { "epoch": 0.699602932193036, "grad_norm": 0.47410455346107483, "learning_rate": 1.033060982586091e-05, "loss": 4.2147, "step": 22905 }, { "epoch": 0.6996334758704948, "grad_norm": 0.4595450758934021, "learning_rate": 1.0328667389319846e-05, "loss": 4.3417, "step": 22906 }, { "epoch": 0.6996640195479535, "grad_norm": 0.4551927447319031, "learning_rate": 1.0326725087865291e-05, "loss": 4.3351, "step": 22907 }, { "epoch": 0.6996945632254123, "grad_norm": 0.4420148432254791, "learning_rate": 1.0324782921515113e-05, "loss": 4.2888, "step": 22908 }, { "epoch": 0.6997251069028712, "grad_norm": 0.4620365798473358, "learning_rate": 1.0322840890287205e-05, "loss": 4.2903, "step": 22909 }, { "epoch": 0.6997556505803298, "grad_norm": 0.46083950996398926, "learning_rate": 1.0320898994199458e-05, "loss": 4.2072, "step": 22910 }, { "epoch": 0.6997861942577887, "grad_norm": 0.4496692717075348, "learning_rate": 1.031895723326973e-05, "loss": 4.2203, "step": 22911 }, { "epoch": 0.6998167379352475, "grad_norm": 0.45360544323921204, "learning_rate": 1.0317015607515912e-05, "loss": 4.2942, "step": 22912 }, { "epoch": 0.6998472816127062, "grad_norm": 0.44270414113998413, "learning_rate": 1.031507411695589e-05, "loss": 4.2949, "step": 22913 }, { "epoch": 0.699877825290165, "grad_norm": 0.4644568860530853, "learning_rate": 1.0313132761607522e-05, "loss": 4.3207, "step": 22914 }, { "epoch": 0.6999083689676237, "grad_norm": 0.46539780497550964, "learning_rate": 1.03111915414887e-05, "loss": 4.3157, "step": 22915 }, { "epoch": 0.6999389126450825, "grad_norm": 0.45628124475479126, "learning_rate": 1.0309250456617277e-05, "loss": 4.3172, "step": 22916 }, { "epoch": 0.6999694563225413, "grad_norm": 0.45470497012138367, "learning_rate": 1.0307309507011146e-05, "loss": 4.2804, "step": 22917 }, { "epoch": 0.7, "grad_norm": 0.46848222613334656, "learning_rate": 1.0305368692688174e-05, "loss": 4.2197, "step": 22918 }, { "epoch": 0.7000305436774588, "grad_norm": 0.4540417492389679, "learning_rate": 1.030342801366622e-05, "loss": 4.2281, "step": 22919 }, { "epoch": 0.7000610873549176, "grad_norm": 0.4568136930465698, "learning_rate": 1.030148746996317e-05, "loss": 4.2442, "step": 22920 }, { "epoch": 0.7000916310323763, "grad_norm": 0.4652986228466034, "learning_rate": 1.0299547061596882e-05, "loss": 4.3297, "step": 22921 }, { "epoch": 0.7001221747098351, "grad_norm": 0.4580927789211273, "learning_rate": 1.0297606788585212e-05, "loss": 4.2256, "step": 22922 }, { "epoch": 0.7001527183872939, "grad_norm": 0.4583151340484619, "learning_rate": 1.0295666650946037e-05, "loss": 4.2828, "step": 22923 }, { "epoch": 0.7001832620647526, "grad_norm": 0.4537148177623749, "learning_rate": 1.029372664869723e-05, "loss": 4.279, "step": 22924 }, { "epoch": 0.7002138057422114, "grad_norm": 0.4532510042190552, "learning_rate": 1.029178678185663e-05, "loss": 4.3003, "step": 22925 }, { "epoch": 0.7002443494196702, "grad_norm": 0.4464282691478729, "learning_rate": 1.0289847050442114e-05, "loss": 4.2266, "step": 22926 }, { "epoch": 0.7002748930971289, "grad_norm": 0.463377982378006, "learning_rate": 1.028790745447155e-05, "loss": 4.2518, "step": 22927 }, { "epoch": 0.7003054367745877, "grad_norm": 0.45504891872406006, "learning_rate": 1.0285967993962773e-05, "loss": 4.327, "step": 22928 }, { "epoch": 0.7003359804520465, "grad_norm": 0.4540759027004242, "learning_rate": 1.0284028668933657e-05, "loss": 4.2924, "step": 22929 }, { "epoch": 0.7003665241295052, "grad_norm": 0.44935640692710876, "learning_rate": 1.0282089479402064e-05, "loss": 4.2978, "step": 22930 }, { "epoch": 0.700397067806964, "grad_norm": 0.4698299765586853, "learning_rate": 1.0280150425385828e-05, "loss": 4.244, "step": 22931 }, { "epoch": 0.7004276114844227, "grad_norm": 0.4534445106983185, "learning_rate": 1.027821150690283e-05, "loss": 4.3025, "step": 22932 }, { "epoch": 0.7004581551618815, "grad_norm": 0.4541190564632416, "learning_rate": 1.0276272723970895e-05, "loss": 4.3405, "step": 22933 }, { "epoch": 0.7004886988393403, "grad_norm": 0.4542959928512573, "learning_rate": 1.0274334076607886e-05, "loss": 4.3278, "step": 22934 }, { "epoch": 0.700519242516799, "grad_norm": 0.4491487741470337, "learning_rate": 1.0272395564831666e-05, "loss": 4.1725, "step": 22935 }, { "epoch": 0.7005497861942578, "grad_norm": 0.45642179250717163, "learning_rate": 1.027045718866007e-05, "loss": 4.2903, "step": 22936 }, { "epoch": 0.7005803298717166, "grad_norm": 0.46151939034461975, "learning_rate": 1.0268518948110942e-05, "loss": 4.2265, "step": 22937 }, { "epoch": 0.7006108735491753, "grad_norm": 0.4728945195674896, "learning_rate": 1.0266580843202142e-05, "loss": 4.1488, "step": 22938 }, { "epoch": 0.7006414172266341, "grad_norm": 0.46150943636894226, "learning_rate": 1.0264642873951497e-05, "loss": 4.2383, "step": 22939 }, { "epoch": 0.7006719609040929, "grad_norm": 0.45653098821640015, "learning_rate": 1.0262705040376862e-05, "loss": 4.3243, "step": 22940 }, { "epoch": 0.7007025045815516, "grad_norm": 0.48796898126602173, "learning_rate": 1.0260767342496088e-05, "loss": 4.1984, "step": 22941 }, { "epoch": 0.7007330482590104, "grad_norm": 0.4543280005455017, "learning_rate": 1.0258829780326997e-05, "loss": 4.2278, "step": 22942 }, { "epoch": 0.7007635919364692, "grad_norm": 0.4616577625274658, "learning_rate": 1.0256892353887443e-05, "loss": 4.2978, "step": 22943 }, { "epoch": 0.7007941356139279, "grad_norm": 0.45623719692230225, "learning_rate": 1.0254955063195268e-05, "loss": 4.2677, "step": 22944 }, { "epoch": 0.7008246792913867, "grad_norm": 0.45559531450271606, "learning_rate": 1.0253017908268293e-05, "loss": 4.2455, "step": 22945 }, { "epoch": 0.7008552229688455, "grad_norm": 0.46907857060432434, "learning_rate": 1.0251080889124365e-05, "loss": 4.2089, "step": 22946 }, { "epoch": 0.7008857666463042, "grad_norm": 0.45430225133895874, "learning_rate": 1.0249144005781327e-05, "loss": 4.2607, "step": 22947 }, { "epoch": 0.700916310323763, "grad_norm": 0.4614831507205963, "learning_rate": 1.0247207258256996e-05, "loss": 4.3078, "step": 22948 }, { "epoch": 0.7009468540012217, "grad_norm": 0.44931742548942566, "learning_rate": 1.0245270646569222e-05, "loss": 4.3201, "step": 22949 }, { "epoch": 0.7009773976786805, "grad_norm": 0.4578937888145447, "learning_rate": 1.0243334170735818e-05, "loss": 4.2888, "step": 22950 }, { "epoch": 0.7010079413561393, "grad_norm": 0.45775264501571655, "learning_rate": 1.0241397830774633e-05, "loss": 4.2855, "step": 22951 }, { "epoch": 0.701038485033598, "grad_norm": 0.4563535749912262, "learning_rate": 1.0239461626703475e-05, "loss": 4.2027, "step": 22952 }, { "epoch": 0.7010690287110568, "grad_norm": 0.4581473767757416, "learning_rate": 1.0237525558540195e-05, "loss": 4.2429, "step": 22953 }, { "epoch": 0.7010995723885156, "grad_norm": 0.45836398005485535, "learning_rate": 1.0235589626302598e-05, "loss": 4.2662, "step": 22954 }, { "epoch": 0.7011301160659743, "grad_norm": 0.44389063119888306, "learning_rate": 1.0233653830008525e-05, "loss": 4.1526, "step": 22955 }, { "epoch": 0.7011606597434331, "grad_norm": 0.4645935595035553, "learning_rate": 1.0231718169675787e-05, "loss": 4.265, "step": 22956 }, { "epoch": 0.7011912034208919, "grad_norm": 0.4629306197166443, "learning_rate": 1.0229782645322209e-05, "loss": 4.2617, "step": 22957 }, { "epoch": 0.7012217470983506, "grad_norm": 0.4654400050640106, "learning_rate": 1.0227847256965628e-05, "loss": 4.2674, "step": 22958 }, { "epoch": 0.7012522907758094, "grad_norm": 0.4537146985530853, "learning_rate": 1.0225912004623844e-05, "loss": 4.2516, "step": 22959 }, { "epoch": 0.7012828344532682, "grad_norm": 0.46104443073272705, "learning_rate": 1.0223976888314682e-05, "loss": 4.2235, "step": 22960 }, { "epoch": 0.7013133781307269, "grad_norm": 0.45312365889549255, "learning_rate": 1.0222041908055974e-05, "loss": 4.1533, "step": 22961 }, { "epoch": 0.7013439218081857, "grad_norm": 0.44740110635757446, "learning_rate": 1.0220107063865511e-05, "loss": 4.0626, "step": 22962 }, { "epoch": 0.7013744654856445, "grad_norm": 0.46336594223976135, "learning_rate": 1.0218172355761124e-05, "loss": 4.048, "step": 22963 }, { "epoch": 0.7014050091631032, "grad_norm": 0.4619162976741791, "learning_rate": 1.0216237783760635e-05, "loss": 4.2119, "step": 22964 }, { "epoch": 0.701435552840562, "grad_norm": 0.4557533264160156, "learning_rate": 1.0214303347881835e-05, "loss": 4.3079, "step": 22965 }, { "epoch": 0.7014660965180207, "grad_norm": 0.45936650037765503, "learning_rate": 1.0212369048142553e-05, "loss": 4.1313, "step": 22966 }, { "epoch": 0.7014966401954795, "grad_norm": 0.45497646927833557, "learning_rate": 1.0210434884560594e-05, "loss": 4.2927, "step": 22967 }, { "epoch": 0.7015271838729383, "grad_norm": 0.44759824872016907, "learning_rate": 1.0208500857153758e-05, "loss": 4.1824, "step": 22968 }, { "epoch": 0.701557727550397, "grad_norm": 0.4576377868652344, "learning_rate": 1.0206566965939865e-05, "loss": 4.2024, "step": 22969 }, { "epoch": 0.7015882712278558, "grad_norm": 0.44969749450683594, "learning_rate": 1.0204633210936709e-05, "loss": 4.3349, "step": 22970 }, { "epoch": 0.7016188149053146, "grad_norm": 0.4508311450481415, "learning_rate": 1.0202699592162101e-05, "loss": 4.2638, "step": 22971 }, { "epoch": 0.7016493585827733, "grad_norm": 0.44509342312812805, "learning_rate": 1.0200766109633857e-05, "loss": 4.2623, "step": 22972 }, { "epoch": 0.7016799022602321, "grad_norm": 0.45491957664489746, "learning_rate": 1.0198832763369759e-05, "loss": 4.2585, "step": 22973 }, { "epoch": 0.7017104459376909, "grad_norm": 0.4683302938938141, "learning_rate": 1.0196899553387615e-05, "loss": 4.249, "step": 22974 }, { "epoch": 0.7017409896151496, "grad_norm": 0.454487681388855, "learning_rate": 1.019496647970524e-05, "loss": 4.3267, "step": 22975 }, { "epoch": 0.7017715332926084, "grad_norm": 0.45479223132133484, "learning_rate": 1.0193033542340411e-05, "loss": 4.2298, "step": 22976 }, { "epoch": 0.7018020769700672, "grad_norm": 0.4433131515979767, "learning_rate": 1.0191100741310933e-05, "loss": 4.3029, "step": 22977 }, { "epoch": 0.7018326206475259, "grad_norm": 0.4566171169281006, "learning_rate": 1.0189168076634618e-05, "loss": 4.3338, "step": 22978 }, { "epoch": 0.7018631643249847, "grad_norm": 0.45687204599380493, "learning_rate": 1.0187235548329232e-05, "loss": 4.2452, "step": 22979 }, { "epoch": 0.7018937080024434, "grad_norm": 0.46676352620124817, "learning_rate": 1.0185303156412598e-05, "loss": 4.2878, "step": 22980 }, { "epoch": 0.7019242516799022, "grad_norm": 0.48129329085350037, "learning_rate": 1.0183370900902484e-05, "loss": 4.2141, "step": 22981 }, { "epoch": 0.701954795357361, "grad_norm": 0.4450681209564209, "learning_rate": 1.0181438781816702e-05, "loss": 4.2687, "step": 22982 }, { "epoch": 0.7019853390348197, "grad_norm": 0.4551369845867157, "learning_rate": 1.0179506799173022e-05, "loss": 4.202, "step": 22983 }, { "epoch": 0.7020158827122785, "grad_norm": 0.4543777406215668, "learning_rate": 1.0177574952989252e-05, "loss": 4.2986, "step": 22984 }, { "epoch": 0.7020464263897374, "grad_norm": 0.4622296988964081, "learning_rate": 1.0175643243283164e-05, "loss": 4.2833, "step": 22985 }, { "epoch": 0.702076970067196, "grad_norm": 0.4522211253643036, "learning_rate": 1.0173711670072556e-05, "loss": 4.2191, "step": 22986 }, { "epoch": 0.7021075137446549, "grad_norm": 0.45957428216934204, "learning_rate": 1.01717802333752e-05, "loss": 4.2773, "step": 22987 }, { "epoch": 0.7021380574221137, "grad_norm": 0.4704744219779968, "learning_rate": 1.0169848933208888e-05, "loss": 4.3309, "step": 22988 }, { "epoch": 0.7021686010995724, "grad_norm": 0.44908347725868225, "learning_rate": 1.016791776959141e-05, "loss": 4.1886, "step": 22989 }, { "epoch": 0.7021991447770312, "grad_norm": 0.4591576159000397, "learning_rate": 1.016598674254053e-05, "loss": 4.2849, "step": 22990 }, { "epoch": 0.70222968845449, "grad_norm": 0.458401083946228, "learning_rate": 1.0164055852074037e-05, "loss": 4.264, "step": 22991 }, { "epoch": 0.7022602321319487, "grad_norm": 0.4644033908843994, "learning_rate": 1.0162125098209718e-05, "loss": 4.2637, "step": 22992 }, { "epoch": 0.7022907758094075, "grad_norm": 0.4667389690876007, "learning_rate": 1.0160194480965335e-05, "loss": 4.3418, "step": 22993 }, { "epoch": 0.7023213194868663, "grad_norm": 0.46373939514160156, "learning_rate": 1.015826400035867e-05, "loss": 4.2856, "step": 22994 }, { "epoch": 0.702351863164325, "grad_norm": 0.4666713774204254, "learning_rate": 1.0156333656407508e-05, "loss": 4.2574, "step": 22995 }, { "epoch": 0.7023824068417838, "grad_norm": 0.46185263991355896, "learning_rate": 1.0154403449129604e-05, "loss": 4.2903, "step": 22996 }, { "epoch": 0.7024129505192425, "grad_norm": 0.4489333927631378, "learning_rate": 1.015247337854275e-05, "loss": 4.1816, "step": 22997 }, { "epoch": 0.7024434941967013, "grad_norm": 0.4516654312610626, "learning_rate": 1.01505434446647e-05, "loss": 4.2008, "step": 22998 }, { "epoch": 0.7024740378741601, "grad_norm": 0.457378089427948, "learning_rate": 1.014861364751324e-05, "loss": 4.3074, "step": 22999 }, { "epoch": 0.7025045815516188, "grad_norm": 0.4579463601112366, "learning_rate": 1.014668398710613e-05, "loss": 4.2382, "step": 23000 }, { "epoch": 0.7025351252290776, "grad_norm": 0.46034568548202515, "learning_rate": 1.0144754463461125e-05, "loss": 4.2039, "step": 23001 }, { "epoch": 0.7025656689065364, "grad_norm": 0.45064789056777954, "learning_rate": 1.0142825076596008e-05, "loss": 4.1693, "step": 23002 }, { "epoch": 0.7025962125839951, "grad_norm": 0.46455323696136475, "learning_rate": 1.0140895826528546e-05, "loss": 4.2822, "step": 23003 }, { "epoch": 0.7026267562614539, "grad_norm": 0.46345818042755127, "learning_rate": 1.0138966713276488e-05, "loss": 4.3344, "step": 23004 }, { "epoch": 0.7026572999389127, "grad_norm": 0.4520067572593689, "learning_rate": 1.0137037736857604e-05, "loss": 4.3044, "step": 23005 }, { "epoch": 0.7026878436163714, "grad_norm": 0.4682999551296234, "learning_rate": 1.0135108897289664e-05, "loss": 4.2746, "step": 23006 }, { "epoch": 0.7027183872938302, "grad_norm": 0.45507267117500305, "learning_rate": 1.013318019459041e-05, "loss": 4.3318, "step": 23007 }, { "epoch": 0.702748930971289, "grad_norm": 0.4607146978378296, "learning_rate": 1.013125162877761e-05, "loss": 4.1904, "step": 23008 }, { "epoch": 0.7027794746487477, "grad_norm": 0.4631039500236511, "learning_rate": 1.012932319986903e-05, "loss": 4.3302, "step": 23009 }, { "epoch": 0.7028100183262065, "grad_norm": 0.4715156853199005, "learning_rate": 1.0127394907882406e-05, "loss": 4.1971, "step": 23010 }, { "epoch": 0.7028405620036653, "grad_norm": 0.4517982304096222, "learning_rate": 1.0125466752835508e-05, "loss": 4.2368, "step": 23011 }, { "epoch": 0.702871105681124, "grad_norm": 0.458405077457428, "learning_rate": 1.012353873474609e-05, "loss": 4.366, "step": 23012 }, { "epoch": 0.7029016493585828, "grad_norm": 0.47398513555526733, "learning_rate": 1.0121610853631902e-05, "loss": 4.2731, "step": 23013 }, { "epoch": 0.7029321930360415, "grad_norm": 0.4592941105365753, "learning_rate": 1.0119683109510683e-05, "loss": 4.2051, "step": 23014 }, { "epoch": 0.7029627367135003, "grad_norm": 0.4617598354816437, "learning_rate": 1.0117755502400203e-05, "loss": 4.1914, "step": 23015 }, { "epoch": 0.7029932803909591, "grad_norm": 0.4590023458003998, "learning_rate": 1.0115828032318189e-05, "loss": 4.1133, "step": 23016 }, { "epoch": 0.7030238240684178, "grad_norm": 0.4609023630619049, "learning_rate": 1.0113900699282408e-05, "loss": 4.1986, "step": 23017 }, { "epoch": 0.7030543677458766, "grad_norm": 0.45247533917427063, "learning_rate": 1.0111973503310588e-05, "loss": 4.2719, "step": 23018 }, { "epoch": 0.7030849114233354, "grad_norm": 0.47367626428604126, "learning_rate": 1.0110046444420482e-05, "loss": 4.2675, "step": 23019 }, { "epoch": 0.7031154551007941, "grad_norm": 0.4585478901863098, "learning_rate": 1.0108119522629845e-05, "loss": 4.2152, "step": 23020 }, { "epoch": 0.7031459987782529, "grad_norm": 0.46187371015548706, "learning_rate": 1.0106192737956396e-05, "loss": 4.3156, "step": 23021 }, { "epoch": 0.7031765424557117, "grad_norm": 0.4590371549129486, "learning_rate": 1.0104266090417892e-05, "loss": 4.2357, "step": 23022 }, { "epoch": 0.7032070861331704, "grad_norm": 0.47585761547088623, "learning_rate": 1.0102339580032075e-05, "loss": 4.3428, "step": 23023 }, { "epoch": 0.7032376298106292, "grad_norm": 0.4658701717853546, "learning_rate": 1.010041320681667e-05, "loss": 4.3126, "step": 23024 }, { "epoch": 0.703268173488088, "grad_norm": 0.46406421065330505, "learning_rate": 1.009848697078942e-05, "loss": 4.2067, "step": 23025 }, { "epoch": 0.7032987171655467, "grad_norm": 0.454013854265213, "learning_rate": 1.0096560871968069e-05, "loss": 4.2674, "step": 23026 }, { "epoch": 0.7033292608430055, "grad_norm": 0.46603184938430786, "learning_rate": 1.009463491037034e-05, "loss": 4.3204, "step": 23027 }, { "epoch": 0.7033598045204643, "grad_norm": 0.4550715684890747, "learning_rate": 1.0092709086013977e-05, "loss": 4.293, "step": 23028 }, { "epoch": 0.703390348197923, "grad_norm": 0.4582831859588623, "learning_rate": 1.0090783398916697e-05, "loss": 4.2204, "step": 23029 }, { "epoch": 0.7034208918753818, "grad_norm": 0.4653182923793793, "learning_rate": 1.008885784909625e-05, "loss": 4.264, "step": 23030 }, { "epoch": 0.7034514355528405, "grad_norm": 0.4621841013431549, "learning_rate": 1.0086932436570357e-05, "loss": 4.1755, "step": 23031 }, { "epoch": 0.7034819792302993, "grad_norm": 0.4613579213619232, "learning_rate": 1.0085007161356732e-05, "loss": 4.2734, "step": 23032 }, { "epoch": 0.7035125229077581, "grad_norm": 0.4590741693973541, "learning_rate": 1.0083082023473117e-05, "loss": 4.2772, "step": 23033 }, { "epoch": 0.7035430665852168, "grad_norm": 0.46610742807388306, "learning_rate": 1.0081157022937244e-05, "loss": 4.1531, "step": 23034 }, { "epoch": 0.7035736102626756, "grad_norm": 0.4567195177078247, "learning_rate": 1.0079232159766818e-05, "loss": 4.2937, "step": 23035 }, { "epoch": 0.7036041539401344, "grad_norm": 0.46467792987823486, "learning_rate": 1.0077307433979574e-05, "loss": 4.2924, "step": 23036 }, { "epoch": 0.7036346976175931, "grad_norm": 0.4575294852256775, "learning_rate": 1.0075382845593243e-05, "loss": 4.2977, "step": 23037 }, { "epoch": 0.7036652412950519, "grad_norm": 0.48946547508239746, "learning_rate": 1.0073458394625526e-05, "loss": 4.3083, "step": 23038 }, { "epoch": 0.7036957849725107, "grad_norm": 0.45837029814720154, "learning_rate": 1.0071534081094153e-05, "loss": 4.2333, "step": 23039 }, { "epoch": 0.7037263286499694, "grad_norm": 0.4522396922111511, "learning_rate": 1.0069609905016847e-05, "loss": 4.2159, "step": 23040 }, { "epoch": 0.7037568723274282, "grad_norm": 0.45263272523880005, "learning_rate": 1.0067685866411314e-05, "loss": 4.2471, "step": 23041 }, { "epoch": 0.703787416004887, "grad_norm": 0.4616856575012207, "learning_rate": 1.0065761965295273e-05, "loss": 4.302, "step": 23042 }, { "epoch": 0.7038179596823457, "grad_norm": 0.4636785686016083, "learning_rate": 1.0063838201686448e-05, "loss": 4.2626, "step": 23043 }, { "epoch": 0.7038485033598045, "grad_norm": 0.4611174762248993, "learning_rate": 1.0061914575602535e-05, "loss": 4.2807, "step": 23044 }, { "epoch": 0.7038790470372633, "grad_norm": 0.45878198742866516, "learning_rate": 1.0059991087061266e-05, "loss": 4.3397, "step": 23045 }, { "epoch": 0.703909590714722, "grad_norm": 0.45369938015937805, "learning_rate": 1.005806773608034e-05, "loss": 4.1157, "step": 23046 }, { "epoch": 0.7039401343921808, "grad_norm": 0.45363712310791016, "learning_rate": 1.0056144522677454e-05, "loss": 4.2823, "step": 23047 }, { "epoch": 0.7039706780696395, "grad_norm": 0.47958725690841675, "learning_rate": 1.0054221446870343e-05, "loss": 4.1888, "step": 23048 }, { "epoch": 0.7040012217470983, "grad_norm": 0.45669102668762207, "learning_rate": 1.0052298508676688e-05, "loss": 4.3448, "step": 23049 }, { "epoch": 0.7040317654245571, "grad_norm": 0.4604009985923767, "learning_rate": 1.0050375708114207e-05, "loss": 4.3158, "step": 23050 }, { "epoch": 0.7040623091020158, "grad_norm": 0.46689555048942566, "learning_rate": 1.0048453045200609e-05, "loss": 4.3011, "step": 23051 }, { "epoch": 0.7040928527794746, "grad_norm": 0.46315911412239075, "learning_rate": 1.0046530519953587e-05, "loss": 4.2364, "step": 23052 }, { "epoch": 0.7041233964569334, "grad_norm": 0.45807650685310364, "learning_rate": 1.0044608132390842e-05, "loss": 4.1467, "step": 23053 }, { "epoch": 0.7041539401343921, "grad_norm": 0.48090770840644836, "learning_rate": 1.0042685882530093e-05, "loss": 4.283, "step": 23054 }, { "epoch": 0.704184483811851, "grad_norm": 0.4541815519332886, "learning_rate": 1.0040763770389014e-05, "loss": 4.3022, "step": 23055 }, { "epoch": 0.7042150274893098, "grad_norm": 0.4689810574054718, "learning_rate": 1.0038841795985312e-05, "loss": 4.2599, "step": 23056 }, { "epoch": 0.7042455711667684, "grad_norm": 0.4584248661994934, "learning_rate": 1.00369199593367e-05, "loss": 4.1937, "step": 23057 }, { "epoch": 0.7042761148442273, "grad_norm": 0.45371997356414795, "learning_rate": 1.0034998260460845e-05, "loss": 4.193, "step": 23058 }, { "epoch": 0.7043066585216861, "grad_norm": 0.46233171224594116, "learning_rate": 1.0033076699375457e-05, "loss": 4.2863, "step": 23059 }, { "epoch": 0.7043372021991448, "grad_norm": 0.47142934799194336, "learning_rate": 1.003115527609824e-05, "loss": 4.3463, "step": 23060 }, { "epoch": 0.7043677458766036, "grad_norm": 0.4532269537448883, "learning_rate": 1.0029233990646866e-05, "loss": 4.1963, "step": 23061 }, { "epoch": 0.7043982895540624, "grad_norm": 0.4508669972419739, "learning_rate": 1.0027312843039027e-05, "loss": 4.2852, "step": 23062 }, { "epoch": 0.7044288332315211, "grad_norm": 0.45702627301216125, "learning_rate": 1.0025391833292424e-05, "loss": 4.19, "step": 23063 }, { "epoch": 0.7044593769089799, "grad_norm": 0.4719793200492859, "learning_rate": 1.0023470961424731e-05, "loss": 4.2992, "step": 23064 }, { "epoch": 0.7044899205864386, "grad_norm": 0.48291823267936707, "learning_rate": 1.0021550227453646e-05, "loss": 4.3327, "step": 23065 }, { "epoch": 0.7045204642638974, "grad_norm": 0.47072353959083557, "learning_rate": 1.0019629631396845e-05, "loss": 4.2608, "step": 23066 }, { "epoch": 0.7045510079413562, "grad_norm": 0.45924296975135803, "learning_rate": 1.0017709173272013e-05, "loss": 4.2946, "step": 23067 }, { "epoch": 0.7045815516188149, "grad_norm": 0.4572850167751312, "learning_rate": 1.0015788853096846e-05, "loss": 4.3343, "step": 23068 }, { "epoch": 0.7046120952962737, "grad_norm": 0.45879343152046204, "learning_rate": 1.0013868670889007e-05, "loss": 4.2453, "step": 23069 }, { "epoch": 0.7046426389737325, "grad_norm": 0.45113834738731384, "learning_rate": 1.0011948626666182e-05, "loss": 4.252, "step": 23070 }, { "epoch": 0.7046731826511912, "grad_norm": 0.4653469920158386, "learning_rate": 1.0010028720446063e-05, "loss": 4.2404, "step": 23071 }, { "epoch": 0.70470372632865, "grad_norm": 0.4519544839859009, "learning_rate": 1.0008108952246306e-05, "loss": 4.1746, "step": 23072 }, { "epoch": 0.7047342700061088, "grad_norm": 0.46737703680992126, "learning_rate": 1.0006189322084597e-05, "loss": 4.2544, "step": 23073 }, { "epoch": 0.7047648136835675, "grad_norm": 0.4730914831161499, "learning_rate": 1.0004269829978624e-05, "loss": 4.2442, "step": 23074 }, { "epoch": 0.7047953573610263, "grad_norm": 0.4533568024635315, "learning_rate": 1.0002350475946037e-05, "loss": 4.2871, "step": 23075 }, { "epoch": 0.7048259010384851, "grad_norm": 0.46412500739097595, "learning_rate": 1.000043126000453e-05, "loss": 4.3305, "step": 23076 }, { "epoch": 0.7048564447159438, "grad_norm": 0.467363566160202, "learning_rate": 9.998512182171766e-06, "loss": 4.1347, "step": 23077 }, { "epoch": 0.7048869883934026, "grad_norm": 0.4553213119506836, "learning_rate": 9.996593242465405e-06, "loss": 4.2375, "step": 23078 }, { "epoch": 0.7049175320708614, "grad_norm": 0.44675305485725403, "learning_rate": 9.99467444090312e-06, "loss": 4.2906, "step": 23079 }, { "epoch": 0.7049480757483201, "grad_norm": 0.45938149094581604, "learning_rate": 9.992755777502593e-06, "loss": 4.3106, "step": 23080 }, { "epoch": 0.7049786194257789, "grad_norm": 0.44512882828712463, "learning_rate": 9.990837252281474e-06, "loss": 4.3005, "step": 23081 }, { "epoch": 0.7050091631032376, "grad_norm": 0.4493720531463623, "learning_rate": 9.988918865257438e-06, "loss": 4.1604, "step": 23082 }, { "epoch": 0.7050397067806964, "grad_norm": 0.4520198404788971, "learning_rate": 9.987000616448135e-06, "loss": 4.1762, "step": 23083 }, { "epoch": 0.7050702504581552, "grad_norm": 0.4533489942550659, "learning_rate": 9.98508250587124e-06, "loss": 4.255, "step": 23084 }, { "epoch": 0.7051007941356139, "grad_norm": 0.4599812626838684, "learning_rate": 9.983164533544418e-06, "loss": 4.2509, "step": 23085 }, { "epoch": 0.7051313378130727, "grad_norm": 0.4591324031352997, "learning_rate": 9.981246699485311e-06, "loss": 4.2406, "step": 23086 }, { "epoch": 0.7051618814905315, "grad_norm": 0.4603704810142517, "learning_rate": 9.979329003711587e-06, "loss": 4.1595, "step": 23087 }, { "epoch": 0.7051924251679902, "grad_norm": 0.459425687789917, "learning_rate": 9.977411446240915e-06, "loss": 4.1524, "step": 23088 }, { "epoch": 0.705222968845449, "grad_norm": 0.45208731293678284, "learning_rate": 9.975494027090926e-06, "loss": 4.2066, "step": 23089 }, { "epoch": 0.7052535125229078, "grad_norm": 0.4620734751224518, "learning_rate": 9.973576746279293e-06, "loss": 4.2375, "step": 23090 }, { "epoch": 0.7052840562003665, "grad_norm": 0.45894110202789307, "learning_rate": 9.971659603823672e-06, "loss": 4.2938, "step": 23091 }, { "epoch": 0.7053145998778253, "grad_norm": 0.4495236575603485, "learning_rate": 9.969742599741707e-06, "loss": 4.2538, "step": 23092 }, { "epoch": 0.7053451435552841, "grad_norm": 0.4673782289028168, "learning_rate": 9.967825734051042e-06, "loss": 4.2979, "step": 23093 }, { "epoch": 0.7053756872327428, "grad_norm": 0.46088293194770813, "learning_rate": 9.965909006769342e-06, "loss": 4.2594, "step": 23094 }, { "epoch": 0.7054062309102016, "grad_norm": 0.45368289947509766, "learning_rate": 9.96399241791424e-06, "loss": 4.3667, "step": 23095 }, { "epoch": 0.7054367745876604, "grad_norm": 0.4569559395313263, "learning_rate": 9.96207596750339e-06, "loss": 4.2226, "step": 23096 }, { "epoch": 0.7054673182651191, "grad_norm": 0.4603409171104431, "learning_rate": 9.960159655554446e-06, "loss": 4.3377, "step": 23097 }, { "epoch": 0.7054978619425779, "grad_norm": 0.4673362076282501, "learning_rate": 9.958243482085036e-06, "loss": 4.2319, "step": 23098 }, { "epoch": 0.7055284056200366, "grad_norm": 0.4525774121284485, "learning_rate": 9.956327447112823e-06, "loss": 4.2622, "step": 23099 }, { "epoch": 0.7055589492974954, "grad_norm": 0.4546589255332947, "learning_rate": 9.954411550655429e-06, "loss": 4.2743, "step": 23100 }, { "epoch": 0.7055894929749542, "grad_norm": 0.4823246896266937, "learning_rate": 9.952495792730502e-06, "loss": 4.2699, "step": 23101 }, { "epoch": 0.7056200366524129, "grad_norm": 0.4622527062892914, "learning_rate": 9.950580173355692e-06, "loss": 4.1996, "step": 23102 }, { "epoch": 0.7056505803298717, "grad_norm": 0.4545964002609253, "learning_rate": 9.948664692548617e-06, "loss": 4.2311, "step": 23103 }, { "epoch": 0.7056811240073305, "grad_norm": 0.4536034166812897, "learning_rate": 9.946749350326928e-06, "loss": 4.3007, "step": 23104 }, { "epoch": 0.7057116676847892, "grad_norm": 0.46026840806007385, "learning_rate": 9.944834146708264e-06, "loss": 4.2579, "step": 23105 }, { "epoch": 0.705742211362248, "grad_norm": 0.45471763610839844, "learning_rate": 9.942919081710247e-06, "loss": 4.2277, "step": 23106 }, { "epoch": 0.7057727550397068, "grad_norm": 0.46993204951286316, "learning_rate": 9.941004155350523e-06, "loss": 4.2628, "step": 23107 }, { "epoch": 0.7058032987171655, "grad_norm": 0.45177143812179565, "learning_rate": 9.939089367646707e-06, "loss": 4.2771, "step": 23108 }, { "epoch": 0.7058338423946243, "grad_norm": 0.48037979006767273, "learning_rate": 9.937174718616446e-06, "loss": 4.3174, "step": 23109 }, { "epoch": 0.7058643860720831, "grad_norm": 0.4621104598045349, "learning_rate": 9.935260208277355e-06, "loss": 4.3159, "step": 23110 }, { "epoch": 0.7058949297495418, "grad_norm": 0.4578273892402649, "learning_rate": 9.933345836647078e-06, "loss": 4.3247, "step": 23111 }, { "epoch": 0.7059254734270006, "grad_norm": 0.45639100670814514, "learning_rate": 9.931431603743222e-06, "loss": 4.156, "step": 23112 }, { "epoch": 0.7059560171044594, "grad_norm": 0.46296778321266174, "learning_rate": 9.929517509583426e-06, "loss": 4.2928, "step": 23113 }, { "epoch": 0.7059865607819181, "grad_norm": 0.4653470516204834, "learning_rate": 9.927603554185317e-06, "loss": 4.2363, "step": 23114 }, { "epoch": 0.7060171044593769, "grad_norm": 0.45537352561950684, "learning_rate": 9.9256897375665e-06, "loss": 4.2933, "step": 23115 }, { "epoch": 0.7060476481368356, "grad_norm": 0.46960756182670593, "learning_rate": 9.923776059744621e-06, "loss": 4.2237, "step": 23116 }, { "epoch": 0.7060781918142944, "grad_norm": 0.4563004672527313, "learning_rate": 9.921862520737277e-06, "loss": 4.2402, "step": 23117 }, { "epoch": 0.7061087354917532, "grad_norm": 0.45318540930747986, "learning_rate": 9.919949120562098e-06, "loss": 4.2485, "step": 23118 }, { "epoch": 0.7061392791692119, "grad_norm": 0.46071451902389526, "learning_rate": 9.918035859236708e-06, "loss": 4.2156, "step": 23119 }, { "epoch": 0.7061698228466707, "grad_norm": 0.45343369245529175, "learning_rate": 9.916122736778707e-06, "loss": 4.2649, "step": 23120 }, { "epoch": 0.7062003665241295, "grad_norm": 0.456037312746048, "learning_rate": 9.914209753205722e-06, "loss": 4.3264, "step": 23121 }, { "epoch": 0.7062309102015882, "grad_norm": 0.4648887515068054, "learning_rate": 9.91229690853537e-06, "loss": 4.3077, "step": 23122 }, { "epoch": 0.706261453879047, "grad_norm": 0.44589248299598694, "learning_rate": 9.910384202785261e-06, "loss": 4.2756, "step": 23123 }, { "epoch": 0.7062919975565058, "grad_norm": 0.46070826053619385, "learning_rate": 9.908471635972993e-06, "loss": 4.264, "step": 23124 }, { "epoch": 0.7063225412339645, "grad_norm": 0.4559106230735779, "learning_rate": 9.906559208116192e-06, "loss": 4.304, "step": 23125 }, { "epoch": 0.7063530849114233, "grad_norm": 0.4667585790157318, "learning_rate": 9.904646919232454e-06, "loss": 4.182, "step": 23126 }, { "epoch": 0.7063836285888822, "grad_norm": 0.46126317977905273, "learning_rate": 9.902734769339395e-06, "loss": 4.2403, "step": 23127 }, { "epoch": 0.7064141722663408, "grad_norm": 0.4577389657497406, "learning_rate": 9.900822758454626e-06, "loss": 4.2564, "step": 23128 }, { "epoch": 0.7064447159437997, "grad_norm": 0.4520096480846405, "learning_rate": 9.898910886595735e-06, "loss": 4.2749, "step": 23129 }, { "epoch": 0.7064752596212583, "grad_norm": 0.47357943654060364, "learning_rate": 9.896999153780349e-06, "loss": 4.2147, "step": 23130 }, { "epoch": 0.7065058032987171, "grad_norm": 0.45870959758758545, "learning_rate": 9.895087560026042e-06, "loss": 4.2607, "step": 23131 }, { "epoch": 0.706536346976176, "grad_norm": 0.46040603518486023, "learning_rate": 9.893176105350436e-06, "loss": 4.2798, "step": 23132 }, { "epoch": 0.7065668906536346, "grad_norm": 0.46132704615592957, "learning_rate": 9.89126478977113e-06, "loss": 4.3045, "step": 23133 }, { "epoch": 0.7065974343310935, "grad_norm": 0.4552106559276581, "learning_rate": 9.889353613305707e-06, "loss": 4.2469, "step": 23134 }, { "epoch": 0.7066279780085523, "grad_norm": 0.44918540120124817, "learning_rate": 9.887442575971778e-06, "loss": 4.3065, "step": 23135 }, { "epoch": 0.706658521686011, "grad_norm": 0.44876402616500854, "learning_rate": 9.88553167778694e-06, "loss": 4.2892, "step": 23136 }, { "epoch": 0.7066890653634698, "grad_norm": 0.45816540718078613, "learning_rate": 9.88362091876878e-06, "loss": 4.1559, "step": 23137 }, { "epoch": 0.7067196090409286, "grad_norm": 0.46071428060531616, "learning_rate": 9.881710298934898e-06, "loss": 4.2956, "step": 23138 }, { "epoch": 0.7067501527183873, "grad_norm": 0.46427345275878906, "learning_rate": 9.879799818302876e-06, "loss": 4.3312, "step": 23139 }, { "epoch": 0.7067806963958461, "grad_norm": 0.45444613695144653, "learning_rate": 9.87788947689032e-06, "loss": 4.2826, "step": 23140 }, { "epoch": 0.7068112400733049, "grad_norm": 0.45392969250679016, "learning_rate": 9.8759792747148e-06, "loss": 4.2728, "step": 23141 }, { "epoch": 0.7068417837507636, "grad_norm": 0.4551650881767273, "learning_rate": 9.874069211793923e-06, "loss": 4.3466, "step": 23142 }, { "epoch": 0.7068723274282224, "grad_norm": 0.45592039823532104, "learning_rate": 9.872159288145263e-06, "loss": 4.2802, "step": 23143 }, { "epoch": 0.7069028711056812, "grad_norm": 0.47649648785591125, "learning_rate": 9.870249503786408e-06, "loss": 4.2551, "step": 23144 }, { "epoch": 0.7069334147831399, "grad_norm": 0.4590950012207031, "learning_rate": 9.868339858734955e-06, "loss": 4.2341, "step": 23145 }, { "epoch": 0.7069639584605987, "grad_norm": 0.46636515855789185, "learning_rate": 9.866430353008465e-06, "loss": 4.3192, "step": 23146 }, { "epoch": 0.7069945021380574, "grad_norm": 0.4687153100967407, "learning_rate": 9.864520986624543e-06, "loss": 4.0984, "step": 23147 }, { "epoch": 0.7070250458155162, "grad_norm": 0.4694165289402008, "learning_rate": 9.862611759600749e-06, "loss": 4.2512, "step": 23148 }, { "epoch": 0.707055589492975, "grad_norm": 0.46264535188674927, "learning_rate": 9.860702671954668e-06, "loss": 4.291, "step": 23149 }, { "epoch": 0.7070861331704337, "grad_norm": 0.4603342115879059, "learning_rate": 9.858793723703893e-06, "loss": 4.3008, "step": 23150 }, { "epoch": 0.7071166768478925, "grad_norm": 0.4621749818325043, "learning_rate": 9.856884914865983e-06, "loss": 4.2156, "step": 23151 }, { "epoch": 0.7071472205253513, "grad_norm": 0.4587376117706299, "learning_rate": 9.854976245458516e-06, "loss": 4.3153, "step": 23152 }, { "epoch": 0.70717776420281, "grad_norm": 0.45951512455940247, "learning_rate": 9.853067715499078e-06, "loss": 4.1724, "step": 23153 }, { "epoch": 0.7072083078802688, "grad_norm": 0.45432522892951965, "learning_rate": 9.851159325005227e-06, "loss": 4.2019, "step": 23154 }, { "epoch": 0.7072388515577276, "grad_norm": 0.4508526623249054, "learning_rate": 9.849251073994547e-06, "loss": 4.2405, "step": 23155 }, { "epoch": 0.7072693952351863, "grad_norm": 0.45899996161460876, "learning_rate": 9.847342962484605e-06, "loss": 4.3243, "step": 23156 }, { "epoch": 0.7072999389126451, "grad_norm": 0.4615086615085602, "learning_rate": 9.845434990492954e-06, "loss": 4.2461, "step": 23157 }, { "epoch": 0.7073304825901039, "grad_norm": 0.4560815095901489, "learning_rate": 9.843527158037177e-06, "loss": 4.2325, "step": 23158 }, { "epoch": 0.7073610262675626, "grad_norm": 0.46405720710754395, "learning_rate": 9.841619465134849e-06, "loss": 4.3499, "step": 23159 }, { "epoch": 0.7073915699450214, "grad_norm": 0.4522605240345001, "learning_rate": 9.839711911803512e-06, "loss": 4.2614, "step": 23160 }, { "epoch": 0.7074221136224802, "grad_norm": 0.4626619815826416, "learning_rate": 9.837804498060743e-06, "loss": 4.1816, "step": 23161 }, { "epoch": 0.7074526572999389, "grad_norm": 0.44665032625198364, "learning_rate": 9.835897223924115e-06, "loss": 4.2428, "step": 23162 }, { "epoch": 0.7074832009773977, "grad_norm": 0.45447635650634766, "learning_rate": 9.833990089411165e-06, "loss": 4.2292, "step": 23163 }, { "epoch": 0.7075137446548564, "grad_norm": 0.46306657791137695, "learning_rate": 9.832083094539479e-06, "loss": 4.2782, "step": 23164 }, { "epoch": 0.7075442883323152, "grad_norm": 0.4662298560142517, "learning_rate": 9.830176239326592e-06, "loss": 4.2546, "step": 23165 }, { "epoch": 0.707574832009774, "grad_norm": 0.4609185755252838, "learning_rate": 9.828269523790071e-06, "loss": 4.235, "step": 23166 }, { "epoch": 0.7076053756872327, "grad_norm": 0.4657934904098511, "learning_rate": 9.826362947947481e-06, "loss": 4.2465, "step": 23167 }, { "epoch": 0.7076359193646915, "grad_norm": 0.45718860626220703, "learning_rate": 9.824456511816364e-06, "loss": 4.2841, "step": 23168 }, { "epoch": 0.7076664630421503, "grad_norm": 0.46439605951309204, "learning_rate": 9.822550215414275e-06, "loss": 4.19, "step": 23169 }, { "epoch": 0.707697006719609, "grad_norm": 0.4702533185482025, "learning_rate": 9.82064405875878e-06, "loss": 4.256, "step": 23170 }, { "epoch": 0.7077275503970678, "grad_norm": 0.45462942123413086, "learning_rate": 9.818738041867418e-06, "loss": 4.2377, "step": 23171 }, { "epoch": 0.7077580940745266, "grad_norm": 0.4618949592113495, "learning_rate": 9.81683216475773e-06, "loss": 4.2398, "step": 23172 }, { "epoch": 0.7077886377519853, "grad_norm": 0.4591268301010132, "learning_rate": 9.814926427447289e-06, "loss": 4.2112, "step": 23173 }, { "epoch": 0.7078191814294441, "grad_norm": 0.46123018860816956, "learning_rate": 9.813020829953614e-06, "loss": 4.1848, "step": 23174 }, { "epoch": 0.7078497251069029, "grad_norm": 0.46019506454467773, "learning_rate": 9.811115372294266e-06, "loss": 4.2591, "step": 23175 }, { "epoch": 0.7078802687843616, "grad_norm": 0.46567749977111816, "learning_rate": 9.809210054486797e-06, "loss": 4.1733, "step": 23176 }, { "epoch": 0.7079108124618204, "grad_norm": 0.4752846956253052, "learning_rate": 9.807304876548735e-06, "loss": 4.3174, "step": 23177 }, { "epoch": 0.7079413561392792, "grad_norm": 0.45860251784324646, "learning_rate": 9.805399838497625e-06, "loss": 4.2314, "step": 23178 }, { "epoch": 0.7079718998167379, "grad_norm": 0.4582398533821106, "learning_rate": 9.803494940351022e-06, "loss": 4.209, "step": 23179 }, { "epoch": 0.7080024434941967, "grad_norm": 0.4491865038871765, "learning_rate": 9.801590182126443e-06, "loss": 4.2631, "step": 23180 }, { "epoch": 0.7080329871716554, "grad_norm": 0.45894959568977356, "learning_rate": 9.799685563841448e-06, "loss": 4.216, "step": 23181 }, { "epoch": 0.7080635308491142, "grad_norm": 0.4599539339542389, "learning_rate": 9.797781085513552e-06, "loss": 4.1819, "step": 23182 }, { "epoch": 0.708094074526573, "grad_norm": 0.46828851103782654, "learning_rate": 9.795876747160304e-06, "loss": 4.1951, "step": 23183 }, { "epoch": 0.7081246182040317, "grad_norm": 0.46990132331848145, "learning_rate": 9.793972548799246e-06, "loss": 4.3387, "step": 23184 }, { "epoch": 0.7081551618814905, "grad_norm": 0.4422408938407898, "learning_rate": 9.792068490447892e-06, "loss": 4.2735, "step": 23185 }, { "epoch": 0.7081857055589493, "grad_norm": 0.47321292757987976, "learning_rate": 9.79016457212379e-06, "loss": 4.3154, "step": 23186 }, { "epoch": 0.708216249236408, "grad_norm": 0.4541053771972656, "learning_rate": 9.788260793844462e-06, "loss": 4.2662, "step": 23187 }, { "epoch": 0.7082467929138668, "grad_norm": 0.45249366760253906, "learning_rate": 9.78635715562743e-06, "loss": 4.2668, "step": 23188 }, { "epoch": 0.7082773365913256, "grad_norm": 0.4654524326324463, "learning_rate": 9.78445365749023e-06, "loss": 4.2951, "step": 23189 }, { "epoch": 0.7083078802687843, "grad_norm": 0.45734909176826477, "learning_rate": 9.782550299450396e-06, "loss": 4.2348, "step": 23190 }, { "epoch": 0.7083384239462431, "grad_norm": 0.4666065275669098, "learning_rate": 9.780647081525438e-06, "loss": 4.2223, "step": 23191 }, { "epoch": 0.7083689676237019, "grad_norm": 0.45242834091186523, "learning_rate": 9.778744003732886e-06, "loss": 4.1848, "step": 23192 }, { "epoch": 0.7083995113011606, "grad_norm": 0.4522998332977295, "learning_rate": 9.776841066090276e-06, "loss": 4.1939, "step": 23193 }, { "epoch": 0.7084300549786194, "grad_norm": 0.4630124568939209, "learning_rate": 9.774938268615106e-06, "loss": 4.2406, "step": 23194 }, { "epoch": 0.7084605986560782, "grad_norm": 0.4552460312843323, "learning_rate": 9.773035611324907e-06, "loss": 4.3115, "step": 23195 }, { "epoch": 0.7084911423335369, "grad_norm": 0.4548306465148926, "learning_rate": 9.771133094237205e-06, "loss": 4.3228, "step": 23196 }, { "epoch": 0.7085216860109957, "grad_norm": 0.4655759632587433, "learning_rate": 9.769230717369506e-06, "loss": 4.3467, "step": 23197 }, { "epoch": 0.7085522296884544, "grad_norm": 0.4761682450771332, "learning_rate": 9.767328480739338e-06, "loss": 4.2184, "step": 23198 }, { "epoch": 0.7085827733659132, "grad_norm": 0.45436403155326843, "learning_rate": 9.7654263843642e-06, "loss": 4.2108, "step": 23199 }, { "epoch": 0.708613317043372, "grad_norm": 0.46247050166130066, "learning_rate": 9.763524428261611e-06, "loss": 4.1448, "step": 23200 }, { "epoch": 0.7086438607208307, "grad_norm": 0.45902833342552185, "learning_rate": 9.761622612449097e-06, "loss": 4.2546, "step": 23201 }, { "epoch": 0.7086744043982895, "grad_norm": 0.4668598771095276, "learning_rate": 9.759720936944162e-06, "loss": 4.3183, "step": 23202 }, { "epoch": 0.7087049480757484, "grad_norm": 0.45419251918792725, "learning_rate": 9.757819401764299e-06, "loss": 4.238, "step": 23203 }, { "epoch": 0.708735491753207, "grad_norm": 0.4828346371650696, "learning_rate": 9.755918006927039e-06, "loss": 4.2557, "step": 23204 }, { "epoch": 0.7087660354306659, "grad_norm": 0.46078556776046753, "learning_rate": 9.754016752449871e-06, "loss": 4.3047, "step": 23205 }, { "epoch": 0.7087965791081247, "grad_norm": 0.4622800350189209, "learning_rate": 9.752115638350313e-06, "loss": 4.2101, "step": 23206 }, { "epoch": 0.7088271227855834, "grad_norm": 0.454279363155365, "learning_rate": 9.750214664645871e-06, "loss": 4.2668, "step": 23207 }, { "epoch": 0.7088576664630422, "grad_norm": 0.46027401089668274, "learning_rate": 9.748313831354034e-06, "loss": 4.3007, "step": 23208 }, { "epoch": 0.708888210140501, "grad_norm": 0.4593225121498108, "learning_rate": 9.746413138492314e-06, "loss": 4.2881, "step": 23209 }, { "epoch": 0.7089187538179597, "grad_norm": 0.45564696192741394, "learning_rate": 9.74451258607822e-06, "loss": 4.2446, "step": 23210 }, { "epoch": 0.7089492974954185, "grad_norm": 0.4710938632488251, "learning_rate": 9.742612174129234e-06, "loss": 4.2921, "step": 23211 }, { "epoch": 0.7089798411728773, "grad_norm": 0.4575028419494629, "learning_rate": 9.74071190266286e-06, "loss": 4.2824, "step": 23212 }, { "epoch": 0.709010384850336, "grad_norm": 0.4635658264160156, "learning_rate": 9.73881177169661e-06, "loss": 4.3445, "step": 23213 }, { "epoch": 0.7090409285277948, "grad_norm": 0.46286195516586304, "learning_rate": 9.736911781247954e-06, "loss": 4.2736, "step": 23214 }, { "epoch": 0.7090714722052535, "grad_norm": 0.453801691532135, "learning_rate": 9.735011931334409e-06, "loss": 4.0864, "step": 23215 }, { "epoch": 0.7091020158827123, "grad_norm": 0.4668639600276947, "learning_rate": 9.73311222197345e-06, "loss": 4.2992, "step": 23216 }, { "epoch": 0.7091325595601711, "grad_norm": 0.4601311981678009, "learning_rate": 9.731212653182583e-06, "loss": 4.2336, "step": 23217 }, { "epoch": 0.7091631032376298, "grad_norm": 0.45837801694869995, "learning_rate": 9.729313224979283e-06, "loss": 4.3389, "step": 23218 }, { "epoch": 0.7091936469150886, "grad_norm": 0.4603736102581024, "learning_rate": 9.727413937381058e-06, "loss": 4.2058, "step": 23219 }, { "epoch": 0.7092241905925474, "grad_norm": 0.46540993452072144, "learning_rate": 9.725514790405375e-06, "loss": 4.306, "step": 23220 }, { "epoch": 0.7092547342700061, "grad_norm": 0.47321778535842896, "learning_rate": 9.72361578406974e-06, "loss": 4.3496, "step": 23221 }, { "epoch": 0.7092852779474649, "grad_norm": 0.45891839265823364, "learning_rate": 9.721716918391618e-06, "loss": 4.2915, "step": 23222 }, { "epoch": 0.7093158216249237, "grad_norm": 0.45134907960891724, "learning_rate": 9.719818193388505e-06, "loss": 4.1973, "step": 23223 }, { "epoch": 0.7093463653023824, "grad_norm": 0.45775100588798523, "learning_rate": 9.717919609077893e-06, "loss": 4.2071, "step": 23224 }, { "epoch": 0.7093769089798412, "grad_norm": 0.46146300435066223, "learning_rate": 9.716021165477243e-06, "loss": 4.2918, "step": 23225 }, { "epoch": 0.7094074526573, "grad_norm": 0.4733916223049164, "learning_rate": 9.714122862604041e-06, "loss": 4.2695, "step": 23226 }, { "epoch": 0.7094379963347587, "grad_norm": 0.459602028131485, "learning_rate": 9.71222470047578e-06, "loss": 4.2838, "step": 23227 }, { "epoch": 0.7094685400122175, "grad_norm": 0.45650410652160645, "learning_rate": 9.710326679109918e-06, "loss": 4.2557, "step": 23228 }, { "epoch": 0.7094990836896763, "grad_norm": 0.4606039524078369, "learning_rate": 9.708428798523941e-06, "loss": 4.2614, "step": 23229 }, { "epoch": 0.709529627367135, "grad_norm": 0.45418477058410645, "learning_rate": 9.70653105873533e-06, "loss": 4.1847, "step": 23230 }, { "epoch": 0.7095601710445938, "grad_norm": 0.45907530188560486, "learning_rate": 9.704633459761539e-06, "loss": 4.2729, "step": 23231 }, { "epoch": 0.7095907147220525, "grad_norm": 0.4523838758468628, "learning_rate": 9.702736001620064e-06, "loss": 4.2275, "step": 23232 }, { "epoch": 0.7096212583995113, "grad_norm": 0.4706580936908722, "learning_rate": 9.700838684328361e-06, "loss": 4.2778, "step": 23233 }, { "epoch": 0.7096518020769701, "grad_norm": 0.453581839799881, "learning_rate": 9.698941507903896e-06, "loss": 4.2607, "step": 23234 }, { "epoch": 0.7096823457544288, "grad_norm": 0.4562436044216156, "learning_rate": 9.69704447236415e-06, "loss": 4.2869, "step": 23235 }, { "epoch": 0.7097128894318876, "grad_norm": 0.4608842134475708, "learning_rate": 9.695147577726577e-06, "loss": 4.3563, "step": 23236 }, { "epoch": 0.7097434331093464, "grad_norm": 0.4599579870700836, "learning_rate": 9.693250824008648e-06, "loss": 4.3027, "step": 23237 }, { "epoch": 0.7097739767868051, "grad_norm": 0.45792585611343384, "learning_rate": 9.691354211227838e-06, "loss": 4.2316, "step": 23238 }, { "epoch": 0.7098045204642639, "grad_norm": 0.4581086337566376, "learning_rate": 9.689457739401592e-06, "loss": 4.2632, "step": 23239 }, { "epoch": 0.7098350641417227, "grad_norm": 0.45950397849082947, "learning_rate": 9.68756140854738e-06, "loss": 4.2091, "step": 23240 }, { "epoch": 0.7098656078191814, "grad_norm": 0.4598842263221741, "learning_rate": 9.68566521868267e-06, "loss": 4.2541, "step": 23241 }, { "epoch": 0.7098961514966402, "grad_norm": 0.45641204714775085, "learning_rate": 9.68376916982491e-06, "loss": 4.1588, "step": 23242 }, { "epoch": 0.709926695174099, "grad_norm": 0.46603450179100037, "learning_rate": 9.681873261991559e-06, "loss": 4.343, "step": 23243 }, { "epoch": 0.7099572388515577, "grad_norm": 0.4667600095272064, "learning_rate": 9.679977495200085e-06, "loss": 4.1377, "step": 23244 }, { "epoch": 0.7099877825290165, "grad_norm": 0.45048508048057556, "learning_rate": 9.678081869467929e-06, "loss": 4.1985, "step": 23245 }, { "epoch": 0.7100183262064753, "grad_norm": 0.4620760381221771, "learning_rate": 9.676186384812547e-06, "loss": 4.2076, "step": 23246 }, { "epoch": 0.710048869883934, "grad_norm": 0.45757630467414856, "learning_rate": 9.674291041251408e-06, "loss": 4.1635, "step": 23247 }, { "epoch": 0.7100794135613928, "grad_norm": 0.45499950647354126, "learning_rate": 9.672395838801947e-06, "loss": 4.2095, "step": 23248 }, { "epoch": 0.7101099572388515, "grad_norm": 0.4708949029445648, "learning_rate": 9.670500777481615e-06, "loss": 4.2349, "step": 23249 }, { "epoch": 0.7101405009163103, "grad_norm": 0.4539317190647125, "learning_rate": 9.66860585730787e-06, "loss": 4.2826, "step": 23250 }, { "epoch": 0.7101710445937691, "grad_norm": 0.46037477254867554, "learning_rate": 9.666711078298144e-06, "loss": 4.2905, "step": 23251 }, { "epoch": 0.7102015882712278, "grad_norm": 0.4777250289916992, "learning_rate": 9.6648164404699e-06, "loss": 4.251, "step": 23252 }, { "epoch": 0.7102321319486866, "grad_norm": 0.47121864557266235, "learning_rate": 9.66292194384057e-06, "loss": 4.2783, "step": 23253 }, { "epoch": 0.7102626756261454, "grad_norm": 0.45556262135505676, "learning_rate": 9.661027588427602e-06, "loss": 4.3198, "step": 23254 }, { "epoch": 0.7102932193036041, "grad_norm": 0.4595850706100464, "learning_rate": 9.659133374248447e-06, "loss": 4.2892, "step": 23255 }, { "epoch": 0.7103237629810629, "grad_norm": 0.4560868740081787, "learning_rate": 9.65723930132053e-06, "loss": 4.2744, "step": 23256 }, { "epoch": 0.7103543066585217, "grad_norm": 0.4665886461734772, "learning_rate": 9.655345369661301e-06, "loss": 4.2816, "step": 23257 }, { "epoch": 0.7103848503359804, "grad_norm": 0.4599325954914093, "learning_rate": 9.653451579288205e-06, "loss": 4.1609, "step": 23258 }, { "epoch": 0.7104153940134392, "grad_norm": 0.45894330739974976, "learning_rate": 9.65155793021866e-06, "loss": 4.2884, "step": 23259 }, { "epoch": 0.710445937690898, "grad_norm": 0.4634177088737488, "learning_rate": 9.649664422470115e-06, "loss": 4.2454, "step": 23260 }, { "epoch": 0.7104764813683567, "grad_norm": 0.4839821457862854, "learning_rate": 9.64777105606001e-06, "loss": 4.3303, "step": 23261 }, { "epoch": 0.7105070250458155, "grad_norm": 0.45814988017082214, "learning_rate": 9.645877831005762e-06, "loss": 4.2734, "step": 23262 }, { "epoch": 0.7105375687232743, "grad_norm": 0.455598384141922, "learning_rate": 9.643984747324819e-06, "loss": 4.2128, "step": 23263 }, { "epoch": 0.710568112400733, "grad_norm": 0.4699303209781647, "learning_rate": 9.642091805034595e-06, "loss": 4.2081, "step": 23264 }, { "epoch": 0.7105986560781918, "grad_norm": 0.4555206298828125, "learning_rate": 9.640199004152537e-06, "loss": 4.2941, "step": 23265 }, { "epoch": 0.7106291997556505, "grad_norm": 0.45620855689048767, "learning_rate": 9.638306344696064e-06, "loss": 4.2574, "step": 23266 }, { "epoch": 0.7106597434331093, "grad_norm": 0.46109870076179504, "learning_rate": 9.636413826682595e-06, "loss": 4.2456, "step": 23267 }, { "epoch": 0.7106902871105681, "grad_norm": 0.47096729278564453, "learning_rate": 9.63452145012956e-06, "loss": 4.1891, "step": 23268 }, { "epoch": 0.7107208307880268, "grad_norm": 0.4664524793624878, "learning_rate": 9.632629215054399e-06, "loss": 4.254, "step": 23269 }, { "epoch": 0.7107513744654856, "grad_norm": 0.4523841440677643, "learning_rate": 9.63073712147451e-06, "loss": 4.2336, "step": 23270 }, { "epoch": 0.7107819181429444, "grad_norm": 0.4608120024204254, "learning_rate": 9.628845169407328e-06, "loss": 4.1133, "step": 23271 }, { "epoch": 0.7108124618204031, "grad_norm": 0.45864880084991455, "learning_rate": 9.626953358870278e-06, "loss": 4.2068, "step": 23272 }, { "epoch": 0.710843005497862, "grad_norm": 0.45768988132476807, "learning_rate": 9.625061689880765e-06, "loss": 4.1712, "step": 23273 }, { "epoch": 0.7108735491753208, "grad_norm": 0.4682902693748474, "learning_rate": 9.623170162456216e-06, "loss": 4.2312, "step": 23274 }, { "epoch": 0.7109040928527794, "grad_norm": 0.4573993384838104, "learning_rate": 9.62127877661405e-06, "loss": 4.1894, "step": 23275 }, { "epoch": 0.7109346365302383, "grad_norm": 0.45780184864997864, "learning_rate": 9.619387532371674e-06, "loss": 4.3351, "step": 23276 }, { "epoch": 0.7109651802076971, "grad_norm": 0.4695846736431122, "learning_rate": 9.6174964297465e-06, "loss": 4.2907, "step": 23277 }, { "epoch": 0.7109957238851558, "grad_norm": 0.470099538564682, "learning_rate": 9.615605468755956e-06, "loss": 4.2778, "step": 23278 }, { "epoch": 0.7110262675626146, "grad_norm": 0.4598619043827057, "learning_rate": 9.613714649417436e-06, "loss": 4.3033, "step": 23279 }, { "epoch": 0.7110568112400732, "grad_norm": 0.45565396547317505, "learning_rate": 9.61182397174836e-06, "loss": 4.1562, "step": 23280 }, { "epoch": 0.711087354917532, "grad_norm": 0.46782729029655457, "learning_rate": 9.609933435766137e-06, "loss": 4.2756, "step": 23281 }, { "epoch": 0.7111178985949909, "grad_norm": 0.46088534593582153, "learning_rate": 9.608043041488158e-06, "loss": 4.2626, "step": 23282 }, { "epoch": 0.7111484422724496, "grad_norm": 0.45752403140068054, "learning_rate": 9.606152788931849e-06, "loss": 4.1723, "step": 23283 }, { "epoch": 0.7111789859499084, "grad_norm": 0.4627731740474701, "learning_rate": 9.604262678114598e-06, "loss": 4.2376, "step": 23284 }, { "epoch": 0.7112095296273672, "grad_norm": 0.45492807030677795, "learning_rate": 9.602372709053816e-06, "loss": 4.2816, "step": 23285 }, { "epoch": 0.7112400733048259, "grad_norm": 0.4768964946269989, "learning_rate": 9.600482881766915e-06, "loss": 4.3043, "step": 23286 }, { "epoch": 0.7112706169822847, "grad_norm": 0.46469080448150635, "learning_rate": 9.598593196271277e-06, "loss": 4.2245, "step": 23287 }, { "epoch": 0.7113011606597435, "grad_norm": 0.4659595787525177, "learning_rate": 9.596703652584307e-06, "loss": 4.2449, "step": 23288 }, { "epoch": 0.7113317043372022, "grad_norm": 0.45490485429763794, "learning_rate": 9.59481425072342e-06, "loss": 4.1531, "step": 23289 }, { "epoch": 0.711362248014661, "grad_norm": 0.4542959928512573, "learning_rate": 9.592924990705988e-06, "loss": 4.2607, "step": 23290 }, { "epoch": 0.7113927916921198, "grad_norm": 0.46251407265663147, "learning_rate": 9.591035872549414e-06, "loss": 4.1823, "step": 23291 }, { "epoch": 0.7114233353695785, "grad_norm": 0.4677458703517914, "learning_rate": 9.589146896271107e-06, "loss": 4.3085, "step": 23292 }, { "epoch": 0.7114538790470373, "grad_norm": 0.45476192235946655, "learning_rate": 9.587258061888438e-06, "loss": 4.2647, "step": 23293 }, { "epoch": 0.7114844227244961, "grad_norm": 0.4607093036174774, "learning_rate": 9.585369369418817e-06, "loss": 4.2193, "step": 23294 }, { "epoch": 0.7115149664019548, "grad_norm": 0.46584054827690125, "learning_rate": 9.58348081887962e-06, "loss": 4.0733, "step": 23295 }, { "epoch": 0.7115455100794136, "grad_norm": 0.46233952045440674, "learning_rate": 9.581592410288248e-06, "loss": 4.2496, "step": 23296 }, { "epoch": 0.7115760537568723, "grad_norm": 0.46129310131073, "learning_rate": 9.57970414366208e-06, "loss": 4.1397, "step": 23297 }, { "epoch": 0.7116065974343311, "grad_norm": 0.4583772122859955, "learning_rate": 9.577816019018499e-06, "loss": 4.2218, "step": 23298 }, { "epoch": 0.7116371411117899, "grad_norm": 0.4688466489315033, "learning_rate": 9.575928036374892e-06, "loss": 4.2632, "step": 23299 }, { "epoch": 0.7116676847892486, "grad_norm": 0.45293721556663513, "learning_rate": 9.574040195748656e-06, "loss": 4.206, "step": 23300 }, { "epoch": 0.7116982284667074, "grad_norm": 0.4572274088859558, "learning_rate": 9.572152497157155e-06, "loss": 4.2085, "step": 23301 }, { "epoch": 0.7117287721441662, "grad_norm": 0.4643566906452179, "learning_rate": 9.57026494061778e-06, "loss": 4.322, "step": 23302 }, { "epoch": 0.7117593158216249, "grad_norm": 0.46130630373954773, "learning_rate": 9.568377526147915e-06, "loss": 4.2153, "step": 23303 }, { "epoch": 0.7117898594990837, "grad_norm": 0.45652180910110474, "learning_rate": 9.566490253764923e-06, "loss": 4.1674, "step": 23304 }, { "epoch": 0.7118204031765425, "grad_norm": 0.44999805092811584, "learning_rate": 9.564603123486194e-06, "loss": 4.201, "step": 23305 }, { "epoch": 0.7118509468540012, "grad_norm": 0.45672672986984253, "learning_rate": 9.562716135329105e-06, "loss": 4.1611, "step": 23306 }, { "epoch": 0.71188149053146, "grad_norm": 0.4572383165359497, "learning_rate": 9.56082928931102e-06, "loss": 4.2155, "step": 23307 }, { "epoch": 0.7119120342089188, "grad_norm": 0.46682098507881165, "learning_rate": 9.558942585449313e-06, "loss": 4.3147, "step": 23308 }, { "epoch": 0.7119425778863775, "grad_norm": 0.4742620885372162, "learning_rate": 9.557056023761373e-06, "loss": 4.215, "step": 23309 }, { "epoch": 0.7119731215638363, "grad_norm": 0.4793708920478821, "learning_rate": 9.55516960426455e-06, "loss": 4.2194, "step": 23310 }, { "epoch": 0.7120036652412951, "grad_norm": 0.46490395069122314, "learning_rate": 9.553283326976228e-06, "loss": 4.2595, "step": 23311 }, { "epoch": 0.7120342089187538, "grad_norm": 0.4716382324695587, "learning_rate": 9.55139719191377e-06, "loss": 4.2755, "step": 23312 }, { "epoch": 0.7120647525962126, "grad_norm": 0.46035581827163696, "learning_rate": 9.54951119909453e-06, "loss": 4.2764, "step": 23313 }, { "epoch": 0.7120952962736713, "grad_norm": 0.4489518702030182, "learning_rate": 9.547625348535894e-06, "loss": 4.2154, "step": 23314 }, { "epoch": 0.7121258399511301, "grad_norm": 0.45816004276275635, "learning_rate": 9.545739640255207e-06, "loss": 4.2593, "step": 23315 }, { "epoch": 0.7121563836285889, "grad_norm": 0.47091352939605713, "learning_rate": 9.543854074269842e-06, "loss": 4.3064, "step": 23316 }, { "epoch": 0.7121869273060476, "grad_norm": 0.4711964726448059, "learning_rate": 9.541968650597169e-06, "loss": 4.334, "step": 23317 }, { "epoch": 0.7122174709835064, "grad_norm": 0.45971328020095825, "learning_rate": 9.540083369254529e-06, "loss": 4.0807, "step": 23318 }, { "epoch": 0.7122480146609652, "grad_norm": 0.46231478452682495, "learning_rate": 9.53819823025929e-06, "loss": 4.1991, "step": 23319 }, { "epoch": 0.7122785583384239, "grad_norm": 0.4745909869670868, "learning_rate": 9.536313233628818e-06, "loss": 4.2689, "step": 23320 }, { "epoch": 0.7123091020158827, "grad_norm": 0.6411056518554688, "learning_rate": 9.53442837938045e-06, "loss": 4.258, "step": 23321 }, { "epoch": 0.7123396456933415, "grad_norm": 0.4663594365119934, "learning_rate": 9.532543667531555e-06, "loss": 4.2432, "step": 23322 }, { "epoch": 0.7123701893708002, "grad_norm": 0.4593493640422821, "learning_rate": 9.53065909809949e-06, "loss": 4.2299, "step": 23323 }, { "epoch": 0.712400733048259, "grad_norm": 0.46918949484825134, "learning_rate": 9.528774671101592e-06, "loss": 4.2449, "step": 23324 }, { "epoch": 0.7124312767257178, "grad_norm": 0.4541480243206024, "learning_rate": 9.526890386555218e-06, "loss": 4.2325, "step": 23325 }, { "epoch": 0.7124618204031765, "grad_norm": 0.45819541811943054, "learning_rate": 9.52500624447773e-06, "loss": 4.2247, "step": 23326 }, { "epoch": 0.7124923640806353, "grad_norm": 0.455024778842926, "learning_rate": 9.523122244886468e-06, "loss": 4.2965, "step": 23327 }, { "epoch": 0.7125229077580941, "grad_norm": 0.4722517132759094, "learning_rate": 9.521238387798766e-06, "loss": 4.1842, "step": 23328 }, { "epoch": 0.7125534514355528, "grad_norm": 0.4730692505836487, "learning_rate": 9.51935467323199e-06, "loss": 4.2609, "step": 23329 }, { "epoch": 0.7125839951130116, "grad_norm": 0.4650084376335144, "learning_rate": 9.517471101203465e-06, "loss": 4.1973, "step": 23330 }, { "epoch": 0.7126145387904703, "grad_norm": 0.46720296144485474, "learning_rate": 9.515587671730553e-06, "loss": 4.332, "step": 23331 }, { "epoch": 0.7126450824679291, "grad_norm": 0.463687539100647, "learning_rate": 9.51370438483058e-06, "loss": 4.2721, "step": 23332 }, { "epoch": 0.7126756261453879, "grad_norm": 0.4723043143749237, "learning_rate": 9.51182124052089e-06, "loss": 4.2328, "step": 23333 }, { "epoch": 0.7127061698228466, "grad_norm": 0.478678435087204, "learning_rate": 9.509938238818836e-06, "loss": 4.3018, "step": 23334 }, { "epoch": 0.7127367135003054, "grad_norm": 0.46114933490753174, "learning_rate": 9.508055379741735e-06, "loss": 4.2564, "step": 23335 }, { "epoch": 0.7127672571777642, "grad_norm": 0.45646363496780396, "learning_rate": 9.506172663306934e-06, "loss": 4.2337, "step": 23336 }, { "epoch": 0.7127978008552229, "grad_norm": 0.4563775360584259, "learning_rate": 9.504290089531775e-06, "loss": 4.2197, "step": 23337 }, { "epoch": 0.7128283445326817, "grad_norm": 0.45844781398773193, "learning_rate": 9.502407658433577e-06, "loss": 4.2651, "step": 23338 }, { "epoch": 0.7128588882101405, "grad_norm": 0.4629414975643158, "learning_rate": 9.500525370029679e-06, "loss": 4.1666, "step": 23339 }, { "epoch": 0.7128894318875992, "grad_norm": 0.4571778178215027, "learning_rate": 9.49864322433742e-06, "loss": 4.2893, "step": 23340 }, { "epoch": 0.712919975565058, "grad_norm": 0.4577096402645111, "learning_rate": 9.496761221374114e-06, "loss": 4.1359, "step": 23341 }, { "epoch": 0.7129505192425168, "grad_norm": 0.47004756331443787, "learning_rate": 9.49487936115711e-06, "loss": 4.2139, "step": 23342 }, { "epoch": 0.7129810629199755, "grad_norm": 0.46682778000831604, "learning_rate": 9.492997643703724e-06, "loss": 4.2659, "step": 23343 }, { "epoch": 0.7130116065974343, "grad_norm": 0.4656996428966522, "learning_rate": 9.49111606903127e-06, "loss": 4.2269, "step": 23344 }, { "epoch": 0.7130421502748931, "grad_norm": 0.4637141525745392, "learning_rate": 9.489234637157086e-06, "loss": 4.2705, "step": 23345 }, { "epoch": 0.7130726939523518, "grad_norm": 0.4608684778213501, "learning_rate": 9.487353348098501e-06, "loss": 4.2878, "step": 23346 }, { "epoch": 0.7131032376298106, "grad_norm": 0.4608429968357086, "learning_rate": 9.485472201872821e-06, "loss": 4.2448, "step": 23347 }, { "epoch": 0.7131337813072693, "grad_norm": 0.477461040019989, "learning_rate": 9.483591198497386e-06, "loss": 4.211, "step": 23348 }, { "epoch": 0.7131643249847281, "grad_norm": 0.4650285542011261, "learning_rate": 9.481710337989494e-06, "loss": 4.2731, "step": 23349 }, { "epoch": 0.713194868662187, "grad_norm": 0.46408507227897644, "learning_rate": 9.479829620366476e-06, "loss": 4.2607, "step": 23350 }, { "epoch": 0.7132254123396456, "grad_norm": 0.4670158922672272, "learning_rate": 9.47794904564565e-06, "loss": 4.1727, "step": 23351 }, { "epoch": 0.7132559560171045, "grad_norm": 0.46026718616485596, "learning_rate": 9.476068613844324e-06, "loss": 4.1408, "step": 23352 }, { "epoch": 0.7132864996945633, "grad_norm": 0.4510129690170288, "learning_rate": 9.474188324979815e-06, "loss": 4.3013, "step": 23353 }, { "epoch": 0.713317043372022, "grad_norm": 0.47206422686576843, "learning_rate": 9.472308179069444e-06, "loss": 4.2493, "step": 23354 }, { "epoch": 0.7133475870494808, "grad_norm": 0.4615730047225952, "learning_rate": 9.470428176130508e-06, "loss": 4.2455, "step": 23355 }, { "epoch": 0.7133781307269396, "grad_norm": 0.4798562228679657, "learning_rate": 9.468548316180324e-06, "loss": 4.3529, "step": 23356 }, { "epoch": 0.7134086744043983, "grad_norm": 0.4557656943798065, "learning_rate": 9.46666859923621e-06, "loss": 4.2923, "step": 23357 }, { "epoch": 0.7134392180818571, "grad_norm": 0.4627242684364319, "learning_rate": 9.464789025315463e-06, "loss": 4.3466, "step": 23358 }, { "epoch": 0.7134697617593159, "grad_norm": 0.46263960003852844, "learning_rate": 9.462909594435381e-06, "loss": 4.2342, "step": 23359 }, { "epoch": 0.7135003054367746, "grad_norm": 0.4568333625793457, "learning_rate": 9.46103030661329e-06, "loss": 4.3461, "step": 23360 }, { "epoch": 0.7135308491142334, "grad_norm": 0.4626292288303375, "learning_rate": 9.459151161866472e-06, "loss": 4.2747, "step": 23361 }, { "epoch": 0.7135613927916922, "grad_norm": 0.4539923369884491, "learning_rate": 9.457272160212242e-06, "loss": 4.3039, "step": 23362 }, { "epoch": 0.7135919364691509, "grad_norm": 0.47475236654281616, "learning_rate": 9.455393301667906e-06, "loss": 4.3051, "step": 23363 }, { "epoch": 0.7136224801466097, "grad_norm": 0.4588775932788849, "learning_rate": 9.453514586250748e-06, "loss": 4.1575, "step": 23364 }, { "epoch": 0.7136530238240684, "grad_norm": 0.46173226833343506, "learning_rate": 9.45163601397808e-06, "loss": 4.1086, "step": 23365 }, { "epoch": 0.7136835675015272, "grad_norm": 0.45982176065444946, "learning_rate": 9.449757584867188e-06, "loss": 4.1708, "step": 23366 }, { "epoch": 0.713714111178986, "grad_norm": 0.4539310336112976, "learning_rate": 9.447879298935372e-06, "loss": 4.1939, "step": 23367 }, { "epoch": 0.7137446548564447, "grad_norm": 0.46019619703292847, "learning_rate": 9.446001156199935e-06, "loss": 4.2142, "step": 23368 }, { "epoch": 0.7137751985339035, "grad_norm": 0.45851168036460876, "learning_rate": 9.444123156678155e-06, "loss": 4.2664, "step": 23369 }, { "epoch": 0.7138057422113623, "grad_norm": 0.4855036437511444, "learning_rate": 9.442245300387332e-06, "loss": 4.1869, "step": 23370 }, { "epoch": 0.713836285888821, "grad_norm": 0.47655877470970154, "learning_rate": 9.440367587344765e-06, "loss": 4.3068, "step": 23371 }, { "epoch": 0.7138668295662798, "grad_norm": 0.46920064091682434, "learning_rate": 9.438490017567721e-06, "loss": 4.3512, "step": 23372 }, { "epoch": 0.7138973732437386, "grad_norm": 0.4793708920478821, "learning_rate": 9.436612591073512e-06, "loss": 4.2496, "step": 23373 }, { "epoch": 0.7139279169211973, "grad_norm": 0.4697871208190918, "learning_rate": 9.434735307879402e-06, "loss": 4.3032, "step": 23374 }, { "epoch": 0.7139584605986561, "grad_norm": 0.46710070967674255, "learning_rate": 9.432858168002698e-06, "loss": 4.189, "step": 23375 }, { "epoch": 0.7139890042761149, "grad_norm": 0.4605410099029541, "learning_rate": 9.430981171460663e-06, "loss": 4.2377, "step": 23376 }, { "epoch": 0.7140195479535736, "grad_norm": 0.4575684666633606, "learning_rate": 9.429104318270599e-06, "loss": 4.2386, "step": 23377 }, { "epoch": 0.7140500916310324, "grad_norm": 0.4607277810573578, "learning_rate": 9.427227608449766e-06, "loss": 4.3598, "step": 23378 }, { "epoch": 0.7140806353084912, "grad_norm": 0.4613499939441681, "learning_rate": 9.425351042015457e-06, "loss": 4.209, "step": 23379 }, { "epoch": 0.7141111789859499, "grad_norm": 0.47643664479255676, "learning_rate": 9.423474618984957e-06, "loss": 4.2583, "step": 23380 }, { "epoch": 0.7141417226634087, "grad_norm": 0.4699414074420929, "learning_rate": 9.421598339375525e-06, "loss": 4.2401, "step": 23381 }, { "epoch": 0.7141722663408674, "grad_norm": 0.45443400740623474, "learning_rate": 9.419722203204457e-06, "loss": 4.2423, "step": 23382 }, { "epoch": 0.7142028100183262, "grad_norm": 0.47788816690444946, "learning_rate": 9.417846210489006e-06, "loss": 4.3048, "step": 23383 }, { "epoch": 0.714233353695785, "grad_norm": 0.4580598771572113, "learning_rate": 9.415970361246459e-06, "loss": 4.3034, "step": 23384 }, { "epoch": 0.7142638973732437, "grad_norm": 0.4669573903083801, "learning_rate": 9.414094655494094e-06, "loss": 4.1614, "step": 23385 }, { "epoch": 0.7142944410507025, "grad_norm": 0.4610667824745178, "learning_rate": 9.412219093249164e-06, "loss": 4.2067, "step": 23386 }, { "epoch": 0.7143249847281613, "grad_norm": 0.4541783630847931, "learning_rate": 9.410343674528946e-06, "loss": 4.335, "step": 23387 }, { "epoch": 0.71435552840562, "grad_norm": 0.4539116621017456, "learning_rate": 9.40846839935072e-06, "loss": 4.2112, "step": 23388 }, { "epoch": 0.7143860720830788, "grad_norm": 0.47054654359817505, "learning_rate": 9.40659326773173e-06, "loss": 4.3206, "step": 23389 }, { "epoch": 0.7144166157605376, "grad_norm": 0.4698219299316406, "learning_rate": 9.404718279689265e-06, "loss": 4.2436, "step": 23390 }, { "epoch": 0.7144471594379963, "grad_norm": 0.4636639654636383, "learning_rate": 9.402843435240577e-06, "loss": 4.1382, "step": 23391 }, { "epoch": 0.7144777031154551, "grad_norm": 0.46121615171432495, "learning_rate": 9.400968734402918e-06, "loss": 4.2548, "step": 23392 }, { "epoch": 0.7145082467929139, "grad_norm": 0.4614015817642212, "learning_rate": 9.399094177193563e-06, "loss": 4.2802, "step": 23393 }, { "epoch": 0.7145387904703726, "grad_norm": 0.47007566690444946, "learning_rate": 9.397219763629774e-06, "loss": 4.2544, "step": 23394 }, { "epoch": 0.7145693341478314, "grad_norm": 0.45650961995124817, "learning_rate": 9.3953454937288e-06, "loss": 4.272, "step": 23395 }, { "epoch": 0.7145998778252902, "grad_norm": 0.4629477560520172, "learning_rate": 9.3934713675079e-06, "loss": 4.265, "step": 23396 }, { "epoch": 0.7146304215027489, "grad_norm": 0.4582749903202057, "learning_rate": 9.391597384984344e-06, "loss": 4.2099, "step": 23397 }, { "epoch": 0.7146609651802077, "grad_norm": 0.46223175525665283, "learning_rate": 9.389723546175364e-06, "loss": 4.2922, "step": 23398 }, { "epoch": 0.7146915088576664, "grad_norm": 0.45261839032173157, "learning_rate": 9.387849851098237e-06, "loss": 4.2576, "step": 23399 }, { "epoch": 0.7147220525351252, "grad_norm": 0.46355685591697693, "learning_rate": 9.385976299770194e-06, "loss": 4.3326, "step": 23400 }, { "epoch": 0.714752596212584, "grad_norm": 0.46512967348098755, "learning_rate": 9.384102892208497e-06, "loss": 4.3335, "step": 23401 }, { "epoch": 0.7147831398900427, "grad_norm": 0.4616113603115082, "learning_rate": 9.382229628430397e-06, "loss": 4.2632, "step": 23402 }, { "epoch": 0.7148136835675015, "grad_norm": 0.46728235483169556, "learning_rate": 9.380356508453133e-06, "loss": 4.2695, "step": 23403 }, { "epoch": 0.7148442272449603, "grad_norm": 0.4527115225791931, "learning_rate": 9.37848353229397e-06, "loss": 4.2765, "step": 23404 }, { "epoch": 0.714874770922419, "grad_norm": 0.4656125009059906, "learning_rate": 9.376610699970126e-06, "loss": 4.2782, "step": 23405 }, { "epoch": 0.7149053145998778, "grad_norm": 0.47074079513549805, "learning_rate": 9.374738011498873e-06, "loss": 4.3251, "step": 23406 }, { "epoch": 0.7149358582773366, "grad_norm": 0.4641278386116028, "learning_rate": 9.37286546689743e-06, "loss": 4.2645, "step": 23407 }, { "epoch": 0.7149664019547953, "grad_norm": 0.4738122224807739, "learning_rate": 9.37099306618306e-06, "loss": 4.302, "step": 23408 }, { "epoch": 0.7149969456322541, "grad_norm": 0.45242661237716675, "learning_rate": 9.369120809372981e-06, "loss": 4.1543, "step": 23409 }, { "epoch": 0.7150274893097129, "grad_norm": 0.4544980823993683, "learning_rate": 9.367248696484446e-06, "loss": 4.2623, "step": 23410 }, { "epoch": 0.7150580329871716, "grad_norm": 0.45495715737342834, "learning_rate": 9.365376727534697e-06, "loss": 4.1843, "step": 23411 }, { "epoch": 0.7150885766646304, "grad_norm": 0.4807482659816742, "learning_rate": 9.363504902540955e-06, "loss": 4.3034, "step": 23412 }, { "epoch": 0.7151191203420892, "grad_norm": 0.4629506766796112, "learning_rate": 9.36163322152046e-06, "loss": 4.2785, "step": 23413 }, { "epoch": 0.7151496640195479, "grad_norm": 0.46609199047088623, "learning_rate": 9.359761684490462e-06, "loss": 4.3097, "step": 23414 }, { "epoch": 0.7151802076970067, "grad_norm": 0.462157666683197, "learning_rate": 9.357890291468166e-06, "loss": 4.2744, "step": 23415 }, { "epoch": 0.7152107513744654, "grad_norm": 0.46651551127433777, "learning_rate": 9.356019042470828e-06, "loss": 4.2759, "step": 23416 }, { "epoch": 0.7152412950519242, "grad_norm": 0.4600817561149597, "learning_rate": 9.354147937515656e-06, "loss": 4.251, "step": 23417 }, { "epoch": 0.715271838729383, "grad_norm": 0.461468905210495, "learning_rate": 9.352276976619889e-06, "loss": 4.1736, "step": 23418 }, { "epoch": 0.7153023824068417, "grad_norm": 0.4517905116081238, "learning_rate": 9.350406159800762e-06, "loss": 4.2456, "step": 23419 }, { "epoch": 0.7153329260843005, "grad_norm": 0.46957120299339294, "learning_rate": 9.348535487075486e-06, "loss": 4.2609, "step": 23420 }, { "epoch": 0.7153634697617594, "grad_norm": 0.46506693959236145, "learning_rate": 9.346664958461297e-06, "loss": 4.3213, "step": 23421 }, { "epoch": 0.715394013439218, "grad_norm": 0.46141573786735535, "learning_rate": 9.34479457397541e-06, "loss": 4.1942, "step": 23422 }, { "epoch": 0.7154245571166769, "grad_norm": 0.46152573823928833, "learning_rate": 9.342924333635038e-06, "loss": 4.3138, "step": 23423 }, { "epoch": 0.7154551007941357, "grad_norm": 0.46134862303733826, "learning_rate": 9.341054237457417e-06, "loss": 4.2719, "step": 23424 }, { "epoch": 0.7154856444715944, "grad_norm": 0.4718113839626312, "learning_rate": 9.339184285459768e-06, "loss": 4.1893, "step": 23425 }, { "epoch": 0.7155161881490532, "grad_norm": 0.45897072553634644, "learning_rate": 9.337314477659292e-06, "loss": 4.2102, "step": 23426 }, { "epoch": 0.715546731826512, "grad_norm": 0.4688519239425659, "learning_rate": 9.335444814073214e-06, "loss": 4.2539, "step": 23427 }, { "epoch": 0.7155772755039707, "grad_norm": 0.45654597878456116, "learning_rate": 9.333575294718758e-06, "loss": 4.3201, "step": 23428 }, { "epoch": 0.7156078191814295, "grad_norm": 0.464203804731369, "learning_rate": 9.331705919613121e-06, "loss": 4.2408, "step": 23429 }, { "epoch": 0.7156383628588882, "grad_norm": 0.4718020558357239, "learning_rate": 9.329836688773533e-06, "loss": 4.2316, "step": 23430 }, { "epoch": 0.715668906536347, "grad_norm": 0.46945077180862427, "learning_rate": 9.327967602217185e-06, "loss": 4.2005, "step": 23431 }, { "epoch": 0.7156994502138058, "grad_norm": 0.47419849038124084, "learning_rate": 9.3260986599613e-06, "loss": 4.3544, "step": 23432 }, { "epoch": 0.7157299938912645, "grad_norm": 0.4640381932258606, "learning_rate": 9.32422986202309e-06, "loss": 4.2216, "step": 23433 }, { "epoch": 0.7157605375687233, "grad_norm": 0.45444563031196594, "learning_rate": 9.322361208419747e-06, "loss": 4.271, "step": 23434 }, { "epoch": 0.7157910812461821, "grad_norm": 0.46755605936050415, "learning_rate": 9.320492699168484e-06, "loss": 4.2292, "step": 23435 }, { "epoch": 0.7158216249236408, "grad_norm": 0.4726644456386566, "learning_rate": 9.318624334286516e-06, "loss": 4.3022, "step": 23436 }, { "epoch": 0.7158521686010996, "grad_norm": 0.4660511314868927, "learning_rate": 9.316756113791036e-06, "loss": 4.3445, "step": 23437 }, { "epoch": 0.7158827122785584, "grad_norm": 0.45273256301879883, "learning_rate": 9.314888037699238e-06, "loss": 4.2423, "step": 23438 }, { "epoch": 0.7159132559560171, "grad_norm": 0.48212647438049316, "learning_rate": 9.313020106028337e-06, "loss": 4.3081, "step": 23439 }, { "epoch": 0.7159437996334759, "grad_norm": 0.46550241112709045, "learning_rate": 9.311152318795519e-06, "loss": 4.3533, "step": 23440 }, { "epoch": 0.7159743433109347, "grad_norm": 0.4649462103843689, "learning_rate": 9.309284676017985e-06, "loss": 4.1674, "step": 23441 }, { "epoch": 0.7160048869883934, "grad_norm": 0.4854906499385834, "learning_rate": 9.307417177712947e-06, "loss": 4.3653, "step": 23442 }, { "epoch": 0.7160354306658522, "grad_norm": 0.457410603761673, "learning_rate": 9.305549823897575e-06, "loss": 4.1751, "step": 23443 }, { "epoch": 0.716065974343311, "grad_norm": 0.46329212188720703, "learning_rate": 9.303682614589076e-06, "loss": 4.2549, "step": 23444 }, { "epoch": 0.7160965180207697, "grad_norm": 0.47728830575942993, "learning_rate": 9.301815549804652e-06, "loss": 4.3353, "step": 23445 }, { "epoch": 0.7161270616982285, "grad_norm": 0.46252667903900146, "learning_rate": 9.299948629561475e-06, "loss": 4.2822, "step": 23446 }, { "epoch": 0.7161576053756872, "grad_norm": 0.45920780301094055, "learning_rate": 9.29808185387675e-06, "loss": 4.2266, "step": 23447 }, { "epoch": 0.716188149053146, "grad_norm": 0.46496331691741943, "learning_rate": 9.296215222767648e-06, "loss": 4.2358, "step": 23448 }, { "epoch": 0.7162186927306048, "grad_norm": 0.46934664249420166, "learning_rate": 9.294348736251371e-06, "loss": 4.1674, "step": 23449 }, { "epoch": 0.7162492364080635, "grad_norm": 0.4576253890991211, "learning_rate": 9.292482394345106e-06, "loss": 4.2282, "step": 23450 }, { "epoch": 0.7162797800855223, "grad_norm": 0.46213918924331665, "learning_rate": 9.290616197066024e-06, "loss": 4.2722, "step": 23451 }, { "epoch": 0.7163103237629811, "grad_norm": 0.4720836579799652, "learning_rate": 9.288750144431325e-06, "loss": 4.1682, "step": 23452 }, { "epoch": 0.7163408674404398, "grad_norm": 0.4695039689540863, "learning_rate": 9.286884236458179e-06, "loss": 4.2038, "step": 23453 }, { "epoch": 0.7163714111178986, "grad_norm": 0.4686947762966156, "learning_rate": 9.285018473163762e-06, "loss": 4.3131, "step": 23454 }, { "epoch": 0.7164019547953574, "grad_norm": 0.46895670890808105, "learning_rate": 9.283152854565259e-06, "loss": 4.2324, "step": 23455 }, { "epoch": 0.7164324984728161, "grad_norm": 0.46541598439216614, "learning_rate": 9.281287380679857e-06, "loss": 4.2571, "step": 23456 }, { "epoch": 0.7164630421502749, "grad_norm": 0.4640890061855316, "learning_rate": 9.279422051524714e-06, "loss": 4.2458, "step": 23457 }, { "epoch": 0.7164935858277337, "grad_norm": 0.46016645431518555, "learning_rate": 9.277556867117019e-06, "loss": 4.2409, "step": 23458 }, { "epoch": 0.7165241295051924, "grad_norm": 0.4670363664627075, "learning_rate": 9.275691827473946e-06, "loss": 4.3431, "step": 23459 }, { "epoch": 0.7165546731826512, "grad_norm": 0.4536665976047516, "learning_rate": 9.273826932612655e-06, "loss": 4.222, "step": 23460 }, { "epoch": 0.71658521686011, "grad_norm": 0.4740830063819885, "learning_rate": 9.271962182550326e-06, "loss": 4.295, "step": 23461 }, { "epoch": 0.7166157605375687, "grad_norm": 0.46428266167640686, "learning_rate": 9.270097577304138e-06, "loss": 4.3155, "step": 23462 }, { "epoch": 0.7166463042150275, "grad_norm": 0.4678960144519806, "learning_rate": 9.268233116891237e-06, "loss": 4.2303, "step": 23463 }, { "epoch": 0.7166768478924862, "grad_norm": 0.4787045121192932, "learning_rate": 9.266368801328815e-06, "loss": 4.3445, "step": 23464 }, { "epoch": 0.716707391569945, "grad_norm": 0.48119303584098816, "learning_rate": 9.264504630634014e-06, "loss": 4.2274, "step": 23465 }, { "epoch": 0.7167379352474038, "grad_norm": 0.46679064631462097, "learning_rate": 9.262640604824008e-06, "loss": 4.2435, "step": 23466 }, { "epoch": 0.7167684789248625, "grad_norm": 0.4693717658519745, "learning_rate": 9.26077672391597e-06, "loss": 4.2747, "step": 23467 }, { "epoch": 0.7167990226023213, "grad_norm": 0.4765844941139221, "learning_rate": 9.258912987927054e-06, "loss": 4.2532, "step": 23468 }, { "epoch": 0.7168295662797801, "grad_norm": 0.46685925126075745, "learning_rate": 9.257049396874411e-06, "loss": 4.3036, "step": 23469 }, { "epoch": 0.7168601099572388, "grad_norm": 0.47632983326911926, "learning_rate": 9.255185950775216e-06, "loss": 4.3429, "step": 23470 }, { "epoch": 0.7168906536346976, "grad_norm": 0.46168532967567444, "learning_rate": 9.253322649646612e-06, "loss": 4.2825, "step": 23471 }, { "epoch": 0.7169211973121564, "grad_norm": 0.45958682894706726, "learning_rate": 9.251459493505763e-06, "loss": 4.208, "step": 23472 }, { "epoch": 0.7169517409896151, "grad_norm": 0.470515638589859, "learning_rate": 9.24959648236983e-06, "loss": 4.2906, "step": 23473 }, { "epoch": 0.7169822846670739, "grad_norm": 0.45908254384994507, "learning_rate": 9.247733616255953e-06, "loss": 4.2665, "step": 23474 }, { "epoch": 0.7170128283445327, "grad_norm": 0.46544259786605835, "learning_rate": 9.24587089518129e-06, "loss": 4.2724, "step": 23475 }, { "epoch": 0.7170433720219914, "grad_norm": 0.4628356993198395, "learning_rate": 9.244008319163006e-06, "loss": 4.3242, "step": 23476 }, { "epoch": 0.7170739156994502, "grad_norm": 0.4752013385295868, "learning_rate": 9.242145888218226e-06, "loss": 4.2595, "step": 23477 }, { "epoch": 0.717104459376909, "grad_norm": 0.4681851267814636, "learning_rate": 9.240283602364111e-06, "loss": 4.3489, "step": 23478 }, { "epoch": 0.7171350030543677, "grad_norm": 0.4542916715145111, "learning_rate": 9.238421461617818e-06, "loss": 4.2518, "step": 23479 }, { "epoch": 0.7171655467318265, "grad_norm": 0.4522629380226135, "learning_rate": 9.236559465996475e-06, "loss": 4.2374, "step": 23480 }, { "epoch": 0.7171960904092852, "grad_norm": 0.4629659354686737, "learning_rate": 9.234697615517238e-06, "loss": 4.2612, "step": 23481 }, { "epoch": 0.717226634086744, "grad_norm": 0.4693998098373413, "learning_rate": 9.232835910197241e-06, "loss": 4.3062, "step": 23482 }, { "epoch": 0.7172571777642028, "grad_norm": 0.4582022726535797, "learning_rate": 9.230974350053637e-06, "loss": 4.2572, "step": 23483 }, { "epoch": 0.7172877214416615, "grad_norm": 0.4550720453262329, "learning_rate": 9.229112935103551e-06, "loss": 4.2793, "step": 23484 }, { "epoch": 0.7173182651191203, "grad_norm": 0.4595988690853119, "learning_rate": 9.227251665364143e-06, "loss": 4.308, "step": 23485 }, { "epoch": 0.7173488087965791, "grad_norm": 0.45761898159980774, "learning_rate": 9.225390540852525e-06, "loss": 4.2484, "step": 23486 }, { "epoch": 0.7173793524740378, "grad_norm": 0.4646134376525879, "learning_rate": 9.223529561585858e-06, "loss": 4.154, "step": 23487 }, { "epoch": 0.7174098961514966, "grad_norm": 0.46691298484802246, "learning_rate": 9.221668727581257e-06, "loss": 4.0793, "step": 23488 }, { "epoch": 0.7174404398289554, "grad_norm": 0.46085602045059204, "learning_rate": 9.219808038855862e-06, "loss": 4.2813, "step": 23489 }, { "epoch": 0.7174709835064141, "grad_norm": 0.4559866786003113, "learning_rate": 9.21794749542682e-06, "loss": 4.2826, "step": 23490 }, { "epoch": 0.717501527183873, "grad_norm": 0.4704851508140564, "learning_rate": 9.21608709731124e-06, "loss": 4.2027, "step": 23491 }, { "epoch": 0.7175320708613317, "grad_norm": 0.478928804397583, "learning_rate": 9.21422684452626e-06, "loss": 4.2234, "step": 23492 }, { "epoch": 0.7175626145387904, "grad_norm": 0.46615278720855713, "learning_rate": 9.21236673708902e-06, "loss": 4.1549, "step": 23493 }, { "epoch": 0.7175931582162492, "grad_norm": 0.4559115469455719, "learning_rate": 9.210506775016628e-06, "loss": 4.0818, "step": 23494 }, { "epoch": 0.717623701893708, "grad_norm": 0.4622216522693634, "learning_rate": 9.208646958326217e-06, "loss": 4.3103, "step": 23495 }, { "epoch": 0.7176542455711667, "grad_norm": 0.4632996618747711, "learning_rate": 9.206787287034921e-06, "loss": 4.2157, "step": 23496 }, { "epoch": 0.7176847892486256, "grad_norm": 0.46644338965415955, "learning_rate": 9.204927761159849e-06, "loss": 4.2364, "step": 23497 }, { "epoch": 0.7177153329260842, "grad_norm": 0.4670228362083435, "learning_rate": 9.203068380718132e-06, "loss": 4.3126, "step": 23498 }, { "epoch": 0.717745876603543, "grad_norm": 0.4703364670276642, "learning_rate": 9.20120914572688e-06, "loss": 4.2517, "step": 23499 }, { "epoch": 0.7177764202810019, "grad_norm": 0.46847978234291077, "learning_rate": 9.199350056203227e-06, "loss": 4.3271, "step": 23500 }, { "epoch": 0.7178069639584606, "grad_norm": 0.47108402848243713, "learning_rate": 9.197491112164282e-06, "loss": 4.3147, "step": 23501 }, { "epoch": 0.7178375076359194, "grad_norm": 0.4629097580909729, "learning_rate": 9.195632313627154e-06, "loss": 4.2689, "step": 23502 }, { "epoch": 0.7178680513133782, "grad_norm": 0.4637078046798706, "learning_rate": 9.193773660608962e-06, "loss": 4.302, "step": 23503 }, { "epoch": 0.7178985949908369, "grad_norm": 0.4652695953845978, "learning_rate": 9.191915153126835e-06, "loss": 4.2925, "step": 23504 }, { "epoch": 0.7179291386682957, "grad_norm": 0.4691864550113678, "learning_rate": 9.190056791197862e-06, "loss": 4.1453, "step": 23505 }, { "epoch": 0.7179596823457545, "grad_norm": 0.45587068796157837, "learning_rate": 9.188198574839163e-06, "loss": 4.2425, "step": 23506 }, { "epoch": 0.7179902260232132, "grad_norm": 0.46406090259552, "learning_rate": 9.186340504067862e-06, "loss": 4.27, "step": 23507 }, { "epoch": 0.718020769700672, "grad_norm": 0.4618607759475708, "learning_rate": 9.184482578901043e-06, "loss": 4.1803, "step": 23508 }, { "epoch": 0.7180513133781308, "grad_norm": 0.4618555009365082, "learning_rate": 9.182624799355827e-06, "loss": 4.1382, "step": 23509 }, { "epoch": 0.7180818570555895, "grad_norm": 0.46340975165367126, "learning_rate": 9.180767165449323e-06, "loss": 4.2602, "step": 23510 }, { "epoch": 0.7181124007330483, "grad_norm": 0.4617864787578583, "learning_rate": 9.178909677198622e-06, "loss": 4.3006, "step": 23511 }, { "epoch": 0.7181429444105071, "grad_norm": 0.463284969329834, "learning_rate": 9.177052334620834e-06, "loss": 4.2778, "step": 23512 }, { "epoch": 0.7181734880879658, "grad_norm": 0.46327611804008484, "learning_rate": 9.175195137733068e-06, "loss": 4.265, "step": 23513 }, { "epoch": 0.7182040317654246, "grad_norm": 0.4598146080970764, "learning_rate": 9.173338086552416e-06, "loss": 4.3214, "step": 23514 }, { "epoch": 0.7182345754428833, "grad_norm": 0.47232785820961, "learning_rate": 9.17148118109597e-06, "loss": 4.1036, "step": 23515 }, { "epoch": 0.7182651191203421, "grad_norm": 0.4563118517398834, "learning_rate": 9.169624421380846e-06, "loss": 4.2607, "step": 23516 }, { "epoch": 0.7182956627978009, "grad_norm": 0.4591200053691864, "learning_rate": 9.167767807424117e-06, "loss": 4.2945, "step": 23517 }, { "epoch": 0.7183262064752596, "grad_norm": 0.46076446771621704, "learning_rate": 9.165911339242899e-06, "loss": 4.2214, "step": 23518 }, { "epoch": 0.7183567501527184, "grad_norm": 0.4575363099575043, "learning_rate": 9.16405501685427e-06, "loss": 4.2703, "step": 23519 }, { "epoch": 0.7183872938301772, "grad_norm": 0.46544384956359863, "learning_rate": 9.162198840275327e-06, "loss": 4.2803, "step": 23520 }, { "epoch": 0.7184178375076359, "grad_norm": 0.4724017381668091, "learning_rate": 9.16034280952317e-06, "loss": 4.3244, "step": 23521 }, { "epoch": 0.7184483811850947, "grad_norm": 0.4600685238838196, "learning_rate": 9.158486924614872e-06, "loss": 4.1573, "step": 23522 }, { "epoch": 0.7184789248625535, "grad_norm": 0.47248902916908264, "learning_rate": 9.156631185567532e-06, "loss": 4.3285, "step": 23523 }, { "epoch": 0.7185094685400122, "grad_norm": 0.48465773463249207, "learning_rate": 9.154775592398244e-06, "loss": 4.2223, "step": 23524 }, { "epoch": 0.718540012217471, "grad_norm": 0.4631551206111908, "learning_rate": 9.152920145124072e-06, "loss": 4.1549, "step": 23525 }, { "epoch": 0.7185705558949298, "grad_norm": 0.4678208827972412, "learning_rate": 9.151064843762114e-06, "loss": 4.2057, "step": 23526 }, { "epoch": 0.7186010995723885, "grad_norm": 0.4592728316783905, "learning_rate": 9.149209688329458e-06, "loss": 4.2853, "step": 23527 }, { "epoch": 0.7186316432498473, "grad_norm": 0.4692494571208954, "learning_rate": 9.14735467884317e-06, "loss": 4.3211, "step": 23528 }, { "epoch": 0.7186621869273061, "grad_norm": 0.45886898040771484, "learning_rate": 9.145499815320347e-06, "loss": 4.3004, "step": 23529 }, { "epoch": 0.7186927306047648, "grad_norm": 0.46282508969306946, "learning_rate": 9.143645097778051e-06, "loss": 4.2762, "step": 23530 }, { "epoch": 0.7187232742822236, "grad_norm": 0.462836891412735, "learning_rate": 9.141790526233373e-06, "loss": 4.2034, "step": 23531 }, { "epoch": 0.7187538179596823, "grad_norm": 0.4593108296394348, "learning_rate": 9.139936100703383e-06, "loss": 4.2964, "step": 23532 }, { "epoch": 0.7187843616371411, "grad_norm": 0.46741440892219543, "learning_rate": 9.138081821205149e-06, "loss": 4.2303, "step": 23533 }, { "epoch": 0.7188149053145999, "grad_norm": 0.4680514633655548, "learning_rate": 9.136227687755752e-06, "loss": 4.2853, "step": 23534 }, { "epoch": 0.7188454489920586, "grad_norm": 0.47056373953819275, "learning_rate": 9.13437370037227e-06, "loss": 4.3358, "step": 23535 }, { "epoch": 0.7188759926695174, "grad_norm": 0.46673399209976196, "learning_rate": 9.132519859071758e-06, "loss": 4.2122, "step": 23536 }, { "epoch": 0.7189065363469762, "grad_norm": 0.46727505326271057, "learning_rate": 9.130666163871296e-06, "loss": 4.2824, "step": 23537 }, { "epoch": 0.7189370800244349, "grad_norm": 0.4605548083782196, "learning_rate": 9.128812614787957e-06, "loss": 4.2347, "step": 23538 }, { "epoch": 0.7189676237018937, "grad_norm": 0.46485698223114014, "learning_rate": 9.126959211838792e-06, "loss": 4.2284, "step": 23539 }, { "epoch": 0.7189981673793525, "grad_norm": 0.47942399978637695, "learning_rate": 9.125105955040875e-06, "loss": 4.2625, "step": 23540 }, { "epoch": 0.7190287110568112, "grad_norm": 0.47070202231407166, "learning_rate": 9.123252844411275e-06, "loss": 4.27, "step": 23541 }, { "epoch": 0.71905925473427, "grad_norm": 0.46455979347229004, "learning_rate": 9.121399879967043e-06, "loss": 4.3541, "step": 23542 }, { "epoch": 0.7190897984117288, "grad_norm": 0.473460853099823, "learning_rate": 9.119547061725247e-06, "loss": 4.1925, "step": 23543 }, { "epoch": 0.7191203420891875, "grad_norm": 0.45748043060302734, "learning_rate": 9.117694389702955e-06, "loss": 4.2694, "step": 23544 }, { "epoch": 0.7191508857666463, "grad_norm": 0.4489545524120331, "learning_rate": 9.115841863917208e-06, "loss": 4.2114, "step": 23545 }, { "epoch": 0.7191814294441051, "grad_norm": 0.47066813707351685, "learning_rate": 9.11398948438508e-06, "loss": 4.189, "step": 23546 }, { "epoch": 0.7192119731215638, "grad_norm": 0.46121543645858765, "learning_rate": 9.112137251123617e-06, "loss": 4.1578, "step": 23547 }, { "epoch": 0.7192425167990226, "grad_norm": 0.469762921333313, "learning_rate": 9.110285164149868e-06, "loss": 4.3098, "step": 23548 }, { "epoch": 0.7192730604764813, "grad_norm": 0.4667692184448242, "learning_rate": 9.1084332234809e-06, "loss": 4.2792, "step": 23549 }, { "epoch": 0.7193036041539401, "grad_norm": 0.4681667387485504, "learning_rate": 9.10658142913375e-06, "loss": 4.2211, "step": 23550 }, { "epoch": 0.7193341478313989, "grad_norm": 0.47512051463127136, "learning_rate": 9.104729781125478e-06, "loss": 4.2858, "step": 23551 }, { "epoch": 0.7193646915088576, "grad_norm": 0.4731586277484894, "learning_rate": 9.10287827947314e-06, "loss": 4.2145, "step": 23552 }, { "epoch": 0.7193952351863164, "grad_norm": 0.4606204330921173, "learning_rate": 9.101026924193765e-06, "loss": 4.2021, "step": 23553 }, { "epoch": 0.7194257788637752, "grad_norm": 0.4610224962234497, "learning_rate": 9.099175715304409e-06, "loss": 4.2532, "step": 23554 }, { "epoch": 0.7194563225412339, "grad_norm": 0.46608439087867737, "learning_rate": 9.097324652822129e-06, "loss": 4.288, "step": 23555 }, { "epoch": 0.7194868662186927, "grad_norm": 0.4572207033634186, "learning_rate": 9.095473736763946e-06, "loss": 4.203, "step": 23556 }, { "epoch": 0.7195174098961515, "grad_norm": 0.47696682810783386, "learning_rate": 9.093622967146914e-06, "loss": 4.2025, "step": 23557 }, { "epoch": 0.7195479535736102, "grad_norm": 0.4654827415943146, "learning_rate": 9.091772343988084e-06, "loss": 4.2952, "step": 23558 }, { "epoch": 0.719578497251069, "grad_norm": 0.48024654388427734, "learning_rate": 9.089921867304477e-06, "loss": 4.2642, "step": 23559 }, { "epoch": 0.7196090409285278, "grad_norm": 0.4659998118877411, "learning_rate": 9.088071537113144e-06, "loss": 4.245, "step": 23560 }, { "epoch": 0.7196395846059865, "grad_norm": 0.4727611243724823, "learning_rate": 9.086221353431113e-06, "loss": 4.3401, "step": 23561 }, { "epoch": 0.7196701282834453, "grad_norm": 0.4750750958919525, "learning_rate": 9.084371316275431e-06, "loss": 4.2437, "step": 23562 }, { "epoch": 0.7197006719609041, "grad_norm": 0.4534725844860077, "learning_rate": 9.082521425663115e-06, "loss": 4.2196, "step": 23563 }, { "epoch": 0.7197312156383628, "grad_norm": 0.4628548324108124, "learning_rate": 9.08067168161122e-06, "loss": 4.257, "step": 23564 }, { "epoch": 0.7197617593158216, "grad_norm": 0.4704812169075012, "learning_rate": 9.078822084136757e-06, "loss": 4.1609, "step": 23565 }, { "epoch": 0.7197923029932803, "grad_norm": 0.4650757908821106, "learning_rate": 9.07697263325677e-06, "loss": 4.2949, "step": 23566 }, { "epoch": 0.7198228466707391, "grad_norm": 0.468289315700531, "learning_rate": 9.075123328988278e-06, "loss": 4.2511, "step": 23567 }, { "epoch": 0.719853390348198, "grad_norm": 0.4591941237449646, "learning_rate": 9.073274171348311e-06, "loss": 4.1909, "step": 23568 }, { "epoch": 0.7198839340256566, "grad_norm": 0.47091177105903625, "learning_rate": 9.071425160353905e-06, "loss": 4.2991, "step": 23569 }, { "epoch": 0.7199144777031155, "grad_norm": 0.4558864235877991, "learning_rate": 9.069576296022072e-06, "loss": 4.2366, "step": 23570 }, { "epoch": 0.7199450213805743, "grad_norm": 0.4617273509502411, "learning_rate": 9.06772757836984e-06, "loss": 4.2859, "step": 23571 }, { "epoch": 0.719975565058033, "grad_norm": 0.47361892461776733, "learning_rate": 9.065879007414239e-06, "loss": 4.2217, "step": 23572 }, { "epoch": 0.7200061087354918, "grad_norm": 0.47326135635375977, "learning_rate": 9.064030583172273e-06, "loss": 4.2465, "step": 23573 }, { "epoch": 0.7200366524129506, "grad_norm": 0.4677063226699829, "learning_rate": 9.062182305660972e-06, "loss": 4.3338, "step": 23574 }, { "epoch": 0.7200671960904093, "grad_norm": 0.4635445475578308, "learning_rate": 9.060334174897362e-06, "loss": 4.3377, "step": 23575 }, { "epoch": 0.7200977397678681, "grad_norm": 0.4596936106681824, "learning_rate": 9.058486190898441e-06, "loss": 4.2436, "step": 23576 }, { "epoch": 0.7201282834453269, "grad_norm": 0.46813318133354187, "learning_rate": 9.056638353681243e-06, "loss": 4.2472, "step": 23577 }, { "epoch": 0.7201588271227856, "grad_norm": 0.4550604224205017, "learning_rate": 9.054790663262774e-06, "loss": 4.3161, "step": 23578 }, { "epoch": 0.7201893708002444, "grad_norm": 0.4708431363105774, "learning_rate": 9.052943119660036e-06, "loss": 4.3236, "step": 23579 }, { "epoch": 0.7202199144777031, "grad_norm": 0.4799439013004303, "learning_rate": 9.051095722890057e-06, "loss": 4.3425, "step": 23580 }, { "epoch": 0.7202504581551619, "grad_norm": 0.4610305428504944, "learning_rate": 9.049248472969834e-06, "loss": 4.2867, "step": 23581 }, { "epoch": 0.7202810018326207, "grad_norm": 0.4566001892089844, "learning_rate": 9.047401369916381e-06, "loss": 4.2383, "step": 23582 }, { "epoch": 0.7203115455100794, "grad_norm": 0.46146294474601746, "learning_rate": 9.045554413746712e-06, "loss": 4.2566, "step": 23583 }, { "epoch": 0.7203420891875382, "grad_norm": 0.4635443389415741, "learning_rate": 9.04370760447782e-06, "loss": 4.3677, "step": 23584 }, { "epoch": 0.720372632864997, "grad_norm": 0.47426077723503113, "learning_rate": 9.041860942126715e-06, "loss": 4.2695, "step": 23585 }, { "epoch": 0.7204031765424557, "grad_norm": 0.46587616205215454, "learning_rate": 9.040014426710411e-06, "loss": 4.2997, "step": 23586 }, { "epoch": 0.7204337202199145, "grad_norm": 0.4603109359741211, "learning_rate": 9.038168058245889e-06, "loss": 4.1902, "step": 23587 }, { "epoch": 0.7204642638973733, "grad_norm": 0.4601374864578247, "learning_rate": 9.036321836750161e-06, "loss": 4.1966, "step": 23588 }, { "epoch": 0.720494807574832, "grad_norm": 0.47846856713294983, "learning_rate": 9.034475762240236e-06, "loss": 4.2748, "step": 23589 }, { "epoch": 0.7205253512522908, "grad_norm": 0.46870994567871094, "learning_rate": 9.032629834733092e-06, "loss": 4.2255, "step": 23590 }, { "epoch": 0.7205558949297496, "grad_norm": 0.4559171199798584, "learning_rate": 9.030784054245733e-06, "loss": 4.2698, "step": 23591 }, { "epoch": 0.7205864386072083, "grad_norm": 0.6372819542884827, "learning_rate": 9.028938420795167e-06, "loss": 4.2207, "step": 23592 }, { "epoch": 0.7206169822846671, "grad_norm": 0.4609927833080292, "learning_rate": 9.027092934398377e-06, "loss": 4.3274, "step": 23593 }, { "epoch": 0.7206475259621259, "grad_norm": 0.46999672055244446, "learning_rate": 9.025247595072341e-06, "loss": 4.1973, "step": 23594 }, { "epoch": 0.7206780696395846, "grad_norm": 0.459688663482666, "learning_rate": 9.023402402834077e-06, "loss": 4.2517, "step": 23595 }, { "epoch": 0.7207086133170434, "grad_norm": 0.4640439450740814, "learning_rate": 9.021557357700553e-06, "loss": 4.2784, "step": 23596 }, { "epoch": 0.7207391569945021, "grad_norm": 0.46999868750572205, "learning_rate": 9.019712459688772e-06, "loss": 4.2919, "step": 23597 }, { "epoch": 0.7207697006719609, "grad_norm": 0.4608972370624542, "learning_rate": 9.017867708815709e-06, "loss": 4.2696, "step": 23598 }, { "epoch": 0.7208002443494197, "grad_norm": 0.4626045525074005, "learning_rate": 9.01602310509835e-06, "loss": 4.2704, "step": 23599 }, { "epoch": 0.7208307880268784, "grad_norm": 0.4485815763473511, "learning_rate": 9.014178648553697e-06, "loss": 4.1947, "step": 23600 }, { "epoch": 0.7208613317043372, "grad_norm": 0.46233367919921875, "learning_rate": 9.01233433919871e-06, "loss": 4.2931, "step": 23601 }, { "epoch": 0.720891875381796, "grad_norm": 0.4616325795650482, "learning_rate": 9.010490177050385e-06, "loss": 4.2474, "step": 23602 }, { "epoch": 0.7209224190592547, "grad_norm": 0.47004953026771545, "learning_rate": 9.008646162125702e-06, "loss": 4.2268, "step": 23603 }, { "epoch": 0.7209529627367135, "grad_norm": 0.465281218290329, "learning_rate": 9.006802294441628e-06, "loss": 4.27, "step": 23604 }, { "epoch": 0.7209835064141723, "grad_norm": 0.4689766466617584, "learning_rate": 9.00495857401515e-06, "loss": 4.2481, "step": 23605 }, { "epoch": 0.721014050091631, "grad_norm": 0.47475510835647583, "learning_rate": 9.00311500086325e-06, "loss": 4.2997, "step": 23606 }, { "epoch": 0.7210445937690898, "grad_norm": 0.46107956767082214, "learning_rate": 9.001271575002884e-06, "loss": 4.2181, "step": 23607 }, { "epoch": 0.7210751374465486, "grad_norm": 0.46478936076164246, "learning_rate": 8.999428296451046e-06, "loss": 4.237, "step": 23608 }, { "epoch": 0.7211056811240073, "grad_norm": 0.4716188311576843, "learning_rate": 8.99758516522469e-06, "loss": 4.2487, "step": 23609 }, { "epoch": 0.7211362248014661, "grad_norm": 0.4647463262081146, "learning_rate": 8.995742181340805e-06, "loss": 4.2264, "step": 23610 }, { "epoch": 0.7211667684789249, "grad_norm": 0.47123652696609497, "learning_rate": 8.99389934481634e-06, "loss": 4.1865, "step": 23611 }, { "epoch": 0.7211973121563836, "grad_norm": 0.46976932883262634, "learning_rate": 8.992056655668282e-06, "loss": 4.2398, "step": 23612 }, { "epoch": 0.7212278558338424, "grad_norm": 0.4742181897163391, "learning_rate": 8.99021411391358e-06, "loss": 4.3698, "step": 23613 }, { "epoch": 0.7212583995113011, "grad_norm": 0.46531644463539124, "learning_rate": 8.98837171956922e-06, "loss": 4.1959, "step": 23614 }, { "epoch": 0.7212889431887599, "grad_norm": 0.4575900733470917, "learning_rate": 8.986529472652142e-06, "loss": 4.1858, "step": 23615 }, { "epoch": 0.7213194868662187, "grad_norm": 0.4572213292121887, "learning_rate": 8.984687373179322e-06, "loss": 4.2594, "step": 23616 }, { "epoch": 0.7213500305436774, "grad_norm": 0.4639011025428772, "learning_rate": 8.982845421167727e-06, "loss": 4.1496, "step": 23617 }, { "epoch": 0.7213805742211362, "grad_norm": 0.4790550470352173, "learning_rate": 8.981003616634301e-06, "loss": 4.3082, "step": 23618 }, { "epoch": 0.721411117898595, "grad_norm": 0.4657193720340729, "learning_rate": 8.979161959596011e-06, "loss": 4.2891, "step": 23619 }, { "epoch": 0.7214416615760537, "grad_norm": 0.46580374240875244, "learning_rate": 8.977320450069822e-06, "loss": 4.2019, "step": 23620 }, { "epoch": 0.7214722052535125, "grad_norm": 0.4663871228694916, "learning_rate": 8.975479088072675e-06, "loss": 4.2718, "step": 23621 }, { "epoch": 0.7215027489309713, "grad_norm": 0.4585276246070862, "learning_rate": 8.97363787362153e-06, "loss": 4.2304, "step": 23622 }, { "epoch": 0.72153329260843, "grad_norm": 0.46907177567481995, "learning_rate": 8.971796806733349e-06, "loss": 4.2062, "step": 23623 }, { "epoch": 0.7215638362858888, "grad_norm": 0.4653521478176117, "learning_rate": 8.969955887425078e-06, "loss": 4.243, "step": 23624 }, { "epoch": 0.7215943799633476, "grad_norm": 0.46430519223213196, "learning_rate": 8.968115115713655e-06, "loss": 4.2407, "step": 23625 }, { "epoch": 0.7216249236408063, "grad_norm": 0.47367215156555176, "learning_rate": 8.966274491616045e-06, "loss": 4.329, "step": 23626 }, { "epoch": 0.7216554673182651, "grad_norm": 0.4575965404510498, "learning_rate": 8.964434015149184e-06, "loss": 4.2447, "step": 23627 }, { "epoch": 0.7216860109957239, "grad_norm": 0.45520955324172974, "learning_rate": 8.962593686330023e-06, "loss": 4.195, "step": 23628 }, { "epoch": 0.7217165546731826, "grad_norm": 0.47191834449768066, "learning_rate": 8.960753505175515e-06, "loss": 4.3667, "step": 23629 }, { "epoch": 0.7217470983506414, "grad_norm": 0.47225651144981384, "learning_rate": 8.958913471702588e-06, "loss": 4.179, "step": 23630 }, { "epoch": 0.7217776420281001, "grad_norm": 0.468020498752594, "learning_rate": 8.957073585928203e-06, "loss": 4.3316, "step": 23631 }, { "epoch": 0.7218081857055589, "grad_norm": 0.4664399027824402, "learning_rate": 8.955233847869276e-06, "loss": 4.3257, "step": 23632 }, { "epoch": 0.7218387293830177, "grad_norm": 0.4682953953742981, "learning_rate": 8.953394257542766e-06, "loss": 4.2455, "step": 23633 }, { "epoch": 0.7218692730604764, "grad_norm": 0.45634087920188904, "learning_rate": 8.95155481496561e-06, "loss": 4.2488, "step": 23634 }, { "epoch": 0.7218998167379352, "grad_norm": 0.48965317010879517, "learning_rate": 8.949715520154733e-06, "loss": 4.2952, "step": 23635 }, { "epoch": 0.721930360415394, "grad_norm": 0.46109259128570557, "learning_rate": 8.947876373127079e-06, "loss": 4.19, "step": 23636 }, { "epoch": 0.7219609040928527, "grad_norm": 0.4688175320625305, "learning_rate": 8.946037373899587e-06, "loss": 4.2573, "step": 23637 }, { "epoch": 0.7219914477703115, "grad_norm": 0.46800094842910767, "learning_rate": 8.944198522489174e-06, "loss": 4.2746, "step": 23638 }, { "epoch": 0.7220219914477704, "grad_norm": 0.47019538283348083, "learning_rate": 8.94235981891279e-06, "loss": 4.2504, "step": 23639 }, { "epoch": 0.722052535125229, "grad_norm": 0.46360117197036743, "learning_rate": 8.94052126318735e-06, "loss": 4.3394, "step": 23640 }, { "epoch": 0.7220830788026878, "grad_norm": 0.45436999201774597, "learning_rate": 8.938682855329791e-06, "loss": 4.2114, "step": 23641 }, { "epoch": 0.7221136224801467, "grad_norm": 0.46587368845939636, "learning_rate": 8.93684459535703e-06, "loss": 4.1878, "step": 23642 }, { "epoch": 0.7221441661576053, "grad_norm": 0.4667831063270569, "learning_rate": 8.93500648328601e-06, "loss": 4.2741, "step": 23643 }, { "epoch": 0.7221747098350642, "grad_norm": 0.4756261706352234, "learning_rate": 8.933168519133634e-06, "loss": 4.2193, "step": 23644 }, { "epoch": 0.722205253512523, "grad_norm": 0.46196508407592773, "learning_rate": 8.931330702916838e-06, "loss": 4.2529, "step": 23645 }, { "epoch": 0.7222357971899817, "grad_norm": 0.4646966755390167, "learning_rate": 8.929493034652547e-06, "loss": 4.2853, "step": 23646 }, { "epoch": 0.7222663408674405, "grad_norm": 0.4717627167701721, "learning_rate": 8.927655514357672e-06, "loss": 4.346, "step": 23647 }, { "epoch": 0.7222968845448992, "grad_norm": 0.4728999435901642, "learning_rate": 8.92581814204914e-06, "loss": 4.2572, "step": 23648 }, { "epoch": 0.722327428222358, "grad_norm": 0.4782777428627014, "learning_rate": 8.923980917743862e-06, "loss": 4.2, "step": 23649 }, { "epoch": 0.7223579718998168, "grad_norm": 0.45927339792251587, "learning_rate": 8.922143841458755e-06, "loss": 4.2485, "step": 23650 }, { "epoch": 0.7223885155772755, "grad_norm": 0.46741241216659546, "learning_rate": 8.920306913210743e-06, "loss": 4.2174, "step": 23651 }, { "epoch": 0.7224190592547343, "grad_norm": 0.46357741951942444, "learning_rate": 8.918470133016727e-06, "loss": 4.3114, "step": 23652 }, { "epoch": 0.7224496029321931, "grad_norm": 0.4577200710773468, "learning_rate": 8.916633500893623e-06, "loss": 4.271, "step": 23653 }, { "epoch": 0.7224801466096518, "grad_norm": 0.46079760789871216, "learning_rate": 8.914797016858351e-06, "loss": 4.2948, "step": 23654 }, { "epoch": 0.7225106902871106, "grad_norm": 0.4681544005870819, "learning_rate": 8.912960680927806e-06, "loss": 4.1904, "step": 23655 }, { "epoch": 0.7225412339645694, "grad_norm": 0.462197482585907, "learning_rate": 8.911124493118911e-06, "loss": 4.2569, "step": 23656 }, { "epoch": 0.7225717776420281, "grad_norm": 0.46256348490715027, "learning_rate": 8.909288453448567e-06, "loss": 4.2386, "step": 23657 }, { "epoch": 0.7226023213194869, "grad_norm": 0.457035094499588, "learning_rate": 8.907452561933666e-06, "loss": 4.1858, "step": 23658 }, { "epoch": 0.7226328649969457, "grad_norm": 0.4590699374675751, "learning_rate": 8.905616818591123e-06, "loss": 4.2847, "step": 23659 }, { "epoch": 0.7226634086744044, "grad_norm": 0.46401578187942505, "learning_rate": 8.903781223437851e-06, "loss": 4.2821, "step": 23660 }, { "epoch": 0.7226939523518632, "grad_norm": 0.46187129616737366, "learning_rate": 8.901945776490734e-06, "loss": 4.234, "step": 23661 }, { "epoch": 0.722724496029322, "grad_norm": 0.4662444591522217, "learning_rate": 8.900110477766676e-06, "loss": 4.341, "step": 23662 }, { "epoch": 0.7227550397067807, "grad_norm": 0.4576139748096466, "learning_rate": 8.898275327282588e-06, "loss": 4.259, "step": 23663 }, { "epoch": 0.7227855833842395, "grad_norm": 0.468286395072937, "learning_rate": 8.896440325055349e-06, "loss": 4.3503, "step": 23664 }, { "epoch": 0.7228161270616982, "grad_norm": 0.46295222640037537, "learning_rate": 8.894605471101875e-06, "loss": 4.2408, "step": 23665 }, { "epoch": 0.722846670739157, "grad_norm": 0.47155192494392395, "learning_rate": 8.892770765439038e-06, "loss": 4.2659, "step": 23666 }, { "epoch": 0.7228772144166158, "grad_norm": 0.46057119965553284, "learning_rate": 8.890936208083742e-06, "loss": 4.2522, "step": 23667 }, { "epoch": 0.7229077580940745, "grad_norm": 0.4616318643093109, "learning_rate": 8.889101799052887e-06, "loss": 4.1706, "step": 23668 }, { "epoch": 0.7229383017715333, "grad_norm": 0.46098029613494873, "learning_rate": 8.887267538363347e-06, "loss": 4.2248, "step": 23669 }, { "epoch": 0.7229688454489921, "grad_norm": 0.46828970313072205, "learning_rate": 8.885433426032028e-06, "loss": 4.2477, "step": 23670 }, { "epoch": 0.7229993891264508, "grad_norm": 0.4688023030757904, "learning_rate": 8.8835994620758e-06, "loss": 4.2635, "step": 23671 }, { "epoch": 0.7230299328039096, "grad_norm": 0.46004247665405273, "learning_rate": 8.881765646511566e-06, "loss": 4.2607, "step": 23672 }, { "epoch": 0.7230604764813684, "grad_norm": 0.4719539284706116, "learning_rate": 8.879931979356196e-06, "loss": 4.2878, "step": 23673 }, { "epoch": 0.7230910201588271, "grad_norm": 0.4625883102416992, "learning_rate": 8.878098460626585e-06, "loss": 4.2434, "step": 23674 }, { "epoch": 0.7231215638362859, "grad_norm": 0.4682137370109558, "learning_rate": 8.876265090339605e-06, "loss": 4.2002, "step": 23675 }, { "epoch": 0.7231521075137447, "grad_norm": 0.4690622091293335, "learning_rate": 8.874431868512143e-06, "loss": 4.2995, "step": 23676 }, { "epoch": 0.7231826511912034, "grad_norm": 0.46533751487731934, "learning_rate": 8.872598795161085e-06, "loss": 4.1796, "step": 23677 }, { "epoch": 0.7232131948686622, "grad_norm": 0.46952053904533386, "learning_rate": 8.870765870303294e-06, "loss": 4.359, "step": 23678 }, { "epoch": 0.723243738546121, "grad_norm": 0.46597397327423096, "learning_rate": 8.868933093955655e-06, "loss": 4.2906, "step": 23679 }, { "epoch": 0.7232742822235797, "grad_norm": 0.4624805152416229, "learning_rate": 8.86710046613505e-06, "loss": 4.2318, "step": 23680 }, { "epoch": 0.7233048259010385, "grad_norm": 0.47874659299850464, "learning_rate": 8.865267986858338e-06, "loss": 4.2559, "step": 23681 }, { "epoch": 0.7233353695784972, "grad_norm": 0.4712092876434326, "learning_rate": 8.863435656142407e-06, "loss": 4.3095, "step": 23682 }, { "epoch": 0.723365913255956, "grad_norm": 0.46698176860809326, "learning_rate": 8.861603474004113e-06, "loss": 4.3563, "step": 23683 }, { "epoch": 0.7233964569334148, "grad_norm": 0.462833046913147, "learning_rate": 8.859771440460333e-06, "loss": 4.2883, "step": 23684 }, { "epoch": 0.7234270006108735, "grad_norm": 0.46517783403396606, "learning_rate": 8.857939555527945e-06, "loss": 4.2081, "step": 23685 }, { "epoch": 0.7234575442883323, "grad_norm": 0.46150943636894226, "learning_rate": 8.856107819223797e-06, "loss": 4.2892, "step": 23686 }, { "epoch": 0.7234880879657911, "grad_norm": 0.46695905923843384, "learning_rate": 8.854276231564773e-06, "loss": 4.2485, "step": 23687 }, { "epoch": 0.7235186316432498, "grad_norm": 0.4647294878959656, "learning_rate": 8.85244479256773e-06, "loss": 4.2495, "step": 23688 }, { "epoch": 0.7235491753207086, "grad_norm": 0.45896631479263306, "learning_rate": 8.850613502249521e-06, "loss": 4.1376, "step": 23689 }, { "epoch": 0.7235797189981674, "grad_norm": 0.46072548627853394, "learning_rate": 8.848782360627016e-06, "loss": 4.2677, "step": 23690 }, { "epoch": 0.7236102626756261, "grad_norm": 0.473117470741272, "learning_rate": 8.846951367717085e-06, "loss": 4.2623, "step": 23691 }, { "epoch": 0.7236408063530849, "grad_norm": 0.47153031826019287, "learning_rate": 8.845120523536571e-06, "loss": 4.289, "step": 23692 }, { "epoch": 0.7236713500305437, "grad_norm": 0.46299004554748535, "learning_rate": 8.843289828102336e-06, "loss": 4.2686, "step": 23693 }, { "epoch": 0.7237018937080024, "grad_norm": 0.46559062600135803, "learning_rate": 8.84145928143125e-06, "loss": 4.2412, "step": 23694 }, { "epoch": 0.7237324373854612, "grad_norm": 0.46757712960243225, "learning_rate": 8.839628883540144e-06, "loss": 4.2999, "step": 23695 }, { "epoch": 0.72376298106292, "grad_norm": 0.46656903624534607, "learning_rate": 8.837798634445887e-06, "loss": 4.2158, "step": 23696 }, { "epoch": 0.7237935247403787, "grad_norm": 0.46407878398895264, "learning_rate": 8.835968534165333e-06, "loss": 4.2588, "step": 23697 }, { "epoch": 0.7238240684178375, "grad_norm": 0.4615831673145294, "learning_rate": 8.834138582715323e-06, "loss": 4.1976, "step": 23698 }, { "epoch": 0.7238546120952962, "grad_norm": 0.4715642035007477, "learning_rate": 8.832308780112717e-06, "loss": 4.2862, "step": 23699 }, { "epoch": 0.723885155772755, "grad_norm": 0.47030290961265564, "learning_rate": 8.830479126374346e-06, "loss": 4.2492, "step": 23700 }, { "epoch": 0.7239156994502138, "grad_norm": 0.4642953872680664, "learning_rate": 8.82864962151707e-06, "loss": 4.1354, "step": 23701 }, { "epoch": 0.7239462431276725, "grad_norm": 0.47247904539108276, "learning_rate": 8.826820265557739e-06, "loss": 4.2444, "step": 23702 }, { "epoch": 0.7239767868051313, "grad_norm": 0.469641774892807, "learning_rate": 8.82499105851319e-06, "loss": 4.3136, "step": 23703 }, { "epoch": 0.7240073304825901, "grad_norm": 0.46766871213912964, "learning_rate": 8.823162000400257e-06, "loss": 4.2037, "step": 23704 }, { "epoch": 0.7240378741600488, "grad_norm": 0.460476279258728, "learning_rate": 8.821333091235796e-06, "loss": 4.1527, "step": 23705 }, { "epoch": 0.7240684178375076, "grad_norm": 0.47880762815475464, "learning_rate": 8.819504331036629e-06, "loss": 4.3499, "step": 23706 }, { "epoch": 0.7240989615149664, "grad_norm": 0.4814471900463104, "learning_rate": 8.81767571981961e-06, "loss": 4.2637, "step": 23707 }, { "epoch": 0.7241295051924251, "grad_norm": 0.4673626124858856, "learning_rate": 8.815847257601576e-06, "loss": 4.1515, "step": 23708 }, { "epoch": 0.7241600488698839, "grad_norm": 0.46243229508399963, "learning_rate": 8.814018944399347e-06, "loss": 4.2221, "step": 23709 }, { "epoch": 0.7241905925473427, "grad_norm": 0.44828030467033386, "learning_rate": 8.81219078022977e-06, "loss": 4.2098, "step": 23710 }, { "epoch": 0.7242211362248014, "grad_norm": 0.4656095802783966, "learning_rate": 8.810362765109683e-06, "loss": 4.2553, "step": 23711 }, { "epoch": 0.7242516799022602, "grad_norm": 0.4617912173271179, "learning_rate": 8.808534899055903e-06, "loss": 4.2274, "step": 23712 }, { "epoch": 0.724282223579719, "grad_norm": 0.46458718180656433, "learning_rate": 8.806707182085266e-06, "loss": 4.3158, "step": 23713 }, { "epoch": 0.7243127672571777, "grad_norm": 0.47644004225730896, "learning_rate": 8.804879614214609e-06, "loss": 4.2049, "step": 23714 }, { "epoch": 0.7243433109346366, "grad_norm": 0.45962250232696533, "learning_rate": 8.803052195460746e-06, "loss": 4.3528, "step": 23715 }, { "epoch": 0.7243738546120952, "grad_norm": 0.4586983025074005, "learning_rate": 8.801224925840515e-06, "loss": 4.2524, "step": 23716 }, { "epoch": 0.724404398289554, "grad_norm": 0.4625586271286011, "learning_rate": 8.79939780537073e-06, "loss": 4.143, "step": 23717 }, { "epoch": 0.7244349419670129, "grad_norm": 0.4633415937423706, "learning_rate": 8.797570834068222e-06, "loss": 4.2351, "step": 23718 }, { "epoch": 0.7244654856444716, "grad_norm": 0.45996513962745667, "learning_rate": 8.795744011949805e-06, "loss": 4.2684, "step": 23719 }, { "epoch": 0.7244960293219304, "grad_norm": 0.4653770327568054, "learning_rate": 8.793917339032312e-06, "loss": 4.2159, "step": 23720 }, { "epoch": 0.7245265729993892, "grad_norm": 0.49874401092529297, "learning_rate": 8.792090815332545e-06, "loss": 4.3124, "step": 23721 }, { "epoch": 0.7245571166768479, "grad_norm": 0.4628436863422394, "learning_rate": 8.790264440867342e-06, "loss": 4.3155, "step": 23722 }, { "epoch": 0.7245876603543067, "grad_norm": 0.47314172983169556, "learning_rate": 8.7884382156535e-06, "loss": 4.1649, "step": 23723 }, { "epoch": 0.7246182040317655, "grad_norm": 0.47031065821647644, "learning_rate": 8.78661213970784e-06, "loss": 4.3935, "step": 23724 }, { "epoch": 0.7246487477092242, "grad_norm": 0.4721237123012543, "learning_rate": 8.784786213047188e-06, "loss": 4.2709, "step": 23725 }, { "epoch": 0.724679291386683, "grad_norm": 0.465549111366272, "learning_rate": 8.782960435688336e-06, "loss": 4.2211, "step": 23726 }, { "epoch": 0.7247098350641418, "grad_norm": 0.4705409109592438, "learning_rate": 8.781134807648108e-06, "loss": 4.2666, "step": 23727 }, { "epoch": 0.7247403787416005, "grad_norm": 0.4697708785533905, "learning_rate": 8.77930932894332e-06, "loss": 4.252, "step": 23728 }, { "epoch": 0.7247709224190593, "grad_norm": 0.475132018327713, "learning_rate": 8.777483999590758e-06, "loss": 4.1435, "step": 23729 }, { "epoch": 0.724801466096518, "grad_norm": 0.46309635043144226, "learning_rate": 8.775658819607252e-06, "loss": 4.2496, "step": 23730 }, { "epoch": 0.7248320097739768, "grad_norm": 0.45730075240135193, "learning_rate": 8.773833789009589e-06, "loss": 4.2019, "step": 23731 }, { "epoch": 0.7248625534514356, "grad_norm": 0.4740052819252014, "learning_rate": 8.772008907814583e-06, "loss": 4.1814, "step": 23732 }, { "epoch": 0.7248930971288943, "grad_norm": 0.47084203362464905, "learning_rate": 8.77018417603904e-06, "loss": 4.3406, "step": 23733 }, { "epoch": 0.7249236408063531, "grad_norm": 0.47242069244384766, "learning_rate": 8.768359593699757e-06, "loss": 4.3003, "step": 23734 }, { "epoch": 0.7249541844838119, "grad_norm": 0.4624892771244049, "learning_rate": 8.766535160813524e-06, "loss": 4.289, "step": 23735 }, { "epoch": 0.7249847281612706, "grad_norm": 0.45896050333976746, "learning_rate": 8.764710877397156e-06, "loss": 4.257, "step": 23736 }, { "epoch": 0.7250152718387294, "grad_norm": 0.4684978723526001, "learning_rate": 8.762886743467435e-06, "loss": 4.2953, "step": 23737 }, { "epoch": 0.7250458155161882, "grad_norm": 0.47092676162719727, "learning_rate": 8.761062759041163e-06, "loss": 4.2425, "step": 23738 }, { "epoch": 0.7250763591936469, "grad_norm": 0.4733501970767975, "learning_rate": 8.759238924135146e-06, "loss": 4.3431, "step": 23739 }, { "epoch": 0.7251069028711057, "grad_norm": 0.47644031047821045, "learning_rate": 8.757415238766156e-06, "loss": 4.2911, "step": 23740 }, { "epoch": 0.7251374465485645, "grad_norm": 0.46977469325065613, "learning_rate": 8.755591702950996e-06, "loss": 4.3673, "step": 23741 }, { "epoch": 0.7251679902260232, "grad_norm": 0.4683748185634613, "learning_rate": 8.753768316706463e-06, "loss": 4.3212, "step": 23742 }, { "epoch": 0.725198533903482, "grad_norm": 0.4801555275917053, "learning_rate": 8.751945080049331e-06, "loss": 4.0676, "step": 23743 }, { "epoch": 0.7252290775809408, "grad_norm": 0.47169604897499084, "learning_rate": 8.750121992996394e-06, "loss": 4.2185, "step": 23744 }, { "epoch": 0.7252596212583995, "grad_norm": 0.45839723944664, "learning_rate": 8.748299055564446e-06, "loss": 4.2715, "step": 23745 }, { "epoch": 0.7252901649358583, "grad_norm": 0.47036170959472656, "learning_rate": 8.746476267770257e-06, "loss": 4.2217, "step": 23746 }, { "epoch": 0.725320708613317, "grad_norm": 0.46413323283195496, "learning_rate": 8.744653629630626e-06, "loss": 4.1877, "step": 23747 }, { "epoch": 0.7253512522907758, "grad_norm": 0.45429617166519165, "learning_rate": 8.742831141162317e-06, "loss": 4.201, "step": 23748 }, { "epoch": 0.7253817959682346, "grad_norm": 0.4784267544746399, "learning_rate": 8.741008802382127e-06, "loss": 4.2742, "step": 23749 }, { "epoch": 0.7254123396456933, "grad_norm": 0.468970388174057, "learning_rate": 8.739186613306824e-06, "loss": 4.3206, "step": 23750 }, { "epoch": 0.7254428833231521, "grad_norm": 0.45841577649116516, "learning_rate": 8.7373645739532e-06, "loss": 4.2652, "step": 23751 }, { "epoch": 0.7254734270006109, "grad_norm": 0.4680122435092926, "learning_rate": 8.735542684338011e-06, "loss": 4.2578, "step": 23752 }, { "epoch": 0.7255039706780696, "grad_norm": 0.47322970628738403, "learning_rate": 8.733720944478049e-06, "loss": 4.3446, "step": 23753 }, { "epoch": 0.7255345143555284, "grad_norm": 0.46304741501808167, "learning_rate": 8.731899354390075e-06, "loss": 4.2789, "step": 23754 }, { "epoch": 0.7255650580329872, "grad_norm": 0.46467453241348267, "learning_rate": 8.73007791409087e-06, "loss": 4.1929, "step": 23755 }, { "epoch": 0.7255956017104459, "grad_norm": 0.4851020574569702, "learning_rate": 8.728256623597208e-06, "loss": 4.2325, "step": 23756 }, { "epoch": 0.7256261453879047, "grad_norm": 0.4696151614189148, "learning_rate": 8.726435482925846e-06, "loss": 4.252, "step": 23757 }, { "epoch": 0.7256566890653635, "grad_norm": 0.46198704838752747, "learning_rate": 8.724614492093561e-06, "loss": 4.262, "step": 23758 }, { "epoch": 0.7256872327428222, "grad_norm": 0.46609818935394287, "learning_rate": 8.722793651117125e-06, "loss": 4.2225, "step": 23759 }, { "epoch": 0.725717776420281, "grad_norm": 0.466924250125885, "learning_rate": 8.72097296001329e-06, "loss": 4.3084, "step": 23760 }, { "epoch": 0.7257483200977398, "grad_norm": 0.4690258502960205, "learning_rate": 8.719152418798827e-06, "loss": 4.3027, "step": 23761 }, { "epoch": 0.7257788637751985, "grad_norm": 0.4701136648654938, "learning_rate": 8.717332027490505e-06, "loss": 4.2509, "step": 23762 }, { "epoch": 0.7258094074526573, "grad_norm": 0.4680876135826111, "learning_rate": 8.715511786105071e-06, "loss": 4.3302, "step": 23763 }, { "epoch": 0.725839951130116, "grad_norm": 0.48455673456192017, "learning_rate": 8.7136916946593e-06, "loss": 4.2475, "step": 23764 }, { "epoch": 0.7258704948075748, "grad_norm": 0.4623424708843231, "learning_rate": 8.711871753169938e-06, "loss": 4.2456, "step": 23765 }, { "epoch": 0.7259010384850336, "grad_norm": 0.4604468047618866, "learning_rate": 8.710051961653751e-06, "loss": 4.2245, "step": 23766 }, { "epoch": 0.7259315821624923, "grad_norm": 0.4721612334251404, "learning_rate": 8.708232320127493e-06, "loss": 4.1762, "step": 23767 }, { "epoch": 0.7259621258399511, "grad_norm": 0.4712405204772949, "learning_rate": 8.70641282860791e-06, "loss": 4.2989, "step": 23768 }, { "epoch": 0.7259926695174099, "grad_norm": 0.47529950737953186, "learning_rate": 8.704593487111759e-06, "loss": 4.3654, "step": 23769 }, { "epoch": 0.7260232131948686, "grad_norm": 0.45798826217651367, "learning_rate": 8.702774295655805e-06, "loss": 4.2796, "step": 23770 }, { "epoch": 0.7260537568723274, "grad_norm": 0.4664430618286133, "learning_rate": 8.700955254256777e-06, "loss": 4.3118, "step": 23771 }, { "epoch": 0.7260843005497862, "grad_norm": 0.46020060777664185, "learning_rate": 8.699136362931434e-06, "loss": 4.2428, "step": 23772 }, { "epoch": 0.7261148442272449, "grad_norm": 0.4547465145587921, "learning_rate": 8.697317621696532e-06, "loss": 4.1417, "step": 23773 }, { "epoch": 0.7261453879047037, "grad_norm": 0.4683111906051636, "learning_rate": 8.695499030568801e-06, "loss": 4.2955, "step": 23774 }, { "epoch": 0.7261759315821625, "grad_norm": 0.4921695590019226, "learning_rate": 8.693680589564992e-06, "loss": 4.2516, "step": 23775 }, { "epoch": 0.7262064752596212, "grad_norm": 0.46965155005455017, "learning_rate": 8.69186229870186e-06, "loss": 4.3453, "step": 23776 }, { "epoch": 0.72623701893708, "grad_norm": 0.4566550552845001, "learning_rate": 8.690044157996127e-06, "loss": 4.2712, "step": 23777 }, { "epoch": 0.7262675626145388, "grad_norm": 0.46949273347854614, "learning_rate": 8.688226167464545e-06, "loss": 4.2956, "step": 23778 }, { "epoch": 0.7262981062919975, "grad_norm": 0.46706730127334595, "learning_rate": 8.686408327123857e-06, "loss": 4.1649, "step": 23779 }, { "epoch": 0.7263286499694563, "grad_norm": 0.4614560008049011, "learning_rate": 8.684590636990797e-06, "loss": 4.1641, "step": 23780 }, { "epoch": 0.726359193646915, "grad_norm": 0.46665382385253906, "learning_rate": 8.682773097082089e-06, "loss": 4.153, "step": 23781 }, { "epoch": 0.7263897373243738, "grad_norm": 0.4544699490070343, "learning_rate": 8.68095570741449e-06, "loss": 4.1337, "step": 23782 }, { "epoch": 0.7264202810018326, "grad_norm": 0.4661329686641693, "learning_rate": 8.679138468004713e-06, "loss": 4.1843, "step": 23783 }, { "epoch": 0.7264508246792913, "grad_norm": 0.4667121171951294, "learning_rate": 8.677321378869507e-06, "loss": 4.2393, "step": 23784 }, { "epoch": 0.7264813683567501, "grad_norm": 0.45752599835395813, "learning_rate": 8.675504440025586e-06, "loss": 4.1982, "step": 23785 }, { "epoch": 0.726511912034209, "grad_norm": 0.47568610310554504, "learning_rate": 8.67368765148969e-06, "loss": 4.2451, "step": 23786 }, { "epoch": 0.7265424557116676, "grad_norm": 0.4642704427242279, "learning_rate": 8.671871013278554e-06, "loss": 4.2443, "step": 23787 }, { "epoch": 0.7265729993891265, "grad_norm": 0.4752981960773468, "learning_rate": 8.67005452540889e-06, "loss": 4.1788, "step": 23788 }, { "epoch": 0.7266035430665853, "grad_norm": 0.4628555476665497, "learning_rate": 8.668238187897429e-06, "loss": 4.2781, "step": 23789 }, { "epoch": 0.726634086744044, "grad_norm": 0.4710497260093689, "learning_rate": 8.666422000760904e-06, "loss": 4.2912, "step": 23790 }, { "epoch": 0.7266646304215028, "grad_norm": 0.467671662569046, "learning_rate": 8.66460596401602e-06, "loss": 4.2139, "step": 23791 }, { "epoch": 0.7266951740989616, "grad_norm": 0.47300398349761963, "learning_rate": 8.662790077679512e-06, "loss": 4.3238, "step": 23792 }, { "epoch": 0.7267257177764203, "grad_norm": 0.46588510274887085, "learning_rate": 8.6609743417681e-06, "loss": 4.3228, "step": 23793 }, { "epoch": 0.7267562614538791, "grad_norm": 0.4693627655506134, "learning_rate": 8.659158756298488e-06, "loss": 4.2693, "step": 23794 }, { "epoch": 0.7267868051313379, "grad_norm": 0.4670296907424927, "learning_rate": 8.657343321287415e-06, "loss": 4.2695, "step": 23795 }, { "epoch": 0.7268173488087966, "grad_norm": 0.48201945424079895, "learning_rate": 8.655528036751576e-06, "loss": 4.2154, "step": 23796 }, { "epoch": 0.7268478924862554, "grad_norm": 0.45269158482551575, "learning_rate": 8.6537129027077e-06, "loss": 4.1693, "step": 23797 }, { "epoch": 0.7268784361637141, "grad_norm": 0.46355926990509033, "learning_rate": 8.651897919172495e-06, "loss": 4.3082, "step": 23798 }, { "epoch": 0.7269089798411729, "grad_norm": 0.4678806960582733, "learning_rate": 8.650083086162664e-06, "loss": 4.2558, "step": 23799 }, { "epoch": 0.7269395235186317, "grad_norm": 0.47278204560279846, "learning_rate": 8.648268403694922e-06, "loss": 4.2888, "step": 23800 }, { "epoch": 0.7269700671960904, "grad_norm": 0.4795403778553009, "learning_rate": 8.64645387178599e-06, "loss": 4.3591, "step": 23801 }, { "epoch": 0.7270006108735492, "grad_norm": 0.46775245666503906, "learning_rate": 8.644639490452555e-06, "loss": 4.2734, "step": 23802 }, { "epoch": 0.727031154551008, "grad_norm": 0.46188512444496155, "learning_rate": 8.642825259711338e-06, "loss": 4.2434, "step": 23803 }, { "epoch": 0.7270616982284667, "grad_norm": 0.4727095663547516, "learning_rate": 8.641011179579043e-06, "loss": 4.2698, "step": 23804 }, { "epoch": 0.7270922419059255, "grad_norm": 0.46883946657180786, "learning_rate": 8.639197250072361e-06, "loss": 4.2672, "step": 23805 }, { "epoch": 0.7271227855833843, "grad_norm": 0.46182361245155334, "learning_rate": 8.637383471208003e-06, "loss": 4.2691, "step": 23806 }, { "epoch": 0.727153329260843, "grad_norm": 0.4729786217212677, "learning_rate": 8.635569843002676e-06, "loss": 4.3086, "step": 23807 }, { "epoch": 0.7271838729383018, "grad_norm": 0.4724673926830292, "learning_rate": 8.633756365473061e-06, "loss": 4.201, "step": 23808 }, { "epoch": 0.7272144166157606, "grad_norm": 0.4650322198867798, "learning_rate": 8.63194303863587e-06, "loss": 4.2945, "step": 23809 }, { "epoch": 0.7272449602932193, "grad_norm": 0.465177983045578, "learning_rate": 8.630129862507799e-06, "loss": 4.1441, "step": 23810 }, { "epoch": 0.7272755039706781, "grad_norm": 0.46782565116882324, "learning_rate": 8.628316837105535e-06, "loss": 4.3151, "step": 23811 }, { "epoch": 0.7273060476481369, "grad_norm": 0.46205198764801025, "learning_rate": 8.626503962445782e-06, "loss": 4.1933, "step": 23812 }, { "epoch": 0.7273365913255956, "grad_norm": 0.46154654026031494, "learning_rate": 8.624691238545224e-06, "loss": 4.3393, "step": 23813 }, { "epoch": 0.7273671350030544, "grad_norm": 0.4643261134624481, "learning_rate": 8.622878665420545e-06, "loss": 4.2726, "step": 23814 }, { "epoch": 0.7273976786805131, "grad_norm": 0.4802188277244568, "learning_rate": 8.621066243088452e-06, "loss": 4.2163, "step": 23815 }, { "epoch": 0.7274282223579719, "grad_norm": 0.4684367775917053, "learning_rate": 8.619253971565614e-06, "loss": 4.3129, "step": 23816 }, { "epoch": 0.7274587660354307, "grad_norm": 0.47980886697769165, "learning_rate": 8.617441850868726e-06, "loss": 4.165, "step": 23817 }, { "epoch": 0.7274893097128894, "grad_norm": 0.4846774935722351, "learning_rate": 8.615629881014483e-06, "loss": 4.2274, "step": 23818 }, { "epoch": 0.7275198533903482, "grad_norm": 0.4670027792453766, "learning_rate": 8.613818062019554e-06, "loss": 4.2626, "step": 23819 }, { "epoch": 0.727550397067807, "grad_norm": 0.4547780454158783, "learning_rate": 8.612006393900624e-06, "loss": 4.2453, "step": 23820 }, { "epoch": 0.7275809407452657, "grad_norm": 0.46320515871047974, "learning_rate": 8.610194876674387e-06, "loss": 4.1826, "step": 23821 }, { "epoch": 0.7276114844227245, "grad_norm": 0.47504204511642456, "learning_rate": 8.608383510357504e-06, "loss": 4.2518, "step": 23822 }, { "epoch": 0.7276420281001833, "grad_norm": 0.4603557288646698, "learning_rate": 8.60657229496666e-06, "loss": 4.27, "step": 23823 }, { "epoch": 0.727672571777642, "grad_norm": 0.46725326776504517, "learning_rate": 8.604761230518544e-06, "loss": 4.2343, "step": 23824 }, { "epoch": 0.7277031154551008, "grad_norm": 0.47463107109069824, "learning_rate": 8.602950317029813e-06, "loss": 4.2834, "step": 23825 }, { "epoch": 0.7277336591325596, "grad_norm": 0.46714699268341064, "learning_rate": 8.601139554517154e-06, "loss": 4.2916, "step": 23826 }, { "epoch": 0.7277642028100183, "grad_norm": 0.4699699282646179, "learning_rate": 8.599328942997229e-06, "loss": 4.3096, "step": 23827 }, { "epoch": 0.7277947464874771, "grad_norm": 0.4596787691116333, "learning_rate": 8.597518482486722e-06, "loss": 4.2851, "step": 23828 }, { "epoch": 0.7278252901649359, "grad_norm": 0.4637181758880615, "learning_rate": 8.595708173002287e-06, "loss": 4.3135, "step": 23829 }, { "epoch": 0.7278558338423946, "grad_norm": 0.4768649935722351, "learning_rate": 8.593898014560612e-06, "loss": 4.3561, "step": 23830 }, { "epoch": 0.7278863775198534, "grad_norm": 0.469402551651001, "learning_rate": 8.592088007178342e-06, "loss": 4.2594, "step": 23831 }, { "epoch": 0.7279169211973121, "grad_norm": 0.4581736624240875, "learning_rate": 8.590278150872163e-06, "loss": 4.2396, "step": 23832 }, { "epoch": 0.7279474648747709, "grad_norm": 0.46194612979888916, "learning_rate": 8.588468445658723e-06, "loss": 4.2079, "step": 23833 }, { "epoch": 0.7279780085522297, "grad_norm": 0.4855896830558777, "learning_rate": 8.586658891554692e-06, "loss": 4.1731, "step": 23834 }, { "epoch": 0.7280085522296884, "grad_norm": 0.46597692370414734, "learning_rate": 8.584849488576737e-06, "loss": 4.2029, "step": 23835 }, { "epoch": 0.7280390959071472, "grad_norm": 0.46175917983055115, "learning_rate": 8.583040236741504e-06, "loss": 4.2255, "step": 23836 }, { "epoch": 0.728069639584606, "grad_norm": 0.4721672236919403, "learning_rate": 8.581231136065665e-06, "loss": 4.2849, "step": 23837 }, { "epoch": 0.7281001832620647, "grad_norm": 0.4798024594783783, "learning_rate": 8.579422186565877e-06, "loss": 4.1226, "step": 23838 }, { "epoch": 0.7281307269395235, "grad_norm": 0.4719237983226776, "learning_rate": 8.577613388258784e-06, "loss": 4.2836, "step": 23839 }, { "epoch": 0.7281612706169823, "grad_norm": 0.46739158034324646, "learning_rate": 8.57580474116105e-06, "loss": 4.2264, "step": 23840 }, { "epoch": 0.728191814294441, "grad_norm": 0.47189900279045105, "learning_rate": 8.573996245289334e-06, "loss": 4.3618, "step": 23841 }, { "epoch": 0.7282223579718998, "grad_norm": 0.47307226061820984, "learning_rate": 8.57218790066027e-06, "loss": 4.2894, "step": 23842 }, { "epoch": 0.7282529016493586, "grad_norm": 0.4741288423538208, "learning_rate": 8.570379707290527e-06, "loss": 4.2502, "step": 23843 }, { "epoch": 0.7282834453268173, "grad_norm": 0.4688854515552521, "learning_rate": 8.568571665196746e-06, "loss": 4.2689, "step": 23844 }, { "epoch": 0.7283139890042761, "grad_norm": 0.47256696224212646, "learning_rate": 8.566763774395564e-06, "loss": 4.2984, "step": 23845 }, { "epoch": 0.7283445326817349, "grad_norm": 0.4660898447036743, "learning_rate": 8.56495603490364e-06, "loss": 4.2642, "step": 23846 }, { "epoch": 0.7283750763591936, "grad_norm": 0.4740598201751709, "learning_rate": 8.563148446737623e-06, "loss": 4.26, "step": 23847 }, { "epoch": 0.7284056200366524, "grad_norm": 0.46136483550071716, "learning_rate": 8.561341009914139e-06, "loss": 4.2652, "step": 23848 }, { "epoch": 0.7284361637141111, "grad_norm": 0.47043314576148987, "learning_rate": 8.55953372444985e-06, "loss": 4.2335, "step": 23849 }, { "epoch": 0.7284667073915699, "grad_norm": 0.4564398527145386, "learning_rate": 8.557726590361378e-06, "loss": 4.2305, "step": 23850 }, { "epoch": 0.7284972510690287, "grad_norm": 0.4713037610054016, "learning_rate": 8.555919607665374e-06, "loss": 4.2721, "step": 23851 }, { "epoch": 0.7285277947464874, "grad_norm": 0.46981188654899597, "learning_rate": 8.554112776378478e-06, "loss": 4.2111, "step": 23852 }, { "epoch": 0.7285583384239462, "grad_norm": 0.459522008895874, "learning_rate": 8.552306096517315e-06, "loss": 4.2031, "step": 23853 }, { "epoch": 0.728588882101405, "grad_norm": 0.47046634554862976, "learning_rate": 8.550499568098524e-06, "loss": 4.2377, "step": 23854 }, { "epoch": 0.7286194257788637, "grad_norm": 0.4610946476459503, "learning_rate": 8.548693191138752e-06, "loss": 4.249, "step": 23855 }, { "epoch": 0.7286499694563225, "grad_norm": 0.46621668338775635, "learning_rate": 8.54688696565461e-06, "loss": 4.2915, "step": 23856 }, { "epoch": 0.7286805131337813, "grad_norm": 0.46655043959617615, "learning_rate": 8.545080891662738e-06, "loss": 4.0755, "step": 23857 }, { "epoch": 0.72871105681124, "grad_norm": 0.46346423029899597, "learning_rate": 8.543274969179776e-06, "loss": 4.2738, "step": 23858 }, { "epoch": 0.7287416004886988, "grad_norm": 0.46920353174209595, "learning_rate": 8.541469198222343e-06, "loss": 4.2683, "step": 23859 }, { "epoch": 0.7287721441661577, "grad_norm": 0.4684615731239319, "learning_rate": 8.539663578807058e-06, "loss": 4.2356, "step": 23860 }, { "epoch": 0.7288026878436163, "grad_norm": 0.46354034543037415, "learning_rate": 8.53785811095056e-06, "loss": 4.1985, "step": 23861 }, { "epoch": 0.7288332315210752, "grad_norm": 0.4672246277332306, "learning_rate": 8.536052794669458e-06, "loss": 4.2303, "step": 23862 }, { "epoch": 0.728863775198534, "grad_norm": 0.4822443127632141, "learning_rate": 8.534247629980386e-06, "loss": 4.2267, "step": 23863 }, { "epoch": 0.7288943188759927, "grad_norm": 0.464081734418869, "learning_rate": 8.532442616899967e-06, "loss": 4.2425, "step": 23864 }, { "epoch": 0.7289248625534515, "grad_norm": 0.4647105932235718, "learning_rate": 8.530637755444807e-06, "loss": 4.2408, "step": 23865 }, { "epoch": 0.7289554062309102, "grad_norm": 0.47414538264274597, "learning_rate": 8.528833045631543e-06, "loss": 4.1844, "step": 23866 }, { "epoch": 0.728985949908369, "grad_norm": 0.4658331274986267, "learning_rate": 8.527028487476772e-06, "loss": 4.2802, "step": 23867 }, { "epoch": 0.7290164935858278, "grad_norm": 0.4698832631111145, "learning_rate": 8.525224080997119e-06, "loss": 4.2313, "step": 23868 }, { "epoch": 0.7290470372632865, "grad_norm": 0.4768945574760437, "learning_rate": 8.523419826209209e-06, "loss": 4.2518, "step": 23869 }, { "epoch": 0.7290775809407453, "grad_norm": 0.46170690655708313, "learning_rate": 8.521615723129633e-06, "loss": 4.2672, "step": 23870 }, { "epoch": 0.7291081246182041, "grad_norm": 0.469247967004776, "learning_rate": 8.519811771775016e-06, "loss": 4.2825, "step": 23871 }, { "epoch": 0.7291386682956628, "grad_norm": 0.47518256306648254, "learning_rate": 8.518007972161973e-06, "loss": 4.299, "step": 23872 }, { "epoch": 0.7291692119731216, "grad_norm": 0.47285333275794983, "learning_rate": 8.516204324307095e-06, "loss": 4.3162, "step": 23873 }, { "epoch": 0.7291997556505804, "grad_norm": 0.4632873237133026, "learning_rate": 8.51440082822701e-06, "loss": 4.1729, "step": 23874 }, { "epoch": 0.7292302993280391, "grad_norm": 0.45756661891937256, "learning_rate": 8.5125974839383e-06, "loss": 4.2719, "step": 23875 }, { "epoch": 0.7292608430054979, "grad_norm": 0.4667717218399048, "learning_rate": 8.510794291457593e-06, "loss": 4.2991, "step": 23876 }, { "epoch": 0.7292913866829567, "grad_norm": 0.4693373739719391, "learning_rate": 8.508991250801473e-06, "loss": 4.2344, "step": 23877 }, { "epoch": 0.7293219303604154, "grad_norm": 0.4726470112800598, "learning_rate": 8.507188361986556e-06, "loss": 4.2311, "step": 23878 }, { "epoch": 0.7293524740378742, "grad_norm": 0.4681941270828247, "learning_rate": 8.505385625029427e-06, "loss": 4.1951, "step": 23879 }, { "epoch": 0.7293830177153329, "grad_norm": 0.4684368371963501, "learning_rate": 8.503583039946705e-06, "loss": 4.2692, "step": 23880 }, { "epoch": 0.7294135613927917, "grad_norm": 0.4932548403739929, "learning_rate": 8.501780606754965e-06, "loss": 4.3235, "step": 23881 }, { "epoch": 0.7294441050702505, "grad_norm": 0.4684416353702545, "learning_rate": 8.499978325470812e-06, "loss": 4.1817, "step": 23882 }, { "epoch": 0.7294746487477092, "grad_norm": 0.48051586747169495, "learning_rate": 8.498176196110852e-06, "loss": 4.2435, "step": 23883 }, { "epoch": 0.729505192425168, "grad_norm": 0.47125139832496643, "learning_rate": 8.49637421869166e-06, "loss": 4.2441, "step": 23884 }, { "epoch": 0.7295357361026268, "grad_norm": 0.47076934576034546, "learning_rate": 8.494572393229835e-06, "loss": 4.3477, "step": 23885 }, { "epoch": 0.7295662797800855, "grad_norm": 0.4740356504917145, "learning_rate": 8.492770719741977e-06, "loss": 4.1957, "step": 23886 }, { "epoch": 0.7295968234575443, "grad_norm": 0.47100549936294556, "learning_rate": 8.490969198244659e-06, "loss": 4.2692, "step": 23887 }, { "epoch": 0.7296273671350031, "grad_norm": 0.4740501046180725, "learning_rate": 8.489167828754474e-06, "loss": 4.234, "step": 23888 }, { "epoch": 0.7296579108124618, "grad_norm": 0.46880748867988586, "learning_rate": 8.48736661128802e-06, "loss": 4.2534, "step": 23889 }, { "epoch": 0.7296884544899206, "grad_norm": 0.47773441672325134, "learning_rate": 8.48556554586187e-06, "loss": 4.2821, "step": 23890 }, { "epoch": 0.7297189981673794, "grad_norm": 0.47132617235183716, "learning_rate": 8.4837646324926e-06, "loss": 4.1855, "step": 23891 }, { "epoch": 0.7297495418448381, "grad_norm": 0.46333813667297363, "learning_rate": 8.48196387119681e-06, "loss": 4.1569, "step": 23892 }, { "epoch": 0.7297800855222969, "grad_norm": 0.4723333716392517, "learning_rate": 8.480163261991064e-06, "loss": 4.2907, "step": 23893 }, { "epoch": 0.7298106291997557, "grad_norm": 0.46472933888435364, "learning_rate": 8.478362804891948e-06, "loss": 4.3462, "step": 23894 }, { "epoch": 0.7298411728772144, "grad_norm": 0.471539705991745, "learning_rate": 8.476562499916046e-06, "loss": 4.1752, "step": 23895 }, { "epoch": 0.7298717165546732, "grad_norm": 0.4715883433818817, "learning_rate": 8.474762347079924e-06, "loss": 4.2297, "step": 23896 }, { "epoch": 0.7299022602321319, "grad_norm": 0.47650009393692017, "learning_rate": 8.472962346400168e-06, "loss": 4.1822, "step": 23897 }, { "epoch": 0.7299328039095907, "grad_norm": 0.47952771186828613, "learning_rate": 8.471162497893336e-06, "loss": 4.3221, "step": 23898 }, { "epoch": 0.7299633475870495, "grad_norm": 0.4730597138404846, "learning_rate": 8.469362801576011e-06, "loss": 4.2471, "step": 23899 }, { "epoch": 0.7299938912645082, "grad_norm": 0.46730631589889526, "learning_rate": 8.467563257464769e-06, "loss": 4.2043, "step": 23900 }, { "epoch": 0.730024434941967, "grad_norm": 0.4652921259403229, "learning_rate": 8.465763865576165e-06, "loss": 4.2653, "step": 23901 }, { "epoch": 0.7300549786194258, "grad_norm": 0.47049206495285034, "learning_rate": 8.463964625926774e-06, "loss": 4.2374, "step": 23902 }, { "epoch": 0.7300855222968845, "grad_norm": 0.46807432174682617, "learning_rate": 8.462165538533171e-06, "loss": 4.169, "step": 23903 }, { "epoch": 0.7301160659743433, "grad_norm": 0.4605726897716522, "learning_rate": 8.460366603411904e-06, "loss": 4.2655, "step": 23904 }, { "epoch": 0.7301466096518021, "grad_norm": 0.463760107755661, "learning_rate": 8.458567820579551e-06, "loss": 4.1598, "step": 23905 }, { "epoch": 0.7301771533292608, "grad_norm": 0.4671131372451782, "learning_rate": 8.456769190052665e-06, "loss": 4.3314, "step": 23906 }, { "epoch": 0.7302076970067196, "grad_norm": 0.4626322090625763, "learning_rate": 8.454970711847818e-06, "loss": 4.2578, "step": 23907 }, { "epoch": 0.7302382406841784, "grad_norm": 0.4742530584335327, "learning_rate": 8.453172385981553e-06, "loss": 4.1998, "step": 23908 }, { "epoch": 0.7302687843616371, "grad_norm": 0.4784690737724304, "learning_rate": 8.451374212470445e-06, "loss": 4.1862, "step": 23909 }, { "epoch": 0.7302993280390959, "grad_norm": 0.4732598066329956, "learning_rate": 8.449576191331035e-06, "loss": 4.2304, "step": 23910 }, { "epoch": 0.7303298717165547, "grad_norm": 0.4828355014324188, "learning_rate": 8.447778322579888e-06, "loss": 4.2104, "step": 23911 }, { "epoch": 0.7303604153940134, "grad_norm": 0.4835346043109894, "learning_rate": 8.445980606233565e-06, "loss": 4.2858, "step": 23912 }, { "epoch": 0.7303909590714722, "grad_norm": 0.47040489315986633, "learning_rate": 8.444183042308597e-06, "loss": 4.3037, "step": 23913 }, { "epoch": 0.7304215027489309, "grad_norm": 0.46740636229515076, "learning_rate": 8.442385630821561e-06, "loss": 4.3069, "step": 23914 }, { "epoch": 0.7304520464263897, "grad_norm": 0.4618876874446869, "learning_rate": 8.440588371788985e-06, "loss": 4.234, "step": 23915 }, { "epoch": 0.7304825901038485, "grad_norm": 0.46785181760787964, "learning_rate": 8.438791265227425e-06, "loss": 4.1385, "step": 23916 }, { "epoch": 0.7305131337813072, "grad_norm": 0.46859264373779297, "learning_rate": 8.436994311153434e-06, "loss": 4.2055, "step": 23917 }, { "epoch": 0.730543677458766, "grad_norm": 0.4847342073917389, "learning_rate": 8.435197509583548e-06, "loss": 4.2057, "step": 23918 }, { "epoch": 0.7305742211362248, "grad_norm": 0.47725629806518555, "learning_rate": 8.433400860534313e-06, "loss": 4.2794, "step": 23919 }, { "epoch": 0.7306047648136835, "grad_norm": 0.4759233295917511, "learning_rate": 8.431604364022284e-06, "loss": 4.2539, "step": 23920 }, { "epoch": 0.7306353084911423, "grad_norm": 0.47411873936653137, "learning_rate": 8.429808020063983e-06, "loss": 4.2294, "step": 23921 }, { "epoch": 0.7306658521686011, "grad_norm": 0.4714445471763611, "learning_rate": 8.42801182867597e-06, "loss": 4.2654, "step": 23922 }, { "epoch": 0.7306963958460598, "grad_norm": 0.4705476760864258, "learning_rate": 8.426215789874766e-06, "loss": 4.2308, "step": 23923 }, { "epoch": 0.7307269395235186, "grad_norm": 0.47344669699668884, "learning_rate": 8.42441990367691e-06, "loss": 4.2846, "step": 23924 }, { "epoch": 0.7307574832009774, "grad_norm": 0.4810895025730133, "learning_rate": 8.422624170098944e-06, "loss": 4.2027, "step": 23925 }, { "epoch": 0.7307880268784361, "grad_norm": 0.475790411233902, "learning_rate": 8.42082858915741e-06, "loss": 4.24, "step": 23926 }, { "epoch": 0.7308185705558949, "grad_norm": 0.46382564306259155, "learning_rate": 8.41903316086882e-06, "loss": 4.2871, "step": 23927 }, { "epoch": 0.7308491142333537, "grad_norm": 0.4685308337211609, "learning_rate": 8.417237885249716e-06, "loss": 4.2041, "step": 23928 }, { "epoch": 0.7308796579108124, "grad_norm": 0.46160009503364563, "learning_rate": 8.41544276231664e-06, "loss": 4.2926, "step": 23929 }, { "epoch": 0.7309102015882712, "grad_norm": 0.4623553156852722, "learning_rate": 8.413647792086098e-06, "loss": 4.331, "step": 23930 }, { "epoch": 0.7309407452657299, "grad_norm": 0.4725455343723297, "learning_rate": 8.411852974574639e-06, "loss": 4.1749, "step": 23931 }, { "epoch": 0.7309712889431887, "grad_norm": 0.4742394983768463, "learning_rate": 8.410058309798768e-06, "loss": 4.3231, "step": 23932 }, { "epoch": 0.7310018326206476, "grad_norm": 0.4579562842845917, "learning_rate": 8.408263797775023e-06, "loss": 4.1718, "step": 23933 }, { "epoch": 0.7310323762981062, "grad_norm": 0.472297728061676, "learning_rate": 8.40646943851993e-06, "loss": 4.1638, "step": 23934 }, { "epoch": 0.731062919975565, "grad_norm": 0.4733768403530121, "learning_rate": 8.404675232049996e-06, "loss": 4.207, "step": 23935 }, { "epoch": 0.7310934636530239, "grad_norm": 0.4631389379501343, "learning_rate": 8.402881178381757e-06, "loss": 4.2308, "step": 23936 }, { "epoch": 0.7311240073304826, "grad_norm": 0.47574952244758606, "learning_rate": 8.401087277531718e-06, "loss": 4.2596, "step": 23937 }, { "epoch": 0.7311545510079414, "grad_norm": 0.4676778316497803, "learning_rate": 8.399293529516413e-06, "loss": 4.1621, "step": 23938 }, { "epoch": 0.7311850946854002, "grad_norm": 0.46571826934814453, "learning_rate": 8.397499934352338e-06, "loss": 4.2656, "step": 23939 }, { "epoch": 0.7312156383628589, "grad_norm": 0.46866562962532043, "learning_rate": 8.395706492056025e-06, "loss": 4.2316, "step": 23940 }, { "epoch": 0.7312461820403177, "grad_norm": 0.46794021129608154, "learning_rate": 8.393913202643969e-06, "loss": 4.2989, "step": 23941 }, { "epoch": 0.7312767257177765, "grad_norm": 0.47083455324172974, "learning_rate": 8.392120066132694e-06, "loss": 4.2889, "step": 23942 }, { "epoch": 0.7313072693952352, "grad_norm": 0.47403478622436523, "learning_rate": 8.390327082538718e-06, "loss": 4.2284, "step": 23943 }, { "epoch": 0.731337813072694, "grad_norm": 0.4728371202945709, "learning_rate": 8.388534251878529e-06, "loss": 4.1255, "step": 23944 }, { "epoch": 0.7313683567501528, "grad_norm": 0.46988940238952637, "learning_rate": 8.38674157416865e-06, "loss": 4.2916, "step": 23945 }, { "epoch": 0.7313989004276115, "grad_norm": 0.4806378483772278, "learning_rate": 8.38494904942559e-06, "loss": 4.3029, "step": 23946 }, { "epoch": 0.7314294441050703, "grad_norm": 0.47174254059791565, "learning_rate": 8.383156677665836e-06, "loss": 4.2097, "step": 23947 }, { "epoch": 0.731459987782529, "grad_norm": 0.47377339005470276, "learning_rate": 8.38136445890591e-06, "loss": 4.3153, "step": 23948 }, { "epoch": 0.7314905314599878, "grad_norm": 0.4719827175140381, "learning_rate": 8.3795723931623e-06, "loss": 4.3318, "step": 23949 }, { "epoch": 0.7315210751374466, "grad_norm": 0.467038631439209, "learning_rate": 8.377780480451514e-06, "loss": 4.218, "step": 23950 }, { "epoch": 0.7315516188149053, "grad_norm": 0.4615541696548462, "learning_rate": 8.375988720790054e-06, "loss": 4.2001, "step": 23951 }, { "epoch": 0.7315821624923641, "grad_norm": 0.4639066457748413, "learning_rate": 8.374197114194407e-06, "loss": 4.1323, "step": 23952 }, { "epoch": 0.7316127061698229, "grad_norm": 0.4756593704223633, "learning_rate": 8.372405660681083e-06, "loss": 4.2388, "step": 23953 }, { "epoch": 0.7316432498472816, "grad_norm": 0.4667426347732544, "learning_rate": 8.370614360266568e-06, "loss": 4.2559, "step": 23954 }, { "epoch": 0.7316737935247404, "grad_norm": 0.47009748220443726, "learning_rate": 8.36882321296735e-06, "loss": 4.2334, "step": 23955 }, { "epoch": 0.7317043372021992, "grad_norm": 0.47188466787338257, "learning_rate": 8.367032218799926e-06, "loss": 4.2794, "step": 23956 }, { "epoch": 0.7317348808796579, "grad_norm": 0.4715974032878876, "learning_rate": 8.365241377780797e-06, "loss": 4.3671, "step": 23957 }, { "epoch": 0.7317654245571167, "grad_norm": 0.45628106594085693, "learning_rate": 8.363450689926435e-06, "loss": 4.212, "step": 23958 }, { "epoch": 0.7317959682345755, "grad_norm": 0.47854554653167725, "learning_rate": 8.361660155253337e-06, "loss": 4.2676, "step": 23959 }, { "epoch": 0.7318265119120342, "grad_norm": 0.47149258852005005, "learning_rate": 8.359869773777999e-06, "loss": 4.2511, "step": 23960 }, { "epoch": 0.731857055589493, "grad_norm": 0.4719417989253998, "learning_rate": 8.35807954551688e-06, "loss": 4.2854, "step": 23961 }, { "epoch": 0.7318875992669518, "grad_norm": 0.47184300422668457, "learning_rate": 8.356289470486487e-06, "loss": 4.2506, "step": 23962 }, { "epoch": 0.7319181429444105, "grad_norm": 0.47370481491088867, "learning_rate": 8.354499548703298e-06, "loss": 4.28, "step": 23963 }, { "epoch": 0.7319486866218693, "grad_norm": 0.47226250171661377, "learning_rate": 8.352709780183782e-06, "loss": 4.245, "step": 23964 }, { "epoch": 0.731979230299328, "grad_norm": 0.4658842086791992, "learning_rate": 8.350920164944436e-06, "loss": 4.2213, "step": 23965 }, { "epoch": 0.7320097739767868, "grad_norm": 0.46487686038017273, "learning_rate": 8.34913070300172e-06, "loss": 4.2651, "step": 23966 }, { "epoch": 0.7320403176542456, "grad_norm": 0.46212631464004517, "learning_rate": 8.347341394372119e-06, "loss": 4.2082, "step": 23967 }, { "epoch": 0.7320708613317043, "grad_norm": 0.4872457683086395, "learning_rate": 8.345552239072112e-06, "loss": 4.1893, "step": 23968 }, { "epoch": 0.7321014050091631, "grad_norm": 0.4737580716609955, "learning_rate": 8.343763237118171e-06, "loss": 4.238, "step": 23969 }, { "epoch": 0.7321319486866219, "grad_norm": 0.4818851351737976, "learning_rate": 8.341974388526757e-06, "loss": 4.3907, "step": 23970 }, { "epoch": 0.7321624923640806, "grad_norm": 0.4744907021522522, "learning_rate": 8.34018569331436e-06, "loss": 4.2413, "step": 23971 }, { "epoch": 0.7321930360415394, "grad_norm": 0.4778231084346771, "learning_rate": 8.33839715149743e-06, "loss": 4.2916, "step": 23972 }, { "epoch": 0.7322235797189982, "grad_norm": 0.48280322551727295, "learning_rate": 8.336608763092444e-06, "loss": 4.3226, "step": 23973 }, { "epoch": 0.7322541233964569, "grad_norm": 0.46512365341186523, "learning_rate": 8.334820528115874e-06, "loss": 4.1077, "step": 23974 }, { "epoch": 0.7322846670739157, "grad_norm": 0.46316400170326233, "learning_rate": 8.333032446584175e-06, "loss": 4.2402, "step": 23975 }, { "epoch": 0.7323152107513745, "grad_norm": 0.4721699655056, "learning_rate": 8.331244518513812e-06, "loss": 4.3279, "step": 23976 }, { "epoch": 0.7323457544288332, "grad_norm": 0.4688858091831207, "learning_rate": 8.329456743921263e-06, "loss": 4.1869, "step": 23977 }, { "epoch": 0.732376298106292, "grad_norm": 0.47487759590148926, "learning_rate": 8.327669122822964e-06, "loss": 4.1807, "step": 23978 }, { "epoch": 0.7324068417837508, "grad_norm": 0.4635690450668335, "learning_rate": 8.325881655235393e-06, "loss": 4.1468, "step": 23979 }, { "epoch": 0.7324373854612095, "grad_norm": 0.4724792540073395, "learning_rate": 8.324094341175007e-06, "loss": 4.387, "step": 23980 }, { "epoch": 0.7324679291386683, "grad_norm": 0.4694082736968994, "learning_rate": 8.32230718065825e-06, "loss": 4.2497, "step": 23981 }, { "epoch": 0.732498472816127, "grad_norm": 0.4710516333580017, "learning_rate": 8.320520173701596e-06, "loss": 4.1531, "step": 23982 }, { "epoch": 0.7325290164935858, "grad_norm": 0.4790499210357666, "learning_rate": 8.318733320321478e-06, "loss": 4.3124, "step": 23983 }, { "epoch": 0.7325595601710446, "grad_norm": 0.46265679597854614, "learning_rate": 8.316946620534371e-06, "loss": 4.2087, "step": 23984 }, { "epoch": 0.7325901038485033, "grad_norm": 0.465736448764801, "learning_rate": 8.315160074356704e-06, "loss": 4.239, "step": 23985 }, { "epoch": 0.7326206475259621, "grad_norm": 0.46221640706062317, "learning_rate": 8.313373681804943e-06, "loss": 4.3053, "step": 23986 }, { "epoch": 0.7326511912034209, "grad_norm": 0.45975103974342346, "learning_rate": 8.311587442895525e-06, "loss": 4.2217, "step": 23987 }, { "epoch": 0.7326817348808796, "grad_norm": 0.4893089830875397, "learning_rate": 8.309801357644906e-06, "loss": 4.2027, "step": 23988 }, { "epoch": 0.7327122785583384, "grad_norm": 0.478193074464798, "learning_rate": 8.30801542606952e-06, "loss": 4.2917, "step": 23989 }, { "epoch": 0.7327428222357972, "grad_norm": 0.47149839997291565, "learning_rate": 8.30622964818582e-06, "loss": 4.2054, "step": 23990 }, { "epoch": 0.7327733659132559, "grad_norm": 0.4830859899520874, "learning_rate": 8.304444024010252e-06, "loss": 4.3204, "step": 23991 }, { "epoch": 0.7328039095907147, "grad_norm": 0.4715908169746399, "learning_rate": 8.302658553559248e-06, "loss": 4.3127, "step": 23992 }, { "epoch": 0.7328344532681735, "grad_norm": 0.47349682450294495, "learning_rate": 8.30087323684925e-06, "loss": 4.237, "step": 23993 }, { "epoch": 0.7328649969456322, "grad_norm": 0.48046404123306274, "learning_rate": 8.299088073896705e-06, "loss": 4.2413, "step": 23994 }, { "epoch": 0.732895540623091, "grad_norm": 0.4745393693447113, "learning_rate": 8.297303064718034e-06, "loss": 4.3553, "step": 23995 }, { "epoch": 0.7329260843005498, "grad_norm": 0.47608962655067444, "learning_rate": 8.295518209329681e-06, "loss": 4.2552, "step": 23996 }, { "epoch": 0.7329566279780085, "grad_norm": 0.46734529733657837, "learning_rate": 8.293733507748091e-06, "loss": 4.3036, "step": 23997 }, { "epoch": 0.7329871716554673, "grad_norm": 0.4696367084980011, "learning_rate": 8.291948959989675e-06, "loss": 4.3494, "step": 23998 }, { "epoch": 0.733017715332926, "grad_norm": 0.4889562129974365, "learning_rate": 8.290164566070888e-06, "loss": 4.2178, "step": 23999 }, { "epoch": 0.7330482590103848, "grad_norm": 0.4590594470500946, "learning_rate": 8.288380326008143e-06, "loss": 4.2703, "step": 24000 }, { "epoch": 0.7330788026878436, "grad_norm": 0.4614262282848358, "learning_rate": 8.286596239817867e-06, "loss": 4.2083, "step": 24001 }, { "epoch": 0.7331093463653023, "grad_norm": 0.4618992805480957, "learning_rate": 8.284812307516501e-06, "loss": 4.2832, "step": 24002 }, { "epoch": 0.7331398900427611, "grad_norm": 0.46852007508277893, "learning_rate": 8.28302852912045e-06, "loss": 4.2042, "step": 24003 }, { "epoch": 0.73317043372022, "grad_norm": 0.46285730600357056, "learning_rate": 8.281244904646155e-06, "loss": 4.1122, "step": 24004 }, { "epoch": 0.7332009773976786, "grad_norm": 0.466802179813385, "learning_rate": 8.279461434110041e-06, "loss": 4.2153, "step": 24005 }, { "epoch": 0.7332315210751374, "grad_norm": 0.4590435326099396, "learning_rate": 8.277678117528515e-06, "loss": 4.1924, "step": 24006 }, { "epoch": 0.7332620647525963, "grad_norm": 0.4605759084224701, "learning_rate": 8.275894954918e-06, "loss": 4.2534, "step": 24007 }, { "epoch": 0.733292608430055, "grad_norm": 0.46194231510162354, "learning_rate": 8.274111946294932e-06, "loss": 4.2594, "step": 24008 }, { "epoch": 0.7333231521075138, "grad_norm": 0.47306573390960693, "learning_rate": 8.272329091675704e-06, "loss": 4.341, "step": 24009 }, { "epoch": 0.7333536957849726, "grad_norm": 0.4727664887905121, "learning_rate": 8.270546391076744e-06, "loss": 4.2267, "step": 24010 }, { "epoch": 0.7333842394624313, "grad_norm": 0.46903368830680847, "learning_rate": 8.268763844514471e-06, "loss": 4.2627, "step": 24011 }, { "epoch": 0.7334147831398901, "grad_norm": 0.48475104570388794, "learning_rate": 8.266981452005285e-06, "loss": 4.3109, "step": 24012 }, { "epoch": 0.7334453268173489, "grad_norm": 0.46588653326034546, "learning_rate": 8.265199213565606e-06, "loss": 4.1346, "step": 24013 }, { "epoch": 0.7334758704948076, "grad_norm": 0.4659941792488098, "learning_rate": 8.263417129211848e-06, "loss": 4.2589, "step": 24014 }, { "epoch": 0.7335064141722664, "grad_norm": 0.478135883808136, "learning_rate": 8.261635198960412e-06, "loss": 4.3393, "step": 24015 }, { "epoch": 0.7335369578497251, "grad_norm": 0.4766333997249603, "learning_rate": 8.259853422827702e-06, "loss": 4.2327, "step": 24016 }, { "epoch": 0.7335675015271839, "grad_norm": 0.46996790170669556, "learning_rate": 8.258071800830133e-06, "loss": 4.3031, "step": 24017 }, { "epoch": 0.7335980452046427, "grad_norm": 0.4780906140804291, "learning_rate": 8.256290332984098e-06, "loss": 4.3104, "step": 24018 }, { "epoch": 0.7336285888821014, "grad_norm": 0.47321784496307373, "learning_rate": 8.254509019306017e-06, "loss": 4.2946, "step": 24019 }, { "epoch": 0.7336591325595602, "grad_norm": 0.48472970724105835, "learning_rate": 8.252727859812271e-06, "loss": 4.2446, "step": 24020 }, { "epoch": 0.733689676237019, "grad_norm": 0.4737069606781006, "learning_rate": 8.25094685451927e-06, "loss": 4.2885, "step": 24021 }, { "epoch": 0.7337202199144777, "grad_norm": 0.4770663380622864, "learning_rate": 8.24916600344342e-06, "loss": 4.2185, "step": 24022 }, { "epoch": 0.7337507635919365, "grad_norm": 0.4706471860408783, "learning_rate": 8.247385306601104e-06, "loss": 4.2142, "step": 24023 }, { "epoch": 0.7337813072693953, "grad_norm": 0.4632413387298584, "learning_rate": 8.245604764008726e-06, "loss": 4.1715, "step": 24024 }, { "epoch": 0.733811850946854, "grad_norm": 0.47692281007766724, "learning_rate": 8.243824375682688e-06, "loss": 4.2345, "step": 24025 }, { "epoch": 0.7338423946243128, "grad_norm": 0.47750675678253174, "learning_rate": 8.242044141639362e-06, "loss": 4.236, "step": 24026 }, { "epoch": 0.7338729383017716, "grad_norm": 0.4760810434818268, "learning_rate": 8.240264061895157e-06, "loss": 4.2565, "step": 24027 }, { "epoch": 0.7339034819792303, "grad_norm": 0.46920493245124817, "learning_rate": 8.238484136466463e-06, "loss": 4.3114, "step": 24028 }, { "epoch": 0.7339340256566891, "grad_norm": 0.4777757525444031, "learning_rate": 8.236704365369655e-06, "loss": 4.305, "step": 24029 }, { "epoch": 0.7339645693341478, "grad_norm": 0.46988895535469055, "learning_rate": 8.234924748621136e-06, "loss": 4.2463, "step": 24030 }, { "epoch": 0.7339951130116066, "grad_norm": 0.46813729405403137, "learning_rate": 8.233145286237279e-06, "loss": 4.2793, "step": 24031 }, { "epoch": 0.7340256566890654, "grad_norm": 0.4695281684398651, "learning_rate": 8.231365978234481e-06, "loss": 4.2719, "step": 24032 }, { "epoch": 0.7340562003665241, "grad_norm": 0.47115790843963623, "learning_rate": 8.229586824629117e-06, "loss": 4.1879, "step": 24033 }, { "epoch": 0.7340867440439829, "grad_norm": 0.4667518734931946, "learning_rate": 8.227807825437565e-06, "loss": 4.268, "step": 24034 }, { "epoch": 0.7341172877214417, "grad_norm": 0.4729737639427185, "learning_rate": 8.226028980676207e-06, "loss": 4.2462, "step": 24035 }, { "epoch": 0.7341478313989004, "grad_norm": 0.4726683795452118, "learning_rate": 8.224250290361432e-06, "loss": 4.3254, "step": 24036 }, { "epoch": 0.7341783750763592, "grad_norm": 0.47002485394477844, "learning_rate": 8.2224717545096e-06, "loss": 4.2109, "step": 24037 }, { "epoch": 0.734208918753818, "grad_norm": 0.4636644423007965, "learning_rate": 8.2206933731371e-06, "loss": 4.2779, "step": 24038 }, { "epoch": 0.7342394624312767, "grad_norm": 0.4664846658706665, "learning_rate": 8.218915146260311e-06, "loss": 4.2951, "step": 24039 }, { "epoch": 0.7342700061087355, "grad_norm": 0.46694862842559814, "learning_rate": 8.217137073895589e-06, "loss": 4.2366, "step": 24040 }, { "epoch": 0.7343005497861943, "grad_norm": 0.46171218156814575, "learning_rate": 8.215359156059316e-06, "loss": 4.2829, "step": 24041 }, { "epoch": 0.734331093463653, "grad_norm": 0.46899181604385376, "learning_rate": 8.213581392767868e-06, "loss": 4.1936, "step": 24042 }, { "epoch": 0.7343616371411118, "grad_norm": 0.47795969247817993, "learning_rate": 8.2118037840376e-06, "loss": 4.1729, "step": 24043 }, { "epoch": 0.7343921808185706, "grad_norm": 0.470359206199646, "learning_rate": 8.210026329884885e-06, "loss": 4.2168, "step": 24044 }, { "epoch": 0.7344227244960293, "grad_norm": 0.5353345274925232, "learning_rate": 8.208249030326098e-06, "loss": 4.3049, "step": 24045 }, { "epoch": 0.7344532681734881, "grad_norm": 0.46646350622177124, "learning_rate": 8.206471885377598e-06, "loss": 4.2326, "step": 24046 }, { "epoch": 0.7344838118509468, "grad_norm": 0.4678727090358734, "learning_rate": 8.204694895055738e-06, "loss": 4.3158, "step": 24047 }, { "epoch": 0.7345143555284056, "grad_norm": 0.46338674426078796, "learning_rate": 8.202918059376891e-06, "loss": 4.1865, "step": 24048 }, { "epoch": 0.7345448992058644, "grad_norm": 0.46615102887153625, "learning_rate": 8.201141378357407e-06, "loss": 4.2884, "step": 24049 }, { "epoch": 0.7345754428833231, "grad_norm": 0.4652101397514343, "learning_rate": 8.19936485201366e-06, "loss": 4.2309, "step": 24050 }, { "epoch": 0.7346059865607819, "grad_norm": 0.47728994488716125, "learning_rate": 8.197588480361993e-06, "loss": 4.2283, "step": 24051 }, { "epoch": 0.7346365302382407, "grad_norm": 0.4662138819694519, "learning_rate": 8.195812263418768e-06, "loss": 4.2702, "step": 24052 }, { "epoch": 0.7346670739156994, "grad_norm": 0.47378599643707275, "learning_rate": 8.194036201200345e-06, "loss": 4.2161, "step": 24053 }, { "epoch": 0.7346976175931582, "grad_norm": 0.46354562044143677, "learning_rate": 8.192260293723064e-06, "loss": 4.2213, "step": 24054 }, { "epoch": 0.734728161270617, "grad_norm": 0.4760388135910034, "learning_rate": 8.190484541003283e-06, "loss": 4.2321, "step": 24055 }, { "epoch": 0.7347587049480757, "grad_norm": 0.46770378947257996, "learning_rate": 8.188708943057363e-06, "loss": 4.2175, "step": 24056 }, { "epoch": 0.7347892486255345, "grad_norm": 0.4599699378013611, "learning_rate": 8.186933499901634e-06, "loss": 4.24, "step": 24057 }, { "epoch": 0.7348197923029933, "grad_norm": 0.46754181385040283, "learning_rate": 8.185158211552455e-06, "loss": 4.2249, "step": 24058 }, { "epoch": 0.734850335980452, "grad_norm": 0.4732602834701538, "learning_rate": 8.183383078026175e-06, "loss": 4.2954, "step": 24059 }, { "epoch": 0.7348808796579108, "grad_norm": 0.5158814787864685, "learning_rate": 8.181608099339128e-06, "loss": 4.3117, "step": 24060 }, { "epoch": 0.7349114233353696, "grad_norm": 0.48080411553382874, "learning_rate": 8.179833275507667e-06, "loss": 4.2194, "step": 24061 }, { "epoch": 0.7349419670128283, "grad_norm": 0.4719151556491852, "learning_rate": 8.178058606548122e-06, "loss": 4.233, "step": 24062 }, { "epoch": 0.7349725106902871, "grad_norm": 0.4748857319355011, "learning_rate": 8.176284092476853e-06, "loss": 4.3164, "step": 24063 }, { "epoch": 0.7350030543677458, "grad_norm": 0.4749665856361389, "learning_rate": 8.174509733310182e-06, "loss": 4.3271, "step": 24064 }, { "epoch": 0.7350335980452046, "grad_norm": 0.4774952232837677, "learning_rate": 8.172735529064442e-06, "loss": 4.2697, "step": 24065 }, { "epoch": 0.7350641417226634, "grad_norm": 0.46446195244789124, "learning_rate": 8.170961479755979e-06, "loss": 4.3028, "step": 24066 }, { "epoch": 0.7350946854001221, "grad_norm": 0.47366946935653687, "learning_rate": 8.169187585401133e-06, "loss": 4.2818, "step": 24067 }, { "epoch": 0.7351252290775809, "grad_norm": 0.4838583469390869, "learning_rate": 8.167413846016224e-06, "loss": 4.3747, "step": 24068 }, { "epoch": 0.7351557727550397, "grad_norm": 0.47254037857055664, "learning_rate": 8.16564026161759e-06, "loss": 4.2109, "step": 24069 }, { "epoch": 0.7351863164324984, "grad_norm": 0.4759182929992676, "learning_rate": 8.16386683222157e-06, "loss": 4.2734, "step": 24070 }, { "epoch": 0.7352168601099572, "grad_norm": 0.47507932782173157, "learning_rate": 8.162093557844478e-06, "loss": 4.3541, "step": 24071 }, { "epoch": 0.735247403787416, "grad_norm": 0.4742051064968109, "learning_rate": 8.160320438502645e-06, "loss": 4.1893, "step": 24072 }, { "epoch": 0.7352779474648747, "grad_norm": 0.47582757472991943, "learning_rate": 8.158547474212409e-06, "loss": 4.2652, "step": 24073 }, { "epoch": 0.7353084911423335, "grad_norm": 0.46969741582870483, "learning_rate": 8.156774664990075e-06, "loss": 4.2971, "step": 24074 }, { "epoch": 0.7353390348197923, "grad_norm": 0.46804821491241455, "learning_rate": 8.155002010851979e-06, "loss": 4.2077, "step": 24075 }, { "epoch": 0.735369578497251, "grad_norm": 0.47280922532081604, "learning_rate": 8.153229511814447e-06, "loss": 4.2745, "step": 24076 }, { "epoch": 0.7354001221747098, "grad_norm": 0.4756146967411041, "learning_rate": 8.151457167893786e-06, "loss": 4.1427, "step": 24077 }, { "epoch": 0.7354306658521687, "grad_norm": 0.4897933006286621, "learning_rate": 8.149684979106328e-06, "loss": 4.273, "step": 24078 }, { "epoch": 0.7354612095296273, "grad_norm": 0.484578013420105, "learning_rate": 8.147912945468386e-06, "loss": 4.3389, "step": 24079 }, { "epoch": 0.7354917532070862, "grad_norm": 0.4763006567955017, "learning_rate": 8.146141066996266e-06, "loss": 4.266, "step": 24080 }, { "epoch": 0.7355222968845448, "grad_norm": 0.4757538139820099, "learning_rate": 8.144369343706296e-06, "loss": 4.2612, "step": 24081 }, { "epoch": 0.7355528405620037, "grad_norm": 0.47252723574638367, "learning_rate": 8.142597775614777e-06, "loss": 4.2322, "step": 24082 }, { "epoch": 0.7355833842394625, "grad_norm": 0.4663196802139282, "learning_rate": 8.140826362738027e-06, "loss": 4.2128, "step": 24083 }, { "epoch": 0.7356139279169212, "grad_norm": 0.47357040643692017, "learning_rate": 8.139055105092367e-06, "loss": 4.364, "step": 24084 }, { "epoch": 0.73564447159438, "grad_norm": 0.47211533784866333, "learning_rate": 8.137284002694085e-06, "loss": 4.3597, "step": 24085 }, { "epoch": 0.7356750152718388, "grad_norm": 0.48420289158821106, "learning_rate": 8.135513055559502e-06, "loss": 4.3561, "step": 24086 }, { "epoch": 0.7357055589492975, "grad_norm": 0.46394315361976624, "learning_rate": 8.133742263704927e-06, "loss": 4.0722, "step": 24087 }, { "epoch": 0.7357361026267563, "grad_norm": 0.48320406675338745, "learning_rate": 8.13197162714665e-06, "loss": 4.1583, "step": 24088 }, { "epoch": 0.7357666463042151, "grad_norm": 0.47306588292121887, "learning_rate": 8.130201145900985e-06, "loss": 4.2664, "step": 24089 }, { "epoch": 0.7357971899816738, "grad_norm": 0.4731422960758209, "learning_rate": 8.12843081998424e-06, "loss": 4.1889, "step": 24090 }, { "epoch": 0.7358277336591326, "grad_norm": 0.46695131063461304, "learning_rate": 8.126660649412695e-06, "loss": 4.2292, "step": 24091 }, { "epoch": 0.7358582773365914, "grad_norm": 0.46830302476882935, "learning_rate": 8.124890634202673e-06, "loss": 4.1592, "step": 24092 }, { "epoch": 0.7358888210140501, "grad_norm": 0.46926504373550415, "learning_rate": 8.12312077437045e-06, "loss": 4.2068, "step": 24093 }, { "epoch": 0.7359193646915089, "grad_norm": 0.47460827231407166, "learning_rate": 8.12135106993234e-06, "loss": 4.2593, "step": 24094 }, { "epoch": 0.7359499083689677, "grad_norm": 0.46855366230010986, "learning_rate": 8.119581520904618e-06, "loss": 4.2527, "step": 24095 }, { "epoch": 0.7359804520464264, "grad_norm": 0.47277402877807617, "learning_rate": 8.117812127303599e-06, "loss": 4.2844, "step": 24096 }, { "epoch": 0.7360109957238852, "grad_norm": 0.46628478169441223, "learning_rate": 8.116042889145557e-06, "loss": 4.3362, "step": 24097 }, { "epoch": 0.7360415394013439, "grad_norm": 0.4648450016975403, "learning_rate": 8.114273806446793e-06, "loss": 4.2545, "step": 24098 }, { "epoch": 0.7360720830788027, "grad_norm": 0.47881749272346497, "learning_rate": 8.112504879223584e-06, "loss": 4.2797, "step": 24099 }, { "epoch": 0.7361026267562615, "grad_norm": 0.46871018409729004, "learning_rate": 8.110736107492229e-06, "loss": 4.3251, "step": 24100 }, { "epoch": 0.7361331704337202, "grad_norm": 0.4688240885734558, "learning_rate": 8.108967491269016e-06, "loss": 4.2899, "step": 24101 }, { "epoch": 0.736163714111179, "grad_norm": 0.4791416525840759, "learning_rate": 8.107199030570215e-06, "loss": 4.2891, "step": 24102 }, { "epoch": 0.7361942577886378, "grad_norm": 0.470041424036026, "learning_rate": 8.105430725412119e-06, "loss": 4.2671, "step": 24103 }, { "epoch": 0.7362248014660965, "grad_norm": 0.4676298499107361, "learning_rate": 8.103662575811017e-06, "loss": 4.2104, "step": 24104 }, { "epoch": 0.7362553451435553, "grad_norm": 0.4733259677886963, "learning_rate": 8.10189458178317e-06, "loss": 4.3009, "step": 24105 }, { "epoch": 0.7362858888210141, "grad_norm": 0.5882560014724731, "learning_rate": 8.100126743344871e-06, "loss": 4.2365, "step": 24106 }, { "epoch": 0.7363164324984728, "grad_norm": 0.47027653455734253, "learning_rate": 8.098359060512401e-06, "loss": 4.2671, "step": 24107 }, { "epoch": 0.7363469761759316, "grad_norm": 0.46617045998573303, "learning_rate": 8.09659153330202e-06, "loss": 4.2781, "step": 24108 }, { "epoch": 0.7363775198533904, "grad_norm": 0.4690770208835602, "learning_rate": 8.094824161730021e-06, "loss": 4.3486, "step": 24109 }, { "epoch": 0.7364080635308491, "grad_norm": 0.46774208545684814, "learning_rate": 8.09305694581267e-06, "loss": 4.2097, "step": 24110 }, { "epoch": 0.7364386072083079, "grad_norm": 0.4843626320362091, "learning_rate": 8.091289885566226e-06, "loss": 4.317, "step": 24111 }, { "epoch": 0.7364691508857667, "grad_norm": 0.47014981508255005, "learning_rate": 8.089522981006969e-06, "loss": 4.2763, "step": 24112 }, { "epoch": 0.7364996945632254, "grad_norm": 0.46490955352783203, "learning_rate": 8.087756232151175e-06, "loss": 4.2821, "step": 24113 }, { "epoch": 0.7365302382406842, "grad_norm": 0.4672079086303711, "learning_rate": 8.085989639015101e-06, "loss": 4.3233, "step": 24114 }, { "epoch": 0.7365607819181429, "grad_norm": 0.47063714265823364, "learning_rate": 8.084223201615022e-06, "loss": 4.287, "step": 24115 }, { "epoch": 0.7365913255956017, "grad_norm": 0.47267431020736694, "learning_rate": 8.08245691996719e-06, "loss": 4.2111, "step": 24116 }, { "epoch": 0.7366218692730605, "grad_norm": 0.4967395067214966, "learning_rate": 8.080690794087875e-06, "loss": 4.1925, "step": 24117 }, { "epoch": 0.7366524129505192, "grad_norm": 0.48160865902900696, "learning_rate": 8.078924823993347e-06, "loss": 4.2941, "step": 24118 }, { "epoch": 0.736682956627978, "grad_norm": 0.46543440222740173, "learning_rate": 8.07715900969985e-06, "loss": 4.2399, "step": 24119 }, { "epoch": 0.7367135003054368, "grad_norm": 0.4695415198802948, "learning_rate": 8.075393351223651e-06, "loss": 4.2711, "step": 24120 }, { "epoch": 0.7367440439828955, "grad_norm": 0.4697463810443878, "learning_rate": 8.073627848581014e-06, "loss": 4.2101, "step": 24121 }, { "epoch": 0.7367745876603543, "grad_norm": 0.4683433175086975, "learning_rate": 8.071862501788182e-06, "loss": 4.2702, "step": 24122 }, { "epoch": 0.7368051313378131, "grad_norm": 0.4787563979625702, "learning_rate": 8.070097310861413e-06, "loss": 4.1433, "step": 24123 }, { "epoch": 0.7368356750152718, "grad_norm": 0.4739190638065338, "learning_rate": 8.068332275816973e-06, "loss": 4.2699, "step": 24124 }, { "epoch": 0.7368662186927306, "grad_norm": 0.4798119068145752, "learning_rate": 8.066567396671104e-06, "loss": 4.3384, "step": 24125 }, { "epoch": 0.7368967623701894, "grad_norm": 0.4724733829498291, "learning_rate": 8.064802673440045e-06, "loss": 4.2997, "step": 24126 }, { "epoch": 0.7369273060476481, "grad_norm": 0.47416162490844727, "learning_rate": 8.063038106140063e-06, "loss": 4.2928, "step": 24127 }, { "epoch": 0.7369578497251069, "grad_norm": 0.4745464622974396, "learning_rate": 8.06127369478739e-06, "loss": 4.26, "step": 24128 }, { "epoch": 0.7369883934025657, "grad_norm": 0.5029509663581848, "learning_rate": 8.05950943939828e-06, "loss": 4.3335, "step": 24129 }, { "epoch": 0.7370189370800244, "grad_norm": 0.4697301983833313, "learning_rate": 8.057745339988985e-06, "loss": 4.2302, "step": 24130 }, { "epoch": 0.7370494807574832, "grad_norm": 0.46995919942855835, "learning_rate": 8.055981396575727e-06, "loss": 4.2916, "step": 24131 }, { "epoch": 0.7370800244349419, "grad_norm": 0.4703696072101593, "learning_rate": 8.054217609174772e-06, "loss": 4.2936, "step": 24132 }, { "epoch": 0.7371105681124007, "grad_norm": 0.4751087725162506, "learning_rate": 8.052453977802338e-06, "loss": 4.2416, "step": 24133 }, { "epoch": 0.7371411117898595, "grad_norm": 0.46731844544410706, "learning_rate": 8.050690502474676e-06, "loss": 4.3627, "step": 24134 }, { "epoch": 0.7371716554673182, "grad_norm": 0.4757908284664154, "learning_rate": 8.048927183208026e-06, "loss": 4.2622, "step": 24135 }, { "epoch": 0.737202199144777, "grad_norm": 0.4759707748889923, "learning_rate": 8.047164020018615e-06, "loss": 4.2375, "step": 24136 }, { "epoch": 0.7372327428222358, "grad_norm": 0.47257691621780396, "learning_rate": 8.045401012922679e-06, "loss": 4.2252, "step": 24137 }, { "epoch": 0.7372632864996945, "grad_norm": 0.4617883265018463, "learning_rate": 8.043638161936461e-06, "loss": 4.254, "step": 24138 }, { "epoch": 0.7372938301771533, "grad_norm": 0.48794156312942505, "learning_rate": 8.041875467076176e-06, "loss": 4.2244, "step": 24139 }, { "epoch": 0.7373243738546121, "grad_norm": 0.48170605301856995, "learning_rate": 8.040112928358074e-06, "loss": 4.2698, "step": 24140 }, { "epoch": 0.7373549175320708, "grad_norm": 0.4796472489833832, "learning_rate": 8.038350545798359e-06, "loss": 4.2816, "step": 24141 }, { "epoch": 0.7373854612095296, "grad_norm": 0.4933841824531555, "learning_rate": 8.036588319413283e-06, "loss": 4.3867, "step": 24142 }, { "epoch": 0.7374160048869884, "grad_norm": 0.46763211488723755, "learning_rate": 8.034826249219049e-06, "loss": 4.1204, "step": 24143 }, { "epoch": 0.7374465485644471, "grad_norm": 0.4752539098262787, "learning_rate": 8.033064335231904e-06, "loss": 4.2389, "step": 24144 }, { "epoch": 0.7374770922419059, "grad_norm": 0.4721072018146515, "learning_rate": 8.031302577468047e-06, "loss": 4.2348, "step": 24145 }, { "epoch": 0.7375076359193647, "grad_norm": 0.46839040517807007, "learning_rate": 8.029540975943718e-06, "loss": 4.2704, "step": 24146 }, { "epoch": 0.7375381795968234, "grad_norm": 0.47658970952033997, "learning_rate": 8.02777953067513e-06, "loss": 4.246, "step": 24147 }, { "epoch": 0.7375687232742822, "grad_norm": 0.46929267048835754, "learning_rate": 8.026018241678502e-06, "loss": 4.3141, "step": 24148 }, { "epoch": 0.7375992669517409, "grad_norm": 0.4656931757926941, "learning_rate": 8.024257108970055e-06, "loss": 4.1446, "step": 24149 }, { "epoch": 0.7376298106291997, "grad_norm": 0.47671037912368774, "learning_rate": 8.022496132565993e-06, "loss": 4.2133, "step": 24150 }, { "epoch": 0.7376603543066585, "grad_norm": 0.4669799506664276, "learning_rate": 8.020735312482538e-06, "loss": 4.3067, "step": 24151 }, { "epoch": 0.7376908979841172, "grad_norm": 0.48217377066612244, "learning_rate": 8.018974648735913e-06, "loss": 4.2272, "step": 24152 }, { "epoch": 0.737721441661576, "grad_norm": 0.48228883743286133, "learning_rate": 8.017214141342311e-06, "loss": 4.326, "step": 24153 }, { "epoch": 0.7377519853390349, "grad_norm": 0.4811781048774719, "learning_rate": 8.015453790317948e-06, "loss": 4.1688, "step": 24154 }, { "epoch": 0.7377825290164935, "grad_norm": 0.47534099221229553, "learning_rate": 8.013693595679042e-06, "loss": 4.2491, "step": 24155 }, { "epoch": 0.7378130726939524, "grad_norm": 0.4709189832210541, "learning_rate": 8.011933557441795e-06, "loss": 4.3233, "step": 24156 }, { "epoch": 0.7378436163714112, "grad_norm": 0.4743463695049286, "learning_rate": 8.010173675622401e-06, "loss": 4.312, "step": 24157 }, { "epoch": 0.7378741600488699, "grad_norm": 0.4704485833644867, "learning_rate": 8.008413950237081e-06, "loss": 4.2838, "step": 24158 }, { "epoch": 0.7379047037263287, "grad_norm": 0.47286343574523926, "learning_rate": 8.006654381302024e-06, "loss": 4.3405, "step": 24159 }, { "epoch": 0.7379352474037875, "grad_norm": 0.4640336036682129, "learning_rate": 8.004894968833434e-06, "loss": 4.3069, "step": 24160 }, { "epoch": 0.7379657910812462, "grad_norm": 0.47661834955215454, "learning_rate": 8.003135712847523e-06, "loss": 4.3111, "step": 24161 }, { "epoch": 0.737996334758705, "grad_norm": 0.46372225880622864, "learning_rate": 8.001376613360473e-06, "loss": 4.214, "step": 24162 }, { "epoch": 0.7380268784361638, "grad_norm": 0.4596109390258789, "learning_rate": 7.99961767038849e-06, "loss": 4.2536, "step": 24163 }, { "epoch": 0.7380574221136225, "grad_norm": 0.471897691488266, "learning_rate": 7.997858883947773e-06, "loss": 4.2804, "step": 24164 }, { "epoch": 0.7380879657910813, "grad_norm": 0.4633316099643707, "learning_rate": 7.996100254054506e-06, "loss": 4.1927, "step": 24165 }, { "epoch": 0.73811850946854, "grad_norm": 0.4716680645942688, "learning_rate": 7.994341780724894e-06, "loss": 4.3776, "step": 24166 }, { "epoch": 0.7381490531459988, "grad_norm": 0.47036194801330566, "learning_rate": 7.99258346397511e-06, "loss": 4.2233, "step": 24167 }, { "epoch": 0.7381795968234576, "grad_norm": 0.47730088233947754, "learning_rate": 7.990825303821357e-06, "loss": 4.1885, "step": 24168 }, { "epoch": 0.7382101405009163, "grad_norm": 0.4710300862789154, "learning_rate": 7.989067300279826e-06, "loss": 4.3307, "step": 24169 }, { "epoch": 0.7382406841783751, "grad_norm": 0.4788055717945099, "learning_rate": 7.987309453366689e-06, "loss": 4.2254, "step": 24170 }, { "epoch": 0.7382712278558339, "grad_norm": 0.46524855494499207, "learning_rate": 7.985551763098153e-06, "loss": 4.2486, "step": 24171 }, { "epoch": 0.7383017715332926, "grad_norm": 0.4824368357658386, "learning_rate": 7.983794229490382e-06, "loss": 4.2249, "step": 24172 }, { "epoch": 0.7383323152107514, "grad_norm": 0.47705453634262085, "learning_rate": 7.982036852559574e-06, "loss": 4.1788, "step": 24173 }, { "epoch": 0.7383628588882102, "grad_norm": 0.47567975521087646, "learning_rate": 7.98027963232189e-06, "loss": 4.3026, "step": 24174 }, { "epoch": 0.7383934025656689, "grad_norm": 0.4770258963108063, "learning_rate": 7.978522568793537e-06, "loss": 4.2656, "step": 24175 }, { "epoch": 0.7384239462431277, "grad_norm": 0.47391918301582336, "learning_rate": 7.976765661990665e-06, "loss": 4.3367, "step": 24176 }, { "epoch": 0.7384544899205865, "grad_norm": 0.5002647042274475, "learning_rate": 7.975008911929465e-06, "loss": 4.2496, "step": 24177 }, { "epoch": 0.7384850335980452, "grad_norm": 0.4646022617816925, "learning_rate": 7.973252318626123e-06, "loss": 4.2844, "step": 24178 }, { "epoch": 0.738515577275504, "grad_norm": 0.4737386107444763, "learning_rate": 7.97149588209679e-06, "loss": 4.3072, "step": 24179 }, { "epoch": 0.7385461209529627, "grad_norm": 0.47194066643714905, "learning_rate": 7.96973960235766e-06, "loss": 4.2344, "step": 24180 }, { "epoch": 0.7385766646304215, "grad_norm": 0.4695035219192505, "learning_rate": 7.96798347942488e-06, "loss": 4.2258, "step": 24181 }, { "epoch": 0.7386072083078803, "grad_norm": 0.4795243442058563, "learning_rate": 7.96622751331464e-06, "loss": 4.2544, "step": 24182 }, { "epoch": 0.738637751985339, "grad_norm": 0.4646989405155182, "learning_rate": 7.964471704043105e-06, "loss": 4.2445, "step": 24183 }, { "epoch": 0.7386682956627978, "grad_norm": 0.4737120568752289, "learning_rate": 7.962716051626429e-06, "loss": 4.2256, "step": 24184 }, { "epoch": 0.7386988393402566, "grad_norm": 0.4729762375354767, "learning_rate": 7.960960556080787e-06, "loss": 4.2595, "step": 24185 }, { "epoch": 0.7387293830177153, "grad_norm": 0.466786652803421, "learning_rate": 7.959205217422353e-06, "loss": 4.2565, "step": 24186 }, { "epoch": 0.7387599266951741, "grad_norm": 0.47561168670654297, "learning_rate": 7.957450035667266e-06, "loss": 4.1665, "step": 24187 }, { "epoch": 0.7387904703726329, "grad_norm": 0.4681379795074463, "learning_rate": 7.95569501083171e-06, "loss": 4.2123, "step": 24188 }, { "epoch": 0.7388210140500916, "grad_norm": 0.46384188532829285, "learning_rate": 7.953940142931832e-06, "loss": 4.2302, "step": 24189 }, { "epoch": 0.7388515577275504, "grad_norm": 0.4634740352630615, "learning_rate": 7.952185431983783e-06, "loss": 4.2402, "step": 24190 }, { "epoch": 0.7388821014050092, "grad_norm": 0.4824027419090271, "learning_rate": 7.95043087800373e-06, "loss": 4.214, "step": 24191 }, { "epoch": 0.7389126450824679, "grad_norm": 0.4597204625606537, "learning_rate": 7.94867648100783e-06, "loss": 4.2039, "step": 24192 }, { "epoch": 0.7389431887599267, "grad_norm": 0.4776986837387085, "learning_rate": 7.946922241012228e-06, "loss": 4.1659, "step": 24193 }, { "epoch": 0.7389737324373855, "grad_norm": 0.47482800483703613, "learning_rate": 7.945168158033079e-06, "loss": 4.3356, "step": 24194 }, { "epoch": 0.7390042761148442, "grad_norm": 0.48043566942214966, "learning_rate": 7.943414232086544e-06, "loss": 4.3897, "step": 24195 }, { "epoch": 0.739034819792303, "grad_norm": 0.46823176741600037, "learning_rate": 7.941660463188755e-06, "loss": 4.1569, "step": 24196 }, { "epoch": 0.7390653634697617, "grad_norm": 0.47657185792922974, "learning_rate": 7.939906851355878e-06, "loss": 4.219, "step": 24197 }, { "epoch": 0.7390959071472205, "grad_norm": 0.469280481338501, "learning_rate": 7.938153396604039e-06, "loss": 4.2043, "step": 24198 }, { "epoch": 0.7391264508246793, "grad_norm": 0.4722101092338562, "learning_rate": 7.936400098949399e-06, "loss": 4.3108, "step": 24199 }, { "epoch": 0.739156994502138, "grad_norm": 0.4769543409347534, "learning_rate": 7.934646958408101e-06, "loss": 4.2777, "step": 24200 }, { "epoch": 0.7391875381795968, "grad_norm": 0.46579796075820923, "learning_rate": 7.932893974996275e-06, "loss": 4.306, "step": 24201 }, { "epoch": 0.7392180818570556, "grad_norm": 0.47651639580726624, "learning_rate": 7.931141148730078e-06, "loss": 4.3099, "step": 24202 }, { "epoch": 0.7392486255345143, "grad_norm": 0.47018471360206604, "learning_rate": 7.929388479625633e-06, "loss": 4.3116, "step": 24203 }, { "epoch": 0.7392791692119731, "grad_norm": 0.47272729873657227, "learning_rate": 7.92763596769909e-06, "loss": 4.2693, "step": 24204 }, { "epoch": 0.7393097128894319, "grad_norm": 0.49209633469581604, "learning_rate": 7.925883612966575e-06, "loss": 4.2901, "step": 24205 }, { "epoch": 0.7393402565668906, "grad_norm": 0.48092225193977356, "learning_rate": 7.924131415444235e-06, "loss": 4.1295, "step": 24206 }, { "epoch": 0.7393708002443494, "grad_norm": 0.46516814827919006, "learning_rate": 7.92237937514819e-06, "loss": 4.2245, "step": 24207 }, { "epoch": 0.7394013439218082, "grad_norm": 0.46668896079063416, "learning_rate": 7.920627492094579e-06, "loss": 4.3005, "step": 24208 }, { "epoch": 0.7394318875992669, "grad_norm": 0.4765765964984894, "learning_rate": 7.918875766299538e-06, "loss": 4.3251, "step": 24209 }, { "epoch": 0.7394624312767257, "grad_norm": 0.47470590472221375, "learning_rate": 7.917124197779183e-06, "loss": 4.3095, "step": 24210 }, { "epoch": 0.7394929749541845, "grad_norm": 0.4840443432331085, "learning_rate": 7.915372786549649e-06, "loss": 4.2785, "step": 24211 }, { "epoch": 0.7395235186316432, "grad_norm": 0.46575772762298584, "learning_rate": 7.91362153262707e-06, "loss": 4.1843, "step": 24212 }, { "epoch": 0.739554062309102, "grad_norm": 0.45905211567878723, "learning_rate": 7.911870436027553e-06, "loss": 4.1945, "step": 24213 }, { "epoch": 0.7395846059865607, "grad_norm": 0.4754701554775238, "learning_rate": 7.91011949676724e-06, "loss": 4.2699, "step": 24214 }, { "epoch": 0.7396151496640195, "grad_norm": 0.47603416442871094, "learning_rate": 7.908368714862236e-06, "loss": 4.1041, "step": 24215 }, { "epoch": 0.7396456933414783, "grad_norm": 0.4752952754497528, "learning_rate": 7.906618090328667e-06, "loss": 4.257, "step": 24216 }, { "epoch": 0.739676237018937, "grad_norm": 0.4763863682746887, "learning_rate": 7.904867623182662e-06, "loss": 4.2137, "step": 24217 }, { "epoch": 0.7397067806963958, "grad_norm": 0.4794788360595703, "learning_rate": 7.903117313440326e-06, "loss": 4.2032, "step": 24218 }, { "epoch": 0.7397373243738546, "grad_norm": 0.4688839614391327, "learning_rate": 7.90136716111778e-06, "loss": 4.245, "step": 24219 }, { "epoch": 0.7397678680513133, "grad_norm": 0.4803043603897095, "learning_rate": 7.899617166231144e-06, "loss": 4.2581, "step": 24220 }, { "epoch": 0.7397984117287721, "grad_norm": 0.48372355103492737, "learning_rate": 7.897867328796515e-06, "loss": 4.1435, "step": 24221 }, { "epoch": 0.739828955406231, "grad_norm": 0.47343140840530396, "learning_rate": 7.896117648830015e-06, "loss": 4.1823, "step": 24222 }, { "epoch": 0.7398594990836896, "grad_norm": 0.4777047336101532, "learning_rate": 7.894368126347762e-06, "loss": 4.2559, "step": 24223 }, { "epoch": 0.7398900427611484, "grad_norm": 0.46317657828330994, "learning_rate": 7.892618761365846e-06, "loss": 4.2194, "step": 24224 }, { "epoch": 0.7399205864386073, "grad_norm": 0.473625510931015, "learning_rate": 7.890869553900387e-06, "loss": 4.3011, "step": 24225 }, { "epoch": 0.739951130116066, "grad_norm": 0.48087456822395325, "learning_rate": 7.889120503967499e-06, "loss": 4.3189, "step": 24226 }, { "epoch": 0.7399816737935248, "grad_norm": 0.468362420797348, "learning_rate": 7.887371611583264e-06, "loss": 4.2141, "step": 24227 }, { "epoch": 0.7400122174709836, "grad_norm": 0.47156259417533875, "learning_rate": 7.885622876763798e-06, "loss": 4.2164, "step": 24228 }, { "epoch": 0.7400427611484423, "grad_norm": 0.4837450385093689, "learning_rate": 7.883874299525209e-06, "loss": 4.314, "step": 24229 }, { "epoch": 0.7400733048259011, "grad_norm": 0.4588444232940674, "learning_rate": 7.882125879883584e-06, "loss": 4.1245, "step": 24230 }, { "epoch": 0.7401038485033598, "grad_norm": 0.4797120988368988, "learning_rate": 7.880377617855034e-06, "loss": 4.2845, "step": 24231 }, { "epoch": 0.7401343921808186, "grad_norm": 0.4697398841381073, "learning_rate": 7.87862951345564e-06, "loss": 4.2915, "step": 24232 }, { "epoch": 0.7401649358582774, "grad_norm": 0.4762457013130188, "learning_rate": 7.876881566701509e-06, "loss": 4.2896, "step": 24233 }, { "epoch": 0.7401954795357361, "grad_norm": 0.47129693627357483, "learning_rate": 7.87513377760874e-06, "loss": 4.2872, "step": 24234 }, { "epoch": 0.7402260232131949, "grad_norm": 0.4820856750011444, "learning_rate": 7.873386146193418e-06, "loss": 4.3043, "step": 24235 }, { "epoch": 0.7402565668906537, "grad_norm": 0.4695911705493927, "learning_rate": 7.871638672471629e-06, "loss": 4.2796, "step": 24236 }, { "epoch": 0.7402871105681124, "grad_norm": 0.47892406582832336, "learning_rate": 7.869891356459477e-06, "loss": 4.2176, "step": 24237 }, { "epoch": 0.7403176542455712, "grad_norm": 0.4668828547000885, "learning_rate": 7.868144198173035e-06, "loss": 4.2714, "step": 24238 }, { "epoch": 0.74034819792303, "grad_norm": 0.4710730314254761, "learning_rate": 7.866397197628397e-06, "loss": 4.1942, "step": 24239 }, { "epoch": 0.7403787416004887, "grad_norm": 0.46584615111351013, "learning_rate": 7.864650354841657e-06, "loss": 4.2949, "step": 24240 }, { "epoch": 0.7404092852779475, "grad_norm": 0.4610357880592346, "learning_rate": 7.862903669828886e-06, "loss": 4.3018, "step": 24241 }, { "epoch": 0.7404398289554063, "grad_norm": 0.47602131962776184, "learning_rate": 7.861157142606168e-06, "loss": 4.2183, "step": 24242 }, { "epoch": 0.740470372632865, "grad_norm": 0.4788828492164612, "learning_rate": 7.8594107731896e-06, "loss": 4.1716, "step": 24243 }, { "epoch": 0.7405009163103238, "grad_norm": 0.6287298798561096, "learning_rate": 7.857664561595237e-06, "loss": 4.2154, "step": 24244 }, { "epoch": 0.7405314599877826, "grad_norm": 0.4726029336452484, "learning_rate": 7.855918507839174e-06, "loss": 4.2576, "step": 24245 }, { "epoch": 0.7405620036652413, "grad_norm": 0.4787428081035614, "learning_rate": 7.854172611937491e-06, "loss": 4.3004, "step": 24246 }, { "epoch": 0.7405925473427001, "grad_norm": 0.47001829743385315, "learning_rate": 7.852426873906249e-06, "loss": 4.2384, "step": 24247 }, { "epoch": 0.7406230910201588, "grad_norm": 0.45948895812034607, "learning_rate": 7.850681293761537e-06, "loss": 4.2205, "step": 24248 }, { "epoch": 0.7406536346976176, "grad_norm": 0.46703851222991943, "learning_rate": 7.848935871519409e-06, "loss": 4.2169, "step": 24249 }, { "epoch": 0.7406841783750764, "grad_norm": 0.49950364232063293, "learning_rate": 7.847190607195955e-06, "loss": 4.2043, "step": 24250 }, { "epoch": 0.7407147220525351, "grad_norm": 0.4848105311393738, "learning_rate": 7.84544550080723e-06, "loss": 4.3425, "step": 24251 }, { "epoch": 0.7407452657299939, "grad_norm": 0.4748460650444031, "learning_rate": 7.843700552369318e-06, "loss": 4.2001, "step": 24252 }, { "epoch": 0.7407758094074527, "grad_norm": 0.48439547419548035, "learning_rate": 7.841955761898264e-06, "loss": 4.2904, "step": 24253 }, { "epoch": 0.7408063530849114, "grad_norm": 0.4756496250629425, "learning_rate": 7.840211129410154e-06, "loss": 4.2234, "step": 24254 }, { "epoch": 0.7408368967623702, "grad_norm": 0.4830014109611511, "learning_rate": 7.838466654921036e-06, "loss": 4.3397, "step": 24255 }, { "epoch": 0.740867440439829, "grad_norm": 0.47094786167144775, "learning_rate": 7.83672233844698e-06, "loss": 4.278, "step": 24256 }, { "epoch": 0.7408979841172877, "grad_norm": 0.47607937455177307, "learning_rate": 7.834978180004054e-06, "loss": 4.2909, "step": 24257 }, { "epoch": 0.7409285277947465, "grad_norm": 0.4737975001335144, "learning_rate": 7.833234179608298e-06, "loss": 4.2607, "step": 24258 }, { "epoch": 0.7409590714722053, "grad_norm": 0.4808282256126404, "learning_rate": 7.831490337275784e-06, "loss": 4.3356, "step": 24259 }, { "epoch": 0.740989615149664, "grad_norm": 0.47316476702690125, "learning_rate": 7.829746653022575e-06, "loss": 4.3126, "step": 24260 }, { "epoch": 0.7410201588271228, "grad_norm": 0.4743880033493042, "learning_rate": 7.828003126864705e-06, "loss": 4.2874, "step": 24261 }, { "epoch": 0.7410507025045816, "grad_norm": 0.48704442381858826, "learning_rate": 7.826259758818241e-06, "loss": 4.1768, "step": 24262 }, { "epoch": 0.7410812461820403, "grad_norm": 0.46812447905540466, "learning_rate": 7.82451654889924e-06, "loss": 4.1923, "step": 24263 }, { "epoch": 0.7411117898594991, "grad_norm": 0.4661746621131897, "learning_rate": 7.822773497123739e-06, "loss": 4.2583, "step": 24264 }, { "epoch": 0.7411423335369578, "grad_norm": 0.47730615735054016, "learning_rate": 7.821030603507804e-06, "loss": 4.1943, "step": 24265 }, { "epoch": 0.7411728772144166, "grad_norm": 0.47219082713127136, "learning_rate": 7.819287868067468e-06, "loss": 4.2285, "step": 24266 }, { "epoch": 0.7412034208918754, "grad_norm": 0.4764057695865631, "learning_rate": 7.817545290818778e-06, "loss": 4.3307, "step": 24267 }, { "epoch": 0.7412339645693341, "grad_norm": 0.4659801721572876, "learning_rate": 7.81580287177779e-06, "loss": 4.3012, "step": 24268 }, { "epoch": 0.7412645082467929, "grad_norm": 0.47625863552093506, "learning_rate": 7.81406061096053e-06, "loss": 4.3214, "step": 24269 }, { "epoch": 0.7412950519242517, "grad_norm": 0.4670340418815613, "learning_rate": 7.812318508383055e-06, "loss": 4.2658, "step": 24270 }, { "epoch": 0.7413255956017104, "grad_norm": 0.48196548223495483, "learning_rate": 7.810576564061403e-06, "loss": 4.128, "step": 24271 }, { "epoch": 0.7413561392791692, "grad_norm": 0.4854242503643036, "learning_rate": 7.808834778011605e-06, "loss": 4.3133, "step": 24272 }, { "epoch": 0.741386682956628, "grad_norm": 0.47996070981025696, "learning_rate": 7.807093150249704e-06, "loss": 4.2813, "step": 24273 }, { "epoch": 0.7414172266340867, "grad_norm": 0.47676482796669006, "learning_rate": 7.805351680791744e-06, "loss": 4.2813, "step": 24274 }, { "epoch": 0.7414477703115455, "grad_norm": 0.4809302091598511, "learning_rate": 7.803610369653743e-06, "loss": 4.2858, "step": 24275 }, { "epoch": 0.7414783139890043, "grad_norm": 0.4746374189853668, "learning_rate": 7.801869216851745e-06, "loss": 4.2291, "step": 24276 }, { "epoch": 0.741508857666463, "grad_norm": 0.47893548011779785, "learning_rate": 7.800128222401787e-06, "loss": 4.1779, "step": 24277 }, { "epoch": 0.7415394013439218, "grad_norm": 0.47126615047454834, "learning_rate": 7.79838738631988e-06, "loss": 4.1724, "step": 24278 }, { "epoch": 0.7415699450213806, "grad_norm": 0.47215819358825684, "learning_rate": 7.796646708622068e-06, "loss": 4.3086, "step": 24279 }, { "epoch": 0.7416004886988393, "grad_norm": 0.47901996970176697, "learning_rate": 7.794906189324383e-06, "loss": 4.1656, "step": 24280 }, { "epoch": 0.7416310323762981, "grad_norm": 0.4831964671611786, "learning_rate": 7.793165828442842e-06, "loss": 4.2466, "step": 24281 }, { "epoch": 0.7416615760537568, "grad_norm": 0.4616754949092865, "learning_rate": 7.791425625993462e-06, "loss": 4.2147, "step": 24282 }, { "epoch": 0.7416921197312156, "grad_norm": 0.47506967186927795, "learning_rate": 7.78968558199228e-06, "loss": 4.2721, "step": 24283 }, { "epoch": 0.7417226634086744, "grad_norm": 0.4728538990020752, "learning_rate": 7.787945696455306e-06, "loss": 4.2769, "step": 24284 }, { "epoch": 0.7417532070861331, "grad_norm": 0.47641369700431824, "learning_rate": 7.786205969398575e-06, "loss": 4.2658, "step": 24285 }, { "epoch": 0.7417837507635919, "grad_norm": 0.47322940826416016, "learning_rate": 7.784466400838086e-06, "loss": 4.2971, "step": 24286 }, { "epoch": 0.7418142944410507, "grad_norm": 0.4796505570411682, "learning_rate": 7.782726990789865e-06, "loss": 4.3586, "step": 24287 }, { "epoch": 0.7418448381185094, "grad_norm": 0.47268110513687134, "learning_rate": 7.780987739269941e-06, "loss": 4.263, "step": 24288 }, { "epoch": 0.7418753817959682, "grad_norm": 0.47071191668510437, "learning_rate": 7.779248646294304e-06, "loss": 4.3471, "step": 24289 }, { "epoch": 0.741905925473427, "grad_norm": 0.4710092842578888, "learning_rate": 7.77750971187898e-06, "loss": 4.2299, "step": 24290 }, { "epoch": 0.7419364691508857, "grad_norm": 0.4757286012172699, "learning_rate": 7.775770936039986e-06, "loss": 4.2272, "step": 24291 }, { "epoch": 0.7419670128283445, "grad_norm": 0.4779282510280609, "learning_rate": 7.774032318793318e-06, "loss": 4.1773, "step": 24292 }, { "epoch": 0.7419975565058033, "grad_norm": 0.46458864212036133, "learning_rate": 7.772293860154991e-06, "loss": 4.2678, "step": 24293 }, { "epoch": 0.742028100183262, "grad_norm": 0.4739830493927002, "learning_rate": 7.770555560141021e-06, "loss": 4.2156, "step": 24294 }, { "epoch": 0.7420586438607208, "grad_norm": 0.4754260778427124, "learning_rate": 7.768817418767393e-06, "loss": 4.2543, "step": 24295 }, { "epoch": 0.7420891875381797, "grad_norm": 0.4773813784122467, "learning_rate": 7.767079436050133e-06, "loss": 4.1952, "step": 24296 }, { "epoch": 0.7421197312156383, "grad_norm": 0.4707504212856293, "learning_rate": 7.765341612005225e-06, "loss": 4.2207, "step": 24297 }, { "epoch": 0.7421502748930972, "grad_norm": 0.47655966877937317, "learning_rate": 7.763603946648687e-06, "loss": 4.2388, "step": 24298 }, { "epoch": 0.7421808185705558, "grad_norm": 0.47552570700645447, "learning_rate": 7.761866439996507e-06, "loss": 4.2764, "step": 24299 }, { "epoch": 0.7422113622480146, "grad_norm": 0.4774915277957916, "learning_rate": 7.76012909206468e-06, "loss": 4.3469, "step": 24300 }, { "epoch": 0.7422419059254735, "grad_norm": 0.4848703444004059, "learning_rate": 7.758391902869209e-06, "loss": 4.2898, "step": 24301 }, { "epoch": 0.7422724496029321, "grad_norm": 0.4754396975040436, "learning_rate": 7.756654872426091e-06, "loss": 4.3363, "step": 24302 }, { "epoch": 0.742302993280391, "grad_norm": 0.46796709299087524, "learning_rate": 7.754918000751315e-06, "loss": 4.1902, "step": 24303 }, { "epoch": 0.7423335369578498, "grad_norm": 0.4733545780181885, "learning_rate": 7.753181287860873e-06, "loss": 4.1411, "step": 24304 }, { "epoch": 0.7423640806353085, "grad_norm": 0.4871024191379547, "learning_rate": 7.751444733770768e-06, "loss": 4.2312, "step": 24305 }, { "epoch": 0.7423946243127673, "grad_norm": 0.459383100271225, "learning_rate": 7.74970833849697e-06, "loss": 4.2568, "step": 24306 }, { "epoch": 0.7424251679902261, "grad_norm": 0.4797091782093048, "learning_rate": 7.747972102055476e-06, "loss": 4.2664, "step": 24307 }, { "epoch": 0.7424557116676848, "grad_norm": 0.4762576222419739, "learning_rate": 7.746236024462283e-06, "loss": 4.1956, "step": 24308 }, { "epoch": 0.7424862553451436, "grad_norm": 0.47347262501716614, "learning_rate": 7.744500105733358e-06, "loss": 4.2094, "step": 24309 }, { "epoch": 0.7425167990226024, "grad_norm": 0.4794597923755646, "learning_rate": 7.74276434588469e-06, "loss": 4.249, "step": 24310 }, { "epoch": 0.7425473427000611, "grad_norm": 0.4736027121543884, "learning_rate": 7.741028744932274e-06, "loss": 4.3361, "step": 24311 }, { "epoch": 0.7425778863775199, "grad_norm": 0.4714619517326355, "learning_rate": 7.739293302892078e-06, "loss": 4.2602, "step": 24312 }, { "epoch": 0.7426084300549787, "grad_norm": 0.4716343283653259, "learning_rate": 7.737558019780075e-06, "loss": 4.2327, "step": 24313 }, { "epoch": 0.7426389737324374, "grad_norm": 0.47802042961120605, "learning_rate": 7.73582289561226e-06, "loss": 4.2919, "step": 24314 }, { "epoch": 0.7426695174098962, "grad_norm": 0.47805866599082947, "learning_rate": 7.734087930404593e-06, "loss": 4.2665, "step": 24315 }, { "epoch": 0.7427000610873549, "grad_norm": 0.472422331571579, "learning_rate": 7.732353124173062e-06, "loss": 4.2699, "step": 24316 }, { "epoch": 0.7427306047648137, "grad_norm": 0.4816410541534424, "learning_rate": 7.730618476933627e-06, "loss": 4.2967, "step": 24317 }, { "epoch": 0.7427611484422725, "grad_norm": 0.47909000515937805, "learning_rate": 7.728883988702265e-06, "loss": 4.2489, "step": 24318 }, { "epoch": 0.7427916921197312, "grad_norm": 0.4727303981781006, "learning_rate": 7.727149659494959e-06, "loss": 4.2157, "step": 24319 }, { "epoch": 0.74282223579719, "grad_norm": 0.46795663237571716, "learning_rate": 7.725415489327656e-06, "loss": 4.2259, "step": 24320 }, { "epoch": 0.7428527794746488, "grad_norm": 0.4667538106441498, "learning_rate": 7.723681478216335e-06, "loss": 4.2536, "step": 24321 }, { "epoch": 0.7428833231521075, "grad_norm": 0.4826545715332031, "learning_rate": 7.72194762617697e-06, "loss": 4.255, "step": 24322 }, { "epoch": 0.7429138668295663, "grad_norm": 0.48204800486564636, "learning_rate": 7.720213933225507e-06, "loss": 4.2706, "step": 24323 }, { "epoch": 0.7429444105070251, "grad_norm": 0.4754965007305145, "learning_rate": 7.71848039937792e-06, "loss": 4.2166, "step": 24324 }, { "epoch": 0.7429749541844838, "grad_norm": 0.47275328636169434, "learning_rate": 7.716747024650179e-06, "loss": 4.3147, "step": 24325 }, { "epoch": 0.7430054978619426, "grad_norm": 0.48106032609939575, "learning_rate": 7.715013809058221e-06, "loss": 4.2076, "step": 24326 }, { "epoch": 0.7430360415394014, "grad_norm": 0.4771660268306732, "learning_rate": 7.713280752618032e-06, "loss": 4.2858, "step": 24327 }, { "epoch": 0.7430665852168601, "grad_norm": 0.47795987129211426, "learning_rate": 7.711547855345543e-06, "loss": 4.1599, "step": 24328 }, { "epoch": 0.7430971288943189, "grad_norm": 0.460007905960083, "learning_rate": 7.709815117256732e-06, "loss": 4.1824, "step": 24329 }, { "epoch": 0.7431276725717776, "grad_norm": 0.46782737970352173, "learning_rate": 7.708082538367542e-06, "loss": 4.1715, "step": 24330 }, { "epoch": 0.7431582162492364, "grad_norm": 0.4746229648590088, "learning_rate": 7.70635011869392e-06, "loss": 4.1865, "step": 24331 }, { "epoch": 0.7431887599266952, "grad_norm": 0.4778219163417816, "learning_rate": 7.704617858251823e-06, "loss": 4.1779, "step": 24332 }, { "epoch": 0.7432193036041539, "grad_norm": 0.46775713562965393, "learning_rate": 7.70288575705721e-06, "loss": 4.2814, "step": 24333 }, { "epoch": 0.7432498472816127, "grad_norm": 0.47794485092163086, "learning_rate": 7.70115381512601e-06, "loss": 4.192, "step": 24334 }, { "epoch": 0.7432803909590715, "grad_norm": 0.48237529397010803, "learning_rate": 7.699422032474186e-06, "loss": 4.2279, "step": 24335 }, { "epoch": 0.7433109346365302, "grad_norm": 0.4808286726474762, "learning_rate": 7.697690409117683e-06, "loss": 4.31, "step": 24336 }, { "epoch": 0.743341478313989, "grad_norm": 0.4634040594100952, "learning_rate": 7.695958945072434e-06, "loss": 4.2038, "step": 24337 }, { "epoch": 0.7433720219914478, "grad_norm": 0.4717668294906616, "learning_rate": 7.694227640354388e-06, "loss": 4.2878, "step": 24338 }, { "epoch": 0.7434025656689065, "grad_norm": 0.49124667048454285, "learning_rate": 7.692496494979492e-06, "loss": 4.293, "step": 24339 }, { "epoch": 0.7434331093463653, "grad_norm": 0.4705090820789337, "learning_rate": 7.690765508963674e-06, "loss": 4.2505, "step": 24340 }, { "epoch": 0.7434636530238241, "grad_norm": 0.4694369435310364, "learning_rate": 7.689034682322876e-06, "loss": 4.2433, "step": 24341 }, { "epoch": 0.7434941967012828, "grad_norm": 0.4819781184196472, "learning_rate": 7.687304015073044e-06, "loss": 4.285, "step": 24342 }, { "epoch": 0.7435247403787416, "grad_norm": 0.4784872829914093, "learning_rate": 7.685573507230098e-06, "loss": 4.237, "step": 24343 }, { "epoch": 0.7435552840562004, "grad_norm": 0.4626355469226837, "learning_rate": 7.683843158809986e-06, "loss": 4.3174, "step": 24344 }, { "epoch": 0.7435858277336591, "grad_norm": 0.4791651964187622, "learning_rate": 7.682112969828633e-06, "loss": 4.2764, "step": 24345 }, { "epoch": 0.7436163714111179, "grad_norm": 0.461889386177063, "learning_rate": 7.680382940301964e-06, "loss": 4.2072, "step": 24346 }, { "epoch": 0.7436469150885766, "grad_norm": 0.4707123935222626, "learning_rate": 7.67865307024592e-06, "loss": 4.165, "step": 24347 }, { "epoch": 0.7436774587660354, "grad_norm": 0.4740563929080963, "learning_rate": 7.676923359676416e-06, "loss": 4.2811, "step": 24348 }, { "epoch": 0.7437080024434942, "grad_norm": 0.4671266973018646, "learning_rate": 7.675193808609385e-06, "loss": 4.2377, "step": 24349 }, { "epoch": 0.7437385461209529, "grad_norm": 0.47288963198661804, "learning_rate": 7.673464417060758e-06, "loss": 4.3215, "step": 24350 }, { "epoch": 0.7437690897984117, "grad_norm": 0.46766507625579834, "learning_rate": 7.671735185046447e-06, "loss": 4.2669, "step": 24351 }, { "epoch": 0.7437996334758705, "grad_norm": 0.47949105501174927, "learning_rate": 7.670006112582379e-06, "loss": 4.3067, "step": 24352 }, { "epoch": 0.7438301771533292, "grad_norm": 0.48121190071105957, "learning_rate": 7.668277199684481e-06, "loss": 4.3132, "step": 24353 }, { "epoch": 0.743860720830788, "grad_norm": 0.46738046407699585, "learning_rate": 7.666548446368663e-06, "loss": 4.1453, "step": 24354 }, { "epoch": 0.7438912645082468, "grad_norm": 0.4749583601951599, "learning_rate": 7.66481985265084e-06, "loss": 4.3196, "step": 24355 }, { "epoch": 0.7439218081857055, "grad_norm": 0.4885413646697998, "learning_rate": 7.663091418546945e-06, "loss": 4.3347, "step": 24356 }, { "epoch": 0.7439523518631643, "grad_norm": 0.49134141206741333, "learning_rate": 7.661363144072872e-06, "loss": 4.2306, "step": 24357 }, { "epoch": 0.7439828955406231, "grad_norm": 0.47730571031570435, "learning_rate": 7.659635029244542e-06, "loss": 4.2494, "step": 24358 }, { "epoch": 0.7440134392180818, "grad_norm": 0.497704416513443, "learning_rate": 7.657907074077877e-06, "loss": 4.3604, "step": 24359 }, { "epoch": 0.7440439828955406, "grad_norm": 0.47960999608039856, "learning_rate": 7.656179278588776e-06, "loss": 4.281, "step": 24360 }, { "epoch": 0.7440745265729994, "grad_norm": 0.48539841175079346, "learning_rate": 7.654451642793145e-06, "loss": 4.2805, "step": 24361 }, { "epoch": 0.7441050702504581, "grad_norm": 0.47312024235725403, "learning_rate": 7.652724166706902e-06, "loss": 4.2363, "step": 24362 }, { "epoch": 0.7441356139279169, "grad_norm": 0.4829474985599518, "learning_rate": 7.65099685034594e-06, "loss": 4.2323, "step": 24363 }, { "epoch": 0.7441661576053756, "grad_norm": 0.47361722588539124, "learning_rate": 7.649269693726177e-06, "loss": 4.1834, "step": 24364 }, { "epoch": 0.7441967012828344, "grad_norm": 0.48135507106781006, "learning_rate": 7.6475426968635e-06, "loss": 4.3784, "step": 24365 }, { "epoch": 0.7442272449602932, "grad_norm": 0.4706636071205139, "learning_rate": 7.64581585977382e-06, "loss": 4.2722, "step": 24366 }, { "epoch": 0.7442577886377519, "grad_norm": 0.47371190786361694, "learning_rate": 7.644089182473043e-06, "loss": 4.265, "step": 24367 }, { "epoch": 0.7442883323152107, "grad_norm": 0.48605042695999146, "learning_rate": 7.642362664977053e-06, "loss": 4.3726, "step": 24368 }, { "epoch": 0.7443188759926695, "grad_norm": 0.47041055560112, "learning_rate": 7.640636307301755e-06, "loss": 4.2942, "step": 24369 }, { "epoch": 0.7443494196701282, "grad_norm": 0.4832253158092499, "learning_rate": 7.638910109463052e-06, "loss": 4.2957, "step": 24370 }, { "epoch": 0.744379963347587, "grad_norm": 0.47885048389434814, "learning_rate": 7.637184071476821e-06, "loss": 4.3022, "step": 24371 }, { "epoch": 0.7444105070250459, "grad_norm": 0.46945279836654663, "learning_rate": 7.635458193358964e-06, "loss": 4.1199, "step": 24372 }, { "epoch": 0.7444410507025045, "grad_norm": 0.4754905700683594, "learning_rate": 7.63373247512538e-06, "loss": 4.217, "step": 24373 }, { "epoch": 0.7444715943799634, "grad_norm": 0.4783127009868622, "learning_rate": 7.63200691679194e-06, "loss": 4.2142, "step": 24374 }, { "epoch": 0.7445021380574222, "grad_norm": 0.47738590836524963, "learning_rate": 7.630281518374552e-06, "loss": 4.3023, "step": 24375 }, { "epoch": 0.7445326817348809, "grad_norm": 0.47360336780548096, "learning_rate": 7.62855627988909e-06, "loss": 4.3126, "step": 24376 }, { "epoch": 0.7445632254123397, "grad_norm": 0.4749950170516968, "learning_rate": 7.626831201351436e-06, "loss": 4.2446, "step": 24377 }, { "epoch": 0.7445937690897985, "grad_norm": 0.47799840569496155, "learning_rate": 7.62510628277748e-06, "loss": 4.2779, "step": 24378 }, { "epoch": 0.7446243127672572, "grad_norm": 0.4622643291950226, "learning_rate": 7.62338152418311e-06, "loss": 4.1319, "step": 24379 }, { "epoch": 0.744654856444716, "grad_norm": 0.4766993224620819, "learning_rate": 7.621656925584195e-06, "loss": 4.2622, "step": 24380 }, { "epoch": 0.7446854001221747, "grad_norm": 0.4827486574649811, "learning_rate": 7.619932486996626e-06, "loss": 4.3171, "step": 24381 }, { "epoch": 0.7447159437996335, "grad_norm": 0.49144402146339417, "learning_rate": 7.618208208436265e-06, "loss": 4.2099, "step": 24382 }, { "epoch": 0.7447464874770923, "grad_norm": 0.4840851128101349, "learning_rate": 7.616484089918999e-06, "loss": 4.2146, "step": 24383 }, { "epoch": 0.744777031154551, "grad_norm": 0.491056889295578, "learning_rate": 7.61476013146071e-06, "loss": 4.3083, "step": 24384 }, { "epoch": 0.7448075748320098, "grad_norm": 0.48196783661842346, "learning_rate": 7.6130363330772555e-06, "loss": 4.2974, "step": 24385 }, { "epoch": 0.7448381185094686, "grad_norm": 0.4794747829437256, "learning_rate": 7.611312694784514e-06, "loss": 4.2667, "step": 24386 }, { "epoch": 0.7448686621869273, "grad_norm": 0.479221910238266, "learning_rate": 7.609589216598368e-06, "loss": 4.2803, "step": 24387 }, { "epoch": 0.7448992058643861, "grad_norm": 0.468965083360672, "learning_rate": 7.6078658985346635e-06, "loss": 4.2187, "step": 24388 }, { "epoch": 0.7449297495418449, "grad_norm": 0.4717327952384949, "learning_rate": 7.606142740609281e-06, "loss": 4.1727, "step": 24389 }, { "epoch": 0.7449602932193036, "grad_norm": 0.4942493438720703, "learning_rate": 7.604419742838095e-06, "loss": 4.2414, "step": 24390 }, { "epoch": 0.7449908368967624, "grad_norm": 0.47482070326805115, "learning_rate": 7.6026969052369585e-06, "loss": 4.2687, "step": 24391 }, { "epoch": 0.7450213805742212, "grad_norm": 0.4741986393928528, "learning_rate": 7.600974227821727e-06, "loss": 4.2122, "step": 24392 }, { "epoch": 0.7450519242516799, "grad_norm": 0.4728230834007263, "learning_rate": 7.599251710608282e-06, "loss": 4.1792, "step": 24393 }, { "epoch": 0.7450824679291387, "grad_norm": 0.4583485424518585, "learning_rate": 7.597529353612465e-06, "loss": 4.2409, "step": 24394 }, { "epoch": 0.7451130116065975, "grad_norm": 0.4652184247970581, "learning_rate": 7.5958071568501436e-06, "loss": 4.2378, "step": 24395 }, { "epoch": 0.7451435552840562, "grad_norm": 0.468218594789505, "learning_rate": 7.59408512033718e-06, "loss": 4.2, "step": 24396 }, { "epoch": 0.745174098961515, "grad_norm": 0.47292256355285645, "learning_rate": 7.592363244089415e-06, "loss": 4.3218, "step": 24397 }, { "epoch": 0.7452046426389737, "grad_norm": 0.4744616448879242, "learning_rate": 7.590641528122722e-06, "loss": 4.2489, "step": 24398 }, { "epoch": 0.7452351863164325, "grad_norm": 0.4744858145713806, "learning_rate": 7.588919972452935e-06, "loss": 4.3215, "step": 24399 }, { "epoch": 0.7452657299938913, "grad_norm": 0.46927064657211304, "learning_rate": 7.587198577095914e-06, "loss": 4.1948, "step": 24400 }, { "epoch": 0.74529627367135, "grad_norm": 0.4718494713306427, "learning_rate": 7.585477342067515e-06, "loss": 4.2526, "step": 24401 }, { "epoch": 0.7453268173488088, "grad_norm": 0.4660177528858185, "learning_rate": 7.583756267383571e-06, "loss": 4.2746, "step": 24402 }, { "epoch": 0.7453573610262676, "grad_norm": 0.48792025446891785, "learning_rate": 7.5820353530599405e-06, "loss": 4.2838, "step": 24403 }, { "epoch": 0.7453879047037263, "grad_norm": 0.4830901622772217, "learning_rate": 7.580314599112473e-06, "loss": 4.2952, "step": 24404 }, { "epoch": 0.7454184483811851, "grad_norm": 0.48039695620536804, "learning_rate": 7.578594005556997e-06, "loss": 4.1832, "step": 24405 }, { "epoch": 0.7454489920586439, "grad_norm": 0.4792764484882355, "learning_rate": 7.576873572409371e-06, "loss": 4.2972, "step": 24406 }, { "epoch": 0.7454795357361026, "grad_norm": 0.4765150547027588, "learning_rate": 7.57515329968542e-06, "loss": 4.2421, "step": 24407 }, { "epoch": 0.7455100794135614, "grad_norm": 0.4684739112854004, "learning_rate": 7.573433187400999e-06, "loss": 4.3222, "step": 24408 }, { "epoch": 0.7455406230910202, "grad_norm": 0.48539456725120544, "learning_rate": 7.571713235571931e-06, "loss": 4.1678, "step": 24409 }, { "epoch": 0.7455711667684789, "grad_norm": 0.47060883045196533, "learning_rate": 7.569993444214069e-06, "loss": 4.2971, "step": 24410 }, { "epoch": 0.7456017104459377, "grad_norm": 0.4959208369255066, "learning_rate": 7.568273813343229e-06, "loss": 4.3131, "step": 24411 }, { "epoch": 0.7456322541233965, "grad_norm": 0.47233307361602783, "learning_rate": 7.566554342975257e-06, "loss": 4.1951, "step": 24412 }, { "epoch": 0.7456627978008552, "grad_norm": 0.46553778648376465, "learning_rate": 7.564835033125989e-06, "loss": 4.2571, "step": 24413 }, { "epoch": 0.745693341478314, "grad_norm": 0.45839211344718933, "learning_rate": 7.563115883811242e-06, "loss": 4.2378, "step": 24414 }, { "epoch": 0.7457238851557727, "grad_norm": 0.4700545370578766, "learning_rate": 7.56139689504686e-06, "loss": 4.3196, "step": 24415 }, { "epoch": 0.7457544288332315, "grad_norm": 0.48172152042388916, "learning_rate": 7.559678066848655e-06, "loss": 4.3322, "step": 24416 }, { "epoch": 0.7457849725106903, "grad_norm": 0.47534188628196716, "learning_rate": 7.557959399232459e-06, "loss": 4.2146, "step": 24417 }, { "epoch": 0.745815516188149, "grad_norm": 0.47126439213752747, "learning_rate": 7.556240892214109e-06, "loss": 4.2694, "step": 24418 }, { "epoch": 0.7458460598656078, "grad_norm": 0.4713950753211975, "learning_rate": 7.554522545809409e-06, "loss": 4.2753, "step": 24419 }, { "epoch": 0.7458766035430666, "grad_norm": 0.4907272756099701, "learning_rate": 7.552804360034188e-06, "loss": 4.3173, "step": 24420 }, { "epoch": 0.7459071472205253, "grad_norm": 0.4821908175945282, "learning_rate": 7.551086334904278e-06, "loss": 4.3134, "step": 24421 }, { "epoch": 0.7459376908979841, "grad_norm": 0.4820196032524109, "learning_rate": 7.549368470435486e-06, "loss": 4.2411, "step": 24422 }, { "epoch": 0.7459682345754429, "grad_norm": 0.4717493951320648, "learning_rate": 7.547650766643624e-06, "loss": 4.2326, "step": 24423 }, { "epoch": 0.7459987782529016, "grad_norm": 0.4798080325126648, "learning_rate": 7.545933223544521e-06, "loss": 4.2779, "step": 24424 }, { "epoch": 0.7460293219303604, "grad_norm": 0.4777074456214905, "learning_rate": 7.544215841153979e-06, "loss": 4.3078, "step": 24425 }, { "epoch": 0.7460598656078192, "grad_norm": 0.4787727892398834, "learning_rate": 7.542498619487814e-06, "loss": 4.2381, "step": 24426 }, { "epoch": 0.7460904092852779, "grad_norm": 0.48811131715774536, "learning_rate": 7.540781558561849e-06, "loss": 4.2818, "step": 24427 }, { "epoch": 0.7461209529627367, "grad_norm": 0.4949754774570465, "learning_rate": 7.539064658391878e-06, "loss": 4.2589, "step": 24428 }, { "epoch": 0.7461514966401955, "grad_norm": 0.4717179238796234, "learning_rate": 7.537347918993715e-06, "loss": 4.2199, "step": 24429 }, { "epoch": 0.7461820403176542, "grad_norm": 0.47669869661331177, "learning_rate": 7.535631340383176e-06, "loss": 4.252, "step": 24430 }, { "epoch": 0.746212583995113, "grad_norm": 0.47049108147621155, "learning_rate": 7.5339149225760516e-06, "loss": 4.2555, "step": 24431 }, { "epoch": 0.7462431276725717, "grad_norm": 0.4706597328186035, "learning_rate": 7.532198665588158e-06, "loss": 4.2268, "step": 24432 }, { "epoch": 0.7462736713500305, "grad_norm": 0.4826476275920868, "learning_rate": 7.530482569435288e-06, "loss": 4.3765, "step": 24433 }, { "epoch": 0.7463042150274893, "grad_norm": 0.4719780683517456, "learning_rate": 7.528766634133244e-06, "loss": 4.2256, "step": 24434 }, { "epoch": 0.746334758704948, "grad_norm": 0.48990291357040405, "learning_rate": 7.5270508596978375e-06, "loss": 4.2717, "step": 24435 }, { "epoch": 0.7463653023824068, "grad_norm": 0.4821470379829407, "learning_rate": 7.525335246144852e-06, "loss": 4.3398, "step": 24436 }, { "epoch": 0.7463958460598656, "grad_norm": 0.48367249965667725, "learning_rate": 7.5236197934900945e-06, "loss": 4.2919, "step": 24437 }, { "epoch": 0.7464263897373243, "grad_norm": 0.46754470467567444, "learning_rate": 7.521904501749346e-06, "loss": 4.216, "step": 24438 }, { "epoch": 0.7464569334147831, "grad_norm": 0.4784437119960785, "learning_rate": 7.520189370938418e-06, "loss": 4.3219, "step": 24439 }, { "epoch": 0.746487477092242, "grad_norm": 0.476159930229187, "learning_rate": 7.518474401073086e-06, "loss": 4.2194, "step": 24440 }, { "epoch": 0.7465180207697006, "grad_norm": 0.49248233437538147, "learning_rate": 7.516759592169159e-06, "loss": 4.1685, "step": 24441 }, { "epoch": 0.7465485644471594, "grad_norm": 0.4795725345611572, "learning_rate": 7.515044944242405e-06, "loss": 4.3135, "step": 24442 }, { "epoch": 0.7465791081246183, "grad_norm": 0.475614070892334, "learning_rate": 7.51333045730862e-06, "loss": 4.1788, "step": 24443 }, { "epoch": 0.746609651802077, "grad_norm": 0.4744988977909088, "learning_rate": 7.511616131383603e-06, "loss": 4.259, "step": 24444 }, { "epoch": 0.7466401954795358, "grad_norm": 0.47423994541168213, "learning_rate": 7.509901966483121e-06, "loss": 4.235, "step": 24445 }, { "epoch": 0.7466707391569946, "grad_norm": 0.4803638756275177, "learning_rate": 7.508187962622962e-06, "loss": 4.2947, "step": 24446 }, { "epoch": 0.7467012828344533, "grad_norm": 0.4858158528804779, "learning_rate": 7.506474119818918e-06, "loss": 4.2519, "step": 24447 }, { "epoch": 0.7467318265119121, "grad_norm": 0.47875261306762695, "learning_rate": 7.504760438086753e-06, "loss": 4.226, "step": 24448 }, { "epoch": 0.7467623701893707, "grad_norm": 0.47885072231292725, "learning_rate": 7.503046917442261e-06, "loss": 4.1846, "step": 24449 }, { "epoch": 0.7467929138668296, "grad_norm": 0.46959295868873596, "learning_rate": 7.501333557901205e-06, "loss": 4.3043, "step": 24450 }, { "epoch": 0.7468234575442884, "grad_norm": 0.47925010323524475, "learning_rate": 7.49962035947937e-06, "loss": 4.2853, "step": 24451 }, { "epoch": 0.746854001221747, "grad_norm": 0.4680120050907135, "learning_rate": 7.497907322192532e-06, "loss": 4.24, "step": 24452 }, { "epoch": 0.7468845448992059, "grad_norm": 0.4829799234867096, "learning_rate": 7.496194446056456e-06, "loss": 4.261, "step": 24453 }, { "epoch": 0.7469150885766647, "grad_norm": 0.4853978753089905, "learning_rate": 7.4944817310869216e-06, "loss": 4.2772, "step": 24454 }, { "epoch": 0.7469456322541234, "grad_norm": 0.4735565483570099, "learning_rate": 7.492769177299696e-06, "loss": 4.2784, "step": 24455 }, { "epoch": 0.7469761759315822, "grad_norm": 0.4636707007884979, "learning_rate": 7.4910567847105405e-06, "loss": 4.1295, "step": 24456 }, { "epoch": 0.747006719609041, "grad_norm": 0.4845636785030365, "learning_rate": 7.489344553335223e-06, "loss": 4.2765, "step": 24457 }, { "epoch": 0.7470372632864997, "grad_norm": 0.4773332178592682, "learning_rate": 7.487632483189525e-06, "loss": 4.2558, "step": 24458 }, { "epoch": 0.7470678069639585, "grad_norm": 0.4758526682853699, "learning_rate": 7.485920574289187e-06, "loss": 4.2826, "step": 24459 }, { "epoch": 0.7470983506414173, "grad_norm": 0.4719695746898651, "learning_rate": 7.484208826649986e-06, "loss": 4.2375, "step": 24460 }, { "epoch": 0.747128894318876, "grad_norm": 0.4799848198890686, "learning_rate": 7.482497240287686e-06, "loss": 4.3212, "step": 24461 }, { "epoch": 0.7471594379963348, "grad_norm": 0.5165478587150574, "learning_rate": 7.480785815218036e-06, "loss": 4.3055, "step": 24462 }, { "epoch": 0.7471899816737936, "grad_norm": 0.47930532693862915, "learning_rate": 7.479074551456797e-06, "loss": 4.2064, "step": 24463 }, { "epoch": 0.7472205253512523, "grad_norm": 0.4763863682746887, "learning_rate": 7.477363449019734e-06, "loss": 4.2376, "step": 24464 }, { "epoch": 0.7472510690287111, "grad_norm": 0.48004505038261414, "learning_rate": 7.475652507922587e-06, "loss": 4.2831, "step": 24465 }, { "epoch": 0.7472816127061698, "grad_norm": 0.46826663613319397, "learning_rate": 7.473941728181125e-06, "loss": 4.3239, "step": 24466 }, { "epoch": 0.7473121563836286, "grad_norm": 0.4784446060657501, "learning_rate": 7.472231109811084e-06, "loss": 4.247, "step": 24467 }, { "epoch": 0.7473427000610874, "grad_norm": 0.4815996289253235, "learning_rate": 7.470520652828225e-06, "loss": 4.1574, "step": 24468 }, { "epoch": 0.7473732437385461, "grad_norm": 0.4705883264541626, "learning_rate": 7.4688103572483015e-06, "loss": 4.1144, "step": 24469 }, { "epoch": 0.7474037874160049, "grad_norm": 0.4829882085323334, "learning_rate": 7.467100223087056e-06, "loss": 4.3038, "step": 24470 }, { "epoch": 0.7474343310934637, "grad_norm": 0.4756353497505188, "learning_rate": 7.465390250360224e-06, "loss": 4.236, "step": 24471 }, { "epoch": 0.7474648747709224, "grad_norm": 0.4776853322982788, "learning_rate": 7.4636804390835675e-06, "loss": 4.3217, "step": 24472 }, { "epoch": 0.7474954184483812, "grad_norm": 0.4774014353752136, "learning_rate": 7.4619707892728154e-06, "loss": 4.2634, "step": 24473 }, { "epoch": 0.74752596212584, "grad_norm": 0.4733627736568451, "learning_rate": 7.4602613009437135e-06, "loss": 4.2982, "step": 24474 }, { "epoch": 0.7475565058032987, "grad_norm": 0.4877729117870331, "learning_rate": 7.458551974112013e-06, "loss": 4.2665, "step": 24475 }, { "epoch": 0.7475870494807575, "grad_norm": 0.47009697556495667, "learning_rate": 7.456842808793435e-06, "loss": 4.3277, "step": 24476 }, { "epoch": 0.7476175931582163, "grad_norm": 0.47589021921157837, "learning_rate": 7.455133805003725e-06, "loss": 4.2663, "step": 24477 }, { "epoch": 0.747648136835675, "grad_norm": 0.4660816490650177, "learning_rate": 7.453424962758626e-06, "loss": 4.1498, "step": 24478 }, { "epoch": 0.7476786805131338, "grad_norm": 0.4843853712081909, "learning_rate": 7.451716282073859e-06, "loss": 4.1742, "step": 24479 }, { "epoch": 0.7477092241905925, "grad_norm": 0.4701416492462158, "learning_rate": 7.450007762965167e-06, "loss": 4.2508, "step": 24480 }, { "epoch": 0.7477397678680513, "grad_norm": 0.4731122553348541, "learning_rate": 7.4482994054482725e-06, "loss": 4.2766, "step": 24481 }, { "epoch": 0.7477703115455101, "grad_norm": 0.46679848432540894, "learning_rate": 7.446591209538908e-06, "loss": 4.2169, "step": 24482 }, { "epoch": 0.7478008552229688, "grad_norm": 0.461555540561676, "learning_rate": 7.444883175252812e-06, "loss": 4.2729, "step": 24483 }, { "epoch": 0.7478313989004276, "grad_norm": 0.4772058129310608, "learning_rate": 7.443175302605693e-06, "loss": 4.2868, "step": 24484 }, { "epoch": 0.7478619425778864, "grad_norm": 0.476008802652359, "learning_rate": 7.441467591613294e-06, "loss": 4.2233, "step": 24485 }, { "epoch": 0.7478924862553451, "grad_norm": 0.48482388257980347, "learning_rate": 7.439760042291333e-06, "loss": 4.1694, "step": 24486 }, { "epoch": 0.7479230299328039, "grad_norm": 0.4817636013031006, "learning_rate": 7.438052654655519e-06, "loss": 4.3287, "step": 24487 }, { "epoch": 0.7479535736102627, "grad_norm": 0.48385199904441833, "learning_rate": 7.436345428721586e-06, "loss": 4.217, "step": 24488 }, { "epoch": 0.7479841172877214, "grad_norm": 0.47851723432540894, "learning_rate": 7.434638364505256e-06, "loss": 4.3177, "step": 24489 }, { "epoch": 0.7480146609651802, "grad_norm": 0.46339133381843567, "learning_rate": 7.432931462022236e-06, "loss": 4.1741, "step": 24490 }, { "epoch": 0.748045204642639, "grad_norm": 0.47793295979499817, "learning_rate": 7.431224721288249e-06, "loss": 4.29, "step": 24491 }, { "epoch": 0.7480757483200977, "grad_norm": 0.4758981168270111, "learning_rate": 7.429518142319014e-06, "loss": 4.2255, "step": 24492 }, { "epoch": 0.7481062919975565, "grad_norm": 0.4918763339519501, "learning_rate": 7.427811725130235e-06, "loss": 4.2857, "step": 24493 }, { "epoch": 0.7481368356750153, "grad_norm": 0.4784141480922699, "learning_rate": 7.426105469737626e-06, "loss": 4.1563, "step": 24494 }, { "epoch": 0.748167379352474, "grad_norm": 0.48116499185562134, "learning_rate": 7.424399376156907e-06, "loss": 4.2501, "step": 24495 }, { "epoch": 0.7481979230299328, "grad_norm": 0.47735586762428284, "learning_rate": 7.422693444403772e-06, "loss": 4.1761, "step": 24496 }, { "epoch": 0.7482284667073915, "grad_norm": 0.47185611724853516, "learning_rate": 7.420987674493943e-06, "loss": 4.2349, "step": 24497 }, { "epoch": 0.7482590103848503, "grad_norm": 0.4875403344631195, "learning_rate": 7.419282066443112e-06, "loss": 4.3327, "step": 24498 }, { "epoch": 0.7482895540623091, "grad_norm": 0.4774131774902344, "learning_rate": 7.417576620266992e-06, "loss": 4.2921, "step": 24499 }, { "epoch": 0.7483200977397678, "grad_norm": 0.47656160593032837, "learning_rate": 7.415871335981289e-06, "loss": 4.2464, "step": 24500 }, { "epoch": 0.7483506414172266, "grad_norm": 0.4765447974205017, "learning_rate": 7.4141662136017e-06, "loss": 4.2081, "step": 24501 }, { "epoch": 0.7483811850946854, "grad_norm": 0.48152169585227966, "learning_rate": 7.412461253143916e-06, "loss": 4.1822, "step": 24502 }, { "epoch": 0.7484117287721441, "grad_norm": 0.46742528676986694, "learning_rate": 7.410756454623652e-06, "loss": 4.2692, "step": 24503 }, { "epoch": 0.7484422724496029, "grad_norm": 0.48324933648109436, "learning_rate": 7.40905181805659e-06, "loss": 4.2752, "step": 24504 }, { "epoch": 0.7484728161270617, "grad_norm": 0.4742741882801056, "learning_rate": 7.407347343458432e-06, "loss": 4.1961, "step": 24505 }, { "epoch": 0.7485033598045204, "grad_norm": 0.47778189182281494, "learning_rate": 7.40564303084488e-06, "loss": 4.3414, "step": 24506 }, { "epoch": 0.7485339034819792, "grad_norm": 0.47068139910697937, "learning_rate": 7.403938880231612e-06, "loss": 4.1509, "step": 24507 }, { "epoch": 0.748564447159438, "grad_norm": 0.47669216990470886, "learning_rate": 7.402234891634324e-06, "loss": 4.2549, "step": 24508 }, { "epoch": 0.7485949908368967, "grad_norm": 0.4804154932498932, "learning_rate": 7.400531065068714e-06, "loss": 4.2009, "step": 24509 }, { "epoch": 0.7486255345143555, "grad_norm": 0.4932955205440521, "learning_rate": 7.398827400550457e-06, "loss": 4.2354, "step": 24510 }, { "epoch": 0.7486560781918143, "grad_norm": 0.48768100142478943, "learning_rate": 7.397123898095245e-06, "loss": 4.2995, "step": 24511 }, { "epoch": 0.748686621869273, "grad_norm": 0.4856146574020386, "learning_rate": 7.395420557718774e-06, "loss": 4.2684, "step": 24512 }, { "epoch": 0.7487171655467318, "grad_norm": 0.4686952233314514, "learning_rate": 7.393717379436707e-06, "loss": 4.2518, "step": 24513 }, { "epoch": 0.7487477092241905, "grad_norm": 0.4716758131980896, "learning_rate": 7.392014363264746e-06, "loss": 4.2545, "step": 24514 }, { "epoch": 0.7487782529016493, "grad_norm": 0.49219372868537903, "learning_rate": 7.3903115092185535e-06, "loss": 4.2891, "step": 24515 }, { "epoch": 0.7488087965791081, "grad_norm": 0.47037172317504883, "learning_rate": 7.388608817313825e-06, "loss": 4.2662, "step": 24516 }, { "epoch": 0.7488393402565668, "grad_norm": 0.47613629698753357, "learning_rate": 7.3869062875662195e-06, "loss": 4.3273, "step": 24517 }, { "epoch": 0.7488698839340256, "grad_norm": 0.47611862421035767, "learning_rate": 7.385203919991435e-06, "loss": 4.3209, "step": 24518 }, { "epoch": 0.7489004276114845, "grad_norm": 0.48479098081588745, "learning_rate": 7.3835017146051235e-06, "loss": 4.2081, "step": 24519 }, { "epoch": 0.7489309712889431, "grad_norm": 0.47700566053390503, "learning_rate": 7.381799671422979e-06, "loss": 4.2446, "step": 24520 }, { "epoch": 0.748961514966402, "grad_norm": 0.47188517451286316, "learning_rate": 7.380097790460655e-06, "loss": 4.2061, "step": 24521 }, { "epoch": 0.7489920586438608, "grad_norm": 0.47398829460144043, "learning_rate": 7.3783960717338314e-06, "loss": 4.1606, "step": 24522 }, { "epoch": 0.7490226023213195, "grad_norm": 0.48580625653266907, "learning_rate": 7.376694515258181e-06, "loss": 4.2307, "step": 24523 }, { "epoch": 0.7490531459987783, "grad_norm": 0.4765439033508301, "learning_rate": 7.374993121049359e-06, "loss": 4.2312, "step": 24524 }, { "epoch": 0.7490836896762371, "grad_norm": 0.4771885275840759, "learning_rate": 7.373291889123035e-06, "loss": 4.3274, "step": 24525 }, { "epoch": 0.7491142333536958, "grad_norm": 0.48743411898612976, "learning_rate": 7.371590819494886e-06, "loss": 4.3854, "step": 24526 }, { "epoch": 0.7491447770311546, "grad_norm": 0.48593059182167053, "learning_rate": 7.369889912180553e-06, "loss": 4.2653, "step": 24527 }, { "epoch": 0.7491753207086134, "grad_norm": 0.4807358682155609, "learning_rate": 7.3681891671957106e-06, "loss": 4.3172, "step": 24528 }, { "epoch": 0.7492058643860721, "grad_norm": 0.4795363247394562, "learning_rate": 7.366488584556022e-06, "loss": 4.2384, "step": 24529 }, { "epoch": 0.7492364080635309, "grad_norm": 0.48169857263565063, "learning_rate": 7.364788164277134e-06, "loss": 4.1485, "step": 24530 }, { "epoch": 0.7492669517409896, "grad_norm": 0.48197779059410095, "learning_rate": 7.363087906374714e-06, "loss": 4.1923, "step": 24531 }, { "epoch": 0.7492974954184484, "grad_norm": 0.47242769598960876, "learning_rate": 7.3613878108644115e-06, "loss": 4.2182, "step": 24532 }, { "epoch": 0.7493280390959072, "grad_norm": 0.4798359274864197, "learning_rate": 7.359687877761873e-06, "loss": 4.2381, "step": 24533 }, { "epoch": 0.7493585827733659, "grad_norm": 0.5080432295799255, "learning_rate": 7.357988107082767e-06, "loss": 4.244, "step": 24534 }, { "epoch": 0.7493891264508247, "grad_norm": 0.46976685523986816, "learning_rate": 7.3562884988427255e-06, "loss": 4.1295, "step": 24535 }, { "epoch": 0.7494196701282835, "grad_norm": 0.48126715421676636, "learning_rate": 7.354589053057409e-06, "loss": 4.2344, "step": 24536 }, { "epoch": 0.7494502138057422, "grad_norm": 0.4774336814880371, "learning_rate": 7.352889769742472e-06, "loss": 4.233, "step": 24537 }, { "epoch": 0.749480757483201, "grad_norm": 0.47831135988235474, "learning_rate": 7.351190648913542e-06, "loss": 4.2998, "step": 24538 }, { "epoch": 0.7495113011606598, "grad_norm": 0.47537651658058167, "learning_rate": 7.3494916905862745e-06, "loss": 4.2877, "step": 24539 }, { "epoch": 0.7495418448381185, "grad_norm": 0.4796135127544403, "learning_rate": 7.34779289477632e-06, "loss": 4.2219, "step": 24540 }, { "epoch": 0.7495723885155773, "grad_norm": 0.4738348424434662, "learning_rate": 7.346094261499303e-06, "loss": 4.2709, "step": 24541 }, { "epoch": 0.7496029321930361, "grad_norm": 0.48520782589912415, "learning_rate": 7.344395790770875e-06, "loss": 4.1513, "step": 24542 }, { "epoch": 0.7496334758704948, "grad_norm": 0.493437796831131, "learning_rate": 7.342697482606678e-06, "loss": 4.2123, "step": 24543 }, { "epoch": 0.7496640195479536, "grad_norm": 0.4877530038356781, "learning_rate": 7.340999337022339e-06, "loss": 4.3602, "step": 24544 }, { "epoch": 0.7496945632254124, "grad_norm": 0.48508983850479126, "learning_rate": 7.339301354033496e-06, "loss": 4.3049, "step": 24545 }, { "epoch": 0.7497251069028711, "grad_norm": 0.47328102588653564, "learning_rate": 7.337603533655796e-06, "loss": 4.228, "step": 24546 }, { "epoch": 0.7497556505803299, "grad_norm": 0.4895673394203186, "learning_rate": 7.335905875904858e-06, "loss": 4.2785, "step": 24547 }, { "epoch": 0.7497861942577886, "grad_norm": 0.4800608456134796, "learning_rate": 7.334208380796312e-06, "loss": 4.1569, "step": 24548 }, { "epoch": 0.7498167379352474, "grad_norm": 0.4898502826690674, "learning_rate": 7.332511048345797e-06, "loss": 4.2811, "step": 24549 }, { "epoch": 0.7498472816127062, "grad_norm": 0.4747452139854431, "learning_rate": 7.330813878568932e-06, "loss": 4.2673, "step": 24550 }, { "epoch": 0.7498778252901649, "grad_norm": 0.4740303158760071, "learning_rate": 7.329116871481353e-06, "loss": 4.2916, "step": 24551 }, { "epoch": 0.7499083689676237, "grad_norm": 0.48150041699409485, "learning_rate": 7.3274200270986745e-06, "loss": 4.2967, "step": 24552 }, { "epoch": 0.7499389126450825, "grad_norm": 0.4858635365962982, "learning_rate": 7.325723345436525e-06, "loss": 4.3261, "step": 24553 }, { "epoch": 0.7499694563225412, "grad_norm": 0.4798848330974579, "learning_rate": 7.324026826510538e-06, "loss": 4.2381, "step": 24554 }, { "epoch": 0.75, "grad_norm": 0.4788278639316559, "learning_rate": 7.3223304703363135e-06, "loss": 4.2369, "step": 24555 }, { "epoch": 0.7500305436774588, "grad_norm": 0.47211673855781555, "learning_rate": 7.320634276929483e-06, "loss": 4.2297, "step": 24556 }, { "epoch": 0.7500610873549175, "grad_norm": 0.4731341600418091, "learning_rate": 7.318938246305671e-06, "loss": 4.2887, "step": 24557 }, { "epoch": 0.7500916310323763, "grad_norm": 0.4652188718318939, "learning_rate": 7.317242378480474e-06, "loss": 4.3189, "step": 24558 }, { "epoch": 0.7501221747098351, "grad_norm": 0.47168534994125366, "learning_rate": 7.3155466734695196e-06, "loss": 4.316, "step": 24559 }, { "epoch": 0.7501527183872938, "grad_norm": 0.47740253806114197, "learning_rate": 7.313851131288429e-06, "loss": 4.2854, "step": 24560 }, { "epoch": 0.7501832620647526, "grad_norm": 0.48196637630462646, "learning_rate": 7.312155751952795e-06, "loss": 4.2306, "step": 24561 }, { "epoch": 0.7502138057422114, "grad_norm": 0.48095548152923584, "learning_rate": 7.310460535478248e-06, "loss": 4.3395, "step": 24562 }, { "epoch": 0.7502443494196701, "grad_norm": 0.4953722059726715, "learning_rate": 7.308765481880373e-06, "loss": 4.2827, "step": 24563 }, { "epoch": 0.7502748930971289, "grad_norm": 0.474802702665329, "learning_rate": 7.3070705911748e-06, "loss": 4.2837, "step": 24564 }, { "epoch": 0.7503054367745876, "grad_norm": 0.48154810070991516, "learning_rate": 7.305375863377126e-06, "loss": 4.2815, "step": 24565 }, { "epoch": 0.7503359804520464, "grad_norm": 0.48582345247268677, "learning_rate": 7.303681298502946e-06, "loss": 4.1516, "step": 24566 }, { "epoch": 0.7503665241295052, "grad_norm": 0.4702417552471161, "learning_rate": 7.301986896567869e-06, "loss": 4.1707, "step": 24567 }, { "epoch": 0.7503970678069639, "grad_norm": 0.47410377860069275, "learning_rate": 7.30029265758751e-06, "loss": 4.2854, "step": 24568 }, { "epoch": 0.7504276114844227, "grad_norm": 0.47973254323005676, "learning_rate": 7.298598581577446e-06, "loss": 4.1705, "step": 24569 }, { "epoch": 0.7504581551618815, "grad_norm": 0.47505587339401245, "learning_rate": 7.296904668553287e-06, "loss": 4.262, "step": 24570 }, { "epoch": 0.7504886988393402, "grad_norm": 0.4709423780441284, "learning_rate": 7.295210918530634e-06, "loss": 4.2354, "step": 24571 }, { "epoch": 0.750519242516799, "grad_norm": 0.4763736128807068, "learning_rate": 7.293517331525071e-06, "loss": 4.2478, "step": 24572 }, { "epoch": 0.7505497861942578, "grad_norm": 0.4722396731376648, "learning_rate": 7.2918239075521975e-06, "loss": 4.2739, "step": 24573 }, { "epoch": 0.7505803298717165, "grad_norm": 0.4684615433216095, "learning_rate": 7.290130646627613e-06, "loss": 4.2099, "step": 24574 }, { "epoch": 0.7506108735491753, "grad_norm": 0.46735909581184387, "learning_rate": 7.288437548766897e-06, "loss": 4.2215, "step": 24575 }, { "epoch": 0.7506414172266341, "grad_norm": 0.4730135500431061, "learning_rate": 7.286744613985638e-06, "loss": 4.2708, "step": 24576 }, { "epoch": 0.7506719609040928, "grad_norm": 0.4862724840641022, "learning_rate": 7.285051842299439e-06, "loss": 4.1735, "step": 24577 }, { "epoch": 0.7507025045815516, "grad_norm": 0.4816000461578369, "learning_rate": 7.283359233723869e-06, "loss": 4.2653, "step": 24578 }, { "epoch": 0.7507330482590104, "grad_norm": 0.4716617166996002, "learning_rate": 7.2816667882745245e-06, "loss": 4.2835, "step": 24579 }, { "epoch": 0.7507635919364691, "grad_norm": 0.4815591275691986, "learning_rate": 7.2799745059669854e-06, "loss": 4.2914, "step": 24580 }, { "epoch": 0.7507941356139279, "grad_norm": 0.476899117231369, "learning_rate": 7.278282386816823e-06, "loss": 4.236, "step": 24581 }, { "epoch": 0.7508246792913866, "grad_norm": 0.476139098405838, "learning_rate": 7.276590430839636e-06, "loss": 4.1603, "step": 24582 }, { "epoch": 0.7508552229688454, "grad_norm": 0.4763505160808563, "learning_rate": 7.274898638050984e-06, "loss": 4.2763, "step": 24583 }, { "epoch": 0.7508857666463042, "grad_norm": 0.47276145219802856, "learning_rate": 7.2732070084664535e-06, "loss": 4.2592, "step": 24584 }, { "epoch": 0.7509163103237629, "grad_norm": 0.47293585538864136, "learning_rate": 7.271515542101628e-06, "loss": 4.2828, "step": 24585 }, { "epoch": 0.7509468540012217, "grad_norm": 0.4857025444507599, "learning_rate": 7.269824238972067e-06, "loss": 4.3449, "step": 24586 }, { "epoch": 0.7509773976786805, "grad_norm": 0.4790824055671692, "learning_rate": 7.268133099093352e-06, "loss": 4.2023, "step": 24587 }, { "epoch": 0.7510079413561392, "grad_norm": 0.4851399064064026, "learning_rate": 7.266442122481057e-06, "loss": 4.3181, "step": 24588 }, { "epoch": 0.751038485033598, "grad_norm": 0.48151901364326477, "learning_rate": 7.264751309150741e-06, "loss": 4.2089, "step": 24589 }, { "epoch": 0.7510690287110569, "grad_norm": 0.4762236773967743, "learning_rate": 7.263060659117976e-06, "loss": 4.2397, "step": 24590 }, { "epoch": 0.7510995723885155, "grad_norm": 0.47774067521095276, "learning_rate": 7.26137017239834e-06, "loss": 4.2424, "step": 24591 }, { "epoch": 0.7511301160659744, "grad_norm": 0.47986316680908203, "learning_rate": 7.259679849007384e-06, "loss": 4.3088, "step": 24592 }, { "epoch": 0.7511606597434332, "grad_norm": 0.47808656096458435, "learning_rate": 7.2579896889606816e-06, "loss": 4.2929, "step": 24593 }, { "epoch": 0.7511912034208919, "grad_norm": 0.4701167047023773, "learning_rate": 7.256299692273783e-06, "loss": 4.1728, "step": 24594 }, { "epoch": 0.7512217470983507, "grad_norm": 0.4720849394798279, "learning_rate": 7.254609858962263e-06, "loss": 4.1287, "step": 24595 }, { "epoch": 0.7512522907758095, "grad_norm": 0.47281312942504883, "learning_rate": 7.252920189041668e-06, "loss": 4.2466, "step": 24596 }, { "epoch": 0.7512828344532682, "grad_norm": 0.4785066843032837, "learning_rate": 7.251230682527568e-06, "loss": 4.2394, "step": 24597 }, { "epoch": 0.751313378130727, "grad_norm": 0.49009591341018677, "learning_rate": 7.249541339435506e-06, "loss": 4.3328, "step": 24598 }, { "epoch": 0.7513439218081857, "grad_norm": 0.48093393445014954, "learning_rate": 7.2478521597810485e-06, "loss": 4.2487, "step": 24599 }, { "epoch": 0.7513744654856445, "grad_norm": 0.46695676445961, "learning_rate": 7.246163143579737e-06, "loss": 4.2552, "step": 24600 }, { "epoch": 0.7514050091631033, "grad_norm": 0.48001524806022644, "learning_rate": 7.244474290847131e-06, "loss": 4.2274, "step": 24601 }, { "epoch": 0.751435552840562, "grad_norm": 0.4790681302547455, "learning_rate": 7.242785601598784e-06, "loss": 4.2475, "step": 24602 }, { "epoch": 0.7514660965180208, "grad_norm": 0.4694800078868866, "learning_rate": 7.2410970758502336e-06, "loss": 4.2718, "step": 24603 }, { "epoch": 0.7514966401954796, "grad_norm": 0.4700786769390106, "learning_rate": 7.239408713617035e-06, "loss": 4.2444, "step": 24604 }, { "epoch": 0.7515271838729383, "grad_norm": 0.47875189781188965, "learning_rate": 7.237720514914736e-06, "loss": 4.3196, "step": 24605 }, { "epoch": 0.7515577275503971, "grad_norm": 0.4845369756221771, "learning_rate": 7.2360324797588725e-06, "loss": 4.3187, "step": 24606 }, { "epoch": 0.7515882712278559, "grad_norm": 0.48014751076698303, "learning_rate": 7.234344608164989e-06, "loss": 4.3043, "step": 24607 }, { "epoch": 0.7516188149053146, "grad_norm": 0.4761461019515991, "learning_rate": 7.2326569001486375e-06, "loss": 4.3125, "step": 24608 }, { "epoch": 0.7516493585827734, "grad_norm": 0.48774921894073486, "learning_rate": 7.230969355725342e-06, "loss": 4.2886, "step": 24609 }, { "epoch": 0.7516799022602322, "grad_norm": 0.47947028279304504, "learning_rate": 7.229281974910654e-06, "loss": 4.2755, "step": 24610 }, { "epoch": 0.7517104459376909, "grad_norm": 0.4842115342617035, "learning_rate": 7.227594757720105e-06, "loss": 4.2546, "step": 24611 }, { "epoch": 0.7517409896151497, "grad_norm": 0.48129361867904663, "learning_rate": 7.225907704169218e-06, "loss": 4.1724, "step": 24612 }, { "epoch": 0.7517715332926085, "grad_norm": 0.48061317205429077, "learning_rate": 7.224220814273541e-06, "loss": 4.2698, "step": 24613 }, { "epoch": 0.7518020769700672, "grad_norm": 0.468647837638855, "learning_rate": 7.222534088048608e-06, "loss": 4.2141, "step": 24614 }, { "epoch": 0.751832620647526, "grad_norm": 0.47805076837539673, "learning_rate": 7.220847525509936e-06, "loss": 4.3003, "step": 24615 }, { "epoch": 0.7518631643249847, "grad_norm": 0.47431087493896484, "learning_rate": 7.219161126673071e-06, "loss": 4.1795, "step": 24616 }, { "epoch": 0.7518937080024435, "grad_norm": 0.4757729172706604, "learning_rate": 7.217474891553525e-06, "loss": 4.3108, "step": 24617 }, { "epoch": 0.7519242516799023, "grad_norm": 0.48102250695228577, "learning_rate": 7.2157888201668275e-06, "loss": 4.1962, "step": 24618 }, { "epoch": 0.751954795357361, "grad_norm": 0.4832747280597687, "learning_rate": 7.214102912528514e-06, "loss": 4.265, "step": 24619 }, { "epoch": 0.7519853390348198, "grad_norm": 0.47668156027793884, "learning_rate": 7.212417168654093e-06, "loss": 4.194, "step": 24620 }, { "epoch": 0.7520158827122786, "grad_norm": 0.4781971871852875, "learning_rate": 7.210731588559094e-06, "loss": 4.2279, "step": 24621 }, { "epoch": 0.7520464263897373, "grad_norm": 0.4713751971721649, "learning_rate": 7.209046172259041e-06, "loss": 4.258, "step": 24622 }, { "epoch": 0.7520769700671961, "grad_norm": 0.46907004714012146, "learning_rate": 7.2073609197694405e-06, "loss": 4.1464, "step": 24623 }, { "epoch": 0.7521075137446549, "grad_norm": 0.4713177978992462, "learning_rate": 7.205675831105815e-06, "loss": 4.2435, "step": 24624 }, { "epoch": 0.7521380574221136, "grad_norm": 0.4844169020652771, "learning_rate": 7.203990906283689e-06, "loss": 4.2097, "step": 24625 }, { "epoch": 0.7521686010995724, "grad_norm": 0.4721042513847351, "learning_rate": 7.2023061453185685e-06, "loss": 4.2162, "step": 24626 }, { "epoch": 0.7521991447770312, "grad_norm": 0.47353285551071167, "learning_rate": 7.200621548225961e-06, "loss": 4.2566, "step": 24627 }, { "epoch": 0.7522296884544899, "grad_norm": 0.4790513813495636, "learning_rate": 7.198937115021387e-06, "loss": 4.2297, "step": 24628 }, { "epoch": 0.7522602321319487, "grad_norm": 0.4854893386363983, "learning_rate": 7.197252845720345e-06, "loss": 4.252, "step": 24629 }, { "epoch": 0.7522907758094075, "grad_norm": 0.47787073254585266, "learning_rate": 7.195568740338349e-06, "loss": 4.2264, "step": 24630 }, { "epoch": 0.7523213194868662, "grad_norm": 0.4678022861480713, "learning_rate": 7.193884798890913e-06, "loss": 4.1932, "step": 24631 }, { "epoch": 0.752351863164325, "grad_norm": 0.5009981393814087, "learning_rate": 7.192201021393527e-06, "loss": 4.2719, "step": 24632 }, { "epoch": 0.7523824068417837, "grad_norm": 0.47566795349121094, "learning_rate": 7.1905174078617105e-06, "loss": 4.1976, "step": 24633 }, { "epoch": 0.7524129505192425, "grad_norm": 0.47474798560142517, "learning_rate": 7.188833958310948e-06, "loss": 4.2171, "step": 24634 }, { "epoch": 0.7524434941967013, "grad_norm": 0.4853631556034088, "learning_rate": 7.187150672756751e-06, "loss": 4.2661, "step": 24635 }, { "epoch": 0.75247403787416, "grad_norm": 0.47326236963272095, "learning_rate": 7.185467551214623e-06, "loss": 4.3059, "step": 24636 }, { "epoch": 0.7525045815516188, "grad_norm": 0.4684756398200989, "learning_rate": 7.1837845937000465e-06, "loss": 4.2369, "step": 24637 }, { "epoch": 0.7525351252290776, "grad_norm": 0.4956415593624115, "learning_rate": 7.182101800228524e-06, "loss": 4.2487, "step": 24638 }, { "epoch": 0.7525656689065363, "grad_norm": 0.47360774874687195, "learning_rate": 7.180419170815561e-06, "loss": 4.1923, "step": 24639 }, { "epoch": 0.7525962125839951, "grad_norm": 0.47128036618232727, "learning_rate": 7.178736705476632e-06, "loss": 4.2633, "step": 24640 }, { "epoch": 0.7526267562614539, "grad_norm": 0.4679684638977051, "learning_rate": 7.177054404227246e-06, "loss": 4.2984, "step": 24641 }, { "epoch": 0.7526572999389126, "grad_norm": 0.47572681307792664, "learning_rate": 7.175372267082881e-06, "loss": 4.231, "step": 24642 }, { "epoch": 0.7526878436163714, "grad_norm": 0.4762548506259918, "learning_rate": 7.173690294059024e-06, "loss": 4.1433, "step": 24643 }, { "epoch": 0.7527183872938302, "grad_norm": 0.4865827262401581, "learning_rate": 7.172008485171164e-06, "loss": 4.2778, "step": 24644 }, { "epoch": 0.7527489309712889, "grad_norm": 0.47036606073379517, "learning_rate": 7.170326840434794e-06, "loss": 4.2399, "step": 24645 }, { "epoch": 0.7527794746487477, "grad_norm": 0.4826416075229645, "learning_rate": 7.168645359865387e-06, "loss": 4.2569, "step": 24646 }, { "epoch": 0.7528100183262064, "grad_norm": 0.49225175380706787, "learning_rate": 7.166964043478436e-06, "loss": 4.3086, "step": 24647 }, { "epoch": 0.7528405620036652, "grad_norm": 0.4816768765449524, "learning_rate": 7.16528289128941e-06, "loss": 4.2119, "step": 24648 }, { "epoch": 0.752871105681124, "grad_norm": 0.4906966984272003, "learning_rate": 7.163601903313794e-06, "loss": 4.2632, "step": 24649 }, { "epoch": 0.7529016493585827, "grad_norm": 0.480052649974823, "learning_rate": 7.1619210795670715e-06, "loss": 4.1858, "step": 24650 }, { "epoch": 0.7529321930360415, "grad_norm": 0.4788689911365509, "learning_rate": 7.160240420064707e-06, "loss": 4.2274, "step": 24651 }, { "epoch": 0.7529627367135003, "grad_norm": 0.4757150113582611, "learning_rate": 7.15855992482218e-06, "loss": 4.1368, "step": 24652 }, { "epoch": 0.752993280390959, "grad_norm": 0.47660788893699646, "learning_rate": 7.156879593854973e-06, "loss": 4.241, "step": 24653 }, { "epoch": 0.7530238240684178, "grad_norm": 0.4698510766029358, "learning_rate": 7.155199427178541e-06, "loss": 4.2536, "step": 24654 }, { "epoch": 0.7530543677458766, "grad_norm": 0.48512712121009827, "learning_rate": 7.153519424808366e-06, "loss": 4.2426, "step": 24655 }, { "epoch": 0.7530849114233353, "grad_norm": 0.4803723692893982, "learning_rate": 7.151839586759917e-06, "loss": 4.2844, "step": 24656 }, { "epoch": 0.7531154551007941, "grad_norm": 0.4803086221218109, "learning_rate": 7.150159913048662e-06, "loss": 4.2337, "step": 24657 }, { "epoch": 0.753145998778253, "grad_norm": 0.4776323437690735, "learning_rate": 7.14848040369005e-06, "loss": 4.3034, "step": 24658 }, { "epoch": 0.7531765424557116, "grad_norm": 0.47882354259490967, "learning_rate": 7.146801058699567e-06, "loss": 4.3437, "step": 24659 }, { "epoch": 0.7532070861331704, "grad_norm": 0.478311687707901, "learning_rate": 7.145121878092659e-06, "loss": 4.2422, "step": 24660 }, { "epoch": 0.7532376298106293, "grad_norm": 0.4722599983215332, "learning_rate": 7.143442861884794e-06, "loss": 4.3457, "step": 24661 }, { "epoch": 0.7532681734880879, "grad_norm": 0.469056636095047, "learning_rate": 7.141764010091437e-06, "loss": 4.074, "step": 24662 }, { "epoch": 0.7532987171655467, "grad_norm": 0.4808342158794403, "learning_rate": 7.140085322728035e-06, "loss": 4.38, "step": 24663 }, { "epoch": 0.7533292608430054, "grad_norm": 0.4682615101337433, "learning_rate": 7.138406799810057e-06, "loss": 4.2744, "step": 24664 }, { "epoch": 0.7533598045204642, "grad_norm": 0.4846223294734955, "learning_rate": 7.136728441352944e-06, "loss": 4.2587, "step": 24665 }, { "epoch": 0.753390348197923, "grad_norm": 0.4779680073261261, "learning_rate": 7.135050247372155e-06, "loss": 4.3428, "step": 24666 }, { "epoch": 0.7534208918753817, "grad_norm": 0.4798752963542938, "learning_rate": 7.133372217883153e-06, "loss": 4.2489, "step": 24667 }, { "epoch": 0.7534514355528406, "grad_norm": 0.470713347196579, "learning_rate": 7.1316943529013715e-06, "loss": 4.2756, "step": 24668 }, { "epoch": 0.7534819792302994, "grad_norm": 0.48645421862602234, "learning_rate": 7.1300166524422674e-06, "loss": 4.1165, "step": 24669 }, { "epoch": 0.753512522907758, "grad_norm": 0.4795549213886261, "learning_rate": 7.128339116521293e-06, "loss": 4.2747, "step": 24670 }, { "epoch": 0.7535430665852169, "grad_norm": 0.48090794682502747, "learning_rate": 7.126661745153884e-06, "loss": 4.2272, "step": 24671 }, { "epoch": 0.7535736102626757, "grad_norm": 0.4696785807609558, "learning_rate": 7.124984538355495e-06, "loss": 4.266, "step": 24672 }, { "epoch": 0.7536041539401344, "grad_norm": 0.4924718737602234, "learning_rate": 7.123307496141557e-06, "loss": 4.2797, "step": 24673 }, { "epoch": 0.7536346976175932, "grad_norm": 0.48534512519836426, "learning_rate": 7.1216306185275275e-06, "loss": 4.2427, "step": 24674 }, { "epoch": 0.753665241295052, "grad_norm": 0.5047276616096497, "learning_rate": 7.1199539055288285e-06, "loss": 4.3082, "step": 24675 }, { "epoch": 0.7536957849725107, "grad_norm": 0.49760255217552185, "learning_rate": 7.1182773571609126e-06, "loss": 4.2504, "step": 24676 }, { "epoch": 0.7537263286499695, "grad_norm": 0.4825148582458496, "learning_rate": 7.116600973439205e-06, "loss": 4.2949, "step": 24677 }, { "epoch": 0.7537568723274283, "grad_norm": 0.4730149507522583, "learning_rate": 7.114924754379149e-06, "loss": 4.2987, "step": 24678 }, { "epoch": 0.753787416004887, "grad_norm": 0.47928860783576965, "learning_rate": 7.113248699996181e-06, "loss": 4.2287, "step": 24679 }, { "epoch": 0.7538179596823458, "grad_norm": 0.48423805832862854, "learning_rate": 7.111572810305722e-06, "loss": 4.1984, "step": 24680 }, { "epoch": 0.7538485033598045, "grad_norm": 0.4812923073768616, "learning_rate": 7.1098970853232166e-06, "loss": 4.2718, "step": 24681 }, { "epoch": 0.7538790470372633, "grad_norm": 0.47381752729415894, "learning_rate": 7.10822152506408e-06, "loss": 4.2131, "step": 24682 }, { "epoch": 0.7539095907147221, "grad_norm": 0.47853901982307434, "learning_rate": 7.106546129543748e-06, "loss": 4.2463, "step": 24683 }, { "epoch": 0.7539401343921808, "grad_norm": 0.4754270911216736, "learning_rate": 7.104870898777652e-06, "loss": 4.239, "step": 24684 }, { "epoch": 0.7539706780696396, "grad_norm": 0.482178270816803, "learning_rate": 7.103195832781201e-06, "loss": 4.3118, "step": 24685 }, { "epoch": 0.7540012217470984, "grad_norm": 0.4775888919830322, "learning_rate": 7.10152093156983e-06, "loss": 4.2464, "step": 24686 }, { "epoch": 0.7540317654245571, "grad_norm": 0.49355408549308777, "learning_rate": 7.099846195158965e-06, "loss": 4.2255, "step": 24687 }, { "epoch": 0.7540623091020159, "grad_norm": 0.4743894338607788, "learning_rate": 7.098171623564012e-06, "loss": 4.2331, "step": 24688 }, { "epoch": 0.7540928527794747, "grad_norm": 0.47885745763778687, "learning_rate": 7.0964972168004044e-06, "loss": 4.2321, "step": 24689 }, { "epoch": 0.7541233964569334, "grad_norm": 0.48134303092956543, "learning_rate": 7.094822974883553e-06, "loss": 4.2158, "step": 24690 }, { "epoch": 0.7541539401343922, "grad_norm": 0.4725243151187897, "learning_rate": 7.093148897828864e-06, "loss": 4.2019, "step": 24691 }, { "epoch": 0.754184483811851, "grad_norm": 0.476998895406723, "learning_rate": 7.091474985651761e-06, "loss": 4.2251, "step": 24692 }, { "epoch": 0.7542150274893097, "grad_norm": 0.47683849930763245, "learning_rate": 7.0898012383676605e-06, "loss": 4.3444, "step": 24693 }, { "epoch": 0.7542455711667685, "grad_norm": 0.4915299415588379, "learning_rate": 7.088127655991964e-06, "loss": 4.2714, "step": 24694 }, { "epoch": 0.7542761148442273, "grad_norm": 0.47887828946113586, "learning_rate": 7.086454238540083e-06, "loss": 4.327, "step": 24695 }, { "epoch": 0.754306658521686, "grad_norm": 0.4935011863708496, "learning_rate": 7.084780986027437e-06, "loss": 4.2064, "step": 24696 }, { "epoch": 0.7543372021991448, "grad_norm": 0.4779396653175354, "learning_rate": 7.083107898469415e-06, "loss": 4.2587, "step": 24697 }, { "epoch": 0.7543677458766035, "grad_norm": 0.48491302132606506, "learning_rate": 7.08143497588144e-06, "loss": 4.2546, "step": 24698 }, { "epoch": 0.7543982895540623, "grad_norm": 0.4706638753414154, "learning_rate": 7.079762218278896e-06, "loss": 4.2354, "step": 24699 }, { "epoch": 0.7544288332315211, "grad_norm": 0.48103582859039307, "learning_rate": 7.078089625677195e-06, "loss": 4.2817, "step": 24700 }, { "epoch": 0.7544593769089798, "grad_norm": 0.4842877686023712, "learning_rate": 7.076417198091748e-06, "loss": 4.3047, "step": 24701 }, { "epoch": 0.7544899205864386, "grad_norm": 0.4840920865535736, "learning_rate": 7.074744935537933e-06, "loss": 4.3183, "step": 24702 }, { "epoch": 0.7545204642638974, "grad_norm": 0.4741629660129547, "learning_rate": 7.073072838031167e-06, "loss": 4.1568, "step": 24703 }, { "epoch": 0.7545510079413561, "grad_norm": 0.4799346625804901, "learning_rate": 7.071400905586828e-06, "loss": 4.2698, "step": 24704 }, { "epoch": 0.7545815516188149, "grad_norm": 0.4749390780925751, "learning_rate": 7.069729138220324e-06, "loss": 4.2642, "step": 24705 }, { "epoch": 0.7546120952962737, "grad_norm": 0.4871152639389038, "learning_rate": 7.068057535947037e-06, "loss": 4.2791, "step": 24706 }, { "epoch": 0.7546426389737324, "grad_norm": 0.4992429316043854, "learning_rate": 7.066386098782374e-06, "loss": 4.3319, "step": 24707 }, { "epoch": 0.7546731826511912, "grad_norm": 0.4728080928325653, "learning_rate": 7.064714826741703e-06, "loss": 4.2984, "step": 24708 }, { "epoch": 0.75470372632865, "grad_norm": 0.4920039474964142, "learning_rate": 7.063043719840426e-06, "loss": 4.2918, "step": 24709 }, { "epoch": 0.7547342700061087, "grad_norm": 0.4813133478164673, "learning_rate": 7.061372778093936e-06, "loss": 4.2593, "step": 24710 }, { "epoch": 0.7547648136835675, "grad_norm": 0.48607397079467773, "learning_rate": 7.059702001517601e-06, "loss": 4.1879, "step": 24711 }, { "epoch": 0.7547953573610263, "grad_norm": 0.4753287434577942, "learning_rate": 7.058031390126815e-06, "loss": 4.1593, "step": 24712 }, { "epoch": 0.754825901038485, "grad_norm": 0.4806613624095917, "learning_rate": 7.056360943936965e-06, "loss": 4.2588, "step": 24713 }, { "epoch": 0.7548564447159438, "grad_norm": 0.4818709194660187, "learning_rate": 7.05469066296342e-06, "loss": 4.2926, "step": 24714 }, { "epoch": 0.7548869883934025, "grad_norm": 0.4930564761161804, "learning_rate": 7.05302054722157e-06, "loss": 4.2844, "step": 24715 }, { "epoch": 0.7549175320708613, "grad_norm": 0.5263206958770752, "learning_rate": 7.05135059672678e-06, "loss": 4.2662, "step": 24716 }, { "epoch": 0.7549480757483201, "grad_norm": 0.48288992047309875, "learning_rate": 7.0496808114944356e-06, "loss": 4.1792, "step": 24717 }, { "epoch": 0.7549786194257788, "grad_norm": 0.4864902198314667, "learning_rate": 7.048011191539913e-06, "loss": 4.334, "step": 24718 }, { "epoch": 0.7550091631032376, "grad_norm": 0.4951504170894623, "learning_rate": 7.0463417368785785e-06, "loss": 4.3537, "step": 24719 }, { "epoch": 0.7550397067806964, "grad_norm": 0.4915436804294586, "learning_rate": 7.04467244752581e-06, "loss": 4.3025, "step": 24720 }, { "epoch": 0.7550702504581551, "grad_norm": 0.4803276062011719, "learning_rate": 7.043003323496974e-06, "loss": 4.2826, "step": 24721 }, { "epoch": 0.7551007941356139, "grad_norm": 0.4864640235900879, "learning_rate": 7.041334364807434e-06, "loss": 4.2847, "step": 24722 }, { "epoch": 0.7551313378130727, "grad_norm": 0.48091912269592285, "learning_rate": 7.039665571472562e-06, "loss": 4.2462, "step": 24723 }, { "epoch": 0.7551618814905314, "grad_norm": 0.47843658924102783, "learning_rate": 7.03799694350773e-06, "loss": 4.2075, "step": 24724 }, { "epoch": 0.7551924251679902, "grad_norm": 0.46869319677352905, "learning_rate": 7.036328480928286e-06, "loss": 4.1684, "step": 24725 }, { "epoch": 0.755222968845449, "grad_norm": 0.4815492331981659, "learning_rate": 7.034660183749603e-06, "loss": 4.2708, "step": 24726 }, { "epoch": 0.7552535125229077, "grad_norm": 0.46775102615356445, "learning_rate": 7.032992051987047e-06, "loss": 4.1431, "step": 24727 }, { "epoch": 0.7552840562003665, "grad_norm": 0.4715102016925812, "learning_rate": 7.031324085655966e-06, "loss": 4.2213, "step": 24728 }, { "epoch": 0.7553145998778253, "grad_norm": 0.47027868032455444, "learning_rate": 7.029656284771722e-06, "loss": 4.2845, "step": 24729 }, { "epoch": 0.755345143555284, "grad_norm": 0.48486924171447754, "learning_rate": 7.027988649349676e-06, "loss": 4.2868, "step": 24730 }, { "epoch": 0.7553756872327428, "grad_norm": 0.4781259000301361, "learning_rate": 7.026321179405176e-06, "loss": 4.3017, "step": 24731 }, { "epoch": 0.7554062309102015, "grad_norm": 0.4713513255119324, "learning_rate": 7.024653874953582e-06, "loss": 4.1944, "step": 24732 }, { "epoch": 0.7554367745876603, "grad_norm": 0.4729114770889282, "learning_rate": 7.022986736010237e-06, "loss": 4.1981, "step": 24733 }, { "epoch": 0.7554673182651191, "grad_norm": 0.480777770280838, "learning_rate": 7.021319762590495e-06, "loss": 4.2385, "step": 24734 }, { "epoch": 0.7554978619425778, "grad_norm": 0.4776122272014618, "learning_rate": 7.019652954709713e-06, "loss": 4.2218, "step": 24735 }, { "epoch": 0.7555284056200366, "grad_norm": 0.4718002676963806, "learning_rate": 7.0179863123832315e-06, "loss": 4.2765, "step": 24736 }, { "epoch": 0.7555589492974955, "grad_norm": 0.4704088270664215, "learning_rate": 7.016319835626387e-06, "loss": 4.2198, "step": 24737 }, { "epoch": 0.7555894929749541, "grad_norm": 0.47243136167526245, "learning_rate": 7.014653524454539e-06, "loss": 4.2098, "step": 24738 }, { "epoch": 0.755620036652413, "grad_norm": 0.48368293046951294, "learning_rate": 7.012987378883018e-06, "loss": 4.1469, "step": 24739 }, { "epoch": 0.7556505803298718, "grad_norm": 0.492349237203598, "learning_rate": 7.011321398927167e-06, "loss": 4.2206, "step": 24740 }, { "epoch": 0.7556811240073305, "grad_norm": 0.46974050998687744, "learning_rate": 7.00965558460234e-06, "loss": 4.3175, "step": 24741 }, { "epoch": 0.7557116676847893, "grad_norm": 0.47811517119407654, "learning_rate": 7.007989935923853e-06, "loss": 4.2674, "step": 24742 }, { "epoch": 0.7557422113622481, "grad_norm": 0.4775124490261078, "learning_rate": 7.006324452907054e-06, "loss": 4.2016, "step": 24743 }, { "epoch": 0.7557727550397068, "grad_norm": 0.48548322916030884, "learning_rate": 7.004659135567285e-06, "loss": 4.3134, "step": 24744 }, { "epoch": 0.7558032987171656, "grad_norm": 0.4820062816143036, "learning_rate": 7.002993983919865e-06, "loss": 4.2067, "step": 24745 }, { "epoch": 0.7558338423946244, "grad_norm": 0.4742109775543213, "learning_rate": 7.001328997980131e-06, "loss": 4.234, "step": 24746 }, { "epoch": 0.7558643860720831, "grad_norm": 0.4857803285121918, "learning_rate": 6.999664177763424e-06, "loss": 4.2517, "step": 24747 }, { "epoch": 0.7558949297495419, "grad_norm": 0.4791828989982605, "learning_rate": 6.9979995232850535e-06, "loss": 4.3179, "step": 24748 }, { "epoch": 0.7559254734270006, "grad_norm": 0.48468443751335144, "learning_rate": 6.996335034560369e-06, "loss": 4.363, "step": 24749 }, { "epoch": 0.7559560171044594, "grad_norm": 0.48044759035110474, "learning_rate": 6.9946707116046726e-06, "loss": 4.21, "step": 24750 }, { "epoch": 0.7559865607819182, "grad_norm": 0.4773324429988861, "learning_rate": 6.9930065544333095e-06, "loss": 4.3025, "step": 24751 }, { "epoch": 0.7560171044593769, "grad_norm": 0.4943501353263855, "learning_rate": 6.991342563061595e-06, "loss": 4.3509, "step": 24752 }, { "epoch": 0.7560476481368357, "grad_norm": 0.4827764332294464, "learning_rate": 6.98967873750484e-06, "loss": 4.2678, "step": 24753 }, { "epoch": 0.7560781918142945, "grad_norm": 0.49403849244117737, "learning_rate": 6.9880150777783735e-06, "loss": 4.2537, "step": 24754 }, { "epoch": 0.7561087354917532, "grad_norm": 0.48014935851097107, "learning_rate": 6.986351583897519e-06, "loss": 4.3068, "step": 24755 }, { "epoch": 0.756139279169212, "grad_norm": 0.47840866446495056, "learning_rate": 6.984688255877581e-06, "loss": 4.2511, "step": 24756 }, { "epoch": 0.7561698228466708, "grad_norm": 0.47709909081459045, "learning_rate": 6.983025093733878e-06, "loss": 4.3303, "step": 24757 }, { "epoch": 0.7562003665241295, "grad_norm": 0.47841620445251465, "learning_rate": 6.981362097481736e-06, "loss": 4.2056, "step": 24758 }, { "epoch": 0.7562309102015883, "grad_norm": 0.48649683594703674, "learning_rate": 6.97969926713645e-06, "loss": 4.2178, "step": 24759 }, { "epoch": 0.7562614538790471, "grad_norm": 0.48037639260292053, "learning_rate": 6.978036602713339e-06, "loss": 4.243, "step": 24760 }, { "epoch": 0.7562919975565058, "grad_norm": 0.4885111451148987, "learning_rate": 6.976374104227718e-06, "loss": 4.2927, "step": 24761 }, { "epoch": 0.7563225412339646, "grad_norm": 0.48161470890045166, "learning_rate": 6.974711771694878e-06, "loss": 4.2456, "step": 24762 }, { "epoch": 0.7563530849114234, "grad_norm": 0.48083260655403137, "learning_rate": 6.973049605130136e-06, "loss": 4.19, "step": 24763 }, { "epoch": 0.7563836285888821, "grad_norm": 0.48503515124320984, "learning_rate": 6.971387604548801e-06, "loss": 4.347, "step": 24764 }, { "epoch": 0.7564141722663409, "grad_norm": 0.4831911027431488, "learning_rate": 6.969725769966165e-06, "loss": 4.1875, "step": 24765 }, { "epoch": 0.7564447159437996, "grad_norm": 0.47316810488700867, "learning_rate": 6.968064101397539e-06, "loss": 4.2948, "step": 24766 }, { "epoch": 0.7564752596212584, "grad_norm": 0.4756770133972168, "learning_rate": 6.966402598858218e-06, "loss": 4.303, "step": 24767 }, { "epoch": 0.7565058032987172, "grad_norm": 0.4840349555015564, "learning_rate": 6.964741262363494e-06, "loss": 4.187, "step": 24768 }, { "epoch": 0.7565363469761759, "grad_norm": 0.4783800542354584, "learning_rate": 6.963080091928678e-06, "loss": 4.1688, "step": 24769 }, { "epoch": 0.7565668906536347, "grad_norm": 0.47758838534355164, "learning_rate": 6.961419087569049e-06, "loss": 4.0095, "step": 24770 }, { "epoch": 0.7565974343310935, "grad_norm": 0.473079651594162, "learning_rate": 6.9597582492999084e-06, "loss": 4.1342, "step": 24771 }, { "epoch": 0.7566279780085522, "grad_norm": 0.47455403208732605, "learning_rate": 6.958097577136557e-06, "loss": 4.1894, "step": 24772 }, { "epoch": 0.756658521686011, "grad_norm": 0.46239376068115234, "learning_rate": 6.956437071094268e-06, "loss": 4.221, "step": 24773 }, { "epoch": 0.7566890653634698, "grad_norm": 0.4794895350933075, "learning_rate": 6.954776731188342e-06, "loss": 4.3271, "step": 24774 }, { "epoch": 0.7567196090409285, "grad_norm": 0.48545870184898376, "learning_rate": 6.953116557434072e-06, "loss": 4.2788, "step": 24775 }, { "epoch": 0.7567501527183873, "grad_norm": 0.4725508987903595, "learning_rate": 6.95145654984673e-06, "loss": 4.23, "step": 24776 }, { "epoch": 0.7567806963958461, "grad_norm": 0.48805293440818787, "learning_rate": 6.949796708441605e-06, "loss": 4.2327, "step": 24777 }, { "epoch": 0.7568112400733048, "grad_norm": 0.4915430545806885, "learning_rate": 6.9481370332339924e-06, "loss": 4.2813, "step": 24778 }, { "epoch": 0.7568417837507636, "grad_norm": 0.475134015083313, "learning_rate": 6.9464775242391535e-06, "loss": 4.1719, "step": 24779 }, { "epoch": 0.7568723274282224, "grad_norm": 0.4849911332130432, "learning_rate": 6.944818181472379e-06, "loss": 4.289, "step": 24780 }, { "epoch": 0.7569028711056811, "grad_norm": 0.47285908460617065, "learning_rate": 6.9431590049489545e-06, "loss": 4.3015, "step": 24781 }, { "epoch": 0.7569334147831399, "grad_norm": 0.4827076196670532, "learning_rate": 6.941499994684148e-06, "loss": 4.2556, "step": 24782 }, { "epoch": 0.7569639584605986, "grad_norm": 0.47115856409072876, "learning_rate": 6.93984115069323e-06, "loss": 4.2165, "step": 24783 }, { "epoch": 0.7569945021380574, "grad_norm": 0.48451632261276245, "learning_rate": 6.938182472991487e-06, "loss": 4.2828, "step": 24784 }, { "epoch": 0.7570250458155162, "grad_norm": 0.47911322116851807, "learning_rate": 6.936523961594177e-06, "loss": 4.1967, "step": 24785 }, { "epoch": 0.7570555894929749, "grad_norm": 0.4866064190864563, "learning_rate": 6.9348656165165835e-06, "loss": 4.293, "step": 24786 }, { "epoch": 0.7570861331704337, "grad_norm": 0.49444836378097534, "learning_rate": 6.933207437773964e-06, "loss": 4.3411, "step": 24787 }, { "epoch": 0.7571166768478925, "grad_norm": 0.48286721110343933, "learning_rate": 6.931549425381595e-06, "loss": 4.247, "step": 24788 }, { "epoch": 0.7571472205253512, "grad_norm": 0.47879207134246826, "learning_rate": 6.9298915793547446e-06, "loss": 4.3172, "step": 24789 }, { "epoch": 0.75717776420281, "grad_norm": 0.49586424231529236, "learning_rate": 6.9282338997086695e-06, "loss": 4.2886, "step": 24790 }, { "epoch": 0.7572083078802688, "grad_norm": 0.48071300983428955, "learning_rate": 6.926576386458633e-06, "loss": 4.2712, "step": 24791 }, { "epoch": 0.7572388515577275, "grad_norm": 0.48696792125701904, "learning_rate": 6.924919039619909e-06, "loss": 4.238, "step": 24792 }, { "epoch": 0.7572693952351863, "grad_norm": 0.48088884353637695, "learning_rate": 6.923261859207742e-06, "loss": 4.2372, "step": 24793 }, { "epoch": 0.7572999389126451, "grad_norm": 0.4863945543766022, "learning_rate": 6.921604845237395e-06, "loss": 4.2438, "step": 24794 }, { "epoch": 0.7573304825901038, "grad_norm": 0.4776535928249359, "learning_rate": 6.919947997724135e-06, "loss": 4.2955, "step": 24795 }, { "epoch": 0.7573610262675626, "grad_norm": 0.48613837361335754, "learning_rate": 6.918291316683204e-06, "loss": 4.2024, "step": 24796 }, { "epoch": 0.7573915699450213, "grad_norm": 0.48759064078330994, "learning_rate": 6.916634802129868e-06, "loss": 4.2291, "step": 24797 }, { "epoch": 0.7574221136224801, "grad_norm": 0.47409504652023315, "learning_rate": 6.914978454079365e-06, "loss": 4.28, "step": 24798 }, { "epoch": 0.7574526572999389, "grad_norm": 0.4794938862323761, "learning_rate": 6.913322272546963e-06, "loss": 4.2599, "step": 24799 }, { "epoch": 0.7574832009773976, "grad_norm": 0.48334139585494995, "learning_rate": 6.9116662575479e-06, "loss": 4.2146, "step": 24800 }, { "epoch": 0.7575137446548564, "grad_norm": 0.47960183024406433, "learning_rate": 6.91001040909742e-06, "loss": 4.2235, "step": 24801 }, { "epoch": 0.7575442883323152, "grad_norm": 0.49563196301460266, "learning_rate": 6.908354727210773e-06, "loss": 4.1768, "step": 24802 }, { "epoch": 0.7575748320097739, "grad_norm": 0.4808397591114044, "learning_rate": 6.906699211903214e-06, "loss": 4.2656, "step": 24803 }, { "epoch": 0.7576053756872327, "grad_norm": 0.4714723825454712, "learning_rate": 6.905043863189972e-06, "loss": 4.2513, "step": 24804 }, { "epoch": 0.7576359193646915, "grad_norm": 0.4801948666572571, "learning_rate": 6.9033886810862955e-06, "loss": 4.2735, "step": 24805 }, { "epoch": 0.7576664630421502, "grad_norm": 0.48898571729660034, "learning_rate": 6.901733665607429e-06, "loss": 4.3064, "step": 24806 }, { "epoch": 0.757697006719609, "grad_norm": 0.47827816009521484, "learning_rate": 6.900078816768599e-06, "loss": 4.2338, "step": 24807 }, { "epoch": 0.7577275503970679, "grad_norm": 0.47922664880752563, "learning_rate": 6.8984241345850494e-06, "loss": 4.3246, "step": 24808 }, { "epoch": 0.7577580940745265, "grad_norm": 0.4776289463043213, "learning_rate": 6.896769619072021e-06, "loss": 4.345, "step": 24809 }, { "epoch": 0.7577886377519854, "grad_norm": 0.4767370820045471, "learning_rate": 6.895115270244737e-06, "loss": 4.1462, "step": 24810 }, { "epoch": 0.7578191814294442, "grad_norm": 0.47879716753959656, "learning_rate": 6.893461088118436e-06, "loss": 4.2799, "step": 24811 }, { "epoch": 0.7578497251069028, "grad_norm": 0.4823344945907593, "learning_rate": 6.891807072708356e-06, "loss": 4.2355, "step": 24812 }, { "epoch": 0.7578802687843617, "grad_norm": 0.47668278217315674, "learning_rate": 6.890153224029716e-06, "loss": 4.2136, "step": 24813 }, { "epoch": 0.7579108124618203, "grad_norm": 0.4752461910247803, "learning_rate": 6.888499542097743e-06, "loss": 4.2385, "step": 24814 }, { "epoch": 0.7579413561392792, "grad_norm": 0.475734680891037, "learning_rate": 6.886846026927671e-06, "loss": 4.2607, "step": 24815 }, { "epoch": 0.757971899816738, "grad_norm": 0.47662031650543213, "learning_rate": 6.885192678534713e-06, "loss": 4.2758, "step": 24816 }, { "epoch": 0.7580024434941967, "grad_norm": 0.4799623489379883, "learning_rate": 6.8835394969341075e-06, "loss": 4.2643, "step": 24817 }, { "epoch": 0.7580329871716555, "grad_norm": 0.4896656274795532, "learning_rate": 6.8818864821410615e-06, "loss": 4.3029, "step": 24818 }, { "epoch": 0.7580635308491143, "grad_norm": 0.4874849021434784, "learning_rate": 6.880233634170805e-06, "loss": 4.363, "step": 24819 }, { "epoch": 0.758094074526573, "grad_norm": 0.4853630065917969, "learning_rate": 6.878580953038557e-06, "loss": 4.2047, "step": 24820 }, { "epoch": 0.7581246182040318, "grad_norm": 0.47755539417266846, "learning_rate": 6.876928438759525e-06, "loss": 4.3169, "step": 24821 }, { "epoch": 0.7581551618814906, "grad_norm": 0.4824736416339874, "learning_rate": 6.875276091348931e-06, "loss": 4.1926, "step": 24822 }, { "epoch": 0.7581857055589493, "grad_norm": 0.47834768891334534, "learning_rate": 6.873623910821997e-06, "loss": 4.304, "step": 24823 }, { "epoch": 0.7582162492364081, "grad_norm": 0.4763719439506531, "learning_rate": 6.8719718971939185e-06, "loss": 4.2814, "step": 24824 }, { "epoch": 0.7582467929138669, "grad_norm": 0.4856188893318176, "learning_rate": 6.870320050479914e-06, "loss": 4.2258, "step": 24825 }, { "epoch": 0.7582773365913256, "grad_norm": 0.4771431088447571, "learning_rate": 6.868668370695205e-06, "loss": 4.1908, "step": 24826 }, { "epoch": 0.7583078802687844, "grad_norm": 0.47554218769073486, "learning_rate": 6.86701685785498e-06, "loss": 4.2625, "step": 24827 }, { "epoch": 0.7583384239462432, "grad_norm": 0.48241564631462097, "learning_rate": 6.865365511974458e-06, "loss": 4.3036, "step": 24828 }, { "epoch": 0.7583689676237019, "grad_norm": 0.4802331328392029, "learning_rate": 6.863714333068838e-06, "loss": 4.1975, "step": 24829 }, { "epoch": 0.7583995113011607, "grad_norm": 0.48030808568000793, "learning_rate": 6.862063321153328e-06, "loss": 4.2289, "step": 24830 }, { "epoch": 0.7584300549786194, "grad_norm": 0.4841996133327484, "learning_rate": 6.860412476243128e-06, "loss": 4.334, "step": 24831 }, { "epoch": 0.7584605986560782, "grad_norm": 0.47219204902648926, "learning_rate": 6.8587617983534304e-06, "loss": 4.224, "step": 24832 }, { "epoch": 0.758491142333537, "grad_norm": 0.4989498257637024, "learning_rate": 6.857111287499438e-06, "loss": 4.1803, "step": 24833 }, { "epoch": 0.7585216860109957, "grad_norm": 0.4810517430305481, "learning_rate": 6.8554609436963595e-06, "loss": 4.2716, "step": 24834 }, { "epoch": 0.7585522296884545, "grad_norm": 0.4839790463447571, "learning_rate": 6.853810766959373e-06, "loss": 4.2727, "step": 24835 }, { "epoch": 0.7585827733659133, "grad_norm": 0.47605884075164795, "learning_rate": 6.85216075730368e-06, "loss": 4.2912, "step": 24836 }, { "epoch": 0.758613317043372, "grad_norm": 0.48631322383880615, "learning_rate": 6.850510914744482e-06, "loss": 4.2383, "step": 24837 }, { "epoch": 0.7586438607208308, "grad_norm": 0.48464080691337585, "learning_rate": 6.848861239296952e-06, "loss": 4.2648, "step": 24838 }, { "epoch": 0.7586744043982896, "grad_norm": 0.4943181276321411, "learning_rate": 6.847211730976291e-06, "loss": 4.2638, "step": 24839 }, { "epoch": 0.7587049480757483, "grad_norm": 0.47814738750457764, "learning_rate": 6.8455623897976916e-06, "loss": 4.26, "step": 24840 }, { "epoch": 0.7587354917532071, "grad_norm": 0.48940858244895935, "learning_rate": 6.843913215776326e-06, "loss": 4.2363, "step": 24841 }, { "epoch": 0.7587660354306659, "grad_norm": 0.4874340891838074, "learning_rate": 6.842264208927388e-06, "loss": 4.2224, "step": 24842 }, { "epoch": 0.7587965791081246, "grad_norm": 0.47325557470321655, "learning_rate": 6.840615369266063e-06, "loss": 4.2401, "step": 24843 }, { "epoch": 0.7588271227855834, "grad_norm": 0.478625625371933, "learning_rate": 6.838966696807525e-06, "loss": 4.3061, "step": 24844 }, { "epoch": 0.7588576664630422, "grad_norm": 0.4888010323047638, "learning_rate": 6.837318191566963e-06, "loss": 4.2365, "step": 24845 }, { "epoch": 0.7588882101405009, "grad_norm": 0.48605653643608093, "learning_rate": 6.835669853559554e-06, "loss": 4.3381, "step": 24846 }, { "epoch": 0.7589187538179597, "grad_norm": 0.47870033979415894, "learning_rate": 6.8340216828004595e-06, "loss": 4.2245, "step": 24847 }, { "epoch": 0.7589492974954184, "grad_norm": 0.48973119258880615, "learning_rate": 6.832373679304879e-06, "loss": 4.2495, "step": 24848 }, { "epoch": 0.7589798411728772, "grad_norm": 0.4809495210647583, "learning_rate": 6.830725843087965e-06, "loss": 4.2526, "step": 24849 }, { "epoch": 0.759010384850336, "grad_norm": 0.4741043150424957, "learning_rate": 6.8290781741649014e-06, "loss": 4.1683, "step": 24850 }, { "epoch": 0.7590409285277947, "grad_norm": 0.4713355004787445, "learning_rate": 6.827430672550863e-06, "loss": 4.2315, "step": 24851 }, { "epoch": 0.7590714722052535, "grad_norm": 0.48248937726020813, "learning_rate": 6.82578333826101e-06, "loss": 4.2465, "step": 24852 }, { "epoch": 0.7591020158827123, "grad_norm": 0.5061601400375366, "learning_rate": 6.824136171310511e-06, "loss": 4.2467, "step": 24853 }, { "epoch": 0.759132559560171, "grad_norm": 0.47802653908729553, "learning_rate": 6.8224891717145436e-06, "loss": 4.2862, "step": 24854 }, { "epoch": 0.7591631032376298, "grad_norm": 0.47774213552474976, "learning_rate": 6.820842339488259e-06, "loss": 4.2946, "step": 24855 }, { "epoch": 0.7591936469150886, "grad_norm": 0.486637681722641, "learning_rate": 6.819195674646822e-06, "loss": 4.3312, "step": 24856 }, { "epoch": 0.7592241905925473, "grad_norm": 0.47699272632598877, "learning_rate": 6.817549177205409e-06, "loss": 4.2637, "step": 24857 }, { "epoch": 0.7592547342700061, "grad_norm": 0.4808458089828491, "learning_rate": 6.8159028471791594e-06, "loss": 4.2106, "step": 24858 }, { "epoch": 0.7592852779474649, "grad_norm": 0.48838186264038086, "learning_rate": 6.814256684583251e-06, "loss": 4.2845, "step": 24859 }, { "epoch": 0.7593158216249236, "grad_norm": 0.4835355877876282, "learning_rate": 6.812610689432822e-06, "loss": 4.3202, "step": 24860 }, { "epoch": 0.7593463653023824, "grad_norm": 0.47687792778015137, "learning_rate": 6.810964861743047e-06, "loss": 4.2837, "step": 24861 }, { "epoch": 0.7593769089798412, "grad_norm": 0.4651937782764435, "learning_rate": 6.80931920152906e-06, "loss": 4.2081, "step": 24862 }, { "epoch": 0.7594074526572999, "grad_norm": 0.47967174649238586, "learning_rate": 6.807673708806034e-06, "loss": 4.2408, "step": 24863 }, { "epoch": 0.7594379963347587, "grad_norm": 0.48036473989486694, "learning_rate": 6.8060283835890994e-06, "loss": 4.2662, "step": 24864 }, { "epoch": 0.7594685400122174, "grad_norm": 0.4802115857601166, "learning_rate": 6.804383225893427e-06, "loss": 4.3131, "step": 24865 }, { "epoch": 0.7594990836896762, "grad_norm": 0.4893636405467987, "learning_rate": 6.802738235734144e-06, "loss": 4.2675, "step": 24866 }, { "epoch": 0.759529627367135, "grad_norm": 0.49214792251586914, "learning_rate": 6.801093413126405e-06, "loss": 4.2666, "step": 24867 }, { "epoch": 0.7595601710445937, "grad_norm": 0.4900408685207367, "learning_rate": 6.799448758085366e-06, "loss": 4.3608, "step": 24868 }, { "epoch": 0.7595907147220525, "grad_norm": 0.4912932813167572, "learning_rate": 6.797804270626151e-06, "loss": 4.2181, "step": 24869 }, { "epoch": 0.7596212583995113, "grad_norm": 0.4852510094642639, "learning_rate": 6.796159950763911e-06, "loss": 4.2237, "step": 24870 }, { "epoch": 0.75965180207697, "grad_norm": 0.4855740964412689, "learning_rate": 6.794515798513796e-06, "loss": 4.2301, "step": 24871 }, { "epoch": 0.7596823457544288, "grad_norm": 0.4778454899787903, "learning_rate": 6.792871813890922e-06, "loss": 4.3074, "step": 24872 }, { "epoch": 0.7597128894318876, "grad_norm": 0.4784538447856903, "learning_rate": 6.79122799691044e-06, "loss": 4.1843, "step": 24873 }, { "epoch": 0.7597434331093463, "grad_norm": 0.47879013419151306, "learning_rate": 6.789584347587494e-06, "loss": 4.1307, "step": 24874 }, { "epoch": 0.7597739767868051, "grad_norm": 0.4848255217075348, "learning_rate": 6.787940865937198e-06, "loss": 4.1417, "step": 24875 }, { "epoch": 0.7598045204642639, "grad_norm": 0.47076278924942017, "learning_rate": 6.786297551974702e-06, "loss": 4.2741, "step": 24876 }, { "epoch": 0.7598350641417226, "grad_norm": 0.4869246780872345, "learning_rate": 6.78465440571513e-06, "loss": 4.1217, "step": 24877 }, { "epoch": 0.7598656078191814, "grad_norm": 0.48119327425956726, "learning_rate": 6.7830114271735996e-06, "loss": 4.2991, "step": 24878 }, { "epoch": 0.7598961514966402, "grad_norm": 0.4707511067390442, "learning_rate": 6.781368616365252e-06, "loss": 4.2541, "step": 24879 }, { "epoch": 0.7599266951740989, "grad_norm": 0.4683864414691925, "learning_rate": 6.779725973305218e-06, "loss": 4.2868, "step": 24880 }, { "epoch": 0.7599572388515577, "grad_norm": 0.47889629006385803, "learning_rate": 6.7780834980086055e-06, "loss": 4.2921, "step": 24881 }, { "epoch": 0.7599877825290164, "grad_norm": 0.49164390563964844, "learning_rate": 6.776441190490556e-06, "loss": 4.1475, "step": 24882 }, { "epoch": 0.7600183262064752, "grad_norm": 0.4738236367702484, "learning_rate": 6.774799050766176e-06, "loss": 4.2046, "step": 24883 }, { "epoch": 0.760048869883934, "grad_norm": 0.4898431599140167, "learning_rate": 6.773157078850589e-06, "loss": 4.3447, "step": 24884 }, { "epoch": 0.7600794135613927, "grad_norm": 0.47565943002700806, "learning_rate": 6.771515274758924e-06, "loss": 4.2017, "step": 24885 }, { "epoch": 0.7601099572388516, "grad_norm": 0.47749799489974976, "learning_rate": 6.769873638506286e-06, "loss": 4.2724, "step": 24886 }, { "epoch": 0.7601405009163104, "grad_norm": 0.47294536232948303, "learning_rate": 6.768232170107791e-06, "loss": 4.269, "step": 24887 }, { "epoch": 0.760171044593769, "grad_norm": 0.4772084057331085, "learning_rate": 6.766590869578565e-06, "loss": 4.2796, "step": 24888 }, { "epoch": 0.7602015882712279, "grad_norm": 0.4869403839111328, "learning_rate": 6.764949736933704e-06, "loss": 4.2877, "step": 24889 }, { "epoch": 0.7602321319486867, "grad_norm": 0.4785246253013611, "learning_rate": 6.7633087721883235e-06, "loss": 4.2768, "step": 24890 }, { "epoch": 0.7602626756261454, "grad_norm": 0.4839174151420593, "learning_rate": 6.7616679753575466e-06, "loss": 4.2838, "step": 24891 }, { "epoch": 0.7602932193036042, "grad_norm": 0.483124703168869, "learning_rate": 6.760027346456468e-06, "loss": 4.2283, "step": 24892 }, { "epoch": 0.760323762981063, "grad_norm": 0.49249550700187683, "learning_rate": 6.75838688550019e-06, "loss": 4.1754, "step": 24893 }, { "epoch": 0.7603543066585217, "grad_norm": 0.48172053694725037, "learning_rate": 6.756746592503829e-06, "loss": 4.2895, "step": 24894 }, { "epoch": 0.7603848503359805, "grad_norm": 0.47704967856407166, "learning_rate": 6.755106467482475e-06, "loss": 4.1963, "step": 24895 }, { "epoch": 0.7604153940134393, "grad_norm": 0.47954919934272766, "learning_rate": 6.7534665104512344e-06, "loss": 4.2167, "step": 24896 }, { "epoch": 0.760445937690898, "grad_norm": 0.48096567392349243, "learning_rate": 6.751826721425219e-06, "loss": 4.294, "step": 24897 }, { "epoch": 0.7604764813683568, "grad_norm": 0.47459322214126587, "learning_rate": 6.750187100419509e-06, "loss": 4.2751, "step": 24898 }, { "epoch": 0.7605070250458155, "grad_norm": 0.4829421043395996, "learning_rate": 6.748547647449216e-06, "loss": 4.2035, "step": 24899 }, { "epoch": 0.7605375687232743, "grad_norm": 0.48120760917663574, "learning_rate": 6.746908362529422e-06, "loss": 4.1634, "step": 24900 }, { "epoch": 0.7605681124007331, "grad_norm": 0.4803934395313263, "learning_rate": 6.745269245675229e-06, "loss": 4.2289, "step": 24901 }, { "epoch": 0.7605986560781918, "grad_norm": 0.4863623380661011, "learning_rate": 6.743630296901732e-06, "loss": 4.2879, "step": 24902 }, { "epoch": 0.7606291997556506, "grad_norm": 0.48231932520866394, "learning_rate": 6.741991516224011e-06, "loss": 4.2162, "step": 24903 }, { "epoch": 0.7606597434331094, "grad_norm": 0.4814736843109131, "learning_rate": 6.740352903657163e-06, "loss": 4.1837, "step": 24904 }, { "epoch": 0.7606902871105681, "grad_norm": 0.4837370812892914, "learning_rate": 6.73871445921628e-06, "loss": 4.2874, "step": 24905 }, { "epoch": 0.7607208307880269, "grad_norm": 0.4834352433681488, "learning_rate": 6.737076182916435e-06, "loss": 4.2474, "step": 24906 }, { "epoch": 0.7607513744654857, "grad_norm": 0.47877609729766846, "learning_rate": 6.735438074772729e-06, "loss": 4.3628, "step": 24907 }, { "epoch": 0.7607819181429444, "grad_norm": 0.501076877117157, "learning_rate": 6.733800134800225e-06, "loss": 4.2826, "step": 24908 }, { "epoch": 0.7608124618204032, "grad_norm": 0.4829834997653961, "learning_rate": 6.732162363014021e-06, "loss": 4.2743, "step": 24909 }, { "epoch": 0.760843005497862, "grad_norm": 0.48379117250442505, "learning_rate": 6.730524759429188e-06, "loss": 4.3166, "step": 24910 }, { "epoch": 0.7608735491753207, "grad_norm": 0.4891217350959778, "learning_rate": 6.728887324060812e-06, "loss": 4.1811, "step": 24911 }, { "epoch": 0.7609040928527795, "grad_norm": 0.47984403371810913, "learning_rate": 6.727250056923956e-06, "loss": 4.2384, "step": 24912 }, { "epoch": 0.7609346365302383, "grad_norm": 0.4824817478656769, "learning_rate": 6.725612958033703e-06, "loss": 4.2349, "step": 24913 }, { "epoch": 0.760965180207697, "grad_norm": 0.48421651124954224, "learning_rate": 6.723976027405135e-06, "loss": 4.1624, "step": 24914 }, { "epoch": 0.7609957238851558, "grad_norm": 0.48101526498794556, "learning_rate": 6.722339265053309e-06, "loss": 4.1769, "step": 24915 }, { "epoch": 0.7610262675626145, "grad_norm": 0.48519715666770935, "learning_rate": 6.720702670993312e-06, "loss": 4.2556, "step": 24916 }, { "epoch": 0.7610568112400733, "grad_norm": 0.4746374785900116, "learning_rate": 6.7190662452401965e-06, "loss": 4.2491, "step": 24917 }, { "epoch": 0.7610873549175321, "grad_norm": 0.48844340443611145, "learning_rate": 6.717429987809035e-06, "loss": 4.2683, "step": 24918 }, { "epoch": 0.7611178985949908, "grad_norm": 0.48951059579849243, "learning_rate": 6.715793898714903e-06, "loss": 4.32, "step": 24919 }, { "epoch": 0.7611484422724496, "grad_norm": 0.4870547652244568, "learning_rate": 6.714157977972852e-06, "loss": 4.2722, "step": 24920 }, { "epoch": 0.7611789859499084, "grad_norm": 0.47191616892814636, "learning_rate": 6.712522225597948e-06, "loss": 4.2173, "step": 24921 }, { "epoch": 0.7612095296273671, "grad_norm": 0.47581204771995544, "learning_rate": 6.710886641605263e-06, "loss": 4.2619, "step": 24922 }, { "epoch": 0.7612400733048259, "grad_norm": 0.48938921093940735, "learning_rate": 6.7092512260098495e-06, "loss": 4.3108, "step": 24923 }, { "epoch": 0.7612706169822847, "grad_norm": 0.4757575988769531, "learning_rate": 6.707615978826753e-06, "loss": 4.3083, "step": 24924 }, { "epoch": 0.7613011606597434, "grad_norm": 0.48028331995010376, "learning_rate": 6.705980900071051e-06, "loss": 4.2259, "step": 24925 }, { "epoch": 0.7613317043372022, "grad_norm": 0.49026620388031006, "learning_rate": 6.704345989757782e-06, "loss": 4.2724, "step": 24926 }, { "epoch": 0.761362248014661, "grad_norm": 0.4728502333164215, "learning_rate": 6.702711247902005e-06, "loss": 4.2668, "step": 24927 }, { "epoch": 0.7613927916921197, "grad_norm": 0.48226645588874817, "learning_rate": 6.7010766745187805e-06, "loss": 4.2834, "step": 24928 }, { "epoch": 0.7614233353695785, "grad_norm": 0.490682452917099, "learning_rate": 6.699442269623143e-06, "loss": 4.2261, "step": 24929 }, { "epoch": 0.7614538790470373, "grad_norm": 0.4825116693973541, "learning_rate": 6.697808033230152e-06, "loss": 4.1536, "step": 24930 }, { "epoch": 0.761484422724496, "grad_norm": 0.47110021114349365, "learning_rate": 6.69617396535486e-06, "loss": 4.2789, "step": 24931 }, { "epoch": 0.7615149664019548, "grad_norm": 0.4829843044281006, "learning_rate": 6.694540066012295e-06, "loss": 4.277, "step": 24932 }, { "epoch": 0.7615455100794135, "grad_norm": 0.4855625033378601, "learning_rate": 6.692906335217522e-06, "loss": 4.3182, "step": 24933 }, { "epoch": 0.7615760537568723, "grad_norm": 0.4908196032047272, "learning_rate": 6.691272772985563e-06, "loss": 4.2795, "step": 24934 }, { "epoch": 0.7616065974343311, "grad_norm": 0.5035399794578552, "learning_rate": 6.6896393793314695e-06, "loss": 4.3761, "step": 24935 }, { "epoch": 0.7616371411117898, "grad_norm": 0.4819846451282501, "learning_rate": 6.688006154270288e-06, "loss": 4.2897, "step": 24936 }, { "epoch": 0.7616676847892486, "grad_norm": 0.48642683029174805, "learning_rate": 6.686373097817042e-06, "loss": 4.2625, "step": 24937 }, { "epoch": 0.7616982284667074, "grad_norm": 0.49045854806900024, "learning_rate": 6.684740209986781e-06, "loss": 4.3675, "step": 24938 }, { "epoch": 0.7617287721441661, "grad_norm": 0.505057156085968, "learning_rate": 6.68310749079453e-06, "loss": 4.191, "step": 24939 }, { "epoch": 0.7617593158216249, "grad_norm": 0.48146575689315796, "learning_rate": 6.6814749402553275e-06, "loss": 4.2636, "step": 24940 }, { "epoch": 0.7617898594990837, "grad_norm": 0.49271437525749207, "learning_rate": 6.6798425583842e-06, "loss": 4.3045, "step": 24941 }, { "epoch": 0.7618204031765424, "grad_norm": 0.4888039827346802, "learning_rate": 6.678210345196189e-06, "loss": 4.2063, "step": 24942 }, { "epoch": 0.7618509468540012, "grad_norm": 0.48830917477607727, "learning_rate": 6.676578300706307e-06, "loss": 4.2748, "step": 24943 }, { "epoch": 0.76188149053146, "grad_norm": 0.47293055057525635, "learning_rate": 6.67494642492959e-06, "loss": 4.2751, "step": 24944 }, { "epoch": 0.7619120342089187, "grad_norm": 0.47260305285453796, "learning_rate": 6.673314717881071e-06, "loss": 4.2706, "step": 24945 }, { "epoch": 0.7619425778863775, "grad_norm": 0.48195040225982666, "learning_rate": 6.671683179575758e-06, "loss": 4.2636, "step": 24946 }, { "epoch": 0.7619731215638362, "grad_norm": 0.4816971719264984, "learning_rate": 6.670051810028688e-06, "loss": 4.1611, "step": 24947 }, { "epoch": 0.762003665241295, "grad_norm": 0.4964480698108673, "learning_rate": 6.668420609254869e-06, "loss": 4.2645, "step": 24948 }, { "epoch": 0.7620342089187538, "grad_norm": 0.4748096466064453, "learning_rate": 6.666789577269325e-06, "loss": 4.2391, "step": 24949 }, { "epoch": 0.7620647525962125, "grad_norm": 0.46665728092193604, "learning_rate": 6.665158714087086e-06, "loss": 4.1357, "step": 24950 }, { "epoch": 0.7620952962736713, "grad_norm": 0.47988083958625793, "learning_rate": 6.6635280197231475e-06, "loss": 4.3227, "step": 24951 }, { "epoch": 0.7621258399511301, "grad_norm": 0.4857044816017151, "learning_rate": 6.661897494192534e-06, "loss": 4.2814, "step": 24952 }, { "epoch": 0.7621563836285888, "grad_norm": 0.48869243264198303, "learning_rate": 6.660267137510268e-06, "loss": 4.1865, "step": 24953 }, { "epoch": 0.7621869273060476, "grad_norm": 0.4800872206687927, "learning_rate": 6.658636949691343e-06, "loss": 4.2777, "step": 24954 }, { "epoch": 0.7622174709835065, "grad_norm": 0.4838218688964844, "learning_rate": 6.657006930750787e-06, "loss": 4.286, "step": 24955 }, { "epoch": 0.7622480146609651, "grad_norm": 0.48729628324508667, "learning_rate": 6.655377080703598e-06, "loss": 4.1081, "step": 24956 }, { "epoch": 0.762278558338424, "grad_norm": 0.48426851630210876, "learning_rate": 6.6537473995647745e-06, "loss": 4.2042, "step": 24957 }, { "epoch": 0.7623091020158828, "grad_norm": 0.4820815920829773, "learning_rate": 6.6521178873493354e-06, "loss": 4.2806, "step": 24958 }, { "epoch": 0.7623396456933415, "grad_norm": 0.48660895228385925, "learning_rate": 6.650488544072287e-06, "loss": 4.2573, "step": 24959 }, { "epoch": 0.7623701893708003, "grad_norm": 0.47998252511024475, "learning_rate": 6.648859369748614e-06, "loss": 4.2772, "step": 24960 }, { "epoch": 0.7624007330482591, "grad_norm": 0.4815707802772522, "learning_rate": 6.647230364393331e-06, "loss": 4.2597, "step": 24961 }, { "epoch": 0.7624312767257178, "grad_norm": 0.47955888509750366, "learning_rate": 6.645601528021442e-06, "loss": 4.1635, "step": 24962 }, { "epoch": 0.7624618204031766, "grad_norm": 0.516834557056427, "learning_rate": 6.643972860647929e-06, "loss": 4.1797, "step": 24963 }, { "epoch": 0.7624923640806353, "grad_norm": 0.4852997064590454, "learning_rate": 6.6423443622878e-06, "loss": 4.1664, "step": 24964 }, { "epoch": 0.7625229077580941, "grad_norm": 0.47944650053977966, "learning_rate": 6.6407160329560405e-06, "loss": 4.294, "step": 24965 }, { "epoch": 0.7625534514355529, "grad_norm": 0.48101118206977844, "learning_rate": 6.639087872667649e-06, "loss": 4.2319, "step": 24966 }, { "epoch": 0.7625839951130116, "grad_norm": 0.4805649518966675, "learning_rate": 6.637459881437621e-06, "loss": 4.3174, "step": 24967 }, { "epoch": 0.7626145387904704, "grad_norm": 0.4878823459148407, "learning_rate": 6.635832059280933e-06, "loss": 4.1307, "step": 24968 }, { "epoch": 0.7626450824679292, "grad_norm": 0.48540008068084717, "learning_rate": 6.634204406212591e-06, "loss": 4.2695, "step": 24969 }, { "epoch": 0.7626756261453879, "grad_norm": 0.4852267801761627, "learning_rate": 6.63257692224756e-06, "loss": 4.2577, "step": 24970 }, { "epoch": 0.7627061698228467, "grad_norm": 0.4780956208705902, "learning_rate": 6.630949607400849e-06, "loss": 4.2242, "step": 24971 }, { "epoch": 0.7627367135003055, "grad_norm": 0.4923604726791382, "learning_rate": 6.629322461687421e-06, "loss": 4.2863, "step": 24972 }, { "epoch": 0.7627672571777642, "grad_norm": 0.4821442663669586, "learning_rate": 6.627695485122273e-06, "loss": 4.1652, "step": 24973 }, { "epoch": 0.762797800855223, "grad_norm": 0.4716311991214752, "learning_rate": 6.626068677720371e-06, "loss": 4.1827, "step": 24974 }, { "epoch": 0.7628283445326818, "grad_norm": 0.4714632034301758, "learning_rate": 6.6244420394967e-06, "loss": 4.2222, "step": 24975 }, { "epoch": 0.7628588882101405, "grad_norm": 0.4936082661151886, "learning_rate": 6.622815570466251e-06, "loss": 4.2674, "step": 24976 }, { "epoch": 0.7628894318875993, "grad_norm": 0.4936147928237915, "learning_rate": 6.621189270643977e-06, "loss": 4.3028, "step": 24977 }, { "epoch": 0.7629199755650581, "grad_norm": 0.47902220487594604, "learning_rate": 6.619563140044863e-06, "loss": 4.2403, "step": 24978 }, { "epoch": 0.7629505192425168, "grad_norm": 0.4862053692340851, "learning_rate": 6.617937178683889e-06, "loss": 4.3237, "step": 24979 }, { "epoch": 0.7629810629199756, "grad_norm": 0.49587517976760864, "learning_rate": 6.6163113865760104e-06, "loss": 4.2554, "step": 24980 }, { "epoch": 0.7630116065974343, "grad_norm": 0.4876997470855713, "learning_rate": 6.6146857637362144e-06, "loss": 4.2456, "step": 24981 }, { "epoch": 0.7630421502748931, "grad_norm": 0.4739096760749817, "learning_rate": 6.61306031017945e-06, "loss": 4.1669, "step": 24982 }, { "epoch": 0.7630726939523519, "grad_norm": 0.48329177498817444, "learning_rate": 6.611435025920693e-06, "loss": 4.2444, "step": 24983 }, { "epoch": 0.7631032376298106, "grad_norm": 0.4936222732067108, "learning_rate": 6.6098099109749175e-06, "loss": 4.3314, "step": 24984 }, { "epoch": 0.7631337813072694, "grad_norm": 0.48400360345840454, "learning_rate": 6.608184965357067e-06, "loss": 4.3089, "step": 24985 }, { "epoch": 0.7631643249847282, "grad_norm": 0.48248258233070374, "learning_rate": 6.606560189082123e-06, "loss": 4.319, "step": 24986 }, { "epoch": 0.7631948686621869, "grad_norm": 0.48620373010635376, "learning_rate": 6.6049355821650365e-06, "loss": 4.2356, "step": 24987 }, { "epoch": 0.7632254123396457, "grad_norm": 0.502940833568573, "learning_rate": 6.603311144620758e-06, "loss": 4.2538, "step": 24988 }, { "epoch": 0.7632559560171045, "grad_norm": 0.4874105155467987, "learning_rate": 6.601686876464253e-06, "loss": 4.2132, "step": 24989 }, { "epoch": 0.7632864996945632, "grad_norm": 0.4862403869628906, "learning_rate": 6.600062777710483e-06, "loss": 4.2705, "step": 24990 }, { "epoch": 0.763317043372022, "grad_norm": 0.4816321134567261, "learning_rate": 6.598438848374388e-06, "loss": 4.2577, "step": 24991 }, { "epoch": 0.7633475870494808, "grad_norm": 0.47945740818977356, "learning_rate": 6.596815088470928e-06, "loss": 4.2208, "step": 24992 }, { "epoch": 0.7633781307269395, "grad_norm": 0.4812130033969879, "learning_rate": 6.595191498015063e-06, "loss": 4.2667, "step": 24993 }, { "epoch": 0.7634086744043983, "grad_norm": 0.4784107804298401, "learning_rate": 6.593568077021722e-06, "loss": 4.2681, "step": 24994 }, { "epoch": 0.7634392180818571, "grad_norm": 0.4770527482032776, "learning_rate": 6.591944825505864e-06, "loss": 4.2847, "step": 24995 }, { "epoch": 0.7634697617593158, "grad_norm": 0.4829127788543701, "learning_rate": 6.590321743482445e-06, "loss": 4.1779, "step": 24996 }, { "epoch": 0.7635003054367746, "grad_norm": 0.4843038022518158, "learning_rate": 6.588698830966386e-06, "loss": 4.375, "step": 24997 }, { "epoch": 0.7635308491142333, "grad_norm": 0.48047393560409546, "learning_rate": 6.587076087972655e-06, "loss": 4.2106, "step": 24998 }, { "epoch": 0.7635613927916921, "grad_norm": 0.4816960394382477, "learning_rate": 6.585453514516171e-06, "loss": 4.2887, "step": 24999 }, { "epoch": 0.7635919364691509, "grad_norm": 0.47607842087745667, "learning_rate": 6.583831110611888e-06, "loss": 4.2887, "step": 25000 }, { "epoch": 0.7636224801466096, "grad_norm": 0.477215051651001, "learning_rate": 6.582208876274745e-06, "loss": 4.2143, "step": 25001 }, { "epoch": 0.7636530238240684, "grad_norm": 0.4858311414718628, "learning_rate": 6.580586811519673e-06, "loss": 4.2693, "step": 25002 }, { "epoch": 0.7636835675015272, "grad_norm": 0.485322505235672, "learning_rate": 6.5789649163616045e-06, "loss": 4.2779, "step": 25003 }, { "epoch": 0.7637141111789859, "grad_norm": 0.4719832241535187, "learning_rate": 6.577343190815485e-06, "loss": 4.207, "step": 25004 }, { "epoch": 0.7637446548564447, "grad_norm": 0.49429455399513245, "learning_rate": 6.5757216348962285e-06, "loss": 4.2988, "step": 25005 }, { "epoch": 0.7637751985339035, "grad_norm": 0.4791110157966614, "learning_rate": 6.574100248618778e-06, "loss": 4.3198, "step": 25006 }, { "epoch": 0.7638057422113622, "grad_norm": 0.5045627355575562, "learning_rate": 6.572479031998066e-06, "loss": 4.2575, "step": 25007 }, { "epoch": 0.763836285888821, "grad_norm": 0.479093998670578, "learning_rate": 6.570857985049006e-06, "loss": 4.2541, "step": 25008 }, { "epoch": 0.7638668295662798, "grad_norm": 0.47098851203918457, "learning_rate": 6.5692371077865325e-06, "loss": 4.0401, "step": 25009 }, { "epoch": 0.7638973732437385, "grad_norm": 0.4887729585170746, "learning_rate": 6.567616400225579e-06, "loss": 4.251, "step": 25010 }, { "epoch": 0.7639279169211973, "grad_norm": 0.48704639077186584, "learning_rate": 6.565995862381047e-06, "loss": 4.2571, "step": 25011 }, { "epoch": 0.7639584605986561, "grad_norm": 0.4850543141365051, "learning_rate": 6.564375494267871e-06, "loss": 4.3772, "step": 25012 }, { "epoch": 0.7639890042761148, "grad_norm": 0.4905889630317688, "learning_rate": 6.562755295900977e-06, "loss": 4.2882, "step": 25013 }, { "epoch": 0.7640195479535736, "grad_norm": 0.4831831157207489, "learning_rate": 6.561135267295265e-06, "loss": 4.1253, "step": 25014 }, { "epoch": 0.7640500916310323, "grad_norm": 0.4911024570465088, "learning_rate": 6.559515408465669e-06, "loss": 4.3415, "step": 25015 }, { "epoch": 0.7640806353084911, "grad_norm": 0.4927687346935272, "learning_rate": 6.55789571942709e-06, "loss": 4.2807, "step": 25016 }, { "epoch": 0.7641111789859499, "grad_norm": 0.4892802834510803, "learning_rate": 6.556276200194453e-06, "loss": 4.2808, "step": 25017 }, { "epoch": 0.7641417226634086, "grad_norm": 0.4805959165096283, "learning_rate": 6.554656850782656e-06, "loss": 4.2891, "step": 25018 }, { "epoch": 0.7641722663408674, "grad_norm": 0.48358818888664246, "learning_rate": 6.553037671206624e-06, "loss": 4.2288, "step": 25019 }, { "epoch": 0.7642028100183262, "grad_norm": 0.481413334608078, "learning_rate": 6.551418661481254e-06, "loss": 4.3098, "step": 25020 }, { "epoch": 0.7642333536957849, "grad_norm": 0.4950627088546753, "learning_rate": 6.5497998216214635e-06, "loss": 4.2303, "step": 25021 }, { "epoch": 0.7642638973732437, "grad_norm": 0.4821529686450958, "learning_rate": 6.5481811516421435e-06, "loss": 4.2302, "step": 25022 }, { "epoch": 0.7642944410507025, "grad_norm": 0.470363974571228, "learning_rate": 6.546562651558208e-06, "loss": 4.2649, "step": 25023 }, { "epoch": 0.7643249847281612, "grad_norm": 0.48581448197364807, "learning_rate": 6.544944321384563e-06, "loss": 4.2645, "step": 25024 }, { "epoch": 0.76435552840562, "grad_norm": 0.49185478687286377, "learning_rate": 6.543326161136101e-06, "loss": 4.1338, "step": 25025 }, { "epoch": 0.7643860720830788, "grad_norm": 0.4855653643608093, "learning_rate": 6.541708170827723e-06, "loss": 4.2131, "step": 25026 }, { "epoch": 0.7644166157605375, "grad_norm": 0.4846288561820984, "learning_rate": 6.5400903504743344e-06, "loss": 4.2868, "step": 25027 }, { "epoch": 0.7644471594379963, "grad_norm": 0.4829818308353424, "learning_rate": 6.538472700090817e-06, "loss": 4.2121, "step": 25028 }, { "epoch": 0.7644777031154552, "grad_norm": 0.4730188846588135, "learning_rate": 6.536855219692075e-06, "loss": 4.1993, "step": 25029 }, { "epoch": 0.7645082467929138, "grad_norm": 0.47691065073013306, "learning_rate": 6.535237909293007e-06, "loss": 4.1922, "step": 25030 }, { "epoch": 0.7645387904703727, "grad_norm": 0.4736936092376709, "learning_rate": 6.533620768908491e-06, "loss": 4.2828, "step": 25031 }, { "epoch": 0.7645693341478313, "grad_norm": 0.4872893989086151, "learning_rate": 6.532003798553429e-06, "loss": 4.2156, "step": 25032 }, { "epoch": 0.7645998778252902, "grad_norm": 0.5076870322227478, "learning_rate": 6.530386998242704e-06, "loss": 4.2201, "step": 25033 }, { "epoch": 0.764630421502749, "grad_norm": 0.48622462153434753, "learning_rate": 6.5287703679911936e-06, "loss": 4.275, "step": 25034 }, { "epoch": 0.7646609651802077, "grad_norm": 0.47807392477989197, "learning_rate": 6.5271539078137985e-06, "loss": 4.192, "step": 25035 }, { "epoch": 0.7646915088576665, "grad_norm": 0.4878414273262024, "learning_rate": 6.525537617725389e-06, "loss": 4.2655, "step": 25036 }, { "epoch": 0.7647220525351253, "grad_norm": 0.4854278862476349, "learning_rate": 6.523921497740854e-06, "loss": 4.1529, "step": 25037 }, { "epoch": 0.764752596212584, "grad_norm": 0.48632895946502686, "learning_rate": 6.522305547875079e-06, "loss": 4.3324, "step": 25038 }, { "epoch": 0.7647831398900428, "grad_norm": 0.47068989276885986, "learning_rate": 6.520689768142932e-06, "loss": 4.1998, "step": 25039 }, { "epoch": 0.7648136835675016, "grad_norm": 0.47875797748565674, "learning_rate": 6.519074158559294e-06, "loss": 4.2793, "step": 25040 }, { "epoch": 0.7648442272449603, "grad_norm": 0.48763200640678406, "learning_rate": 6.517458719139047e-06, "loss": 4.261, "step": 25041 }, { "epoch": 0.7648747709224191, "grad_norm": 0.4770960509777069, "learning_rate": 6.515843449897055e-06, "loss": 4.262, "step": 25042 }, { "epoch": 0.7649053145998779, "grad_norm": 0.4803352355957031, "learning_rate": 6.5142283508481976e-06, "loss": 4.2141, "step": 25043 }, { "epoch": 0.7649358582773366, "grad_norm": 0.47368159890174866, "learning_rate": 6.51261342200735e-06, "loss": 4.3105, "step": 25044 }, { "epoch": 0.7649664019547954, "grad_norm": 0.5015738606452942, "learning_rate": 6.510998663389367e-06, "loss": 4.3121, "step": 25045 }, { "epoch": 0.7649969456322542, "grad_norm": 0.4750176966190338, "learning_rate": 6.509384075009128e-06, "loss": 4.2013, "step": 25046 }, { "epoch": 0.7650274893097129, "grad_norm": 0.48593759536743164, "learning_rate": 6.5077696568815045e-06, "loss": 4.319, "step": 25047 }, { "epoch": 0.7650580329871717, "grad_norm": 0.48051464557647705, "learning_rate": 6.506155409021353e-06, "loss": 4.19, "step": 25048 }, { "epoch": 0.7650885766646304, "grad_norm": 0.482713520526886, "learning_rate": 6.504541331443528e-06, "loss": 4.2644, "step": 25049 }, { "epoch": 0.7651191203420892, "grad_norm": 0.4811048209667206, "learning_rate": 6.502927424162908e-06, "loss": 4.1926, "step": 25050 }, { "epoch": 0.765149664019548, "grad_norm": 0.4756028950214386, "learning_rate": 6.501313687194341e-06, "loss": 4.1984, "step": 25051 }, { "epoch": 0.7651802076970067, "grad_norm": 0.4964989721775055, "learning_rate": 6.4997001205526935e-06, "loss": 4.2772, "step": 25052 }, { "epoch": 0.7652107513744655, "grad_norm": 0.4947451949119568, "learning_rate": 6.498086724252814e-06, "loss": 4.297, "step": 25053 }, { "epoch": 0.7652412950519243, "grad_norm": 0.4717279076576233, "learning_rate": 6.496473498309563e-06, "loss": 4.2893, "step": 25054 }, { "epoch": 0.765271838729383, "grad_norm": 0.5070272088050842, "learning_rate": 6.494860442737799e-06, "loss": 4.2155, "step": 25055 }, { "epoch": 0.7653023824068418, "grad_norm": 0.4857027232646942, "learning_rate": 6.493247557552365e-06, "loss": 4.2523, "step": 25056 }, { "epoch": 0.7653329260843006, "grad_norm": 0.4811548590660095, "learning_rate": 6.491634842768113e-06, "loss": 4.301, "step": 25057 }, { "epoch": 0.7653634697617593, "grad_norm": 0.48243167996406555, "learning_rate": 6.490022298399906e-06, "loss": 4.28, "step": 25058 }, { "epoch": 0.7653940134392181, "grad_norm": 0.47798168659210205, "learning_rate": 6.488409924462571e-06, "loss": 4.2581, "step": 25059 }, { "epoch": 0.7654245571166769, "grad_norm": 0.47857680916786194, "learning_rate": 6.486797720970964e-06, "loss": 4.2933, "step": 25060 }, { "epoch": 0.7654551007941356, "grad_norm": 0.48302221298217773, "learning_rate": 6.485185687939935e-06, "loss": 4.2524, "step": 25061 }, { "epoch": 0.7654856444715944, "grad_norm": 0.5031826496124268, "learning_rate": 6.483573825384314e-06, "loss": 4.3096, "step": 25062 }, { "epoch": 0.7655161881490532, "grad_norm": 0.48649752140045166, "learning_rate": 6.481962133318956e-06, "loss": 4.1939, "step": 25063 }, { "epoch": 0.7655467318265119, "grad_norm": 0.48399415612220764, "learning_rate": 6.480350611758687e-06, "loss": 4.3175, "step": 25064 }, { "epoch": 0.7655772755039707, "grad_norm": 0.4903055429458618, "learning_rate": 6.478739260718361e-06, "loss": 4.276, "step": 25065 }, { "epoch": 0.7656078191814294, "grad_norm": 0.4886949956417084, "learning_rate": 6.477128080212802e-06, "loss": 4.1888, "step": 25066 }, { "epoch": 0.7656383628588882, "grad_norm": 0.48341813683509827, "learning_rate": 6.475517070256843e-06, "loss": 4.2967, "step": 25067 }, { "epoch": 0.765668906536347, "grad_norm": 0.48475566506385803, "learning_rate": 6.473906230865323e-06, "loss": 4.2653, "step": 25068 }, { "epoch": 0.7656994502138057, "grad_norm": 0.4830489754676819, "learning_rate": 6.47229556205308e-06, "loss": 4.1732, "step": 25069 }, { "epoch": 0.7657299938912645, "grad_norm": 0.49271413683891296, "learning_rate": 6.47068506383493e-06, "loss": 4.2544, "step": 25070 }, { "epoch": 0.7657605375687233, "grad_norm": 0.48655959963798523, "learning_rate": 6.469074736225708e-06, "loss": 4.243, "step": 25071 }, { "epoch": 0.765791081246182, "grad_norm": 0.4809548258781433, "learning_rate": 6.467464579240254e-06, "loss": 4.2698, "step": 25072 }, { "epoch": 0.7658216249236408, "grad_norm": 0.4830303490161896, "learning_rate": 6.465854592893372e-06, "loss": 4.1352, "step": 25073 }, { "epoch": 0.7658521686010996, "grad_norm": 0.49133872985839844, "learning_rate": 6.464244777199896e-06, "loss": 4.288, "step": 25074 }, { "epoch": 0.7658827122785583, "grad_norm": 0.48178356885910034, "learning_rate": 6.462635132174658e-06, "loss": 4.2457, "step": 25075 }, { "epoch": 0.7659132559560171, "grad_norm": 0.4714881479740143, "learning_rate": 6.461025657832459e-06, "loss": 4.1602, "step": 25076 }, { "epoch": 0.7659437996334759, "grad_norm": 0.4993206560611725, "learning_rate": 6.4594163541881304e-06, "loss": 4.1847, "step": 25077 }, { "epoch": 0.7659743433109346, "grad_norm": 0.4862625002861023, "learning_rate": 6.457807221256495e-06, "loss": 4.3798, "step": 25078 }, { "epoch": 0.7660048869883934, "grad_norm": 0.4841289818286896, "learning_rate": 6.4561982590523626e-06, "loss": 4.1881, "step": 25079 }, { "epoch": 0.7660354306658522, "grad_norm": 0.4850847125053406, "learning_rate": 6.454589467590539e-06, "loss": 4.342, "step": 25080 }, { "epoch": 0.7660659743433109, "grad_norm": 0.4873429238796234, "learning_rate": 6.452980846885851e-06, "loss": 4.22, "step": 25081 }, { "epoch": 0.7660965180207697, "grad_norm": 0.49335190653800964, "learning_rate": 6.451372396953098e-06, "loss": 4.2825, "step": 25082 }, { "epoch": 0.7661270616982284, "grad_norm": 0.4778861701488495, "learning_rate": 6.449764117807105e-06, "loss": 4.2953, "step": 25083 }, { "epoch": 0.7661576053756872, "grad_norm": 0.48179906606674194, "learning_rate": 6.448156009462663e-06, "loss": 4.264, "step": 25084 }, { "epoch": 0.766188149053146, "grad_norm": 0.48737210035324097, "learning_rate": 6.446548071934589e-06, "loss": 4.2622, "step": 25085 }, { "epoch": 0.7662186927306047, "grad_norm": 0.4783722460269928, "learning_rate": 6.44494030523769e-06, "loss": 4.2465, "step": 25086 }, { "epoch": 0.7662492364080635, "grad_norm": 0.4777164161205292, "learning_rate": 6.443332709386759e-06, "loss": 4.3192, "step": 25087 }, { "epoch": 0.7662797800855223, "grad_norm": 0.4869871735572815, "learning_rate": 6.441725284396605e-06, "loss": 4.2909, "step": 25088 }, { "epoch": 0.766310323762981, "grad_norm": 0.48772427439689636, "learning_rate": 6.440118030282036e-06, "loss": 4.3738, "step": 25089 }, { "epoch": 0.7663408674404398, "grad_norm": 0.493480384349823, "learning_rate": 6.438510947057836e-06, "loss": 4.3099, "step": 25090 }, { "epoch": 0.7663714111178986, "grad_norm": 0.5009865760803223, "learning_rate": 6.4369040347388086e-06, "loss": 4.3141, "step": 25091 }, { "epoch": 0.7664019547953573, "grad_norm": 0.48862460255622864, "learning_rate": 6.435297293339756e-06, "loss": 4.3105, "step": 25092 }, { "epoch": 0.7664324984728161, "grad_norm": 0.4820125997066498, "learning_rate": 6.433690722875463e-06, "loss": 4.3584, "step": 25093 }, { "epoch": 0.7664630421502749, "grad_norm": 0.4862652122974396, "learning_rate": 6.432084323360729e-06, "loss": 4.2958, "step": 25094 }, { "epoch": 0.7664935858277336, "grad_norm": 0.5017984509468079, "learning_rate": 6.430478094810335e-06, "loss": 4.2827, "step": 25095 }, { "epoch": 0.7665241295051924, "grad_norm": 0.4955407977104187, "learning_rate": 6.428872037239084e-06, "loss": 4.3688, "step": 25096 }, { "epoch": 0.7665546731826511, "grad_norm": 0.4868742525577545, "learning_rate": 6.427266150661757e-06, "loss": 4.1475, "step": 25097 }, { "epoch": 0.7665852168601099, "grad_norm": 0.47910118103027344, "learning_rate": 6.425660435093131e-06, "loss": 4.2358, "step": 25098 }, { "epoch": 0.7666157605375687, "grad_norm": 0.48255655169487, "learning_rate": 6.424054890547998e-06, "loss": 4.1997, "step": 25099 }, { "epoch": 0.7666463042150274, "grad_norm": 0.47634002566337585, "learning_rate": 6.422449517041151e-06, "loss": 4.249, "step": 25100 }, { "epoch": 0.7666768478924862, "grad_norm": 0.4912710189819336, "learning_rate": 6.420844314587357e-06, "loss": 4.3747, "step": 25101 }, { "epoch": 0.766707391569945, "grad_norm": 0.4835568964481354, "learning_rate": 6.419239283201403e-06, "loss": 4.1885, "step": 25102 }, { "epoch": 0.7667379352474037, "grad_norm": 0.49046462774276733, "learning_rate": 6.4176344228980725e-06, "loss": 4.2458, "step": 25103 }, { "epoch": 0.7667684789248626, "grad_norm": 0.4842047691345215, "learning_rate": 6.416029733692128e-06, "loss": 4.258, "step": 25104 }, { "epoch": 0.7667990226023214, "grad_norm": 0.4852282702922821, "learning_rate": 6.414425215598352e-06, "loss": 4.2877, "step": 25105 }, { "epoch": 0.76682956627978, "grad_norm": 0.48189398646354675, "learning_rate": 6.412820868631525e-06, "loss": 4.2763, "step": 25106 }, { "epoch": 0.7668601099572389, "grad_norm": 0.4910815954208374, "learning_rate": 6.411216692806407e-06, "loss": 4.2884, "step": 25107 }, { "epoch": 0.7668906536346977, "grad_norm": 0.4839589297771454, "learning_rate": 6.409612688137776e-06, "loss": 4.2799, "step": 25108 }, { "epoch": 0.7669211973121564, "grad_norm": 0.48782408237457275, "learning_rate": 6.408008854640404e-06, "loss": 4.2724, "step": 25109 }, { "epoch": 0.7669517409896152, "grad_norm": 0.4832213521003723, "learning_rate": 6.406405192329049e-06, "loss": 4.0999, "step": 25110 }, { "epoch": 0.766982284667074, "grad_norm": 0.4860314726829529, "learning_rate": 6.404801701218486e-06, "loss": 4.2257, "step": 25111 }, { "epoch": 0.7670128283445327, "grad_norm": 0.4778914153575897, "learning_rate": 6.403198381323475e-06, "loss": 4.1342, "step": 25112 }, { "epoch": 0.7670433720219915, "grad_norm": 0.4788612127304077, "learning_rate": 6.401595232658772e-06, "loss": 4.2357, "step": 25113 }, { "epoch": 0.7670739156994502, "grad_norm": 0.48567456007003784, "learning_rate": 6.399992255239148e-06, "loss": 4.2378, "step": 25114 }, { "epoch": 0.767104459376909, "grad_norm": 0.47629883885383606, "learning_rate": 6.398389449079356e-06, "loss": 4.2626, "step": 25115 }, { "epoch": 0.7671350030543678, "grad_norm": 0.48186632990837097, "learning_rate": 6.396786814194153e-06, "loss": 4.2604, "step": 25116 }, { "epoch": 0.7671655467318265, "grad_norm": 0.4793094992637634, "learning_rate": 6.395184350598307e-06, "loss": 4.2655, "step": 25117 }, { "epoch": 0.7671960904092853, "grad_norm": 0.49250414967536926, "learning_rate": 6.393582058306557e-06, "loss": 4.214, "step": 25118 }, { "epoch": 0.7672266340867441, "grad_norm": 0.490031898021698, "learning_rate": 6.391979937333661e-06, "loss": 4.3295, "step": 25119 }, { "epoch": 0.7672571777642028, "grad_norm": 0.4887254238128662, "learning_rate": 6.390377987694385e-06, "loss": 4.2585, "step": 25120 }, { "epoch": 0.7672877214416616, "grad_norm": 0.47525545954704285, "learning_rate": 6.388776209403457e-06, "loss": 4.2797, "step": 25121 }, { "epoch": 0.7673182651191204, "grad_norm": 0.4945725202560425, "learning_rate": 6.387174602475635e-06, "loss": 4.3306, "step": 25122 }, { "epoch": 0.7673488087965791, "grad_norm": 0.4809618890285492, "learning_rate": 6.385573166925674e-06, "loss": 4.1407, "step": 25123 }, { "epoch": 0.7673793524740379, "grad_norm": 0.4853019416332245, "learning_rate": 6.383971902768304e-06, "loss": 4.2019, "step": 25124 }, { "epoch": 0.7674098961514967, "grad_norm": 0.4827820062637329, "learning_rate": 6.382370810018285e-06, "loss": 4.201, "step": 25125 }, { "epoch": 0.7674404398289554, "grad_norm": 0.48432403802871704, "learning_rate": 6.380769888690341e-06, "loss": 4.2403, "step": 25126 }, { "epoch": 0.7674709835064142, "grad_norm": 0.48704320192337036, "learning_rate": 6.379169138799229e-06, "loss": 4.3101, "step": 25127 }, { "epoch": 0.767501527183873, "grad_norm": 0.48210862278938293, "learning_rate": 6.377568560359676e-06, "loss": 4.2479, "step": 25128 }, { "epoch": 0.7675320708613317, "grad_norm": 0.4951590299606323, "learning_rate": 6.375968153386427e-06, "loss": 4.2089, "step": 25129 }, { "epoch": 0.7675626145387905, "grad_norm": 0.4929838180541992, "learning_rate": 6.374367917894211e-06, "loss": 4.2975, "step": 25130 }, { "epoch": 0.7675931582162492, "grad_norm": 0.4714950621128082, "learning_rate": 6.372767853897771e-06, "loss": 4.2004, "step": 25131 }, { "epoch": 0.767623701893708, "grad_norm": 0.4828876554965973, "learning_rate": 6.371167961411828e-06, "loss": 4.2675, "step": 25132 }, { "epoch": 0.7676542455711668, "grad_norm": 0.483810693025589, "learning_rate": 6.369568240451121e-06, "loss": 4.1756, "step": 25133 }, { "epoch": 0.7676847892486255, "grad_norm": 0.4864361584186554, "learning_rate": 6.367968691030382e-06, "loss": 4.1369, "step": 25134 }, { "epoch": 0.7677153329260843, "grad_norm": 0.4869646430015564, "learning_rate": 6.36636931316433e-06, "loss": 4.1289, "step": 25135 }, { "epoch": 0.7677458766035431, "grad_norm": 0.47765612602233887, "learning_rate": 6.364770106867696e-06, "loss": 4.2365, "step": 25136 }, { "epoch": 0.7677764202810018, "grad_norm": 0.48990845680236816, "learning_rate": 6.363171072155213e-06, "loss": 4.2747, "step": 25137 }, { "epoch": 0.7678069639584606, "grad_norm": 0.4967602789402008, "learning_rate": 6.361572209041589e-06, "loss": 4.2754, "step": 25138 }, { "epoch": 0.7678375076359194, "grad_norm": 0.49286651611328125, "learning_rate": 6.359973517541551e-06, "loss": 4.1463, "step": 25139 }, { "epoch": 0.7678680513133781, "grad_norm": 0.4912342429161072, "learning_rate": 6.3583749976698275e-06, "loss": 4.299, "step": 25140 }, { "epoch": 0.7678985949908369, "grad_norm": 0.480595201253891, "learning_rate": 6.356776649441124e-06, "loss": 4.2875, "step": 25141 }, { "epoch": 0.7679291386682957, "grad_norm": 0.4856966733932495, "learning_rate": 6.355178472870168e-06, "loss": 4.3297, "step": 25142 }, { "epoch": 0.7679596823457544, "grad_norm": 0.49579063057899475, "learning_rate": 6.353580467971673e-06, "loss": 4.3528, "step": 25143 }, { "epoch": 0.7679902260232132, "grad_norm": 0.49373936653137207, "learning_rate": 6.351982634760342e-06, "loss": 4.2164, "step": 25144 }, { "epoch": 0.768020769700672, "grad_norm": 0.48377737402915955, "learning_rate": 6.350384973250894e-06, "loss": 4.2123, "step": 25145 }, { "epoch": 0.7680513133781307, "grad_norm": 0.48800280690193176, "learning_rate": 6.348787483458049e-06, "loss": 4.2954, "step": 25146 }, { "epoch": 0.7680818570555895, "grad_norm": 0.5002375245094299, "learning_rate": 6.347190165396497e-06, "loss": 4.165, "step": 25147 }, { "epoch": 0.7681124007330482, "grad_norm": 0.48539987206459045, "learning_rate": 6.3455930190809645e-06, "loss": 4.1222, "step": 25148 }, { "epoch": 0.768142944410507, "grad_norm": 0.4879908859729767, "learning_rate": 6.343996044526141e-06, "loss": 4.3055, "step": 25149 }, { "epoch": 0.7681734880879658, "grad_norm": 0.49337732791900635, "learning_rate": 6.342399241746738e-06, "loss": 4.357, "step": 25150 }, { "epoch": 0.7682040317654245, "grad_norm": 0.48018160462379456, "learning_rate": 6.3408026107574654e-06, "loss": 4.2645, "step": 25151 }, { "epoch": 0.7682345754428833, "grad_norm": 0.48566222190856934, "learning_rate": 6.339206151573007e-06, "loss": 4.3002, "step": 25152 }, { "epoch": 0.7682651191203421, "grad_norm": 0.48292598128318787, "learning_rate": 6.337609864208075e-06, "loss": 4.0695, "step": 25153 }, { "epoch": 0.7682956627978008, "grad_norm": 0.48397526144981384, "learning_rate": 6.336013748677369e-06, "loss": 4.3476, "step": 25154 }, { "epoch": 0.7683262064752596, "grad_norm": 0.481465220451355, "learning_rate": 6.334417804995577e-06, "loss": 4.19, "step": 25155 }, { "epoch": 0.7683567501527184, "grad_norm": 0.4945606589317322, "learning_rate": 6.332822033177394e-06, "loss": 4.2931, "step": 25156 }, { "epoch": 0.7683872938301771, "grad_norm": 0.4830414354801178, "learning_rate": 6.331226433237525e-06, "loss": 4.2856, "step": 25157 }, { "epoch": 0.7684178375076359, "grad_norm": 0.47431662678718567, "learning_rate": 6.32963100519065e-06, "loss": 4.1601, "step": 25158 }, { "epoch": 0.7684483811850947, "grad_norm": 0.48711520433425903, "learning_rate": 6.328035749051458e-06, "loss": 4.1041, "step": 25159 }, { "epoch": 0.7684789248625534, "grad_norm": 0.491263747215271, "learning_rate": 6.326440664834646e-06, "loss": 4.0496, "step": 25160 }, { "epoch": 0.7685094685400122, "grad_norm": 0.48839133977890015, "learning_rate": 6.3248457525548895e-06, "loss": 4.1902, "step": 25161 }, { "epoch": 0.768540012217471, "grad_norm": 0.4886019229888916, "learning_rate": 6.32325101222688e-06, "loss": 4.2501, "step": 25162 }, { "epoch": 0.7685705558949297, "grad_norm": 0.49292632937431335, "learning_rate": 6.321656443865309e-06, "loss": 4.2872, "step": 25163 }, { "epoch": 0.7686010995723885, "grad_norm": 0.4833655059337616, "learning_rate": 6.3200620474848424e-06, "loss": 4.2173, "step": 25164 }, { "epoch": 0.7686316432498472, "grad_norm": 0.4884723722934723, "learning_rate": 6.318467823100177e-06, "loss": 4.1819, "step": 25165 }, { "epoch": 0.768662186927306, "grad_norm": 0.4980907738208771, "learning_rate": 6.316873770725976e-06, "loss": 4.2253, "step": 25166 }, { "epoch": 0.7686927306047648, "grad_norm": 0.48436394333839417, "learning_rate": 6.315279890376921e-06, "loss": 4.3126, "step": 25167 }, { "epoch": 0.7687232742822235, "grad_norm": 0.4792293310165405, "learning_rate": 6.313686182067702e-06, "loss": 4.247, "step": 25168 }, { "epoch": 0.7687538179596823, "grad_norm": 0.49177587032318115, "learning_rate": 6.3120926458129725e-06, "loss": 4.2664, "step": 25169 }, { "epoch": 0.7687843616371411, "grad_norm": 0.48919564485549927, "learning_rate": 6.310499281627416e-06, "loss": 4.3235, "step": 25170 }, { "epoch": 0.7688149053145998, "grad_norm": 0.47902849316596985, "learning_rate": 6.308906089525707e-06, "loss": 4.1943, "step": 25171 }, { "epoch": 0.7688454489920586, "grad_norm": 0.5032914876937866, "learning_rate": 6.307313069522502e-06, "loss": 4.2591, "step": 25172 }, { "epoch": 0.7688759926695174, "grad_norm": 0.49266740679740906, "learning_rate": 6.3057202216324854e-06, "loss": 4.2077, "step": 25173 }, { "epoch": 0.7689065363469761, "grad_norm": 0.4863511919975281, "learning_rate": 6.304127545870308e-06, "loss": 4.2209, "step": 25174 }, { "epoch": 0.768937080024435, "grad_norm": 0.4935063123703003, "learning_rate": 6.302535042250646e-06, "loss": 4.3477, "step": 25175 }, { "epoch": 0.7689676237018938, "grad_norm": 0.48528215289115906, "learning_rate": 6.300942710788152e-06, "loss": 4.3002, "step": 25176 }, { "epoch": 0.7689981673793524, "grad_norm": 0.4790232479572296, "learning_rate": 6.299350551497499e-06, "loss": 4.2486, "step": 25177 }, { "epoch": 0.7690287110568113, "grad_norm": 0.4965853989124298, "learning_rate": 6.29775856439333e-06, "loss": 4.2339, "step": 25178 }, { "epoch": 0.7690592547342701, "grad_norm": 0.48185282945632935, "learning_rate": 6.296166749490317e-06, "loss": 4.2281, "step": 25179 }, { "epoch": 0.7690897984117288, "grad_norm": 0.49424266815185547, "learning_rate": 6.294575106803122e-06, "loss": 4.3507, "step": 25180 }, { "epoch": 0.7691203420891876, "grad_norm": 0.4976723790168762, "learning_rate": 6.292983636346381e-06, "loss": 4.3286, "step": 25181 }, { "epoch": 0.7691508857666463, "grad_norm": 0.4935538172721863, "learning_rate": 6.291392338134766e-06, "loss": 4.2602, "step": 25182 }, { "epoch": 0.7691814294441051, "grad_norm": 0.49269771575927734, "learning_rate": 6.2898012121829134e-06, "loss": 4.3055, "step": 25183 }, { "epoch": 0.7692119731215639, "grad_norm": 0.48147207498550415, "learning_rate": 6.288210258505481e-06, "loss": 4.2719, "step": 25184 }, { "epoch": 0.7692425167990226, "grad_norm": 0.495069295167923, "learning_rate": 6.2866194771171255e-06, "loss": 4.2822, "step": 25185 }, { "epoch": 0.7692730604764814, "grad_norm": 0.47645142674446106, "learning_rate": 6.285028868032478e-06, "loss": 4.1494, "step": 25186 }, { "epoch": 0.7693036041539402, "grad_norm": 0.4834972620010376, "learning_rate": 6.283438431266192e-06, "loss": 4.2111, "step": 25187 }, { "epoch": 0.7693341478313989, "grad_norm": 0.4865909814834595, "learning_rate": 6.281848166832918e-06, "loss": 4.282, "step": 25188 }, { "epoch": 0.7693646915088577, "grad_norm": 0.4908045530319214, "learning_rate": 6.280258074747291e-06, "loss": 4.2535, "step": 25189 }, { "epoch": 0.7693952351863165, "grad_norm": 0.49153411388397217, "learning_rate": 6.278668155023948e-06, "loss": 4.2568, "step": 25190 }, { "epoch": 0.7694257788637752, "grad_norm": 0.5025091171264648, "learning_rate": 6.277078407677539e-06, "loss": 4.2282, "step": 25191 }, { "epoch": 0.769456322541234, "grad_norm": 0.48148295283317566, "learning_rate": 6.2754888327226864e-06, "loss": 4.2957, "step": 25192 }, { "epoch": 0.7694868662186928, "grad_norm": 0.4780513644218445, "learning_rate": 6.273899430174038e-06, "loss": 4.2819, "step": 25193 }, { "epoch": 0.7695174098961515, "grad_norm": 0.48766961693763733, "learning_rate": 6.272310200046233e-06, "loss": 4.2917, "step": 25194 }, { "epoch": 0.7695479535736103, "grad_norm": 0.4880090057849884, "learning_rate": 6.2707211423538884e-06, "loss": 4.3689, "step": 25195 }, { "epoch": 0.7695784972510691, "grad_norm": 0.488729327917099, "learning_rate": 6.269132257111643e-06, "loss": 4.3066, "step": 25196 }, { "epoch": 0.7696090409285278, "grad_norm": 0.4923734962940216, "learning_rate": 6.267543544334137e-06, "loss": 4.3198, "step": 25197 }, { "epoch": 0.7696395846059866, "grad_norm": 0.4848828911781311, "learning_rate": 6.265955004035978e-06, "loss": 4.2793, "step": 25198 }, { "epoch": 0.7696701282834453, "grad_norm": 0.48760533332824707, "learning_rate": 6.264366636231814e-06, "loss": 4.304, "step": 25199 }, { "epoch": 0.7697006719609041, "grad_norm": 0.4922195076942444, "learning_rate": 6.262778440936251e-06, "loss": 4.3164, "step": 25200 }, { "epoch": 0.7697312156383629, "grad_norm": 0.48948195576667786, "learning_rate": 6.26119041816392e-06, "loss": 4.2932, "step": 25201 }, { "epoch": 0.7697617593158216, "grad_norm": 0.48412230610847473, "learning_rate": 6.259602567929451e-06, "loss": 4.2699, "step": 25202 }, { "epoch": 0.7697923029932804, "grad_norm": 0.48702964186668396, "learning_rate": 6.258014890247449e-06, "loss": 4.2244, "step": 25203 }, { "epoch": 0.7698228466707392, "grad_norm": 0.4914727210998535, "learning_rate": 6.256427385132549e-06, "loss": 4.2912, "step": 25204 }, { "epoch": 0.7698533903481979, "grad_norm": 0.48878198862075806, "learning_rate": 6.25484005259935e-06, "loss": 4.13, "step": 25205 }, { "epoch": 0.7698839340256567, "grad_norm": 0.48539891839027405, "learning_rate": 6.253252892662484e-06, "loss": 4.3081, "step": 25206 }, { "epoch": 0.7699144777031155, "grad_norm": 0.4846034049987793, "learning_rate": 6.251665905336548e-06, "loss": 4.2958, "step": 25207 }, { "epoch": 0.7699450213805742, "grad_norm": 0.48941493034362793, "learning_rate": 6.250079090636174e-06, "loss": 4.2438, "step": 25208 }, { "epoch": 0.769975565058033, "grad_norm": 0.47914543747901917, "learning_rate": 6.2484924485759546e-06, "loss": 4.2485, "step": 25209 }, { "epoch": 0.7700061087354918, "grad_norm": 0.4861823320388794, "learning_rate": 6.246905979170506e-06, "loss": 4.2613, "step": 25210 }, { "epoch": 0.7700366524129505, "grad_norm": 0.4728500247001648, "learning_rate": 6.245319682434442e-06, "loss": 4.1719, "step": 25211 }, { "epoch": 0.7700671960904093, "grad_norm": 0.4913610816001892, "learning_rate": 6.243733558382356e-06, "loss": 4.3978, "step": 25212 }, { "epoch": 0.7700977397678681, "grad_norm": 0.49281394481658936, "learning_rate": 6.242147607028859e-06, "loss": 4.1928, "step": 25213 }, { "epoch": 0.7701282834453268, "grad_norm": 0.4924512505531311, "learning_rate": 6.240561828388558e-06, "loss": 4.2636, "step": 25214 }, { "epoch": 0.7701588271227856, "grad_norm": 0.49427035450935364, "learning_rate": 6.2389762224760455e-06, "loss": 4.2241, "step": 25215 }, { "epoch": 0.7701893708002443, "grad_norm": 0.4849706292152405, "learning_rate": 6.237390789305931e-06, "loss": 4.2805, "step": 25216 }, { "epoch": 0.7702199144777031, "grad_norm": 0.4889867603778839, "learning_rate": 6.235805528892797e-06, "loss": 4.1854, "step": 25217 }, { "epoch": 0.7702504581551619, "grad_norm": 0.48848795890808105, "learning_rate": 6.2342204412512515e-06, "loss": 4.1815, "step": 25218 }, { "epoch": 0.7702810018326206, "grad_norm": 0.47376006841659546, "learning_rate": 6.232635526395891e-06, "loss": 4.2327, "step": 25219 }, { "epoch": 0.7703115455100794, "grad_norm": 0.48526549339294434, "learning_rate": 6.231050784341302e-06, "loss": 4.2818, "step": 25220 }, { "epoch": 0.7703420891875382, "grad_norm": 0.4822188913822174, "learning_rate": 6.229466215102081e-06, "loss": 4.2743, "step": 25221 }, { "epoch": 0.7703726328649969, "grad_norm": 0.48998111486434937, "learning_rate": 6.227881818692819e-06, "loss": 4.2037, "step": 25222 }, { "epoch": 0.7704031765424557, "grad_norm": 0.49220582842826843, "learning_rate": 6.2262975951280916e-06, "loss": 4.2411, "step": 25223 }, { "epoch": 0.7704337202199145, "grad_norm": 0.4875843822956085, "learning_rate": 6.224713544422495e-06, "loss": 4.2334, "step": 25224 }, { "epoch": 0.7704642638973732, "grad_norm": 0.4859277009963989, "learning_rate": 6.223129666590621e-06, "loss": 4.2268, "step": 25225 }, { "epoch": 0.770494807574832, "grad_norm": 0.4873678386211395, "learning_rate": 6.221545961647041e-06, "loss": 4.2739, "step": 25226 }, { "epoch": 0.7705253512522908, "grad_norm": 0.4907958209514618, "learning_rate": 6.219962429606341e-06, "loss": 4.118, "step": 25227 }, { "epoch": 0.7705558949297495, "grad_norm": 0.4808870851993561, "learning_rate": 6.2183790704831105e-06, "loss": 4.1568, "step": 25228 }, { "epoch": 0.7705864386072083, "grad_norm": 0.49223676323890686, "learning_rate": 6.216795884291912e-06, "loss": 4.2125, "step": 25229 }, { "epoch": 0.7706169822846671, "grad_norm": 0.4919454753398895, "learning_rate": 6.215212871047332e-06, "loss": 4.355, "step": 25230 }, { "epoch": 0.7706475259621258, "grad_norm": 0.48562297224998474, "learning_rate": 6.213630030763951e-06, "loss": 4.2741, "step": 25231 }, { "epoch": 0.7706780696395846, "grad_norm": 0.4940554201602936, "learning_rate": 6.212047363456333e-06, "loss": 4.2429, "step": 25232 }, { "epoch": 0.7707086133170433, "grad_norm": 0.4879302382469177, "learning_rate": 6.2104648691390595e-06, "loss": 4.3261, "step": 25233 }, { "epoch": 0.7707391569945021, "grad_norm": 0.49808764457702637, "learning_rate": 6.208882547826688e-06, "loss": 4.3041, "step": 25234 }, { "epoch": 0.7707697006719609, "grad_norm": 0.4943639636039734, "learning_rate": 6.207300399533808e-06, "loss": 4.2257, "step": 25235 }, { "epoch": 0.7708002443494196, "grad_norm": 0.4883975684642792, "learning_rate": 6.205718424274964e-06, "loss": 4.2686, "step": 25236 }, { "epoch": 0.7708307880268784, "grad_norm": 0.49721652269363403, "learning_rate": 6.2041366220647435e-06, "loss": 4.114, "step": 25237 }, { "epoch": 0.7708613317043372, "grad_norm": 0.4878843426704407, "learning_rate": 6.2025549929176915e-06, "loss": 4.2037, "step": 25238 }, { "epoch": 0.7708918753817959, "grad_norm": 0.4855339229106903, "learning_rate": 6.200973536848389e-06, "loss": 4.2663, "step": 25239 }, { "epoch": 0.7709224190592547, "grad_norm": 0.4800005555152893, "learning_rate": 6.1993922538713835e-06, "loss": 4.1504, "step": 25240 }, { "epoch": 0.7709529627367135, "grad_norm": 0.48152944445610046, "learning_rate": 6.197811144001237e-06, "loss": 4.2173, "step": 25241 }, { "epoch": 0.7709835064141722, "grad_norm": 0.48692795634269714, "learning_rate": 6.196230207252518e-06, "loss": 4.2911, "step": 25242 }, { "epoch": 0.771014050091631, "grad_norm": 0.4831638038158417, "learning_rate": 6.194649443639769e-06, "loss": 4.282, "step": 25243 }, { "epoch": 0.7710445937690898, "grad_norm": 0.48475182056427, "learning_rate": 6.1930688531775496e-06, "loss": 4.3232, "step": 25244 }, { "epoch": 0.7710751374465485, "grad_norm": 0.4851915240287781, "learning_rate": 6.191488435880424e-06, "loss": 4.2938, "step": 25245 }, { "epoch": 0.7711056811240073, "grad_norm": 0.4779575765132904, "learning_rate": 6.189908191762927e-06, "loss": 4.2727, "step": 25246 }, { "epoch": 0.771136224801466, "grad_norm": 0.5018808245658875, "learning_rate": 6.188328120839623e-06, "loss": 4.2515, "step": 25247 }, { "epoch": 0.7711667684789248, "grad_norm": 0.4803673326969147, "learning_rate": 6.18674822312505e-06, "loss": 4.3009, "step": 25248 }, { "epoch": 0.7711973121563837, "grad_norm": 0.49041885137557983, "learning_rate": 6.185168498633756e-06, "loss": 4.2395, "step": 25249 }, { "epoch": 0.7712278558338423, "grad_norm": 0.48765161633491516, "learning_rate": 6.183588947380295e-06, "loss": 4.1773, "step": 25250 }, { "epoch": 0.7712583995113012, "grad_norm": 0.4868217706680298, "learning_rate": 6.1820095693791994e-06, "loss": 4.1955, "step": 25251 }, { "epoch": 0.77128894318876, "grad_norm": 0.4847608506679535, "learning_rate": 6.180430364645026e-06, "loss": 4.2184, "step": 25252 }, { "epoch": 0.7713194868662187, "grad_norm": 0.4885379672050476, "learning_rate": 6.178851333192303e-06, "loss": 4.239, "step": 25253 }, { "epoch": 0.7713500305436775, "grad_norm": 0.4856261610984802, "learning_rate": 6.177272475035567e-06, "loss": 4.2772, "step": 25254 }, { "epoch": 0.7713805742211363, "grad_norm": 0.48092836141586304, "learning_rate": 6.17569379018936e-06, "loss": 4.2613, "step": 25255 }, { "epoch": 0.771411117898595, "grad_norm": 0.486920028924942, "learning_rate": 6.17411527866823e-06, "loss": 4.1709, "step": 25256 }, { "epoch": 0.7714416615760538, "grad_norm": 0.4920075237751007, "learning_rate": 6.172536940486689e-06, "loss": 4.3038, "step": 25257 }, { "epoch": 0.7714722052535126, "grad_norm": 0.48170486092567444, "learning_rate": 6.17095877565928e-06, "loss": 4.2784, "step": 25258 }, { "epoch": 0.7715027489309713, "grad_norm": 0.4878879189491272, "learning_rate": 6.169380784200543e-06, "loss": 4.222, "step": 25259 }, { "epoch": 0.7715332926084301, "grad_norm": 0.4819347858428955, "learning_rate": 6.167802966124991e-06, "loss": 4.1594, "step": 25260 }, { "epoch": 0.7715638362858889, "grad_norm": 0.48542237281799316, "learning_rate": 6.166225321447161e-06, "loss": 4.1943, "step": 25261 }, { "epoch": 0.7715943799633476, "grad_norm": 0.47664618492126465, "learning_rate": 6.164647850181584e-06, "loss": 4.1633, "step": 25262 }, { "epoch": 0.7716249236408064, "grad_norm": 0.485819548368454, "learning_rate": 6.1630705523427724e-06, "loss": 4.3155, "step": 25263 }, { "epoch": 0.7716554673182651, "grad_norm": 0.4825473129749298, "learning_rate": 6.161493427945261e-06, "loss": 4.146, "step": 25264 }, { "epoch": 0.7716860109957239, "grad_norm": 0.4889480173587799, "learning_rate": 6.1599164770035605e-06, "loss": 4.2431, "step": 25265 }, { "epoch": 0.7717165546731827, "grad_norm": 0.4774789810180664, "learning_rate": 6.158339699532193e-06, "loss": 4.1939, "step": 25266 }, { "epoch": 0.7717470983506414, "grad_norm": 0.489106684923172, "learning_rate": 6.156763095545687e-06, "loss": 4.31, "step": 25267 }, { "epoch": 0.7717776420281002, "grad_norm": 0.49730175733566284, "learning_rate": 6.155186665058551e-06, "loss": 4.1679, "step": 25268 }, { "epoch": 0.771808185705559, "grad_norm": 0.4890144169330597, "learning_rate": 6.153610408085295e-06, "loss": 4.264, "step": 25269 }, { "epoch": 0.7718387293830177, "grad_norm": 0.486441045999527, "learning_rate": 6.1520343246404434e-06, "loss": 4.2707, "step": 25270 }, { "epoch": 0.7718692730604765, "grad_norm": 0.4947393536567688, "learning_rate": 6.150458414738497e-06, "loss": 4.2688, "step": 25271 }, { "epoch": 0.7718998167379353, "grad_norm": 0.49321818351745605, "learning_rate": 6.148882678393969e-06, "loss": 4.2553, "step": 25272 }, { "epoch": 0.771930360415394, "grad_norm": 0.4871281385421753, "learning_rate": 6.147307115621378e-06, "loss": 4.2968, "step": 25273 }, { "epoch": 0.7719609040928528, "grad_norm": 0.49631163477897644, "learning_rate": 6.1457317264352195e-06, "loss": 4.334, "step": 25274 }, { "epoch": 0.7719914477703116, "grad_norm": 0.4894465208053589, "learning_rate": 6.14415651085e-06, "loss": 4.2034, "step": 25275 }, { "epoch": 0.7720219914477703, "grad_norm": 0.48974037170410156, "learning_rate": 6.1425814688802345e-06, "loss": 4.2662, "step": 25276 }, { "epoch": 0.7720525351252291, "grad_norm": 0.4889557361602783, "learning_rate": 6.141006600540408e-06, "loss": 4.2851, "step": 25277 }, { "epoch": 0.7720830788026879, "grad_norm": 0.4855390191078186, "learning_rate": 6.139431905845033e-06, "loss": 4.2159, "step": 25278 }, { "epoch": 0.7721136224801466, "grad_norm": 0.4810795485973358, "learning_rate": 6.1378573848086095e-06, "loss": 4.1158, "step": 25279 }, { "epoch": 0.7721441661576054, "grad_norm": 0.4921770989894867, "learning_rate": 6.136283037445625e-06, "loss": 4.3068, "step": 25280 }, { "epoch": 0.7721747098350641, "grad_norm": 0.4815264642238617, "learning_rate": 6.134708863770591e-06, "loss": 4.2322, "step": 25281 }, { "epoch": 0.7722052535125229, "grad_norm": 0.48812976479530334, "learning_rate": 6.133134863797982e-06, "loss": 4.1373, "step": 25282 }, { "epoch": 0.7722357971899817, "grad_norm": 0.5010309219360352, "learning_rate": 6.13156103754231e-06, "loss": 4.239, "step": 25283 }, { "epoch": 0.7722663408674404, "grad_norm": 0.4784940779209137, "learning_rate": 6.129987385018046e-06, "loss": 4.2518, "step": 25284 }, { "epoch": 0.7722968845448992, "grad_norm": 0.48403242230415344, "learning_rate": 6.128413906239703e-06, "loss": 4.1239, "step": 25285 }, { "epoch": 0.772327428222358, "grad_norm": 0.48656952381134033, "learning_rate": 6.126840601221742e-06, "loss": 4.2597, "step": 25286 }, { "epoch": 0.7723579718998167, "grad_norm": 0.4932362139225006, "learning_rate": 6.125267469978676e-06, "loss": 4.1875, "step": 25287 }, { "epoch": 0.7723885155772755, "grad_norm": 0.4943167567253113, "learning_rate": 6.123694512524966e-06, "loss": 4.3192, "step": 25288 }, { "epoch": 0.7724190592547343, "grad_norm": 0.474597692489624, "learning_rate": 6.122121728875107e-06, "loss": 4.2233, "step": 25289 }, { "epoch": 0.772449602932193, "grad_norm": 0.4882618188858032, "learning_rate": 6.120549119043587e-06, "loss": 4.2988, "step": 25290 }, { "epoch": 0.7724801466096518, "grad_norm": 0.48719868063926697, "learning_rate": 6.118976683044872e-06, "loss": 4.234, "step": 25291 }, { "epoch": 0.7725106902871106, "grad_norm": 0.4819559156894684, "learning_rate": 6.117404420893444e-06, "loss": 4.2248, "step": 25292 }, { "epoch": 0.7725412339645693, "grad_norm": 0.48268792033195496, "learning_rate": 6.115832332603791e-06, "loss": 4.3062, "step": 25293 }, { "epoch": 0.7725717776420281, "grad_norm": 0.4832046627998352, "learning_rate": 6.114260418190371e-06, "loss": 4.2589, "step": 25294 }, { "epoch": 0.7726023213194869, "grad_norm": 0.48181456327438354, "learning_rate": 6.112688677667666e-06, "loss": 4.1959, "step": 25295 }, { "epoch": 0.7726328649969456, "grad_norm": 0.49059823155403137, "learning_rate": 6.111117111050152e-06, "loss": 4.2153, "step": 25296 }, { "epoch": 0.7726634086744044, "grad_norm": 0.4861631989479065, "learning_rate": 6.109545718352292e-06, "loss": 4.1848, "step": 25297 }, { "epoch": 0.7726939523518631, "grad_norm": 0.4864398241043091, "learning_rate": 6.107974499588559e-06, "loss": 4.2841, "step": 25298 }, { "epoch": 0.7727244960293219, "grad_norm": 0.4852043390274048, "learning_rate": 6.106403454773421e-06, "loss": 4.321, "step": 25299 }, { "epoch": 0.7727550397067807, "grad_norm": 0.4863254725933075, "learning_rate": 6.104832583921333e-06, "loss": 4.2694, "step": 25300 }, { "epoch": 0.7727855833842394, "grad_norm": 0.4942863881587982, "learning_rate": 6.103261887046774e-06, "loss": 4.3402, "step": 25301 }, { "epoch": 0.7728161270616982, "grad_norm": 0.4957125186920166, "learning_rate": 6.101691364164189e-06, "loss": 4.2725, "step": 25302 }, { "epoch": 0.772846670739157, "grad_norm": 0.48358163237571716, "learning_rate": 6.100121015288051e-06, "loss": 4.2869, "step": 25303 }, { "epoch": 0.7728772144166157, "grad_norm": 0.4837222695350647, "learning_rate": 6.098550840432821e-06, "loss": 4.1879, "step": 25304 }, { "epoch": 0.7729077580940745, "grad_norm": 0.4882420599460602, "learning_rate": 6.096980839612945e-06, "loss": 4.3774, "step": 25305 }, { "epoch": 0.7729383017715333, "grad_norm": 0.4900572896003723, "learning_rate": 6.095411012842889e-06, "loss": 4.2925, "step": 25306 }, { "epoch": 0.772968845448992, "grad_norm": 0.4867642819881439, "learning_rate": 6.093841360137107e-06, "loss": 4.3802, "step": 25307 }, { "epoch": 0.7729993891264508, "grad_norm": 0.4827978014945984, "learning_rate": 6.092271881510042e-06, "loss": 4.1414, "step": 25308 }, { "epoch": 0.7730299328039096, "grad_norm": 0.4952244758605957, "learning_rate": 6.090702576976151e-06, "loss": 4.3918, "step": 25309 }, { "epoch": 0.7730604764813683, "grad_norm": 0.4926292896270752, "learning_rate": 6.089133446549888e-06, "loss": 4.2021, "step": 25310 }, { "epoch": 0.7730910201588271, "grad_norm": 0.48970016837120056, "learning_rate": 6.087564490245693e-06, "loss": 4.3092, "step": 25311 }, { "epoch": 0.7731215638362859, "grad_norm": 0.48011890053749084, "learning_rate": 6.085995708078016e-06, "loss": 4.1437, "step": 25312 }, { "epoch": 0.7731521075137446, "grad_norm": 0.48824548721313477, "learning_rate": 6.084427100061304e-06, "loss": 4.2225, "step": 25313 }, { "epoch": 0.7731826511912034, "grad_norm": 0.4858337938785553, "learning_rate": 6.082858666210001e-06, "loss": 4.1723, "step": 25314 }, { "epoch": 0.7732131948686621, "grad_norm": 0.4949093759059906, "learning_rate": 6.081290406538537e-06, "loss": 4.2063, "step": 25315 }, { "epoch": 0.7732437385461209, "grad_norm": 0.4897229075431824, "learning_rate": 6.079722321061365e-06, "loss": 4.202, "step": 25316 }, { "epoch": 0.7732742822235797, "grad_norm": 0.49690762162208557, "learning_rate": 6.078154409792911e-06, "loss": 4.3301, "step": 25317 }, { "epoch": 0.7733048259010384, "grad_norm": 0.49282601475715637, "learning_rate": 6.076586672747625e-06, "loss": 4.2994, "step": 25318 }, { "epoch": 0.7733353695784972, "grad_norm": 0.47763219475746155, "learning_rate": 6.075019109939928e-06, "loss": 4.2455, "step": 25319 }, { "epoch": 0.773365913255956, "grad_norm": 0.48027077317237854, "learning_rate": 6.07345172138426e-06, "loss": 4.2209, "step": 25320 }, { "epoch": 0.7733964569334147, "grad_norm": 0.49163755774497986, "learning_rate": 6.07188450709506e-06, "loss": 4.2916, "step": 25321 }, { "epoch": 0.7734270006108735, "grad_norm": 0.4960217773914337, "learning_rate": 6.070317467086745e-06, "loss": 4.3092, "step": 25322 }, { "epoch": 0.7734575442883324, "grad_norm": 0.491766095161438, "learning_rate": 6.068750601373749e-06, "loss": 4.3125, "step": 25323 }, { "epoch": 0.773488087965791, "grad_norm": 0.4888482689857483, "learning_rate": 6.067183909970506e-06, "loss": 4.2739, "step": 25324 }, { "epoch": 0.7735186316432499, "grad_norm": 0.48441365361213684, "learning_rate": 6.065617392891429e-06, "loss": 4.2058, "step": 25325 }, { "epoch": 0.7735491753207087, "grad_norm": 0.48184800148010254, "learning_rate": 6.064051050150948e-06, "loss": 4.3094, "step": 25326 }, { "epoch": 0.7735797189981674, "grad_norm": 0.4936631917953491, "learning_rate": 6.0624848817634914e-06, "loss": 4.2884, "step": 25327 }, { "epoch": 0.7736102626756262, "grad_norm": 0.4899698793888092, "learning_rate": 6.0609188877434665e-06, "loss": 4.1503, "step": 25328 }, { "epoch": 0.773640806353085, "grad_norm": 0.4916066825389862, "learning_rate": 6.059353068105306e-06, "loss": 4.2635, "step": 25329 }, { "epoch": 0.7736713500305437, "grad_norm": 0.4875187873840332, "learning_rate": 6.057787422863415e-06, "loss": 4.2748, "step": 25330 }, { "epoch": 0.7737018937080025, "grad_norm": 0.5002895593643188, "learning_rate": 6.0562219520322175e-06, "loss": 4.2635, "step": 25331 }, { "epoch": 0.7737324373854612, "grad_norm": 0.48123419284820557, "learning_rate": 6.054656655626126e-06, "loss": 4.2369, "step": 25332 }, { "epoch": 0.77376298106292, "grad_norm": 0.4827340543270111, "learning_rate": 6.053091533659544e-06, "loss": 4.183, "step": 25333 }, { "epoch": 0.7737935247403788, "grad_norm": 0.4877179265022278, "learning_rate": 6.051526586146891e-06, "loss": 4.2244, "step": 25334 }, { "epoch": 0.7738240684178375, "grad_norm": 0.48386892676353455, "learning_rate": 6.049961813102581e-06, "loss": 4.1781, "step": 25335 }, { "epoch": 0.7738546120952963, "grad_norm": 0.4898056089878082, "learning_rate": 6.04839721454101e-06, "loss": 4.1769, "step": 25336 }, { "epoch": 0.7738851557727551, "grad_norm": 0.49469876289367676, "learning_rate": 6.046832790476589e-06, "loss": 4.2932, "step": 25337 }, { "epoch": 0.7739156994502138, "grad_norm": 0.49762269854545593, "learning_rate": 6.045268540923729e-06, "loss": 4.3506, "step": 25338 }, { "epoch": 0.7739462431276726, "grad_norm": 0.5038540959358215, "learning_rate": 6.043704465896821e-06, "loss": 4.1478, "step": 25339 }, { "epoch": 0.7739767868051314, "grad_norm": 0.4851968288421631, "learning_rate": 6.042140565410273e-06, "loss": 4.2527, "step": 25340 }, { "epoch": 0.7740073304825901, "grad_norm": 0.4826926589012146, "learning_rate": 6.040576839478493e-06, "loss": 4.2741, "step": 25341 }, { "epoch": 0.7740378741600489, "grad_norm": 0.48325422406196594, "learning_rate": 6.039013288115861e-06, "loss": 4.283, "step": 25342 }, { "epoch": 0.7740684178375077, "grad_norm": 0.505332887172699, "learning_rate": 6.0374499113367815e-06, "loss": 4.2136, "step": 25343 }, { "epoch": 0.7740989615149664, "grad_norm": 0.48559457063674927, "learning_rate": 6.0358867091556585e-06, "loss": 4.1197, "step": 25344 }, { "epoch": 0.7741295051924252, "grad_norm": 0.4882011115550995, "learning_rate": 6.034323681586876e-06, "loss": 4.2501, "step": 25345 }, { "epoch": 0.774160048869884, "grad_norm": 0.4816661477088928, "learning_rate": 6.032760828644818e-06, "loss": 4.306, "step": 25346 }, { "epoch": 0.7741905925473427, "grad_norm": 0.4969853460788727, "learning_rate": 6.031198150343892e-06, "loss": 4.271, "step": 25347 }, { "epoch": 0.7742211362248015, "grad_norm": 0.4963219463825226, "learning_rate": 6.02963564669847e-06, "loss": 4.31, "step": 25348 }, { "epoch": 0.7742516799022602, "grad_norm": 0.49348184466362, "learning_rate": 6.028073317722954e-06, "loss": 4.2572, "step": 25349 }, { "epoch": 0.774282223579719, "grad_norm": 0.4850276708602905, "learning_rate": 6.026511163431714e-06, "loss": 4.3037, "step": 25350 }, { "epoch": 0.7743127672571778, "grad_norm": 0.504705011844635, "learning_rate": 6.02494918383914e-06, "loss": 4.2071, "step": 25351 }, { "epoch": 0.7743433109346365, "grad_norm": 0.4884819984436035, "learning_rate": 6.023387378959624e-06, "loss": 4.2803, "step": 25352 }, { "epoch": 0.7743738546120953, "grad_norm": 0.4770660996437073, "learning_rate": 6.021825748807528e-06, "loss": 4.1977, "step": 25353 }, { "epoch": 0.7744043982895541, "grad_norm": 0.49803537130355835, "learning_rate": 6.02026429339724e-06, "loss": 4.1796, "step": 25354 }, { "epoch": 0.7744349419670128, "grad_norm": 0.4854281544685364, "learning_rate": 6.018703012743146e-06, "loss": 4.2413, "step": 25355 }, { "epoch": 0.7744654856444716, "grad_norm": 0.48784470558166504, "learning_rate": 6.017141906859605e-06, "loss": 4.2341, "step": 25356 }, { "epoch": 0.7744960293219304, "grad_norm": 0.49360495805740356, "learning_rate": 6.015580975760995e-06, "loss": 4.3647, "step": 25357 }, { "epoch": 0.7745265729993891, "grad_norm": 0.5032250881195068, "learning_rate": 6.0140202194617025e-06, "loss": 4.2017, "step": 25358 }, { "epoch": 0.7745571166768479, "grad_norm": 0.4897403419017792, "learning_rate": 6.0124596379760814e-06, "loss": 4.1815, "step": 25359 }, { "epoch": 0.7745876603543067, "grad_norm": 0.4836980402469635, "learning_rate": 6.010899231318512e-06, "loss": 4.1968, "step": 25360 }, { "epoch": 0.7746182040317654, "grad_norm": 0.4887596666812897, "learning_rate": 6.00933899950335e-06, "loss": 4.3082, "step": 25361 }, { "epoch": 0.7746487477092242, "grad_norm": 0.48008978366851807, "learning_rate": 6.007778942544973e-06, "loss": 4.305, "step": 25362 }, { "epoch": 0.774679291386683, "grad_norm": 0.4870204031467438, "learning_rate": 6.006219060457735e-06, "loss": 4.2383, "step": 25363 }, { "epoch": 0.7747098350641417, "grad_norm": 0.48464927077293396, "learning_rate": 6.004659353256012e-06, "loss": 4.2537, "step": 25364 }, { "epoch": 0.7747403787416005, "grad_norm": 0.48573336005210876, "learning_rate": 6.003099820954147e-06, "loss": 4.2792, "step": 25365 }, { "epoch": 0.7747709224190592, "grad_norm": 0.4887091815471649, "learning_rate": 6.0015404635665185e-06, "loss": 4.2908, "step": 25366 }, { "epoch": 0.774801466096518, "grad_norm": 0.49210548400878906, "learning_rate": 5.999981281107467e-06, "loss": 4.2647, "step": 25367 }, { "epoch": 0.7748320097739768, "grad_norm": 0.4867823123931885, "learning_rate": 5.998422273591356e-06, "loss": 4.3263, "step": 25368 }, { "epoch": 0.7748625534514355, "grad_norm": 0.4779494106769562, "learning_rate": 5.996863441032546e-06, "loss": 4.301, "step": 25369 }, { "epoch": 0.7748930971288943, "grad_norm": 0.47965747117996216, "learning_rate": 5.995304783445383e-06, "loss": 4.22, "step": 25370 }, { "epoch": 0.7749236408063531, "grad_norm": 0.4971233308315277, "learning_rate": 5.993746300844216e-06, "loss": 4.2969, "step": 25371 }, { "epoch": 0.7749541844838118, "grad_norm": 0.4948396682739258, "learning_rate": 5.992187993243406e-06, "loss": 4.3059, "step": 25372 }, { "epoch": 0.7749847281612706, "grad_norm": 0.4938194155693054, "learning_rate": 5.990629860657288e-06, "loss": 4.2642, "step": 25373 }, { "epoch": 0.7750152718387294, "grad_norm": 0.4830183684825897, "learning_rate": 5.989071903100216e-06, "loss": 4.2103, "step": 25374 }, { "epoch": 0.7750458155161881, "grad_norm": 0.490640252828598, "learning_rate": 5.9875141205865375e-06, "loss": 4.2111, "step": 25375 }, { "epoch": 0.7750763591936469, "grad_norm": 0.4924805760383606, "learning_rate": 5.985956513130586e-06, "loss": 4.1739, "step": 25376 }, { "epoch": 0.7751069028711057, "grad_norm": 0.4932164251804352, "learning_rate": 5.984399080746716e-06, "loss": 4.2572, "step": 25377 }, { "epoch": 0.7751374465485644, "grad_norm": 0.494783878326416, "learning_rate": 5.9828418234492615e-06, "loss": 4.1827, "step": 25378 }, { "epoch": 0.7751679902260232, "grad_norm": 0.4869297444820404, "learning_rate": 5.981284741252552e-06, "loss": 4.261, "step": 25379 }, { "epoch": 0.775198533903482, "grad_norm": 0.4897947609424591, "learning_rate": 5.979727834170934e-06, "loss": 4.2463, "step": 25380 }, { "epoch": 0.7752290775809407, "grad_norm": 0.484142929315567, "learning_rate": 5.9781711022187465e-06, "loss": 4.283, "step": 25381 }, { "epoch": 0.7752596212583995, "grad_norm": 0.49535679817199707, "learning_rate": 5.9766145454103115e-06, "loss": 4.2798, "step": 25382 }, { "epoch": 0.7752901649358582, "grad_norm": 0.49495789408683777, "learning_rate": 5.975058163759972e-06, "loss": 4.2616, "step": 25383 }, { "epoch": 0.775320708613317, "grad_norm": 0.4839947521686554, "learning_rate": 5.973501957282049e-06, "loss": 4.288, "step": 25384 }, { "epoch": 0.7753512522907758, "grad_norm": 0.49702560901641846, "learning_rate": 5.9719459259908735e-06, "loss": 4.3029, "step": 25385 }, { "epoch": 0.7753817959682345, "grad_norm": 0.48401957750320435, "learning_rate": 5.9703900699007856e-06, "loss": 4.2756, "step": 25386 }, { "epoch": 0.7754123396456933, "grad_norm": 0.47918519377708435, "learning_rate": 5.96883438902609e-06, "loss": 4.2751, "step": 25387 }, { "epoch": 0.7754428833231521, "grad_norm": 0.48710280656814575, "learning_rate": 5.967278883381122e-06, "loss": 4.2231, "step": 25388 }, { "epoch": 0.7754734270006108, "grad_norm": 0.47990259528160095, "learning_rate": 5.965723552980212e-06, "loss": 4.2108, "step": 25389 }, { "epoch": 0.7755039706780696, "grad_norm": 0.49826598167419434, "learning_rate": 5.964168397837663e-06, "loss": 4.0721, "step": 25390 }, { "epoch": 0.7755345143555284, "grad_norm": 0.4895620346069336, "learning_rate": 5.962613417967811e-06, "loss": 4.2843, "step": 25391 }, { "epoch": 0.7755650580329871, "grad_norm": 0.48561012744903564, "learning_rate": 5.961058613384956e-06, "loss": 4.2816, "step": 25392 }, { "epoch": 0.775595601710446, "grad_norm": 0.49541667103767395, "learning_rate": 5.9595039841034315e-06, "loss": 4.2406, "step": 25393 }, { "epoch": 0.7756261453879048, "grad_norm": 0.4964974522590637, "learning_rate": 5.957949530137535e-06, "loss": 4.192, "step": 25394 }, { "epoch": 0.7756566890653634, "grad_norm": 0.4856224060058594, "learning_rate": 5.956395251501598e-06, "loss": 4.2266, "step": 25395 }, { "epoch": 0.7756872327428223, "grad_norm": 0.47940731048583984, "learning_rate": 5.954841148209913e-06, "loss": 4.2497, "step": 25396 }, { "epoch": 0.775717776420281, "grad_norm": 0.48821118474006653, "learning_rate": 5.9532872202768045e-06, "loss": 4.2952, "step": 25397 }, { "epoch": 0.7757483200977398, "grad_norm": 0.4821169078350067, "learning_rate": 5.951733467716564e-06, "loss": 4.1364, "step": 25398 }, { "epoch": 0.7757788637751986, "grad_norm": 0.4835699498653412, "learning_rate": 5.950179890543509e-06, "loss": 4.2532, "step": 25399 }, { "epoch": 0.7758094074526573, "grad_norm": 0.5092998147010803, "learning_rate": 5.94862648877195e-06, "loss": 4.2459, "step": 25400 }, { "epoch": 0.7758399511301161, "grad_norm": 0.47959986329078674, "learning_rate": 5.947073262416175e-06, "loss": 4.2664, "step": 25401 }, { "epoch": 0.7758704948075749, "grad_norm": 0.48715952038764954, "learning_rate": 5.94552021149049e-06, "loss": 4.2355, "step": 25402 }, { "epoch": 0.7759010384850336, "grad_norm": 0.48301127552986145, "learning_rate": 5.943967336009207e-06, "loss": 4.244, "step": 25403 }, { "epoch": 0.7759315821624924, "grad_norm": 0.4973221719264984, "learning_rate": 5.942414635986607e-06, "loss": 4.3651, "step": 25404 }, { "epoch": 0.7759621258399512, "grad_norm": 0.4901081621646881, "learning_rate": 5.940862111436992e-06, "loss": 4.2668, "step": 25405 }, { "epoch": 0.7759926695174099, "grad_norm": 0.48336872458457947, "learning_rate": 5.939309762374668e-06, "loss": 4.3068, "step": 25406 }, { "epoch": 0.7760232131948687, "grad_norm": 0.4974803030490875, "learning_rate": 5.937757588813911e-06, "loss": 4.1198, "step": 25407 }, { "epoch": 0.7760537568723275, "grad_norm": 0.4831768274307251, "learning_rate": 5.936205590769028e-06, "loss": 4.2795, "step": 25408 }, { "epoch": 0.7760843005497862, "grad_norm": 0.4801293611526489, "learning_rate": 5.934653768254303e-06, "loss": 4.2082, "step": 25409 }, { "epoch": 0.776114844227245, "grad_norm": 0.4792669713497162, "learning_rate": 5.933102121284015e-06, "loss": 4.2962, "step": 25410 }, { "epoch": 0.7761453879047038, "grad_norm": 0.4847677946090698, "learning_rate": 5.9315506498724585e-06, "loss": 4.22, "step": 25411 }, { "epoch": 0.7761759315821625, "grad_norm": 0.4840545058250427, "learning_rate": 5.9299993540339245e-06, "loss": 4.2808, "step": 25412 }, { "epoch": 0.7762064752596213, "grad_norm": 0.48211658000946045, "learning_rate": 5.928448233782688e-06, "loss": 4.2358, "step": 25413 }, { "epoch": 0.77623701893708, "grad_norm": 0.4923877418041229, "learning_rate": 5.926897289133041e-06, "loss": 4.2792, "step": 25414 }, { "epoch": 0.7762675626145388, "grad_norm": 0.48404985666275024, "learning_rate": 5.925346520099248e-06, "loss": 4.1073, "step": 25415 }, { "epoch": 0.7762981062919976, "grad_norm": 0.48774588108062744, "learning_rate": 5.923795926695597e-06, "loss": 4.1819, "step": 25416 }, { "epoch": 0.7763286499694563, "grad_norm": 0.4940001964569092, "learning_rate": 5.922245508936372e-06, "loss": 4.2376, "step": 25417 }, { "epoch": 0.7763591936469151, "grad_norm": 0.4868963062763214, "learning_rate": 5.9206952668358355e-06, "loss": 4.1968, "step": 25418 }, { "epoch": 0.7763897373243739, "grad_norm": 0.4945116937160492, "learning_rate": 5.919145200408266e-06, "loss": 4.226, "step": 25419 }, { "epoch": 0.7764202810018326, "grad_norm": 0.48478642106056213, "learning_rate": 5.9175953096679445e-06, "loss": 4.2043, "step": 25420 }, { "epoch": 0.7764508246792914, "grad_norm": 0.4947502017021179, "learning_rate": 5.916045594629127e-06, "loss": 4.2783, "step": 25421 }, { "epoch": 0.7764813683567502, "grad_norm": 0.48456066846847534, "learning_rate": 5.91449605530609e-06, "loss": 4.2806, "step": 25422 }, { "epoch": 0.7765119120342089, "grad_norm": 0.4926474392414093, "learning_rate": 5.912946691713106e-06, "loss": 4.3186, "step": 25423 }, { "epoch": 0.7765424557116677, "grad_norm": 0.4941122829914093, "learning_rate": 5.911397503864438e-06, "loss": 4.2653, "step": 25424 }, { "epoch": 0.7765729993891265, "grad_norm": 0.5034254193305969, "learning_rate": 5.909848491774339e-06, "loss": 4.2653, "step": 25425 }, { "epoch": 0.7766035430665852, "grad_norm": 0.5017790794372559, "learning_rate": 5.9082996554570894e-06, "loss": 4.2992, "step": 25426 }, { "epoch": 0.776634086744044, "grad_norm": 0.4887230098247528, "learning_rate": 5.9067509949269325e-06, "loss": 4.2884, "step": 25427 }, { "epoch": 0.7766646304215028, "grad_norm": 0.4835464060306549, "learning_rate": 5.905202510198135e-06, "loss": 4.2148, "step": 25428 }, { "epoch": 0.7766951740989615, "grad_norm": 0.4957624673843384, "learning_rate": 5.903654201284964e-06, "loss": 4.3432, "step": 25429 }, { "epoch": 0.7767257177764203, "grad_norm": 0.5005906224250793, "learning_rate": 5.902106068201657e-06, "loss": 4.1744, "step": 25430 }, { "epoch": 0.776756261453879, "grad_norm": 0.4901221692562103, "learning_rate": 5.90055811096249e-06, "loss": 4.2577, "step": 25431 }, { "epoch": 0.7767868051313378, "grad_norm": 0.49547263979911804, "learning_rate": 5.899010329581694e-06, "loss": 4.2842, "step": 25432 }, { "epoch": 0.7768173488087966, "grad_norm": 0.4956043064594269, "learning_rate": 5.897462724073532e-06, "loss": 4.227, "step": 25433 }, { "epoch": 0.7768478924862553, "grad_norm": 0.4977847933769226, "learning_rate": 5.895915294452259e-06, "loss": 4.1922, "step": 25434 }, { "epoch": 0.7768784361637141, "grad_norm": 0.48413828015327454, "learning_rate": 5.894368040732109e-06, "loss": 4.2154, "step": 25435 }, { "epoch": 0.7769089798411729, "grad_norm": 0.4848678708076477, "learning_rate": 5.892820962927337e-06, "loss": 4.2021, "step": 25436 }, { "epoch": 0.7769395235186316, "grad_norm": 0.49216532707214355, "learning_rate": 5.891274061052193e-06, "loss": 4.3204, "step": 25437 }, { "epoch": 0.7769700671960904, "grad_norm": 0.500654935836792, "learning_rate": 5.889727335120904e-06, "loss": 4.3142, "step": 25438 }, { "epoch": 0.7770006108735492, "grad_norm": 0.4848496615886688, "learning_rate": 5.888180785147732e-06, "loss": 4.1184, "step": 25439 }, { "epoch": 0.7770311545510079, "grad_norm": 0.49502724409103394, "learning_rate": 5.886634411146896e-06, "loss": 4.3193, "step": 25440 }, { "epoch": 0.7770616982284667, "grad_norm": 0.4831704795360565, "learning_rate": 5.88508821313265e-06, "loss": 4.2183, "step": 25441 }, { "epoch": 0.7770922419059255, "grad_norm": 0.48727652430534363, "learning_rate": 5.883542191119221e-06, "loss": 4.1742, "step": 25442 }, { "epoch": 0.7771227855833842, "grad_norm": 0.4926339387893677, "learning_rate": 5.8819963451208525e-06, "loss": 4.3164, "step": 25443 }, { "epoch": 0.777153329260843, "grad_norm": 0.4850957989692688, "learning_rate": 5.880450675151766e-06, "loss": 4.3159, "step": 25444 }, { "epoch": 0.7771838729383018, "grad_norm": 0.4902249276638031, "learning_rate": 5.878905181226202e-06, "loss": 4.3776, "step": 25445 }, { "epoch": 0.7772144166157605, "grad_norm": 0.4962617754936218, "learning_rate": 5.8773598633583945e-06, "loss": 4.3142, "step": 25446 }, { "epoch": 0.7772449602932193, "grad_norm": 0.5027171969413757, "learning_rate": 5.875814721562561e-06, "loss": 4.2154, "step": 25447 }, { "epoch": 0.777275503970678, "grad_norm": 0.48824214935302734, "learning_rate": 5.874269755852943e-06, "loss": 4.167, "step": 25448 }, { "epoch": 0.7773060476481368, "grad_norm": 0.4897719919681549, "learning_rate": 5.8727249662437454e-06, "loss": 4.2369, "step": 25449 }, { "epoch": 0.7773365913255956, "grad_norm": 0.49191638827323914, "learning_rate": 5.871180352749206e-06, "loss": 4.3832, "step": 25450 }, { "epoch": 0.7773671350030543, "grad_norm": 0.4874940514564514, "learning_rate": 5.8696359153835505e-06, "loss": 4.2266, "step": 25451 }, { "epoch": 0.7773976786805131, "grad_norm": 0.47930067777633667, "learning_rate": 5.868091654160987e-06, "loss": 4.2514, "step": 25452 }, { "epoch": 0.7774282223579719, "grad_norm": 0.4944573640823364, "learning_rate": 5.866547569095737e-06, "loss": 4.2195, "step": 25453 }, { "epoch": 0.7774587660354306, "grad_norm": 0.5057590007781982, "learning_rate": 5.865003660202032e-06, "loss": 4.2451, "step": 25454 }, { "epoch": 0.7774893097128894, "grad_norm": 0.49192091822624207, "learning_rate": 5.863459927494075e-06, "loss": 4.2508, "step": 25455 }, { "epoch": 0.7775198533903482, "grad_norm": 0.4928964078426361, "learning_rate": 5.861916370986073e-06, "loss": 4.2055, "step": 25456 }, { "epoch": 0.7775503970678069, "grad_norm": 0.4898829460144043, "learning_rate": 5.860372990692256e-06, "loss": 4.3059, "step": 25457 }, { "epoch": 0.7775809407452657, "grad_norm": 0.4953901469707489, "learning_rate": 5.858829786626818e-06, "loss": 4.2453, "step": 25458 }, { "epoch": 0.7776114844227245, "grad_norm": 0.4793749451637268, "learning_rate": 5.8572867588039734e-06, "loss": 4.1835, "step": 25459 }, { "epoch": 0.7776420281001832, "grad_norm": 0.4849420189857483, "learning_rate": 5.85574390723794e-06, "loss": 4.2704, "step": 25460 }, { "epoch": 0.777672571777642, "grad_norm": 0.49481716752052307, "learning_rate": 5.85420123194291e-06, "loss": 4.2555, "step": 25461 }, { "epoch": 0.7777031154551008, "grad_norm": 0.49963411688804626, "learning_rate": 5.852658732933092e-06, "loss": 4.3324, "step": 25462 }, { "epoch": 0.7777336591325595, "grad_norm": 0.4962807297706604, "learning_rate": 5.851116410222696e-06, "loss": 4.2735, "step": 25463 }, { "epoch": 0.7777642028100183, "grad_norm": 0.4892823398113251, "learning_rate": 5.849574263825911e-06, "loss": 4.2647, "step": 25464 }, { "epoch": 0.777794746487477, "grad_norm": 0.4816809296607971, "learning_rate": 5.84803229375695e-06, "loss": 4.1574, "step": 25465 }, { "epoch": 0.7778252901649358, "grad_norm": 0.4902202785015106, "learning_rate": 5.8464905000299914e-06, "loss": 4.2395, "step": 25466 }, { "epoch": 0.7778558338423947, "grad_norm": 0.49810633063316345, "learning_rate": 5.8449488826592455e-06, "loss": 4.3504, "step": 25467 }, { "epoch": 0.7778863775198533, "grad_norm": 0.4921821355819702, "learning_rate": 5.84340744165891e-06, "loss": 4.2545, "step": 25468 }, { "epoch": 0.7779169211973122, "grad_norm": 0.4868035912513733, "learning_rate": 5.841866177043165e-06, "loss": 4.2707, "step": 25469 }, { "epoch": 0.777947464874771, "grad_norm": 0.4889999032020569, "learning_rate": 5.840325088826215e-06, "loss": 4.1399, "step": 25470 }, { "epoch": 0.7779780085522296, "grad_norm": 0.4852887690067291, "learning_rate": 5.838784177022236e-06, "loss": 4.3124, "step": 25471 }, { "epoch": 0.7780085522296885, "grad_norm": 0.4855390191078186, "learning_rate": 5.837243441645429e-06, "loss": 4.228, "step": 25472 }, { "epoch": 0.7780390959071473, "grad_norm": 0.5043566226959229, "learning_rate": 5.835702882709968e-06, "loss": 4.2967, "step": 25473 }, { "epoch": 0.778069639584606, "grad_norm": 0.5014128684997559, "learning_rate": 5.834162500230051e-06, "loss": 4.071, "step": 25474 }, { "epoch": 0.7781001832620648, "grad_norm": 0.4835292398929596, "learning_rate": 5.832622294219847e-06, "loss": 4.2263, "step": 25475 }, { "epoch": 0.7781307269395236, "grad_norm": 0.49264317750930786, "learning_rate": 5.831082264693544e-06, "loss": 4.2186, "step": 25476 }, { "epoch": 0.7781612706169823, "grad_norm": 0.4892556071281433, "learning_rate": 5.829542411665329e-06, "loss": 4.2612, "step": 25477 }, { "epoch": 0.7781918142944411, "grad_norm": 0.48937591910362244, "learning_rate": 5.8280027351493686e-06, "loss": 4.2617, "step": 25478 }, { "epoch": 0.7782223579718999, "grad_norm": 0.486372172832489, "learning_rate": 5.82646323515984e-06, "loss": 4.2018, "step": 25479 }, { "epoch": 0.7782529016493586, "grad_norm": 0.4834485352039337, "learning_rate": 5.824923911710933e-06, "loss": 4.1875, "step": 25480 }, { "epoch": 0.7782834453268174, "grad_norm": 0.49360159039497375, "learning_rate": 5.8233847648168026e-06, "loss": 4.2628, "step": 25481 }, { "epoch": 0.7783139890042761, "grad_norm": 0.4949939250946045, "learning_rate": 5.821845794491635e-06, "loss": 4.3272, "step": 25482 }, { "epoch": 0.7783445326817349, "grad_norm": 0.49054333567619324, "learning_rate": 5.820307000749586e-06, "loss": 4.2526, "step": 25483 }, { "epoch": 0.7783750763591937, "grad_norm": 0.4952270984649658, "learning_rate": 5.8187683836048335e-06, "loss": 4.2685, "step": 25484 }, { "epoch": 0.7784056200366524, "grad_norm": 0.48257362842559814, "learning_rate": 5.817229943071548e-06, "loss": 4.3195, "step": 25485 }, { "epoch": 0.7784361637141112, "grad_norm": 0.48764973878860474, "learning_rate": 5.8156916791638815e-06, "loss": 4.2128, "step": 25486 }, { "epoch": 0.77846670739157, "grad_norm": 0.49408453702926636, "learning_rate": 5.814153591896013e-06, "loss": 4.2439, "step": 25487 }, { "epoch": 0.7784972510690287, "grad_norm": 0.49536603689193726, "learning_rate": 5.812615681282099e-06, "loss": 4.1819, "step": 25488 }, { "epoch": 0.7785277947464875, "grad_norm": 0.4879956543445587, "learning_rate": 5.811077947336288e-06, "loss": 4.249, "step": 25489 }, { "epoch": 0.7785583384239463, "grad_norm": 0.4976138174533844, "learning_rate": 5.8095403900727485e-06, "loss": 4.3014, "step": 25490 }, { "epoch": 0.778588882101405, "grad_norm": 0.48379987478256226, "learning_rate": 5.808003009505644e-06, "loss": 4.2232, "step": 25491 }, { "epoch": 0.7786194257788638, "grad_norm": 0.48352351784706116, "learning_rate": 5.806465805649119e-06, "loss": 4.3029, "step": 25492 }, { "epoch": 0.7786499694563226, "grad_norm": 0.5006685853004456, "learning_rate": 5.80492877851733e-06, "loss": 4.224, "step": 25493 }, { "epoch": 0.7786805131337813, "grad_norm": 0.4911626875400543, "learning_rate": 5.803391928124438e-06, "loss": 4.182, "step": 25494 }, { "epoch": 0.7787110568112401, "grad_norm": 0.4988963007926941, "learning_rate": 5.801855254484578e-06, "loss": 4.2943, "step": 25495 }, { "epoch": 0.7787416004886989, "grad_norm": 0.4997003376483917, "learning_rate": 5.800318757611908e-06, "loss": 4.2391, "step": 25496 }, { "epoch": 0.7787721441661576, "grad_norm": 0.4898681044578552, "learning_rate": 5.798782437520583e-06, "loss": 4.2078, "step": 25497 }, { "epoch": 0.7788026878436164, "grad_norm": 0.48795285820961, "learning_rate": 5.797246294224734e-06, "loss": 4.1741, "step": 25498 }, { "epoch": 0.7788332315210751, "grad_norm": 0.49326395988464355, "learning_rate": 5.7957103277385155e-06, "loss": 4.2314, "step": 25499 }, { "epoch": 0.7788637751985339, "grad_norm": 0.4876728951931, "learning_rate": 5.794174538076061e-06, "loss": 4.2641, "step": 25500 }, { "epoch": 0.7788943188759927, "grad_norm": 0.5068423748016357, "learning_rate": 5.792638925251523e-06, "loss": 4.1526, "step": 25501 }, { "epoch": 0.7789248625534514, "grad_norm": 0.5019737482070923, "learning_rate": 5.791103489279026e-06, "loss": 4.3416, "step": 25502 }, { "epoch": 0.7789554062309102, "grad_norm": 0.4903946816921234, "learning_rate": 5.789568230172723e-06, "loss": 4.2551, "step": 25503 }, { "epoch": 0.778985949908369, "grad_norm": 0.48168590664863586, "learning_rate": 5.788033147946737e-06, "loss": 4.2095, "step": 25504 }, { "epoch": 0.7790164935858277, "grad_norm": 0.48794376850128174, "learning_rate": 5.7864982426152125e-06, "loss": 4.2585, "step": 25505 }, { "epoch": 0.7790470372632865, "grad_norm": 0.5008757710456848, "learning_rate": 5.784963514192271e-06, "loss": 4.3008, "step": 25506 }, { "epoch": 0.7790775809407453, "grad_norm": 0.49599939584732056, "learning_rate": 5.783428962692047e-06, "loss": 4.2155, "step": 25507 }, { "epoch": 0.779108124618204, "grad_norm": 0.48736703395843506, "learning_rate": 5.781894588128684e-06, "loss": 4.2458, "step": 25508 }, { "epoch": 0.7791386682956628, "grad_norm": 0.4818844199180603, "learning_rate": 5.78036039051629e-06, "loss": 4.1952, "step": 25509 }, { "epoch": 0.7791692119731216, "grad_norm": 0.48346009850502014, "learning_rate": 5.778826369868997e-06, "loss": 4.3126, "step": 25510 }, { "epoch": 0.7791997556505803, "grad_norm": 0.4997071623802185, "learning_rate": 5.7772925262009416e-06, "loss": 4.2577, "step": 25511 }, { "epoch": 0.7792302993280391, "grad_norm": 0.49816322326660156, "learning_rate": 5.775758859526232e-06, "loss": 4.2473, "step": 25512 }, { "epoch": 0.7792608430054979, "grad_norm": 0.48857495188713074, "learning_rate": 5.774225369858994e-06, "loss": 4.1324, "step": 25513 }, { "epoch": 0.7792913866829566, "grad_norm": 0.4903108477592468, "learning_rate": 5.7726920572133525e-06, "loss": 4.2084, "step": 25514 }, { "epoch": 0.7793219303604154, "grad_norm": 0.500588595867157, "learning_rate": 5.771158921603415e-06, "loss": 4.3405, "step": 25515 }, { "epoch": 0.7793524740378741, "grad_norm": 0.5122499465942383, "learning_rate": 5.769625963043312e-06, "loss": 4.134, "step": 25516 }, { "epoch": 0.7793830177153329, "grad_norm": 0.4955594837665558, "learning_rate": 5.7680931815471405e-06, "loss": 4.3326, "step": 25517 }, { "epoch": 0.7794135613927917, "grad_norm": 0.4903062582015991, "learning_rate": 5.766560577129032e-06, "loss": 4.2096, "step": 25518 }, { "epoch": 0.7794441050702504, "grad_norm": 0.4861328899860382, "learning_rate": 5.765028149803089e-06, "loss": 4.2294, "step": 25519 }, { "epoch": 0.7794746487477092, "grad_norm": 0.48470538854599, "learning_rate": 5.7634958995834156e-06, "loss": 4.1848, "step": 25520 }, { "epoch": 0.779505192425168, "grad_norm": 0.48946234583854675, "learning_rate": 5.761963826484123e-06, "loss": 4.3279, "step": 25521 }, { "epoch": 0.7795357361026267, "grad_norm": 0.4921625256538391, "learning_rate": 5.760431930519331e-06, "loss": 4.2893, "step": 25522 }, { "epoch": 0.7795662797800855, "grad_norm": 0.4892491400241852, "learning_rate": 5.758900211703125e-06, "loss": 4.2962, "step": 25523 }, { "epoch": 0.7795968234575443, "grad_norm": 0.48133495450019836, "learning_rate": 5.757368670049618e-06, "loss": 4.2675, "step": 25524 }, { "epoch": 0.779627367135003, "grad_norm": 0.5198847651481628, "learning_rate": 5.755837305572917e-06, "loss": 4.3137, "step": 25525 }, { "epoch": 0.7796579108124618, "grad_norm": 0.49574777483940125, "learning_rate": 5.754306118287112e-06, "loss": 4.2568, "step": 25526 }, { "epoch": 0.7796884544899206, "grad_norm": 0.49684804677963257, "learning_rate": 5.752775108206304e-06, "loss": 4.2992, "step": 25527 }, { "epoch": 0.7797189981673793, "grad_norm": 0.49672242999076843, "learning_rate": 5.7512442753446e-06, "loss": 4.3272, "step": 25528 }, { "epoch": 0.7797495418448381, "grad_norm": 0.48832130432128906, "learning_rate": 5.749713619716076e-06, "loss": 4.2772, "step": 25529 }, { "epoch": 0.7797800855222969, "grad_norm": 0.48789122700691223, "learning_rate": 5.74818314133484e-06, "loss": 4.2636, "step": 25530 }, { "epoch": 0.7798106291997556, "grad_norm": 0.4964219033718109, "learning_rate": 5.746652840214986e-06, "loss": 4.2636, "step": 25531 }, { "epoch": 0.7798411728772144, "grad_norm": 0.48732635378837585, "learning_rate": 5.7451227163705906e-06, "loss": 4.2342, "step": 25532 }, { "epoch": 0.7798717165546731, "grad_norm": 0.4918873608112335, "learning_rate": 5.743592769815759e-06, "loss": 4.32, "step": 25533 }, { "epoch": 0.7799022602321319, "grad_norm": 0.4846739172935486, "learning_rate": 5.742063000564568e-06, "loss": 4.3044, "step": 25534 }, { "epoch": 0.7799328039095907, "grad_norm": 0.5072282552719116, "learning_rate": 5.740533408631097e-06, "loss": 4.2133, "step": 25535 }, { "epoch": 0.7799633475870494, "grad_norm": 0.5002427101135254, "learning_rate": 5.739003994029446e-06, "loss": 4.2414, "step": 25536 }, { "epoch": 0.7799938912645082, "grad_norm": 0.49768468737602234, "learning_rate": 5.737474756773678e-06, "loss": 4.2938, "step": 25537 }, { "epoch": 0.780024434941967, "grad_norm": 0.48780083656311035, "learning_rate": 5.735945696877887e-06, "loss": 4.2283, "step": 25538 }, { "epoch": 0.7800549786194257, "grad_norm": 0.4822632670402527, "learning_rate": 5.734416814356155e-06, "loss": 4.1422, "step": 25539 }, { "epoch": 0.7800855222968845, "grad_norm": 0.4851227402687073, "learning_rate": 5.732888109222545e-06, "loss": 4.3059, "step": 25540 }, { "epoch": 0.7801160659743434, "grad_norm": 0.48365676403045654, "learning_rate": 5.731359581491142e-06, "loss": 4.29, "step": 25541 }, { "epoch": 0.780146609651802, "grad_norm": 0.4811047315597534, "learning_rate": 5.729831231176022e-06, "loss": 4.2377, "step": 25542 }, { "epoch": 0.7801771533292609, "grad_norm": 0.4865950644016266, "learning_rate": 5.728303058291249e-06, "loss": 4.2487, "step": 25543 }, { "epoch": 0.7802076970067197, "grad_norm": 0.5057483911514282, "learning_rate": 5.7267750628508974e-06, "loss": 4.3379, "step": 25544 }, { "epoch": 0.7802382406841784, "grad_norm": 0.4888453781604767, "learning_rate": 5.7252472448690445e-06, "loss": 4.2209, "step": 25545 }, { "epoch": 0.7802687843616372, "grad_norm": 0.4901796281337738, "learning_rate": 5.723719604359743e-06, "loss": 4.1672, "step": 25546 }, { "epoch": 0.7802993280390959, "grad_norm": 0.48487430810928345, "learning_rate": 5.722192141337074e-06, "loss": 4.3058, "step": 25547 }, { "epoch": 0.7803298717165547, "grad_norm": 0.4920792579650879, "learning_rate": 5.720664855815086e-06, "loss": 4.2478, "step": 25548 }, { "epoch": 0.7803604153940135, "grad_norm": 0.506247878074646, "learning_rate": 5.719137747807854e-06, "loss": 4.2816, "step": 25549 }, { "epoch": 0.7803909590714722, "grad_norm": 0.4901735484600067, "learning_rate": 5.7176108173294305e-06, "loss": 4.2903, "step": 25550 }, { "epoch": 0.780421502748931, "grad_norm": 0.4939350187778473, "learning_rate": 5.716084064393884e-06, "loss": 4.2537, "step": 25551 }, { "epoch": 0.7804520464263898, "grad_norm": 0.4837179183959961, "learning_rate": 5.714557489015257e-06, "loss": 4.2196, "step": 25552 }, { "epoch": 0.7804825901038485, "grad_norm": 0.48209816217422485, "learning_rate": 5.713031091207624e-06, "loss": 4.1732, "step": 25553 }, { "epoch": 0.7805131337813073, "grad_norm": 0.48780447244644165, "learning_rate": 5.7115048709850235e-06, "loss": 4.274, "step": 25554 }, { "epoch": 0.7805436774587661, "grad_norm": 0.4852561056613922, "learning_rate": 5.709978828361515e-06, "loss": 4.1541, "step": 25555 }, { "epoch": 0.7805742211362248, "grad_norm": 0.4996359944343567, "learning_rate": 5.708452963351155e-06, "loss": 4.33, "step": 25556 }, { "epoch": 0.7806047648136836, "grad_norm": 0.48896753787994385, "learning_rate": 5.70692727596798e-06, "loss": 4.2396, "step": 25557 }, { "epoch": 0.7806353084911424, "grad_norm": 0.49037066102027893, "learning_rate": 5.7054017662260454e-06, "loss": 4.2222, "step": 25558 }, { "epoch": 0.7806658521686011, "grad_norm": 0.5009043216705322, "learning_rate": 5.703876434139404e-06, "loss": 4.2913, "step": 25559 }, { "epoch": 0.7806963958460599, "grad_norm": 0.48252999782562256, "learning_rate": 5.702351279722088e-06, "loss": 4.2651, "step": 25560 }, { "epoch": 0.7807269395235187, "grad_norm": 0.493295282125473, "learning_rate": 5.7008263029881465e-06, "loss": 4.1975, "step": 25561 }, { "epoch": 0.7807574832009774, "grad_norm": 0.4958776831626892, "learning_rate": 5.6993015039516236e-06, "loss": 4.348, "step": 25562 }, { "epoch": 0.7807880268784362, "grad_norm": 0.49251851439476013, "learning_rate": 5.697776882626549e-06, "loss": 4.2041, "step": 25563 }, { "epoch": 0.7808185705558949, "grad_norm": 0.5076796412467957, "learning_rate": 5.696252439026975e-06, "loss": 4.3131, "step": 25564 }, { "epoch": 0.7808491142333537, "grad_norm": 0.48278698325157166, "learning_rate": 5.69472817316693e-06, "loss": 4.1389, "step": 25565 }, { "epoch": 0.7808796579108125, "grad_norm": 0.4843387007713318, "learning_rate": 5.693204085060441e-06, "loss": 4.2365, "step": 25566 }, { "epoch": 0.7809102015882712, "grad_norm": 0.48197242617607117, "learning_rate": 5.691680174721553e-06, "loss": 4.2388, "step": 25567 }, { "epoch": 0.78094074526573, "grad_norm": 0.5071352124214172, "learning_rate": 5.690156442164291e-06, "loss": 4.2085, "step": 25568 }, { "epoch": 0.7809712889431888, "grad_norm": 0.4913792014122009, "learning_rate": 5.688632887402682e-06, "loss": 4.3254, "step": 25569 }, { "epoch": 0.7810018326206475, "grad_norm": 0.48659801483154297, "learning_rate": 5.687109510450769e-06, "loss": 4.1926, "step": 25570 }, { "epoch": 0.7810323762981063, "grad_norm": 0.4868543744087219, "learning_rate": 5.6855863113225606e-06, "loss": 4.2944, "step": 25571 }, { "epoch": 0.7810629199755651, "grad_norm": 0.4862358570098877, "learning_rate": 5.684063290032088e-06, "loss": 4.2571, "step": 25572 }, { "epoch": 0.7810934636530238, "grad_norm": 0.49895572662353516, "learning_rate": 5.6825404465933845e-06, "loss": 4.2759, "step": 25573 }, { "epoch": 0.7811240073304826, "grad_norm": 0.482413649559021, "learning_rate": 5.681017781020456e-06, "loss": 4.2654, "step": 25574 }, { "epoch": 0.7811545510079414, "grad_norm": 0.4849465787410736, "learning_rate": 5.67949529332733e-06, "loss": 4.3035, "step": 25575 }, { "epoch": 0.7811850946854001, "grad_norm": 0.48470181226730347, "learning_rate": 5.677972983528032e-06, "loss": 4.2919, "step": 25576 }, { "epoch": 0.7812156383628589, "grad_norm": 0.4940682351589203, "learning_rate": 5.676450851636561e-06, "loss": 4.3314, "step": 25577 }, { "epoch": 0.7812461820403177, "grad_norm": 0.4908665716648102, "learning_rate": 5.674928897666945e-06, "loss": 4.2947, "step": 25578 }, { "epoch": 0.7812767257177764, "grad_norm": 0.4994204640388489, "learning_rate": 5.673407121633201e-06, "loss": 4.1282, "step": 25579 }, { "epoch": 0.7813072693952352, "grad_norm": 0.48555776476860046, "learning_rate": 5.671885523549336e-06, "loss": 4.1682, "step": 25580 }, { "epoch": 0.7813378130726939, "grad_norm": 0.4879995882511139, "learning_rate": 5.670364103429349e-06, "loss": 4.2494, "step": 25581 }, { "epoch": 0.7813683567501527, "grad_norm": 0.4946382939815521, "learning_rate": 5.6688428612872655e-06, "loss": 4.2699, "step": 25582 }, { "epoch": 0.7813989004276115, "grad_norm": 0.4916069209575653, "learning_rate": 5.667321797137079e-06, "loss": 4.2359, "step": 25583 }, { "epoch": 0.7814294441050702, "grad_norm": 0.49930137395858765, "learning_rate": 5.665800910992805e-06, "loss": 4.3259, "step": 25584 }, { "epoch": 0.781459987782529, "grad_norm": 0.4844387471675873, "learning_rate": 5.664280202868438e-06, "loss": 4.1891, "step": 25585 }, { "epoch": 0.7814905314599878, "grad_norm": 0.47802212834358215, "learning_rate": 5.662759672777984e-06, "loss": 4.1865, "step": 25586 }, { "epoch": 0.7815210751374465, "grad_norm": 0.5005815029144287, "learning_rate": 5.661239320735451e-06, "loss": 4.3697, "step": 25587 }, { "epoch": 0.7815516188149053, "grad_norm": 0.4918702244758606, "learning_rate": 5.659719146754824e-06, "loss": 4.1574, "step": 25588 }, { "epoch": 0.7815821624923641, "grad_norm": 0.48970651626586914, "learning_rate": 5.658199150850108e-06, "loss": 4.2522, "step": 25589 }, { "epoch": 0.7816127061698228, "grad_norm": 0.4909796416759491, "learning_rate": 5.6566793330353e-06, "loss": 4.3058, "step": 25590 }, { "epoch": 0.7816432498472816, "grad_norm": 0.4956430196762085, "learning_rate": 5.655159693324388e-06, "loss": 4.2172, "step": 25591 }, { "epoch": 0.7816737935247404, "grad_norm": 0.4970787465572357, "learning_rate": 5.653640231731363e-06, "loss": 4.2278, "step": 25592 }, { "epoch": 0.7817043372021991, "grad_norm": 0.48095598816871643, "learning_rate": 5.652120948270229e-06, "loss": 4.2814, "step": 25593 }, { "epoch": 0.7817348808796579, "grad_norm": 0.5006640553474426, "learning_rate": 5.650601842954959e-06, "loss": 4.232, "step": 25594 }, { "epoch": 0.7817654245571167, "grad_norm": 0.4881022274494171, "learning_rate": 5.64908291579955e-06, "loss": 4.263, "step": 25595 }, { "epoch": 0.7817959682345754, "grad_norm": 0.4933825135231018, "learning_rate": 5.647564166817979e-06, "loss": 4.1647, "step": 25596 }, { "epoch": 0.7818265119120342, "grad_norm": 0.5035550594329834, "learning_rate": 5.646045596024241e-06, "loss": 4.2332, "step": 25597 }, { "epoch": 0.7818570555894929, "grad_norm": 0.49961474537849426, "learning_rate": 5.6445272034323125e-06, "loss": 4.3349, "step": 25598 }, { "epoch": 0.7818875992669517, "grad_norm": 0.4922657310962677, "learning_rate": 5.6430089890561645e-06, "loss": 4.2019, "step": 25599 }, { "epoch": 0.7819181429444105, "grad_norm": 0.5020859837532043, "learning_rate": 5.6414909529097866e-06, "loss": 4.2389, "step": 25600 }, { "epoch": 0.7819486866218692, "grad_norm": 0.4862465262413025, "learning_rate": 5.639973095007161e-06, "loss": 4.2789, "step": 25601 }, { "epoch": 0.781979230299328, "grad_norm": 0.49907442927360535, "learning_rate": 5.638455415362254e-06, "loss": 4.3066, "step": 25602 }, { "epoch": 0.7820097739767868, "grad_norm": 0.4899959862232208, "learning_rate": 5.636937913989038e-06, "loss": 4.2287, "step": 25603 }, { "epoch": 0.7820403176542455, "grad_norm": 0.49120932817459106, "learning_rate": 5.6354205909014995e-06, "loss": 4.1468, "step": 25604 }, { "epoch": 0.7820708613317043, "grad_norm": 0.4933964014053345, "learning_rate": 5.633903446113592e-06, "loss": 4.3315, "step": 25605 }, { "epoch": 0.7821014050091631, "grad_norm": 0.4865107536315918, "learning_rate": 5.6323864796392924e-06, "loss": 4.2961, "step": 25606 }, { "epoch": 0.7821319486866218, "grad_norm": 0.4930713176727295, "learning_rate": 5.630869691492577e-06, "loss": 4.3136, "step": 25607 }, { "epoch": 0.7821624923640806, "grad_norm": 0.49370861053466797, "learning_rate": 5.629353081687394e-06, "loss": 4.2693, "step": 25608 }, { "epoch": 0.7821930360415394, "grad_norm": 0.5065662264823914, "learning_rate": 5.627836650237717e-06, "loss": 4.2258, "step": 25609 }, { "epoch": 0.7822235797189981, "grad_norm": 0.5035523772239685, "learning_rate": 5.626320397157517e-06, "loss": 4.2182, "step": 25610 }, { "epoch": 0.782254123396457, "grad_norm": 0.500633955001831, "learning_rate": 5.6248043224607446e-06, "loss": 4.2413, "step": 25611 }, { "epoch": 0.7822846670739158, "grad_norm": 0.49496936798095703, "learning_rate": 5.623288426161352e-06, "loss": 4.2267, "step": 25612 }, { "epoch": 0.7823152107513744, "grad_norm": 0.5064134001731873, "learning_rate": 5.621772708273313e-06, "loss": 4.2558, "step": 25613 }, { "epoch": 0.7823457544288333, "grad_norm": 0.4914108216762543, "learning_rate": 5.620257168810569e-06, "loss": 4.3051, "step": 25614 }, { "epoch": 0.782376298106292, "grad_norm": 0.48950472474098206, "learning_rate": 5.61874180778709e-06, "loss": 4.196, "step": 25615 }, { "epoch": 0.7824068417837508, "grad_norm": 0.4955596923828125, "learning_rate": 5.617226625216812e-06, "loss": 4.224, "step": 25616 }, { "epoch": 0.7824373854612096, "grad_norm": 0.49253591895103455, "learning_rate": 5.615711621113695e-06, "loss": 4.2871, "step": 25617 }, { "epoch": 0.7824679291386683, "grad_norm": 0.4862496256828308, "learning_rate": 5.614196795491694e-06, "loss": 4.2143, "step": 25618 }, { "epoch": 0.782498472816127, "grad_norm": 0.4877965450286865, "learning_rate": 5.612682148364742e-06, "loss": 4.3138, "step": 25619 }, { "epoch": 0.7825290164935859, "grad_norm": 0.4856550395488739, "learning_rate": 5.611167679746796e-06, "loss": 4.2377, "step": 25620 }, { "epoch": 0.7825595601710446, "grad_norm": 0.4955466687679291, "learning_rate": 5.609653389651803e-06, "loss": 4.3298, "step": 25621 }, { "epoch": 0.7825901038485034, "grad_norm": 0.4923091232776642, "learning_rate": 5.608139278093694e-06, "loss": 4.2603, "step": 25622 }, { "epoch": 0.7826206475259622, "grad_norm": 0.48957765102386475, "learning_rate": 5.606625345086417e-06, "loss": 4.2898, "step": 25623 }, { "epoch": 0.7826511912034209, "grad_norm": 0.49110376834869385, "learning_rate": 5.6051115906439185e-06, "loss": 4.1979, "step": 25624 }, { "epoch": 0.7826817348808797, "grad_norm": 0.5074560642242432, "learning_rate": 5.603598014780123e-06, "loss": 4.3225, "step": 25625 }, { "epoch": 0.7827122785583385, "grad_norm": 0.4884619116783142, "learning_rate": 5.602084617508979e-06, "loss": 4.1795, "step": 25626 }, { "epoch": 0.7827428222357972, "grad_norm": 0.48504260182380676, "learning_rate": 5.600571398844409e-06, "loss": 4.2929, "step": 25627 }, { "epoch": 0.782773365913256, "grad_norm": 0.4906224310398102, "learning_rate": 5.59905835880036e-06, "loss": 4.2902, "step": 25628 }, { "epoch": 0.7828039095907148, "grad_norm": 0.4872666597366333, "learning_rate": 5.597545497390749e-06, "loss": 4.2561, "step": 25629 }, { "epoch": 0.7828344532681735, "grad_norm": 0.4927855432033539, "learning_rate": 5.5960328146295175e-06, "loss": 4.2292, "step": 25630 }, { "epoch": 0.7828649969456323, "grad_norm": 0.4822557866573334, "learning_rate": 5.594520310530582e-06, "loss": 4.2021, "step": 25631 }, { "epoch": 0.782895540623091, "grad_norm": 0.49854129552841187, "learning_rate": 5.593007985107884e-06, "loss": 4.262, "step": 25632 }, { "epoch": 0.7829260843005498, "grad_norm": 0.4906822443008423, "learning_rate": 5.59149583837533e-06, "loss": 4.2973, "step": 25633 }, { "epoch": 0.7829566279780086, "grad_norm": 0.499776154756546, "learning_rate": 5.589983870346854e-06, "loss": 4.2479, "step": 25634 }, { "epoch": 0.7829871716554673, "grad_norm": 0.4931563138961792, "learning_rate": 5.588472081036383e-06, "loss": 4.2807, "step": 25635 }, { "epoch": 0.7830177153329261, "grad_norm": 0.5008875131607056, "learning_rate": 5.586960470457825e-06, "loss": 4.2817, "step": 25636 }, { "epoch": 0.7830482590103849, "grad_norm": 0.5077012181282043, "learning_rate": 5.585449038625101e-06, "loss": 4.277, "step": 25637 }, { "epoch": 0.7830788026878436, "grad_norm": 0.4964672327041626, "learning_rate": 5.583937785552138e-06, "loss": 4.2134, "step": 25638 }, { "epoch": 0.7831093463653024, "grad_norm": 0.489772766828537, "learning_rate": 5.5824267112528335e-06, "loss": 4.1947, "step": 25639 }, { "epoch": 0.7831398900427612, "grad_norm": 0.4912532866001129, "learning_rate": 5.580915815741111e-06, "loss": 4.2897, "step": 25640 }, { "epoch": 0.7831704337202199, "grad_norm": 0.49085578322410583, "learning_rate": 5.579405099030887e-06, "loss": 4.3361, "step": 25641 }, { "epoch": 0.7832009773976787, "grad_norm": 0.4893455505371094, "learning_rate": 5.577894561136057e-06, "loss": 4.3138, "step": 25642 }, { "epoch": 0.7832315210751375, "grad_norm": 0.5447370409965515, "learning_rate": 5.5763842020705474e-06, "loss": 4.1678, "step": 25643 }, { "epoch": 0.7832620647525962, "grad_norm": 0.4914744198322296, "learning_rate": 5.5748740218482555e-06, "loss": 4.2276, "step": 25644 }, { "epoch": 0.783292608430055, "grad_norm": 0.49478763341903687, "learning_rate": 5.573364020483077e-06, "loss": 4.2967, "step": 25645 }, { "epoch": 0.7833231521075138, "grad_norm": 0.5016651153564453, "learning_rate": 5.571854197988924e-06, "loss": 4.3222, "step": 25646 }, { "epoch": 0.7833536957849725, "grad_norm": 0.491943895816803, "learning_rate": 5.570344554379708e-06, "loss": 4.273, "step": 25647 }, { "epoch": 0.7833842394624313, "grad_norm": 0.491353839635849, "learning_rate": 5.568835089669311e-06, "loss": 4.2082, "step": 25648 }, { "epoch": 0.78341478313989, "grad_norm": 0.5093901753425598, "learning_rate": 5.567325803871645e-06, "loss": 4.3035, "step": 25649 }, { "epoch": 0.7834453268173488, "grad_norm": 0.4972222149372101, "learning_rate": 5.565816697000597e-06, "loss": 4.2445, "step": 25650 }, { "epoch": 0.7834758704948076, "grad_norm": 0.4980255663394928, "learning_rate": 5.564307769070065e-06, "loss": 4.3, "step": 25651 }, { "epoch": 0.7835064141722663, "grad_norm": 0.49297234416007996, "learning_rate": 5.5627990200939535e-06, "loss": 4.275, "step": 25652 }, { "epoch": 0.7835369578497251, "grad_norm": 0.4909452199935913, "learning_rate": 5.561290450086134e-06, "loss": 4.289, "step": 25653 }, { "epoch": 0.7835675015271839, "grad_norm": 0.49138343334198, "learning_rate": 5.559782059060511e-06, "loss": 4.2559, "step": 25654 }, { "epoch": 0.7835980452046426, "grad_norm": 0.48569807410240173, "learning_rate": 5.5582738470309755e-06, "loss": 4.2541, "step": 25655 }, { "epoch": 0.7836285888821014, "grad_norm": 0.5005301833152771, "learning_rate": 5.5567658140114025e-06, "loss": 4.308, "step": 25656 }, { "epoch": 0.7836591325595602, "grad_norm": 0.49491778016090393, "learning_rate": 5.555257960015684e-06, "loss": 4.3114, "step": 25657 }, { "epoch": 0.7836896762370189, "grad_norm": 0.49871474504470825, "learning_rate": 5.55375028505771e-06, "loss": 4.2404, "step": 25658 }, { "epoch": 0.7837202199144777, "grad_norm": 0.49969470500946045, "learning_rate": 5.552242789151355e-06, "loss": 4.2488, "step": 25659 }, { "epoch": 0.7837507635919365, "grad_norm": 0.4947771728038788, "learning_rate": 5.550735472310492e-06, "loss": 4.2875, "step": 25660 }, { "epoch": 0.7837813072693952, "grad_norm": 0.4897732138633728, "learning_rate": 5.549228334549014e-06, "loss": 4.2539, "step": 25661 }, { "epoch": 0.783811850946854, "grad_norm": 0.4945889711380005, "learning_rate": 5.547721375880785e-06, "loss": 4.2182, "step": 25662 }, { "epoch": 0.7838423946243128, "grad_norm": 0.49166053533554077, "learning_rate": 5.546214596319685e-06, "loss": 4.2535, "step": 25663 }, { "epoch": 0.7838729383017715, "grad_norm": 0.483641117811203, "learning_rate": 5.5447079958796e-06, "loss": 4.2225, "step": 25664 }, { "epoch": 0.7839034819792303, "grad_norm": 0.4970664978027344, "learning_rate": 5.54320157457438e-06, "loss": 4.3476, "step": 25665 }, { "epoch": 0.783934025656689, "grad_norm": 0.49709996581077576, "learning_rate": 5.541695332417918e-06, "loss": 4.2095, "step": 25666 }, { "epoch": 0.7839645693341478, "grad_norm": 0.4940583109855652, "learning_rate": 5.540189269424062e-06, "loss": 4.2688, "step": 25667 }, { "epoch": 0.7839951130116066, "grad_norm": 0.5011662840843201, "learning_rate": 5.538683385606688e-06, "loss": 4.266, "step": 25668 }, { "epoch": 0.7840256566890653, "grad_norm": 0.48909732699394226, "learning_rate": 5.537177680979672e-06, "loss": 4.2391, "step": 25669 }, { "epoch": 0.7840562003665241, "grad_norm": 0.49063369631767273, "learning_rate": 5.535672155556859e-06, "loss": 4.2367, "step": 25670 }, { "epoch": 0.7840867440439829, "grad_norm": 0.4893277585506439, "learning_rate": 5.5341668093521206e-06, "loss": 4.2716, "step": 25671 }, { "epoch": 0.7841172877214416, "grad_norm": 0.491489440202713, "learning_rate": 5.532661642379322e-06, "loss": 4.2978, "step": 25672 }, { "epoch": 0.7841478313989004, "grad_norm": 0.49592673778533936, "learning_rate": 5.531156654652311e-06, "loss": 4.344, "step": 25673 }, { "epoch": 0.7841783750763592, "grad_norm": 0.4918704926967621, "learning_rate": 5.529651846184958e-06, "loss": 4.3451, "step": 25674 }, { "epoch": 0.7842089187538179, "grad_norm": 0.4998569190502167, "learning_rate": 5.528147216991111e-06, "loss": 4.2671, "step": 25675 }, { "epoch": 0.7842394624312767, "grad_norm": 0.5040147304534912, "learning_rate": 5.5266427670846164e-06, "loss": 4.2622, "step": 25676 }, { "epoch": 0.7842700061087355, "grad_norm": 0.4862798750400543, "learning_rate": 5.525138496479335e-06, "loss": 4.2137, "step": 25677 }, { "epoch": 0.7843005497861942, "grad_norm": 0.4910570979118347, "learning_rate": 5.523634405189124e-06, "loss": 4.1657, "step": 25678 }, { "epoch": 0.784331093463653, "grad_norm": 0.5017520785331726, "learning_rate": 5.522130493227814e-06, "loss": 4.3296, "step": 25679 }, { "epoch": 0.7843616371411118, "grad_norm": 0.49465543031692505, "learning_rate": 5.5206267606092655e-06, "loss": 4.2523, "step": 25680 }, { "epoch": 0.7843921808185705, "grad_norm": 0.4881516993045807, "learning_rate": 5.5191232073473295e-06, "loss": 4.2882, "step": 25681 }, { "epoch": 0.7844227244960293, "grad_norm": 0.49437230825424194, "learning_rate": 5.5176198334558365e-06, "loss": 4.1534, "step": 25682 }, { "epoch": 0.784453268173488, "grad_norm": 0.5036155581474304, "learning_rate": 5.516116638948637e-06, "loss": 4.2577, "step": 25683 }, { "epoch": 0.7844838118509468, "grad_norm": 0.4977491796016693, "learning_rate": 5.514613623839565e-06, "loss": 4.272, "step": 25684 }, { "epoch": 0.7845143555284056, "grad_norm": 0.49321219325065613, "learning_rate": 5.5131107881424645e-06, "loss": 4.1468, "step": 25685 }, { "epoch": 0.7845448992058643, "grad_norm": 0.5075358748435974, "learning_rate": 5.511608131871179e-06, "loss": 4.2238, "step": 25686 }, { "epoch": 0.7845754428833231, "grad_norm": 0.4907991290092468, "learning_rate": 5.51010565503953e-06, "loss": 4.227, "step": 25687 }, { "epoch": 0.784605986560782, "grad_norm": 0.4920029640197754, "learning_rate": 5.508603357661357e-06, "loss": 4.2566, "step": 25688 }, { "epoch": 0.7846365302382406, "grad_norm": 0.49330976605415344, "learning_rate": 5.5071012397505035e-06, "loss": 4.2489, "step": 25689 }, { "epoch": 0.7846670739156995, "grad_norm": 0.4868151545524597, "learning_rate": 5.505599301320791e-06, "loss": 4.2512, "step": 25690 }, { "epoch": 0.7846976175931583, "grad_norm": 0.4927594065666199, "learning_rate": 5.504097542386041e-06, "loss": 4.2301, "step": 25691 }, { "epoch": 0.784728161270617, "grad_norm": 0.4983966052532196, "learning_rate": 5.5025959629600975e-06, "loss": 4.2706, "step": 25692 }, { "epoch": 0.7847587049480758, "grad_norm": 0.5001124143600464, "learning_rate": 5.501094563056769e-06, "loss": 4.1696, "step": 25693 }, { "epoch": 0.7847892486255346, "grad_norm": 0.49032336473464966, "learning_rate": 5.499593342689888e-06, "loss": 4.2416, "step": 25694 }, { "epoch": 0.7848197923029933, "grad_norm": 0.49750059843063354, "learning_rate": 5.498092301873284e-06, "loss": 4.2492, "step": 25695 }, { "epoch": 0.7848503359804521, "grad_norm": 0.4893060624599457, "learning_rate": 5.496591440620766e-06, "loss": 4.1379, "step": 25696 }, { "epoch": 0.7848808796579108, "grad_norm": 0.4874076545238495, "learning_rate": 5.4950907589461644e-06, "loss": 4.2167, "step": 25697 }, { "epoch": 0.7849114233353696, "grad_norm": 0.48420450091362, "learning_rate": 5.493590256863282e-06, "loss": 4.2727, "step": 25698 }, { "epoch": 0.7849419670128284, "grad_norm": 0.4898054003715515, "learning_rate": 5.492089934385944e-06, "loss": 4.2592, "step": 25699 }, { "epoch": 0.7849725106902871, "grad_norm": 0.4922638237476349, "learning_rate": 5.490589791527972e-06, "loss": 4.2233, "step": 25700 }, { "epoch": 0.7850030543677459, "grad_norm": 0.4956161379814148, "learning_rate": 5.489089828303162e-06, "loss": 4.2404, "step": 25701 }, { "epoch": 0.7850335980452047, "grad_norm": 0.5034058094024658, "learning_rate": 5.487590044725335e-06, "loss": 4.2671, "step": 25702 }, { "epoch": 0.7850641417226634, "grad_norm": 0.48803359270095825, "learning_rate": 5.486090440808306e-06, "loss": 4.2825, "step": 25703 }, { "epoch": 0.7850946854001222, "grad_norm": 0.4869316816329956, "learning_rate": 5.484591016565868e-06, "loss": 4.259, "step": 25704 }, { "epoch": 0.785125229077581, "grad_norm": 0.48664847016334534, "learning_rate": 5.483091772011839e-06, "loss": 4.1898, "step": 25705 }, { "epoch": 0.7851557727550397, "grad_norm": 0.49058997631073, "learning_rate": 5.481592707160016e-06, "loss": 4.2472, "step": 25706 }, { "epoch": 0.7851863164324985, "grad_norm": 0.5166900753974915, "learning_rate": 5.4800938220242074e-06, "loss": 4.3028, "step": 25707 }, { "epoch": 0.7852168601099573, "grad_norm": 0.4902782440185547, "learning_rate": 5.4785951166182045e-06, "loss": 4.2247, "step": 25708 }, { "epoch": 0.785247403787416, "grad_norm": 0.4932991564273834, "learning_rate": 5.477096590955822e-06, "loss": 4.2144, "step": 25709 }, { "epoch": 0.7852779474648748, "grad_norm": 0.49594277143478394, "learning_rate": 5.475598245050842e-06, "loss": 4.1906, "step": 25710 }, { "epoch": 0.7853084911423336, "grad_norm": 0.49188676476478577, "learning_rate": 5.474100078917066e-06, "loss": 4.251, "step": 25711 }, { "epoch": 0.7853390348197923, "grad_norm": 0.5013412237167358, "learning_rate": 5.472602092568297e-06, "loss": 4.2547, "step": 25712 }, { "epoch": 0.7853695784972511, "grad_norm": 0.4999169409275055, "learning_rate": 5.471104286018313e-06, "loss": 4.2858, "step": 25713 }, { "epoch": 0.7854001221747098, "grad_norm": 0.49577149748802185, "learning_rate": 5.469606659280921e-06, "loss": 4.2694, "step": 25714 }, { "epoch": 0.7854306658521686, "grad_norm": 0.4892454147338867, "learning_rate": 5.468109212369896e-06, "loss": 4.1794, "step": 25715 }, { "epoch": 0.7854612095296274, "grad_norm": 0.5014078617095947, "learning_rate": 5.46661194529903e-06, "loss": 4.3933, "step": 25716 }, { "epoch": 0.7854917532070861, "grad_norm": 0.502656877040863, "learning_rate": 5.465114858082118e-06, "loss": 4.2698, "step": 25717 }, { "epoch": 0.7855222968845449, "grad_norm": 0.49268433451652527, "learning_rate": 5.46361795073293e-06, "loss": 4.2922, "step": 25718 }, { "epoch": 0.7855528405620037, "grad_norm": 0.5017307996749878, "learning_rate": 5.462121223265257e-06, "loss": 4.2646, "step": 25719 }, { "epoch": 0.7855833842394624, "grad_norm": 0.4882773458957672, "learning_rate": 5.460624675692885e-06, "loss": 4.1939, "step": 25720 }, { "epoch": 0.7856139279169212, "grad_norm": 0.49402377009391785, "learning_rate": 5.45912830802959e-06, "loss": 4.1809, "step": 25721 }, { "epoch": 0.78564447159438, "grad_norm": 0.4833982586860657, "learning_rate": 5.457632120289139e-06, "loss": 4.2925, "step": 25722 }, { "epoch": 0.7856750152718387, "grad_norm": 0.4900956153869629, "learning_rate": 5.456136112485324e-06, "loss": 4.2545, "step": 25723 }, { "epoch": 0.7857055589492975, "grad_norm": 0.497750848531723, "learning_rate": 5.454640284631906e-06, "loss": 4.2785, "step": 25724 }, { "epoch": 0.7857361026267563, "grad_norm": 0.48422279953956604, "learning_rate": 5.453144636742663e-06, "loss": 4.2198, "step": 25725 }, { "epoch": 0.785766646304215, "grad_norm": 0.498189777135849, "learning_rate": 5.451649168831374e-06, "loss": 4.2597, "step": 25726 }, { "epoch": 0.7857971899816738, "grad_norm": 0.5081023573875427, "learning_rate": 5.450153880911798e-06, "loss": 4.2775, "step": 25727 }, { "epoch": 0.7858277336591326, "grad_norm": 0.4933333992958069, "learning_rate": 5.448658772997703e-06, "loss": 4.3054, "step": 25728 }, { "epoch": 0.7858582773365913, "grad_norm": 0.4882643222808838, "learning_rate": 5.447163845102868e-06, "loss": 4.2904, "step": 25729 }, { "epoch": 0.7858888210140501, "grad_norm": 0.5048599243164062, "learning_rate": 5.44566909724104e-06, "loss": 4.3026, "step": 25730 }, { "epoch": 0.7859193646915088, "grad_norm": 0.4865899384021759, "learning_rate": 5.444174529426e-06, "loss": 4.2517, "step": 25731 }, { "epoch": 0.7859499083689676, "grad_norm": 0.48807159066200256, "learning_rate": 5.4426801416714916e-06, "loss": 4.2556, "step": 25732 }, { "epoch": 0.7859804520464264, "grad_norm": 0.48885393142700195, "learning_rate": 5.44118593399128e-06, "loss": 4.2655, "step": 25733 }, { "epoch": 0.7860109957238851, "grad_norm": 0.4988972246646881, "learning_rate": 5.439691906399136e-06, "loss": 4.2475, "step": 25734 }, { "epoch": 0.7860415394013439, "grad_norm": 0.5488502979278564, "learning_rate": 5.438198058908797e-06, "loss": 4.2556, "step": 25735 }, { "epoch": 0.7860720830788027, "grad_norm": 0.49674081802368164, "learning_rate": 5.4367043915340334e-06, "loss": 4.2813, "step": 25736 }, { "epoch": 0.7861026267562614, "grad_norm": 0.5038264393806458, "learning_rate": 5.435210904288585e-06, "loss": 4.1557, "step": 25737 }, { "epoch": 0.7861331704337202, "grad_norm": 0.496809720993042, "learning_rate": 5.433717597186214e-06, "loss": 4.2352, "step": 25738 }, { "epoch": 0.786163714111179, "grad_norm": 0.5053209662437439, "learning_rate": 5.43222447024066e-06, "loss": 4.2608, "step": 25739 }, { "epoch": 0.7861942577886377, "grad_norm": 0.5032590627670288, "learning_rate": 5.430731523465682e-06, "loss": 4.2774, "step": 25740 }, { "epoch": 0.7862248014660965, "grad_norm": 0.5041967034339905, "learning_rate": 5.429238756875013e-06, "loss": 4.3784, "step": 25741 }, { "epoch": 0.7862553451435553, "grad_norm": 0.495744913816452, "learning_rate": 5.4277461704824066e-06, "loss": 4.2019, "step": 25742 }, { "epoch": 0.786285888821014, "grad_norm": 0.508870542049408, "learning_rate": 5.4262537643016086e-06, "loss": 4.2766, "step": 25743 }, { "epoch": 0.7863164324984728, "grad_norm": 0.4864768087863922, "learning_rate": 5.424761538346351e-06, "loss": 4.2705, "step": 25744 }, { "epoch": 0.7863469761759316, "grad_norm": 0.5046385526657104, "learning_rate": 5.423269492630378e-06, "loss": 4.3707, "step": 25745 }, { "epoch": 0.7863775198533903, "grad_norm": 0.5005388259887695, "learning_rate": 5.4217776271674344e-06, "loss": 4.3167, "step": 25746 }, { "epoch": 0.7864080635308491, "grad_norm": 0.4968571960926056, "learning_rate": 5.420285941971245e-06, "loss": 4.2509, "step": 25747 }, { "epoch": 0.7864386072083078, "grad_norm": 0.49614977836608887, "learning_rate": 5.4187944370555575e-06, "loss": 4.2352, "step": 25748 }, { "epoch": 0.7864691508857666, "grad_norm": 0.4831103980541229, "learning_rate": 5.417303112434088e-06, "loss": 4.257, "step": 25749 }, { "epoch": 0.7864996945632254, "grad_norm": 0.5048219561576843, "learning_rate": 5.415811968120577e-06, "loss": 4.2208, "step": 25750 }, { "epoch": 0.7865302382406841, "grad_norm": 0.4980454444885254, "learning_rate": 5.414321004128764e-06, "loss": 4.1712, "step": 25751 }, { "epoch": 0.7865607819181429, "grad_norm": 0.49350693821907043, "learning_rate": 5.412830220472359e-06, "loss": 4.2111, "step": 25752 }, { "epoch": 0.7865913255956017, "grad_norm": 0.5170696377754211, "learning_rate": 5.411339617165104e-06, "loss": 4.1325, "step": 25753 }, { "epoch": 0.7866218692730604, "grad_norm": 0.5008599162101746, "learning_rate": 5.4098491942207146e-06, "loss": 4.2935, "step": 25754 }, { "epoch": 0.7866524129505192, "grad_norm": 0.5002163648605347, "learning_rate": 5.408358951652911e-06, "loss": 4.3214, "step": 25755 }, { "epoch": 0.786682956627978, "grad_norm": 0.5101760625839233, "learning_rate": 5.406868889475419e-06, "loss": 4.2751, "step": 25756 }, { "epoch": 0.7867135003054367, "grad_norm": 0.5070928335189819, "learning_rate": 5.405379007701966e-06, "loss": 4.3113, "step": 25757 }, { "epoch": 0.7867440439828955, "grad_norm": 0.4883427023887634, "learning_rate": 5.403889306346258e-06, "loss": 4.2773, "step": 25758 }, { "epoch": 0.7867745876603544, "grad_norm": 0.5002567768096924, "learning_rate": 5.4023997854220135e-06, "loss": 4.2112, "step": 25759 }, { "epoch": 0.786805131337813, "grad_norm": 0.48957329988479614, "learning_rate": 5.400910444942958e-06, "loss": 4.3028, "step": 25760 }, { "epoch": 0.7868356750152719, "grad_norm": 0.49097657203674316, "learning_rate": 5.39942128492279e-06, "loss": 4.2042, "step": 25761 }, { "epoch": 0.7868662186927307, "grad_norm": 0.4925180673599243, "learning_rate": 5.397932305375228e-06, "loss": 4.235, "step": 25762 }, { "epoch": 0.7868967623701894, "grad_norm": 0.49643567204475403, "learning_rate": 5.396443506313989e-06, "loss": 4.233, "step": 25763 }, { "epoch": 0.7869273060476482, "grad_norm": 0.4847470223903656, "learning_rate": 5.394954887752768e-06, "loss": 4.2533, "step": 25764 }, { "epoch": 0.7869578497251069, "grad_norm": 0.49724718928337097, "learning_rate": 5.393466449705281e-06, "loss": 4.3079, "step": 25765 }, { "epoch": 0.7869883934025657, "grad_norm": 0.5034345388412476, "learning_rate": 5.3919781921852265e-06, "loss": 4.2101, "step": 25766 }, { "epoch": 0.7870189370800245, "grad_norm": 0.49677038192749023, "learning_rate": 5.390490115206306e-06, "loss": 4.2431, "step": 25767 }, { "epoch": 0.7870494807574832, "grad_norm": 0.49358418583869934, "learning_rate": 5.3890022187822355e-06, "loss": 4.1942, "step": 25768 }, { "epoch": 0.787080024434942, "grad_norm": 0.5003625154495239, "learning_rate": 5.387514502926702e-06, "loss": 4.2977, "step": 25769 }, { "epoch": 0.7871105681124008, "grad_norm": 0.4956183135509491, "learning_rate": 5.3860269676533985e-06, "loss": 4.3126, "step": 25770 }, { "epoch": 0.7871411117898595, "grad_norm": 0.49308204650878906, "learning_rate": 5.384539612976039e-06, "loss": 4.1211, "step": 25771 }, { "epoch": 0.7871716554673183, "grad_norm": 0.4968908429145813, "learning_rate": 5.383052438908301e-06, "loss": 4.3416, "step": 25772 }, { "epoch": 0.7872021991447771, "grad_norm": 0.5017104148864746, "learning_rate": 5.3815654454638846e-06, "loss": 4.2979, "step": 25773 }, { "epoch": 0.7872327428222358, "grad_norm": 0.5027527213096619, "learning_rate": 5.380078632656488e-06, "loss": 4.2042, "step": 25774 }, { "epoch": 0.7872632864996946, "grad_norm": 0.5003440380096436, "learning_rate": 5.378592000499791e-06, "loss": 4.2198, "step": 25775 }, { "epoch": 0.7872938301771534, "grad_norm": 0.5234846472740173, "learning_rate": 5.377105549007483e-06, "loss": 4.1909, "step": 25776 }, { "epoch": 0.7873243738546121, "grad_norm": 0.5031172633171082, "learning_rate": 5.375619278193261e-06, "loss": 4.1954, "step": 25777 }, { "epoch": 0.7873549175320709, "grad_norm": 0.49775364995002747, "learning_rate": 5.3741331880707955e-06, "loss": 4.24, "step": 25778 }, { "epoch": 0.7873854612095297, "grad_norm": 0.492682546377182, "learning_rate": 5.372647278653775e-06, "loss": 4.3079, "step": 25779 }, { "epoch": 0.7874160048869884, "grad_norm": 0.4949329197406769, "learning_rate": 5.371161549955892e-06, "loss": 4.2458, "step": 25780 }, { "epoch": 0.7874465485644472, "grad_norm": 0.4985285997390747, "learning_rate": 5.369676001990806e-06, "loss": 4.1552, "step": 25781 }, { "epoch": 0.7874770922419059, "grad_norm": 0.5063414573669434, "learning_rate": 5.3681906347722165e-06, "loss": 4.1045, "step": 25782 }, { "epoch": 0.7875076359193647, "grad_norm": 0.5017011165618896, "learning_rate": 5.36670544831378e-06, "loss": 4.268, "step": 25783 }, { "epoch": 0.7875381795968235, "grad_norm": 0.49367162585258484, "learning_rate": 5.365220442629191e-06, "loss": 4.2852, "step": 25784 }, { "epoch": 0.7875687232742822, "grad_norm": 0.49045929312705994, "learning_rate": 5.36373561773211e-06, "loss": 4.2316, "step": 25785 }, { "epoch": 0.787599266951741, "grad_norm": 0.5047215223312378, "learning_rate": 5.362250973636204e-06, "loss": 4.2856, "step": 25786 }, { "epoch": 0.7876298106291998, "grad_norm": 0.5068309903144836, "learning_rate": 5.36076651035515e-06, "loss": 4.2185, "step": 25787 }, { "epoch": 0.7876603543066585, "grad_norm": 0.4917011260986328, "learning_rate": 5.359282227902626e-06, "loss": 4.2794, "step": 25788 }, { "epoch": 0.7876908979841173, "grad_norm": 0.49176034331321716, "learning_rate": 5.35779812629228e-06, "loss": 4.2233, "step": 25789 }, { "epoch": 0.7877214416615761, "grad_norm": 0.4982333183288574, "learning_rate": 5.356314205537785e-06, "loss": 4.2455, "step": 25790 }, { "epoch": 0.7877519853390348, "grad_norm": 0.4993048310279846, "learning_rate": 5.354830465652813e-06, "loss": 4.212, "step": 25791 }, { "epoch": 0.7877825290164936, "grad_norm": 0.4854014217853546, "learning_rate": 5.353346906651011e-06, "loss": 4.2727, "step": 25792 }, { "epoch": 0.7878130726939524, "grad_norm": 0.49418410658836365, "learning_rate": 5.351863528546042e-06, "loss": 4.1631, "step": 25793 }, { "epoch": 0.7878436163714111, "grad_norm": 0.49120214581489563, "learning_rate": 5.350380331351576e-06, "loss": 4.2654, "step": 25794 }, { "epoch": 0.7878741600488699, "grad_norm": 0.4943239390850067, "learning_rate": 5.348897315081255e-06, "loss": 4.2523, "step": 25795 }, { "epoch": 0.7879047037263287, "grad_norm": 0.4991791546344757, "learning_rate": 5.347414479748741e-06, "loss": 4.2149, "step": 25796 }, { "epoch": 0.7879352474037874, "grad_norm": 0.5174658298492432, "learning_rate": 5.345931825367692e-06, "loss": 4.3194, "step": 25797 }, { "epoch": 0.7879657910812462, "grad_norm": 0.4952668845653534, "learning_rate": 5.3444493519517466e-06, "loss": 4.2545, "step": 25798 }, { "epoch": 0.7879963347587049, "grad_norm": 0.4955403208732605, "learning_rate": 5.3429670595145695e-06, "loss": 4.3087, "step": 25799 }, { "epoch": 0.7880268784361637, "grad_norm": 0.49186116456985474, "learning_rate": 5.341484948069803e-06, "loss": 4.199, "step": 25800 }, { "epoch": 0.7880574221136225, "grad_norm": 0.5013721585273743, "learning_rate": 5.340003017631082e-06, "loss": 4.2774, "step": 25801 }, { "epoch": 0.7880879657910812, "grad_norm": 0.4974331557750702, "learning_rate": 5.3385212682120685e-06, "loss": 4.2844, "step": 25802 }, { "epoch": 0.78811850946854, "grad_norm": 0.4995882213115692, "learning_rate": 5.337039699826393e-06, "loss": 4.1049, "step": 25803 }, { "epoch": 0.7881490531459988, "grad_norm": 0.4952652156352997, "learning_rate": 5.335558312487701e-06, "loss": 4.2774, "step": 25804 }, { "epoch": 0.7881795968234575, "grad_norm": 0.48325279355049133, "learning_rate": 5.334077106209645e-06, "loss": 4.1278, "step": 25805 }, { "epoch": 0.7882101405009163, "grad_norm": 0.49323445558547974, "learning_rate": 5.332596081005842e-06, "loss": 4.2549, "step": 25806 }, { "epoch": 0.7882406841783751, "grad_norm": 0.4999222755432129, "learning_rate": 5.331115236889939e-06, "loss": 4.2829, "step": 25807 }, { "epoch": 0.7882712278558338, "grad_norm": 0.4984950125217438, "learning_rate": 5.329634573875578e-06, "loss": 4.2377, "step": 25808 }, { "epoch": 0.7883017715332926, "grad_norm": 0.4956302046775818, "learning_rate": 5.328154091976379e-06, "loss": 4.185, "step": 25809 }, { "epoch": 0.7883323152107514, "grad_norm": 0.4950990676879883, "learning_rate": 5.326673791205977e-06, "loss": 4.2751, "step": 25810 }, { "epoch": 0.7883628588882101, "grad_norm": 0.4964326322078705, "learning_rate": 5.3251936715780135e-06, "loss": 4.3348, "step": 25811 }, { "epoch": 0.7883934025656689, "grad_norm": 0.4976639747619629, "learning_rate": 5.3237137331061e-06, "loss": 4.2655, "step": 25812 }, { "epoch": 0.7884239462431277, "grad_norm": 0.48993152379989624, "learning_rate": 5.322233975803872e-06, "loss": 4.1096, "step": 25813 }, { "epoch": 0.7884544899205864, "grad_norm": 0.4883376955986023, "learning_rate": 5.32075439968496e-06, "loss": 4.242, "step": 25814 }, { "epoch": 0.7884850335980452, "grad_norm": 0.496669739484787, "learning_rate": 5.319275004762981e-06, "loss": 4.3408, "step": 25815 }, { "epoch": 0.7885155772755039, "grad_norm": 0.49970847368240356, "learning_rate": 5.317795791051544e-06, "loss": 4.1464, "step": 25816 }, { "epoch": 0.7885461209529627, "grad_norm": 0.5055446028709412, "learning_rate": 5.316316758564291e-06, "loss": 4.2739, "step": 25817 }, { "epoch": 0.7885766646304215, "grad_norm": 0.4977000653743744, "learning_rate": 5.314837907314823e-06, "loss": 4.2726, "step": 25818 }, { "epoch": 0.7886072083078802, "grad_norm": 0.4972505271434784, "learning_rate": 5.313359237316773e-06, "loss": 4.2186, "step": 25819 }, { "epoch": 0.788637751985339, "grad_norm": 0.504349410533905, "learning_rate": 5.311880748583736e-06, "loss": 4.2214, "step": 25820 }, { "epoch": 0.7886682956627978, "grad_norm": 0.4973170757293701, "learning_rate": 5.310402441129336e-06, "loss": 4.3307, "step": 25821 }, { "epoch": 0.7886988393402565, "grad_norm": 0.505559504032135, "learning_rate": 5.308924314967192e-06, "loss": 4.3069, "step": 25822 }, { "epoch": 0.7887293830177153, "grad_norm": 0.49548131227493286, "learning_rate": 5.307446370110899e-06, "loss": 4.2271, "step": 25823 }, { "epoch": 0.7887599266951741, "grad_norm": 0.4937587380409241, "learning_rate": 5.305968606574072e-06, "loss": 4.3853, "step": 25824 }, { "epoch": 0.7887904703726328, "grad_norm": 0.48794126510620117, "learning_rate": 5.304491024370323e-06, "loss": 4.2817, "step": 25825 }, { "epoch": 0.7888210140500916, "grad_norm": 0.5013288855552673, "learning_rate": 5.303013623513245e-06, "loss": 4.3004, "step": 25826 }, { "epoch": 0.7888515577275504, "grad_norm": 0.4926062524318695, "learning_rate": 5.30153640401645e-06, "loss": 4.2882, "step": 25827 }, { "epoch": 0.7888821014050091, "grad_norm": 0.5088395476341248, "learning_rate": 5.300059365893542e-06, "loss": 4.1836, "step": 25828 }, { "epoch": 0.788912645082468, "grad_norm": 0.4879406988620758, "learning_rate": 5.298582509158112e-06, "loss": 4.2198, "step": 25829 }, { "epoch": 0.7889431887599268, "grad_norm": 0.4950309097766876, "learning_rate": 5.2971058338237674e-06, "loss": 4.2394, "step": 25830 }, { "epoch": 0.7889737324373854, "grad_norm": 0.5033910274505615, "learning_rate": 5.295629339904099e-06, "loss": 4.2199, "step": 25831 }, { "epoch": 0.7890042761148442, "grad_norm": 0.5091927647590637, "learning_rate": 5.294153027412696e-06, "loss": 4.2469, "step": 25832 }, { "epoch": 0.7890348197923029, "grad_norm": 0.4884200692176819, "learning_rate": 5.292676896363163e-06, "loss": 4.1962, "step": 25833 }, { "epoch": 0.7890653634697617, "grad_norm": 0.5001296401023865, "learning_rate": 5.2912009467690814e-06, "loss": 4.2055, "step": 25834 }, { "epoch": 0.7890959071472206, "grad_norm": 0.49439799785614014, "learning_rate": 5.2897251786440474e-06, "loss": 4.2314, "step": 25835 }, { "epoch": 0.7891264508246792, "grad_norm": 0.5012564063072205, "learning_rate": 5.288249592001651e-06, "loss": 4.3003, "step": 25836 }, { "epoch": 0.789156994502138, "grad_norm": 0.5010641813278198, "learning_rate": 5.286774186855473e-06, "loss": 4.2152, "step": 25837 }, { "epoch": 0.7891875381795969, "grad_norm": 0.4994233548641205, "learning_rate": 5.285298963219096e-06, "loss": 4.349, "step": 25838 }, { "epoch": 0.7892180818570556, "grad_norm": 0.49965226650238037, "learning_rate": 5.283823921106118e-06, "loss": 4.2841, "step": 25839 }, { "epoch": 0.7892486255345144, "grad_norm": 0.4953327476978302, "learning_rate": 5.282349060530101e-06, "loss": 4.2746, "step": 25840 }, { "epoch": 0.7892791692119732, "grad_norm": 0.5034763216972351, "learning_rate": 5.280874381504636e-06, "loss": 4.1228, "step": 25841 }, { "epoch": 0.7893097128894319, "grad_norm": 0.504449725151062, "learning_rate": 5.279399884043304e-06, "loss": 4.1242, "step": 25842 }, { "epoch": 0.7893402565668907, "grad_norm": 0.48742127418518066, "learning_rate": 5.277925568159669e-06, "loss": 4.2325, "step": 25843 }, { "epoch": 0.7893708002443495, "grad_norm": 0.49138113856315613, "learning_rate": 5.276451433867316e-06, "loss": 4.2256, "step": 25844 }, { "epoch": 0.7894013439218082, "grad_norm": 0.5083811283111572, "learning_rate": 5.274977481179821e-06, "loss": 4.3182, "step": 25845 }, { "epoch": 0.789431887599267, "grad_norm": 0.4958066940307617, "learning_rate": 5.27350371011075e-06, "loss": 4.1979, "step": 25846 }, { "epoch": 0.7894624312767257, "grad_norm": 0.4974024295806885, "learning_rate": 5.272030120673669e-06, "loss": 4.2487, "step": 25847 }, { "epoch": 0.7894929749541845, "grad_norm": 0.486629456281662, "learning_rate": 5.270556712882152e-06, "loss": 4.2433, "step": 25848 }, { "epoch": 0.7895235186316433, "grad_norm": 0.49673935770988464, "learning_rate": 5.269083486749757e-06, "loss": 4.3277, "step": 25849 }, { "epoch": 0.789554062309102, "grad_norm": 0.4987516701221466, "learning_rate": 5.267610442290064e-06, "loss": 4.2579, "step": 25850 }, { "epoch": 0.7895846059865608, "grad_norm": 0.5035579800605774, "learning_rate": 5.266137579516619e-06, "loss": 4.2133, "step": 25851 }, { "epoch": 0.7896151496640196, "grad_norm": 0.487888365983963, "learning_rate": 5.2646648984429916e-06, "loss": 4.1945, "step": 25852 }, { "epoch": 0.7896456933414783, "grad_norm": 0.4984501600265503, "learning_rate": 5.263192399082747e-06, "loss": 4.2882, "step": 25853 }, { "epoch": 0.7896762370189371, "grad_norm": 0.49546942114830017, "learning_rate": 5.261720081449434e-06, "loss": 4.1728, "step": 25854 }, { "epoch": 0.7897067806963959, "grad_norm": 0.49153491854667664, "learning_rate": 5.26024794555661e-06, "loss": 4.252, "step": 25855 }, { "epoch": 0.7897373243738546, "grad_norm": 0.5014365315437317, "learning_rate": 5.2587759914178416e-06, "loss": 4.2336, "step": 25856 }, { "epoch": 0.7897678680513134, "grad_norm": 0.5050495862960815, "learning_rate": 5.257304219046663e-06, "loss": 4.285, "step": 25857 }, { "epoch": 0.7897984117287722, "grad_norm": 0.4891408681869507, "learning_rate": 5.255832628456636e-06, "loss": 4.2243, "step": 25858 }, { "epoch": 0.7898289554062309, "grad_norm": 0.49171483516693115, "learning_rate": 5.254361219661316e-06, "loss": 4.2681, "step": 25859 }, { "epoch": 0.7898594990836897, "grad_norm": 0.4982854425907135, "learning_rate": 5.252889992674237e-06, "loss": 4.1078, "step": 25860 }, { "epoch": 0.7898900427611485, "grad_norm": 0.49129167199134827, "learning_rate": 5.251418947508962e-06, "loss": 4.1852, "step": 25861 }, { "epoch": 0.7899205864386072, "grad_norm": 0.4944114089012146, "learning_rate": 5.2499480841790186e-06, "loss": 4.2786, "step": 25862 }, { "epoch": 0.789951130116066, "grad_norm": 0.4945419430732727, "learning_rate": 5.2484774026979626e-06, "loss": 4.3113, "step": 25863 }, { "epoch": 0.7899816737935247, "grad_norm": 0.496969074010849, "learning_rate": 5.247006903079332e-06, "loss": 4.2949, "step": 25864 }, { "epoch": 0.7900122174709835, "grad_norm": 0.4949483573436737, "learning_rate": 5.2455365853366575e-06, "loss": 4.2277, "step": 25865 }, { "epoch": 0.7900427611484423, "grad_norm": 0.4894202947616577, "learning_rate": 5.2440664494834865e-06, "loss": 4.2126, "step": 25866 }, { "epoch": 0.790073304825901, "grad_norm": 0.5082806348800659, "learning_rate": 5.242596495533358e-06, "loss": 4.228, "step": 25867 }, { "epoch": 0.7901038485033598, "grad_norm": 0.4933708608150482, "learning_rate": 5.241126723499795e-06, "loss": 4.3174, "step": 25868 }, { "epoch": 0.7901343921808186, "grad_norm": 0.5073224306106567, "learning_rate": 5.239657133396339e-06, "loss": 4.3421, "step": 25869 }, { "epoch": 0.7901649358582773, "grad_norm": 0.48403266072273254, "learning_rate": 5.238187725236523e-06, "loss": 4.2672, "step": 25870 }, { "epoch": 0.7901954795357361, "grad_norm": 0.49458208680152893, "learning_rate": 5.236718499033868e-06, "loss": 4.2953, "step": 25871 }, { "epoch": 0.7902260232131949, "grad_norm": 0.4894702732563019, "learning_rate": 5.23524945480191e-06, "loss": 4.235, "step": 25872 }, { "epoch": 0.7902565668906536, "grad_norm": 0.5004519820213318, "learning_rate": 5.233780592554174e-06, "loss": 4.2731, "step": 25873 }, { "epoch": 0.7902871105681124, "grad_norm": 0.5091608166694641, "learning_rate": 5.23231191230418e-06, "loss": 4.2268, "step": 25874 }, { "epoch": 0.7903176542455712, "grad_norm": 0.49694201350212097, "learning_rate": 5.230843414065453e-06, "loss": 4.3345, "step": 25875 }, { "epoch": 0.7903481979230299, "grad_norm": 0.49594923853874207, "learning_rate": 5.229375097851521e-06, "loss": 4.3064, "step": 25876 }, { "epoch": 0.7903787416004887, "grad_norm": 0.4858320355415344, "learning_rate": 5.227906963675891e-06, "loss": 4.3162, "step": 25877 }, { "epoch": 0.7904092852779475, "grad_norm": 0.4984927475452423, "learning_rate": 5.2264390115520925e-06, "loss": 4.2734, "step": 25878 }, { "epoch": 0.7904398289554062, "grad_norm": 0.4948062300682068, "learning_rate": 5.22497124149364e-06, "loss": 4.2313, "step": 25879 }, { "epoch": 0.790470372632865, "grad_norm": 0.4985238313674927, "learning_rate": 5.2235036535140334e-06, "loss": 4.2724, "step": 25880 }, { "epoch": 0.7905009163103237, "grad_norm": 0.49403873085975647, "learning_rate": 5.222036247626808e-06, "loss": 4.1991, "step": 25881 }, { "epoch": 0.7905314599877825, "grad_norm": 0.5069119930267334, "learning_rate": 5.220569023845454e-06, "loss": 4.3125, "step": 25882 }, { "epoch": 0.7905620036652413, "grad_norm": 0.49091076850891113, "learning_rate": 5.219101982183491e-06, "loss": 4.2465, "step": 25883 }, { "epoch": 0.7905925473427, "grad_norm": 0.49505627155303955, "learning_rate": 5.217635122654435e-06, "loss": 4.3489, "step": 25884 }, { "epoch": 0.7906230910201588, "grad_norm": 0.4890121817588806, "learning_rate": 5.216168445271774e-06, "loss": 4.2023, "step": 25885 }, { "epoch": 0.7906536346976176, "grad_norm": 0.4890202283859253, "learning_rate": 5.214701950049025e-06, "loss": 4.2744, "step": 25886 }, { "epoch": 0.7906841783750763, "grad_norm": 0.490734338760376, "learning_rate": 5.213235636999692e-06, "loss": 4.2288, "step": 25887 }, { "epoch": 0.7907147220525351, "grad_norm": 0.49237072467803955, "learning_rate": 5.211769506137265e-06, "loss": 4.1494, "step": 25888 }, { "epoch": 0.7907452657299939, "grad_norm": 0.5190905332565308, "learning_rate": 5.2103035574752515e-06, "loss": 4.2078, "step": 25889 }, { "epoch": 0.7907758094074526, "grad_norm": 0.501035213470459, "learning_rate": 5.208837791027155e-06, "loss": 4.1981, "step": 25890 }, { "epoch": 0.7908063530849114, "grad_norm": 0.5053672790527344, "learning_rate": 5.207372206806457e-06, "loss": 4.2109, "step": 25891 }, { "epoch": 0.7908368967623702, "grad_norm": 0.5039876699447632, "learning_rate": 5.205906804826665e-06, "loss": 4.1901, "step": 25892 }, { "epoch": 0.7908674404398289, "grad_norm": 0.49849992990493774, "learning_rate": 5.204441585101264e-06, "loss": 4.3044, "step": 25893 }, { "epoch": 0.7908979841172877, "grad_norm": 0.49548253417015076, "learning_rate": 5.202976547643751e-06, "loss": 4.3053, "step": 25894 }, { "epoch": 0.7909285277947465, "grad_norm": 0.4914454519748688, "learning_rate": 5.201511692467603e-06, "loss": 4.2305, "step": 25895 }, { "epoch": 0.7909590714722052, "grad_norm": 0.496447890996933, "learning_rate": 5.200047019586324e-06, "loss": 4.2666, "step": 25896 }, { "epoch": 0.790989615149664, "grad_norm": 0.4948928952217102, "learning_rate": 5.1985825290133875e-06, "loss": 4.2623, "step": 25897 }, { "epoch": 0.7910201588271227, "grad_norm": 0.4969938397407532, "learning_rate": 5.197118220762287e-06, "loss": 4.2016, "step": 25898 }, { "epoch": 0.7910507025045815, "grad_norm": 0.4963144063949585, "learning_rate": 5.195654094846494e-06, "loss": 4.238, "step": 25899 }, { "epoch": 0.7910812461820403, "grad_norm": 0.4971006214618683, "learning_rate": 5.1941901512794986e-06, "loss": 4.2225, "step": 25900 }, { "epoch": 0.791111789859499, "grad_norm": 0.499021053314209, "learning_rate": 5.192726390074782e-06, "loss": 4.1824, "step": 25901 }, { "epoch": 0.7911423335369578, "grad_norm": 0.4939724802970886, "learning_rate": 5.191262811245812e-06, "loss": 4.1704, "step": 25902 }, { "epoch": 0.7911728772144166, "grad_norm": 0.5021686553955078, "learning_rate": 5.189799414806068e-06, "loss": 4.3289, "step": 25903 }, { "epoch": 0.7912034208918753, "grad_norm": 0.503673791885376, "learning_rate": 5.188336200769034e-06, "loss": 4.2487, "step": 25904 }, { "epoch": 0.7912339645693341, "grad_norm": 0.5025995969772339, "learning_rate": 5.186873169148168e-06, "loss": 4.2229, "step": 25905 }, { "epoch": 0.791264508246793, "grad_norm": 0.4975298345088959, "learning_rate": 5.185410319956948e-06, "loss": 4.3309, "step": 25906 }, { "epoch": 0.7912950519242516, "grad_norm": 0.5007157325744629, "learning_rate": 5.183947653208851e-06, "loss": 4.3471, "step": 25907 }, { "epoch": 0.7913255956017105, "grad_norm": 0.501494824886322, "learning_rate": 5.1824851689173286e-06, "loss": 4.2604, "step": 25908 }, { "epoch": 0.7913561392791693, "grad_norm": 0.4933198094367981, "learning_rate": 5.181022867095858e-06, "loss": 4.1407, "step": 25909 }, { "epoch": 0.791386682956628, "grad_norm": 0.4894958436489105, "learning_rate": 5.179560747757903e-06, "loss": 4.2379, "step": 25910 }, { "epoch": 0.7914172266340868, "grad_norm": 0.49225959181785583, "learning_rate": 5.178098810916915e-06, "loss": 4.2289, "step": 25911 }, { "epoch": 0.7914477703115456, "grad_norm": 0.5030831098556519, "learning_rate": 5.176637056586364e-06, "loss": 4.1709, "step": 25912 }, { "epoch": 0.7914783139890043, "grad_norm": 0.49946463108062744, "learning_rate": 5.175175484779712e-06, "loss": 4.2982, "step": 25913 }, { "epoch": 0.7915088576664631, "grad_norm": 0.4885551333427429, "learning_rate": 5.1737140955104095e-06, "loss": 4.2215, "step": 25914 }, { "epoch": 0.7915394013439218, "grad_norm": 0.5027944445610046, "learning_rate": 5.172252888791917e-06, "loss": 4.3255, "step": 25915 }, { "epoch": 0.7915699450213806, "grad_norm": 0.502860426902771, "learning_rate": 5.1707918646376835e-06, "loss": 4.2643, "step": 25916 }, { "epoch": 0.7916004886988394, "grad_norm": 0.4963799715042114, "learning_rate": 5.169331023061164e-06, "loss": 4.2562, "step": 25917 }, { "epoch": 0.7916310323762981, "grad_norm": 0.4967341125011444, "learning_rate": 5.167870364075816e-06, "loss": 4.2505, "step": 25918 }, { "epoch": 0.7916615760537569, "grad_norm": 0.49173489212989807, "learning_rate": 5.166409887695075e-06, "loss": 4.2191, "step": 25919 }, { "epoch": 0.7916921197312157, "grad_norm": 0.5029585957527161, "learning_rate": 5.1649495939323945e-06, "loss": 4.32, "step": 25920 }, { "epoch": 0.7917226634086744, "grad_norm": 0.5017942786216736, "learning_rate": 5.163489482801228e-06, "loss": 4.2591, "step": 25921 }, { "epoch": 0.7917532070861332, "grad_norm": 0.510216236114502, "learning_rate": 5.162029554315009e-06, "loss": 4.2771, "step": 25922 }, { "epoch": 0.791783750763592, "grad_norm": 0.5031577944755554, "learning_rate": 5.160569808487181e-06, "loss": 4.2874, "step": 25923 }, { "epoch": 0.7918142944410507, "grad_norm": 0.49407267570495605, "learning_rate": 5.159110245331194e-06, "loss": 4.2234, "step": 25924 }, { "epoch": 0.7918448381185095, "grad_norm": 0.4875231683254242, "learning_rate": 5.157650864860483e-06, "loss": 4.2155, "step": 25925 }, { "epoch": 0.7918753817959683, "grad_norm": 0.5025026798248291, "learning_rate": 5.156191667088473e-06, "loss": 4.3187, "step": 25926 }, { "epoch": 0.791905925473427, "grad_norm": 0.49700868129730225, "learning_rate": 5.1547326520286156e-06, "loss": 4.2029, "step": 25927 }, { "epoch": 0.7919364691508858, "grad_norm": 0.4945688545703888, "learning_rate": 5.153273819694332e-06, "loss": 4.2516, "step": 25928 }, { "epoch": 0.7919670128283446, "grad_norm": 0.4979942739009857, "learning_rate": 5.1518151700990615e-06, "loss": 4.252, "step": 25929 }, { "epoch": 0.7919975565058033, "grad_norm": 0.498019278049469, "learning_rate": 5.15035670325624e-06, "loss": 4.1748, "step": 25930 }, { "epoch": 0.7920281001832621, "grad_norm": 0.5021533370018005, "learning_rate": 5.148898419179282e-06, "loss": 4.2511, "step": 25931 }, { "epoch": 0.7920586438607208, "grad_norm": 0.49069544672966003, "learning_rate": 5.14744031788163e-06, "loss": 4.1938, "step": 25932 }, { "epoch": 0.7920891875381796, "grad_norm": 0.5119098424911499, "learning_rate": 5.145982399376695e-06, "loss": 4.3245, "step": 25933 }, { "epoch": 0.7921197312156384, "grad_norm": 0.506682276725769, "learning_rate": 5.144524663677907e-06, "loss": 4.2945, "step": 25934 }, { "epoch": 0.7921502748930971, "grad_norm": 0.4958575963973999, "learning_rate": 5.1430671107987e-06, "loss": 4.2385, "step": 25935 }, { "epoch": 0.7921808185705559, "grad_norm": 0.4984113872051239, "learning_rate": 5.141609740752473e-06, "loss": 4.3186, "step": 25936 }, { "epoch": 0.7922113622480147, "grad_norm": 0.4986687898635864, "learning_rate": 5.140152553552657e-06, "loss": 4.2474, "step": 25937 }, { "epoch": 0.7922419059254734, "grad_norm": 0.49639248847961426, "learning_rate": 5.138695549212674e-06, "loss": 4.0646, "step": 25938 }, { "epoch": 0.7922724496029322, "grad_norm": 0.48606979846954346, "learning_rate": 5.1372387277459244e-06, "loss": 4.1604, "step": 25939 }, { "epoch": 0.792302993280391, "grad_norm": 0.49108606576919556, "learning_rate": 5.135782089165839e-06, "loss": 4.273, "step": 25940 }, { "epoch": 0.7923335369578497, "grad_norm": 0.49909642338752747, "learning_rate": 5.13432563348582e-06, "loss": 4.1958, "step": 25941 }, { "epoch": 0.7923640806353085, "grad_norm": 0.5007122159004211, "learning_rate": 5.132869360719273e-06, "loss": 4.281, "step": 25942 }, { "epoch": 0.7923946243127673, "grad_norm": 0.4975948631763458, "learning_rate": 5.131413270879612e-06, "loss": 4.308, "step": 25943 }, { "epoch": 0.792425167990226, "grad_norm": 0.5162900686264038, "learning_rate": 5.1299573639802505e-06, "loss": 4.3061, "step": 25944 }, { "epoch": 0.7924557116676848, "grad_norm": 0.49135592579841614, "learning_rate": 5.12850164003458e-06, "loss": 4.2961, "step": 25945 }, { "epoch": 0.7924862553451436, "grad_norm": 0.5027112364768982, "learning_rate": 5.127046099056016e-06, "loss": 4.2513, "step": 25946 }, { "epoch": 0.7925167990226023, "grad_norm": 0.5028770565986633, "learning_rate": 5.125590741057959e-06, "loss": 4.2172, "step": 25947 }, { "epoch": 0.7925473427000611, "grad_norm": 0.49933671951293945, "learning_rate": 5.1241355660538e-06, "loss": 4.268, "step": 25948 }, { "epoch": 0.7925778863775198, "grad_norm": 0.5048502087593079, "learning_rate": 5.122680574056951e-06, "loss": 4.2501, "step": 25949 }, { "epoch": 0.7926084300549786, "grad_norm": 0.5095407962799072, "learning_rate": 5.121225765080798e-06, "loss": 4.2683, "step": 25950 }, { "epoch": 0.7926389737324374, "grad_norm": 0.5051966905593872, "learning_rate": 5.119771139138737e-06, "loss": 4.2153, "step": 25951 }, { "epoch": 0.7926695174098961, "grad_norm": 0.5025104880332947, "learning_rate": 5.118316696244172e-06, "loss": 4.2565, "step": 25952 }, { "epoch": 0.7927000610873549, "grad_norm": 0.5210338234901428, "learning_rate": 5.11686243641048e-06, "loss": 4.2638, "step": 25953 }, { "epoch": 0.7927306047648137, "grad_norm": 0.5026377439498901, "learning_rate": 5.115408359651058e-06, "loss": 4.2661, "step": 25954 }, { "epoch": 0.7927611484422724, "grad_norm": 0.5056468844413757, "learning_rate": 5.113954465979304e-06, "loss": 4.1788, "step": 25955 }, { "epoch": 0.7927916921197312, "grad_norm": 0.49373307824134827, "learning_rate": 5.112500755408594e-06, "loss": 4.2953, "step": 25956 }, { "epoch": 0.79282223579719, "grad_norm": 0.5107533931732178, "learning_rate": 5.111047227952309e-06, "loss": 4.23, "step": 25957 }, { "epoch": 0.7928527794746487, "grad_norm": 0.498685747385025, "learning_rate": 5.109593883623845e-06, "loss": 4.2071, "step": 25958 }, { "epoch": 0.7928833231521075, "grad_norm": 0.49523279070854187, "learning_rate": 5.108140722436569e-06, "loss": 4.09, "step": 25959 }, { "epoch": 0.7929138668295663, "grad_norm": 0.5094695091247559, "learning_rate": 5.106687744403868e-06, "loss": 4.3455, "step": 25960 }, { "epoch": 0.792944410507025, "grad_norm": 0.49986404180526733, "learning_rate": 5.105234949539128e-06, "loss": 4.2653, "step": 25961 }, { "epoch": 0.7929749541844838, "grad_norm": 0.49902620911598206, "learning_rate": 5.103782337855712e-06, "loss": 4.2228, "step": 25962 }, { "epoch": 0.7930054978619426, "grad_norm": 0.5164153575897217, "learning_rate": 5.102329909367004e-06, "loss": 4.3275, "step": 25963 }, { "epoch": 0.7930360415394013, "grad_norm": 0.5065268278121948, "learning_rate": 5.100877664086379e-06, "loss": 4.2753, "step": 25964 }, { "epoch": 0.7930665852168601, "grad_norm": 0.497663289308548, "learning_rate": 5.099425602027199e-06, "loss": 4.2937, "step": 25965 }, { "epoch": 0.7930971288943188, "grad_norm": 0.5058523416519165, "learning_rate": 5.0979737232028456e-06, "loss": 4.044, "step": 25966 }, { "epoch": 0.7931276725717776, "grad_norm": 0.4970744550228119, "learning_rate": 5.096522027626674e-06, "loss": 4.3491, "step": 25967 }, { "epoch": 0.7931582162492364, "grad_norm": 0.49624377489089966, "learning_rate": 5.095070515312056e-06, "loss": 4.2912, "step": 25968 }, { "epoch": 0.7931887599266951, "grad_norm": 0.5019291639328003, "learning_rate": 5.093619186272367e-06, "loss": 4.2052, "step": 25969 }, { "epoch": 0.7932193036041539, "grad_norm": 0.5037716031074524, "learning_rate": 5.0921680405209535e-06, "loss": 4.2832, "step": 25970 }, { "epoch": 0.7932498472816127, "grad_norm": 0.4933033287525177, "learning_rate": 5.090717078071192e-06, "loss": 4.1712, "step": 25971 }, { "epoch": 0.7932803909590714, "grad_norm": 0.5288951992988586, "learning_rate": 5.089266298936426e-06, "loss": 4.2985, "step": 25972 }, { "epoch": 0.7933109346365302, "grad_norm": 0.5113157629966736, "learning_rate": 5.08781570313003e-06, "loss": 4.336, "step": 25973 }, { "epoch": 0.793341478313989, "grad_norm": 0.5017086267471313, "learning_rate": 5.0863652906653454e-06, "loss": 4.2633, "step": 25974 }, { "epoch": 0.7933720219914477, "grad_norm": 0.5088302493095398, "learning_rate": 5.084915061555742e-06, "loss": 4.2622, "step": 25975 }, { "epoch": 0.7934025656689065, "grad_norm": 0.5011610388755798, "learning_rate": 5.083465015814559e-06, "loss": 4.2593, "step": 25976 }, { "epoch": 0.7934331093463654, "grad_norm": 0.4987744688987732, "learning_rate": 5.082015153455152e-06, "loss": 4.159, "step": 25977 }, { "epoch": 0.793463653023824, "grad_norm": 0.49817007780075073, "learning_rate": 5.0805654744908785e-06, "loss": 4.1854, "step": 25978 }, { "epoch": 0.7934941967012829, "grad_norm": 0.5021609663963318, "learning_rate": 5.079115978935076e-06, "loss": 4.2512, "step": 25979 }, { "epoch": 0.7935247403787417, "grad_norm": 0.49999386072158813, "learning_rate": 5.077666666801092e-06, "loss": 4.2223, "step": 25980 }, { "epoch": 0.7935552840562003, "grad_norm": 0.4985935688018799, "learning_rate": 5.076217538102282e-06, "loss": 4.2464, "step": 25981 }, { "epoch": 0.7935858277336592, "grad_norm": 0.49692097306251526, "learning_rate": 5.074768592851975e-06, "loss": 4.3351, "step": 25982 }, { "epoch": 0.7936163714111178, "grad_norm": 0.49739083647727966, "learning_rate": 5.073319831063522e-06, "loss": 4.2195, "step": 25983 }, { "epoch": 0.7936469150885767, "grad_norm": 0.5038279294967651, "learning_rate": 5.071871252750254e-06, "loss": 4.284, "step": 25984 }, { "epoch": 0.7936774587660355, "grad_norm": 0.509091854095459, "learning_rate": 5.070422857925514e-06, "loss": 4.2973, "step": 25985 }, { "epoch": 0.7937080024434942, "grad_norm": 0.5086316466331482, "learning_rate": 5.068974646602645e-06, "loss": 4.206, "step": 25986 }, { "epoch": 0.793738546120953, "grad_norm": 0.49586644768714905, "learning_rate": 5.067526618794966e-06, "loss": 4.1962, "step": 25987 }, { "epoch": 0.7937690897984118, "grad_norm": 0.4914783835411072, "learning_rate": 5.066078774515823e-06, "loss": 4.2121, "step": 25988 }, { "epoch": 0.7937996334758705, "grad_norm": 0.5115635991096497, "learning_rate": 5.0646311137785455e-06, "loss": 4.2372, "step": 25989 }, { "epoch": 0.7938301771533293, "grad_norm": 0.5103872418403625, "learning_rate": 5.063183636596447e-06, "loss": 4.1856, "step": 25990 }, { "epoch": 0.7938607208307881, "grad_norm": 0.508836567401886, "learning_rate": 5.06173634298287e-06, "loss": 4.2184, "step": 25991 }, { "epoch": 0.7938912645082468, "grad_norm": 0.5130457282066345, "learning_rate": 5.0602892329511455e-06, "loss": 4.3031, "step": 25992 }, { "epoch": 0.7939218081857056, "grad_norm": 0.5060549378395081, "learning_rate": 5.058842306514583e-06, "loss": 4.2906, "step": 25993 }, { "epoch": 0.7939523518631644, "grad_norm": 0.4890287220478058, "learning_rate": 5.057395563686512e-06, "loss": 4.1609, "step": 25994 }, { "epoch": 0.7939828955406231, "grad_norm": 0.4984530508518219, "learning_rate": 5.05594900448026e-06, "loss": 4.2224, "step": 25995 }, { "epoch": 0.7940134392180819, "grad_norm": 0.4887661635875702, "learning_rate": 5.054502628909133e-06, "loss": 4.2145, "step": 25996 }, { "epoch": 0.7940439828955406, "grad_norm": 0.49979862570762634, "learning_rate": 5.053056436986461e-06, "loss": 4.2185, "step": 25997 }, { "epoch": 0.7940745265729994, "grad_norm": 0.4906594455242157, "learning_rate": 5.0516104287255474e-06, "loss": 4.3113, "step": 25998 }, { "epoch": 0.7941050702504582, "grad_norm": 0.5050090551376343, "learning_rate": 5.050164604139715e-06, "loss": 4.1658, "step": 25999 }, { "epoch": 0.7941356139279169, "grad_norm": 0.49780383706092834, "learning_rate": 5.04871896324228e-06, "loss": 4.2739, "step": 26000 }, { "epoch": 0.7941661576053757, "grad_norm": 0.49289992451667786, "learning_rate": 5.04727350604654e-06, "loss": 4.204, "step": 26001 }, { "epoch": 0.7941967012828345, "grad_norm": 0.4895276427268982, "learning_rate": 5.045828232565819e-06, "loss": 4.2644, "step": 26002 }, { "epoch": 0.7942272449602932, "grad_norm": 0.48876628279685974, "learning_rate": 5.044383142813408e-06, "loss": 4.2226, "step": 26003 }, { "epoch": 0.794257788637752, "grad_norm": 0.4997219741344452, "learning_rate": 5.0429382368026305e-06, "loss": 4.2093, "step": 26004 }, { "epoch": 0.7942883323152108, "grad_norm": 0.4994533956050873, "learning_rate": 5.041493514546775e-06, "loss": 4.2959, "step": 26005 }, { "epoch": 0.7943188759926695, "grad_norm": 0.4982043206691742, "learning_rate": 5.040048976059156e-06, "loss": 4.0964, "step": 26006 }, { "epoch": 0.7943494196701283, "grad_norm": 0.4958636462688446, "learning_rate": 5.038604621353063e-06, "loss": 4.2498, "step": 26007 }, { "epoch": 0.7943799633475871, "grad_norm": 0.49309855699539185, "learning_rate": 5.0371604504418e-06, "loss": 4.2888, "step": 26008 }, { "epoch": 0.7944105070250458, "grad_norm": 0.5094420909881592, "learning_rate": 5.035716463338672e-06, "loss": 4.2815, "step": 26009 }, { "epoch": 0.7944410507025046, "grad_norm": 0.5021280646324158, "learning_rate": 5.034272660056958e-06, "loss": 4.1951, "step": 26010 }, { "epoch": 0.7944715943799634, "grad_norm": 0.503502368927002, "learning_rate": 5.032829040609963e-06, "loss": 4.2848, "step": 26011 }, { "epoch": 0.7945021380574221, "grad_norm": 0.4926105737686157, "learning_rate": 5.031385605010983e-06, "loss": 4.2526, "step": 26012 }, { "epoch": 0.7945326817348809, "grad_norm": 0.501520574092865, "learning_rate": 5.029942353273296e-06, "loss": 4.3103, "step": 26013 }, { "epoch": 0.7945632254123396, "grad_norm": 0.5050225853919983, "learning_rate": 5.0284992854102046e-06, "loss": 4.2028, "step": 26014 }, { "epoch": 0.7945937690897984, "grad_norm": 0.4971127510070801, "learning_rate": 5.027056401434982e-06, "loss": 4.1712, "step": 26015 }, { "epoch": 0.7946243127672572, "grad_norm": 0.5096738934516907, "learning_rate": 5.025613701360918e-06, "loss": 4.1681, "step": 26016 }, { "epoch": 0.7946548564447159, "grad_norm": 0.5003857016563416, "learning_rate": 5.024171185201307e-06, "loss": 4.2595, "step": 26017 }, { "epoch": 0.7946854001221747, "grad_norm": 0.4903331995010376, "learning_rate": 5.022728852969416e-06, "loss": 4.2236, "step": 26018 }, { "epoch": 0.7947159437996335, "grad_norm": 0.5210511088371277, "learning_rate": 5.0212867046785375e-06, "loss": 4.2257, "step": 26019 }, { "epoch": 0.7947464874770922, "grad_norm": 0.5073223114013672, "learning_rate": 5.0198447403419445e-06, "loss": 4.3608, "step": 26020 }, { "epoch": 0.794777031154551, "grad_norm": 0.5078797340393066, "learning_rate": 5.018402959972909e-06, "loss": 4.231, "step": 26021 }, { "epoch": 0.7948075748320098, "grad_norm": 0.5031489133834839, "learning_rate": 5.016961363584707e-06, "loss": 4.2007, "step": 26022 }, { "epoch": 0.7948381185094685, "grad_norm": 0.5046947598457336, "learning_rate": 5.015519951190625e-06, "loss": 4.2996, "step": 26023 }, { "epoch": 0.7948686621869273, "grad_norm": 0.5114737153053284, "learning_rate": 5.0140787228039195e-06, "loss": 4.3054, "step": 26024 }, { "epoch": 0.7948992058643861, "grad_norm": 0.4964752495288849, "learning_rate": 5.0126376784378675e-06, "loss": 4.2687, "step": 26025 }, { "epoch": 0.7949297495418448, "grad_norm": 0.51624995470047, "learning_rate": 5.011196818105742e-06, "loss": 4.3639, "step": 26026 }, { "epoch": 0.7949602932193036, "grad_norm": 0.5117276906967163, "learning_rate": 5.0097561418207986e-06, "loss": 4.3125, "step": 26027 }, { "epoch": 0.7949908368967624, "grad_norm": 0.4915013611316681, "learning_rate": 5.00831564959631e-06, "loss": 4.2095, "step": 26028 }, { "epoch": 0.7950213805742211, "grad_norm": 0.5026375651359558, "learning_rate": 5.006875341445541e-06, "loss": 4.2615, "step": 26029 }, { "epoch": 0.7950519242516799, "grad_norm": 0.49484455585479736, "learning_rate": 5.005435217381746e-06, "loss": 4.2302, "step": 26030 }, { "epoch": 0.7950824679291386, "grad_norm": 0.5025985240936279, "learning_rate": 5.003995277418197e-06, "loss": 4.2713, "step": 26031 }, { "epoch": 0.7951130116065974, "grad_norm": 0.48543381690979004, "learning_rate": 5.0025555215681364e-06, "loss": 4.2283, "step": 26032 }, { "epoch": 0.7951435552840562, "grad_norm": 0.49907994270324707, "learning_rate": 5.0011159498448286e-06, "loss": 4.209, "step": 26033 }, { "epoch": 0.7951740989615149, "grad_norm": 0.5040673017501831, "learning_rate": 4.999676562261535e-06, "loss": 4.3225, "step": 26034 }, { "epoch": 0.7952046426389737, "grad_norm": 0.4997180104255676, "learning_rate": 4.998237358831501e-06, "loss": 4.2356, "step": 26035 }, { "epoch": 0.7952351863164325, "grad_norm": 0.5004348754882812, "learning_rate": 4.996798339567974e-06, "loss": 4.2508, "step": 26036 }, { "epoch": 0.7952657299938912, "grad_norm": 0.5006157755851746, "learning_rate": 4.9953595044842175e-06, "loss": 4.2142, "step": 26037 }, { "epoch": 0.79529627367135, "grad_norm": 0.4971458315849304, "learning_rate": 4.993920853593464e-06, "loss": 4.2982, "step": 26038 }, { "epoch": 0.7953268173488088, "grad_norm": 0.49886518716812134, "learning_rate": 4.9924823869089675e-06, "loss": 4.2465, "step": 26039 }, { "epoch": 0.7953573610262675, "grad_norm": 0.5113346576690674, "learning_rate": 4.991044104443979e-06, "loss": 4.2911, "step": 26040 }, { "epoch": 0.7953879047037263, "grad_norm": 0.5073890686035156, "learning_rate": 4.989606006211728e-06, "loss": 4.2148, "step": 26041 }, { "epoch": 0.7954184483811851, "grad_norm": 0.5078361630439758, "learning_rate": 4.988168092225462e-06, "loss": 4.1223, "step": 26042 }, { "epoch": 0.7954489920586438, "grad_norm": 0.4941658079624176, "learning_rate": 4.986730362498429e-06, "loss": 4.1906, "step": 26043 }, { "epoch": 0.7954795357361026, "grad_norm": 0.49301156401634216, "learning_rate": 4.985292817043852e-06, "loss": 4.2814, "step": 26044 }, { "epoch": 0.7955100794135614, "grad_norm": 0.5049213171005249, "learning_rate": 4.9838554558749754e-06, "loss": 4.1431, "step": 26045 }, { "epoch": 0.7955406230910201, "grad_norm": 0.5095836520195007, "learning_rate": 4.982418279005038e-06, "loss": 4.2517, "step": 26046 }, { "epoch": 0.7955711667684789, "grad_norm": 0.49785444140434265, "learning_rate": 4.980981286447264e-06, "loss": 4.183, "step": 26047 }, { "epoch": 0.7956017104459376, "grad_norm": 0.5020216703414917, "learning_rate": 4.979544478214892e-06, "loss": 4.1835, "step": 26048 }, { "epoch": 0.7956322541233964, "grad_norm": 0.49550652503967285, "learning_rate": 4.978107854321143e-06, "loss": 4.2527, "step": 26049 }, { "epoch": 0.7956627978008552, "grad_norm": 0.495157390832901, "learning_rate": 4.976671414779255e-06, "loss": 4.2408, "step": 26050 }, { "epoch": 0.7956933414783139, "grad_norm": 0.5014527440071106, "learning_rate": 4.975235159602448e-06, "loss": 4.2219, "step": 26051 }, { "epoch": 0.7957238851557727, "grad_norm": 0.5092971324920654, "learning_rate": 4.973799088803937e-06, "loss": 4.2292, "step": 26052 }, { "epoch": 0.7957544288332316, "grad_norm": 0.5018011331558228, "learning_rate": 4.97236320239696e-06, "loss": 4.2344, "step": 26053 }, { "epoch": 0.7957849725106902, "grad_norm": 0.4992453157901764, "learning_rate": 4.970927500394734e-06, "loss": 4.2821, "step": 26054 }, { "epoch": 0.795815516188149, "grad_norm": 0.5066924691200256, "learning_rate": 4.969491982810473e-06, "loss": 4.1756, "step": 26055 }, { "epoch": 0.7958460598656079, "grad_norm": 0.5133704543113708, "learning_rate": 4.968056649657396e-06, "loss": 4.2441, "step": 26056 }, { "epoch": 0.7958766035430666, "grad_norm": 0.5119593739509583, "learning_rate": 4.966621500948729e-06, "loss": 4.225, "step": 26057 }, { "epoch": 0.7959071472205254, "grad_norm": 0.4991025924682617, "learning_rate": 4.9651865366976695e-06, "loss": 4.3206, "step": 26058 }, { "epoch": 0.7959376908979842, "grad_norm": 0.49603891372680664, "learning_rate": 4.96375175691744e-06, "loss": 4.264, "step": 26059 }, { "epoch": 0.7959682345754429, "grad_norm": 0.500791072845459, "learning_rate": 4.962317161621255e-06, "loss": 4.3035, "step": 26060 }, { "epoch": 0.7959987782529017, "grad_norm": 0.501176655292511, "learning_rate": 4.960882750822313e-06, "loss": 4.2901, "step": 26061 }, { "epoch": 0.7960293219303605, "grad_norm": 0.49152544140815735, "learning_rate": 4.959448524533827e-06, "loss": 4.2576, "step": 26062 }, { "epoch": 0.7960598656078192, "grad_norm": 0.5001646876335144, "learning_rate": 4.958014482769008e-06, "loss": 4.3305, "step": 26063 }, { "epoch": 0.796090409285278, "grad_norm": 0.4910973906517029, "learning_rate": 4.956580625541046e-06, "loss": 4.2234, "step": 26064 }, { "epoch": 0.7961209529627367, "grad_norm": 0.49819305539131165, "learning_rate": 4.95514695286316e-06, "loss": 4.2956, "step": 26065 }, { "epoch": 0.7961514966401955, "grad_norm": 0.50341796875, "learning_rate": 4.953713464748541e-06, "loss": 4.3687, "step": 26066 }, { "epoch": 0.7961820403176543, "grad_norm": 0.501465916633606, "learning_rate": 4.952280161210385e-06, "loss": 4.144, "step": 26067 }, { "epoch": 0.796212583995113, "grad_norm": 0.5001277327537537, "learning_rate": 4.950847042261897e-06, "loss": 4.2866, "step": 26068 }, { "epoch": 0.7962431276725718, "grad_norm": 0.5065600872039795, "learning_rate": 4.949414107916262e-06, "loss": 4.2784, "step": 26069 }, { "epoch": 0.7962736713500306, "grad_norm": 0.4957652986049652, "learning_rate": 4.947981358186682e-06, "loss": 4.2128, "step": 26070 }, { "epoch": 0.7963042150274893, "grad_norm": 0.5033467411994934, "learning_rate": 4.946548793086353e-06, "loss": 4.3287, "step": 26071 }, { "epoch": 0.7963347587049481, "grad_norm": 0.5001158118247986, "learning_rate": 4.945116412628454e-06, "loss": 4.2362, "step": 26072 }, { "epoch": 0.7963653023824069, "grad_norm": 0.4941392242908478, "learning_rate": 4.943684216826177e-06, "loss": 4.3186, "step": 26073 }, { "epoch": 0.7963958460598656, "grad_norm": 0.5043723583221436, "learning_rate": 4.942252205692718e-06, "loss": 4.2625, "step": 26074 }, { "epoch": 0.7964263897373244, "grad_norm": 0.48935016989707947, "learning_rate": 4.940820379241251e-06, "loss": 4.1543, "step": 26075 }, { "epoch": 0.7964569334147832, "grad_norm": 0.49437811970710754, "learning_rate": 4.9393887374849626e-06, "loss": 4.2311, "step": 26076 }, { "epoch": 0.7964874770922419, "grad_norm": 0.49141955375671387, "learning_rate": 4.9379572804370445e-06, "loss": 4.1759, "step": 26077 }, { "epoch": 0.7965180207697007, "grad_norm": 0.4997637867927551, "learning_rate": 4.936526008110662e-06, "loss": 4.1789, "step": 26078 }, { "epoch": 0.7965485644471595, "grad_norm": 0.5047147870063782, "learning_rate": 4.935094920518998e-06, "loss": 4.2968, "step": 26079 }, { "epoch": 0.7965791081246182, "grad_norm": 0.4964887499809265, "learning_rate": 4.93366401767524e-06, "loss": 4.3146, "step": 26080 }, { "epoch": 0.796609651802077, "grad_norm": 0.49694588780403137, "learning_rate": 4.9322332995925535e-06, "loss": 4.2484, "step": 26081 }, { "epoch": 0.7966401954795357, "grad_norm": 0.488088995218277, "learning_rate": 4.930802766284106e-06, "loss": 4.2444, "step": 26082 }, { "epoch": 0.7966707391569945, "grad_norm": 0.5093958973884583, "learning_rate": 4.929372417763084e-06, "loss": 4.2976, "step": 26083 }, { "epoch": 0.7967012828344533, "grad_norm": 0.5000442266464233, "learning_rate": 4.927942254042641e-06, "loss": 4.3126, "step": 26084 }, { "epoch": 0.796731826511912, "grad_norm": 0.5036869049072266, "learning_rate": 4.926512275135964e-06, "loss": 4.2086, "step": 26085 }, { "epoch": 0.7967623701893708, "grad_norm": 0.5050557255744934, "learning_rate": 4.925082481056198e-06, "loss": 4.1924, "step": 26086 }, { "epoch": 0.7967929138668296, "grad_norm": 0.5002496242523193, "learning_rate": 4.923652871816523e-06, "loss": 4.2242, "step": 26087 }, { "epoch": 0.7968234575442883, "grad_norm": 0.5024288892745972, "learning_rate": 4.922223447430102e-06, "loss": 4.2282, "step": 26088 }, { "epoch": 0.7968540012217471, "grad_norm": 0.5103318691253662, "learning_rate": 4.920794207910087e-06, "loss": 4.3129, "step": 26089 }, { "epoch": 0.7968845448992059, "grad_norm": 0.5000793933868408, "learning_rate": 4.919365153269645e-06, "loss": 4.2848, "step": 26090 }, { "epoch": 0.7969150885766646, "grad_norm": 0.4882287085056305, "learning_rate": 4.917936283521937e-06, "loss": 4.1507, "step": 26091 }, { "epoch": 0.7969456322541234, "grad_norm": 0.49941205978393555, "learning_rate": 4.916507598680109e-06, "loss": 4.2473, "step": 26092 }, { "epoch": 0.7969761759315822, "grad_norm": 0.4992043375968933, "learning_rate": 4.915079098757319e-06, "loss": 4.1147, "step": 26093 }, { "epoch": 0.7970067196090409, "grad_norm": 0.5015504956245422, "learning_rate": 4.9136507837667325e-06, "loss": 4.2679, "step": 26094 }, { "epoch": 0.7970372632864997, "grad_norm": 0.49865761399269104, "learning_rate": 4.912222653721482e-06, "loss": 4.1717, "step": 26095 }, { "epoch": 0.7970678069639585, "grad_norm": 0.5076724290847778, "learning_rate": 4.910794708634733e-06, "loss": 4.2629, "step": 26096 }, { "epoch": 0.7970983506414172, "grad_norm": 0.5015053153038025, "learning_rate": 4.90936694851962e-06, "loss": 4.2401, "step": 26097 }, { "epoch": 0.797128894318876, "grad_norm": 0.5098310708999634, "learning_rate": 4.9079393733893e-06, "loss": 4.3377, "step": 26098 }, { "epoch": 0.7971594379963347, "grad_norm": 0.49347731471061707, "learning_rate": 4.906511983256915e-06, "loss": 4.2186, "step": 26099 }, { "epoch": 0.7971899816737935, "grad_norm": 0.5017090439796448, "learning_rate": 4.905084778135596e-06, "loss": 4.2192, "step": 26100 }, { "epoch": 0.7972205253512523, "grad_norm": 0.5166072249412537, "learning_rate": 4.903657758038494e-06, "loss": 4.2449, "step": 26101 }, { "epoch": 0.797251069028711, "grad_norm": 0.5016539692878723, "learning_rate": 4.902230922978756e-06, "loss": 4.177, "step": 26102 }, { "epoch": 0.7972816127061698, "grad_norm": 0.5136421918869019, "learning_rate": 4.900804272969503e-06, "loss": 4.1942, "step": 26103 }, { "epoch": 0.7973121563836286, "grad_norm": 0.510278582572937, "learning_rate": 4.899377808023878e-06, "loss": 4.3789, "step": 26104 }, { "epoch": 0.7973427000610873, "grad_norm": 0.4984161853790283, "learning_rate": 4.897951528155023e-06, "loss": 4.1725, "step": 26105 }, { "epoch": 0.7973732437385461, "grad_norm": 0.5065441131591797, "learning_rate": 4.896525433376059e-06, "loss": 4.2455, "step": 26106 }, { "epoch": 0.7974037874160049, "grad_norm": 0.500840425491333, "learning_rate": 4.895099523700123e-06, "loss": 4.2077, "step": 26107 }, { "epoch": 0.7974343310934636, "grad_norm": 0.5002557635307312, "learning_rate": 4.893673799140344e-06, "loss": 4.2441, "step": 26108 }, { "epoch": 0.7974648747709224, "grad_norm": 0.5006167888641357, "learning_rate": 4.892248259709844e-06, "loss": 4.2829, "step": 26109 }, { "epoch": 0.7974954184483812, "grad_norm": 0.4927249252796173, "learning_rate": 4.890822905421755e-06, "loss": 4.2171, "step": 26110 }, { "epoch": 0.7975259621258399, "grad_norm": 0.5001134872436523, "learning_rate": 4.889397736289203e-06, "loss": 4.2662, "step": 26111 }, { "epoch": 0.7975565058032987, "grad_norm": 0.501774251461029, "learning_rate": 4.887972752325304e-06, "loss": 4.2764, "step": 26112 }, { "epoch": 0.7975870494807575, "grad_norm": 0.5022282600402832, "learning_rate": 4.886547953543177e-06, "loss": 4.2021, "step": 26113 }, { "epoch": 0.7976175931582162, "grad_norm": 0.5027840733528137, "learning_rate": 4.88512333995595e-06, "loss": 4.2544, "step": 26114 }, { "epoch": 0.797648136835675, "grad_norm": 0.4989405572414398, "learning_rate": 4.8836989115767256e-06, "loss": 4.1961, "step": 26115 }, { "epoch": 0.7976786805131337, "grad_norm": 0.5079154968261719, "learning_rate": 4.882274668418637e-06, "loss": 4.294, "step": 26116 }, { "epoch": 0.7977092241905925, "grad_norm": 0.5075361132621765, "learning_rate": 4.880850610494784e-06, "loss": 4.2603, "step": 26117 }, { "epoch": 0.7977397678680513, "grad_norm": 0.49416157603263855, "learning_rate": 4.87942673781828e-06, "loss": 4.2951, "step": 26118 }, { "epoch": 0.79777031154551, "grad_norm": 0.5155966281890869, "learning_rate": 4.878003050402247e-06, "loss": 4.195, "step": 26119 }, { "epoch": 0.7978008552229688, "grad_norm": 0.5246282815933228, "learning_rate": 4.87657954825978e-06, "loss": 4.2889, "step": 26120 }, { "epoch": 0.7978313989004276, "grad_norm": 0.49477481842041016, "learning_rate": 4.87515623140399e-06, "loss": 4.2348, "step": 26121 }, { "epoch": 0.7978619425778863, "grad_norm": 0.4937001168727875, "learning_rate": 4.873733099847994e-06, "loss": 4.3042, "step": 26122 }, { "epoch": 0.7978924862553451, "grad_norm": 0.4958846867084503, "learning_rate": 4.872310153604875e-06, "loss": 4.264, "step": 26123 }, { "epoch": 0.797923029932804, "grad_norm": 0.5017611384391785, "learning_rate": 4.870887392687745e-06, "loss": 4.2537, "step": 26124 }, { "epoch": 0.7979535736102626, "grad_norm": 0.49817267060279846, "learning_rate": 4.869464817109711e-06, "loss": 4.2756, "step": 26125 }, { "epoch": 0.7979841172877215, "grad_norm": 0.501535177230835, "learning_rate": 4.86804242688386e-06, "loss": 4.1823, "step": 26126 }, { "epoch": 0.7980146609651803, "grad_norm": 0.509967029094696, "learning_rate": 4.866620222023297e-06, "loss": 4.271, "step": 26127 }, { "epoch": 0.798045204642639, "grad_norm": 0.5088651180267334, "learning_rate": 4.865198202541107e-06, "loss": 4.2812, "step": 26128 }, { "epoch": 0.7980757483200978, "grad_norm": 0.5022264122962952, "learning_rate": 4.8637763684503985e-06, "loss": 4.2896, "step": 26129 }, { "epoch": 0.7981062919975566, "grad_norm": 0.5107333064079285, "learning_rate": 4.862354719764245e-06, "loss": 4.3162, "step": 26130 }, { "epoch": 0.7981368356750153, "grad_norm": 0.49901413917541504, "learning_rate": 4.860933256495753e-06, "loss": 4.1824, "step": 26131 }, { "epoch": 0.7981673793524741, "grad_norm": 0.5066625475883484, "learning_rate": 4.859511978657996e-06, "loss": 4.2312, "step": 26132 }, { "epoch": 0.7981979230299328, "grad_norm": 0.5018373131752014, "learning_rate": 4.858090886264075e-06, "loss": 4.3589, "step": 26133 }, { "epoch": 0.7982284667073916, "grad_norm": 0.5113309621810913, "learning_rate": 4.856669979327061e-06, "loss": 4.3089, "step": 26134 }, { "epoch": 0.7982590103848504, "grad_norm": 0.4949142634868622, "learning_rate": 4.8552492578600425e-06, "loss": 4.1597, "step": 26135 }, { "epoch": 0.7982895540623091, "grad_norm": 0.5002157688140869, "learning_rate": 4.853828721876105e-06, "loss": 4.2467, "step": 26136 }, { "epoch": 0.7983200977397679, "grad_norm": 0.5117446184158325, "learning_rate": 4.8524083713883226e-06, "loss": 4.2457, "step": 26137 }, { "epoch": 0.7983506414172267, "grad_norm": 0.5055320858955383, "learning_rate": 4.850988206409773e-06, "loss": 4.261, "step": 26138 }, { "epoch": 0.7983811850946854, "grad_norm": 0.49897775053977966, "learning_rate": 4.849568226953541e-06, "loss": 4.264, "step": 26139 }, { "epoch": 0.7984117287721442, "grad_norm": 0.5093231797218323, "learning_rate": 4.84814843303269e-06, "loss": 4.3302, "step": 26140 }, { "epoch": 0.798442272449603, "grad_norm": 0.5066191554069519, "learning_rate": 4.846728824660294e-06, "loss": 4.2872, "step": 26141 }, { "epoch": 0.7984728161270617, "grad_norm": 0.5027077794075012, "learning_rate": 4.845309401849437e-06, "loss": 4.2465, "step": 26142 }, { "epoch": 0.7985033598045205, "grad_norm": 0.5056401491165161, "learning_rate": 4.843890164613171e-06, "loss": 4.192, "step": 26143 }, { "epoch": 0.7985339034819793, "grad_norm": 0.5111910104751587, "learning_rate": 4.8424711129645774e-06, "loss": 4.1696, "step": 26144 }, { "epoch": 0.798564447159438, "grad_norm": 0.49544769525527954, "learning_rate": 4.8410522469167166e-06, "loss": 4.2748, "step": 26145 }, { "epoch": 0.7985949908368968, "grad_norm": 0.5071126818656921, "learning_rate": 4.839633566482649e-06, "loss": 4.3304, "step": 26146 }, { "epoch": 0.7986255345143555, "grad_norm": 0.4991220235824585, "learning_rate": 4.838215071675442e-06, "loss": 4.2594, "step": 26147 }, { "epoch": 0.7986560781918143, "grad_norm": 0.49942949414253235, "learning_rate": 4.836796762508153e-06, "loss": 4.2739, "step": 26148 }, { "epoch": 0.7986866218692731, "grad_norm": 0.49340689182281494, "learning_rate": 4.83537863899384e-06, "loss": 4.0899, "step": 26149 }, { "epoch": 0.7987171655467318, "grad_norm": 0.5066094994544983, "learning_rate": 4.8339607011455705e-06, "loss": 4.2847, "step": 26150 }, { "epoch": 0.7987477092241906, "grad_norm": 0.5095321536064148, "learning_rate": 4.832542948976387e-06, "loss": 4.2261, "step": 26151 }, { "epoch": 0.7987782529016494, "grad_norm": 0.5008634924888611, "learning_rate": 4.8311253824993515e-06, "loss": 4.286, "step": 26152 }, { "epoch": 0.7988087965791081, "grad_norm": 0.4958342909812927, "learning_rate": 4.829708001727518e-06, "loss": 4.1734, "step": 26153 }, { "epoch": 0.7988393402565669, "grad_norm": 0.49489885568618774, "learning_rate": 4.82829080667393e-06, "loss": 4.3126, "step": 26154 }, { "epoch": 0.7988698839340257, "grad_norm": 0.5071201324462891, "learning_rate": 4.826873797351639e-06, "loss": 4.2799, "step": 26155 }, { "epoch": 0.7989004276114844, "grad_norm": 0.5080379247665405, "learning_rate": 4.825456973773698e-06, "loss": 4.2352, "step": 26156 }, { "epoch": 0.7989309712889432, "grad_norm": 0.5077608227729797, "learning_rate": 4.824040335953139e-06, "loss": 4.265, "step": 26157 }, { "epoch": 0.798961514966402, "grad_norm": 0.5014238953590393, "learning_rate": 4.822623883903024e-06, "loss": 4.1986, "step": 26158 }, { "epoch": 0.7989920586438607, "grad_norm": 0.5088315010070801, "learning_rate": 4.821207617636378e-06, "loss": 4.2419, "step": 26159 }, { "epoch": 0.7990226023213195, "grad_norm": 0.5096257925033569, "learning_rate": 4.819791537166254e-06, "loss": 4.2301, "step": 26160 }, { "epoch": 0.7990531459987783, "grad_norm": 0.5019564032554626, "learning_rate": 4.818375642505679e-06, "loss": 4.2749, "step": 26161 }, { "epoch": 0.799083689676237, "grad_norm": 0.4945474863052368, "learning_rate": 4.8169599336677026e-06, "loss": 4.2259, "step": 26162 }, { "epoch": 0.7991142333536958, "grad_norm": 0.5119823813438416, "learning_rate": 4.815544410665346e-06, "loss": 4.2937, "step": 26163 }, { "epoch": 0.7991447770311545, "grad_norm": 0.504905641078949, "learning_rate": 4.814129073511659e-06, "loss": 4.2956, "step": 26164 }, { "epoch": 0.7991753207086133, "grad_norm": 0.5034576654434204, "learning_rate": 4.812713922219653e-06, "loss": 4.3154, "step": 26165 }, { "epoch": 0.7992058643860721, "grad_norm": 0.5048794746398926, "learning_rate": 4.811298956802371e-06, "loss": 4.3374, "step": 26166 }, { "epoch": 0.7992364080635308, "grad_norm": 0.5070033669471741, "learning_rate": 4.809884177272847e-06, "loss": 4.2492, "step": 26167 }, { "epoch": 0.7992669517409896, "grad_norm": 0.5121033787727356, "learning_rate": 4.808469583644093e-06, "loss": 4.3106, "step": 26168 }, { "epoch": 0.7992974954184484, "grad_norm": 0.5108093023300171, "learning_rate": 4.8070551759291424e-06, "loss": 4.2435, "step": 26169 }, { "epoch": 0.7993280390959071, "grad_norm": 0.5124495625495911, "learning_rate": 4.805640954141022e-06, "loss": 4.2245, "step": 26170 }, { "epoch": 0.7993585827733659, "grad_norm": 0.5118391513824463, "learning_rate": 4.804226918292742e-06, "loss": 4.2718, "step": 26171 }, { "epoch": 0.7993891264508247, "grad_norm": 0.4996582567691803, "learning_rate": 4.8028130683973274e-06, "loss": 4.1773, "step": 26172 }, { "epoch": 0.7994196701282834, "grad_norm": 0.4967682957649231, "learning_rate": 4.801399404467805e-06, "loss": 4.24, "step": 26173 }, { "epoch": 0.7994502138057422, "grad_norm": 0.5098633766174316, "learning_rate": 4.799985926517178e-06, "loss": 4.2888, "step": 26174 }, { "epoch": 0.799480757483201, "grad_norm": 0.49641162157058716, "learning_rate": 4.7985726345584706e-06, "loss": 4.2281, "step": 26175 }, { "epoch": 0.7995113011606597, "grad_norm": 0.5038971900939941, "learning_rate": 4.797159528604692e-06, "loss": 4.2323, "step": 26176 }, { "epoch": 0.7995418448381185, "grad_norm": 0.5042867660522461, "learning_rate": 4.795746608668847e-06, "loss": 4.2273, "step": 26177 }, { "epoch": 0.7995723885155773, "grad_norm": 0.5081518888473511, "learning_rate": 4.794333874763951e-06, "loss": 4.2035, "step": 26178 }, { "epoch": 0.799602932193036, "grad_norm": 0.4916114807128906, "learning_rate": 4.792921326903018e-06, "loss": 4.2064, "step": 26179 }, { "epoch": 0.7996334758704948, "grad_norm": 0.5043055415153503, "learning_rate": 4.791508965099043e-06, "loss": 4.2713, "step": 26180 }, { "epoch": 0.7996640195479535, "grad_norm": 0.5164105296134949, "learning_rate": 4.790096789365037e-06, "loss": 4.2437, "step": 26181 }, { "epoch": 0.7996945632254123, "grad_norm": 0.507132887840271, "learning_rate": 4.788684799714e-06, "loss": 4.1627, "step": 26182 }, { "epoch": 0.7997251069028711, "grad_norm": 0.5018838047981262, "learning_rate": 4.7872729961589286e-06, "loss": 4.3301, "step": 26183 }, { "epoch": 0.7997556505803298, "grad_norm": 0.5102026462554932, "learning_rate": 4.785861378712836e-06, "loss": 4.1617, "step": 26184 }, { "epoch": 0.7997861942577886, "grad_norm": 0.49639859795570374, "learning_rate": 4.7844499473887054e-06, "loss": 4.3015, "step": 26185 }, { "epoch": 0.7998167379352474, "grad_norm": 0.5111733675003052, "learning_rate": 4.783038702199535e-06, "loss": 4.2402, "step": 26186 }, { "epoch": 0.7998472816127061, "grad_norm": 0.5014985799789429, "learning_rate": 4.781627643158332e-06, "loss": 4.2516, "step": 26187 }, { "epoch": 0.7998778252901649, "grad_norm": 0.5050371289253235, "learning_rate": 4.780216770278067e-06, "loss": 4.3311, "step": 26188 }, { "epoch": 0.7999083689676237, "grad_norm": 0.5120833516120911, "learning_rate": 4.7788060835717464e-06, "loss": 4.3148, "step": 26189 }, { "epoch": 0.7999389126450824, "grad_norm": 0.49460461735725403, "learning_rate": 4.77739558305236e-06, "loss": 4.2023, "step": 26190 }, { "epoch": 0.7999694563225412, "grad_norm": 0.49839600920677185, "learning_rate": 4.775985268732891e-06, "loss": 4.1416, "step": 26191 }, { "epoch": 0.8, "grad_norm": 0.50612473487854, "learning_rate": 4.7745751406263165e-06, "loss": 4.2892, "step": 26192 }, { "epoch": 0.8000305436774587, "grad_norm": 0.5035895705223083, "learning_rate": 4.773165198745633e-06, "loss": 4.302, "step": 26193 }, { "epoch": 0.8000610873549175, "grad_norm": 0.5039677619934082, "learning_rate": 4.7717554431038116e-06, "loss": 4.1891, "step": 26194 }, { "epoch": 0.8000916310323763, "grad_norm": 0.5010828971862793, "learning_rate": 4.7703458737138384e-06, "loss": 4.2528, "step": 26195 }, { "epoch": 0.800122174709835, "grad_norm": 0.5097514390945435, "learning_rate": 4.768936490588699e-06, "loss": 4.2567, "step": 26196 }, { "epoch": 0.8001527183872938, "grad_norm": 0.4975373446941376, "learning_rate": 4.767527293741356e-06, "loss": 4.1229, "step": 26197 }, { "epoch": 0.8001832620647525, "grad_norm": 0.4973946213722229, "learning_rate": 4.7661182831847975e-06, "loss": 4.1549, "step": 26198 }, { "epoch": 0.8002138057422113, "grad_norm": 0.5002349615097046, "learning_rate": 4.764709458931985e-06, "loss": 4.1884, "step": 26199 }, { "epoch": 0.8002443494196702, "grad_norm": 0.5080177187919617, "learning_rate": 4.7633008209958945e-06, "loss": 4.2165, "step": 26200 }, { "epoch": 0.8002748930971288, "grad_norm": 0.5000213384628296, "learning_rate": 4.761892369389509e-06, "loss": 4.3293, "step": 26201 }, { "epoch": 0.8003054367745877, "grad_norm": 0.49726617336273193, "learning_rate": 4.7604841041257754e-06, "loss": 4.3084, "step": 26202 }, { "epoch": 0.8003359804520465, "grad_norm": 0.5022318363189697, "learning_rate": 4.7590760252176735e-06, "loss": 4.2747, "step": 26203 }, { "epoch": 0.8003665241295052, "grad_norm": 0.5059753656387329, "learning_rate": 4.7576681326781695e-06, "loss": 4.1271, "step": 26204 }, { "epoch": 0.800397067806964, "grad_norm": 0.4991397261619568, "learning_rate": 4.756260426520218e-06, "loss": 4.2474, "step": 26205 }, { "epoch": 0.8004276114844228, "grad_norm": 0.5016005635261536, "learning_rate": 4.75485290675679e-06, "loss": 4.1966, "step": 26206 }, { "epoch": 0.8004581551618815, "grad_norm": 0.5110897421836853, "learning_rate": 4.753445573400836e-06, "loss": 4.3314, "step": 26207 }, { "epoch": 0.8004886988393403, "grad_norm": 0.4995787739753723, "learning_rate": 4.752038426465322e-06, "loss": 4.254, "step": 26208 }, { "epoch": 0.8005192425167991, "grad_norm": 0.5241604447364807, "learning_rate": 4.750631465963196e-06, "loss": 4.2316, "step": 26209 }, { "epoch": 0.8005497861942578, "grad_norm": 0.50064617395401, "learning_rate": 4.749224691907425e-06, "loss": 4.2255, "step": 26210 }, { "epoch": 0.8005803298717166, "grad_norm": 0.5156192183494568, "learning_rate": 4.747818104310944e-06, "loss": 4.2292, "step": 26211 }, { "epoch": 0.8006108735491754, "grad_norm": 0.5026746988296509, "learning_rate": 4.746411703186718e-06, "loss": 4.2594, "step": 26212 }, { "epoch": 0.8006414172266341, "grad_norm": 0.5023619532585144, "learning_rate": 4.745005488547699e-06, "loss": 4.3169, "step": 26213 }, { "epoch": 0.8006719609040929, "grad_norm": 0.49903419613838196, "learning_rate": 4.74359946040682e-06, "loss": 4.255, "step": 26214 }, { "epoch": 0.8007025045815516, "grad_norm": 0.5004108548164368, "learning_rate": 4.742193618777044e-06, "loss": 4.2924, "step": 26215 }, { "epoch": 0.8007330482590104, "grad_norm": 0.5009230971336365, "learning_rate": 4.740787963671297e-06, "loss": 4.3362, "step": 26216 }, { "epoch": 0.8007635919364692, "grad_norm": 0.5031852722167969, "learning_rate": 4.739382495102535e-06, "loss": 4.2394, "step": 26217 }, { "epoch": 0.8007941356139279, "grad_norm": 0.5029003024101257, "learning_rate": 4.7379772130837e-06, "loss": 4.1256, "step": 26218 }, { "epoch": 0.8008246792913867, "grad_norm": 0.5072387456893921, "learning_rate": 4.736572117627722e-06, "loss": 4.0795, "step": 26219 }, { "epoch": 0.8008552229688455, "grad_norm": 0.49985456466674805, "learning_rate": 4.73516720874754e-06, "loss": 4.1876, "step": 26220 }, { "epoch": 0.8008857666463042, "grad_norm": 0.5048103928565979, "learning_rate": 4.7337624864561035e-06, "loss": 4.2358, "step": 26221 }, { "epoch": 0.800916310323763, "grad_norm": 0.5043458342552185, "learning_rate": 4.732357950766331e-06, "loss": 4.3303, "step": 26222 }, { "epoch": 0.8009468540012218, "grad_norm": 0.49974891543388367, "learning_rate": 4.730953601691154e-06, "loss": 4.2303, "step": 26223 }, { "epoch": 0.8009773976786805, "grad_norm": 0.499972939491272, "learning_rate": 4.7295494392435165e-06, "loss": 4.2224, "step": 26224 }, { "epoch": 0.8010079413561393, "grad_norm": 0.5061936974525452, "learning_rate": 4.7281454634363346e-06, "loss": 4.3182, "step": 26225 }, { "epoch": 0.8010384850335981, "grad_norm": 0.5075553059577942, "learning_rate": 4.7267416742825365e-06, "loss": 4.281, "step": 26226 }, { "epoch": 0.8010690287110568, "grad_norm": 0.49707168340682983, "learning_rate": 4.725338071795057e-06, "loss": 4.2143, "step": 26227 }, { "epoch": 0.8010995723885156, "grad_norm": 0.5059929490089417, "learning_rate": 4.723934655986811e-06, "loss": 4.3541, "step": 26228 }, { "epoch": 0.8011301160659744, "grad_norm": 0.5163086652755737, "learning_rate": 4.7225314268707215e-06, "loss": 4.3092, "step": 26229 }, { "epoch": 0.8011606597434331, "grad_norm": 0.5046088695526123, "learning_rate": 4.7211283844597196e-06, "loss": 4.2442, "step": 26230 }, { "epoch": 0.8011912034208919, "grad_norm": 0.5002896785736084, "learning_rate": 4.719725528766706e-06, "loss": 4.239, "step": 26231 }, { "epoch": 0.8012217470983506, "grad_norm": 0.5054364800453186, "learning_rate": 4.718322859804614e-06, "loss": 4.2115, "step": 26232 }, { "epoch": 0.8012522907758094, "grad_norm": 0.5123698115348816, "learning_rate": 4.716920377586345e-06, "loss": 4.2177, "step": 26233 }, { "epoch": 0.8012828344532682, "grad_norm": 0.4975607991218567, "learning_rate": 4.715518082124817e-06, "loss": 4.2018, "step": 26234 }, { "epoch": 0.8013133781307269, "grad_norm": 0.5009346604347229, "learning_rate": 4.714115973432953e-06, "loss": 4.2741, "step": 26235 }, { "epoch": 0.8013439218081857, "grad_norm": 0.501799464225769, "learning_rate": 4.712714051523645e-06, "loss": 4.2508, "step": 26236 }, { "epoch": 0.8013744654856445, "grad_norm": 0.5162593126296997, "learning_rate": 4.711312316409816e-06, "loss": 4.276, "step": 26237 }, { "epoch": 0.8014050091631032, "grad_norm": 0.516482412815094, "learning_rate": 4.709910768104358e-06, "loss": 4.3617, "step": 26238 }, { "epoch": 0.801435552840562, "grad_norm": 0.5037822127342224, "learning_rate": 4.70850940662019e-06, "loss": 4.3277, "step": 26239 }, { "epoch": 0.8014660965180208, "grad_norm": 0.501498818397522, "learning_rate": 4.707108231970206e-06, "loss": 4.133, "step": 26240 }, { "epoch": 0.8014966401954795, "grad_norm": 0.5003426671028137, "learning_rate": 4.705707244167312e-06, "loss": 4.3337, "step": 26241 }, { "epoch": 0.8015271838729383, "grad_norm": 0.5053972601890564, "learning_rate": 4.704306443224402e-06, "loss": 4.2338, "step": 26242 }, { "epoch": 0.8015577275503971, "grad_norm": 0.4941844940185547, "learning_rate": 4.702905829154378e-06, "loss": 4.2759, "step": 26243 }, { "epoch": 0.8015882712278558, "grad_norm": 0.5019181370735168, "learning_rate": 4.701505401970141e-06, "loss": 4.2344, "step": 26244 }, { "epoch": 0.8016188149053146, "grad_norm": 0.506908655166626, "learning_rate": 4.700105161684573e-06, "loss": 4.2215, "step": 26245 }, { "epoch": 0.8016493585827734, "grad_norm": 0.5044887065887451, "learning_rate": 4.698705108310575e-06, "loss": 4.2101, "step": 26246 }, { "epoch": 0.8016799022602321, "grad_norm": 0.5213648080825806, "learning_rate": 4.697305241861044e-06, "loss": 4.2191, "step": 26247 }, { "epoch": 0.8017104459376909, "grad_norm": 0.4966999590396881, "learning_rate": 4.695905562348854e-06, "loss": 4.2298, "step": 26248 }, { "epoch": 0.8017409896151496, "grad_norm": 0.5082286596298218, "learning_rate": 4.6945060697869084e-06, "loss": 4.2353, "step": 26249 }, { "epoch": 0.8017715332926084, "grad_norm": 0.5194751620292664, "learning_rate": 4.693106764188079e-06, "loss": 4.2972, "step": 26250 }, { "epoch": 0.8018020769700672, "grad_norm": 0.5017236471176147, "learning_rate": 4.691707645565257e-06, "loss": 4.2598, "step": 26251 }, { "epoch": 0.8018326206475259, "grad_norm": 0.5007879734039307, "learning_rate": 4.690308713931329e-06, "loss": 4.2802, "step": 26252 }, { "epoch": 0.8018631643249847, "grad_norm": 0.5002084374427795, "learning_rate": 4.6889099692991654e-06, "loss": 4.2227, "step": 26253 }, { "epoch": 0.8018937080024435, "grad_norm": 0.5257595777511597, "learning_rate": 4.687511411681658e-06, "loss": 4.1929, "step": 26254 }, { "epoch": 0.8019242516799022, "grad_norm": 0.5087822675704956, "learning_rate": 4.6861130410916745e-06, "loss": 4.2746, "step": 26255 }, { "epoch": 0.801954795357361, "grad_norm": 0.5228520035743713, "learning_rate": 4.684714857542089e-06, "loss": 4.1997, "step": 26256 }, { "epoch": 0.8019853390348198, "grad_norm": 0.5012233257293701, "learning_rate": 4.683316861045778e-06, "loss": 4.2248, "step": 26257 }, { "epoch": 0.8020158827122785, "grad_norm": 0.5113126635551453, "learning_rate": 4.681919051615618e-06, "loss": 4.3166, "step": 26258 }, { "epoch": 0.8020464263897373, "grad_norm": 0.49950170516967773, "learning_rate": 4.6805214292644725e-06, "loss": 4.1841, "step": 26259 }, { "epoch": 0.8020769700671961, "grad_norm": 0.5021470189094543, "learning_rate": 4.679123994005214e-06, "loss": 4.2797, "step": 26260 }, { "epoch": 0.8021075137446548, "grad_norm": 0.50962233543396, "learning_rate": 4.677726745850713e-06, "loss": 4.1426, "step": 26261 }, { "epoch": 0.8021380574221136, "grad_norm": 0.5112044811248779, "learning_rate": 4.6763296848138235e-06, "loss": 4.3123, "step": 26262 }, { "epoch": 0.8021686010995724, "grad_norm": 0.4978160262107849, "learning_rate": 4.674932810907421e-06, "loss": 4.2663, "step": 26263 }, { "epoch": 0.8021991447770311, "grad_norm": 0.5049143433570862, "learning_rate": 4.673536124144362e-06, "loss": 4.2836, "step": 26264 }, { "epoch": 0.8022296884544899, "grad_norm": 0.5099672079086304, "learning_rate": 4.672139624537505e-06, "loss": 4.2359, "step": 26265 }, { "epoch": 0.8022602321319486, "grad_norm": 0.5142747163772583, "learning_rate": 4.670743312099715e-06, "loss": 4.2698, "step": 26266 }, { "epoch": 0.8022907758094074, "grad_norm": 0.5074055194854736, "learning_rate": 4.6693471868438364e-06, "loss": 4.2414, "step": 26267 }, { "epoch": 0.8023213194868662, "grad_norm": 0.5114005208015442, "learning_rate": 4.6679512487827374e-06, "loss": 4.3211, "step": 26268 }, { "epoch": 0.8023518631643249, "grad_norm": 0.5126875638961792, "learning_rate": 4.666555497929259e-06, "loss": 4.2449, "step": 26269 }, { "epoch": 0.8023824068417837, "grad_norm": 0.5097728967666626, "learning_rate": 4.665159934296268e-06, "loss": 4.2665, "step": 26270 }, { "epoch": 0.8024129505192426, "grad_norm": 0.5074166059494019, "learning_rate": 4.663764557896594e-06, "loss": 4.139, "step": 26271 }, { "epoch": 0.8024434941967012, "grad_norm": 0.5137078762054443, "learning_rate": 4.662369368743105e-06, "loss": 4.1798, "step": 26272 }, { "epoch": 0.80247403787416, "grad_norm": 0.5064513087272644, "learning_rate": 4.660974366848627e-06, "loss": 4.2526, "step": 26273 }, { "epoch": 0.8025045815516189, "grad_norm": 0.49484509229660034, "learning_rate": 4.65957955222602e-06, "loss": 4.2046, "step": 26274 }, { "epoch": 0.8025351252290776, "grad_norm": 0.5113715529441833, "learning_rate": 4.6581849248881256e-06, "loss": 4.2873, "step": 26275 }, { "epoch": 0.8025656689065364, "grad_norm": 0.5178815722465515, "learning_rate": 4.656790484847778e-06, "loss": 4.1476, "step": 26276 }, { "epoch": 0.8025962125839952, "grad_norm": 0.5140617489814758, "learning_rate": 4.6553962321178174e-06, "loss": 4.1741, "step": 26277 }, { "epoch": 0.8026267562614539, "grad_norm": 0.5044178366661072, "learning_rate": 4.654002166711091e-06, "loss": 4.2716, "step": 26278 }, { "epoch": 0.8026572999389127, "grad_norm": 0.5031461715698242, "learning_rate": 4.65260828864042e-06, "loss": 4.1087, "step": 26279 }, { "epoch": 0.8026878436163715, "grad_norm": 0.4994344413280487, "learning_rate": 4.651214597918649e-06, "loss": 4.1466, "step": 26280 }, { "epoch": 0.8027183872938302, "grad_norm": 0.5064891576766968, "learning_rate": 4.649821094558609e-06, "loss": 4.1931, "step": 26281 }, { "epoch": 0.802748930971289, "grad_norm": 0.5084371566772461, "learning_rate": 4.648427778573128e-06, "loss": 4.3083, "step": 26282 }, { "epoch": 0.8027794746487477, "grad_norm": 0.4980567991733551, "learning_rate": 4.64703464997504e-06, "loss": 4.1127, "step": 26283 }, { "epoch": 0.8028100183262065, "grad_norm": 0.5133302211761475, "learning_rate": 4.645641708777162e-06, "loss": 4.1764, "step": 26284 }, { "epoch": 0.8028405620036653, "grad_norm": 0.5098308324813843, "learning_rate": 4.644248954992334e-06, "loss": 4.1576, "step": 26285 }, { "epoch": 0.802871105681124, "grad_norm": 0.5145687460899353, "learning_rate": 4.642856388633368e-06, "loss": 4.2679, "step": 26286 }, { "epoch": 0.8029016493585828, "grad_norm": 0.5045031905174255, "learning_rate": 4.641464009713087e-06, "loss": 4.2576, "step": 26287 }, { "epoch": 0.8029321930360416, "grad_norm": 0.4981899559497833, "learning_rate": 4.640071818244313e-06, "loss": 4.2158, "step": 26288 }, { "epoch": 0.8029627367135003, "grad_norm": 0.5058580636978149, "learning_rate": 4.638679814239871e-06, "loss": 4.1462, "step": 26289 }, { "epoch": 0.8029932803909591, "grad_norm": 0.5237205028533936, "learning_rate": 4.637287997712569e-06, "loss": 4.3261, "step": 26290 }, { "epoch": 0.8030238240684179, "grad_norm": 0.5040566325187683, "learning_rate": 4.6358963686752245e-06, "loss": 4.1808, "step": 26291 }, { "epoch": 0.8030543677458766, "grad_norm": 0.5063934326171875, "learning_rate": 4.634504927140659e-06, "loss": 4.2489, "step": 26292 }, { "epoch": 0.8030849114233354, "grad_norm": 0.5050255656242371, "learning_rate": 4.633113673121669e-06, "loss": 4.2407, "step": 26293 }, { "epoch": 0.8031154551007942, "grad_norm": 0.5160956978797913, "learning_rate": 4.631722606631075e-06, "loss": 4.2195, "step": 26294 }, { "epoch": 0.8031459987782529, "grad_norm": 0.5066955089569092, "learning_rate": 4.630331727681691e-06, "loss": 4.1975, "step": 26295 }, { "epoch": 0.8031765424557117, "grad_norm": 0.5148592591285706, "learning_rate": 4.628941036286308e-06, "loss": 4.3857, "step": 26296 }, { "epoch": 0.8032070861331705, "grad_norm": 0.5038106441497803, "learning_rate": 4.627550532457739e-06, "loss": 4.3026, "step": 26297 }, { "epoch": 0.8032376298106292, "grad_norm": 0.5143670439720154, "learning_rate": 4.6261602162087915e-06, "loss": 4.2709, "step": 26298 }, { "epoch": 0.803268173488088, "grad_norm": 0.4956055283546448, "learning_rate": 4.624770087552258e-06, "loss": 4.2132, "step": 26299 }, { "epoch": 0.8032987171655467, "grad_norm": 0.5082458853721619, "learning_rate": 4.6233801465009466e-06, "loss": 4.2795, "step": 26300 }, { "epoch": 0.8033292608430055, "grad_norm": 0.5104307532310486, "learning_rate": 4.621990393067652e-06, "loss": 4.2631, "step": 26301 }, { "epoch": 0.8033598045204643, "grad_norm": 0.502076268196106, "learning_rate": 4.620600827265162e-06, "loss": 4.292, "step": 26302 }, { "epoch": 0.803390348197923, "grad_norm": 0.5097767114639282, "learning_rate": 4.619211449106287e-06, "loss": 4.1767, "step": 26303 }, { "epoch": 0.8034208918753818, "grad_norm": 0.5047262907028198, "learning_rate": 4.617822258603802e-06, "loss": 4.2316, "step": 26304 }, { "epoch": 0.8034514355528406, "grad_norm": 0.4998367726802826, "learning_rate": 4.616433255770506e-06, "loss": 4.2607, "step": 26305 }, { "epoch": 0.8034819792302993, "grad_norm": 0.5039618611335754, "learning_rate": 4.615044440619198e-06, "loss": 4.3047, "step": 26306 }, { "epoch": 0.8035125229077581, "grad_norm": 0.5250687599182129, "learning_rate": 4.613655813162648e-06, "loss": 4.2736, "step": 26307 }, { "epoch": 0.8035430665852169, "grad_norm": 0.5002567768096924, "learning_rate": 4.612267373413654e-06, "loss": 4.2649, "step": 26308 }, { "epoch": 0.8035736102626756, "grad_norm": 0.5055344700813293, "learning_rate": 4.610879121385e-06, "loss": 4.2034, "step": 26309 }, { "epoch": 0.8036041539401344, "grad_norm": 0.5148578882217407, "learning_rate": 4.60949105708946e-06, "loss": 4.2033, "step": 26310 }, { "epoch": 0.8036346976175932, "grad_norm": 0.5081884860992432, "learning_rate": 4.608103180539819e-06, "loss": 4.36, "step": 26311 }, { "epoch": 0.8036652412950519, "grad_norm": 0.5064934492111206, "learning_rate": 4.606715491748864e-06, "loss": 4.249, "step": 26312 }, { "epoch": 0.8036957849725107, "grad_norm": 0.5128198266029358, "learning_rate": 4.605327990729358e-06, "loss": 4.2615, "step": 26313 }, { "epoch": 0.8037263286499694, "grad_norm": 0.4954322278499603, "learning_rate": 4.60394067749409e-06, "loss": 4.1313, "step": 26314 }, { "epoch": 0.8037568723274282, "grad_norm": 0.5104618072509766, "learning_rate": 4.6025535520558185e-06, "loss": 4.234, "step": 26315 }, { "epoch": 0.803787416004887, "grad_norm": 0.5130077600479126, "learning_rate": 4.601166614427329e-06, "loss": 4.3234, "step": 26316 }, { "epoch": 0.8038179596823457, "grad_norm": 0.5045337080955505, "learning_rate": 4.5997798646213844e-06, "loss": 4.2789, "step": 26317 }, { "epoch": 0.8038485033598045, "grad_norm": 0.5126585960388184, "learning_rate": 4.598393302650758e-06, "loss": 4.3151, "step": 26318 }, { "epoch": 0.8038790470372633, "grad_norm": 0.495294451713562, "learning_rate": 4.5970069285282105e-06, "loss": 4.2757, "step": 26319 }, { "epoch": 0.803909590714722, "grad_norm": 0.5035927891731262, "learning_rate": 4.595620742266515e-06, "loss": 4.2645, "step": 26320 }, { "epoch": 0.8039401343921808, "grad_norm": 0.5088582038879395, "learning_rate": 4.594234743878423e-06, "loss": 4.2983, "step": 26321 }, { "epoch": 0.8039706780696396, "grad_norm": 0.5076777338981628, "learning_rate": 4.592848933376706e-06, "loss": 4.3121, "step": 26322 }, { "epoch": 0.8040012217470983, "grad_norm": 0.5086384415626526, "learning_rate": 4.591463310774125e-06, "loss": 4.2769, "step": 26323 }, { "epoch": 0.8040317654245571, "grad_norm": 0.502474308013916, "learning_rate": 4.590077876083429e-06, "loss": 4.2616, "step": 26324 }, { "epoch": 0.8040623091020159, "grad_norm": 0.5114534497261047, "learning_rate": 4.588692629317379e-06, "loss": 4.2776, "step": 26325 }, { "epoch": 0.8040928527794746, "grad_norm": 0.5022157430648804, "learning_rate": 4.587307570488738e-06, "loss": 4.129, "step": 26326 }, { "epoch": 0.8041233964569334, "grad_norm": 0.4990514814853668, "learning_rate": 4.585922699610246e-06, "loss": 4.1867, "step": 26327 }, { "epoch": 0.8041539401343922, "grad_norm": 0.5119796991348267, "learning_rate": 4.584538016694656e-06, "loss": 4.0494, "step": 26328 }, { "epoch": 0.8041844838118509, "grad_norm": 0.5050615072250366, "learning_rate": 4.583153521754729e-06, "loss": 4.352, "step": 26329 }, { "epoch": 0.8042150274893097, "grad_norm": 0.5016344785690308, "learning_rate": 4.5817692148032e-06, "loss": 4.1179, "step": 26330 }, { "epoch": 0.8042455711667684, "grad_norm": 0.49979421496391296, "learning_rate": 4.580385095852827e-06, "loss": 4.2387, "step": 26331 }, { "epoch": 0.8042761148442272, "grad_norm": 0.5162326693534851, "learning_rate": 4.579001164916344e-06, "loss": 4.2961, "step": 26332 }, { "epoch": 0.804306658521686, "grad_norm": 0.49984389543533325, "learning_rate": 4.5776174220064916e-06, "loss": 4.2956, "step": 26333 }, { "epoch": 0.8043372021991447, "grad_norm": 0.4925520718097687, "learning_rate": 4.576233867136023e-06, "loss": 4.2458, "step": 26334 }, { "epoch": 0.8043677458766035, "grad_norm": 0.4982687830924988, "learning_rate": 4.574850500317662e-06, "loss": 4.2674, "step": 26335 }, { "epoch": 0.8043982895540623, "grad_norm": 0.5045994520187378, "learning_rate": 4.5734673215641534e-06, "loss": 4.2315, "step": 26336 }, { "epoch": 0.804428833231521, "grad_norm": 0.5071181654930115, "learning_rate": 4.572084330888243e-06, "loss": 4.211, "step": 26337 }, { "epoch": 0.8044593769089798, "grad_norm": 0.5075258016586304, "learning_rate": 4.570701528302648e-06, "loss": 4.2756, "step": 26338 }, { "epoch": 0.8044899205864386, "grad_norm": 0.5036094784736633, "learning_rate": 4.569318913820106e-06, "loss": 4.1736, "step": 26339 }, { "epoch": 0.8045204642638973, "grad_norm": 0.5035235285758972, "learning_rate": 4.5679364874533556e-06, "loss": 4.2511, "step": 26340 }, { "epoch": 0.8045510079413561, "grad_norm": 0.50592041015625, "learning_rate": 4.566554249215113e-06, "loss": 4.2258, "step": 26341 }, { "epoch": 0.804581551618815, "grad_norm": 0.5060641169548035, "learning_rate": 4.565172199118115e-06, "loss": 4.2948, "step": 26342 }, { "epoch": 0.8046120952962736, "grad_norm": 0.516747236251831, "learning_rate": 4.563790337175084e-06, "loss": 4.1798, "step": 26343 }, { "epoch": 0.8046426389737324, "grad_norm": 0.505857527256012, "learning_rate": 4.56240866339874e-06, "loss": 4.1718, "step": 26344 }, { "epoch": 0.8046731826511913, "grad_norm": 0.5188959836959839, "learning_rate": 4.561027177801805e-06, "loss": 4.2538, "step": 26345 }, { "epoch": 0.80470372632865, "grad_norm": 0.5079131126403809, "learning_rate": 4.559645880397009e-06, "loss": 4.2941, "step": 26346 }, { "epoch": 0.8047342700061088, "grad_norm": 0.49539458751678467, "learning_rate": 4.5582647711970625e-06, "loss": 4.271, "step": 26347 }, { "epoch": 0.8047648136835674, "grad_norm": 0.5020556449890137, "learning_rate": 4.556883850214677e-06, "loss": 4.2706, "step": 26348 }, { "epoch": 0.8047953573610263, "grad_norm": 0.5162799954414368, "learning_rate": 4.555503117462576e-06, "loss": 4.3342, "step": 26349 }, { "epoch": 0.8048259010384851, "grad_norm": 0.5092746019363403, "learning_rate": 4.554122572953465e-06, "loss": 4.3099, "step": 26350 }, { "epoch": 0.8048564447159438, "grad_norm": 0.5161798596382141, "learning_rate": 4.552742216700068e-06, "loss": 4.2634, "step": 26351 }, { "epoch": 0.8048869883934026, "grad_norm": 0.506773054599762, "learning_rate": 4.551362048715077e-06, "loss": 4.3407, "step": 26352 }, { "epoch": 0.8049175320708614, "grad_norm": 0.5096845030784607, "learning_rate": 4.54998206901121e-06, "loss": 4.238, "step": 26353 }, { "epoch": 0.8049480757483201, "grad_norm": 0.5024495124816895, "learning_rate": 4.54860227760118e-06, "loss": 4.2769, "step": 26354 }, { "epoch": 0.8049786194257789, "grad_norm": 0.5177858471870422, "learning_rate": 4.547222674497675e-06, "loss": 4.2362, "step": 26355 }, { "epoch": 0.8050091631032377, "grad_norm": 0.501762866973877, "learning_rate": 4.5458432597134085e-06, "loss": 4.2714, "step": 26356 }, { "epoch": 0.8050397067806964, "grad_norm": 0.511486828327179, "learning_rate": 4.544464033261087e-06, "loss": 4.2044, "step": 26357 }, { "epoch": 0.8050702504581552, "grad_norm": 0.5051857233047485, "learning_rate": 4.543084995153393e-06, "loss": 4.35, "step": 26358 }, { "epoch": 0.805100794135614, "grad_norm": 0.5067710876464844, "learning_rate": 4.541706145403035e-06, "loss": 4.1939, "step": 26359 }, { "epoch": 0.8051313378130727, "grad_norm": 0.511271059513092, "learning_rate": 4.540327484022716e-06, "loss": 4.2674, "step": 26360 }, { "epoch": 0.8051618814905315, "grad_norm": 0.5063843727111816, "learning_rate": 4.538949011025112e-06, "loss": 4.1791, "step": 26361 }, { "epoch": 0.8051924251679903, "grad_norm": 0.5043644309043884, "learning_rate": 4.53757072642293e-06, "loss": 4.2278, "step": 26362 }, { "epoch": 0.805222968845449, "grad_norm": 0.5120737552642822, "learning_rate": 4.53619263022885e-06, "loss": 4.2602, "step": 26363 }, { "epoch": 0.8052535125229078, "grad_norm": 0.49901312589645386, "learning_rate": 4.534814722455574e-06, "loss": 4.3026, "step": 26364 }, { "epoch": 0.8052840562003665, "grad_norm": 0.5158275365829468, "learning_rate": 4.5334370031157786e-06, "loss": 4.2636, "step": 26365 }, { "epoch": 0.8053145998778253, "grad_norm": 0.519645631313324, "learning_rate": 4.532059472222144e-06, "loss": 4.4043, "step": 26366 }, { "epoch": 0.8053451435552841, "grad_norm": 0.5124277472496033, "learning_rate": 4.530682129787364e-06, "loss": 4.2204, "step": 26367 }, { "epoch": 0.8053756872327428, "grad_norm": 0.49958497285842896, "learning_rate": 4.529304975824125e-06, "loss": 4.1718, "step": 26368 }, { "epoch": 0.8054062309102016, "grad_norm": 0.5041654109954834, "learning_rate": 4.527928010345092e-06, "loss": 4.2566, "step": 26369 }, { "epoch": 0.8054367745876604, "grad_norm": 0.5102007389068604, "learning_rate": 4.526551233362952e-06, "loss": 4.213, "step": 26370 }, { "epoch": 0.8054673182651191, "grad_norm": 0.5050758719444275, "learning_rate": 4.525174644890387e-06, "loss": 4.3284, "step": 26371 }, { "epoch": 0.8054978619425779, "grad_norm": 0.5002518892288208, "learning_rate": 4.523798244940058e-06, "loss": 4.2393, "step": 26372 }, { "epoch": 0.8055284056200367, "grad_norm": 0.49895960092544556, "learning_rate": 4.522422033524651e-06, "loss": 4.2671, "step": 26373 }, { "epoch": 0.8055589492974954, "grad_norm": 0.5232671499252319, "learning_rate": 4.5210460106568345e-06, "loss": 4.1937, "step": 26374 }, { "epoch": 0.8055894929749542, "grad_norm": 0.49732086062431335, "learning_rate": 4.519670176349275e-06, "loss": 4.1821, "step": 26375 }, { "epoch": 0.805620036652413, "grad_norm": 0.5051604509353638, "learning_rate": 4.518294530614639e-06, "loss": 4.1345, "step": 26376 }, { "epoch": 0.8056505803298717, "grad_norm": 0.5062140822410583, "learning_rate": 4.516919073465603e-06, "loss": 4.2084, "step": 26377 }, { "epoch": 0.8056811240073305, "grad_norm": 0.5058149099349976, "learning_rate": 4.515543804914824e-06, "loss": 4.1996, "step": 26378 }, { "epoch": 0.8057116676847893, "grad_norm": 0.4963720440864563, "learning_rate": 4.51416872497496e-06, "loss": 4.2871, "step": 26379 }, { "epoch": 0.805742211362248, "grad_norm": 0.5208814144134521, "learning_rate": 4.512793833658683e-06, "loss": 4.3048, "step": 26380 }, { "epoch": 0.8057727550397068, "grad_norm": 0.5077724456787109, "learning_rate": 4.511419130978639e-06, "loss": 4.1988, "step": 26381 }, { "epoch": 0.8058032987171655, "grad_norm": 0.5153466463088989, "learning_rate": 4.5100446169475005e-06, "loss": 4.2418, "step": 26382 }, { "epoch": 0.8058338423946243, "grad_norm": 0.5125442147254944, "learning_rate": 4.50867029157791e-06, "loss": 4.2698, "step": 26383 }, { "epoch": 0.8058643860720831, "grad_norm": 0.5113568305969238, "learning_rate": 4.507296154882529e-06, "loss": 4.245, "step": 26384 }, { "epoch": 0.8058949297495418, "grad_norm": 0.5048091411590576, "learning_rate": 4.505922206874013e-06, "loss": 4.3003, "step": 26385 }, { "epoch": 0.8059254734270006, "grad_norm": 0.5021765232086182, "learning_rate": 4.504548447565002e-06, "loss": 4.3143, "step": 26386 }, { "epoch": 0.8059560171044594, "grad_norm": 0.49877771735191345, "learning_rate": 4.503174876968152e-06, "loss": 4.2494, "step": 26387 }, { "epoch": 0.8059865607819181, "grad_norm": 0.5105487108230591, "learning_rate": 4.501801495096114e-06, "loss": 4.3624, "step": 26388 }, { "epoch": 0.8060171044593769, "grad_norm": 0.49619120359420776, "learning_rate": 4.500428301961527e-06, "loss": 4.2159, "step": 26389 }, { "epoch": 0.8060476481368357, "grad_norm": 0.5059364438056946, "learning_rate": 4.499055297577032e-06, "loss": 4.1521, "step": 26390 }, { "epoch": 0.8060781918142944, "grad_norm": 0.5029287934303284, "learning_rate": 4.497682481955282e-06, "loss": 4.1894, "step": 26391 }, { "epoch": 0.8061087354917532, "grad_norm": 0.5050390958786011, "learning_rate": 4.496309855108908e-06, "loss": 4.2697, "step": 26392 }, { "epoch": 0.806139279169212, "grad_norm": 0.5085843205451965, "learning_rate": 4.494937417050551e-06, "loss": 4.2837, "step": 26393 }, { "epoch": 0.8061698228466707, "grad_norm": 0.5211244821548462, "learning_rate": 4.493565167792846e-06, "loss": 4.2869, "step": 26394 }, { "epoch": 0.8062003665241295, "grad_norm": 0.5063890218734741, "learning_rate": 4.492193107348436e-06, "loss": 4.2727, "step": 26395 }, { "epoch": 0.8062309102015883, "grad_norm": 0.5041356682777405, "learning_rate": 4.490821235729942e-06, "loss": 4.2624, "step": 26396 }, { "epoch": 0.806261453879047, "grad_norm": 0.5072652101516724, "learning_rate": 4.489449552950007e-06, "loss": 4.2803, "step": 26397 }, { "epoch": 0.8062919975565058, "grad_norm": 0.5200812220573425, "learning_rate": 4.48807805902125e-06, "loss": 4.2326, "step": 26398 }, { "epoch": 0.8063225412339645, "grad_norm": 0.5069330930709839, "learning_rate": 4.48670675395631e-06, "loss": 4.3061, "step": 26399 }, { "epoch": 0.8063530849114233, "grad_norm": 0.5116064548492432, "learning_rate": 4.485335637767801e-06, "loss": 4.2892, "step": 26400 }, { "epoch": 0.8063836285888821, "grad_norm": 0.5323977470397949, "learning_rate": 4.483964710468355e-06, "loss": 4.3022, "step": 26401 }, { "epoch": 0.8064141722663408, "grad_norm": 0.5079097747802734, "learning_rate": 4.482593972070601e-06, "loss": 4.2635, "step": 26402 }, { "epoch": 0.8064447159437996, "grad_norm": 0.49915432929992676, "learning_rate": 4.481223422587147e-06, "loss": 4.1829, "step": 26403 }, { "epoch": 0.8064752596212584, "grad_norm": 0.5025632977485657, "learning_rate": 4.47985306203062e-06, "loss": 4.2566, "step": 26404 }, { "epoch": 0.8065058032987171, "grad_norm": 0.5085695385932922, "learning_rate": 4.478482890413641e-06, "loss": 4.2838, "step": 26405 }, { "epoch": 0.8065363469761759, "grad_norm": 0.5092218518257141, "learning_rate": 4.477112907748812e-06, "loss": 4.3576, "step": 26406 }, { "epoch": 0.8065668906536347, "grad_norm": 0.5009681582450867, "learning_rate": 4.475743114048761e-06, "loss": 4.3039, "step": 26407 }, { "epoch": 0.8065974343310934, "grad_norm": 0.511232316493988, "learning_rate": 4.4743735093260995e-06, "loss": 4.2614, "step": 26408 }, { "epoch": 0.8066279780085522, "grad_norm": 0.5122485160827637, "learning_rate": 4.473004093593428e-06, "loss": 4.2253, "step": 26409 }, { "epoch": 0.806658521686011, "grad_norm": 0.5164437294006348, "learning_rate": 4.471634866863369e-06, "loss": 4.2654, "step": 26410 }, { "epoch": 0.8066890653634697, "grad_norm": 0.5062381625175476, "learning_rate": 4.470265829148524e-06, "loss": 4.1877, "step": 26411 }, { "epoch": 0.8067196090409285, "grad_norm": 0.507328450679779, "learning_rate": 4.4688969804614874e-06, "loss": 4.1951, "step": 26412 }, { "epoch": 0.8067501527183873, "grad_norm": 0.5112524628639221, "learning_rate": 4.467528320814873e-06, "loss": 4.3191, "step": 26413 }, { "epoch": 0.806780696395846, "grad_norm": 0.514323890209198, "learning_rate": 4.466159850221288e-06, "loss": 4.2337, "step": 26414 }, { "epoch": 0.8068112400733048, "grad_norm": 0.6075662970542908, "learning_rate": 4.464791568693322e-06, "loss": 4.312, "step": 26415 }, { "epoch": 0.8068417837507635, "grad_norm": 0.5238834619522095, "learning_rate": 4.463423476243583e-06, "loss": 4.215, "step": 26416 }, { "epoch": 0.8068723274282223, "grad_norm": 0.5078688263893127, "learning_rate": 4.4620555728846575e-06, "loss": 4.3011, "step": 26417 }, { "epoch": 0.8069028711056812, "grad_norm": 0.5097888112068176, "learning_rate": 4.460687858629148e-06, "loss": 4.3431, "step": 26418 }, { "epoch": 0.8069334147831398, "grad_norm": 0.5128111839294434, "learning_rate": 4.4593203334896475e-06, "loss": 4.3449, "step": 26419 }, { "epoch": 0.8069639584605987, "grad_norm": 0.5008273124694824, "learning_rate": 4.457952997478743e-06, "loss": 4.2433, "step": 26420 }, { "epoch": 0.8069945021380575, "grad_norm": 0.5139942765235901, "learning_rate": 4.456585850609024e-06, "loss": 4.2585, "step": 26421 }, { "epoch": 0.8070250458155162, "grad_norm": 0.5007789134979248, "learning_rate": 4.45521889289309e-06, "loss": 4.233, "step": 26422 }, { "epoch": 0.807055589492975, "grad_norm": 0.5133314728736877, "learning_rate": 4.453852124343514e-06, "loss": 4.2656, "step": 26423 }, { "epoch": 0.8070861331704338, "grad_norm": 0.5114167928695679, "learning_rate": 4.452485544972887e-06, "loss": 4.3315, "step": 26424 }, { "epoch": 0.8071166768478925, "grad_norm": 0.496450811624527, "learning_rate": 4.451119154793787e-06, "loss": 4.0697, "step": 26425 }, { "epoch": 0.8071472205253513, "grad_norm": 0.5217861533164978, "learning_rate": 4.449752953818803e-06, "loss": 4.3099, "step": 26426 }, { "epoch": 0.8071777642028101, "grad_norm": 0.8543444871902466, "learning_rate": 4.4483869420605035e-06, "loss": 4.27, "step": 26427 }, { "epoch": 0.8072083078802688, "grad_norm": 0.5050068497657776, "learning_rate": 4.447021119531478e-06, "loss": 4.2251, "step": 26428 }, { "epoch": 0.8072388515577276, "grad_norm": 0.5095927119255066, "learning_rate": 4.44565548624429e-06, "loss": 4.0988, "step": 26429 }, { "epoch": 0.8072693952351864, "grad_norm": 0.5095160007476807, "learning_rate": 4.444290042211521e-06, "loss": 4.3268, "step": 26430 }, { "epoch": 0.8072999389126451, "grad_norm": 0.5092508792877197, "learning_rate": 4.442924787445748e-06, "loss": 4.1967, "step": 26431 }, { "epoch": 0.8073304825901039, "grad_norm": 0.5063174962997437, "learning_rate": 4.4415597219595315e-06, "loss": 4.2587, "step": 26432 }, { "epoch": 0.8073610262675626, "grad_norm": 0.5028467178344727, "learning_rate": 4.440194845765449e-06, "loss": 4.2489, "step": 26433 }, { "epoch": 0.8073915699450214, "grad_norm": 0.5211876630783081, "learning_rate": 4.438830158876056e-06, "loss": 4.1852, "step": 26434 }, { "epoch": 0.8074221136224802, "grad_norm": 0.5166431665420532, "learning_rate": 4.437465661303927e-06, "loss": 4.2802, "step": 26435 }, { "epoch": 0.8074526572999389, "grad_norm": 0.5032907128334045, "learning_rate": 4.436101353061631e-06, "loss": 4.1884, "step": 26436 }, { "epoch": 0.8074832009773977, "grad_norm": 0.5099887847900391, "learning_rate": 4.434737234161715e-06, "loss": 4.1979, "step": 26437 }, { "epoch": 0.8075137446548565, "grad_norm": 0.5209398865699768, "learning_rate": 4.4333733046167445e-06, "loss": 4.3698, "step": 26438 }, { "epoch": 0.8075442883323152, "grad_norm": 0.5029606819152832, "learning_rate": 4.43200956443929e-06, "loss": 4.2476, "step": 26439 }, { "epoch": 0.807574832009774, "grad_norm": 0.507683277130127, "learning_rate": 4.430646013641893e-06, "loss": 4.2749, "step": 26440 }, { "epoch": 0.8076053756872328, "grad_norm": 0.5129883289337158, "learning_rate": 4.429282652237119e-06, "loss": 4.179, "step": 26441 }, { "epoch": 0.8076359193646915, "grad_norm": 0.5116779208183289, "learning_rate": 4.427919480237513e-06, "loss": 4.2296, "step": 26442 }, { "epoch": 0.8076664630421503, "grad_norm": 0.5055157542228699, "learning_rate": 4.4265564976556265e-06, "loss": 4.2508, "step": 26443 }, { "epoch": 0.8076970067196091, "grad_norm": 0.5082084536552429, "learning_rate": 4.4251937045040105e-06, "loss": 4.2379, "step": 26444 }, { "epoch": 0.8077275503970678, "grad_norm": 0.5166848301887512, "learning_rate": 4.423831100795223e-06, "loss": 4.1599, "step": 26445 }, { "epoch": 0.8077580940745266, "grad_norm": 0.5050244331359863, "learning_rate": 4.422468686541792e-06, "loss": 4.2652, "step": 26446 }, { "epoch": 0.8077886377519854, "grad_norm": 0.5035524964332581, "learning_rate": 4.421106461756275e-06, "loss": 4.1529, "step": 26447 }, { "epoch": 0.8078191814294441, "grad_norm": 0.5059950351715088, "learning_rate": 4.419744426451216e-06, "loss": 4.3027, "step": 26448 }, { "epoch": 0.8078497251069029, "grad_norm": 0.5300307869911194, "learning_rate": 4.418382580639146e-06, "loss": 4.2748, "step": 26449 }, { "epoch": 0.8078802687843616, "grad_norm": 0.5065904855728149, "learning_rate": 4.417020924332616e-06, "loss": 4.2627, "step": 26450 }, { "epoch": 0.8079108124618204, "grad_norm": 0.5102670788764954, "learning_rate": 4.41565945754415e-06, "loss": 4.2315, "step": 26451 }, { "epoch": 0.8079413561392792, "grad_norm": 0.5096065998077393, "learning_rate": 4.414298180286291e-06, "loss": 4.302, "step": 26452 }, { "epoch": 0.8079718998167379, "grad_norm": 0.5114228129386902, "learning_rate": 4.412937092571579e-06, "loss": 4.2731, "step": 26453 }, { "epoch": 0.8080024434941967, "grad_norm": 0.5040168762207031, "learning_rate": 4.411576194412534e-06, "loss": 4.2724, "step": 26454 }, { "epoch": 0.8080329871716555, "grad_norm": 0.5065605044364929, "learning_rate": 4.410215485821692e-06, "loss": 4.2207, "step": 26455 }, { "epoch": 0.8080635308491142, "grad_norm": 0.5120987296104431, "learning_rate": 4.40885496681159e-06, "loss": 4.2551, "step": 26456 }, { "epoch": 0.808094074526573, "grad_norm": 0.5118252038955688, "learning_rate": 4.407494637394746e-06, "loss": 4.1575, "step": 26457 }, { "epoch": 0.8081246182040318, "grad_norm": 0.4975169599056244, "learning_rate": 4.40613449758368e-06, "loss": 4.1104, "step": 26458 }, { "epoch": 0.8081551618814905, "grad_norm": 0.5006018877029419, "learning_rate": 4.40477454739093e-06, "loss": 4.2127, "step": 26459 }, { "epoch": 0.8081857055589493, "grad_norm": 0.519216001033783, "learning_rate": 4.403414786829002e-06, "loss": 4.3007, "step": 26460 }, { "epoch": 0.8082162492364081, "grad_norm": 0.5100432634353638, "learning_rate": 4.402055215910422e-06, "loss": 4.2797, "step": 26461 }, { "epoch": 0.8082467929138668, "grad_norm": 0.5121197700500488, "learning_rate": 4.400695834647719e-06, "loss": 4.2107, "step": 26462 }, { "epoch": 0.8082773365913256, "grad_norm": 0.5026658177375793, "learning_rate": 4.399336643053395e-06, "loss": 4.262, "step": 26463 }, { "epoch": 0.8083078802687843, "grad_norm": 0.5121279358863831, "learning_rate": 4.3979776411399745e-06, "loss": 4.2342, "step": 26464 }, { "epoch": 0.8083384239462431, "grad_norm": 0.5024948716163635, "learning_rate": 4.39661882891996e-06, "loss": 4.2333, "step": 26465 }, { "epoch": 0.8083689676237019, "grad_norm": 0.5160332322120667, "learning_rate": 4.395260206405871e-06, "loss": 4.1828, "step": 26466 }, { "epoch": 0.8083995113011606, "grad_norm": 0.51211017370224, "learning_rate": 4.39390177361022e-06, "loss": 4.257, "step": 26467 }, { "epoch": 0.8084300549786194, "grad_norm": 0.5138396620750427, "learning_rate": 4.392543530545504e-06, "loss": 4.2741, "step": 26468 }, { "epoch": 0.8084605986560782, "grad_norm": 0.5077533721923828, "learning_rate": 4.391185477224235e-06, "loss": 4.3415, "step": 26469 }, { "epoch": 0.8084911423335369, "grad_norm": 0.5167361497879028, "learning_rate": 4.389827613658923e-06, "loss": 4.2982, "step": 26470 }, { "epoch": 0.8085216860109957, "grad_norm": 0.5072558522224426, "learning_rate": 4.388469939862058e-06, "loss": 4.2527, "step": 26471 }, { "epoch": 0.8085522296884545, "grad_norm": 0.5258452892303467, "learning_rate": 4.387112455846157e-06, "loss": 4.2678, "step": 26472 }, { "epoch": 0.8085827733659132, "grad_norm": 0.5097219347953796, "learning_rate": 4.3857551616237e-06, "loss": 4.1773, "step": 26473 }, { "epoch": 0.808613317043372, "grad_norm": 0.5094216465950012, "learning_rate": 4.384398057207204e-06, "loss": 4.2234, "step": 26474 }, { "epoch": 0.8086438607208308, "grad_norm": 0.5078884363174438, "learning_rate": 4.383041142609145e-06, "loss": 4.2081, "step": 26475 }, { "epoch": 0.8086744043982895, "grad_norm": 0.5035696029663086, "learning_rate": 4.381684417842033e-06, "loss": 4.2757, "step": 26476 }, { "epoch": 0.8087049480757483, "grad_norm": 0.513918936252594, "learning_rate": 4.38032788291835e-06, "loss": 4.3263, "step": 26477 }, { "epoch": 0.8087354917532071, "grad_norm": 0.5096690654754639, "learning_rate": 4.378971537850587e-06, "loss": 4.2847, "step": 26478 }, { "epoch": 0.8087660354306658, "grad_norm": 0.5053152441978455, "learning_rate": 4.3776153826512425e-06, "loss": 4.2406, "step": 26479 }, { "epoch": 0.8087965791081246, "grad_norm": 0.5141384601593018, "learning_rate": 4.3762594173327895e-06, "loss": 4.2645, "step": 26480 }, { "epoch": 0.8088271227855833, "grad_norm": 0.5163310766220093, "learning_rate": 4.3749036419077265e-06, "loss": 4.3068, "step": 26481 }, { "epoch": 0.8088576664630421, "grad_norm": 0.5140888690948486, "learning_rate": 4.373548056388524e-06, "loss": 4.2388, "step": 26482 }, { "epoch": 0.8088882101405009, "grad_norm": 0.509585976600647, "learning_rate": 4.372192660787669e-06, "loss": 4.222, "step": 26483 }, { "epoch": 0.8089187538179596, "grad_norm": 0.5048778653144836, "learning_rate": 4.370837455117649e-06, "loss": 4.2544, "step": 26484 }, { "epoch": 0.8089492974954184, "grad_norm": 0.5100120306015015, "learning_rate": 4.369482439390926e-06, "loss": 4.2564, "step": 26485 }, { "epoch": 0.8089798411728772, "grad_norm": 0.5016438364982605, "learning_rate": 4.368127613619988e-06, "loss": 4.3096, "step": 26486 }, { "epoch": 0.8090103848503359, "grad_norm": 0.5159134268760681, "learning_rate": 4.366772977817313e-06, "loss": 4.249, "step": 26487 }, { "epoch": 0.8090409285277947, "grad_norm": 0.5028467178344727, "learning_rate": 4.365418531995369e-06, "loss": 4.3067, "step": 26488 }, { "epoch": 0.8090714722052536, "grad_norm": 0.5123492479324341, "learning_rate": 4.3640642761666155e-06, "loss": 4.225, "step": 26489 }, { "epoch": 0.8091020158827122, "grad_norm": 0.5006774663925171, "learning_rate": 4.362710210343543e-06, "loss": 4.2142, "step": 26490 }, { "epoch": 0.809132559560171, "grad_norm": 0.5151249170303345, "learning_rate": 4.361356334538599e-06, "loss": 4.2477, "step": 26491 }, { "epoch": 0.8091631032376299, "grad_norm": 0.5171753168106079, "learning_rate": 4.360002648764261e-06, "loss": 4.172, "step": 26492 }, { "epoch": 0.8091936469150885, "grad_norm": 0.516798734664917, "learning_rate": 4.358649153032995e-06, "loss": 4.2496, "step": 26493 }, { "epoch": 0.8092241905925474, "grad_norm": 0.5042980909347534, "learning_rate": 4.357295847357251e-06, "loss": 4.2179, "step": 26494 }, { "epoch": 0.8092547342700062, "grad_norm": 0.5169507265090942, "learning_rate": 4.3559427317495015e-06, "loss": 4.3485, "step": 26495 }, { "epoch": 0.8092852779474649, "grad_norm": 0.5222065448760986, "learning_rate": 4.354589806222207e-06, "loss": 4.2711, "step": 26496 }, { "epoch": 0.8093158216249237, "grad_norm": 0.5105941295623779, "learning_rate": 4.353237070787811e-06, "loss": 4.2556, "step": 26497 }, { "epoch": 0.8093463653023824, "grad_norm": 0.5157419443130493, "learning_rate": 4.351884525458782e-06, "loss": 4.1964, "step": 26498 }, { "epoch": 0.8093769089798412, "grad_norm": 0.499929279088974, "learning_rate": 4.3505321702475646e-06, "loss": 4.2424, "step": 26499 }, { "epoch": 0.8094074526573, "grad_norm": 0.515038251876831, "learning_rate": 4.349180005166611e-06, "loss": 4.2905, "step": 26500 }, { "epoch": 0.8094379963347587, "grad_norm": 0.5160240530967712, "learning_rate": 4.347828030228385e-06, "loss": 4.2434, "step": 26501 }, { "epoch": 0.8094685400122175, "grad_norm": 0.5066840648651123, "learning_rate": 4.3464762454453165e-06, "loss": 4.263, "step": 26502 }, { "epoch": 0.8094990836896763, "grad_norm": 0.5137537717819214, "learning_rate": 4.345124650829868e-06, "loss": 4.1498, "step": 26503 }, { "epoch": 0.809529627367135, "grad_norm": 0.5115258693695068, "learning_rate": 4.3437732463944696e-06, "loss": 4.2851, "step": 26504 }, { "epoch": 0.8095601710445938, "grad_norm": 0.5169661045074463, "learning_rate": 4.3424220321515744e-06, "loss": 4.2214, "step": 26505 }, { "epoch": 0.8095907147220526, "grad_norm": 0.5133694410324097, "learning_rate": 4.341071008113617e-06, "loss": 4.2144, "step": 26506 }, { "epoch": 0.8096212583995113, "grad_norm": 0.5092632174491882, "learning_rate": 4.3397201742930495e-06, "loss": 4.1784, "step": 26507 }, { "epoch": 0.8096518020769701, "grad_norm": 0.5261865854263306, "learning_rate": 4.338369530702291e-06, "loss": 4.3284, "step": 26508 }, { "epoch": 0.8096823457544289, "grad_norm": 0.5192919969558716, "learning_rate": 4.337019077353788e-06, "loss": 4.3051, "step": 26509 }, { "epoch": 0.8097128894318876, "grad_norm": 0.5252369046211243, "learning_rate": 4.33566881425998e-06, "loss": 4.2992, "step": 26510 }, { "epoch": 0.8097434331093464, "grad_norm": 0.5060902237892151, "learning_rate": 4.334318741433288e-06, "loss": 4.234, "step": 26511 }, { "epoch": 0.8097739767868052, "grad_norm": 0.5075603127479553, "learning_rate": 4.332968858886149e-06, "loss": 4.2886, "step": 26512 }, { "epoch": 0.8098045204642639, "grad_norm": 0.5099732279777527, "learning_rate": 4.3316191666309985e-06, "loss": 4.3109, "step": 26513 }, { "epoch": 0.8098350641417227, "grad_norm": 0.5182734131813049, "learning_rate": 4.33026966468025e-06, "loss": 4.1367, "step": 26514 }, { "epoch": 0.8098656078191814, "grad_norm": 0.5033965110778809, "learning_rate": 4.328920353046343e-06, "loss": 4.2329, "step": 26515 }, { "epoch": 0.8098961514966402, "grad_norm": 0.5132295489311218, "learning_rate": 4.327571231741687e-06, "loss": 4.2318, "step": 26516 }, { "epoch": 0.809926695174099, "grad_norm": 0.510897159576416, "learning_rate": 4.326222300778712e-06, "loss": 4.1665, "step": 26517 }, { "epoch": 0.8099572388515577, "grad_norm": 0.5308191776275635, "learning_rate": 4.3248735601698425e-06, "loss": 4.3997, "step": 26518 }, { "epoch": 0.8099877825290165, "grad_norm": 0.503455400466919, "learning_rate": 4.323525009927487e-06, "loss": 4.1908, "step": 26519 }, { "epoch": 0.8100183262064753, "grad_norm": 0.5018823146820068, "learning_rate": 4.322176650064075e-06, "loss": 4.1981, "step": 26520 }, { "epoch": 0.810048869883934, "grad_norm": 0.5125343799591064, "learning_rate": 4.320828480592013e-06, "loss": 4.296, "step": 26521 }, { "epoch": 0.8100794135613928, "grad_norm": 0.5158100128173828, "learning_rate": 4.31948050152371e-06, "loss": 4.3052, "step": 26522 }, { "epoch": 0.8101099572388516, "grad_norm": 0.5190898776054382, "learning_rate": 4.318132712871581e-06, "loss": 4.1475, "step": 26523 }, { "epoch": 0.8101405009163103, "grad_norm": 0.4958098530769348, "learning_rate": 4.3167851146480445e-06, "loss": 4.1808, "step": 26524 }, { "epoch": 0.8101710445937691, "grad_norm": 0.5007150173187256, "learning_rate": 4.315437706865497e-06, "loss": 4.2271, "step": 26525 }, { "epoch": 0.8102015882712279, "grad_norm": 0.5064306855201721, "learning_rate": 4.314090489536346e-06, "loss": 4.3076, "step": 26526 }, { "epoch": 0.8102321319486866, "grad_norm": 0.5061997175216675, "learning_rate": 4.312743462673008e-06, "loss": 4.3075, "step": 26527 }, { "epoch": 0.8102626756261454, "grad_norm": 0.5344104170799255, "learning_rate": 4.311396626287873e-06, "loss": 4.2637, "step": 26528 }, { "epoch": 0.8102932193036042, "grad_norm": 0.5067076683044434, "learning_rate": 4.310049980393343e-06, "loss": 4.2274, "step": 26529 }, { "epoch": 0.8103237629810629, "grad_norm": 0.5192949175834656, "learning_rate": 4.308703525001828e-06, "loss": 4.2741, "step": 26530 }, { "epoch": 0.8103543066585217, "grad_norm": 0.5172397494316101, "learning_rate": 4.307357260125713e-06, "loss": 4.0279, "step": 26531 }, { "epoch": 0.8103848503359804, "grad_norm": 0.5208736062049866, "learning_rate": 4.306011185777404e-06, "loss": 4.3283, "step": 26532 }, { "epoch": 0.8104153940134392, "grad_norm": 0.51142418384552, "learning_rate": 4.3046653019692825e-06, "loss": 4.3018, "step": 26533 }, { "epoch": 0.810445937690898, "grad_norm": 0.5131887197494507, "learning_rate": 4.303319608713757e-06, "loss": 4.2551, "step": 26534 }, { "epoch": 0.8104764813683567, "grad_norm": 0.5137356519699097, "learning_rate": 4.3019741060232014e-06, "loss": 4.3266, "step": 26535 }, { "epoch": 0.8105070250458155, "grad_norm": 0.5074629783630371, "learning_rate": 4.300628793910016e-06, "loss": 4.255, "step": 26536 }, { "epoch": 0.8105375687232743, "grad_norm": 0.5456635355949402, "learning_rate": 4.299283672386581e-06, "loss": 4.2949, "step": 26537 }, { "epoch": 0.810568112400733, "grad_norm": 0.5146714448928833, "learning_rate": 4.29793874146529e-06, "loss": 4.3414, "step": 26538 }, { "epoch": 0.8105986560781918, "grad_norm": 0.5136258006095886, "learning_rate": 4.296594001158513e-06, "loss": 4.2372, "step": 26539 }, { "epoch": 0.8106291997556506, "grad_norm": 0.5108209252357483, "learning_rate": 4.295249451478642e-06, "loss": 4.2953, "step": 26540 }, { "epoch": 0.8106597434331093, "grad_norm": 0.5172068476676941, "learning_rate": 4.293905092438058e-06, "loss": 4.2949, "step": 26541 }, { "epoch": 0.8106902871105681, "grad_norm": 0.5167880058288574, "learning_rate": 4.2925609240491325e-06, "loss": 4.2462, "step": 26542 }, { "epoch": 0.8107208307880269, "grad_norm": 0.5209549069404602, "learning_rate": 4.291216946324245e-06, "loss": 4.2531, "step": 26543 }, { "epoch": 0.8107513744654856, "grad_norm": 0.5110713243484497, "learning_rate": 4.289873159275776e-06, "loss": 4.2583, "step": 26544 }, { "epoch": 0.8107819181429444, "grad_norm": 0.5138733386993408, "learning_rate": 4.288529562916086e-06, "loss": 4.2351, "step": 26545 }, { "epoch": 0.8108124618204032, "grad_norm": 0.5169470310211182, "learning_rate": 4.287186157257553e-06, "loss": 4.2494, "step": 26546 }, { "epoch": 0.8108430054978619, "grad_norm": 0.5281558036804199, "learning_rate": 4.285842942312554e-06, "loss": 4.2209, "step": 26547 }, { "epoch": 0.8108735491753207, "grad_norm": 0.5086445212364197, "learning_rate": 4.284499918093441e-06, "loss": 4.2243, "step": 26548 }, { "epoch": 0.8109040928527794, "grad_norm": 0.5004574656486511, "learning_rate": 4.283157084612596e-06, "loss": 4.2373, "step": 26549 }, { "epoch": 0.8109346365302382, "grad_norm": 0.5059789419174194, "learning_rate": 4.281814441882367e-06, "loss": 4.2626, "step": 26550 }, { "epoch": 0.810965180207697, "grad_norm": 0.5069054365158081, "learning_rate": 4.280471989915133e-06, "loss": 4.2225, "step": 26551 }, { "epoch": 0.8109957238851557, "grad_norm": 0.5157119631767273, "learning_rate": 4.279129728723247e-06, "loss": 4.2831, "step": 26552 }, { "epoch": 0.8110262675626145, "grad_norm": 0.5138410329818726, "learning_rate": 4.27778765831906e-06, "loss": 4.305, "step": 26553 }, { "epoch": 0.8110568112400733, "grad_norm": 0.5011116862297058, "learning_rate": 4.276445778714936e-06, "loss": 4.2633, "step": 26554 }, { "epoch": 0.811087354917532, "grad_norm": 0.5011466145515442, "learning_rate": 4.275104089923238e-06, "loss": 4.2017, "step": 26555 }, { "epoch": 0.8111178985949908, "grad_norm": 0.5133069157600403, "learning_rate": 4.273762591956304e-06, "loss": 4.1643, "step": 26556 }, { "epoch": 0.8111484422724496, "grad_norm": 0.5108277797698975, "learning_rate": 4.272421284826497e-06, "loss": 4.2813, "step": 26557 }, { "epoch": 0.8111789859499083, "grad_norm": 0.5041320323944092, "learning_rate": 4.271080168546168e-06, "loss": 4.3033, "step": 26558 }, { "epoch": 0.8112095296273671, "grad_norm": 0.49779513478279114, "learning_rate": 4.269739243127657e-06, "loss": 4.1615, "step": 26559 }, { "epoch": 0.811240073304826, "grad_norm": 0.5082481503486633, "learning_rate": 4.268398508583313e-06, "loss": 4.2376, "step": 26560 }, { "epoch": 0.8112706169822846, "grad_norm": 0.5092038512229919, "learning_rate": 4.267057964925492e-06, "loss": 4.2636, "step": 26561 }, { "epoch": 0.8113011606597434, "grad_norm": 0.5399723649024963, "learning_rate": 4.2657176121665195e-06, "loss": 4.2313, "step": 26562 }, { "epoch": 0.8113317043372023, "grad_norm": 0.506101131439209, "learning_rate": 4.264377450318749e-06, "loss": 4.2542, "step": 26563 }, { "epoch": 0.811362248014661, "grad_norm": 0.5050498843193054, "learning_rate": 4.263037479394519e-06, "loss": 4.2407, "step": 26564 }, { "epoch": 0.8113927916921198, "grad_norm": 0.5134888291358948, "learning_rate": 4.261697699406161e-06, "loss": 4.3409, "step": 26565 }, { "epoch": 0.8114233353695784, "grad_norm": 0.5129977464675903, "learning_rate": 4.26035811036602e-06, "loss": 4.2974, "step": 26566 }, { "epoch": 0.8114538790470373, "grad_norm": 0.5049427151679993, "learning_rate": 4.259018712286425e-06, "loss": 4.2651, "step": 26567 }, { "epoch": 0.8114844227244961, "grad_norm": 0.5083494186401367, "learning_rate": 4.257679505179704e-06, "loss": 4.2225, "step": 26568 }, { "epoch": 0.8115149664019548, "grad_norm": 0.51739102602005, "learning_rate": 4.256340489058197e-06, "loss": 4.351, "step": 26569 }, { "epoch": 0.8115455100794136, "grad_norm": 0.5018405318260193, "learning_rate": 4.255001663934222e-06, "loss": 4.2533, "step": 26570 }, { "epoch": 0.8115760537568724, "grad_norm": 0.5035724639892578, "learning_rate": 4.253663029820113e-06, "loss": 4.1966, "step": 26571 }, { "epoch": 0.8116065974343311, "grad_norm": 0.520342230796814, "learning_rate": 4.252324586728201e-06, "loss": 4.1038, "step": 26572 }, { "epoch": 0.8116371411117899, "grad_norm": 0.5191919207572937, "learning_rate": 4.2509863346708e-06, "loss": 4.2539, "step": 26573 }, { "epoch": 0.8116676847892487, "grad_norm": 0.517581045627594, "learning_rate": 4.249648273660234e-06, "loss": 4.3129, "step": 26574 }, { "epoch": 0.8116982284667074, "grad_norm": 0.5128952264785767, "learning_rate": 4.248310403708833e-06, "loss": 4.3184, "step": 26575 }, { "epoch": 0.8117287721441662, "grad_norm": 0.5198490619659424, "learning_rate": 4.246972724828899e-06, "loss": 4.1398, "step": 26576 }, { "epoch": 0.811759315821625, "grad_norm": 0.5097854733467102, "learning_rate": 4.245635237032758e-06, "loss": 4.2081, "step": 26577 }, { "epoch": 0.8117898594990837, "grad_norm": 0.5205259323120117, "learning_rate": 4.244297940332731e-06, "loss": 4.2336, "step": 26578 }, { "epoch": 0.8118204031765425, "grad_norm": 0.5182914733886719, "learning_rate": 4.242960834741119e-06, "loss": 4.2596, "step": 26579 }, { "epoch": 0.8118509468540013, "grad_norm": 0.5171597003936768, "learning_rate": 4.241623920270238e-06, "loss": 4.3072, "step": 26580 }, { "epoch": 0.81188149053146, "grad_norm": 0.513043224811554, "learning_rate": 4.2402871969324024e-06, "loss": 4.2425, "step": 26581 }, { "epoch": 0.8119120342089188, "grad_norm": 0.5033140182495117, "learning_rate": 4.238950664739918e-06, "loss": 4.1833, "step": 26582 }, { "epoch": 0.8119425778863775, "grad_norm": 0.5182359218597412, "learning_rate": 4.237614323705083e-06, "loss": 4.3088, "step": 26583 }, { "epoch": 0.8119731215638363, "grad_norm": 0.5141447186470032, "learning_rate": 4.236278173840216e-06, "loss": 4.2478, "step": 26584 }, { "epoch": 0.8120036652412951, "grad_norm": 0.5138096809387207, "learning_rate": 4.234942215157603e-06, "loss": 4.3184, "step": 26585 }, { "epoch": 0.8120342089187538, "grad_norm": 0.5141370296478271, "learning_rate": 4.233606447669561e-06, "loss": 4.2788, "step": 26586 }, { "epoch": 0.8120647525962126, "grad_norm": 0.5135433077812195, "learning_rate": 4.232270871388375e-06, "loss": 4.2757, "step": 26587 }, { "epoch": 0.8120952962736714, "grad_norm": 0.5087941288948059, "learning_rate": 4.2309354863263455e-06, "loss": 4.2904, "step": 26588 }, { "epoch": 0.8121258399511301, "grad_norm": 0.5139163732528687, "learning_rate": 4.229600292495781e-06, "loss": 4.2839, "step": 26589 }, { "epoch": 0.8121563836285889, "grad_norm": 0.5144854784011841, "learning_rate": 4.228265289908958e-06, "loss": 4.2946, "step": 26590 }, { "epoch": 0.8121869273060477, "grad_norm": 0.5114044547080994, "learning_rate": 4.226930478578178e-06, "loss": 4.2273, "step": 26591 }, { "epoch": 0.8122174709835064, "grad_norm": 0.5155004858970642, "learning_rate": 4.225595858515735e-06, "loss": 4.2389, "step": 26592 }, { "epoch": 0.8122480146609652, "grad_norm": 0.503551721572876, "learning_rate": 4.224261429733906e-06, "loss": 4.2737, "step": 26593 }, { "epoch": 0.812278558338424, "grad_norm": 0.5016354918479919, "learning_rate": 4.2229271922449825e-06, "loss": 4.2327, "step": 26594 }, { "epoch": 0.8123091020158827, "grad_norm": 0.505258321762085, "learning_rate": 4.221593146061259e-06, "loss": 4.0517, "step": 26595 }, { "epoch": 0.8123396456933415, "grad_norm": 0.5013167262077332, "learning_rate": 4.220259291195003e-06, "loss": 4.2871, "step": 26596 }, { "epoch": 0.8123701893708003, "grad_norm": 0.5079953670501709, "learning_rate": 4.21892562765851e-06, "loss": 4.195, "step": 26597 }, { "epoch": 0.812400733048259, "grad_norm": 0.5124481320381165, "learning_rate": 4.2175921554640535e-06, "loss": 4.2629, "step": 26598 }, { "epoch": 0.8124312767257178, "grad_norm": 0.5076354146003723, "learning_rate": 4.2162588746239044e-06, "loss": 4.2597, "step": 26599 }, { "epoch": 0.8124618204031765, "grad_norm": 0.5120406746864319, "learning_rate": 4.214925785150353e-06, "loss": 4.2035, "step": 26600 }, { "epoch": 0.8124923640806353, "grad_norm": 0.5067823529243469, "learning_rate": 4.213592887055659e-06, "loss": 4.1734, "step": 26601 }, { "epoch": 0.8125229077580941, "grad_norm": 0.5231399536132812, "learning_rate": 4.212260180352104e-06, "loss": 4.2846, "step": 26602 }, { "epoch": 0.8125534514355528, "grad_norm": 0.5086603760719299, "learning_rate": 4.210927665051964e-06, "loss": 4.2636, "step": 26603 }, { "epoch": 0.8125839951130116, "grad_norm": 0.5082381963729858, "learning_rate": 4.209595341167493e-06, "loss": 4.2212, "step": 26604 }, { "epoch": 0.8126145387904704, "grad_norm": 0.5220853090286255, "learning_rate": 4.208263208710969e-06, "loss": 4.2435, "step": 26605 }, { "epoch": 0.8126450824679291, "grad_norm": 0.500514030456543, "learning_rate": 4.206931267694664e-06, "loss": 4.1382, "step": 26606 }, { "epoch": 0.8126756261453879, "grad_norm": 0.5131641030311584, "learning_rate": 4.2055995181308236e-06, "loss": 4.2405, "step": 26607 }, { "epoch": 0.8127061698228467, "grad_norm": 0.5087196826934814, "learning_rate": 4.204267960031722e-06, "loss": 4.2274, "step": 26608 }, { "epoch": 0.8127367135003054, "grad_norm": 0.5099329948425293, "learning_rate": 4.2029365934096235e-06, "loss": 4.2843, "step": 26609 }, { "epoch": 0.8127672571777642, "grad_norm": 0.5088294148445129, "learning_rate": 4.201605418276772e-06, "loss": 4.2479, "step": 26610 }, { "epoch": 0.812797800855223, "grad_norm": 0.5108663439750671, "learning_rate": 4.2002744346454345e-06, "loss": 4.2009, "step": 26611 }, { "epoch": 0.8128283445326817, "grad_norm": 0.5118897557258606, "learning_rate": 4.198943642527872e-06, "loss": 4.2942, "step": 26612 }, { "epoch": 0.8128588882101405, "grad_norm": 0.5106804370880127, "learning_rate": 4.197613041936329e-06, "loss": 4.2837, "step": 26613 }, { "epoch": 0.8128894318875992, "grad_norm": 0.5082725286483765, "learning_rate": 4.196282632883053e-06, "loss": 4.1631, "step": 26614 }, { "epoch": 0.812919975565058, "grad_norm": 0.5096566677093506, "learning_rate": 4.194952415380301e-06, "loss": 4.2746, "step": 26615 }, { "epoch": 0.8129505192425168, "grad_norm": 0.5097278952598572, "learning_rate": 4.193622389440319e-06, "loss": 4.1724, "step": 26616 }, { "epoch": 0.8129810629199755, "grad_norm": 0.5110272765159607, "learning_rate": 4.192292555075355e-06, "loss": 4.2263, "step": 26617 }, { "epoch": 0.8130116065974343, "grad_norm": 0.5227630734443665, "learning_rate": 4.190962912297647e-06, "loss": 4.2554, "step": 26618 }, { "epoch": 0.8130421502748931, "grad_norm": 0.5165668725967407, "learning_rate": 4.189633461119444e-06, "loss": 4.3169, "step": 26619 }, { "epoch": 0.8130726939523518, "grad_norm": 0.5080270171165466, "learning_rate": 4.188304201552989e-06, "loss": 4.2651, "step": 26620 }, { "epoch": 0.8131032376298106, "grad_norm": 0.5084660649299622, "learning_rate": 4.186975133610513e-06, "loss": 4.216, "step": 26621 }, { "epoch": 0.8131337813072694, "grad_norm": 0.5398327112197876, "learning_rate": 4.185646257304257e-06, "loss": 4.2268, "step": 26622 }, { "epoch": 0.8131643249847281, "grad_norm": 0.5208584666252136, "learning_rate": 4.184317572646462e-06, "loss": 4.2292, "step": 26623 }, { "epoch": 0.8131948686621869, "grad_norm": 0.5306352972984314, "learning_rate": 4.182989079649354e-06, "loss": 4.265, "step": 26624 }, { "epoch": 0.8132254123396457, "grad_norm": 0.5076165795326233, "learning_rate": 4.181660778325169e-06, "loss": 4.2361, "step": 26625 }, { "epoch": 0.8132559560171044, "grad_norm": 0.5091703534126282, "learning_rate": 4.180332668686143e-06, "loss": 4.33, "step": 26626 }, { "epoch": 0.8132864996945632, "grad_norm": 0.517605185508728, "learning_rate": 4.179004750744492e-06, "loss": 4.2691, "step": 26627 }, { "epoch": 0.813317043372022, "grad_norm": 0.5080813765525818, "learning_rate": 4.177677024512453e-06, "loss": 4.2116, "step": 26628 }, { "epoch": 0.8133475870494807, "grad_norm": 0.5118028521537781, "learning_rate": 4.176349490002243e-06, "loss": 4.2951, "step": 26629 }, { "epoch": 0.8133781307269395, "grad_norm": 0.5010181069374084, "learning_rate": 4.175022147226096e-06, "loss": 4.2508, "step": 26630 }, { "epoch": 0.8134086744043982, "grad_norm": 0.5189031362533569, "learning_rate": 4.173694996196228e-06, "loss": 4.3065, "step": 26631 }, { "epoch": 0.813439218081857, "grad_norm": 0.512181282043457, "learning_rate": 4.1723680369248504e-06, "loss": 4.2547, "step": 26632 }, { "epoch": 0.8134697617593158, "grad_norm": 0.5163279175758362, "learning_rate": 4.171041269424189e-06, "loss": 4.2239, "step": 26633 }, { "epoch": 0.8135003054367745, "grad_norm": 0.5197033882141113, "learning_rate": 4.169714693706467e-06, "loss": 4.34, "step": 26634 }, { "epoch": 0.8135308491142333, "grad_norm": 0.5185473561286926, "learning_rate": 4.168388309783885e-06, "loss": 4.2002, "step": 26635 }, { "epoch": 0.8135613927916922, "grad_norm": 0.5090319514274597, "learning_rate": 4.167062117668663e-06, "loss": 4.2202, "step": 26636 }, { "epoch": 0.8135919364691508, "grad_norm": 0.5157842636108398, "learning_rate": 4.1657361173730175e-06, "loss": 4.2473, "step": 26637 }, { "epoch": 0.8136224801466097, "grad_norm": 0.5214745998382568, "learning_rate": 4.164410308909145e-06, "loss": 4.2834, "step": 26638 }, { "epoch": 0.8136530238240685, "grad_norm": 0.5141980051994324, "learning_rate": 4.16308469228926e-06, "loss": 4.2424, "step": 26639 }, { "epoch": 0.8136835675015271, "grad_norm": 0.5137900114059448, "learning_rate": 4.161759267525572e-06, "loss": 4.2484, "step": 26640 }, { "epoch": 0.813714111178986, "grad_norm": 0.5148286819458008, "learning_rate": 4.160434034630276e-06, "loss": 4.3002, "step": 26641 }, { "epoch": 0.8137446548564448, "grad_norm": 0.5035222768783569, "learning_rate": 4.1591089936155766e-06, "loss": 4.1827, "step": 26642 }, { "epoch": 0.8137751985339035, "grad_norm": 0.5065028667449951, "learning_rate": 4.157784144493682e-06, "loss": 4.3094, "step": 26643 }, { "epoch": 0.8138057422113623, "grad_norm": 0.5233144164085388, "learning_rate": 4.156459487276787e-06, "loss": 4.2951, "step": 26644 }, { "epoch": 0.8138362858888211, "grad_norm": 0.49957045912742615, "learning_rate": 4.155135021977077e-06, "loss": 4.2119, "step": 26645 }, { "epoch": 0.8138668295662798, "grad_norm": 0.5119561553001404, "learning_rate": 4.153810748606765e-06, "loss": 4.2675, "step": 26646 }, { "epoch": 0.8138973732437386, "grad_norm": 0.5143136978149414, "learning_rate": 4.152486667178029e-06, "loss": 4.1139, "step": 26647 }, { "epoch": 0.8139279169211973, "grad_norm": 0.5253949761390686, "learning_rate": 4.151162777703071e-06, "loss": 4.1229, "step": 26648 }, { "epoch": 0.8139584605986561, "grad_norm": 0.5130338072776794, "learning_rate": 4.149839080194074e-06, "loss": 4.248, "step": 26649 }, { "epoch": 0.8139890042761149, "grad_norm": 0.5157113075256348, "learning_rate": 4.148515574663228e-06, "loss": 4.2503, "step": 26650 }, { "epoch": 0.8140195479535736, "grad_norm": 0.4979798495769501, "learning_rate": 4.147192261122723e-06, "loss": 4.2015, "step": 26651 }, { "epoch": 0.8140500916310324, "grad_norm": 0.510229229927063, "learning_rate": 4.145869139584738e-06, "loss": 4.3272, "step": 26652 }, { "epoch": 0.8140806353084912, "grad_norm": 0.5119092464447021, "learning_rate": 4.144546210061456e-06, "loss": 4.2696, "step": 26653 }, { "epoch": 0.8141111789859499, "grad_norm": 0.5208322405815125, "learning_rate": 4.143223472565067e-06, "loss": 4.2598, "step": 26654 }, { "epoch": 0.8141417226634087, "grad_norm": 0.5050727725028992, "learning_rate": 4.141900927107734e-06, "loss": 4.2785, "step": 26655 }, { "epoch": 0.8141722663408675, "grad_norm": 0.5116502046585083, "learning_rate": 4.140578573701645e-06, "loss": 4.2125, "step": 26656 }, { "epoch": 0.8142028100183262, "grad_norm": 0.5094660520553589, "learning_rate": 4.13925641235898e-06, "loss": 4.2375, "step": 26657 }, { "epoch": 0.814233353695785, "grad_norm": 0.5121549367904663, "learning_rate": 4.137934443091901e-06, "loss": 4.228, "step": 26658 }, { "epoch": 0.8142638973732438, "grad_norm": 0.5103076100349426, "learning_rate": 4.1366126659125925e-06, "loss": 4.2397, "step": 26659 }, { "epoch": 0.8142944410507025, "grad_norm": 0.5040779113769531, "learning_rate": 4.135291080833212e-06, "loss": 4.2612, "step": 26660 }, { "epoch": 0.8143249847281613, "grad_norm": 0.5090126395225525, "learning_rate": 4.133969687865941e-06, "loss": 4.1709, "step": 26661 }, { "epoch": 0.8143555284056201, "grad_norm": 0.512392520904541, "learning_rate": 4.13264848702293e-06, "loss": 4.1888, "step": 26662 }, { "epoch": 0.8143860720830788, "grad_norm": 0.5135572552680969, "learning_rate": 4.1313274783163605e-06, "loss": 4.2058, "step": 26663 }, { "epoch": 0.8144166157605376, "grad_norm": 0.5129281282424927, "learning_rate": 4.130006661758384e-06, "loss": 4.2825, "step": 26664 }, { "epoch": 0.8144471594379963, "grad_norm": 0.5072507858276367, "learning_rate": 4.128686037361171e-06, "loss": 4.2961, "step": 26665 }, { "epoch": 0.8144777031154551, "grad_norm": 0.5066205859184265, "learning_rate": 4.1273656051368705e-06, "loss": 4.2656, "step": 26666 }, { "epoch": 0.8145082467929139, "grad_norm": 0.5282188057899475, "learning_rate": 4.12604536509765e-06, "loss": 4.3475, "step": 26667 }, { "epoch": 0.8145387904703726, "grad_norm": 0.5274799466133118, "learning_rate": 4.124725317255665e-06, "loss": 4.197, "step": 26668 }, { "epoch": 0.8145693341478314, "grad_norm": 0.5065462589263916, "learning_rate": 4.123405461623062e-06, "loss": 4.2056, "step": 26669 }, { "epoch": 0.8145998778252902, "grad_norm": 0.5175550580024719, "learning_rate": 4.122085798211997e-06, "loss": 4.1905, "step": 26670 }, { "epoch": 0.8146304215027489, "grad_norm": 0.5100314021110535, "learning_rate": 4.120766327034628e-06, "loss": 4.2967, "step": 26671 }, { "epoch": 0.8146609651802077, "grad_norm": 0.5095317363739014, "learning_rate": 4.119447048103095e-06, "loss": 4.28, "step": 26672 }, { "epoch": 0.8146915088576665, "grad_norm": 0.5173993110656738, "learning_rate": 4.118127961429546e-06, "loss": 4.2837, "step": 26673 }, { "epoch": 0.8147220525351252, "grad_norm": 0.5134795308113098, "learning_rate": 4.1168090670261395e-06, "loss": 4.2612, "step": 26674 }, { "epoch": 0.814752596212584, "grad_norm": 0.5098286867141724, "learning_rate": 4.1154903649050005e-06, "loss": 4.2329, "step": 26675 }, { "epoch": 0.8147831398900428, "grad_norm": 0.5208704471588135, "learning_rate": 4.114171855078283e-06, "loss": 4.2418, "step": 26676 }, { "epoch": 0.8148136835675015, "grad_norm": 0.5040541291236877, "learning_rate": 4.112853537558128e-06, "loss": 4.0694, "step": 26677 }, { "epoch": 0.8148442272449603, "grad_norm": 0.521790623664856, "learning_rate": 4.11153541235666e-06, "loss": 4.2947, "step": 26678 }, { "epoch": 0.8148747709224191, "grad_norm": 0.514051079750061, "learning_rate": 4.110217479486028e-06, "loss": 4.1892, "step": 26679 }, { "epoch": 0.8149053145998778, "grad_norm": 0.5047088265419006, "learning_rate": 4.108899738958369e-06, "loss": 4.2612, "step": 26680 }, { "epoch": 0.8149358582773366, "grad_norm": 0.5128682851791382, "learning_rate": 4.1075821907858054e-06, "loss": 4.2486, "step": 26681 }, { "epoch": 0.8149664019547953, "grad_norm": 0.5050448775291443, "learning_rate": 4.1062648349804805e-06, "loss": 4.2322, "step": 26682 }, { "epoch": 0.8149969456322541, "grad_norm": 0.5129859447479248, "learning_rate": 4.10494767155451e-06, "loss": 4.238, "step": 26683 }, { "epoch": 0.8150274893097129, "grad_norm": 0.508163332939148, "learning_rate": 4.103630700520031e-06, "loss": 4.2956, "step": 26684 }, { "epoch": 0.8150580329871716, "grad_norm": 0.5053358674049377, "learning_rate": 4.102313921889175e-06, "loss": 4.2966, "step": 26685 }, { "epoch": 0.8150885766646304, "grad_norm": 0.5147135853767395, "learning_rate": 4.1009973356740506e-06, "loss": 4.2422, "step": 26686 }, { "epoch": 0.8151191203420892, "grad_norm": 0.5145206451416016, "learning_rate": 4.099680941886791e-06, "loss": 4.2362, "step": 26687 }, { "epoch": 0.8151496640195479, "grad_norm": 0.5117397904396057, "learning_rate": 4.09836474053952e-06, "loss": 4.3013, "step": 26688 }, { "epoch": 0.8151802076970067, "grad_norm": 0.5074101090431213, "learning_rate": 4.097048731644345e-06, "loss": 4.2258, "step": 26689 }, { "epoch": 0.8152107513744655, "grad_norm": 0.5197652578353882, "learning_rate": 4.0957329152133935e-06, "loss": 4.2263, "step": 26690 }, { "epoch": 0.8152412950519242, "grad_norm": 0.5120489597320557, "learning_rate": 4.094417291258779e-06, "loss": 4.2826, "step": 26691 }, { "epoch": 0.815271838729383, "grad_norm": 0.5110423564910889, "learning_rate": 4.093101859792614e-06, "loss": 4.1886, "step": 26692 }, { "epoch": 0.8153023824068418, "grad_norm": 0.5118690729141235, "learning_rate": 4.091786620827001e-06, "loss": 4.2348, "step": 26693 }, { "epoch": 0.8153329260843005, "grad_norm": 0.5197970867156982, "learning_rate": 4.090471574374069e-06, "loss": 4.3322, "step": 26694 }, { "epoch": 0.8153634697617593, "grad_norm": 0.5159637331962585, "learning_rate": 4.089156720445908e-06, "loss": 4.3073, "step": 26695 }, { "epoch": 0.8153940134392181, "grad_norm": 0.5196604132652283, "learning_rate": 4.0878420590546305e-06, "loss": 4.2382, "step": 26696 }, { "epoch": 0.8154245571166768, "grad_norm": 0.5113546252250671, "learning_rate": 4.086527590212352e-06, "loss": 4.2559, "step": 26697 }, { "epoch": 0.8154551007941356, "grad_norm": 0.5052378177642822, "learning_rate": 4.0852133139311575e-06, "loss": 4.2609, "step": 26698 }, { "epoch": 0.8154856444715943, "grad_norm": 0.5094252824783325, "learning_rate": 4.083899230223165e-06, "loss": 4.2326, "step": 26699 }, { "epoch": 0.8155161881490531, "grad_norm": 0.5172905921936035, "learning_rate": 4.0825853391004615e-06, "loss": 4.3002, "step": 26700 }, { "epoch": 0.8155467318265119, "grad_norm": 0.5263187885284424, "learning_rate": 4.081271640575149e-06, "loss": 4.2906, "step": 26701 }, { "epoch": 0.8155772755039706, "grad_norm": 0.5103886723518372, "learning_rate": 4.079958134659329e-06, "loss": 4.3427, "step": 26702 }, { "epoch": 0.8156078191814294, "grad_norm": 0.5190864205360413, "learning_rate": 4.078644821365082e-06, "loss": 4.2992, "step": 26703 }, { "epoch": 0.8156383628588882, "grad_norm": 0.5180233716964722, "learning_rate": 4.077331700704512e-06, "loss": 4.3125, "step": 26704 }, { "epoch": 0.8156689065363469, "grad_norm": 0.5215978622436523, "learning_rate": 4.076018772689713e-06, "loss": 4.2239, "step": 26705 }, { "epoch": 0.8156994502138057, "grad_norm": 0.5191221237182617, "learning_rate": 4.074706037332759e-06, "loss": 4.2314, "step": 26706 }, { "epoch": 0.8157299938912645, "grad_norm": 0.5112354755401611, "learning_rate": 4.073393494645753e-06, "loss": 4.3078, "step": 26707 }, { "epoch": 0.8157605375687232, "grad_norm": 0.5323611497879028, "learning_rate": 4.072081144640772e-06, "loss": 4.2863, "step": 26708 }, { "epoch": 0.815791081246182, "grad_norm": 0.5269733667373657, "learning_rate": 4.070768987329895e-06, "loss": 4.2984, "step": 26709 }, { "epoch": 0.8158216249236409, "grad_norm": 0.5051021575927734, "learning_rate": 4.069457022725207e-06, "loss": 4.2019, "step": 26710 }, { "epoch": 0.8158521686010995, "grad_norm": 0.5117663145065308, "learning_rate": 4.068145250838795e-06, "loss": 4.308, "step": 26711 }, { "epoch": 0.8158827122785584, "grad_norm": 0.4986546039581299, "learning_rate": 4.066833671682727e-06, "loss": 4.2662, "step": 26712 }, { "epoch": 0.8159132559560172, "grad_norm": 0.5088989734649658, "learning_rate": 4.065522285269085e-06, "loss": 4.1653, "step": 26713 }, { "epoch": 0.8159437996334759, "grad_norm": 0.505105197429657, "learning_rate": 4.0642110916099455e-06, "loss": 4.3025, "step": 26714 }, { "epoch": 0.8159743433109347, "grad_norm": 0.5108690857887268, "learning_rate": 4.062900090717376e-06, "loss": 4.3048, "step": 26715 }, { "epoch": 0.8160048869883934, "grad_norm": 0.5106217265129089, "learning_rate": 4.061589282603456e-06, "loss": 4.2733, "step": 26716 }, { "epoch": 0.8160354306658522, "grad_norm": 0.5123521089553833, "learning_rate": 4.06027866728024e-06, "loss": 4.1944, "step": 26717 }, { "epoch": 0.816065974343311, "grad_norm": 0.5116584300994873, "learning_rate": 4.058968244759809e-06, "loss": 4.2666, "step": 26718 }, { "epoch": 0.8160965180207697, "grad_norm": 0.5232813954353333, "learning_rate": 4.057658015054228e-06, "loss": 4.1975, "step": 26719 }, { "epoch": 0.8161270616982285, "grad_norm": 0.5111209154129028, "learning_rate": 4.056347978175548e-06, "loss": 4.2251, "step": 26720 }, { "epoch": 0.8161576053756873, "grad_norm": 0.5019347667694092, "learning_rate": 4.055038134135844e-06, "loss": 4.1737, "step": 26721 }, { "epoch": 0.816188149053146, "grad_norm": 0.5012087821960449, "learning_rate": 4.053728482947178e-06, "loss": 4.2491, "step": 26722 }, { "epoch": 0.8162186927306048, "grad_norm": 0.5216823816299438, "learning_rate": 4.0524190246216035e-06, "loss": 4.2753, "step": 26723 }, { "epoch": 0.8162492364080636, "grad_norm": 0.5095167756080627, "learning_rate": 4.0511097591711705e-06, "loss": 4.2081, "step": 26724 }, { "epoch": 0.8162797800855223, "grad_norm": 0.505334198474884, "learning_rate": 4.049800686607946e-06, "loss": 4.1719, "step": 26725 }, { "epoch": 0.8163103237629811, "grad_norm": 0.5305028557777405, "learning_rate": 4.048491806943975e-06, "loss": 4.3197, "step": 26726 }, { "epoch": 0.8163408674404399, "grad_norm": 0.5051312446594238, "learning_rate": 4.047183120191309e-06, "loss": 4.2001, "step": 26727 }, { "epoch": 0.8163714111178986, "grad_norm": 0.5130263566970825, "learning_rate": 4.045874626362009e-06, "loss": 4.3306, "step": 26728 }, { "epoch": 0.8164019547953574, "grad_norm": 0.5123002529144287, "learning_rate": 4.044566325468108e-06, "loss": 4.1469, "step": 26729 }, { "epoch": 0.8164324984728162, "grad_norm": 0.5152097940444946, "learning_rate": 4.043258217521659e-06, "loss": 4.1858, "step": 26730 }, { "epoch": 0.8164630421502749, "grad_norm": 0.5114421844482422, "learning_rate": 4.041950302534714e-06, "loss": 4.0884, "step": 26731 }, { "epoch": 0.8164935858277337, "grad_norm": 0.5124003291130066, "learning_rate": 4.0406425805193e-06, "loss": 4.2971, "step": 26732 }, { "epoch": 0.8165241295051924, "grad_norm": 0.5187271237373352, "learning_rate": 4.039335051487472e-06, "loss": 4.2104, "step": 26733 }, { "epoch": 0.8165546731826512, "grad_norm": 0.5115519762039185, "learning_rate": 4.038027715451259e-06, "loss": 4.3293, "step": 26734 }, { "epoch": 0.81658521686011, "grad_norm": 0.5112931728363037, "learning_rate": 4.0367205724227e-06, "loss": 4.2474, "step": 26735 }, { "epoch": 0.8166157605375687, "grad_norm": 0.5212411284446716, "learning_rate": 4.035413622413842e-06, "loss": 4.3301, "step": 26736 }, { "epoch": 0.8166463042150275, "grad_norm": 0.5134070515632629, "learning_rate": 4.034106865436701e-06, "loss": 4.233, "step": 26737 }, { "epoch": 0.8166768478924863, "grad_norm": 0.5077490210533142, "learning_rate": 4.0328003015033255e-06, "loss": 4.2457, "step": 26738 }, { "epoch": 0.816707391569945, "grad_norm": 0.5161463618278503, "learning_rate": 4.0314939306257296e-06, "loss": 4.1365, "step": 26739 }, { "epoch": 0.8167379352474038, "grad_norm": 0.5093921422958374, "learning_rate": 4.030187752815959e-06, "loss": 4.2209, "step": 26740 }, { "epoch": 0.8167684789248626, "grad_norm": 0.5139901041984558, "learning_rate": 4.028881768086023e-06, "loss": 4.177, "step": 26741 }, { "epoch": 0.8167990226023213, "grad_norm": 0.5167277455329895, "learning_rate": 4.027575976447961e-06, "loss": 4.2315, "step": 26742 }, { "epoch": 0.8168295662797801, "grad_norm": 0.5268420577049255, "learning_rate": 4.026270377913785e-06, "loss": 4.2593, "step": 26743 }, { "epoch": 0.8168601099572389, "grad_norm": 0.5238678455352783, "learning_rate": 4.024964972495521e-06, "loss": 4.2112, "step": 26744 }, { "epoch": 0.8168906536346976, "grad_norm": 0.5132110714912415, "learning_rate": 4.023659760205195e-06, "loss": 4.1912, "step": 26745 }, { "epoch": 0.8169211973121564, "grad_norm": 0.515879213809967, "learning_rate": 4.022354741054812e-06, "loss": 4.2253, "step": 26746 }, { "epoch": 0.8169517409896152, "grad_norm": 0.5320779085159302, "learning_rate": 4.021049915056394e-06, "loss": 4.1622, "step": 26747 }, { "epoch": 0.8169822846670739, "grad_norm": 0.5137647986412048, "learning_rate": 4.019745282221962e-06, "loss": 4.2073, "step": 26748 }, { "epoch": 0.8170128283445327, "grad_norm": 0.5141134858131409, "learning_rate": 4.0184408425635175e-06, "loss": 4.1648, "step": 26749 }, { "epoch": 0.8170433720219914, "grad_norm": 0.5127884745597839, "learning_rate": 4.01713659609308e-06, "loss": 4.1829, "step": 26750 }, { "epoch": 0.8170739156994502, "grad_norm": 0.5077299475669861, "learning_rate": 4.0158325428226505e-06, "loss": 4.2577, "step": 26751 }, { "epoch": 0.817104459376909, "grad_norm": 0.5064815282821655, "learning_rate": 4.014528682764238e-06, "loss": 4.2513, "step": 26752 }, { "epoch": 0.8171350030543677, "grad_norm": 0.5105260610580444, "learning_rate": 4.013225015929856e-06, "loss": 4.2739, "step": 26753 }, { "epoch": 0.8171655467318265, "grad_norm": 0.505365252494812, "learning_rate": 4.011921542331501e-06, "loss": 4.2474, "step": 26754 }, { "epoch": 0.8171960904092853, "grad_norm": 0.5170316696166992, "learning_rate": 4.010618261981169e-06, "loss": 4.1349, "step": 26755 }, { "epoch": 0.817226634086744, "grad_norm": 0.5080515146255493, "learning_rate": 4.009315174890874e-06, "loss": 4.3156, "step": 26756 }, { "epoch": 0.8172571777642028, "grad_norm": 0.5204246640205383, "learning_rate": 4.008012281072601e-06, "loss": 4.3124, "step": 26757 }, { "epoch": 0.8172877214416616, "grad_norm": 0.516119122505188, "learning_rate": 4.006709580538351e-06, "loss": 4.2355, "step": 26758 }, { "epoch": 0.8173182651191203, "grad_norm": 0.553307294845581, "learning_rate": 4.0054070733001245e-06, "loss": 4.2283, "step": 26759 }, { "epoch": 0.8173488087965791, "grad_norm": 0.5197386741638184, "learning_rate": 4.004104759369903e-06, "loss": 4.2556, "step": 26760 }, { "epoch": 0.8173793524740379, "grad_norm": 0.515500545501709, "learning_rate": 4.0028026387596866e-06, "loss": 4.2502, "step": 26761 }, { "epoch": 0.8174098961514966, "grad_norm": 0.5075567960739136, "learning_rate": 4.001500711481465e-06, "loss": 4.208, "step": 26762 }, { "epoch": 0.8174404398289554, "grad_norm": 0.5277114510536194, "learning_rate": 4.000198977547221e-06, "loss": 4.2636, "step": 26763 }, { "epoch": 0.8174709835064141, "grad_norm": 0.5068972110748291, "learning_rate": 3.998897436968943e-06, "loss": 4.2176, "step": 26764 }, { "epoch": 0.8175015271838729, "grad_norm": 0.5047657489776611, "learning_rate": 3.997596089758612e-06, "loss": 4.1933, "step": 26765 }, { "epoch": 0.8175320708613317, "grad_norm": 0.5124587416648865, "learning_rate": 3.99629493592821e-06, "loss": 4.309, "step": 26766 }, { "epoch": 0.8175626145387904, "grad_norm": 0.5146477222442627, "learning_rate": 3.9949939754897245e-06, "loss": 4.3444, "step": 26767 }, { "epoch": 0.8175931582162492, "grad_norm": 0.5143574476242065, "learning_rate": 3.993693208455126e-06, "loss": 4.2338, "step": 26768 }, { "epoch": 0.817623701893708, "grad_norm": 0.5135514140129089, "learning_rate": 3.9923926348364e-06, "loss": 4.2731, "step": 26769 }, { "epoch": 0.8176542455711667, "grad_norm": 0.5123773217201233, "learning_rate": 3.991092254645509e-06, "loss": 4.3, "step": 26770 }, { "epoch": 0.8176847892486255, "grad_norm": 0.5114405751228333, "learning_rate": 3.989792067894441e-06, "loss": 4.3156, "step": 26771 }, { "epoch": 0.8177153329260843, "grad_norm": 0.5127400755882263, "learning_rate": 3.9884920745951515e-06, "loss": 4.3134, "step": 26772 }, { "epoch": 0.817745876603543, "grad_norm": 0.5095498561859131, "learning_rate": 3.9871922747596245e-06, "loss": 4.2503, "step": 26773 }, { "epoch": 0.8177764202810018, "grad_norm": 0.51431804895401, "learning_rate": 3.9858926683998185e-06, "loss": 4.2535, "step": 26774 }, { "epoch": 0.8178069639584606, "grad_norm": 0.5104228258132935, "learning_rate": 3.9845932555276995e-06, "loss": 4.2646, "step": 26775 }, { "epoch": 0.8178375076359193, "grad_norm": 0.5190010070800781, "learning_rate": 3.983294036155244e-06, "loss": 4.2351, "step": 26776 }, { "epoch": 0.8178680513133781, "grad_norm": 0.5144399404525757, "learning_rate": 3.981995010294398e-06, "loss": 4.191, "step": 26777 }, { "epoch": 0.817898594990837, "grad_norm": 0.5211185216903687, "learning_rate": 3.980696177957133e-06, "loss": 4.3104, "step": 26778 }, { "epoch": 0.8179291386682956, "grad_norm": 0.5054084062576294, "learning_rate": 3.97939753915541e-06, "loss": 4.1955, "step": 26779 }, { "epoch": 0.8179596823457544, "grad_norm": 0.5166770815849304, "learning_rate": 3.978099093901178e-06, "loss": 4.2325, "step": 26780 }, { "epoch": 0.8179902260232131, "grad_norm": 0.5142841935157776, "learning_rate": 3.976800842206399e-06, "loss": 4.2957, "step": 26781 }, { "epoch": 0.818020769700672, "grad_norm": 0.5010937452316284, "learning_rate": 3.975502784083018e-06, "loss": 4.157, "step": 26782 }, { "epoch": 0.8180513133781308, "grad_norm": 0.49993592500686646, "learning_rate": 3.974204919542993e-06, "loss": 4.1953, "step": 26783 }, { "epoch": 0.8180818570555894, "grad_norm": 0.5139613747596741, "learning_rate": 3.9729072485982786e-06, "loss": 4.3094, "step": 26784 }, { "epoch": 0.8181124007330483, "grad_norm": 0.5180090665817261, "learning_rate": 3.971609771260814e-06, "loss": 4.1867, "step": 26785 }, { "epoch": 0.8181429444105071, "grad_norm": 0.5257875323295593, "learning_rate": 3.970312487542554e-06, "loss": 4.2363, "step": 26786 }, { "epoch": 0.8181734880879658, "grad_norm": 0.5063012838363647, "learning_rate": 3.9690153974554414e-06, "loss": 4.2582, "step": 26787 }, { "epoch": 0.8182040317654246, "grad_norm": 0.5178560614585876, "learning_rate": 3.967718501011411e-06, "loss": 4.2612, "step": 26788 }, { "epoch": 0.8182345754428834, "grad_norm": 0.5220862030982971, "learning_rate": 3.966421798222408e-06, "loss": 4.284, "step": 26789 }, { "epoch": 0.818265119120342, "grad_norm": 0.5192540287971497, "learning_rate": 3.965125289100383e-06, "loss": 4.3092, "step": 26790 }, { "epoch": 0.8182956627978009, "grad_norm": 0.5134410858154297, "learning_rate": 3.963828973657258e-06, "loss": 4.3692, "step": 26791 }, { "epoch": 0.8183262064752597, "grad_norm": 0.50501948595047, "learning_rate": 3.962532851904974e-06, "loss": 4.2397, "step": 26792 }, { "epoch": 0.8183567501527184, "grad_norm": 0.5182650089263916, "learning_rate": 3.961236923855472e-06, "loss": 4.3015, "step": 26793 }, { "epoch": 0.8183872938301772, "grad_norm": 0.513271689414978, "learning_rate": 3.959941189520671e-06, "loss": 4.2186, "step": 26794 }, { "epoch": 0.818417837507636, "grad_norm": 0.5135789513587952, "learning_rate": 3.958645648912512e-06, "loss": 4.2629, "step": 26795 }, { "epoch": 0.8184483811850947, "grad_norm": 0.5146118402481079, "learning_rate": 3.957350302042928e-06, "loss": 4.2727, "step": 26796 }, { "epoch": 0.8184789248625535, "grad_norm": 0.5107238292694092, "learning_rate": 3.956055148923831e-06, "loss": 4.1727, "step": 26797 }, { "epoch": 0.8185094685400122, "grad_norm": 0.5319544672966003, "learning_rate": 3.954760189567161e-06, "loss": 4.2885, "step": 26798 }, { "epoch": 0.818540012217471, "grad_norm": 0.5089853405952454, "learning_rate": 3.953465423984828e-06, "loss": 4.2466, "step": 26799 }, { "epoch": 0.8185705558949298, "grad_norm": 0.5108386278152466, "learning_rate": 3.952170852188758e-06, "loss": 4.3393, "step": 26800 }, { "epoch": 0.8186010995723885, "grad_norm": 0.5148922801017761, "learning_rate": 3.950876474190882e-06, "loss": 4.2198, "step": 26801 }, { "epoch": 0.8186316432498473, "grad_norm": 0.5124871134757996, "learning_rate": 3.949582290003106e-06, "loss": 4.2941, "step": 26802 }, { "epoch": 0.8186621869273061, "grad_norm": 0.511116623878479, "learning_rate": 3.948288299637342e-06, "loss": 4.1475, "step": 26803 }, { "epoch": 0.8186927306047648, "grad_norm": 0.5162940621376038, "learning_rate": 3.94699450310552e-06, "loss": 4.1635, "step": 26804 }, { "epoch": 0.8187232742822236, "grad_norm": 0.5120949745178223, "learning_rate": 3.9457009004195384e-06, "loss": 4.3333, "step": 26805 }, { "epoch": 0.8187538179596824, "grad_norm": 0.5075333714485168, "learning_rate": 3.944407491591312e-06, "loss": 4.2799, "step": 26806 }, { "epoch": 0.8187843616371411, "grad_norm": 0.51515793800354, "learning_rate": 3.943114276632759e-06, "loss": 4.2486, "step": 26807 }, { "epoch": 0.8188149053145999, "grad_norm": 0.5054381489753723, "learning_rate": 3.941821255555772e-06, "loss": 4.2576, "step": 26808 }, { "epoch": 0.8188454489920587, "grad_norm": 0.5063759088516235, "learning_rate": 3.940528428372262e-06, "loss": 4.2713, "step": 26809 }, { "epoch": 0.8188759926695174, "grad_norm": 0.5153377056121826, "learning_rate": 3.9392357950941425e-06, "loss": 4.3026, "step": 26810 }, { "epoch": 0.8189065363469762, "grad_norm": 0.5110103487968445, "learning_rate": 3.937943355733303e-06, "loss": 4.2732, "step": 26811 }, { "epoch": 0.818937080024435, "grad_norm": 0.5070550441741943, "learning_rate": 3.936651110301645e-06, "loss": 4.2322, "step": 26812 }, { "epoch": 0.8189676237018937, "grad_norm": 0.5169020891189575, "learning_rate": 3.935359058811078e-06, "loss": 4.2899, "step": 26813 }, { "epoch": 0.8189981673793525, "grad_norm": 0.5143757462501526, "learning_rate": 3.934067201273483e-06, "loss": 4.2992, "step": 26814 }, { "epoch": 0.8190287110568112, "grad_norm": 0.5213654041290283, "learning_rate": 3.932775537700769e-06, "loss": 4.3092, "step": 26815 }, { "epoch": 0.81905925473427, "grad_norm": 0.5212015509605408, "learning_rate": 3.931484068104818e-06, "loss": 4.257, "step": 26816 }, { "epoch": 0.8190897984117288, "grad_norm": 0.5174930095672607, "learning_rate": 3.930192792497528e-06, "loss": 4.2384, "step": 26817 }, { "epoch": 0.8191203420891875, "grad_norm": 0.5133824944496155, "learning_rate": 3.928901710890789e-06, "loss": 4.1147, "step": 26818 }, { "epoch": 0.8191508857666463, "grad_norm": 0.5113807320594788, "learning_rate": 3.92761082329648e-06, "loss": 4.3387, "step": 26819 }, { "epoch": 0.8191814294441051, "grad_norm": 0.5232800245285034, "learning_rate": 3.9263201297264905e-06, "loss": 4.1747, "step": 26820 }, { "epoch": 0.8192119731215638, "grad_norm": 0.5017217993736267, "learning_rate": 3.925029630192712e-06, "loss": 4.2753, "step": 26821 }, { "epoch": 0.8192425167990226, "grad_norm": 0.5047610402107239, "learning_rate": 3.923739324707015e-06, "loss": 4.2153, "step": 26822 }, { "epoch": 0.8192730604764814, "grad_norm": 0.5209649801254272, "learning_rate": 3.92244921328129e-06, "loss": 4.3721, "step": 26823 }, { "epoch": 0.8193036041539401, "grad_norm": 0.5221765041351318, "learning_rate": 3.921159295927415e-06, "loss": 4.3075, "step": 26824 }, { "epoch": 0.8193341478313989, "grad_norm": 0.5217137932777405, "learning_rate": 3.919869572657259e-06, "loss": 4.3457, "step": 26825 }, { "epoch": 0.8193646915088577, "grad_norm": 0.5130830407142639, "learning_rate": 3.918580043482703e-06, "loss": 4.2254, "step": 26826 }, { "epoch": 0.8193952351863164, "grad_norm": 0.5086867809295654, "learning_rate": 3.917290708415625e-06, "loss": 4.2766, "step": 26827 }, { "epoch": 0.8194257788637752, "grad_norm": 0.5300053954124451, "learning_rate": 3.916001567467884e-06, "loss": 4.1718, "step": 26828 }, { "epoch": 0.819456322541234, "grad_norm": 0.5143715739250183, "learning_rate": 3.914712620651359e-06, "loss": 4.1758, "step": 26829 }, { "epoch": 0.8194868662186927, "grad_norm": 0.5070039629936218, "learning_rate": 3.91342386797792e-06, "loss": 4.2408, "step": 26830 }, { "epoch": 0.8195174098961515, "grad_norm": 0.5057529211044312, "learning_rate": 3.9121353094594225e-06, "loss": 4.1709, "step": 26831 }, { "epoch": 0.8195479535736102, "grad_norm": 0.5092191100120544, "learning_rate": 3.910846945107746e-06, "loss": 4.2579, "step": 26832 }, { "epoch": 0.819578497251069, "grad_norm": 0.5268328189849854, "learning_rate": 3.909558774934744e-06, "loss": 4.0586, "step": 26833 }, { "epoch": 0.8196090409285278, "grad_norm": 0.509554922580719, "learning_rate": 3.908270798952271e-06, "loss": 4.2273, "step": 26834 }, { "epoch": 0.8196395846059865, "grad_norm": 0.5185906291007996, "learning_rate": 3.906983017172197e-06, "loss": 4.193, "step": 26835 }, { "epoch": 0.8196701282834453, "grad_norm": 0.5067502856254578, "learning_rate": 3.905695429606374e-06, "loss": 4.2763, "step": 26836 }, { "epoch": 0.8197006719609041, "grad_norm": 0.507716178894043, "learning_rate": 3.904408036266655e-06, "loss": 4.2571, "step": 26837 }, { "epoch": 0.8197312156383628, "grad_norm": 0.5189154148101807, "learning_rate": 3.9031208371649055e-06, "loss": 4.2957, "step": 26838 }, { "epoch": 0.8197617593158216, "grad_norm": 0.5018414855003357, "learning_rate": 3.901833832312962e-06, "loss": 4.132, "step": 26839 }, { "epoch": 0.8197923029932804, "grad_norm": 0.5271931290626526, "learning_rate": 3.900547021722684e-06, "loss": 4.2761, "step": 26840 }, { "epoch": 0.8198228466707391, "grad_norm": 0.5113943815231323, "learning_rate": 3.899260405405921e-06, "loss": 4.2569, "step": 26841 }, { "epoch": 0.8198533903481979, "grad_norm": 0.5150453448295593, "learning_rate": 3.897973983374515e-06, "loss": 4.2738, "step": 26842 }, { "epoch": 0.8198839340256567, "grad_norm": 0.5098899006843567, "learning_rate": 3.896687755640308e-06, "loss": 4.216, "step": 26843 }, { "epoch": 0.8199144777031154, "grad_norm": 0.5172078609466553, "learning_rate": 3.895401722215153e-06, "loss": 4.3395, "step": 26844 }, { "epoch": 0.8199450213805742, "grad_norm": 0.5145512223243713, "learning_rate": 3.894115883110882e-06, "loss": 4.2297, "step": 26845 }, { "epoch": 0.819975565058033, "grad_norm": 0.5314691066741943, "learning_rate": 3.8928302383393375e-06, "loss": 4.1201, "step": 26846 }, { "epoch": 0.8200061087354917, "grad_norm": 0.5210084319114685, "learning_rate": 3.89154478791236e-06, "loss": 4.2432, "step": 26847 }, { "epoch": 0.8200366524129505, "grad_norm": 0.5180568099021912, "learning_rate": 3.8902595318417836e-06, "loss": 4.364, "step": 26848 }, { "epoch": 0.8200671960904092, "grad_norm": 0.5061709880828857, "learning_rate": 3.888974470139436e-06, "loss": 4.2247, "step": 26849 }, { "epoch": 0.820097739767868, "grad_norm": 0.520538330078125, "learning_rate": 3.887689602817163e-06, "loss": 4.1638, "step": 26850 }, { "epoch": 0.8201282834453268, "grad_norm": 0.5127109885215759, "learning_rate": 3.886404929886778e-06, "loss": 4.2399, "step": 26851 }, { "epoch": 0.8201588271227855, "grad_norm": 0.5207796096801758, "learning_rate": 3.8851204513601246e-06, "loss": 4.3077, "step": 26852 }, { "epoch": 0.8201893708002443, "grad_norm": 0.5079475045204163, "learning_rate": 3.883836167249016e-06, "loss": 4.2955, "step": 26853 }, { "epoch": 0.8202199144777031, "grad_norm": 0.5209510922431946, "learning_rate": 3.882552077565288e-06, "loss": 4.3019, "step": 26854 }, { "epoch": 0.8202504581551618, "grad_norm": 0.5211213231086731, "learning_rate": 3.881268182320763e-06, "loss": 4.2772, "step": 26855 }, { "epoch": 0.8202810018326206, "grad_norm": 0.5244266986846924, "learning_rate": 3.879984481527258e-06, "loss": 4.2578, "step": 26856 }, { "epoch": 0.8203115455100795, "grad_norm": 0.5192564129829407, "learning_rate": 3.878700975196592e-06, "loss": 4.2548, "step": 26857 }, { "epoch": 0.8203420891875381, "grad_norm": 0.5214663743972778, "learning_rate": 3.877417663340591e-06, "loss": 4.2451, "step": 26858 }, { "epoch": 0.820372632864997, "grad_norm": 0.5191038846969604, "learning_rate": 3.876134545971061e-06, "loss": 4.2563, "step": 26859 }, { "epoch": 0.8204031765424558, "grad_norm": 0.514581561088562, "learning_rate": 3.874851623099821e-06, "loss": 4.3047, "step": 26860 }, { "epoch": 0.8204337202199145, "grad_norm": 0.5287381410598755, "learning_rate": 3.873568894738691e-06, "loss": 4.2494, "step": 26861 }, { "epoch": 0.8204642638973733, "grad_norm": 0.519461989402771, "learning_rate": 3.872286360899466e-06, "loss": 4.2668, "step": 26862 }, { "epoch": 0.8204948075748321, "grad_norm": 0.5268833637237549, "learning_rate": 3.871004021593972e-06, "loss": 4.3297, "step": 26863 }, { "epoch": 0.8205253512522908, "grad_norm": 0.5239618420600891, "learning_rate": 3.869721876834004e-06, "loss": 4.2463, "step": 26864 }, { "epoch": 0.8205558949297496, "grad_norm": 0.5144235491752625, "learning_rate": 3.868439926631368e-06, "loss": 4.2461, "step": 26865 }, { "epoch": 0.8205864386072083, "grad_norm": 0.5163370966911316, "learning_rate": 3.867158170997873e-06, "loss": 4.1791, "step": 26866 }, { "epoch": 0.8206169822846671, "grad_norm": 0.5212745070457458, "learning_rate": 3.865876609945312e-06, "loss": 4.3129, "step": 26867 }, { "epoch": 0.8206475259621259, "grad_norm": 0.5184438228607178, "learning_rate": 3.864595243485494e-06, "loss": 4.2029, "step": 26868 }, { "epoch": 0.8206780696395846, "grad_norm": 0.5273308157920837, "learning_rate": 3.8633140716302194e-06, "loss": 4.1389, "step": 26869 }, { "epoch": 0.8207086133170434, "grad_norm": 0.5250038504600525, "learning_rate": 3.862033094391274e-06, "loss": 4.158, "step": 26870 }, { "epoch": 0.8207391569945022, "grad_norm": 0.5906999111175537, "learning_rate": 3.860752311780458e-06, "loss": 4.1693, "step": 26871 }, { "epoch": 0.8207697006719609, "grad_norm": 0.5174599289894104, "learning_rate": 3.859471723809569e-06, "loss": 4.2902, "step": 26872 }, { "epoch": 0.8208002443494197, "grad_norm": 0.5128732919692993, "learning_rate": 3.8581913304903875e-06, "loss": 4.3734, "step": 26873 }, { "epoch": 0.8208307880268785, "grad_norm": 0.5179375410079956, "learning_rate": 3.856911131834709e-06, "loss": 4.2846, "step": 26874 }, { "epoch": 0.8208613317043372, "grad_norm": 0.5138686299324036, "learning_rate": 3.855631127854326e-06, "loss": 4.319, "step": 26875 }, { "epoch": 0.820891875381796, "grad_norm": 0.5212234258651733, "learning_rate": 3.854351318561014e-06, "loss": 4.2655, "step": 26876 }, { "epoch": 0.8209224190592548, "grad_norm": 0.5044896006584167, "learning_rate": 3.853071703966559e-06, "loss": 4.2964, "step": 26877 }, { "epoch": 0.8209529627367135, "grad_norm": 0.5148908495903015, "learning_rate": 3.851792284082753e-06, "loss": 4.2172, "step": 26878 }, { "epoch": 0.8209835064141723, "grad_norm": 0.5157005190849304, "learning_rate": 3.850513058921368e-06, "loss": 4.1196, "step": 26879 }, { "epoch": 0.8210140500916311, "grad_norm": 0.5155482292175293, "learning_rate": 3.849234028494178e-06, "loss": 4.3505, "step": 26880 }, { "epoch": 0.8210445937690898, "grad_norm": 0.5185734629631042, "learning_rate": 3.8479551928129716e-06, "loss": 4.1182, "step": 26881 }, { "epoch": 0.8210751374465486, "grad_norm": 0.5128143429756165, "learning_rate": 3.846676551889511e-06, "loss": 4.2531, "step": 26882 }, { "epoch": 0.8211056811240073, "grad_norm": 0.5289955735206604, "learning_rate": 3.8453981057355785e-06, "loss": 4.1994, "step": 26883 }, { "epoch": 0.8211362248014661, "grad_norm": 0.5002834796905518, "learning_rate": 3.8441198543629405e-06, "loss": 4.2345, "step": 26884 }, { "epoch": 0.8211667684789249, "grad_norm": 0.5168660283088684, "learning_rate": 3.842841797783364e-06, "loss": 4.1801, "step": 26885 }, { "epoch": 0.8211973121563836, "grad_norm": 0.5217836499214172, "learning_rate": 3.84156393600863e-06, "loss": 4.1687, "step": 26886 }, { "epoch": 0.8212278558338424, "grad_norm": 0.5082864761352539, "learning_rate": 3.840286269050489e-06, "loss": 4.3128, "step": 26887 }, { "epoch": 0.8212583995113012, "grad_norm": 0.512384831905365, "learning_rate": 3.83900879692071e-06, "loss": 4.3306, "step": 26888 }, { "epoch": 0.8212889431887599, "grad_norm": 0.5166139602661133, "learning_rate": 3.8377315196310635e-06, "loss": 4.2712, "step": 26889 }, { "epoch": 0.8213194868662187, "grad_norm": 0.5279572606086731, "learning_rate": 3.836454437193299e-06, "loss": 4.3649, "step": 26890 }, { "epoch": 0.8213500305436775, "grad_norm": 0.5439587831497192, "learning_rate": 3.8351775496191785e-06, "loss": 4.2856, "step": 26891 }, { "epoch": 0.8213805742211362, "grad_norm": 0.5298242568969727, "learning_rate": 3.833900856920467e-06, "loss": 4.2131, "step": 26892 }, { "epoch": 0.821411117898595, "grad_norm": 0.5089830160140991, "learning_rate": 3.832624359108905e-06, "loss": 4.0827, "step": 26893 }, { "epoch": 0.8214416615760538, "grad_norm": 0.5175626873970032, "learning_rate": 3.83134805619626e-06, "loss": 4.3435, "step": 26894 }, { "epoch": 0.8214722052535125, "grad_norm": 0.5237915515899658, "learning_rate": 3.830071948194272e-06, "loss": 4.2804, "step": 26895 }, { "epoch": 0.8215027489309713, "grad_norm": 0.5144072771072388, "learning_rate": 3.828796035114704e-06, "loss": 4.1007, "step": 26896 }, { "epoch": 0.8215332926084301, "grad_norm": 0.5120814442634583, "learning_rate": 3.827520316969288e-06, "loss": 4.2412, "step": 26897 }, { "epoch": 0.8215638362858888, "grad_norm": 0.5237574577331543, "learning_rate": 3.8262447937697845e-06, "loss": 4.3036, "step": 26898 }, { "epoch": 0.8215943799633476, "grad_norm": 0.5118467211723328, "learning_rate": 3.824969465527925e-06, "loss": 4.2392, "step": 26899 }, { "epoch": 0.8216249236408063, "grad_norm": 0.5199813842773438, "learning_rate": 3.823694332255465e-06, "loss": 4.2444, "step": 26900 }, { "epoch": 0.8216554673182651, "grad_norm": 0.507075309753418, "learning_rate": 3.822419393964136e-06, "loss": 4.2371, "step": 26901 }, { "epoch": 0.8216860109957239, "grad_norm": 0.5167623162269592, "learning_rate": 3.821144650665675e-06, "loss": 4.2802, "step": 26902 }, { "epoch": 0.8217165546731826, "grad_norm": 0.5114424824714661, "learning_rate": 3.819870102371834e-06, "loss": 4.2704, "step": 26903 }, { "epoch": 0.8217470983506414, "grad_norm": 0.5274495482444763, "learning_rate": 3.8185957490943306e-06, "loss": 4.1934, "step": 26904 }, { "epoch": 0.8217776420281002, "grad_norm": 0.5243099927902222, "learning_rate": 3.817321590844908e-06, "loss": 4.2491, "step": 26905 }, { "epoch": 0.8218081857055589, "grad_norm": 0.5106531977653503, "learning_rate": 3.816047627635302e-06, "loss": 4.2306, "step": 26906 }, { "epoch": 0.8218387293830177, "grad_norm": 0.5169731378555298, "learning_rate": 3.814773859477233e-06, "loss": 4.242, "step": 26907 }, { "epoch": 0.8218692730604765, "grad_norm": 0.5117142200469971, "learning_rate": 3.8135002863824294e-06, "loss": 4.2126, "step": 26908 }, { "epoch": 0.8218998167379352, "grad_norm": 0.5165237784385681, "learning_rate": 3.8122269083626316e-06, "loss": 4.2761, "step": 26909 }, { "epoch": 0.821930360415394, "grad_norm": 0.5277606844902039, "learning_rate": 3.8109537254295475e-06, "loss": 4.2375, "step": 26910 }, { "epoch": 0.8219609040928528, "grad_norm": 0.5147795677185059, "learning_rate": 3.809680737594912e-06, "loss": 4.2313, "step": 26911 }, { "epoch": 0.8219914477703115, "grad_norm": 0.5344505906105042, "learning_rate": 3.80840794487044e-06, "loss": 4.2457, "step": 26912 }, { "epoch": 0.8220219914477703, "grad_norm": 0.5204110741615295, "learning_rate": 3.8071353472678457e-06, "loss": 4.2923, "step": 26913 }, { "epoch": 0.822052535125229, "grad_norm": 0.5187944769859314, "learning_rate": 3.80586294479886e-06, "loss": 4.2137, "step": 26914 }, { "epoch": 0.8220830788026878, "grad_norm": 0.5168003439903259, "learning_rate": 3.804590737475183e-06, "loss": 4.2859, "step": 26915 }, { "epoch": 0.8221136224801466, "grad_norm": 0.5125711560249329, "learning_rate": 3.803318725308541e-06, "loss": 4.3438, "step": 26916 }, { "epoch": 0.8221441661576053, "grad_norm": 0.5231514573097229, "learning_rate": 3.8020469083106443e-06, "loss": 4.2599, "step": 26917 }, { "epoch": 0.8221747098350641, "grad_norm": 0.5155528783798218, "learning_rate": 3.800775286493194e-06, "loss": 4.2511, "step": 26918 }, { "epoch": 0.8222052535125229, "grad_norm": 0.5237703919410706, "learning_rate": 3.799503859867909e-06, "loss": 4.1442, "step": 26919 }, { "epoch": 0.8222357971899816, "grad_norm": 0.5308732986450195, "learning_rate": 3.7982326284464936e-06, "loss": 4.1637, "step": 26920 }, { "epoch": 0.8222663408674404, "grad_norm": 0.523159384727478, "learning_rate": 3.796961592240647e-06, "loss": 4.1843, "step": 26921 }, { "epoch": 0.8222968845448992, "grad_norm": 0.511146068572998, "learning_rate": 3.795690751262079e-06, "loss": 4.2401, "step": 26922 }, { "epoch": 0.8223274282223579, "grad_norm": 0.5147857666015625, "learning_rate": 3.794420105522492e-06, "loss": 4.244, "step": 26923 }, { "epoch": 0.8223579718998167, "grad_norm": 0.5123663544654846, "learning_rate": 3.793149655033576e-06, "loss": 4.3672, "step": 26924 }, { "epoch": 0.8223885155772755, "grad_norm": 0.5162217617034912, "learning_rate": 3.791879399807041e-06, "loss": 4.2928, "step": 26925 }, { "epoch": 0.8224190592547342, "grad_norm": 0.5127853751182556, "learning_rate": 3.79060933985457e-06, "loss": 4.2822, "step": 26926 }, { "epoch": 0.822449602932193, "grad_norm": 0.5099231600761414, "learning_rate": 3.78933947518787e-06, "loss": 4.215, "step": 26927 }, { "epoch": 0.8224801466096519, "grad_norm": 0.5058813095092773, "learning_rate": 3.78806980581862e-06, "loss": 4.2259, "step": 26928 }, { "epoch": 0.8225106902871105, "grad_norm": 0.5173808336257935, "learning_rate": 3.7868003317585247e-06, "loss": 4.1936, "step": 26929 }, { "epoch": 0.8225412339645694, "grad_norm": 0.5095087289810181, "learning_rate": 3.785531053019259e-06, "loss": 4.2141, "step": 26930 }, { "epoch": 0.822571777642028, "grad_norm": 0.5183113217353821, "learning_rate": 3.7842619696125238e-06, "loss": 4.1329, "step": 26931 }, { "epoch": 0.8226023213194869, "grad_norm": 0.5234844088554382, "learning_rate": 3.7829930815499876e-06, "loss": 4.316, "step": 26932 }, { "epoch": 0.8226328649969457, "grad_norm": 0.5171345472335815, "learning_rate": 3.7817243888433442e-06, "loss": 4.2374, "step": 26933 }, { "epoch": 0.8226634086744044, "grad_norm": 0.5092455148696899, "learning_rate": 3.780455891504281e-06, "loss": 4.2657, "step": 26934 }, { "epoch": 0.8226939523518632, "grad_norm": 0.5143428444862366, "learning_rate": 3.779187589544464e-06, "loss": 4.2302, "step": 26935 }, { "epoch": 0.822724496029322, "grad_norm": 0.511615514755249, "learning_rate": 3.7779194829755753e-06, "loss": 4.2872, "step": 26936 }, { "epoch": 0.8227550397067807, "grad_norm": 0.5224612355232239, "learning_rate": 3.7766515718093006e-06, "loss": 4.1914, "step": 26937 }, { "epoch": 0.8227855833842395, "grad_norm": 0.5180742740631104, "learning_rate": 3.775383856057302e-06, "loss": 4.3568, "step": 26938 }, { "epoch": 0.8228161270616983, "grad_norm": 0.5214342474937439, "learning_rate": 3.7741163357312563e-06, "loss": 4.3609, "step": 26939 }, { "epoch": 0.822846670739157, "grad_norm": 0.5167776942253113, "learning_rate": 3.7728490108428412e-06, "loss": 4.2381, "step": 26940 }, { "epoch": 0.8228772144166158, "grad_norm": 0.5271548628807068, "learning_rate": 3.77158188140371e-06, "loss": 4.2724, "step": 26941 }, { "epoch": 0.8229077580940746, "grad_norm": 0.5128822326660156, "learning_rate": 3.7703149474255488e-06, "loss": 4.2867, "step": 26942 }, { "epoch": 0.8229383017715333, "grad_norm": 0.5163521766662598, "learning_rate": 3.769048208920012e-06, "loss": 4.2629, "step": 26943 }, { "epoch": 0.8229688454489921, "grad_norm": 0.518500804901123, "learning_rate": 3.767781665898756e-06, "loss": 4.2978, "step": 26944 }, { "epoch": 0.8229993891264509, "grad_norm": 0.5214426517486572, "learning_rate": 3.7665153183734536e-06, "loss": 4.2362, "step": 26945 }, { "epoch": 0.8230299328039096, "grad_norm": 0.5253978967666626, "learning_rate": 3.7652491663557663e-06, "loss": 4.3651, "step": 26946 }, { "epoch": 0.8230604764813684, "grad_norm": 0.5140535235404968, "learning_rate": 3.763983209857344e-06, "loss": 4.2699, "step": 26947 }, { "epoch": 0.8230910201588271, "grad_norm": 0.5063416957855225, "learning_rate": 3.7627174488898494e-06, "loss": 4.1622, "step": 26948 }, { "epoch": 0.8231215638362859, "grad_norm": 0.5251699090003967, "learning_rate": 3.761451883464931e-06, "loss": 4.289, "step": 26949 }, { "epoch": 0.8231521075137447, "grad_norm": 0.5118324756622314, "learning_rate": 3.7601865135942437e-06, "loss": 4.1943, "step": 26950 }, { "epoch": 0.8231826511912034, "grad_norm": 0.5193928480148315, "learning_rate": 3.7589213392894453e-06, "loss": 4.2108, "step": 26951 }, { "epoch": 0.8232131948686622, "grad_norm": 0.5207298994064331, "learning_rate": 3.7576563605621755e-06, "loss": 4.3056, "step": 26952 }, { "epoch": 0.823243738546121, "grad_norm": 0.5077539682388306, "learning_rate": 3.7563915774240814e-06, "loss": 4.2837, "step": 26953 }, { "epoch": 0.8232742822235797, "grad_norm": 0.5152943730354309, "learning_rate": 3.755126989886823e-06, "loss": 4.2055, "step": 26954 }, { "epoch": 0.8233048259010385, "grad_norm": 0.5156954526901245, "learning_rate": 3.753862597962024e-06, "loss": 4.2971, "step": 26955 }, { "epoch": 0.8233353695784973, "grad_norm": 0.5069894790649414, "learning_rate": 3.7525984016613365e-06, "loss": 4.1436, "step": 26956 }, { "epoch": 0.823365913255956, "grad_norm": 0.5165656805038452, "learning_rate": 3.751334400996406e-06, "loss": 4.113, "step": 26957 }, { "epoch": 0.8233964569334148, "grad_norm": 0.5153194665908813, "learning_rate": 3.750070595978866e-06, "loss": 4.3152, "step": 26958 }, { "epoch": 0.8234270006108736, "grad_norm": 0.5193097591400146, "learning_rate": 3.748806986620343e-06, "loss": 4.2963, "step": 26959 }, { "epoch": 0.8234575442883323, "grad_norm": 0.5091028213500977, "learning_rate": 3.747543572932488e-06, "loss": 4.1718, "step": 26960 }, { "epoch": 0.8234880879657911, "grad_norm": 0.5176295042037964, "learning_rate": 3.7462803549269206e-06, "loss": 4.1969, "step": 26961 }, { "epoch": 0.8235186316432499, "grad_norm": 0.5131046772003174, "learning_rate": 3.7450173326152774e-06, "loss": 4.2391, "step": 26962 }, { "epoch": 0.8235491753207086, "grad_norm": 0.514726996421814, "learning_rate": 3.7437545060091924e-06, "loss": 4.3339, "step": 26963 }, { "epoch": 0.8235797189981674, "grad_norm": 0.5112354755401611, "learning_rate": 3.7424918751202855e-06, "loss": 4.1994, "step": 26964 }, { "epoch": 0.8236102626756261, "grad_norm": 0.5067444443702698, "learning_rate": 3.7412294399601864e-06, "loss": 4.1809, "step": 26965 }, { "epoch": 0.8236408063530849, "grad_norm": 0.5215620398521423, "learning_rate": 3.7399672005405174e-06, "loss": 4.2883, "step": 26966 }, { "epoch": 0.8236713500305437, "grad_norm": 0.5286732912063599, "learning_rate": 3.7387051568728987e-06, "loss": 4.2633, "step": 26967 }, { "epoch": 0.8237018937080024, "grad_norm": 0.5201115608215332, "learning_rate": 3.7374433089689574e-06, "loss": 4.1472, "step": 26968 }, { "epoch": 0.8237324373854612, "grad_norm": 0.5149109363555908, "learning_rate": 3.736181656840304e-06, "loss": 4.27, "step": 26969 }, { "epoch": 0.82376298106292, "grad_norm": 0.5151001811027527, "learning_rate": 3.7349202004985594e-06, "loss": 4.2653, "step": 26970 }, { "epoch": 0.8237935247403787, "grad_norm": 0.5156072378158569, "learning_rate": 3.7336589399553424e-06, "loss": 4.1955, "step": 26971 }, { "epoch": 0.8238240684178375, "grad_norm": 0.5177525877952576, "learning_rate": 3.7323978752222573e-06, "loss": 4.0875, "step": 26972 }, { "epoch": 0.8238546120952963, "grad_norm": 0.5246430039405823, "learning_rate": 3.7311370063109254e-06, "loss": 4.3207, "step": 26973 }, { "epoch": 0.823885155772755, "grad_norm": 0.514268159866333, "learning_rate": 3.7298763332329485e-06, "loss": 4.2965, "step": 26974 }, { "epoch": 0.8239156994502138, "grad_norm": 0.5158438086509705, "learning_rate": 3.728615855999931e-06, "loss": 4.3138, "step": 26975 }, { "epoch": 0.8239462431276726, "grad_norm": 0.5306569337844849, "learning_rate": 3.727355574623484e-06, "loss": 4.1837, "step": 26976 }, { "epoch": 0.8239767868051313, "grad_norm": 0.5205339789390564, "learning_rate": 3.7260954891152196e-06, "loss": 4.1942, "step": 26977 }, { "epoch": 0.8240073304825901, "grad_norm": 0.5290195941925049, "learning_rate": 3.724835599486723e-06, "loss": 4.3206, "step": 26978 }, { "epoch": 0.8240378741600489, "grad_norm": 0.5142123699188232, "learning_rate": 3.7235759057496046e-06, "loss": 4.2428, "step": 26979 }, { "epoch": 0.8240684178375076, "grad_norm": 0.5188470482826233, "learning_rate": 3.722316407915469e-06, "loss": 4.3297, "step": 26980 }, { "epoch": 0.8240989615149664, "grad_norm": 0.5114272832870483, "learning_rate": 3.721057105995901e-06, "loss": 4.2229, "step": 26981 }, { "epoch": 0.8241295051924251, "grad_norm": 0.5087364912033081, "learning_rate": 3.719798000002503e-06, "loss": 4.1861, "step": 26982 }, { "epoch": 0.8241600488698839, "grad_norm": 0.519163966178894, "learning_rate": 3.7185390899468624e-06, "loss": 4.2966, "step": 26983 }, { "epoch": 0.8241905925473427, "grad_norm": 0.5250780582427979, "learning_rate": 3.717280375840576e-06, "loss": 4.1931, "step": 26984 }, { "epoch": 0.8242211362248014, "grad_norm": 0.526134192943573, "learning_rate": 3.7160218576952345e-06, "loss": 4.2671, "step": 26985 }, { "epoch": 0.8242516799022602, "grad_norm": 0.5057029724121094, "learning_rate": 3.71476353552242e-06, "loss": 4.2621, "step": 26986 }, { "epoch": 0.824282223579719, "grad_norm": 0.5148968696594238, "learning_rate": 3.7135054093337176e-06, "loss": 4.2392, "step": 26987 }, { "epoch": 0.8243127672571777, "grad_norm": 0.5250880122184753, "learning_rate": 3.7122474791407237e-06, "loss": 4.3131, "step": 26988 }, { "epoch": 0.8243433109346365, "grad_norm": 0.5127683281898499, "learning_rate": 3.7109897449550125e-06, "loss": 4.2318, "step": 26989 }, { "epoch": 0.8243738546120953, "grad_norm": 0.5204471945762634, "learning_rate": 3.7097322067881578e-06, "loss": 4.2899, "step": 26990 }, { "epoch": 0.824404398289554, "grad_norm": 0.5228097438812256, "learning_rate": 3.708474864651751e-06, "loss": 4.2499, "step": 26991 }, { "epoch": 0.8244349419670128, "grad_norm": 0.5162155628204346, "learning_rate": 3.707217718557357e-06, "loss": 4.1764, "step": 26992 }, { "epoch": 0.8244654856444716, "grad_norm": 0.5090057253837585, "learning_rate": 3.7059607685165585e-06, "loss": 4.2778, "step": 26993 }, { "epoch": 0.8244960293219303, "grad_norm": 0.5169192552566528, "learning_rate": 3.704704014540933e-06, "loss": 4.2639, "step": 26994 }, { "epoch": 0.8245265729993891, "grad_norm": 0.5204024314880371, "learning_rate": 3.7034474566420397e-06, "loss": 4.282, "step": 26995 }, { "epoch": 0.824557116676848, "grad_norm": 0.5203313827514648, "learning_rate": 3.702191094831456e-06, "loss": 4.2122, "step": 26996 }, { "epoch": 0.8245876603543066, "grad_norm": 0.5244329571723938, "learning_rate": 3.700934929120753e-06, "loss": 4.2393, "step": 26997 }, { "epoch": 0.8246182040317654, "grad_norm": 0.5201360583305359, "learning_rate": 3.699678959521491e-06, "loss": 4.2819, "step": 26998 }, { "epoch": 0.8246487477092241, "grad_norm": 0.523410439491272, "learning_rate": 3.6984231860452384e-06, "loss": 4.3128, "step": 26999 }, { "epoch": 0.8246792913866829, "grad_norm": 0.5224142670631409, "learning_rate": 3.697167608703553e-06, "loss": 4.2842, "step": 27000 }, { "epoch": 0.8247098350641417, "grad_norm": 0.5161523222923279, "learning_rate": 3.695912227507997e-06, "loss": 4.2604, "step": 27001 }, { "epoch": 0.8247403787416004, "grad_norm": 0.5106552839279175, "learning_rate": 3.6946570424701344e-06, "loss": 4.2254, "step": 27002 }, { "epoch": 0.8247709224190592, "grad_norm": 0.5134937763214111, "learning_rate": 3.6934020536015164e-06, "loss": 4.222, "step": 27003 }, { "epoch": 0.824801466096518, "grad_norm": 0.5151110291481018, "learning_rate": 3.692147260913703e-06, "loss": 4.2303, "step": 27004 }, { "epoch": 0.8248320097739767, "grad_norm": 0.5166007280349731, "learning_rate": 3.6908926644182413e-06, "loss": 4.2433, "step": 27005 }, { "epoch": 0.8248625534514356, "grad_norm": 0.5361452102661133, "learning_rate": 3.689638264126691e-06, "loss": 4.1739, "step": 27006 }, { "epoch": 0.8248930971288944, "grad_norm": 0.5171798467636108, "learning_rate": 3.6883840600505953e-06, "loss": 4.1492, "step": 27007 }, { "epoch": 0.824923640806353, "grad_norm": 0.5085719227790833, "learning_rate": 3.6871300522015066e-06, "loss": 4.0201, "step": 27008 }, { "epoch": 0.8249541844838119, "grad_norm": 0.5179634094238281, "learning_rate": 3.685876240590966e-06, "loss": 4.2546, "step": 27009 }, { "epoch": 0.8249847281612707, "grad_norm": 0.5229610204696655, "learning_rate": 3.6846226252305218e-06, "loss": 4.3303, "step": 27010 }, { "epoch": 0.8250152718387294, "grad_norm": 0.5231561660766602, "learning_rate": 3.683369206131723e-06, "loss": 4.1992, "step": 27011 }, { "epoch": 0.8250458155161882, "grad_norm": 0.523104190826416, "learning_rate": 3.6821159833060948e-06, "loss": 4.3021, "step": 27012 }, { "epoch": 0.825076359193647, "grad_norm": 0.5264303684234619, "learning_rate": 3.680862956765188e-06, "loss": 4.2756, "step": 27013 }, { "epoch": 0.8251069028711057, "grad_norm": 0.5139498710632324, "learning_rate": 3.679610126520541e-06, "loss": 4.2326, "step": 27014 }, { "epoch": 0.8251374465485645, "grad_norm": 0.5110592246055603, "learning_rate": 3.6783574925836813e-06, "loss": 4.0848, "step": 27015 }, { "epoch": 0.8251679902260232, "grad_norm": 0.5417124032974243, "learning_rate": 3.677105054966154e-06, "loss": 4.3862, "step": 27016 }, { "epoch": 0.825198533903482, "grad_norm": 0.5112292766571045, "learning_rate": 3.6758528136794755e-06, "loss": 4.2558, "step": 27017 }, { "epoch": 0.8252290775809408, "grad_norm": 0.520439624786377, "learning_rate": 3.674600768735184e-06, "loss": 4.2365, "step": 27018 }, { "epoch": 0.8252596212583995, "grad_norm": 0.5285243391990662, "learning_rate": 3.6733489201448118e-06, "loss": 4.1914, "step": 27019 }, { "epoch": 0.8252901649358583, "grad_norm": 0.5108596086502075, "learning_rate": 3.6720972679198772e-06, "loss": 4.2312, "step": 27020 }, { "epoch": 0.8253207086133171, "grad_norm": 0.5185489654541016, "learning_rate": 3.670845812071916e-06, "loss": 4.265, "step": 27021 }, { "epoch": 0.8253512522907758, "grad_norm": 0.513891875743866, "learning_rate": 3.669594552612443e-06, "loss": 4.2232, "step": 27022 }, { "epoch": 0.8253817959682346, "grad_norm": 0.516645073890686, "learning_rate": 3.668343489552972e-06, "loss": 4.2287, "step": 27023 }, { "epoch": 0.8254123396456934, "grad_norm": 0.5259003639221191, "learning_rate": 3.667092622905033e-06, "loss": 4.2446, "step": 27024 }, { "epoch": 0.8254428833231521, "grad_norm": 0.5218417644500732, "learning_rate": 3.6658419526801436e-06, "loss": 4.1348, "step": 27025 }, { "epoch": 0.8254734270006109, "grad_norm": 0.5131126046180725, "learning_rate": 3.6645914788898117e-06, "loss": 4.2545, "step": 27026 }, { "epoch": 0.8255039706780697, "grad_norm": 0.5183165669441223, "learning_rate": 3.663341201545556e-06, "loss": 4.2636, "step": 27027 }, { "epoch": 0.8255345143555284, "grad_norm": 0.5086237788200378, "learning_rate": 3.6620911206588947e-06, "loss": 4.2287, "step": 27028 }, { "epoch": 0.8255650580329872, "grad_norm": 0.5227437615394592, "learning_rate": 3.6608412362413246e-06, "loss": 4.2985, "step": 27029 }, { "epoch": 0.825595601710446, "grad_norm": 0.5221162438392639, "learning_rate": 3.6595915483043613e-06, "loss": 4.2389, "step": 27030 }, { "epoch": 0.8256261453879047, "grad_norm": 0.514885663986206, "learning_rate": 3.658342056859515e-06, "loss": 4.1832, "step": 27031 }, { "epoch": 0.8256566890653635, "grad_norm": 0.5165203809738159, "learning_rate": 3.657092761918282e-06, "loss": 4.2869, "step": 27032 }, { "epoch": 0.8256872327428222, "grad_norm": 0.5235357880592346, "learning_rate": 3.6558436634921756e-06, "loss": 4.2321, "step": 27033 }, { "epoch": 0.825717776420281, "grad_norm": 0.5244979858398438, "learning_rate": 3.6545947615926834e-06, "loss": 4.0645, "step": 27034 }, { "epoch": 0.8257483200977398, "grad_norm": 0.5164155960083008, "learning_rate": 3.653346056231316e-06, "loss": 4.2868, "step": 27035 }, { "epoch": 0.8257788637751985, "grad_norm": 0.5090646743774414, "learning_rate": 3.652097547419564e-06, "loss": 4.201, "step": 27036 }, { "epoch": 0.8258094074526573, "grad_norm": 0.5147533416748047, "learning_rate": 3.650849235168932e-06, "loss": 4.2913, "step": 27037 }, { "epoch": 0.8258399511301161, "grad_norm": 0.5247508883476257, "learning_rate": 3.6496011194909e-06, "loss": 4.2754, "step": 27038 }, { "epoch": 0.8258704948075748, "grad_norm": 0.5201461911201477, "learning_rate": 3.6483532003969757e-06, "loss": 4.2091, "step": 27039 }, { "epoch": 0.8259010384850336, "grad_norm": 0.5197369456291199, "learning_rate": 3.6471054778986326e-06, "loss": 4.2419, "step": 27040 }, { "epoch": 0.8259315821624924, "grad_norm": 0.5195742249488831, "learning_rate": 3.64585795200737e-06, "loss": 4.2338, "step": 27041 }, { "epoch": 0.8259621258399511, "grad_norm": 0.5023184418678284, "learning_rate": 3.6446106227346787e-06, "loss": 4.1573, "step": 27042 }, { "epoch": 0.8259926695174099, "grad_norm": 0.5218999981880188, "learning_rate": 3.6433634900920306e-06, "loss": 4.2574, "step": 27043 }, { "epoch": 0.8260232131948687, "grad_norm": 0.5134264230728149, "learning_rate": 3.642116554090913e-06, "loss": 4.1675, "step": 27044 }, { "epoch": 0.8260537568723274, "grad_norm": 0.5174772143363953, "learning_rate": 3.64086981474282e-06, "loss": 4.3022, "step": 27045 }, { "epoch": 0.8260843005497862, "grad_norm": 0.516006350517273, "learning_rate": 3.6396232720592114e-06, "loss": 4.3144, "step": 27046 }, { "epoch": 0.826114844227245, "grad_norm": 0.5132851600646973, "learning_rate": 3.6383769260515734e-06, "loss": 4.1038, "step": 27047 }, { "epoch": 0.8261453879047037, "grad_norm": 0.5298725962638855, "learning_rate": 3.63713077673139e-06, "loss": 4.2988, "step": 27048 }, { "epoch": 0.8261759315821625, "grad_norm": 0.5159995555877686, "learning_rate": 3.6358848241101196e-06, "loss": 4.2627, "step": 27049 }, { "epoch": 0.8262064752596212, "grad_norm": 0.5247719883918762, "learning_rate": 3.63463906819925e-06, "loss": 4.2434, "step": 27050 }, { "epoch": 0.82623701893708, "grad_norm": 0.5239090919494629, "learning_rate": 3.6333935090102354e-06, "loss": 4.2711, "step": 27051 }, { "epoch": 0.8262675626145388, "grad_norm": 0.5175654888153076, "learning_rate": 3.632148146554559e-06, "loss": 4.1645, "step": 27052 }, { "epoch": 0.8262981062919975, "grad_norm": 0.5045316815376282, "learning_rate": 3.6309029808436813e-06, "loss": 4.1841, "step": 27053 }, { "epoch": 0.8263286499694563, "grad_norm": 0.5199565291404724, "learning_rate": 3.6296580118890614e-06, "loss": 4.2267, "step": 27054 }, { "epoch": 0.8263591936469151, "grad_norm": 0.5172978043556213, "learning_rate": 3.6284132397021663e-06, "loss": 4.2429, "step": 27055 }, { "epoch": 0.8263897373243738, "grad_norm": 0.5202601552009583, "learning_rate": 3.6271686642944642e-06, "loss": 4.1836, "step": 27056 }, { "epoch": 0.8264202810018326, "grad_norm": 0.5154701471328735, "learning_rate": 3.6259242856774038e-06, "loss": 4.1988, "step": 27057 }, { "epoch": 0.8264508246792914, "grad_norm": 0.5132851004600525, "learning_rate": 3.624680103862449e-06, "loss": 4.2931, "step": 27058 }, { "epoch": 0.8264813683567501, "grad_norm": 0.5134190320968628, "learning_rate": 3.6234361188610592e-06, "loss": 4.2871, "step": 27059 }, { "epoch": 0.8265119120342089, "grad_norm": 0.5105116367340088, "learning_rate": 3.622192330684679e-06, "loss": 4.2616, "step": 27060 }, { "epoch": 0.8265424557116677, "grad_norm": 0.5177317261695862, "learning_rate": 3.620948739344765e-06, "loss": 4.2451, "step": 27061 }, { "epoch": 0.8265729993891264, "grad_norm": 0.5229635238647461, "learning_rate": 3.619705344852775e-06, "loss": 4.2308, "step": 27062 }, { "epoch": 0.8266035430665852, "grad_norm": 0.510501503944397, "learning_rate": 3.618462147220142e-06, "loss": 4.1487, "step": 27063 }, { "epoch": 0.8266340867440439, "grad_norm": 0.5281028747558594, "learning_rate": 3.6172191464583283e-06, "loss": 4.3428, "step": 27064 }, { "epoch": 0.8266646304215027, "grad_norm": 0.517598569393158, "learning_rate": 3.6159763425787667e-06, "loss": 4.221, "step": 27065 }, { "epoch": 0.8266951740989615, "grad_norm": 0.5127164125442505, "learning_rate": 3.614733735592904e-06, "loss": 4.2032, "step": 27066 }, { "epoch": 0.8267257177764202, "grad_norm": 0.5232509970664978, "learning_rate": 3.6134913255121915e-06, "loss": 4.2321, "step": 27067 }, { "epoch": 0.826756261453879, "grad_norm": 0.5135456323623657, "learning_rate": 3.6122491123480566e-06, "loss": 4.3112, "step": 27068 }, { "epoch": 0.8267868051313378, "grad_norm": 0.5183190107345581, "learning_rate": 3.6110070961119372e-06, "loss": 4.3403, "step": 27069 }, { "epoch": 0.8268173488087965, "grad_norm": 0.5189636945724487, "learning_rate": 3.60976527681528e-06, "loss": 4.1428, "step": 27070 }, { "epoch": 0.8268478924862553, "grad_norm": 0.5212761163711548, "learning_rate": 3.6085236544695035e-06, "loss": 4.1835, "step": 27071 }, { "epoch": 0.8268784361637141, "grad_norm": 0.525288999080658, "learning_rate": 3.607282229086048e-06, "loss": 4.2448, "step": 27072 }, { "epoch": 0.8269089798411728, "grad_norm": 0.5157827734947205, "learning_rate": 3.6060410006763494e-06, "loss": 4.128, "step": 27073 }, { "epoch": 0.8269395235186316, "grad_norm": 0.5330657362937927, "learning_rate": 3.6047999692518263e-06, "loss": 4.201, "step": 27074 }, { "epoch": 0.8269700671960905, "grad_norm": 0.5102701187133789, "learning_rate": 3.6035591348239114e-06, "loss": 4.2462, "step": 27075 }, { "epoch": 0.8270006108735491, "grad_norm": 0.5052616596221924, "learning_rate": 3.6023184974040337e-06, "loss": 4.2242, "step": 27076 }, { "epoch": 0.827031154551008, "grad_norm": 0.5114020705223083, "learning_rate": 3.601078057003604e-06, "loss": 4.2831, "step": 27077 }, { "epoch": 0.8270616982284668, "grad_norm": 0.5101133584976196, "learning_rate": 3.599837813634052e-06, "loss": 4.2537, "step": 27078 }, { "epoch": 0.8270922419059255, "grad_norm": 0.526486337184906, "learning_rate": 3.5985977673067994e-06, "loss": 4.3344, "step": 27079 }, { "epoch": 0.8271227855833843, "grad_norm": 0.5152745842933655, "learning_rate": 3.597357918033259e-06, "loss": 4.2431, "step": 27080 }, { "epoch": 0.827153329260843, "grad_norm": 0.5288645029067993, "learning_rate": 3.596118265824852e-06, "loss": 4.0025, "step": 27081 }, { "epoch": 0.8271838729383018, "grad_norm": 0.5066139101982117, "learning_rate": 3.594878810692981e-06, "loss": 4.2301, "step": 27082 }, { "epoch": 0.8272144166157606, "grad_norm": 0.50884610414505, "learning_rate": 3.593639552649075e-06, "loss": 4.2055, "step": 27083 }, { "epoch": 0.8272449602932193, "grad_norm": 0.5193528532981873, "learning_rate": 3.592400491704534e-06, "loss": 4.2954, "step": 27084 }, { "epoch": 0.8272755039706781, "grad_norm": 0.5117691159248352, "learning_rate": 3.591161627870765e-06, "loss": 4.2819, "step": 27085 }, { "epoch": 0.8273060476481369, "grad_norm": 0.5063450932502747, "learning_rate": 3.5899229611591756e-06, "loss": 4.2005, "step": 27086 }, { "epoch": 0.8273365913255956, "grad_norm": 0.5312691330909729, "learning_rate": 3.5886844915811817e-06, "loss": 4.2688, "step": 27087 }, { "epoch": 0.8273671350030544, "grad_norm": 0.5235485434532166, "learning_rate": 3.5874462191481717e-06, "loss": 4.2953, "step": 27088 }, { "epoch": 0.8273976786805132, "grad_norm": 0.5198565125465393, "learning_rate": 3.586208143871553e-06, "loss": 4.2383, "step": 27089 }, { "epoch": 0.8274282223579719, "grad_norm": 0.520665168762207, "learning_rate": 3.58497026576273e-06, "loss": 4.3104, "step": 27090 }, { "epoch": 0.8274587660354307, "grad_norm": 0.5188652873039246, "learning_rate": 3.583732584833094e-06, "loss": 4.2828, "step": 27091 }, { "epoch": 0.8274893097128895, "grad_norm": 0.5125453472137451, "learning_rate": 3.582495101094041e-06, "loss": 4.2062, "step": 27092 }, { "epoch": 0.8275198533903482, "grad_norm": 0.5153718590736389, "learning_rate": 3.5812578145569737e-06, "loss": 4.2601, "step": 27093 }, { "epoch": 0.827550397067807, "grad_norm": 0.5269548892974854, "learning_rate": 3.5800207252332713e-06, "loss": 4.3033, "step": 27094 }, { "epoch": 0.8275809407452658, "grad_norm": 0.5207512974739075, "learning_rate": 3.578783833134333e-06, "loss": 4.2877, "step": 27095 }, { "epoch": 0.8276114844227245, "grad_norm": 0.5204352736473083, "learning_rate": 3.5775471382715504e-06, "loss": 4.2429, "step": 27096 }, { "epoch": 0.8276420281001833, "grad_norm": 0.5211683511734009, "learning_rate": 3.5763106406562998e-06, "loss": 4.2138, "step": 27097 }, { "epoch": 0.827672571777642, "grad_norm": 0.5040959119796753, "learning_rate": 3.5750743402999775e-06, "loss": 4.283, "step": 27098 }, { "epoch": 0.8277031154551008, "grad_norm": 0.5183928608894348, "learning_rate": 3.573838237213961e-06, "loss": 4.2592, "step": 27099 }, { "epoch": 0.8277336591325596, "grad_norm": 0.5071162581443787, "learning_rate": 3.5726023314096272e-06, "loss": 4.2539, "step": 27100 }, { "epoch": 0.8277642028100183, "grad_norm": 0.515450119972229, "learning_rate": 3.571366622898367e-06, "loss": 4.2043, "step": 27101 }, { "epoch": 0.8277947464874771, "grad_norm": 0.5302026867866516, "learning_rate": 3.5701311116915463e-06, "loss": 4.2775, "step": 27102 }, { "epoch": 0.8278252901649359, "grad_norm": 0.5231992602348328, "learning_rate": 3.568895797800545e-06, "loss": 4.378, "step": 27103 }, { "epoch": 0.8278558338423946, "grad_norm": 0.5089848637580872, "learning_rate": 3.5676606812367454e-06, "loss": 4.234, "step": 27104 }, { "epoch": 0.8278863775198534, "grad_norm": 0.5199156403541565, "learning_rate": 3.5664257620115077e-06, "loss": 4.3361, "step": 27105 }, { "epoch": 0.8279169211973122, "grad_norm": 0.5137585997581482, "learning_rate": 3.565191040136209e-06, "loss": 4.2579, "step": 27106 }, { "epoch": 0.8279474648747709, "grad_norm": 0.5230370759963989, "learning_rate": 3.5639565156222215e-06, "loss": 4.3462, "step": 27107 }, { "epoch": 0.8279780085522297, "grad_norm": 0.5128672122955322, "learning_rate": 3.562722188480902e-06, "loss": 4.2211, "step": 27108 }, { "epoch": 0.8280085522296885, "grad_norm": 0.5194436311721802, "learning_rate": 3.561488058723622e-06, "loss": 4.2413, "step": 27109 }, { "epoch": 0.8280390959071472, "grad_norm": 0.5283065438270569, "learning_rate": 3.5602541263617477e-06, "loss": 4.226, "step": 27110 }, { "epoch": 0.828069639584606, "grad_norm": 0.5256876945495605, "learning_rate": 3.559020391406634e-06, "loss": 4.3626, "step": 27111 }, { "epoch": 0.8281001832620648, "grad_norm": 0.5157943367958069, "learning_rate": 3.557786853869641e-06, "loss": 4.1694, "step": 27112 }, { "epoch": 0.8281307269395235, "grad_norm": 0.5184507966041565, "learning_rate": 3.556553513762137e-06, "loss": 4.2225, "step": 27113 }, { "epoch": 0.8281612706169823, "grad_norm": 0.5178449749946594, "learning_rate": 3.555320371095469e-06, "loss": 4.1708, "step": 27114 }, { "epoch": 0.828191814294441, "grad_norm": 0.5212231874465942, "learning_rate": 3.5540874258809863e-06, "loss": 4.1981, "step": 27115 }, { "epoch": 0.8282223579718998, "grad_norm": 0.5279015898704529, "learning_rate": 3.552854678130052e-06, "loss": 4.3798, "step": 27116 }, { "epoch": 0.8282529016493586, "grad_norm": 0.5315384268760681, "learning_rate": 3.551622127854007e-06, "loss": 4.2625, "step": 27117 }, { "epoch": 0.8282834453268173, "grad_norm": 0.5179693102836609, "learning_rate": 3.5503897750642083e-06, "loss": 4.2396, "step": 27118 }, { "epoch": 0.8283139890042761, "grad_norm": 0.5164383053779602, "learning_rate": 3.549157619771995e-06, "loss": 4.2567, "step": 27119 }, { "epoch": 0.8283445326817349, "grad_norm": 0.5188227891921997, "learning_rate": 3.5479256619887184e-06, "loss": 4.0737, "step": 27120 }, { "epoch": 0.8283750763591936, "grad_norm": 0.522078275680542, "learning_rate": 3.5466939017257227e-06, "loss": 4.3332, "step": 27121 }, { "epoch": 0.8284056200366524, "grad_norm": 0.519722044467926, "learning_rate": 3.545462338994343e-06, "loss": 4.1505, "step": 27122 }, { "epoch": 0.8284361637141112, "grad_norm": 0.5336379408836365, "learning_rate": 3.5442309738059204e-06, "loss": 4.2803, "step": 27123 }, { "epoch": 0.8284667073915699, "grad_norm": 0.5190594792366028, "learning_rate": 3.5429998061718013e-06, "loss": 4.2726, "step": 27124 }, { "epoch": 0.8284972510690287, "grad_norm": 0.5201122760772705, "learning_rate": 3.54176883610331e-06, "loss": 4.1461, "step": 27125 }, { "epoch": 0.8285277947464875, "grad_norm": 0.5155718326568604, "learning_rate": 3.540538063611784e-06, "loss": 4.2782, "step": 27126 }, { "epoch": 0.8285583384239462, "grad_norm": 0.505034863948822, "learning_rate": 3.5393074887085653e-06, "loss": 4.1842, "step": 27127 }, { "epoch": 0.828588882101405, "grad_norm": 0.5288826823234558, "learning_rate": 3.538077111404969e-06, "loss": 4.2308, "step": 27128 }, { "epoch": 0.8286194257788638, "grad_norm": 0.5266300439834595, "learning_rate": 3.536846931712337e-06, "loss": 4.3174, "step": 27129 }, { "epoch": 0.8286499694563225, "grad_norm": 0.5209817290306091, "learning_rate": 3.535616949641987e-06, "loss": 4.1653, "step": 27130 }, { "epoch": 0.8286805131337813, "grad_norm": 0.5223767161369324, "learning_rate": 3.5343871652052495e-06, "loss": 4.2444, "step": 27131 }, { "epoch": 0.82871105681124, "grad_norm": 0.52518630027771, "learning_rate": 3.5331575784134486e-06, "loss": 4.2019, "step": 27132 }, { "epoch": 0.8287416004886988, "grad_norm": 0.5322864055633545, "learning_rate": 3.531928189277897e-06, "loss": 4.3023, "step": 27133 }, { "epoch": 0.8287721441661576, "grad_norm": 0.5166540145874023, "learning_rate": 3.5306989978099227e-06, "loss": 4.1394, "step": 27134 }, { "epoch": 0.8288026878436163, "grad_norm": 0.5124260187149048, "learning_rate": 3.5294700040208432e-06, "loss": 4.1434, "step": 27135 }, { "epoch": 0.8288332315210751, "grad_norm": 0.5121431946754456, "learning_rate": 3.5282412079219674e-06, "loss": 4.2438, "step": 27136 }, { "epoch": 0.8288637751985339, "grad_norm": 0.513818085193634, "learning_rate": 3.527012609524616e-06, "loss": 4.1359, "step": 27137 }, { "epoch": 0.8288943188759926, "grad_norm": 0.5259261727333069, "learning_rate": 3.525784208840105e-06, "loss": 4.2489, "step": 27138 }, { "epoch": 0.8289248625534514, "grad_norm": 0.5222840905189514, "learning_rate": 3.524556005879734e-06, "loss": 4.1054, "step": 27139 }, { "epoch": 0.8289554062309102, "grad_norm": 0.5143033266067505, "learning_rate": 3.523328000654816e-06, "loss": 4.2426, "step": 27140 }, { "epoch": 0.8289859499083689, "grad_norm": 0.5233211517333984, "learning_rate": 3.522100193176667e-06, "loss": 4.2437, "step": 27141 }, { "epoch": 0.8290164935858277, "grad_norm": 0.5166222453117371, "learning_rate": 3.5208725834565777e-06, "loss": 4.2888, "step": 27142 }, { "epoch": 0.8290470372632865, "grad_norm": 0.5226908922195435, "learning_rate": 3.519645171505859e-06, "loss": 4.2092, "step": 27143 }, { "epoch": 0.8290775809407452, "grad_norm": 0.5230981707572937, "learning_rate": 3.518417957335815e-06, "loss": 4.3058, "step": 27144 }, { "epoch": 0.829108124618204, "grad_norm": 0.5218015909194946, "learning_rate": 3.517190940957743e-06, "loss": 4.2939, "step": 27145 }, { "epoch": 0.8291386682956629, "grad_norm": 0.5175791382789612, "learning_rate": 3.515964122382934e-06, "loss": 4.2539, "step": 27146 }, { "epoch": 0.8291692119731215, "grad_norm": 0.5250207781791687, "learning_rate": 3.5147375016226946e-06, "loss": 4.2714, "step": 27147 }, { "epoch": 0.8291997556505804, "grad_norm": 0.525180459022522, "learning_rate": 3.513511078688306e-06, "loss": 4.1802, "step": 27148 }, { "epoch": 0.829230299328039, "grad_norm": 0.5263708233833313, "learning_rate": 3.512284853591077e-06, "loss": 4.2221, "step": 27149 }, { "epoch": 0.8292608430054978, "grad_norm": 0.5278252959251404, "learning_rate": 3.511058826342281e-06, "loss": 4.3634, "step": 27150 }, { "epoch": 0.8292913866829567, "grad_norm": 0.5217106938362122, "learning_rate": 3.5098329969532162e-06, "loss": 4.313, "step": 27151 }, { "epoch": 0.8293219303604153, "grad_norm": 0.5172218680381775, "learning_rate": 3.508607365435174e-06, "loss": 4.3043, "step": 27152 }, { "epoch": 0.8293524740378742, "grad_norm": 0.5255950093269348, "learning_rate": 3.507381931799428e-06, "loss": 4.1195, "step": 27153 }, { "epoch": 0.829383017715333, "grad_norm": 0.5160309672355652, "learning_rate": 3.5061566960572667e-06, "loss": 4.2682, "step": 27154 }, { "epoch": 0.8294135613927917, "grad_norm": 0.5144042372703552, "learning_rate": 3.504931658219976e-06, "loss": 4.2733, "step": 27155 }, { "epoch": 0.8294441050702505, "grad_norm": 0.5135857462882996, "learning_rate": 3.503706818298827e-06, "loss": 4.0961, "step": 27156 }, { "epoch": 0.8294746487477093, "grad_norm": 0.5164952874183655, "learning_rate": 3.5024821763051026e-06, "loss": 4.2897, "step": 27157 }, { "epoch": 0.829505192425168, "grad_norm": 0.514595091342926, "learning_rate": 3.501257732250082e-06, "loss": 4.2098, "step": 27158 }, { "epoch": 0.8295357361026268, "grad_norm": 0.5181030035018921, "learning_rate": 3.5000334861450295e-06, "loss": 4.2658, "step": 27159 }, { "epoch": 0.8295662797800856, "grad_norm": 0.5200554132461548, "learning_rate": 3.49880943800123e-06, "loss": 4.2268, "step": 27160 }, { "epoch": 0.8295968234575443, "grad_norm": 0.516872227191925, "learning_rate": 3.497585587829938e-06, "loss": 4.2254, "step": 27161 }, { "epoch": 0.8296273671350031, "grad_norm": 0.520995557308197, "learning_rate": 3.496361935642439e-06, "loss": 4.2759, "step": 27162 }, { "epoch": 0.8296579108124619, "grad_norm": 0.5135115385055542, "learning_rate": 3.495138481449986e-06, "loss": 4.2403, "step": 27163 }, { "epoch": 0.8296884544899206, "grad_norm": 0.5157291889190674, "learning_rate": 3.493915225263855e-06, "loss": 4.2206, "step": 27164 }, { "epoch": 0.8297189981673794, "grad_norm": 0.5207358002662659, "learning_rate": 3.492692167095296e-06, "loss": 4.2548, "step": 27165 }, { "epoch": 0.8297495418448381, "grad_norm": 0.5152044296264648, "learning_rate": 3.491469306955586e-06, "loss": 4.2749, "step": 27166 }, { "epoch": 0.8297800855222969, "grad_norm": 0.5201117992401123, "learning_rate": 3.490246644855971e-06, "loss": 4.2761, "step": 27167 }, { "epoch": 0.8298106291997557, "grad_norm": 0.508485734462738, "learning_rate": 3.489024180807715e-06, "loss": 4.2857, "step": 27168 }, { "epoch": 0.8298411728772144, "grad_norm": 0.5187520384788513, "learning_rate": 3.487801914822078e-06, "loss": 4.2139, "step": 27169 }, { "epoch": 0.8298717165546732, "grad_norm": 0.523170530796051, "learning_rate": 3.486579846910304e-06, "loss": 4.2563, "step": 27170 }, { "epoch": 0.829902260232132, "grad_norm": 0.5123530626296997, "learning_rate": 3.4853579770836505e-06, "loss": 4.2872, "step": 27171 }, { "epoch": 0.8299328039095907, "grad_norm": 0.5280125737190247, "learning_rate": 3.484136305353372e-06, "loss": 4.3431, "step": 27172 }, { "epoch": 0.8299633475870495, "grad_norm": 0.5184436440467834, "learning_rate": 3.48291483173071e-06, "loss": 4.2667, "step": 27173 }, { "epoch": 0.8299938912645083, "grad_norm": 0.5239182710647583, "learning_rate": 3.4816935562269116e-06, "loss": 4.2972, "step": 27174 }, { "epoch": 0.830024434941967, "grad_norm": 0.5109221935272217, "learning_rate": 3.4804724788532306e-06, "loss": 4.1493, "step": 27175 }, { "epoch": 0.8300549786194258, "grad_norm": 0.529473066329956, "learning_rate": 3.4792515996209003e-06, "loss": 4.3029, "step": 27176 }, { "epoch": 0.8300855222968846, "grad_norm": 0.5312463641166687, "learning_rate": 3.478030918541167e-06, "loss": 4.294, "step": 27177 }, { "epoch": 0.8301160659743433, "grad_norm": 0.5123356580734253, "learning_rate": 3.476810435625272e-06, "loss": 4.2331, "step": 27178 }, { "epoch": 0.8301466096518021, "grad_norm": 0.5183026790618896, "learning_rate": 3.475590150884442e-06, "loss": 4.1448, "step": 27179 }, { "epoch": 0.8301771533292609, "grad_norm": 0.5128403902053833, "learning_rate": 3.474370064329921e-06, "loss": 4.3166, "step": 27180 }, { "epoch": 0.8302076970067196, "grad_norm": 0.522344172000885, "learning_rate": 3.473150175972947e-06, "loss": 4.2908, "step": 27181 }, { "epoch": 0.8302382406841784, "grad_norm": 0.524253249168396, "learning_rate": 3.4719304858247425e-06, "loss": 4.2626, "step": 27182 }, { "epoch": 0.8302687843616371, "grad_norm": 0.5196768641471863, "learning_rate": 3.4707109938965476e-06, "loss": 4.28, "step": 27183 }, { "epoch": 0.8302993280390959, "grad_norm": 0.5186429619789124, "learning_rate": 3.4694917001995812e-06, "loss": 4.2672, "step": 27184 }, { "epoch": 0.8303298717165547, "grad_norm": 0.5157769322395325, "learning_rate": 3.4682726047450735e-06, "loss": 4.282, "step": 27185 }, { "epoch": 0.8303604153940134, "grad_norm": 0.5235504508018494, "learning_rate": 3.4670537075442573e-06, "loss": 4.272, "step": 27186 }, { "epoch": 0.8303909590714722, "grad_norm": 0.5087651610374451, "learning_rate": 3.4658350086083423e-06, "loss": 4.2682, "step": 27187 }, { "epoch": 0.830421502748931, "grad_norm": 0.523418128490448, "learning_rate": 3.4646165079485567e-06, "loss": 4.2567, "step": 27188 }, { "epoch": 0.8304520464263897, "grad_norm": 0.5198652148246765, "learning_rate": 3.4633982055761238e-06, "loss": 4.2199, "step": 27189 }, { "epoch": 0.8304825901038485, "grad_norm": 0.5328856706619263, "learning_rate": 3.462180101502252e-06, "loss": 4.1901, "step": 27190 }, { "epoch": 0.8305131337813073, "grad_norm": 0.5262247920036316, "learning_rate": 3.4609621957381657e-06, "loss": 4.3391, "step": 27191 }, { "epoch": 0.830543677458766, "grad_norm": 0.5186995267868042, "learning_rate": 3.459744488295072e-06, "loss": 4.2248, "step": 27192 }, { "epoch": 0.8305742211362248, "grad_norm": 0.5221457481384277, "learning_rate": 3.4585269791841875e-06, "loss": 4.2218, "step": 27193 }, { "epoch": 0.8306047648136836, "grad_norm": 0.5199198126792908, "learning_rate": 3.4573096684167193e-06, "loss": 4.2901, "step": 27194 }, { "epoch": 0.8306353084911423, "grad_norm": 0.5148423910140991, "learning_rate": 3.456092556003879e-06, "loss": 4.1942, "step": 27195 }, { "epoch": 0.8306658521686011, "grad_norm": 0.5170858502388, "learning_rate": 3.4548756419568675e-06, "loss": 4.3297, "step": 27196 }, { "epoch": 0.8306963958460599, "grad_norm": 0.5205278992652893, "learning_rate": 3.453658926286893e-06, "loss": 4.3039, "step": 27197 }, { "epoch": 0.8307269395235186, "grad_norm": 0.5186446309089661, "learning_rate": 3.4524424090051662e-06, "loss": 4.1483, "step": 27198 }, { "epoch": 0.8307574832009774, "grad_norm": 0.5227020978927612, "learning_rate": 3.451226090122872e-06, "loss": 4.2391, "step": 27199 }, { "epoch": 0.8307880268784361, "grad_norm": 0.5191143155097961, "learning_rate": 3.4500099696512274e-06, "loss": 4.2754, "step": 27200 }, { "epoch": 0.8308185705558949, "grad_norm": 0.5199189782142639, "learning_rate": 3.448794047601414e-06, "loss": 4.3013, "step": 27201 }, { "epoch": 0.8308491142333537, "grad_norm": 0.5134647488594055, "learning_rate": 3.4475783239846322e-06, "loss": 4.244, "step": 27202 }, { "epoch": 0.8308796579108124, "grad_norm": 0.5193409323692322, "learning_rate": 3.446362798812086e-06, "loss": 4.224, "step": 27203 }, { "epoch": 0.8309102015882712, "grad_norm": 0.5129612684249878, "learning_rate": 3.4451474720949533e-06, "loss": 4.1756, "step": 27204 }, { "epoch": 0.83094074526573, "grad_norm": 0.5277451276779175, "learning_rate": 3.4439323438444303e-06, "loss": 4.3487, "step": 27205 }, { "epoch": 0.8309712889431887, "grad_norm": 0.5419039726257324, "learning_rate": 3.4427174140717085e-06, "loss": 4.1737, "step": 27206 }, { "epoch": 0.8310018326206475, "grad_norm": 0.5268315672874451, "learning_rate": 3.44150268278797e-06, "loss": 4.2417, "step": 27207 }, { "epoch": 0.8310323762981063, "grad_norm": 0.5303349494934082, "learning_rate": 3.440288150004403e-06, "loss": 4.3256, "step": 27208 }, { "epoch": 0.831062919975565, "grad_norm": 0.525405764579773, "learning_rate": 3.4390738157321882e-06, "loss": 4.2734, "step": 27209 }, { "epoch": 0.8310934636530238, "grad_norm": 0.5206036567687988, "learning_rate": 3.4378596799825e-06, "loss": 4.2499, "step": 27210 }, { "epoch": 0.8311240073304826, "grad_norm": 0.517116367816925, "learning_rate": 3.4366457427665254e-06, "loss": 4.2649, "step": 27211 }, { "epoch": 0.8311545510079413, "grad_norm": 0.5202446579933167, "learning_rate": 3.4354320040954456e-06, "loss": 4.3184, "step": 27212 }, { "epoch": 0.8311850946854001, "grad_norm": 0.5152005553245544, "learning_rate": 3.4342184639804265e-06, "loss": 4.246, "step": 27213 }, { "epoch": 0.8312156383628588, "grad_norm": 0.5178190469741821, "learning_rate": 3.4330051224326476e-06, "loss": 4.1881, "step": 27214 }, { "epoch": 0.8312461820403176, "grad_norm": 0.5216838121414185, "learning_rate": 3.431791979463278e-06, "loss": 4.3064, "step": 27215 }, { "epoch": 0.8312767257177764, "grad_norm": 0.5312618613243103, "learning_rate": 3.4305790350834866e-06, "loss": 4.2658, "step": 27216 }, { "epoch": 0.8313072693952351, "grad_norm": 0.5111692547798157, "learning_rate": 3.4293662893044505e-06, "loss": 4.2327, "step": 27217 }, { "epoch": 0.8313378130726939, "grad_norm": 0.5273435711860657, "learning_rate": 3.4281537421373216e-06, "loss": 4.33, "step": 27218 }, { "epoch": 0.8313683567501527, "grad_norm": 0.5189850926399231, "learning_rate": 3.426941393593275e-06, "loss": 4.2243, "step": 27219 }, { "epoch": 0.8313989004276114, "grad_norm": 0.5152440071105957, "learning_rate": 3.425729243683476e-06, "loss": 4.154, "step": 27220 }, { "epoch": 0.8314294441050702, "grad_norm": 0.5299806594848633, "learning_rate": 3.4245172924190742e-06, "loss": 4.2437, "step": 27221 }, { "epoch": 0.831459987782529, "grad_norm": 0.5209282636642456, "learning_rate": 3.4233055398112333e-06, "loss": 4.2055, "step": 27222 }, { "epoch": 0.8314905314599877, "grad_norm": 0.5158315300941467, "learning_rate": 3.422093985871119e-06, "loss": 4.2219, "step": 27223 }, { "epoch": 0.8315210751374466, "grad_norm": 0.5285570621490479, "learning_rate": 3.4208826306098786e-06, "loss": 4.231, "step": 27224 }, { "epoch": 0.8315516188149054, "grad_norm": 0.5190460085868835, "learning_rate": 3.4196714740386634e-06, "loss": 4.2484, "step": 27225 }, { "epoch": 0.831582162492364, "grad_norm": 0.5189223289489746, "learning_rate": 3.418460516168631e-06, "loss": 4.2303, "step": 27226 }, { "epoch": 0.8316127061698229, "grad_norm": 0.511798083782196, "learning_rate": 3.4172497570109264e-06, "loss": 4.2156, "step": 27227 }, { "epoch": 0.8316432498472817, "grad_norm": 0.5286402106285095, "learning_rate": 3.416039196576698e-06, "loss": 4.2996, "step": 27228 }, { "epoch": 0.8316737935247404, "grad_norm": 0.5070249438285828, "learning_rate": 3.4148288348770985e-06, "loss": 4.21, "step": 27229 }, { "epoch": 0.8317043372021992, "grad_norm": 0.5195037722587585, "learning_rate": 3.4136186719232662e-06, "loss": 4.2594, "step": 27230 }, { "epoch": 0.8317348808796579, "grad_norm": 0.5293185710906982, "learning_rate": 3.4124087077263473e-06, "loss": 4.2438, "step": 27231 }, { "epoch": 0.8317654245571167, "grad_norm": 0.5219656229019165, "learning_rate": 3.4111989422974778e-06, "loss": 4.2333, "step": 27232 }, { "epoch": 0.8317959682345755, "grad_norm": 0.5270786285400391, "learning_rate": 3.4099893756477986e-06, "loss": 4.2369, "step": 27233 }, { "epoch": 0.8318265119120342, "grad_norm": 0.530696451663971, "learning_rate": 3.4087800077884508e-06, "loss": 4.4143, "step": 27234 }, { "epoch": 0.831857055589493, "grad_norm": 0.5242940783500671, "learning_rate": 3.4075708387305643e-06, "loss": 4.2736, "step": 27235 }, { "epoch": 0.8318875992669518, "grad_norm": 0.5218550562858582, "learning_rate": 3.4063618684852722e-06, "loss": 4.3109, "step": 27236 }, { "epoch": 0.8319181429444105, "grad_norm": 0.5165331959724426, "learning_rate": 3.405153097063715e-06, "loss": 4.2372, "step": 27237 }, { "epoch": 0.8319486866218693, "grad_norm": 0.5273338556289673, "learning_rate": 3.4039445244770124e-06, "loss": 4.2398, "step": 27238 }, { "epoch": 0.8319792302993281, "grad_norm": 0.5858929753303528, "learning_rate": 3.402736150736302e-06, "loss": 4.288, "step": 27239 }, { "epoch": 0.8320097739767868, "grad_norm": 0.5193300247192383, "learning_rate": 3.401527975852695e-06, "loss": 4.2272, "step": 27240 }, { "epoch": 0.8320403176542456, "grad_norm": 0.5214798450469971, "learning_rate": 3.400319999837334e-06, "loss": 4.3176, "step": 27241 }, { "epoch": 0.8320708613317044, "grad_norm": 0.5195006132125854, "learning_rate": 3.3991122227013258e-06, "loss": 4.1561, "step": 27242 }, { "epoch": 0.8321014050091631, "grad_norm": 0.5178567171096802, "learning_rate": 3.3979046444558016e-06, "loss": 4.2213, "step": 27243 }, { "epoch": 0.8321319486866219, "grad_norm": 0.5155194997787476, "learning_rate": 3.39669726511187e-06, "loss": 4.2297, "step": 27244 }, { "epoch": 0.8321624923640807, "grad_norm": 0.5232563614845276, "learning_rate": 3.3954900846806553e-06, "loss": 4.2553, "step": 27245 }, { "epoch": 0.8321930360415394, "grad_norm": 0.523052453994751, "learning_rate": 3.3942831031732763e-06, "loss": 4.2325, "step": 27246 }, { "epoch": 0.8322235797189982, "grad_norm": 0.511796236038208, "learning_rate": 3.393076320600838e-06, "loss": 4.2885, "step": 27247 }, { "epoch": 0.8322541233964569, "grad_norm": 0.5202916860580444, "learning_rate": 3.3918697369744568e-06, "loss": 4.2708, "step": 27248 }, { "epoch": 0.8322846670739157, "grad_norm": 0.524311900138855, "learning_rate": 3.3906633523052373e-06, "loss": 4.2787, "step": 27249 }, { "epoch": 0.8323152107513745, "grad_norm": 0.5169097781181335, "learning_rate": 3.389457166604293e-06, "loss": 4.2703, "step": 27250 }, { "epoch": 0.8323457544288332, "grad_norm": 0.5286955833435059, "learning_rate": 3.388251179882729e-06, "loss": 4.2878, "step": 27251 }, { "epoch": 0.832376298106292, "grad_norm": 0.5399132966995239, "learning_rate": 3.387045392151644e-06, "loss": 4.2722, "step": 27252 }, { "epoch": 0.8324068417837508, "grad_norm": 0.5310275554656982, "learning_rate": 3.385839803422147e-06, "loss": 4.1525, "step": 27253 }, { "epoch": 0.8324373854612095, "grad_norm": 0.5185624361038208, "learning_rate": 3.38463441370534e-06, "loss": 4.255, "step": 27254 }, { "epoch": 0.8324679291386683, "grad_norm": 0.5198400616645813, "learning_rate": 3.383429223012316e-06, "loss": 4.17, "step": 27255 }, { "epoch": 0.8324984728161271, "grad_norm": 0.514132022857666, "learning_rate": 3.382224231354167e-06, "loss": 4.3386, "step": 27256 }, { "epoch": 0.8325290164935858, "grad_norm": 0.5201302766799927, "learning_rate": 3.381019438742003e-06, "loss": 4.2076, "step": 27257 }, { "epoch": 0.8325595601710446, "grad_norm": 0.5219787359237671, "learning_rate": 3.379814845186899e-06, "loss": 4.0742, "step": 27258 }, { "epoch": 0.8325901038485034, "grad_norm": 0.5212032794952393, "learning_rate": 3.3786104506999594e-06, "loss": 4.2707, "step": 27259 }, { "epoch": 0.8326206475259621, "grad_norm": 0.5181771516799927, "learning_rate": 3.377406255292273e-06, "loss": 4.303, "step": 27260 }, { "epoch": 0.8326511912034209, "grad_norm": 0.5111106634140015, "learning_rate": 3.37620225897492e-06, "loss": 4.2318, "step": 27261 }, { "epoch": 0.8326817348808797, "grad_norm": 0.5123850703239441, "learning_rate": 3.3749984617589908e-06, "loss": 4.1563, "step": 27262 }, { "epoch": 0.8327122785583384, "grad_norm": 0.5114474296569824, "learning_rate": 3.3737948636555746e-06, "loss": 4.0713, "step": 27263 }, { "epoch": 0.8327428222357972, "grad_norm": 0.5100837349891663, "learning_rate": 3.372591464675742e-06, "loss": 4.2102, "step": 27264 }, { "epoch": 0.8327733659132559, "grad_norm": 0.5156163573265076, "learning_rate": 3.3713882648305855e-06, "loss": 4.0278, "step": 27265 }, { "epoch": 0.8328039095907147, "grad_norm": 0.5304287672042847, "learning_rate": 3.370185264131173e-06, "loss": 4.2168, "step": 27266 }, { "epoch": 0.8328344532681735, "grad_norm": 0.5169495344161987, "learning_rate": 3.3689824625885854e-06, "loss": 4.2305, "step": 27267 }, { "epoch": 0.8328649969456322, "grad_norm": 0.5230304002761841, "learning_rate": 3.3677798602139016e-06, "loss": 4.2541, "step": 27268 }, { "epoch": 0.832895540623091, "grad_norm": 0.5194669365882874, "learning_rate": 3.3665774570181857e-06, "loss": 4.2581, "step": 27269 }, { "epoch": 0.8329260843005498, "grad_norm": 0.5236641764640808, "learning_rate": 3.3653752530125203e-06, "loss": 4.2938, "step": 27270 }, { "epoch": 0.8329566279780085, "grad_norm": 0.5222075581550598, "learning_rate": 3.3641732482079634e-06, "loss": 4.2721, "step": 27271 }, { "epoch": 0.8329871716554673, "grad_norm": 0.5251353979110718, "learning_rate": 3.3629714426155924e-06, "loss": 4.2288, "step": 27272 }, { "epoch": 0.8330177153329261, "grad_norm": 0.5110880136489868, "learning_rate": 3.3617698362464616e-06, "loss": 4.2068, "step": 27273 }, { "epoch": 0.8330482590103848, "grad_norm": 0.5220624208450317, "learning_rate": 3.360568429111649e-06, "loss": 4.1202, "step": 27274 }, { "epoch": 0.8330788026878436, "grad_norm": 0.51832515001297, "learning_rate": 3.359367221222201e-06, "loss": 4.1763, "step": 27275 }, { "epoch": 0.8331093463653024, "grad_norm": 0.5097280144691467, "learning_rate": 3.3581662125891865e-06, "loss": 4.129, "step": 27276 }, { "epoch": 0.8331398900427611, "grad_norm": 0.506707489490509, "learning_rate": 3.356965403223669e-06, "loss": 4.1067, "step": 27277 }, { "epoch": 0.8331704337202199, "grad_norm": 0.5309474468231201, "learning_rate": 3.3557647931366927e-06, "loss": 4.3248, "step": 27278 }, { "epoch": 0.8332009773976787, "grad_norm": 0.5261409282684326, "learning_rate": 3.3545643823393174e-06, "loss": 4.2705, "step": 27279 }, { "epoch": 0.8332315210751374, "grad_norm": 0.5303714275360107, "learning_rate": 3.3533641708426015e-06, "loss": 4.295, "step": 27280 }, { "epoch": 0.8332620647525962, "grad_norm": 0.5156955718994141, "learning_rate": 3.3521641586575865e-06, "loss": 4.1726, "step": 27281 }, { "epoch": 0.8332926084300549, "grad_norm": 0.5229058861732483, "learning_rate": 3.350964345795335e-06, "loss": 4.2452, "step": 27282 }, { "epoch": 0.8333231521075137, "grad_norm": 0.5434076189994812, "learning_rate": 3.3497647322668773e-06, "loss": 4.2295, "step": 27283 }, { "epoch": 0.8333536957849725, "grad_norm": 0.5247915387153625, "learning_rate": 3.348565318083266e-06, "loss": 4.2486, "step": 27284 }, { "epoch": 0.8333842394624312, "grad_norm": 0.5437939167022705, "learning_rate": 3.347366103255553e-06, "loss": 4.189, "step": 27285 }, { "epoch": 0.83341478313989, "grad_norm": 0.5359681844711304, "learning_rate": 3.346167087794769e-06, "loss": 4.3044, "step": 27286 }, { "epoch": 0.8334453268173488, "grad_norm": 0.5216103196144104, "learning_rate": 3.3449682717119595e-06, "loss": 4.2907, "step": 27287 }, { "epoch": 0.8334758704948075, "grad_norm": 0.5213223099708557, "learning_rate": 3.343769655018164e-06, "loss": 4.2129, "step": 27288 }, { "epoch": 0.8335064141722663, "grad_norm": 0.517684280872345, "learning_rate": 3.3425712377244094e-06, "loss": 4.2494, "step": 27289 }, { "epoch": 0.8335369578497251, "grad_norm": 0.5250616073608398, "learning_rate": 3.341373019841737e-06, "loss": 4.263, "step": 27290 }, { "epoch": 0.8335675015271838, "grad_norm": 0.5216748118400574, "learning_rate": 3.340175001381185e-06, "loss": 4.2887, "step": 27291 }, { "epoch": 0.8335980452046426, "grad_norm": 0.5140225887298584, "learning_rate": 3.3389771823537724e-06, "loss": 4.0841, "step": 27292 }, { "epoch": 0.8336285888821015, "grad_norm": 0.5214257836341858, "learning_rate": 3.337779562770532e-06, "loss": 4.1575, "step": 27293 }, { "epoch": 0.8336591325595601, "grad_norm": 0.5112031102180481, "learning_rate": 3.3365821426424997e-06, "loss": 4.2779, "step": 27294 }, { "epoch": 0.833689676237019, "grad_norm": 0.5193483233451843, "learning_rate": 3.335384921980689e-06, "loss": 4.1227, "step": 27295 }, { "epoch": 0.8337202199144778, "grad_norm": 0.5260064601898193, "learning_rate": 3.334187900796126e-06, "loss": 4.2505, "step": 27296 }, { "epoch": 0.8337507635919365, "grad_norm": 0.5164173245429993, "learning_rate": 3.3329910790998424e-06, "loss": 4.2269, "step": 27297 }, { "epoch": 0.8337813072693953, "grad_norm": 0.5198250412940979, "learning_rate": 3.3317944569028425e-06, "loss": 4.1157, "step": 27298 }, { "epoch": 0.833811850946854, "grad_norm": 0.5126309990882874, "learning_rate": 3.330598034216159e-06, "loss": 4.2415, "step": 27299 }, { "epoch": 0.8338423946243128, "grad_norm": 0.5285829901695251, "learning_rate": 3.3294018110507946e-06, "loss": 4.2457, "step": 27300 }, { "epoch": 0.8338729383017716, "grad_norm": 0.5211889743804932, "learning_rate": 3.3282057874177737e-06, "loss": 4.2871, "step": 27301 }, { "epoch": 0.8339034819792303, "grad_norm": 0.5256186127662659, "learning_rate": 3.327009963328101e-06, "loss": 4.284, "step": 27302 }, { "epoch": 0.8339340256566891, "grad_norm": 0.5141552090644836, "learning_rate": 3.325814338792796e-06, "loss": 4.1892, "step": 27303 }, { "epoch": 0.8339645693341479, "grad_norm": 0.5194526314735413, "learning_rate": 3.324618913822855e-06, "loss": 4.2475, "step": 27304 }, { "epoch": 0.8339951130116066, "grad_norm": 0.5176764726638794, "learning_rate": 3.3234236884293e-06, "loss": 4.1328, "step": 27305 }, { "epoch": 0.8340256566890654, "grad_norm": 0.5210158824920654, "learning_rate": 3.3222286626231225e-06, "loss": 4.3127, "step": 27306 }, { "epoch": 0.8340562003665242, "grad_norm": 0.5200232863426208, "learning_rate": 3.32103383641533e-06, "loss": 4.1876, "step": 27307 }, { "epoch": 0.8340867440439829, "grad_norm": 0.5330102443695068, "learning_rate": 3.31983920981693e-06, "loss": 4.2281, "step": 27308 }, { "epoch": 0.8341172877214417, "grad_norm": 0.540022611618042, "learning_rate": 3.3186447828389115e-06, "loss": 4.3108, "step": 27309 }, { "epoch": 0.8341478313989005, "grad_norm": 0.5198485255241394, "learning_rate": 3.3174505554922798e-06, "loss": 4.2565, "step": 27310 }, { "epoch": 0.8341783750763592, "grad_norm": 0.5214583277702332, "learning_rate": 3.3162565277880336e-06, "loss": 4.2583, "step": 27311 }, { "epoch": 0.834208918753818, "grad_norm": 0.5443146824836731, "learning_rate": 3.3150626997371564e-06, "loss": 4.3569, "step": 27312 }, { "epoch": 0.8342394624312768, "grad_norm": 0.5262551307678223, "learning_rate": 3.313869071350648e-06, "loss": 4.3004, "step": 27313 }, { "epoch": 0.8342700061087355, "grad_norm": 0.5276558995246887, "learning_rate": 3.312675642639501e-06, "loss": 4.3241, "step": 27314 }, { "epoch": 0.8343005497861943, "grad_norm": 0.5310578346252441, "learning_rate": 3.3114824136146944e-06, "loss": 4.2387, "step": 27315 }, { "epoch": 0.834331093463653, "grad_norm": 0.5084661245346069, "learning_rate": 3.310289384287224e-06, "loss": 4.2279, "step": 27316 }, { "epoch": 0.8343616371411118, "grad_norm": 0.5190728306770325, "learning_rate": 3.3090965546680674e-06, "loss": 4.2554, "step": 27317 }, { "epoch": 0.8343921808185706, "grad_norm": 0.5341870784759521, "learning_rate": 3.3079039247682186e-06, "loss": 4.2604, "step": 27318 }, { "epoch": 0.8344227244960293, "grad_norm": 0.5254253149032593, "learning_rate": 3.3067114945986494e-06, "loss": 4.2751, "step": 27319 }, { "epoch": 0.8344532681734881, "grad_norm": 0.5340825915336609, "learning_rate": 3.305519264170334e-06, "loss": 4.2911, "step": 27320 }, { "epoch": 0.8344838118509469, "grad_norm": 0.52073073387146, "learning_rate": 3.304327233494259e-06, "loss": 4.1183, "step": 27321 }, { "epoch": 0.8345143555284056, "grad_norm": 0.5225076079368591, "learning_rate": 3.303135402581403e-06, "loss": 4.2296, "step": 27322 }, { "epoch": 0.8345448992058644, "grad_norm": 0.5207280516624451, "learning_rate": 3.301943771442728e-06, "loss": 4.2604, "step": 27323 }, { "epoch": 0.8345754428833232, "grad_norm": 0.5289736986160278, "learning_rate": 3.300752340089214e-06, "loss": 4.2835, "step": 27324 }, { "epoch": 0.8346059865607819, "grad_norm": 0.5316551327705383, "learning_rate": 3.2995611085318373e-06, "loss": 4.3167, "step": 27325 }, { "epoch": 0.8346365302382407, "grad_norm": 0.5153854489326477, "learning_rate": 3.2983700767815513e-06, "loss": 4.1696, "step": 27326 }, { "epoch": 0.8346670739156995, "grad_norm": 0.5298906564712524, "learning_rate": 3.2971792448493297e-06, "loss": 4.2986, "step": 27327 }, { "epoch": 0.8346976175931582, "grad_norm": 0.5392146110534668, "learning_rate": 3.2959886127461425e-06, "loss": 4.0211, "step": 27328 }, { "epoch": 0.834728161270617, "grad_norm": 0.518200695514679, "learning_rate": 3.2947981804829413e-06, "loss": 4.2575, "step": 27329 }, { "epoch": 0.8347587049480758, "grad_norm": 0.5185311436653137, "learning_rate": 3.2936079480706927e-06, "loss": 4.2582, "step": 27330 }, { "epoch": 0.8347892486255345, "grad_norm": 0.5265215039253235, "learning_rate": 3.2924179155203627e-06, "loss": 4.2484, "step": 27331 }, { "epoch": 0.8348197923029933, "grad_norm": 0.5266724824905396, "learning_rate": 3.291228082842898e-06, "loss": 4.2528, "step": 27332 }, { "epoch": 0.834850335980452, "grad_norm": 0.523430347442627, "learning_rate": 3.2900384500492628e-06, "loss": 4.2651, "step": 27333 }, { "epoch": 0.8348808796579108, "grad_norm": 0.5236620903015137, "learning_rate": 3.2888490171504026e-06, "loss": 4.2308, "step": 27334 }, { "epoch": 0.8349114233353696, "grad_norm": 0.5257148742675781, "learning_rate": 3.2876597841572683e-06, "loss": 4.1758, "step": 27335 }, { "epoch": 0.8349419670128283, "grad_norm": 0.5420834422111511, "learning_rate": 3.2864707510808197e-06, "loss": 4.1619, "step": 27336 }, { "epoch": 0.8349725106902871, "grad_norm": 0.5177781581878662, "learning_rate": 3.2852819179319955e-06, "loss": 4.3117, "step": 27337 }, { "epoch": 0.8350030543677459, "grad_norm": 0.5243755578994751, "learning_rate": 3.2840932847217426e-06, "loss": 4.2269, "step": 27338 }, { "epoch": 0.8350335980452046, "grad_norm": 0.5194937586784363, "learning_rate": 3.282904851461013e-06, "loss": 4.2807, "step": 27339 }, { "epoch": 0.8350641417226634, "grad_norm": 0.5152067542076111, "learning_rate": 3.281716618160741e-06, "loss": 4.2299, "step": 27340 }, { "epoch": 0.8350946854001222, "grad_norm": 0.5311686992645264, "learning_rate": 3.2805285848318686e-06, "loss": 4.3352, "step": 27341 }, { "epoch": 0.8351252290775809, "grad_norm": 0.5288111567497253, "learning_rate": 3.2793407514853437e-06, "loss": 4.2413, "step": 27342 }, { "epoch": 0.8351557727550397, "grad_norm": 0.5245752334594727, "learning_rate": 3.2781531181320908e-06, "loss": 4.1995, "step": 27343 }, { "epoch": 0.8351863164324985, "grad_norm": 0.5302436351776123, "learning_rate": 3.2769656847830482e-06, "loss": 4.2913, "step": 27344 }, { "epoch": 0.8352168601099572, "grad_norm": 0.5207074880599976, "learning_rate": 3.2757784514491573e-06, "loss": 4.1461, "step": 27345 }, { "epoch": 0.835247403787416, "grad_norm": 0.5161213874816895, "learning_rate": 3.27459141814134e-06, "loss": 4.2785, "step": 27346 }, { "epoch": 0.8352779474648748, "grad_norm": 0.530159056186676, "learning_rate": 3.2734045848705347e-06, "loss": 4.2543, "step": 27347 }, { "epoch": 0.8353084911423335, "grad_norm": 0.5231870412826538, "learning_rate": 3.2722179516476577e-06, "loss": 4.3148, "step": 27348 }, { "epoch": 0.8353390348197923, "grad_norm": 0.5287466645240784, "learning_rate": 3.2710315184836472e-06, "loss": 4.2599, "step": 27349 }, { "epoch": 0.835369578497251, "grad_norm": 0.5247224569320679, "learning_rate": 3.269845285389417e-06, "loss": 4.2786, "step": 27350 }, { "epoch": 0.8354001221747098, "grad_norm": 0.5167814493179321, "learning_rate": 3.268659252375897e-06, "loss": 4.2226, "step": 27351 }, { "epoch": 0.8354306658521686, "grad_norm": 0.531534731388092, "learning_rate": 3.2674734194540006e-06, "loss": 4.3272, "step": 27352 }, { "epoch": 0.8354612095296273, "grad_norm": 0.5309650897979736, "learning_rate": 3.266287786634656e-06, "loss": 4.2317, "step": 27353 }, { "epoch": 0.8354917532070861, "grad_norm": 0.5198873281478882, "learning_rate": 3.2651023539287672e-06, "loss": 4.2753, "step": 27354 }, { "epoch": 0.8355222968845449, "grad_norm": 0.5212116241455078, "learning_rate": 3.2639171213472568e-06, "loss": 4.3403, "step": 27355 }, { "epoch": 0.8355528405620036, "grad_norm": 0.5201042294502258, "learning_rate": 3.262732088901041e-06, "loss": 4.2935, "step": 27356 }, { "epoch": 0.8355833842394624, "grad_norm": 0.5258821845054626, "learning_rate": 3.261547256601025e-06, "loss": 4.2297, "step": 27357 }, { "epoch": 0.8356139279169212, "grad_norm": 0.5097886919975281, "learning_rate": 3.2603626244581187e-06, "loss": 4.0985, "step": 27358 }, { "epoch": 0.8356444715943799, "grad_norm": 0.5343301892280579, "learning_rate": 3.2591781924832337e-06, "loss": 4.2726, "step": 27359 }, { "epoch": 0.8356750152718387, "grad_norm": 0.5269476771354675, "learning_rate": 3.2579939606872725e-06, "loss": 4.2826, "step": 27360 }, { "epoch": 0.8357055589492975, "grad_norm": 0.5204296112060547, "learning_rate": 3.2568099290811367e-06, "loss": 4.1917, "step": 27361 }, { "epoch": 0.8357361026267562, "grad_norm": 0.5237536430358887, "learning_rate": 3.2556260976757374e-06, "loss": 4.3568, "step": 27362 }, { "epoch": 0.835766646304215, "grad_norm": 0.5223538875579834, "learning_rate": 3.2544424664819607e-06, "loss": 4.2777, "step": 27363 }, { "epoch": 0.8357971899816737, "grad_norm": 0.5224460363388062, "learning_rate": 3.2532590355107194e-06, "loss": 4.1937, "step": 27364 }, { "epoch": 0.8358277336591325, "grad_norm": 0.52472984790802, "learning_rate": 3.2520758047729053e-06, "loss": 4.271, "step": 27365 }, { "epoch": 0.8358582773365913, "grad_norm": 0.5300654768943787, "learning_rate": 3.2508927742794043e-06, "loss": 4.2008, "step": 27366 }, { "epoch": 0.83588882101405, "grad_norm": 0.5146130323410034, "learning_rate": 3.249709944041121e-06, "loss": 4.22, "step": 27367 }, { "epoch": 0.8359193646915088, "grad_norm": 0.5422568917274475, "learning_rate": 3.248527314068936e-06, "loss": 4.2411, "step": 27368 }, { "epoch": 0.8359499083689677, "grad_norm": 0.5288293361663818, "learning_rate": 3.247344884373743e-06, "loss": 4.3013, "step": 27369 }, { "epoch": 0.8359804520464263, "grad_norm": 0.5204082131385803, "learning_rate": 3.246162654966434e-06, "loss": 4.1462, "step": 27370 }, { "epoch": 0.8360109957238852, "grad_norm": 0.5257996320724487, "learning_rate": 3.244980625857888e-06, "loss": 4.1485, "step": 27371 }, { "epoch": 0.836041539401344, "grad_norm": 0.5283426642417908, "learning_rate": 3.243798797058989e-06, "loss": 4.2556, "step": 27372 }, { "epoch": 0.8360720830788027, "grad_norm": 0.5196787118911743, "learning_rate": 3.242617168580625e-06, "loss": 4.1567, "step": 27373 }, { "epoch": 0.8361026267562615, "grad_norm": 0.5182865262031555, "learning_rate": 3.2414357404336653e-06, "loss": 4.202, "step": 27374 }, { "epoch": 0.8361331704337203, "grad_norm": 0.522702157497406, "learning_rate": 3.2402545126289955e-06, "loss": 4.3252, "step": 27375 }, { "epoch": 0.836163714111179, "grad_norm": 0.524756669998169, "learning_rate": 3.239073485177496e-06, "loss": 4.3004, "step": 27376 }, { "epoch": 0.8361942577886378, "grad_norm": 0.5188365578651428, "learning_rate": 3.2378926580900275e-06, "loss": 4.1698, "step": 27377 }, { "epoch": 0.8362248014660966, "grad_norm": 0.5174666047096252, "learning_rate": 3.236712031377473e-06, "loss": 4.2535, "step": 27378 }, { "epoch": 0.8362553451435553, "grad_norm": 0.5182991623878479, "learning_rate": 3.2355316050507038e-06, "loss": 4.2847, "step": 27379 }, { "epoch": 0.8362858888210141, "grad_norm": 0.5119960904121399, "learning_rate": 3.2343513791205872e-06, "loss": 4.2209, "step": 27380 }, { "epoch": 0.8363164324984728, "grad_norm": 0.5172443389892578, "learning_rate": 3.2331713535979802e-06, "loss": 4.2165, "step": 27381 }, { "epoch": 0.8363469761759316, "grad_norm": 0.5263558030128479, "learning_rate": 3.2319915284937634e-06, "loss": 4.2464, "step": 27382 }, { "epoch": 0.8363775198533904, "grad_norm": 0.5175617337226868, "learning_rate": 3.2308119038187867e-06, "loss": 4.2133, "step": 27383 }, { "epoch": 0.8364080635308491, "grad_norm": 0.5225811004638672, "learning_rate": 3.2296324795839243e-06, "loss": 4.3005, "step": 27384 }, { "epoch": 0.8364386072083079, "grad_norm": 0.5214516520500183, "learning_rate": 3.228453255800021e-06, "loss": 4.3082, "step": 27385 }, { "epoch": 0.8364691508857667, "grad_norm": 0.5249029994010925, "learning_rate": 3.227274232477942e-06, "loss": 4.1845, "step": 27386 }, { "epoch": 0.8364996945632254, "grad_norm": 0.5159972310066223, "learning_rate": 3.226095409628552e-06, "loss": 4.2377, "step": 27387 }, { "epoch": 0.8365302382406842, "grad_norm": 0.5264322757720947, "learning_rate": 3.2249167872626885e-06, "loss": 4.2877, "step": 27388 }, { "epoch": 0.836560781918143, "grad_norm": 0.5250056385993958, "learning_rate": 3.223738365391213e-06, "loss": 4.2755, "step": 27389 }, { "epoch": 0.8365913255956017, "grad_norm": 0.5203920006752014, "learning_rate": 3.2225601440249804e-06, "loss": 4.2962, "step": 27390 }, { "epoch": 0.8366218692730605, "grad_norm": 0.5189597606658936, "learning_rate": 3.2213821231748266e-06, "loss": 4.166, "step": 27391 }, { "epoch": 0.8366524129505193, "grad_norm": 0.5311151146888733, "learning_rate": 3.2202043028516068e-06, "loss": 4.3126, "step": 27392 }, { "epoch": 0.836682956627978, "grad_norm": 0.5159003734588623, "learning_rate": 3.2190266830661676e-06, "loss": 4.1739, "step": 27393 }, { "epoch": 0.8367135003054368, "grad_norm": 0.5231338739395142, "learning_rate": 3.217849263829345e-06, "loss": 4.2859, "step": 27394 }, { "epoch": 0.8367440439828956, "grad_norm": 0.5190629959106445, "learning_rate": 3.216672045151989e-06, "loss": 4.2358, "step": 27395 }, { "epoch": 0.8367745876603543, "grad_norm": 0.5206655263900757, "learning_rate": 3.2154950270449264e-06, "loss": 4.1799, "step": 27396 }, { "epoch": 0.8368051313378131, "grad_norm": 0.5161539316177368, "learning_rate": 3.2143182095190073e-06, "loss": 4.241, "step": 27397 }, { "epoch": 0.8368356750152718, "grad_norm": 0.5239182114601135, "learning_rate": 3.2131415925850616e-06, "loss": 4.2104, "step": 27398 }, { "epoch": 0.8368662186927306, "grad_norm": 0.515771210193634, "learning_rate": 3.211965176253917e-06, "loss": 4.2865, "step": 27399 }, { "epoch": 0.8368967623701894, "grad_norm": 0.5213866829872131, "learning_rate": 3.210788960536412e-06, "loss": 4.2974, "step": 27400 }, { "epoch": 0.8369273060476481, "grad_norm": 0.5228848457336426, "learning_rate": 3.20961294544338e-06, "loss": 4.2386, "step": 27401 }, { "epoch": 0.8369578497251069, "grad_norm": 0.5192946195602417, "learning_rate": 3.208437130985642e-06, "loss": 4.2511, "step": 27402 }, { "epoch": 0.8369883934025657, "grad_norm": 0.5289452075958252, "learning_rate": 3.207261517174026e-06, "loss": 4.2915, "step": 27403 }, { "epoch": 0.8370189370800244, "grad_norm": 0.5275238752365112, "learning_rate": 3.2060861040193624e-06, "loss": 4.2515, "step": 27404 }, { "epoch": 0.8370494807574832, "grad_norm": 0.5234233140945435, "learning_rate": 3.204910891532467e-06, "loss": 4.2058, "step": 27405 }, { "epoch": 0.837080024434942, "grad_norm": 0.5164599418640137, "learning_rate": 3.2037358797241595e-06, "loss": 4.1501, "step": 27406 }, { "epoch": 0.8371105681124007, "grad_norm": 0.5299174189567566, "learning_rate": 3.2025610686052697e-06, "loss": 4.2974, "step": 27407 }, { "epoch": 0.8371411117898595, "grad_norm": 0.5302034020423889, "learning_rate": 3.2013864581866032e-06, "loss": 4.2446, "step": 27408 }, { "epoch": 0.8371716554673183, "grad_norm": 0.5236837863922119, "learning_rate": 3.200212048478976e-06, "loss": 4.2833, "step": 27409 }, { "epoch": 0.837202199144777, "grad_norm": 0.518775463104248, "learning_rate": 3.199037839493213e-06, "loss": 4.2147, "step": 27410 }, { "epoch": 0.8372327428222358, "grad_norm": 0.5175622701644897, "learning_rate": 3.1978638312401166e-06, "loss": 4.2379, "step": 27411 }, { "epoch": 0.8372632864996946, "grad_norm": 0.5185785293579102, "learning_rate": 3.196690023730492e-06, "loss": 4.2464, "step": 27412 }, { "epoch": 0.8372938301771533, "grad_norm": 0.5245734453201294, "learning_rate": 3.1955164169751585e-06, "loss": 4.3295, "step": 27413 }, { "epoch": 0.8373243738546121, "grad_norm": 0.5164895057678223, "learning_rate": 3.19434301098491e-06, "loss": 4.2226, "step": 27414 }, { "epoch": 0.8373549175320708, "grad_norm": 0.5168240666389465, "learning_rate": 3.19316980577056e-06, "loss": 4.3208, "step": 27415 }, { "epoch": 0.8373854612095296, "grad_norm": 0.5228341817855835, "learning_rate": 3.191996801342906e-06, "loss": 4.2006, "step": 27416 }, { "epoch": 0.8374160048869884, "grad_norm": 0.5208260416984558, "learning_rate": 3.190823997712747e-06, "loss": 4.2997, "step": 27417 }, { "epoch": 0.8374465485644471, "grad_norm": 0.5188159346580505, "learning_rate": 3.1896513948908913e-06, "loss": 4.2741, "step": 27418 }, { "epoch": 0.8374770922419059, "grad_norm": 0.5215023756027222, "learning_rate": 3.1884789928881247e-06, "loss": 4.1612, "step": 27419 }, { "epoch": 0.8375076359193647, "grad_norm": 0.5262836217880249, "learning_rate": 3.1873067917152445e-06, "loss": 4.2295, "step": 27420 }, { "epoch": 0.8375381795968234, "grad_norm": 0.5183801054954529, "learning_rate": 3.1861347913830524e-06, "loss": 4.219, "step": 27421 }, { "epoch": 0.8375687232742822, "grad_norm": 0.5391124486923218, "learning_rate": 3.1849629919023265e-06, "loss": 4.3103, "step": 27422 }, { "epoch": 0.837599266951741, "grad_norm": 0.5434053540229797, "learning_rate": 3.1837913932838635e-06, "loss": 4.1825, "step": 27423 }, { "epoch": 0.8376298106291997, "grad_norm": 0.5192779302597046, "learning_rate": 3.182619995538455e-06, "loss": 4.1517, "step": 27424 }, { "epoch": 0.8376603543066585, "grad_norm": 0.5247185826301575, "learning_rate": 3.1814487986768754e-06, "loss": 4.2081, "step": 27425 }, { "epoch": 0.8376908979841173, "grad_norm": 0.5188416242599487, "learning_rate": 3.1802778027099216e-06, "loss": 4.2208, "step": 27426 }, { "epoch": 0.837721441661576, "grad_norm": 0.5308013558387756, "learning_rate": 3.1791070076483604e-06, "loss": 4.171, "step": 27427 }, { "epoch": 0.8377519853390348, "grad_norm": 0.5212807059288025, "learning_rate": 3.177936413502988e-06, "loss": 4.2413, "step": 27428 }, { "epoch": 0.8377825290164936, "grad_norm": 0.5196550488471985, "learning_rate": 3.176766020284569e-06, "loss": 4.1886, "step": 27429 }, { "epoch": 0.8378130726939523, "grad_norm": 0.5168006420135498, "learning_rate": 3.175595828003891e-06, "loss": 4.272, "step": 27430 }, { "epoch": 0.8378436163714111, "grad_norm": 0.5307250618934631, "learning_rate": 3.1744258366717185e-06, "loss": 4.1876, "step": 27431 }, { "epoch": 0.8378741600488698, "grad_norm": 0.5240527391433716, "learning_rate": 3.173256046298834e-06, "loss": 4.251, "step": 27432 }, { "epoch": 0.8379047037263286, "grad_norm": 0.5273460149765015, "learning_rate": 3.1720864568959953e-06, "loss": 4.2724, "step": 27433 }, { "epoch": 0.8379352474037874, "grad_norm": 0.531889021396637, "learning_rate": 3.170917068473983e-06, "loss": 4.3111, "step": 27434 }, { "epoch": 0.8379657910812461, "grad_norm": 0.5213308930397034, "learning_rate": 3.1697478810435636e-06, "loss": 4.2683, "step": 27435 }, { "epoch": 0.8379963347587049, "grad_norm": 0.5259993076324463, "learning_rate": 3.1685788946154956e-06, "loss": 4.2914, "step": 27436 }, { "epoch": 0.8380268784361637, "grad_norm": 0.5214309096336365, "learning_rate": 3.167410109200547e-06, "loss": 4.2492, "step": 27437 }, { "epoch": 0.8380574221136224, "grad_norm": 0.5222087502479553, "learning_rate": 3.1662415248094824e-06, "loss": 4.2666, "step": 27438 }, { "epoch": 0.8380879657910812, "grad_norm": 0.5303325057029724, "learning_rate": 3.1650731414530536e-06, "loss": 4.1632, "step": 27439 }, { "epoch": 0.83811850946854, "grad_norm": 0.5235286355018616, "learning_rate": 3.1639049591420222e-06, "loss": 4.2972, "step": 27440 }, { "epoch": 0.8381490531459987, "grad_norm": 0.5226173400878906, "learning_rate": 3.1627369778871484e-06, "loss": 4.2184, "step": 27441 }, { "epoch": 0.8381795968234576, "grad_norm": 0.5258209705352783, "learning_rate": 3.1615691976991794e-06, "loss": 4.2953, "step": 27442 }, { "epoch": 0.8382101405009164, "grad_norm": 0.5216047167778015, "learning_rate": 3.1604016185888764e-06, "loss": 4.155, "step": 27443 }, { "epoch": 0.838240684178375, "grad_norm": 0.5290799736976624, "learning_rate": 3.1592342405669855e-06, "loss": 4.2616, "step": 27444 }, { "epoch": 0.8382712278558339, "grad_norm": 0.5333868861198425, "learning_rate": 3.158067063644246e-06, "loss": 4.2781, "step": 27445 }, { "epoch": 0.8383017715332927, "grad_norm": 0.5242345929145813, "learning_rate": 3.156900087831416e-06, "loss": 4.2177, "step": 27446 }, { "epoch": 0.8383323152107514, "grad_norm": 0.5239906907081604, "learning_rate": 3.155733313139242e-06, "loss": 4.1974, "step": 27447 }, { "epoch": 0.8383628588882102, "grad_norm": 0.5247843861579895, "learning_rate": 3.1545667395784574e-06, "loss": 4.2596, "step": 27448 }, { "epoch": 0.8383934025656689, "grad_norm": 0.5341424345970154, "learning_rate": 3.1534003671598143e-06, "loss": 4.2295, "step": 27449 }, { "epoch": 0.8384239462431277, "grad_norm": 0.5245701670646667, "learning_rate": 3.152234195894041e-06, "loss": 4.3415, "step": 27450 }, { "epoch": 0.8384544899205865, "grad_norm": 0.5229818224906921, "learning_rate": 3.1510682257918784e-06, "loss": 4.324, "step": 27451 }, { "epoch": 0.8384850335980452, "grad_norm": 0.5163506865501404, "learning_rate": 3.1499024568640707e-06, "loss": 4.2978, "step": 27452 }, { "epoch": 0.838515577275504, "grad_norm": 0.5270302891731262, "learning_rate": 3.14873688912134e-06, "loss": 4.3488, "step": 27453 }, { "epoch": 0.8385461209529628, "grad_norm": 0.5262014865875244, "learning_rate": 3.1475715225744247e-06, "loss": 4.2447, "step": 27454 }, { "epoch": 0.8385766646304215, "grad_norm": 0.5354069471359253, "learning_rate": 3.146406357234058e-06, "loss": 4.3523, "step": 27455 }, { "epoch": 0.8386072083078803, "grad_norm": 0.5299333333969116, "learning_rate": 3.1452413931109593e-06, "loss": 4.2559, "step": 27456 }, { "epoch": 0.8386377519853391, "grad_norm": 0.5278199315071106, "learning_rate": 3.144076630215864e-06, "loss": 4.2911, "step": 27457 }, { "epoch": 0.8386682956627978, "grad_norm": 0.5242691040039062, "learning_rate": 3.142912068559489e-06, "loss": 4.2915, "step": 27458 }, { "epoch": 0.8386988393402566, "grad_norm": 0.5151869654655457, "learning_rate": 3.141747708152565e-06, "loss": 4.2235, "step": 27459 }, { "epoch": 0.8387293830177154, "grad_norm": 0.5174522995948792, "learning_rate": 3.1405835490058017e-06, "loss": 4.2139, "step": 27460 }, { "epoch": 0.8387599266951741, "grad_norm": 0.5219931602478027, "learning_rate": 3.13941959112993e-06, "loss": 4.2411, "step": 27461 }, { "epoch": 0.8387904703726329, "grad_norm": 0.5171012878417969, "learning_rate": 3.1382558345356583e-06, "loss": 4.2364, "step": 27462 }, { "epoch": 0.8388210140500917, "grad_norm": 0.5233641266822815, "learning_rate": 3.137092279233703e-06, "loss": 4.226, "step": 27463 }, { "epoch": 0.8388515577275504, "grad_norm": 0.5321037173271179, "learning_rate": 3.135928925234788e-06, "loss": 4.2303, "step": 27464 }, { "epoch": 0.8388821014050092, "grad_norm": 0.5171554088592529, "learning_rate": 3.1347657725496083e-06, "loss": 4.1876, "step": 27465 }, { "epoch": 0.8389126450824679, "grad_norm": 0.5314476490020752, "learning_rate": 3.1336028211888887e-06, "loss": 4.2873, "step": 27466 }, { "epoch": 0.8389431887599267, "grad_norm": 0.5226276516914368, "learning_rate": 3.132440071163326e-06, "loss": 4.2148, "step": 27467 }, { "epoch": 0.8389737324373855, "grad_norm": 0.5197207927703857, "learning_rate": 3.1312775224836304e-06, "loss": 4.2144, "step": 27468 }, { "epoch": 0.8390042761148442, "grad_norm": 0.5326266288757324, "learning_rate": 3.130115175160511e-06, "loss": 4.3406, "step": 27469 }, { "epoch": 0.839034819792303, "grad_norm": 0.5222922563552856, "learning_rate": 3.128953029204662e-06, "loss": 4.2144, "step": 27470 }, { "epoch": 0.8390653634697618, "grad_norm": 0.5190636515617371, "learning_rate": 3.1277910846267855e-06, "loss": 4.249, "step": 27471 }, { "epoch": 0.8390959071472205, "grad_norm": 0.5160184502601624, "learning_rate": 3.126629341437587e-06, "loss": 4.2568, "step": 27472 }, { "epoch": 0.8391264508246793, "grad_norm": 0.5192318558692932, "learning_rate": 3.125467799647755e-06, "loss": 4.2336, "step": 27473 }, { "epoch": 0.8391569945021381, "grad_norm": 0.5207018256187439, "learning_rate": 3.124306459267992e-06, "loss": 4.2182, "step": 27474 }, { "epoch": 0.8391875381795968, "grad_norm": 0.5342780351638794, "learning_rate": 3.1231453203089873e-06, "loss": 4.1559, "step": 27475 }, { "epoch": 0.8392180818570556, "grad_norm": 0.5208015441894531, "learning_rate": 3.121984382781426e-06, "loss": 4.1727, "step": 27476 }, { "epoch": 0.8392486255345144, "grad_norm": 0.5151470899581909, "learning_rate": 3.120823646696003e-06, "loss": 4.152, "step": 27477 }, { "epoch": 0.8392791692119731, "grad_norm": 0.5217791795730591, "learning_rate": 3.119663112063409e-06, "loss": 4.1981, "step": 27478 }, { "epoch": 0.8393097128894319, "grad_norm": 0.5111575722694397, "learning_rate": 3.118502778894325e-06, "loss": 4.2189, "step": 27479 }, { "epoch": 0.8393402565668907, "grad_norm": 0.5303838849067688, "learning_rate": 3.117342647199434e-06, "loss": 4.2506, "step": 27480 }, { "epoch": 0.8393708002443494, "grad_norm": 0.5191221833229065, "learning_rate": 3.116182716989427e-06, "loss": 4.1971, "step": 27481 }, { "epoch": 0.8394013439218082, "grad_norm": 0.5253806114196777, "learning_rate": 3.115022988274971e-06, "loss": 4.3283, "step": 27482 }, { "epoch": 0.8394318875992669, "grad_norm": 0.5147779583930969, "learning_rate": 3.1138634610667545e-06, "loss": 4.2274, "step": 27483 }, { "epoch": 0.8394624312767257, "grad_norm": 0.5322998762130737, "learning_rate": 3.1127041353754467e-06, "loss": 4.3229, "step": 27484 }, { "epoch": 0.8394929749541845, "grad_norm": 0.52097088098526, "learning_rate": 3.111545011211725e-06, "loss": 4.2593, "step": 27485 }, { "epoch": 0.8395235186316432, "grad_norm": 0.5171836614608765, "learning_rate": 3.1103860885862673e-06, "loss": 4.2976, "step": 27486 }, { "epoch": 0.839554062309102, "grad_norm": 0.503492534160614, "learning_rate": 3.109227367509732e-06, "loss": 4.1891, "step": 27487 }, { "epoch": 0.8395846059865608, "grad_norm": 0.5243250131607056, "learning_rate": 3.108068847992798e-06, "loss": 4.303, "step": 27488 }, { "epoch": 0.8396151496640195, "grad_norm": 0.5172983407974243, "learning_rate": 3.106910530046134e-06, "loss": 4.2911, "step": 27489 }, { "epoch": 0.8396456933414783, "grad_norm": 0.5135059356689453, "learning_rate": 3.1057524136804017e-06, "loss": 4.2064, "step": 27490 }, { "epoch": 0.8396762370189371, "grad_norm": 0.5149348974227905, "learning_rate": 3.1045944989062575e-06, "loss": 4.2819, "step": 27491 }, { "epoch": 0.8397067806963958, "grad_norm": 0.5243583917617798, "learning_rate": 3.103436785734376e-06, "loss": 4.2641, "step": 27492 }, { "epoch": 0.8397373243738546, "grad_norm": 0.5267967581748962, "learning_rate": 3.1022792741754043e-06, "loss": 4.2677, "step": 27493 }, { "epoch": 0.8397678680513134, "grad_norm": 0.5206582546234131, "learning_rate": 3.101121964240006e-06, "loss": 4.1461, "step": 27494 }, { "epoch": 0.8397984117287721, "grad_norm": 0.5178813934326172, "learning_rate": 3.0999648559388416e-06, "loss": 4.2173, "step": 27495 }, { "epoch": 0.8398289554062309, "grad_norm": 0.5141335129737854, "learning_rate": 3.098807949282556e-06, "loss": 4.2827, "step": 27496 }, { "epoch": 0.8398594990836897, "grad_norm": 0.515567421913147, "learning_rate": 3.097651244281807e-06, "loss": 4.1713, "step": 27497 }, { "epoch": 0.8398900427611484, "grad_norm": 0.5252550840377808, "learning_rate": 3.096494740947248e-06, "loss": 4.3149, "step": 27498 }, { "epoch": 0.8399205864386072, "grad_norm": 0.5222194194793701, "learning_rate": 3.095338439289519e-06, "loss": 4.2599, "step": 27499 }, { "epoch": 0.8399511301160659, "grad_norm": 0.5266978144645691, "learning_rate": 3.0941823393192763e-06, "loss": 4.3011, "step": 27500 }, { "epoch": 0.8399816737935247, "grad_norm": 0.5263999700546265, "learning_rate": 3.093026441047156e-06, "loss": 4.3296, "step": 27501 }, { "epoch": 0.8400122174709835, "grad_norm": 0.5177682638168335, "learning_rate": 3.0918707444838017e-06, "loss": 4.1664, "step": 27502 }, { "epoch": 0.8400427611484422, "grad_norm": 0.5189309120178223, "learning_rate": 3.090715249639864e-06, "loss": 4.1891, "step": 27503 }, { "epoch": 0.840073304825901, "grad_norm": 0.5316573977470398, "learning_rate": 3.08955995652597e-06, "loss": 4.2525, "step": 27504 }, { "epoch": 0.8401038485033598, "grad_norm": 0.5263019800186157, "learning_rate": 3.0884048651527693e-06, "loss": 4.3422, "step": 27505 }, { "epoch": 0.8401343921808185, "grad_norm": 0.5183097124099731, "learning_rate": 3.0872499755308842e-06, "loss": 4.2092, "step": 27506 }, { "epoch": 0.8401649358582773, "grad_norm": 0.5164127349853516, "learning_rate": 3.086095287670962e-06, "loss": 4.2984, "step": 27507 }, { "epoch": 0.8401954795357361, "grad_norm": 0.5311179757118225, "learning_rate": 3.0849408015836218e-06, "loss": 4.1893, "step": 27508 }, { "epoch": 0.8402260232131948, "grad_norm": 0.5174503922462463, "learning_rate": 3.0837865172795024e-06, "loss": 4.27, "step": 27509 }, { "epoch": 0.8402565668906536, "grad_norm": 0.5308229327201843, "learning_rate": 3.0826324347692254e-06, "loss": 4.24, "step": 27510 }, { "epoch": 0.8402871105681124, "grad_norm": 0.512937068939209, "learning_rate": 3.081478554063419e-06, "loss": 4.2693, "step": 27511 }, { "epoch": 0.8403176542455711, "grad_norm": 0.5188986659049988, "learning_rate": 3.080324875172716e-06, "loss": 4.1812, "step": 27512 }, { "epoch": 0.84034819792303, "grad_norm": 0.5116248726844788, "learning_rate": 3.0791713981077247e-06, "loss": 4.1744, "step": 27513 }, { "epoch": 0.8403787416004886, "grad_norm": 0.5321827530860901, "learning_rate": 3.078018122879078e-06, "loss": 4.2741, "step": 27514 }, { "epoch": 0.8404092852779474, "grad_norm": 0.5267541408538818, "learning_rate": 3.0768650494973878e-06, "loss": 4.2358, "step": 27515 }, { "epoch": 0.8404398289554063, "grad_norm": 0.5208742022514343, "learning_rate": 3.0757121779732693e-06, "loss": 4.2345, "step": 27516 }, { "epoch": 0.840470372632865, "grad_norm": 0.5274169445037842, "learning_rate": 3.0745595083173483e-06, "loss": 4.3267, "step": 27517 }, { "epoch": 0.8405009163103238, "grad_norm": 0.5235780477523804, "learning_rate": 3.0734070405402243e-06, "loss": 4.2673, "step": 27518 }, { "epoch": 0.8405314599877826, "grad_norm": 0.5324519276618958, "learning_rate": 3.0722547746525163e-06, "loss": 4.3487, "step": 27519 }, { "epoch": 0.8405620036652413, "grad_norm": 0.525108277797699, "learning_rate": 3.071102710664836e-06, "loss": 4.2385, "step": 27520 }, { "epoch": 0.8405925473427001, "grad_norm": 0.519836962223053, "learning_rate": 3.0699508485877907e-06, "loss": 4.2404, "step": 27521 }, { "epoch": 0.8406230910201589, "grad_norm": 0.5264012217521667, "learning_rate": 3.0687991884319755e-06, "loss": 4.3335, "step": 27522 }, { "epoch": 0.8406536346976176, "grad_norm": 0.515871524810791, "learning_rate": 3.067647730208009e-06, "loss": 4.1951, "step": 27523 }, { "epoch": 0.8406841783750764, "grad_norm": 0.5165116786956787, "learning_rate": 3.066496473926481e-06, "loss": 4.2168, "step": 27524 }, { "epoch": 0.8407147220525352, "grad_norm": 0.5216238498687744, "learning_rate": 3.0653454195979953e-06, "loss": 4.2178, "step": 27525 }, { "epoch": 0.8407452657299939, "grad_norm": 0.5162181854248047, "learning_rate": 3.0641945672331586e-06, "loss": 4.27, "step": 27526 }, { "epoch": 0.8407758094074527, "grad_norm": 0.5266979932785034, "learning_rate": 3.063043916842556e-06, "loss": 4.2388, "step": 27527 }, { "epoch": 0.8408063530849115, "grad_norm": 0.5223562121391296, "learning_rate": 3.0618934684367855e-06, "loss": 4.2357, "step": 27528 }, { "epoch": 0.8408368967623702, "grad_norm": 0.5159503817558289, "learning_rate": 3.060743222026449e-06, "loss": 4.2506, "step": 27529 }, { "epoch": 0.840867440439829, "grad_norm": 0.5128119587898254, "learning_rate": 3.059593177622122e-06, "loss": 4.1419, "step": 27530 }, { "epoch": 0.8408979841172877, "grad_norm": 0.5172625184059143, "learning_rate": 3.0584433352344066e-06, "loss": 4.1115, "step": 27531 }, { "epoch": 0.8409285277947465, "grad_norm": 0.5328326225280762, "learning_rate": 3.0572936948738806e-06, "loss": 4.3191, "step": 27532 }, { "epoch": 0.8409590714722053, "grad_norm": 0.5314822793006897, "learning_rate": 3.056144256551133e-06, "loss": 4.3093, "step": 27533 }, { "epoch": 0.840989615149664, "grad_norm": 0.534952700138092, "learning_rate": 3.054995020276752e-06, "loss": 4.3759, "step": 27534 }, { "epoch": 0.8410201588271228, "grad_norm": 0.5190327167510986, "learning_rate": 3.05384598606131e-06, "loss": 4.2528, "step": 27535 }, { "epoch": 0.8410507025045816, "grad_norm": 0.5269882678985596, "learning_rate": 3.052697153915399e-06, "loss": 4.175, "step": 27536 }, { "epoch": 0.8410812461820403, "grad_norm": 0.5292335748672485, "learning_rate": 3.0515485238495815e-06, "loss": 4.2822, "step": 27537 }, { "epoch": 0.8411117898594991, "grad_norm": 0.5265788435935974, "learning_rate": 3.0504000958744477e-06, "loss": 4.2611, "step": 27538 }, { "epoch": 0.8411423335369579, "grad_norm": 0.5161496996879578, "learning_rate": 3.0492518700005606e-06, "loss": 4.2688, "step": 27539 }, { "epoch": 0.8411728772144166, "grad_norm": 0.528551459312439, "learning_rate": 3.0481038462385036e-06, "loss": 4.2694, "step": 27540 }, { "epoch": 0.8412034208918754, "grad_norm": 0.5271220803260803, "learning_rate": 3.046956024598835e-06, "loss": 4.1737, "step": 27541 }, { "epoch": 0.8412339645693342, "grad_norm": 0.5234312415122986, "learning_rate": 3.0458084050921293e-06, "loss": 4.2615, "step": 27542 }, { "epoch": 0.8412645082467929, "grad_norm": 0.5345685482025146, "learning_rate": 3.044660987728956e-06, "loss": 4.132, "step": 27543 }, { "epoch": 0.8412950519242517, "grad_norm": 0.5219985246658325, "learning_rate": 3.0435137725198764e-06, "loss": 4.2483, "step": 27544 }, { "epoch": 0.8413255956017105, "grad_norm": 0.5314735770225525, "learning_rate": 3.042366759475451e-06, "loss": 4.2818, "step": 27545 }, { "epoch": 0.8413561392791692, "grad_norm": 0.5359415411949158, "learning_rate": 3.0412199486062525e-06, "loss": 4.2768, "step": 27546 }, { "epoch": 0.841386682956628, "grad_norm": 0.5199763774871826, "learning_rate": 3.040073339922825e-06, "loss": 4.2787, "step": 27547 }, { "epoch": 0.8414172266340867, "grad_norm": 0.5291706323623657, "learning_rate": 3.0389269334357375e-06, "loss": 4.2201, "step": 27548 }, { "epoch": 0.8414477703115455, "grad_norm": 0.5225903391838074, "learning_rate": 3.037780729155537e-06, "loss": 4.2245, "step": 27549 }, { "epoch": 0.8414783139890043, "grad_norm": 0.5259420871734619, "learning_rate": 3.0366347270927824e-06, "loss": 4.3337, "step": 27550 }, { "epoch": 0.841508857666463, "grad_norm": 0.5242589116096497, "learning_rate": 3.0354889272580263e-06, "loss": 4.2405, "step": 27551 }, { "epoch": 0.8415394013439218, "grad_norm": 0.5304179787635803, "learning_rate": 3.034343329661815e-06, "loss": 4.2403, "step": 27552 }, { "epoch": 0.8415699450213806, "grad_norm": 0.5183896422386169, "learning_rate": 3.033197934314702e-06, "loss": 4.3069, "step": 27553 }, { "epoch": 0.8416004886988393, "grad_norm": 0.5393655896186829, "learning_rate": 3.0320527412272286e-06, "loss": 4.276, "step": 27554 }, { "epoch": 0.8416310323762981, "grad_norm": 0.5295876860618591, "learning_rate": 3.0309077504099364e-06, "loss": 4.3408, "step": 27555 }, { "epoch": 0.8416615760537569, "grad_norm": 0.5201375484466553, "learning_rate": 3.0297629618733727e-06, "loss": 4.2252, "step": 27556 }, { "epoch": 0.8416921197312156, "grad_norm": 0.5306163430213928, "learning_rate": 3.0286183756280812e-06, "loss": 4.2495, "step": 27557 }, { "epoch": 0.8417226634086744, "grad_norm": 0.5124179124832153, "learning_rate": 3.0274739916845903e-06, "loss": 4.2023, "step": 27558 }, { "epoch": 0.8417532070861332, "grad_norm": 0.5331820845603943, "learning_rate": 3.0263298100534466e-06, "loss": 4.3976, "step": 27559 }, { "epoch": 0.8417837507635919, "grad_norm": 0.5245589017868042, "learning_rate": 3.0251858307451865e-06, "loss": 4.2447, "step": 27560 }, { "epoch": 0.8418142944410507, "grad_norm": 0.5162078142166138, "learning_rate": 3.0240420537703317e-06, "loss": 4.1457, "step": 27561 }, { "epoch": 0.8418448381185095, "grad_norm": 0.5238122344017029, "learning_rate": 3.0228984791394216e-06, "loss": 4.2201, "step": 27562 }, { "epoch": 0.8418753817959682, "grad_norm": 0.5311130881309509, "learning_rate": 3.021755106862992e-06, "loss": 4.3391, "step": 27563 }, { "epoch": 0.841905925473427, "grad_norm": 0.5310178995132446, "learning_rate": 3.020611936951556e-06, "loss": 4.2807, "step": 27564 }, { "epoch": 0.8419364691508857, "grad_norm": 0.525424063205719, "learning_rate": 3.019468969415651e-06, "loss": 4.3368, "step": 27565 }, { "epoch": 0.8419670128283445, "grad_norm": 0.5205733180046082, "learning_rate": 3.0183262042657923e-06, "loss": 4.2929, "step": 27566 }, { "epoch": 0.8419975565058033, "grad_norm": 0.5163671374320984, "learning_rate": 3.0171836415125108e-06, "loss": 4.1799, "step": 27567 }, { "epoch": 0.842028100183262, "grad_norm": 0.5239550471305847, "learning_rate": 3.016041281166318e-06, "loss": 4.2062, "step": 27568 }, { "epoch": 0.8420586438607208, "grad_norm": 0.5286685824394226, "learning_rate": 3.014899123237741e-06, "loss": 4.3341, "step": 27569 }, { "epoch": 0.8420891875381796, "grad_norm": 0.5243308544158936, "learning_rate": 3.0137571677372854e-06, "loss": 4.2278, "step": 27570 }, { "epoch": 0.8421197312156383, "grad_norm": 0.5230745673179626, "learning_rate": 3.012615414675479e-06, "loss": 4.1702, "step": 27571 }, { "epoch": 0.8421502748930971, "grad_norm": 0.519710898399353, "learning_rate": 3.0114738640628193e-06, "loss": 4.2352, "step": 27572 }, { "epoch": 0.8421808185705559, "grad_norm": 0.5247854590415955, "learning_rate": 3.010332515909828e-06, "loss": 4.2212, "step": 27573 }, { "epoch": 0.8422113622480146, "grad_norm": 0.5251541137695312, "learning_rate": 3.009191370227013e-06, "loss": 4.2079, "step": 27574 }, { "epoch": 0.8422419059254734, "grad_norm": 0.5289444923400879, "learning_rate": 3.0080504270248777e-06, "loss": 4.2482, "step": 27575 }, { "epoch": 0.8422724496029322, "grad_norm": 0.5284065008163452, "learning_rate": 3.0069096863139275e-06, "loss": 4.2678, "step": 27576 }, { "epoch": 0.8423029932803909, "grad_norm": 0.5240095853805542, "learning_rate": 3.005769148104673e-06, "loss": 4.1691, "step": 27577 }, { "epoch": 0.8423335369578497, "grad_norm": 0.5268610119819641, "learning_rate": 3.004628812407603e-06, "loss": 4.2066, "step": 27578 }, { "epoch": 0.8423640806353085, "grad_norm": 0.5266751646995544, "learning_rate": 3.0034886792332265e-06, "loss": 4.2465, "step": 27579 }, { "epoch": 0.8423946243127672, "grad_norm": 0.5142289400100708, "learning_rate": 3.002348748592046e-06, "loss": 4.2192, "step": 27580 }, { "epoch": 0.842425167990226, "grad_norm": 0.5148634314537048, "learning_rate": 3.0012090204945443e-06, "loss": 4.2358, "step": 27581 }, { "epoch": 0.8424557116676847, "grad_norm": 0.5347248911857605, "learning_rate": 3.000069494951227e-06, "loss": 4.2084, "step": 27582 }, { "epoch": 0.8424862553451435, "grad_norm": 0.5247768759727478, "learning_rate": 2.9989301719725747e-06, "loss": 4.2444, "step": 27583 }, { "epoch": 0.8425167990226023, "grad_norm": 0.5302004218101501, "learning_rate": 2.9977910515690903e-06, "loss": 4.2052, "step": 27584 }, { "epoch": 0.842547342700061, "grad_norm": 0.5273535251617432, "learning_rate": 2.996652133751254e-06, "loss": 4.2602, "step": 27585 }, { "epoch": 0.8425778863775198, "grad_norm": 0.5273438096046448, "learning_rate": 2.9955134185295524e-06, "loss": 4.2281, "step": 27586 }, { "epoch": 0.8426084300549787, "grad_norm": 0.5151602625846863, "learning_rate": 2.994374905914471e-06, "loss": 4.2107, "step": 27587 }, { "epoch": 0.8426389737324373, "grad_norm": 0.522794783115387, "learning_rate": 2.993236595916499e-06, "loss": 4.3203, "step": 27588 }, { "epoch": 0.8426695174098962, "grad_norm": 0.5158728957176208, "learning_rate": 2.9920984885461077e-06, "loss": 4.2216, "step": 27589 }, { "epoch": 0.842700061087355, "grad_norm": 0.5244628190994263, "learning_rate": 2.9909605838137815e-06, "loss": 4.2324, "step": 27590 }, { "epoch": 0.8427306047648137, "grad_norm": 0.5234636068344116, "learning_rate": 2.9898228817300006e-06, "loss": 4.2232, "step": 27591 }, { "epoch": 0.8427611484422725, "grad_norm": 0.5273486375808716, "learning_rate": 2.9886853823052342e-06, "loss": 4.1446, "step": 27592 }, { "epoch": 0.8427916921197313, "grad_norm": 0.5208358764648438, "learning_rate": 2.987548085549957e-06, "loss": 4.2158, "step": 27593 }, { "epoch": 0.84282223579719, "grad_norm": 0.5232867002487183, "learning_rate": 2.9864109914746473e-06, "loss": 4.264, "step": 27594 }, { "epoch": 0.8428527794746488, "grad_norm": 0.5443152785301208, "learning_rate": 2.985274100089763e-06, "loss": 4.2433, "step": 27595 }, { "epoch": 0.8428833231521076, "grad_norm": 0.5185171961784363, "learning_rate": 2.9841374114057824e-06, "loss": 4.1803, "step": 27596 }, { "epoch": 0.8429138668295663, "grad_norm": 0.5281649827957153, "learning_rate": 2.9830009254331713e-06, "loss": 4.2043, "step": 27597 }, { "epoch": 0.8429444105070251, "grad_norm": 0.5268514156341553, "learning_rate": 2.9818646421823857e-06, "loss": 4.2296, "step": 27598 }, { "epoch": 0.8429749541844838, "grad_norm": 0.530737578868866, "learning_rate": 2.980728561663898e-06, "loss": 4.1887, "step": 27599 }, { "epoch": 0.8430054978619426, "grad_norm": 0.5366184711456299, "learning_rate": 2.979592683888166e-06, "loss": 4.2367, "step": 27600 }, { "epoch": 0.8430360415394014, "grad_norm": 0.5187533497810364, "learning_rate": 2.978457008865637e-06, "loss": 4.2797, "step": 27601 }, { "epoch": 0.8430665852168601, "grad_norm": 0.5159745812416077, "learning_rate": 2.9773215366067835e-06, "loss": 4.1557, "step": 27602 }, { "epoch": 0.8430971288943189, "grad_norm": 0.5145462155342102, "learning_rate": 2.9761862671220496e-06, "loss": 4.2441, "step": 27603 }, { "epoch": 0.8431276725717777, "grad_norm": 0.525440514087677, "learning_rate": 2.975051200421891e-06, "loss": 4.2806, "step": 27604 }, { "epoch": 0.8431582162492364, "grad_norm": 0.5235674977302551, "learning_rate": 2.973916336516766e-06, "loss": 4.189, "step": 27605 }, { "epoch": 0.8431887599266952, "grad_norm": 0.5290127396583557, "learning_rate": 2.9727816754171106e-06, "loss": 4.3028, "step": 27606 }, { "epoch": 0.843219303604154, "grad_norm": 0.5233579874038696, "learning_rate": 2.9716472171333833e-06, "loss": 4.2304, "step": 27607 }, { "epoch": 0.8432498472816127, "grad_norm": 0.5214971899986267, "learning_rate": 2.970512961676028e-06, "loss": 4.2528, "step": 27608 }, { "epoch": 0.8432803909590715, "grad_norm": 0.5239723324775696, "learning_rate": 2.9693789090554814e-06, "loss": 4.183, "step": 27609 }, { "epoch": 0.8433109346365303, "grad_norm": 0.5252644419670105, "learning_rate": 2.968245059282193e-06, "loss": 4.2419, "step": 27610 }, { "epoch": 0.843341478313989, "grad_norm": 0.5310831665992737, "learning_rate": 2.967111412366602e-06, "loss": 4.2502, "step": 27611 }, { "epoch": 0.8433720219914478, "grad_norm": 0.5125880837440491, "learning_rate": 2.965977968319139e-06, "loss": 4.2067, "step": 27612 }, { "epoch": 0.8434025656689066, "grad_norm": 0.5189141035079956, "learning_rate": 2.964844727150254e-06, "loss": 4.2804, "step": 27613 }, { "epoch": 0.8434331093463653, "grad_norm": 0.5185500383377075, "learning_rate": 2.963711688870366e-06, "loss": 4.2811, "step": 27614 }, { "epoch": 0.8434636530238241, "grad_norm": 0.5283374786376953, "learning_rate": 2.9625788534899197e-06, "loss": 4.2358, "step": 27615 }, { "epoch": 0.8434941967012828, "grad_norm": 0.5266808271408081, "learning_rate": 2.9614462210193344e-06, "loss": 4.2347, "step": 27616 }, { "epoch": 0.8435247403787416, "grad_norm": 0.5278066396713257, "learning_rate": 2.960313791469049e-06, "loss": 4.2664, "step": 27617 }, { "epoch": 0.8435552840562004, "grad_norm": 0.5204272866249084, "learning_rate": 2.9591815648494834e-06, "loss": 4.1803, "step": 27618 }, { "epoch": 0.8435858277336591, "grad_norm": 0.5207576751708984, "learning_rate": 2.9580495411710705e-06, "loss": 4.2658, "step": 27619 }, { "epoch": 0.8436163714111179, "grad_norm": 0.5299383401870728, "learning_rate": 2.9569177204442217e-06, "loss": 4.3003, "step": 27620 }, { "epoch": 0.8436469150885767, "grad_norm": 0.5309410095214844, "learning_rate": 2.955786102679367e-06, "loss": 4.2456, "step": 27621 }, { "epoch": 0.8436774587660354, "grad_norm": 0.5261467695236206, "learning_rate": 2.9546546878869264e-06, "loss": 4.268, "step": 27622 }, { "epoch": 0.8437080024434942, "grad_norm": 0.536931037902832, "learning_rate": 2.9535234760773106e-06, "loss": 4.2564, "step": 27623 }, { "epoch": 0.843738546120953, "grad_norm": 0.518910825252533, "learning_rate": 2.9523924672609393e-06, "loss": 4.1379, "step": 27624 }, { "epoch": 0.8437690897984117, "grad_norm": 0.5240901708602905, "learning_rate": 2.951261661448232e-06, "loss": 4.1544, "step": 27625 }, { "epoch": 0.8437996334758705, "grad_norm": 0.5182163715362549, "learning_rate": 2.9501310586495884e-06, "loss": 4.2634, "step": 27626 }, { "epoch": 0.8438301771533293, "grad_norm": 0.5166484117507935, "learning_rate": 2.949000658875428e-06, "loss": 4.1121, "step": 27627 }, { "epoch": 0.843860720830788, "grad_norm": 0.5201172828674316, "learning_rate": 2.9478704621361597e-06, "loss": 4.2584, "step": 27628 }, { "epoch": 0.8438912645082468, "grad_norm": 0.5260877013206482, "learning_rate": 2.94674046844218e-06, "loss": 4.2332, "step": 27629 }, { "epoch": 0.8439218081857056, "grad_norm": 0.5284245610237122, "learning_rate": 2.945610677803903e-06, "loss": 4.2673, "step": 27630 }, { "epoch": 0.8439523518631643, "grad_norm": 0.5284184217453003, "learning_rate": 2.9444810902317323e-06, "loss": 4.223, "step": 27631 }, { "epoch": 0.8439828955406231, "grad_norm": 0.5281185507774353, "learning_rate": 2.9433517057360556e-06, "loss": 4.1867, "step": 27632 }, { "epoch": 0.8440134392180818, "grad_norm": 0.5142526626586914, "learning_rate": 2.942222524327287e-06, "loss": 4.3194, "step": 27633 }, { "epoch": 0.8440439828955406, "grad_norm": 0.51439368724823, "learning_rate": 2.9410935460158105e-06, "loss": 4.261, "step": 27634 }, { "epoch": 0.8440745265729994, "grad_norm": 0.5237551331520081, "learning_rate": 2.939964770812026e-06, "loss": 4.1947, "step": 27635 }, { "epoch": 0.8441050702504581, "grad_norm": 0.5157970786094666, "learning_rate": 2.9388361987263358e-06, "loss": 4.2477, "step": 27636 }, { "epoch": 0.8441356139279169, "grad_norm": 0.5292183756828308, "learning_rate": 2.937707829769115e-06, "loss": 4.276, "step": 27637 }, { "epoch": 0.8441661576053757, "grad_norm": 0.5192272663116455, "learning_rate": 2.9365796639507644e-06, "loss": 4.2031, "step": 27638 }, { "epoch": 0.8441967012828344, "grad_norm": 0.522224485874176, "learning_rate": 2.9354517012816716e-06, "loss": 4.1925, "step": 27639 }, { "epoch": 0.8442272449602932, "grad_norm": 0.5245406627655029, "learning_rate": 2.9343239417722157e-06, "loss": 4.3207, "step": 27640 }, { "epoch": 0.844257788637752, "grad_norm": 0.5217563509941101, "learning_rate": 2.9331963854327848e-06, "loss": 4.2489, "step": 27641 }, { "epoch": 0.8442883323152107, "grad_norm": 0.5206745862960815, "learning_rate": 2.9320690322737654e-06, "loss": 4.1878, "step": 27642 }, { "epoch": 0.8443188759926695, "grad_norm": 0.5170406699180603, "learning_rate": 2.9309418823055268e-06, "loss": 4.2491, "step": 27643 }, { "epoch": 0.8443494196701283, "grad_norm": 0.5306368470191956, "learning_rate": 2.9298149355384554e-06, "loss": 4.2166, "step": 27644 }, { "epoch": 0.844379963347587, "grad_norm": 0.5192552804946899, "learning_rate": 2.9286881919829284e-06, "loss": 4.2716, "step": 27645 }, { "epoch": 0.8444105070250458, "grad_norm": 0.5161667466163635, "learning_rate": 2.927561651649316e-06, "loss": 4.174, "step": 27646 }, { "epoch": 0.8444410507025046, "grad_norm": 0.5231190919876099, "learning_rate": 2.926435314547987e-06, "loss": 4.2468, "step": 27647 }, { "epoch": 0.8444715943799633, "grad_norm": 0.5328113436698914, "learning_rate": 2.9253091806893256e-06, "loss": 4.2998, "step": 27648 }, { "epoch": 0.8445021380574221, "grad_norm": 0.5171188712120056, "learning_rate": 2.9241832500836842e-06, "loss": 4.1701, "step": 27649 }, { "epoch": 0.8445326817348808, "grad_norm": 0.5246210098266602, "learning_rate": 2.923057522741443e-06, "loss": 4.2809, "step": 27650 }, { "epoch": 0.8445632254123396, "grad_norm": 0.5219091773033142, "learning_rate": 2.921931998672958e-06, "loss": 4.2623, "step": 27651 }, { "epoch": 0.8445937690897984, "grad_norm": 0.5323207974433899, "learning_rate": 2.920806677888596e-06, "loss": 4.3021, "step": 27652 }, { "epoch": 0.8446243127672571, "grad_norm": 0.5340846180915833, "learning_rate": 2.9196815603987236e-06, "loss": 4.2745, "step": 27653 }, { "epoch": 0.8446548564447159, "grad_norm": 0.526480495929718, "learning_rate": 2.918556646213691e-06, "loss": 4.2496, "step": 27654 }, { "epoch": 0.8446854001221747, "grad_norm": 0.5148622989654541, "learning_rate": 2.9174319353438616e-06, "loss": 4.1838, "step": 27655 }, { "epoch": 0.8447159437996334, "grad_norm": 0.5254064798355103, "learning_rate": 2.9163074277995943e-06, "loss": 4.2744, "step": 27656 }, { "epoch": 0.8447464874770922, "grad_norm": 0.5378144383430481, "learning_rate": 2.9151831235912336e-06, "loss": 4.2754, "step": 27657 }, { "epoch": 0.844777031154551, "grad_norm": 0.532666802406311, "learning_rate": 2.914059022729135e-06, "loss": 4.3384, "step": 27658 }, { "epoch": 0.8448075748320097, "grad_norm": 0.5334048867225647, "learning_rate": 2.912935125223659e-06, "loss": 4.2938, "step": 27659 }, { "epoch": 0.8448381185094685, "grad_norm": 0.5302366018295288, "learning_rate": 2.9118114310851373e-06, "loss": 4.2276, "step": 27660 }, { "epoch": 0.8448686621869274, "grad_norm": 0.5219445824623108, "learning_rate": 2.9106879403239306e-06, "loss": 4.2979, "step": 27661 }, { "epoch": 0.844899205864386, "grad_norm": 0.5257343053817749, "learning_rate": 2.9095646529503724e-06, "loss": 4.2653, "step": 27662 }, { "epoch": 0.8449297495418449, "grad_norm": 0.5235369205474854, "learning_rate": 2.908441568974815e-06, "loss": 4.2022, "step": 27663 }, { "epoch": 0.8449602932193035, "grad_norm": 0.5283836722373962, "learning_rate": 2.9073186884075953e-06, "loss": 4.2179, "step": 27664 }, { "epoch": 0.8449908368967624, "grad_norm": 0.5238118767738342, "learning_rate": 2.9061960112590462e-06, "loss": 4.2243, "step": 27665 }, { "epoch": 0.8450213805742212, "grad_norm": 0.5207312703132629, "learning_rate": 2.905073537539507e-06, "loss": 4.2531, "step": 27666 }, { "epoch": 0.8450519242516799, "grad_norm": 0.5293183922767639, "learning_rate": 2.903951267259325e-06, "loss": 4.2881, "step": 27667 }, { "epoch": 0.8450824679291387, "grad_norm": 0.5187250971794128, "learning_rate": 2.9028292004288164e-06, "loss": 4.145, "step": 27668 }, { "epoch": 0.8451130116065975, "grad_norm": 0.5247485041618347, "learning_rate": 2.9017073370583207e-06, "loss": 4.2624, "step": 27669 }, { "epoch": 0.8451435552840562, "grad_norm": 0.5196885466575623, "learning_rate": 2.900585677158174e-06, "loss": 4.1908, "step": 27670 }, { "epoch": 0.845174098961515, "grad_norm": 0.5214905738830566, "learning_rate": 2.899464220738693e-06, "loss": 4.2401, "step": 27671 }, { "epoch": 0.8452046426389738, "grad_norm": 0.5289657711982727, "learning_rate": 2.898342967810205e-06, "loss": 4.2667, "step": 27672 }, { "epoch": 0.8452351863164325, "grad_norm": 0.5284175872802734, "learning_rate": 2.8972219183830445e-06, "loss": 4.2911, "step": 27673 }, { "epoch": 0.8452657299938913, "grad_norm": 0.5196959376335144, "learning_rate": 2.896101072467519e-06, "loss": 4.2336, "step": 27674 }, { "epoch": 0.8452962736713501, "grad_norm": 0.5278449654579163, "learning_rate": 2.8949804300739567e-06, "loss": 4.2776, "step": 27675 }, { "epoch": 0.8453268173488088, "grad_norm": 0.5298087000846863, "learning_rate": 2.89385999121268e-06, "loss": 4.2775, "step": 27676 }, { "epoch": 0.8453573610262676, "grad_norm": 0.5179811120033264, "learning_rate": 2.8927397558940002e-06, "loss": 4.2993, "step": 27677 }, { "epoch": 0.8453879047037264, "grad_norm": 0.5229349136352539, "learning_rate": 2.8916197241282276e-06, "loss": 4.235, "step": 27678 }, { "epoch": 0.8454184483811851, "grad_norm": 0.53391033411026, "learning_rate": 2.8904998959256828e-06, "loss": 4.2751, "step": 27679 }, { "epoch": 0.8454489920586439, "grad_norm": 0.5211958885192871, "learning_rate": 2.889380271296668e-06, "loss": 4.2723, "step": 27680 }, { "epoch": 0.8454795357361026, "grad_norm": 0.5304234623908997, "learning_rate": 2.8882608502515036e-06, "loss": 4.322, "step": 27681 }, { "epoch": 0.8455100794135614, "grad_norm": 0.5231600403785706, "learning_rate": 2.887141632800483e-06, "loss": 4.2139, "step": 27682 }, { "epoch": 0.8455406230910202, "grad_norm": 0.5334931015968323, "learning_rate": 2.886022618953921e-06, "loss": 4.3274, "step": 27683 }, { "epoch": 0.8455711667684789, "grad_norm": 0.5266143083572388, "learning_rate": 2.8849038087221226e-06, "loss": 4.1664, "step": 27684 }, { "epoch": 0.8456017104459377, "grad_norm": 0.532599687576294, "learning_rate": 2.88378520211538e-06, "loss": 4.2563, "step": 27685 }, { "epoch": 0.8456322541233965, "grad_norm": 0.5295602679252625, "learning_rate": 2.882666799143999e-06, "loss": 4.298, "step": 27686 }, { "epoch": 0.8456627978008552, "grad_norm": 0.5269266963005066, "learning_rate": 2.881548599818279e-06, "loss": 4.2689, "step": 27687 }, { "epoch": 0.845693341478314, "grad_norm": 0.5336281061172485, "learning_rate": 2.8804306041485095e-06, "loss": 4.2509, "step": 27688 }, { "epoch": 0.8457238851557728, "grad_norm": 0.5104916095733643, "learning_rate": 2.879312812144988e-06, "loss": 4.27, "step": 27689 }, { "epoch": 0.8457544288332315, "grad_norm": 0.5332537293434143, "learning_rate": 2.8781952238180144e-06, "loss": 4.2964, "step": 27690 }, { "epoch": 0.8457849725106903, "grad_norm": 0.5302167534828186, "learning_rate": 2.8770778391778635e-06, "loss": 4.2595, "step": 27691 }, { "epoch": 0.8458155161881491, "grad_norm": 0.5350817441940308, "learning_rate": 2.8759606582348385e-06, "loss": 4.2839, "step": 27692 }, { "epoch": 0.8458460598656078, "grad_norm": 0.5301754474639893, "learning_rate": 2.8748436809992118e-06, "loss": 4.3117, "step": 27693 }, { "epoch": 0.8458766035430666, "grad_norm": 0.519822359085083, "learning_rate": 2.8737269074812807e-06, "loss": 4.2925, "step": 27694 }, { "epoch": 0.8459071472205254, "grad_norm": 0.5282449126243591, "learning_rate": 2.8726103376913173e-06, "loss": 4.2561, "step": 27695 }, { "epoch": 0.8459376908979841, "grad_norm": 0.5359607934951782, "learning_rate": 2.8714939716396105e-06, "loss": 4.2737, "step": 27696 }, { "epoch": 0.8459682345754429, "grad_norm": 0.5349973440170288, "learning_rate": 2.870377809336433e-06, "loss": 4.1994, "step": 27697 }, { "epoch": 0.8459987782529016, "grad_norm": 0.5251171588897705, "learning_rate": 2.869261850792071e-06, "loss": 4.2504, "step": 27698 }, { "epoch": 0.8460293219303604, "grad_norm": 0.520735502243042, "learning_rate": 2.8681460960167857e-06, "loss": 4.2212, "step": 27699 }, { "epoch": 0.8460598656078192, "grad_norm": 0.5277981758117676, "learning_rate": 2.8670305450208603e-06, "loss": 4.3209, "step": 27700 }, { "epoch": 0.8460904092852779, "grad_norm": 0.5332475900650024, "learning_rate": 2.86591519781457e-06, "loss": 4.2966, "step": 27701 }, { "epoch": 0.8461209529627367, "grad_norm": 0.5285179615020752, "learning_rate": 2.8648000544081734e-06, "loss": 4.2703, "step": 27702 }, { "epoch": 0.8461514966401955, "grad_norm": 0.5331529974937439, "learning_rate": 2.8636851148119427e-06, "loss": 4.2113, "step": 27703 }, { "epoch": 0.8461820403176542, "grad_norm": 0.5271046757698059, "learning_rate": 2.8625703790361473e-06, "loss": 4.2521, "step": 27704 }, { "epoch": 0.846212583995113, "grad_norm": 0.5255555510520935, "learning_rate": 2.8614558470910464e-06, "loss": 4.2167, "step": 27705 }, { "epoch": 0.8462431276725718, "grad_norm": 0.5189014673233032, "learning_rate": 2.860341518986903e-06, "loss": 4.1542, "step": 27706 }, { "epoch": 0.8462736713500305, "grad_norm": 0.5212870240211487, "learning_rate": 2.8592273947339847e-06, "loss": 4.2638, "step": 27707 }, { "epoch": 0.8463042150274893, "grad_norm": 0.5240402817726135, "learning_rate": 2.8581134743425356e-06, "loss": 4.2508, "step": 27708 }, { "epoch": 0.8463347587049481, "grad_norm": 0.5293326377868652, "learning_rate": 2.8569997578228288e-06, "loss": 4.2442, "step": 27709 }, { "epoch": 0.8463653023824068, "grad_norm": 0.5371275544166565, "learning_rate": 2.8558862451851076e-06, "loss": 4.3168, "step": 27710 }, { "epoch": 0.8463958460598656, "grad_norm": 0.51395583152771, "learning_rate": 2.85477293643962e-06, "loss": 4.1787, "step": 27711 }, { "epoch": 0.8464263897373244, "grad_norm": 0.5277537107467651, "learning_rate": 2.853659831596628e-06, "loss": 4.2044, "step": 27712 }, { "epoch": 0.8464569334147831, "grad_norm": 0.5358405113220215, "learning_rate": 2.8525469306663803e-06, "loss": 4.3723, "step": 27713 }, { "epoch": 0.8464874770922419, "grad_norm": 0.523605465888977, "learning_rate": 2.8514342336591144e-06, "loss": 4.3012, "step": 27714 }, { "epoch": 0.8465180207697006, "grad_norm": 0.5863571166992188, "learning_rate": 2.850321740585085e-06, "loss": 4.1954, "step": 27715 }, { "epoch": 0.8465485644471594, "grad_norm": 0.5268048644065857, "learning_rate": 2.849209451454529e-06, "loss": 4.1802, "step": 27716 }, { "epoch": 0.8465791081246182, "grad_norm": 0.5212218761444092, "learning_rate": 2.848097366277688e-06, "loss": 4.2554, "step": 27717 }, { "epoch": 0.8466096518020769, "grad_norm": 0.5192314386367798, "learning_rate": 2.8469854850648126e-06, "loss": 4.1216, "step": 27718 }, { "epoch": 0.8466401954795357, "grad_norm": 0.5383297204971313, "learning_rate": 2.8458738078261245e-06, "loss": 4.2857, "step": 27719 }, { "epoch": 0.8466707391569945, "grad_norm": 0.5255829095840454, "learning_rate": 2.8447623345718656e-06, "loss": 4.2184, "step": 27720 }, { "epoch": 0.8467012828344532, "grad_norm": 0.5194351673126221, "learning_rate": 2.8436510653122776e-06, "loss": 4.3159, "step": 27721 }, { "epoch": 0.846731826511912, "grad_norm": 0.5298538208007812, "learning_rate": 2.8425400000575806e-06, "loss": 4.2737, "step": 27722 }, { "epoch": 0.8467623701893708, "grad_norm": 0.5264773368835449, "learning_rate": 2.8414291388180136e-06, "loss": 4.2477, "step": 27723 }, { "epoch": 0.8467929138668295, "grad_norm": 0.5231369733810425, "learning_rate": 2.8403184816037987e-06, "loss": 4.2354, "step": 27724 }, { "epoch": 0.8468234575442883, "grad_norm": 0.5187313556671143, "learning_rate": 2.839208028425169e-06, "loss": 4.262, "step": 27725 }, { "epoch": 0.8468540012217471, "grad_norm": 0.5216492414474487, "learning_rate": 2.8380977792923395e-06, "loss": 4.24, "step": 27726 }, { "epoch": 0.8468845448992058, "grad_norm": 0.5282841324806213, "learning_rate": 2.836987734215543e-06, "loss": 4.1736, "step": 27727 }, { "epoch": 0.8469150885766646, "grad_norm": 0.5253962874412537, "learning_rate": 2.8358778932049913e-06, "loss": 4.2267, "step": 27728 }, { "epoch": 0.8469456322541234, "grad_norm": 0.5317990779876709, "learning_rate": 2.834768256270906e-06, "loss": 4.2161, "step": 27729 }, { "epoch": 0.8469761759315821, "grad_norm": 0.5270935297012329, "learning_rate": 2.833658823423513e-06, "loss": 4.3095, "step": 27730 }, { "epoch": 0.847006719609041, "grad_norm": 0.5280472636222839, "learning_rate": 2.832549594673015e-06, "loss": 4.2421, "step": 27731 }, { "epoch": 0.8470372632864996, "grad_norm": 0.5156907439231873, "learning_rate": 2.8314405700296336e-06, "loss": 4.1209, "step": 27732 }, { "epoch": 0.8470678069639584, "grad_norm": 0.5239344239234924, "learning_rate": 2.83033174950357e-06, "loss": 4.3171, "step": 27733 }, { "epoch": 0.8470983506414173, "grad_norm": 0.5235161781311035, "learning_rate": 2.829223133105044e-06, "loss": 4.1238, "step": 27734 }, { "epoch": 0.847128894318876, "grad_norm": 0.5244288444519043, "learning_rate": 2.8281147208442633e-06, "loss": 4.3488, "step": 27735 }, { "epoch": 0.8471594379963348, "grad_norm": 0.5208213329315186, "learning_rate": 2.8270065127314253e-06, "loss": 4.2108, "step": 27736 }, { "epoch": 0.8471899816737936, "grad_norm": 0.5269577503204346, "learning_rate": 2.8258985087767394e-06, "loss": 4.3121, "step": 27737 }, { "epoch": 0.8472205253512523, "grad_norm": 0.5318726301193237, "learning_rate": 2.82479070899041e-06, "loss": 4.2499, "step": 27738 }, { "epoch": 0.8472510690287111, "grad_norm": 0.5322127938270569, "learning_rate": 2.8236831133826304e-06, "loss": 4.3313, "step": 27739 }, { "epoch": 0.8472816127061699, "grad_norm": 0.5383973121643066, "learning_rate": 2.8225757219636052e-06, "loss": 4.1277, "step": 27740 }, { "epoch": 0.8473121563836286, "grad_norm": 0.518540620803833, "learning_rate": 2.8214685347435293e-06, "loss": 4.2967, "step": 27741 }, { "epoch": 0.8473427000610874, "grad_norm": 0.5328620672225952, "learning_rate": 2.820361551732592e-06, "loss": 4.2845, "step": 27742 }, { "epoch": 0.8473732437385462, "grad_norm": 0.5455102920532227, "learning_rate": 2.819254772940988e-06, "loss": 4.1611, "step": 27743 }, { "epoch": 0.8474037874160049, "grad_norm": 0.5252188444137573, "learning_rate": 2.818148198378914e-06, "loss": 4.2479, "step": 27744 }, { "epoch": 0.8474343310934637, "grad_norm": 0.5217140913009644, "learning_rate": 2.817041828056549e-06, "loss": 4.1887, "step": 27745 }, { "epoch": 0.8474648747709225, "grad_norm": 0.5249258279800415, "learning_rate": 2.815935661984087e-06, "loss": 4.3045, "step": 27746 }, { "epoch": 0.8474954184483812, "grad_norm": 0.5222756266593933, "learning_rate": 2.814829700171717e-06, "loss": 4.3302, "step": 27747 }, { "epoch": 0.84752596212584, "grad_norm": 0.5317671298980713, "learning_rate": 2.813723942629609e-06, "loss": 4.2455, "step": 27748 }, { "epoch": 0.8475565058032987, "grad_norm": 0.511833131313324, "learning_rate": 2.8126183893679575e-06, "loss": 4.1574, "step": 27749 }, { "epoch": 0.8475870494807575, "grad_norm": 0.5211731791496277, "learning_rate": 2.811513040396932e-06, "loss": 4.2889, "step": 27750 }, { "epoch": 0.8476175931582163, "grad_norm": 0.5304078459739685, "learning_rate": 2.8104078957267134e-06, "loss": 4.1801, "step": 27751 }, { "epoch": 0.847648136835675, "grad_norm": 0.5302100777626038, "learning_rate": 2.809302955367482e-06, "loss": 4.2082, "step": 27752 }, { "epoch": 0.8476786805131338, "grad_norm": 0.5205042362213135, "learning_rate": 2.8081982193294027e-06, "loss": 4.1982, "step": 27753 }, { "epoch": 0.8477092241905926, "grad_norm": 0.5329110026359558, "learning_rate": 2.8070936876226555e-06, "loss": 4.1267, "step": 27754 }, { "epoch": 0.8477397678680513, "grad_norm": 0.5248117446899414, "learning_rate": 2.8059893602574077e-06, "loss": 4.2966, "step": 27755 }, { "epoch": 0.8477703115455101, "grad_norm": 0.5188255906105042, "learning_rate": 2.8048852372438317e-06, "loss": 4.2227, "step": 27756 }, { "epoch": 0.8478008552229689, "grad_norm": 0.5275401473045349, "learning_rate": 2.80378131859208e-06, "loss": 4.3093, "step": 27757 }, { "epoch": 0.8478313989004276, "grad_norm": 0.519511878490448, "learning_rate": 2.8026776043123315e-06, "loss": 4.0859, "step": 27758 }, { "epoch": 0.8478619425778864, "grad_norm": 0.5326976776123047, "learning_rate": 2.8015740944147385e-06, "loss": 4.2203, "step": 27759 }, { "epoch": 0.8478924862553452, "grad_norm": 0.5253163576126099, "learning_rate": 2.8004707889094678e-06, "loss": 4.2419, "step": 27760 }, { "epoch": 0.8479230299328039, "grad_norm": 0.5249308943748474, "learning_rate": 2.799367687806681e-06, "loss": 4.2239, "step": 27761 }, { "epoch": 0.8479535736102627, "grad_norm": 0.5268840193748474, "learning_rate": 2.7982647911165228e-06, "loss": 4.2458, "step": 27762 }, { "epoch": 0.8479841172877215, "grad_norm": 0.5196308493614197, "learning_rate": 2.797162098849157e-06, "loss": 4.1728, "step": 27763 }, { "epoch": 0.8480146609651802, "grad_norm": 0.5284284353256226, "learning_rate": 2.7960596110147396e-06, "loss": 4.3312, "step": 27764 }, { "epoch": 0.848045204642639, "grad_norm": 0.5314545631408691, "learning_rate": 2.7949573276234152e-06, "loss": 4.3093, "step": 27765 }, { "epoch": 0.8480757483200977, "grad_norm": 0.5338394641876221, "learning_rate": 2.793855248685337e-06, "loss": 4.2269, "step": 27766 }, { "epoch": 0.8481062919975565, "grad_norm": 0.5243538618087769, "learning_rate": 2.7927533742106493e-06, "loss": 4.2772, "step": 27767 }, { "epoch": 0.8481368356750153, "grad_norm": 0.5246620178222656, "learning_rate": 2.791651704209497e-06, "loss": 4.2277, "step": 27768 }, { "epoch": 0.848167379352474, "grad_norm": 0.527157187461853, "learning_rate": 2.7905502386920303e-06, "loss": 4.2013, "step": 27769 }, { "epoch": 0.8481979230299328, "grad_norm": 0.5267552733421326, "learning_rate": 2.7894489776683823e-06, "loss": 4.1573, "step": 27770 }, { "epoch": 0.8482284667073916, "grad_norm": 0.5198023319244385, "learning_rate": 2.7883479211487014e-06, "loss": 4.2856, "step": 27771 }, { "epoch": 0.8482590103848503, "grad_norm": 0.5270707607269287, "learning_rate": 2.7872470691431174e-06, "loss": 4.3198, "step": 27772 }, { "epoch": 0.8482895540623091, "grad_norm": 0.521091639995575, "learning_rate": 2.7861464216617754e-06, "loss": 4.2292, "step": 27773 }, { "epoch": 0.8483200977397679, "grad_norm": 0.5158686637878418, "learning_rate": 2.785045978714798e-06, "loss": 4.1517, "step": 27774 }, { "epoch": 0.8483506414172266, "grad_norm": 0.5296640396118164, "learning_rate": 2.78394574031233e-06, "loss": 4.2669, "step": 27775 }, { "epoch": 0.8483811850946854, "grad_norm": 0.5269907116889954, "learning_rate": 2.7828457064644932e-06, "loss": 4.1912, "step": 27776 }, { "epoch": 0.8484117287721442, "grad_norm": 0.5282758474349976, "learning_rate": 2.7817458771814157e-06, "loss": 4.2793, "step": 27777 }, { "epoch": 0.8484422724496029, "grad_norm": 0.52113276720047, "learning_rate": 2.780646252473232e-06, "loss": 4.2415, "step": 27778 }, { "epoch": 0.8484728161270617, "grad_norm": 0.5310044288635254, "learning_rate": 2.779546832350061e-06, "loss": 4.3268, "step": 27779 }, { "epoch": 0.8485033598045205, "grad_norm": 0.5166872143745422, "learning_rate": 2.7784476168220246e-06, "loss": 4.2158, "step": 27780 }, { "epoch": 0.8485339034819792, "grad_norm": 0.527716875076294, "learning_rate": 2.7773486058992492e-06, "loss": 4.2596, "step": 27781 }, { "epoch": 0.848564447159438, "grad_norm": 0.5324795246124268, "learning_rate": 2.7762497995918483e-06, "loss": 4.2916, "step": 27782 }, { "epoch": 0.8485949908368967, "grad_norm": 0.5274553298950195, "learning_rate": 2.7751511979099476e-06, "loss": 4.2413, "step": 27783 }, { "epoch": 0.8486255345143555, "grad_norm": 0.5251079201698303, "learning_rate": 2.7740528008636498e-06, "loss": 4.331, "step": 27784 }, { "epoch": 0.8486560781918143, "grad_norm": 0.5247934460639954, "learning_rate": 2.7729546084630768e-06, "loss": 4.2675, "step": 27785 }, { "epoch": 0.848686621869273, "grad_norm": 0.5216862559318542, "learning_rate": 2.771856620718344e-06, "loss": 4.2753, "step": 27786 }, { "epoch": 0.8487171655467318, "grad_norm": 0.5344294905662537, "learning_rate": 2.7707588376395534e-06, "loss": 4.1399, "step": 27787 }, { "epoch": 0.8487477092241906, "grad_norm": 0.5267574191093445, "learning_rate": 2.769661259236811e-06, "loss": 4.1672, "step": 27788 }, { "epoch": 0.8487782529016493, "grad_norm": 0.5210410356521606, "learning_rate": 2.768563885520234e-06, "loss": 4.1973, "step": 27789 }, { "epoch": 0.8488087965791081, "grad_norm": 0.5276154279708862, "learning_rate": 2.767466716499914e-06, "loss": 4.2407, "step": 27790 }, { "epoch": 0.8488393402565669, "grad_norm": 0.5093408226966858, "learning_rate": 2.766369752185957e-06, "loss": 4.1672, "step": 27791 }, { "epoch": 0.8488698839340256, "grad_norm": 0.5175289511680603, "learning_rate": 2.7652729925884718e-06, "loss": 4.2101, "step": 27792 }, { "epoch": 0.8489004276114844, "grad_norm": 0.5253337025642395, "learning_rate": 2.7641764377175446e-06, "loss": 4.248, "step": 27793 }, { "epoch": 0.8489309712889432, "grad_norm": 0.5227012038230896, "learning_rate": 2.763080087583278e-06, "loss": 4.2464, "step": 27794 }, { "epoch": 0.8489615149664019, "grad_norm": 0.5275260210037231, "learning_rate": 2.76198394219577e-06, "loss": 4.2324, "step": 27795 }, { "epoch": 0.8489920586438607, "grad_norm": 0.5277039408683777, "learning_rate": 2.7608880015651066e-06, "loss": 4.2991, "step": 27796 }, { "epoch": 0.8490226023213195, "grad_norm": 0.5288251638412476, "learning_rate": 2.75979226570138e-06, "loss": 4.2439, "step": 27797 }, { "epoch": 0.8490531459987782, "grad_norm": 0.5250224471092224, "learning_rate": 2.758696734614685e-06, "loss": 4.3293, "step": 27798 }, { "epoch": 0.849083689676237, "grad_norm": 0.5252296328544617, "learning_rate": 2.7576014083151023e-06, "loss": 4.2477, "step": 27799 }, { "epoch": 0.8491142333536957, "grad_norm": 0.5399988293647766, "learning_rate": 2.7565062868127213e-06, "loss": 4.175, "step": 27800 }, { "epoch": 0.8491447770311545, "grad_norm": 0.5185645222663879, "learning_rate": 2.7554113701176193e-06, "loss": 4.2211, "step": 27801 }, { "epoch": 0.8491753207086133, "grad_norm": 0.517722487449646, "learning_rate": 2.7543166582398887e-06, "loss": 4.2713, "step": 27802 }, { "epoch": 0.849205864386072, "grad_norm": 0.518997311592102, "learning_rate": 2.753222151189594e-06, "loss": 4.3034, "step": 27803 }, { "epoch": 0.8492364080635308, "grad_norm": 0.53087317943573, "learning_rate": 2.7521278489768294e-06, "loss": 4.2177, "step": 27804 }, { "epoch": 0.8492669517409897, "grad_norm": 0.5394022464752197, "learning_rate": 2.751033751611656e-06, "loss": 4.2842, "step": 27805 }, { "epoch": 0.8492974954184483, "grad_norm": 0.5134795904159546, "learning_rate": 2.7499398591041588e-06, "loss": 4.1164, "step": 27806 }, { "epoch": 0.8493280390959072, "grad_norm": 0.5199604630470276, "learning_rate": 2.7488461714644004e-06, "loss": 4.2286, "step": 27807 }, { "epoch": 0.849358582773366, "grad_norm": 0.5258460640907288, "learning_rate": 2.7477526887024543e-06, "loss": 4.2476, "step": 27808 }, { "epoch": 0.8493891264508246, "grad_norm": 0.5259020924568176, "learning_rate": 2.7466594108283976e-06, "loss": 4.2904, "step": 27809 }, { "epoch": 0.8494196701282835, "grad_norm": 0.5250588059425354, "learning_rate": 2.7455663378522843e-06, "loss": 4.1728, "step": 27810 }, { "epoch": 0.8494502138057423, "grad_norm": 0.5257167220115662, "learning_rate": 2.7444734697841814e-06, "loss": 4.3261, "step": 27811 }, { "epoch": 0.849480757483201, "grad_norm": 0.5302586555480957, "learning_rate": 2.7433808066341603e-06, "loss": 4.214, "step": 27812 }, { "epoch": 0.8495113011606598, "grad_norm": 0.5328149199485779, "learning_rate": 2.7422883484122696e-06, "loss": 4.2274, "step": 27813 }, { "epoch": 0.8495418448381185, "grad_norm": 0.5296342372894287, "learning_rate": 2.7411960951285813e-06, "loss": 4.2224, "step": 27814 }, { "epoch": 0.8495723885155773, "grad_norm": 0.5214897394180298, "learning_rate": 2.740104046793138e-06, "loss": 4.2877, "step": 27815 }, { "epoch": 0.8496029321930361, "grad_norm": 0.5110769271850586, "learning_rate": 2.7390122034159998e-06, "loss": 4.1901, "step": 27816 }, { "epoch": 0.8496334758704948, "grad_norm": 0.5223926305770874, "learning_rate": 2.7379205650072295e-06, "loss": 4.2709, "step": 27817 }, { "epoch": 0.8496640195479536, "grad_norm": 0.5178421139717102, "learning_rate": 2.736829131576865e-06, "loss": 4.2, "step": 27818 }, { "epoch": 0.8496945632254124, "grad_norm": 0.5179824233055115, "learning_rate": 2.735737903134966e-06, "loss": 4.1718, "step": 27819 }, { "epoch": 0.8497251069028711, "grad_norm": 0.5215340256690979, "learning_rate": 2.734646879691574e-06, "loss": 4.2824, "step": 27820 }, { "epoch": 0.8497556505803299, "grad_norm": 0.532465398311615, "learning_rate": 2.733556061256734e-06, "loss": 4.3585, "step": 27821 }, { "epoch": 0.8497861942577887, "grad_norm": 0.5312660932540894, "learning_rate": 2.7324654478404903e-06, "loss": 4.2922, "step": 27822 }, { "epoch": 0.8498167379352474, "grad_norm": 0.5235936641693115, "learning_rate": 2.7313750394528907e-06, "loss": 4.2696, "step": 27823 }, { "epoch": 0.8498472816127062, "grad_norm": 0.5196578502655029, "learning_rate": 2.7302848361039635e-06, "loss": 4.2006, "step": 27824 }, { "epoch": 0.849877825290165, "grad_norm": 0.5216009616851807, "learning_rate": 2.7291948378037558e-06, "loss": 4.2323, "step": 27825 }, { "epoch": 0.8499083689676237, "grad_norm": 0.5209169983863831, "learning_rate": 2.728105044562307e-06, "loss": 4.2433, "step": 27826 }, { "epoch": 0.8499389126450825, "grad_norm": 0.5278211832046509, "learning_rate": 2.727015456389642e-06, "loss": 4.1884, "step": 27827 }, { "epoch": 0.8499694563225413, "grad_norm": 0.5251302719116211, "learning_rate": 2.7259260732957954e-06, "loss": 4.1864, "step": 27828 }, { "epoch": 0.85, "grad_norm": 0.526818037033081, "learning_rate": 2.7248368952908053e-06, "loss": 4.2279, "step": 27829 }, { "epoch": 0.8500305436774588, "grad_norm": 0.5274018049240112, "learning_rate": 2.7237479223846896e-06, "loss": 4.2122, "step": 27830 }, { "epoch": 0.8500610873549175, "grad_norm": 0.5237107872962952, "learning_rate": 2.722659154587484e-06, "loss": 4.3264, "step": 27831 }, { "epoch": 0.8500916310323763, "grad_norm": 0.5189381837844849, "learning_rate": 2.721570591909206e-06, "loss": 4.2403, "step": 27832 }, { "epoch": 0.8501221747098351, "grad_norm": 0.5252922177314758, "learning_rate": 2.7204822343598863e-06, "loss": 4.1932, "step": 27833 }, { "epoch": 0.8501527183872938, "grad_norm": 0.5272456407546997, "learning_rate": 2.719394081949536e-06, "loss": 4.1774, "step": 27834 }, { "epoch": 0.8501832620647526, "grad_norm": 0.5267201662063599, "learning_rate": 2.7183061346881866e-06, "loss": 4.1902, "step": 27835 }, { "epoch": 0.8502138057422114, "grad_norm": 0.5174322724342346, "learning_rate": 2.7172183925858434e-06, "loss": 4.2094, "step": 27836 }, { "epoch": 0.8502443494196701, "grad_norm": 0.5289528369903564, "learning_rate": 2.716130855652532e-06, "loss": 4.2845, "step": 27837 }, { "epoch": 0.8502748930971289, "grad_norm": 0.5289947986602783, "learning_rate": 2.715043523898256e-06, "loss": 4.3262, "step": 27838 }, { "epoch": 0.8503054367745877, "grad_norm": 0.5212990045547485, "learning_rate": 2.7139563973330312e-06, "loss": 4.2384, "step": 27839 }, { "epoch": 0.8503359804520464, "grad_norm": 0.5228579640388489, "learning_rate": 2.7128694759668756e-06, "loss": 4.2757, "step": 27840 }, { "epoch": 0.8503665241295052, "grad_norm": 0.5288039445877075, "learning_rate": 2.7117827598097807e-06, "loss": 4.1162, "step": 27841 }, { "epoch": 0.850397067806964, "grad_norm": 0.528564453125, "learning_rate": 2.7106962488717634e-06, "loss": 4.2254, "step": 27842 }, { "epoch": 0.8504276114844227, "grad_norm": 0.5358631014823914, "learning_rate": 2.709609943162833e-06, "loss": 4.2578, "step": 27843 }, { "epoch": 0.8504581551618815, "grad_norm": 0.5162424445152283, "learning_rate": 2.7085238426929753e-06, "loss": 4.2444, "step": 27844 }, { "epoch": 0.8504886988393403, "grad_norm": 0.5346264839172363, "learning_rate": 2.707437947472202e-06, "loss": 4.2679, "step": 27845 }, { "epoch": 0.850519242516799, "grad_norm": 0.5221571922302246, "learning_rate": 2.706352257510514e-06, "loss": 4.2705, "step": 27846 }, { "epoch": 0.8505497861942578, "grad_norm": 0.5258424878120422, "learning_rate": 2.705266772817899e-06, "loss": 4.1646, "step": 27847 }, { "epoch": 0.8505803298717165, "grad_norm": 0.5225841403007507, "learning_rate": 2.704181493404359e-06, "loss": 4.1634, "step": 27848 }, { "epoch": 0.8506108735491753, "grad_norm": 0.5263267755508423, "learning_rate": 2.70309641927988e-06, "loss": 4.1904, "step": 27849 }, { "epoch": 0.8506414172266341, "grad_norm": 0.5282689332962036, "learning_rate": 2.7020115504544585e-06, "loss": 4.2905, "step": 27850 }, { "epoch": 0.8506719609040928, "grad_norm": 0.5449254512786865, "learning_rate": 2.700926886938085e-06, "loss": 4.2588, "step": 27851 }, { "epoch": 0.8507025045815516, "grad_norm": 0.5192610025405884, "learning_rate": 2.6998424287407343e-06, "loss": 4.271, "step": 27852 }, { "epoch": 0.8507330482590104, "grad_norm": 0.5406900644302368, "learning_rate": 2.698758175872401e-06, "loss": 4.2877, "step": 27853 }, { "epoch": 0.8507635919364691, "grad_norm": 0.5328556299209595, "learning_rate": 2.6976741283430723e-06, "loss": 4.1807, "step": 27854 }, { "epoch": 0.8507941356139279, "grad_norm": 0.525952160358429, "learning_rate": 2.69659028616272e-06, "loss": 4.1844, "step": 27855 }, { "epoch": 0.8508246792913867, "grad_norm": 0.526688814163208, "learning_rate": 2.695506649341328e-06, "loss": 4.2633, "step": 27856 }, { "epoch": 0.8508552229688454, "grad_norm": 0.5358201265335083, "learning_rate": 2.6944232178888804e-06, "loss": 4.2702, "step": 27857 }, { "epoch": 0.8508857666463042, "grad_norm": 0.531302809715271, "learning_rate": 2.6933399918153412e-06, "loss": 4.2482, "step": 27858 }, { "epoch": 0.850916310323763, "grad_norm": 0.5244551301002502, "learning_rate": 2.692256971130688e-06, "loss": 4.3036, "step": 27859 }, { "epoch": 0.8509468540012217, "grad_norm": 0.5222229957580566, "learning_rate": 2.6911741558449e-06, "loss": 4.2012, "step": 27860 }, { "epoch": 0.8509773976786805, "grad_norm": 0.5267735123634338, "learning_rate": 2.6900915459679376e-06, "loss": 4.244, "step": 27861 }, { "epoch": 0.8510079413561393, "grad_norm": 0.5274255275726318, "learning_rate": 2.689009141509771e-06, "loss": 4.1678, "step": 27862 }, { "epoch": 0.851038485033598, "grad_norm": 0.5294972062110901, "learning_rate": 2.687926942480376e-06, "loss": 4.1873, "step": 27863 }, { "epoch": 0.8510690287110568, "grad_norm": 0.5279883146286011, "learning_rate": 2.6868449488897025e-06, "loss": 4.2782, "step": 27864 }, { "epoch": 0.8510995723885155, "grad_norm": 0.5386819243431091, "learning_rate": 2.685763160747726e-06, "loss": 4.3085, "step": 27865 }, { "epoch": 0.8511301160659743, "grad_norm": 0.5226253271102905, "learning_rate": 2.6846815780643993e-06, "loss": 4.2892, "step": 27866 }, { "epoch": 0.8511606597434331, "grad_norm": 0.5343140363693237, "learning_rate": 2.6836002008496786e-06, "loss": 4.2527, "step": 27867 }, { "epoch": 0.8511912034208918, "grad_norm": 0.5279397368431091, "learning_rate": 2.682519029113531e-06, "loss": 4.2414, "step": 27868 }, { "epoch": 0.8512217470983506, "grad_norm": 0.5387014746665955, "learning_rate": 2.6814380628658986e-06, "loss": 4.1937, "step": 27869 }, { "epoch": 0.8512522907758094, "grad_norm": 0.5285269618034363, "learning_rate": 2.680357302116743e-06, "loss": 4.2604, "step": 27870 }, { "epoch": 0.8512828344532681, "grad_norm": 0.521508514881134, "learning_rate": 2.6792767468760168e-06, "loss": 4.1729, "step": 27871 }, { "epoch": 0.8513133781307269, "grad_norm": 0.5359972715377808, "learning_rate": 2.6781963971536594e-06, "loss": 4.3509, "step": 27872 }, { "epoch": 0.8513439218081857, "grad_norm": 0.5288277268409729, "learning_rate": 2.677116252959627e-06, "loss": 4.2992, "step": 27873 }, { "epoch": 0.8513744654856444, "grad_norm": 0.5336837768554688, "learning_rate": 2.6760363143038647e-06, "loss": 4.1781, "step": 27874 }, { "epoch": 0.8514050091631032, "grad_norm": 0.5291066765785217, "learning_rate": 2.674956581196311e-06, "loss": 4.28, "step": 27875 }, { "epoch": 0.851435552840562, "grad_norm": 0.5385873317718506, "learning_rate": 2.6738770536469117e-06, "loss": 4.3417, "step": 27876 }, { "epoch": 0.8514660965180207, "grad_norm": 0.5190248489379883, "learning_rate": 2.6727977316656078e-06, "loss": 4.2807, "step": 27877 }, { "epoch": 0.8514966401954795, "grad_norm": 0.5246717929840088, "learning_rate": 2.671718615262331e-06, "loss": 4.1833, "step": 27878 }, { "epoch": 0.8515271838729384, "grad_norm": 0.5225078463554382, "learning_rate": 2.67063970444702e-06, "loss": 4.277, "step": 27879 }, { "epoch": 0.851557727550397, "grad_norm": 0.5302911400794983, "learning_rate": 2.6695609992296174e-06, "loss": 4.2725, "step": 27880 }, { "epoch": 0.8515882712278559, "grad_norm": 0.5251222848892212, "learning_rate": 2.668482499620045e-06, "loss": 4.2506, "step": 27881 }, { "epoch": 0.8516188149053145, "grad_norm": 0.5254901051521301, "learning_rate": 2.667404205628232e-06, "loss": 4.2725, "step": 27882 }, { "epoch": 0.8516493585827734, "grad_norm": 0.5319457054138184, "learning_rate": 2.6663261172641146e-06, "loss": 4.3204, "step": 27883 }, { "epoch": 0.8516799022602322, "grad_norm": 0.5132576823234558, "learning_rate": 2.6652482345376124e-06, "loss": 4.319, "step": 27884 }, { "epoch": 0.8517104459376909, "grad_norm": 0.5205449461936951, "learning_rate": 2.664170557458656e-06, "loss": 4.2875, "step": 27885 }, { "epoch": 0.8517409896151497, "grad_norm": 0.5269181132316589, "learning_rate": 2.6630930860371632e-06, "loss": 4.2475, "step": 27886 }, { "epoch": 0.8517715332926085, "grad_norm": 0.5152468085289001, "learning_rate": 2.6620158202830537e-06, "loss": 4.269, "step": 27887 }, { "epoch": 0.8518020769700672, "grad_norm": 0.5303454399108887, "learning_rate": 2.660938760206258e-06, "loss": 4.2354, "step": 27888 }, { "epoch": 0.851832620647526, "grad_norm": 0.5187409520149231, "learning_rate": 2.659861905816677e-06, "loss": 4.214, "step": 27889 }, { "epoch": 0.8518631643249848, "grad_norm": 0.5223835706710815, "learning_rate": 2.6587852571242327e-06, "loss": 4.2175, "step": 27890 }, { "epoch": 0.8518937080024435, "grad_norm": 0.5253710150718689, "learning_rate": 2.6577088141388486e-06, "loss": 4.1948, "step": 27891 }, { "epoch": 0.8519242516799023, "grad_norm": 0.529542088508606, "learning_rate": 2.656632576870419e-06, "loss": 4.3004, "step": 27892 }, { "epoch": 0.8519547953573611, "grad_norm": 0.5286762118339539, "learning_rate": 2.6555565453288604e-06, "loss": 4.1979, "step": 27893 }, { "epoch": 0.8519853390348198, "grad_norm": 0.5201264023780823, "learning_rate": 2.6544807195240858e-06, "loss": 4.1902, "step": 27894 }, { "epoch": 0.8520158827122786, "grad_norm": 0.520234227180481, "learning_rate": 2.6534050994659916e-06, "loss": 4.2292, "step": 27895 }, { "epoch": 0.8520464263897374, "grad_norm": 0.5267826914787292, "learning_rate": 2.6523296851644925e-06, "loss": 4.2704, "step": 27896 }, { "epoch": 0.8520769700671961, "grad_norm": 0.5250803232192993, "learning_rate": 2.6512544766294835e-06, "loss": 4.3098, "step": 27897 }, { "epoch": 0.8521075137446549, "grad_norm": 0.52254718542099, "learning_rate": 2.650179473870859e-06, "loss": 4.2896, "step": 27898 }, { "epoch": 0.8521380574221136, "grad_norm": 0.5325995087623596, "learning_rate": 2.649104676898531e-06, "loss": 4.1632, "step": 27899 }, { "epoch": 0.8521686010995724, "grad_norm": 0.5206179618835449, "learning_rate": 2.6480300857223807e-06, "loss": 4.2921, "step": 27900 }, { "epoch": 0.8521991447770312, "grad_norm": 0.5298280715942383, "learning_rate": 2.6469557003523077e-06, "loss": 4.3029, "step": 27901 }, { "epoch": 0.8522296884544899, "grad_norm": 0.5308434963226318, "learning_rate": 2.6458815207982157e-06, "loss": 4.2304, "step": 27902 }, { "epoch": 0.8522602321319487, "grad_norm": 0.5271506905555725, "learning_rate": 2.6448075470699772e-06, "loss": 4.2876, "step": 27903 }, { "epoch": 0.8522907758094075, "grad_norm": 0.5228958129882812, "learning_rate": 2.643733779177493e-06, "loss": 4.2162, "step": 27904 }, { "epoch": 0.8523213194868662, "grad_norm": 0.5203920602798462, "learning_rate": 2.642660217130649e-06, "loss": 4.1906, "step": 27905 }, { "epoch": 0.852351863164325, "grad_norm": 0.5284794569015503, "learning_rate": 2.6415868609393214e-06, "loss": 4.1934, "step": 27906 }, { "epoch": 0.8523824068417838, "grad_norm": 0.5218096375465393, "learning_rate": 2.6405137106134013e-06, "loss": 4.1943, "step": 27907 }, { "epoch": 0.8524129505192425, "grad_norm": 0.5238064527511597, "learning_rate": 2.639440766162771e-06, "loss": 4.2704, "step": 27908 }, { "epoch": 0.8524434941967013, "grad_norm": 0.5327004194259644, "learning_rate": 2.6383680275973016e-06, "loss": 4.2547, "step": 27909 }, { "epoch": 0.8524740378741601, "grad_norm": 0.5284520983695984, "learning_rate": 2.637295494926878e-06, "loss": 4.2335, "step": 27910 }, { "epoch": 0.8525045815516188, "grad_norm": 0.5194964408874512, "learning_rate": 2.6362231681613725e-06, "loss": 4.2189, "step": 27911 }, { "epoch": 0.8525351252290776, "grad_norm": 0.528735876083374, "learning_rate": 2.6351510473106635e-06, "loss": 4.2727, "step": 27912 }, { "epoch": 0.8525656689065364, "grad_norm": 0.5191797018051147, "learning_rate": 2.6340791323846093e-06, "loss": 4.1916, "step": 27913 }, { "epoch": 0.8525962125839951, "grad_norm": 0.5410308837890625, "learning_rate": 2.633007423393094e-06, "loss": 4.2659, "step": 27914 }, { "epoch": 0.8526267562614539, "grad_norm": 0.5273935198783875, "learning_rate": 2.6319359203459736e-06, "loss": 4.2253, "step": 27915 }, { "epoch": 0.8526572999389126, "grad_norm": 0.5346801280975342, "learning_rate": 2.6308646232531262e-06, "loss": 4.2831, "step": 27916 }, { "epoch": 0.8526878436163714, "grad_norm": 0.5375012159347534, "learning_rate": 2.6297935321244025e-06, "loss": 4.2075, "step": 27917 }, { "epoch": 0.8527183872938302, "grad_norm": 0.5223531126976013, "learning_rate": 2.6287226469696724e-06, "loss": 4.3128, "step": 27918 }, { "epoch": 0.8527489309712889, "grad_norm": 0.5335622429847717, "learning_rate": 2.6276519677987997e-06, "loss": 4.3102, "step": 27919 }, { "epoch": 0.8527794746487477, "grad_norm": 0.5308752655982971, "learning_rate": 2.626581494621633e-06, "loss": 4.296, "step": 27920 }, { "epoch": 0.8528100183262065, "grad_norm": 0.5344061255455017, "learning_rate": 2.6255112274480354e-06, "loss": 4.2481, "step": 27921 }, { "epoch": 0.8528405620036652, "grad_norm": 0.5365579724311829, "learning_rate": 2.6244411662878636e-06, "loss": 4.3445, "step": 27922 }, { "epoch": 0.852871105681124, "grad_norm": 0.5301744341850281, "learning_rate": 2.62337131115096e-06, "loss": 4.1836, "step": 27923 }, { "epoch": 0.8529016493585828, "grad_norm": 0.5228102803230286, "learning_rate": 2.622301662047183e-06, "loss": 4.2973, "step": 27924 }, { "epoch": 0.8529321930360415, "grad_norm": 0.5240347385406494, "learning_rate": 2.6212322189863857e-06, "loss": 4.2335, "step": 27925 }, { "epoch": 0.8529627367135003, "grad_norm": 0.5229697227478027, "learning_rate": 2.6201629819784025e-06, "loss": 4.2019, "step": 27926 }, { "epoch": 0.8529932803909591, "grad_norm": 0.5352457165718079, "learning_rate": 2.6190939510330913e-06, "loss": 4.2076, "step": 27927 }, { "epoch": 0.8530238240684178, "grad_norm": 0.52420574426651, "learning_rate": 2.618025126160284e-06, "loss": 4.277, "step": 27928 }, { "epoch": 0.8530543677458766, "grad_norm": 0.527754008769989, "learning_rate": 2.616956507369833e-06, "loss": 4.3118, "step": 27929 }, { "epoch": 0.8530849114233354, "grad_norm": 0.5267193913459778, "learning_rate": 2.6158880946715676e-06, "loss": 4.2067, "step": 27930 }, { "epoch": 0.8531154551007941, "grad_norm": 0.5186911225318909, "learning_rate": 2.614819888075332e-06, "loss": 4.2113, "step": 27931 }, { "epoch": 0.8531459987782529, "grad_norm": 0.5273700952529907, "learning_rate": 2.613751887590954e-06, "loss": 4.2865, "step": 27932 }, { "epoch": 0.8531765424557116, "grad_norm": 0.5264861583709717, "learning_rate": 2.6126840932282794e-06, "loss": 4.2882, "step": 27933 }, { "epoch": 0.8532070861331704, "grad_norm": 0.5348880290985107, "learning_rate": 2.611616504997125e-06, "loss": 4.2379, "step": 27934 }, { "epoch": 0.8532376298106292, "grad_norm": 0.5273817777633667, "learning_rate": 2.6105491229073298e-06, "loss": 4.3028, "step": 27935 }, { "epoch": 0.8532681734880879, "grad_norm": 0.5279483795166016, "learning_rate": 2.6094819469687254e-06, "loss": 4.2892, "step": 27936 }, { "epoch": 0.8532987171655467, "grad_norm": 0.5353319644927979, "learning_rate": 2.6084149771911286e-06, "loss": 4.2678, "step": 27937 }, { "epoch": 0.8533292608430055, "grad_norm": 0.5217149257659912, "learning_rate": 2.6073482135843654e-06, "loss": 4.253, "step": 27938 }, { "epoch": 0.8533598045204642, "grad_norm": 0.524384081363678, "learning_rate": 2.606281656158266e-06, "loss": 4.2724, "step": 27939 }, { "epoch": 0.853390348197923, "grad_norm": 0.5293756723403931, "learning_rate": 2.6052153049226426e-06, "loss": 4.2812, "step": 27940 }, { "epoch": 0.8534208918753818, "grad_norm": 0.5195784568786621, "learning_rate": 2.6041491598873148e-06, "loss": 4.2204, "step": 27941 }, { "epoch": 0.8534514355528405, "grad_norm": 0.5214735865592957, "learning_rate": 2.6030832210621025e-06, "loss": 4.2298, "step": 27942 }, { "epoch": 0.8534819792302993, "grad_norm": 0.524789571762085, "learning_rate": 2.6020174884568232e-06, "loss": 4.2453, "step": 27943 }, { "epoch": 0.8535125229077581, "grad_norm": 0.5308339595794678, "learning_rate": 2.6009519620812772e-06, "loss": 4.3065, "step": 27944 }, { "epoch": 0.8535430665852168, "grad_norm": 0.5287142395973206, "learning_rate": 2.599886641945287e-06, "loss": 4.132, "step": 27945 }, { "epoch": 0.8535736102626756, "grad_norm": 0.5279754400253296, "learning_rate": 2.598821528058654e-06, "loss": 4.3278, "step": 27946 }, { "epoch": 0.8536041539401344, "grad_norm": 0.519401490688324, "learning_rate": 2.597756620431188e-06, "loss": 4.2483, "step": 27947 }, { "epoch": 0.8536346976175931, "grad_norm": 0.5276210308074951, "learning_rate": 2.5966919190726996e-06, "loss": 4.2394, "step": 27948 }, { "epoch": 0.853665241295052, "grad_norm": 0.5213777422904968, "learning_rate": 2.595627423992983e-06, "loss": 4.2067, "step": 27949 }, { "epoch": 0.8536957849725106, "grad_norm": 0.5228036642074585, "learning_rate": 2.5945631352018495e-06, "loss": 4.2608, "step": 27950 }, { "epoch": 0.8537263286499694, "grad_norm": 0.52635657787323, "learning_rate": 2.593499052709089e-06, "loss": 4.1451, "step": 27951 }, { "epoch": 0.8537568723274283, "grad_norm": 0.5280200242996216, "learning_rate": 2.5924351765244994e-06, "loss": 4.2706, "step": 27952 }, { "epoch": 0.853787416004887, "grad_norm": 0.5343918800354004, "learning_rate": 2.5913715066578884e-06, "loss": 4.1788, "step": 27953 }, { "epoch": 0.8538179596823458, "grad_norm": 0.5301112532615662, "learning_rate": 2.5903080431190357e-06, "loss": 4.2542, "step": 27954 }, { "epoch": 0.8538485033598046, "grad_norm": 0.5271849036216736, "learning_rate": 2.5892447859177355e-06, "loss": 4.182, "step": 27955 }, { "epoch": 0.8538790470372633, "grad_norm": 0.5293887853622437, "learning_rate": 2.588181735063791e-06, "loss": 4.2845, "step": 27956 }, { "epoch": 0.853909590714722, "grad_norm": 0.5390943288803101, "learning_rate": 2.5871188905669724e-06, "loss": 4.2816, "step": 27957 }, { "epoch": 0.8539401343921809, "grad_norm": 0.5365090370178223, "learning_rate": 2.5860562524370773e-06, "loss": 4.2835, "step": 27958 }, { "epoch": 0.8539706780696396, "grad_norm": 0.5316359400749207, "learning_rate": 2.584993820683884e-06, "loss": 4.2424, "step": 27959 }, { "epoch": 0.8540012217470984, "grad_norm": 0.5191694498062134, "learning_rate": 2.5839315953171824e-06, "loss": 4.2509, "step": 27960 }, { "epoch": 0.8540317654245572, "grad_norm": 0.5316932797431946, "learning_rate": 2.5828695763467415e-06, "loss": 4.2092, "step": 27961 }, { "epoch": 0.8540623091020159, "grad_norm": 0.5326728820800781, "learning_rate": 2.5818077637823513e-06, "loss": 4.2937, "step": 27962 }, { "epoch": 0.8540928527794747, "grad_norm": 0.5385786890983582, "learning_rate": 2.580746157633779e-06, "loss": 4.2901, "step": 27963 }, { "epoch": 0.8541233964569335, "grad_norm": 0.5198867917060852, "learning_rate": 2.5796847579108024e-06, "loss": 4.2375, "step": 27964 }, { "epoch": 0.8541539401343922, "grad_norm": 0.5239222049713135, "learning_rate": 2.5786235646232004e-06, "loss": 4.1974, "step": 27965 }, { "epoch": 0.854184483811851, "grad_norm": 0.5277904868125916, "learning_rate": 2.577562577780737e-06, "loss": 4.2649, "step": 27966 }, { "epoch": 0.8542150274893097, "grad_norm": 0.5252023339271545, "learning_rate": 2.5765017973931854e-06, "loss": 4.1968, "step": 27967 }, { "epoch": 0.8542455711667685, "grad_norm": 0.5210546851158142, "learning_rate": 2.5754412234703067e-06, "loss": 4.2603, "step": 27968 }, { "epoch": 0.8542761148442273, "grad_norm": 0.5260559916496277, "learning_rate": 2.574380856021871e-06, "loss": 4.2624, "step": 27969 }, { "epoch": 0.854306658521686, "grad_norm": 0.5215132832527161, "learning_rate": 2.573320695057646e-06, "loss": 4.3347, "step": 27970 }, { "epoch": 0.8543372021991448, "grad_norm": 0.5311945676803589, "learning_rate": 2.5722607405873816e-06, "loss": 4.2004, "step": 27971 }, { "epoch": 0.8543677458766036, "grad_norm": 0.5285662412643433, "learning_rate": 2.5712009926208453e-06, "loss": 4.3001, "step": 27972 }, { "epoch": 0.8543982895540623, "grad_norm": 0.5277795791625977, "learning_rate": 2.570141451167796e-06, "loss": 4.3, "step": 27973 }, { "epoch": 0.8544288332315211, "grad_norm": 0.5203686952590942, "learning_rate": 2.5690821162379837e-06, "loss": 4.2413, "step": 27974 }, { "epoch": 0.8544593769089799, "grad_norm": 0.5254347324371338, "learning_rate": 2.5680229878411705e-06, "loss": 4.1759, "step": 27975 }, { "epoch": 0.8544899205864386, "grad_norm": 0.5288122296333313, "learning_rate": 2.5669640659871014e-06, "loss": 4.2374, "step": 27976 }, { "epoch": 0.8545204642638974, "grad_norm": 0.5311905145645142, "learning_rate": 2.565905350685524e-06, "loss": 4.191, "step": 27977 }, { "epoch": 0.8545510079413562, "grad_norm": 0.5369570255279541, "learning_rate": 2.564846841946189e-06, "loss": 4.2863, "step": 27978 }, { "epoch": 0.8545815516188149, "grad_norm": 0.5324487686157227, "learning_rate": 2.5637885397788527e-06, "loss": 4.3168, "step": 27979 }, { "epoch": 0.8546120952962737, "grad_norm": 0.5377600789070129, "learning_rate": 2.5627304441932425e-06, "loss": 4.2838, "step": 27980 }, { "epoch": 0.8546426389737324, "grad_norm": 0.537277340888977, "learning_rate": 2.5616725551991155e-06, "loss": 4.1299, "step": 27981 }, { "epoch": 0.8546731826511912, "grad_norm": 0.5246355533599854, "learning_rate": 2.5606148728061994e-06, "loss": 4.3132, "step": 27982 }, { "epoch": 0.85470372632865, "grad_norm": 0.5228933691978455, "learning_rate": 2.5595573970242425e-06, "loss": 4.2745, "step": 27983 }, { "epoch": 0.8547342700061087, "grad_norm": 0.5230043530464172, "learning_rate": 2.558500127862981e-06, "loss": 4.2593, "step": 27984 }, { "epoch": 0.8547648136835675, "grad_norm": 0.5335659384727478, "learning_rate": 2.557443065332141e-06, "loss": 4.2076, "step": 27985 }, { "epoch": 0.8547953573610263, "grad_norm": 0.521491527557373, "learning_rate": 2.556386209441464e-06, "loss": 4.1206, "step": 27986 }, { "epoch": 0.854825901038485, "grad_norm": 0.5259117484092712, "learning_rate": 2.5553295602006837e-06, "loss": 4.1632, "step": 27987 }, { "epoch": 0.8548564447159438, "grad_norm": 0.5279264450073242, "learning_rate": 2.5542731176195182e-06, "loss": 4.3297, "step": 27988 }, { "epoch": 0.8548869883934026, "grad_norm": 0.53998863697052, "learning_rate": 2.5532168817076983e-06, "loss": 4.3199, "step": 27989 }, { "epoch": 0.8549175320708613, "grad_norm": 0.5242747664451599, "learning_rate": 2.5521608524749608e-06, "loss": 4.2267, "step": 27990 }, { "epoch": 0.8549480757483201, "grad_norm": 0.5265076160430908, "learning_rate": 2.551105029931017e-06, "loss": 4.2405, "step": 27991 }, { "epoch": 0.8549786194257789, "grad_norm": 0.5333331823348999, "learning_rate": 2.550049414085587e-06, "loss": 4.2978, "step": 27992 }, { "epoch": 0.8550091631032376, "grad_norm": 0.5307447910308838, "learning_rate": 2.548994004948399e-06, "loss": 4.298, "step": 27993 }, { "epoch": 0.8550397067806964, "grad_norm": 0.5237420797348022, "learning_rate": 2.5479388025291624e-06, "loss": 4.2364, "step": 27994 }, { "epoch": 0.8550702504581552, "grad_norm": 0.5265572667121887, "learning_rate": 2.5468838068375966e-06, "loss": 4.205, "step": 27995 }, { "epoch": 0.8551007941356139, "grad_norm": 0.5294337272644043, "learning_rate": 2.5458290178834223e-06, "loss": 4.3082, "step": 27996 }, { "epoch": 0.8551313378130727, "grad_norm": 0.5264562964439392, "learning_rate": 2.5447744356763366e-06, "loss": 4.2702, "step": 27997 }, { "epoch": 0.8551618814905314, "grad_norm": 0.5278714299201965, "learning_rate": 2.5437200602260653e-06, "loss": 4.1952, "step": 27998 }, { "epoch": 0.8551924251679902, "grad_norm": 0.5446579456329346, "learning_rate": 2.5426658915423034e-06, "loss": 4.2768, "step": 27999 }, { "epoch": 0.855222968845449, "grad_norm": 0.5296427607536316, "learning_rate": 2.5416119296347656e-06, "loss": 4.2364, "step": 28000 }, { "epoch": 0.8552535125229077, "grad_norm": 0.537071168422699, "learning_rate": 2.540558174513155e-06, "loss": 4.2876, "step": 28001 }, { "epoch": 0.8552840562003665, "grad_norm": 0.5350896120071411, "learning_rate": 2.5395046261871698e-06, "loss": 4.303, "step": 28002 }, { "epoch": 0.8553145998778253, "grad_norm": 0.5324069261550903, "learning_rate": 2.5384512846665127e-06, "loss": 4.275, "step": 28003 }, { "epoch": 0.855345143555284, "grad_norm": 0.5257439017295837, "learning_rate": 2.5373981499608903e-06, "loss": 4.2109, "step": 28004 }, { "epoch": 0.8553756872327428, "grad_norm": 0.5274279117584229, "learning_rate": 2.536345222079986e-06, "loss": 4.2395, "step": 28005 }, { "epoch": 0.8554062309102016, "grad_norm": 0.5185511708259583, "learning_rate": 2.535292501033504e-06, "loss": 4.1432, "step": 28006 }, { "epoch": 0.8554367745876603, "grad_norm": 0.527586042881012, "learning_rate": 2.5342399868311356e-06, "loss": 4.2754, "step": 28007 }, { "epoch": 0.8554673182651191, "grad_norm": 0.5302326083183289, "learning_rate": 2.5331876794825653e-06, "loss": 4.2854, "step": 28008 }, { "epoch": 0.8554978619425779, "grad_norm": 0.526431143283844, "learning_rate": 2.5321355789974884e-06, "loss": 4.2476, "step": 28009 }, { "epoch": 0.8555284056200366, "grad_norm": 0.5258839726448059, "learning_rate": 2.5310836853855963e-06, "loss": 4.2583, "step": 28010 }, { "epoch": 0.8555589492974954, "grad_norm": 0.5301758646965027, "learning_rate": 2.5300319986565625e-06, "loss": 4.3032, "step": 28011 }, { "epoch": 0.8555894929749542, "grad_norm": 0.5282660126686096, "learning_rate": 2.5289805188200762e-06, "loss": 4.2108, "step": 28012 }, { "epoch": 0.8556200366524129, "grad_norm": 0.5245193839073181, "learning_rate": 2.5279292458858267e-06, "loss": 4.227, "step": 28013 }, { "epoch": 0.8556505803298717, "grad_norm": 0.5324469208717346, "learning_rate": 2.5268781798634815e-06, "loss": 4.3312, "step": 28014 }, { "epoch": 0.8556811240073304, "grad_norm": 0.5234119296073914, "learning_rate": 2.5258273207627274e-06, "loss": 4.2284, "step": 28015 }, { "epoch": 0.8557116676847892, "grad_norm": 0.530987024307251, "learning_rate": 2.524776668593232e-06, "loss": 4.2802, "step": 28016 }, { "epoch": 0.855742211362248, "grad_norm": 0.5288305282592773, "learning_rate": 2.5237262233646723e-06, "loss": 4.2676, "step": 28017 }, { "epoch": 0.8557727550397067, "grad_norm": 0.5302279591560364, "learning_rate": 2.522675985086728e-06, "loss": 4.2409, "step": 28018 }, { "epoch": 0.8558032987171655, "grad_norm": 0.5348086357116699, "learning_rate": 2.5216259537690578e-06, "loss": 4.3729, "step": 28019 }, { "epoch": 0.8558338423946243, "grad_norm": 0.5288509130477905, "learning_rate": 2.5205761294213343e-06, "loss": 4.2259, "step": 28020 }, { "epoch": 0.855864386072083, "grad_norm": 0.5290906429290771, "learning_rate": 2.5195265120532273e-06, "loss": 4.2532, "step": 28021 }, { "epoch": 0.8558949297495418, "grad_norm": 0.5256127715110779, "learning_rate": 2.518477101674399e-06, "loss": 4.2425, "step": 28022 }, { "epoch": 0.8559254734270006, "grad_norm": 0.5373120307922363, "learning_rate": 2.5174278982945053e-06, "loss": 4.1287, "step": 28023 }, { "epoch": 0.8559560171044593, "grad_norm": 0.5342352390289307, "learning_rate": 2.516378901923219e-06, "loss": 4.2437, "step": 28024 }, { "epoch": 0.8559865607819181, "grad_norm": 0.5324668884277344, "learning_rate": 2.5153301125701885e-06, "loss": 4.3057, "step": 28025 }, { "epoch": 0.856017104459377, "grad_norm": 0.5298081040382385, "learning_rate": 2.5142815302450715e-06, "loss": 4.3068, "step": 28026 }, { "epoch": 0.8560476481368356, "grad_norm": 0.5353045463562012, "learning_rate": 2.513233154957531e-06, "loss": 4.2301, "step": 28027 }, { "epoch": 0.8560781918142945, "grad_norm": 0.519048810005188, "learning_rate": 2.512184986717209e-06, "loss": 4.2475, "step": 28028 }, { "epoch": 0.8561087354917533, "grad_norm": 0.5373870730400085, "learning_rate": 2.5111370255337607e-06, "loss": 4.3007, "step": 28029 }, { "epoch": 0.856139279169212, "grad_norm": 0.5291171669960022, "learning_rate": 2.510089271416843e-06, "loss": 4.1237, "step": 28030 }, { "epoch": 0.8561698228466708, "grad_norm": 0.5329328179359436, "learning_rate": 2.5090417243760934e-06, "loss": 4.1932, "step": 28031 }, { "epoch": 0.8562003665241295, "grad_norm": 0.5272175073623657, "learning_rate": 2.5079943844211612e-06, "loss": 4.2445, "step": 28032 }, { "epoch": 0.8562309102015883, "grad_norm": 0.5524016618728638, "learning_rate": 2.5069472515616867e-06, "loss": 4.2851, "step": 28033 }, { "epoch": 0.8562614538790471, "grad_norm": 0.5240517258644104, "learning_rate": 2.5059003258073145e-06, "loss": 4.2448, "step": 28034 }, { "epoch": 0.8562919975565058, "grad_norm": 0.5316019058227539, "learning_rate": 2.504853607167687e-06, "loss": 4.2955, "step": 28035 }, { "epoch": 0.8563225412339646, "grad_norm": 0.5248025059700012, "learning_rate": 2.5038070956524327e-06, "loss": 4.2525, "step": 28036 }, { "epoch": 0.8563530849114234, "grad_norm": 0.5244911909103394, "learning_rate": 2.502760791271197e-06, "loss": 4.2685, "step": 28037 }, { "epoch": 0.8563836285888821, "grad_norm": 0.5400928258895874, "learning_rate": 2.501714694033608e-06, "loss": 4.2585, "step": 28038 }, { "epoch": 0.8564141722663409, "grad_norm": 0.5264529585838318, "learning_rate": 2.500668803949302e-06, "loss": 4.3234, "step": 28039 }, { "epoch": 0.8564447159437997, "grad_norm": 0.534114420413971, "learning_rate": 2.4996231210278997e-06, "loss": 4.3046, "step": 28040 }, { "epoch": 0.8564752596212584, "grad_norm": 0.5291829705238342, "learning_rate": 2.4985776452790434e-06, "loss": 4.2807, "step": 28041 }, { "epoch": 0.8565058032987172, "grad_norm": 0.5272077918052673, "learning_rate": 2.497532376712347e-06, "loss": 4.1982, "step": 28042 }, { "epoch": 0.856536346976176, "grad_norm": 0.5282602310180664, "learning_rate": 2.4964873153374397e-06, "loss": 4.2974, "step": 28043 }, { "epoch": 0.8565668906536347, "grad_norm": 0.5269343256950378, "learning_rate": 2.4954424611639467e-06, "loss": 4.1974, "step": 28044 }, { "epoch": 0.8565974343310935, "grad_norm": 0.5421529412269592, "learning_rate": 2.494397814201482e-06, "loss": 4.2453, "step": 28045 }, { "epoch": 0.8566279780085523, "grad_norm": 0.5403796434402466, "learning_rate": 2.493353374459667e-06, "loss": 4.3985, "step": 28046 }, { "epoch": 0.856658521686011, "grad_norm": 0.5290344953536987, "learning_rate": 2.4923091419481266e-06, "loss": 4.2675, "step": 28047 }, { "epoch": 0.8566890653634698, "grad_norm": 0.5324459075927734, "learning_rate": 2.491265116676461e-06, "loss": 4.2533, "step": 28048 }, { "epoch": 0.8567196090409285, "grad_norm": 0.5272078514099121, "learning_rate": 2.490221298654297e-06, "loss": 4.2637, "step": 28049 }, { "epoch": 0.8567501527183873, "grad_norm": 0.542232096195221, "learning_rate": 2.489177687891231e-06, "loss": 4.2442, "step": 28050 }, { "epoch": 0.8567806963958461, "grad_norm": 0.5201784372329712, "learning_rate": 2.4881342843968813e-06, "loss": 4.2132, "step": 28051 }, { "epoch": 0.8568112400733048, "grad_norm": 0.5289995074272156, "learning_rate": 2.4870910881808595e-06, "loss": 4.2097, "step": 28052 }, { "epoch": 0.8568417837507636, "grad_norm": 0.534476637840271, "learning_rate": 2.486048099252766e-06, "loss": 4.2951, "step": 28053 }, { "epoch": 0.8568723274282224, "grad_norm": 0.5213998556137085, "learning_rate": 2.4850053176221966e-06, "loss": 4.1969, "step": 28054 }, { "epoch": 0.8569028711056811, "grad_norm": 0.531960129737854, "learning_rate": 2.483962743298765e-06, "loss": 4.1877, "step": 28055 }, { "epoch": 0.8569334147831399, "grad_norm": 0.5238230228424072, "learning_rate": 2.4829203762920584e-06, "loss": 4.301, "step": 28056 }, { "epoch": 0.8569639584605987, "grad_norm": 0.5325986742973328, "learning_rate": 2.481878216611683e-06, "loss": 4.2917, "step": 28057 }, { "epoch": 0.8569945021380574, "grad_norm": 0.5293317437171936, "learning_rate": 2.4808362642672362e-06, "loss": 4.2776, "step": 28058 }, { "epoch": 0.8570250458155162, "grad_norm": 0.5207747220993042, "learning_rate": 2.4797945192683054e-06, "loss": 4.2086, "step": 28059 }, { "epoch": 0.857055589492975, "grad_norm": 0.5321256518363953, "learning_rate": 2.4787529816244826e-06, "loss": 4.3364, "step": 28060 }, { "epoch": 0.8570861331704337, "grad_norm": 0.5509780645370483, "learning_rate": 2.477711651345366e-06, "loss": 4.3058, "step": 28061 }, { "epoch": 0.8571166768478925, "grad_norm": 0.5409027338027954, "learning_rate": 2.4766705284405335e-06, "loss": 4.228, "step": 28062 }, { "epoch": 0.8571472205253513, "grad_norm": 0.5304800271987915, "learning_rate": 2.475629612919575e-06, "loss": 4.3217, "step": 28063 }, { "epoch": 0.85717776420281, "grad_norm": 0.5281372666358948, "learning_rate": 2.474588904792083e-06, "loss": 4.2622, "step": 28064 }, { "epoch": 0.8572083078802688, "grad_norm": 0.5377338528633118, "learning_rate": 2.4735484040676245e-06, "loss": 4.2657, "step": 28065 }, { "epoch": 0.8572388515577275, "grad_norm": 0.522411584854126, "learning_rate": 2.4725081107557944e-06, "loss": 4.247, "step": 28066 }, { "epoch": 0.8572693952351863, "grad_norm": 0.5342553853988647, "learning_rate": 2.471468024866158e-06, "loss": 4.3434, "step": 28067 }, { "epoch": 0.8572999389126451, "grad_norm": 0.5269238948822021, "learning_rate": 2.4704281464083045e-06, "loss": 4.2557, "step": 28068 }, { "epoch": 0.8573304825901038, "grad_norm": 0.5215880274772644, "learning_rate": 2.4693884753917983e-06, "loss": 4.129, "step": 28069 }, { "epoch": 0.8573610262675626, "grad_norm": 0.5335209965705872, "learning_rate": 2.468349011826221e-06, "loss": 4.2167, "step": 28070 }, { "epoch": 0.8573915699450214, "grad_norm": 0.5319469571113586, "learning_rate": 2.4673097557211338e-06, "loss": 4.1889, "step": 28071 }, { "epoch": 0.8574221136224801, "grad_norm": 0.5292919278144836, "learning_rate": 2.466270707086116e-06, "loss": 4.2097, "step": 28072 }, { "epoch": 0.8574526572999389, "grad_norm": 0.5353457927703857, "learning_rate": 2.4652318659307257e-06, "loss": 4.2638, "step": 28073 }, { "epoch": 0.8574832009773977, "grad_norm": 0.5380054116249084, "learning_rate": 2.4641932322645306e-06, "loss": 4.3143, "step": 28074 }, { "epoch": 0.8575137446548564, "grad_norm": 0.5263524651527405, "learning_rate": 2.463154806097098e-06, "loss": 4.1914, "step": 28075 }, { "epoch": 0.8575442883323152, "grad_norm": 0.5267607569694519, "learning_rate": 2.462116587437985e-06, "loss": 4.2134, "step": 28076 }, { "epoch": 0.857574832009774, "grad_norm": 0.5255419015884399, "learning_rate": 2.4610785762967493e-06, "loss": 4.2283, "step": 28077 }, { "epoch": 0.8576053756872327, "grad_norm": 0.546950101852417, "learning_rate": 2.4600407726829587e-06, "loss": 4.1159, "step": 28078 }, { "epoch": 0.8576359193646915, "grad_norm": 0.5295298099517822, "learning_rate": 2.459003176606156e-06, "loss": 4.2868, "step": 28079 }, { "epoch": 0.8576664630421503, "grad_norm": 0.5253463983535767, "learning_rate": 2.4579657880759e-06, "loss": 4.2456, "step": 28080 }, { "epoch": 0.857697006719609, "grad_norm": 0.5256808996200562, "learning_rate": 2.4569286071017492e-06, "loss": 4.2268, "step": 28081 }, { "epoch": 0.8577275503970678, "grad_norm": 0.5417764186859131, "learning_rate": 2.4558916336932415e-06, "loss": 4.3387, "step": 28082 }, { "epoch": 0.8577580940745265, "grad_norm": 0.5203818082809448, "learning_rate": 2.454854867859935e-06, "loss": 4.1573, "step": 28083 }, { "epoch": 0.8577886377519853, "grad_norm": 0.5319849252700806, "learning_rate": 2.4538183096113693e-06, "loss": 4.3302, "step": 28084 }, { "epoch": 0.8578191814294441, "grad_norm": 0.5250775814056396, "learning_rate": 2.4527819589570926e-06, "loss": 4.2685, "step": 28085 }, { "epoch": 0.8578497251069028, "grad_norm": 0.5418581366539001, "learning_rate": 2.4517458159066446e-06, "loss": 4.2248, "step": 28086 }, { "epoch": 0.8578802687843616, "grad_norm": 0.5285242199897766, "learning_rate": 2.450709880469562e-06, "loss": 4.2207, "step": 28087 }, { "epoch": 0.8579108124618204, "grad_norm": 0.53141850233078, "learning_rate": 2.4496741526553874e-06, "loss": 4.2282, "step": 28088 }, { "epoch": 0.8579413561392791, "grad_norm": 0.5472190380096436, "learning_rate": 2.4486386324736626e-06, "loss": 4.2342, "step": 28089 }, { "epoch": 0.8579718998167379, "grad_norm": 0.5253996253013611, "learning_rate": 2.447603319933911e-06, "loss": 4.2799, "step": 28090 }, { "epoch": 0.8580024434941967, "grad_norm": 0.5351995229721069, "learning_rate": 2.446568215045669e-06, "loss": 4.3436, "step": 28091 }, { "epoch": 0.8580329871716554, "grad_norm": 0.5245857238769531, "learning_rate": 2.445533317818477e-06, "loss": 4.2895, "step": 28092 }, { "epoch": 0.8580635308491142, "grad_norm": 0.530778706073761, "learning_rate": 2.4444986282618515e-06, "loss": 4.2751, "step": 28093 }, { "epoch": 0.858094074526573, "grad_norm": 0.5275421738624573, "learning_rate": 2.4434641463853214e-06, "loss": 4.2641, "step": 28094 }, { "epoch": 0.8581246182040317, "grad_norm": 0.5290459394454956, "learning_rate": 2.4424298721984205e-06, "loss": 4.2096, "step": 28095 }, { "epoch": 0.8581551618814905, "grad_norm": 0.534882664680481, "learning_rate": 2.441395805710661e-06, "loss": 4.3148, "step": 28096 }, { "epoch": 0.8581857055589494, "grad_norm": 0.5275418758392334, "learning_rate": 2.4403619469315687e-06, "loss": 4.2319, "step": 28097 }, { "epoch": 0.858216249236408, "grad_norm": 0.5328581929206848, "learning_rate": 2.439328295870669e-06, "loss": 4.2139, "step": 28098 }, { "epoch": 0.8582467929138669, "grad_norm": 0.5222436785697937, "learning_rate": 2.438294852537468e-06, "loss": 4.2051, "step": 28099 }, { "epoch": 0.8582773365913255, "grad_norm": 0.52979975938797, "learning_rate": 2.4372616169414886e-06, "loss": 4.272, "step": 28100 }, { "epoch": 0.8583078802687844, "grad_norm": 0.5277209877967834, "learning_rate": 2.436228589092246e-06, "loss": 4.2994, "step": 28101 }, { "epoch": 0.8583384239462432, "grad_norm": 0.5298748016357422, "learning_rate": 2.4351957689992404e-06, "loss": 4.2388, "step": 28102 }, { "epoch": 0.8583689676237019, "grad_norm": 0.5219042897224426, "learning_rate": 2.4341631566719954e-06, "loss": 4.2564, "step": 28103 }, { "epoch": 0.8583995113011607, "grad_norm": 0.5146057605743408, "learning_rate": 2.4331307521200053e-06, "loss": 4.1047, "step": 28104 }, { "epoch": 0.8584300549786195, "grad_norm": 0.5273036360740662, "learning_rate": 2.4320985553527853e-06, "loss": 4.2625, "step": 28105 }, { "epoch": 0.8584605986560782, "grad_norm": 0.5275761485099792, "learning_rate": 2.4310665663798417e-06, "loss": 4.2354, "step": 28106 }, { "epoch": 0.858491142333537, "grad_norm": 0.5256001949310303, "learning_rate": 2.4300347852106663e-06, "loss": 4.2676, "step": 28107 }, { "epoch": 0.8585216860109958, "grad_norm": 0.5409285426139832, "learning_rate": 2.429003211854766e-06, "loss": 4.2099, "step": 28108 }, { "epoch": 0.8585522296884545, "grad_norm": 0.5208927989006042, "learning_rate": 2.4279718463216417e-06, "loss": 4.1647, "step": 28109 }, { "epoch": 0.8585827733659133, "grad_norm": 0.5202971696853638, "learning_rate": 2.426940688620782e-06, "loss": 4.1934, "step": 28110 }, { "epoch": 0.8586133170433721, "grad_norm": 0.5298035740852356, "learning_rate": 2.4259097387616837e-06, "loss": 4.2472, "step": 28111 }, { "epoch": 0.8586438607208308, "grad_norm": 0.5209118127822876, "learning_rate": 2.4248789967538486e-06, "loss": 4.2186, "step": 28112 }, { "epoch": 0.8586744043982896, "grad_norm": 0.5349254012107849, "learning_rate": 2.423848462606751e-06, "loss": 4.2846, "step": 28113 }, { "epoch": 0.8587049480757484, "grad_norm": 0.530181884765625, "learning_rate": 2.422818136329896e-06, "loss": 4.1705, "step": 28114 }, { "epoch": 0.8587354917532071, "grad_norm": 0.5275227427482605, "learning_rate": 2.421788017932758e-06, "loss": 4.2169, "step": 28115 }, { "epoch": 0.8587660354306659, "grad_norm": 0.5254154205322266, "learning_rate": 2.420758107424828e-06, "loss": 4.1873, "step": 28116 }, { "epoch": 0.8587965791081246, "grad_norm": 0.5415675044059753, "learning_rate": 2.419728404815588e-06, "loss": 4.2828, "step": 28117 }, { "epoch": 0.8588271227855834, "grad_norm": 0.5325067639350891, "learning_rate": 2.418698910114517e-06, "loss": 4.3879, "step": 28118 }, { "epoch": 0.8588576664630422, "grad_norm": 0.5397466421127319, "learning_rate": 2.4176696233310927e-06, "loss": 4.3003, "step": 28119 }, { "epoch": 0.8588882101405009, "grad_norm": 0.5242062211036682, "learning_rate": 2.4166405444747992e-06, "loss": 4.2054, "step": 28120 }, { "epoch": 0.8589187538179597, "grad_norm": 0.5299602150917053, "learning_rate": 2.4156116735551015e-06, "loss": 4.2747, "step": 28121 }, { "epoch": 0.8589492974954185, "grad_norm": 0.5363380312919617, "learning_rate": 2.414583010581481e-06, "loss": 4.2903, "step": 28122 }, { "epoch": 0.8589798411728772, "grad_norm": 0.5384120941162109, "learning_rate": 2.4135545555634134e-06, "loss": 4.2159, "step": 28123 }, { "epoch": 0.859010384850336, "grad_norm": 0.5185882449150085, "learning_rate": 2.4125263085103546e-06, "loss": 4.1865, "step": 28124 }, { "epoch": 0.8590409285277948, "grad_norm": 0.5295257568359375, "learning_rate": 2.4114982694317777e-06, "loss": 4.267, "step": 28125 }, { "epoch": 0.8590714722052535, "grad_norm": 0.5284509062767029, "learning_rate": 2.410470438337156e-06, "loss": 4.2511, "step": 28126 }, { "epoch": 0.8591020158827123, "grad_norm": 0.5280120372772217, "learning_rate": 2.4094428152359463e-06, "loss": 4.298, "step": 28127 }, { "epoch": 0.8591325595601711, "grad_norm": 0.5325009822845459, "learning_rate": 2.4084154001376065e-06, "loss": 4.3192, "step": 28128 }, { "epoch": 0.8591631032376298, "grad_norm": 0.5271163582801819, "learning_rate": 2.40738819305161e-06, "loss": 4.2744, "step": 28129 }, { "epoch": 0.8591936469150886, "grad_norm": 0.5360667705535889, "learning_rate": 2.4063611939874e-06, "loss": 4.2207, "step": 28130 }, { "epoch": 0.8592241905925473, "grad_norm": 0.5240610241889954, "learning_rate": 2.405334402954443e-06, "loss": 4.23, "step": 28131 }, { "epoch": 0.8592547342700061, "grad_norm": 0.5237508416175842, "learning_rate": 2.4043078199621897e-06, "loss": 4.1872, "step": 28132 }, { "epoch": 0.8592852779474649, "grad_norm": 0.5234427452087402, "learning_rate": 2.403281445020089e-06, "loss": 4.2323, "step": 28133 }, { "epoch": 0.8593158216249236, "grad_norm": 0.5397931337356567, "learning_rate": 2.4022552781375967e-06, "loss": 4.2829, "step": 28134 }, { "epoch": 0.8593463653023824, "grad_norm": 0.5356723070144653, "learning_rate": 2.4012293193241524e-06, "loss": 4.2126, "step": 28135 }, { "epoch": 0.8593769089798412, "grad_norm": 0.525303065776825, "learning_rate": 2.4002035685892128e-06, "loss": 4.1271, "step": 28136 }, { "epoch": 0.8594074526572999, "grad_norm": 0.5252490639686584, "learning_rate": 2.3991780259422196e-06, "loss": 4.2969, "step": 28137 }, { "epoch": 0.8594379963347587, "grad_norm": 0.5314795970916748, "learning_rate": 2.3981526913926135e-06, "loss": 4.2587, "step": 28138 }, { "epoch": 0.8594685400122175, "grad_norm": 0.5324274897575378, "learning_rate": 2.397127564949833e-06, "loss": 4.2036, "step": 28139 }, { "epoch": 0.8594990836896762, "grad_norm": 0.536549985408783, "learning_rate": 2.396102646623327e-06, "loss": 4.2251, "step": 28140 }, { "epoch": 0.859529627367135, "grad_norm": 0.5394290685653687, "learning_rate": 2.3950779364225214e-06, "loss": 4.2109, "step": 28141 }, { "epoch": 0.8595601710445938, "grad_norm": 0.5237520337104797, "learning_rate": 2.394053434356855e-06, "loss": 4.1845, "step": 28142 }, { "epoch": 0.8595907147220525, "grad_norm": 0.5394224524497986, "learning_rate": 2.393029140435765e-06, "loss": 4.2262, "step": 28143 }, { "epoch": 0.8596212583995113, "grad_norm": 0.5342580080032349, "learning_rate": 2.392005054668675e-06, "loss": 4.2732, "step": 28144 }, { "epoch": 0.8596518020769701, "grad_norm": 0.5314900279045105, "learning_rate": 2.3909811770650185e-06, "loss": 4.2521, "step": 28145 }, { "epoch": 0.8596823457544288, "grad_norm": 0.5321723222732544, "learning_rate": 2.3899575076342275e-06, "loss": 4.2327, "step": 28146 }, { "epoch": 0.8597128894318876, "grad_norm": 0.5450416803359985, "learning_rate": 2.388934046385721e-06, "loss": 4.2896, "step": 28147 }, { "epoch": 0.8597434331093463, "grad_norm": 0.5289819240570068, "learning_rate": 2.3879107933289233e-06, "loss": 4.3347, "step": 28148 }, { "epoch": 0.8597739767868051, "grad_norm": 0.5356807112693787, "learning_rate": 2.3868877484732597e-06, "loss": 4.3444, "step": 28149 }, { "epoch": 0.8598045204642639, "grad_norm": 0.5319788455963135, "learning_rate": 2.3858649118281396e-06, "loss": 4.2398, "step": 28150 }, { "epoch": 0.8598350641417226, "grad_norm": 0.5242642760276794, "learning_rate": 2.3848422834029964e-06, "loss": 4.1651, "step": 28151 }, { "epoch": 0.8598656078191814, "grad_norm": 0.5390172600746155, "learning_rate": 2.383819863207232e-06, "loss": 4.3769, "step": 28152 }, { "epoch": 0.8598961514966402, "grad_norm": 0.5340988039970398, "learning_rate": 2.382797651250268e-06, "loss": 4.2588, "step": 28153 }, { "epoch": 0.8599266951740989, "grad_norm": 0.5313727259635925, "learning_rate": 2.3817756475415176e-06, "loss": 4.3175, "step": 28154 }, { "epoch": 0.8599572388515577, "grad_norm": 0.5294703245162964, "learning_rate": 2.380753852090381e-06, "loss": 4.2068, "step": 28155 }, { "epoch": 0.8599877825290165, "grad_norm": 0.529013454914093, "learning_rate": 2.3797322649062757e-06, "loss": 4.1898, "step": 28156 }, { "epoch": 0.8600183262064752, "grad_norm": 0.5266774892807007, "learning_rate": 2.3787108859986114e-06, "loss": 4.2418, "step": 28157 }, { "epoch": 0.860048869883934, "grad_norm": 0.5253687500953674, "learning_rate": 2.3776897153767825e-06, "loss": 4.2278, "step": 28158 }, { "epoch": 0.8600794135613928, "grad_norm": 0.530127227306366, "learning_rate": 2.376668753050193e-06, "loss": 4.1833, "step": 28159 }, { "epoch": 0.8601099572388515, "grad_norm": 0.5284995436668396, "learning_rate": 2.3756479990282523e-06, "loss": 4.0684, "step": 28160 }, { "epoch": 0.8601405009163103, "grad_norm": 0.5315219163894653, "learning_rate": 2.3746274533203466e-06, "loss": 4.3113, "step": 28161 }, { "epoch": 0.8601710445937691, "grad_norm": 0.5306499600410461, "learning_rate": 2.373607115935886e-06, "loss": 4.2407, "step": 28162 }, { "epoch": 0.8602015882712278, "grad_norm": 0.5347791314125061, "learning_rate": 2.3725869868842566e-06, "loss": 4.2031, "step": 28163 }, { "epoch": 0.8602321319486866, "grad_norm": 0.5187878608703613, "learning_rate": 2.371567066174846e-06, "loss": 4.1969, "step": 28164 }, { "epoch": 0.8602626756261453, "grad_norm": 0.5390495657920837, "learning_rate": 2.3705473538170596e-06, "loss": 4.253, "step": 28165 }, { "epoch": 0.8602932193036041, "grad_norm": 0.5308225750923157, "learning_rate": 2.369527849820272e-06, "loss": 4.2722, "step": 28166 }, { "epoch": 0.860323762981063, "grad_norm": 0.5202808380126953, "learning_rate": 2.3685085541938767e-06, "loss": 4.1943, "step": 28167 }, { "epoch": 0.8603543066585216, "grad_norm": 0.5215576887130737, "learning_rate": 2.367489466947265e-06, "loss": 4.2037, "step": 28168 }, { "epoch": 0.8603848503359804, "grad_norm": 0.5284984707832336, "learning_rate": 2.3664705880898115e-06, "loss": 4.1921, "step": 28169 }, { "epoch": 0.8604153940134392, "grad_norm": 0.5183195471763611, "learning_rate": 2.3654519176308956e-06, "loss": 4.275, "step": 28170 }, { "epoch": 0.8604459376908979, "grad_norm": 0.5276667475700378, "learning_rate": 2.3644334555799093e-06, "loss": 4.2213, "step": 28171 }, { "epoch": 0.8604764813683567, "grad_norm": 0.5240126848220825, "learning_rate": 2.3634152019462176e-06, "loss": 4.1935, "step": 28172 }, { "epoch": 0.8605070250458156, "grad_norm": 0.5355263352394104, "learning_rate": 2.3623971567391988e-06, "loss": 4.2812, "step": 28173 }, { "epoch": 0.8605375687232742, "grad_norm": 0.5354782342910767, "learning_rate": 2.361379319968235e-06, "loss": 4.1699, "step": 28174 }, { "epoch": 0.860568112400733, "grad_norm": 0.5396733283996582, "learning_rate": 2.3603616916426875e-06, "loss": 4.1884, "step": 28175 }, { "epoch": 0.8605986560781919, "grad_norm": 0.5250255465507507, "learning_rate": 2.3593442717719267e-06, "loss": 4.1717, "step": 28176 }, { "epoch": 0.8606291997556506, "grad_norm": 0.536409854888916, "learning_rate": 2.358327060365331e-06, "loss": 4.2169, "step": 28177 }, { "epoch": 0.8606597434331094, "grad_norm": 0.521987795829773, "learning_rate": 2.3573100574322577e-06, "loss": 4.2365, "step": 28178 }, { "epoch": 0.8606902871105682, "grad_norm": 0.5198222994804382, "learning_rate": 2.3562932629820704e-06, "loss": 4.2643, "step": 28179 }, { "epoch": 0.8607208307880269, "grad_norm": 0.534129798412323, "learning_rate": 2.3552766770241346e-06, "loss": 4.3488, "step": 28180 }, { "epoch": 0.8607513744654857, "grad_norm": 0.5242107510566711, "learning_rate": 2.3542602995678066e-06, "loss": 4.0342, "step": 28181 }, { "epoch": 0.8607819181429444, "grad_norm": 0.5245711803436279, "learning_rate": 2.3532441306224536e-06, "loss": 4.2899, "step": 28182 }, { "epoch": 0.8608124618204032, "grad_norm": 0.5203289985656738, "learning_rate": 2.352228170197418e-06, "loss": 4.2273, "step": 28183 }, { "epoch": 0.860843005497862, "grad_norm": 0.5309549570083618, "learning_rate": 2.351212418302062e-06, "loss": 4.246, "step": 28184 }, { "epoch": 0.8608735491753207, "grad_norm": 0.5402168035507202, "learning_rate": 2.350196874945745e-06, "loss": 4.363, "step": 28185 }, { "epoch": 0.8609040928527795, "grad_norm": 0.5279735326766968, "learning_rate": 2.349181540137804e-06, "loss": 4.2526, "step": 28186 }, { "epoch": 0.8609346365302383, "grad_norm": 0.5270362496376038, "learning_rate": 2.348166413887595e-06, "loss": 4.3024, "step": 28187 }, { "epoch": 0.860965180207697, "grad_norm": 0.5367329716682434, "learning_rate": 2.3471514962044695e-06, "loss": 4.3299, "step": 28188 }, { "epoch": 0.8609957238851558, "grad_norm": 0.5285533666610718, "learning_rate": 2.3461367870977637e-06, "loss": 4.2835, "step": 28189 }, { "epoch": 0.8610262675626146, "grad_norm": 0.5301806330680847, "learning_rate": 2.34512228657682e-06, "loss": 4.2008, "step": 28190 }, { "epoch": 0.8610568112400733, "grad_norm": 0.5275025367736816, "learning_rate": 2.3441079946509932e-06, "loss": 4.2182, "step": 28191 }, { "epoch": 0.8610873549175321, "grad_norm": 0.5332916975021362, "learning_rate": 2.343093911329605e-06, "loss": 4.2306, "step": 28192 }, { "epoch": 0.8611178985949909, "grad_norm": 0.5345675349235535, "learning_rate": 2.3420800366220047e-06, "loss": 4.2713, "step": 28193 }, { "epoch": 0.8611484422724496, "grad_norm": 0.5393587350845337, "learning_rate": 2.3410663705375175e-06, "loss": 4.2622, "step": 28194 }, { "epoch": 0.8611789859499084, "grad_norm": 0.5292951464653015, "learning_rate": 2.3400529130854885e-06, "loss": 4.2022, "step": 28195 }, { "epoch": 0.8612095296273672, "grad_norm": 0.5334609746932983, "learning_rate": 2.339039664275239e-06, "loss": 4.2067, "step": 28196 }, { "epoch": 0.8612400733048259, "grad_norm": 0.5343595147132874, "learning_rate": 2.338026624116105e-06, "loss": 4.1669, "step": 28197 }, { "epoch": 0.8612706169822847, "grad_norm": 0.5340554118156433, "learning_rate": 2.33701379261741e-06, "loss": 4.2372, "step": 28198 }, { "epoch": 0.8613011606597434, "grad_norm": 0.5314974188804626, "learning_rate": 2.336001169788482e-06, "loss": 4.2472, "step": 28199 }, { "epoch": 0.8613317043372022, "grad_norm": 0.5277349352836609, "learning_rate": 2.3349887556386426e-06, "loss": 4.2774, "step": 28200 }, { "epoch": 0.861362248014661, "grad_norm": 0.5282987952232361, "learning_rate": 2.333976550177211e-06, "loss": 4.1264, "step": 28201 }, { "epoch": 0.8613927916921197, "grad_norm": 0.5295078158378601, "learning_rate": 2.3329645534135194e-06, "loss": 4.2069, "step": 28202 }, { "epoch": 0.8614233353695785, "grad_norm": 0.5320532321929932, "learning_rate": 2.3319527653568706e-06, "loss": 4.1285, "step": 28203 }, { "epoch": 0.8614538790470373, "grad_norm": 0.5305083394050598, "learning_rate": 2.330941186016589e-06, "loss": 4.135, "step": 28204 }, { "epoch": 0.861484422724496, "grad_norm": 0.5326453447341919, "learning_rate": 2.3299298154019906e-06, "loss": 4.2835, "step": 28205 }, { "epoch": 0.8615149664019548, "grad_norm": 0.5418381094932556, "learning_rate": 2.32891865352238e-06, "loss": 4.4086, "step": 28206 }, { "epoch": 0.8615455100794136, "grad_norm": 0.5356830954551697, "learning_rate": 2.3279077003870718e-06, "loss": 4.2531, "step": 28207 }, { "epoch": 0.8615760537568723, "grad_norm": 0.5419373512268066, "learning_rate": 2.3268969560053783e-06, "loss": 4.2288, "step": 28208 }, { "epoch": 0.8616065974343311, "grad_norm": 0.5244423151016235, "learning_rate": 2.325886420386597e-06, "loss": 4.2491, "step": 28209 }, { "epoch": 0.8616371411117899, "grad_norm": 0.547549843788147, "learning_rate": 2.324876093540043e-06, "loss": 4.2826, "step": 28210 }, { "epoch": 0.8616676847892486, "grad_norm": 0.5294981598854065, "learning_rate": 2.323865975475012e-06, "loss": 4.203, "step": 28211 }, { "epoch": 0.8616982284667074, "grad_norm": 0.5299951434135437, "learning_rate": 2.3228560662008043e-06, "loss": 4.2227, "step": 28212 }, { "epoch": 0.8617287721441662, "grad_norm": 0.5261077880859375, "learning_rate": 2.321846365726718e-06, "loss": 4.1893, "step": 28213 }, { "epoch": 0.8617593158216249, "grad_norm": 0.5333106517791748, "learning_rate": 2.3208368740620545e-06, "loss": 4.2535, "step": 28214 }, { "epoch": 0.8617898594990837, "grad_norm": 0.5243209600448608, "learning_rate": 2.319827591216106e-06, "loss": 4.197, "step": 28215 }, { "epoch": 0.8618204031765424, "grad_norm": 0.5309550762176514, "learning_rate": 2.318818517198168e-06, "loss": 4.2254, "step": 28216 }, { "epoch": 0.8618509468540012, "grad_norm": 0.5320018529891968, "learning_rate": 2.3178096520175246e-06, "loss": 4.2884, "step": 28217 }, { "epoch": 0.86188149053146, "grad_norm": 0.5247091054916382, "learning_rate": 2.316800995683471e-06, "loss": 4.2582, "step": 28218 }, { "epoch": 0.8619120342089187, "grad_norm": 0.523829460144043, "learning_rate": 2.315792548205298e-06, "loss": 4.2507, "step": 28219 }, { "epoch": 0.8619425778863775, "grad_norm": 0.537855327129364, "learning_rate": 2.31478430959228e-06, "loss": 4.2746, "step": 28220 }, { "epoch": 0.8619731215638363, "grad_norm": 0.516058087348938, "learning_rate": 2.313776279853708e-06, "loss": 4.1795, "step": 28221 }, { "epoch": 0.862003665241295, "grad_norm": 0.5325811505317688, "learning_rate": 2.312768458998865e-06, "loss": 4.2948, "step": 28222 }, { "epoch": 0.8620342089187538, "grad_norm": 0.5248048901557922, "learning_rate": 2.311760847037023e-06, "loss": 4.2555, "step": 28223 }, { "epoch": 0.8620647525962126, "grad_norm": 0.5424729585647583, "learning_rate": 2.3107534439774677e-06, "loss": 4.3409, "step": 28224 }, { "epoch": 0.8620952962736713, "grad_norm": 0.533652663230896, "learning_rate": 2.3097462498294698e-06, "loss": 4.2561, "step": 28225 }, { "epoch": 0.8621258399511301, "grad_norm": 0.5311244130134583, "learning_rate": 2.3087392646023054e-06, "loss": 4.2945, "step": 28226 }, { "epoch": 0.8621563836285889, "grad_norm": 0.5312528610229492, "learning_rate": 2.307732488305242e-06, "loss": 4.1589, "step": 28227 }, { "epoch": 0.8621869273060476, "grad_norm": 0.5296534895896912, "learning_rate": 2.3067259209475583e-06, "loss": 4.2511, "step": 28228 }, { "epoch": 0.8622174709835064, "grad_norm": 0.5334506630897522, "learning_rate": 2.3057195625385108e-06, "loss": 4.2204, "step": 28229 }, { "epoch": 0.8622480146609652, "grad_norm": 0.5313472151756287, "learning_rate": 2.3047134130873727e-06, "loss": 4.3105, "step": 28230 }, { "epoch": 0.8622785583384239, "grad_norm": 0.5794172883033752, "learning_rate": 2.3037074726034115e-06, "loss": 4.3278, "step": 28231 }, { "epoch": 0.8623091020158827, "grad_norm": 0.5273047685623169, "learning_rate": 2.3027017410958806e-06, "loss": 4.2807, "step": 28232 }, { "epoch": 0.8623396456933414, "grad_norm": 0.5241838693618774, "learning_rate": 2.301696218574048e-06, "loss": 4.2019, "step": 28233 }, { "epoch": 0.8623701893708002, "grad_norm": 0.5246680378913879, "learning_rate": 2.3006909050471647e-06, "loss": 4.2028, "step": 28234 }, { "epoch": 0.862400733048259, "grad_norm": 0.5241464972496033, "learning_rate": 2.29968580052449e-06, "loss": 4.2824, "step": 28235 }, { "epoch": 0.8624312767257177, "grad_norm": 0.5362768769264221, "learning_rate": 2.2986809050152853e-06, "loss": 4.3951, "step": 28236 }, { "epoch": 0.8624618204031765, "grad_norm": 0.5294899940490723, "learning_rate": 2.2976762185287937e-06, "loss": 4.2391, "step": 28237 }, { "epoch": 0.8624923640806353, "grad_norm": 0.520894467830658, "learning_rate": 2.296671741074269e-06, "loss": 4.1773, "step": 28238 }, { "epoch": 0.862522907758094, "grad_norm": 0.5454412698745728, "learning_rate": 2.2956674726609644e-06, "loss": 4.3194, "step": 28239 }, { "epoch": 0.8625534514355528, "grad_norm": 0.5339770913124084, "learning_rate": 2.2946634132981175e-06, "loss": 4.1717, "step": 28240 }, { "epoch": 0.8625839951130116, "grad_norm": 0.5394524335861206, "learning_rate": 2.293659562994982e-06, "loss": 4.3083, "step": 28241 }, { "epoch": 0.8626145387904703, "grad_norm": 0.5446884036064148, "learning_rate": 2.2926559217608e-06, "loss": 4.2419, "step": 28242 }, { "epoch": 0.8626450824679291, "grad_norm": 0.5212631225585938, "learning_rate": 2.2916524896048035e-06, "loss": 4.2765, "step": 28243 }, { "epoch": 0.862675626145388, "grad_norm": 0.5315840244293213, "learning_rate": 2.2906492665362404e-06, "loss": 4.2552, "step": 28244 }, { "epoch": 0.8627061698228466, "grad_norm": 0.5287367105484009, "learning_rate": 2.289646252564348e-06, "loss": 4.2316, "step": 28245 }, { "epoch": 0.8627367135003055, "grad_norm": 0.529079794883728, "learning_rate": 2.2886434476983547e-06, "loss": 4.2101, "step": 28246 }, { "epoch": 0.8627672571777643, "grad_norm": 0.5272803902626038, "learning_rate": 2.287640851947498e-06, "loss": 4.2532, "step": 28247 }, { "epoch": 0.862797800855223, "grad_norm": 0.5214528441429138, "learning_rate": 2.2866384653210144e-06, "loss": 4.2228, "step": 28248 }, { "epoch": 0.8628283445326818, "grad_norm": 0.5394098162651062, "learning_rate": 2.2856362878281244e-06, "loss": 4.2736, "step": 28249 }, { "epoch": 0.8628588882101405, "grad_norm": 0.5341584086418152, "learning_rate": 2.2846343194780656e-06, "loss": 4.233, "step": 28250 }, { "epoch": 0.8628894318875993, "grad_norm": 0.5239729285240173, "learning_rate": 2.2836325602800494e-06, "loss": 4.2467, "step": 28251 }, { "epoch": 0.8629199755650581, "grad_norm": 0.5348212718963623, "learning_rate": 2.2826310102433106e-06, "loss": 4.3114, "step": 28252 }, { "epoch": 0.8629505192425168, "grad_norm": 0.5278213024139404, "learning_rate": 2.2816296693770722e-06, "loss": 4.2585, "step": 28253 }, { "epoch": 0.8629810629199756, "grad_norm": 0.5311410427093506, "learning_rate": 2.280628537690546e-06, "loss": 4.1425, "step": 28254 }, { "epoch": 0.8630116065974344, "grad_norm": 0.5349856615066528, "learning_rate": 2.279627615192953e-06, "loss": 4.3437, "step": 28255 }, { "epoch": 0.8630421502748931, "grad_norm": 0.5292772054672241, "learning_rate": 2.2786269018935157e-06, "loss": 4.2272, "step": 28256 }, { "epoch": 0.8630726939523519, "grad_norm": 0.5250909924507141, "learning_rate": 2.2776263978014413e-06, "loss": 4.2381, "step": 28257 }, { "epoch": 0.8631032376298107, "grad_norm": 0.5392882823944092, "learning_rate": 2.2766261029259412e-06, "loss": 4.1938, "step": 28258 }, { "epoch": 0.8631337813072694, "grad_norm": 0.5418145656585693, "learning_rate": 2.2756260172762307e-06, "loss": 4.1155, "step": 28259 }, { "epoch": 0.8631643249847282, "grad_norm": 0.5308504104614258, "learning_rate": 2.2746261408615106e-06, "loss": 4.2484, "step": 28260 }, { "epoch": 0.863194868662187, "grad_norm": 0.5364878177642822, "learning_rate": 2.273626473690993e-06, "loss": 4.2954, "step": 28261 }, { "epoch": 0.8632254123396457, "grad_norm": 0.5261299014091492, "learning_rate": 2.2726270157738844e-06, "loss": 4.2693, "step": 28262 }, { "epoch": 0.8632559560171045, "grad_norm": 0.5302987098693848, "learning_rate": 2.2716277671193775e-06, "loss": 4.2919, "step": 28263 }, { "epoch": 0.8632864996945633, "grad_norm": 0.532113790512085, "learning_rate": 2.2706287277366845e-06, "loss": 4.2172, "step": 28264 }, { "epoch": 0.863317043372022, "grad_norm": 0.5292692184448242, "learning_rate": 2.2696298976350005e-06, "loss": 4.0926, "step": 28265 }, { "epoch": 0.8633475870494808, "grad_norm": 0.5244417786598206, "learning_rate": 2.2686312768235156e-06, "loss": 4.1399, "step": 28266 }, { "epoch": 0.8633781307269395, "grad_norm": 0.5383631587028503, "learning_rate": 2.2676328653114364e-06, "loss": 4.2566, "step": 28267 }, { "epoch": 0.8634086744043983, "grad_norm": 0.5333553552627563, "learning_rate": 2.2666346631079443e-06, "loss": 4.1754, "step": 28268 }, { "epoch": 0.8634392180818571, "grad_norm": 0.5435386300086975, "learning_rate": 2.265636670222235e-06, "loss": 4.2842, "step": 28269 }, { "epoch": 0.8634697617593158, "grad_norm": 0.5297269225120544, "learning_rate": 2.2646388866635005e-06, "loss": 4.191, "step": 28270 }, { "epoch": 0.8635003054367746, "grad_norm": 0.5302384495735168, "learning_rate": 2.2636413124409227e-06, "loss": 4.2524, "step": 28271 }, { "epoch": 0.8635308491142334, "grad_norm": 0.5402272939682007, "learning_rate": 2.2626439475636945e-06, "loss": 4.347, "step": 28272 }, { "epoch": 0.8635613927916921, "grad_norm": 0.5291469693183899, "learning_rate": 2.2616467920409917e-06, "loss": 4.2589, "step": 28273 }, { "epoch": 0.8635919364691509, "grad_norm": 0.5239687561988831, "learning_rate": 2.260649845881993e-06, "loss": 4.2003, "step": 28274 }, { "epoch": 0.8636224801466097, "grad_norm": 0.548736035823822, "learning_rate": 2.2596531090958856e-06, "loss": 4.2327, "step": 28275 }, { "epoch": 0.8636530238240684, "grad_norm": 0.5372143387794495, "learning_rate": 2.2586565816918455e-06, "loss": 3.9822, "step": 28276 }, { "epoch": 0.8636835675015272, "grad_norm": 0.5265926718711853, "learning_rate": 2.257660263679043e-06, "loss": 4.2178, "step": 28277 }, { "epoch": 0.863714111178986, "grad_norm": 0.5293514132499695, "learning_rate": 2.256664155066657e-06, "loss": 4.2999, "step": 28278 }, { "epoch": 0.8637446548564447, "grad_norm": 0.5243238806724548, "learning_rate": 2.2556682558638605e-06, "loss": 4.2151, "step": 28279 }, { "epoch": 0.8637751985339035, "grad_norm": 0.5423420667648315, "learning_rate": 2.2546725660798155e-06, "loss": 4.233, "step": 28280 }, { "epoch": 0.8638057422113622, "grad_norm": 0.5277048349380493, "learning_rate": 2.253677085723699e-06, "loss": 4.3534, "step": 28281 }, { "epoch": 0.863836285888821, "grad_norm": 0.5319881439208984, "learning_rate": 2.252681814804669e-06, "loss": 4.2182, "step": 28282 }, { "epoch": 0.8638668295662798, "grad_norm": 0.5244086384773254, "learning_rate": 2.2516867533318943e-06, "loss": 4.2365, "step": 28283 }, { "epoch": 0.8638973732437385, "grad_norm": 0.5280134677886963, "learning_rate": 2.250691901314539e-06, "loss": 4.1874, "step": 28284 }, { "epoch": 0.8639279169211973, "grad_norm": 0.5321569442749023, "learning_rate": 2.2496972587617543e-06, "loss": 4.249, "step": 28285 }, { "epoch": 0.8639584605986561, "grad_norm": 0.5267623662948608, "learning_rate": 2.2487028256827053e-06, "loss": 4.2615, "step": 28286 }, { "epoch": 0.8639890042761148, "grad_norm": 0.5232105851173401, "learning_rate": 2.2477086020865513e-06, "loss": 4.215, "step": 28287 }, { "epoch": 0.8640195479535736, "grad_norm": 0.5368859767913818, "learning_rate": 2.24671458798244e-06, "loss": 4.3129, "step": 28288 }, { "epoch": 0.8640500916310324, "grad_norm": 0.5326852798461914, "learning_rate": 2.2457207833795263e-06, "loss": 4.27, "step": 28289 }, { "epoch": 0.8640806353084911, "grad_norm": 0.5312557220458984, "learning_rate": 2.24472718828696e-06, "loss": 4.2835, "step": 28290 }, { "epoch": 0.8641111789859499, "grad_norm": 0.5224679708480835, "learning_rate": 2.2437338027138876e-06, "loss": 4.2352, "step": 28291 }, { "epoch": 0.8641417226634087, "grad_norm": 0.5198266506195068, "learning_rate": 2.2427406266694596e-06, "loss": 4.2128, "step": 28292 }, { "epoch": 0.8641722663408674, "grad_norm": 0.5438230037689209, "learning_rate": 2.241747660162821e-06, "loss": 4.2089, "step": 28293 }, { "epoch": 0.8642028100183262, "grad_norm": 0.5300233364105225, "learning_rate": 2.24075490320311e-06, "loss": 4.2781, "step": 28294 }, { "epoch": 0.864233353695785, "grad_norm": 0.5291438102722168, "learning_rate": 2.2397623557994713e-06, "loss": 4.2569, "step": 28295 }, { "epoch": 0.8642638973732437, "grad_norm": 0.5281867384910583, "learning_rate": 2.238770017961045e-06, "loss": 4.1645, "step": 28296 }, { "epoch": 0.8642944410507025, "grad_norm": 0.530813992023468, "learning_rate": 2.2377778896969626e-06, "loss": 4.2948, "step": 28297 }, { "epoch": 0.8643249847281612, "grad_norm": 0.5423721671104431, "learning_rate": 2.2367859710163667e-06, "loss": 4.2344, "step": 28298 }, { "epoch": 0.86435552840562, "grad_norm": 0.525242030620575, "learning_rate": 2.2357942619283812e-06, "loss": 4.3256, "step": 28299 }, { "epoch": 0.8643860720830788, "grad_norm": 0.520130455493927, "learning_rate": 2.2348027624421426e-06, "loss": 4.2642, "step": 28300 }, { "epoch": 0.8644166157605375, "grad_norm": 0.5355226993560791, "learning_rate": 2.233811472566785e-06, "loss": 4.3355, "step": 28301 }, { "epoch": 0.8644471594379963, "grad_norm": 0.5228787660598755, "learning_rate": 2.2328203923114243e-06, "loss": 4.2135, "step": 28302 }, { "epoch": 0.8644777031154551, "grad_norm": 0.5339783430099487, "learning_rate": 2.231829521685197e-06, "loss": 4.147, "step": 28303 }, { "epoch": 0.8645082467929138, "grad_norm": 0.5234789848327637, "learning_rate": 2.230838860697218e-06, "loss": 4.2712, "step": 28304 }, { "epoch": 0.8645387904703726, "grad_norm": 0.5315524935722351, "learning_rate": 2.2298484093566165e-06, "loss": 4.263, "step": 28305 }, { "epoch": 0.8645693341478314, "grad_norm": 0.5322576761245728, "learning_rate": 2.2288581676725013e-06, "loss": 4.2372, "step": 28306 }, { "epoch": 0.8645998778252901, "grad_norm": 0.5276505351066589, "learning_rate": 2.2278681356540043e-06, "loss": 4.207, "step": 28307 }, { "epoch": 0.8646304215027489, "grad_norm": 0.5389391779899597, "learning_rate": 2.2268783133102265e-06, "loss": 4.2574, "step": 28308 }, { "epoch": 0.8646609651802077, "grad_norm": 0.5272442698478699, "learning_rate": 2.2258887006502916e-06, "loss": 4.2735, "step": 28309 }, { "epoch": 0.8646915088576664, "grad_norm": 0.5348106026649475, "learning_rate": 2.224899297683311e-06, "loss": 4.2266, "step": 28310 }, { "epoch": 0.8647220525351252, "grad_norm": 0.5462524890899658, "learning_rate": 2.223910104418389e-06, "loss": 4.2517, "step": 28311 }, { "epoch": 0.864752596212584, "grad_norm": 0.5232529044151306, "learning_rate": 2.222921120864635e-06, "loss": 4.1826, "step": 28312 }, { "epoch": 0.8647831398900427, "grad_norm": 0.5222824215888977, "learning_rate": 2.2219323470311636e-06, "loss": 4.2222, "step": 28313 }, { "epoch": 0.8648136835675015, "grad_norm": 0.5335538387298584, "learning_rate": 2.220943782927068e-06, "loss": 4.2611, "step": 28314 }, { "epoch": 0.8648442272449602, "grad_norm": 0.5289366841316223, "learning_rate": 2.219955428561457e-06, "loss": 4.331, "step": 28315 }, { "epoch": 0.864874770922419, "grad_norm": 0.5418328642845154, "learning_rate": 2.218967283943427e-06, "loss": 4.2765, "step": 28316 }, { "epoch": 0.8649053145998779, "grad_norm": 0.5308566093444824, "learning_rate": 2.217979349082075e-06, "loss": 4.205, "step": 28317 }, { "epoch": 0.8649358582773365, "grad_norm": 0.5358874201774597, "learning_rate": 2.2169916239865087e-06, "loss": 4.1361, "step": 28318 }, { "epoch": 0.8649664019547953, "grad_norm": 0.5381378531455994, "learning_rate": 2.216004108665806e-06, "loss": 4.3011, "step": 28319 }, { "epoch": 0.8649969456322542, "grad_norm": 0.5311499238014221, "learning_rate": 2.2150168031290747e-06, "loss": 4.2251, "step": 28320 }, { "epoch": 0.8650274893097128, "grad_norm": 0.5250537991523743, "learning_rate": 2.2140297073853985e-06, "loss": 4.2369, "step": 28321 }, { "epoch": 0.8650580329871717, "grad_norm": 0.5202180743217468, "learning_rate": 2.2130428214438614e-06, "loss": 4.2123, "step": 28322 }, { "epoch": 0.8650885766646305, "grad_norm": 0.529973566532135, "learning_rate": 2.212056145313557e-06, "loss": 4.2138, "step": 28323 }, { "epoch": 0.8651191203420892, "grad_norm": 0.5471616983413696, "learning_rate": 2.211069679003569e-06, "loss": 4.2425, "step": 28324 }, { "epoch": 0.865149664019548, "grad_norm": 0.5364882349967957, "learning_rate": 2.210083422522977e-06, "loss": 4.2966, "step": 28325 }, { "epoch": 0.8651802076970068, "grad_norm": 0.5287774205207825, "learning_rate": 2.2090973758808644e-06, "loss": 4.3191, "step": 28326 }, { "epoch": 0.8652107513744655, "grad_norm": 0.5356457829475403, "learning_rate": 2.208111539086313e-06, "loss": 4.2668, "step": 28327 }, { "epoch": 0.8652412950519243, "grad_norm": 0.5265788435935974, "learning_rate": 2.2071259121483947e-06, "loss": 4.3037, "step": 28328 }, { "epoch": 0.8652718387293831, "grad_norm": 0.5406325459480286, "learning_rate": 2.2061404950761868e-06, "loss": 4.2779, "step": 28329 }, { "epoch": 0.8653023824068418, "grad_norm": 0.5369817018508911, "learning_rate": 2.2051552878787655e-06, "loss": 4.3067, "step": 28330 }, { "epoch": 0.8653329260843006, "grad_norm": 0.5261664390563965, "learning_rate": 2.2041702905651967e-06, "loss": 4.2436, "step": 28331 }, { "epoch": 0.8653634697617593, "grad_norm": 0.5349728465080261, "learning_rate": 2.203185503144556e-06, "loss": 4.2481, "step": 28332 }, { "epoch": 0.8653940134392181, "grad_norm": 0.5238677263259888, "learning_rate": 2.2022009256259024e-06, "loss": 4.195, "step": 28333 }, { "epoch": 0.8654245571166769, "grad_norm": 0.5343533158302307, "learning_rate": 2.2012165580183123e-06, "loss": 4.2949, "step": 28334 }, { "epoch": 0.8654551007941356, "grad_norm": 0.5371793508529663, "learning_rate": 2.200232400330837e-06, "loss": 4.2252, "step": 28335 }, { "epoch": 0.8654856444715944, "grad_norm": 0.5366499423980713, "learning_rate": 2.19924845257255e-06, "loss": 4.221, "step": 28336 }, { "epoch": 0.8655161881490532, "grad_norm": 0.5247464776039124, "learning_rate": 2.1982647147525014e-06, "loss": 4.2805, "step": 28337 }, { "epoch": 0.8655467318265119, "grad_norm": 0.5501605868339539, "learning_rate": 2.197281186879757e-06, "loss": 4.2153, "step": 28338 }, { "epoch": 0.8655772755039707, "grad_norm": 0.5262987017631531, "learning_rate": 2.1962978689633652e-06, "loss": 4.2524, "step": 28339 }, { "epoch": 0.8656078191814295, "grad_norm": 0.5299748778343201, "learning_rate": 2.195314761012382e-06, "loss": 4.3062, "step": 28340 }, { "epoch": 0.8656383628588882, "grad_norm": 0.5218067765235901, "learning_rate": 2.1943318630358646e-06, "loss": 4.1932, "step": 28341 }, { "epoch": 0.865668906536347, "grad_norm": 0.533138632774353, "learning_rate": 2.1933491750428552e-06, "loss": 4.3323, "step": 28342 }, { "epoch": 0.8656994502138058, "grad_norm": 0.5304123759269714, "learning_rate": 2.1923666970424086e-06, "loss": 4.3021, "step": 28343 }, { "epoch": 0.8657299938912645, "grad_norm": 0.5444827079772949, "learning_rate": 2.191384429043572e-06, "loss": 4.3154, "step": 28344 }, { "epoch": 0.8657605375687233, "grad_norm": 0.5325029492378235, "learning_rate": 2.190402371055378e-06, "loss": 4.2359, "step": 28345 }, { "epoch": 0.8657910812461821, "grad_norm": 0.5352311730384827, "learning_rate": 2.18942052308688e-06, "loss": 4.2849, "step": 28346 }, { "epoch": 0.8658216249236408, "grad_norm": 0.5319965481758118, "learning_rate": 2.1884388851471203e-06, "loss": 4.2597, "step": 28347 }, { "epoch": 0.8658521686010996, "grad_norm": 0.5215669274330139, "learning_rate": 2.1874574572451262e-06, "loss": 4.148, "step": 28348 }, { "epoch": 0.8658827122785583, "grad_norm": 0.5207663178443909, "learning_rate": 2.1864762393899452e-06, "loss": 4.299, "step": 28349 }, { "epoch": 0.8659132559560171, "grad_norm": 0.5185745358467102, "learning_rate": 2.1854952315906037e-06, "loss": 4.2336, "step": 28350 }, { "epoch": 0.8659437996334759, "grad_norm": 0.5314834117889404, "learning_rate": 2.1845144338561413e-06, "loss": 4.2942, "step": 28351 }, { "epoch": 0.8659743433109346, "grad_norm": 0.5280306935310364, "learning_rate": 2.1835338461955847e-06, "loss": 4.2791, "step": 28352 }, { "epoch": 0.8660048869883934, "grad_norm": 0.535595178604126, "learning_rate": 2.1825534686179595e-06, "loss": 4.2536, "step": 28353 }, { "epoch": 0.8660354306658522, "grad_norm": 0.5213989615440369, "learning_rate": 2.1815733011322947e-06, "loss": 4.2355, "step": 28354 }, { "epoch": 0.8660659743433109, "grad_norm": 0.5350274443626404, "learning_rate": 2.1805933437476222e-06, "loss": 4.2473, "step": 28355 }, { "epoch": 0.8660965180207697, "grad_norm": 0.5357035994529724, "learning_rate": 2.179613596472954e-06, "loss": 4.2784, "step": 28356 }, { "epoch": 0.8661270616982285, "grad_norm": 0.5341383218765259, "learning_rate": 2.1786340593173165e-06, "loss": 4.238, "step": 28357 }, { "epoch": 0.8661576053756872, "grad_norm": 0.538324236869812, "learning_rate": 2.1776547322897327e-06, "loss": 4.1985, "step": 28358 }, { "epoch": 0.866188149053146, "grad_norm": 0.530247688293457, "learning_rate": 2.1766756153992126e-06, "loss": 4.2269, "step": 28359 }, { "epoch": 0.8662186927306048, "grad_norm": 0.5249478816986084, "learning_rate": 2.1756967086547756e-06, "loss": 4.2432, "step": 28360 }, { "epoch": 0.8662492364080635, "grad_norm": 0.5335418581962585, "learning_rate": 2.1747180120654352e-06, "loss": 4.3212, "step": 28361 }, { "epoch": 0.8662797800855223, "grad_norm": 0.5308148860931396, "learning_rate": 2.1737395256402004e-06, "loss": 4.2767, "step": 28362 }, { "epoch": 0.8663103237629811, "grad_norm": 0.5335373282432556, "learning_rate": 2.1727612493880805e-06, "loss": 4.2262, "step": 28363 }, { "epoch": 0.8663408674404398, "grad_norm": 0.5266566276550293, "learning_rate": 2.1717831833180907e-06, "loss": 4.2244, "step": 28364 }, { "epoch": 0.8663714111178986, "grad_norm": 0.5306997895240784, "learning_rate": 2.170805327439224e-06, "loss": 4.3629, "step": 28365 }, { "epoch": 0.8664019547953573, "grad_norm": 0.5324711799621582, "learning_rate": 2.1698276817604944e-06, "loss": 4.3185, "step": 28366 }, { "epoch": 0.8664324984728161, "grad_norm": 0.5285162925720215, "learning_rate": 2.1688502462909014e-06, "loss": 4.3015, "step": 28367 }, { "epoch": 0.8664630421502749, "grad_norm": 0.528761088848114, "learning_rate": 2.1678730210394348e-06, "loss": 4.28, "step": 28368 }, { "epoch": 0.8664935858277336, "grad_norm": 0.5299690961837769, "learning_rate": 2.1668960060151095e-06, "loss": 4.2614, "step": 28369 }, { "epoch": 0.8665241295051924, "grad_norm": 0.52571040391922, "learning_rate": 2.165919201226904e-06, "loss": 4.1255, "step": 28370 }, { "epoch": 0.8665546731826512, "grad_norm": 0.5251391530036926, "learning_rate": 2.164942606683823e-06, "loss": 4.1864, "step": 28371 }, { "epoch": 0.8665852168601099, "grad_norm": 0.5246294140815735, "learning_rate": 2.163966222394859e-06, "loss": 4.2052, "step": 28372 }, { "epoch": 0.8666157605375687, "grad_norm": 0.5384082198143005, "learning_rate": 2.1629900483689957e-06, "loss": 4.2827, "step": 28373 }, { "epoch": 0.8666463042150275, "grad_norm": 0.5232259631156921, "learning_rate": 2.1620140846152242e-06, "loss": 4.2825, "step": 28374 }, { "epoch": 0.8666768478924862, "grad_norm": 0.5431506633758545, "learning_rate": 2.161038331142534e-06, "loss": 4.2966, "step": 28375 }, { "epoch": 0.866707391569945, "grad_norm": 0.5249344706535339, "learning_rate": 2.1600627879599044e-06, "loss": 4.2007, "step": 28376 }, { "epoch": 0.8667379352474038, "grad_norm": 0.5301926136016846, "learning_rate": 2.1590874550763195e-06, "loss": 4.2522, "step": 28377 }, { "epoch": 0.8667684789248625, "grad_norm": 0.5357106328010559, "learning_rate": 2.158112332500764e-06, "loss": 4.2267, "step": 28378 }, { "epoch": 0.8667990226023213, "grad_norm": 0.5341749787330627, "learning_rate": 2.1571374202422085e-06, "loss": 4.2693, "step": 28379 }, { "epoch": 0.8668295662797801, "grad_norm": 0.5414693355560303, "learning_rate": 2.1561627183096374e-06, "loss": 4.2394, "step": 28380 }, { "epoch": 0.8668601099572388, "grad_norm": 0.5268587470054626, "learning_rate": 2.1551882267120155e-06, "loss": 4.3059, "step": 28381 }, { "epoch": 0.8668906536346976, "grad_norm": 0.5337581038475037, "learning_rate": 2.1542139454583276e-06, "loss": 4.2722, "step": 28382 }, { "epoch": 0.8669211973121563, "grad_norm": 0.5125944018363953, "learning_rate": 2.153239874557536e-06, "loss": 4.2605, "step": 28383 }, { "epoch": 0.8669517409896151, "grad_norm": 0.5282191038131714, "learning_rate": 2.1522660140186083e-06, "loss": 4.2923, "step": 28384 }, { "epoch": 0.8669822846670739, "grad_norm": 0.5365642309188843, "learning_rate": 2.1512923638505155e-06, "loss": 4.1923, "step": 28385 }, { "epoch": 0.8670128283445326, "grad_norm": 0.5439921617507935, "learning_rate": 2.150318924062225e-06, "loss": 4.0814, "step": 28386 }, { "epoch": 0.8670433720219914, "grad_norm": 0.5297921299934387, "learning_rate": 2.149345694662691e-06, "loss": 4.1373, "step": 28387 }, { "epoch": 0.8670739156994502, "grad_norm": 0.5212216377258301, "learning_rate": 2.1483726756608815e-06, "loss": 4.1347, "step": 28388 }, { "epoch": 0.8671044593769089, "grad_norm": 0.529169499874115, "learning_rate": 2.147399867065758e-06, "loss": 4.1247, "step": 28389 }, { "epoch": 0.8671350030543677, "grad_norm": 0.5342528820037842, "learning_rate": 2.1464272688862698e-06, "loss": 4.3036, "step": 28390 }, { "epoch": 0.8671655467318266, "grad_norm": 0.5295559167861938, "learning_rate": 2.145454881131376e-06, "loss": 4.2071, "step": 28391 }, { "epoch": 0.8671960904092852, "grad_norm": 0.5371735095977783, "learning_rate": 2.144482703810033e-06, "loss": 4.2645, "step": 28392 }, { "epoch": 0.867226634086744, "grad_norm": 0.5263355374336243, "learning_rate": 2.1435107369311843e-06, "loss": 4.2404, "step": 28393 }, { "epoch": 0.8672571777642029, "grad_norm": 0.5278381705284119, "learning_rate": 2.142538980503783e-06, "loss": 4.1824, "step": 28394 }, { "epoch": 0.8672877214416616, "grad_norm": 0.5369970798492432, "learning_rate": 2.141567434536784e-06, "loss": 4.2993, "step": 28395 }, { "epoch": 0.8673182651191204, "grad_norm": 0.5338731408119202, "learning_rate": 2.1405960990391188e-06, "loss": 4.1976, "step": 28396 }, { "epoch": 0.8673488087965792, "grad_norm": 0.5262903571128845, "learning_rate": 2.1396249740197464e-06, "loss": 4.2525, "step": 28397 }, { "epoch": 0.8673793524740379, "grad_norm": 0.5273003578186035, "learning_rate": 2.138654059487599e-06, "loss": 4.3062, "step": 28398 }, { "epoch": 0.8674098961514967, "grad_norm": 0.5323200821876526, "learning_rate": 2.137683355451614e-06, "loss": 4.2376, "step": 28399 }, { "epoch": 0.8674404398289554, "grad_norm": 0.5435197353363037, "learning_rate": 2.1367128619207364e-06, "loss": 4.2868, "step": 28400 }, { "epoch": 0.8674709835064142, "grad_norm": 0.5382201075553894, "learning_rate": 2.1357425789038958e-06, "loss": 4.2082, "step": 28401 }, { "epoch": 0.867501527183873, "grad_norm": 0.5365861654281616, "learning_rate": 2.1347725064100265e-06, "loss": 4.3122, "step": 28402 }, { "epoch": 0.8675320708613317, "grad_norm": 0.5345374941825867, "learning_rate": 2.1338026444480686e-06, "loss": 4.2548, "step": 28403 }, { "epoch": 0.8675626145387905, "grad_norm": 0.5390551686286926, "learning_rate": 2.1328329930269427e-06, "loss": 4.2588, "step": 28404 }, { "epoch": 0.8675931582162493, "grad_norm": 0.5304029583930969, "learning_rate": 2.1318635521555803e-06, "loss": 4.2493, "step": 28405 }, { "epoch": 0.867623701893708, "grad_norm": 0.5235434174537659, "learning_rate": 2.1308943218429107e-06, "loss": 4.263, "step": 28406 }, { "epoch": 0.8676542455711668, "grad_norm": 0.5272219777107239, "learning_rate": 2.1299253020978516e-06, "loss": 4.2045, "step": 28407 }, { "epoch": 0.8676847892486256, "grad_norm": 0.5327891707420349, "learning_rate": 2.1289564929293294e-06, "loss": 4.243, "step": 28408 }, { "epoch": 0.8677153329260843, "grad_norm": 0.5298610925674438, "learning_rate": 2.127987894346267e-06, "loss": 4.2966, "step": 28409 }, { "epoch": 0.8677458766035431, "grad_norm": 0.5322943329811096, "learning_rate": 2.1270195063575775e-06, "loss": 4.1807, "step": 28410 }, { "epoch": 0.8677764202810019, "grad_norm": 0.5410043597221375, "learning_rate": 2.1260513289721786e-06, "loss": 4.3365, "step": 28411 }, { "epoch": 0.8678069639584606, "grad_norm": 0.5347226858139038, "learning_rate": 2.1250833621989903e-06, "loss": 4.3344, "step": 28412 }, { "epoch": 0.8678375076359194, "grad_norm": 0.5279396772384644, "learning_rate": 2.12411560604692e-06, "loss": 4.2452, "step": 28413 }, { "epoch": 0.8678680513133782, "grad_norm": 0.5389357805252075, "learning_rate": 2.1231480605248736e-06, "loss": 4.3174, "step": 28414 }, { "epoch": 0.8678985949908369, "grad_norm": 0.5329198837280273, "learning_rate": 2.1221807256417702e-06, "loss": 4.2456, "step": 28415 }, { "epoch": 0.8679291386682957, "grad_norm": 0.5281931757926941, "learning_rate": 2.1212136014065074e-06, "loss": 4.2152, "step": 28416 }, { "epoch": 0.8679596823457544, "grad_norm": 0.5317512154579163, "learning_rate": 2.1202466878280006e-06, "loss": 4.2896, "step": 28417 }, { "epoch": 0.8679902260232132, "grad_norm": 0.5324931740760803, "learning_rate": 2.1192799849151374e-06, "loss": 4.2751, "step": 28418 }, { "epoch": 0.868020769700672, "grad_norm": 0.527140200138092, "learning_rate": 2.118313492676832e-06, "loss": 4.2228, "step": 28419 }, { "epoch": 0.8680513133781307, "grad_norm": 0.5239043831825256, "learning_rate": 2.117347211121981e-06, "loss": 4.1599, "step": 28420 }, { "epoch": 0.8680818570555895, "grad_norm": 0.5316625237464905, "learning_rate": 2.116381140259474e-06, "loss": 4.2535, "step": 28421 }, { "epoch": 0.8681124007330483, "grad_norm": 0.5337551832199097, "learning_rate": 2.1154152800982123e-06, "loss": 4.2771, "step": 28422 }, { "epoch": 0.868142944410507, "grad_norm": 0.5288212299346924, "learning_rate": 2.114449630647092e-06, "loss": 4.358, "step": 28423 }, { "epoch": 0.8681734880879658, "grad_norm": 0.5310804843902588, "learning_rate": 2.113484191914997e-06, "loss": 4.2796, "step": 28424 }, { "epoch": 0.8682040317654246, "grad_norm": 0.5339038968086243, "learning_rate": 2.11251896391082e-06, "loss": 4.092, "step": 28425 }, { "epoch": 0.8682345754428833, "grad_norm": 0.5311205983161926, "learning_rate": 2.1115539466434548e-06, "loss": 4.3116, "step": 28426 }, { "epoch": 0.8682651191203421, "grad_norm": 0.5217221975326538, "learning_rate": 2.1105891401217713e-06, "loss": 4.2506, "step": 28427 }, { "epoch": 0.8682956627978009, "grad_norm": 0.5336500406265259, "learning_rate": 2.1096245443546715e-06, "loss": 4.1866, "step": 28428 }, { "epoch": 0.8683262064752596, "grad_norm": 0.5377392768859863, "learning_rate": 2.1086601593510196e-06, "loss": 4.3039, "step": 28429 }, { "epoch": 0.8683567501527184, "grad_norm": 0.5345081686973572, "learning_rate": 2.1076959851197094e-06, "loss": 4.2094, "step": 28430 }, { "epoch": 0.8683872938301771, "grad_norm": 0.5416843891143799, "learning_rate": 2.1067320216696135e-06, "loss": 4.3021, "step": 28431 }, { "epoch": 0.8684178375076359, "grad_norm": 0.5297727584838867, "learning_rate": 2.1057682690096005e-06, "loss": 4.2558, "step": 28432 }, { "epoch": 0.8684483811850947, "grad_norm": 0.5292603373527527, "learning_rate": 2.104804727148549e-06, "loss": 4.2612, "step": 28433 }, { "epoch": 0.8684789248625534, "grad_norm": 0.5444904565811157, "learning_rate": 2.103841396095338e-06, "loss": 4.1625, "step": 28434 }, { "epoch": 0.8685094685400122, "grad_norm": 0.5368309617042542, "learning_rate": 2.1028782758588273e-06, "loss": 4.2508, "step": 28435 }, { "epoch": 0.868540012217471, "grad_norm": 0.5345635414123535, "learning_rate": 2.1019153664478875e-06, "loss": 4.2542, "step": 28436 }, { "epoch": 0.8685705558949297, "grad_norm": 0.5272272229194641, "learning_rate": 2.100952667871389e-06, "loss": 4.2974, "step": 28437 }, { "epoch": 0.8686010995723885, "grad_norm": 0.5225290060043335, "learning_rate": 2.0999901801381923e-06, "loss": 4.204, "step": 28438 }, { "epoch": 0.8686316432498473, "grad_norm": 0.5166175365447998, "learning_rate": 2.0990279032571556e-06, "loss": 4.1513, "step": 28439 }, { "epoch": 0.868662186927306, "grad_norm": 0.5465388894081116, "learning_rate": 2.098065837237151e-06, "loss": 4.1771, "step": 28440 }, { "epoch": 0.8686927306047648, "grad_norm": 0.5293681025505066, "learning_rate": 2.097103982087023e-06, "loss": 4.2799, "step": 28441 }, { "epoch": 0.8687232742822236, "grad_norm": 0.5301427245140076, "learning_rate": 2.0961423378156375e-06, "loss": 4.2952, "step": 28442 }, { "epoch": 0.8687538179596823, "grad_norm": 0.5328695774078369, "learning_rate": 2.0951809044318454e-06, "loss": 4.3456, "step": 28443 }, { "epoch": 0.8687843616371411, "grad_norm": 0.524664580821991, "learning_rate": 2.0942196819445035e-06, "loss": 4.1726, "step": 28444 }, { "epoch": 0.8688149053145999, "grad_norm": 0.5328121781349182, "learning_rate": 2.0932586703624498e-06, "loss": 4.1914, "step": 28445 }, { "epoch": 0.8688454489920586, "grad_norm": 0.5288755297660828, "learning_rate": 2.0922978696945484e-06, "loss": 4.2784, "step": 28446 }, { "epoch": 0.8688759926695174, "grad_norm": 0.5365233421325684, "learning_rate": 2.0913372799496315e-06, "loss": 4.178, "step": 28447 }, { "epoch": 0.8689065363469761, "grad_norm": 0.5318231582641602, "learning_rate": 2.0903769011365564e-06, "loss": 4.224, "step": 28448 }, { "epoch": 0.8689370800244349, "grad_norm": 0.5268213152885437, "learning_rate": 2.0894167332641573e-06, "loss": 4.2936, "step": 28449 }, { "epoch": 0.8689676237018937, "grad_norm": 0.5459451079368591, "learning_rate": 2.0884567763412746e-06, "loss": 4.284, "step": 28450 }, { "epoch": 0.8689981673793524, "grad_norm": 0.5321351885795593, "learning_rate": 2.087497030376756e-06, "loss": 4.2462, "step": 28451 }, { "epoch": 0.8690287110568112, "grad_norm": 0.5322147011756897, "learning_rate": 2.086537495379429e-06, "loss": 4.2693, "step": 28452 }, { "epoch": 0.86905925473427, "grad_norm": 0.5270321369171143, "learning_rate": 2.0855781713581324e-06, "loss": 4.3314, "step": 28453 }, { "epoch": 0.8690897984117287, "grad_norm": 0.5317291021347046, "learning_rate": 2.0846190583217016e-06, "loss": 4.2863, "step": 28454 }, { "epoch": 0.8691203420891875, "grad_norm": 0.5264912247657776, "learning_rate": 2.083660156278963e-06, "loss": 4.316, "step": 28455 }, { "epoch": 0.8691508857666463, "grad_norm": 0.5271325707435608, "learning_rate": 2.0827014652387457e-06, "loss": 4.1874, "step": 28456 }, { "epoch": 0.869181429444105, "grad_norm": 0.5416244268417358, "learning_rate": 2.0817429852098836e-06, "loss": 4.2721, "step": 28457 }, { "epoch": 0.8692119731215638, "grad_norm": 0.528976321220398, "learning_rate": 2.080784716201195e-06, "loss": 4.1428, "step": 28458 }, { "epoch": 0.8692425167990226, "grad_norm": 0.539695143699646, "learning_rate": 2.079826658221509e-06, "loss": 4.2591, "step": 28459 }, { "epoch": 0.8692730604764813, "grad_norm": 0.5255183577537537, "learning_rate": 2.0788688112796384e-06, "loss": 4.2352, "step": 28460 }, { "epoch": 0.8693036041539401, "grad_norm": 0.5401445627212524, "learning_rate": 2.0779111753844115e-06, "loss": 4.2613, "step": 28461 }, { "epoch": 0.869334147831399, "grad_norm": 0.5257570743560791, "learning_rate": 2.0769537505446358e-06, "loss": 4.263, "step": 28462 }, { "epoch": 0.8693646915088576, "grad_norm": 0.5402336716651917, "learning_rate": 2.0759965367691396e-06, "loss": 4.2637, "step": 28463 }, { "epoch": 0.8693952351863165, "grad_norm": 0.5474028587341309, "learning_rate": 2.075039534066725e-06, "loss": 4.2644, "step": 28464 }, { "epoch": 0.8694257788637751, "grad_norm": 0.5428876876831055, "learning_rate": 2.0740827424462123e-06, "loss": 4.274, "step": 28465 }, { "epoch": 0.869456322541234, "grad_norm": 0.5316603779792786, "learning_rate": 2.073126161916403e-06, "loss": 4.2532, "step": 28466 }, { "epoch": 0.8694868662186928, "grad_norm": 0.5302574634552002, "learning_rate": 2.0721697924861088e-06, "loss": 4.2376, "step": 28467 }, { "epoch": 0.8695174098961514, "grad_norm": 0.529338538646698, "learning_rate": 2.0712136341641405e-06, "loss": 4.2087, "step": 28468 }, { "epoch": 0.8695479535736103, "grad_norm": 0.5318306684494019, "learning_rate": 2.0702576869592927e-06, "loss": 4.2456, "step": 28469 }, { "epoch": 0.8695784972510691, "grad_norm": 0.5523210167884827, "learning_rate": 2.06930195088037e-06, "loss": 4.2667, "step": 28470 }, { "epoch": 0.8696090409285278, "grad_norm": 0.5198724269866943, "learning_rate": 2.0683464259361797e-06, "loss": 4.2135, "step": 28471 }, { "epoch": 0.8696395846059866, "grad_norm": 0.5345883369445801, "learning_rate": 2.067391112135508e-06, "loss": 4.2305, "step": 28472 }, { "epoch": 0.8696701282834454, "grad_norm": 0.5255001187324524, "learning_rate": 2.0664360094871603e-06, "loss": 4.2308, "step": 28473 }, { "epoch": 0.8697006719609041, "grad_norm": 0.528096079826355, "learning_rate": 2.065481117999929e-06, "loss": 4.2247, "step": 28474 }, { "epoch": 0.8697312156383629, "grad_norm": 0.5355638265609741, "learning_rate": 2.064526437682604e-06, "loss": 4.1764, "step": 28475 }, { "epoch": 0.8697617593158217, "grad_norm": 0.5308415293693542, "learning_rate": 2.063571968543976e-06, "loss": 4.2846, "step": 28476 }, { "epoch": 0.8697923029932804, "grad_norm": 0.5341421961784363, "learning_rate": 2.0626177105928375e-06, "loss": 4.2078, "step": 28477 }, { "epoch": 0.8698228466707392, "grad_norm": 0.5250175595283508, "learning_rate": 2.061663663837965e-06, "loss": 4.2386, "step": 28478 }, { "epoch": 0.869853390348198, "grad_norm": 0.5499847531318665, "learning_rate": 2.060709828288149e-06, "loss": 4.3117, "step": 28479 }, { "epoch": 0.8698839340256567, "grad_norm": 0.5401793122291565, "learning_rate": 2.0597562039521762e-06, "loss": 4.294, "step": 28480 }, { "epoch": 0.8699144777031155, "grad_norm": 0.5318470001220703, "learning_rate": 2.058802790838818e-06, "loss": 4.2539, "step": 28481 }, { "epoch": 0.8699450213805742, "grad_norm": 0.5182434320449829, "learning_rate": 2.0578495889568642e-06, "loss": 4.2268, "step": 28482 }, { "epoch": 0.869975565058033, "grad_norm": 0.533231794834137, "learning_rate": 2.056896598315078e-06, "loss": 4.3553, "step": 28483 }, { "epoch": 0.8700061087354918, "grad_norm": 0.5308945775032043, "learning_rate": 2.05594381892224e-06, "loss": 4.2026, "step": 28484 }, { "epoch": 0.8700366524129505, "grad_norm": 0.5311793684959412, "learning_rate": 2.0549912507871304e-06, "loss": 4.2133, "step": 28485 }, { "epoch": 0.8700671960904093, "grad_norm": 0.5382401943206787, "learning_rate": 2.054038893918511e-06, "loss": 4.3198, "step": 28486 }, { "epoch": 0.8700977397678681, "grad_norm": 0.5373902320861816, "learning_rate": 2.05308674832515e-06, "loss": 4.324, "step": 28487 }, { "epoch": 0.8701282834453268, "grad_norm": 0.520379900932312, "learning_rate": 2.0521348140158244e-06, "loss": 4.1529, "step": 28488 }, { "epoch": 0.8701588271227856, "grad_norm": 0.5242760181427002, "learning_rate": 2.051183090999284e-06, "loss": 4.2543, "step": 28489 }, { "epoch": 0.8701893708002444, "grad_norm": 0.5278785824775696, "learning_rate": 2.0502315792843064e-06, "loss": 4.2671, "step": 28490 }, { "epoch": 0.8702199144777031, "grad_norm": 0.5334159731864929, "learning_rate": 2.0492802788796423e-06, "loss": 4.2466, "step": 28491 }, { "epoch": 0.8702504581551619, "grad_norm": 0.5389953255653381, "learning_rate": 2.0483291897940598e-06, "loss": 4.2809, "step": 28492 }, { "epoch": 0.8702810018326207, "grad_norm": 0.5359757542610168, "learning_rate": 2.047378312036305e-06, "loss": 4.2722, "step": 28493 }, { "epoch": 0.8703115455100794, "grad_norm": 0.5247374773025513, "learning_rate": 2.0464276456151456e-06, "loss": 4.2594, "step": 28494 }, { "epoch": 0.8703420891875382, "grad_norm": 0.5384243130683899, "learning_rate": 2.0454771905393218e-06, "loss": 4.2534, "step": 28495 }, { "epoch": 0.870372632864997, "grad_norm": 0.5330963134765625, "learning_rate": 2.0445269468175932e-06, "loss": 4.1624, "step": 28496 }, { "epoch": 0.8704031765424557, "grad_norm": 0.5439870953559875, "learning_rate": 2.0435769144587112e-06, "loss": 4.367, "step": 28497 }, { "epoch": 0.8704337202199145, "grad_norm": 0.5324500203132629, "learning_rate": 2.0426270934714163e-06, "loss": 4.3075, "step": 28498 }, { "epoch": 0.8704642638973732, "grad_norm": 0.5331281423568726, "learning_rate": 2.04167748386446e-06, "loss": 4.2017, "step": 28499 }, { "epoch": 0.870494807574832, "grad_norm": 0.5298261642456055, "learning_rate": 2.0407280856465787e-06, "loss": 4.2018, "step": 28500 }, { "epoch": 0.8705253512522908, "grad_norm": 0.5314458608627319, "learning_rate": 2.0397788988265193e-06, "loss": 4.2491, "step": 28501 }, { "epoch": 0.8705558949297495, "grad_norm": 0.5420308113098145, "learning_rate": 2.0388299234130244e-06, "loss": 4.2193, "step": 28502 }, { "epoch": 0.8705864386072083, "grad_norm": 0.5315548181533813, "learning_rate": 2.037881159414823e-06, "loss": 4.3055, "step": 28503 }, { "epoch": 0.8706169822846671, "grad_norm": 0.5386930108070374, "learning_rate": 2.036932606840658e-06, "loss": 4.2399, "step": 28504 }, { "epoch": 0.8706475259621258, "grad_norm": 0.5295156240463257, "learning_rate": 2.0359842656992643e-06, "loss": 4.164, "step": 28505 }, { "epoch": 0.8706780696395846, "grad_norm": 0.5351036787033081, "learning_rate": 2.0350361359993632e-06, "loss": 4.2166, "step": 28506 }, { "epoch": 0.8707086133170434, "grad_norm": 0.5287265181541443, "learning_rate": 2.0340882177496996e-06, "loss": 4.2652, "step": 28507 }, { "epoch": 0.8707391569945021, "grad_norm": 0.5430094003677368, "learning_rate": 2.033140510958992e-06, "loss": 4.3387, "step": 28508 }, { "epoch": 0.8707697006719609, "grad_norm": 0.5319337844848633, "learning_rate": 2.0321930156359637e-06, "loss": 4.1034, "step": 28509 }, { "epoch": 0.8708002443494197, "grad_norm": 0.5388320684432983, "learning_rate": 2.031245731789344e-06, "loss": 4.3559, "step": 28510 }, { "epoch": 0.8708307880268784, "grad_norm": 0.5364012718200684, "learning_rate": 2.0302986594278594e-06, "loss": 4.1898, "step": 28511 }, { "epoch": 0.8708613317043372, "grad_norm": 0.5310107469558716, "learning_rate": 2.0293517985602194e-06, "loss": 4.1366, "step": 28512 }, { "epoch": 0.870891875381796, "grad_norm": 0.5444678068161011, "learning_rate": 2.0284051491951478e-06, "loss": 4.2669, "step": 28513 }, { "epoch": 0.8709224190592547, "grad_norm": 0.5270525813102722, "learning_rate": 2.027458711341365e-06, "loss": 4.2624, "step": 28514 }, { "epoch": 0.8709529627367135, "grad_norm": 0.5281726121902466, "learning_rate": 2.0265124850075783e-06, "loss": 4.2248, "step": 28515 }, { "epoch": 0.8709835064141722, "grad_norm": 0.5318307876586914, "learning_rate": 2.0255664702025055e-06, "loss": 4.2876, "step": 28516 }, { "epoch": 0.871014050091631, "grad_norm": 0.5311794281005859, "learning_rate": 2.024620666934851e-06, "loss": 4.1125, "step": 28517 }, { "epoch": 0.8710445937690898, "grad_norm": 0.5383880734443665, "learning_rate": 2.0236750752133245e-06, "loss": 4.2703, "step": 28518 }, { "epoch": 0.8710751374465485, "grad_norm": 0.5372950434684753, "learning_rate": 2.0227296950466406e-06, "loss": 4.2358, "step": 28519 }, { "epoch": 0.8711056811240073, "grad_norm": 0.537382960319519, "learning_rate": 2.021784526443496e-06, "loss": 4.2712, "step": 28520 }, { "epoch": 0.8711362248014661, "grad_norm": 0.5340351462364197, "learning_rate": 2.020839569412594e-06, "loss": 4.3194, "step": 28521 }, { "epoch": 0.8711667684789248, "grad_norm": 0.5355277061462402, "learning_rate": 2.0198948239626397e-06, "loss": 4.3187, "step": 28522 }, { "epoch": 0.8711973121563836, "grad_norm": 0.5281839370727539, "learning_rate": 2.018950290102331e-06, "loss": 4.2704, "step": 28523 }, { "epoch": 0.8712278558338424, "grad_norm": 0.5380346179008484, "learning_rate": 2.0180059678403585e-06, "loss": 4.3168, "step": 28524 }, { "epoch": 0.8712583995113011, "grad_norm": 0.5456503033638, "learning_rate": 2.0170618571854233e-06, "loss": 4.2797, "step": 28525 }, { "epoch": 0.8712889431887599, "grad_norm": 0.5277737975120544, "learning_rate": 2.016117958146213e-06, "loss": 4.2192, "step": 28526 }, { "epoch": 0.8713194868662187, "grad_norm": 0.5344062447547913, "learning_rate": 2.015174270731421e-06, "loss": 4.2436, "step": 28527 }, { "epoch": 0.8713500305436774, "grad_norm": 0.5350877046585083, "learning_rate": 2.0142307949497423e-06, "loss": 4.2719, "step": 28528 }, { "epoch": 0.8713805742211362, "grad_norm": 0.5348016619682312, "learning_rate": 2.013287530809857e-06, "loss": 4.2862, "step": 28529 }, { "epoch": 0.871411117898595, "grad_norm": 0.5357043743133545, "learning_rate": 2.012344478320449e-06, "loss": 4.2695, "step": 28530 }, { "epoch": 0.8714416615760537, "grad_norm": 0.537955641746521, "learning_rate": 2.0114016374902096e-06, "loss": 4.247, "step": 28531 }, { "epoch": 0.8714722052535125, "grad_norm": 0.5418717265129089, "learning_rate": 2.0104590083278085e-06, "loss": 4.2104, "step": 28532 }, { "epoch": 0.8715027489309712, "grad_norm": 0.5395832061767578, "learning_rate": 2.0095165908419396e-06, "loss": 4.2753, "step": 28533 }, { "epoch": 0.87153329260843, "grad_norm": 0.5365983843803406, "learning_rate": 2.0085743850412648e-06, "loss": 4.3198, "step": 28534 }, { "epoch": 0.8715638362858888, "grad_norm": 0.5354751944541931, "learning_rate": 2.0076323909344663e-06, "loss": 4.2185, "step": 28535 }, { "epoch": 0.8715943799633475, "grad_norm": 0.5279141068458557, "learning_rate": 2.0066906085302236e-06, "loss": 4.2521, "step": 28536 }, { "epoch": 0.8716249236408063, "grad_norm": 0.5359323024749756, "learning_rate": 2.0057490378371985e-06, "loss": 4.1689, "step": 28537 }, { "epoch": 0.8716554673182652, "grad_norm": 0.5353569388389587, "learning_rate": 2.004807678864068e-06, "loss": 4.2701, "step": 28538 }, { "epoch": 0.8716860109957238, "grad_norm": 0.5294047594070435, "learning_rate": 2.0038665316194918e-06, "loss": 4.3235, "step": 28539 }, { "epoch": 0.8717165546731827, "grad_norm": 0.5242594480514526, "learning_rate": 2.002925596112146e-06, "loss": 4.1662, "step": 28540 }, { "epoch": 0.8717470983506415, "grad_norm": 0.5360583066940308, "learning_rate": 2.0019848723506816e-06, "loss": 4.3059, "step": 28541 }, { "epoch": 0.8717776420281002, "grad_norm": 0.5291494131088257, "learning_rate": 2.001044360343771e-06, "loss": 4.3439, "step": 28542 }, { "epoch": 0.871808185705559, "grad_norm": 0.5381472110748291, "learning_rate": 2.0001040601000664e-06, "loss": 4.256, "step": 28543 }, { "epoch": 0.8718387293830178, "grad_norm": 0.5360993146896362, "learning_rate": 1.999163971628229e-06, "loss": 4.2727, "step": 28544 }, { "epoch": 0.8718692730604765, "grad_norm": 0.5357820987701416, "learning_rate": 1.9982240949369206e-06, "loss": 4.1975, "step": 28545 }, { "epoch": 0.8718998167379353, "grad_norm": 0.5331522226333618, "learning_rate": 1.997284430034782e-06, "loss": 4.1612, "step": 28546 }, { "epoch": 0.8719303604153941, "grad_norm": 0.5308563113212585, "learning_rate": 1.9963449769304754e-06, "loss": 4.2694, "step": 28547 }, { "epoch": 0.8719609040928528, "grad_norm": 0.5366162061691284, "learning_rate": 1.9954057356326495e-06, "loss": 4.2428, "step": 28548 }, { "epoch": 0.8719914477703116, "grad_norm": 0.5507071018218994, "learning_rate": 1.994466706149947e-06, "loss": 4.2597, "step": 28549 }, { "epoch": 0.8720219914477703, "grad_norm": 0.5456147789955139, "learning_rate": 1.993527888491026e-06, "loss": 4.3631, "step": 28550 }, { "epoch": 0.8720525351252291, "grad_norm": 0.5453421473503113, "learning_rate": 1.9925892826645144e-06, "loss": 4.2715, "step": 28551 }, { "epoch": 0.8720830788026879, "grad_norm": 0.5242753624916077, "learning_rate": 1.9916508886790613e-06, "loss": 4.1587, "step": 28552 }, { "epoch": 0.8721136224801466, "grad_norm": 0.5341664552688599, "learning_rate": 1.9907127065433157e-06, "loss": 4.2944, "step": 28553 }, { "epoch": 0.8721441661576054, "grad_norm": 0.543670117855072, "learning_rate": 1.9897747362659063e-06, "loss": 4.2119, "step": 28554 }, { "epoch": 0.8721747098350642, "grad_norm": 0.5406770706176758, "learning_rate": 1.9888369778554682e-06, "loss": 4.2889, "step": 28555 }, { "epoch": 0.8722052535125229, "grad_norm": 0.5314831733703613, "learning_rate": 1.9878994313206445e-06, "loss": 4.1666, "step": 28556 }, { "epoch": 0.8722357971899817, "grad_norm": 0.5403806567192078, "learning_rate": 1.986962096670056e-06, "loss": 4.2301, "step": 28557 }, { "epoch": 0.8722663408674405, "grad_norm": 0.5247026085853577, "learning_rate": 1.9860249739123426e-06, "loss": 4.2276, "step": 28558 }, { "epoch": 0.8722968845448992, "grad_norm": 0.534307599067688, "learning_rate": 1.9850880630561315e-06, "loss": 4.2865, "step": 28559 }, { "epoch": 0.872327428222358, "grad_norm": 0.5409654378890991, "learning_rate": 1.984151364110043e-06, "loss": 4.3058, "step": 28560 }, { "epoch": 0.8723579718998168, "grad_norm": 0.5190026760101318, "learning_rate": 1.983214877082709e-06, "loss": 4.1097, "step": 28561 }, { "epoch": 0.8723885155772755, "grad_norm": 0.5544431805610657, "learning_rate": 1.982278601982751e-06, "loss": 4.252, "step": 28562 }, { "epoch": 0.8724190592547343, "grad_norm": 0.5252922773361206, "learning_rate": 1.981342538818787e-06, "loss": 4.1742, "step": 28563 }, { "epoch": 0.8724496029321931, "grad_norm": 0.5372561812400818, "learning_rate": 1.980406687599437e-06, "loss": 4.2671, "step": 28564 }, { "epoch": 0.8724801466096518, "grad_norm": 0.529158353805542, "learning_rate": 1.97947104833332e-06, "loss": 4.294, "step": 28565 }, { "epoch": 0.8725106902871106, "grad_norm": 0.5220789313316345, "learning_rate": 1.9785356210290457e-06, "loss": 4.1023, "step": 28566 }, { "epoch": 0.8725412339645693, "grad_norm": 0.5330892205238342, "learning_rate": 1.9776004056952345e-06, "loss": 4.2148, "step": 28567 }, { "epoch": 0.8725717776420281, "grad_norm": 0.5388369560241699, "learning_rate": 1.9766654023404913e-06, "loss": 4.2898, "step": 28568 }, { "epoch": 0.8726023213194869, "grad_norm": 0.5224902033805847, "learning_rate": 1.975730610973431e-06, "loss": 4.2819, "step": 28569 }, { "epoch": 0.8726328649969456, "grad_norm": 0.5219690799713135, "learning_rate": 1.9747960316026494e-06, "loss": 4.1643, "step": 28570 }, { "epoch": 0.8726634086744044, "grad_norm": 0.5314709544181824, "learning_rate": 1.9738616642367674e-06, "loss": 4.2018, "step": 28571 }, { "epoch": 0.8726939523518632, "grad_norm": 0.5354231595993042, "learning_rate": 1.9729275088843727e-06, "loss": 4.2318, "step": 28572 }, { "epoch": 0.8727244960293219, "grad_norm": 0.5333374738693237, "learning_rate": 1.9719935655540783e-06, "loss": 4.2655, "step": 28573 }, { "epoch": 0.8727550397067807, "grad_norm": 0.5541529655456543, "learning_rate": 1.971059834254477e-06, "loss": 4.1364, "step": 28574 }, { "epoch": 0.8727855833842395, "grad_norm": 0.5222293734550476, "learning_rate": 1.9701263149941667e-06, "loss": 4.2198, "step": 28575 }, { "epoch": 0.8728161270616982, "grad_norm": 0.5242906212806702, "learning_rate": 1.9691930077817473e-06, "loss": 4.1973, "step": 28576 }, { "epoch": 0.872846670739157, "grad_norm": 0.5315817594528198, "learning_rate": 1.9682599126258054e-06, "loss": 4.2911, "step": 28577 }, { "epoch": 0.8728772144166158, "grad_norm": 0.5292638540267944, "learning_rate": 1.9673270295349376e-06, "loss": 4.2232, "step": 28578 }, { "epoch": 0.8729077580940745, "grad_norm": 0.5262378454208374, "learning_rate": 1.966394358517734e-06, "loss": 4.237, "step": 28579 }, { "epoch": 0.8729383017715333, "grad_norm": 0.5333622097969055, "learning_rate": 1.9654618995827795e-06, "loss": 4.2634, "step": 28580 }, { "epoch": 0.872968845448992, "grad_norm": 0.5324727296829224, "learning_rate": 1.9645296527386614e-06, "loss": 4.2072, "step": 28581 }, { "epoch": 0.8729993891264508, "grad_norm": 0.5395719408988953, "learning_rate": 1.963597617993959e-06, "loss": 4.2111, "step": 28582 }, { "epoch": 0.8730299328039096, "grad_norm": 0.5380925536155701, "learning_rate": 1.9626657953572603e-06, "loss": 4.2869, "step": 28583 }, { "epoch": 0.8730604764813683, "grad_norm": 0.5355387926101685, "learning_rate": 1.961734184837144e-06, "loss": 4.245, "step": 28584 }, { "epoch": 0.8730910201588271, "grad_norm": 0.7017421722412109, "learning_rate": 1.9608027864421814e-06, "loss": 4.1293, "step": 28585 }, { "epoch": 0.8731215638362859, "grad_norm": 0.5243749022483826, "learning_rate": 1.959871600180957e-06, "loss": 4.2466, "step": 28586 }, { "epoch": 0.8731521075137446, "grad_norm": 0.5368677973747253, "learning_rate": 1.958940626062042e-06, "loss": 4.2421, "step": 28587 }, { "epoch": 0.8731826511912034, "grad_norm": 0.5275542140007019, "learning_rate": 1.958009864094004e-06, "loss": 4.2116, "step": 28588 }, { "epoch": 0.8732131948686622, "grad_norm": 0.5344138741493225, "learning_rate": 1.957079314285415e-06, "loss": 4.327, "step": 28589 }, { "epoch": 0.8732437385461209, "grad_norm": 0.5339420437812805, "learning_rate": 1.9561489766448474e-06, "loss": 4.2201, "step": 28590 }, { "epoch": 0.8732742822235797, "grad_norm": 0.5342255234718323, "learning_rate": 1.955218851180862e-06, "loss": 4.2623, "step": 28591 }, { "epoch": 0.8733048259010385, "grad_norm": 0.532900869846344, "learning_rate": 1.954288937902024e-06, "loss": 4.2738, "step": 28592 }, { "epoch": 0.8733353695784972, "grad_norm": 0.537026584148407, "learning_rate": 1.953359236816901e-06, "loss": 4.2122, "step": 28593 }, { "epoch": 0.873365913255956, "grad_norm": 0.5537216663360596, "learning_rate": 1.9524297479340454e-06, "loss": 4.3138, "step": 28594 }, { "epoch": 0.8733964569334148, "grad_norm": 0.5267674922943115, "learning_rate": 1.951500471262019e-06, "loss": 4.2565, "step": 28595 }, { "epoch": 0.8734270006108735, "grad_norm": 0.5351249575614929, "learning_rate": 1.9505714068093817e-06, "loss": 4.2161, "step": 28596 }, { "epoch": 0.8734575442883323, "grad_norm": 0.5369988083839417, "learning_rate": 1.9496425545846797e-06, "loss": 4.2801, "step": 28597 }, { "epoch": 0.873488087965791, "grad_norm": 0.531709611415863, "learning_rate": 1.948713914596473e-06, "loss": 4.2555, "step": 28598 }, { "epoch": 0.8735186316432498, "grad_norm": 0.5320348143577576, "learning_rate": 1.947785486853307e-06, "loss": 4.2141, "step": 28599 }, { "epoch": 0.8735491753207086, "grad_norm": 0.5443146228790283, "learning_rate": 1.9468572713637363e-06, "loss": 4.1857, "step": 28600 }, { "epoch": 0.8735797189981673, "grad_norm": 0.5329030752182007, "learning_rate": 1.9459292681362983e-06, "loss": 4.2943, "step": 28601 }, { "epoch": 0.8736102626756261, "grad_norm": 0.5268675684928894, "learning_rate": 1.945001477179548e-06, "loss": 4.2131, "step": 28602 }, { "epoch": 0.8736408063530849, "grad_norm": 0.5333412885665894, "learning_rate": 1.944073898502019e-06, "loss": 4.2341, "step": 28603 }, { "epoch": 0.8736713500305436, "grad_norm": 0.5328530669212341, "learning_rate": 1.9431465321122584e-06, "loss": 4.3056, "step": 28604 }, { "epoch": 0.8737018937080024, "grad_norm": 0.5308814644813538, "learning_rate": 1.9422193780188003e-06, "loss": 4.2417, "step": 28605 }, { "epoch": 0.8737324373854612, "grad_norm": 0.5348837375640869, "learning_rate": 1.94129243623018e-06, "loss": 4.2381, "step": 28606 }, { "epoch": 0.8737629810629199, "grad_norm": 0.5208391547203064, "learning_rate": 1.940365706754943e-06, "loss": 4.271, "step": 28607 }, { "epoch": 0.8737935247403787, "grad_norm": 0.5372517704963684, "learning_rate": 1.939439189601611e-06, "loss": 4.3142, "step": 28608 }, { "epoch": 0.8738240684178376, "grad_norm": 0.5452192425727844, "learning_rate": 1.9385128847787175e-06, "loss": 4.3349, "step": 28609 }, { "epoch": 0.8738546120952962, "grad_norm": 0.5377761125564575, "learning_rate": 1.937586792294796e-06, "loss": 4.2326, "step": 28610 }, { "epoch": 0.873885155772755, "grad_norm": 0.5196437239646912, "learning_rate": 1.9366609121583694e-06, "loss": 4.2282, "step": 28611 }, { "epoch": 0.8739156994502139, "grad_norm": 0.5352487564086914, "learning_rate": 1.935735244377962e-06, "loss": 4.2267, "step": 28612 }, { "epoch": 0.8739462431276726, "grad_norm": 0.5300273299217224, "learning_rate": 1.9348097889621024e-06, "loss": 4.2153, "step": 28613 }, { "epoch": 0.8739767868051314, "grad_norm": 0.5351583957672119, "learning_rate": 1.933884545919304e-06, "loss": 4.2613, "step": 28614 }, { "epoch": 0.87400733048259, "grad_norm": 0.537863552570343, "learning_rate": 1.9329595152580953e-06, "loss": 4.357, "step": 28615 }, { "epoch": 0.8740378741600489, "grad_norm": 0.537977397441864, "learning_rate": 1.932034696986984e-06, "loss": 4.2615, "step": 28616 }, { "epoch": 0.8740684178375077, "grad_norm": 0.5282866954803467, "learning_rate": 1.9311100911144938e-06, "loss": 4.2764, "step": 28617 }, { "epoch": 0.8740989615149664, "grad_norm": 0.5430788397789001, "learning_rate": 1.930185697649134e-06, "loss": 4.3153, "step": 28618 }, { "epoch": 0.8741295051924252, "grad_norm": 0.538301944732666, "learning_rate": 1.9292615165994093e-06, "loss": 4.2315, "step": 28619 }, { "epoch": 0.874160048869884, "grad_norm": 0.5299733281135559, "learning_rate": 1.928337547973838e-06, "loss": 4.3066, "step": 28620 }, { "epoch": 0.8741905925473427, "grad_norm": 0.5390923023223877, "learning_rate": 1.9274137917809272e-06, "loss": 4.3853, "step": 28621 }, { "epoch": 0.8742211362248015, "grad_norm": 0.5313707590103149, "learning_rate": 1.926490248029178e-06, "loss": 4.2789, "step": 28622 }, { "epoch": 0.8742516799022603, "grad_norm": 0.5307267904281616, "learning_rate": 1.925566916727098e-06, "loss": 4.2419, "step": 28623 }, { "epoch": 0.874282223579719, "grad_norm": 0.5263580679893494, "learning_rate": 1.9246437978831882e-06, "loss": 4.1881, "step": 28624 }, { "epoch": 0.8743127672571778, "grad_norm": 0.5473373532295227, "learning_rate": 1.9237208915059425e-06, "loss": 4.2263, "step": 28625 }, { "epoch": 0.8743433109346366, "grad_norm": 0.5301110148429871, "learning_rate": 1.9227981976038644e-06, "loss": 4.1702, "step": 28626 }, { "epoch": 0.8743738546120953, "grad_norm": 0.5254786610603333, "learning_rate": 1.9218757161854534e-06, "loss": 4.2036, "step": 28627 }, { "epoch": 0.8744043982895541, "grad_norm": 0.5462298393249512, "learning_rate": 1.920953447259194e-06, "loss": 4.234, "step": 28628 }, { "epoch": 0.8744349419670129, "grad_norm": 0.5275749564170837, "learning_rate": 1.920031390833582e-06, "loss": 4.2262, "step": 28629 }, { "epoch": 0.8744654856444716, "grad_norm": 0.5219482779502869, "learning_rate": 1.919109546917111e-06, "loss": 4.2063, "step": 28630 }, { "epoch": 0.8744960293219304, "grad_norm": 0.5376715064048767, "learning_rate": 1.918187915518263e-06, "loss": 4.3081, "step": 28631 }, { "epoch": 0.8745265729993891, "grad_norm": 0.54018235206604, "learning_rate": 1.9172664966455283e-06, "loss": 4.1333, "step": 28632 }, { "epoch": 0.8745571166768479, "grad_norm": 0.5330274105072021, "learning_rate": 1.916345290307389e-06, "loss": 4.2709, "step": 28633 }, { "epoch": 0.8745876603543067, "grad_norm": 0.5263622999191284, "learning_rate": 1.915424296512325e-06, "loss": 4.2125, "step": 28634 }, { "epoch": 0.8746182040317654, "grad_norm": 0.5252482891082764, "learning_rate": 1.91450351526882e-06, "loss": 4.3027, "step": 28635 }, { "epoch": 0.8746487477092242, "grad_norm": 0.5300630331039429, "learning_rate": 1.913582946585349e-06, "loss": 4.1604, "step": 28636 }, { "epoch": 0.874679291386683, "grad_norm": 0.5360408425331116, "learning_rate": 1.912662590470388e-06, "loss": 4.3039, "step": 28637 }, { "epoch": 0.8747098350641417, "grad_norm": 0.5227243304252625, "learning_rate": 1.9117424469324184e-06, "loss": 4.2679, "step": 28638 }, { "epoch": 0.8747403787416005, "grad_norm": 0.5377680063247681, "learning_rate": 1.9108225159799015e-06, "loss": 4.1939, "step": 28639 }, { "epoch": 0.8747709224190593, "grad_norm": 0.5556685328483582, "learning_rate": 1.909902797621313e-06, "loss": 4.2374, "step": 28640 }, { "epoch": 0.874801466096518, "grad_norm": 0.5293798446655273, "learning_rate": 1.908983291865124e-06, "loss": 4.1508, "step": 28641 }, { "epoch": 0.8748320097739768, "grad_norm": 0.5287722945213318, "learning_rate": 1.9080639987197972e-06, "loss": 4.2325, "step": 28642 }, { "epoch": 0.8748625534514356, "grad_norm": 0.5270318984985352, "learning_rate": 1.9071449181937956e-06, "loss": 4.1813, "step": 28643 }, { "epoch": 0.8748930971288943, "grad_norm": 0.5353477001190186, "learning_rate": 1.9062260502955898e-06, "loss": 4.2346, "step": 28644 }, { "epoch": 0.8749236408063531, "grad_norm": 0.5335184931755066, "learning_rate": 1.9053073950336287e-06, "loss": 4.1769, "step": 28645 }, { "epoch": 0.8749541844838119, "grad_norm": 0.5369129180908203, "learning_rate": 1.9043889524163805e-06, "loss": 4.2571, "step": 28646 }, { "epoch": 0.8749847281612706, "grad_norm": 0.531749963760376, "learning_rate": 1.9034707224522942e-06, "loss": 4.2753, "step": 28647 }, { "epoch": 0.8750152718387294, "grad_norm": 0.535403311252594, "learning_rate": 1.9025527051498322e-06, "loss": 4.2688, "step": 28648 }, { "epoch": 0.8750458155161881, "grad_norm": 0.548251211643219, "learning_rate": 1.9016349005174377e-06, "loss": 4.2354, "step": 28649 }, { "epoch": 0.8750763591936469, "grad_norm": 0.520236611366272, "learning_rate": 1.9007173085635738e-06, "loss": 4.1494, "step": 28650 }, { "epoch": 0.8751069028711057, "grad_norm": 0.5388016104698181, "learning_rate": 1.899799929296675e-06, "loss": 4.1595, "step": 28651 }, { "epoch": 0.8751374465485644, "grad_norm": 0.5159248113632202, "learning_rate": 1.8988827627252015e-06, "loss": 4.2145, "step": 28652 }, { "epoch": 0.8751679902260232, "grad_norm": 0.5263202786445618, "learning_rate": 1.8979658088575852e-06, "loss": 4.2919, "step": 28653 }, { "epoch": 0.875198533903482, "grad_norm": 0.5343793630599976, "learning_rate": 1.8970490677022778e-06, "loss": 4.0873, "step": 28654 }, { "epoch": 0.8752290775809407, "grad_norm": 0.5387331247329712, "learning_rate": 1.89613253926772e-06, "loss": 4.2058, "step": 28655 }, { "epoch": 0.8752596212583995, "grad_norm": 0.5359386801719666, "learning_rate": 1.895216223562346e-06, "loss": 4.2803, "step": 28656 }, { "epoch": 0.8752901649358583, "grad_norm": 0.5300402641296387, "learning_rate": 1.894300120594597e-06, "loss": 4.2809, "step": 28657 }, { "epoch": 0.875320708613317, "grad_norm": 0.5255011320114136, "learning_rate": 1.8933842303729077e-06, "loss": 4.2372, "step": 28658 }, { "epoch": 0.8753512522907758, "grad_norm": 0.5278374552726746, "learning_rate": 1.8924685529057073e-06, "loss": 4.1576, "step": 28659 }, { "epoch": 0.8753817959682346, "grad_norm": 0.5381895899772644, "learning_rate": 1.8915530882014309e-06, "loss": 4.2303, "step": 28660 }, { "epoch": 0.8754123396456933, "grad_norm": 0.5437948703765869, "learning_rate": 1.890637836268508e-06, "loss": 4.2257, "step": 28661 }, { "epoch": 0.8754428833231521, "grad_norm": 0.5354057550430298, "learning_rate": 1.889722797115362e-06, "loss": 4.2599, "step": 28662 }, { "epoch": 0.8754734270006109, "grad_norm": 0.542069673538208, "learning_rate": 1.8888079707504252e-06, "loss": 4.2493, "step": 28663 }, { "epoch": 0.8755039706780696, "grad_norm": 0.5405601263046265, "learning_rate": 1.8878933571821132e-06, "loss": 4.2267, "step": 28664 }, { "epoch": 0.8755345143555284, "grad_norm": 0.5228622555732727, "learning_rate": 1.8869789564188472e-06, "loss": 4.2393, "step": 28665 }, { "epoch": 0.8755650580329871, "grad_norm": 0.5430485606193542, "learning_rate": 1.8860647684690535e-06, "loss": 4.2667, "step": 28666 }, { "epoch": 0.8755956017104459, "grad_norm": 0.5462319254875183, "learning_rate": 1.8851507933411422e-06, "loss": 4.2586, "step": 28667 }, { "epoch": 0.8756261453879047, "grad_norm": 0.5412963628768921, "learning_rate": 1.8842370310435314e-06, "loss": 4.247, "step": 28668 }, { "epoch": 0.8756566890653634, "grad_norm": 0.5288152694702148, "learning_rate": 1.8833234815846395e-06, "loss": 4.2366, "step": 28669 }, { "epoch": 0.8756872327428222, "grad_norm": 0.5448445081710815, "learning_rate": 1.8824101449728708e-06, "loss": 4.2128, "step": 28670 }, { "epoch": 0.875717776420281, "grad_norm": 0.5261744856834412, "learning_rate": 1.8814970212166355e-06, "loss": 4.247, "step": 28671 }, { "epoch": 0.8757483200977397, "grad_norm": 0.5362186431884766, "learning_rate": 1.8805841103243488e-06, "loss": 4.2795, "step": 28672 }, { "epoch": 0.8757788637751985, "grad_norm": 0.5320841073989868, "learning_rate": 1.8796714123044067e-06, "loss": 4.1974, "step": 28673 }, { "epoch": 0.8758094074526573, "grad_norm": 0.5314723253250122, "learning_rate": 1.8787589271652196e-06, "loss": 4.2353, "step": 28674 }, { "epoch": 0.875839951130116, "grad_norm": 0.5290333032608032, "learning_rate": 1.8778466549151885e-06, "loss": 4.2261, "step": 28675 }, { "epoch": 0.8758704948075748, "grad_norm": 0.525825023651123, "learning_rate": 1.876934595562707e-06, "loss": 4.2852, "step": 28676 }, { "epoch": 0.8759010384850336, "grad_norm": 0.5324527025222778, "learning_rate": 1.8760227491161769e-06, "loss": 4.3325, "step": 28677 }, { "epoch": 0.8759315821624923, "grad_norm": 0.5253403186798096, "learning_rate": 1.8751111155839996e-06, "loss": 4.1863, "step": 28678 }, { "epoch": 0.8759621258399511, "grad_norm": 0.5272693037986755, "learning_rate": 1.8741996949745656e-06, "loss": 4.2927, "step": 28679 }, { "epoch": 0.87599266951741, "grad_norm": 0.5325803160667419, "learning_rate": 1.873288487296257e-06, "loss": 4.2207, "step": 28680 }, { "epoch": 0.8760232131948686, "grad_norm": 0.5553435683250427, "learning_rate": 1.8723774925574783e-06, "loss": 4.2629, "step": 28681 }, { "epoch": 0.8760537568723274, "grad_norm": 0.52809077501297, "learning_rate": 1.871466710766609e-06, "loss": 4.2683, "step": 28682 }, { "epoch": 0.8760843005497861, "grad_norm": 0.525530993938446, "learning_rate": 1.8705561419320394e-06, "loss": 4.1224, "step": 28683 }, { "epoch": 0.876114844227245, "grad_norm": 0.5313866138458252, "learning_rate": 1.8696457860621463e-06, "loss": 4.2115, "step": 28684 }, { "epoch": 0.8761453879047038, "grad_norm": 0.5447548627853394, "learning_rate": 1.8687356431653176e-06, "loss": 4.3066, "step": 28685 }, { "epoch": 0.8761759315821624, "grad_norm": 0.5391666889190674, "learning_rate": 1.8678257132499377e-06, "loss": 4.2375, "step": 28686 }, { "epoch": 0.8762064752596213, "grad_norm": 0.5315272808074951, "learning_rate": 1.8669159963243754e-06, "loss": 4.2827, "step": 28687 }, { "epoch": 0.8762370189370801, "grad_norm": 0.5299342274665833, "learning_rate": 1.86600649239701e-06, "loss": 4.236, "step": 28688 }, { "epoch": 0.8762675626145388, "grad_norm": 0.531358540058136, "learning_rate": 1.8650972014762236e-06, "loss": 4.2679, "step": 28689 }, { "epoch": 0.8762981062919976, "grad_norm": 0.5370873212814331, "learning_rate": 1.8641881235703762e-06, "loss": 4.252, "step": 28690 }, { "epoch": 0.8763286499694564, "grad_norm": 0.5291135311126709, "learning_rate": 1.8632792586878445e-06, "loss": 4.2606, "step": 28691 }, { "epoch": 0.8763591936469151, "grad_norm": 0.5324072241783142, "learning_rate": 1.8623706068369995e-06, "loss": 4.251, "step": 28692 }, { "epoch": 0.8763897373243739, "grad_norm": 0.5286335349082947, "learning_rate": 1.8614621680262011e-06, "loss": 4.2883, "step": 28693 }, { "epoch": 0.8764202810018327, "grad_norm": 0.5435317754745483, "learning_rate": 1.8605539422638207e-06, "loss": 4.2444, "step": 28694 }, { "epoch": 0.8764508246792914, "grad_norm": 0.5325727462768555, "learning_rate": 1.8596459295582153e-06, "loss": 4.2968, "step": 28695 }, { "epoch": 0.8764813683567502, "grad_norm": 0.5407867431640625, "learning_rate": 1.8587381299177503e-06, "loss": 4.3187, "step": 28696 }, { "epoch": 0.876511912034209, "grad_norm": 0.5254884362220764, "learning_rate": 1.8578305433507775e-06, "loss": 4.2241, "step": 28697 }, { "epoch": 0.8765424557116677, "grad_norm": 0.5259983539581299, "learning_rate": 1.8569231698656597e-06, "loss": 4.1644, "step": 28698 }, { "epoch": 0.8765729993891265, "grad_norm": 0.5294187068939209, "learning_rate": 1.8560160094707486e-06, "loss": 4.2579, "step": 28699 }, { "epoch": 0.8766035430665852, "grad_norm": 0.5298564434051514, "learning_rate": 1.8551090621743982e-06, "loss": 4.2589, "step": 28700 }, { "epoch": 0.876634086744044, "grad_norm": 0.5532500147819519, "learning_rate": 1.854202327984958e-06, "loss": 4.2093, "step": 28701 }, { "epoch": 0.8766646304215028, "grad_norm": 0.537400484085083, "learning_rate": 1.8532958069107736e-06, "loss": 4.2655, "step": 28702 }, { "epoch": 0.8766951740989615, "grad_norm": 0.5348734855651855, "learning_rate": 1.8523894989602025e-06, "loss": 4.3434, "step": 28703 }, { "epoch": 0.8767257177764203, "grad_norm": 0.5350594520568848, "learning_rate": 1.8514834041415768e-06, "loss": 4.2492, "step": 28704 }, { "epoch": 0.8767562614538791, "grad_norm": 0.5383266806602478, "learning_rate": 1.8505775224632454e-06, "loss": 4.1993, "step": 28705 }, { "epoch": 0.8767868051313378, "grad_norm": 0.5281527638435364, "learning_rate": 1.8496718539335545e-06, "loss": 4.2532, "step": 28706 }, { "epoch": 0.8768173488087966, "grad_norm": 0.5254100561141968, "learning_rate": 1.8487663985608333e-06, "loss": 4.1811, "step": 28707 }, { "epoch": 0.8768478924862554, "grad_norm": 0.5303024649620056, "learning_rate": 1.8478611563534199e-06, "loss": 4.2732, "step": 28708 }, { "epoch": 0.8768784361637141, "grad_norm": 0.5335816144943237, "learning_rate": 1.8469561273196601e-06, "loss": 4.2715, "step": 28709 }, { "epoch": 0.8769089798411729, "grad_norm": 0.5330376625061035, "learning_rate": 1.846051311467878e-06, "loss": 4.2291, "step": 28710 }, { "epoch": 0.8769395235186317, "grad_norm": 0.5367935299873352, "learning_rate": 1.8451467088064028e-06, "loss": 4.1264, "step": 28711 }, { "epoch": 0.8769700671960904, "grad_norm": 0.5379639863967896, "learning_rate": 1.8442423193435698e-06, "loss": 4.2351, "step": 28712 }, { "epoch": 0.8770006108735492, "grad_norm": 0.5339131951332092, "learning_rate": 1.8433381430877e-06, "loss": 4.1176, "step": 28713 }, { "epoch": 0.877031154551008, "grad_norm": 0.5283979773521423, "learning_rate": 1.8424341800471228e-06, "loss": 4.298, "step": 28714 }, { "epoch": 0.8770616982284667, "grad_norm": 0.5284944772720337, "learning_rate": 1.8415304302301623e-06, "loss": 4.2556, "step": 28715 }, { "epoch": 0.8770922419059255, "grad_norm": 0.5273510813713074, "learning_rate": 1.8406268936451365e-06, "loss": 4.1026, "step": 28716 }, { "epoch": 0.8771227855833842, "grad_norm": 0.525266170501709, "learning_rate": 1.8397235703003669e-06, "loss": 4.2204, "step": 28717 }, { "epoch": 0.877153329260843, "grad_norm": 0.5348018407821655, "learning_rate": 1.8388204602041686e-06, "loss": 4.2611, "step": 28718 }, { "epoch": 0.8771838729383018, "grad_norm": 0.5303236842155457, "learning_rate": 1.8379175633648576e-06, "loss": 4.2622, "step": 28719 }, { "epoch": 0.8772144166157605, "grad_norm": 0.5335129499435425, "learning_rate": 1.8370148797907548e-06, "loss": 4.1994, "step": 28720 }, { "epoch": 0.8772449602932193, "grad_norm": 0.5301157832145691, "learning_rate": 1.8361124094901594e-06, "loss": 4.232, "step": 28721 }, { "epoch": 0.8772755039706781, "grad_norm": 0.5326896905899048, "learning_rate": 1.8352101524713865e-06, "loss": 4.3135, "step": 28722 }, { "epoch": 0.8773060476481368, "grad_norm": 0.5370095372200012, "learning_rate": 1.8343081087427494e-06, "loss": 4.3372, "step": 28723 }, { "epoch": 0.8773365913255956, "grad_norm": 0.5318073034286499, "learning_rate": 1.8334062783125412e-06, "loss": 4.2302, "step": 28724 }, { "epoch": 0.8773671350030544, "grad_norm": 0.5468233227729797, "learning_rate": 1.8325046611890773e-06, "loss": 4.3263, "step": 28725 }, { "epoch": 0.8773976786805131, "grad_norm": 0.5377587080001831, "learning_rate": 1.831603257380654e-06, "loss": 4.2454, "step": 28726 }, { "epoch": 0.8774282223579719, "grad_norm": 0.5346369743347168, "learning_rate": 1.8307020668955705e-06, "loss": 4.2365, "step": 28727 }, { "epoch": 0.8774587660354307, "grad_norm": 0.5436012148857117, "learning_rate": 1.8298010897421252e-06, "loss": 4.2972, "step": 28728 }, { "epoch": 0.8774893097128894, "grad_norm": 0.5258139967918396, "learning_rate": 1.8289003259286175e-06, "loss": 4.178, "step": 28729 }, { "epoch": 0.8775198533903482, "grad_norm": 0.5364252924919128, "learning_rate": 1.8279997754633321e-06, "loss": 4.2266, "step": 28730 }, { "epoch": 0.8775503970678069, "grad_norm": 0.550690770149231, "learning_rate": 1.8270994383545736e-06, "loss": 4.2275, "step": 28731 }, { "epoch": 0.8775809407452657, "grad_norm": 0.5326966047286987, "learning_rate": 1.8261993146106187e-06, "loss": 4.1997, "step": 28732 }, { "epoch": 0.8776114844227245, "grad_norm": 0.5435638427734375, "learning_rate": 1.8252994042397608e-06, "loss": 4.2578, "step": 28733 }, { "epoch": 0.8776420281001832, "grad_norm": 0.5260800123214722, "learning_rate": 1.8243997072502933e-06, "loss": 4.1473, "step": 28734 }, { "epoch": 0.877672571777642, "grad_norm": 0.535917341709137, "learning_rate": 1.8235002236504873e-06, "loss": 4.2389, "step": 28735 }, { "epoch": 0.8777031154551008, "grad_norm": 0.5349516272544861, "learning_rate": 1.8226009534486305e-06, "loss": 4.2436, "step": 28736 }, { "epoch": 0.8777336591325595, "grad_norm": 0.5346302390098572, "learning_rate": 1.821701896653011e-06, "loss": 4.3181, "step": 28737 }, { "epoch": 0.8777642028100183, "grad_norm": 0.5378560423851013, "learning_rate": 1.8208030532718912e-06, "loss": 4.2181, "step": 28738 }, { "epoch": 0.8777947464874771, "grad_norm": 0.5375206470489502, "learning_rate": 1.8199044233135566e-06, "loss": 4.2519, "step": 28739 }, { "epoch": 0.8778252901649358, "grad_norm": 0.5353532433509827, "learning_rate": 1.8190060067862836e-06, "loss": 4.3044, "step": 28740 }, { "epoch": 0.8778558338423946, "grad_norm": 0.5265066027641296, "learning_rate": 1.8181078036983378e-06, "loss": 4.104, "step": 28741 }, { "epoch": 0.8778863775198534, "grad_norm": 0.5375415682792664, "learning_rate": 1.8172098140579963e-06, "loss": 4.2668, "step": 28742 }, { "epoch": 0.8779169211973121, "grad_norm": 0.5287687182426453, "learning_rate": 1.8163120378735216e-06, "loss": 4.2841, "step": 28743 }, { "epoch": 0.8779474648747709, "grad_norm": 0.5351164937019348, "learning_rate": 1.8154144751531792e-06, "loss": 4.2401, "step": 28744 }, { "epoch": 0.8779780085522297, "grad_norm": 0.5381284952163696, "learning_rate": 1.814517125905238e-06, "loss": 4.2355, "step": 28745 }, { "epoch": 0.8780085522296884, "grad_norm": 0.5435724854469299, "learning_rate": 1.8136199901379603e-06, "loss": 4.1718, "step": 28746 }, { "epoch": 0.8780390959071472, "grad_norm": 0.5363152623176575, "learning_rate": 1.8127230678596007e-06, "loss": 4.1247, "step": 28747 }, { "epoch": 0.8780696395846059, "grad_norm": 0.5395558476448059, "learning_rate": 1.811826359078425e-06, "loss": 4.1613, "step": 28748 }, { "epoch": 0.8781001832620647, "grad_norm": 0.5314704179763794, "learning_rate": 1.8109298638026822e-06, "loss": 4.2679, "step": 28749 }, { "epoch": 0.8781307269395235, "grad_norm": 0.5371525883674622, "learning_rate": 1.8100335820406323e-06, "loss": 4.3194, "step": 28750 }, { "epoch": 0.8781612706169822, "grad_norm": 0.5258859395980835, "learning_rate": 1.8091375138005296e-06, "loss": 4.1976, "step": 28751 }, { "epoch": 0.878191814294441, "grad_norm": 0.5463101863861084, "learning_rate": 1.8082416590906176e-06, "loss": 4.2217, "step": 28752 }, { "epoch": 0.8782223579718998, "grad_norm": 0.5358560085296631, "learning_rate": 1.807346017919148e-06, "loss": 4.2679, "step": 28753 }, { "epoch": 0.8782529016493585, "grad_norm": 0.5291793346405029, "learning_rate": 1.8064505902943729e-06, "loss": 4.1863, "step": 28754 }, { "epoch": 0.8782834453268173, "grad_norm": 0.5295708179473877, "learning_rate": 1.8055553762245269e-06, "loss": 4.2473, "step": 28755 }, { "epoch": 0.8783139890042762, "grad_norm": 0.5392158031463623, "learning_rate": 1.8046603757178621e-06, "loss": 4.2441, "step": 28756 }, { "epoch": 0.8783445326817348, "grad_norm": 0.5879674553871155, "learning_rate": 1.8037655887826105e-06, "loss": 4.1773, "step": 28757 }, { "epoch": 0.8783750763591937, "grad_norm": 0.5288432836532593, "learning_rate": 1.8028710154270212e-06, "loss": 4.2348, "step": 28758 }, { "epoch": 0.8784056200366525, "grad_norm": 0.5327450633049011, "learning_rate": 1.801976655659321e-06, "loss": 4.1922, "step": 28759 }, { "epoch": 0.8784361637141112, "grad_norm": 0.5348791480064392, "learning_rate": 1.801082509487753e-06, "loss": 4.1792, "step": 28760 }, { "epoch": 0.87846670739157, "grad_norm": 0.5369258522987366, "learning_rate": 1.8001885769205419e-06, "loss": 4.3163, "step": 28761 }, { "epoch": 0.8784972510690288, "grad_norm": 0.528396725654602, "learning_rate": 1.7992948579659218e-06, "loss": 4.2363, "step": 28762 }, { "epoch": 0.8785277947464875, "grad_norm": 0.5467326045036316, "learning_rate": 1.7984013526321287e-06, "loss": 4.1526, "step": 28763 }, { "epoch": 0.8785583384239463, "grad_norm": 0.5404489040374756, "learning_rate": 1.7975080609273776e-06, "loss": 4.3693, "step": 28764 }, { "epoch": 0.878588882101405, "grad_norm": 0.5412145256996155, "learning_rate": 1.7966149828599038e-06, "loss": 4.1768, "step": 28765 }, { "epoch": 0.8786194257788638, "grad_norm": 0.5371912717819214, "learning_rate": 1.7957221184379203e-06, "loss": 4.3321, "step": 28766 }, { "epoch": 0.8786499694563226, "grad_norm": 0.5280422568321228, "learning_rate": 1.7948294676696564e-06, "loss": 4.2277, "step": 28767 }, { "epoch": 0.8786805131337813, "grad_norm": 0.5243067145347595, "learning_rate": 1.7939370305633307e-06, "loss": 4.1659, "step": 28768 }, { "epoch": 0.8787110568112401, "grad_norm": 0.5350722074508667, "learning_rate": 1.793044807127156e-06, "loss": 4.2625, "step": 28769 }, { "epoch": 0.8787416004886989, "grad_norm": 0.539339542388916, "learning_rate": 1.792152797369348e-06, "loss": 4.3485, "step": 28770 }, { "epoch": 0.8787721441661576, "grad_norm": 0.5285560488700867, "learning_rate": 1.791261001298125e-06, "loss": 4.1919, "step": 28771 }, { "epoch": 0.8788026878436164, "grad_norm": 0.5272430777549744, "learning_rate": 1.7903694189216918e-06, "loss": 4.3005, "step": 28772 }, { "epoch": 0.8788332315210752, "grad_norm": 0.5323160290718079, "learning_rate": 1.7894780502482638e-06, "loss": 4.3025, "step": 28773 }, { "epoch": 0.8788637751985339, "grad_norm": 0.5306088924407959, "learning_rate": 1.7885868952860457e-06, "loss": 4.2228, "step": 28774 }, { "epoch": 0.8788943188759927, "grad_norm": 0.5336002111434937, "learning_rate": 1.7876959540432391e-06, "loss": 4.25, "step": 28775 }, { "epoch": 0.8789248625534515, "grad_norm": 0.5290183424949646, "learning_rate": 1.786805226528049e-06, "loss": 4.2985, "step": 28776 }, { "epoch": 0.8789554062309102, "grad_norm": 0.5275185704231262, "learning_rate": 1.785914712748682e-06, "loss": 4.265, "step": 28777 }, { "epoch": 0.878985949908369, "grad_norm": 0.5353313088417053, "learning_rate": 1.7850244127133291e-06, "loss": 4.2213, "step": 28778 }, { "epoch": 0.8790164935858278, "grad_norm": 0.5345965623855591, "learning_rate": 1.7841343264301951e-06, "loss": 4.3082, "step": 28779 }, { "epoch": 0.8790470372632865, "grad_norm": 0.535683810710907, "learning_rate": 1.783244453907476e-06, "loss": 4.3662, "step": 28780 }, { "epoch": 0.8790775809407453, "grad_norm": 0.5409845113754272, "learning_rate": 1.7823547951533571e-06, "loss": 4.2438, "step": 28781 }, { "epoch": 0.879108124618204, "grad_norm": 0.5408432483673096, "learning_rate": 1.7814653501760398e-06, "loss": 4.1754, "step": 28782 }, { "epoch": 0.8791386682956628, "grad_norm": 0.5420117378234863, "learning_rate": 1.780576118983704e-06, "loss": 4.2343, "step": 28783 }, { "epoch": 0.8791692119731216, "grad_norm": 0.534853994846344, "learning_rate": 1.7796871015845402e-06, "loss": 4.138, "step": 28784 }, { "epoch": 0.8791997556505803, "grad_norm": 0.5274142622947693, "learning_rate": 1.7787982979867446e-06, "loss": 4.1506, "step": 28785 }, { "epoch": 0.8792302993280391, "grad_norm": 0.5451440215110779, "learning_rate": 1.777909708198483e-06, "loss": 4.2334, "step": 28786 }, { "epoch": 0.8792608430054979, "grad_norm": 0.539364755153656, "learning_rate": 1.7770213322279516e-06, "loss": 4.2481, "step": 28787 }, { "epoch": 0.8792913866829566, "grad_norm": 0.5398077964782715, "learning_rate": 1.7761331700833244e-06, "loss": 4.2584, "step": 28788 }, { "epoch": 0.8793219303604154, "grad_norm": 0.536119282245636, "learning_rate": 1.775245221772781e-06, "loss": 4.287, "step": 28789 }, { "epoch": 0.8793524740378742, "grad_norm": 0.5306323170661926, "learning_rate": 1.7743574873044926e-06, "loss": 4.3005, "step": 28790 }, { "epoch": 0.8793830177153329, "grad_norm": 0.5346431732177734, "learning_rate": 1.7734699666866417e-06, "loss": 4.2613, "step": 28791 }, { "epoch": 0.8794135613927917, "grad_norm": 0.5497190952301025, "learning_rate": 1.772582659927388e-06, "loss": 4.2195, "step": 28792 }, { "epoch": 0.8794441050702505, "grad_norm": 0.5307582020759583, "learning_rate": 1.771695567034909e-06, "loss": 4.1598, "step": 28793 }, { "epoch": 0.8794746487477092, "grad_norm": 0.53494793176651, "learning_rate": 1.770808688017378e-06, "loss": 4.2614, "step": 28794 }, { "epoch": 0.879505192425168, "grad_norm": 0.5321529507637024, "learning_rate": 1.7699220228829472e-06, "loss": 4.246, "step": 28795 }, { "epoch": 0.8795357361026268, "grad_norm": 0.5349010229110718, "learning_rate": 1.7690355716397906e-06, "loss": 4.2621, "step": 28796 }, { "epoch": 0.8795662797800855, "grad_norm": 0.5270666480064392, "learning_rate": 1.7681493342960682e-06, "loss": 4.2582, "step": 28797 }, { "epoch": 0.8795968234575443, "grad_norm": 0.5409772992134094, "learning_rate": 1.7672633108599401e-06, "loss": 4.3008, "step": 28798 }, { "epoch": 0.879627367135003, "grad_norm": 0.5299100875854492, "learning_rate": 1.766377501339564e-06, "loss": 4.1909, "step": 28799 }, { "epoch": 0.8796579108124618, "grad_norm": 0.534020185470581, "learning_rate": 1.765491905743094e-06, "loss": 4.2369, "step": 28800 }, { "epoch": 0.8796884544899206, "grad_norm": 0.532081663608551, "learning_rate": 1.7646065240786853e-06, "loss": 4.2287, "step": 28801 }, { "epoch": 0.8797189981673793, "grad_norm": 0.541102409362793, "learning_rate": 1.7637213563544946e-06, "loss": 4.2322, "step": 28802 }, { "epoch": 0.8797495418448381, "grad_norm": 0.5351551175117493, "learning_rate": 1.762836402578663e-06, "loss": 4.1399, "step": 28803 }, { "epoch": 0.8797800855222969, "grad_norm": 0.5448837280273438, "learning_rate": 1.7619516627593507e-06, "loss": 4.2232, "step": 28804 }, { "epoch": 0.8798106291997556, "grad_norm": 0.553547739982605, "learning_rate": 1.7610671369046928e-06, "loss": 4.1909, "step": 28805 }, { "epoch": 0.8798411728772144, "grad_norm": 0.5351730585098267, "learning_rate": 1.7601828250228408e-06, "loss": 4.1819, "step": 28806 }, { "epoch": 0.8798717165546732, "grad_norm": 0.525140106678009, "learning_rate": 1.7592987271219302e-06, "loss": 4.2934, "step": 28807 }, { "epoch": 0.8799022602321319, "grad_norm": 0.5413393378257751, "learning_rate": 1.75841484321011e-06, "loss": 4.3109, "step": 28808 }, { "epoch": 0.8799328039095907, "grad_norm": 0.5310330390930176, "learning_rate": 1.7575311732955097e-06, "loss": 4.1848, "step": 28809 }, { "epoch": 0.8799633475870495, "grad_norm": 0.5347558856010437, "learning_rate": 1.75664771738627e-06, "loss": 4.2601, "step": 28810 }, { "epoch": 0.8799938912645082, "grad_norm": 0.5273199677467346, "learning_rate": 1.7557644754905318e-06, "loss": 4.164, "step": 28811 }, { "epoch": 0.880024434941967, "grad_norm": 0.526209831237793, "learning_rate": 1.7548814476164133e-06, "loss": 4.1989, "step": 28812 }, { "epoch": 0.8800549786194258, "grad_norm": 0.5253981947898865, "learning_rate": 1.7539986337720554e-06, "loss": 4.1779, "step": 28813 }, { "epoch": 0.8800855222968845, "grad_norm": 0.5284695029258728, "learning_rate": 1.753116033965585e-06, "loss": 4.265, "step": 28814 }, { "epoch": 0.8801160659743433, "grad_norm": 0.5274850726127625, "learning_rate": 1.752233648205126e-06, "loss": 4.1746, "step": 28815 }, { "epoch": 0.880146609651802, "grad_norm": 0.5354143977165222, "learning_rate": 1.7513514764988082e-06, "loss": 4.2766, "step": 28816 }, { "epoch": 0.8801771533292608, "grad_norm": 0.5185978412628174, "learning_rate": 1.750469518854747e-06, "loss": 4.2249, "step": 28817 }, { "epoch": 0.8802076970067196, "grad_norm": 0.5336384773254395, "learning_rate": 1.7495877752810669e-06, "loss": 4.2444, "step": 28818 }, { "epoch": 0.8802382406841783, "grad_norm": 0.5426248908042908, "learning_rate": 1.7487062457858888e-06, "loss": 4.1152, "step": 28819 }, { "epoch": 0.8802687843616371, "grad_norm": 0.5460252165794373, "learning_rate": 1.7478249303773286e-06, "loss": 4.3147, "step": 28820 }, { "epoch": 0.8802993280390959, "grad_norm": 0.539562463760376, "learning_rate": 1.7469438290634938e-06, "loss": 4.2084, "step": 28821 }, { "epoch": 0.8803298717165546, "grad_norm": 0.531976580619812, "learning_rate": 1.7460629418525082e-06, "loss": 4.2558, "step": 28822 }, { "epoch": 0.8803604153940134, "grad_norm": 0.5372300148010254, "learning_rate": 1.7451822687524711e-06, "loss": 4.2391, "step": 28823 }, { "epoch": 0.8803909590714722, "grad_norm": 0.5377475023269653, "learning_rate": 1.744301809771498e-06, "loss": 4.3132, "step": 28824 }, { "epoch": 0.8804215027489309, "grad_norm": 0.5346876382827759, "learning_rate": 1.7434215649177022e-06, "loss": 4.3096, "step": 28825 }, { "epoch": 0.8804520464263897, "grad_norm": 0.5353708863258362, "learning_rate": 1.742541534199174e-06, "loss": 4.2887, "step": 28826 }, { "epoch": 0.8804825901038486, "grad_norm": 0.5287215709686279, "learning_rate": 1.7416617176240241e-06, "loss": 4.1987, "step": 28827 }, { "epoch": 0.8805131337813072, "grad_norm": 0.5336534380912781, "learning_rate": 1.7407821152003567e-06, "loss": 4.2683, "step": 28828 }, { "epoch": 0.880543677458766, "grad_norm": 0.5406923890113831, "learning_rate": 1.7399027269362655e-06, "loss": 4.0948, "step": 28829 }, { "epoch": 0.8805742211362249, "grad_norm": 0.538981556892395, "learning_rate": 1.7390235528398468e-06, "loss": 4.2686, "step": 28830 }, { "epoch": 0.8806047648136835, "grad_norm": 0.5466633439064026, "learning_rate": 1.7381445929192026e-06, "loss": 4.2032, "step": 28831 }, { "epoch": 0.8806353084911424, "grad_norm": 0.5348817706108093, "learning_rate": 1.7372658471824149e-06, "loss": 4.1803, "step": 28832 }, { "epoch": 0.880665852168601, "grad_norm": 0.5449703335762024, "learning_rate": 1.7363873156375886e-06, "loss": 4.2892, "step": 28833 }, { "epoch": 0.8806963958460599, "grad_norm": 0.5405811667442322, "learning_rate": 1.735508998292798e-06, "loss": 4.198, "step": 28834 }, { "epoch": 0.8807269395235187, "grad_norm": 0.5468375086784363, "learning_rate": 1.7346308951561446e-06, "loss": 4.1833, "step": 28835 }, { "epoch": 0.8807574832009774, "grad_norm": 0.5371249318122864, "learning_rate": 1.7337530062356999e-06, "loss": 4.2002, "step": 28836 }, { "epoch": 0.8807880268784362, "grad_norm": 0.5322884321212769, "learning_rate": 1.7328753315395601e-06, "loss": 4.2309, "step": 28837 }, { "epoch": 0.880818570555895, "grad_norm": 0.5477154850959778, "learning_rate": 1.7319978710757939e-06, "loss": 4.2734, "step": 28838 }, { "epoch": 0.8808491142333537, "grad_norm": 0.5328636169433594, "learning_rate": 1.731120624852492e-06, "loss": 4.2886, "step": 28839 }, { "epoch": 0.8808796579108125, "grad_norm": 0.5308818221092224, "learning_rate": 1.73024359287772e-06, "loss": 4.3112, "step": 28840 }, { "epoch": 0.8809102015882713, "grad_norm": 0.5374764204025269, "learning_rate": 1.7293667751595604e-06, "loss": 4.2638, "step": 28841 }, { "epoch": 0.88094074526573, "grad_norm": 0.5470196008682251, "learning_rate": 1.7284901717060903e-06, "loss": 4.2209, "step": 28842 }, { "epoch": 0.8809712889431888, "grad_norm": 0.5375726819038391, "learning_rate": 1.7276137825253724e-06, "loss": 4.3308, "step": 28843 }, { "epoch": 0.8810018326206476, "grad_norm": 0.5397383570671082, "learning_rate": 1.7267376076254782e-06, "loss": 4.2224, "step": 28844 }, { "epoch": 0.8810323762981063, "grad_norm": 0.5403071045875549, "learning_rate": 1.7258616470144817e-06, "loss": 4.3117, "step": 28845 }, { "epoch": 0.8810629199755651, "grad_norm": 0.5168006420135498, "learning_rate": 1.7249859007004404e-06, "loss": 4.1305, "step": 28846 }, { "epoch": 0.8810934636530239, "grad_norm": 0.528982937335968, "learning_rate": 1.7241103686914201e-06, "loss": 4.233, "step": 28847 }, { "epoch": 0.8811240073304826, "grad_norm": 0.5364367365837097, "learning_rate": 1.7232350509954864e-06, "loss": 4.2707, "step": 28848 }, { "epoch": 0.8811545510079414, "grad_norm": 0.5348756313323975, "learning_rate": 1.7223599476206914e-06, "loss": 4.2989, "step": 28849 }, { "epoch": 0.8811850946854001, "grad_norm": 0.5306353569030762, "learning_rate": 1.7214850585751008e-06, "loss": 4.2884, "step": 28850 }, { "epoch": 0.8812156383628589, "grad_norm": 0.5357789397239685, "learning_rate": 1.720610383866761e-06, "loss": 4.2648, "step": 28851 }, { "epoch": 0.8812461820403177, "grad_norm": 0.5334287285804749, "learning_rate": 1.7197359235037347e-06, "loss": 4.1877, "step": 28852 }, { "epoch": 0.8812767257177764, "grad_norm": 0.5370439887046814, "learning_rate": 1.7188616774940713e-06, "loss": 4.3082, "step": 28853 }, { "epoch": 0.8813072693952352, "grad_norm": 0.5338090658187866, "learning_rate": 1.7179876458458116e-06, "loss": 4.1224, "step": 28854 }, { "epoch": 0.881337813072694, "grad_norm": 0.5283915400505066, "learning_rate": 1.717113828567013e-06, "loss": 4.3083, "step": 28855 }, { "epoch": 0.8813683567501527, "grad_norm": 0.5361432433128357, "learning_rate": 1.7162402256657189e-06, "loss": 4.2497, "step": 28856 }, { "epoch": 0.8813989004276115, "grad_norm": 0.5376472473144531, "learning_rate": 1.7153668371499704e-06, "loss": 4.216, "step": 28857 }, { "epoch": 0.8814294441050703, "grad_norm": 0.5277714729309082, "learning_rate": 1.7144936630278107e-06, "loss": 4.2458, "step": 28858 }, { "epoch": 0.881459987782529, "grad_norm": 0.5316923260688782, "learning_rate": 1.7136207033072837e-06, "loss": 4.2298, "step": 28859 }, { "epoch": 0.8814905314599878, "grad_norm": 0.52704256772995, "learning_rate": 1.7127479579964217e-06, "loss": 4.2785, "step": 28860 }, { "epoch": 0.8815210751374466, "grad_norm": 0.5329053997993469, "learning_rate": 1.71187542710326e-06, "loss": 4.2589, "step": 28861 }, { "epoch": 0.8815516188149053, "grad_norm": 0.5231311917304993, "learning_rate": 1.7110031106358393e-06, "loss": 4.1586, "step": 28862 }, { "epoch": 0.8815821624923641, "grad_norm": 0.5348355174064636, "learning_rate": 1.7101310086021839e-06, "loss": 4.2827, "step": 28863 }, { "epoch": 0.8816127061698229, "grad_norm": 0.5349363684654236, "learning_rate": 1.709259121010326e-06, "loss": 4.3384, "step": 28864 }, { "epoch": 0.8816432498472816, "grad_norm": 0.5340648293495178, "learning_rate": 1.7083874478682983e-06, "loss": 4.1655, "step": 28865 }, { "epoch": 0.8816737935247404, "grad_norm": 0.5396425127983093, "learning_rate": 1.7075159891841247e-06, "loss": 4.2857, "step": 28866 }, { "epoch": 0.8817043372021991, "grad_norm": 0.5430277585983276, "learning_rate": 1.7066447449658213e-06, "loss": 4.2589, "step": 28867 }, { "epoch": 0.8817348808796579, "grad_norm": 0.5357505083084106, "learning_rate": 1.7057737152214177e-06, "loss": 4.29, "step": 28868 }, { "epoch": 0.8817654245571167, "grad_norm": 0.5370087623596191, "learning_rate": 1.7049028999589324e-06, "loss": 4.266, "step": 28869 }, { "epoch": 0.8817959682345754, "grad_norm": 0.5325821042060852, "learning_rate": 1.704032299186384e-06, "loss": 4.2661, "step": 28870 }, { "epoch": 0.8818265119120342, "grad_norm": 0.5329123735427856, "learning_rate": 1.7031619129117854e-06, "loss": 4.237, "step": 28871 }, { "epoch": 0.881857055589493, "grad_norm": 0.5334113836288452, "learning_rate": 1.7022917411431528e-06, "loss": 4.2265, "step": 28872 }, { "epoch": 0.8818875992669517, "grad_norm": 0.5367509126663208, "learning_rate": 1.7014217838885044e-06, "loss": 4.3319, "step": 28873 }, { "epoch": 0.8819181429444105, "grad_norm": 0.542838990688324, "learning_rate": 1.7005520411558368e-06, "loss": 4.3264, "step": 28874 }, { "epoch": 0.8819486866218693, "grad_norm": 0.5514458417892456, "learning_rate": 1.6996825129531684e-06, "loss": 4.1521, "step": 28875 }, { "epoch": 0.881979230299328, "grad_norm": 0.529465913772583, "learning_rate": 1.6988131992885071e-06, "loss": 4.1508, "step": 28876 }, { "epoch": 0.8820097739767868, "grad_norm": 0.5247125625610352, "learning_rate": 1.6979441001698487e-06, "loss": 4.2283, "step": 28877 }, { "epoch": 0.8820403176542456, "grad_norm": 0.5423442125320435, "learning_rate": 1.6970752156051983e-06, "loss": 4.2022, "step": 28878 }, { "epoch": 0.8820708613317043, "grad_norm": 0.535984456539154, "learning_rate": 1.6962065456025632e-06, "loss": 4.2145, "step": 28879 }, { "epoch": 0.8821014050091631, "grad_norm": 0.5391912460327148, "learning_rate": 1.6953380901699317e-06, "loss": 4.1892, "step": 28880 }, { "epoch": 0.8821319486866218, "grad_norm": 0.542738139629364, "learning_rate": 1.6944698493153083e-06, "loss": 4.2577, "step": 28881 }, { "epoch": 0.8821624923640806, "grad_norm": 0.5218790173530579, "learning_rate": 1.693601823046681e-06, "loss": 4.282, "step": 28882 }, { "epoch": 0.8821930360415394, "grad_norm": 0.5398485660552979, "learning_rate": 1.6927340113720464e-06, "loss": 4.1449, "step": 28883 }, { "epoch": 0.8822235797189981, "grad_norm": 0.5435378551483154, "learning_rate": 1.691866414299395e-06, "loss": 4.1661, "step": 28884 }, { "epoch": 0.8822541233964569, "grad_norm": 0.5421687960624695, "learning_rate": 1.690999031836707e-06, "loss": 4.2346, "step": 28885 }, { "epoch": 0.8822846670739157, "grad_norm": 0.5387794375419617, "learning_rate": 1.6901318639919783e-06, "loss": 4.3395, "step": 28886 }, { "epoch": 0.8823152107513744, "grad_norm": 0.5363582372665405, "learning_rate": 1.6892649107731916e-06, "loss": 4.241, "step": 28887 }, { "epoch": 0.8823457544288332, "grad_norm": 0.5279212594032288, "learning_rate": 1.688398172188327e-06, "loss": 4.2322, "step": 28888 }, { "epoch": 0.882376298106292, "grad_norm": 0.547768771648407, "learning_rate": 1.6875316482453634e-06, "loss": 4.3333, "step": 28889 }, { "epoch": 0.8824068417837507, "grad_norm": 0.5364329814910889, "learning_rate": 1.6866653389522869e-06, "loss": 4.3262, "step": 28890 }, { "epoch": 0.8824373854612095, "grad_norm": 0.5313085913658142, "learning_rate": 1.6857992443170629e-06, "loss": 4.2821, "step": 28891 }, { "epoch": 0.8824679291386683, "grad_norm": 0.5285146832466125, "learning_rate": 1.6849333643476766e-06, "loss": 4.1835, "step": 28892 }, { "epoch": 0.882498472816127, "grad_norm": 0.5307739973068237, "learning_rate": 1.6840676990520971e-06, "loss": 4.1793, "step": 28893 }, { "epoch": 0.8825290164935858, "grad_norm": 0.5430839657783508, "learning_rate": 1.6832022484382897e-06, "loss": 4.2267, "step": 28894 }, { "epoch": 0.8825595601710446, "grad_norm": 0.5405313372612, "learning_rate": 1.682337012514229e-06, "loss": 4.2666, "step": 28895 }, { "epoch": 0.8825901038485033, "grad_norm": 0.53106290102005, "learning_rate": 1.6814719912878862e-06, "loss": 4.2775, "step": 28896 }, { "epoch": 0.8826206475259621, "grad_norm": 0.536385715007782, "learning_rate": 1.6806071847672133e-06, "loss": 4.2402, "step": 28897 }, { "epoch": 0.8826511912034208, "grad_norm": 0.5293566584587097, "learning_rate": 1.6797425929601846e-06, "loss": 4.1817, "step": 28898 }, { "epoch": 0.8826817348808796, "grad_norm": 0.5404972434043884, "learning_rate": 1.6788782158747546e-06, "loss": 4.1237, "step": 28899 }, { "epoch": 0.8827122785583384, "grad_norm": 0.5278803706169128, "learning_rate": 1.678014053518881e-06, "loss": 4.1548, "step": 28900 }, { "epoch": 0.8827428222357971, "grad_norm": 0.5349828600883484, "learning_rate": 1.6771501059005269e-06, "loss": 4.299, "step": 28901 }, { "epoch": 0.882773365913256, "grad_norm": 0.5348954796791077, "learning_rate": 1.6762863730276384e-06, "loss": 4.2105, "step": 28902 }, { "epoch": 0.8828039095907148, "grad_norm": 0.5393632054328918, "learning_rate": 1.6754228549081735e-06, "loss": 4.2977, "step": 28903 }, { "epoch": 0.8828344532681734, "grad_norm": 0.5344574451446533, "learning_rate": 1.6745595515500866e-06, "loss": 4.1622, "step": 28904 }, { "epoch": 0.8828649969456323, "grad_norm": 0.5380615592002869, "learning_rate": 1.6736964629613162e-06, "loss": 4.2522, "step": 28905 }, { "epoch": 0.8828955406230911, "grad_norm": 0.5342372059822083, "learning_rate": 1.6728335891498192e-06, "loss": 4.0905, "step": 28906 }, { "epoch": 0.8829260843005498, "grad_norm": 0.5259943604469299, "learning_rate": 1.6719709301235398e-06, "loss": 4.2933, "step": 28907 }, { "epoch": 0.8829566279780086, "grad_norm": 0.5332635045051575, "learning_rate": 1.671108485890413e-06, "loss": 4.1686, "step": 28908 }, { "epoch": 0.8829871716554674, "grad_norm": 0.5367195010185242, "learning_rate": 1.6702462564583882e-06, "loss": 4.2752, "step": 28909 }, { "epoch": 0.8830177153329261, "grad_norm": 0.5399711728096008, "learning_rate": 1.6693842418354034e-06, "loss": 4.296, "step": 28910 }, { "epoch": 0.8830482590103849, "grad_norm": 0.5406705141067505, "learning_rate": 1.6685224420293883e-06, "loss": 4.203, "step": 28911 }, { "epoch": 0.8830788026878437, "grad_norm": 0.5325051546096802, "learning_rate": 1.6676608570482838e-06, "loss": 4.1519, "step": 28912 }, { "epoch": 0.8831093463653024, "grad_norm": 0.5280051827430725, "learning_rate": 1.6667994869000254e-06, "loss": 4.2134, "step": 28913 }, { "epoch": 0.8831398900427612, "grad_norm": 0.5379155874252319, "learning_rate": 1.6659383315925398e-06, "loss": 4.277, "step": 28914 }, { "epoch": 0.8831704337202199, "grad_norm": 0.5371837615966797, "learning_rate": 1.6650773911337541e-06, "loss": 4.2163, "step": 28915 }, { "epoch": 0.8832009773976787, "grad_norm": 0.5317551493644714, "learning_rate": 1.664216665531604e-06, "loss": 4.2559, "step": 28916 }, { "epoch": 0.8832315210751375, "grad_norm": 0.5388967990875244, "learning_rate": 1.6633561547940047e-06, "loss": 4.2795, "step": 28917 }, { "epoch": 0.8832620647525962, "grad_norm": 0.5277723670005798, "learning_rate": 1.6624958589288864e-06, "loss": 4.057, "step": 28918 }, { "epoch": 0.883292608430055, "grad_norm": 0.5273631811141968, "learning_rate": 1.661635777944165e-06, "loss": 4.229, "step": 28919 }, { "epoch": 0.8833231521075138, "grad_norm": 0.5306424498558044, "learning_rate": 1.6607759118477616e-06, "loss": 4.2163, "step": 28920 }, { "epoch": 0.8833536957849725, "grad_norm": 0.5391117930412292, "learning_rate": 1.6599162606475983e-06, "loss": 4.2835, "step": 28921 }, { "epoch": 0.8833842394624313, "grad_norm": 0.534782886505127, "learning_rate": 1.659056824351582e-06, "loss": 4.1487, "step": 28922 }, { "epoch": 0.8834147831398901, "grad_norm": 0.5323623418807983, "learning_rate": 1.6581976029676316e-06, "loss": 4.2115, "step": 28923 }, { "epoch": 0.8834453268173488, "grad_norm": 0.5306249260902405, "learning_rate": 1.6573385965036602e-06, "loss": 4.2668, "step": 28924 }, { "epoch": 0.8834758704948076, "grad_norm": 0.5253881812095642, "learning_rate": 1.6564798049675701e-06, "loss": 4.2141, "step": 28925 }, { "epoch": 0.8835064141722664, "grad_norm": 0.5315787196159363, "learning_rate": 1.655621228367274e-06, "loss": 4.2324, "step": 28926 }, { "epoch": 0.8835369578497251, "grad_norm": 0.5280238389968872, "learning_rate": 1.6547628667106767e-06, "loss": 4.2316, "step": 28927 }, { "epoch": 0.8835675015271839, "grad_norm": 0.5310842394828796, "learning_rate": 1.6539047200056778e-06, "loss": 4.3112, "step": 28928 }, { "epoch": 0.8835980452046427, "grad_norm": 0.5371289253234863, "learning_rate": 1.6530467882601846e-06, "loss": 4.2869, "step": 28929 }, { "epoch": 0.8836285888821014, "grad_norm": 0.5367380976676941, "learning_rate": 1.6521890714820965e-06, "loss": 4.1737, "step": 28930 }, { "epoch": 0.8836591325595602, "grad_norm": 0.5514864921569824, "learning_rate": 1.6513315696793014e-06, "loss": 4.1642, "step": 28931 }, { "epoch": 0.8836896762370189, "grad_norm": 0.5348948836326599, "learning_rate": 1.6504742828597041e-06, "loss": 4.2584, "step": 28932 }, { "epoch": 0.8837202199144777, "grad_norm": 0.5374717712402344, "learning_rate": 1.649617211031193e-06, "loss": 4.2275, "step": 28933 }, { "epoch": 0.8837507635919365, "grad_norm": 0.5531418919563293, "learning_rate": 1.6487603542016643e-06, "loss": 4.2518, "step": 28934 }, { "epoch": 0.8837813072693952, "grad_norm": 0.5283486247062683, "learning_rate": 1.6479037123790064e-06, "loss": 4.1932, "step": 28935 }, { "epoch": 0.883811850946854, "grad_norm": 0.5298910737037659, "learning_rate": 1.6470472855710988e-06, "loss": 4.2271, "step": 28936 }, { "epoch": 0.8838423946243128, "grad_norm": 0.5321426391601562, "learning_rate": 1.6461910737858383e-06, "loss": 4.1237, "step": 28937 }, { "epoch": 0.8838729383017715, "grad_norm": 0.5335003733634949, "learning_rate": 1.6453350770311043e-06, "loss": 4.2009, "step": 28938 }, { "epoch": 0.8839034819792303, "grad_norm": 0.5321909189224243, "learning_rate": 1.644479295314777e-06, "loss": 4.2868, "step": 28939 }, { "epoch": 0.8839340256566891, "grad_norm": 0.5433357954025269, "learning_rate": 1.643623728644736e-06, "loss": 4.2446, "step": 28940 }, { "epoch": 0.8839645693341478, "grad_norm": 0.5365417003631592, "learning_rate": 1.6427683770288638e-06, "loss": 4.1408, "step": 28941 }, { "epoch": 0.8839951130116066, "grad_norm": 0.5335661172866821, "learning_rate": 1.6419132404750293e-06, "loss": 4.2538, "step": 28942 }, { "epoch": 0.8840256566890654, "grad_norm": 0.5206893086433411, "learning_rate": 1.6410583189911065e-06, "loss": 4.2653, "step": 28943 }, { "epoch": 0.8840562003665241, "grad_norm": 0.527490496635437, "learning_rate": 1.6402036125849757e-06, "loss": 4.1739, "step": 28944 }, { "epoch": 0.8840867440439829, "grad_norm": 0.5412108898162842, "learning_rate": 1.6393491212644995e-06, "loss": 4.3642, "step": 28945 }, { "epoch": 0.8841172877214417, "grad_norm": 0.5390883684158325, "learning_rate": 1.6384948450375442e-06, "loss": 4.2682, "step": 28946 }, { "epoch": 0.8841478313989004, "grad_norm": 0.5458168387413025, "learning_rate": 1.6376407839119811e-06, "loss": 4.2688, "step": 28947 }, { "epoch": 0.8841783750763592, "grad_norm": 0.5267506837844849, "learning_rate": 1.636786937895668e-06, "loss": 4.2231, "step": 28948 }, { "epoch": 0.8842089187538179, "grad_norm": 0.5450286269187927, "learning_rate": 1.6359333069964733e-06, "loss": 4.199, "step": 28949 }, { "epoch": 0.8842394624312767, "grad_norm": 0.5285808444023132, "learning_rate": 1.6350798912222492e-06, "loss": 4.1923, "step": 28950 }, { "epoch": 0.8842700061087355, "grad_norm": 0.5426785349845886, "learning_rate": 1.634226690580859e-06, "loss": 4.321, "step": 28951 }, { "epoch": 0.8843005497861942, "grad_norm": 0.5337677597999573, "learning_rate": 1.6333737050801574e-06, "loss": 4.2417, "step": 28952 }, { "epoch": 0.884331093463653, "grad_norm": 0.5354217886924744, "learning_rate": 1.6325209347279962e-06, "loss": 4.2992, "step": 28953 }, { "epoch": 0.8843616371411118, "grad_norm": 0.5341305732727051, "learning_rate": 1.6316683795322308e-06, "loss": 4.2978, "step": 28954 }, { "epoch": 0.8843921808185705, "grad_norm": 0.5295758247375488, "learning_rate": 1.6308160395007127e-06, "loss": 4.2858, "step": 28955 }, { "epoch": 0.8844227244960293, "grad_norm": 0.5329744219779968, "learning_rate": 1.6299639146412804e-06, "loss": 4.2676, "step": 28956 }, { "epoch": 0.8844532681734881, "grad_norm": 0.5283518433570862, "learning_rate": 1.6291120049617887e-06, "loss": 4.247, "step": 28957 }, { "epoch": 0.8844838118509468, "grad_norm": 0.5298802256584167, "learning_rate": 1.628260310470081e-06, "loss": 4.2116, "step": 28958 }, { "epoch": 0.8845143555284056, "grad_norm": 0.525749921798706, "learning_rate": 1.6274088311739933e-06, "loss": 4.169, "step": 28959 }, { "epoch": 0.8845448992058644, "grad_norm": 0.5373978018760681, "learning_rate": 1.6265575670813744e-06, "loss": 4.2646, "step": 28960 }, { "epoch": 0.8845754428833231, "grad_norm": 0.5381863713264465, "learning_rate": 1.6257065182000542e-06, "loss": 4.3317, "step": 28961 }, { "epoch": 0.8846059865607819, "grad_norm": 0.5413655042648315, "learning_rate": 1.6248556845378738e-06, "loss": 4.1449, "step": 28962 }, { "epoch": 0.8846365302382407, "grad_norm": 0.533267080783844, "learning_rate": 1.624005066102663e-06, "loss": 4.2579, "step": 28963 }, { "epoch": 0.8846670739156994, "grad_norm": 0.520960807800293, "learning_rate": 1.6231546629022598e-06, "loss": 4.2042, "step": 28964 }, { "epoch": 0.8846976175931582, "grad_norm": 0.5399668216705322, "learning_rate": 1.622304474944486e-06, "loss": 4.2395, "step": 28965 }, { "epoch": 0.8847281612706169, "grad_norm": 0.5410081744194031, "learning_rate": 1.6214545022371796e-06, "loss": 4.309, "step": 28966 }, { "epoch": 0.8847587049480757, "grad_norm": 0.5382394194602966, "learning_rate": 1.6206047447881568e-06, "loss": 4.2327, "step": 28967 }, { "epoch": 0.8847892486255345, "grad_norm": 0.534099817276001, "learning_rate": 1.619755202605247e-06, "loss": 4.3124, "step": 28968 }, { "epoch": 0.8848197923029932, "grad_norm": 0.5339522361755371, "learning_rate": 1.618905875696275e-06, "loss": 4.2712, "step": 28969 }, { "epoch": 0.884850335980452, "grad_norm": 0.5345101952552795, "learning_rate": 1.6180567640690564e-06, "loss": 4.3203, "step": 28970 }, { "epoch": 0.8848808796579108, "grad_norm": 0.5329996347427368, "learning_rate": 1.61720786773141e-06, "loss": 4.2928, "step": 28971 }, { "epoch": 0.8849114233353695, "grad_norm": 0.5296903848648071, "learning_rate": 1.6163591866911548e-06, "loss": 4.1088, "step": 28972 }, { "epoch": 0.8849419670128283, "grad_norm": 0.5319156050682068, "learning_rate": 1.615510720956101e-06, "loss": 4.205, "step": 28973 }, { "epoch": 0.8849725106902872, "grad_norm": 0.5326223373413086, "learning_rate": 1.6146624705340646e-06, "loss": 4.1981, "step": 28974 }, { "epoch": 0.8850030543677458, "grad_norm": 0.5378370881080627, "learning_rate": 1.6138144354328561e-06, "loss": 4.2831, "step": 28975 }, { "epoch": 0.8850335980452047, "grad_norm": 0.5328694581985474, "learning_rate": 1.612966615660283e-06, "loss": 4.2191, "step": 28976 }, { "epoch": 0.8850641417226635, "grad_norm": 0.5308480262756348, "learning_rate": 1.6121190112241474e-06, "loss": 4.251, "step": 28977 }, { "epoch": 0.8850946854001221, "grad_norm": 0.536472499370575, "learning_rate": 1.6112716221322599e-06, "loss": 4.2606, "step": 28978 }, { "epoch": 0.885125229077581, "grad_norm": 0.5324305891990662, "learning_rate": 1.610424448392414e-06, "loss": 4.2619, "step": 28979 }, { "epoch": 0.8851557727550398, "grad_norm": 0.530509889125824, "learning_rate": 1.6095774900124206e-06, "loss": 4.3325, "step": 28980 }, { "epoch": 0.8851863164324985, "grad_norm": 0.5308665633201599, "learning_rate": 1.6087307470000728e-06, "loss": 4.3214, "step": 28981 }, { "epoch": 0.8852168601099573, "grad_norm": 0.5279977917671204, "learning_rate": 1.6078842193631676e-06, "loss": 4.208, "step": 28982 }, { "epoch": 0.885247403787416, "grad_norm": 0.5334872007369995, "learning_rate": 1.6070379071095015e-06, "loss": 4.2003, "step": 28983 }, { "epoch": 0.8852779474648748, "grad_norm": 0.531777560710907, "learning_rate": 1.6061918102468598e-06, "loss": 4.2981, "step": 28984 }, { "epoch": 0.8853084911423336, "grad_norm": 0.5332992076873779, "learning_rate": 1.605345928783039e-06, "loss": 4.2242, "step": 28985 }, { "epoch": 0.8853390348197923, "grad_norm": 0.5294615626335144, "learning_rate": 1.6045002627258305e-06, "loss": 4.2342, "step": 28986 }, { "epoch": 0.8853695784972511, "grad_norm": 0.5416300892829895, "learning_rate": 1.6036548120830137e-06, "loss": 4.1908, "step": 28987 }, { "epoch": 0.8854001221747099, "grad_norm": 0.5314809083938599, "learning_rate": 1.6028095768623741e-06, "loss": 4.2903, "step": 28988 }, { "epoch": 0.8854306658521686, "grad_norm": 0.5492119789123535, "learning_rate": 1.601964557071703e-06, "loss": 4.2608, "step": 28989 }, { "epoch": 0.8854612095296274, "grad_norm": 0.5226776599884033, "learning_rate": 1.6011197527187687e-06, "loss": 4.2026, "step": 28990 }, { "epoch": 0.8854917532070862, "grad_norm": 0.5449325442314148, "learning_rate": 1.60027516381136e-06, "loss": 4.2874, "step": 28991 }, { "epoch": 0.8855222968845449, "grad_norm": 0.5328801870346069, "learning_rate": 1.5994307903572452e-06, "loss": 4.2965, "step": 28992 }, { "epoch": 0.8855528405620037, "grad_norm": 0.5361608266830444, "learning_rate": 1.5985866323642045e-06, "loss": 4.1601, "step": 28993 }, { "epoch": 0.8855833842394625, "grad_norm": 0.5360986590385437, "learning_rate": 1.5977426898400067e-06, "loss": 4.2443, "step": 28994 }, { "epoch": 0.8856139279169212, "grad_norm": 0.5338917374610901, "learning_rate": 1.5968989627924257e-06, "loss": 4.277, "step": 28995 }, { "epoch": 0.88564447159438, "grad_norm": 0.5344725251197815, "learning_rate": 1.596055451229228e-06, "loss": 4.2883, "step": 28996 }, { "epoch": 0.8856750152718388, "grad_norm": 0.5356543660163879, "learning_rate": 1.5952121551581795e-06, "loss": 4.3373, "step": 28997 }, { "epoch": 0.8857055589492975, "grad_norm": 0.5384328961372375, "learning_rate": 1.5943690745870487e-06, "loss": 4.325, "step": 28998 }, { "epoch": 0.8857361026267563, "grad_norm": 0.5314751863479614, "learning_rate": 1.5935262095235936e-06, "loss": 4.2664, "step": 28999 }, { "epoch": 0.885766646304215, "grad_norm": 0.5384527444839478, "learning_rate": 1.5926835599755801e-06, "loss": 4.1793, "step": 29000 }, { "epoch": 0.8857971899816738, "grad_norm": 0.5398458242416382, "learning_rate": 1.5918411259507603e-06, "loss": 4.2383, "step": 29001 }, { "epoch": 0.8858277336591326, "grad_norm": 0.5315545797348022, "learning_rate": 1.590998907456895e-06, "loss": 4.2662, "step": 29002 }, { "epoch": 0.8858582773365913, "grad_norm": 0.5235714316368103, "learning_rate": 1.5901569045017412e-06, "loss": 4.2297, "step": 29003 }, { "epoch": 0.8858888210140501, "grad_norm": 0.5226279497146606, "learning_rate": 1.589315117093046e-06, "loss": 4.1806, "step": 29004 }, { "epoch": 0.8859193646915089, "grad_norm": 0.5335018038749695, "learning_rate": 1.588473545238564e-06, "loss": 4.2546, "step": 29005 }, { "epoch": 0.8859499083689676, "grad_norm": 0.5404806137084961, "learning_rate": 1.5876321889460449e-06, "loss": 4.2424, "step": 29006 }, { "epoch": 0.8859804520464264, "grad_norm": 0.523267388343811, "learning_rate": 1.5867910482232323e-06, "loss": 4.263, "step": 29007 }, { "epoch": 0.8860109957238852, "grad_norm": 0.5296383500099182, "learning_rate": 1.5859501230778728e-06, "loss": 4.2553, "step": 29008 }, { "epoch": 0.8860415394013439, "grad_norm": 0.5381290912628174, "learning_rate": 1.5851094135177102e-06, "loss": 4.2906, "step": 29009 }, { "epoch": 0.8860720830788027, "grad_norm": 0.5286397337913513, "learning_rate": 1.584268919550483e-06, "loss": 4.2683, "step": 29010 }, { "epoch": 0.8861026267562615, "grad_norm": 0.5263230204582214, "learning_rate": 1.583428641183929e-06, "loss": 4.218, "step": 29011 }, { "epoch": 0.8861331704337202, "grad_norm": 0.5353114008903503, "learning_rate": 1.5825885784257892e-06, "loss": 4.1545, "step": 29012 }, { "epoch": 0.886163714111179, "grad_norm": 0.5349960923194885, "learning_rate": 1.5817487312837942e-06, "loss": 4.2184, "step": 29013 }, { "epoch": 0.8861942577886378, "grad_norm": 0.5332745909690857, "learning_rate": 1.5809090997656789e-06, "loss": 4.1978, "step": 29014 }, { "epoch": 0.8862248014660965, "grad_norm": 0.5344841480255127, "learning_rate": 1.580069683879179e-06, "loss": 4.1707, "step": 29015 }, { "epoch": 0.8862553451435553, "grad_norm": 0.5409181118011475, "learning_rate": 1.5792304836320132e-06, "loss": 4.2271, "step": 29016 }, { "epoch": 0.886285888821014, "grad_norm": 0.5431014895439148, "learning_rate": 1.5783914990319198e-06, "loss": 4.2316, "step": 29017 }, { "epoch": 0.8863164324984728, "grad_norm": 0.5302416682243347, "learning_rate": 1.5775527300866123e-06, "loss": 4.2561, "step": 29018 }, { "epoch": 0.8863469761759316, "grad_norm": 0.5332489013671875, "learning_rate": 1.5767141768038229e-06, "loss": 4.3137, "step": 29019 }, { "epoch": 0.8863775198533903, "grad_norm": 0.5392764210700989, "learning_rate": 1.575875839191268e-06, "loss": 4.2973, "step": 29020 }, { "epoch": 0.8864080635308491, "grad_norm": 0.5504304766654968, "learning_rate": 1.5750377172566693e-06, "loss": 4.1928, "step": 29021 }, { "epoch": 0.8864386072083079, "grad_norm": 0.5312033891677856, "learning_rate": 1.5741998110077372e-06, "loss": 4.262, "step": 29022 }, { "epoch": 0.8864691508857666, "grad_norm": 0.5230019092559814, "learning_rate": 1.5733621204521986e-06, "loss": 4.2166, "step": 29023 }, { "epoch": 0.8864996945632254, "grad_norm": 0.5307066440582275, "learning_rate": 1.572524645597759e-06, "loss": 4.2973, "step": 29024 }, { "epoch": 0.8865302382406842, "grad_norm": 0.5322291254997253, "learning_rate": 1.571687386452128e-06, "loss": 4.2975, "step": 29025 }, { "epoch": 0.8865607819181429, "grad_norm": 0.5364043712615967, "learning_rate": 1.5708503430230199e-06, "loss": 4.3052, "step": 29026 }, { "epoch": 0.8865913255956017, "grad_norm": 0.5292202830314636, "learning_rate": 1.5700135153181333e-06, "loss": 4.3168, "step": 29027 }, { "epoch": 0.8866218692730605, "grad_norm": 0.5320586562156677, "learning_rate": 1.5691769033451792e-06, "loss": 4.1914, "step": 29028 }, { "epoch": 0.8866524129505192, "grad_norm": 0.5389965176582336, "learning_rate": 1.568340507111865e-06, "loss": 4.268, "step": 29029 }, { "epoch": 0.886682956627978, "grad_norm": 0.5321423411369324, "learning_rate": 1.567504326625882e-06, "loss": 4.2673, "step": 29030 }, { "epoch": 0.8867135003054367, "grad_norm": 0.5367414951324463, "learning_rate": 1.5666683618949408e-06, "loss": 4.1487, "step": 29031 }, { "epoch": 0.8867440439828955, "grad_norm": 0.5385171175003052, "learning_rate": 1.5658326129267265e-06, "loss": 4.2457, "step": 29032 }, { "epoch": 0.8867745876603543, "grad_norm": 0.539264976978302, "learning_rate": 1.5649970797289387e-06, "loss": 4.3263, "step": 29033 }, { "epoch": 0.886805131337813, "grad_norm": 0.533126175403595, "learning_rate": 1.5641617623092797e-06, "loss": 4.281, "step": 29034 }, { "epoch": 0.8868356750152718, "grad_norm": 0.5336560010910034, "learning_rate": 1.5633266606754265e-06, "loss": 4.2634, "step": 29035 }, { "epoch": 0.8868662186927306, "grad_norm": 0.542083203792572, "learning_rate": 1.5624917748350731e-06, "loss": 4.2586, "step": 29036 }, { "epoch": 0.8868967623701893, "grad_norm": 0.5265738368034363, "learning_rate": 1.5616571047959133e-06, "loss": 4.2898, "step": 29037 }, { "epoch": 0.8869273060476481, "grad_norm": 0.5331128239631653, "learning_rate": 1.5608226505656242e-06, "loss": 4.2253, "step": 29038 }, { "epoch": 0.8869578497251069, "grad_norm": 0.5323585271835327, "learning_rate": 1.5599884121518971e-06, "loss": 4.1372, "step": 29039 }, { "epoch": 0.8869883934025656, "grad_norm": 0.5411012768745422, "learning_rate": 1.559154389562406e-06, "loss": 4.2865, "step": 29040 }, { "epoch": 0.8870189370800244, "grad_norm": 0.534071147441864, "learning_rate": 1.5583205828048313e-06, "loss": 4.3506, "step": 29041 }, { "epoch": 0.8870494807574832, "grad_norm": 0.5344822406768799, "learning_rate": 1.5574869918868501e-06, "loss": 4.2518, "step": 29042 }, { "epoch": 0.8870800244349419, "grad_norm": 0.5412062406539917, "learning_rate": 1.5566536168161422e-06, "loss": 4.3011, "step": 29043 }, { "epoch": 0.8871105681124007, "grad_norm": 0.5312209725379944, "learning_rate": 1.5558204576003738e-06, "loss": 4.2407, "step": 29044 }, { "epoch": 0.8871411117898595, "grad_norm": 0.5310267210006714, "learning_rate": 1.554987514247222e-06, "loss": 4.2674, "step": 29045 }, { "epoch": 0.8871716554673182, "grad_norm": 0.5319299697875977, "learning_rate": 1.5541547867643585e-06, "loss": 4.1266, "step": 29046 }, { "epoch": 0.887202199144777, "grad_norm": 0.5323746204376221, "learning_rate": 1.553322275159441e-06, "loss": 4.1309, "step": 29047 }, { "epoch": 0.8872327428222357, "grad_norm": 0.5382806062698364, "learning_rate": 1.5524899794401443e-06, "loss": 4.2555, "step": 29048 }, { "epoch": 0.8872632864996945, "grad_norm": 0.5304918885231018, "learning_rate": 1.5516578996141257e-06, "loss": 4.2364, "step": 29049 }, { "epoch": 0.8872938301771534, "grad_norm": 0.5346905589103699, "learning_rate": 1.5508260356890458e-06, "loss": 4.2475, "step": 29050 }, { "epoch": 0.887324373854612, "grad_norm": 0.5426796674728394, "learning_rate": 1.5499943876725737e-06, "loss": 4.2845, "step": 29051 }, { "epoch": 0.8873549175320709, "grad_norm": 0.5351393222808838, "learning_rate": 1.5491629555723557e-06, "loss": 4.2232, "step": 29052 }, { "epoch": 0.8873854612095297, "grad_norm": 0.533606231212616, "learning_rate": 1.54833173939605e-06, "loss": 4.3018, "step": 29053 }, { "epoch": 0.8874160048869884, "grad_norm": 0.5404815673828125, "learning_rate": 1.547500739151317e-06, "loss": 4.2978, "step": 29054 }, { "epoch": 0.8874465485644472, "grad_norm": 0.5356022715568542, "learning_rate": 1.546669954845803e-06, "loss": 4.2263, "step": 29055 }, { "epoch": 0.887477092241906, "grad_norm": 0.5445472002029419, "learning_rate": 1.5458393864871524e-06, "loss": 4.3281, "step": 29056 }, { "epoch": 0.8875076359193647, "grad_norm": 0.5293208360671997, "learning_rate": 1.5450090340830198e-06, "loss": 4.1819, "step": 29057 }, { "epoch": 0.8875381795968235, "grad_norm": 0.5275977253913879, "learning_rate": 1.5441788976410466e-06, "loss": 4.3087, "step": 29058 }, { "epoch": 0.8875687232742823, "grad_norm": 0.5343866944313049, "learning_rate": 1.5433489771688791e-06, "loss": 4.2042, "step": 29059 }, { "epoch": 0.887599266951741, "grad_norm": 0.5414147973060608, "learning_rate": 1.542519272674159e-06, "loss": 4.2748, "step": 29060 }, { "epoch": 0.8876298106291998, "grad_norm": 0.5416095852851868, "learning_rate": 1.5416897841645239e-06, "loss": 4.248, "step": 29061 }, { "epoch": 0.8876603543066586, "grad_norm": 0.5362367630004883, "learning_rate": 1.54086051164761e-06, "loss": 4.2852, "step": 29062 }, { "epoch": 0.8876908979841173, "grad_norm": 0.544434130191803, "learning_rate": 1.540031455131058e-06, "loss": 4.1917, "step": 29063 }, { "epoch": 0.8877214416615761, "grad_norm": 0.5353603959083557, "learning_rate": 1.5392026146224953e-06, "loss": 4.21, "step": 29064 }, { "epoch": 0.8877519853390348, "grad_norm": 0.5452003479003906, "learning_rate": 1.53837399012956e-06, "loss": 4.209, "step": 29065 }, { "epoch": 0.8877825290164936, "grad_norm": 0.5260306596755981, "learning_rate": 1.5375455816598744e-06, "loss": 4.2347, "step": 29066 }, { "epoch": 0.8878130726939524, "grad_norm": 0.5337033271789551, "learning_rate": 1.5367173892210706e-06, "loss": 4.2393, "step": 29067 }, { "epoch": 0.8878436163714111, "grad_norm": 0.5476911664009094, "learning_rate": 1.535889412820779e-06, "loss": 4.2422, "step": 29068 }, { "epoch": 0.8878741600488699, "grad_norm": 0.5307296514511108, "learning_rate": 1.53506165246661e-06, "loss": 4.2109, "step": 29069 }, { "epoch": 0.8879047037263287, "grad_norm": 0.5398482084274292, "learning_rate": 1.5342341081661992e-06, "loss": 4.3021, "step": 29070 }, { "epoch": 0.8879352474037874, "grad_norm": 0.5365771651268005, "learning_rate": 1.5334067799271546e-06, "loss": 4.1876, "step": 29071 }, { "epoch": 0.8879657910812462, "grad_norm": 0.5338141322135925, "learning_rate": 1.532579667757103e-06, "loss": 4.2972, "step": 29072 }, { "epoch": 0.887996334758705, "grad_norm": 0.5410630106925964, "learning_rate": 1.5317527716636526e-06, "loss": 4.229, "step": 29073 }, { "epoch": 0.8880268784361637, "grad_norm": 0.540733814239502, "learning_rate": 1.530926091654425e-06, "loss": 4.2993, "step": 29074 }, { "epoch": 0.8880574221136225, "grad_norm": 0.5349777936935425, "learning_rate": 1.5300996277370222e-06, "loss": 4.2614, "step": 29075 }, { "epoch": 0.8880879657910813, "grad_norm": 0.5359297394752502, "learning_rate": 1.5292733799190606e-06, "loss": 4.2595, "step": 29076 }, { "epoch": 0.88811850946854, "grad_norm": 0.5282548069953918, "learning_rate": 1.5284473482081508e-06, "loss": 4.2245, "step": 29077 }, { "epoch": 0.8881490531459988, "grad_norm": 0.5274338126182556, "learning_rate": 1.5276215326118892e-06, "loss": 4.2273, "step": 29078 }, { "epoch": 0.8881795968234576, "grad_norm": 0.5273115038871765, "learning_rate": 1.526795933137884e-06, "loss": 4.088, "step": 29079 }, { "epoch": 0.8882101405009163, "grad_norm": 0.5358035564422607, "learning_rate": 1.5259705497937426e-06, "loss": 4.244, "step": 29080 }, { "epoch": 0.8882406841783751, "grad_norm": 0.5340235233306885, "learning_rate": 1.5251453825870566e-06, "loss": 4.267, "step": 29081 }, { "epoch": 0.8882712278558338, "grad_norm": 0.5322134494781494, "learning_rate": 1.5243204315254277e-06, "loss": 4.3022, "step": 29082 }, { "epoch": 0.8883017715332926, "grad_norm": 0.5394293069839478, "learning_rate": 1.5234956966164477e-06, "loss": 4.1612, "step": 29083 }, { "epoch": 0.8883323152107514, "grad_norm": 0.5318138003349304, "learning_rate": 1.5226711778677128e-06, "loss": 4.2507, "step": 29084 }, { "epoch": 0.8883628588882101, "grad_norm": 0.5343635082244873, "learning_rate": 1.5218468752868198e-06, "loss": 4.2668, "step": 29085 }, { "epoch": 0.8883934025656689, "grad_norm": 0.5299781560897827, "learning_rate": 1.5210227888813545e-06, "loss": 4.1895, "step": 29086 }, { "epoch": 0.8884239462431277, "grad_norm": 0.5408962368965149, "learning_rate": 1.5201989186588995e-06, "loss": 4.3019, "step": 29087 }, { "epoch": 0.8884544899205864, "grad_norm": 0.5343977808952332, "learning_rate": 1.5193752646270486e-06, "loss": 4.2993, "step": 29088 }, { "epoch": 0.8884850335980452, "grad_norm": 0.5310707688331604, "learning_rate": 1.5185518267933797e-06, "loss": 4.2866, "step": 29089 }, { "epoch": 0.888515577275504, "grad_norm": 0.5375187397003174, "learning_rate": 1.5177286051654749e-06, "loss": 4.2664, "step": 29090 }, { "epoch": 0.8885461209529627, "grad_norm": 0.5265147686004639, "learning_rate": 1.5169055997509202e-06, "loss": 4.1792, "step": 29091 }, { "epoch": 0.8885766646304215, "grad_norm": 0.5358359813690186, "learning_rate": 1.5160828105572872e-06, "loss": 4.174, "step": 29092 }, { "epoch": 0.8886072083078803, "grad_norm": 0.5335102081298828, "learning_rate": 1.515260237592153e-06, "loss": 4.2746, "step": 29093 }, { "epoch": 0.888637751985339, "grad_norm": 0.5411263704299927, "learning_rate": 1.5144378808630982e-06, "loss": 4.2575, "step": 29094 }, { "epoch": 0.8886682956627978, "grad_norm": 0.5341129302978516, "learning_rate": 1.513615740377683e-06, "loss": 4.3019, "step": 29095 }, { "epoch": 0.8886988393402566, "grad_norm": 0.5339829325675964, "learning_rate": 1.5127938161434846e-06, "loss": 4.2066, "step": 29096 }, { "epoch": 0.8887293830177153, "grad_norm": 0.5405072569847107, "learning_rate": 1.511972108168072e-06, "loss": 4.3027, "step": 29097 }, { "epoch": 0.8887599266951741, "grad_norm": 0.5354701280593872, "learning_rate": 1.5111506164590061e-06, "loss": 4.2684, "step": 29098 }, { "epoch": 0.8887904703726328, "grad_norm": 0.5334126353263855, "learning_rate": 1.5103293410238556e-06, "loss": 4.2959, "step": 29099 }, { "epoch": 0.8888210140500916, "grad_norm": 0.5274851322174072, "learning_rate": 1.5095082818701783e-06, "loss": 4.2417, "step": 29100 }, { "epoch": 0.8888515577275504, "grad_norm": 0.5452975630760193, "learning_rate": 1.5086874390055378e-06, "loss": 4.2317, "step": 29101 }, { "epoch": 0.8888821014050091, "grad_norm": 0.5303709506988525, "learning_rate": 1.5078668124374863e-06, "loss": 4.2892, "step": 29102 }, { "epoch": 0.8889126450824679, "grad_norm": 0.5301187038421631, "learning_rate": 1.507046402173587e-06, "loss": 4.1504, "step": 29103 }, { "epoch": 0.8889431887599267, "grad_norm": 0.5371794104576111, "learning_rate": 1.5062262082213867e-06, "loss": 4.3283, "step": 29104 }, { "epoch": 0.8889737324373854, "grad_norm": 0.538255512714386, "learning_rate": 1.5054062305884465e-06, "loss": 4.3587, "step": 29105 }, { "epoch": 0.8890042761148442, "grad_norm": 0.5336411595344543, "learning_rate": 1.5045864692823069e-06, "loss": 4.2, "step": 29106 }, { "epoch": 0.889034819792303, "grad_norm": 0.5308699607849121, "learning_rate": 1.5037669243105178e-06, "loss": 4.2516, "step": 29107 }, { "epoch": 0.8890653634697617, "grad_norm": 0.5364317893981934, "learning_rate": 1.5029475956806316e-06, "loss": 4.2996, "step": 29108 }, { "epoch": 0.8890959071472205, "grad_norm": 0.5486617088317871, "learning_rate": 1.5021284834001865e-06, "loss": 4.1607, "step": 29109 }, { "epoch": 0.8891264508246793, "grad_norm": 0.52725750207901, "learning_rate": 1.5013095874767236e-06, "loss": 4.1442, "step": 29110 }, { "epoch": 0.889156994502138, "grad_norm": 0.5373978018760681, "learning_rate": 1.5004909079177871e-06, "loss": 4.1978, "step": 29111 }, { "epoch": 0.8891875381795968, "grad_norm": 0.5461440682411194, "learning_rate": 1.4996724447309124e-06, "loss": 4.302, "step": 29112 }, { "epoch": 0.8892180818570556, "grad_norm": 0.5262266397476196, "learning_rate": 1.4988541979236354e-06, "loss": 4.236, "step": 29113 }, { "epoch": 0.8892486255345143, "grad_norm": 0.5393782258033752, "learning_rate": 1.4980361675034943e-06, "loss": 4.0729, "step": 29114 }, { "epoch": 0.8892791692119731, "grad_norm": 0.5400288701057434, "learning_rate": 1.4972183534780137e-06, "loss": 4.2358, "step": 29115 }, { "epoch": 0.8893097128894318, "grad_norm": 0.5315520763397217, "learning_rate": 1.4964007558547321e-06, "loss": 4.2484, "step": 29116 }, { "epoch": 0.8893402565668906, "grad_norm": 0.5387417078018188, "learning_rate": 1.4955833746411685e-06, "loss": 4.2278, "step": 29117 }, { "epoch": 0.8893708002443494, "grad_norm": 0.5373644232749939, "learning_rate": 1.4947662098448584e-06, "loss": 4.2383, "step": 29118 }, { "epoch": 0.8894013439218081, "grad_norm": 0.5347680449485779, "learning_rate": 1.4939492614733208e-06, "loss": 4.2907, "step": 29119 }, { "epoch": 0.889431887599267, "grad_norm": 0.542415201663971, "learning_rate": 1.4931325295340747e-06, "loss": 4.2229, "step": 29120 }, { "epoch": 0.8894624312767258, "grad_norm": 0.5234854221343994, "learning_rate": 1.4923160140346421e-06, "loss": 4.1065, "step": 29121 }, { "epoch": 0.8894929749541844, "grad_norm": 0.5265049934387207, "learning_rate": 1.491499714982547e-06, "loss": 4.2303, "step": 29122 }, { "epoch": 0.8895235186316433, "grad_norm": 0.5427213907241821, "learning_rate": 1.4906836323852953e-06, "loss": 4.243, "step": 29123 }, { "epoch": 0.8895540623091021, "grad_norm": 0.5338770747184753, "learning_rate": 1.489867766250408e-06, "loss": 4.2867, "step": 29124 }, { "epoch": 0.8895846059865608, "grad_norm": 0.534089982509613, "learning_rate": 1.4890521165854016e-06, "loss": 4.2904, "step": 29125 }, { "epoch": 0.8896151496640196, "grad_norm": 0.5326022505760193, "learning_rate": 1.4882366833977758e-06, "loss": 4.1606, "step": 29126 }, { "epoch": 0.8896456933414784, "grad_norm": 0.5212555527687073, "learning_rate": 1.4874214666950408e-06, "loss": 4.2514, "step": 29127 }, { "epoch": 0.889676237018937, "grad_norm": 0.5329018235206604, "learning_rate": 1.4866064664847106e-06, "loss": 4.2828, "step": 29128 }, { "epoch": 0.8897067806963959, "grad_norm": 0.5384880900382996, "learning_rate": 1.4857916827742818e-06, "loss": 4.2392, "step": 29129 }, { "epoch": 0.8897373243738547, "grad_norm": 0.5373215079307556, "learning_rate": 1.4849771155712567e-06, "loss": 4.3253, "step": 29130 }, { "epoch": 0.8897678680513134, "grad_norm": 0.5412926077842712, "learning_rate": 1.484162764883143e-06, "loss": 4.3292, "step": 29131 }, { "epoch": 0.8897984117287722, "grad_norm": 0.5370444059371948, "learning_rate": 1.4833486307174293e-06, "loss": 4.2324, "step": 29132 }, { "epoch": 0.8898289554062309, "grad_norm": 0.5716355443000793, "learning_rate": 1.482534713081618e-06, "loss": 4.2133, "step": 29133 }, { "epoch": 0.8898594990836897, "grad_norm": 0.5507797002792358, "learning_rate": 1.481721011983203e-06, "loss": 4.3038, "step": 29134 }, { "epoch": 0.8898900427611485, "grad_norm": 0.5387045741081238, "learning_rate": 1.4809075274296701e-06, "loss": 4.1998, "step": 29135 }, { "epoch": 0.8899205864386072, "grad_norm": 0.5359452366828918, "learning_rate": 1.4800942594285161e-06, "loss": 4.279, "step": 29136 }, { "epoch": 0.889951130116066, "grad_norm": 0.5393223762512207, "learning_rate": 1.4792812079872265e-06, "loss": 4.2435, "step": 29137 }, { "epoch": 0.8899816737935248, "grad_norm": 0.5301626920700073, "learning_rate": 1.4784683731132841e-06, "loss": 4.115, "step": 29138 }, { "epoch": 0.8900122174709835, "grad_norm": 0.5451668500900269, "learning_rate": 1.4776557548141834e-06, "loss": 4.2757, "step": 29139 }, { "epoch": 0.8900427611484423, "grad_norm": 0.5372932553291321, "learning_rate": 1.4768433530973957e-06, "loss": 4.2472, "step": 29140 }, { "epoch": 0.8900733048259011, "grad_norm": 0.5345705151557922, "learning_rate": 1.476031167970407e-06, "loss": 4.1564, "step": 29141 }, { "epoch": 0.8901038485033598, "grad_norm": 0.5338410139083862, "learning_rate": 1.4752191994406945e-06, "loss": 4.2406, "step": 29142 }, { "epoch": 0.8901343921808186, "grad_norm": 0.5363603830337524, "learning_rate": 1.4744074475157328e-06, "loss": 4.2704, "step": 29143 }, { "epoch": 0.8901649358582774, "grad_norm": 0.5324701070785522, "learning_rate": 1.4735959122029963e-06, "loss": 4.1663, "step": 29144 }, { "epoch": 0.8901954795357361, "grad_norm": 0.5415309071540833, "learning_rate": 1.4727845935099655e-06, "loss": 4.2675, "step": 29145 }, { "epoch": 0.8902260232131949, "grad_norm": 0.5311774015426636, "learning_rate": 1.4719734914440953e-06, "loss": 4.2446, "step": 29146 }, { "epoch": 0.8902565668906537, "grad_norm": 0.5478113889694214, "learning_rate": 1.4711626060128686e-06, "loss": 4.2392, "step": 29147 }, { "epoch": 0.8902871105681124, "grad_norm": 0.5324789881706238, "learning_rate": 1.4703519372237408e-06, "loss": 4.262, "step": 29148 }, { "epoch": 0.8903176542455712, "grad_norm": 0.541046142578125, "learning_rate": 1.4695414850841831e-06, "loss": 4.2818, "step": 29149 }, { "epoch": 0.8903481979230299, "grad_norm": 0.5436310172080994, "learning_rate": 1.4687312496016543e-06, "loss": 4.1982, "step": 29150 }, { "epoch": 0.8903787416004887, "grad_norm": 0.5397612452507019, "learning_rate": 1.4679212307836144e-06, "loss": 4.1994, "step": 29151 }, { "epoch": 0.8904092852779475, "grad_norm": 0.5242812037467957, "learning_rate": 1.4671114286375215e-06, "loss": 4.08, "step": 29152 }, { "epoch": 0.8904398289554062, "grad_norm": 0.5363955497741699, "learning_rate": 1.4663018431708364e-06, "loss": 4.1426, "step": 29153 }, { "epoch": 0.890470372632865, "grad_norm": 0.5360877513885498, "learning_rate": 1.4654924743910059e-06, "loss": 4.2504, "step": 29154 }, { "epoch": 0.8905009163103238, "grad_norm": 0.5433953404426575, "learning_rate": 1.464683322305488e-06, "loss": 4.3186, "step": 29155 }, { "epoch": 0.8905314599877825, "grad_norm": 0.5426445603370667, "learning_rate": 1.4638743869217348e-06, "loss": 4.2475, "step": 29156 }, { "epoch": 0.8905620036652413, "grad_norm": 0.5340393781661987, "learning_rate": 1.463065668247185e-06, "loss": 4.2657, "step": 29157 }, { "epoch": 0.8905925473427001, "grad_norm": 0.5344642400741577, "learning_rate": 1.4622571662892937e-06, "loss": 4.2938, "step": 29158 }, { "epoch": 0.8906230910201588, "grad_norm": 0.5337228178977966, "learning_rate": 1.4614488810555076e-06, "loss": 4.1941, "step": 29159 }, { "epoch": 0.8906536346976176, "grad_norm": 0.5378387570381165, "learning_rate": 1.4606408125532572e-06, "loss": 4.2863, "step": 29160 }, { "epoch": 0.8906841783750764, "grad_norm": 0.5467535257339478, "learning_rate": 1.459832960789992e-06, "loss": 4.2338, "step": 29161 }, { "epoch": 0.8907147220525351, "grad_norm": 0.5521866083145142, "learning_rate": 1.45902532577315e-06, "loss": 4.2649, "step": 29162 }, { "epoch": 0.8907452657299939, "grad_norm": 0.531119704246521, "learning_rate": 1.4582179075101621e-06, "loss": 4.2543, "step": 29163 }, { "epoch": 0.8907758094074527, "grad_norm": 0.5316260457038879, "learning_rate": 1.4574107060084692e-06, "loss": 4.2399, "step": 29164 }, { "epoch": 0.8908063530849114, "grad_norm": 0.5397611856460571, "learning_rate": 1.4566037212755013e-06, "loss": 4.2275, "step": 29165 }, { "epoch": 0.8908368967623702, "grad_norm": 0.5376284122467041, "learning_rate": 1.4557969533186832e-06, "loss": 4.2471, "step": 29166 }, { "epoch": 0.8908674404398289, "grad_norm": 0.5371903777122498, "learning_rate": 1.4549904021454508e-06, "loss": 4.2635, "step": 29167 }, { "epoch": 0.8908979841172877, "grad_norm": 0.5342926979064941, "learning_rate": 1.4541840677632257e-06, "loss": 4.2105, "step": 29168 }, { "epoch": 0.8909285277947465, "grad_norm": 0.5366441011428833, "learning_rate": 1.4533779501794325e-06, "loss": 4.3392, "step": 29169 }, { "epoch": 0.8909590714722052, "grad_norm": 0.5351477861404419, "learning_rate": 1.452572049401499e-06, "loss": 4.3021, "step": 29170 }, { "epoch": 0.890989615149664, "grad_norm": 0.5444660186767578, "learning_rate": 1.451766365436838e-06, "loss": 4.3491, "step": 29171 }, { "epoch": 0.8910201588271228, "grad_norm": 0.5284535884857178, "learning_rate": 1.4509608982928718e-06, "loss": 4.2284, "step": 29172 }, { "epoch": 0.8910507025045815, "grad_norm": 0.5429897308349609, "learning_rate": 1.4501556479770195e-06, "loss": 4.3164, "step": 29173 }, { "epoch": 0.8910812461820403, "grad_norm": 0.5350131988525391, "learning_rate": 1.4493506144966862e-06, "loss": 4.2413, "step": 29174 }, { "epoch": 0.8911117898594991, "grad_norm": 0.531169056892395, "learning_rate": 1.4485457978592937e-06, "loss": 4.2007, "step": 29175 }, { "epoch": 0.8911423335369578, "grad_norm": 0.5356537103652954, "learning_rate": 1.4477411980722526e-06, "loss": 4.2421, "step": 29176 }, { "epoch": 0.8911728772144166, "grad_norm": 0.5322461724281311, "learning_rate": 1.446936815142963e-06, "loss": 4.2082, "step": 29177 }, { "epoch": 0.8912034208918754, "grad_norm": 0.5316743850708008, "learning_rate": 1.4461326490788352e-06, "loss": 4.2482, "step": 29178 }, { "epoch": 0.8912339645693341, "grad_norm": 0.5385717749595642, "learning_rate": 1.4453286998872801e-06, "loss": 4.2279, "step": 29179 }, { "epoch": 0.8912645082467929, "grad_norm": 0.5310308337211609, "learning_rate": 1.4445249675756916e-06, "loss": 4.2484, "step": 29180 }, { "epoch": 0.8912950519242516, "grad_norm": 0.5358208417892456, "learning_rate": 1.4437214521514698e-06, "loss": 4.2471, "step": 29181 }, { "epoch": 0.8913255956017104, "grad_norm": 0.5398648381233215, "learning_rate": 1.4429181536220221e-06, "loss": 4.1347, "step": 29182 }, { "epoch": 0.8913561392791692, "grad_norm": 0.5385845303535461, "learning_rate": 1.4421150719947318e-06, "loss": 4.2196, "step": 29183 }, { "epoch": 0.8913866829566279, "grad_norm": 0.5286623239517212, "learning_rate": 1.4413122072770069e-06, "loss": 4.2838, "step": 29184 }, { "epoch": 0.8914172266340867, "grad_norm": 0.538658857345581, "learning_rate": 1.4405095594762274e-06, "loss": 4.2746, "step": 29185 }, { "epoch": 0.8914477703115455, "grad_norm": 0.5398544073104858, "learning_rate": 1.4397071285997904e-06, "loss": 4.2944, "step": 29186 }, { "epoch": 0.8914783139890042, "grad_norm": 0.5249348282814026, "learning_rate": 1.438904914655087e-06, "loss": 4.1285, "step": 29187 }, { "epoch": 0.891508857666463, "grad_norm": 0.5413594841957092, "learning_rate": 1.4381029176494976e-06, "loss": 4.2282, "step": 29188 }, { "epoch": 0.8915394013439218, "grad_norm": 0.5477301478385925, "learning_rate": 1.437301137590405e-06, "loss": 4.2819, "step": 29189 }, { "epoch": 0.8915699450213805, "grad_norm": 0.5398930311203003, "learning_rate": 1.4364995744852034e-06, "loss": 4.1236, "step": 29190 }, { "epoch": 0.8916004886988393, "grad_norm": 0.5311588644981384, "learning_rate": 1.435698228341259e-06, "loss": 4.1493, "step": 29191 }, { "epoch": 0.8916310323762981, "grad_norm": 0.5315595269203186, "learning_rate": 1.4348970991659577e-06, "loss": 4.2035, "step": 29192 }, { "epoch": 0.8916615760537568, "grad_norm": 0.5329658389091492, "learning_rate": 1.4340961869666796e-06, "loss": 4.2157, "step": 29193 }, { "epoch": 0.8916921197312156, "grad_norm": 0.5316641330718994, "learning_rate": 1.4332954917507886e-06, "loss": 4.2431, "step": 29194 }, { "epoch": 0.8917226634086745, "grad_norm": 0.5376736521720886, "learning_rate": 1.432495013525667e-06, "loss": 4.3016, "step": 29195 }, { "epoch": 0.8917532070861331, "grad_norm": 0.5365568399429321, "learning_rate": 1.4316947522986818e-06, "loss": 4.2121, "step": 29196 }, { "epoch": 0.891783750763592, "grad_norm": 0.5398986339569092, "learning_rate": 1.4308947080771963e-06, "loss": 4.1263, "step": 29197 }, { "epoch": 0.8918142944410506, "grad_norm": 0.5480301976203918, "learning_rate": 1.430094880868585e-06, "loss": 4.3111, "step": 29198 }, { "epoch": 0.8918448381185095, "grad_norm": 0.5380779504776001, "learning_rate": 1.429295270680206e-06, "loss": 4.287, "step": 29199 }, { "epoch": 0.8918753817959683, "grad_norm": 0.5326458215713501, "learning_rate": 1.428495877519423e-06, "loss": 4.1574, "step": 29200 }, { "epoch": 0.891905925473427, "grad_norm": 0.5362026691436768, "learning_rate": 1.4276967013936021e-06, "loss": 4.3255, "step": 29201 }, { "epoch": 0.8919364691508858, "grad_norm": 0.54857337474823, "learning_rate": 1.4268977423100932e-06, "loss": 4.2861, "step": 29202 }, { "epoch": 0.8919670128283446, "grad_norm": 0.5416375994682312, "learning_rate": 1.426099000276257e-06, "loss": 4.3041, "step": 29203 }, { "epoch": 0.8919975565058033, "grad_norm": 0.5300522446632385, "learning_rate": 1.4253004752994514e-06, "loss": 4.2225, "step": 29204 }, { "epoch": 0.8920281001832621, "grad_norm": 0.5446966886520386, "learning_rate": 1.4245021673870208e-06, "loss": 4.2991, "step": 29205 }, { "epoch": 0.8920586438607209, "grad_norm": 0.5335254669189453, "learning_rate": 1.4237040765463227e-06, "loss": 4.2213, "step": 29206 }, { "epoch": 0.8920891875381796, "grad_norm": 0.5438063144683838, "learning_rate": 1.4229062027847045e-06, "loss": 4.2493, "step": 29207 }, { "epoch": 0.8921197312156384, "grad_norm": 0.5385432839393616, "learning_rate": 1.4221085461095074e-06, "loss": 4.2914, "step": 29208 }, { "epoch": 0.8921502748930972, "grad_norm": 0.5402324795722961, "learning_rate": 1.4213111065280781e-06, "loss": 4.1741, "step": 29209 }, { "epoch": 0.8921808185705559, "grad_norm": 0.5311601758003235, "learning_rate": 1.4205138840477667e-06, "loss": 4.2525, "step": 29210 }, { "epoch": 0.8922113622480147, "grad_norm": 0.5363690257072449, "learning_rate": 1.4197168786759058e-06, "loss": 4.2675, "step": 29211 }, { "epoch": 0.8922419059254735, "grad_norm": 0.5371882915496826, "learning_rate": 1.4189200904198314e-06, "loss": 4.2337, "step": 29212 }, { "epoch": 0.8922724496029322, "grad_norm": 0.5397000312805176, "learning_rate": 1.4181235192868902e-06, "loss": 4.3013, "step": 29213 }, { "epoch": 0.892302993280391, "grad_norm": 0.5478427410125732, "learning_rate": 1.4173271652844044e-06, "loss": 4.1813, "step": 29214 }, { "epoch": 0.8923335369578497, "grad_norm": 0.540723979473114, "learning_rate": 1.4165310284197152e-06, "loss": 4.2361, "step": 29215 }, { "epoch": 0.8923640806353085, "grad_norm": 0.5353982448577881, "learning_rate": 1.4157351087001502e-06, "loss": 4.2424, "step": 29216 }, { "epoch": 0.8923946243127673, "grad_norm": 0.5416456460952759, "learning_rate": 1.414939406133034e-06, "loss": 4.2471, "step": 29217 }, { "epoch": 0.892425167990226, "grad_norm": 0.538037121295929, "learning_rate": 1.4141439207257023e-06, "loss": 4.2726, "step": 29218 }, { "epoch": 0.8924557116676848, "grad_norm": 0.5295500755310059, "learning_rate": 1.4133486524854716e-06, "loss": 4.2566, "step": 29219 }, { "epoch": 0.8924862553451436, "grad_norm": 0.5396034121513367, "learning_rate": 1.412553601419664e-06, "loss": 4.2367, "step": 29220 }, { "epoch": 0.8925167990226023, "grad_norm": 0.543150782585144, "learning_rate": 1.4117587675356092e-06, "loss": 4.2142, "step": 29221 }, { "epoch": 0.8925473427000611, "grad_norm": 0.5346242189407349, "learning_rate": 1.4109641508406157e-06, "loss": 4.1276, "step": 29222 }, { "epoch": 0.8925778863775199, "grad_norm": 0.5440124869346619, "learning_rate": 1.4101697513420026e-06, "loss": 4.2189, "step": 29223 }, { "epoch": 0.8926084300549786, "grad_norm": 0.5309931635856628, "learning_rate": 1.409375569047089e-06, "loss": 4.269, "step": 29224 }, { "epoch": 0.8926389737324374, "grad_norm": 0.5526460409164429, "learning_rate": 1.40858160396318e-06, "loss": 4.2676, "step": 29225 }, { "epoch": 0.8926695174098962, "grad_norm": 0.5468651652336121, "learning_rate": 1.407787856097592e-06, "loss": 4.2513, "step": 29226 }, { "epoch": 0.8927000610873549, "grad_norm": 0.5414085388183594, "learning_rate": 1.4069943254576279e-06, "loss": 4.3246, "step": 29227 }, { "epoch": 0.8927306047648137, "grad_norm": 0.5394572615623474, "learning_rate": 1.4062010120506037e-06, "loss": 4.2604, "step": 29228 }, { "epoch": 0.8927611484422725, "grad_norm": 0.5391072630882263, "learning_rate": 1.4054079158838106e-06, "loss": 4.1197, "step": 29229 }, { "epoch": 0.8927916921197312, "grad_norm": 0.5427294969558716, "learning_rate": 1.4046150369645628e-06, "loss": 4.2524, "step": 29230 }, { "epoch": 0.89282223579719, "grad_norm": 0.5370122194290161, "learning_rate": 1.403822375300154e-06, "loss": 4.2685, "step": 29231 }, { "epoch": 0.8928527794746487, "grad_norm": 0.5472649335861206, "learning_rate": 1.4030299308978838e-06, "loss": 4.2745, "step": 29232 }, { "epoch": 0.8928833231521075, "grad_norm": 0.5356006622314453, "learning_rate": 1.4022377037650497e-06, "loss": 4.1556, "step": 29233 }, { "epoch": 0.8929138668295663, "grad_norm": 0.5270691514015198, "learning_rate": 1.4014456939089454e-06, "loss": 4.229, "step": 29234 }, { "epoch": 0.892944410507025, "grad_norm": 0.540393590927124, "learning_rate": 1.4006539013368652e-06, "loss": 4.2136, "step": 29235 }, { "epoch": 0.8929749541844838, "grad_norm": 0.5385555624961853, "learning_rate": 1.3998623260560978e-06, "loss": 4.2413, "step": 29236 }, { "epoch": 0.8930054978619426, "grad_norm": 0.5359633564949036, "learning_rate": 1.3990709680739288e-06, "loss": 4.3366, "step": 29237 }, { "epoch": 0.8930360415394013, "grad_norm": 0.5329158306121826, "learning_rate": 1.3982798273976528e-06, "loss": 4.2278, "step": 29238 }, { "epoch": 0.8930665852168601, "grad_norm": 0.5276246070861816, "learning_rate": 1.3974889040345468e-06, "loss": 4.2213, "step": 29239 }, { "epoch": 0.8930971288943189, "grad_norm": 0.5442470908164978, "learning_rate": 1.3966981979918942e-06, "loss": 4.3008, "step": 29240 }, { "epoch": 0.8931276725717776, "grad_norm": 0.5318512320518494, "learning_rate": 1.3959077092769806e-06, "loss": 4.2806, "step": 29241 }, { "epoch": 0.8931582162492364, "grad_norm": 0.534984827041626, "learning_rate": 1.3951174378970755e-06, "loss": 4.1626, "step": 29242 }, { "epoch": 0.8931887599266952, "grad_norm": 0.5304186344146729, "learning_rate": 1.3943273838594672e-06, "loss": 4.2771, "step": 29243 }, { "epoch": 0.8932193036041539, "grad_norm": 0.5424540042877197, "learning_rate": 1.3935375471714223e-06, "loss": 4.327, "step": 29244 }, { "epoch": 0.8932498472816127, "grad_norm": 0.5400077700614929, "learning_rate": 1.39274792784021e-06, "loss": 4.2859, "step": 29245 }, { "epoch": 0.8932803909590715, "grad_norm": 0.537774920463562, "learning_rate": 1.3919585258731078e-06, "loss": 4.2342, "step": 29246 }, { "epoch": 0.8933109346365302, "grad_norm": 0.532181978225708, "learning_rate": 1.3911693412773819e-06, "loss": 4.3681, "step": 29247 }, { "epoch": 0.893341478313989, "grad_norm": 0.5345516800880432, "learning_rate": 1.390380374060296e-06, "loss": 4.2185, "step": 29248 }, { "epoch": 0.8933720219914477, "grad_norm": 0.5426689982414246, "learning_rate": 1.3895916242291196e-06, "loss": 4.1621, "step": 29249 }, { "epoch": 0.8934025656689065, "grad_norm": 0.5276427865028381, "learning_rate": 1.3888030917911104e-06, "loss": 4.1669, "step": 29250 }, { "epoch": 0.8934331093463653, "grad_norm": 0.5364940166473389, "learning_rate": 1.3880147767535295e-06, "loss": 4.2633, "step": 29251 }, { "epoch": 0.893463653023824, "grad_norm": 0.5323401093482971, "learning_rate": 1.3872266791236432e-06, "loss": 4.3199, "step": 29252 }, { "epoch": 0.8934941967012828, "grad_norm": 0.5498700737953186, "learning_rate": 1.3864387989086958e-06, "loss": 4.2566, "step": 29253 }, { "epoch": 0.8935247403787416, "grad_norm": 0.5292588472366333, "learning_rate": 1.3856511361159452e-06, "loss": 4.2489, "step": 29254 }, { "epoch": 0.8935552840562003, "grad_norm": 0.5289468765258789, "learning_rate": 1.3848636907526524e-06, "loss": 4.1779, "step": 29255 }, { "epoch": 0.8935858277336591, "grad_norm": 0.5358998775482178, "learning_rate": 1.3840764628260561e-06, "loss": 4.3385, "step": 29256 }, { "epoch": 0.8936163714111179, "grad_norm": 0.535938024520874, "learning_rate": 1.3832894523434143e-06, "loss": 4.2482, "step": 29257 }, { "epoch": 0.8936469150885766, "grad_norm": 0.5350697040557861, "learning_rate": 1.3825026593119628e-06, "loss": 4.2393, "step": 29258 }, { "epoch": 0.8936774587660354, "grad_norm": 0.5454307794570923, "learning_rate": 1.3817160837389598e-06, "loss": 4.2216, "step": 29259 }, { "epoch": 0.8937080024434942, "grad_norm": 0.5395957231521606, "learning_rate": 1.3809297256316356e-06, "loss": 4.3597, "step": 29260 }, { "epoch": 0.8937385461209529, "grad_norm": 0.5376335382461548, "learning_rate": 1.3801435849972371e-06, "loss": 4.2952, "step": 29261 }, { "epoch": 0.8937690897984117, "grad_norm": 0.5372282266616821, "learning_rate": 1.3793576618429976e-06, "loss": 4.1744, "step": 29262 }, { "epoch": 0.8937996334758705, "grad_norm": 0.5366321802139282, "learning_rate": 1.3785719561761584e-06, "loss": 4.1879, "step": 29263 }, { "epoch": 0.8938301771533292, "grad_norm": 0.5400797724723816, "learning_rate": 1.3777864680039527e-06, "loss": 4.3514, "step": 29264 }, { "epoch": 0.893860720830788, "grad_norm": 0.5808458924293518, "learning_rate": 1.3770011973336106e-06, "loss": 4.2227, "step": 29265 }, { "epoch": 0.8938912645082467, "grad_norm": 0.548588216304779, "learning_rate": 1.3762161441723682e-06, "loss": 4.2572, "step": 29266 }, { "epoch": 0.8939218081857055, "grad_norm": 0.5324852466583252, "learning_rate": 1.3754313085274445e-06, "loss": 4.1754, "step": 29267 }, { "epoch": 0.8939523518631644, "grad_norm": 0.5396049618721008, "learning_rate": 1.3746466904060728e-06, "loss": 4.268, "step": 29268 }, { "epoch": 0.893982895540623, "grad_norm": 0.5335177183151245, "learning_rate": 1.3738622898154807e-06, "loss": 4.2533, "step": 29269 }, { "epoch": 0.8940134392180819, "grad_norm": 0.5383560657501221, "learning_rate": 1.373078106762879e-06, "loss": 4.2768, "step": 29270 }, { "epoch": 0.8940439828955407, "grad_norm": 0.5500653982162476, "learning_rate": 1.372294141255498e-06, "loss": 4.2183, "step": 29271 }, { "epoch": 0.8940745265729994, "grad_norm": 0.5333700776100159, "learning_rate": 1.371510393300554e-06, "loss": 4.2391, "step": 29272 }, { "epoch": 0.8941050702504582, "grad_norm": 0.5365039706230164, "learning_rate": 1.370726862905261e-06, "loss": 4.107, "step": 29273 }, { "epoch": 0.894135613927917, "grad_norm": 0.5379716157913208, "learning_rate": 1.3699435500768382e-06, "loss": 4.1436, "step": 29274 }, { "epoch": 0.8941661576053757, "grad_norm": 0.5378476977348328, "learning_rate": 1.3691604548224934e-06, "loss": 4.2634, "step": 29275 }, { "epoch": 0.8941967012828345, "grad_norm": 0.5443698763847351, "learning_rate": 1.368377577149435e-06, "loss": 4.3022, "step": 29276 }, { "epoch": 0.8942272449602933, "grad_norm": 0.5340369939804077, "learning_rate": 1.367594917064874e-06, "loss": 4.2223, "step": 29277 }, { "epoch": 0.894257788637752, "grad_norm": 0.5336399078369141, "learning_rate": 1.3668124745760209e-06, "loss": 4.2425, "step": 29278 }, { "epoch": 0.8942883323152108, "grad_norm": 0.5339417457580566, "learning_rate": 1.366030249690073e-06, "loss": 4.2116, "step": 29279 }, { "epoch": 0.8943188759926696, "grad_norm": 0.5369459986686707, "learning_rate": 1.3652482424142355e-06, "loss": 4.2, "step": 29280 }, { "epoch": 0.8943494196701283, "grad_norm": 0.5388270616531372, "learning_rate": 1.3644664527557138e-06, "loss": 4.1363, "step": 29281 }, { "epoch": 0.8943799633475871, "grad_norm": 0.5424663424491882, "learning_rate": 1.3636848807216968e-06, "loss": 4.24, "step": 29282 }, { "epoch": 0.8944105070250458, "grad_norm": 0.5305489897727966, "learning_rate": 1.3629035263193896e-06, "loss": 4.1983, "step": 29283 }, { "epoch": 0.8944410507025046, "grad_norm": 0.5363173484802246, "learning_rate": 1.3621223895559808e-06, "loss": 4.245, "step": 29284 }, { "epoch": 0.8944715943799634, "grad_norm": 0.5381738543510437, "learning_rate": 1.3613414704386623e-06, "loss": 4.2925, "step": 29285 }, { "epoch": 0.8945021380574221, "grad_norm": 0.5294613838195801, "learning_rate": 1.3605607689746308e-06, "loss": 4.2767, "step": 29286 }, { "epoch": 0.8945326817348809, "grad_norm": 0.5365129709243774, "learning_rate": 1.3597802851710666e-06, "loss": 4.3548, "step": 29287 }, { "epoch": 0.8945632254123397, "grad_norm": 0.5518777370452881, "learning_rate": 1.3590000190351614e-06, "loss": 4.2325, "step": 29288 }, { "epoch": 0.8945937690897984, "grad_norm": 0.5317081809043884, "learning_rate": 1.3582199705741011e-06, "loss": 4.238, "step": 29289 }, { "epoch": 0.8946243127672572, "grad_norm": 0.5496431589126587, "learning_rate": 1.3574401397950632e-06, "loss": 4.149, "step": 29290 }, { "epoch": 0.894654856444716, "grad_norm": 0.540468156337738, "learning_rate": 1.356660526705228e-06, "loss": 4.2431, "step": 29291 }, { "epoch": 0.8946854001221747, "grad_norm": 0.5296717286109924, "learning_rate": 1.3558811313117787e-06, "loss": 4.2048, "step": 29292 }, { "epoch": 0.8947159437996335, "grad_norm": 0.542924702167511, "learning_rate": 1.3551019536218845e-06, "loss": 4.2209, "step": 29293 }, { "epoch": 0.8947464874770923, "grad_norm": 0.5545341372489929, "learning_rate": 1.3543229936427233e-06, "loss": 4.2358, "step": 29294 }, { "epoch": 0.894777031154551, "grad_norm": 0.5461336970329285, "learning_rate": 1.3535442513814722e-06, "loss": 4.3122, "step": 29295 }, { "epoch": 0.8948075748320098, "grad_norm": 0.5335978865623474, "learning_rate": 1.3527657268452954e-06, "loss": 4.2248, "step": 29296 }, { "epoch": 0.8948381185094686, "grad_norm": 0.5464184284210205, "learning_rate": 1.351987420041359e-06, "loss": 4.1988, "step": 29297 }, { "epoch": 0.8948686621869273, "grad_norm": 0.5467372536659241, "learning_rate": 1.351209330976838e-06, "loss": 4.2299, "step": 29298 }, { "epoch": 0.8948992058643861, "grad_norm": 0.5438433885574341, "learning_rate": 1.350431459658888e-06, "loss": 4.3296, "step": 29299 }, { "epoch": 0.8949297495418448, "grad_norm": 0.5385398864746094, "learning_rate": 1.3496538060946779e-06, "loss": 4.1682, "step": 29300 }, { "epoch": 0.8949602932193036, "grad_norm": 0.532932698726654, "learning_rate": 1.3488763702913632e-06, "loss": 4.2808, "step": 29301 }, { "epoch": 0.8949908368967624, "grad_norm": 0.5323124527931213, "learning_rate": 1.348099152256102e-06, "loss": 4.1872, "step": 29302 }, { "epoch": 0.8950213805742211, "grad_norm": 0.53934645652771, "learning_rate": 1.3473221519960582e-06, "loss": 4.2929, "step": 29303 }, { "epoch": 0.8950519242516799, "grad_norm": 0.5373091101646423, "learning_rate": 1.346545369518376e-06, "loss": 4.2983, "step": 29304 }, { "epoch": 0.8950824679291387, "grad_norm": 0.540498673915863, "learning_rate": 1.3457688048302136e-06, "loss": 4.2633, "step": 29305 }, { "epoch": 0.8951130116065974, "grad_norm": 0.5343202352523804, "learning_rate": 1.3449924579387208e-06, "loss": 4.0834, "step": 29306 }, { "epoch": 0.8951435552840562, "grad_norm": 0.5561695694923401, "learning_rate": 1.3442163288510417e-06, "loss": 4.2859, "step": 29307 }, { "epoch": 0.895174098961515, "grad_norm": 0.5380220413208008, "learning_rate": 1.3434404175743266e-06, "loss": 4.3085, "step": 29308 }, { "epoch": 0.8952046426389737, "grad_norm": 0.5333263874053955, "learning_rate": 1.3426647241157191e-06, "loss": 4.1654, "step": 29309 }, { "epoch": 0.8952351863164325, "grad_norm": 0.5555686354637146, "learning_rate": 1.3418892484823613e-06, "loss": 4.3193, "step": 29310 }, { "epoch": 0.8952657299938913, "grad_norm": 0.5428145527839661, "learning_rate": 1.3411139906813892e-06, "loss": 4.3258, "step": 29311 }, { "epoch": 0.89529627367135, "grad_norm": 0.5388712882995605, "learning_rate": 1.3403389507199494e-06, "loss": 4.2182, "step": 29312 }, { "epoch": 0.8953268173488088, "grad_norm": 0.5450446009635925, "learning_rate": 1.3395641286051724e-06, "loss": 4.3529, "step": 29313 }, { "epoch": 0.8953573610262676, "grad_norm": 0.5281980633735657, "learning_rate": 1.338789524344189e-06, "loss": 4.21, "step": 29314 }, { "epoch": 0.8953879047037263, "grad_norm": 0.5391073226928711, "learning_rate": 1.338015137944143e-06, "loss": 4.3583, "step": 29315 }, { "epoch": 0.8954184483811851, "grad_norm": 0.5419557094573975, "learning_rate": 1.3372409694121514e-06, "loss": 4.2617, "step": 29316 }, { "epoch": 0.8954489920586438, "grad_norm": 0.5452107191085815, "learning_rate": 1.3364670187553552e-06, "loss": 4.2583, "step": 29317 }, { "epoch": 0.8954795357361026, "grad_norm": 0.5321465730667114, "learning_rate": 1.3356932859808685e-06, "loss": 4.2047, "step": 29318 }, { "epoch": 0.8955100794135614, "grad_norm": 0.5421437621116638, "learning_rate": 1.3349197710958189e-06, "loss": 4.3389, "step": 29319 }, { "epoch": 0.8955406230910201, "grad_norm": 0.5395039319992065, "learning_rate": 1.3341464741073367e-06, "loss": 4.2974, "step": 29320 }, { "epoch": 0.8955711667684789, "grad_norm": 0.5722985863685608, "learning_rate": 1.333373395022533e-06, "loss": 4.2823, "step": 29321 }, { "epoch": 0.8956017104459377, "grad_norm": 0.5387619137763977, "learning_rate": 1.332600533848527e-06, "loss": 4.1557, "step": 29322 }, { "epoch": 0.8956322541233964, "grad_norm": 0.5385749936103821, "learning_rate": 1.331827890592438e-06, "loss": 4.3081, "step": 29323 }, { "epoch": 0.8956627978008552, "grad_norm": 0.534217357635498, "learning_rate": 1.3310554652613772e-06, "loss": 4.2173, "step": 29324 }, { "epoch": 0.895693341478314, "grad_norm": 0.5468341112136841, "learning_rate": 1.330283257862458e-06, "loss": 4.2476, "step": 29325 }, { "epoch": 0.8957238851557727, "grad_norm": 0.5334830284118652, "learning_rate": 1.3295112684027944e-06, "loss": 4.2616, "step": 29326 }, { "epoch": 0.8957544288332315, "grad_norm": 0.5308409333229065, "learning_rate": 1.3287394968894862e-06, "loss": 4.2162, "step": 29327 }, { "epoch": 0.8957849725106903, "grad_norm": 0.5392492413520813, "learning_rate": 1.3279679433296444e-06, "loss": 4.3073, "step": 29328 }, { "epoch": 0.895815516188149, "grad_norm": 0.5331312417984009, "learning_rate": 1.3271966077303743e-06, "loss": 4.2014, "step": 29329 }, { "epoch": 0.8958460598656078, "grad_norm": 0.5332909822463989, "learning_rate": 1.326425490098776e-06, "loss": 4.2886, "step": 29330 }, { "epoch": 0.8958766035430665, "grad_norm": 0.5352224111557007, "learning_rate": 1.325654590441952e-06, "loss": 4.2533, "step": 29331 }, { "epoch": 0.8959071472205253, "grad_norm": 0.5555237531661987, "learning_rate": 1.324883908766994e-06, "loss": 4.2671, "step": 29332 }, { "epoch": 0.8959376908979841, "grad_norm": 0.5417527556419373, "learning_rate": 1.3241134450810017e-06, "loss": 4.3244, "step": 29333 }, { "epoch": 0.8959682345754428, "grad_norm": 0.5429779887199402, "learning_rate": 1.323343199391075e-06, "loss": 4.2939, "step": 29334 }, { "epoch": 0.8959987782529016, "grad_norm": 0.5434951186180115, "learning_rate": 1.3225731717042971e-06, "loss": 4.2846, "step": 29335 }, { "epoch": 0.8960293219303604, "grad_norm": 0.5416971445083618, "learning_rate": 1.3218033620277654e-06, "loss": 4.2506, "step": 29336 }, { "epoch": 0.8960598656078191, "grad_norm": 0.5349331498146057, "learning_rate": 1.32103377036856e-06, "loss": 4.27, "step": 29337 }, { "epoch": 0.896090409285278, "grad_norm": 0.5354852676391602, "learning_rate": 1.3202643967337752e-06, "loss": 4.1634, "step": 29338 }, { "epoch": 0.8961209529627367, "grad_norm": 0.5336781144142151, "learning_rate": 1.319495241130489e-06, "loss": 4.3128, "step": 29339 }, { "epoch": 0.8961514966401954, "grad_norm": 0.5354260802268982, "learning_rate": 1.318726303565787e-06, "loss": 4.2645, "step": 29340 }, { "epoch": 0.8961820403176542, "grad_norm": 0.5417737364768982, "learning_rate": 1.3179575840467446e-06, "loss": 4.1825, "step": 29341 }, { "epoch": 0.896212583995113, "grad_norm": 0.5354546308517456, "learning_rate": 1.3171890825804444e-06, "loss": 4.1694, "step": 29342 }, { "epoch": 0.8962431276725717, "grad_norm": 0.5397396683692932, "learning_rate": 1.316420799173962e-06, "loss": 4.2819, "step": 29343 }, { "epoch": 0.8962736713500306, "grad_norm": 0.5364176034927368, "learning_rate": 1.3156527338343661e-06, "loss": 4.2383, "step": 29344 }, { "epoch": 0.8963042150274894, "grad_norm": 0.5417961478233337, "learning_rate": 1.3148848865687347e-06, "loss": 4.2134, "step": 29345 }, { "epoch": 0.896334758704948, "grad_norm": 0.540625810623169, "learning_rate": 1.3141172573841399e-06, "loss": 4.3214, "step": 29346 }, { "epoch": 0.8963653023824069, "grad_norm": 0.5317307710647583, "learning_rate": 1.3133498462876399e-06, "loss": 4.2895, "step": 29347 }, { "epoch": 0.8963958460598656, "grad_norm": 0.5443502068519592, "learning_rate": 1.3125826532863122e-06, "loss": 4.264, "step": 29348 }, { "epoch": 0.8964263897373244, "grad_norm": 0.5335021018981934, "learning_rate": 1.3118156783872099e-06, "loss": 4.2773, "step": 29349 }, { "epoch": 0.8964569334147832, "grad_norm": 0.5521517395973206, "learning_rate": 1.3110489215973991e-06, "loss": 4.1483, "step": 29350 }, { "epoch": 0.8964874770922419, "grad_norm": 0.5481549501419067, "learning_rate": 1.310282382923947e-06, "loss": 4.3443, "step": 29351 }, { "epoch": 0.8965180207697007, "grad_norm": 0.5355800986289978, "learning_rate": 1.3095160623738972e-06, "loss": 4.2676, "step": 29352 }, { "epoch": 0.8965485644471595, "grad_norm": 0.5289245247840881, "learning_rate": 1.3087499599543195e-06, "loss": 4.2051, "step": 29353 }, { "epoch": 0.8965791081246182, "grad_norm": 0.5418809652328491, "learning_rate": 1.307984075672264e-06, "loss": 4.2313, "step": 29354 }, { "epoch": 0.896609651802077, "grad_norm": 0.535069465637207, "learning_rate": 1.3072184095347716e-06, "loss": 4.1339, "step": 29355 }, { "epoch": 0.8966401954795358, "grad_norm": 0.5417359471321106, "learning_rate": 1.306452961548904e-06, "loss": 4.2563, "step": 29356 }, { "epoch": 0.8966707391569945, "grad_norm": 0.532245934009552, "learning_rate": 1.305687731721711e-06, "loss": 4.221, "step": 29357 }, { "epoch": 0.8967012828344533, "grad_norm": 0.5261358022689819, "learning_rate": 1.304922720060228e-06, "loss": 4.2774, "step": 29358 }, { "epoch": 0.8967318265119121, "grad_norm": 0.5343772768974304, "learning_rate": 1.304157926571503e-06, "loss": 4.3286, "step": 29359 }, { "epoch": 0.8967623701893708, "grad_norm": 0.5448666214942932, "learning_rate": 1.3033933512625857e-06, "loss": 4.2905, "step": 29360 }, { "epoch": 0.8967929138668296, "grad_norm": 0.5394651889801025, "learning_rate": 1.3026289941405035e-06, "loss": 4.202, "step": 29361 }, { "epoch": 0.8968234575442884, "grad_norm": 0.5358663201332092, "learning_rate": 1.3018648552123008e-06, "loss": 4.2222, "step": 29362 }, { "epoch": 0.8968540012217471, "grad_norm": 0.5291154384613037, "learning_rate": 1.3011009344850167e-06, "loss": 4.209, "step": 29363 }, { "epoch": 0.8968845448992059, "grad_norm": 0.5402807593345642, "learning_rate": 1.3003372319656787e-06, "loss": 4.1941, "step": 29364 }, { "epoch": 0.8969150885766646, "grad_norm": 0.5369986295700073, "learning_rate": 1.2995737476613228e-06, "loss": 4.2052, "step": 29365 }, { "epoch": 0.8969456322541234, "grad_norm": 0.5318880677223206, "learning_rate": 1.2988104815789743e-06, "loss": 4.2439, "step": 29366 }, { "epoch": 0.8969761759315822, "grad_norm": 0.5342497229576111, "learning_rate": 1.298047433725666e-06, "loss": 4.2971, "step": 29367 }, { "epoch": 0.8970067196090409, "grad_norm": 0.5327747464179993, "learning_rate": 1.2972846041084174e-06, "loss": 4.2874, "step": 29368 }, { "epoch": 0.8970372632864997, "grad_norm": 0.5345257520675659, "learning_rate": 1.296521992734262e-06, "loss": 4.232, "step": 29369 }, { "epoch": 0.8970678069639585, "grad_norm": 0.53859943151474, "learning_rate": 1.2957595996102106e-06, "loss": 4.3195, "step": 29370 }, { "epoch": 0.8970983506414172, "grad_norm": 0.5442186594009399, "learning_rate": 1.2949974247432912e-06, "loss": 4.1988, "step": 29371 }, { "epoch": 0.897128894318876, "grad_norm": 0.5335299968719482, "learning_rate": 1.2942354681405172e-06, "loss": 4.2773, "step": 29372 }, { "epoch": 0.8971594379963348, "grad_norm": 0.5378250479698181, "learning_rate": 1.2934737298089028e-06, "loss": 4.3649, "step": 29373 }, { "epoch": 0.8971899816737935, "grad_norm": 0.5317795872688293, "learning_rate": 1.29271220975547e-06, "loss": 4.1471, "step": 29374 }, { "epoch": 0.8972205253512523, "grad_norm": 0.5386078357696533, "learning_rate": 1.2919509079872188e-06, "loss": 4.2795, "step": 29375 }, { "epoch": 0.8972510690287111, "grad_norm": 0.5360790491104126, "learning_rate": 1.2911898245111687e-06, "loss": 4.253, "step": 29376 }, { "epoch": 0.8972816127061698, "grad_norm": 0.541225016117096, "learning_rate": 1.290428959334325e-06, "loss": 4.2139, "step": 29377 }, { "epoch": 0.8973121563836286, "grad_norm": 0.5404791235923767, "learning_rate": 1.2896683124636876e-06, "loss": 4.2553, "step": 29378 }, { "epoch": 0.8973427000610874, "grad_norm": 0.5342963337898254, "learning_rate": 1.2889078839062678e-06, "loss": 4.2737, "step": 29379 }, { "epoch": 0.8973732437385461, "grad_norm": 0.5377717018127441, "learning_rate": 1.2881476736690656e-06, "loss": 4.1678, "step": 29380 }, { "epoch": 0.8974037874160049, "grad_norm": 0.5357669591903687, "learning_rate": 1.2873876817590752e-06, "loss": 4.2195, "step": 29381 }, { "epoch": 0.8974343310934636, "grad_norm": 0.5426848530769348, "learning_rate": 1.286627908183302e-06, "loss": 4.2999, "step": 29382 }, { "epoch": 0.8974648747709224, "grad_norm": 0.5399574041366577, "learning_rate": 1.2858683529487354e-06, "loss": 4.3196, "step": 29383 }, { "epoch": 0.8974954184483812, "grad_norm": 0.5326959490776062, "learning_rate": 1.2851090160623747e-06, "loss": 4.2487, "step": 29384 }, { "epoch": 0.8975259621258399, "grad_norm": 0.5239003896713257, "learning_rate": 1.284349897531209e-06, "loss": 4.2558, "step": 29385 }, { "epoch": 0.8975565058032987, "grad_norm": 0.5334659218788147, "learning_rate": 1.2835909973622217e-06, "loss": 4.2233, "step": 29386 }, { "epoch": 0.8975870494807575, "grad_norm": 0.5347321629524231, "learning_rate": 1.2828323155624073e-06, "loss": 4.2633, "step": 29387 }, { "epoch": 0.8976175931582162, "grad_norm": 0.5500729084014893, "learning_rate": 1.2820738521387544e-06, "loss": 4.2397, "step": 29388 }, { "epoch": 0.897648136835675, "grad_norm": 0.5429818034172058, "learning_rate": 1.281315607098238e-06, "loss": 4.157, "step": 29389 }, { "epoch": 0.8976786805131338, "grad_norm": 0.5341501235961914, "learning_rate": 1.2805575804478415e-06, "loss": 4.2109, "step": 29390 }, { "epoch": 0.8977092241905925, "grad_norm": 0.541393518447876, "learning_rate": 1.279799772194551e-06, "loss": 4.2637, "step": 29391 }, { "epoch": 0.8977397678680513, "grad_norm": 0.5403104424476624, "learning_rate": 1.2790421823453386e-06, "loss": 4.2414, "step": 29392 }, { "epoch": 0.8977703115455101, "grad_norm": 0.534355103969574, "learning_rate": 1.2782848109071793e-06, "loss": 4.1735, "step": 29393 }, { "epoch": 0.8978008552229688, "grad_norm": 0.5437164902687073, "learning_rate": 1.277527657887051e-06, "loss": 4.3034, "step": 29394 }, { "epoch": 0.8978313989004276, "grad_norm": 0.5359377264976501, "learning_rate": 1.2767707232919202e-06, "loss": 4.1996, "step": 29395 }, { "epoch": 0.8978619425778864, "grad_norm": 0.5381782054901123, "learning_rate": 1.2760140071287562e-06, "loss": 4.227, "step": 29396 }, { "epoch": 0.8978924862553451, "grad_norm": 0.5446101427078247, "learning_rate": 1.2752575094045343e-06, "loss": 4.2526, "step": 29397 }, { "epoch": 0.8979230299328039, "grad_norm": 0.5410175323486328, "learning_rate": 1.2745012301262126e-06, "loss": 4.2166, "step": 29398 }, { "epoch": 0.8979535736102626, "grad_norm": 0.5408188104629517, "learning_rate": 1.273745169300758e-06, "loss": 4.2876, "step": 29399 }, { "epoch": 0.8979841172877214, "grad_norm": 0.5409181118011475, "learning_rate": 1.2729893269351311e-06, "loss": 4.2139, "step": 29400 }, { "epoch": 0.8980146609651802, "grad_norm": 0.5344985127449036, "learning_rate": 1.272233703036288e-06, "loss": 4.1938, "step": 29401 }, { "epoch": 0.8980452046426389, "grad_norm": 0.5311101675033569, "learning_rate": 1.2714782976111895e-06, "loss": 4.2208, "step": 29402 }, { "epoch": 0.8980757483200977, "grad_norm": 0.5432251691818237, "learning_rate": 1.2707231106667883e-06, "loss": 4.3385, "step": 29403 }, { "epoch": 0.8981062919975565, "grad_norm": 0.5329123139381409, "learning_rate": 1.2699681422100402e-06, "loss": 4.335, "step": 29404 }, { "epoch": 0.8981368356750152, "grad_norm": 0.5307278037071228, "learning_rate": 1.2692133922479004e-06, "loss": 4.2391, "step": 29405 }, { "epoch": 0.898167379352474, "grad_norm": 0.547029972076416, "learning_rate": 1.268458860787311e-06, "loss": 4.2968, "step": 29406 }, { "epoch": 0.8981979230299328, "grad_norm": 0.5399024486541748, "learning_rate": 1.2677045478352217e-06, "loss": 4.2801, "step": 29407 }, { "epoch": 0.8982284667073915, "grad_norm": 0.5265435576438904, "learning_rate": 1.2669504533985799e-06, "loss": 4.2599, "step": 29408 }, { "epoch": 0.8982590103848503, "grad_norm": 0.52399080991745, "learning_rate": 1.2661965774843271e-06, "loss": 4.0179, "step": 29409 }, { "epoch": 0.8982895540623091, "grad_norm": 0.5306622385978699, "learning_rate": 1.2654429200994023e-06, "loss": 4.1331, "step": 29410 }, { "epoch": 0.8983200977397678, "grad_norm": 0.5245652794837952, "learning_rate": 1.2646894812507527e-06, "loss": 4.1712, "step": 29411 }, { "epoch": 0.8983506414172266, "grad_norm": 0.5350177884101868, "learning_rate": 1.2639362609453088e-06, "loss": 4.222, "step": 29412 }, { "epoch": 0.8983811850946855, "grad_norm": 0.541153609752655, "learning_rate": 1.2631832591900066e-06, "loss": 4.2306, "step": 29413 }, { "epoch": 0.8984117287721441, "grad_norm": 0.5401158332824707, "learning_rate": 1.26243047599178e-06, "loss": 4.1956, "step": 29414 }, { "epoch": 0.898442272449603, "grad_norm": 0.5437586307525635, "learning_rate": 1.2616779113575643e-06, "loss": 4.1508, "step": 29415 }, { "epoch": 0.8984728161270616, "grad_norm": 0.5386518239974976, "learning_rate": 1.2609255652942852e-06, "loss": 4.1999, "step": 29416 }, { "epoch": 0.8985033598045205, "grad_norm": 0.5430493354797363, "learning_rate": 1.2601734378088647e-06, "loss": 4.1992, "step": 29417 }, { "epoch": 0.8985339034819793, "grad_norm": 0.5374379754066467, "learning_rate": 1.259421528908236e-06, "loss": 4.1995, "step": 29418 }, { "epoch": 0.898564447159438, "grad_norm": 0.5351465940475464, "learning_rate": 1.258669838599319e-06, "loss": 4.2684, "step": 29419 }, { "epoch": 0.8985949908368968, "grad_norm": 0.5304794907569885, "learning_rate": 1.2579183668890354e-06, "loss": 4.2604, "step": 29420 }, { "epoch": 0.8986255345143556, "grad_norm": 0.5368799567222595, "learning_rate": 1.2571671137843021e-06, "loss": 4.1982, "step": 29421 }, { "epoch": 0.8986560781918143, "grad_norm": 0.5435047745704651, "learning_rate": 1.2564160792920444e-06, "loss": 4.3127, "step": 29422 }, { "epoch": 0.8986866218692731, "grad_norm": 0.5390270352363586, "learning_rate": 1.2556652634191646e-06, "loss": 4.2279, "step": 29423 }, { "epoch": 0.8987171655467319, "grad_norm": 0.5395887494087219, "learning_rate": 1.2549146661725852e-06, "loss": 4.2089, "step": 29424 }, { "epoch": 0.8987477092241906, "grad_norm": 0.5377487540245056, "learning_rate": 1.2541642875592202e-06, "loss": 4.2742, "step": 29425 }, { "epoch": 0.8987782529016494, "grad_norm": 0.5428380966186523, "learning_rate": 1.2534141275859668e-06, "loss": 4.1944, "step": 29426 }, { "epoch": 0.8988087965791082, "grad_norm": 0.5347914099693298, "learning_rate": 1.2526641862597388e-06, "loss": 4.2769, "step": 29427 }, { "epoch": 0.8988393402565669, "grad_norm": 0.5535741448402405, "learning_rate": 1.2519144635874475e-06, "loss": 4.2806, "step": 29428 }, { "epoch": 0.8988698839340257, "grad_norm": 0.5365418791770935, "learning_rate": 1.2511649595759846e-06, "loss": 4.2212, "step": 29429 }, { "epoch": 0.8989004276114845, "grad_norm": 0.5324082374572754, "learning_rate": 1.250415674232261e-06, "loss": 4.1981, "step": 29430 }, { "epoch": 0.8989309712889432, "grad_norm": 0.5375253558158875, "learning_rate": 1.2496666075631685e-06, "loss": 4.2603, "step": 29431 }, { "epoch": 0.898961514966402, "grad_norm": 0.5412420630455017, "learning_rate": 1.2489177595756046e-06, "loss": 4.1515, "step": 29432 }, { "epoch": 0.8989920586438607, "grad_norm": 0.5502234697341919, "learning_rate": 1.248169130276472e-06, "loss": 4.2074, "step": 29433 }, { "epoch": 0.8990226023213195, "grad_norm": 0.5292955040931702, "learning_rate": 1.247420719672651e-06, "loss": 4.2499, "step": 29434 }, { "epoch": 0.8990531459987783, "grad_norm": 0.540450930595398, "learning_rate": 1.2466725277710423e-06, "loss": 4.3125, "step": 29435 }, { "epoch": 0.899083689676237, "grad_norm": 0.5396162867546082, "learning_rate": 1.245924554578537e-06, "loss": 4.2775, "step": 29436 }, { "epoch": 0.8991142333536958, "grad_norm": 0.5406888723373413, "learning_rate": 1.2451768001020104e-06, "loss": 4.2864, "step": 29437 }, { "epoch": 0.8991447770311546, "grad_norm": 0.539100170135498, "learning_rate": 1.2444292643483569e-06, "loss": 4.285, "step": 29438 }, { "epoch": 0.8991753207086133, "grad_norm": 0.5424057245254517, "learning_rate": 1.2436819473244599e-06, "loss": 4.1776, "step": 29439 }, { "epoch": 0.8992058643860721, "grad_norm": 0.5363398194313049, "learning_rate": 1.2429348490371946e-06, "loss": 4.2822, "step": 29440 }, { "epoch": 0.8992364080635309, "grad_norm": 0.5423746109008789, "learning_rate": 1.2421879694934442e-06, "loss": 4.2394, "step": 29441 }, { "epoch": 0.8992669517409896, "grad_norm": 0.5482781529426575, "learning_rate": 1.2414413087000838e-06, "loss": 4.212, "step": 29442 }, { "epoch": 0.8992974954184484, "grad_norm": 0.5430704355239868, "learning_rate": 1.2406948666639883e-06, "loss": 4.3099, "step": 29443 }, { "epoch": 0.8993280390959072, "grad_norm": 0.5343769788742065, "learning_rate": 1.2399486433920305e-06, "loss": 4.2518, "step": 29444 }, { "epoch": 0.8993585827733659, "grad_norm": 0.533225953578949, "learning_rate": 1.239202638891085e-06, "loss": 4.2191, "step": 29445 }, { "epoch": 0.8993891264508247, "grad_norm": 0.5428805351257324, "learning_rate": 1.2384568531680157e-06, "loss": 4.1828, "step": 29446 }, { "epoch": 0.8994196701282835, "grad_norm": 0.527531623840332, "learning_rate": 1.2377112862296896e-06, "loss": 4.1146, "step": 29447 }, { "epoch": 0.8994502138057422, "grad_norm": 0.5428506731987, "learning_rate": 1.2369659380829763e-06, "loss": 4.2213, "step": 29448 }, { "epoch": 0.899480757483201, "grad_norm": 0.5457907319068909, "learning_rate": 1.236220808734731e-06, "loss": 4.206, "step": 29449 }, { "epoch": 0.8995113011606597, "grad_norm": 0.5347514152526855, "learning_rate": 1.2354758981918236e-06, "loss": 4.1753, "step": 29450 }, { "epoch": 0.8995418448381185, "grad_norm": 0.533555269241333, "learning_rate": 1.234731206461104e-06, "loss": 4.1886, "step": 29451 }, { "epoch": 0.8995723885155773, "grad_norm": 0.5444450974464417, "learning_rate": 1.2339867335494332e-06, "loss": 4.2506, "step": 29452 }, { "epoch": 0.899602932193036, "grad_norm": 0.5483982563018799, "learning_rate": 1.2332424794636698e-06, "loss": 4.3643, "step": 29453 }, { "epoch": 0.8996334758704948, "grad_norm": 0.55143803358078, "learning_rate": 1.2324984442106585e-06, "loss": 4.3322, "step": 29454 }, { "epoch": 0.8996640195479536, "grad_norm": 0.5323114395141602, "learning_rate": 1.231754627797252e-06, "loss": 4.2471, "step": 29455 }, { "epoch": 0.8996945632254123, "grad_norm": 0.5399729609489441, "learning_rate": 1.2310110302303084e-06, "loss": 4.2413, "step": 29456 }, { "epoch": 0.8997251069028711, "grad_norm": 0.5404921174049377, "learning_rate": 1.2302676515166617e-06, "loss": 4.2321, "step": 29457 }, { "epoch": 0.8997556505803299, "grad_norm": 0.5512617826461792, "learning_rate": 1.2295244916631616e-06, "loss": 4.2163, "step": 29458 }, { "epoch": 0.8997861942577886, "grad_norm": 0.5254191756248474, "learning_rate": 1.2287815506766554e-06, "loss": 4.2468, "step": 29459 }, { "epoch": 0.8998167379352474, "grad_norm": 0.537412703037262, "learning_rate": 1.2280388285639738e-06, "loss": 4.1412, "step": 29460 }, { "epoch": 0.8998472816127062, "grad_norm": 0.5397601127624512, "learning_rate": 1.2272963253319668e-06, "loss": 4.2147, "step": 29461 }, { "epoch": 0.8998778252901649, "grad_norm": 0.5361614227294922, "learning_rate": 1.2265540409874627e-06, "loss": 4.3339, "step": 29462 }, { "epoch": 0.8999083689676237, "grad_norm": 0.5419182777404785, "learning_rate": 1.2258119755372998e-06, "loss": 4.2884, "step": 29463 }, { "epoch": 0.8999389126450825, "grad_norm": 0.5382839441299438, "learning_rate": 1.2250701289883066e-06, "loss": 4.222, "step": 29464 }, { "epoch": 0.8999694563225412, "grad_norm": 0.5282162427902222, "learning_rate": 1.2243285013473189e-06, "loss": 4.2701, "step": 29465 }, { "epoch": 0.9, "grad_norm": 0.5494298338890076, "learning_rate": 1.2235870926211619e-06, "loss": 4.3791, "step": 29466 }, { "epoch": 0.9000305436774587, "grad_norm": 0.5373774170875549, "learning_rate": 1.2228459028166662e-06, "loss": 4.2598, "step": 29467 }, { "epoch": 0.9000610873549175, "grad_norm": 0.5304580926895142, "learning_rate": 1.2221049319406486e-06, "loss": 4.3021, "step": 29468 }, { "epoch": 0.9000916310323763, "grad_norm": 0.5379312634468079, "learning_rate": 1.221364179999937e-06, "loss": 4.2951, "step": 29469 }, { "epoch": 0.900122174709835, "grad_norm": 0.5450813174247742, "learning_rate": 1.2206236470013537e-06, "loss": 4.2155, "step": 29470 }, { "epoch": 0.9001527183872938, "grad_norm": 0.5396101474761963, "learning_rate": 1.219883332951713e-06, "loss": 4.2545, "step": 29471 }, { "epoch": 0.9001832620647526, "grad_norm": 0.5337061882019043, "learning_rate": 1.219143237857831e-06, "loss": 4.224, "step": 29472 }, { "epoch": 0.9002138057422113, "grad_norm": 0.5310841798782349, "learning_rate": 1.2184033617265278e-06, "loss": 4.2347, "step": 29473 }, { "epoch": 0.9002443494196701, "grad_norm": 0.5387784838676453, "learning_rate": 1.217663704564609e-06, "loss": 4.209, "step": 29474 }, { "epoch": 0.9002748930971289, "grad_norm": 0.5433221459388733, "learning_rate": 1.2169242663788883e-06, "loss": 4.3654, "step": 29475 }, { "epoch": 0.9003054367745876, "grad_norm": 0.545941948890686, "learning_rate": 1.216185047176177e-06, "loss": 4.3055, "step": 29476 }, { "epoch": 0.9003359804520464, "grad_norm": 0.5307426452636719, "learning_rate": 1.2154460469632812e-06, "loss": 4.2605, "step": 29477 }, { "epoch": 0.9003665241295052, "grad_norm": 0.5477779507637024, "learning_rate": 1.214707265746995e-06, "loss": 4.2977, "step": 29478 }, { "epoch": 0.9003970678069639, "grad_norm": 0.5356569886207581, "learning_rate": 1.2139687035341352e-06, "loss": 4.2216, "step": 29479 }, { "epoch": 0.9004276114844227, "grad_norm": 0.5340792536735535, "learning_rate": 1.2132303603314881e-06, "loss": 4.24, "step": 29480 }, { "epoch": 0.9004581551618815, "grad_norm": 0.5387305617332458, "learning_rate": 1.2124922361458623e-06, "loss": 4.3474, "step": 29481 }, { "epoch": 0.9004886988393402, "grad_norm": 0.5353055596351624, "learning_rate": 1.2117543309840523e-06, "loss": 4.211, "step": 29482 }, { "epoch": 0.900519242516799, "grad_norm": 0.5609932541847229, "learning_rate": 1.2110166448528471e-06, "loss": 4.2496, "step": 29483 }, { "epoch": 0.9005497861942577, "grad_norm": 0.5473545789718628, "learning_rate": 1.2102791777590466e-06, "loss": 4.1891, "step": 29484 }, { "epoch": 0.9005803298717165, "grad_norm": 0.5477701425552368, "learning_rate": 1.2095419297094345e-06, "loss": 4.2513, "step": 29485 }, { "epoch": 0.9006108735491754, "grad_norm": 0.5400740504264832, "learning_rate": 1.2088049007108027e-06, "loss": 4.2371, "step": 29486 }, { "epoch": 0.900641417226634, "grad_norm": 0.5337699055671692, "learning_rate": 1.208068090769937e-06, "loss": 4.2514, "step": 29487 }, { "epoch": 0.9006719609040928, "grad_norm": 0.5338168740272522, "learning_rate": 1.2073314998936186e-06, "loss": 4.2603, "step": 29488 }, { "epoch": 0.9007025045815517, "grad_norm": 0.5504452586174011, "learning_rate": 1.2065951280886334e-06, "loss": 4.2871, "step": 29489 }, { "epoch": 0.9007330482590103, "grad_norm": 0.5336157083511353, "learning_rate": 1.2058589753617622e-06, "loss": 4.339, "step": 29490 }, { "epoch": 0.9007635919364692, "grad_norm": 0.525484025478363, "learning_rate": 1.2051230417197772e-06, "loss": 4.2109, "step": 29491 }, { "epoch": 0.900794135613928, "grad_norm": 0.5415917038917542, "learning_rate": 1.204387327169465e-06, "loss": 4.2798, "step": 29492 }, { "epoch": 0.9008246792913867, "grad_norm": 0.5435121059417725, "learning_rate": 1.2036518317175865e-06, "loss": 4.3235, "step": 29493 }, { "epoch": 0.9008552229688455, "grad_norm": 0.5311324596405029, "learning_rate": 1.2029165553709254e-06, "loss": 4.2024, "step": 29494 }, { "epoch": 0.9008857666463043, "grad_norm": 0.5370587110519409, "learning_rate": 1.2021814981362428e-06, "loss": 4.2515, "step": 29495 }, { "epoch": 0.900916310323763, "grad_norm": 0.5287290811538696, "learning_rate": 1.2014466600203139e-06, "loss": 4.2082, "step": 29496 }, { "epoch": 0.9009468540012218, "grad_norm": 0.5265693664550781, "learning_rate": 1.2007120410299e-06, "loss": 4.1714, "step": 29497 }, { "epoch": 0.9009773976786805, "grad_norm": 0.5383579134941101, "learning_rate": 1.1999776411717677e-06, "loss": 4.2737, "step": 29498 }, { "epoch": 0.9010079413561393, "grad_norm": 0.5358138680458069, "learning_rate": 1.1992434604526758e-06, "loss": 4.2274, "step": 29499 }, { "epoch": 0.9010384850335981, "grad_norm": 0.5337955951690674, "learning_rate": 1.1985094988793856e-06, "loss": 4.1989, "step": 29500 }, { "epoch": 0.9010690287110568, "grad_norm": 0.5280449390411377, "learning_rate": 1.1977757564586606e-06, "loss": 4.0713, "step": 29501 }, { "epoch": 0.9010995723885156, "grad_norm": 0.5460107922554016, "learning_rate": 1.1970422331972487e-06, "loss": 4.2175, "step": 29502 }, { "epoch": 0.9011301160659744, "grad_norm": 0.5403152704238892, "learning_rate": 1.1963089291019052e-06, "loss": 4.1903, "step": 29503 }, { "epoch": 0.9011606597434331, "grad_norm": 0.541964590549469, "learning_rate": 1.1955758441793892e-06, "loss": 4.2097, "step": 29504 }, { "epoch": 0.9011912034208919, "grad_norm": 0.5311426520347595, "learning_rate": 1.1948429784364418e-06, "loss": 4.2179, "step": 29505 }, { "epoch": 0.9012217470983507, "grad_norm": 0.5335279107093811, "learning_rate": 1.1941103318798163e-06, "loss": 4.2174, "step": 29506 }, { "epoch": 0.9012522907758094, "grad_norm": 0.5351047515869141, "learning_rate": 1.1933779045162575e-06, "loss": 4.1796, "step": 29507 }, { "epoch": 0.9012828344532682, "grad_norm": 0.5470022559165955, "learning_rate": 1.1926456963525067e-06, "loss": 4.1789, "step": 29508 }, { "epoch": 0.901313378130727, "grad_norm": 0.5355365872383118, "learning_rate": 1.191913707395309e-06, "loss": 4.2623, "step": 29509 }, { "epoch": 0.9013439218081857, "grad_norm": 0.5311266779899597, "learning_rate": 1.1911819376514032e-06, "loss": 4.1916, "step": 29510 }, { "epoch": 0.9013744654856445, "grad_norm": 0.5470030903816223, "learning_rate": 1.1904503871275257e-06, "loss": 4.2265, "step": 29511 }, { "epoch": 0.9014050091631033, "grad_norm": 0.5401369333267212, "learning_rate": 1.18971905583041e-06, "loss": 4.2739, "step": 29512 }, { "epoch": 0.901435552840562, "grad_norm": 0.5385494828224182, "learning_rate": 1.1889879437667977e-06, "loss": 4.253, "step": 29513 }, { "epoch": 0.9014660965180208, "grad_norm": 0.5320092439651489, "learning_rate": 1.1882570509434143e-06, "loss": 4.2103, "step": 29514 }, { "epoch": 0.9014966401954795, "grad_norm": 0.5382282137870789, "learning_rate": 1.1875263773669903e-06, "loss": 4.1246, "step": 29515 }, { "epoch": 0.9015271838729383, "grad_norm": 0.5504067540168762, "learning_rate": 1.1867959230442538e-06, "loss": 4.3075, "step": 29516 }, { "epoch": 0.9015577275503971, "grad_norm": 0.5469108819961548, "learning_rate": 1.1860656879819298e-06, "loss": 4.2073, "step": 29517 }, { "epoch": 0.9015882712278558, "grad_norm": 0.5342901349067688, "learning_rate": 1.1853356721867465e-06, "loss": 4.0742, "step": 29518 }, { "epoch": 0.9016188149053146, "grad_norm": 0.5400019884109497, "learning_rate": 1.1846058756654177e-06, "loss": 4.1995, "step": 29519 }, { "epoch": 0.9016493585827734, "grad_norm": 0.5355473160743713, "learning_rate": 1.1838762984246687e-06, "loss": 4.283, "step": 29520 }, { "epoch": 0.9016799022602321, "grad_norm": 0.5448489785194397, "learning_rate": 1.1831469404712192e-06, "loss": 4.2725, "step": 29521 }, { "epoch": 0.9017104459376909, "grad_norm": 0.5281271934509277, "learning_rate": 1.1824178018117777e-06, "loss": 4.1362, "step": 29522 }, { "epoch": 0.9017409896151497, "grad_norm": 0.5373484492301941, "learning_rate": 1.1816888824530637e-06, "loss": 4.2001, "step": 29523 }, { "epoch": 0.9017715332926084, "grad_norm": 0.5303577184677124, "learning_rate": 1.180960182401783e-06, "loss": 4.2228, "step": 29524 }, { "epoch": 0.9018020769700672, "grad_norm": 0.5390422940254211, "learning_rate": 1.1802317016646524e-06, "loss": 4.1846, "step": 29525 }, { "epoch": 0.901832620647526, "grad_norm": 0.5429186820983887, "learning_rate": 1.1795034402483724e-06, "loss": 4.2949, "step": 29526 }, { "epoch": 0.9018631643249847, "grad_norm": 0.5421867966651917, "learning_rate": 1.1787753981596538e-06, "loss": 4.3218, "step": 29527 }, { "epoch": 0.9018937080024435, "grad_norm": 0.5326561331748962, "learning_rate": 1.1780475754051946e-06, "loss": 4.2021, "step": 29528 }, { "epoch": 0.9019242516799023, "grad_norm": 0.5375156998634338, "learning_rate": 1.1773199719916999e-06, "loss": 4.2254, "step": 29529 }, { "epoch": 0.901954795357361, "grad_norm": 0.5293070077896118, "learning_rate": 1.1765925879258705e-06, "loss": 4.103, "step": 29530 }, { "epoch": 0.9019853390348198, "grad_norm": 0.5402916669845581, "learning_rate": 1.1758654232144006e-06, "loss": 4.2621, "step": 29531 }, { "epoch": 0.9020158827122785, "grad_norm": 0.548827588558197, "learning_rate": 1.175138477863988e-06, "loss": 4.2384, "step": 29532 }, { "epoch": 0.9020464263897373, "grad_norm": 0.5407500863075256, "learning_rate": 1.1744117518813241e-06, "loss": 4.3132, "step": 29533 }, { "epoch": 0.9020769700671961, "grad_norm": 0.5363165736198425, "learning_rate": 1.1736852452731012e-06, "loss": 4.2708, "step": 29534 }, { "epoch": 0.9021075137446548, "grad_norm": 0.5411479473114014, "learning_rate": 1.172958958046011e-06, "loss": 4.2815, "step": 29535 }, { "epoch": 0.9021380574221136, "grad_norm": 0.5358153581619263, "learning_rate": 1.1722328902067341e-06, "loss": 4.2269, "step": 29536 }, { "epoch": 0.9021686010995724, "grad_norm": 0.533112645149231, "learning_rate": 1.17150704176196e-06, "loss": 4.2664, "step": 29537 }, { "epoch": 0.9021991447770311, "grad_norm": 0.5374063849449158, "learning_rate": 1.1707814127183748e-06, "loss": 4.1992, "step": 29538 }, { "epoch": 0.9022296884544899, "grad_norm": 0.5383467674255371, "learning_rate": 1.1700560030826562e-06, "loss": 4.2456, "step": 29539 }, { "epoch": 0.9022602321319487, "grad_norm": 0.5503168106079102, "learning_rate": 1.1693308128614856e-06, "loss": 4.2594, "step": 29540 }, { "epoch": 0.9022907758094074, "grad_norm": 0.538203239440918, "learning_rate": 1.1686058420615403e-06, "loss": 4.3273, "step": 29541 }, { "epoch": 0.9023213194868662, "grad_norm": 0.5348511338233948, "learning_rate": 1.1678810906894877e-06, "loss": 4.2072, "step": 29542 }, { "epoch": 0.902351863164325, "grad_norm": 0.54254549741745, "learning_rate": 1.1671565587520083e-06, "loss": 4.3259, "step": 29543 }, { "epoch": 0.9023824068417837, "grad_norm": 0.5238407254219055, "learning_rate": 1.1664322462557775e-06, "loss": 4.2481, "step": 29544 }, { "epoch": 0.9024129505192425, "grad_norm": 0.5466111302375793, "learning_rate": 1.1657081532074538e-06, "loss": 4.211, "step": 29545 }, { "epoch": 0.9024434941967013, "grad_norm": 0.5390013456344604, "learning_rate": 1.1649842796137096e-06, "loss": 4.2555, "step": 29546 }, { "epoch": 0.90247403787416, "grad_norm": 0.5419100522994995, "learning_rate": 1.1642606254812145e-06, "loss": 4.1402, "step": 29547 }, { "epoch": 0.9025045815516188, "grad_norm": 0.5383071899414062, "learning_rate": 1.1635371908166215e-06, "loss": 4.2536, "step": 29548 }, { "epoch": 0.9025351252290775, "grad_norm": 0.5370238423347473, "learning_rate": 1.1628139756266003e-06, "loss": 4.273, "step": 29549 }, { "epoch": 0.9025656689065363, "grad_norm": 0.5367551445960999, "learning_rate": 1.162090979917807e-06, "loss": 4.268, "step": 29550 }, { "epoch": 0.9025962125839951, "grad_norm": 0.535584032535553, "learning_rate": 1.1613682036968942e-06, "loss": 4.271, "step": 29551 }, { "epoch": 0.9026267562614538, "grad_norm": 0.5424248576164246, "learning_rate": 1.1606456469705263e-06, "loss": 4.264, "step": 29552 }, { "epoch": 0.9026572999389126, "grad_norm": 0.5306806564331055, "learning_rate": 1.1599233097453478e-06, "loss": 4.2528, "step": 29553 }, { "epoch": 0.9026878436163714, "grad_norm": 0.5328992605209351, "learning_rate": 1.1592011920280115e-06, "loss": 4.2989, "step": 29554 }, { "epoch": 0.9027183872938301, "grad_norm": 0.5401114225387573, "learning_rate": 1.158479293825171e-06, "loss": 4.2728, "step": 29555 }, { "epoch": 0.9027489309712889, "grad_norm": 0.5333418250083923, "learning_rate": 1.1577576151434705e-06, "loss": 4.2704, "step": 29556 }, { "epoch": 0.9027794746487477, "grad_norm": 0.5627045035362244, "learning_rate": 1.157036155989552e-06, "loss": 4.2726, "step": 29557 }, { "epoch": 0.9028100183262064, "grad_norm": 0.5361441373825073, "learning_rate": 1.1563149163700604e-06, "loss": 4.2713, "step": 29558 }, { "epoch": 0.9028405620036652, "grad_norm": 0.5373868346214294, "learning_rate": 1.1555938962916346e-06, "loss": 4.2065, "step": 29559 }, { "epoch": 0.902871105681124, "grad_norm": 0.5294935703277588, "learning_rate": 1.1548730957609167e-06, "loss": 4.2427, "step": 29560 }, { "epoch": 0.9029016493585827, "grad_norm": 0.5773046612739563, "learning_rate": 1.1541525147845456e-06, "loss": 4.3166, "step": 29561 }, { "epoch": 0.9029321930360416, "grad_norm": 0.5352131128311157, "learning_rate": 1.1534321533691493e-06, "loss": 4.2518, "step": 29562 }, { "epoch": 0.9029627367135004, "grad_norm": 0.5322648286819458, "learning_rate": 1.152712011521362e-06, "loss": 4.2088, "step": 29563 }, { "epoch": 0.902993280390959, "grad_norm": 0.5307580232620239, "learning_rate": 1.1519920892478191e-06, "loss": 4.2868, "step": 29564 }, { "epoch": 0.9030238240684179, "grad_norm": 0.533801794052124, "learning_rate": 1.1512723865551468e-06, "loss": 4.2715, "step": 29565 }, { "epoch": 0.9030543677458766, "grad_norm": 0.5340440273284912, "learning_rate": 1.1505529034499723e-06, "loss": 4.271, "step": 29566 }, { "epoch": 0.9030849114233354, "grad_norm": 0.5419012308120728, "learning_rate": 1.1498336399389158e-06, "loss": 4.2022, "step": 29567 }, { "epoch": 0.9031154551007942, "grad_norm": 0.5402578711509705, "learning_rate": 1.1491145960286025e-06, "loss": 4.2641, "step": 29568 }, { "epoch": 0.9031459987782529, "grad_norm": 0.5453734397888184, "learning_rate": 1.1483957717256604e-06, "loss": 4.2341, "step": 29569 }, { "epoch": 0.9031765424557117, "grad_norm": 0.5411208868026733, "learning_rate": 1.1476771670366982e-06, "loss": 4.2682, "step": 29570 }, { "epoch": 0.9032070861331705, "grad_norm": 0.5348100066184998, "learning_rate": 1.146958781968338e-06, "loss": 4.2607, "step": 29571 }, { "epoch": 0.9032376298106292, "grad_norm": 0.5435726046562195, "learning_rate": 1.1462406165271887e-06, "loss": 4.1592, "step": 29572 }, { "epoch": 0.903268173488088, "grad_norm": 0.542894184589386, "learning_rate": 1.1455226707198702e-06, "loss": 4.1741, "step": 29573 }, { "epoch": 0.9032987171655468, "grad_norm": 0.5321255326271057, "learning_rate": 1.1448049445529852e-06, "loss": 4.2002, "step": 29574 }, { "epoch": 0.9033292608430055, "grad_norm": 0.5449292659759521, "learning_rate": 1.1440874380331507e-06, "loss": 4.3124, "step": 29575 }, { "epoch": 0.9033598045204643, "grad_norm": 0.5353059768676758, "learning_rate": 1.1433701511669641e-06, "loss": 4.2586, "step": 29576 }, { "epoch": 0.9033903481979231, "grad_norm": 0.5257336497306824, "learning_rate": 1.1426530839610345e-06, "loss": 4.2123, "step": 29577 }, { "epoch": 0.9034208918753818, "grad_norm": 0.537246823310852, "learning_rate": 1.1419362364219672e-06, "loss": 4.2671, "step": 29578 }, { "epoch": 0.9034514355528406, "grad_norm": 0.5359526872634888, "learning_rate": 1.141219608556357e-06, "loss": 4.1081, "step": 29579 }, { "epoch": 0.9034819792302994, "grad_norm": 0.5370513796806335, "learning_rate": 1.1405032003708044e-06, "loss": 4.2583, "step": 29580 }, { "epoch": 0.9035125229077581, "grad_norm": 0.5432626008987427, "learning_rate": 1.1397870118719123e-06, "loss": 4.1546, "step": 29581 }, { "epoch": 0.9035430665852169, "grad_norm": 0.5487577319145203, "learning_rate": 1.1390710430662616e-06, "loss": 4.2833, "step": 29582 }, { "epoch": 0.9035736102626756, "grad_norm": 0.5485790371894836, "learning_rate": 1.138355293960458e-06, "loss": 4.298, "step": 29583 }, { "epoch": 0.9036041539401344, "grad_norm": 0.544209361076355, "learning_rate": 1.1376397645610799e-06, "loss": 4.3451, "step": 29584 }, { "epoch": 0.9036346976175932, "grad_norm": 0.5384740233421326, "learning_rate": 1.1369244548747244e-06, "loss": 4.2456, "step": 29585 }, { "epoch": 0.9036652412950519, "grad_norm": 0.5303200483322144, "learning_rate": 1.1362093649079752e-06, "loss": 4.2595, "step": 29586 }, { "epoch": 0.9036957849725107, "grad_norm": 0.5401589870452881, "learning_rate": 1.1354944946674161e-06, "loss": 4.098, "step": 29587 }, { "epoch": 0.9037263286499695, "grad_norm": 0.5393297672271729, "learning_rate": 1.134779844159628e-06, "loss": 4.237, "step": 29588 }, { "epoch": 0.9037568723274282, "grad_norm": 0.5295404195785522, "learning_rate": 1.1340654133911914e-06, "loss": 4.1242, "step": 29589 }, { "epoch": 0.903787416004887, "grad_norm": 0.539840042591095, "learning_rate": 1.133351202368685e-06, "loss": 4.1869, "step": 29590 }, { "epoch": 0.9038179596823458, "grad_norm": 0.5268235802650452, "learning_rate": 1.132637211098686e-06, "loss": 4.252, "step": 29591 }, { "epoch": 0.9038485033598045, "grad_norm": 0.5372026562690735, "learning_rate": 1.1319234395877675e-06, "loss": 4.2654, "step": 29592 }, { "epoch": 0.9038790470372633, "grad_norm": 0.5420426726341248, "learning_rate": 1.131209887842502e-06, "loss": 4.265, "step": 29593 }, { "epoch": 0.9039095907147221, "grad_norm": 0.5411059260368347, "learning_rate": 1.1304965558694564e-06, "loss": 4.1823, "step": 29594 }, { "epoch": 0.9039401343921808, "grad_norm": 0.552197277545929, "learning_rate": 1.129783443675206e-06, "loss": 4.3137, "step": 29595 }, { "epoch": 0.9039706780696396, "grad_norm": 0.5425721406936646, "learning_rate": 1.1290705512663092e-06, "loss": 4.3115, "step": 29596 }, { "epoch": 0.9040012217470984, "grad_norm": 0.5318388938903809, "learning_rate": 1.128357878649333e-06, "loss": 4.3163, "step": 29597 }, { "epoch": 0.9040317654245571, "grad_norm": 0.5388373136520386, "learning_rate": 1.1276454258308423e-06, "loss": 4.2301, "step": 29598 }, { "epoch": 0.9040623091020159, "grad_norm": 0.5452359914779663, "learning_rate": 1.1269331928173922e-06, "loss": 4.3577, "step": 29599 }, { "epoch": 0.9040928527794746, "grad_norm": 0.5602850317955017, "learning_rate": 1.1262211796155441e-06, "loss": 4.2645, "step": 29600 }, { "epoch": 0.9041233964569334, "grad_norm": 0.5429000854492188, "learning_rate": 1.1255093862318488e-06, "loss": 4.1244, "step": 29601 }, { "epoch": 0.9041539401343922, "grad_norm": 0.5326734185218811, "learning_rate": 1.1247978126728676e-06, "loss": 4.3135, "step": 29602 }, { "epoch": 0.9041844838118509, "grad_norm": 0.5423542857170105, "learning_rate": 1.124086458945145e-06, "loss": 4.2849, "step": 29603 }, { "epoch": 0.9042150274893097, "grad_norm": 0.5464478731155396, "learning_rate": 1.123375325055237e-06, "loss": 4.2158, "step": 29604 }, { "epoch": 0.9042455711667685, "grad_norm": 0.5437322854995728, "learning_rate": 1.1226644110096856e-06, "loss": 4.1921, "step": 29605 }, { "epoch": 0.9042761148442272, "grad_norm": 0.54707932472229, "learning_rate": 1.121953716815044e-06, "loss": 4.2679, "step": 29606 }, { "epoch": 0.904306658521686, "grad_norm": 0.527041494846344, "learning_rate": 1.1212432424778457e-06, "loss": 4.2239, "step": 29607 }, { "epoch": 0.9043372021991448, "grad_norm": 0.5453523993492126, "learning_rate": 1.1205329880046383e-06, "loss": 4.1721, "step": 29608 }, { "epoch": 0.9043677458766035, "grad_norm": 0.5493337512016296, "learning_rate": 1.1198229534019667e-06, "loss": 4.2754, "step": 29609 }, { "epoch": 0.9043982895540623, "grad_norm": 0.5453200936317444, "learning_rate": 1.1191131386763588e-06, "loss": 4.2647, "step": 29610 }, { "epoch": 0.9044288332315211, "grad_norm": 0.5348610281944275, "learning_rate": 1.1184035438343537e-06, "loss": 4.2006, "step": 29611 }, { "epoch": 0.9044593769089798, "grad_norm": 0.5274361968040466, "learning_rate": 1.117694168882491e-06, "loss": 4.1981, "step": 29612 }, { "epoch": 0.9044899205864386, "grad_norm": 0.5399001240730286, "learning_rate": 1.116985013827293e-06, "loss": 4.212, "step": 29613 }, { "epoch": 0.9045204642638974, "grad_norm": 0.5407041311264038, "learning_rate": 1.1162760786752935e-06, "loss": 4.3271, "step": 29614 }, { "epoch": 0.9045510079413561, "grad_norm": 0.5313969254493713, "learning_rate": 1.1155673634330232e-06, "loss": 4.205, "step": 29615 }, { "epoch": 0.9045815516188149, "grad_norm": 0.5604315996170044, "learning_rate": 1.1148588681069993e-06, "loss": 4.1664, "step": 29616 }, { "epoch": 0.9046120952962736, "grad_norm": 0.5259791016578674, "learning_rate": 1.1141505927037554e-06, "loss": 4.2123, "step": 29617 }, { "epoch": 0.9046426389737324, "grad_norm": 0.5317436456680298, "learning_rate": 1.1134425372298058e-06, "loss": 4.2445, "step": 29618 }, { "epoch": 0.9046731826511912, "grad_norm": 0.5440040826797485, "learning_rate": 1.1127347016916729e-06, "loss": 4.3111, "step": 29619 }, { "epoch": 0.9047037263286499, "grad_norm": 0.5411386489868164, "learning_rate": 1.1120270860958737e-06, "loss": 4.2501, "step": 29620 }, { "epoch": 0.9047342700061087, "grad_norm": 0.540669858455658, "learning_rate": 1.1113196904489197e-06, "loss": 4.2331, "step": 29621 }, { "epoch": 0.9047648136835675, "grad_norm": 0.5485720038414001, "learning_rate": 1.1106125147573282e-06, "loss": 4.2714, "step": 29622 }, { "epoch": 0.9047953573610262, "grad_norm": 0.5344053506851196, "learning_rate": 1.109905559027616e-06, "loss": 4.1959, "step": 29623 }, { "epoch": 0.904825901038485, "grad_norm": 0.5381012558937073, "learning_rate": 1.1091988232662802e-06, "loss": 4.2057, "step": 29624 }, { "epoch": 0.9048564447159438, "grad_norm": 0.5222718715667725, "learning_rate": 1.1084923074798332e-06, "loss": 4.1683, "step": 29625 }, { "epoch": 0.9048869883934025, "grad_norm": 0.5445924997329712, "learning_rate": 1.1077860116747856e-06, "loss": 4.0741, "step": 29626 }, { "epoch": 0.9049175320708613, "grad_norm": 0.5400240421295166, "learning_rate": 1.1070799358576328e-06, "loss": 4.2446, "step": 29627 }, { "epoch": 0.9049480757483201, "grad_norm": 0.541978120803833, "learning_rate": 1.1063740800348805e-06, "loss": 4.2823, "step": 29628 }, { "epoch": 0.9049786194257788, "grad_norm": 0.5509395003318787, "learning_rate": 1.1056684442130317e-06, "loss": 4.0902, "step": 29629 }, { "epoch": 0.9050091631032376, "grad_norm": 0.5631933212280273, "learning_rate": 1.104963028398573e-06, "loss": 4.2294, "step": 29630 }, { "epoch": 0.9050397067806965, "grad_norm": 0.5431158542633057, "learning_rate": 1.1042578325980047e-06, "loss": 4.1365, "step": 29631 }, { "epoch": 0.9050702504581551, "grad_norm": 0.5269982218742371, "learning_rate": 1.1035528568178245e-06, "loss": 4.1653, "step": 29632 }, { "epoch": 0.905100794135614, "grad_norm": 0.5420429110527039, "learning_rate": 1.1028481010645214e-06, "loss": 4.2687, "step": 29633 }, { "epoch": 0.9051313378130726, "grad_norm": 0.5371055603027344, "learning_rate": 1.1021435653445766e-06, "loss": 4.2256, "step": 29634 }, { "epoch": 0.9051618814905315, "grad_norm": 0.5412259101867676, "learning_rate": 1.1014392496644877e-06, "loss": 4.2945, "step": 29635 }, { "epoch": 0.9051924251679903, "grad_norm": 0.5401274561882019, "learning_rate": 1.1007351540307326e-06, "loss": 4.2138, "step": 29636 }, { "epoch": 0.905222968845449, "grad_norm": 0.5365917682647705, "learning_rate": 1.100031278449798e-06, "loss": 4.3335, "step": 29637 }, { "epoch": 0.9052535125229078, "grad_norm": 0.5306866765022278, "learning_rate": 1.0993276229281618e-06, "loss": 4.2729, "step": 29638 }, { "epoch": 0.9052840562003666, "grad_norm": 0.5433425307273865, "learning_rate": 1.0986241874723053e-06, "loss": 4.2666, "step": 29639 }, { "epoch": 0.9053145998778253, "grad_norm": 0.5362576842308044, "learning_rate": 1.0979209720887063e-06, "loss": 4.329, "step": 29640 }, { "epoch": 0.9053451435552841, "grad_norm": 0.5322737693786621, "learning_rate": 1.0972179767838348e-06, "loss": 4.2627, "step": 29641 }, { "epoch": 0.9053756872327429, "grad_norm": 0.5403699278831482, "learning_rate": 1.0965152015641688e-06, "loss": 4.3023, "step": 29642 }, { "epoch": 0.9054062309102016, "grad_norm": 0.5461094975471497, "learning_rate": 1.0958126464361784e-06, "loss": 4.2575, "step": 29643 }, { "epoch": 0.9054367745876604, "grad_norm": 0.5496639013290405, "learning_rate": 1.0951103114063305e-06, "loss": 4.3752, "step": 29644 }, { "epoch": 0.9054673182651192, "grad_norm": 0.5338779091835022, "learning_rate": 1.094408196481092e-06, "loss": 4.0419, "step": 29645 }, { "epoch": 0.9054978619425779, "grad_norm": 0.5338245630264282, "learning_rate": 1.0937063016669301e-06, "loss": 4.236, "step": 29646 }, { "epoch": 0.9055284056200367, "grad_norm": 0.5371598601341248, "learning_rate": 1.0930046269703038e-06, "loss": 4.2377, "step": 29647 }, { "epoch": 0.9055589492974954, "grad_norm": 0.5341405868530273, "learning_rate": 1.0923031723976769e-06, "loss": 4.2073, "step": 29648 }, { "epoch": 0.9055894929749542, "grad_norm": 0.5387265682220459, "learning_rate": 1.0916019379555055e-06, "loss": 4.145, "step": 29649 }, { "epoch": 0.905620036652413, "grad_norm": 0.5398678779602051, "learning_rate": 1.090900923650251e-06, "loss": 4.3039, "step": 29650 }, { "epoch": 0.9056505803298717, "grad_norm": 0.532745361328125, "learning_rate": 1.0902001294883612e-06, "loss": 4.0337, "step": 29651 }, { "epoch": 0.9056811240073305, "grad_norm": 0.5426315665245056, "learning_rate": 1.0894995554762922e-06, "loss": 4.2518, "step": 29652 }, { "epoch": 0.9057116676847893, "grad_norm": 0.5409258008003235, "learning_rate": 1.088799201620494e-06, "loss": 4.2261, "step": 29653 }, { "epoch": 0.905742211362248, "grad_norm": 0.5657207369804382, "learning_rate": 1.0880990679274171e-06, "loss": 4.2593, "step": 29654 }, { "epoch": 0.9057727550397068, "grad_norm": 0.5421237349510193, "learning_rate": 1.087399154403504e-06, "loss": 4.3195, "step": 29655 }, { "epoch": 0.9058032987171656, "grad_norm": 0.5317585468292236, "learning_rate": 1.0866994610552017e-06, "loss": 4.2483, "step": 29656 }, { "epoch": 0.9058338423946243, "grad_norm": 0.5388652086257935, "learning_rate": 1.0859999878889582e-06, "loss": 4.2558, "step": 29657 }, { "epoch": 0.9058643860720831, "grad_norm": 0.5446824431419373, "learning_rate": 1.0853007349112015e-06, "loss": 4.2368, "step": 29658 }, { "epoch": 0.9058949297495419, "grad_norm": 0.5416761040687561, "learning_rate": 1.0846017021283767e-06, "loss": 4.2472, "step": 29659 }, { "epoch": 0.9059254734270006, "grad_norm": 0.5342644453048706, "learning_rate": 1.0839028895469255e-06, "loss": 4.1739, "step": 29660 }, { "epoch": 0.9059560171044594, "grad_norm": 0.5435739755630493, "learning_rate": 1.0832042971732708e-06, "loss": 4.3953, "step": 29661 }, { "epoch": 0.9059865607819182, "grad_norm": 0.5548791885375977, "learning_rate": 1.082505925013852e-06, "loss": 4.2727, "step": 29662 }, { "epoch": 0.9060171044593769, "grad_norm": 0.5470574498176575, "learning_rate": 1.0818077730751025e-06, "loss": 4.2471, "step": 29663 }, { "epoch": 0.9060476481368357, "grad_norm": 0.5407088994979858, "learning_rate": 1.0811098413634425e-06, "loss": 4.3177, "step": 29664 }, { "epoch": 0.9060781918142944, "grad_norm": 0.5306084752082825, "learning_rate": 1.0804121298853054e-06, "loss": 4.2668, "step": 29665 }, { "epoch": 0.9061087354917532, "grad_norm": 0.5441644787788391, "learning_rate": 1.079714638647114e-06, "loss": 4.312, "step": 29666 }, { "epoch": 0.906139279169212, "grad_norm": 0.5365111231803894, "learning_rate": 1.0790173676552829e-06, "loss": 4.2556, "step": 29667 }, { "epoch": 0.9061698228466707, "grad_norm": 0.5438171625137329, "learning_rate": 1.07832031691624e-06, "loss": 4.172, "step": 29668 }, { "epoch": 0.9062003665241295, "grad_norm": 0.5332595109939575, "learning_rate": 1.0776234864363993e-06, "loss": 4.2141, "step": 29669 }, { "epoch": 0.9062309102015883, "grad_norm": 0.549186646938324, "learning_rate": 1.0769268762221813e-06, "loss": 4.1476, "step": 29670 }, { "epoch": 0.906261453879047, "grad_norm": 0.5378463864326477, "learning_rate": 1.0762304862799971e-06, "loss": 4.2409, "step": 29671 }, { "epoch": 0.9062919975565058, "grad_norm": 0.5467721819877625, "learning_rate": 1.0755343166162585e-06, "loss": 4.2102, "step": 29672 }, { "epoch": 0.9063225412339646, "grad_norm": 0.5683416128158569, "learning_rate": 1.074838367237374e-06, "loss": 4.209, "step": 29673 }, { "epoch": 0.9063530849114233, "grad_norm": 0.5436566472053528, "learning_rate": 1.0741426381497583e-06, "loss": 4.2142, "step": 29674 }, { "epoch": 0.9063836285888821, "grad_norm": 0.5339717864990234, "learning_rate": 1.0734471293598087e-06, "loss": 4.2886, "step": 29675 }, { "epoch": 0.9064141722663409, "grad_norm": 0.5338248014450073, "learning_rate": 1.072751840873934e-06, "loss": 4.2612, "step": 29676 }, { "epoch": 0.9064447159437996, "grad_norm": 0.5319821238517761, "learning_rate": 1.0720567726985404e-06, "loss": 4.3182, "step": 29677 }, { "epoch": 0.9064752596212584, "grad_norm": 0.5414626002311707, "learning_rate": 1.071361924840017e-06, "loss": 4.208, "step": 29678 }, { "epoch": 0.9065058032987172, "grad_norm": 0.548805832862854, "learning_rate": 1.07066729730477e-06, "loss": 4.2655, "step": 29679 }, { "epoch": 0.9065363469761759, "grad_norm": 0.5495772361755371, "learning_rate": 1.0699728900991912e-06, "loss": 4.2839, "step": 29680 }, { "epoch": 0.9065668906536347, "grad_norm": 0.5462018847465515, "learning_rate": 1.0692787032296757e-06, "loss": 4.2164, "step": 29681 }, { "epoch": 0.9065974343310934, "grad_norm": 0.5448733568191528, "learning_rate": 1.0685847367026159e-06, "loss": 4.2768, "step": 29682 }, { "epoch": 0.9066279780085522, "grad_norm": 0.5408427715301514, "learning_rate": 1.0678909905244005e-06, "loss": 4.2842, "step": 29683 }, { "epoch": 0.906658521686011, "grad_norm": 0.5335367918014526, "learning_rate": 1.0671974647014166e-06, "loss": 4.2226, "step": 29684 }, { "epoch": 0.9066890653634697, "grad_norm": 0.5435020327568054, "learning_rate": 1.0665041592400532e-06, "loss": 4.1947, "step": 29685 }, { "epoch": 0.9067196090409285, "grad_norm": 0.5380153656005859, "learning_rate": 1.0658110741466887e-06, "loss": 4.2738, "step": 29686 }, { "epoch": 0.9067501527183873, "grad_norm": 0.5444970726966858, "learning_rate": 1.0651182094277068e-06, "loss": 4.1977, "step": 29687 }, { "epoch": 0.906780696395846, "grad_norm": 0.5426235198974609, "learning_rate": 1.0644255650894886e-06, "loss": 4.2413, "step": 29688 }, { "epoch": 0.9068112400733048, "grad_norm": 0.5374647378921509, "learning_rate": 1.0637331411384093e-06, "loss": 4.2533, "step": 29689 }, { "epoch": 0.9068417837507636, "grad_norm": 0.5343108773231506, "learning_rate": 1.0630409375808475e-06, "loss": 4.222, "step": 29690 }, { "epoch": 0.9068723274282223, "grad_norm": 0.5328062772750854, "learning_rate": 1.0623489544231756e-06, "loss": 4.1756, "step": 29691 }, { "epoch": 0.9069028711056811, "grad_norm": 0.5429850220680237, "learning_rate": 1.0616571916717638e-06, "loss": 4.2274, "step": 29692 }, { "epoch": 0.9069334147831399, "grad_norm": 0.5496813654899597, "learning_rate": 1.060965649332979e-06, "loss": 4.2483, "step": 29693 }, { "epoch": 0.9069639584605986, "grad_norm": 0.5539111495018005, "learning_rate": 1.0602743274131966e-06, "loss": 4.3479, "step": 29694 }, { "epoch": 0.9069945021380574, "grad_norm": 0.5328570008277893, "learning_rate": 1.0595832259187754e-06, "loss": 4.2267, "step": 29695 }, { "epoch": 0.9070250458155162, "grad_norm": 0.5383915305137634, "learning_rate": 1.05889234485608e-06, "loss": 4.1911, "step": 29696 }, { "epoch": 0.9070555894929749, "grad_norm": 0.5438861846923828, "learning_rate": 1.0582016842314747e-06, "loss": 4.218, "step": 29697 }, { "epoch": 0.9070861331704337, "grad_norm": 0.5444780588150024, "learning_rate": 1.0575112440513124e-06, "loss": 4.2853, "step": 29698 }, { "epoch": 0.9071166768478924, "grad_norm": 0.5445752739906311, "learning_rate": 1.0568210243219579e-06, "loss": 4.2674, "step": 29699 }, { "epoch": 0.9071472205253512, "grad_norm": 0.5343034267425537, "learning_rate": 1.0561310250497587e-06, "loss": 4.2949, "step": 29700 }, { "epoch": 0.90717776420281, "grad_norm": 0.5423833727836609, "learning_rate": 1.0554412462410707e-06, "loss": 4.2316, "step": 29701 }, { "epoch": 0.9072083078802687, "grad_norm": 0.5422952175140381, "learning_rate": 1.0547516879022502e-06, "loss": 4.1887, "step": 29702 }, { "epoch": 0.9072388515577275, "grad_norm": 0.5491526126861572, "learning_rate": 1.054062350039639e-06, "loss": 4.2566, "step": 29703 }, { "epoch": 0.9072693952351863, "grad_norm": 0.5386155247688293, "learning_rate": 1.053373232659588e-06, "loss": 4.2614, "step": 29704 }, { "epoch": 0.907299938912645, "grad_norm": 0.5432488322257996, "learning_rate": 1.0526843357684475e-06, "loss": 4.1377, "step": 29705 }, { "epoch": 0.9073304825901038, "grad_norm": 0.5304120182991028, "learning_rate": 1.0519956593725483e-06, "loss": 4.2318, "step": 29706 }, { "epoch": 0.9073610262675627, "grad_norm": 0.5425206422805786, "learning_rate": 1.0513072034782384e-06, "loss": 4.3302, "step": 29707 }, { "epoch": 0.9073915699450213, "grad_norm": 0.536692202091217, "learning_rate": 1.0506189680918598e-06, "loss": 4.289, "step": 29708 }, { "epoch": 0.9074221136224802, "grad_norm": 0.5368486642837524, "learning_rate": 1.0499309532197437e-06, "loss": 4.2897, "step": 29709 }, { "epoch": 0.907452657299939, "grad_norm": 0.5449431538581848, "learning_rate": 1.049243158868224e-06, "loss": 4.2414, "step": 29710 }, { "epoch": 0.9074832009773977, "grad_norm": 0.5381166338920593, "learning_rate": 1.0485555850436425e-06, "loss": 4.2278, "step": 29711 }, { "epoch": 0.9075137446548565, "grad_norm": 0.5342543721199036, "learning_rate": 1.0478682317523247e-06, "loss": 4.198, "step": 29712 }, { "epoch": 0.9075442883323153, "grad_norm": 0.5377903580665588, "learning_rate": 1.0471810990005964e-06, "loss": 4.1266, "step": 29713 }, { "epoch": 0.907574832009774, "grad_norm": 0.540505051612854, "learning_rate": 1.0464941867947885e-06, "loss": 4.3269, "step": 29714 }, { "epoch": 0.9076053756872328, "grad_norm": 0.5450121164321899, "learning_rate": 1.0458074951412211e-06, "loss": 4.3266, "step": 29715 }, { "epoch": 0.9076359193646915, "grad_norm": 0.5505521893501282, "learning_rate": 1.0451210240462251e-06, "loss": 4.2532, "step": 29716 }, { "epoch": 0.9076664630421503, "grad_norm": 0.5418888926506042, "learning_rate": 1.0444347735161092e-06, "loss": 4.2984, "step": 29717 }, { "epoch": 0.9076970067196091, "grad_norm": 0.5363011956214905, "learning_rate": 1.043748743557202e-06, "loss": 4.215, "step": 29718 }, { "epoch": 0.9077275503970678, "grad_norm": 0.5351585745811462, "learning_rate": 1.0430629341758201e-06, "loss": 4.1915, "step": 29719 }, { "epoch": 0.9077580940745266, "grad_norm": 0.5454728603363037, "learning_rate": 1.0423773453782731e-06, "loss": 4.1851, "step": 29720 }, { "epoch": 0.9077886377519854, "grad_norm": 0.5498400926589966, "learning_rate": 1.041691977170875e-06, "loss": 4.2895, "step": 29721 }, { "epoch": 0.9078191814294441, "grad_norm": 0.5370751023292542, "learning_rate": 1.0410068295599402e-06, "loss": 4.1894, "step": 29722 }, { "epoch": 0.9078497251069029, "grad_norm": 0.545071542263031, "learning_rate": 1.0403219025517692e-06, "loss": 4.2583, "step": 29723 }, { "epoch": 0.9078802687843617, "grad_norm": 0.5512874722480774, "learning_rate": 1.0396371961526735e-06, "loss": 4.1816, "step": 29724 }, { "epoch": 0.9079108124618204, "grad_norm": 0.5451040863990784, "learning_rate": 1.0389527103689622e-06, "loss": 4.213, "step": 29725 }, { "epoch": 0.9079413561392792, "grad_norm": 0.5374826192855835, "learning_rate": 1.0382684452069302e-06, "loss": 4.3142, "step": 29726 }, { "epoch": 0.907971899816738, "grad_norm": 0.5453928709030151, "learning_rate": 1.0375844006728808e-06, "loss": 4.1594, "step": 29727 }, { "epoch": 0.9080024434941967, "grad_norm": 0.5403574705123901, "learning_rate": 1.0369005767731117e-06, "loss": 4.2178, "step": 29728 }, { "epoch": 0.9080329871716555, "grad_norm": 0.5511260032653809, "learning_rate": 1.0362169735139205e-06, "loss": 4.2464, "step": 29729 }, { "epoch": 0.9080635308491143, "grad_norm": 0.539707601070404, "learning_rate": 1.0355335909015996e-06, "loss": 4.2991, "step": 29730 }, { "epoch": 0.908094074526573, "grad_norm": 0.5401676893234253, "learning_rate": 1.0348504289424438e-06, "loss": 4.2257, "step": 29731 }, { "epoch": 0.9081246182040318, "grad_norm": 0.5375111699104309, "learning_rate": 1.03416748764274e-06, "loss": 4.1499, "step": 29732 }, { "epoch": 0.9081551618814905, "grad_norm": 0.5442059636116028, "learning_rate": 1.03348476700878e-06, "loss": 4.2774, "step": 29733 }, { "epoch": 0.9081857055589493, "grad_norm": 0.530182957649231, "learning_rate": 1.032802267046845e-06, "loss": 4.2393, "step": 29734 }, { "epoch": 0.9082162492364081, "grad_norm": 0.5376734733581543, "learning_rate": 1.032119987763222e-06, "loss": 4.2875, "step": 29735 }, { "epoch": 0.9082467929138668, "grad_norm": 0.5354138612747192, "learning_rate": 1.0314379291641974e-06, "loss": 4.3077, "step": 29736 }, { "epoch": 0.9082773365913256, "grad_norm": 0.5312807559967041, "learning_rate": 1.0307560912560439e-06, "loss": 4.2063, "step": 29737 }, { "epoch": 0.9083078802687844, "grad_norm": 0.5389956831932068, "learning_rate": 1.0300744740450425e-06, "loss": 4.2472, "step": 29738 }, { "epoch": 0.9083384239462431, "grad_norm": 0.5457947850227356, "learning_rate": 1.0293930775374717e-06, "loss": 4.1947, "step": 29739 }, { "epoch": 0.9083689676237019, "grad_norm": 0.5324745774269104, "learning_rate": 1.0287119017396013e-06, "loss": 4.2401, "step": 29740 }, { "epoch": 0.9083995113011607, "grad_norm": 0.5412973761558533, "learning_rate": 1.028030946657707e-06, "loss": 4.1404, "step": 29741 }, { "epoch": 0.9084300549786194, "grad_norm": 0.5364453196525574, "learning_rate": 1.0273502122980587e-06, "loss": 4.2172, "step": 29742 }, { "epoch": 0.9084605986560782, "grad_norm": 0.5329918265342712, "learning_rate": 1.0266696986669212e-06, "loss": 4.1988, "step": 29743 }, { "epoch": 0.908491142333537, "grad_norm": 0.5308332443237305, "learning_rate": 1.0259894057705582e-06, "loss": 4.2862, "step": 29744 }, { "epoch": 0.9085216860109957, "grad_norm": 0.5470565557479858, "learning_rate": 1.025309333615243e-06, "loss": 4.2973, "step": 29745 }, { "epoch": 0.9085522296884545, "grad_norm": 0.5430251359939575, "learning_rate": 1.024629482207226e-06, "loss": 4.3779, "step": 29746 }, { "epoch": 0.9085827733659133, "grad_norm": 0.5325264930725098, "learning_rate": 1.0239498515527717e-06, "loss": 4.2184, "step": 29747 }, { "epoch": 0.908613317043372, "grad_norm": 0.5500622987747192, "learning_rate": 1.0232704416581446e-06, "loss": 4.2427, "step": 29748 }, { "epoch": 0.9086438607208308, "grad_norm": 0.5430145263671875, "learning_rate": 1.0225912525295893e-06, "loss": 4.2974, "step": 29749 }, { "epoch": 0.9086744043982895, "grad_norm": 0.5404999852180481, "learning_rate": 1.0219122841733652e-06, "loss": 4.2918, "step": 29750 }, { "epoch": 0.9087049480757483, "grad_norm": 0.5392161011695862, "learning_rate": 1.0212335365957227e-06, "loss": 4.2497, "step": 29751 }, { "epoch": 0.9087354917532071, "grad_norm": 0.5469281077384949, "learning_rate": 1.020555009802912e-06, "loss": 4.2385, "step": 29752 }, { "epoch": 0.9087660354306658, "grad_norm": 0.5400023460388184, "learning_rate": 1.0198767038011814e-06, "loss": 4.2731, "step": 29753 }, { "epoch": 0.9087965791081246, "grad_norm": 0.5281352400779724, "learning_rate": 1.0191986185967728e-06, "loss": 4.2874, "step": 29754 }, { "epoch": 0.9088271227855834, "grad_norm": 0.5423547625541687, "learning_rate": 1.0185207541959342e-06, "loss": 4.3056, "step": 29755 }, { "epoch": 0.9088576664630421, "grad_norm": 0.5322928428649902, "learning_rate": 1.0178431106049047e-06, "loss": 4.2912, "step": 29756 }, { "epoch": 0.9088882101405009, "grad_norm": 0.5337964296340942, "learning_rate": 1.017165687829924e-06, "loss": 4.2854, "step": 29757 }, { "epoch": 0.9089187538179597, "grad_norm": 0.5575234889984131, "learning_rate": 1.0164884858772318e-06, "loss": 4.2744, "step": 29758 }, { "epoch": 0.9089492974954184, "grad_norm": 0.5344478487968445, "learning_rate": 1.0158115047530558e-06, "loss": 4.2126, "step": 29759 }, { "epoch": 0.9089798411728772, "grad_norm": 0.5358936786651611, "learning_rate": 1.0151347444636416e-06, "loss": 4.2944, "step": 29760 }, { "epoch": 0.909010384850336, "grad_norm": 0.5418521165847778, "learning_rate": 1.014458205015209e-06, "loss": 4.3486, "step": 29761 }, { "epoch": 0.9090409285277947, "grad_norm": 0.5460615754127502, "learning_rate": 1.0137818864139948e-06, "loss": 4.2368, "step": 29762 }, { "epoch": 0.9090714722052535, "grad_norm": 0.5448694229125977, "learning_rate": 1.0131057886662186e-06, "loss": 4.1518, "step": 29763 }, { "epoch": 0.9091020158827123, "grad_norm": 0.5475598573684692, "learning_rate": 1.0124299117781122e-06, "loss": 4.2249, "step": 29764 }, { "epoch": 0.909132559560171, "grad_norm": 0.5380885004997253, "learning_rate": 1.0117542557559006e-06, "loss": 4.269, "step": 29765 }, { "epoch": 0.9091631032376298, "grad_norm": 0.5414441823959351, "learning_rate": 1.0110788206057958e-06, "loss": 4.2957, "step": 29766 }, { "epoch": 0.9091936469150885, "grad_norm": 0.5392526388168335, "learning_rate": 1.010403606334026e-06, "loss": 4.2821, "step": 29767 }, { "epoch": 0.9092241905925473, "grad_norm": 0.5408474206924438, "learning_rate": 1.0097286129468031e-06, "loss": 4.263, "step": 29768 }, { "epoch": 0.9092547342700061, "grad_norm": 0.535990834236145, "learning_rate": 1.0090538404503414e-06, "loss": 4.2544, "step": 29769 }, { "epoch": 0.9092852779474648, "grad_norm": 0.5408339500427246, "learning_rate": 1.0083792888508581e-06, "loss": 4.2805, "step": 29770 }, { "epoch": 0.9093158216249236, "grad_norm": 0.5347608327865601, "learning_rate": 1.0077049581545622e-06, "loss": 4.1588, "step": 29771 }, { "epoch": 0.9093463653023824, "grad_norm": 0.5416397452354431, "learning_rate": 1.0070308483676599e-06, "loss": 4.2579, "step": 29772 }, { "epoch": 0.9093769089798411, "grad_norm": 0.5447630286216736, "learning_rate": 1.0063569594963628e-06, "loss": 4.2587, "step": 29773 }, { "epoch": 0.9094074526572999, "grad_norm": 0.5409234762191772, "learning_rate": 1.0056832915468716e-06, "loss": 4.3141, "step": 29774 }, { "epoch": 0.9094379963347587, "grad_norm": 0.5389142036437988, "learning_rate": 1.0050098445253953e-06, "loss": 4.1841, "step": 29775 }, { "epoch": 0.9094685400122174, "grad_norm": 0.536363959312439, "learning_rate": 1.0043366184381286e-06, "loss": 4.2479, "step": 29776 }, { "epoch": 0.9094990836896762, "grad_norm": 0.5463253259658813, "learning_rate": 1.0036636132912697e-06, "loss": 4.2119, "step": 29777 }, { "epoch": 0.909529627367135, "grad_norm": 0.5407874584197998, "learning_rate": 1.002990829091019e-06, "loss": 4.2836, "step": 29778 }, { "epoch": 0.9095601710445937, "grad_norm": 0.5304567813873291, "learning_rate": 1.0023182658435715e-06, "loss": 4.189, "step": 29779 }, { "epoch": 0.9095907147220526, "grad_norm": 0.5368268489837646, "learning_rate": 1.001645923555114e-06, "loss": 4.2817, "step": 29780 }, { "epoch": 0.9096212583995114, "grad_norm": 0.5286033153533936, "learning_rate": 1.0009738022318415e-06, "loss": 4.217, "step": 29781 }, { "epoch": 0.90965180207697, "grad_norm": 0.5479660630226135, "learning_rate": 1.0003019018799465e-06, "loss": 4.2705, "step": 29782 }, { "epoch": 0.9096823457544289, "grad_norm": 0.5382640957832336, "learning_rate": 9.99630222505607e-07, "loss": 4.27, "step": 29783 }, { "epoch": 0.9097128894318876, "grad_norm": 0.550221860408783, "learning_rate": 9.989587641150184e-07, "loss": 4.3158, "step": 29784 }, { "epoch": 0.9097434331093464, "grad_norm": 0.5417762994766235, "learning_rate": 9.982875267143504e-07, "loss": 4.2849, "step": 29785 }, { "epoch": 0.9097739767868052, "grad_norm": 0.5404262542724609, "learning_rate": 9.976165103097902e-07, "loss": 4.2623, "step": 29786 }, { "epoch": 0.9098045204642639, "grad_norm": 0.5377844572067261, "learning_rate": 9.969457149075185e-07, "loss": 4.2462, "step": 29787 }, { "epoch": 0.9098350641417227, "grad_norm": 0.5316528081893921, "learning_rate": 9.962751405137055e-07, "loss": 4.2617, "step": 29788 }, { "epoch": 0.9098656078191815, "grad_norm": 0.5424718260765076, "learning_rate": 9.956047871345297e-07, "loss": 4.2499, "step": 29789 }, { "epoch": 0.9098961514966402, "grad_norm": 0.5317355990409851, "learning_rate": 9.94934654776164e-07, "loss": 4.2166, "step": 29790 }, { "epoch": 0.909926695174099, "grad_norm": 0.5476506948471069, "learning_rate": 9.942647434447756e-07, "loss": 4.3101, "step": 29791 }, { "epoch": 0.9099572388515578, "grad_norm": 0.5451643466949463, "learning_rate": 9.935950531465344e-07, "loss": 4.2959, "step": 29792 }, { "epoch": 0.9099877825290165, "grad_norm": 0.5396924614906311, "learning_rate": 9.929255838876077e-07, "loss": 4.2244, "step": 29793 }, { "epoch": 0.9100183262064753, "grad_norm": 0.5410189032554626, "learning_rate": 9.922563356741577e-07, "loss": 4.3485, "step": 29794 }, { "epoch": 0.9100488698839341, "grad_norm": 0.5400967597961426, "learning_rate": 9.915873085123455e-07, "loss": 4.2402, "step": 29795 }, { "epoch": 0.9100794135613928, "grad_norm": 0.5389940142631531, "learning_rate": 9.909185024083363e-07, "loss": 4.165, "step": 29796 }, { "epoch": 0.9101099572388516, "grad_norm": 0.5422478914260864, "learning_rate": 9.9024991736828e-07, "loss": 4.3195, "step": 29797 }, { "epoch": 0.9101405009163103, "grad_norm": 0.5381609201431274, "learning_rate": 9.895815533983415e-07, "loss": 4.3, "step": 29798 }, { "epoch": 0.9101710445937691, "grad_norm": 0.5459067225456238, "learning_rate": 9.889134105046687e-07, "loss": 4.3186, "step": 29799 }, { "epoch": 0.9102015882712279, "grad_norm": 0.5362516641616821, "learning_rate": 9.882454886934123e-07, "loss": 4.2527, "step": 29800 }, { "epoch": 0.9102321319486866, "grad_norm": 0.5414581298828125, "learning_rate": 9.87577787970731e-07, "loss": 4.2125, "step": 29801 }, { "epoch": 0.9102626756261454, "grad_norm": 0.5312038660049438, "learning_rate": 9.869103083427645e-07, "loss": 4.1813, "step": 29802 }, { "epoch": 0.9102932193036042, "grad_norm": 0.5323333144187927, "learning_rate": 9.862430498156605e-07, "loss": 4.2495, "step": 29803 }, { "epoch": 0.9103237629810629, "grad_norm": 0.5358121395111084, "learning_rate": 9.855760123955643e-07, "loss": 4.2502, "step": 29804 }, { "epoch": 0.9103543066585217, "grad_norm": 0.539175271987915, "learning_rate": 9.849091960886153e-07, "loss": 4.196, "step": 29805 }, { "epoch": 0.9103848503359805, "grad_norm": 0.5525004267692566, "learning_rate": 9.842426009009587e-07, "loss": 4.251, "step": 29806 }, { "epoch": 0.9104153940134392, "grad_norm": 0.5274463295936584, "learning_rate": 9.835762268387256e-07, "loss": 4.2318, "step": 29807 }, { "epoch": 0.910445937690898, "grad_norm": 0.5446296334266663, "learning_rate": 9.829100739080527e-07, "loss": 4.2629, "step": 29808 }, { "epoch": 0.9104764813683568, "grad_norm": 0.5378876328468323, "learning_rate": 9.82244142115077e-07, "loss": 4.2679, "step": 29809 }, { "epoch": 0.9105070250458155, "grad_norm": 0.5402528047561646, "learning_rate": 9.815784314659294e-07, "loss": 4.2943, "step": 29810 }, { "epoch": 0.9105375687232743, "grad_norm": 0.5412092208862305, "learning_rate": 9.809129419667357e-07, "loss": 4.2791, "step": 29811 }, { "epoch": 0.9105681124007331, "grad_norm": 0.5341628789901733, "learning_rate": 9.802476736236244e-07, "loss": 4.2011, "step": 29812 }, { "epoch": 0.9105986560781918, "grad_norm": 0.5372666716575623, "learning_rate": 9.795826264427265e-07, "loss": 4.2204, "step": 29813 }, { "epoch": 0.9106291997556506, "grad_norm": 0.5352531671524048, "learning_rate": 9.789178004301596e-07, "loss": 4.2264, "step": 29814 }, { "epoch": 0.9106597434331093, "grad_norm": 0.5321789979934692, "learning_rate": 9.782531955920466e-07, "loss": 4.2507, "step": 29815 }, { "epoch": 0.9106902871105681, "grad_norm": 0.5428717732429504, "learning_rate": 9.775888119345072e-07, "loss": 4.1779, "step": 29816 }, { "epoch": 0.9107208307880269, "grad_norm": 0.5458091497421265, "learning_rate": 9.769246494636591e-07, "loss": 4.2817, "step": 29817 }, { "epoch": 0.9107513744654856, "grad_norm": 0.5368713140487671, "learning_rate": 9.762607081856167e-07, "loss": 4.307, "step": 29818 }, { "epoch": 0.9107819181429444, "grad_norm": 0.5404400825500488, "learning_rate": 9.755969881064946e-07, "loss": 4.2337, "step": 29819 }, { "epoch": 0.9108124618204032, "grad_norm": 0.5383018255233765, "learning_rate": 9.74933489232402e-07, "loss": 4.2239, "step": 29820 }, { "epoch": 0.9108430054978619, "grad_norm": 0.5372126698493958, "learning_rate": 9.742702115694503e-07, "loss": 4.2093, "step": 29821 }, { "epoch": 0.9108735491753207, "grad_norm": 0.5407499074935913, "learning_rate": 9.736071551237487e-07, "loss": 4.2231, "step": 29822 }, { "epoch": 0.9109040928527795, "grad_norm": 0.5373311638832092, "learning_rate": 9.729443199013949e-07, "loss": 4.2177, "step": 29823 }, { "epoch": 0.9109346365302382, "grad_norm": 0.5348559021949768, "learning_rate": 9.722817059084981e-07, "loss": 4.161, "step": 29824 }, { "epoch": 0.910965180207697, "grad_norm": 0.5381422638893127, "learning_rate": 9.716193131511537e-07, "loss": 4.1866, "step": 29825 }, { "epoch": 0.9109957238851558, "grad_norm": 0.5361599922180176, "learning_rate": 9.709571416354674e-07, "loss": 4.2087, "step": 29826 }, { "epoch": 0.9110262675626145, "grad_norm": 0.5350817441940308, "learning_rate": 9.702951913675345e-07, "loss": 4.2214, "step": 29827 }, { "epoch": 0.9110568112400733, "grad_norm": 0.5411084890365601, "learning_rate": 9.696334623534447e-07, "loss": 4.3181, "step": 29828 }, { "epoch": 0.9110873549175321, "grad_norm": 0.5498883128166199, "learning_rate": 9.689719545992988e-07, "loss": 4.3831, "step": 29829 }, { "epoch": 0.9111178985949908, "grad_norm": 0.528215229511261, "learning_rate": 9.68310668111183e-07, "loss": 4.1063, "step": 29830 }, { "epoch": 0.9111484422724496, "grad_norm": 0.5403653383255005, "learning_rate": 9.676496028951849e-07, "loss": 4.3473, "step": 29831 }, { "epoch": 0.9111789859499083, "grad_norm": 0.5482434630393982, "learning_rate": 9.669887589573962e-07, "loss": 4.1456, "step": 29832 }, { "epoch": 0.9112095296273671, "grad_norm": 0.5404235124588013, "learning_rate": 9.66328136303893e-07, "loss": 4.2576, "step": 29833 }, { "epoch": 0.9112400733048259, "grad_norm": 0.5421210527420044, "learning_rate": 9.656677349407673e-07, "loss": 4.2358, "step": 29834 }, { "epoch": 0.9112706169822846, "grad_norm": 0.5445266962051392, "learning_rate": 9.650075548740977e-07, "loss": 4.3085, "step": 29835 }, { "epoch": 0.9113011606597434, "grad_norm": 0.5381705164909363, "learning_rate": 9.643475961099575e-07, "loss": 4.3191, "step": 29836 }, { "epoch": 0.9113317043372022, "grad_norm": 0.5315487384796143, "learning_rate": 9.636878586544301e-07, "loss": 4.2323, "step": 29837 }, { "epoch": 0.9113622480146609, "grad_norm": 0.5391931533813477, "learning_rate": 9.630283425135832e-07, "loss": 4.1535, "step": 29838 }, { "epoch": 0.9113927916921197, "grad_norm": 0.5424102544784546, "learning_rate": 9.623690476934982e-07, "loss": 4.1997, "step": 29839 }, { "epoch": 0.9114233353695785, "grad_norm": 0.5329025983810425, "learning_rate": 9.61709974200234e-07, "loss": 4.2363, "step": 29840 }, { "epoch": 0.9114538790470372, "grad_norm": 0.5583856105804443, "learning_rate": 9.610511220398717e-07, "loss": 4.2986, "step": 29841 }, { "epoch": 0.911484422724496, "grad_norm": 0.5534997582435608, "learning_rate": 9.603924912184647e-07, "loss": 4.2707, "step": 29842 }, { "epoch": 0.9115149664019548, "grad_norm": 0.5359036326408386, "learning_rate": 9.597340817420864e-07, "loss": 4.3159, "step": 29843 }, { "epoch": 0.9115455100794135, "grad_norm": 0.5313184261322021, "learning_rate": 9.590758936168009e-07, "loss": 4.128, "step": 29844 }, { "epoch": 0.9115760537568723, "grad_norm": 0.5417550206184387, "learning_rate": 9.584179268486593e-07, "loss": 4.2644, "step": 29845 }, { "epoch": 0.9116065974343311, "grad_norm": 0.533915638923645, "learning_rate": 9.577601814437259e-07, "loss": 4.2441, "step": 29846 }, { "epoch": 0.9116371411117898, "grad_norm": 0.5409644842147827, "learning_rate": 9.571026574080572e-07, "loss": 4.2922, "step": 29847 }, { "epoch": 0.9116676847892486, "grad_norm": 0.5493549704551697, "learning_rate": 9.564453547477038e-07, "loss": 4.1575, "step": 29848 }, { "epoch": 0.9116982284667073, "grad_norm": 0.5412837862968445, "learning_rate": 9.557882734687217e-07, "loss": 4.2615, "step": 29849 }, { "epoch": 0.9117287721441661, "grad_norm": 0.5392070412635803, "learning_rate": 9.551314135771595e-07, "loss": 4.1433, "step": 29850 }, { "epoch": 0.911759315821625, "grad_norm": 0.543261706829071, "learning_rate": 9.544747750790616e-07, "loss": 4.1525, "step": 29851 }, { "epoch": 0.9117898594990836, "grad_norm": 0.5422153472900391, "learning_rate": 9.538183579804822e-07, "loss": 4.2546, "step": 29852 }, { "epoch": 0.9118204031765424, "grad_norm": 0.5307973623275757, "learning_rate": 9.531621622874603e-07, "loss": 4.2747, "step": 29853 }, { "epoch": 0.9118509468540013, "grad_norm": 0.5369324684143066, "learning_rate": 9.525061880060359e-07, "loss": 4.2699, "step": 29854 }, { "epoch": 0.91188149053146, "grad_norm": 0.5323897004127502, "learning_rate": 9.518504351422541e-07, "loss": 4.1659, "step": 29855 }, { "epoch": 0.9119120342089188, "grad_norm": 0.5396856665611267, "learning_rate": 9.511949037021462e-07, "loss": 4.1512, "step": 29856 }, { "epoch": 0.9119425778863776, "grad_norm": 0.5397454500198364, "learning_rate": 9.505395936917488e-07, "loss": 4.2677, "step": 29857 }, { "epoch": 0.9119731215638363, "grad_norm": 0.5384970307350159, "learning_rate": 9.498845051171045e-07, "loss": 4.2882, "step": 29858 }, { "epoch": 0.9120036652412951, "grad_norm": 0.5350223779678345, "learning_rate": 9.492296379842336e-07, "loss": 4.1969, "step": 29859 }, { "epoch": 0.9120342089187539, "grad_norm": 0.5445971488952637, "learning_rate": 9.485749922991727e-07, "loss": 4.2208, "step": 29860 }, { "epoch": 0.9120647525962126, "grad_norm": 0.5418384075164795, "learning_rate": 9.479205680679531e-07, "loss": 4.3784, "step": 29861 }, { "epoch": 0.9120952962736714, "grad_norm": 0.544689416885376, "learning_rate": 9.472663652965896e-07, "loss": 4.2175, "step": 29862 }, { "epoch": 0.9121258399511302, "grad_norm": 0.5352890491485596, "learning_rate": 9.466123839911106e-07, "loss": 4.2406, "step": 29863 }, { "epoch": 0.9121563836285889, "grad_norm": 0.545637845993042, "learning_rate": 9.459586241575418e-07, "loss": 4.0945, "step": 29864 }, { "epoch": 0.9121869273060477, "grad_norm": 0.5371882319450378, "learning_rate": 9.45305085801898e-07, "loss": 4.2341, "step": 29865 }, { "epoch": 0.9122174709835064, "grad_norm": 0.5474726557731628, "learning_rate": 9.446517689301993e-07, "loss": 4.3098, "step": 29866 }, { "epoch": 0.9122480146609652, "grad_norm": 0.5303820371627808, "learning_rate": 9.439986735484574e-07, "loss": 4.1504, "step": 29867 }, { "epoch": 0.912278558338424, "grad_norm": 0.5493586659431458, "learning_rate": 9.433457996626898e-07, "loss": 4.3188, "step": 29868 }, { "epoch": 0.9123091020158827, "grad_norm": 0.537844181060791, "learning_rate": 9.426931472789058e-07, "loss": 4.2791, "step": 29869 }, { "epoch": 0.9123396456933415, "grad_norm": 0.5314826965332031, "learning_rate": 9.42040716403117e-07, "loss": 4.2626, "step": 29870 }, { "epoch": 0.9123701893708003, "grad_norm": 0.5388978123664856, "learning_rate": 9.413885070413242e-07, "loss": 4.2349, "step": 29871 }, { "epoch": 0.912400733048259, "grad_norm": 0.5436479449272156, "learning_rate": 9.407365191995421e-07, "loss": 4.2361, "step": 29872 }, { "epoch": 0.9124312767257178, "grad_norm": 0.5434285402297974, "learning_rate": 9.400847528837631e-07, "loss": 4.302, "step": 29873 }, { "epoch": 0.9124618204031766, "grad_norm": 0.5259504318237305, "learning_rate": 9.394332080999963e-07, "loss": 4.21, "step": 29874 }, { "epoch": 0.9124923640806353, "grad_norm": 0.5384178757667542, "learning_rate": 9.387818848542423e-07, "loss": 4.2712, "step": 29875 }, { "epoch": 0.9125229077580941, "grad_norm": 0.5304687023162842, "learning_rate": 9.381307831524911e-07, "loss": 4.3186, "step": 29876 }, { "epoch": 0.9125534514355529, "grad_norm": 0.5321681499481201, "learning_rate": 9.374799030007403e-07, "loss": 4.2916, "step": 29877 }, { "epoch": 0.9125839951130116, "grad_norm": 0.5397470593452454, "learning_rate": 9.368292444049881e-07, "loss": 4.1132, "step": 29878 }, { "epoch": 0.9126145387904704, "grad_norm": 0.5239682197570801, "learning_rate": 9.361788073712158e-07, "loss": 4.2709, "step": 29879 }, { "epoch": 0.9126450824679292, "grad_norm": 0.5396919250488281, "learning_rate": 9.355285919054185e-07, "loss": 4.2178, "step": 29880 }, { "epoch": 0.9126756261453879, "grad_norm": 0.5309796333312988, "learning_rate": 9.34878598013586e-07, "loss": 4.1589, "step": 29881 }, { "epoch": 0.9127061698228467, "grad_norm": 0.5433579087257385, "learning_rate": 9.342288257016968e-07, "loss": 4.3672, "step": 29882 }, { "epoch": 0.9127367135003054, "grad_norm": 0.5305562019348145, "learning_rate": 9.335792749757377e-07, "loss": 4.196, "step": 29883 }, { "epoch": 0.9127672571777642, "grad_norm": 0.5373139977455139, "learning_rate": 9.329299458416873e-07, "loss": 4.265, "step": 29884 }, { "epoch": 0.912797800855223, "grad_norm": 0.5404906272888184, "learning_rate": 9.322808383055243e-07, "loss": 4.2812, "step": 29885 }, { "epoch": 0.9128283445326817, "grad_norm": 0.5387222170829773, "learning_rate": 9.316319523732298e-07, "loss": 4.235, "step": 29886 }, { "epoch": 0.9128588882101405, "grad_norm": 0.538994550704956, "learning_rate": 9.309832880507685e-07, "loss": 4.2822, "step": 29887 }, { "epoch": 0.9128894318875993, "grad_norm": 0.5477582812309265, "learning_rate": 9.303348453441218e-07, "loss": 4.3071, "step": 29888 }, { "epoch": 0.912919975565058, "grad_norm": 0.5422325730323792, "learning_rate": 9.296866242592572e-07, "loss": 4.2291, "step": 29889 }, { "epoch": 0.9129505192425168, "grad_norm": 0.5378122329711914, "learning_rate": 9.290386248021449e-07, "loss": 4.2361, "step": 29890 }, { "epoch": 0.9129810629199756, "grad_norm": 0.5505344271659851, "learning_rate": 9.283908469787467e-07, "loss": 4.2096, "step": 29891 }, { "epoch": 0.9130116065974343, "grad_norm": 0.53858482837677, "learning_rate": 9.277432907950357e-07, "loss": 4.2957, "step": 29892 }, { "epoch": 0.9130421502748931, "grad_norm": 0.5502220392227173, "learning_rate": 9.270959562569625e-07, "loss": 4.291, "step": 29893 }, { "epoch": 0.9130726939523519, "grad_norm": 0.5377557277679443, "learning_rate": 9.264488433704977e-07, "loss": 4.179, "step": 29894 }, { "epoch": 0.9131032376298106, "grad_norm": 0.5560786724090576, "learning_rate": 9.258019521415973e-07, "loss": 4.325, "step": 29895 }, { "epoch": 0.9131337813072694, "grad_norm": 0.540052592754364, "learning_rate": 9.251552825762122e-07, "loss": 4.2086, "step": 29896 }, { "epoch": 0.9131643249847282, "grad_norm": 0.5362732410430908, "learning_rate": 9.245088346803016e-07, "loss": 4.2101, "step": 29897 }, { "epoch": 0.9131948686621869, "grad_norm": 0.5499110221862793, "learning_rate": 9.23862608459819e-07, "loss": 4.138, "step": 29898 }, { "epoch": 0.9132254123396457, "grad_norm": 0.5395761728286743, "learning_rate": 9.232166039207124e-07, "loss": 4.3061, "step": 29899 }, { "epoch": 0.9132559560171044, "grad_norm": 0.5341073274612427, "learning_rate": 9.225708210689271e-07, "loss": 4.2385, "step": 29900 }, { "epoch": 0.9132864996945632, "grad_norm": 0.5319384932518005, "learning_rate": 9.219252599104139e-07, "loss": 4.187, "step": 29901 }, { "epoch": 0.913317043372022, "grad_norm": 0.5447475910186768, "learning_rate": 9.212799204511097e-07, "loss": 4.1879, "step": 29902 }, { "epoch": 0.9133475870494807, "grad_norm": 0.5389200448989868, "learning_rate": 9.20634802696968e-07, "loss": 4.2992, "step": 29903 }, { "epoch": 0.9133781307269395, "grad_norm": 0.5457732677459717, "learning_rate": 9.199899066539175e-07, "loss": 4.2456, "step": 29904 }, { "epoch": 0.9134086744043983, "grad_norm": 0.5394842624664307, "learning_rate": 9.193452323279006e-07, "loss": 4.2609, "step": 29905 }, { "epoch": 0.913439218081857, "grad_norm": 0.5464442372322083, "learning_rate": 9.187007797248542e-07, "loss": 4.1502, "step": 29906 }, { "epoch": 0.9134697617593158, "grad_norm": 0.5379722118377686, "learning_rate": 9.180565488507098e-07, "loss": 4.2411, "step": 29907 }, { "epoch": 0.9135003054367746, "grad_norm": 0.5384520292282104, "learning_rate": 9.174125397114014e-07, "loss": 4.3178, "step": 29908 }, { "epoch": 0.9135308491142333, "grad_norm": 0.5329968333244324, "learning_rate": 9.167687523128604e-07, "loss": 4.2336, "step": 29909 }, { "epoch": 0.9135613927916921, "grad_norm": 0.5465874075889587, "learning_rate": 9.161251866610071e-07, "loss": 4.301, "step": 29910 }, { "epoch": 0.9135919364691509, "grad_norm": 0.5678038001060486, "learning_rate": 9.154818427617756e-07, "loss": 4.2856, "step": 29911 }, { "epoch": 0.9136224801466096, "grad_norm": 0.5395184755325317, "learning_rate": 9.148387206210862e-07, "loss": 4.297, "step": 29912 }, { "epoch": 0.9136530238240684, "grad_norm": 0.5448497533798218, "learning_rate": 9.141958202448564e-07, "loss": 4.2535, "step": 29913 }, { "epoch": 0.9136835675015272, "grad_norm": 0.5349546670913696, "learning_rate": 9.135531416390119e-07, "loss": 4.1458, "step": 29914 }, { "epoch": 0.9137141111789859, "grad_norm": 0.5475652813911438, "learning_rate": 9.129106848094677e-07, "loss": 4.1857, "step": 29915 }, { "epoch": 0.9137446548564447, "grad_norm": 0.5348473787307739, "learning_rate": 9.122684497621409e-07, "loss": 4.2636, "step": 29916 }, { "epoch": 0.9137751985339034, "grad_norm": 0.5485242009162903, "learning_rate": 9.116264365029437e-07, "loss": 4.3232, "step": 29917 }, { "epoch": 0.9138057422113622, "grad_norm": 0.5385925769805908, "learning_rate": 9.109846450377824e-07, "loss": 4.2318, "step": 29918 }, { "epoch": 0.913836285888821, "grad_norm": 0.5455538034439087, "learning_rate": 9.103430753725716e-07, "loss": 4.3052, "step": 29919 }, { "epoch": 0.9138668295662797, "grad_norm": 0.5417786240577698, "learning_rate": 9.097017275132208e-07, "loss": 4.2381, "step": 29920 }, { "epoch": 0.9138973732437385, "grad_norm": 0.5338066220283508, "learning_rate": 9.090606014656278e-07, "loss": 4.2568, "step": 29921 }, { "epoch": 0.9139279169211973, "grad_norm": 0.5368257761001587, "learning_rate": 9.084196972357018e-07, "loss": 4.2378, "step": 29922 }, { "epoch": 0.913958460598656, "grad_norm": 0.5362082719802856, "learning_rate": 9.077790148293435e-07, "loss": 4.17, "step": 29923 }, { "epoch": 0.9139890042761148, "grad_norm": 0.5289928317070007, "learning_rate": 9.071385542524513e-07, "loss": 4.2035, "step": 29924 }, { "epoch": 0.9140195479535737, "grad_norm": 0.5348824858665466, "learning_rate": 9.064983155109174e-07, "loss": 4.1891, "step": 29925 }, { "epoch": 0.9140500916310323, "grad_norm": 0.533697783946991, "learning_rate": 9.058582986106484e-07, "loss": 4.1918, "step": 29926 }, { "epoch": 0.9140806353084912, "grad_norm": 0.5358957052230835, "learning_rate": 9.052185035575256e-07, "loss": 4.2742, "step": 29927 }, { "epoch": 0.91411117898595, "grad_norm": 0.5356571674346924, "learning_rate": 9.045789303574414e-07, "loss": 4.1673, "step": 29928 }, { "epoch": 0.9141417226634087, "grad_norm": 0.5391323566436768, "learning_rate": 9.039395790162941e-07, "loss": 4.3034, "step": 29929 }, { "epoch": 0.9141722663408675, "grad_norm": 0.5338905453681946, "learning_rate": 9.033004495399594e-07, "loss": 4.0795, "step": 29930 }, { "epoch": 0.9142028100183263, "grad_norm": 0.5369899868965149, "learning_rate": 9.026615419343326e-07, "loss": 4.1896, "step": 29931 }, { "epoch": 0.914233353695785, "grad_norm": 0.5457500219345093, "learning_rate": 9.020228562052868e-07, "loss": 4.296, "step": 29932 }, { "epoch": 0.9142638973732438, "grad_norm": 0.53931725025177, "learning_rate": 9.013843923587062e-07, "loss": 4.268, "step": 29933 }, { "epoch": 0.9142944410507025, "grad_norm": 0.54103684425354, "learning_rate": 9.007461504004694e-07, "loss": 4.303, "step": 29934 }, { "epoch": 0.9143249847281613, "grad_norm": 0.5455342531204224, "learning_rate": 9.001081303364551e-07, "loss": 4.2582, "step": 29935 }, { "epoch": 0.9143555284056201, "grad_norm": 0.5438883900642395, "learning_rate": 8.994703321725334e-07, "loss": 4.2662, "step": 29936 }, { "epoch": 0.9143860720830788, "grad_norm": 0.54240483045578, "learning_rate": 8.988327559145832e-07, "loss": 4.2736, "step": 29937 }, { "epoch": 0.9144166157605376, "grad_norm": 0.543037474155426, "learning_rate": 8.981954015684662e-07, "loss": 4.1279, "step": 29938 }, { "epoch": 0.9144471594379964, "grad_norm": 0.5459842085838318, "learning_rate": 8.975582691400586e-07, "loss": 4.2998, "step": 29939 }, { "epoch": 0.9144777031154551, "grad_norm": 0.5399442315101624, "learning_rate": 8.969213586352276e-07, "loss": 4.2735, "step": 29940 }, { "epoch": 0.9145082467929139, "grad_norm": 0.5438244342803955, "learning_rate": 8.962846700598298e-07, "loss": 4.216, "step": 29941 }, { "epoch": 0.9145387904703727, "grad_norm": 0.5399749875068665, "learning_rate": 8.956482034197328e-07, "loss": 4.2545, "step": 29942 }, { "epoch": 0.9145693341478314, "grad_norm": 0.5388093590736389, "learning_rate": 8.950119587207983e-07, "loss": 4.1692, "step": 29943 }, { "epoch": 0.9145998778252902, "grad_norm": 0.5486934185028076, "learning_rate": 8.943759359688802e-07, "loss": 4.2535, "step": 29944 }, { "epoch": 0.914630421502749, "grad_norm": 0.5431752800941467, "learning_rate": 8.937401351698376e-07, "loss": 4.2496, "step": 29945 }, { "epoch": 0.9146609651802077, "grad_norm": 0.5542266964912415, "learning_rate": 8.931045563295243e-07, "loss": 4.1252, "step": 29946 }, { "epoch": 0.9146915088576665, "grad_norm": 0.5412447452545166, "learning_rate": 8.924691994537937e-07, "loss": 4.3053, "step": 29947 }, { "epoch": 0.9147220525351252, "grad_norm": 0.5386687517166138, "learning_rate": 8.918340645484885e-07, "loss": 4.3011, "step": 29948 }, { "epoch": 0.914752596212584, "grad_norm": 0.5421130657196045, "learning_rate": 8.911991516194678e-07, "loss": 4.2459, "step": 29949 }, { "epoch": 0.9147831398900428, "grad_norm": 0.5433126091957092, "learning_rate": 8.905644606725689e-07, "loss": 4.271, "step": 29950 }, { "epoch": 0.9148136835675015, "grad_norm": 0.5395674705505371, "learning_rate": 8.899299917136394e-07, "loss": 4.2474, "step": 29951 }, { "epoch": 0.9148442272449603, "grad_norm": 0.5483600497245789, "learning_rate": 8.892957447485195e-07, "loss": 4.2439, "step": 29952 }, { "epoch": 0.9148747709224191, "grad_norm": 0.5500244498252869, "learning_rate": 8.886617197830516e-07, "loss": 4.2255, "step": 29953 }, { "epoch": 0.9149053145998778, "grad_norm": 0.5433428883552551, "learning_rate": 8.880279168230727e-07, "loss": 4.0962, "step": 29954 }, { "epoch": 0.9149358582773366, "grad_norm": 0.5369985699653625, "learning_rate": 8.873943358744168e-07, "loss": 4.3079, "step": 29955 }, { "epoch": 0.9149664019547954, "grad_norm": 0.5509548783302307, "learning_rate": 8.867609769429186e-07, "loss": 4.3316, "step": 29956 }, { "epoch": 0.9149969456322541, "grad_norm": 0.5384106636047363, "learning_rate": 8.861278400344119e-07, "loss": 4.3145, "step": 29957 }, { "epoch": 0.9150274893097129, "grad_norm": 0.5378031134605408, "learning_rate": 8.854949251547201e-07, "loss": 4.3376, "step": 29958 }, { "epoch": 0.9150580329871717, "grad_norm": 0.5388500690460205, "learning_rate": 8.848622323096773e-07, "loss": 4.229, "step": 29959 }, { "epoch": 0.9150885766646304, "grad_norm": 0.543470025062561, "learning_rate": 8.842297615051093e-07, "loss": 4.1682, "step": 29960 }, { "epoch": 0.9151191203420892, "grad_norm": 0.5355914235115051, "learning_rate": 8.83597512746831e-07, "loss": 4.2403, "step": 29961 }, { "epoch": 0.915149664019548, "grad_norm": 0.5388451218605042, "learning_rate": 8.829654860406766e-07, "loss": 4.3309, "step": 29962 }, { "epoch": 0.9151802076970067, "grad_norm": 0.5330700278282166, "learning_rate": 8.823336813924582e-07, "loss": 4.2332, "step": 29963 }, { "epoch": 0.9152107513744655, "grad_norm": 0.5381163358688354, "learning_rate": 8.817020988079877e-07, "loss": 4.2948, "step": 29964 }, { "epoch": 0.9152412950519242, "grad_norm": 0.5460942983627319, "learning_rate": 8.810707382930938e-07, "loss": 4.3053, "step": 29965 }, { "epoch": 0.915271838729383, "grad_norm": 0.5416526794433594, "learning_rate": 8.804395998535747e-07, "loss": 4.1541, "step": 29966 }, { "epoch": 0.9153023824068418, "grad_norm": 0.5340256094932556, "learning_rate": 8.798086834952535e-07, "loss": 4.264, "step": 29967 }, { "epoch": 0.9153329260843005, "grad_norm": 0.5383102893829346, "learning_rate": 8.791779892239365e-07, "loss": 4.1666, "step": 29968 }, { "epoch": 0.9153634697617593, "grad_norm": 0.5443533062934875, "learning_rate": 8.785475170454249e-07, "loss": 4.2928, "step": 29969 }, { "epoch": 0.9153940134392181, "grad_norm": 0.5406866669654846, "learning_rate": 8.779172669655306e-07, "loss": 4.2539, "step": 29970 }, { "epoch": 0.9154245571166768, "grad_norm": 0.5503225326538086, "learning_rate": 8.772872389900571e-07, "loss": 4.3702, "step": 29971 }, { "epoch": 0.9154551007941356, "grad_norm": 0.5495643019676208, "learning_rate": 8.766574331247974e-07, "loss": 4.3055, "step": 29972 }, { "epoch": 0.9154856444715944, "grad_norm": 0.5544146299362183, "learning_rate": 8.760278493755574e-07, "loss": 4.2137, "step": 29973 }, { "epoch": 0.9155161881490531, "grad_norm": 0.5383111834526062, "learning_rate": 8.753984877481358e-07, "loss": 4.1992, "step": 29974 }, { "epoch": 0.9155467318265119, "grad_norm": 0.540160596370697, "learning_rate": 8.747693482483193e-07, "loss": 4.2785, "step": 29975 }, { "epoch": 0.9155772755039707, "grad_norm": 0.5394518971443176, "learning_rate": 8.741404308819062e-07, "loss": 4.1647, "step": 29976 }, { "epoch": 0.9156078191814294, "grad_norm": 0.5416259765625, "learning_rate": 8.735117356546918e-07, "loss": 4.3011, "step": 29977 }, { "epoch": 0.9156383628588882, "grad_norm": 0.5370528101921082, "learning_rate": 8.728832625724548e-07, "loss": 4.2104, "step": 29978 }, { "epoch": 0.915668906536347, "grad_norm": 0.5310826897621155, "learning_rate": 8.722550116409878e-07, "loss": 4.2522, "step": 29979 }, { "epoch": 0.9156994502138057, "grad_norm": 0.5489898920059204, "learning_rate": 8.71626982866075e-07, "loss": 4.2972, "step": 29980 }, { "epoch": 0.9157299938912645, "grad_norm": 0.5316219925880432, "learning_rate": 8.709991762534952e-07, "loss": 4.2162, "step": 29981 }, { "epoch": 0.9157605375687232, "grad_norm": 0.543060302734375, "learning_rate": 8.703715918090355e-07, "loss": 4.2033, "step": 29982 }, { "epoch": 0.915791081246182, "grad_norm": 0.5341836214065552, "learning_rate": 8.69744229538469e-07, "loss": 4.1843, "step": 29983 }, { "epoch": 0.9158216249236408, "grad_norm": 0.5432453751564026, "learning_rate": 8.691170894475714e-07, "loss": 4.2324, "step": 29984 }, { "epoch": 0.9158521686010995, "grad_norm": 0.5397934913635254, "learning_rate": 8.684901715421245e-07, "loss": 4.2307, "step": 29985 }, { "epoch": 0.9158827122785583, "grad_norm": 0.5311691164970398, "learning_rate": 8.678634758278903e-07, "loss": 4.2309, "step": 29986 }, { "epoch": 0.9159132559560171, "grad_norm": 0.5432760715484619, "learning_rate": 8.672370023106474e-07, "loss": 4.2062, "step": 29987 }, { "epoch": 0.9159437996334758, "grad_norm": 0.5378558039665222, "learning_rate": 8.666107509961635e-07, "loss": 4.2767, "step": 29988 }, { "epoch": 0.9159743433109346, "grad_norm": 0.5488084554672241, "learning_rate": 8.659847218901979e-07, "loss": 4.2507, "step": 29989 }, { "epoch": 0.9160048869883934, "grad_norm": 0.5337338447570801, "learning_rate": 8.653589149985208e-07, "loss": 4.3346, "step": 29990 }, { "epoch": 0.9160354306658521, "grad_norm": 0.5437413454055786, "learning_rate": 8.647333303268973e-07, "loss": 4.2719, "step": 29991 }, { "epoch": 0.9160659743433109, "grad_norm": 0.5306124091148376, "learning_rate": 8.641079678810782e-07, "loss": 4.1634, "step": 29992 }, { "epoch": 0.9160965180207697, "grad_norm": 0.5428765416145325, "learning_rate": 8.634828276668311e-07, "loss": 4.3018, "step": 29993 }, { "epoch": 0.9161270616982284, "grad_norm": 0.5453405380249023, "learning_rate": 8.628579096899015e-07, "loss": 4.2713, "step": 29994 }, { "epoch": 0.9161576053756872, "grad_norm": 0.5399835705757141, "learning_rate": 8.622332139560541e-07, "loss": 4.1701, "step": 29995 }, { "epoch": 0.916188149053146, "grad_norm": 0.5360457897186279, "learning_rate": 8.616087404710344e-07, "loss": 4.2074, "step": 29996 }, { "epoch": 0.9162186927306047, "grad_norm": 0.5331292748451233, "learning_rate": 8.609844892405933e-07, "loss": 4.181, "step": 29997 }, { "epoch": 0.9162492364080635, "grad_norm": 0.5354067087173462, "learning_rate": 8.60360460270479e-07, "loss": 4.238, "step": 29998 }, { "epoch": 0.9162797800855222, "grad_norm": 0.5326817035675049, "learning_rate": 8.597366535664397e-07, "loss": 4.2733, "step": 29999 }, { "epoch": 0.916310323762981, "grad_norm": 0.5384762287139893, "learning_rate": 8.591130691342125e-07, "loss": 4.1962, "step": 30000 }, { "epoch": 0.9163408674404399, "grad_norm": 0.5504787564277649, "learning_rate": 8.584897069795456e-07, "loss": 4.1515, "step": 30001 }, { "epoch": 0.9163714111178985, "grad_norm": 0.5276365876197815, "learning_rate": 8.578665671081759e-07, "loss": 4.1763, "step": 30002 }, { "epoch": 0.9164019547953574, "grad_norm": 0.5480294227600098, "learning_rate": 8.572436495258407e-07, "loss": 4.1996, "step": 30003 }, { "epoch": 0.9164324984728162, "grad_norm": 0.5396473407745361, "learning_rate": 8.566209542382769e-07, "loss": 4.3098, "step": 30004 }, { "epoch": 0.9164630421502749, "grad_norm": 0.5352142453193665, "learning_rate": 8.55998481251219e-07, "loss": 4.2295, "step": 30005 }, { "epoch": 0.9164935858277337, "grad_norm": 0.5492842793464661, "learning_rate": 8.553762305703927e-07, "loss": 4.2979, "step": 30006 }, { "epoch": 0.9165241295051925, "grad_norm": 0.5458008646965027, "learning_rate": 8.547542022015326e-07, "loss": 4.2751, "step": 30007 }, { "epoch": 0.9165546731826512, "grad_norm": 0.5449216365814209, "learning_rate": 8.541323961503672e-07, "loss": 4.1927, "step": 30008 }, { "epoch": 0.91658521686011, "grad_norm": 0.5399520993232727, "learning_rate": 8.535108124226199e-07, "loss": 4.2627, "step": 30009 }, { "epoch": 0.9166157605375688, "grad_norm": 0.5395204424858093, "learning_rate": 8.528894510240109e-07, "loss": 4.3251, "step": 30010 }, { "epoch": 0.9166463042150275, "grad_norm": 0.5349261164665222, "learning_rate": 8.522683119602664e-07, "loss": 4.1374, "step": 30011 }, { "epoch": 0.9166768478924863, "grad_norm": 0.5550367832183838, "learning_rate": 8.516473952371013e-07, "loss": 4.2651, "step": 30012 }, { "epoch": 0.9167073915699451, "grad_norm": 0.5408240556716919, "learning_rate": 8.51026700860233e-07, "loss": 4.1996, "step": 30013 }, { "epoch": 0.9167379352474038, "grad_norm": 0.5353665947914124, "learning_rate": 8.50406228835382e-07, "loss": 4.2999, "step": 30014 }, { "epoch": 0.9167684789248626, "grad_norm": 0.534452497959137, "learning_rate": 8.497859791682521e-07, "loss": 4.2122, "step": 30015 }, { "epoch": 0.9167990226023213, "grad_norm": 0.5408872961997986, "learning_rate": 8.491659518645667e-07, "loss": 4.2417, "step": 30016 }, { "epoch": 0.9168295662797801, "grad_norm": 0.5462433099746704, "learning_rate": 8.48546146930021e-07, "loss": 4.1932, "step": 30017 }, { "epoch": 0.9168601099572389, "grad_norm": 0.5347154140472412, "learning_rate": 8.479265643703299e-07, "loss": 4.2258, "step": 30018 }, { "epoch": 0.9168906536346976, "grad_norm": 0.5445514917373657, "learning_rate": 8.473072041911973e-07, "loss": 4.2313, "step": 30019 }, { "epoch": 0.9169211973121564, "grad_norm": 0.5328634977340698, "learning_rate": 8.466880663983268e-07, "loss": 4.2947, "step": 30020 }, { "epoch": 0.9169517409896152, "grad_norm": 0.5454590916633606, "learning_rate": 8.46069150997414e-07, "loss": 4.2279, "step": 30021 }, { "epoch": 0.9169822846670739, "grad_norm": 0.5480746626853943, "learning_rate": 8.454504579941652e-07, "loss": 4.3498, "step": 30022 }, { "epoch": 0.9170128283445327, "grad_norm": 0.5412290096282959, "learning_rate": 8.448319873942706e-07, "loss": 4.3221, "step": 30023 }, { "epoch": 0.9170433720219915, "grad_norm": 0.5407236218452454, "learning_rate": 8.442137392034283e-07, "loss": 4.229, "step": 30024 }, { "epoch": 0.9170739156994502, "grad_norm": 0.5497868061065674, "learning_rate": 8.43595713427331e-07, "loss": 4.2005, "step": 30025 }, { "epoch": 0.917104459376909, "grad_norm": 0.5447207093238831, "learning_rate": 8.429779100716656e-07, "loss": 4.3116, "step": 30026 }, { "epoch": 0.9171350030543678, "grad_norm": 0.5413086414337158, "learning_rate": 8.42360329142125e-07, "loss": 4.1358, "step": 30027 }, { "epoch": 0.9171655467318265, "grad_norm": 0.5481472611427307, "learning_rate": 8.417429706443936e-07, "loss": 4.2839, "step": 30028 }, { "epoch": 0.9171960904092853, "grad_norm": 0.5517070889472961, "learning_rate": 8.411258345841528e-07, "loss": 4.2521, "step": 30029 }, { "epoch": 0.9172266340867441, "grad_norm": 0.5440831184387207, "learning_rate": 8.405089209670868e-07, "loss": 4.162, "step": 30030 }, { "epoch": 0.9172571777642028, "grad_norm": 0.5546680092811584, "learning_rate": 8.398922297988831e-07, "loss": 4.31, "step": 30031 }, { "epoch": 0.9172877214416616, "grad_norm": 0.5369184613227844, "learning_rate": 8.392757610852064e-07, "loss": 4.1702, "step": 30032 }, { "epoch": 0.9173182651191203, "grad_norm": 0.5340459942817688, "learning_rate": 8.386595148317467e-07, "loss": 4.228, "step": 30033 }, { "epoch": 0.9173488087965791, "grad_norm": 0.5328902006149292, "learning_rate": 8.38043491044166e-07, "loss": 4.1178, "step": 30034 }, { "epoch": 0.9173793524740379, "grad_norm": 0.5388893485069275, "learning_rate": 8.37427689728143e-07, "loss": 4.2893, "step": 30035 }, { "epoch": 0.9174098961514966, "grad_norm": 0.5326005220413208, "learning_rate": 8.368121108893485e-07, "loss": 4.2124, "step": 30036 }, { "epoch": 0.9174404398289554, "grad_norm": 0.5486278533935547, "learning_rate": 8.361967545334442e-07, "loss": 4.1836, "step": 30037 }, { "epoch": 0.9174709835064142, "grad_norm": 0.5388724207878113, "learning_rate": 8.355816206661038e-07, "loss": 4.2395, "step": 30038 }, { "epoch": 0.9175015271838729, "grad_norm": 0.5402132272720337, "learning_rate": 8.349667092929864e-07, "loss": 4.3167, "step": 30039 }, { "epoch": 0.9175320708613317, "grad_norm": 0.5343481302261353, "learning_rate": 8.343520204197541e-07, "loss": 4.248, "step": 30040 }, { "epoch": 0.9175626145387905, "grad_norm": 0.5348613262176514, "learning_rate": 8.33737554052072e-07, "loss": 4.241, "step": 30041 }, { "epoch": 0.9175931582162492, "grad_norm": 0.5431370735168457, "learning_rate": 8.33123310195591e-07, "loss": 4.2743, "step": 30042 }, { "epoch": 0.917623701893708, "grad_norm": 0.5404887199401855, "learning_rate": 8.325092888559649e-07, "loss": 4.2373, "step": 30043 }, { "epoch": 0.9176542455711668, "grad_norm": 0.5395395159721375, "learning_rate": 8.318954900388559e-07, "loss": 4.2611, "step": 30044 }, { "epoch": 0.9176847892486255, "grad_norm": 0.5436522364616394, "learning_rate": 8.312819137499095e-07, "loss": 4.2633, "step": 30045 }, { "epoch": 0.9177153329260843, "grad_norm": 0.5329990983009338, "learning_rate": 8.306685599947767e-07, "loss": 4.2632, "step": 30046 }, { "epoch": 0.9177458766035431, "grad_norm": 0.5394822359085083, "learning_rate": 8.300554287791029e-07, "loss": 4.2696, "step": 30047 }, { "epoch": 0.9177764202810018, "grad_norm": 0.5406895279884338, "learning_rate": 8.294425201085421e-07, "loss": 4.2545, "step": 30048 }, { "epoch": 0.9178069639584606, "grad_norm": 0.5383464694023132, "learning_rate": 8.288298339887257e-07, "loss": 4.3217, "step": 30049 }, { "epoch": 0.9178375076359193, "grad_norm": 0.5412232875823975, "learning_rate": 8.282173704253049e-07, "loss": 4.3181, "step": 30050 }, { "epoch": 0.9178680513133781, "grad_norm": 0.5399829745292664, "learning_rate": 8.276051294239084e-07, "loss": 4.173, "step": 30051 }, { "epoch": 0.9178985949908369, "grad_norm": 0.5409294366836548, "learning_rate": 8.269931109901847e-07, "loss": 4.2995, "step": 30052 }, { "epoch": 0.9179291386682956, "grad_norm": 0.5472570061683655, "learning_rate": 8.263813151297623e-07, "loss": 4.179, "step": 30053 }, { "epoch": 0.9179596823457544, "grad_norm": 0.5414745807647705, "learning_rate": 8.257697418482757e-07, "loss": 4.2303, "step": 30054 }, { "epoch": 0.9179902260232132, "grad_norm": 0.5392891764640808, "learning_rate": 8.251583911513594e-07, "loss": 4.2339, "step": 30055 }, { "epoch": 0.9180207697006719, "grad_norm": 0.5360494256019592, "learning_rate": 8.245472630446366e-07, "loss": 4.1527, "step": 30056 }, { "epoch": 0.9180513133781307, "grad_norm": 0.5363681316375732, "learning_rate": 8.239363575337389e-07, "loss": 4.1809, "step": 30057 }, { "epoch": 0.9180818570555895, "grad_norm": 0.5391442775726318, "learning_rate": 8.23325674624284e-07, "loss": 4.186, "step": 30058 }, { "epoch": 0.9181124007330482, "grad_norm": 0.5429312586784363, "learning_rate": 8.227152143219063e-07, "loss": 4.2843, "step": 30059 }, { "epoch": 0.918142944410507, "grad_norm": 0.5413423776626587, "learning_rate": 8.221049766322153e-07, "loss": 4.1969, "step": 30060 }, { "epoch": 0.9181734880879658, "grad_norm": 0.5352870225906372, "learning_rate": 8.21494961560837e-07, "loss": 4.1785, "step": 30061 }, { "epoch": 0.9182040317654245, "grad_norm": 0.5421130061149597, "learning_rate": 8.208851691133862e-07, "loss": 4.1484, "step": 30062 }, { "epoch": 0.9182345754428833, "grad_norm": 0.5457395315170288, "learning_rate": 8.20275599295478e-07, "loss": 4.2345, "step": 30063 }, { "epoch": 0.9182651191203421, "grad_norm": 0.5396611094474792, "learning_rate": 8.196662521127218e-07, "loss": 4.2244, "step": 30064 }, { "epoch": 0.9182956627978008, "grad_norm": 0.54085373878479, "learning_rate": 8.190571275707326e-07, "loss": 4.3306, "step": 30065 }, { "epoch": 0.9183262064752596, "grad_norm": 0.5437172055244446, "learning_rate": 8.184482256751169e-07, "loss": 4.2118, "step": 30066 }, { "epoch": 0.9183567501527183, "grad_norm": 0.5292904376983643, "learning_rate": 8.178395464314842e-07, "loss": 4.218, "step": 30067 }, { "epoch": 0.9183872938301771, "grad_norm": 0.5333614945411682, "learning_rate": 8.172310898454299e-07, "loss": 4.2326, "step": 30068 }, { "epoch": 0.918417837507636, "grad_norm": 0.54203861951828, "learning_rate": 8.166228559225664e-07, "loss": 4.2623, "step": 30069 }, { "epoch": 0.9184483811850946, "grad_norm": 0.5429631471633911, "learning_rate": 8.160148446684889e-07, "loss": 4.1499, "step": 30070 }, { "epoch": 0.9184789248625534, "grad_norm": 0.5376062393188477, "learning_rate": 8.154070560887961e-07, "loss": 4.2054, "step": 30071 }, { "epoch": 0.9185094685400123, "grad_norm": 0.5365701913833618, "learning_rate": 8.147994901890887e-07, "loss": 4.2775, "step": 30072 }, { "epoch": 0.918540012217471, "grad_norm": 0.5473949313163757, "learning_rate": 8.141921469749569e-07, "loss": 4.2038, "step": 30073 }, { "epoch": 0.9185705558949298, "grad_norm": 0.5416730642318726, "learning_rate": 8.135850264519907e-07, "loss": 4.2346, "step": 30074 }, { "epoch": 0.9186010995723886, "grad_norm": 0.5444685816764832, "learning_rate": 8.129781286257798e-07, "loss": 4.2474, "step": 30075 }, { "epoch": 0.9186316432498473, "grad_norm": 0.5531109571456909, "learning_rate": 8.1237145350192e-07, "loss": 4.2412, "step": 30076 }, { "epoch": 0.9186621869273061, "grad_norm": 0.5332814455032349, "learning_rate": 8.1176500108599e-07, "loss": 4.2752, "step": 30077 }, { "epoch": 0.9186927306047649, "grad_norm": 0.560123085975647, "learning_rate": 8.111587713835744e-07, "loss": 4.149, "step": 30078 }, { "epoch": 0.9187232742822236, "grad_norm": 0.5523462295532227, "learning_rate": 8.105527644002603e-07, "loss": 4.4036, "step": 30079 }, { "epoch": 0.9187538179596824, "grad_norm": 0.5492538213729858, "learning_rate": 8.09946980141621e-07, "loss": 4.2352, "step": 30080 }, { "epoch": 0.9187843616371412, "grad_norm": 0.5387312769889832, "learning_rate": 8.093414186132381e-07, "loss": 4.2069, "step": 30081 }, { "epoch": 0.9188149053145999, "grad_norm": 0.5360623598098755, "learning_rate": 8.087360798206878e-07, "loss": 4.3018, "step": 30082 }, { "epoch": 0.9188454489920587, "grad_norm": 0.5365385413169861, "learning_rate": 8.081309637695406e-07, "loss": 4.308, "step": 30083 }, { "epoch": 0.9188759926695174, "grad_norm": 0.5277459621429443, "learning_rate": 8.075260704653725e-07, "loss": 4.2244, "step": 30084 }, { "epoch": 0.9189065363469762, "grad_norm": 0.545151948928833, "learning_rate": 8.06921399913746e-07, "loss": 4.2865, "step": 30085 }, { "epoch": 0.918937080024435, "grad_norm": 0.5447747111320496, "learning_rate": 8.063169521202341e-07, "loss": 4.2822, "step": 30086 }, { "epoch": 0.9189676237018937, "grad_norm": 0.5384877920150757, "learning_rate": 8.057127270904046e-07, "loss": 4.2559, "step": 30087 }, { "epoch": 0.9189981673793525, "grad_norm": 0.5546615719795227, "learning_rate": 8.051087248298172e-07, "loss": 4.2781, "step": 30088 }, { "epoch": 0.9190287110568113, "grad_norm": 0.5376670956611633, "learning_rate": 8.045049453440312e-07, "loss": 4.2876, "step": 30089 }, { "epoch": 0.91905925473427, "grad_norm": 0.5492122769355774, "learning_rate": 8.039013886386087e-07, "loss": 4.2148, "step": 30090 }, { "epoch": 0.9190897984117288, "grad_norm": 0.5376339554786682, "learning_rate": 8.032980547191065e-07, "loss": 4.3164, "step": 30091 }, { "epoch": 0.9191203420891876, "grad_norm": 0.5376648902893066, "learning_rate": 8.026949435910786e-07, "loss": 4.2302, "step": 30092 }, { "epoch": 0.9191508857666463, "grad_norm": 0.5465971827507019, "learning_rate": 8.020920552600814e-07, "loss": 4.3363, "step": 30093 }, { "epoch": 0.9191814294441051, "grad_norm": 0.541537344455719, "learning_rate": 8.014893897316634e-07, "loss": 4.2175, "step": 30094 }, { "epoch": 0.9192119731215639, "grad_norm": 0.5401496887207031, "learning_rate": 8.008869470113728e-07, "loss": 4.2623, "step": 30095 }, { "epoch": 0.9192425167990226, "grad_norm": 0.5364915728569031, "learning_rate": 8.002847271047609e-07, "loss": 4.2685, "step": 30096 }, { "epoch": 0.9192730604764814, "grad_norm": 0.5541171431541443, "learning_rate": 7.996827300173676e-07, "loss": 4.2549, "step": 30097 }, { "epoch": 0.9193036041539401, "grad_norm": 0.5318507552146912, "learning_rate": 7.990809557547385e-07, "loss": 4.1528, "step": 30098 }, { "epoch": 0.9193341478313989, "grad_norm": 0.5351061224937439, "learning_rate": 7.984794043224137e-07, "loss": 4.2387, "step": 30099 }, { "epoch": 0.9193646915088577, "grad_norm": 0.536543607711792, "learning_rate": 7.97878075725933e-07, "loss": 4.3072, "step": 30100 }, { "epoch": 0.9193952351863164, "grad_norm": 0.535992443561554, "learning_rate": 7.97276969970831e-07, "loss": 4.2013, "step": 30101 }, { "epoch": 0.9194257788637752, "grad_norm": 0.5474892854690552, "learning_rate": 7.96676087062645e-07, "loss": 4.2297, "step": 30102 }, { "epoch": 0.919456322541234, "grad_norm": 0.5383867621421814, "learning_rate": 7.960754270069065e-07, "loss": 4.2225, "step": 30103 }, { "epoch": 0.9194868662186927, "grad_norm": 0.5348415970802307, "learning_rate": 7.954749898091446e-07, "loss": 4.1724, "step": 30104 }, { "epoch": 0.9195174098961515, "grad_norm": 0.5462570786476135, "learning_rate": 7.948747754748909e-07, "loss": 4.2677, "step": 30105 }, { "epoch": 0.9195479535736103, "grad_norm": 0.5458955764770508, "learning_rate": 7.942747840096687e-07, "loss": 4.2172, "step": 30106 }, { "epoch": 0.919578497251069, "grad_norm": 0.5266650319099426, "learning_rate": 7.93675015419007e-07, "loss": 4.2246, "step": 30107 }, { "epoch": 0.9196090409285278, "grad_norm": 0.5323946475982666, "learning_rate": 7.930754697084208e-07, "loss": 4.0854, "step": 30108 }, { "epoch": 0.9196395846059866, "grad_norm": 0.5335870981216431, "learning_rate": 7.924761468834363e-07, "loss": 4.2591, "step": 30109 }, { "epoch": 0.9196701282834453, "grad_norm": 0.5314416885375977, "learning_rate": 7.918770469495712e-07, "loss": 4.2669, "step": 30110 }, { "epoch": 0.9197006719609041, "grad_norm": 0.5563884973526001, "learning_rate": 7.912781699123406e-07, "loss": 4.1232, "step": 30111 }, { "epoch": 0.9197312156383629, "grad_norm": 0.5436794757843018, "learning_rate": 7.906795157772567e-07, "loss": 4.2322, "step": 30112 }, { "epoch": 0.9197617593158216, "grad_norm": 0.5370625853538513, "learning_rate": 7.900810845498347e-07, "loss": 4.3428, "step": 30113 }, { "epoch": 0.9197923029932804, "grad_norm": 0.5341896414756775, "learning_rate": 7.894828762355838e-07, "loss": 4.3033, "step": 30114 }, { "epoch": 0.9198228466707391, "grad_norm": 0.5340572595596313, "learning_rate": 7.888848908400137e-07, "loss": 4.2804, "step": 30115 }, { "epoch": 0.9198533903481979, "grad_norm": 0.5374202728271484, "learning_rate": 7.882871283686255e-07, "loss": 4.2775, "step": 30116 }, { "epoch": 0.9198839340256567, "grad_norm": 0.5480576157569885, "learning_rate": 7.876895888269259e-07, "loss": 4.1815, "step": 30117 }, { "epoch": 0.9199144777031154, "grad_norm": 0.5489635467529297, "learning_rate": 7.870922722204216e-07, "loss": 4.3041, "step": 30118 }, { "epoch": 0.9199450213805742, "grad_norm": 0.5358465313911438, "learning_rate": 7.864951785546054e-07, "loss": 4.3015, "step": 30119 }, { "epoch": 0.919975565058033, "grad_norm": 0.5237394571304321, "learning_rate": 7.858983078349757e-07, "loss": 4.1991, "step": 30120 }, { "epoch": 0.9200061087354917, "grad_norm": 0.5273293256759644, "learning_rate": 7.853016600670338e-07, "loss": 4.2134, "step": 30121 }, { "epoch": 0.9200366524129505, "grad_norm": 0.5362922549247742, "learning_rate": 7.847052352562668e-07, "loss": 4.3173, "step": 30122 }, { "epoch": 0.9200671960904093, "grad_norm": 0.5329052209854126, "learning_rate": 7.841090334081675e-07, "loss": 4.2491, "step": 30123 }, { "epoch": 0.920097739767868, "grad_norm": 0.5373199582099915, "learning_rate": 7.835130545282287e-07, "loss": 4.3323, "step": 30124 }, { "epoch": 0.9201282834453268, "grad_norm": 0.5434773564338684, "learning_rate": 7.829172986219352e-07, "loss": 4.1845, "step": 30125 }, { "epoch": 0.9201588271227856, "grad_norm": 0.5414265990257263, "learning_rate": 7.82321765694774e-07, "loss": 4.2655, "step": 30126 }, { "epoch": 0.9201893708002443, "grad_norm": 0.5448581576347351, "learning_rate": 7.817264557522297e-07, "loss": 4.3842, "step": 30127 }, { "epoch": 0.9202199144777031, "grad_norm": 0.5570494532585144, "learning_rate": 7.811313687997785e-07, "loss": 4.3248, "step": 30128 }, { "epoch": 0.9202504581551619, "grad_norm": 0.542582094669342, "learning_rate": 7.80536504842902e-07, "loss": 4.1855, "step": 30129 }, { "epoch": 0.9202810018326206, "grad_norm": 0.5457533001899719, "learning_rate": 7.79941863887082e-07, "loss": 4.2823, "step": 30130 }, { "epoch": 0.9203115455100794, "grad_norm": 0.5386358499526978, "learning_rate": 7.793474459377892e-07, "loss": 4.2864, "step": 30131 }, { "epoch": 0.9203420891875381, "grad_norm": 0.5316039323806763, "learning_rate": 7.787532510004969e-07, "loss": 4.2665, "step": 30132 }, { "epoch": 0.9203726328649969, "grad_norm": 0.5325855016708374, "learning_rate": 7.781592790806758e-07, "loss": 4.254, "step": 30133 }, { "epoch": 0.9204031765424557, "grad_norm": 0.5379498600959778, "learning_rate": 7.775655301837991e-07, "loss": 4.2917, "step": 30134 }, { "epoch": 0.9204337202199144, "grad_norm": 0.5391603708267212, "learning_rate": 7.769720043153267e-07, "loss": 4.2652, "step": 30135 }, { "epoch": 0.9204642638973732, "grad_norm": 0.541030764579773, "learning_rate": 7.763787014807289e-07, "loss": 4.3282, "step": 30136 }, { "epoch": 0.920494807574832, "grad_norm": 0.5457220673561096, "learning_rate": 7.757856216854681e-07, "loss": 4.2191, "step": 30137 }, { "epoch": 0.9205253512522907, "grad_norm": 0.533751368522644, "learning_rate": 7.751927649350038e-07, "loss": 4.21, "step": 30138 }, { "epoch": 0.9205558949297495, "grad_norm": 0.5379401445388794, "learning_rate": 7.746001312347928e-07, "loss": 4.291, "step": 30139 }, { "epoch": 0.9205864386072083, "grad_norm": 0.5439754128456116, "learning_rate": 7.740077205902918e-07, "loss": 4.1755, "step": 30140 }, { "epoch": 0.920616982284667, "grad_norm": 0.5393325090408325, "learning_rate": 7.734155330069631e-07, "loss": 4.2614, "step": 30141 }, { "epoch": 0.9206475259621258, "grad_norm": 0.5418540835380554, "learning_rate": 7.728235684902496e-07, "loss": 4.2365, "step": 30142 }, { "epoch": 0.9206780696395847, "grad_norm": 0.5382347702980042, "learning_rate": 7.722318270456052e-07, "loss": 4.278, "step": 30143 }, { "epoch": 0.9207086133170433, "grad_norm": 0.5473703145980835, "learning_rate": 7.71640308678484e-07, "loss": 4.1596, "step": 30144 }, { "epoch": 0.9207391569945022, "grad_norm": 0.5314816236495972, "learning_rate": 7.710490133943232e-07, "loss": 4.2321, "step": 30145 }, { "epoch": 0.920769700671961, "grad_norm": 0.5371547937393188, "learning_rate": 7.704579411985713e-07, "loss": 4.2112, "step": 30146 }, { "epoch": 0.9208002443494196, "grad_norm": 0.544863760471344, "learning_rate": 7.698670920966739e-07, "loss": 4.2494, "step": 30147 }, { "epoch": 0.9208307880268785, "grad_norm": 0.5486980080604553, "learning_rate": 7.692764660940654e-07, "loss": 4.2251, "step": 30148 }, { "epoch": 0.9208613317043371, "grad_norm": 0.5348631143569946, "learning_rate": 7.686860631961889e-07, "loss": 4.1924, "step": 30149 }, { "epoch": 0.920891875381796, "grad_norm": 0.5683534741401672, "learning_rate": 7.680958834084761e-07, "loss": 4.2255, "step": 30150 }, { "epoch": 0.9209224190592548, "grad_norm": 0.5470377802848816, "learning_rate": 7.675059267363671e-07, "loss": 4.2364, "step": 30151 }, { "epoch": 0.9209529627367135, "grad_norm": 0.5354524254798889, "learning_rate": 7.66916193185288e-07, "loss": 4.2427, "step": 30152 }, { "epoch": 0.9209835064141723, "grad_norm": 0.5393096208572388, "learning_rate": 7.663266827606707e-07, "loss": 4.2637, "step": 30153 }, { "epoch": 0.9210140500916311, "grad_norm": 0.5363968014717102, "learning_rate": 7.657373954679414e-07, "loss": 4.2016, "step": 30154 }, { "epoch": 0.9210445937690898, "grad_norm": 0.5393890142440796, "learning_rate": 7.651483313125291e-07, "loss": 4.2417, "step": 30155 }, { "epoch": 0.9210751374465486, "grad_norm": 0.5355798006057739, "learning_rate": 7.64559490299857e-07, "loss": 4.2202, "step": 30156 }, { "epoch": 0.9211056811240074, "grad_norm": 0.5371939539909363, "learning_rate": 7.639708724353462e-07, "loss": 4.1552, "step": 30157 }, { "epoch": 0.9211362248014661, "grad_norm": 0.5541199445724487, "learning_rate": 7.633824777244169e-07, "loss": 4.2561, "step": 30158 }, { "epoch": 0.9211667684789249, "grad_norm": 0.5404513478279114, "learning_rate": 7.627943061724846e-07, "loss": 4.2269, "step": 30159 }, { "epoch": 0.9211973121563837, "grad_norm": 0.5397822260856628, "learning_rate": 7.62206357784967e-07, "loss": 4.283, "step": 30160 }, { "epoch": 0.9212278558338424, "grad_norm": 0.5437715649604797, "learning_rate": 7.616186325672791e-07, "loss": 4.2969, "step": 30161 }, { "epoch": 0.9212583995113012, "grad_norm": 0.5384669899940491, "learning_rate": 7.610311305248308e-07, "loss": 4.3172, "step": 30162 }, { "epoch": 0.92128894318876, "grad_norm": 0.542220413684845, "learning_rate": 7.604438516630286e-07, "loss": 4.3351, "step": 30163 }, { "epoch": 0.9213194868662187, "grad_norm": 0.5456938743591309, "learning_rate": 7.598567959872849e-07, "loss": 4.3022, "step": 30164 }, { "epoch": 0.9213500305436775, "grad_norm": 0.5338190793991089, "learning_rate": 7.592699635030037e-07, "loss": 4.3125, "step": 30165 }, { "epoch": 0.9213805742211362, "grad_norm": 0.5419740676879883, "learning_rate": 7.586833542155835e-07, "loss": 4.3028, "step": 30166 }, { "epoch": 0.921411117898595, "grad_norm": 0.5381286144256592, "learning_rate": 7.58096968130434e-07, "loss": 4.2793, "step": 30167 }, { "epoch": 0.9214416615760538, "grad_norm": 0.5426186323165894, "learning_rate": 7.575108052529478e-07, "loss": 4.2507, "step": 30168 }, { "epoch": 0.9214722052535125, "grad_norm": 0.5387921929359436, "learning_rate": 7.569248655885236e-07, "loss": 4.3783, "step": 30169 }, { "epoch": 0.9215027489309713, "grad_norm": 0.5516935586929321, "learning_rate": 7.563391491425543e-07, "loss": 4.247, "step": 30170 }, { "epoch": 0.9215332926084301, "grad_norm": 0.5637854337692261, "learning_rate": 7.557536559204381e-07, "loss": 4.2502, "step": 30171 }, { "epoch": 0.9215638362858888, "grad_norm": 0.5297351479530334, "learning_rate": 7.551683859275627e-07, "loss": 4.273, "step": 30172 }, { "epoch": 0.9215943799633476, "grad_norm": 0.5462613105773926, "learning_rate": 7.545833391693152e-07, "loss": 4.3231, "step": 30173 }, { "epoch": 0.9216249236408064, "grad_norm": 0.54515540599823, "learning_rate": 7.53998515651086e-07, "loss": 4.2509, "step": 30174 }, { "epoch": 0.9216554673182651, "grad_norm": 0.5463672280311584, "learning_rate": 7.534139153782621e-07, "loss": 4.3218, "step": 30175 }, { "epoch": 0.9216860109957239, "grad_norm": 0.5311451554298401, "learning_rate": 7.528295383562173e-07, "loss": 4.1701, "step": 30176 }, { "epoch": 0.9217165546731827, "grad_norm": 0.5392712950706482, "learning_rate": 7.522453845903387e-07, "loss": 4.2853, "step": 30177 }, { "epoch": 0.9217470983506414, "grad_norm": 0.5360833406448364, "learning_rate": 7.516614540860084e-07, "loss": 4.2745, "step": 30178 }, { "epoch": 0.9217776420281002, "grad_norm": 0.5449299216270447, "learning_rate": 7.510777468485941e-07, "loss": 4.2033, "step": 30179 }, { "epoch": 0.921808185705559, "grad_norm": 0.5419668555259705, "learning_rate": 7.504942628834749e-07, "loss": 4.2496, "step": 30180 }, { "epoch": 0.9218387293830177, "grad_norm": 0.5303663611412048, "learning_rate": 7.499110021960243e-07, "loss": 4.1976, "step": 30181 }, { "epoch": 0.9218692730604765, "grad_norm": 0.5450571179389954, "learning_rate": 7.493279647916102e-07, "loss": 4.2062, "step": 30182 }, { "epoch": 0.9218998167379352, "grad_norm": 0.5398207306861877, "learning_rate": 7.48745150675606e-07, "loss": 4.2803, "step": 30183 }, { "epoch": 0.921930360415394, "grad_norm": 0.5455742478370667, "learning_rate": 7.481625598533687e-07, "loss": 4.2679, "step": 30184 }, { "epoch": 0.9219609040928528, "grad_norm": 0.5426114201545715, "learning_rate": 7.475801923302689e-07, "loss": 4.1783, "step": 30185 }, { "epoch": 0.9219914477703115, "grad_norm": 0.5345029234886169, "learning_rate": 7.469980481116689e-07, "loss": 4.2997, "step": 30186 }, { "epoch": 0.9220219914477703, "grad_norm": 0.546900749206543, "learning_rate": 7.464161272029257e-07, "loss": 4.1495, "step": 30187 }, { "epoch": 0.9220525351252291, "grad_norm": 0.5408920049667358, "learning_rate": 7.458344296093989e-07, "loss": 4.1784, "step": 30188 }, { "epoch": 0.9220830788026878, "grad_norm": 0.5431793332099915, "learning_rate": 7.45252955336448e-07, "loss": 4.2766, "step": 30189 }, { "epoch": 0.9221136224801466, "grad_norm": 0.5273508429527283, "learning_rate": 7.446717043894186e-07, "loss": 4.1538, "step": 30190 }, { "epoch": 0.9221441661576054, "grad_norm": 0.5444768071174622, "learning_rate": 7.440906767736705e-07, "loss": 4.2368, "step": 30191 }, { "epoch": 0.9221747098350641, "grad_norm": 0.5462663173675537, "learning_rate": 7.435098724945521e-07, "loss": 4.249, "step": 30192 }, { "epoch": 0.9222052535125229, "grad_norm": 0.540320873260498, "learning_rate": 7.429292915574065e-07, "loss": 4.1862, "step": 30193 }, { "epoch": 0.9222357971899817, "grad_norm": 0.5387220978736877, "learning_rate": 7.423489339675849e-07, "loss": 4.1526, "step": 30194 }, { "epoch": 0.9222663408674404, "grad_norm": 0.539222240447998, "learning_rate": 7.417687997304301e-07, "loss": 4.3296, "step": 30195 }, { "epoch": 0.9222968845448992, "grad_norm": 0.5565441250801086, "learning_rate": 7.411888888512797e-07, "loss": 4.2878, "step": 30196 }, { "epoch": 0.922327428222358, "grad_norm": 0.5422361493110657, "learning_rate": 7.406092013354793e-07, "loss": 4.2702, "step": 30197 }, { "epoch": 0.9223579718998167, "grad_norm": 0.5353508591651917, "learning_rate": 7.400297371883607e-07, "loss": 4.1945, "step": 30198 }, { "epoch": 0.9223885155772755, "grad_norm": 0.5398227572441101, "learning_rate": 7.394504964152616e-07, "loss": 4.1946, "step": 30199 }, { "epoch": 0.9224190592547342, "grad_norm": 0.5438676476478577, "learning_rate": 7.388714790215162e-07, "loss": 4.2935, "step": 30200 }, { "epoch": 0.922449602932193, "grad_norm": 0.5390154719352722, "learning_rate": 7.382926850124538e-07, "loss": 4.3145, "step": 30201 }, { "epoch": 0.9224801466096518, "grad_norm": 0.5369040369987488, "learning_rate": 7.377141143934035e-07, "loss": 4.254, "step": 30202 }, { "epoch": 0.9225106902871105, "grad_norm": 0.5429297089576721, "learning_rate": 7.371357671696972e-07, "loss": 4.2077, "step": 30203 }, { "epoch": 0.9225412339645693, "grad_norm": 0.5388301610946655, "learning_rate": 7.365576433466525e-07, "loss": 4.2318, "step": 30204 }, { "epoch": 0.9225717776420281, "grad_norm": 0.5256545543670654, "learning_rate": 7.359797429295961e-07, "loss": 4.1792, "step": 30205 }, { "epoch": 0.9226023213194868, "grad_norm": 0.5318673253059387, "learning_rate": 7.354020659238542e-07, "loss": 4.2966, "step": 30206 }, { "epoch": 0.9226328649969456, "grad_norm": 0.5563167929649353, "learning_rate": 7.348246123347391e-07, "loss": 4.3317, "step": 30207 }, { "epoch": 0.9226634086744044, "grad_norm": 0.5390856266021729, "learning_rate": 7.342473821675689e-07, "loss": 4.3318, "step": 30208 }, { "epoch": 0.9226939523518631, "grad_norm": 0.5406957864761353, "learning_rate": 7.336703754276614e-07, "loss": 4.2669, "step": 30209 }, { "epoch": 0.9227244960293219, "grad_norm": 0.5404450297355652, "learning_rate": 7.330935921203235e-07, "loss": 4.3006, "step": 30210 }, { "epoch": 0.9227550397067807, "grad_norm": 0.5373772978782654, "learning_rate": 7.325170322508706e-07, "loss": 4.1892, "step": 30211 }, { "epoch": 0.9227855833842394, "grad_norm": 0.5416747331619263, "learning_rate": 7.31940695824615e-07, "loss": 4.2535, "step": 30212 }, { "epoch": 0.9228161270616982, "grad_norm": 0.5343784689903259, "learning_rate": 7.313645828468551e-07, "loss": 4.2277, "step": 30213 }, { "epoch": 0.922846670739157, "grad_norm": 0.5390113592147827, "learning_rate": 7.307886933229008e-07, "loss": 4.2266, "step": 30214 }, { "epoch": 0.9228772144166157, "grad_norm": 0.5429314374923706, "learning_rate": 7.302130272580532e-07, "loss": 4.266, "step": 30215 }, { "epoch": 0.9229077580940745, "grad_norm": 0.5380094051361084, "learning_rate": 7.296375846576109e-07, "loss": 4.1891, "step": 30216 }, { "epoch": 0.9229383017715332, "grad_norm": 0.531857967376709, "learning_rate": 7.290623655268752e-07, "loss": 4.1517, "step": 30217 }, { "epoch": 0.922968845448992, "grad_norm": 0.5408108234405518, "learning_rate": 7.284873698711392e-07, "loss": 4.1955, "step": 30218 }, { "epoch": 0.9229993891264509, "grad_norm": 0.5363494157791138, "learning_rate": 7.279125976956986e-07, "loss": 4.311, "step": 30219 }, { "epoch": 0.9230299328039095, "grad_norm": 0.5389130711555481, "learning_rate": 7.27338049005849e-07, "loss": 4.2353, "step": 30220 }, { "epoch": 0.9230604764813684, "grad_norm": 0.5406259894371033, "learning_rate": 7.267637238068753e-07, "loss": 4.3148, "step": 30221 }, { "epoch": 0.9230910201588272, "grad_norm": 0.5441179871559143, "learning_rate": 7.261896221040704e-07, "loss": 4.2052, "step": 30222 }, { "epoch": 0.9231215638362859, "grad_norm": 0.5325833559036255, "learning_rate": 7.256157439027162e-07, "loss": 4.2026, "step": 30223 }, { "epoch": 0.9231521075137447, "grad_norm": 0.5329098701477051, "learning_rate": 7.250420892081001e-07, "loss": 4.2576, "step": 30224 }, { "epoch": 0.9231826511912035, "grad_norm": 0.5406657457351685, "learning_rate": 7.244686580255011e-07, "loss": 4.1893, "step": 30225 }, { "epoch": 0.9232131948686622, "grad_norm": 0.5437902212142944, "learning_rate": 7.238954503602014e-07, "loss": 4.3265, "step": 30226 }, { "epoch": 0.923243738546121, "grad_norm": 0.5464355945587158, "learning_rate": 7.23322466217477e-07, "loss": 4.2453, "step": 30227 }, { "epoch": 0.9232742822235798, "grad_norm": 0.5465424060821533, "learning_rate": 7.227497056026045e-07, "loss": 4.2496, "step": 30228 }, { "epoch": 0.9233048259010385, "grad_norm": 0.5401867032051086, "learning_rate": 7.221771685208601e-07, "loss": 4.1965, "step": 30229 }, { "epoch": 0.9233353695784973, "grad_norm": 0.5380569696426392, "learning_rate": 7.21604854977509e-07, "loss": 4.0756, "step": 30230 }, { "epoch": 0.9233659132559561, "grad_norm": 0.5291113257408142, "learning_rate": 7.210327649778276e-07, "loss": 4.1904, "step": 30231 }, { "epoch": 0.9233964569334148, "grad_norm": 0.5355595350265503, "learning_rate": 7.204608985270811e-07, "loss": 4.2443, "step": 30232 }, { "epoch": 0.9234270006108736, "grad_norm": 0.5311578512191772, "learning_rate": 7.198892556305292e-07, "loss": 4.1685, "step": 30233 }, { "epoch": 0.9234575442883323, "grad_norm": 0.545585036277771, "learning_rate": 7.193178362934483e-07, "loss": 4.1961, "step": 30234 }, { "epoch": 0.9234880879657911, "grad_norm": 0.5393211841583252, "learning_rate": 7.187466405210841e-07, "loss": 4.3603, "step": 30235 }, { "epoch": 0.9235186316432499, "grad_norm": 0.545099675655365, "learning_rate": 7.181756683187074e-07, "loss": 4.1937, "step": 30236 }, { "epoch": 0.9235491753207086, "grad_norm": 0.5413538217544556, "learning_rate": 7.176049196915724e-07, "loss": 4.2326, "step": 30237 }, { "epoch": 0.9235797189981674, "grad_norm": 0.5418756604194641, "learning_rate": 7.170343946449331e-07, "loss": 4.1428, "step": 30238 }, { "epoch": 0.9236102626756262, "grad_norm": 0.5375291705131531, "learning_rate": 7.16464093184041e-07, "loss": 4.2835, "step": 30239 }, { "epoch": 0.9236408063530849, "grad_norm": 0.5433512330055237, "learning_rate": 7.15894015314153e-07, "loss": 4.4024, "step": 30240 }, { "epoch": 0.9236713500305437, "grad_norm": 0.5478798747062683, "learning_rate": 7.15324161040512e-07, "loss": 4.2853, "step": 30241 }, { "epoch": 0.9237018937080025, "grad_norm": 0.5420944094657898, "learning_rate": 7.147545303683695e-07, "loss": 4.099, "step": 30242 }, { "epoch": 0.9237324373854612, "grad_norm": 0.5398492813110352, "learning_rate": 7.141851233029683e-07, "loss": 4.2916, "step": 30243 }, { "epoch": 0.92376298106292, "grad_norm": 0.5421462059020996, "learning_rate": 7.136159398495518e-07, "loss": 4.278, "step": 30244 }, { "epoch": 0.9237935247403788, "grad_norm": 0.5298044681549072, "learning_rate": 7.130469800133571e-07, "loss": 4.2646, "step": 30245 }, { "epoch": 0.9238240684178375, "grad_norm": 0.538443386554718, "learning_rate": 7.124782437996275e-07, "loss": 4.2654, "step": 30246 }, { "epoch": 0.9238546120952963, "grad_norm": 0.5420747995376587, "learning_rate": 7.119097312135975e-07, "loss": 4.3157, "step": 30247 }, { "epoch": 0.923885155772755, "grad_norm": 0.5369430184364319, "learning_rate": 7.113414422605047e-07, "loss": 4.1246, "step": 30248 }, { "epoch": 0.9239156994502138, "grad_norm": 0.5499420166015625, "learning_rate": 7.107733769455754e-07, "loss": 4.2826, "step": 30249 }, { "epoch": 0.9239462431276726, "grad_norm": 0.5359364748001099, "learning_rate": 7.102055352740444e-07, "loss": 4.2767, "step": 30250 }, { "epoch": 0.9239767868051313, "grad_norm": 0.5361760854721069, "learning_rate": 7.096379172511436e-07, "loss": 4.1606, "step": 30251 }, { "epoch": 0.9240073304825901, "grad_norm": 0.542641282081604, "learning_rate": 7.090705228820909e-07, "loss": 4.3008, "step": 30252 }, { "epoch": 0.9240378741600489, "grad_norm": 0.5378396511077881, "learning_rate": 7.085033521721157e-07, "loss": 4.2775, "step": 30253 }, { "epoch": 0.9240684178375076, "grad_norm": 0.5366104245185852, "learning_rate": 7.079364051264414e-07, "loss": 4.1934, "step": 30254 }, { "epoch": 0.9240989615149664, "grad_norm": 0.5411900877952576, "learning_rate": 7.073696817502861e-07, "loss": 4.2703, "step": 30255 }, { "epoch": 0.9241295051924252, "grad_norm": 0.5407072305679321, "learning_rate": 7.068031820488652e-07, "loss": 4.2528, "step": 30256 }, { "epoch": 0.9241600488698839, "grad_norm": 0.5406691431999207, "learning_rate": 7.062369060274021e-07, "loss": 4.2789, "step": 30257 }, { "epoch": 0.9241905925473427, "grad_norm": 0.5343035459518433, "learning_rate": 7.056708536911038e-07, "loss": 4.2306, "step": 30258 }, { "epoch": 0.9242211362248015, "grad_norm": 0.5431945323944092, "learning_rate": 7.051050250451885e-07, "loss": 4.2488, "step": 30259 }, { "epoch": 0.9242516799022602, "grad_norm": 0.5431735515594482, "learning_rate": 7.045394200948574e-07, "loss": 4.2441, "step": 30260 }, { "epoch": 0.924282223579719, "grad_norm": 0.547902524471283, "learning_rate": 7.039740388453286e-07, "loss": 4.287, "step": 30261 }, { "epoch": 0.9243127672571778, "grad_norm": 0.5466777682304382, "learning_rate": 7.034088813017981e-07, "loss": 4.2303, "step": 30262 }, { "epoch": 0.9243433109346365, "grad_norm": 0.5562000870704651, "learning_rate": 7.028439474694781e-07, "loss": 4.2854, "step": 30263 }, { "epoch": 0.9243738546120953, "grad_norm": 0.5470778942108154, "learning_rate": 7.022792373535619e-07, "loss": 4.2059, "step": 30264 }, { "epoch": 0.924404398289554, "grad_norm": 0.5356627106666565, "learning_rate": 7.017147509592565e-07, "loss": 4.1972, "step": 30265 }, { "epoch": 0.9244349419670128, "grad_norm": 0.551150381565094, "learning_rate": 7.011504882917547e-07, "loss": 4.2763, "step": 30266 }, { "epoch": 0.9244654856444716, "grad_norm": 0.5387298464775085, "learning_rate": 7.005864493562525e-07, "loss": 4.2587, "step": 30267 }, { "epoch": 0.9244960293219303, "grad_norm": 0.5374043583869934, "learning_rate": 7.000226341579458e-07, "loss": 4.1695, "step": 30268 }, { "epoch": 0.9245265729993891, "grad_norm": 0.5421648025512695, "learning_rate": 6.994590427020247e-07, "loss": 4.1286, "step": 30269 }, { "epoch": 0.9245571166768479, "grad_norm": 0.5384442806243896, "learning_rate": 6.98895674993677e-07, "loss": 4.1781, "step": 30270 }, { "epoch": 0.9245876603543066, "grad_norm": 0.5367587208747864, "learning_rate": 6.983325310380928e-07, "loss": 4.149, "step": 30271 }, { "epoch": 0.9246182040317654, "grad_norm": 0.5429978370666504, "learning_rate": 6.977696108404541e-07, "loss": 4.1837, "step": 30272 }, { "epoch": 0.9246487477092242, "grad_norm": 0.5385275483131409, "learning_rate": 6.972069144059457e-07, "loss": 4.1958, "step": 30273 }, { "epoch": 0.9246792913866829, "grad_norm": 0.5468604564666748, "learning_rate": 6.966444417397522e-07, "loss": 4.2477, "step": 30274 }, { "epoch": 0.9247098350641417, "grad_norm": 0.5455518364906311, "learning_rate": 6.960821928470473e-07, "loss": 4.1586, "step": 30275 }, { "epoch": 0.9247403787416005, "grad_norm": 0.5423122644424438, "learning_rate": 6.955201677330075e-07, "loss": 4.2785, "step": 30276 }, { "epoch": 0.9247709224190592, "grad_norm": 0.5526497960090637, "learning_rate": 6.94958366402812e-07, "loss": 4.1308, "step": 30277 }, { "epoch": 0.924801466096518, "grad_norm": 0.5577557682991028, "learning_rate": 6.943967888616288e-07, "loss": 4.2227, "step": 30278 }, { "epoch": 0.9248320097739768, "grad_norm": 0.5406444072723389, "learning_rate": 6.938354351146314e-07, "loss": 4.2315, "step": 30279 }, { "epoch": 0.9248625534514355, "grad_norm": 0.5408860445022583, "learning_rate": 6.93274305166991e-07, "loss": 4.2901, "step": 30280 }, { "epoch": 0.9248930971288943, "grad_norm": 0.5494334101676941, "learning_rate": 6.927133990238671e-07, "loss": 4.2656, "step": 30281 }, { "epoch": 0.924923640806353, "grad_norm": 0.5410646200180054, "learning_rate": 6.921527166904307e-07, "loss": 4.3143, "step": 30282 }, { "epoch": 0.9249541844838118, "grad_norm": 0.5445473194122314, "learning_rate": 6.915922581718414e-07, "loss": 4.2709, "step": 30283 }, { "epoch": 0.9249847281612706, "grad_norm": 0.5405327677726746, "learning_rate": 6.910320234732593e-07, "loss": 4.1837, "step": 30284 }, { "epoch": 0.9250152718387293, "grad_norm": 0.5399514436721802, "learning_rate": 6.904720125998465e-07, "loss": 4.3023, "step": 30285 }, { "epoch": 0.9250458155161881, "grad_norm": 0.5428220629692078, "learning_rate": 6.899122255567547e-07, "loss": 4.2053, "step": 30286 }, { "epoch": 0.925076359193647, "grad_norm": 0.5434588193893433, "learning_rate": 6.893526623491409e-07, "loss": 4.2666, "step": 30287 }, { "epoch": 0.9251069028711056, "grad_norm": 0.5384628176689148, "learning_rate": 6.887933229821564e-07, "loss": 4.2301, "step": 30288 }, { "epoch": 0.9251374465485644, "grad_norm": 0.537873387336731, "learning_rate": 6.8823420746095e-07, "loss": 4.2923, "step": 30289 }, { "epoch": 0.9251679902260233, "grad_norm": 0.5471452474594116, "learning_rate": 6.876753157906756e-07, "loss": 4.314, "step": 30290 }, { "epoch": 0.925198533903482, "grad_norm": 0.5512984395027161, "learning_rate": 6.871166479764685e-07, "loss": 4.2169, "step": 30291 }, { "epoch": 0.9252290775809408, "grad_norm": 0.5376979112625122, "learning_rate": 6.865582040234853e-07, "loss": 4.231, "step": 30292 }, { "epoch": 0.9252596212583996, "grad_norm": 0.5386693477630615, "learning_rate": 6.859999839368553e-07, "loss": 4.2525, "step": 30293 }, { "epoch": 0.9252901649358583, "grad_norm": 0.5373440384864807, "learning_rate": 6.8544198772173e-07, "loss": 4.3024, "step": 30294 }, { "epoch": 0.9253207086133171, "grad_norm": 0.5341577529907227, "learning_rate": 6.848842153832386e-07, "loss": 4.1644, "step": 30295 }, { "epoch": 0.9253512522907759, "grad_norm": 0.5457087159156799, "learning_rate": 6.843266669265186e-07, "loss": 4.2157, "step": 30296 }, { "epoch": 0.9253817959682346, "grad_norm": 0.5347622632980347, "learning_rate": 6.837693423567077e-07, "loss": 4.1939, "step": 30297 }, { "epoch": 0.9254123396456934, "grad_norm": 0.5471875667572021, "learning_rate": 6.832122416789322e-07, "loss": 4.2644, "step": 30298 }, { "epoch": 0.925442883323152, "grad_norm": 0.5502838492393494, "learning_rate": 6.82655364898327e-07, "loss": 4.2771, "step": 30299 }, { "epoch": 0.9254734270006109, "grad_norm": 0.5467242002487183, "learning_rate": 6.820987120200128e-07, "loss": 4.252, "step": 30300 }, { "epoch": 0.9255039706780697, "grad_norm": 0.5345280766487122, "learning_rate": 6.815422830491191e-07, "loss": 4.2489, "step": 30301 }, { "epoch": 0.9255345143555284, "grad_norm": 0.5412507653236389, "learning_rate": 6.809860779907723e-07, "loss": 4.3108, "step": 30302 }, { "epoch": 0.9255650580329872, "grad_norm": 0.5470754504203796, "learning_rate": 6.804300968500877e-07, "loss": 4.2111, "step": 30303 }, { "epoch": 0.925595601710446, "grad_norm": 0.5405928492546082, "learning_rate": 6.79874339632186e-07, "loss": 4.29, "step": 30304 }, { "epoch": 0.9256261453879047, "grad_norm": 0.5437327027320862, "learning_rate": 6.793188063421884e-07, "loss": 4.2601, "step": 30305 }, { "epoch": 0.9256566890653635, "grad_norm": 0.5479752421379089, "learning_rate": 6.787634969852047e-07, "loss": 4.1773, "step": 30306 }, { "epoch": 0.9256872327428223, "grad_norm": 0.5445454716682434, "learning_rate": 6.782084115663528e-07, "loss": 4.3031, "step": 30307 }, { "epoch": 0.925717776420281, "grad_norm": 0.5298299193382263, "learning_rate": 6.776535500907427e-07, "loss": 4.2384, "step": 30308 }, { "epoch": 0.9257483200977398, "grad_norm": 0.5445855259895325, "learning_rate": 6.770989125634758e-07, "loss": 4.1765, "step": 30309 }, { "epoch": 0.9257788637751986, "grad_norm": 0.5400585532188416, "learning_rate": 6.765444989896674e-07, "loss": 4.248, "step": 30310 }, { "epoch": 0.9258094074526573, "grad_norm": 0.5331843495368958, "learning_rate": 6.759903093744219e-07, "loss": 4.2272, "step": 30311 }, { "epoch": 0.9258399511301161, "grad_norm": 0.540306031703949, "learning_rate": 6.754363437228378e-07, "loss": 4.2475, "step": 30312 }, { "epoch": 0.9258704948075749, "grad_norm": 0.5519540309906006, "learning_rate": 6.748826020400168e-07, "loss": 4.2771, "step": 30313 }, { "epoch": 0.9259010384850336, "grad_norm": 0.5384891629219055, "learning_rate": 6.743290843310602e-07, "loss": 4.2136, "step": 30314 }, { "epoch": 0.9259315821624924, "grad_norm": 0.5446702837944031, "learning_rate": 6.737757906010611e-07, "loss": 4.141, "step": 30315 }, { "epoch": 0.9259621258399511, "grad_norm": 0.5468188524246216, "learning_rate": 6.732227208551184e-07, "loss": 4.2927, "step": 30316 }, { "epoch": 0.9259926695174099, "grad_norm": 0.5456528067588806, "learning_rate": 6.726698750983168e-07, "loss": 4.2939, "step": 30317 }, { "epoch": 0.9260232131948687, "grad_norm": 0.5308946371078491, "learning_rate": 6.721172533357551e-07, "loss": 4.2142, "step": 30318 }, { "epoch": 0.9260537568723274, "grad_norm": 0.5408042073249817, "learning_rate": 6.715648555725179e-07, "loss": 4.2673, "step": 30319 }, { "epoch": 0.9260843005497862, "grad_norm": 0.5381773710250854, "learning_rate": 6.710126818136903e-07, "loss": 4.1033, "step": 30320 }, { "epoch": 0.926114844227245, "grad_norm": 0.5357599854469299, "learning_rate": 6.704607320643569e-07, "loss": 4.3241, "step": 30321 }, { "epoch": 0.9261453879047037, "grad_norm": 0.5369138717651367, "learning_rate": 6.699090063296026e-07, "loss": 4.2158, "step": 30322 }, { "epoch": 0.9261759315821625, "grad_norm": 0.5419740676879883, "learning_rate": 6.693575046145067e-07, "loss": 4.1153, "step": 30323 }, { "epoch": 0.9262064752596213, "grad_norm": 0.5452011823654175, "learning_rate": 6.68806226924143e-07, "loss": 4.2166, "step": 30324 }, { "epoch": 0.92623701893708, "grad_norm": 0.5374305844306946, "learning_rate": 6.682551732635933e-07, "loss": 4.2476, "step": 30325 }, { "epoch": 0.9262675626145388, "grad_norm": 0.5478960871696472, "learning_rate": 6.67704343637926e-07, "loss": 4.294, "step": 30326 }, { "epoch": 0.9262981062919976, "grad_norm": 0.5409120321273804, "learning_rate": 6.671537380522147e-07, "loss": 4.2765, "step": 30327 }, { "epoch": 0.9263286499694563, "grad_norm": 0.5369663834571838, "learning_rate": 6.666033565115304e-07, "loss": 4.2884, "step": 30328 }, { "epoch": 0.9263591936469151, "grad_norm": 0.5421770811080933, "learning_rate": 6.660531990209385e-07, "loss": 4.1987, "step": 30329 }, { "epoch": 0.9263897373243739, "grad_norm": 0.5426992177963257, "learning_rate": 6.65503265585507e-07, "loss": 4.2668, "step": 30330 }, { "epoch": 0.9264202810018326, "grad_norm": 0.5380759239196777, "learning_rate": 6.649535562103015e-07, "loss": 4.2682, "step": 30331 }, { "epoch": 0.9264508246792914, "grad_norm": 0.5359057188034058, "learning_rate": 6.644040709003762e-07, "loss": 4.2499, "step": 30332 }, { "epoch": 0.9264813683567501, "grad_norm": 0.5363698601722717, "learning_rate": 6.638548096607966e-07, "loss": 4.2555, "step": 30333 }, { "epoch": 0.9265119120342089, "grad_norm": 0.5467796921730042, "learning_rate": 6.633057724966196e-07, "loss": 4.1806, "step": 30334 }, { "epoch": 0.9265424557116677, "grad_norm": 0.5412095189094543, "learning_rate": 6.62756959412894e-07, "loss": 4.2375, "step": 30335 }, { "epoch": 0.9265729993891264, "grad_norm": 0.5384718179702759, "learning_rate": 6.622083704146853e-07, "loss": 4.2021, "step": 30336 }, { "epoch": 0.9266035430665852, "grad_norm": 0.5327919721603394, "learning_rate": 6.61660005507031e-07, "loss": 4.2507, "step": 30337 }, { "epoch": 0.926634086744044, "grad_norm": 0.5414368510246277, "learning_rate": 6.61111864694991e-07, "loss": 4.2292, "step": 30338 }, { "epoch": 0.9266646304215027, "grad_norm": 0.5339512825012207, "learning_rate": 6.605639479836084e-07, "loss": 4.3498, "step": 30339 }, { "epoch": 0.9266951740989615, "grad_norm": 0.5309001803398132, "learning_rate": 6.600162553779238e-07, "loss": 4.2426, "step": 30340 }, { "epoch": 0.9267257177764203, "grad_norm": 0.5518163442611694, "learning_rate": 6.594687868829857e-07, "loss": 4.2391, "step": 30341 }, { "epoch": 0.926756261453879, "grad_norm": 0.5385361909866333, "learning_rate": 6.58921542503832e-07, "loss": 4.234, "step": 30342 }, { "epoch": 0.9267868051313378, "grad_norm": 0.5419536232948303, "learning_rate": 6.583745222455029e-07, "loss": 4.266, "step": 30343 }, { "epoch": 0.9268173488087966, "grad_norm": 0.5394806265830994, "learning_rate": 6.578277261130361e-07, "loss": 4.1924, "step": 30344 }, { "epoch": 0.9268478924862553, "grad_norm": 0.5450239181518555, "learning_rate": 6.572811541114638e-07, "loss": 4.3116, "step": 30345 }, { "epoch": 0.9268784361637141, "grad_norm": 0.5362126231193542, "learning_rate": 6.567348062458207e-07, "loss": 4.1728, "step": 30346 }, { "epoch": 0.9269089798411729, "grad_norm": 0.5434700846672058, "learning_rate": 6.561886825211333e-07, "loss": 4.3212, "step": 30347 }, { "epoch": 0.9269395235186316, "grad_norm": 0.5358166694641113, "learning_rate": 6.556427829424366e-07, "loss": 4.316, "step": 30348 }, { "epoch": 0.9269700671960904, "grad_norm": 0.5383638739585876, "learning_rate": 6.550971075147516e-07, "loss": 4.2361, "step": 30349 }, { "epoch": 0.9270006108735491, "grad_norm": 0.5438426733016968, "learning_rate": 6.545516562431076e-07, "loss": 4.2566, "step": 30350 }, { "epoch": 0.9270311545510079, "grad_norm": 0.5557587742805481, "learning_rate": 6.540064291325198e-07, "loss": 4.2438, "step": 30351 }, { "epoch": 0.9270616982284667, "grad_norm": 0.5395983457565308, "learning_rate": 6.534614261880123e-07, "loss": 4.291, "step": 30352 }, { "epoch": 0.9270922419059254, "grad_norm": 0.5398306846618652, "learning_rate": 6.529166474146059e-07, "loss": 4.2673, "step": 30353 }, { "epoch": 0.9271227855833842, "grad_norm": 0.5488178730010986, "learning_rate": 6.52372092817316e-07, "loss": 4.3465, "step": 30354 }, { "epoch": 0.927153329260843, "grad_norm": 0.5465682744979858, "learning_rate": 6.518277624011499e-07, "loss": 4.2599, "step": 30355 }, { "epoch": 0.9271838729383017, "grad_norm": 0.5383803248405457, "learning_rate": 6.512836561711256e-07, "loss": 4.2322, "step": 30356 }, { "epoch": 0.9272144166157605, "grad_norm": 0.5286613702774048, "learning_rate": 6.507397741322502e-07, "loss": 4.1453, "step": 30357 }, { "epoch": 0.9272449602932193, "grad_norm": 0.5389631986618042, "learning_rate": 6.501961162895337e-07, "loss": 4.2234, "step": 30358 }, { "epoch": 0.927275503970678, "grad_norm": 0.5474242568016052, "learning_rate": 6.496526826479832e-07, "loss": 4.1773, "step": 30359 }, { "epoch": 0.9273060476481368, "grad_norm": 0.5373024940490723, "learning_rate": 6.491094732125974e-07, "loss": 4.1747, "step": 30360 }, { "epoch": 0.9273365913255956, "grad_norm": 0.5528672933578491, "learning_rate": 6.485664879883807e-07, "loss": 4.307, "step": 30361 }, { "epoch": 0.9273671350030543, "grad_norm": 0.541972815990448, "learning_rate": 6.480237269803346e-07, "loss": 4.1417, "step": 30362 }, { "epoch": 0.9273976786805131, "grad_norm": 0.5418521761894226, "learning_rate": 6.474811901934525e-07, "loss": 4.2361, "step": 30363 }, { "epoch": 0.927428222357972, "grad_norm": 0.548280656337738, "learning_rate": 6.469388776327329e-07, "loss": 4.2955, "step": 30364 }, { "epoch": 0.9274587660354306, "grad_norm": 0.5409902334213257, "learning_rate": 6.463967893031691e-07, "loss": 4.1586, "step": 30365 }, { "epoch": 0.9274893097128895, "grad_norm": 0.5417909622192383, "learning_rate": 6.45854925209749e-07, "loss": 4.1999, "step": 30366 }, { "epoch": 0.9275198533903481, "grad_norm": 0.5453059077262878, "learning_rate": 6.453132853574683e-07, "loss": 4.2841, "step": 30367 }, { "epoch": 0.927550397067807, "grad_norm": 0.5366210341453552, "learning_rate": 6.447718697513067e-07, "loss": 4.2193, "step": 30368 }, { "epoch": 0.9275809407452658, "grad_norm": 0.5406305193901062, "learning_rate": 6.442306783962543e-07, "loss": 4.2192, "step": 30369 }, { "epoch": 0.9276114844227245, "grad_norm": 0.5463451743125916, "learning_rate": 6.436897112972906e-07, "loss": 4.322, "step": 30370 }, { "epoch": 0.9276420281001833, "grad_norm": 0.5311887264251709, "learning_rate": 6.431489684594005e-07, "loss": 4.2189, "step": 30371 }, { "epoch": 0.9276725717776421, "grad_norm": 0.5440161228179932, "learning_rate": 6.426084498875607e-07, "loss": 4.2773, "step": 30372 }, { "epoch": 0.9277031154551008, "grad_norm": 0.5438272356987, "learning_rate": 6.420681555867503e-07, "loss": 4.2617, "step": 30373 }, { "epoch": 0.9277336591325596, "grad_norm": 0.5431838035583496, "learning_rate": 6.415280855619377e-07, "loss": 4.2563, "step": 30374 }, { "epoch": 0.9277642028100184, "grad_norm": 0.5470262169837952, "learning_rate": 6.409882398180995e-07, "loss": 4.2522, "step": 30375 }, { "epoch": 0.9277947464874771, "grad_norm": 0.537693977355957, "learning_rate": 6.404486183602121e-07, "loss": 4.2214, "step": 30376 }, { "epoch": 0.9278252901649359, "grad_norm": 0.543733537197113, "learning_rate": 6.399092211932328e-07, "loss": 4.0928, "step": 30377 }, { "epoch": 0.9278558338423947, "grad_norm": 0.5429977774620056, "learning_rate": 6.393700483221355e-07, "loss": 4.2884, "step": 30378 }, { "epoch": 0.9278863775198534, "grad_norm": 0.5406696796417236, "learning_rate": 6.388310997518854e-07, "loss": 4.2776, "step": 30379 }, { "epoch": 0.9279169211973122, "grad_norm": 0.5473310947418213, "learning_rate": 6.382923754874425e-07, "loss": 4.3434, "step": 30380 }, { "epoch": 0.927947464874771, "grad_norm": 0.5519495010375977, "learning_rate": 6.377538755337642e-07, "loss": 4.3093, "step": 30381 }, { "epoch": 0.9279780085522297, "grad_norm": 0.5437111854553223, "learning_rate": 6.372155998958156e-07, "loss": 4.218, "step": 30382 }, { "epoch": 0.9280085522296885, "grad_norm": 0.5377645492553711, "learning_rate": 6.366775485785459e-07, "loss": 4.2686, "step": 30383 }, { "epoch": 0.9280390959071472, "grad_norm": 0.5388761758804321, "learning_rate": 6.361397215869147e-07, "loss": 4.2724, "step": 30384 }, { "epoch": 0.928069639584606, "grad_norm": 0.5372890830039978, "learning_rate": 6.356021189258738e-07, "loss": 4.1727, "step": 30385 }, { "epoch": 0.9281001832620648, "grad_norm": 0.5363969206809998, "learning_rate": 6.350647406003662e-07, "loss": 4.2438, "step": 30386 }, { "epoch": 0.9281307269395235, "grad_norm": 0.5432440042495728, "learning_rate": 6.345275866153494e-07, "loss": 4.2733, "step": 30387 }, { "epoch": 0.9281612706169823, "grad_norm": 0.5427057147026062, "learning_rate": 6.339906569757609e-07, "loss": 4.2358, "step": 30388 }, { "epoch": 0.9281918142944411, "grad_norm": 0.5392197966575623, "learning_rate": 6.334539516865495e-07, "loss": 4.288, "step": 30389 }, { "epoch": 0.9282223579718998, "grad_norm": 0.5357863903045654, "learning_rate": 6.329174707526559e-07, "loss": 4.1948, "step": 30390 }, { "epoch": 0.9282529016493586, "grad_norm": 0.5379456281661987, "learning_rate": 6.323812141790176e-07, "loss": 4.1837, "step": 30391 }, { "epoch": 0.9282834453268174, "grad_norm": 0.5337057709693909, "learning_rate": 6.318451819705751e-07, "loss": 4.2101, "step": 30392 }, { "epoch": 0.9283139890042761, "grad_norm": 0.5435710549354553, "learning_rate": 6.313093741322635e-07, "loss": 4.2701, "step": 30393 }, { "epoch": 0.9283445326817349, "grad_norm": 0.5393975377082825, "learning_rate": 6.307737906690147e-07, "loss": 4.2771, "step": 30394 }, { "epoch": 0.9283750763591937, "grad_norm": 0.5462089776992798, "learning_rate": 6.302384315857613e-07, "loss": 4.3108, "step": 30395 }, { "epoch": 0.9284056200366524, "grad_norm": 0.5485597252845764, "learning_rate": 6.297032968874323e-07, "loss": 4.2105, "step": 30396 }, { "epoch": 0.9284361637141112, "grad_norm": 0.5442824363708496, "learning_rate": 6.291683865789544e-07, "loss": 4.1706, "step": 30397 }, { "epoch": 0.9284667073915699, "grad_norm": 0.5472920536994934, "learning_rate": 6.286337006652571e-07, "loss": 4.191, "step": 30398 }, { "epoch": 0.9284972510690287, "grad_norm": 0.5396224856376648, "learning_rate": 6.280992391512558e-07, "loss": 4.1866, "step": 30399 }, { "epoch": 0.9285277947464875, "grad_norm": 0.5464332699775696, "learning_rate": 6.2756500204188e-07, "loss": 4.3478, "step": 30400 }, { "epoch": 0.9285583384239462, "grad_norm": 0.5471386313438416, "learning_rate": 6.270309893420395e-07, "loss": 4.2404, "step": 30401 }, { "epoch": 0.928588882101405, "grad_norm": 0.5433207154273987, "learning_rate": 6.264972010566583e-07, "loss": 4.1968, "step": 30402 }, { "epoch": 0.9286194257788638, "grad_norm": 0.5525714755058289, "learning_rate": 6.259636371906463e-07, "loss": 4.298, "step": 30403 }, { "epoch": 0.9286499694563225, "grad_norm": 0.545375406742096, "learning_rate": 6.254302977489246e-07, "loss": 4.2968, "step": 30404 }, { "epoch": 0.9286805131337813, "grad_norm": 0.5397754907608032, "learning_rate": 6.24897182736392e-07, "loss": 4.2948, "step": 30405 }, { "epoch": 0.9287110568112401, "grad_norm": 0.5449417233467102, "learning_rate": 6.243642921579667e-07, "loss": 4.1247, "step": 30406 }, { "epoch": 0.9287416004886988, "grad_norm": 0.5356228947639465, "learning_rate": 6.238316260185534e-07, "loss": 4.2487, "step": 30407 }, { "epoch": 0.9287721441661576, "grad_norm": 0.5333553552627563, "learning_rate": 6.232991843230507e-07, "loss": 4.1852, "step": 30408 }, { "epoch": 0.9288026878436164, "grad_norm": 0.5398694276809692, "learning_rate": 6.227669670763686e-07, "loss": 4.2188, "step": 30409 }, { "epoch": 0.9288332315210751, "grad_norm": 0.5413042902946472, "learning_rate": 6.222349742834061e-07, "loss": 4.2695, "step": 30410 }, { "epoch": 0.9288637751985339, "grad_norm": 0.5431334972381592, "learning_rate": 6.217032059490563e-07, "loss": 4.2391, "step": 30411 }, { "epoch": 0.9288943188759927, "grad_norm": 0.5380210280418396, "learning_rate": 6.211716620782209e-07, "loss": 4.1529, "step": 30412 }, { "epoch": 0.9289248625534514, "grad_norm": 0.5410745143890381, "learning_rate": 6.206403426757934e-07, "loss": 4.2705, "step": 30413 }, { "epoch": 0.9289554062309102, "grad_norm": 0.5409232378005981, "learning_rate": 6.201092477466641e-07, "loss": 4.2066, "step": 30414 }, { "epoch": 0.9289859499083689, "grad_norm": 0.5407488942146301, "learning_rate": 6.195783772957264e-07, "loss": 4.2659, "step": 30415 }, { "epoch": 0.9290164935858277, "grad_norm": 0.546766996383667, "learning_rate": 6.190477313278626e-07, "loss": 4.2737, "step": 30416 }, { "epoch": 0.9290470372632865, "grad_norm": 0.5435542464256287, "learning_rate": 6.18517309847963e-07, "loss": 4.2711, "step": 30417 }, { "epoch": 0.9290775809407452, "grad_norm": 0.5443126559257507, "learning_rate": 6.179871128609127e-07, "loss": 4.2349, "step": 30418 }, { "epoch": 0.929108124618204, "grad_norm": 0.5448988080024719, "learning_rate": 6.174571403715856e-07, "loss": 4.2272, "step": 30419 }, { "epoch": 0.9291386682956628, "grad_norm": 0.5299794673919678, "learning_rate": 6.169273923848696e-07, "loss": 4.3015, "step": 30420 }, { "epoch": 0.9291692119731215, "grad_norm": 0.5380605459213257, "learning_rate": 6.16397868905641e-07, "loss": 4.179, "step": 30421 }, { "epoch": 0.9291997556505803, "grad_norm": 0.5373935103416443, "learning_rate": 6.158685699387712e-07, "loss": 4.2458, "step": 30422 }, { "epoch": 0.9292302993280391, "grad_norm": 0.5369980931282043, "learning_rate": 6.153394954891367e-07, "loss": 4.2268, "step": 30423 }, { "epoch": 0.9292608430054978, "grad_norm": 0.545657217502594, "learning_rate": 6.148106455616115e-07, "loss": 4.2145, "step": 30424 }, { "epoch": 0.9292913866829566, "grad_norm": 0.5390727519989014, "learning_rate": 6.142820201610583e-07, "loss": 4.253, "step": 30425 }, { "epoch": 0.9293219303604154, "grad_norm": 0.5394935607910156, "learning_rate": 6.137536192923509e-07, "loss": 4.2415, "step": 30426 }, { "epoch": 0.9293524740378741, "grad_norm": 0.5385823249816895, "learning_rate": 6.132254429603524e-07, "loss": 4.3099, "step": 30427 }, { "epoch": 0.9293830177153329, "grad_norm": 0.5475724339485168, "learning_rate": 6.126974911699252e-07, "loss": 4.303, "step": 30428 }, { "epoch": 0.9294135613927917, "grad_norm": 0.5367172956466675, "learning_rate": 6.121697639259294e-07, "loss": 4.2785, "step": 30429 }, { "epoch": 0.9294441050702504, "grad_norm": 0.554932177066803, "learning_rate": 6.116422612332279e-07, "loss": 4.2951, "step": 30430 }, { "epoch": 0.9294746487477092, "grad_norm": 0.5433570742607117, "learning_rate": 6.11114983096675e-07, "loss": 4.2669, "step": 30431 }, { "epoch": 0.9295051924251679, "grad_norm": 0.5448840260505676, "learning_rate": 6.105879295211253e-07, "loss": 4.2671, "step": 30432 }, { "epoch": 0.9295357361026267, "grad_norm": 0.539823055267334, "learning_rate": 6.10061100511436e-07, "loss": 4.1235, "step": 30433 }, { "epoch": 0.9295662797800855, "grad_norm": 0.5348883271217346, "learning_rate": 6.095344960724503e-07, "loss": 4.287, "step": 30434 }, { "epoch": 0.9295968234575442, "grad_norm": 0.5428653359413147, "learning_rate": 6.090081162090228e-07, "loss": 4.238, "step": 30435 }, { "epoch": 0.929627367135003, "grad_norm": 0.544685959815979, "learning_rate": 6.08481960925994e-07, "loss": 4.2989, "step": 30436 }, { "epoch": 0.9296579108124619, "grad_norm": 0.5382101535797119, "learning_rate": 6.079560302282156e-07, "loss": 4.2354, "step": 30437 }, { "epoch": 0.9296884544899205, "grad_norm": 0.5416276454925537, "learning_rate": 6.074303241205281e-07, "loss": 4.2464, "step": 30438 }, { "epoch": 0.9297189981673794, "grad_norm": 0.536922037601471, "learning_rate": 6.069048426077695e-07, "loss": 4.2226, "step": 30439 }, { "epoch": 0.9297495418448382, "grad_norm": 0.5406647324562073, "learning_rate": 6.063795856947774e-07, "loss": 4.2464, "step": 30440 }, { "epoch": 0.9297800855222969, "grad_norm": 0.5415308475494385, "learning_rate": 6.058545533863951e-07, "loss": 4.2713, "step": 30441 }, { "epoch": 0.9298106291997557, "grad_norm": 0.5432948470115662, "learning_rate": 6.053297456874496e-07, "loss": 4.2631, "step": 30442 }, { "epoch": 0.9298411728772145, "grad_norm": 0.5410482883453369, "learning_rate": 6.048051626027756e-07, "loss": 4.2669, "step": 30443 }, { "epoch": 0.9298717165546732, "grad_norm": 0.5405938625335693, "learning_rate": 6.042808041372056e-07, "loss": 4.2462, "step": 30444 }, { "epoch": 0.929902260232132, "grad_norm": 0.5431084036827087, "learning_rate": 6.037566702955632e-07, "loss": 4.2966, "step": 30445 }, { "epoch": 0.9299328039095908, "grad_norm": 0.5427024364471436, "learning_rate": 6.032327610826782e-07, "loss": 4.2682, "step": 30446 }, { "epoch": 0.9299633475870495, "grad_norm": 0.5437419414520264, "learning_rate": 6.027090765033689e-07, "loss": 4.3047, "step": 30447 }, { "epoch": 0.9299938912645083, "grad_norm": 0.5300607085227966, "learning_rate": 6.021856165624646e-07, "loss": 4.1999, "step": 30448 }, { "epoch": 0.930024434941967, "grad_norm": 0.5293052792549133, "learning_rate": 6.016623812647809e-07, "loss": 4.1981, "step": 30449 }, { "epoch": 0.9300549786194258, "grad_norm": 0.5379508137702942, "learning_rate": 6.011393706151363e-07, "loss": 4.2686, "step": 30450 }, { "epoch": 0.9300855222968846, "grad_norm": 0.5375418066978455, "learning_rate": 6.006165846183437e-07, "loss": 4.1714, "step": 30451 }, { "epoch": 0.9301160659743433, "grad_norm": 0.5373920798301697, "learning_rate": 6.000940232792212e-07, "loss": 4.2428, "step": 30452 }, { "epoch": 0.9301466096518021, "grad_norm": 0.5394179224967957, "learning_rate": 5.995716866025763e-07, "loss": 4.2903, "step": 30453 }, { "epoch": 0.9301771533292609, "grad_norm": 0.5469231009483337, "learning_rate": 5.990495745932218e-07, "loss": 4.3542, "step": 30454 }, { "epoch": 0.9302076970067196, "grad_norm": 0.5392048954963684, "learning_rate": 5.985276872559647e-07, "loss": 4.2869, "step": 30455 }, { "epoch": 0.9302382406841784, "grad_norm": 0.5373165607452393, "learning_rate": 5.980060245956071e-07, "loss": 4.2111, "step": 30456 }, { "epoch": 0.9302687843616372, "grad_norm": 0.5373611450195312, "learning_rate": 5.974845866169559e-07, "loss": 4.0919, "step": 30457 }, { "epoch": 0.9302993280390959, "grad_norm": 0.5354089140892029, "learning_rate": 5.969633733248103e-07, "loss": 4.247, "step": 30458 }, { "epoch": 0.9303298717165547, "grad_norm": 0.5488746166229248, "learning_rate": 5.964423847239691e-07, "loss": 4.2403, "step": 30459 }, { "epoch": 0.9303604153940135, "grad_norm": 0.540911078453064, "learning_rate": 5.959216208192286e-07, "loss": 4.2521, "step": 30460 }, { "epoch": 0.9303909590714722, "grad_norm": 0.5321784019470215, "learning_rate": 5.954010816153877e-07, "loss": 4.2046, "step": 30461 }, { "epoch": 0.930421502748931, "grad_norm": 0.5422274470329285, "learning_rate": 5.94880767117234e-07, "loss": 4.175, "step": 30462 }, { "epoch": 0.9304520464263898, "grad_norm": 0.5497432351112366, "learning_rate": 5.943606773295641e-07, "loss": 4.2514, "step": 30463 }, { "epoch": 0.9304825901038485, "grad_norm": 0.5367833375930786, "learning_rate": 5.938408122571625e-07, "loss": 4.1989, "step": 30464 }, { "epoch": 0.9305131337813073, "grad_norm": 0.5431863069534302, "learning_rate": 5.933211719048176e-07, "loss": 4.2192, "step": 30465 }, { "epoch": 0.930543677458766, "grad_norm": 0.5415171980857849, "learning_rate": 5.928017562773141e-07, "loss": 4.2596, "step": 30466 }, { "epoch": 0.9305742211362248, "grad_norm": 0.5458512902259827, "learning_rate": 5.922825653794289e-07, "loss": 4.2176, "step": 30467 }, { "epoch": 0.9306047648136836, "grad_norm": 0.5616271495819092, "learning_rate": 5.917635992159499e-07, "loss": 4.2576, "step": 30468 }, { "epoch": 0.9306353084911423, "grad_norm": 0.540919303894043, "learning_rate": 5.912448577916563e-07, "loss": 4.1607, "step": 30469 }, { "epoch": 0.9306658521686011, "grad_norm": 0.5487394332885742, "learning_rate": 5.907263411113167e-07, "loss": 4.3402, "step": 30470 }, { "epoch": 0.9306963958460599, "grad_norm": 0.5484641194343567, "learning_rate": 5.902080491797079e-07, "loss": 4.3369, "step": 30471 }, { "epoch": 0.9307269395235186, "grad_norm": 0.5420916676521301, "learning_rate": 5.896899820016094e-07, "loss": 4.2952, "step": 30472 }, { "epoch": 0.9307574832009774, "grad_norm": 0.5446056127548218, "learning_rate": 5.89172139581784e-07, "loss": 4.2528, "step": 30473 }, { "epoch": 0.9307880268784362, "grad_norm": 0.5413417816162109, "learning_rate": 5.886545219250001e-07, "loss": 4.1832, "step": 30474 }, { "epoch": 0.9308185705558949, "grad_norm": 0.5362928509712219, "learning_rate": 5.88137129036026e-07, "loss": 4.2418, "step": 30475 }, { "epoch": 0.9308491142333537, "grad_norm": 0.5457212328910828, "learning_rate": 5.876199609196248e-07, "loss": 4.1622, "step": 30476 }, { "epoch": 0.9308796579108125, "grad_norm": 0.5435457229614258, "learning_rate": 5.871030175805564e-07, "loss": 4.2532, "step": 30477 }, { "epoch": 0.9309102015882712, "grad_norm": 0.5411593914031982, "learning_rate": 5.865862990235837e-07, "loss": 4.245, "step": 30478 }, { "epoch": 0.93094074526573, "grad_norm": 0.5381315350532532, "learning_rate": 5.860698052534669e-07, "loss": 4.3084, "step": 30479 }, { "epoch": 0.9309712889431888, "grad_norm": 0.5465293526649475, "learning_rate": 5.85553536274952e-07, "loss": 4.286, "step": 30480 }, { "epoch": 0.9310018326206475, "grad_norm": 0.541442334651947, "learning_rate": 5.85037492092802e-07, "loss": 4.2136, "step": 30481 }, { "epoch": 0.9310323762981063, "grad_norm": 0.5303965210914612, "learning_rate": 5.845216727117631e-07, "loss": 4.1468, "step": 30482 }, { "epoch": 0.931062919975565, "grad_norm": 0.532841682434082, "learning_rate": 5.840060781365869e-07, "loss": 4.2651, "step": 30483 }, { "epoch": 0.9310934636530238, "grad_norm": 0.5436328649520874, "learning_rate": 5.834907083720198e-07, "loss": 4.1964, "step": 30484 }, { "epoch": 0.9311240073304826, "grad_norm": 0.5401646494865417, "learning_rate": 5.829755634228051e-07, "loss": 4.1678, "step": 30485 }, { "epoch": 0.9311545510079413, "grad_norm": 0.5424900054931641, "learning_rate": 5.824606432936947e-07, "loss": 4.2789, "step": 30486 }, { "epoch": 0.9311850946854001, "grad_norm": 0.5440675616264343, "learning_rate": 5.819459479894179e-07, "loss": 4.2407, "step": 30487 }, { "epoch": 0.9312156383628589, "grad_norm": 0.5396493673324585, "learning_rate": 5.814314775147184e-07, "loss": 4.2695, "step": 30488 }, { "epoch": 0.9312461820403176, "grad_norm": 0.5439600348472595, "learning_rate": 5.809172318743394e-07, "loss": 4.3133, "step": 30489 }, { "epoch": 0.9312767257177764, "grad_norm": 0.5381695628166199, "learning_rate": 5.804032110730079e-07, "loss": 4.3053, "step": 30490 }, { "epoch": 0.9313072693952352, "grad_norm": 0.549537718296051, "learning_rate": 5.79889415115456e-07, "loss": 4.1921, "step": 30491 }, { "epoch": 0.9313378130726939, "grad_norm": 0.5441498160362244, "learning_rate": 5.793758440064245e-07, "loss": 4.2831, "step": 30492 }, { "epoch": 0.9313683567501527, "grad_norm": 0.5320107340812683, "learning_rate": 5.78862497750629e-07, "loss": 4.1923, "step": 30493 }, { "epoch": 0.9313989004276115, "grad_norm": 0.5429648160934448, "learning_rate": 5.783493763528075e-07, "loss": 4.291, "step": 30494 }, { "epoch": 0.9314294441050702, "grad_norm": 0.5413582921028137, "learning_rate": 5.778364798176783e-07, "loss": 4.1699, "step": 30495 }, { "epoch": 0.931459987782529, "grad_norm": 0.5458396077156067, "learning_rate": 5.773238081499654e-07, "loss": 4.2806, "step": 30496 }, { "epoch": 0.9314905314599878, "grad_norm": 0.5426694750785828, "learning_rate": 5.768113613543874e-07, "loss": 4.2183, "step": 30497 }, { "epoch": 0.9315210751374465, "grad_norm": 0.5417694449424744, "learning_rate": 5.762991394356654e-07, "loss": 4.0779, "step": 30498 }, { "epoch": 0.9315516188149053, "grad_norm": 0.5523737072944641, "learning_rate": 5.75787142398515e-07, "loss": 4.208, "step": 30499 }, { "epoch": 0.931582162492364, "grad_norm": 0.5448234677314758, "learning_rate": 5.752753702476493e-07, "loss": 4.2036, "step": 30500 }, { "epoch": 0.9316127061698228, "grad_norm": 0.5224588513374329, "learning_rate": 5.747638229877811e-07, "loss": 4.0905, "step": 30501 }, { "epoch": 0.9316432498472816, "grad_norm": 0.5419923663139343, "learning_rate": 5.742525006236205e-07, "loss": 4.2926, "step": 30502 }, { "epoch": 0.9316737935247403, "grad_norm": 0.5412686467170715, "learning_rate": 5.737414031598775e-07, "loss": 4.267, "step": 30503 }, { "epoch": 0.9317043372021991, "grad_norm": 0.5421257019042969, "learning_rate": 5.732305306012542e-07, "loss": 4.2185, "step": 30504 }, { "epoch": 0.931734880879658, "grad_norm": 0.5344026684761047, "learning_rate": 5.727198829524549e-07, "loss": 4.264, "step": 30505 }, { "epoch": 0.9317654245571166, "grad_norm": 0.5375940799713135, "learning_rate": 5.722094602181871e-07, "loss": 4.2835, "step": 30506 }, { "epoch": 0.9317959682345754, "grad_norm": 0.540880024433136, "learning_rate": 5.716992624031442e-07, "loss": 4.3322, "step": 30507 }, { "epoch": 0.9318265119120342, "grad_norm": 0.5357640385627747, "learning_rate": 5.711892895120252e-07, "loss": 4.2235, "step": 30508 }, { "epoch": 0.9318570555894929, "grad_norm": 0.5447571277618408, "learning_rate": 5.706795415495291e-07, "loss": 4.261, "step": 30509 }, { "epoch": 0.9318875992669517, "grad_norm": 0.534461259841919, "learning_rate": 5.70170018520344e-07, "loss": 4.2077, "step": 30510 }, { "epoch": 0.9319181429444106, "grad_norm": 0.5439531207084656, "learning_rate": 5.696607204291659e-07, "loss": 4.1941, "step": 30511 }, { "epoch": 0.9319486866218692, "grad_norm": 0.5330735445022583, "learning_rate": 5.691516472806829e-07, "loss": 4.151, "step": 30512 }, { "epoch": 0.931979230299328, "grad_norm": 0.5401971340179443, "learning_rate": 5.686427990795801e-07, "loss": 4.2615, "step": 30513 }, { "epoch": 0.9320097739767869, "grad_norm": 0.5538039803504944, "learning_rate": 5.681341758305425e-07, "loss": 4.2549, "step": 30514 }, { "epoch": 0.9320403176542456, "grad_norm": 0.5459572076797485, "learning_rate": 5.676257775382582e-07, "loss": 4.242, "step": 30515 }, { "epoch": 0.9320708613317044, "grad_norm": 0.543414294719696, "learning_rate": 5.671176042074039e-07, "loss": 4.2627, "step": 30516 }, { "epoch": 0.932101405009163, "grad_norm": 0.5439690947532654, "learning_rate": 5.66609655842662e-07, "loss": 4.3098, "step": 30517 }, { "epoch": 0.9321319486866219, "grad_norm": 0.5372835397720337, "learning_rate": 5.661019324487038e-07, "loss": 4.1719, "step": 30518 }, { "epoch": 0.9321624923640807, "grad_norm": 0.5390027165412903, "learning_rate": 5.655944340302089e-07, "loss": 4.1874, "step": 30519 }, { "epoch": 0.9321930360415394, "grad_norm": 0.540871798992157, "learning_rate": 5.65087160591854e-07, "loss": 4.2946, "step": 30520 }, { "epoch": 0.9322235797189982, "grad_norm": 0.5480046272277832, "learning_rate": 5.645801121382993e-07, "loss": 4.2148, "step": 30521 }, { "epoch": 0.932254123396457, "grad_norm": 0.5394946336746216, "learning_rate": 5.64073288674219e-07, "loss": 4.3173, "step": 30522 }, { "epoch": 0.9322846670739157, "grad_norm": 0.5367418527603149, "learning_rate": 5.635666902042813e-07, "loss": 4.2507, "step": 30523 }, { "epoch": 0.9323152107513745, "grad_norm": 0.539506733417511, "learning_rate": 5.630603167331494e-07, "loss": 4.2307, "step": 30524 }, { "epoch": 0.9323457544288333, "grad_norm": 0.5527842044830322, "learning_rate": 5.625541682654862e-07, "loss": 4.2127, "step": 30525 }, { "epoch": 0.932376298106292, "grad_norm": 0.5555781126022339, "learning_rate": 5.620482448059488e-07, "loss": 4.3731, "step": 30526 }, { "epoch": 0.9324068417837508, "grad_norm": 0.5377906560897827, "learning_rate": 5.615425463592005e-07, "loss": 4.1285, "step": 30527 }, { "epoch": 0.9324373854612096, "grad_norm": 0.5353099703788757, "learning_rate": 5.61037072929893e-07, "loss": 4.1922, "step": 30528 }, { "epoch": 0.9324679291386683, "grad_norm": 0.5357482433319092, "learning_rate": 5.605318245226837e-07, "loss": 4.2533, "step": 30529 }, { "epoch": 0.9324984728161271, "grad_norm": 0.5339236259460449, "learning_rate": 5.600268011422217e-07, "loss": 4.1692, "step": 30530 }, { "epoch": 0.9325290164935859, "grad_norm": 0.5420980453491211, "learning_rate": 5.595220027931586e-07, "loss": 4.1745, "step": 30531 }, { "epoch": 0.9325595601710446, "grad_norm": 0.5397403836250305, "learning_rate": 5.590174294801437e-07, "loss": 4.2639, "step": 30532 }, { "epoch": 0.9325901038485034, "grad_norm": 0.5525330305099487, "learning_rate": 5.585130812078204e-07, "loss": 4.3607, "step": 30533 }, { "epoch": 0.9326206475259621, "grad_norm": 0.5320428609848022, "learning_rate": 5.580089579808379e-07, "loss": 4.2211, "step": 30534 }, { "epoch": 0.9326511912034209, "grad_norm": 0.5435020327568054, "learning_rate": 5.575050598038284e-07, "loss": 4.282, "step": 30535 }, { "epoch": 0.9326817348808797, "grad_norm": 0.5329622626304626, "learning_rate": 5.570013866814383e-07, "loss": 4.255, "step": 30536 }, { "epoch": 0.9327122785583384, "grad_norm": 0.5456370115280151, "learning_rate": 5.564979386183056e-07, "loss": 4.2373, "step": 30537 }, { "epoch": 0.9327428222357972, "grad_norm": 0.5302307605743408, "learning_rate": 5.559947156190625e-07, "loss": 4.2472, "step": 30538 }, { "epoch": 0.932773365913256, "grad_norm": 0.5358021259307861, "learning_rate": 5.554917176883445e-07, "loss": 4.2445, "step": 30539 }, { "epoch": 0.9328039095907147, "grad_norm": 0.5459439754486084, "learning_rate": 5.549889448307838e-07, "loss": 4.2645, "step": 30540 }, { "epoch": 0.9328344532681735, "grad_norm": 0.5510344505310059, "learning_rate": 5.544863970510044e-07, "loss": 4.2481, "step": 30541 }, { "epoch": 0.9328649969456323, "grad_norm": 0.5349565744400024, "learning_rate": 5.539840743536417e-07, "loss": 4.2019, "step": 30542 }, { "epoch": 0.932895540623091, "grad_norm": 0.5413448810577393, "learning_rate": 5.53481976743317e-07, "loss": 4.288, "step": 30543 }, { "epoch": 0.9329260843005498, "grad_norm": 0.5406962037086487, "learning_rate": 5.529801042246486e-07, "loss": 4.2809, "step": 30544 }, { "epoch": 0.9329566279780086, "grad_norm": 0.5406663417816162, "learning_rate": 5.524784568022634e-07, "loss": 4.1776, "step": 30545 }, { "epoch": 0.9329871716554673, "grad_norm": 0.5426854491233826, "learning_rate": 5.519770344807801e-07, "loss": 4.274, "step": 30546 }, { "epoch": 0.9330177153329261, "grad_norm": 0.5476168394088745, "learning_rate": 5.514758372648116e-07, "loss": 4.3173, "step": 30547 }, { "epoch": 0.9330482590103848, "grad_norm": 0.5508755445480347, "learning_rate": 5.509748651589791e-07, "loss": 4.2889, "step": 30548 }, { "epoch": 0.9330788026878436, "grad_norm": 0.5467782020568848, "learning_rate": 5.504741181678874e-07, "loss": 4.2355, "step": 30549 }, { "epoch": 0.9331093463653024, "grad_norm": 0.5339289307594299, "learning_rate": 5.499735962961522e-07, "loss": 4.2351, "step": 30550 }, { "epoch": 0.9331398900427611, "grad_norm": 0.542044997215271, "learning_rate": 5.494732995483836e-07, "loss": 4.1424, "step": 30551 }, { "epoch": 0.9331704337202199, "grad_norm": 0.5377381443977356, "learning_rate": 5.489732279291837e-07, "loss": 4.1654, "step": 30552 }, { "epoch": 0.9332009773976787, "grad_norm": 0.541898787021637, "learning_rate": 5.48473381443157e-07, "loss": 4.2926, "step": 30553 }, { "epoch": 0.9332315210751374, "grad_norm": 0.5453792214393616, "learning_rate": 5.479737600949109e-07, "loss": 4.2489, "step": 30554 }, { "epoch": 0.9332620647525962, "grad_norm": 0.5474909543991089, "learning_rate": 5.474743638890389e-07, "loss": 4.243, "step": 30555 }, { "epoch": 0.933292608430055, "grad_norm": 0.532804012298584, "learning_rate": 5.469751928301459e-07, "loss": 4.1416, "step": 30556 }, { "epoch": 0.9333231521075137, "grad_norm": 0.544083297252655, "learning_rate": 5.464762469228224e-07, "loss": 4.2689, "step": 30557 }, { "epoch": 0.9333536957849725, "grad_norm": 0.5377040505409241, "learning_rate": 5.459775261716677e-07, "loss": 4.2061, "step": 30558 }, { "epoch": 0.9333842394624313, "grad_norm": 0.5378138422966003, "learning_rate": 5.454790305812695e-07, "loss": 4.2969, "step": 30559 }, { "epoch": 0.93341478313989, "grad_norm": 0.5412835478782654, "learning_rate": 5.44980760156219e-07, "loss": 4.1649, "step": 30560 }, { "epoch": 0.9334453268173488, "grad_norm": 0.5450003147125244, "learning_rate": 5.444827149011039e-07, "loss": 4.3102, "step": 30561 }, { "epoch": 0.9334758704948076, "grad_norm": 0.5374467372894287, "learning_rate": 5.439848948205095e-07, "loss": 4.3108, "step": 30562 }, { "epoch": 0.9335064141722663, "grad_norm": 0.5404836535453796, "learning_rate": 5.434872999190211e-07, "loss": 4.2541, "step": 30563 }, { "epoch": 0.9335369578497251, "grad_norm": 0.5519136786460876, "learning_rate": 5.429899302012181e-07, "loss": 4.2029, "step": 30564 }, { "epoch": 0.9335675015271838, "grad_norm": 0.5459276437759399, "learning_rate": 5.424927856716861e-07, "loss": 4.247, "step": 30565 }, { "epoch": 0.9335980452046426, "grad_norm": 0.5387715697288513, "learning_rate": 5.419958663349934e-07, "loss": 4.2202, "step": 30566 }, { "epoch": 0.9336285888821014, "grad_norm": 0.5492512583732605, "learning_rate": 5.414991721957197e-07, "loss": 4.3071, "step": 30567 }, { "epoch": 0.9336591325595601, "grad_norm": 0.544261634349823, "learning_rate": 5.410027032584391e-07, "loss": 4.2115, "step": 30568 }, { "epoch": 0.9336896762370189, "grad_norm": 0.5364976525306702, "learning_rate": 5.405064595277232e-07, "loss": 4.2679, "step": 30569 }, { "epoch": 0.9337202199144777, "grad_norm": 0.543677568435669, "learning_rate": 5.400104410081374e-07, "loss": 4.2291, "step": 30570 }, { "epoch": 0.9337507635919364, "grad_norm": 0.5406813621520996, "learning_rate": 5.395146477042562e-07, "loss": 4.207, "step": 30571 }, { "epoch": 0.9337813072693952, "grad_norm": 0.5466201305389404, "learning_rate": 5.390190796206368e-07, "loss": 4.2562, "step": 30572 }, { "epoch": 0.933811850946854, "grad_norm": 0.5478765368461609, "learning_rate": 5.385237367618478e-07, "loss": 4.2438, "step": 30573 }, { "epoch": 0.9338423946243127, "grad_norm": 0.5409747958183289, "learning_rate": 5.380286191324469e-07, "loss": 4.2184, "step": 30574 }, { "epoch": 0.9338729383017715, "grad_norm": 0.5449666976928711, "learning_rate": 5.375337267369912e-07, "loss": 4.2777, "step": 30575 }, { "epoch": 0.9339034819792303, "grad_norm": 0.5443900227546692, "learning_rate": 5.370390595800412e-07, "loss": 4.3282, "step": 30576 }, { "epoch": 0.933934025656689, "grad_norm": 0.5323287844657898, "learning_rate": 5.365446176661515e-07, "loss": 4.3001, "step": 30577 }, { "epoch": 0.9339645693341478, "grad_norm": 0.5412923097610474, "learning_rate": 5.360504009998685e-07, "loss": 4.3099, "step": 30578 }, { "epoch": 0.9339951130116066, "grad_norm": 0.5382622480392456, "learning_rate": 5.355564095857524e-07, "loss": 4.2239, "step": 30579 }, { "epoch": 0.9340256566890653, "grad_norm": 0.5315948128700256, "learning_rate": 5.350626434283468e-07, "loss": 4.2823, "step": 30580 }, { "epoch": 0.9340562003665241, "grad_norm": 0.5464969277381897, "learning_rate": 5.345691025321953e-07, "loss": 4.2396, "step": 30581 }, { "epoch": 0.9340867440439828, "grad_norm": 0.5467866063117981, "learning_rate": 5.34075786901847e-07, "loss": 4.1701, "step": 30582 }, { "epoch": 0.9341172877214416, "grad_norm": 0.5362310409545898, "learning_rate": 5.3358269654184e-07, "loss": 4.2736, "step": 30583 }, { "epoch": 0.9341478313989005, "grad_norm": 0.5448839664459229, "learning_rate": 5.330898314567178e-07, "loss": 4.2654, "step": 30584 }, { "epoch": 0.9341783750763591, "grad_norm": 0.5267997980117798, "learning_rate": 5.325971916510186e-07, "loss": 4.1228, "step": 30585 }, { "epoch": 0.934208918753818, "grad_norm": 0.5452637076377869, "learning_rate": 5.321047771292747e-07, "loss": 4.3042, "step": 30586 }, { "epoch": 0.9342394624312768, "grad_norm": 0.547400712966919, "learning_rate": 5.316125878960216e-07, "loss": 4.2284, "step": 30587 }, { "epoch": 0.9342700061087355, "grad_norm": 0.5410003662109375, "learning_rate": 5.31120623955797e-07, "loss": 4.1892, "step": 30588 }, { "epoch": 0.9343005497861943, "grad_norm": 0.5420529246330261, "learning_rate": 5.306288853131225e-07, "loss": 4.2072, "step": 30589 }, { "epoch": 0.9343310934636531, "grad_norm": 0.5396847724914551, "learning_rate": 5.301373719725278e-07, "loss": 4.2806, "step": 30590 }, { "epoch": 0.9343616371411118, "grad_norm": 0.5441593527793884, "learning_rate": 5.296460839385398e-07, "loss": 4.303, "step": 30591 }, { "epoch": 0.9343921808185706, "grad_norm": 0.547610878944397, "learning_rate": 5.291550212156826e-07, "loss": 4.2484, "step": 30592 }, { "epoch": 0.9344227244960294, "grad_norm": 0.5422391891479492, "learning_rate": 5.28664183808475e-07, "loss": 4.3353, "step": 30593 }, { "epoch": 0.9344532681734881, "grad_norm": 0.5318683981895447, "learning_rate": 5.281735717214381e-07, "loss": 4.2209, "step": 30594 }, { "epoch": 0.9344838118509469, "grad_norm": 0.5392351746559143, "learning_rate": 5.276831849590908e-07, "loss": 4.1055, "step": 30595 }, { "epoch": 0.9345143555284057, "grad_norm": 0.5407288074493408, "learning_rate": 5.27193023525946e-07, "loss": 4.2504, "step": 30596 }, { "epoch": 0.9345448992058644, "grad_norm": 0.5395016670227051, "learning_rate": 5.267030874265194e-07, "loss": 4.2639, "step": 30597 }, { "epoch": 0.9345754428833232, "grad_norm": 0.5358907580375671, "learning_rate": 5.26213376665316e-07, "loss": 4.1728, "step": 30598 }, { "epoch": 0.9346059865607819, "grad_norm": 0.5304133892059326, "learning_rate": 5.257238912468543e-07, "loss": 4.3147, "step": 30599 }, { "epoch": 0.9346365302382407, "grad_norm": 0.5381649732589722, "learning_rate": 5.252346311756335e-07, "loss": 4.2898, "step": 30600 }, { "epoch": 0.9346670739156995, "grad_norm": 0.5400688648223877, "learning_rate": 5.24745596456161e-07, "loss": 4.2052, "step": 30601 }, { "epoch": 0.9346976175931582, "grad_norm": 0.5372908115386963, "learning_rate": 5.242567870929416e-07, "loss": 4.1695, "step": 30602 }, { "epoch": 0.934728161270617, "grad_norm": 0.5478989481925964, "learning_rate": 5.237682030904717e-07, "loss": 4.1387, "step": 30603 }, { "epoch": 0.9347587049480758, "grad_norm": 0.5500645637512207, "learning_rate": 5.232798444532561e-07, "loss": 4.225, "step": 30604 }, { "epoch": 0.9347892486255345, "grad_norm": 0.5411380529403687, "learning_rate": 5.227917111857856e-07, "loss": 4.2096, "step": 30605 }, { "epoch": 0.9348197923029933, "grad_norm": 0.543326735496521, "learning_rate": 5.223038032925565e-07, "loss": 4.2579, "step": 30606 }, { "epoch": 0.9348503359804521, "grad_norm": 0.5496124625205994, "learning_rate": 5.218161207780597e-07, "loss": 4.2361, "step": 30607 }, { "epoch": 0.9348808796579108, "grad_norm": 0.5355411767959595, "learning_rate": 5.213286636467918e-07, "loss": 4.2085, "step": 30608 }, { "epoch": 0.9349114233353696, "grad_norm": 0.5317981839179993, "learning_rate": 5.208414319032323e-07, "loss": 4.2223, "step": 30609 }, { "epoch": 0.9349419670128284, "grad_norm": 0.5396331548690796, "learning_rate": 5.203544255518722e-07, "loss": 4.2213, "step": 30610 }, { "epoch": 0.9349725106902871, "grad_norm": 0.5323724746704102, "learning_rate": 5.198676445971967e-07, "loss": 4.2523, "step": 30611 }, { "epoch": 0.9350030543677459, "grad_norm": 0.5642461776733398, "learning_rate": 5.193810890436857e-07, "loss": 4.2642, "step": 30612 }, { "epoch": 0.9350335980452047, "grad_norm": 0.5489547848701477, "learning_rate": 5.188947588958187e-07, "loss": 4.1787, "step": 30613 }, { "epoch": 0.9350641417226634, "grad_norm": 0.5449106097221375, "learning_rate": 5.184086541580758e-07, "loss": 4.3418, "step": 30614 }, { "epoch": 0.9350946854001222, "grad_norm": 0.5452313423156738, "learning_rate": 5.179227748349308e-07, "loss": 4.2417, "step": 30615 }, { "epoch": 0.9351252290775809, "grad_norm": 0.5256088376045227, "learning_rate": 5.174371209308609e-07, "loss": 4.0566, "step": 30616 }, { "epoch": 0.9351557727550397, "grad_norm": 0.5395809412002563, "learning_rate": 5.16951692450332e-07, "loss": 4.1897, "step": 30617 }, { "epoch": 0.9351863164324985, "grad_norm": 0.5334806442260742, "learning_rate": 5.164664893978155e-07, "loss": 4.2011, "step": 30618 }, { "epoch": 0.9352168601099572, "grad_norm": 0.5372982621192932, "learning_rate": 5.159815117777828e-07, "loss": 4.1749, "step": 30619 }, { "epoch": 0.935247403787416, "grad_norm": 0.5342720150947571, "learning_rate": 5.154967595946997e-07, "loss": 4.2408, "step": 30620 }, { "epoch": 0.9352779474648748, "grad_norm": 0.5391808748245239, "learning_rate": 5.15012232853021e-07, "loss": 4.1325, "step": 30621 }, { "epoch": 0.9353084911423335, "grad_norm": 0.5488347411155701, "learning_rate": 5.145279315572182e-07, "loss": 4.2633, "step": 30622 }, { "epoch": 0.9353390348197923, "grad_norm": 0.5339236855506897, "learning_rate": 5.140438557117433e-07, "loss": 4.1623, "step": 30623 }, { "epoch": 0.9353695784972511, "grad_norm": 0.529802680015564, "learning_rate": 5.135600053210538e-07, "loss": 4.16, "step": 30624 }, { "epoch": 0.9354001221747098, "grad_norm": 0.5386685729026794, "learning_rate": 5.130763803896127e-07, "loss": 4.1122, "step": 30625 }, { "epoch": 0.9354306658521686, "grad_norm": 0.5336064696311951, "learning_rate": 5.12592980921861e-07, "loss": 4.4006, "step": 30626 }, { "epoch": 0.9354612095296274, "grad_norm": 0.5406835675239563, "learning_rate": 5.12109806922259e-07, "loss": 4.2602, "step": 30627 }, { "epoch": 0.9354917532070861, "grad_norm": 0.5394592881202698, "learning_rate": 5.116268583952532e-07, "loss": 4.1615, "step": 30628 }, { "epoch": 0.9355222968845449, "grad_norm": 0.5453547835350037, "learning_rate": 5.1114413534529e-07, "loss": 4.3238, "step": 30629 }, { "epoch": 0.9355528405620037, "grad_norm": 0.5463187098503113, "learning_rate": 5.106616377768103e-07, "loss": 4.3949, "step": 30630 }, { "epoch": 0.9355833842394624, "grad_norm": 0.53132164478302, "learning_rate": 5.101793656942633e-07, "loss": 4.2329, "step": 30631 }, { "epoch": 0.9356139279169212, "grad_norm": 0.5539228916168213, "learning_rate": 5.096973191020843e-07, "loss": 4.3458, "step": 30632 }, { "epoch": 0.9356444715943799, "grad_norm": 0.5381065607070923, "learning_rate": 5.09215498004717e-07, "loss": 4.2692, "step": 30633 }, { "epoch": 0.9356750152718387, "grad_norm": 0.5449045896530151, "learning_rate": 5.087339024065912e-07, "loss": 4.2457, "step": 30634 }, { "epoch": 0.9357055589492975, "grad_norm": 0.5445415377616882, "learning_rate": 5.082525323121479e-07, "loss": 4.308, "step": 30635 }, { "epoch": 0.9357361026267562, "grad_norm": 0.5435057282447815, "learning_rate": 5.077713877258139e-07, "loss": 4.2842, "step": 30636 }, { "epoch": 0.935766646304215, "grad_norm": 0.531882107257843, "learning_rate": 5.072904686520219e-07, "loss": 4.229, "step": 30637 }, { "epoch": 0.9357971899816738, "grad_norm": 0.5403867363929749, "learning_rate": 5.068097750951961e-07, "loss": 4.2997, "step": 30638 }, { "epoch": 0.9358277336591325, "grad_norm": 0.5591911673545837, "learning_rate": 5.063293070597719e-07, "loss": 4.1854, "step": 30639 }, { "epoch": 0.9358582773365913, "grad_norm": 0.539128303527832, "learning_rate": 5.058490645501624e-07, "loss": 4.2516, "step": 30640 }, { "epoch": 0.9358888210140501, "grad_norm": 0.5459896326065063, "learning_rate": 5.053690475707946e-07, "loss": 4.257, "step": 30641 }, { "epoch": 0.9359193646915088, "grad_norm": 0.5375474095344543, "learning_rate": 5.048892561260899e-07, "loss": 4.1487, "step": 30642 }, { "epoch": 0.9359499083689676, "grad_norm": 0.5415015816688538, "learning_rate": 5.044096902204615e-07, "loss": 4.2621, "step": 30643 }, { "epoch": 0.9359804520464264, "grad_norm": 0.5552595257759094, "learning_rate": 5.039303498583281e-07, "loss": 4.159, "step": 30644 }, { "epoch": 0.9360109957238851, "grad_norm": 0.5456039309501648, "learning_rate": 5.034512350441056e-07, "loss": 4.2943, "step": 30645 }, { "epoch": 0.9360415394013439, "grad_norm": 0.5394244194030762, "learning_rate": 5.029723457821989e-07, "loss": 4.1172, "step": 30646 }, { "epoch": 0.9360720830788027, "grad_norm": 0.533052384853363, "learning_rate": 5.024936820770209e-07, "loss": 4.1776, "step": 30647 }, { "epoch": 0.9361026267562614, "grad_norm": 0.5629889965057373, "learning_rate": 5.020152439329823e-07, "loss": 4.0827, "step": 30648 }, { "epoch": 0.9361331704337202, "grad_norm": 0.5393263697624207, "learning_rate": 5.015370313544821e-07, "loss": 4.2573, "step": 30649 }, { "epoch": 0.9361637141111789, "grad_norm": 0.5415729880332947, "learning_rate": 5.010590443459279e-07, "loss": 4.2161, "step": 30650 }, { "epoch": 0.9361942577886377, "grad_norm": 0.5349292755126953, "learning_rate": 5.00581282911719e-07, "loss": 4.2073, "step": 30651 }, { "epoch": 0.9362248014660965, "grad_norm": 0.5391725897789001, "learning_rate": 5.001037470562548e-07, "loss": 4.2785, "step": 30652 }, { "epoch": 0.9362553451435552, "grad_norm": 0.5439910292625427, "learning_rate": 4.996264367839316e-07, "loss": 4.1574, "step": 30653 }, { "epoch": 0.936285888821014, "grad_norm": 0.5504588484764099, "learning_rate": 4.991493520991431e-07, "loss": 4.3161, "step": 30654 }, { "epoch": 0.9363164324984729, "grad_norm": 0.5465688109397888, "learning_rate": 4.986724930062858e-07, "loss": 4.2504, "step": 30655 }, { "epoch": 0.9363469761759315, "grad_norm": 0.5461796522140503, "learning_rate": 4.98195859509748e-07, "loss": 4.2305, "step": 30656 }, { "epoch": 0.9363775198533903, "grad_norm": 0.5385167598724365, "learning_rate": 4.977194516139178e-07, "loss": 4.2296, "step": 30657 }, { "epoch": 0.9364080635308492, "grad_norm": 0.5338660478591919, "learning_rate": 4.972432693231805e-07, "loss": 4.2137, "step": 30658 }, { "epoch": 0.9364386072083078, "grad_norm": 0.5440177917480469, "learning_rate": 4.967673126419242e-07, "loss": 4.2538, "step": 30659 }, { "epoch": 0.9364691508857667, "grad_norm": 0.545761227607727, "learning_rate": 4.96291581574529e-07, "loss": 4.2761, "step": 30660 }, { "epoch": 0.9364996945632255, "grad_norm": 0.5454255938529968, "learning_rate": 4.958160761253771e-07, "loss": 4.2738, "step": 30661 }, { "epoch": 0.9365302382406842, "grad_norm": 0.5453680753707886, "learning_rate": 4.95340796298846e-07, "loss": 4.2537, "step": 30662 }, { "epoch": 0.936560781918143, "grad_norm": 0.5446559190750122, "learning_rate": 4.948657420993097e-07, "loss": 4.3223, "step": 30663 }, { "epoch": 0.9365913255956018, "grad_norm": 0.5367113947868347, "learning_rate": 4.943909135311425e-07, "loss": 4.1571, "step": 30664 }, { "epoch": 0.9366218692730605, "grad_norm": 0.5469987392425537, "learning_rate": 4.939163105987216e-07, "loss": 4.2761, "step": 30665 }, { "epoch": 0.9366524129505193, "grad_norm": 0.542750358581543, "learning_rate": 4.9344193330641e-07, "loss": 4.2825, "step": 30666 }, { "epoch": 0.936682956627978, "grad_norm": 0.5426617860794067, "learning_rate": 4.929677816585792e-07, "loss": 4.228, "step": 30667 }, { "epoch": 0.9367135003054368, "grad_norm": 0.532705545425415, "learning_rate": 4.924938556595953e-07, "loss": 4.281, "step": 30668 }, { "epoch": 0.9367440439828956, "grad_norm": 0.5320682525634766, "learning_rate": 4.920201553138187e-07, "loss": 4.1446, "step": 30669 }, { "epoch": 0.9367745876603543, "grad_norm": 0.5340704917907715, "learning_rate": 4.915466806256153e-07, "loss": 4.2333, "step": 30670 }, { "epoch": 0.9368051313378131, "grad_norm": 0.5438275337219238, "learning_rate": 4.910734315993426e-07, "loss": 4.2981, "step": 30671 }, { "epoch": 0.9368356750152719, "grad_norm": 0.5437321066856384, "learning_rate": 4.906004082393556e-07, "loss": 4.2955, "step": 30672 }, { "epoch": 0.9368662186927306, "grad_norm": 0.5444427728652954, "learning_rate": 4.901276105500147e-07, "loss": 4.2234, "step": 30673 }, { "epoch": 0.9368967623701894, "grad_norm": 0.5369757413864136, "learning_rate": 4.89655038535669e-07, "loss": 4.2898, "step": 30674 }, { "epoch": 0.9369273060476482, "grad_norm": 0.5342071652412415, "learning_rate": 4.891826922006737e-07, "loss": 4.2153, "step": 30675 }, { "epoch": 0.9369578497251069, "grad_norm": 0.527866005897522, "learning_rate": 4.887105715493751e-07, "loss": 4.2322, "step": 30676 }, { "epoch": 0.9369883934025657, "grad_norm": 0.5379437804222107, "learning_rate": 4.882386765861169e-07, "loss": 4.2441, "step": 30677 }, { "epoch": 0.9370189370800245, "grad_norm": 0.5385555028915405, "learning_rate": 4.877670073152512e-07, "loss": 4.2142, "step": 30678 }, { "epoch": 0.9370494807574832, "grad_norm": 0.5492112040519714, "learning_rate": 4.872955637411192e-07, "loss": 4.2644, "step": 30679 }, { "epoch": 0.937080024434942, "grad_norm": 0.5391868352890015, "learning_rate": 4.86824345868056e-07, "loss": 4.2992, "step": 30680 }, { "epoch": 0.9371105681124008, "grad_norm": 0.541303813457489, "learning_rate": 4.863533537004084e-07, "loss": 4.2287, "step": 30681 }, { "epoch": 0.9371411117898595, "grad_norm": 0.5347381234169006, "learning_rate": 4.85882587242506e-07, "loss": 4.2311, "step": 30682 }, { "epoch": 0.9371716554673183, "grad_norm": 0.5340501070022583, "learning_rate": 4.8541204649869e-07, "loss": 4.2644, "step": 30683 }, { "epoch": 0.937202199144777, "grad_norm": 0.5379582047462463, "learning_rate": 4.849417314732874e-07, "loss": 4.204, "step": 30684 }, { "epoch": 0.9372327428222358, "grad_norm": 0.5412428975105286, "learning_rate": 4.84471642170628e-07, "loss": 4.3546, "step": 30685 }, { "epoch": 0.9372632864996946, "grad_norm": 0.5345508456230164, "learning_rate": 4.840017785950446e-07, "loss": 4.2611, "step": 30686 }, { "epoch": 0.9372938301771533, "grad_norm": 0.5511336922645569, "learning_rate": 4.835321407508641e-07, "loss": 4.3493, "step": 30687 }, { "epoch": 0.9373243738546121, "grad_norm": 0.5320158004760742, "learning_rate": 4.830627286424055e-07, "loss": 4.1828, "step": 30688 }, { "epoch": 0.9373549175320709, "grad_norm": 0.5524861812591553, "learning_rate": 4.825935422739958e-07, "loss": 4.2146, "step": 30689 }, { "epoch": 0.9373854612095296, "grad_norm": 0.5539007782936096, "learning_rate": 4.821245816499537e-07, "loss": 4.1605, "step": 30690 }, { "epoch": 0.9374160048869884, "grad_norm": 0.5364658236503601, "learning_rate": 4.816558467745924e-07, "loss": 4.2064, "step": 30691 }, { "epoch": 0.9374465485644472, "grad_norm": 0.5339534878730774, "learning_rate": 4.811873376522335e-07, "loss": 4.2495, "step": 30692 }, { "epoch": 0.9374770922419059, "grad_norm": 0.5400444865226746, "learning_rate": 4.807190542871903e-07, "loss": 4.227, "step": 30693 }, { "epoch": 0.9375076359193647, "grad_norm": 0.5344892144203186, "learning_rate": 4.802509966837732e-07, "loss": 4.1962, "step": 30694 }, { "epoch": 0.9375381795968235, "grad_norm": 0.5321178436279297, "learning_rate": 4.797831648462897e-07, "loss": 4.2143, "step": 30695 }, { "epoch": 0.9375687232742822, "grad_norm": 0.5393494367599487, "learning_rate": 4.793155587790532e-07, "loss": 4.2063, "step": 30696 }, { "epoch": 0.937599266951741, "grad_norm": 0.5406288504600525, "learning_rate": 4.78848178486363e-07, "loss": 4.2054, "step": 30697 }, { "epoch": 0.9376298106291997, "grad_norm": 0.5507325530052185, "learning_rate": 4.783810239725267e-07, "loss": 4.2536, "step": 30698 }, { "epoch": 0.9376603543066585, "grad_norm": 0.5624834895133972, "learning_rate": 4.779140952418437e-07, "loss": 4.2889, "step": 30699 }, { "epoch": 0.9376908979841173, "grad_norm": 0.5443341135978699, "learning_rate": 4.774473922986134e-07, "loss": 4.3232, "step": 30700 }, { "epoch": 0.937721441661576, "grad_norm": 0.5411130785942078, "learning_rate": 4.76980915147135e-07, "loss": 4.1277, "step": 30701 }, { "epoch": 0.9377519853390348, "grad_norm": 0.5476241111755371, "learning_rate": 4.765146637916995e-07, "loss": 4.2847, "step": 30702 }, { "epoch": 0.9377825290164936, "grad_norm": 0.5332970023155212, "learning_rate": 4.7604863823660083e-07, "loss": 4.1828, "step": 30703 }, { "epoch": 0.9378130726939523, "grad_norm": 0.551556408405304, "learning_rate": 4.755828384861355e-07, "loss": 4.264, "step": 30704 }, { "epoch": 0.9378436163714111, "grad_norm": 0.5473548769950867, "learning_rate": 4.751172645445834e-07, "loss": 4.297, "step": 30705 }, { "epoch": 0.9378741600488699, "grad_norm": 0.5426938533782959, "learning_rate": 4.746519164162383e-07, "loss": 4.2149, "step": 30706 }, { "epoch": 0.9379047037263286, "grad_norm": 0.5394343137741089, "learning_rate": 4.7418679410538567e-07, "loss": 4.2044, "step": 30707 }, { "epoch": 0.9379352474037874, "grad_norm": 0.5354258418083191, "learning_rate": 4.7372189761629994e-07, "loss": 4.2361, "step": 30708 }, { "epoch": 0.9379657910812462, "grad_norm": 0.5411779880523682, "learning_rate": 4.7325722695326924e-07, "loss": 4.2685, "step": 30709 }, { "epoch": 0.9379963347587049, "grad_norm": 0.5472131371498108, "learning_rate": 4.7279278212057077e-07, "loss": 4.2629, "step": 30710 }, { "epoch": 0.9380268784361637, "grad_norm": 0.5391733646392822, "learning_rate": 4.7232856312247887e-07, "loss": 4.2575, "step": 30711 }, { "epoch": 0.9380574221136225, "grad_norm": 0.536753237247467, "learning_rate": 4.718645699632679e-07, "loss": 4.2309, "step": 30712 }, { "epoch": 0.9380879657910812, "grad_norm": 0.5412745475769043, "learning_rate": 4.714008026472122e-07, "loss": 4.1556, "step": 30713 }, { "epoch": 0.93811850946854, "grad_norm": 0.5414756536483765, "learning_rate": 4.709372611785806e-07, "loss": 4.2651, "step": 30714 }, { "epoch": 0.9381490531459987, "grad_norm": 0.5358896255493164, "learning_rate": 4.7047394556164194e-07, "loss": 4.2177, "step": 30715 }, { "epoch": 0.9381795968234575, "grad_norm": 0.5457159280776978, "learning_rate": 4.700108558006594e-07, "loss": 4.2176, "step": 30716 }, { "epoch": 0.9382101405009163, "grad_norm": 0.5395523309707642, "learning_rate": 4.6954799189989906e-07, "loss": 4.2483, "step": 30717 }, { "epoch": 0.938240684178375, "grad_norm": 0.5394914746284485, "learning_rate": 4.6908535386362696e-07, "loss": 4.3174, "step": 30718 }, { "epoch": 0.9382712278558338, "grad_norm": 0.5442805886268616, "learning_rate": 4.6862294169609247e-07, "loss": 4.2389, "step": 30719 }, { "epoch": 0.9383017715332926, "grad_norm": 0.5387309193611145, "learning_rate": 4.6816075540156156e-07, "loss": 4.3161, "step": 30720 }, { "epoch": 0.9383323152107513, "grad_norm": 0.537739098072052, "learning_rate": 4.6769879498428924e-07, "loss": 4.2563, "step": 30721 }, { "epoch": 0.9383628588882101, "grad_norm": 0.5366028547286987, "learning_rate": 4.672370604485249e-07, "loss": 4.3012, "step": 30722 }, { "epoch": 0.9383934025656689, "grad_norm": 0.5432336330413818, "learning_rate": 4.667755517985234e-07, "loss": 4.2946, "step": 30723 }, { "epoch": 0.9384239462431276, "grad_norm": 0.5370850563049316, "learning_rate": 4.6631426903853415e-07, "loss": 4.0881, "step": 30724 }, { "epoch": 0.9384544899205864, "grad_norm": 0.5388533473014832, "learning_rate": 4.6585321217280373e-07, "loss": 4.2002, "step": 30725 }, { "epoch": 0.9384850335980452, "grad_norm": 0.5300008654594421, "learning_rate": 4.6539238120557603e-07, "loss": 4.1666, "step": 30726 }, { "epoch": 0.9385155772755039, "grad_norm": 0.5429930090904236, "learning_rate": 4.6493177614109484e-07, "loss": 4.3388, "step": 30727 }, { "epoch": 0.9385461209529627, "grad_norm": 0.5482731461524963, "learning_rate": 4.644713969836012e-07, "loss": 4.2313, "step": 30728 }, { "epoch": 0.9385766646304216, "grad_norm": 0.5495635271072388, "learning_rate": 4.640112437373362e-07, "loss": 4.3252, "step": 30729 }, { "epoch": 0.9386072083078802, "grad_norm": 0.5310304164886475, "learning_rate": 4.6355131640653526e-07, "loss": 4.1896, "step": 30730 }, { "epoch": 0.938637751985339, "grad_norm": 0.5355029702186584, "learning_rate": 4.6309161499542844e-07, "loss": 4.2927, "step": 30731 }, { "epoch": 0.9386682956627977, "grad_norm": 0.536456823348999, "learning_rate": 4.626321395082567e-07, "loss": 4.2308, "step": 30732 }, { "epoch": 0.9386988393402566, "grad_norm": 0.5345041751861572, "learning_rate": 4.621728899492445e-07, "loss": 4.2091, "step": 30733 }, { "epoch": 0.9387293830177154, "grad_norm": 0.5431950688362122, "learning_rate": 4.617138663226245e-07, "loss": 4.2726, "step": 30734 }, { "epoch": 0.938759926695174, "grad_norm": 0.5359575152397156, "learning_rate": 4.6125506863262116e-07, "loss": 4.2273, "step": 30735 }, { "epoch": 0.9387904703726329, "grad_norm": 0.5414655208587646, "learning_rate": 4.6079649688345604e-07, "loss": 4.2, "step": 30736 }, { "epoch": 0.9388210140500917, "grad_norm": 0.5513031482696533, "learning_rate": 4.603381510793564e-07, "loss": 4.3326, "step": 30737 }, { "epoch": 0.9388515577275504, "grad_norm": 0.5471000671386719, "learning_rate": 4.5988003122454104e-07, "loss": 4.2115, "step": 30738 }, { "epoch": 0.9388821014050092, "grad_norm": 0.5491583347320557, "learning_rate": 4.59422137323226e-07, "loss": 4.203, "step": 30739 }, { "epoch": 0.938912645082468, "grad_norm": 0.5404041409492493, "learning_rate": 4.5896446937962745e-07, "loss": 4.2957, "step": 30740 }, { "epoch": 0.9389431887599267, "grad_norm": 0.5350150465965271, "learning_rate": 4.585070273979669e-07, "loss": 4.1591, "step": 30741 }, { "epoch": 0.9389737324373855, "grad_norm": 0.5459004044532776, "learning_rate": 4.5804981138244385e-07, "loss": 4.231, "step": 30742 }, { "epoch": 0.9390042761148443, "grad_norm": 0.5497288107872009, "learning_rate": 4.575928213372771e-07, "loss": 4.2381, "step": 30743 }, { "epoch": 0.939034819792303, "grad_norm": 0.5325332283973694, "learning_rate": 4.571360572666716e-07, "loss": 4.1503, "step": 30744 }, { "epoch": 0.9390653634697618, "grad_norm": 0.5426483154296875, "learning_rate": 4.566795191748352e-07, "loss": 4.2398, "step": 30745 }, { "epoch": 0.9390959071472206, "grad_norm": 0.5451627373695374, "learning_rate": 4.562232070659644e-07, "loss": 4.2314, "step": 30746 }, { "epoch": 0.9391264508246793, "grad_norm": 0.5400595664978027, "learning_rate": 4.557671209442699e-07, "loss": 4.2669, "step": 30747 }, { "epoch": 0.9391569945021381, "grad_norm": 0.5645750164985657, "learning_rate": 4.553112608139454e-07, "loss": 4.2947, "step": 30748 }, { "epoch": 0.9391875381795968, "grad_norm": 0.5411245822906494, "learning_rate": 4.5485562667919035e-07, "loss": 4.1622, "step": 30749 }, { "epoch": 0.9392180818570556, "grad_norm": 0.5392976403236389, "learning_rate": 4.544002185441987e-07, "loss": 4.1148, "step": 30750 }, { "epoch": 0.9392486255345144, "grad_norm": 0.5374360084533691, "learning_rate": 4.539450364131642e-07, "loss": 4.2373, "step": 30751 }, { "epoch": 0.9392791692119731, "grad_norm": 0.5454980731010437, "learning_rate": 4.534900802902781e-07, "loss": 4.3292, "step": 30752 }, { "epoch": 0.9393097128894319, "grad_norm": 0.5350771546363831, "learning_rate": 4.530353501797313e-07, "loss": 4.2494, "step": 30753 }, { "epoch": 0.9393402565668907, "grad_norm": 0.5437685251235962, "learning_rate": 4.5258084608570395e-07, "loss": 4.1912, "step": 30754 }, { "epoch": 0.9393708002443494, "grad_norm": 0.5400617122650146, "learning_rate": 4.521265680123926e-07, "loss": 4.3282, "step": 30755 }, { "epoch": 0.9394013439218082, "grad_norm": 0.5402862429618835, "learning_rate": 4.516725159639662e-07, "loss": 4.23, "step": 30756 }, { "epoch": 0.939431887599267, "grad_norm": 0.5478328466415405, "learning_rate": 4.512186899446158e-07, "loss": 4.2253, "step": 30757 }, { "epoch": 0.9394624312767257, "grad_norm": 0.5412443280220032, "learning_rate": 4.507650899585186e-07, "loss": 4.2636, "step": 30758 }, { "epoch": 0.9394929749541845, "grad_norm": 0.5468473434448242, "learning_rate": 4.503117160098463e-07, "loss": 4.1087, "step": 30759 }, { "epoch": 0.9395235186316433, "grad_norm": 0.5407103896141052, "learning_rate": 4.4985856810277895e-07, "loss": 4.1187, "step": 30760 }, { "epoch": 0.939554062309102, "grad_norm": 0.5487048029899597, "learning_rate": 4.494056462414825e-07, "loss": 4.4027, "step": 30761 }, { "epoch": 0.9395846059865608, "grad_norm": 0.5391703248023987, "learning_rate": 4.489529504301343e-07, "loss": 4.2786, "step": 30762 }, { "epoch": 0.9396151496640196, "grad_norm": 0.5416385531425476, "learning_rate": 4.485004806728976e-07, "loss": 4.2778, "step": 30763 }, { "epoch": 0.9396456933414783, "grad_norm": 0.5421842336654663, "learning_rate": 4.480482369739414e-07, "loss": 4.2715, "step": 30764 }, { "epoch": 0.9396762370189371, "grad_norm": 0.5394047498703003, "learning_rate": 4.475962193374261e-07, "loss": 4.194, "step": 30765 }, { "epoch": 0.9397067806963958, "grad_norm": 0.5405811071395874, "learning_rate": 4.47144427767518e-07, "loss": 4.208, "step": 30766 }, { "epoch": 0.9397373243738546, "grad_norm": 0.5491033792495728, "learning_rate": 4.466928622683747e-07, "loss": 4.2186, "step": 30767 }, { "epoch": 0.9397678680513134, "grad_norm": 0.5515275597572327, "learning_rate": 4.462415228441541e-07, "loss": 4.25, "step": 30768 }, { "epoch": 0.9397984117287721, "grad_norm": 0.5407595634460449, "learning_rate": 4.4579040949901117e-07, "loss": 4.1829, "step": 30769 }, { "epoch": 0.9398289554062309, "grad_norm": 0.542592465877533, "learning_rate": 4.4533952223710094e-07, "loss": 4.2201, "step": 30770 }, { "epoch": 0.9398594990836897, "grad_norm": 0.5500609874725342, "learning_rate": 4.4488886106257287e-07, "loss": 4.2393, "step": 30771 }, { "epoch": 0.9398900427611484, "grad_norm": 0.5389677882194519, "learning_rate": 4.44438425979582e-07, "loss": 4.1434, "step": 30772 }, { "epoch": 0.9399205864386072, "grad_norm": 0.5374099612236023, "learning_rate": 4.4398821699226933e-07, "loss": 4.2344, "step": 30773 }, { "epoch": 0.939951130116066, "grad_norm": 0.5406518578529358, "learning_rate": 4.435382341047817e-07, "loss": 4.1225, "step": 30774 }, { "epoch": 0.9399816737935247, "grad_norm": 0.5409268736839294, "learning_rate": 4.430884773212657e-07, "loss": 4.2681, "step": 30775 }, { "epoch": 0.9400122174709835, "grad_norm": 0.543635368347168, "learning_rate": 4.426389466458597e-07, "loss": 4.3131, "step": 30776 }, { "epoch": 0.9400427611484423, "grad_norm": 0.5425919890403748, "learning_rate": 4.4218964208270206e-07, "loss": 4.2427, "step": 30777 }, { "epoch": 0.940073304825901, "grad_norm": 0.5427553653717041, "learning_rate": 4.417405636359312e-07, "loss": 4.1951, "step": 30778 }, { "epoch": 0.9401038485033598, "grad_norm": 0.5387569069862366, "learning_rate": 4.412917113096798e-07, "loss": 4.2642, "step": 30779 }, { "epoch": 0.9401343921808186, "grad_norm": 0.5413556694984436, "learning_rate": 4.4084308510808356e-07, "loss": 4.2976, "step": 30780 }, { "epoch": 0.9401649358582773, "grad_norm": 0.5359664559364319, "learning_rate": 4.403946850352725e-07, "loss": 4.1236, "step": 30781 }, { "epoch": 0.9401954795357361, "grad_norm": 0.5363466739654541, "learning_rate": 4.3994651109537375e-07, "loss": 4.1888, "step": 30782 }, { "epoch": 0.9402260232131948, "grad_norm": 0.5426889657974243, "learning_rate": 4.394985632925175e-07, "loss": 4.3135, "step": 30783 }, { "epoch": 0.9402565668906536, "grad_norm": 0.5410072803497314, "learning_rate": 4.3905084163082534e-07, "loss": 4.2694, "step": 30784 }, { "epoch": 0.9402871105681124, "grad_norm": 0.5340622663497925, "learning_rate": 4.3860334611441624e-07, "loss": 4.1815, "step": 30785 }, { "epoch": 0.9403176542455711, "grad_norm": 0.5437231063842773, "learning_rate": 4.381560767474202e-07, "loss": 4.3098, "step": 30786 }, { "epoch": 0.9403481979230299, "grad_norm": 0.538399338722229, "learning_rate": 4.377090335339451e-07, "loss": 4.2568, "step": 30787 }, { "epoch": 0.9403787416004887, "grad_norm": 0.5371557474136353, "learning_rate": 4.372622164781126e-07, "loss": 4.2225, "step": 30788 }, { "epoch": 0.9404092852779474, "grad_norm": 0.550431489944458, "learning_rate": 4.3681562558403613e-07, "loss": 4.1322, "step": 30789 }, { "epoch": 0.9404398289554062, "grad_norm": 0.5385536551475525, "learning_rate": 4.363692608558262e-07, "loss": 4.2273, "step": 30790 }, { "epoch": 0.940470372632865, "grad_norm": 0.5426472425460815, "learning_rate": 4.3592312229759624e-07, "loss": 4.2406, "step": 30791 }, { "epoch": 0.9405009163103237, "grad_norm": 0.5419461727142334, "learning_rate": 4.354772099134513e-07, "loss": 4.2228, "step": 30792 }, { "epoch": 0.9405314599877825, "grad_norm": 0.5346925258636475, "learning_rate": 4.3503152370749646e-07, "loss": 4.2174, "step": 30793 }, { "epoch": 0.9405620036652413, "grad_norm": 0.5435278415679932, "learning_rate": 4.345860636838367e-07, "loss": 4.3034, "step": 30794 }, { "epoch": 0.9405925473427, "grad_norm": 0.5343207120895386, "learning_rate": 4.341408298465743e-07, "loss": 4.1424, "step": 30795 }, { "epoch": 0.9406230910201588, "grad_norm": 0.538792610168457, "learning_rate": 4.336958221998061e-07, "loss": 4.18, "step": 30796 }, { "epoch": 0.9406536346976176, "grad_norm": 0.5371400713920593, "learning_rate": 4.3325104074763147e-07, "loss": 4.1932, "step": 30797 }, { "epoch": 0.9406841783750763, "grad_norm": 0.547186553478241, "learning_rate": 4.3280648549414714e-07, "loss": 4.3191, "step": 30798 }, { "epoch": 0.9407147220525351, "grad_norm": 0.542897641658783, "learning_rate": 4.323621564434416e-07, "loss": 4.1724, "step": 30799 }, { "epoch": 0.9407452657299938, "grad_norm": 0.5367977023124695, "learning_rate": 4.3191805359961144e-07, "loss": 4.2317, "step": 30800 }, { "epoch": 0.9407758094074526, "grad_norm": 0.544414222240448, "learning_rate": 4.314741769667424e-07, "loss": 4.1582, "step": 30801 }, { "epoch": 0.9408063530849115, "grad_norm": 0.5357167720794678, "learning_rate": 4.3103052654892284e-07, "loss": 4.191, "step": 30802 }, { "epoch": 0.9408368967623701, "grad_norm": 0.5421864986419678, "learning_rate": 4.3058710235023835e-07, "loss": 4.2471, "step": 30803 }, { "epoch": 0.940867440439829, "grad_norm": 0.5324133038520813, "learning_rate": 4.30143904374769e-07, "loss": 4.0745, "step": 30804 }, { "epoch": 0.9408979841172878, "grad_norm": 0.5444470047950745, "learning_rate": 4.2970093262659774e-07, "loss": 4.277, "step": 30805 }, { "epoch": 0.9409285277947464, "grad_norm": 0.5397806167602539, "learning_rate": 4.292581871098045e-07, "loss": 4.2713, "step": 30806 }, { "epoch": 0.9409590714722053, "grad_norm": 0.5364676117897034, "learning_rate": 4.2881566782846106e-07, "loss": 4.1953, "step": 30807 }, { "epoch": 0.9409896151496641, "grad_norm": 0.5506376624107361, "learning_rate": 4.2837337478665027e-07, "loss": 4.3078, "step": 30808 }, { "epoch": 0.9410201588271228, "grad_norm": 0.5396809577941895, "learning_rate": 4.279313079884356e-07, "loss": 4.2871, "step": 30809 }, { "epoch": 0.9410507025045816, "grad_norm": 0.5416973829269409, "learning_rate": 4.274894674378915e-07, "loss": 4.2122, "step": 30810 }, { "epoch": 0.9410812461820404, "grad_norm": 0.5407295227050781, "learning_rate": 4.2704785313908424e-07, "loss": 4.1848, "step": 30811 }, { "epoch": 0.9411117898594991, "grad_norm": 0.535923182964325, "learning_rate": 4.266064650960855e-07, "loss": 4.309, "step": 30812 }, { "epoch": 0.9411423335369579, "grad_norm": 0.5432413220405579, "learning_rate": 4.2616530331295037e-07, "loss": 4.2458, "step": 30813 }, { "epoch": 0.9411728772144167, "grad_norm": 0.5367676019668579, "learning_rate": 4.257243677937478e-07, "loss": 4.2159, "step": 30814 }, { "epoch": 0.9412034208918754, "grad_norm": 0.5532793998718262, "learning_rate": 4.2528365854253846e-07, "loss": 4.2362, "step": 30815 }, { "epoch": 0.9412339645693342, "grad_norm": 0.5415738224983215, "learning_rate": 4.248431755633747e-07, "loss": 4.2799, "step": 30816 }, { "epoch": 0.9412645082467929, "grad_norm": 0.5389605164527893, "learning_rate": 4.2440291886031714e-07, "loss": 4.2451, "step": 30817 }, { "epoch": 0.9412950519242517, "grad_norm": 0.5405271649360657, "learning_rate": 4.2396288843741527e-07, "loss": 4.245, "step": 30818 }, { "epoch": 0.9413255956017105, "grad_norm": 0.5345408320426941, "learning_rate": 4.235230842987242e-07, "loss": 4.1886, "step": 30819 }, { "epoch": 0.9413561392791692, "grad_norm": 0.5458348393440247, "learning_rate": 4.2308350644829077e-07, "loss": 4.3335, "step": 30820 }, { "epoch": 0.941386682956628, "grad_norm": 0.5460513830184937, "learning_rate": 4.226441548901644e-07, "loss": 4.2347, "step": 30821 }, { "epoch": 0.9414172266340868, "grad_norm": 0.5413763523101807, "learning_rate": 4.222050296283919e-07, "loss": 4.2418, "step": 30822 }, { "epoch": 0.9414477703115455, "grad_norm": 0.5434168577194214, "learning_rate": 4.2176613066701175e-07, "loss": 4.2393, "step": 30823 }, { "epoch": 0.9414783139890043, "grad_norm": 0.5432154536247253, "learning_rate": 4.2132745801007066e-07, "loss": 4.2149, "step": 30824 }, { "epoch": 0.9415088576664631, "grad_norm": 0.5349271297454834, "learning_rate": 4.2088901166160157e-07, "loss": 4.2197, "step": 30825 }, { "epoch": 0.9415394013439218, "grad_norm": 0.5372838377952576, "learning_rate": 4.204507916256456e-07, "loss": 4.2016, "step": 30826 }, { "epoch": 0.9415699450213806, "grad_norm": 0.5378932952880859, "learning_rate": 4.2001279790623573e-07, "loss": 4.2206, "step": 30827 }, { "epoch": 0.9416004886988394, "grad_norm": 0.5514754056930542, "learning_rate": 4.1957503050740754e-07, "loss": 4.2772, "step": 30828 }, { "epoch": 0.9416310323762981, "grad_norm": 0.548521101474762, "learning_rate": 4.191374894331884e-07, "loss": 4.2939, "step": 30829 }, { "epoch": 0.9416615760537569, "grad_norm": 0.536230742931366, "learning_rate": 4.187001746876085e-07, "loss": 4.29, "step": 30830 }, { "epoch": 0.9416921197312157, "grad_norm": 0.5332106351852417, "learning_rate": 4.18263086274695e-07, "loss": 4.2558, "step": 30831 }, { "epoch": 0.9417226634086744, "grad_norm": 0.5407538414001465, "learning_rate": 4.178262241984754e-07, "loss": 4.3033, "step": 30832 }, { "epoch": 0.9417532070861332, "grad_norm": 0.5392947793006897, "learning_rate": 4.1738958846296306e-07, "loss": 4.2084, "step": 30833 }, { "epoch": 0.9417837507635919, "grad_norm": 0.5454258918762207, "learning_rate": 4.169531790721881e-07, "loss": 4.3217, "step": 30834 }, { "epoch": 0.9418142944410507, "grad_norm": 0.5400986671447754, "learning_rate": 4.1651699603016404e-07, "loss": 4.315, "step": 30835 }, { "epoch": 0.9418448381185095, "grad_norm": 0.5311955809593201, "learning_rate": 4.1608103934090425e-07, "loss": 4.1524, "step": 30836 }, { "epoch": 0.9418753817959682, "grad_norm": 0.5583860874176025, "learning_rate": 4.156453090084306e-07, "loss": 4.2317, "step": 30837 }, { "epoch": 0.941905925473427, "grad_norm": 0.5502889156341553, "learning_rate": 4.152098050367481e-07, "loss": 4.2151, "step": 30838 }, { "epoch": 0.9419364691508858, "grad_norm": 0.5261583924293518, "learning_rate": 4.1477452742987034e-07, "loss": 4.2322, "step": 30839 }, { "epoch": 0.9419670128283445, "grad_norm": 0.5419524908065796, "learning_rate": 4.1433947619180515e-07, "loss": 4.1888, "step": 30840 }, { "epoch": 0.9419975565058033, "grad_norm": 0.5380277633666992, "learning_rate": 4.139046513265521e-07, "loss": 4.2028, "step": 30841 }, { "epoch": 0.9420281001832621, "grad_norm": 0.5583705306053162, "learning_rate": 4.134700528381247e-07, "loss": 4.1297, "step": 30842 }, { "epoch": 0.9420586438607208, "grad_norm": 0.5392508506774902, "learning_rate": 4.130356807305169e-07, "loss": 4.242, "step": 30843 }, { "epoch": 0.9420891875381796, "grad_norm": 0.5442895889282227, "learning_rate": 4.126015350077311e-07, "loss": 4.2787, "step": 30844 }, { "epoch": 0.9421197312156384, "grad_norm": 0.5470716953277588, "learning_rate": 4.1216761567376695e-07, "loss": 4.2654, "step": 30845 }, { "epoch": 0.9421502748930971, "grad_norm": 0.5433416366577148, "learning_rate": 4.1173392273261556e-07, "loss": 4.0694, "step": 30846 }, { "epoch": 0.9421808185705559, "grad_norm": 0.5436220765113831, "learning_rate": 4.1130045618827107e-07, "loss": 4.2708, "step": 30847 }, { "epoch": 0.9422113622480146, "grad_norm": 0.5498811602592468, "learning_rate": 4.1086721604472745e-07, "loss": 4.2276, "step": 30848 }, { "epoch": 0.9422419059254734, "grad_norm": 0.5537204742431641, "learning_rate": 4.1043420230597043e-07, "loss": 4.2772, "step": 30849 }, { "epoch": 0.9422724496029322, "grad_norm": 0.5435551404953003, "learning_rate": 4.100014149759884e-07, "loss": 4.2298, "step": 30850 }, { "epoch": 0.9423029932803909, "grad_norm": 0.5367217063903809, "learning_rate": 4.0956885405877e-07, "loss": 4.2465, "step": 30851 }, { "epoch": 0.9423335369578497, "grad_norm": 0.5326486825942993, "learning_rate": 4.091365195582897e-07, "loss": 4.2334, "step": 30852 }, { "epoch": 0.9423640806353085, "grad_norm": 0.5364925265312195, "learning_rate": 4.0870441147853324e-07, "loss": 4.2739, "step": 30853 }, { "epoch": 0.9423946243127672, "grad_norm": 0.5520687103271484, "learning_rate": 4.082725298234807e-07, "loss": 4.3245, "step": 30854 }, { "epoch": 0.942425167990226, "grad_norm": 0.5348197817802429, "learning_rate": 4.0784087459710685e-07, "loss": 4.2245, "step": 30855 }, { "epoch": 0.9424557116676848, "grad_norm": 0.5481111407279968, "learning_rate": 4.0740944580338615e-07, "loss": 4.3166, "step": 30856 }, { "epoch": 0.9424862553451435, "grad_norm": 0.5504150986671448, "learning_rate": 4.069782434462904e-07, "loss": 4.2801, "step": 30857 }, { "epoch": 0.9425167990226023, "grad_norm": 0.5348779559135437, "learning_rate": 4.0654726752978876e-07, "loss": 4.2682, "step": 30858 }, { "epoch": 0.9425473427000611, "grad_norm": 0.5518062710762024, "learning_rate": 4.06116518057853e-07, "loss": 4.1812, "step": 30859 }, { "epoch": 0.9425778863775198, "grad_norm": 0.539008617401123, "learning_rate": 4.056859950344466e-07, "loss": 4.282, "step": 30860 }, { "epoch": 0.9426084300549786, "grad_norm": 0.5404438376426697, "learning_rate": 4.0525569846353584e-07, "loss": 4.2442, "step": 30861 }, { "epoch": 0.9426389737324374, "grad_norm": 0.5359524488449097, "learning_rate": 4.0482562834907866e-07, "loss": 4.287, "step": 30862 }, { "epoch": 0.9426695174098961, "grad_norm": 0.5456588864326477, "learning_rate": 4.0439578469504136e-07, "loss": 4.2535, "step": 30863 }, { "epoch": 0.9427000610873549, "grad_norm": 0.5392951369285583, "learning_rate": 4.0396616750537353e-07, "loss": 4.27, "step": 30864 }, { "epoch": 0.9427306047648136, "grad_norm": 0.5374866127967834, "learning_rate": 4.0353677678403866e-07, "loss": 4.2346, "step": 30865 }, { "epoch": 0.9427611484422724, "grad_norm": 0.5378006100654602, "learning_rate": 4.0310761253498366e-07, "loss": 4.2616, "step": 30866 }, { "epoch": 0.9427916921197312, "grad_norm": 0.5292854309082031, "learning_rate": 4.0267867476216634e-07, "loss": 4.1691, "step": 30867 }, { "epoch": 0.9428222357971899, "grad_norm": 0.535354733467102, "learning_rate": 4.022499634695309e-07, "loss": 4.252, "step": 30868 }, { "epoch": 0.9428527794746487, "grad_norm": 0.5413949489593506, "learning_rate": 4.0182147866102694e-07, "loss": 4.1815, "step": 30869 }, { "epoch": 0.9428833231521075, "grad_norm": 0.5410352349281311, "learning_rate": 4.01393220340604e-07, "loss": 4.3031, "step": 30870 }, { "epoch": 0.9429138668295662, "grad_norm": 0.5374215841293335, "learning_rate": 4.009651885121951e-07, "loss": 4.2483, "step": 30871 }, { "epoch": 0.942944410507025, "grad_norm": 0.541772186756134, "learning_rate": 4.0053738317975267e-07, "loss": 4.2903, "step": 30872 }, { "epoch": 0.9429749541844838, "grad_norm": 0.5406238436698914, "learning_rate": 4.001098043472068e-07, "loss": 4.2902, "step": 30873 }, { "epoch": 0.9430054978619425, "grad_norm": 0.5419502854347229, "learning_rate": 3.9968245201849887e-07, "loss": 4.2631, "step": 30874 }, { "epoch": 0.9430360415394013, "grad_norm": 0.5454708337783813, "learning_rate": 3.992553261975646e-07, "loss": 4.2008, "step": 30875 }, { "epoch": 0.9430665852168602, "grad_norm": 0.5374528169631958, "learning_rate": 3.9882842688833135e-07, "loss": 4.2434, "step": 30876 }, { "epoch": 0.9430971288943188, "grad_norm": 0.5421702861785889, "learning_rate": 3.984017540947349e-07, "loss": 4.2103, "step": 30877 }, { "epoch": 0.9431276725717777, "grad_norm": 0.5440645813941956, "learning_rate": 3.979753078207027e-07, "loss": 4.2661, "step": 30878 }, { "epoch": 0.9431582162492365, "grad_norm": 0.5346789360046387, "learning_rate": 3.975490880701621e-07, "loss": 4.2094, "step": 30879 }, { "epoch": 0.9431887599266952, "grad_norm": 0.5400931239128113, "learning_rate": 3.97123094847035e-07, "loss": 4.181, "step": 30880 }, { "epoch": 0.943219303604154, "grad_norm": 0.5378258228302002, "learning_rate": 3.966973281552461e-07, "loss": 4.2745, "step": 30881 }, { "epoch": 0.9432498472816127, "grad_norm": 0.538698673248291, "learning_rate": 3.962717879987143e-07, "loss": 4.2371, "step": 30882 }, { "epoch": 0.9432803909590715, "grad_norm": 0.5415828227996826, "learning_rate": 3.9584647438135616e-07, "loss": 4.2755, "step": 30883 }, { "epoch": 0.9433109346365303, "grad_norm": 0.5325161814689636, "learning_rate": 3.9542138730709056e-07, "loss": 4.1452, "step": 30884 }, { "epoch": 0.943341478313989, "grad_norm": 0.5478675961494446, "learning_rate": 3.949965267798339e-07, "loss": 4.2376, "step": 30885 }, { "epoch": 0.9433720219914478, "grad_norm": 0.5492081642150879, "learning_rate": 3.945718928034942e-07, "loss": 4.2755, "step": 30886 }, { "epoch": 0.9434025656689066, "grad_norm": 0.5483230948448181, "learning_rate": 3.941474853819793e-07, "loss": 4.3048, "step": 30887 }, { "epoch": 0.9434331093463653, "grad_norm": 0.5352974534034729, "learning_rate": 3.9372330451920015e-07, "loss": 4.2266, "step": 30888 }, { "epoch": 0.9434636530238241, "grad_norm": 0.5422396063804626, "learning_rate": 3.932993502190618e-07, "loss": 4.2664, "step": 30889 }, { "epoch": 0.9434941967012829, "grad_norm": 0.5367359519004822, "learning_rate": 3.9287562248546683e-07, "loss": 4.2163, "step": 30890 }, { "epoch": 0.9435247403787416, "grad_norm": 0.5414021015167236, "learning_rate": 3.9245212132232035e-07, "loss": 4.2214, "step": 30891 }, { "epoch": 0.9435552840562004, "grad_norm": 0.5326661467552185, "learning_rate": 3.9202884673351925e-07, "loss": 4.2789, "step": 30892 }, { "epoch": 0.9435858277336592, "grad_norm": 0.5385148525238037, "learning_rate": 3.9160579872295766e-07, "loss": 4.2487, "step": 30893 }, { "epoch": 0.9436163714111179, "grad_norm": 0.5417255759239197, "learning_rate": 3.91182977294538e-07, "loss": 4.2576, "step": 30894 }, { "epoch": 0.9436469150885767, "grad_norm": 0.5389524698257446, "learning_rate": 3.907603824521461e-07, "loss": 4.1919, "step": 30895 }, { "epoch": 0.9436774587660355, "grad_norm": 0.5410565137863159, "learning_rate": 3.90338014199676e-07, "loss": 4.2145, "step": 30896 }, { "epoch": 0.9437080024434942, "grad_norm": 0.553062379360199, "learning_rate": 3.8991587254101905e-07, "loss": 4.2542, "step": 30897 }, { "epoch": 0.943738546120953, "grad_norm": 0.5520685315132141, "learning_rate": 3.894939574800555e-07, "loss": 4.2311, "step": 30898 }, { "epoch": 0.9437690897984117, "grad_norm": 0.5440025925636292, "learning_rate": 3.890722690206794e-07, "loss": 4.2599, "step": 30899 }, { "epoch": 0.9437996334758705, "grad_norm": 0.5389785766601562, "learning_rate": 3.886508071667655e-07, "loss": 4.2492, "step": 30900 }, { "epoch": 0.9438301771533293, "grad_norm": 0.5342019200325012, "learning_rate": 3.882295719222023e-07, "loss": 4.1375, "step": 30901 }, { "epoch": 0.943860720830788, "grad_norm": 0.5453613996505737, "learning_rate": 3.87808563290859e-07, "loss": 4.2572, "step": 30902 }, { "epoch": 0.9438912645082468, "grad_norm": 0.5430076122283936, "learning_rate": 3.8738778127661854e-07, "loss": 4.2431, "step": 30903 }, { "epoch": 0.9439218081857056, "grad_norm": 0.5465799570083618, "learning_rate": 3.869672258833529e-07, "loss": 4.1961, "step": 30904 }, { "epoch": 0.9439523518631643, "grad_norm": 0.5400447845458984, "learning_rate": 3.8654689711493384e-07, "loss": 4.2748, "step": 30905 }, { "epoch": 0.9439828955406231, "grad_norm": 0.5458593368530273, "learning_rate": 3.861267949752334e-07, "loss": 4.3075, "step": 30906 }, { "epoch": 0.9440134392180819, "grad_norm": 0.5368319153785706, "learning_rate": 3.8570691946811787e-07, "loss": 4.2649, "step": 30907 }, { "epoch": 0.9440439828955406, "grad_norm": 0.5459772944450378, "learning_rate": 3.852872705974564e-07, "loss": 4.2314, "step": 30908 }, { "epoch": 0.9440745265729994, "grad_norm": 0.5377733707427979, "learning_rate": 3.84867848367107e-07, "loss": 4.2317, "step": 30909 }, { "epoch": 0.9441050702504582, "grad_norm": 0.5401142239570618, "learning_rate": 3.84448652780936e-07, "loss": 4.2439, "step": 30910 }, { "epoch": 0.9441356139279169, "grad_norm": 0.542579710483551, "learning_rate": 3.8402968384280423e-07, "loss": 4.2164, "step": 30911 }, { "epoch": 0.9441661576053757, "grad_norm": 0.5357009172439575, "learning_rate": 3.83610941556567e-07, "loss": 4.2711, "step": 30912 }, { "epoch": 0.9441967012828345, "grad_norm": 0.5428920984268188, "learning_rate": 3.831924259260794e-07, "loss": 4.19, "step": 30913 }, { "epoch": 0.9442272449602932, "grad_norm": 0.5400699973106384, "learning_rate": 3.8277413695519683e-07, "loss": 4.0647, "step": 30914 }, { "epoch": 0.944257788637752, "grad_norm": 0.5364899635314941, "learning_rate": 3.823560746477689e-07, "loss": 4.2321, "step": 30915 }, { "epoch": 0.9442883323152107, "grad_norm": 0.535148561000824, "learning_rate": 3.8193823900764813e-07, "loss": 4.153, "step": 30916 }, { "epoch": 0.9443188759926695, "grad_norm": 0.5414966344833374, "learning_rate": 3.815206300386759e-07, "loss": 4.3307, "step": 30917 }, { "epoch": 0.9443494196701283, "grad_norm": 0.5420851111412048, "learning_rate": 3.811032477447046e-07, "loss": 4.3181, "step": 30918 }, { "epoch": 0.944379963347587, "grad_norm": 0.5401728749275208, "learning_rate": 3.8068609212957017e-07, "loss": 4.25, "step": 30919 }, { "epoch": 0.9444105070250458, "grad_norm": 0.5417587757110596, "learning_rate": 3.802691631971195e-07, "loss": 4.3095, "step": 30920 }, { "epoch": 0.9444410507025046, "grad_norm": 0.5391029119491577, "learning_rate": 3.7985246095118553e-07, "loss": 4.3466, "step": 30921 }, { "epoch": 0.9444715943799633, "grad_norm": 0.5349929332733154, "learning_rate": 3.7943598539560976e-07, "loss": 4.1341, "step": 30922 }, { "epoch": 0.9445021380574221, "grad_norm": 0.5319403409957886, "learning_rate": 3.7901973653422517e-07, "loss": 4.3116, "step": 30923 }, { "epoch": 0.9445326817348809, "grad_norm": 0.5517042875289917, "learning_rate": 3.7860371437086484e-07, "loss": 4.2662, "step": 30924 }, { "epoch": 0.9445632254123396, "grad_norm": 0.5490822196006775, "learning_rate": 3.781879189093618e-07, "loss": 4.1224, "step": 30925 }, { "epoch": 0.9445937690897984, "grad_norm": 0.5420420169830322, "learning_rate": 3.7777235015353793e-07, "loss": 4.2727, "step": 30926 }, { "epoch": 0.9446243127672572, "grad_norm": 0.5445762872695923, "learning_rate": 3.773570081072264e-07, "loss": 4.2184, "step": 30927 }, { "epoch": 0.9446548564447159, "grad_norm": 0.5453162789344788, "learning_rate": 3.7694189277424907e-07, "loss": 4.1122, "step": 30928 }, { "epoch": 0.9446854001221747, "grad_norm": 0.5347256660461426, "learning_rate": 3.765270041584251e-07, "loss": 4.1235, "step": 30929 }, { "epoch": 0.9447159437996335, "grad_norm": 0.5257876515388489, "learning_rate": 3.761123422635765e-07, "loss": 4.1091, "step": 30930 }, { "epoch": 0.9447464874770922, "grad_norm": 0.5424308180809021, "learning_rate": 3.7569790709352513e-07, "loss": 4.1707, "step": 30931 }, { "epoch": 0.944777031154551, "grad_norm": 0.5351117253303528, "learning_rate": 3.752836986520819e-07, "loss": 4.1791, "step": 30932 }, { "epoch": 0.9448075748320097, "grad_norm": 0.5413739085197449, "learning_rate": 3.748697169430632e-07, "loss": 4.3245, "step": 30933 }, { "epoch": 0.9448381185094685, "grad_norm": 0.5365799069404602, "learning_rate": 3.744559619702798e-07, "loss": 4.2838, "step": 30934 }, { "epoch": 0.9448686621869273, "grad_norm": 0.5429856181144714, "learning_rate": 3.740424337375426e-07, "loss": 4.2394, "step": 30935 }, { "epoch": 0.944899205864386, "grad_norm": 0.5513620972633362, "learning_rate": 3.736291322486568e-07, "loss": 4.2131, "step": 30936 }, { "epoch": 0.9449297495418448, "grad_norm": 0.5452992916107178, "learning_rate": 3.7321605750742784e-07, "loss": 4.3525, "step": 30937 }, { "epoch": 0.9449602932193036, "grad_norm": 0.5364831686019897, "learning_rate": 3.728032095176609e-07, "loss": 4.1978, "step": 30938 }, { "epoch": 0.9449908368967623, "grad_norm": 0.5402660965919495, "learning_rate": 3.723905882831613e-07, "loss": 4.2877, "step": 30939 }, { "epoch": 0.9450213805742211, "grad_norm": 0.5461151599884033, "learning_rate": 3.719781938077177e-07, "loss": 4.1988, "step": 30940 }, { "epoch": 0.9450519242516799, "grad_norm": 0.5382745265960693, "learning_rate": 3.715660260951354e-07, "loss": 4.2812, "step": 30941 }, { "epoch": 0.9450824679291386, "grad_norm": 0.5448988080024719, "learning_rate": 3.711540851492085e-07, "loss": 4.2272, "step": 30942 }, { "epoch": 0.9451130116065974, "grad_norm": 0.5533973574638367, "learning_rate": 3.7074237097372845e-07, "loss": 4.3278, "step": 30943 }, { "epoch": 0.9451435552840562, "grad_norm": 0.5530880689620972, "learning_rate": 3.703308835724867e-07, "loss": 4.1816, "step": 30944 }, { "epoch": 0.9451740989615149, "grad_norm": 0.5398696660995483, "learning_rate": 3.6991962294927186e-07, "loss": 4.266, "step": 30945 }, { "epoch": 0.9452046426389737, "grad_norm": 0.5422381162643433, "learning_rate": 3.695085891078698e-07, "loss": 4.1233, "step": 30946 }, { "epoch": 0.9452351863164326, "grad_norm": 0.552548885345459, "learning_rate": 3.6909778205206636e-07, "loss": 4.3735, "step": 30947 }, { "epoch": 0.9452657299938912, "grad_norm": 0.5423280000686646, "learning_rate": 3.686872017856446e-07, "loss": 4.2562, "step": 30948 }, { "epoch": 0.94529627367135, "grad_norm": 0.5346642136573792, "learning_rate": 3.6827684831238216e-07, "loss": 4.1999, "step": 30949 }, { "epoch": 0.9453268173488087, "grad_norm": 0.5553524494171143, "learning_rate": 3.6786672163606207e-07, "loss": 4.2656, "step": 30950 }, { "epoch": 0.9453573610262676, "grad_norm": 0.5405322313308716, "learning_rate": 3.6745682176045347e-07, "loss": 4.281, "step": 30951 }, { "epoch": 0.9453879047037264, "grad_norm": 0.5417546033859253, "learning_rate": 3.6704714868933677e-07, "loss": 4.2666, "step": 30952 }, { "epoch": 0.945418448381185, "grad_norm": 0.5322191715240479, "learning_rate": 3.666377024264839e-07, "loss": 4.268, "step": 30953 }, { "epoch": 0.9454489920586439, "grad_norm": 0.5401768684387207, "learning_rate": 3.6622848297565846e-07, "loss": 4.2674, "step": 30954 }, { "epoch": 0.9454795357361027, "grad_norm": 0.540490984916687, "learning_rate": 3.6581949034063534e-07, "loss": 4.242, "step": 30955 }, { "epoch": 0.9455100794135614, "grad_norm": 0.5482848286628723, "learning_rate": 3.6541072452517813e-07, "loss": 4.1625, "step": 30956 }, { "epoch": 0.9455406230910202, "grad_norm": 0.5406772494316101, "learning_rate": 3.650021855330504e-07, "loss": 4.1956, "step": 30957 }, { "epoch": 0.945571166768479, "grad_norm": 0.5356491208076477, "learning_rate": 3.645938733680132e-07, "loss": 4.2442, "step": 30958 }, { "epoch": 0.9456017104459377, "grad_norm": 0.5392158627510071, "learning_rate": 3.641857880338273e-07, "loss": 4.2672, "step": 30959 }, { "epoch": 0.9456322541233965, "grad_norm": 0.5409272909164429, "learning_rate": 3.6377792953424803e-07, "loss": 4.1676, "step": 30960 }, { "epoch": 0.9456627978008553, "grad_norm": 0.5440170764923096, "learning_rate": 3.633702978730308e-07, "loss": 4.1431, "step": 30961 }, { "epoch": 0.945693341478314, "grad_norm": 0.534144401550293, "learning_rate": 3.629628930539336e-07, "loss": 4.2528, "step": 30962 }, { "epoch": 0.9457238851557728, "grad_norm": 0.5371074676513672, "learning_rate": 3.6255571508070075e-07, "loss": 4.2551, "step": 30963 }, { "epoch": 0.9457544288332316, "grad_norm": 0.5493578314781189, "learning_rate": 3.621487639570875e-07, "loss": 4.2389, "step": 30964 }, { "epoch": 0.9457849725106903, "grad_norm": 0.5355247855186462, "learning_rate": 3.6174203968683815e-07, "loss": 4.2738, "step": 30965 }, { "epoch": 0.9458155161881491, "grad_norm": 0.5311487317085266, "learning_rate": 3.6133554227369414e-07, "loss": 4.293, "step": 30966 }, { "epoch": 0.9458460598656078, "grad_norm": 0.540124773979187, "learning_rate": 3.6092927172140525e-07, "loss": 4.1799, "step": 30967 }, { "epoch": 0.9458766035430666, "grad_norm": 0.5419949293136597, "learning_rate": 3.605232280337073e-07, "loss": 4.2085, "step": 30968 }, { "epoch": 0.9459071472205254, "grad_norm": 0.5617150068283081, "learning_rate": 3.6011741121433904e-07, "loss": 4.2528, "step": 30969 }, { "epoch": 0.9459376908979841, "grad_norm": 0.545879065990448, "learning_rate": 3.5971182126704193e-07, "loss": 4.2682, "step": 30970 }, { "epoch": 0.9459682345754429, "grad_norm": 0.5405320525169373, "learning_rate": 3.5930645819554356e-07, "loss": 4.2762, "step": 30971 }, { "epoch": 0.9459987782529017, "grad_norm": 0.5441510081291199, "learning_rate": 3.589013220035797e-07, "loss": 4.2345, "step": 30972 }, { "epoch": 0.9460293219303604, "grad_norm": 0.5467279553413391, "learning_rate": 3.5849641269488364e-07, "loss": 4.3722, "step": 30973 }, { "epoch": 0.9460598656078192, "grad_norm": 0.5447943210601807, "learning_rate": 3.580917302731773e-07, "loss": 4.2909, "step": 30974 }, { "epoch": 0.946090409285278, "grad_norm": 0.5331687331199646, "learning_rate": 3.576872747421911e-07, "loss": 4.2662, "step": 30975 }, { "epoch": 0.9461209529627367, "grad_norm": 0.535004198551178, "learning_rate": 3.572830461056498e-07, "loss": 4.2932, "step": 30976 }, { "epoch": 0.9461514966401955, "grad_norm": 0.5544666647911072, "learning_rate": 3.568790443672698e-07, "loss": 4.2463, "step": 30977 }, { "epoch": 0.9461820403176543, "grad_norm": 0.5386369824409485, "learning_rate": 3.564752695307788e-07, "loss": 4.2234, "step": 30978 }, { "epoch": 0.946212583995113, "grad_norm": 0.5480799674987793, "learning_rate": 3.5607172159988767e-07, "loss": 4.1823, "step": 30979 }, { "epoch": 0.9462431276725718, "grad_norm": 0.5365858674049377, "learning_rate": 3.5566840057831564e-07, "loss": 4.1722, "step": 30980 }, { "epoch": 0.9462736713500306, "grad_norm": 0.5422358512878418, "learning_rate": 3.552653064697764e-07, "loss": 4.2548, "step": 30981 }, { "epoch": 0.9463042150274893, "grad_norm": 0.5502883791923523, "learning_rate": 3.5486243927797816e-07, "loss": 4.3034, "step": 30982 }, { "epoch": 0.9463347587049481, "grad_norm": 0.5442650318145752, "learning_rate": 3.544597990066345e-07, "loss": 4.1786, "step": 30983 }, { "epoch": 0.9463653023824068, "grad_norm": 0.5455142259597778, "learning_rate": 3.540573856594509e-07, "loss": 4.2829, "step": 30984 }, { "epoch": 0.9463958460598656, "grad_norm": 0.5546532273292542, "learning_rate": 3.536551992401327e-07, "loss": 4.1866, "step": 30985 }, { "epoch": 0.9464263897373244, "grad_norm": 0.5405873656272888, "learning_rate": 3.5325323975238243e-07, "loss": 4.2291, "step": 30986 }, { "epoch": 0.9464569334147831, "grad_norm": 0.5347638726234436, "learning_rate": 3.528515071999028e-07, "loss": 4.0971, "step": 30987 }, { "epoch": 0.9464874770922419, "grad_norm": 0.5411320924758911, "learning_rate": 3.5245000158639076e-07, "loss": 4.1767, "step": 30988 }, { "epoch": 0.9465180207697007, "grad_norm": 0.5435691475868225, "learning_rate": 3.520487229155406e-07, "loss": 4.1941, "step": 30989 }, { "epoch": 0.9465485644471594, "grad_norm": 0.5479936599731445, "learning_rate": 3.516476711910577e-07, "loss": 4.2629, "step": 30990 }, { "epoch": 0.9465791081246182, "grad_norm": 0.5381700992584229, "learning_rate": 3.5124684641662244e-07, "loss": 4.2949, "step": 30991 }, { "epoch": 0.946609651802077, "grad_norm": 0.5378504991531372, "learning_rate": 3.5084624859593187e-07, "loss": 4.2455, "step": 30992 }, { "epoch": 0.9466401954795357, "grad_norm": 0.5365647673606873, "learning_rate": 3.504458777326747e-07, "loss": 4.0922, "step": 30993 }, { "epoch": 0.9466707391569945, "grad_norm": 0.5419278740882874, "learning_rate": 3.500457338305313e-07, "loss": 4.2195, "step": 30994 }, { "epoch": 0.9467012828344533, "grad_norm": 0.5362370014190674, "learning_rate": 3.4964581689319595e-07, "loss": 4.1992, "step": 30995 }, { "epoch": 0.946731826511912, "grad_norm": 0.563796877861023, "learning_rate": 3.4924612692434356e-07, "loss": 4.2896, "step": 30996 }, { "epoch": 0.9467623701893708, "grad_norm": 0.5368059873580933, "learning_rate": 3.4884666392765716e-07, "loss": 4.2013, "step": 30997 }, { "epoch": 0.9467929138668295, "grad_norm": 0.5416677594184875, "learning_rate": 3.4844742790681453e-07, "loss": 4.2053, "step": 30998 }, { "epoch": 0.9468234575442883, "grad_norm": 0.5447730422019958, "learning_rate": 3.4804841886548755e-07, "loss": 4.076, "step": 30999 }, { "epoch": 0.9468540012217471, "grad_norm": 0.5487433671951294, "learning_rate": 3.47649636807354e-07, "loss": 4.318, "step": 31000 }, { "epoch": 0.9468845448992058, "grad_norm": 0.5381028652191162, "learning_rate": 3.4725108173608856e-07, "loss": 4.1905, "step": 31001 }, { "epoch": 0.9469150885766646, "grad_norm": 0.539971113204956, "learning_rate": 3.468527536553551e-07, "loss": 4.2522, "step": 31002 }, { "epoch": 0.9469456322541234, "grad_norm": 0.5454782843589783, "learning_rate": 3.4645465256882283e-07, "loss": 4.1711, "step": 31003 }, { "epoch": 0.9469761759315821, "grad_norm": 0.5276846885681152, "learning_rate": 3.4605677848016104e-07, "loss": 4.1924, "step": 31004 }, { "epoch": 0.9470067196090409, "grad_norm": 0.5455727577209473, "learning_rate": 3.4565913139302796e-07, "loss": 4.2266, "step": 31005 }, { "epoch": 0.9470372632864997, "grad_norm": 0.5357871055603027, "learning_rate": 3.452617113110873e-07, "loss": 4.11, "step": 31006 }, { "epoch": 0.9470678069639584, "grad_norm": 0.5449666976928711, "learning_rate": 3.44864518238e-07, "loss": 4.2552, "step": 31007 }, { "epoch": 0.9470983506414172, "grad_norm": 0.5435340404510498, "learning_rate": 3.4446755217741875e-07, "loss": 4.3283, "step": 31008 }, { "epoch": 0.947128894318876, "grad_norm": 0.5373547673225403, "learning_rate": 3.4407081313300447e-07, "loss": 4.2545, "step": 31009 }, { "epoch": 0.9471594379963347, "grad_norm": 0.5408435463905334, "learning_rate": 3.43674301108407e-07, "loss": 4.2944, "step": 31010 }, { "epoch": 0.9471899816737935, "grad_norm": 0.535073459148407, "learning_rate": 3.432780161072763e-07, "loss": 4.2077, "step": 31011 }, { "epoch": 0.9472205253512523, "grad_norm": 0.5463140606880188, "learning_rate": 3.4288195813326207e-07, "loss": 4.2644, "step": 31012 }, { "epoch": 0.947251069028711, "grad_norm": 0.5472217202186584, "learning_rate": 3.424861271900115e-07, "loss": 4.3511, "step": 31013 }, { "epoch": 0.9472816127061698, "grad_norm": 0.5512489676475525, "learning_rate": 3.420905232811661e-07, "loss": 4.1737, "step": 31014 }, { "epoch": 0.9473121563836285, "grad_norm": 0.5481220483779907, "learning_rate": 3.416951464103757e-07, "loss": 4.1539, "step": 31015 }, { "epoch": 0.9473427000610873, "grad_norm": 0.5427537560462952, "learning_rate": 3.4129999658127356e-07, "loss": 4.2417, "step": 31016 }, { "epoch": 0.9473732437385461, "grad_norm": 0.5341973900794983, "learning_rate": 3.409050737974984e-07, "loss": 4.0913, "step": 31017 }, { "epoch": 0.9474037874160048, "grad_norm": 0.5395221710205078, "learning_rate": 3.405103780626917e-07, "loss": 4.3165, "step": 31018 }, { "epoch": 0.9474343310934636, "grad_norm": 0.5563510060310364, "learning_rate": 3.40115909380484e-07, "loss": 4.2395, "step": 31019 }, { "epoch": 0.9474648747709224, "grad_norm": 0.5405120253562927, "learning_rate": 3.397216677545084e-07, "loss": 4.248, "step": 31020 }, { "epoch": 0.9474954184483811, "grad_norm": 0.5426160097122192, "learning_rate": 3.3932765318839264e-07, "loss": 4.2496, "step": 31021 }, { "epoch": 0.94752596212584, "grad_norm": 0.5440481901168823, "learning_rate": 3.389338656857671e-07, "loss": 4.2342, "step": 31022 }, { "epoch": 0.9475565058032988, "grad_norm": 0.5524691343307495, "learning_rate": 3.385403052502567e-07, "loss": 4.2163, "step": 31023 }, { "epoch": 0.9475870494807574, "grad_norm": 0.5489378571510315, "learning_rate": 3.3814697188548905e-07, "loss": 4.203, "step": 31024 }, { "epoch": 0.9476175931582163, "grad_norm": 0.5361405611038208, "learning_rate": 3.377538655950779e-07, "loss": 4.2916, "step": 31025 }, { "epoch": 0.9476481368356751, "grad_norm": 0.5460878610610962, "learning_rate": 3.373609863826482e-07, "loss": 4.2076, "step": 31026 }, { "epoch": 0.9476786805131338, "grad_norm": 0.5494603514671326, "learning_rate": 3.369683342518165e-07, "loss": 4.2219, "step": 31027 }, { "epoch": 0.9477092241905926, "grad_norm": 0.5404630899429321, "learning_rate": 3.365759092061993e-07, "loss": 4.314, "step": 31028 }, { "epoch": 0.9477397678680514, "grad_norm": 0.5449851751327515, "learning_rate": 3.361837112494048e-07, "loss": 4.2403, "step": 31029 }, { "epoch": 0.9477703115455101, "grad_norm": 0.5406471490859985, "learning_rate": 3.3579174038505247e-07, "loss": 4.1993, "step": 31030 }, { "epoch": 0.9478008552229689, "grad_norm": 0.5466958284378052, "learning_rate": 3.3539999661674204e-07, "loss": 4.2202, "step": 31031 }, { "epoch": 0.9478313989004276, "grad_norm": 0.5540319681167603, "learning_rate": 3.350084799480874e-07, "loss": 4.2422, "step": 31032 }, { "epoch": 0.9478619425778864, "grad_norm": 0.5469534397125244, "learning_rate": 3.346171903826911e-07, "loss": 4.2768, "step": 31033 }, { "epoch": 0.9478924862553452, "grad_norm": 0.5357775092124939, "learning_rate": 3.342261279241532e-07, "loss": 4.2547, "step": 31034 }, { "epoch": 0.9479230299328039, "grad_norm": 0.5464038252830505, "learning_rate": 3.338352925760818e-07, "loss": 4.1764, "step": 31035 }, { "epoch": 0.9479535736102627, "grad_norm": 0.5460106730461121, "learning_rate": 3.3344468434206854e-07, "loss": 4.2446, "step": 31036 }, { "epoch": 0.9479841172877215, "grad_norm": 0.5344069600105286, "learning_rate": 3.3305430322571054e-07, "loss": 4.2551, "step": 31037 }, { "epoch": 0.9480146609651802, "grad_norm": 0.5381438732147217, "learning_rate": 3.326641492306076e-07, "loss": 4.1678, "step": 31038 }, { "epoch": 0.948045204642639, "grad_norm": 0.5363252758979797, "learning_rate": 3.322742223603459e-07, "loss": 4.2319, "step": 31039 }, { "epoch": 0.9480757483200978, "grad_norm": 0.5431049466133118, "learning_rate": 3.318845226185197e-07, "loss": 4.1262, "step": 31040 }, { "epoch": 0.9481062919975565, "grad_norm": 0.5424254536628723, "learning_rate": 3.3149505000871773e-07, "loss": 4.2993, "step": 31041 }, { "epoch": 0.9481368356750153, "grad_norm": 0.536848247051239, "learning_rate": 3.3110580453452335e-07, "loss": 4.213, "step": 31042 }, { "epoch": 0.9481673793524741, "grad_norm": 0.5303897261619568, "learning_rate": 3.3071678619951694e-07, "loss": 4.2787, "step": 31043 }, { "epoch": 0.9481979230299328, "grad_norm": 0.5643481016159058, "learning_rate": 3.3032799500729015e-07, "loss": 4.2743, "step": 31044 }, { "epoch": 0.9482284667073916, "grad_norm": 0.5511536598205566, "learning_rate": 3.299394309614151e-07, "loss": 4.2763, "step": 31045 }, { "epoch": 0.9482590103848504, "grad_norm": 0.5531484484672546, "learning_rate": 3.295510940654695e-07, "loss": 4.3148, "step": 31046 }, { "epoch": 0.9482895540623091, "grad_norm": 0.5388051867485046, "learning_rate": 3.2916298432303374e-07, "loss": 4.2026, "step": 31047 }, { "epoch": 0.9483200977397679, "grad_norm": 0.5387284755706787, "learning_rate": 3.2877510173768e-07, "loss": 4.257, "step": 31048 }, { "epoch": 0.9483506414172266, "grad_norm": 0.529813289642334, "learning_rate": 3.283874463129777e-07, "loss": 4.1806, "step": 31049 }, { "epoch": 0.9483811850946854, "grad_norm": 0.5383124947547913, "learning_rate": 3.280000180524961e-07, "loss": 4.273, "step": 31050 }, { "epoch": 0.9484117287721442, "grad_norm": 0.5458213686943054, "learning_rate": 3.2761281695980194e-07, "loss": 4.2914, "step": 31051 }, { "epoch": 0.9484422724496029, "grad_norm": 0.5503880381584167, "learning_rate": 3.2722584303846446e-07, "loss": 4.1682, "step": 31052 }, { "epoch": 0.9484728161270617, "grad_norm": 0.5376272201538086, "learning_rate": 3.2683909629204477e-07, "loss": 4.1294, "step": 31053 }, { "epoch": 0.9485033598045205, "grad_norm": 0.5377720594406128, "learning_rate": 3.2645257672410114e-07, "loss": 4.3022, "step": 31054 }, { "epoch": 0.9485339034819792, "grad_norm": 0.5526289939880371, "learning_rate": 3.260662843381945e-07, "loss": 4.2529, "step": 31055 }, { "epoch": 0.948564447159438, "grad_norm": 0.542432963848114, "learning_rate": 3.256802191378833e-07, "loss": 4.2202, "step": 31056 }, { "epoch": 0.9485949908368968, "grad_norm": 0.5536737442016602, "learning_rate": 3.252943811267201e-07, "loss": 4.2555, "step": 31057 }, { "epoch": 0.9486255345143555, "grad_norm": 0.5322566032409668, "learning_rate": 3.2490877030825763e-07, "loss": 4.0866, "step": 31058 }, { "epoch": 0.9486560781918143, "grad_norm": 0.5447034239768982, "learning_rate": 3.2452338668604586e-07, "loss": 4.1984, "step": 31059 }, { "epoch": 0.9486866218692731, "grad_norm": 0.5344063639640808, "learning_rate": 3.2413823026363474e-07, "loss": 4.277, "step": 31060 }, { "epoch": 0.9487171655467318, "grad_norm": 0.5556546449661255, "learning_rate": 3.237533010445715e-07, "loss": 4.2129, "step": 31061 }, { "epoch": 0.9487477092241906, "grad_norm": 0.5343551635742188, "learning_rate": 3.233685990323976e-07, "loss": 4.2359, "step": 31062 }, { "epoch": 0.9487782529016494, "grad_norm": 0.5378296971321106, "learning_rate": 3.229841242306547e-07, "loss": 4.2203, "step": 31063 }, { "epoch": 0.9488087965791081, "grad_norm": 0.5484780669212341, "learning_rate": 3.2259987664289003e-07, "loss": 4.3813, "step": 31064 }, { "epoch": 0.9488393402565669, "grad_norm": 0.5519217252731323, "learning_rate": 3.222158562726313e-07, "loss": 4.3118, "step": 31065 }, { "epoch": 0.9488698839340256, "grad_norm": 0.5546037554740906, "learning_rate": 3.218320631234201e-07, "loss": 4.3253, "step": 31066 }, { "epoch": 0.9489004276114844, "grad_norm": 0.5394432544708252, "learning_rate": 3.2144849719878964e-07, "loss": 4.2881, "step": 31067 }, { "epoch": 0.9489309712889432, "grad_norm": 0.5382447838783264, "learning_rate": 3.210651585022706e-07, "loss": 4.2801, "step": 31068 }, { "epoch": 0.9489615149664019, "grad_norm": 0.5393043756484985, "learning_rate": 3.2068204703739613e-07, "loss": 4.1365, "step": 31069 }, { "epoch": 0.9489920586438607, "grad_norm": 0.5414528846740723, "learning_rate": 3.2029916280768843e-07, "loss": 4.3021, "step": 31070 }, { "epoch": 0.9490226023213195, "grad_norm": 0.5388184785842896, "learning_rate": 3.1991650581667534e-07, "loss": 4.2186, "step": 31071 }, { "epoch": 0.9490531459987782, "grad_norm": 0.5423685312271118, "learning_rate": 3.1953407606788166e-07, "loss": 4.2094, "step": 31072 }, { "epoch": 0.949083689676237, "grad_norm": 0.540168285369873, "learning_rate": 3.191518735648269e-07, "loss": 4.2229, "step": 31073 }, { "epoch": 0.9491142333536958, "grad_norm": 0.5389865040779114, "learning_rate": 3.1876989831103043e-07, "loss": 4.3394, "step": 31074 }, { "epoch": 0.9491447770311545, "grad_norm": 0.5374816060066223, "learning_rate": 3.183881503100089e-07, "loss": 4.1985, "step": 31075 }, { "epoch": 0.9491753207086133, "grad_norm": 0.5396314263343811, "learning_rate": 3.1800662956527615e-07, "loss": 4.2528, "step": 31076 }, { "epoch": 0.9492058643860721, "grad_norm": 0.5423129200935364, "learning_rate": 3.1762533608034885e-07, "loss": 4.2255, "step": 31077 }, { "epoch": 0.9492364080635308, "grad_norm": 0.5360361933708191, "learning_rate": 3.172442698587352e-07, "loss": 4.2067, "step": 31078 }, { "epoch": 0.9492669517409896, "grad_norm": 0.5462660789489746, "learning_rate": 3.1686343090394366e-07, "loss": 4.2797, "step": 31079 }, { "epoch": 0.9492974954184484, "grad_norm": 0.5519376397132874, "learning_rate": 3.164828192194796e-07, "loss": 4.2869, "step": 31080 }, { "epoch": 0.9493280390959071, "grad_norm": 0.5482290387153625, "learning_rate": 3.161024348088515e-07, "loss": 4.2494, "step": 31081 }, { "epoch": 0.9493585827733659, "grad_norm": 0.5512661337852478, "learning_rate": 3.157222776755592e-07, "loss": 4.2764, "step": 31082 }, { "epoch": 0.9493891264508246, "grad_norm": 0.5537965893745422, "learning_rate": 3.1534234782310544e-07, "loss": 4.2304, "step": 31083 }, { "epoch": 0.9494196701282834, "grad_norm": 0.5412765145301819, "learning_rate": 3.14962645254982e-07, "loss": 4.1465, "step": 31084 }, { "epoch": 0.9494502138057422, "grad_norm": 0.5454320907592773, "learning_rate": 3.145831699746915e-07, "loss": 4.1207, "step": 31085 }, { "epoch": 0.9494807574832009, "grad_norm": 0.5444226264953613, "learning_rate": 3.142039219857257e-07, "loss": 4.2165, "step": 31086 }, { "epoch": 0.9495113011606597, "grad_norm": 0.5364000797271729, "learning_rate": 3.1382490129157614e-07, "loss": 4.2121, "step": 31087 }, { "epoch": 0.9495418448381185, "grad_norm": 0.537569522857666, "learning_rate": 3.134461078957346e-07, "loss": 4.2534, "step": 31088 }, { "epoch": 0.9495723885155772, "grad_norm": 0.5434393882751465, "learning_rate": 3.130675418016843e-07, "loss": 4.2907, "step": 31089 }, { "epoch": 0.949602932193036, "grad_norm": 0.5423684120178223, "learning_rate": 3.1268920301291693e-07, "loss": 4.2663, "step": 31090 }, { "epoch": 0.9496334758704948, "grad_norm": 0.550016462802887, "learning_rate": 3.1231109153291026e-07, "loss": 4.2688, "step": 31091 }, { "epoch": 0.9496640195479535, "grad_norm": 0.5384196043014526, "learning_rate": 3.119332073651504e-07, "loss": 4.2721, "step": 31092 }, { "epoch": 0.9496945632254123, "grad_norm": 0.5359638929367065, "learning_rate": 3.115555505131151e-07, "loss": 4.26, "step": 31093 }, { "epoch": 0.9497251069028712, "grad_norm": 0.5494295358657837, "learning_rate": 3.1117812098027946e-07, "loss": 4.2508, "step": 31094 }, { "epoch": 0.9497556505803298, "grad_norm": 0.5432023406028748, "learning_rate": 3.1080091877012384e-07, "loss": 4.2159, "step": 31095 }, { "epoch": 0.9497861942577887, "grad_norm": 0.5402694940567017, "learning_rate": 3.1042394388611505e-07, "loss": 4.1824, "step": 31096 }, { "epoch": 0.9498167379352475, "grad_norm": 0.541584849357605, "learning_rate": 3.1004719633172806e-07, "loss": 4.2475, "step": 31097 }, { "epoch": 0.9498472816127062, "grad_norm": 0.5412406921386719, "learning_rate": 3.096706761104323e-07, "loss": 4.1623, "step": 31098 }, { "epoch": 0.949877825290165, "grad_norm": 0.5438846349716187, "learning_rate": 3.092943832256889e-07, "loss": 4.2733, "step": 31099 }, { "epoch": 0.9499083689676237, "grad_norm": 0.5432496666908264, "learning_rate": 3.089183176809729e-07, "loss": 4.2724, "step": 31100 }, { "epoch": 0.9499389126450825, "grad_norm": 0.5409735441207886, "learning_rate": 3.0854247947973424e-07, "loss": 4.1961, "step": 31101 }, { "epoch": 0.9499694563225413, "grad_norm": 0.5399622917175293, "learning_rate": 3.081668686254452e-07, "loss": 4.2362, "step": 31102 }, { "epoch": 0.95, "grad_norm": 0.5400933623313904, "learning_rate": 3.077914851215585e-07, "loss": 4.2041, "step": 31103 }, { "epoch": 0.9500305436774588, "grad_norm": 0.5503819584846497, "learning_rate": 3.0741632897152705e-07, "loss": 4.2591, "step": 31104 }, { "epoch": 0.9500610873549176, "grad_norm": 0.5395212769508362, "learning_rate": 3.0704140017881466e-07, "loss": 4.2988, "step": 31105 }, { "epoch": 0.9500916310323763, "grad_norm": 0.5424867868423462, "learning_rate": 3.066666987468658e-07, "loss": 4.1746, "step": 31106 }, { "epoch": 0.9501221747098351, "grad_norm": 0.5427084565162659, "learning_rate": 3.062922246791305e-07, "loss": 4.1775, "step": 31107 }, { "epoch": 0.9501527183872939, "grad_norm": 0.5386514663696289, "learning_rate": 3.059179779790616e-07, "loss": 4.2375, "step": 31108 }, { "epoch": 0.9501832620647526, "grad_norm": 0.5370856523513794, "learning_rate": 3.055439586501008e-07, "loss": 4.2517, "step": 31109 }, { "epoch": 0.9502138057422114, "grad_norm": 0.5393168926239014, "learning_rate": 3.051701666956952e-07, "loss": 4.2445, "step": 31110 }, { "epoch": 0.9502443494196702, "grad_norm": 0.5471973419189453, "learning_rate": 3.0479660211928107e-07, "loss": 4.3677, "step": 31111 }, { "epoch": 0.9502748930971289, "grad_norm": 0.5456666946411133, "learning_rate": 3.044232649243056e-07, "loss": 4.2793, "step": 31112 }, { "epoch": 0.9503054367745877, "grad_norm": 0.5415616035461426, "learning_rate": 3.040501551141994e-07, "loss": 4.1307, "step": 31113 }, { "epoch": 0.9503359804520465, "grad_norm": 0.5380381345748901, "learning_rate": 3.0367727269240145e-07, "loss": 4.1877, "step": 31114 }, { "epoch": 0.9503665241295052, "grad_norm": 0.5323153138160706, "learning_rate": 3.033046176623477e-07, "loss": 4.2267, "step": 31115 }, { "epoch": 0.950397067806964, "grad_norm": 0.5365927815437317, "learning_rate": 3.029321900274606e-07, "loss": 4.2579, "step": 31116 }, { "epoch": 0.9504276114844227, "grad_norm": 0.5444545745849609, "learning_rate": 3.0255998979117906e-07, "loss": 4.2725, "step": 31117 }, { "epoch": 0.9504581551618815, "grad_norm": 0.5372694730758667, "learning_rate": 3.0218801695692524e-07, "loss": 4.3438, "step": 31118 }, { "epoch": 0.9504886988393403, "grad_norm": 0.5461190342903137, "learning_rate": 3.018162715281242e-07, "loss": 4.3034, "step": 31119 }, { "epoch": 0.950519242516799, "grad_norm": 0.5506799221038818, "learning_rate": 3.0144475350819824e-07, "loss": 4.244, "step": 31120 }, { "epoch": 0.9505497861942578, "grad_norm": 0.538324773311615, "learning_rate": 3.0107346290057236e-07, "loss": 4.2167, "step": 31121 }, { "epoch": 0.9505803298717166, "grad_norm": 0.5586873292922974, "learning_rate": 3.007023997086578e-07, "loss": 4.2436, "step": 31122 }, { "epoch": 0.9506108735491753, "grad_norm": 0.5440844297409058, "learning_rate": 3.0033156393587945e-07, "loss": 4.3163, "step": 31123 }, { "epoch": 0.9506414172266341, "grad_norm": 0.5435771942138672, "learning_rate": 2.9996095558564585e-07, "loss": 4.2348, "step": 31124 }, { "epoch": 0.9506719609040929, "grad_norm": 0.5323965549468994, "learning_rate": 2.995905746613681e-07, "loss": 4.1838, "step": 31125 }, { "epoch": 0.9507025045815516, "grad_norm": 0.5426923036575317, "learning_rate": 2.9922042116646563e-07, "loss": 4.2089, "step": 31126 }, { "epoch": 0.9507330482590104, "grad_norm": 0.5419337749481201, "learning_rate": 2.988504951043358e-07, "loss": 4.2784, "step": 31127 }, { "epoch": 0.9507635919364692, "grad_norm": 0.5401503443717957, "learning_rate": 2.984807964783898e-07, "loss": 4.2635, "step": 31128 }, { "epoch": 0.9507941356139279, "grad_norm": 0.5444408059120178, "learning_rate": 2.9811132529203314e-07, "loss": 4.2904, "step": 31129 }, { "epoch": 0.9508246792913867, "grad_norm": 0.5481789708137512, "learning_rate": 2.977420815486659e-07, "loss": 4.2055, "step": 31130 }, { "epoch": 0.9508552229688455, "grad_norm": 0.551930844783783, "learning_rate": 2.973730652516882e-07, "loss": 4.2527, "step": 31131 }, { "epoch": 0.9508857666463042, "grad_norm": 0.5444566011428833, "learning_rate": 2.970042764044972e-07, "loss": 4.2646, "step": 31132 }, { "epoch": 0.950916310323763, "grad_norm": 0.5339038372039795, "learning_rate": 2.966357150104876e-07, "loss": 4.1932, "step": 31133 }, { "epoch": 0.9509468540012217, "grad_norm": 0.5430819392204285, "learning_rate": 2.962673810730565e-07, "loss": 4.3026, "step": 31134 }, { "epoch": 0.9509773976786805, "grad_norm": 0.5311962962150574, "learning_rate": 2.9589927459559017e-07, "loss": 4.2472, "step": 31135 }, { "epoch": 0.9510079413561393, "grad_norm": 0.5465847849845886, "learning_rate": 2.955313955814831e-07, "loss": 4.178, "step": 31136 }, { "epoch": 0.951038485033598, "grad_norm": 0.5324253439903259, "learning_rate": 2.9516374403411873e-07, "loss": 4.1795, "step": 31137 }, { "epoch": 0.9510690287110568, "grad_norm": 0.5498024821281433, "learning_rate": 2.9479631995688593e-07, "loss": 4.1669, "step": 31138 }, { "epoch": 0.9510995723885156, "grad_norm": 0.5493994951248169, "learning_rate": 2.9442912335316543e-07, "loss": 4.2464, "step": 31139 }, { "epoch": 0.9511301160659743, "grad_norm": 0.5349670648574829, "learning_rate": 2.9406215422633774e-07, "loss": 4.2229, "step": 31140 }, { "epoch": 0.9511606597434331, "grad_norm": 0.5432365536689758, "learning_rate": 2.9369541257978084e-07, "loss": 4.2531, "step": 31141 }, { "epoch": 0.9511912034208919, "grad_norm": 0.5449725985527039, "learning_rate": 2.933288984168725e-07, "loss": 4.2588, "step": 31142 }, { "epoch": 0.9512217470983506, "grad_norm": 0.5522128939628601, "learning_rate": 2.929626117409906e-07, "loss": 4.2602, "step": 31143 }, { "epoch": 0.9512522907758094, "grad_norm": 0.5397893190383911, "learning_rate": 2.925965525555019e-07, "loss": 4.239, "step": 31144 }, { "epoch": 0.9512828344532682, "grad_norm": 0.5391940474510193, "learning_rate": 2.9223072086378147e-07, "loss": 4.2573, "step": 31145 }, { "epoch": 0.9513133781307269, "grad_norm": 0.5406990647315979, "learning_rate": 2.918651166691988e-07, "loss": 4.3513, "step": 31146 }, { "epoch": 0.9513439218081857, "grad_norm": 0.5346055030822754, "learning_rate": 2.9149973997511517e-07, "loss": 4.2742, "step": 31147 }, { "epoch": 0.9513744654856445, "grad_norm": 0.5368362665176392, "learning_rate": 2.911345907848972e-07, "loss": 4.1912, "step": 31148 }, { "epoch": 0.9514050091631032, "grad_norm": 0.5427349805831909, "learning_rate": 2.907696691019063e-07, "loss": 4.2069, "step": 31149 }, { "epoch": 0.951435552840562, "grad_norm": 0.5391665697097778, "learning_rate": 2.9040497492950346e-07, "loss": 4.2001, "step": 31150 }, { "epoch": 0.9514660965180207, "grad_norm": 0.5433951616287231, "learning_rate": 2.9004050827105e-07, "loss": 4.2295, "step": 31151 }, { "epoch": 0.9514966401954795, "grad_norm": 0.561847984790802, "learning_rate": 2.89676269129896e-07, "loss": 4.2369, "step": 31152 }, { "epoch": 0.9515271838729383, "grad_norm": 0.5490949749946594, "learning_rate": 2.8931225750939706e-07, "loss": 4.077, "step": 31153 }, { "epoch": 0.951557727550397, "grad_norm": 0.537505030632019, "learning_rate": 2.889484734129061e-07, "loss": 4.1753, "step": 31154 }, { "epoch": 0.9515882712278558, "grad_norm": 0.5466387867927551, "learning_rate": 2.8858491684377044e-07, "loss": 4.2444, "step": 31155 }, { "epoch": 0.9516188149053146, "grad_norm": 0.5407359004020691, "learning_rate": 2.882215878053374e-07, "loss": 4.2301, "step": 31156 }, { "epoch": 0.9516493585827733, "grad_norm": 0.531938910484314, "learning_rate": 2.87858486300957e-07, "loss": 4.2005, "step": 31157 }, { "epoch": 0.9516799022602321, "grad_norm": 0.5452718138694763, "learning_rate": 2.8749561233396563e-07, "loss": 4.2839, "step": 31158 }, { "epoch": 0.9517104459376909, "grad_norm": 0.525499165058136, "learning_rate": 2.8713296590771043e-07, "loss": 4.1923, "step": 31159 }, { "epoch": 0.9517409896151496, "grad_norm": 0.5386474132537842, "learning_rate": 2.8677054702552777e-07, "loss": 4.1593, "step": 31160 }, { "epoch": 0.9517715332926084, "grad_norm": 0.5435231328010559, "learning_rate": 2.8640835569075653e-07, "loss": 4.2497, "step": 31161 }, { "epoch": 0.9518020769700672, "grad_norm": 0.5367279052734375, "learning_rate": 2.860463919067274e-07, "loss": 4.2942, "step": 31162 }, { "epoch": 0.9518326206475259, "grad_norm": 0.5468617081642151, "learning_rate": 2.8568465567677673e-07, "loss": 4.3118, "step": 31163 }, { "epoch": 0.9518631643249847, "grad_norm": 0.5362396240234375, "learning_rate": 2.85323147004235e-07, "loss": 4.1924, "step": 31164 }, { "epoch": 0.9518937080024434, "grad_norm": 0.5493225455284119, "learning_rate": 2.8496186589243023e-07, "loss": 4.27, "step": 31165 }, { "epoch": 0.9519242516799022, "grad_norm": 0.5366678833961487, "learning_rate": 2.846008123446875e-07, "loss": 4.2125, "step": 31166 }, { "epoch": 0.951954795357361, "grad_norm": 0.5346881151199341, "learning_rate": 2.842399863643319e-07, "loss": 4.2207, "step": 31167 }, { "epoch": 0.9519853390348197, "grad_norm": 0.5410087704658508, "learning_rate": 2.838793879546886e-07, "loss": 4.2238, "step": 31168 }, { "epoch": 0.9520158827122785, "grad_norm": 0.5416857004165649, "learning_rate": 2.835190171190744e-07, "loss": 4.2349, "step": 31169 }, { "epoch": 0.9520464263897374, "grad_norm": 0.5384538769721985, "learning_rate": 2.8315887386080876e-07, "loss": 4.2469, "step": 31170 }, { "epoch": 0.952076970067196, "grad_norm": 0.5382059812545776, "learning_rate": 2.8279895818320856e-07, "loss": 4.1215, "step": 31171 }, { "epoch": 0.9521075137446549, "grad_norm": 0.5442319512367249, "learning_rate": 2.8243927008958504e-07, "loss": 4.2705, "step": 31172 }, { "epoch": 0.9521380574221137, "grad_norm": 0.5366573333740234, "learning_rate": 2.820798095832494e-07, "loss": 4.2813, "step": 31173 }, { "epoch": 0.9521686010995724, "grad_norm": 0.5506243705749512, "learning_rate": 2.817205766675185e-07, "loss": 4.2932, "step": 31174 }, { "epoch": 0.9521991447770312, "grad_norm": 0.5465124249458313, "learning_rate": 2.813615713456924e-07, "loss": 4.2859, "step": 31175 }, { "epoch": 0.95222968845449, "grad_norm": 0.5410732626914978, "learning_rate": 2.810027936210796e-07, "loss": 4.2472, "step": 31176 }, { "epoch": 0.9522602321319487, "grad_norm": 0.5413599014282227, "learning_rate": 2.80644243496983e-07, "loss": 4.2152, "step": 31177 }, { "epoch": 0.9522907758094075, "grad_norm": 0.5543507933616638, "learning_rate": 2.802859209767056e-07, "loss": 4.2378, "step": 31178 }, { "epoch": 0.9523213194868663, "grad_norm": 0.5491299629211426, "learning_rate": 2.799278260635446e-07, "loss": 4.2862, "step": 31179 }, { "epoch": 0.952351863164325, "grad_norm": 0.5515795946121216, "learning_rate": 2.795699587607975e-07, "loss": 4.2268, "step": 31180 }, { "epoch": 0.9523824068417838, "grad_norm": 0.5298249125480652, "learning_rate": 2.792123190717616e-07, "loss": 4.2387, "step": 31181 }, { "epoch": 0.9524129505192425, "grad_norm": 0.5384054183959961, "learning_rate": 2.7885490699972593e-07, "loss": 4.0928, "step": 31182 }, { "epoch": 0.9524434941967013, "grad_norm": 0.5409261584281921, "learning_rate": 2.784977225479851e-07, "loss": 4.2779, "step": 31183 }, { "epoch": 0.9524740378741601, "grad_norm": 0.538419783115387, "learning_rate": 2.781407657198254e-07, "loss": 4.2107, "step": 31184 }, { "epoch": 0.9525045815516188, "grad_norm": 0.5519149899482727, "learning_rate": 2.777840365185358e-07, "loss": 4.3203, "step": 31185 }, { "epoch": 0.9525351252290776, "grad_norm": 0.5393933653831482, "learning_rate": 2.7742753494739705e-07, "loss": 4.2588, "step": 31186 }, { "epoch": 0.9525656689065364, "grad_norm": 0.5338723659515381, "learning_rate": 2.770712610096954e-07, "loss": 4.2256, "step": 31187 }, { "epoch": 0.9525962125839951, "grad_norm": 0.5426453351974487, "learning_rate": 2.7671521470870877e-07, "loss": 4.1771, "step": 31188 }, { "epoch": 0.9526267562614539, "grad_norm": 0.5357959866523743, "learning_rate": 2.7635939604771787e-07, "loss": 4.288, "step": 31189 }, { "epoch": 0.9526572999389127, "grad_norm": 0.5457759499549866, "learning_rate": 2.760038050299979e-07, "loss": 4.2971, "step": 31190 }, { "epoch": 0.9526878436163714, "grad_norm": 0.5456764698028564, "learning_rate": 2.756484416588212e-07, "loss": 4.2542, "step": 31191 }, { "epoch": 0.9527183872938302, "grad_norm": 0.546515166759491, "learning_rate": 2.752933059374629e-07, "loss": 4.0237, "step": 31192 }, { "epoch": 0.952748930971289, "grad_norm": 0.5397354960441589, "learning_rate": 2.7493839786918996e-07, "loss": 4.2368, "step": 31193 }, { "epoch": 0.9527794746487477, "grad_norm": 0.5379648208618164, "learning_rate": 2.7458371745727185e-07, "loss": 4.1789, "step": 31194 }, { "epoch": 0.9528100183262065, "grad_norm": 0.5368974804878235, "learning_rate": 2.7422926470497543e-07, "loss": 4.2661, "step": 31195 }, { "epoch": 0.9528405620036653, "grad_norm": 0.5500456094741821, "learning_rate": 2.738750396155593e-07, "loss": 4.2553, "step": 31196 }, { "epoch": 0.952871105681124, "grad_norm": 0.5766680240631104, "learning_rate": 2.735210421922929e-07, "loss": 4.2018, "step": 31197 }, { "epoch": 0.9529016493585828, "grad_norm": 0.5413593053817749, "learning_rate": 2.731672724384321e-07, "loss": 4.2426, "step": 31198 }, { "epoch": 0.9529321930360415, "grad_norm": 0.552792489528656, "learning_rate": 2.728137303572298e-07, "loss": 4.2613, "step": 31199 }, { "epoch": 0.9529627367135003, "grad_norm": 0.5527782440185547, "learning_rate": 2.7246041595194726e-07, "loss": 4.2247, "step": 31200 }, { "epoch": 0.9529932803909591, "grad_norm": 0.537336528301239, "learning_rate": 2.721073292258319e-07, "loss": 4.1287, "step": 31201 }, { "epoch": 0.9530238240684178, "grad_norm": 0.5452502369880676, "learning_rate": 2.717544701821423e-07, "loss": 4.2936, "step": 31202 }, { "epoch": 0.9530543677458766, "grad_norm": 0.5421555042266846, "learning_rate": 2.714018388241202e-07, "loss": 4.2094, "step": 31203 }, { "epoch": 0.9530849114233354, "grad_norm": 0.5474961400032043, "learning_rate": 2.710494351550158e-07, "loss": 4.261, "step": 31204 }, { "epoch": 0.9531154551007941, "grad_norm": 0.5367752909660339, "learning_rate": 2.706972591780765e-07, "loss": 4.2991, "step": 31205 }, { "epoch": 0.9531459987782529, "grad_norm": 0.5315191745758057, "learning_rate": 2.703453108965387e-07, "loss": 4.2632, "step": 31206 }, { "epoch": 0.9531765424557117, "grad_norm": 0.5474645495414734, "learning_rate": 2.6999359031364693e-07, "loss": 4.1034, "step": 31207 }, { "epoch": 0.9532070861331704, "grad_norm": 0.5417958498001099, "learning_rate": 2.69642097432643e-07, "loss": 4.2134, "step": 31208 }, { "epoch": 0.9532376298106292, "grad_norm": 0.5381478667259216, "learning_rate": 2.69290832256755e-07, "loss": 4.1871, "step": 31209 }, { "epoch": 0.953268173488088, "grad_norm": 0.5427830815315247, "learning_rate": 2.689397947892219e-07, "loss": 4.2663, "step": 31210 }, { "epoch": 0.9532987171655467, "grad_norm": 0.5364192724227905, "learning_rate": 2.6858898503327735e-07, "loss": 4.2498, "step": 31211 }, { "epoch": 0.9533292608430055, "grad_norm": 0.5415329933166504, "learning_rate": 2.6823840299214917e-07, "loss": 4.3341, "step": 31212 }, { "epoch": 0.9533598045204643, "grad_norm": 0.5425602197647095, "learning_rate": 2.6788804866906546e-07, "loss": 4.3004, "step": 31213 }, { "epoch": 0.953390348197923, "grad_norm": 0.529828667640686, "learning_rate": 2.6753792206725416e-07, "loss": 4.2613, "step": 31214 }, { "epoch": 0.9534208918753818, "grad_norm": 0.5316717624664307, "learning_rate": 2.6718802318993483e-07, "loss": 4.2192, "step": 31215 }, { "epoch": 0.9534514355528405, "grad_norm": 0.5541785955429077, "learning_rate": 2.668383520403356e-07, "loss": 4.3267, "step": 31216 }, { "epoch": 0.9534819792302993, "grad_norm": 0.5356664657592773, "learning_rate": 2.6648890862166766e-07, "loss": 4.2156, "step": 31217 }, { "epoch": 0.9535125229077581, "grad_norm": 0.5474389791488647, "learning_rate": 2.6613969293715346e-07, "loss": 4.2669, "step": 31218 }, { "epoch": 0.9535430665852168, "grad_norm": 0.5433639883995056, "learning_rate": 2.657907049900099e-07, "loss": 4.2442, "step": 31219 }, { "epoch": 0.9535736102626756, "grad_norm": 0.5329425930976868, "learning_rate": 2.654419447834483e-07, "loss": 4.2171, "step": 31220 }, { "epoch": 0.9536041539401344, "grad_norm": 0.5441465377807617, "learning_rate": 2.6509341232068e-07, "loss": 4.2635, "step": 31221 }, { "epoch": 0.9536346976175931, "grad_norm": 0.5396842956542969, "learning_rate": 2.647451076049134e-07, "loss": 4.182, "step": 31222 }, { "epoch": 0.9536652412950519, "grad_norm": 0.5442036986351013, "learning_rate": 2.643970306393545e-07, "loss": 4.1921, "step": 31223 }, { "epoch": 0.9536957849725107, "grad_norm": 0.5444502234458923, "learning_rate": 2.640491814272117e-07, "loss": 4.2922, "step": 31224 }, { "epoch": 0.9537263286499694, "grad_norm": 0.5503065586090088, "learning_rate": 2.63701559971688e-07, "loss": 4.2928, "step": 31225 }, { "epoch": 0.9537568723274282, "grad_norm": 0.5383390784263611, "learning_rate": 2.6335416627597806e-07, "loss": 4.2694, "step": 31226 }, { "epoch": 0.953787416004887, "grad_norm": 0.5362972021102905, "learning_rate": 2.6300700034328773e-07, "loss": 4.2264, "step": 31227 }, { "epoch": 0.9538179596823457, "grad_norm": 0.5372009873390198, "learning_rate": 2.626600621768088e-07, "loss": 4.2937, "step": 31228 }, { "epoch": 0.9538485033598045, "grad_norm": 0.5490292906761169, "learning_rate": 2.6231335177973883e-07, "loss": 4.2171, "step": 31229 }, { "epoch": 0.9538790470372633, "grad_norm": 0.6131801605224609, "learning_rate": 2.619668691552696e-07, "loss": 4.2495, "step": 31230 }, { "epoch": 0.953909590714722, "grad_norm": 0.5464380383491516, "learning_rate": 2.6162061430659023e-07, "loss": 4.2666, "step": 31231 }, { "epoch": 0.9539401343921808, "grad_norm": 0.5461010336875916, "learning_rate": 2.612745872368844e-07, "loss": 4.3247, "step": 31232 }, { "epoch": 0.9539706780696395, "grad_norm": 0.5428072810173035, "learning_rate": 2.609287879493494e-07, "loss": 4.284, "step": 31233 }, { "epoch": 0.9540012217470983, "grad_norm": 0.5421921610832214, "learning_rate": 2.605832164471578e-07, "loss": 4.2966, "step": 31234 }, { "epoch": 0.9540317654245571, "grad_norm": 0.5389423966407776, "learning_rate": 2.6023787273349587e-07, "loss": 4.2558, "step": 31235 }, { "epoch": 0.9540623091020158, "grad_norm": 0.5492185950279236, "learning_rate": 2.598927568115472e-07, "loss": 4.2125, "step": 31236 }, { "epoch": 0.9540928527794746, "grad_norm": 0.5461561679840088, "learning_rate": 2.595478686844843e-07, "loss": 4.238, "step": 31237 }, { "epoch": 0.9541233964569334, "grad_norm": 0.5357695817947388, "learning_rate": 2.5920320835548515e-07, "loss": 4.3016, "step": 31238 }, { "epoch": 0.9541539401343921, "grad_norm": 0.5401557683944702, "learning_rate": 2.588587758277222e-07, "loss": 4.1864, "step": 31239 }, { "epoch": 0.954184483811851, "grad_norm": 0.5515663027763367, "learning_rate": 2.5851457110436517e-07, "loss": 4.2316, "step": 31240 }, { "epoch": 0.9542150274893098, "grad_norm": 0.5359730124473572, "learning_rate": 2.5817059418858646e-07, "loss": 4.2349, "step": 31241 }, { "epoch": 0.9542455711667684, "grad_norm": 0.5448746681213379, "learning_rate": 2.578268450835558e-07, "loss": 4.3216, "step": 31242 }, { "epoch": 0.9542761148442273, "grad_norm": 0.537120521068573, "learning_rate": 2.57483323792429e-07, "loss": 4.2779, "step": 31243 }, { "epoch": 0.9543066585216861, "grad_norm": 0.5521698594093323, "learning_rate": 2.571400303183785e-07, "loss": 4.2652, "step": 31244 }, { "epoch": 0.9543372021991448, "grad_norm": 0.5485398173332214, "learning_rate": 2.5679696466456015e-07, "loss": 4.1815, "step": 31245 }, { "epoch": 0.9543677458766036, "grad_norm": 0.5432600378990173, "learning_rate": 2.5645412683413526e-07, "loss": 4.2936, "step": 31246 }, { "epoch": 0.9543982895540624, "grad_norm": 0.5450129508972168, "learning_rate": 2.5611151683025415e-07, "loss": 4.2906, "step": 31247 }, { "epoch": 0.9544288332315211, "grad_norm": 0.5486661791801453, "learning_rate": 2.5576913465608086e-07, "loss": 4.3528, "step": 31248 }, { "epoch": 0.9544593769089799, "grad_norm": 0.5485596656799316, "learning_rate": 2.5542698031476296e-07, "loss": 4.2654, "step": 31249 }, { "epoch": 0.9544899205864386, "grad_norm": 0.5391497611999512, "learning_rate": 2.5508505380945067e-07, "loss": 4.2714, "step": 31250 }, { "epoch": 0.9545204642638974, "grad_norm": 0.5403720140457153, "learning_rate": 2.547433551432915e-07, "loss": 4.2376, "step": 31251 }, { "epoch": 0.9545510079413562, "grad_norm": 0.5474361181259155, "learning_rate": 2.544018843194329e-07, "loss": 4.2354, "step": 31252 }, { "epoch": 0.9545815516188149, "grad_norm": 0.5348550081253052, "learning_rate": 2.540606413410224e-07, "loss": 4.1664, "step": 31253 }, { "epoch": 0.9546120952962737, "grad_norm": 0.5474473237991333, "learning_rate": 2.537196262111963e-07, "loss": 4.1495, "step": 31254 }, { "epoch": 0.9546426389737325, "grad_norm": 0.5464016199111938, "learning_rate": 2.5337883893309655e-07, "loss": 4.269, "step": 31255 }, { "epoch": 0.9546731826511912, "grad_norm": 0.5461854934692383, "learning_rate": 2.530382795098624e-07, "loss": 4.2289, "step": 31256 }, { "epoch": 0.95470372632865, "grad_norm": 0.5496368408203125, "learning_rate": 2.526979479446273e-07, "loss": 4.2286, "step": 31257 }, { "epoch": 0.9547342700061088, "grad_norm": 0.5455157160758972, "learning_rate": 2.52357844240525e-07, "loss": 4.3124, "step": 31258 }, { "epoch": 0.9547648136835675, "grad_norm": 0.5421806573867798, "learning_rate": 2.520179684006918e-07, "loss": 4.2577, "step": 31259 }, { "epoch": 0.9547953573610263, "grad_norm": 0.5477085113525391, "learning_rate": 2.5167832042825026e-07, "loss": 4.3354, "step": 31260 }, { "epoch": 0.9548259010384851, "grad_norm": 0.5439205765724182, "learning_rate": 2.513389003263311e-07, "loss": 4.1728, "step": 31261 }, { "epoch": 0.9548564447159438, "grad_norm": 0.5350223779678345, "learning_rate": 2.509997080980625e-07, "loss": 4.2425, "step": 31262 }, { "epoch": 0.9548869883934026, "grad_norm": 0.5459021329879761, "learning_rate": 2.506607437465586e-07, "loss": 4.2412, "step": 31263 }, { "epoch": 0.9549175320708614, "grad_norm": 0.5377346873283386, "learning_rate": 2.5032200727495013e-07, "loss": 4.3342, "step": 31264 }, { "epoch": 0.9549480757483201, "grad_norm": 0.5349006056785583, "learning_rate": 2.499834986863514e-07, "loss": 4.1869, "step": 31265 }, { "epoch": 0.9549786194257789, "grad_norm": 0.5479778051376343, "learning_rate": 2.496452179838793e-07, "loss": 4.1469, "step": 31266 }, { "epoch": 0.9550091631032376, "grad_norm": 0.5414137244224548, "learning_rate": 2.49307165170648e-07, "loss": 4.2366, "step": 31267 }, { "epoch": 0.9550397067806964, "grad_norm": 0.5414913296699524, "learning_rate": 2.4896934024977167e-07, "loss": 4.2282, "step": 31268 }, { "epoch": 0.9550702504581552, "grad_norm": 0.5463815927505493, "learning_rate": 2.4863174322436176e-07, "loss": 4.2626, "step": 31269 }, { "epoch": 0.9551007941356139, "grad_norm": 0.5342279076576233, "learning_rate": 2.482943740975241e-07, "loss": 4.2022, "step": 31270 }, { "epoch": 0.9551313378130727, "grad_norm": 0.5510480403900146, "learning_rate": 2.479572328723645e-07, "loss": 4.3004, "step": 31271 }, { "epoch": 0.9551618814905315, "grad_norm": 0.5580520629882812, "learning_rate": 2.476203195519916e-07, "loss": 4.2718, "step": 31272 }, { "epoch": 0.9551924251679902, "grad_norm": 0.5509020090103149, "learning_rate": 2.472836341395057e-07, "loss": 4.1512, "step": 31273 }, { "epoch": 0.955222968845449, "grad_norm": 0.5502440333366394, "learning_rate": 2.469471766380016e-07, "loss": 4.2727, "step": 31274 }, { "epoch": 0.9552535125229078, "grad_norm": 0.5357339382171631, "learning_rate": 2.466109470505851e-07, "loss": 4.2078, "step": 31275 }, { "epoch": 0.9552840562003665, "grad_norm": 0.539017915725708, "learning_rate": 2.462749453803481e-07, "loss": 4.0912, "step": 31276 }, { "epoch": 0.9553145998778253, "grad_norm": 0.5411527752876282, "learning_rate": 2.459391716303855e-07, "loss": 4.2297, "step": 31277 }, { "epoch": 0.9553451435552841, "grad_norm": 0.5745784640312195, "learning_rate": 2.4560362580378635e-07, "loss": 4.2344, "step": 31278 }, { "epoch": 0.9553756872327428, "grad_norm": 0.5485788583755493, "learning_rate": 2.452683079036427e-07, "loss": 4.3067, "step": 31279 }, { "epoch": 0.9554062309102016, "grad_norm": 0.541325032711029, "learning_rate": 2.44933217933041e-07, "loss": 4.219, "step": 31280 }, { "epoch": 0.9554367745876604, "grad_norm": 0.5407606959342957, "learning_rate": 2.445983558950676e-07, "loss": 4.265, "step": 31281 }, { "epoch": 0.9554673182651191, "grad_norm": 0.5336489677429199, "learning_rate": 2.442637217928062e-07, "loss": 4.1932, "step": 31282 }, { "epoch": 0.9554978619425779, "grad_norm": 0.5448383688926697, "learning_rate": 2.4392931562933483e-07, "loss": 4.2144, "step": 31283 }, { "epoch": 0.9555284056200366, "grad_norm": 0.5408494472503662, "learning_rate": 2.4359513740773723e-07, "loss": 4.2155, "step": 31284 }, { "epoch": 0.9555589492974954, "grad_norm": 0.5362230539321899, "learning_rate": 2.4326118713108305e-07, "loss": 4.1627, "step": 31285 }, { "epoch": 0.9555894929749542, "grad_norm": 0.53133225440979, "learning_rate": 2.4292746480245596e-07, "loss": 4.1277, "step": 31286 }, { "epoch": 0.9556200366524129, "grad_norm": 0.5382297039031982, "learning_rate": 2.4259397042492303e-07, "loss": 4.1764, "step": 31287 }, { "epoch": 0.9556505803298717, "grad_norm": 0.5472421050071716, "learning_rate": 2.4226070400155675e-07, "loss": 4.2556, "step": 31288 }, { "epoch": 0.9556811240073305, "grad_norm": 0.5509927868843079, "learning_rate": 2.4192766553542413e-07, "loss": 4.2657, "step": 31289 }, { "epoch": 0.9557116676847892, "grad_norm": 0.5394356846809387, "learning_rate": 2.4159485502959487e-07, "loss": 4.3308, "step": 31290 }, { "epoch": 0.955742211362248, "grad_norm": 0.5346647500991821, "learning_rate": 2.4126227248712776e-07, "loss": 4.2547, "step": 31291 }, { "epoch": 0.9557727550397068, "grad_norm": 0.5441999435424805, "learning_rate": 2.4092991791109245e-07, "loss": 4.1685, "step": 31292 }, { "epoch": 0.9558032987171655, "grad_norm": 0.545478880405426, "learning_rate": 2.405977913045448e-07, "loss": 4.229, "step": 31293 }, { "epoch": 0.9558338423946243, "grad_norm": 0.543389081954956, "learning_rate": 2.402658926705437e-07, "loss": 4.2299, "step": 31294 }, { "epoch": 0.9558643860720831, "grad_norm": 0.5380848050117493, "learning_rate": 2.3993422201214197e-07, "loss": 4.3245, "step": 31295 }, { "epoch": 0.9558949297495418, "grad_norm": 0.5588867664337158, "learning_rate": 2.396027793323985e-07, "loss": 4.1907, "step": 31296 }, { "epoch": 0.9559254734270006, "grad_norm": 0.5459279417991638, "learning_rate": 2.392715646343607e-07, "loss": 4.1755, "step": 31297 }, { "epoch": 0.9559560171044594, "grad_norm": 0.5440768599510193, "learning_rate": 2.389405779210818e-07, "loss": 4.2966, "step": 31298 }, { "epoch": 0.9559865607819181, "grad_norm": 0.533795952796936, "learning_rate": 2.3860981919560656e-07, "loss": 4.1574, "step": 31299 }, { "epoch": 0.9560171044593769, "grad_norm": 0.5462945699691772, "learning_rate": 2.3827928846098246e-07, "loss": 4.2706, "step": 31300 }, { "epoch": 0.9560476481368356, "grad_norm": 0.5394673347473145, "learning_rate": 2.3794898572025436e-07, "loss": 4.279, "step": 31301 }, { "epoch": 0.9560781918142944, "grad_norm": 0.5350743532180786, "learning_rate": 2.3761891097645873e-07, "loss": 4.252, "step": 31302 }, { "epoch": 0.9561087354917532, "grad_norm": 0.5423493385314941, "learning_rate": 2.3728906423263751e-07, "loss": 4.2124, "step": 31303 }, { "epoch": 0.9561392791692119, "grad_norm": 0.5382147431373596, "learning_rate": 2.3695944549183002e-07, "loss": 4.1972, "step": 31304 }, { "epoch": 0.9561698228466707, "grad_norm": 0.5342358946800232, "learning_rate": 2.3663005475706434e-07, "loss": 4.2825, "step": 31305 }, { "epoch": 0.9562003665241295, "grad_norm": 0.5415842533111572, "learning_rate": 2.3630089203137974e-07, "loss": 4.2558, "step": 31306 }, { "epoch": 0.9562309102015882, "grad_norm": 0.5451757907867432, "learning_rate": 2.3597195731780707e-07, "loss": 4.2414, "step": 31307 }, { "epoch": 0.956261453879047, "grad_norm": 0.5270605087280273, "learning_rate": 2.3564325061937177e-07, "loss": 4.2651, "step": 31308 }, { "epoch": 0.9562919975565058, "grad_norm": 0.5373495817184448, "learning_rate": 2.3531477193910188e-07, "loss": 4.2486, "step": 31309 }, { "epoch": 0.9563225412339645, "grad_norm": 0.5450970530509949, "learning_rate": 2.3498652128002284e-07, "loss": 4.3216, "step": 31310 }, { "epoch": 0.9563530849114233, "grad_norm": 0.5428794026374817, "learning_rate": 2.3465849864515166e-07, "loss": 4.2516, "step": 31311 }, { "epoch": 0.9563836285888822, "grad_norm": 0.5350186824798584, "learning_rate": 2.3433070403751643e-07, "loss": 4.3124, "step": 31312 }, { "epoch": 0.9564141722663408, "grad_norm": 0.5400316119194031, "learning_rate": 2.3400313746013146e-07, "loss": 4.1912, "step": 31313 }, { "epoch": 0.9564447159437997, "grad_norm": 0.5431938171386719, "learning_rate": 2.3367579891601099e-07, "loss": 4.0947, "step": 31314 }, { "epoch": 0.9564752596212583, "grad_norm": 0.5468397736549377, "learning_rate": 2.3334868840817204e-07, "loss": 4.2477, "step": 31315 }, { "epoch": 0.9565058032987171, "grad_norm": 0.5481431484222412, "learning_rate": 2.3302180593962608e-07, "loss": 4.2287, "step": 31316 }, { "epoch": 0.956536346976176, "grad_norm": 0.5424798727035522, "learning_rate": 2.3269515151338182e-07, "loss": 4.2369, "step": 31317 }, { "epoch": 0.9565668906536346, "grad_norm": 0.5428889393806458, "learning_rate": 2.3236872513244802e-07, "loss": 4.3069, "step": 31318 }, { "epoch": 0.9565974343310935, "grad_norm": 0.5331659317016602, "learning_rate": 2.3204252679982773e-07, "loss": 4.053, "step": 31319 }, { "epoch": 0.9566279780085523, "grad_norm": 0.5425511598587036, "learning_rate": 2.3171655651852698e-07, "loss": 4.302, "step": 31320 }, { "epoch": 0.956658521686011, "grad_norm": 0.5418448448181152, "learning_rate": 2.3139081429154884e-07, "loss": 4.3377, "step": 31321 }, { "epoch": 0.9566890653634698, "grad_norm": 0.5347316861152649, "learning_rate": 2.3106530012188821e-07, "loss": 4.2286, "step": 31322 }, { "epoch": 0.9567196090409286, "grad_norm": 0.5349270105361938, "learning_rate": 2.3074001401254542e-07, "loss": 4.2488, "step": 31323 }, { "epoch": 0.9567501527183873, "grad_norm": 0.5443567037582397, "learning_rate": 2.3041495596651251e-07, "loss": 4.2352, "step": 31324 }, { "epoch": 0.9567806963958461, "grad_norm": 0.5386067628860474, "learning_rate": 2.3009012598678438e-07, "loss": 4.2631, "step": 31325 }, { "epoch": 0.9568112400733049, "grad_norm": 0.5543131232261658, "learning_rate": 2.29765524076353e-07, "loss": 4.3427, "step": 31326 }, { "epoch": 0.9568417837507636, "grad_norm": 0.5437530875205994, "learning_rate": 2.2944115023820767e-07, "loss": 4.2051, "step": 31327 }, { "epoch": 0.9568723274282224, "grad_norm": 0.5384805798530579, "learning_rate": 2.2911700447532936e-07, "loss": 4.2184, "step": 31328 }, { "epoch": 0.9569028711056812, "grad_norm": 0.5441144704818726, "learning_rate": 2.287930867907101e-07, "loss": 4.2427, "step": 31329 }, { "epoch": 0.9569334147831399, "grad_norm": 0.541693389415741, "learning_rate": 2.2846939718732808e-07, "loss": 4.2847, "step": 31330 }, { "epoch": 0.9569639584605987, "grad_norm": 0.5511772036552429, "learning_rate": 2.2814593566816422e-07, "loss": 4.3703, "step": 31331 }, { "epoch": 0.9569945021380574, "grad_norm": 0.5396431088447571, "learning_rate": 2.2782270223619672e-07, "loss": 4.1829, "step": 31332 }, { "epoch": 0.9570250458155162, "grad_norm": 0.5347623229026794, "learning_rate": 2.2749969689440377e-07, "loss": 4.269, "step": 31333 }, { "epoch": 0.957055589492975, "grad_norm": 0.531062662601471, "learning_rate": 2.2717691964575515e-07, "loss": 4.2233, "step": 31334 }, { "epoch": 0.9570861331704337, "grad_norm": 0.5409833788871765, "learning_rate": 2.268543704932291e-07, "loss": 4.2306, "step": 31335 }, { "epoch": 0.9571166768478925, "grad_norm": 0.5421401262283325, "learning_rate": 2.265320494397899e-07, "loss": 4.3314, "step": 31336 }, { "epoch": 0.9571472205253513, "grad_norm": 0.5517075657844543, "learning_rate": 2.2620995648840736e-07, "loss": 4.2595, "step": 31337 }, { "epoch": 0.95717776420281, "grad_norm": 0.5490601062774658, "learning_rate": 2.2588809164204584e-07, "loss": 4.1747, "step": 31338 }, { "epoch": 0.9572083078802688, "grad_norm": 0.5453906059265137, "learning_rate": 2.2556645490367235e-07, "loss": 4.3393, "step": 31339 }, { "epoch": 0.9572388515577276, "grad_norm": 0.5435771942138672, "learning_rate": 2.2524504627624565e-07, "loss": 4.2246, "step": 31340 }, { "epoch": 0.9572693952351863, "grad_norm": 0.5299131274223328, "learning_rate": 2.2492386576272728e-07, "loss": 4.1208, "step": 31341 }, { "epoch": 0.9572999389126451, "grad_norm": 0.5337021350860596, "learning_rate": 2.2460291336607043e-07, "loss": 4.1734, "step": 31342 }, { "epoch": 0.9573304825901039, "grad_norm": 0.5380479693412781, "learning_rate": 2.2428218908923383e-07, "loss": 4.2565, "step": 31343 }, { "epoch": 0.9573610262675626, "grad_norm": 0.5377606153488159, "learning_rate": 2.2396169293517067e-07, "loss": 4.1609, "step": 31344 }, { "epoch": 0.9573915699450214, "grad_norm": 0.5358710885047913, "learning_rate": 2.236414249068286e-07, "loss": 4.3039, "step": 31345 }, { "epoch": 0.9574221136224802, "grad_norm": 0.543666422367096, "learning_rate": 2.2332138500716083e-07, "loss": 4.2827, "step": 31346 }, { "epoch": 0.9574526572999389, "grad_norm": 0.5475319623947144, "learning_rate": 2.230015732391122e-07, "loss": 4.2013, "step": 31347 }, { "epoch": 0.9574832009773977, "grad_norm": 0.5522728562355042, "learning_rate": 2.2268198960562482e-07, "loss": 4.2158, "step": 31348 }, { "epoch": 0.9575137446548564, "grad_norm": 0.5410450100898743, "learning_rate": 2.2236263410964353e-07, "loss": 4.2181, "step": 31349 }, { "epoch": 0.9575442883323152, "grad_norm": 0.5428544282913208, "learning_rate": 2.2204350675411045e-07, "loss": 4.2521, "step": 31350 }, { "epoch": 0.957574832009774, "grad_norm": 0.5846300721168518, "learning_rate": 2.217246075419621e-07, "loss": 4.2181, "step": 31351 }, { "epoch": 0.9576053756872327, "grad_norm": 0.5473644137382507, "learning_rate": 2.2140593647613506e-07, "loss": 4.325, "step": 31352 }, { "epoch": 0.9576359193646915, "grad_norm": 0.533176839351654, "learning_rate": 2.2108749355956303e-07, "loss": 4.2182, "step": 31353 }, { "epoch": 0.9576664630421503, "grad_norm": 0.5473110675811768, "learning_rate": 2.2076927879517705e-07, "loss": 4.267, "step": 31354 }, { "epoch": 0.957697006719609, "grad_norm": 0.5397263169288635, "learning_rate": 2.2045129218591086e-07, "loss": 4.1942, "step": 31355 }, { "epoch": 0.9577275503970678, "grad_norm": 0.5426350235939026, "learning_rate": 2.201335337346899e-07, "loss": 4.2463, "step": 31356 }, { "epoch": 0.9577580940745266, "grad_norm": 0.5443404912948608, "learning_rate": 2.1981600344443964e-07, "loss": 4.2747, "step": 31357 }, { "epoch": 0.9577886377519853, "grad_norm": 0.5439895391464233, "learning_rate": 2.194987013180855e-07, "loss": 4.2001, "step": 31358 }, { "epoch": 0.9578191814294441, "grad_norm": 0.5439493060112, "learning_rate": 2.1918162735854453e-07, "loss": 4.2734, "step": 31359 }, { "epoch": 0.9578497251069029, "grad_norm": 0.545958399772644, "learning_rate": 2.1886478156874223e-07, "loss": 4.3032, "step": 31360 }, { "epoch": 0.9578802687843616, "grad_norm": 0.5438959002494812, "learning_rate": 2.1854816395159018e-07, "loss": 4.228, "step": 31361 }, { "epoch": 0.9579108124618204, "grad_norm": 0.5429679751396179, "learning_rate": 2.182317745100082e-07, "loss": 4.3293, "step": 31362 }, { "epoch": 0.9579413561392792, "grad_norm": 0.5402674674987793, "learning_rate": 2.179156132469079e-07, "loss": 4.1908, "step": 31363 }, { "epoch": 0.9579718998167379, "grad_norm": 0.5342541337013245, "learning_rate": 2.1759968016520083e-07, "loss": 4.0719, "step": 31364 }, { "epoch": 0.9580024434941967, "grad_norm": 0.5486817359924316, "learning_rate": 2.1728397526779298e-07, "loss": 4.2879, "step": 31365 }, { "epoch": 0.9580329871716554, "grad_norm": 0.5393545627593994, "learning_rate": 2.1696849855759593e-07, "loss": 4.2369, "step": 31366 }, { "epoch": 0.9580635308491142, "grad_norm": 0.5338056087493896, "learning_rate": 2.166532500375129e-07, "loss": 4.1406, "step": 31367 }, { "epoch": 0.958094074526573, "grad_norm": 0.5425416827201843, "learning_rate": 2.163382297104416e-07, "loss": 4.3561, "step": 31368 }, { "epoch": 0.9581246182040317, "grad_norm": 0.5426628589630127, "learning_rate": 2.1602343757929078e-07, "loss": 4.2131, "step": 31369 }, { "epoch": 0.9581551618814905, "grad_norm": 0.5458523035049438, "learning_rate": 2.1570887364695257e-07, "loss": 4.2015, "step": 31370 }, { "epoch": 0.9581857055589493, "grad_norm": 0.5403971076011658, "learning_rate": 2.1539453791632746e-07, "loss": 4.1029, "step": 31371 }, { "epoch": 0.958216249236408, "grad_norm": 0.552287220954895, "learning_rate": 2.1508043039030756e-07, "loss": 4.1752, "step": 31372 }, { "epoch": 0.9582467929138668, "grad_norm": 0.5438511371612549, "learning_rate": 2.14766551071785e-07, "loss": 4.2759, "step": 31373 }, { "epoch": 0.9582773365913256, "grad_norm": 0.5410513281822205, "learning_rate": 2.1445289996364913e-07, "loss": 4.2329, "step": 31374 }, { "epoch": 0.9583078802687843, "grad_norm": 0.5427879095077515, "learning_rate": 2.1413947706878934e-07, "loss": 4.1781, "step": 31375 }, { "epoch": 0.9583384239462431, "grad_norm": 0.5455029010772705, "learning_rate": 2.1382628239009217e-07, "loss": 4.2067, "step": 31376 }, { "epoch": 0.9583689676237019, "grad_norm": 0.5475518107414246, "learning_rate": 2.1351331593043588e-07, "loss": 4.2686, "step": 31377 }, { "epoch": 0.9583995113011606, "grad_norm": 0.5447806119918823, "learning_rate": 2.1320057769271263e-07, "loss": 4.2316, "step": 31378 }, { "epoch": 0.9584300549786194, "grad_norm": 0.5383335947990417, "learning_rate": 2.128880676797923e-07, "loss": 4.2606, "step": 31379 }, { "epoch": 0.9584605986560782, "grad_norm": 0.5425111651420593, "learning_rate": 2.1257578589455597e-07, "loss": 4.2534, "step": 31380 }, { "epoch": 0.9584911423335369, "grad_norm": 0.5422403812408447, "learning_rate": 2.1226373233987907e-07, "loss": 4.3439, "step": 31381 }, { "epoch": 0.9585216860109957, "grad_norm": 0.5487364530563354, "learning_rate": 2.1195190701863433e-07, "loss": 4.248, "step": 31382 }, { "epoch": 0.9585522296884544, "grad_norm": 0.5425996780395508, "learning_rate": 2.1164030993369444e-07, "loss": 4.2357, "step": 31383 }, { "epoch": 0.9585827733659132, "grad_norm": 0.5470730662345886, "learning_rate": 2.113289410879238e-07, "loss": 4.3362, "step": 31384 }, { "epoch": 0.958613317043372, "grad_norm": 0.5320239663124084, "learning_rate": 2.1101780048419506e-07, "loss": 4.2713, "step": 31385 }, { "epoch": 0.9586438607208307, "grad_norm": 0.5361529588699341, "learning_rate": 2.1070688812537265e-07, "loss": 4.1954, "step": 31386 }, { "epoch": 0.9586744043982895, "grad_norm": 0.5337449312210083, "learning_rate": 2.1039620401431536e-07, "loss": 4.2058, "step": 31387 }, { "epoch": 0.9587049480757484, "grad_norm": 0.5429146885871887, "learning_rate": 2.1008574815388482e-07, "loss": 4.1768, "step": 31388 }, { "epoch": 0.958735491753207, "grad_norm": 0.5385307669639587, "learning_rate": 2.097755205469426e-07, "loss": 4.2202, "step": 31389 }, { "epoch": 0.9587660354306659, "grad_norm": 0.548546552658081, "learning_rate": 2.0946552119634199e-07, "loss": 4.3267, "step": 31390 }, { "epoch": 0.9587965791081247, "grad_norm": 0.5521602034568787, "learning_rate": 2.0915575010493625e-07, "loss": 4.3283, "step": 31391 }, { "epoch": 0.9588271227855834, "grad_norm": 0.5417184233665466, "learning_rate": 2.0884620727558145e-07, "loss": 4.3228, "step": 31392 }, { "epoch": 0.9588576664630422, "grad_norm": 0.5424174666404724, "learning_rate": 2.085368927111253e-07, "loss": 4.2569, "step": 31393 }, { "epoch": 0.958888210140501, "grad_norm": 0.5393056869506836, "learning_rate": 2.082278064144183e-07, "loss": 4.1679, "step": 31394 }, { "epoch": 0.9589187538179597, "grad_norm": 0.5446954965591431, "learning_rate": 2.079189483883054e-07, "loss": 4.2874, "step": 31395 }, { "epoch": 0.9589492974954185, "grad_norm": 0.5446645021438599, "learning_rate": 2.0761031863562597e-07, "loss": 4.1623, "step": 31396 }, { "epoch": 0.9589798411728773, "grad_norm": 0.5350188612937927, "learning_rate": 2.07301917159225e-07, "loss": 4.1824, "step": 31397 }, { "epoch": 0.959010384850336, "grad_norm": 0.5443116426467896, "learning_rate": 2.0699374396194737e-07, "loss": 4.2578, "step": 31398 }, { "epoch": 0.9590409285277948, "grad_norm": 0.5432596206665039, "learning_rate": 2.0668579904662145e-07, "loss": 4.2741, "step": 31399 }, { "epoch": 0.9590714722052535, "grad_norm": 0.5414344072341919, "learning_rate": 2.0637808241608935e-07, "loss": 4.2687, "step": 31400 }, { "epoch": 0.9591020158827123, "grad_norm": 0.5375163555145264, "learning_rate": 2.0607059407317941e-07, "loss": 4.2942, "step": 31401 }, { "epoch": 0.9591325595601711, "grad_norm": 0.5494044423103333, "learning_rate": 2.0576333402072823e-07, "loss": 4.2504, "step": 31402 }, { "epoch": 0.9591631032376298, "grad_norm": 0.5443550944328308, "learning_rate": 2.0545630226155855e-07, "loss": 4.2908, "step": 31403 }, { "epoch": 0.9591936469150886, "grad_norm": 0.5487063527107239, "learning_rate": 2.051494987985042e-07, "loss": 4.2473, "step": 31404 }, { "epoch": 0.9592241905925474, "grad_norm": 0.5310472846031189, "learning_rate": 2.0484292363438518e-07, "loss": 4.2251, "step": 31405 }, { "epoch": 0.9592547342700061, "grad_norm": 0.5434796214103699, "learning_rate": 2.045365767720242e-07, "loss": 4.1709, "step": 31406 }, { "epoch": 0.9592852779474649, "grad_norm": 0.5475386381149292, "learning_rate": 2.042304582142468e-07, "loss": 4.2749, "step": 31407 }, { "epoch": 0.9593158216249237, "grad_norm": 0.537071704864502, "learning_rate": 2.039245679638646e-07, "loss": 4.2787, "step": 31408 }, { "epoch": 0.9593463653023824, "grad_norm": 0.5410412549972534, "learning_rate": 2.0361890602370037e-07, "loss": 4.2948, "step": 31409 }, { "epoch": 0.9593769089798412, "grad_norm": 0.5502815842628479, "learning_rate": 2.0331347239656572e-07, "loss": 4.3414, "step": 31410 }, { "epoch": 0.9594074526573, "grad_norm": 0.5468928813934326, "learning_rate": 2.0300826708527232e-07, "loss": 4.2046, "step": 31411 }, { "epoch": 0.9594379963347587, "grad_norm": 0.5437605977058411, "learning_rate": 2.027032900926318e-07, "loss": 4.2706, "step": 31412 }, { "epoch": 0.9594685400122175, "grad_norm": 0.5488194823265076, "learning_rate": 2.023985414214502e-07, "loss": 4.1548, "step": 31413 }, { "epoch": 0.9594990836896763, "grad_norm": 0.5373386740684509, "learning_rate": 2.020940210745337e-07, "loss": 4.3059, "step": 31414 }, { "epoch": 0.959529627367135, "grad_norm": 0.5392566919326782, "learning_rate": 2.0178972905469107e-07, "loss": 4.1536, "step": 31415 }, { "epoch": 0.9595601710445938, "grad_norm": 0.5447371602058411, "learning_rate": 2.0148566536471736e-07, "loss": 4.1934, "step": 31416 }, { "epoch": 0.9595907147220525, "grad_norm": 0.5388429760932922, "learning_rate": 2.0118183000741863e-07, "loss": 4.2156, "step": 31417 }, { "epoch": 0.9596212583995113, "grad_norm": 0.5444401502609253, "learning_rate": 2.0087822298558712e-07, "loss": 4.2416, "step": 31418 }, { "epoch": 0.9596518020769701, "grad_norm": 0.5349085927009583, "learning_rate": 2.0057484430202055e-07, "loss": 4.1321, "step": 31419 }, { "epoch": 0.9596823457544288, "grad_norm": 0.5384911894798279, "learning_rate": 2.0027169395951395e-07, "loss": 4.2704, "step": 31420 }, { "epoch": 0.9597128894318876, "grad_norm": 0.5257370471954346, "learning_rate": 1.9996877196085395e-07, "loss": 4.1625, "step": 31421 }, { "epoch": 0.9597434331093464, "grad_norm": 0.5467524528503418, "learning_rate": 1.9966607830883e-07, "loss": 4.3091, "step": 31422 }, { "epoch": 0.9597739767868051, "grad_norm": 0.5390830636024475, "learning_rate": 1.9936361300623708e-07, "loss": 4.1884, "step": 31423 }, { "epoch": 0.9598045204642639, "grad_norm": 0.5434642434120178, "learning_rate": 1.9906137605585073e-07, "loss": 4.3411, "step": 31424 }, { "epoch": 0.9598350641417227, "grad_norm": 0.5452819466590881, "learning_rate": 1.9875936746045764e-07, "loss": 4.1892, "step": 31425 }, { "epoch": 0.9598656078191814, "grad_norm": 0.5568991303443909, "learning_rate": 1.984575872228417e-07, "loss": 4.1888, "step": 31426 }, { "epoch": 0.9598961514966402, "grad_norm": 0.5446910262107849, "learning_rate": 1.9815603534577564e-07, "loss": 4.2542, "step": 31427 }, { "epoch": 0.959926695174099, "grad_norm": 0.5485333800315857, "learning_rate": 1.9785471183203785e-07, "loss": 4.1787, "step": 31428 }, { "epoch": 0.9599572388515577, "grad_norm": 0.5467479228973389, "learning_rate": 1.9755361668440665e-07, "loss": 4.2621, "step": 31429 }, { "epoch": 0.9599877825290165, "grad_norm": 0.547998309135437, "learning_rate": 1.9725274990564923e-07, "loss": 4.2672, "step": 31430 }, { "epoch": 0.9600183262064753, "grad_norm": 0.5448600053787231, "learning_rate": 1.969521114985412e-07, "loss": 4.1635, "step": 31431 }, { "epoch": 0.960048869883934, "grad_norm": 0.548579752445221, "learning_rate": 1.9665170146584423e-07, "loss": 4.2973, "step": 31432 }, { "epoch": 0.9600794135613928, "grad_norm": 0.5414347648620605, "learning_rate": 1.9635151981033107e-07, "loss": 4.2305, "step": 31433 }, { "epoch": 0.9601099572388515, "grad_norm": 0.5400357246398926, "learning_rate": 1.9605156653476065e-07, "loss": 4.2613, "step": 31434 }, { "epoch": 0.9601405009163103, "grad_norm": 0.5523902773857117, "learning_rate": 1.9575184164189464e-07, "loss": 4.1614, "step": 31435 }, { "epoch": 0.9601710445937691, "grad_norm": 0.5391033291816711, "learning_rate": 1.9545234513449473e-07, "loss": 4.187, "step": 31436 }, { "epoch": 0.9602015882712278, "grad_norm": 0.5361407995223999, "learning_rate": 1.951530770153226e-07, "loss": 4.2135, "step": 31437 }, { "epoch": 0.9602321319486866, "grad_norm": 0.56024169921875, "learning_rate": 1.9485403728712327e-07, "loss": 4.2084, "step": 31438 }, { "epoch": 0.9602626756261454, "grad_norm": 0.5461932420730591, "learning_rate": 1.945552259526612e-07, "loss": 4.1983, "step": 31439 }, { "epoch": 0.9602932193036041, "grad_norm": 0.5455536246299744, "learning_rate": 1.9425664301468138e-07, "loss": 4.1951, "step": 31440 }, { "epoch": 0.9603237629810629, "grad_norm": 0.5426663756370544, "learning_rate": 1.9395828847593167e-07, "loss": 4.2986, "step": 31441 }, { "epoch": 0.9603543066585217, "grad_norm": 0.5402932167053223, "learning_rate": 1.936601623391654e-07, "loss": 4.2373, "step": 31442 }, { "epoch": 0.9603848503359804, "grad_norm": 0.5292791128158569, "learning_rate": 1.933622646071248e-07, "loss": 4.1734, "step": 31443 }, { "epoch": 0.9604153940134392, "grad_norm": 0.5411161184310913, "learning_rate": 1.930645952825494e-07, "loss": 4.2107, "step": 31444 }, { "epoch": 0.960445937690898, "grad_norm": 0.5385631918907166, "learning_rate": 1.9276715436818137e-07, "loss": 4.2175, "step": 31445 }, { "epoch": 0.9604764813683567, "grad_norm": 0.5417091250419617, "learning_rate": 1.9246994186676582e-07, "loss": 4.2243, "step": 31446 }, { "epoch": 0.9605070250458155, "grad_norm": 0.5455078482627869, "learning_rate": 1.9217295778103107e-07, "loss": 4.2671, "step": 31447 }, { "epoch": 0.9605375687232743, "grad_norm": 0.5573007464408875, "learning_rate": 1.918762021137166e-07, "loss": 4.3033, "step": 31448 }, { "epoch": 0.960568112400733, "grad_norm": 0.5441323518753052, "learning_rate": 1.915796748675508e-07, "loss": 4.2576, "step": 31449 }, { "epoch": 0.9605986560781918, "grad_norm": 0.5426662564277649, "learning_rate": 1.9128337604526758e-07, "loss": 4.235, "step": 31450 }, { "epoch": 0.9606291997556505, "grad_norm": 0.5328143835067749, "learning_rate": 1.9098730564959532e-07, "loss": 4.1592, "step": 31451 }, { "epoch": 0.9606597434331093, "grad_norm": 0.542131245136261, "learning_rate": 1.9069146368325408e-07, "loss": 4.0135, "step": 31452 }, { "epoch": 0.9606902871105681, "grad_norm": 0.5388253331184387, "learning_rate": 1.9039585014897498e-07, "loss": 4.2511, "step": 31453 }, { "epoch": 0.9607208307880268, "grad_norm": 0.5463339686393738, "learning_rate": 1.901004650494781e-07, "loss": 4.2597, "step": 31454 }, { "epoch": 0.9607513744654856, "grad_norm": 0.546056866645813, "learning_rate": 1.8980530838748068e-07, "loss": 4.2676, "step": 31455 }, { "epoch": 0.9607819181429444, "grad_norm": 0.5449870824813843, "learning_rate": 1.895103801657e-07, "loss": 4.3051, "step": 31456 }, { "epoch": 0.9608124618204031, "grad_norm": 0.5484133958816528, "learning_rate": 1.892156803868589e-07, "loss": 4.237, "step": 31457 }, { "epoch": 0.960843005497862, "grad_norm": 0.5364605188369751, "learning_rate": 1.8892120905366072e-07, "loss": 4.2844, "step": 31458 }, { "epoch": 0.9608735491753208, "grad_norm": 0.5454187989234924, "learning_rate": 1.886269661688228e-07, "loss": 4.1584, "step": 31459 }, { "epoch": 0.9609040928527794, "grad_norm": 0.5431866645812988, "learning_rate": 1.8833295173505406e-07, "loss": 4.2333, "step": 31460 }, { "epoch": 0.9609346365302383, "grad_norm": 0.5374144315719604, "learning_rate": 1.8803916575506065e-07, "loss": 4.2656, "step": 31461 }, { "epoch": 0.9609651802076971, "grad_norm": 0.5392152070999146, "learning_rate": 1.8774560823154596e-07, "loss": 4.3086, "step": 31462 }, { "epoch": 0.9609957238851558, "grad_norm": 0.5407684445381165, "learning_rate": 1.874522791672162e-07, "loss": 4.1712, "step": 31463 }, { "epoch": 0.9610262675626146, "grad_norm": 0.5441737771034241, "learning_rate": 1.8715917856476917e-07, "loss": 4.2642, "step": 31464 }, { "epoch": 0.9610568112400732, "grad_norm": 0.547418475151062, "learning_rate": 1.8686630642690828e-07, "loss": 4.1813, "step": 31465 }, { "epoch": 0.961087354917532, "grad_norm": 0.5445320010185242, "learning_rate": 1.865736627563258e-07, "loss": 4.3103, "step": 31466 }, { "epoch": 0.9611178985949909, "grad_norm": 0.539280354976654, "learning_rate": 1.8628124755571407e-07, "loss": 4.2303, "step": 31467 }, { "epoch": 0.9611484422724496, "grad_norm": 0.5397601127624512, "learning_rate": 1.8598906082777369e-07, "loss": 4.2657, "step": 31468 }, { "epoch": 0.9611789859499084, "grad_norm": 0.5357274413108826, "learning_rate": 1.856971025751858e-07, "loss": 4.2784, "step": 31469 }, { "epoch": 0.9612095296273672, "grad_norm": 0.5330942273139954, "learning_rate": 1.8540537280064552e-07, "loss": 4.2078, "step": 31470 }, { "epoch": 0.9612400733048259, "grad_norm": 0.5506974458694458, "learning_rate": 1.8511387150683678e-07, "loss": 4.2413, "step": 31471 }, { "epoch": 0.9612706169822847, "grad_norm": 0.5498377680778503, "learning_rate": 1.848225986964408e-07, "loss": 4.2477, "step": 31472 }, { "epoch": 0.9613011606597435, "grad_norm": 0.5432787537574768, "learning_rate": 1.8453155437214432e-07, "loss": 4.2574, "step": 31473 }, { "epoch": 0.9613317043372022, "grad_norm": 0.5412864089012146, "learning_rate": 1.8424073853662294e-07, "loss": 4.2703, "step": 31474 }, { "epoch": 0.961362248014661, "grad_norm": 0.542540431022644, "learning_rate": 1.839501511925551e-07, "loss": 4.2086, "step": 31475 }, { "epoch": 0.9613927916921198, "grad_norm": 0.5489080548286438, "learning_rate": 1.8365979234261922e-07, "loss": 4.2323, "step": 31476 }, { "epoch": 0.9614233353695785, "grad_norm": 0.5466824769973755, "learning_rate": 1.8336966198948813e-07, "loss": 4.2483, "step": 31477 }, { "epoch": 0.9614538790470373, "grad_norm": 0.5307103395462036, "learning_rate": 1.8307976013582917e-07, "loss": 4.1608, "step": 31478 }, { "epoch": 0.9614844227244961, "grad_norm": 0.5342298150062561, "learning_rate": 1.8279008678431797e-07, "loss": 4.2126, "step": 31479 }, { "epoch": 0.9615149664019548, "grad_norm": 0.5457093715667725, "learning_rate": 1.825006419376135e-07, "loss": 4.3161, "step": 31480 }, { "epoch": 0.9615455100794136, "grad_norm": 0.535385251045227, "learning_rate": 1.8221142559839145e-07, "loss": 4.1033, "step": 31481 }, { "epoch": 0.9615760537568723, "grad_norm": 0.5417075157165527, "learning_rate": 1.8192243776930518e-07, "loss": 4.2627, "step": 31482 }, { "epoch": 0.9616065974343311, "grad_norm": 0.5346576571464539, "learning_rate": 1.8163367845301926e-07, "loss": 4.2687, "step": 31483 }, { "epoch": 0.9616371411117899, "grad_norm": 0.5378327369689941, "learning_rate": 1.8134514765219268e-07, "loss": 4.2746, "step": 31484 }, { "epoch": 0.9616676847892486, "grad_norm": 0.5303854942321777, "learning_rate": 1.8105684536948165e-07, "loss": 4.1636, "step": 31485 }, { "epoch": 0.9616982284667074, "grad_norm": 0.5449132919311523, "learning_rate": 1.8076877160753958e-07, "loss": 4.242, "step": 31486 }, { "epoch": 0.9617287721441662, "grad_norm": 0.5465012788772583, "learning_rate": 1.804809263690227e-07, "loss": 4.1475, "step": 31487 }, { "epoch": 0.9617593158216249, "grad_norm": 0.5547817349433899, "learning_rate": 1.8019330965657887e-07, "loss": 4.2138, "step": 31488 }, { "epoch": 0.9617898594990837, "grad_norm": 0.5489679574966431, "learning_rate": 1.7990592147285323e-07, "loss": 4.3305, "step": 31489 }, { "epoch": 0.9618204031765425, "grad_norm": 0.5468608736991882, "learning_rate": 1.796187618204964e-07, "loss": 4.3365, "step": 31490 }, { "epoch": 0.9618509468540012, "grad_norm": 0.5376638770103455, "learning_rate": 1.7933183070215355e-07, "loss": 4.2571, "step": 31491 }, { "epoch": 0.96188149053146, "grad_norm": 0.5495393872261047, "learning_rate": 1.7904512812046136e-07, "loss": 4.1669, "step": 31492 }, { "epoch": 0.9619120342089188, "grad_norm": 0.5406758189201355, "learning_rate": 1.7875865407806225e-07, "loss": 4.2104, "step": 31493 }, { "epoch": 0.9619425778863775, "grad_norm": 0.56678307056427, "learning_rate": 1.7847240857759572e-07, "loss": 4.2643, "step": 31494 }, { "epoch": 0.9619731215638363, "grad_norm": 0.5425278544425964, "learning_rate": 1.7818639162169303e-07, "loss": 4.2873, "step": 31495 }, { "epoch": 0.9620036652412951, "grad_norm": 0.544735312461853, "learning_rate": 1.7790060321299373e-07, "loss": 4.26, "step": 31496 }, { "epoch": 0.9620342089187538, "grad_norm": 0.5351816415786743, "learning_rate": 1.7761504335412625e-07, "loss": 4.1897, "step": 31497 }, { "epoch": 0.9620647525962126, "grad_norm": 0.5386773347854614, "learning_rate": 1.773297120477163e-07, "loss": 4.2499, "step": 31498 }, { "epoch": 0.9620952962736713, "grad_norm": 0.5453287363052368, "learning_rate": 1.770446092963951e-07, "loss": 4.2794, "step": 31499 }, { "epoch": 0.9621258399511301, "grad_norm": 0.5339376926422119, "learning_rate": 1.7675973510278832e-07, "loss": 4.2081, "step": 31500 }, { "epoch": 0.9621563836285889, "grad_norm": 0.5481802225112915, "learning_rate": 1.7647508946951608e-07, "loss": 4.1687, "step": 31501 }, { "epoch": 0.9621869273060476, "grad_norm": 0.5410556197166443, "learning_rate": 1.7619067239920128e-07, "loss": 4.1904, "step": 31502 }, { "epoch": 0.9622174709835064, "grad_norm": 0.5541787147521973, "learning_rate": 1.759064838944613e-07, "loss": 4.3087, "step": 31503 }, { "epoch": 0.9622480146609652, "grad_norm": 0.5387333631515503, "learning_rate": 1.7562252395791345e-07, "loss": 4.1738, "step": 31504 }, { "epoch": 0.9622785583384239, "grad_norm": 0.5483113527297974, "learning_rate": 1.7533879259217235e-07, "loss": 4.2204, "step": 31505 }, { "epoch": 0.9623091020158827, "grad_norm": 0.5320111513137817, "learning_rate": 1.7505528979985254e-07, "loss": 4.1867, "step": 31506 }, { "epoch": 0.9623396456933415, "grad_norm": 0.5488905310630798, "learning_rate": 1.7477201558356028e-07, "loss": 4.1441, "step": 31507 }, { "epoch": 0.9623701893708002, "grad_norm": 0.553291916847229, "learning_rate": 1.7448896994590736e-07, "loss": 4.277, "step": 31508 }, { "epoch": 0.962400733048259, "grad_norm": 0.5412018299102783, "learning_rate": 1.7420615288949726e-07, "loss": 4.1808, "step": 31509 }, { "epoch": 0.9624312767257178, "grad_norm": 0.5488579273223877, "learning_rate": 1.7392356441693624e-07, "loss": 4.2185, "step": 31510 }, { "epoch": 0.9624618204031765, "grad_norm": 0.5453528165817261, "learning_rate": 1.73641204530825e-07, "loss": 4.2925, "step": 31511 }, { "epoch": 0.9624923640806353, "grad_norm": 0.5378180742263794, "learning_rate": 1.7335907323376422e-07, "loss": 4.2168, "step": 31512 }, { "epoch": 0.9625229077580941, "grad_norm": 0.543374240398407, "learning_rate": 1.7307717052835183e-07, "loss": 4.3062, "step": 31513 }, { "epoch": 0.9625534514355528, "grad_norm": 0.539866030216217, "learning_rate": 1.7279549641718017e-07, "loss": 4.2552, "step": 31514 }, { "epoch": 0.9625839951130116, "grad_norm": 0.5339023470878601, "learning_rate": 1.7251405090284723e-07, "loss": 4.2285, "step": 31515 }, { "epoch": 0.9626145387904703, "grad_norm": 0.532845139503479, "learning_rate": 1.7223283398794255e-07, "loss": 4.2152, "step": 31516 }, { "epoch": 0.9626450824679291, "grad_norm": 0.5513556599617004, "learning_rate": 1.7195184567505296e-07, "loss": 4.308, "step": 31517 }, { "epoch": 0.9626756261453879, "grad_norm": 0.5493237376213074, "learning_rate": 1.7167108596677084e-07, "loss": 4.2131, "step": 31518 }, { "epoch": 0.9627061698228466, "grad_norm": 0.5385405421257019, "learning_rate": 1.7139055486567747e-07, "loss": 4.2228, "step": 31519 }, { "epoch": 0.9627367135003054, "grad_norm": 0.54490065574646, "learning_rate": 1.7111025237435684e-07, "loss": 4.1832, "step": 31520 }, { "epoch": 0.9627672571777642, "grad_norm": 0.5349005460739136, "learning_rate": 1.7083017849538752e-07, "loss": 4.1615, "step": 31521 }, { "epoch": 0.9627978008552229, "grad_norm": 0.5386205911636353, "learning_rate": 1.705503332313535e-07, "loss": 4.2432, "step": 31522 }, { "epoch": 0.9628283445326817, "grad_norm": 0.547208309173584, "learning_rate": 1.7027071658482774e-07, "loss": 4.0604, "step": 31523 }, { "epoch": 0.9628588882101405, "grad_norm": 0.5385310053825378, "learning_rate": 1.6999132855838596e-07, "loss": 4.2873, "step": 31524 }, { "epoch": 0.9628894318875992, "grad_norm": 0.5521124005317688, "learning_rate": 1.697121691546011e-07, "loss": 4.3074, "step": 31525 }, { "epoch": 0.962919975565058, "grad_norm": 0.5506302118301392, "learning_rate": 1.6943323837604054e-07, "loss": 4.3398, "step": 31526 }, { "epoch": 0.9629505192425168, "grad_norm": 0.5385859608650208, "learning_rate": 1.6915453622527722e-07, "loss": 4.249, "step": 31527 }, { "epoch": 0.9629810629199755, "grad_norm": 0.545444667339325, "learning_rate": 1.68876062704873e-07, "loss": 4.2688, "step": 31528 }, { "epoch": 0.9630116065974343, "grad_norm": 0.5400381088256836, "learning_rate": 1.6859781781739525e-07, "loss": 4.2328, "step": 31529 }, { "epoch": 0.9630421502748931, "grad_norm": 0.5413937568664551, "learning_rate": 1.6831980156540305e-07, "loss": 4.2451, "step": 31530 }, { "epoch": 0.9630726939523518, "grad_norm": 0.5453662872314453, "learning_rate": 1.6804201395145825e-07, "loss": 4.2891, "step": 31531 }, { "epoch": 0.9631032376298106, "grad_norm": 0.549816906452179, "learning_rate": 1.677644549781171e-07, "loss": 4.2864, "step": 31532 }, { "epoch": 0.9631337813072693, "grad_norm": 0.534960150718689, "learning_rate": 1.674871246479387e-07, "loss": 4.2427, "step": 31533 }, { "epoch": 0.9631643249847281, "grad_norm": 0.5313218832015991, "learning_rate": 1.67210022963471e-07, "loss": 4.2212, "step": 31534 }, { "epoch": 0.963194868662187, "grad_norm": 0.5397818684577942, "learning_rate": 1.6693314992727028e-07, "loss": 4.2268, "step": 31535 }, { "epoch": 0.9632254123396456, "grad_norm": 0.536622941493988, "learning_rate": 1.666565055418845e-07, "loss": 4.2082, "step": 31536 }, { "epoch": 0.9632559560171045, "grad_norm": 0.5456007122993469, "learning_rate": 1.6638008980985886e-07, "loss": 4.2723, "step": 31537 }, { "epoch": 0.9632864996945633, "grad_norm": 0.5422637462615967, "learning_rate": 1.6610390273373854e-07, "loss": 4.1966, "step": 31538 }, { "epoch": 0.963317043372022, "grad_norm": 0.5311083197593689, "learning_rate": 1.6582794431606873e-07, "loss": 4.1899, "step": 31539 }, { "epoch": 0.9633475870494808, "grad_norm": 0.5407480597496033, "learning_rate": 1.6555221455939184e-07, "loss": 4.2412, "step": 31540 }, { "epoch": 0.9633781307269396, "grad_norm": 0.5449026823043823, "learning_rate": 1.6527671346624195e-07, "loss": 4.2696, "step": 31541 }, { "epoch": 0.9634086744043983, "grad_norm": 0.5444325804710388, "learning_rate": 1.650014410391587e-07, "loss": 4.1075, "step": 31542 }, { "epoch": 0.9634392180818571, "grad_norm": 0.5393434762954712, "learning_rate": 1.6472639728067617e-07, "loss": 4.2023, "step": 31543 }, { "epoch": 0.9634697617593159, "grad_norm": 0.5362578630447388, "learning_rate": 1.6445158219332846e-07, "loss": 4.1598, "step": 31544 }, { "epoch": 0.9635003054367746, "grad_norm": 0.5341852903366089, "learning_rate": 1.641769957796413e-07, "loss": 4.2935, "step": 31545 }, { "epoch": 0.9635308491142334, "grad_norm": 0.5570939183235168, "learning_rate": 1.6390263804214878e-07, "loss": 4.3685, "step": 31546 }, { "epoch": 0.9635613927916922, "grad_norm": 0.5474662184715271, "learning_rate": 1.636285089833711e-07, "loss": 4.2727, "step": 31547 }, { "epoch": 0.9635919364691509, "grad_norm": 0.5382285714149475, "learning_rate": 1.6335460860583685e-07, "loss": 4.2123, "step": 31548 }, { "epoch": 0.9636224801466097, "grad_norm": 0.5384281277656555, "learning_rate": 1.6308093691206616e-07, "loss": 4.2025, "step": 31549 }, { "epoch": 0.9636530238240684, "grad_norm": 0.5384284853935242, "learning_rate": 1.6280749390457928e-07, "loss": 4.1635, "step": 31550 }, { "epoch": 0.9636835675015272, "grad_norm": 0.541307806968689, "learning_rate": 1.6253427958589361e-07, "loss": 4.1621, "step": 31551 }, { "epoch": 0.963714111178986, "grad_norm": 0.5490143895149231, "learning_rate": 1.6226129395852385e-07, "loss": 4.2975, "step": 31552 }, { "epoch": 0.9637446548564447, "grad_norm": 0.5395698547363281, "learning_rate": 1.619885370249874e-07, "loss": 4.325, "step": 31553 }, { "epoch": 0.9637751985339035, "grad_norm": 0.5344930291175842, "learning_rate": 1.6171600878779058e-07, "loss": 4.2628, "step": 31554 }, { "epoch": 0.9638057422113623, "grad_norm": 0.5463530421257019, "learning_rate": 1.6144370924944808e-07, "loss": 4.2568, "step": 31555 }, { "epoch": 0.963836285888821, "grad_norm": 0.5424749255180359, "learning_rate": 1.6117163841246062e-07, "loss": 4.2517, "step": 31556 }, { "epoch": 0.9638668295662798, "grad_norm": 0.5389271974563599, "learning_rate": 1.6089979627933738e-07, "loss": 4.2465, "step": 31557 }, { "epoch": 0.9638973732437386, "grad_norm": 0.5455057621002197, "learning_rate": 1.6062818285258464e-07, "loss": 4.2785, "step": 31558 }, { "epoch": 0.9639279169211973, "grad_norm": 0.5533576011657715, "learning_rate": 1.6035679813469483e-07, "loss": 4.3252, "step": 31559 }, { "epoch": 0.9639584605986561, "grad_norm": 0.5458120107650757, "learning_rate": 1.6008564212817434e-07, "loss": 4.2032, "step": 31560 }, { "epoch": 0.9639890042761149, "grad_norm": 0.5405052304267883, "learning_rate": 1.598147148355128e-07, "loss": 4.2231, "step": 31561 }, { "epoch": 0.9640195479535736, "grad_norm": 0.5563735961914062, "learning_rate": 1.59544016259211e-07, "loss": 4.1527, "step": 31562 }, { "epoch": 0.9640500916310324, "grad_norm": 0.5382112264633179, "learning_rate": 1.5927354640175863e-07, "loss": 4.1642, "step": 31563 }, { "epoch": 0.9640806353084912, "grad_norm": 0.5431631207466125, "learning_rate": 1.590033052656481e-07, "loss": 4.3081, "step": 31564 }, { "epoch": 0.9641111789859499, "grad_norm": 0.5456756353378296, "learning_rate": 1.5873329285336637e-07, "loss": 4.2736, "step": 31565 }, { "epoch": 0.9641417226634087, "grad_norm": 0.539749264717102, "learning_rate": 1.584635091673975e-07, "loss": 4.2385, "step": 31566 }, { "epoch": 0.9641722663408674, "grad_norm": 0.5430951118469238, "learning_rate": 1.5819395421022843e-07, "loss": 4.2073, "step": 31567 }, { "epoch": 0.9642028100183262, "grad_norm": 0.5370920896530151, "learning_rate": 1.579246279843377e-07, "loss": 4.249, "step": 31568 }, { "epoch": 0.964233353695785, "grad_norm": 0.5357581377029419, "learning_rate": 1.576555304922095e-07, "loss": 4.244, "step": 31569 }, { "epoch": 0.9642638973732437, "grad_norm": 0.546323835849762, "learning_rate": 1.5738666173631954e-07, "loss": 4.2931, "step": 31570 }, { "epoch": 0.9642944410507025, "grad_norm": 0.541195273399353, "learning_rate": 1.571180217191437e-07, "loss": 4.207, "step": 31571 }, { "epoch": 0.9643249847281613, "grad_norm": 0.5519038438796997, "learning_rate": 1.5684961044315217e-07, "loss": 4.1028, "step": 31572 }, { "epoch": 0.96435552840562, "grad_norm": 0.5385211110115051, "learning_rate": 1.5658142791082353e-07, "loss": 4.324, "step": 31573 }, { "epoch": 0.9643860720830788, "grad_norm": 0.5422922968864441, "learning_rate": 1.5631347412461973e-07, "loss": 4.2776, "step": 31574 }, { "epoch": 0.9644166157605376, "grad_norm": 0.5342966914176941, "learning_rate": 1.5604574908701375e-07, "loss": 4.2436, "step": 31575 }, { "epoch": 0.9644471594379963, "grad_norm": 0.5384919047355652, "learning_rate": 1.5577825280046754e-07, "loss": 4.2313, "step": 31576 }, { "epoch": 0.9644777031154551, "grad_norm": 0.5331222414970398, "learning_rate": 1.55510985267443e-07, "loss": 4.2366, "step": 31577 }, { "epoch": 0.9645082467929139, "grad_norm": 0.5565207004547119, "learning_rate": 1.5524394649040487e-07, "loss": 4.2588, "step": 31578 }, { "epoch": 0.9645387904703726, "grad_norm": 0.5487965941429138, "learning_rate": 1.5497713647180668e-07, "loss": 4.3345, "step": 31579 }, { "epoch": 0.9645693341478314, "grad_norm": 0.5985954403877258, "learning_rate": 1.5471055521411038e-07, "loss": 4.2913, "step": 31580 }, { "epoch": 0.9645998778252902, "grad_norm": 0.5436145663261414, "learning_rate": 1.5444420271976677e-07, "loss": 4.2789, "step": 31581 }, { "epoch": 0.9646304215027489, "grad_norm": 0.541452169418335, "learning_rate": 1.5417807899123227e-07, "loss": 4.2747, "step": 31582 }, { "epoch": 0.9646609651802077, "grad_norm": 0.5433874130249023, "learning_rate": 1.5391218403095208e-07, "loss": 4.2114, "step": 31583 }, { "epoch": 0.9646915088576664, "grad_norm": 0.5448042154312134, "learning_rate": 1.5364651784137706e-07, "loss": 4.3232, "step": 31584 }, { "epoch": 0.9647220525351252, "grad_norm": 0.5454953908920288, "learning_rate": 1.5338108042495525e-07, "loss": 4.1529, "step": 31585 }, { "epoch": 0.964752596212584, "grad_norm": 0.5457218289375305, "learning_rate": 1.5311587178412634e-07, "loss": 4.2523, "step": 31586 }, { "epoch": 0.9647831398900427, "grad_norm": 0.5401110053062439, "learning_rate": 1.528508919213356e-07, "loss": 4.2596, "step": 31587 }, { "epoch": 0.9648136835675015, "grad_norm": 0.5381261110305786, "learning_rate": 1.5258614083902e-07, "loss": 4.2377, "step": 31588 }, { "epoch": 0.9648442272449603, "grad_norm": 0.540769636631012, "learning_rate": 1.52321618539622e-07, "loss": 4.1614, "step": 31589 }, { "epoch": 0.964874770922419, "grad_norm": 0.5392007827758789, "learning_rate": 1.5205732502557302e-07, "loss": 4.2718, "step": 31590 }, { "epoch": 0.9649053145998778, "grad_norm": 0.5520443320274353, "learning_rate": 1.5179326029930995e-07, "loss": 4.2264, "step": 31591 }, { "epoch": 0.9649358582773366, "grad_norm": 0.539236307144165, "learning_rate": 1.5152942436325866e-07, "loss": 4.3027, "step": 31592 }, { "epoch": 0.9649664019547953, "grad_norm": 0.5401033759117126, "learning_rate": 1.5126581721985333e-07, "loss": 4.2446, "step": 31593 }, { "epoch": 0.9649969456322541, "grad_norm": 0.5517289638519287, "learning_rate": 1.5100243887151976e-07, "loss": 4.2863, "step": 31594 }, { "epoch": 0.9650274893097129, "grad_norm": 0.5443615913391113, "learning_rate": 1.5073928932068104e-07, "loss": 4.3052, "step": 31595 }, { "epoch": 0.9650580329871716, "grad_norm": 0.5474039316177368, "learning_rate": 1.5047636856976578e-07, "loss": 4.2128, "step": 31596 }, { "epoch": 0.9650885766646304, "grad_norm": 0.5456700325012207, "learning_rate": 1.5021367662118592e-07, "loss": 4.1825, "step": 31597 }, { "epoch": 0.9651191203420892, "grad_norm": 0.5372307300567627, "learning_rate": 1.499512134773673e-07, "loss": 4.3147, "step": 31598 }, { "epoch": 0.9651496640195479, "grad_norm": 0.5442238450050354, "learning_rate": 1.4968897914072744e-07, "loss": 4.1687, "step": 31599 }, { "epoch": 0.9651802076970067, "grad_norm": 0.5424662828445435, "learning_rate": 1.4942697361367274e-07, "loss": 4.2889, "step": 31600 }, { "epoch": 0.9652107513744654, "grad_norm": 0.5482172966003418, "learning_rate": 1.491651968986263e-07, "loss": 4.3649, "step": 31601 }, { "epoch": 0.9652412950519242, "grad_norm": 0.5435373783111572, "learning_rate": 1.4890364899798892e-07, "loss": 4.1606, "step": 31602 }, { "epoch": 0.965271838729383, "grad_norm": 0.5429417490959167, "learning_rate": 1.486423299141726e-07, "loss": 4.2688, "step": 31603 }, { "epoch": 0.9653023824068417, "grad_norm": 0.55321204662323, "learning_rate": 1.483812396495865e-07, "loss": 4.2496, "step": 31604 }, { "epoch": 0.9653329260843005, "grad_norm": 0.5542105436325073, "learning_rate": 1.481203782066287e-07, "loss": 4.2858, "step": 31605 }, { "epoch": 0.9653634697617594, "grad_norm": 0.5457796454429626, "learning_rate": 1.4785974558770844e-07, "loss": 4.3085, "step": 31606 }, { "epoch": 0.965394013439218, "grad_norm": 0.5421690940856934, "learning_rate": 1.4759934179521816e-07, "loss": 4.2739, "step": 31607 }, { "epoch": 0.9654245571166769, "grad_norm": 0.5502095222473145, "learning_rate": 1.473391668315588e-07, "loss": 4.1969, "step": 31608 }, { "epoch": 0.9654551007941357, "grad_norm": 0.5446838736534119, "learning_rate": 1.470792206991256e-07, "loss": 4.2093, "step": 31609 }, { "epoch": 0.9654856444715944, "grad_norm": 0.5534235835075378, "learning_rate": 1.4681950340031392e-07, "loss": 4.2559, "step": 31610 }, { "epoch": 0.9655161881490532, "grad_norm": 0.5472370386123657, "learning_rate": 1.465600149375107e-07, "loss": 4.231, "step": 31611 }, { "epoch": 0.965546731826512, "grad_norm": 0.5366801023483276, "learning_rate": 1.463007553131085e-07, "loss": 4.1713, "step": 31612 }, { "epoch": 0.9655772755039707, "grad_norm": 0.5430813431739807, "learning_rate": 1.4604172452949428e-07, "loss": 4.2611, "step": 31613 }, { "epoch": 0.9656078191814295, "grad_norm": 0.5530029535293579, "learning_rate": 1.4578292258905224e-07, "loss": 4.238, "step": 31614 }, { "epoch": 0.9656383628588882, "grad_norm": 0.5396674275398254, "learning_rate": 1.4552434949416661e-07, "loss": 4.2267, "step": 31615 }, { "epoch": 0.965668906536347, "grad_norm": 0.5350387096405029, "learning_rate": 1.45266005247216e-07, "loss": 4.2663, "step": 31616 }, { "epoch": 0.9656994502138058, "grad_norm": 0.5383177399635315, "learning_rate": 1.4500788985057912e-07, "loss": 4.1511, "step": 31617 }, { "epoch": 0.9657299938912645, "grad_norm": 0.5405554175376892, "learning_rate": 1.4475000330663734e-07, "loss": 4.2719, "step": 31618 }, { "epoch": 0.9657605375687233, "grad_norm": 0.5512341260910034, "learning_rate": 1.4449234561775826e-07, "loss": 4.27, "step": 31619 }, { "epoch": 0.9657910812461821, "grad_norm": 0.543938934803009, "learning_rate": 1.4423491678631774e-07, "loss": 4.2643, "step": 31620 }, { "epoch": 0.9658216249236408, "grad_norm": 0.5383390784263611, "learning_rate": 1.4397771681468886e-07, "loss": 4.2189, "step": 31621 }, { "epoch": 0.9658521686010996, "grad_norm": 0.542401134967804, "learning_rate": 1.4372074570523642e-07, "loss": 4.1892, "step": 31622 }, { "epoch": 0.9658827122785584, "grad_norm": 0.5425679683685303, "learning_rate": 1.4346400346032517e-07, "loss": 4.1818, "step": 31623 }, { "epoch": 0.9659132559560171, "grad_norm": 0.5356294512748718, "learning_rate": 1.4320749008231993e-07, "loss": 4.1692, "step": 31624 }, { "epoch": 0.9659437996334759, "grad_norm": 0.5338842868804932, "learning_rate": 1.4295120557358543e-07, "loss": 4.2319, "step": 31625 }, { "epoch": 0.9659743433109347, "grad_norm": 0.5424193739891052, "learning_rate": 1.4269514993647815e-07, "loss": 4.2991, "step": 31626 }, { "epoch": 0.9660048869883934, "grad_norm": 0.5356938242912292, "learning_rate": 1.4243932317335729e-07, "loss": 4.2428, "step": 31627 }, { "epoch": 0.9660354306658522, "grad_norm": 0.5469694137573242, "learning_rate": 1.421837252865793e-07, "loss": 4.2839, "step": 31628 }, { "epoch": 0.966065974343311, "grad_norm": 0.5557963252067566, "learning_rate": 1.419283562784951e-07, "loss": 4.2048, "step": 31629 }, { "epoch": 0.9660965180207697, "grad_norm": 0.5381077527999878, "learning_rate": 1.4167321615145835e-07, "loss": 4.1621, "step": 31630 }, { "epoch": 0.9661270616982285, "grad_norm": 0.5351373553276062, "learning_rate": 1.4141830490781438e-07, "loss": 4.2527, "step": 31631 }, { "epoch": 0.9661576053756872, "grad_norm": 0.5462647676467896, "learning_rate": 1.4116362254991688e-07, "loss": 4.195, "step": 31632 }, { "epoch": 0.966188149053146, "grad_norm": 0.5472984910011292, "learning_rate": 1.4090916908010289e-07, "loss": 4.2719, "step": 31633 }, { "epoch": 0.9662186927306048, "grad_norm": 0.5486299395561218, "learning_rate": 1.4065494450072326e-07, "loss": 4.3164, "step": 31634 }, { "epoch": 0.9662492364080635, "grad_norm": 0.536867082118988, "learning_rate": 1.4040094881411226e-07, "loss": 4.2402, "step": 31635 }, { "epoch": 0.9662797800855223, "grad_norm": 0.5473704934120178, "learning_rate": 1.4014718202261246e-07, "loss": 4.1518, "step": 31636 }, { "epoch": 0.9663103237629811, "grad_norm": 0.5411453247070312, "learning_rate": 1.3989364412856086e-07, "loss": 4.2808, "step": 31637 }, { "epoch": 0.9663408674404398, "grad_norm": 0.5341193079948425, "learning_rate": 1.3964033513428897e-07, "loss": 4.187, "step": 31638 }, { "epoch": 0.9663714111178986, "grad_norm": 0.5489588379859924, "learning_rate": 1.3938725504213102e-07, "loss": 4.2244, "step": 31639 }, { "epoch": 0.9664019547953574, "grad_norm": 0.5400782227516174, "learning_rate": 1.3913440385441567e-07, "loss": 4.2566, "step": 31640 }, { "epoch": 0.9664324984728161, "grad_norm": 0.549676239490509, "learning_rate": 1.3888178157347165e-07, "loss": 4.2331, "step": 31641 }, { "epoch": 0.9664630421502749, "grad_norm": 0.5412217378616333, "learning_rate": 1.3862938820162486e-07, "loss": 4.2329, "step": 31642 }, { "epoch": 0.9664935858277337, "grad_norm": 0.5523335933685303, "learning_rate": 1.3837722374120122e-07, "loss": 4.3269, "step": 31643 }, { "epoch": 0.9665241295051924, "grad_norm": 0.5609344244003296, "learning_rate": 1.3812528819452108e-07, "loss": 4.1725, "step": 31644 }, { "epoch": 0.9665546731826512, "grad_norm": 0.5519314408302307, "learning_rate": 1.3787358156390207e-07, "loss": 4.1686, "step": 31645 }, { "epoch": 0.96658521686011, "grad_norm": 0.5471329689025879, "learning_rate": 1.376221038516673e-07, "loss": 4.259, "step": 31646 }, { "epoch": 0.9666157605375687, "grad_norm": 0.5439388155937195, "learning_rate": 1.3737085506012605e-07, "loss": 4.2041, "step": 31647 }, { "epoch": 0.9666463042150275, "grad_norm": 0.5521594882011414, "learning_rate": 1.3711983519159587e-07, "loss": 4.2274, "step": 31648 }, { "epoch": 0.9666768478924862, "grad_norm": 0.5324216485023499, "learning_rate": 1.368690442483861e-07, "loss": 4.2067, "step": 31649 }, { "epoch": 0.966707391569945, "grad_norm": 0.5296671986579895, "learning_rate": 1.3661848223280593e-07, "loss": 4.0344, "step": 31650 }, { "epoch": 0.9667379352474038, "grad_norm": 0.552221953868866, "learning_rate": 1.3636814914716467e-07, "loss": 4.2446, "step": 31651 }, { "epoch": 0.9667684789248625, "grad_norm": 0.5431516170501709, "learning_rate": 1.3611804499376325e-07, "loss": 4.2328, "step": 31652 }, { "epoch": 0.9667990226023213, "grad_norm": 0.555662214756012, "learning_rate": 1.3586816977490813e-07, "loss": 4.2034, "step": 31653 }, { "epoch": 0.9668295662797801, "grad_norm": 0.5478335022926331, "learning_rate": 1.356185234928975e-07, "loss": 4.1831, "step": 31654 }, { "epoch": 0.9668601099572388, "grad_norm": 0.5376634001731873, "learning_rate": 1.3536910615003229e-07, "loss": 4.2751, "step": 31655 }, { "epoch": 0.9668906536346976, "grad_norm": 0.5451435446739197, "learning_rate": 1.3511991774860788e-07, "loss": 4.3375, "step": 31656 }, { "epoch": 0.9669211973121564, "grad_norm": 0.5511873960494995, "learning_rate": 1.348709582909169e-07, "loss": 4.309, "step": 31657 }, { "epoch": 0.9669517409896151, "grad_norm": 0.5586621165275574, "learning_rate": 1.346222277792547e-07, "loss": 4.2305, "step": 31658 }, { "epoch": 0.9669822846670739, "grad_norm": 0.554360568523407, "learning_rate": 1.3437372621591115e-07, "loss": 4.3153, "step": 31659 }, { "epoch": 0.9670128283445327, "grad_norm": 0.5364485383033752, "learning_rate": 1.3412545360317051e-07, "loss": 4.1574, "step": 31660 }, { "epoch": 0.9670433720219914, "grad_norm": 0.5371171236038208, "learning_rate": 1.3387740994332543e-07, "loss": 4.151, "step": 31661 }, { "epoch": 0.9670739156994502, "grad_norm": 0.5402591824531555, "learning_rate": 1.3362959523865182e-07, "loss": 4.2028, "step": 31662 }, { "epoch": 0.967104459376909, "grad_norm": 0.546785831451416, "learning_rate": 1.3338200949143677e-07, "loss": 4.2823, "step": 31663 }, { "epoch": 0.9671350030543677, "grad_norm": 0.547426164150238, "learning_rate": 1.3313465270396174e-07, "loss": 4.2137, "step": 31664 }, { "epoch": 0.9671655467318265, "grad_norm": 0.5378833413124084, "learning_rate": 1.3288752487849722e-07, "loss": 4.2045, "step": 31665 }, { "epoch": 0.9671960904092852, "grad_norm": 0.5403113961219788, "learning_rate": 1.3264062601732463e-07, "loss": 4.3108, "step": 31666 }, { "epoch": 0.967226634086744, "grad_norm": 0.5475873351097107, "learning_rate": 1.3239395612271722e-07, "loss": 4.1976, "step": 31667 }, { "epoch": 0.9672571777642028, "grad_norm": 0.5461804866790771, "learning_rate": 1.3214751519694259e-07, "loss": 4.3074, "step": 31668 }, { "epoch": 0.9672877214416615, "grad_norm": 0.5452144742012024, "learning_rate": 1.3190130324226834e-07, "loss": 4.1397, "step": 31669 }, { "epoch": 0.9673182651191203, "grad_norm": 0.5407319068908691, "learning_rate": 1.316553202609705e-07, "loss": 4.2754, "step": 31670 }, { "epoch": 0.9673488087965791, "grad_norm": 0.5443270802497864, "learning_rate": 1.3140956625530277e-07, "loss": 4.1894, "step": 31671 }, { "epoch": 0.9673793524740378, "grad_norm": 0.5331618189811707, "learning_rate": 1.3116404122753834e-07, "loss": 4.2003, "step": 31672 }, { "epoch": 0.9674098961514966, "grad_norm": 0.5436285138130188, "learning_rate": 1.309187451799282e-07, "loss": 4.2825, "step": 31673 }, { "epoch": 0.9674404398289554, "grad_norm": 0.5479286313056946, "learning_rate": 1.306736781147372e-07, "loss": 4.313, "step": 31674 }, { "epoch": 0.9674709835064141, "grad_norm": 0.5535497069358826, "learning_rate": 1.3042884003422184e-07, "loss": 4.0231, "step": 31675 }, { "epoch": 0.967501527183873, "grad_norm": 0.5321487784385681, "learning_rate": 1.3018423094063314e-07, "loss": 4.3, "step": 31676 }, { "epoch": 0.9675320708613317, "grad_norm": 0.5280725359916687, "learning_rate": 1.2993985083622483e-07, "loss": 4.0784, "step": 31677 }, { "epoch": 0.9675626145387904, "grad_norm": 0.5378438830375671, "learning_rate": 1.2969569972324792e-07, "loss": 4.2208, "step": 31678 }, { "epoch": 0.9675931582162492, "grad_norm": 0.5578454732894897, "learning_rate": 1.2945177760395056e-07, "loss": 4.2674, "step": 31679 }, { "epoch": 0.967623701893708, "grad_norm": 0.5368794798851013, "learning_rate": 1.292080844805754e-07, "loss": 4.2017, "step": 31680 }, { "epoch": 0.9676542455711667, "grad_norm": 0.5430641174316406, "learning_rate": 1.2896462035537348e-07, "loss": 4.2751, "step": 31681 }, { "epoch": 0.9676847892486256, "grad_norm": 0.5465752482414246, "learning_rate": 1.2872138523057632e-07, "loss": 4.3348, "step": 31682 }, { "epoch": 0.9677153329260842, "grad_norm": 0.5419654250144958, "learning_rate": 1.2847837910843207e-07, "loss": 4.1257, "step": 31683 }, { "epoch": 0.967745876603543, "grad_norm": 0.5562393665313721, "learning_rate": 1.2823560199117513e-07, "loss": 4.1982, "step": 31684 }, { "epoch": 0.9677764202810019, "grad_norm": 0.5416777729988098, "learning_rate": 1.2799305388103977e-07, "loss": 4.2715, "step": 31685 }, { "epoch": 0.9678069639584606, "grad_norm": 0.5441668033599854, "learning_rate": 1.2775073478026034e-07, "loss": 4.222, "step": 31686 }, { "epoch": 0.9678375076359194, "grad_norm": 0.5485057830810547, "learning_rate": 1.2750864469106839e-07, "loss": 4.2182, "step": 31687 }, { "epoch": 0.9678680513133782, "grad_norm": 0.550769567489624, "learning_rate": 1.2726678361568988e-07, "loss": 4.2217, "step": 31688 }, { "epoch": 0.9678985949908369, "grad_norm": 0.539770245552063, "learning_rate": 1.270251515563592e-07, "loss": 4.2691, "step": 31689 }, { "epoch": 0.9679291386682957, "grad_norm": 0.5405187010765076, "learning_rate": 1.267837485152912e-07, "loss": 4.2035, "step": 31690 }, { "epoch": 0.9679596823457545, "grad_norm": 0.5397090911865234, "learning_rate": 1.2654257449471741e-07, "loss": 4.2408, "step": 31691 }, { "epoch": 0.9679902260232132, "grad_norm": 0.5331079363822937, "learning_rate": 1.2630162949685276e-07, "loss": 4.2462, "step": 31692 }, { "epoch": 0.968020769700672, "grad_norm": 0.5340840816497803, "learning_rate": 1.2606091352392046e-07, "loss": 4.2624, "step": 31693 }, { "epoch": 0.9680513133781308, "grad_norm": 0.5327959656715393, "learning_rate": 1.2582042657812988e-07, "loss": 4.1677, "step": 31694 }, { "epoch": 0.9680818570555895, "grad_norm": 0.5363376140594482, "learning_rate": 1.255801686617042e-07, "loss": 4.2917, "step": 31695 }, { "epoch": 0.9681124007330483, "grad_norm": 0.5408561825752258, "learning_rate": 1.2534013977685e-07, "loss": 4.2414, "step": 31696 }, { "epoch": 0.9681429444105071, "grad_norm": 0.5429800748825073, "learning_rate": 1.2510033992577664e-07, "loss": 4.2134, "step": 31697 }, { "epoch": 0.9681734880879658, "grad_norm": 0.5452497601509094, "learning_rate": 1.2486076911069345e-07, "loss": 4.2665, "step": 31698 }, { "epoch": 0.9682040317654246, "grad_norm": 0.5356080532073975, "learning_rate": 1.2462142733380978e-07, "loss": 4.1998, "step": 31699 }, { "epoch": 0.9682345754428833, "grad_norm": 0.5340761542320251, "learning_rate": 1.2438231459732386e-07, "loss": 4.1088, "step": 31700 }, { "epoch": 0.9682651191203421, "grad_norm": 0.551501989364624, "learning_rate": 1.2414343090344227e-07, "loss": 4.1783, "step": 31701 }, { "epoch": 0.9682956627978009, "grad_norm": 0.548274576663971, "learning_rate": 1.2390477625436048e-07, "loss": 4.1977, "step": 31702 }, { "epoch": 0.9683262064752596, "grad_norm": 0.5379554033279419, "learning_rate": 1.2366635065227672e-07, "loss": 4.2312, "step": 31703 }, { "epoch": 0.9683567501527184, "grad_norm": 0.5627069473266602, "learning_rate": 1.2342815409938647e-07, "loss": 4.2677, "step": 31704 }, { "epoch": 0.9683872938301772, "grad_norm": 0.5444843769073486, "learning_rate": 1.2319018659788516e-07, "loss": 4.2934, "step": 31705 }, { "epoch": 0.9684178375076359, "grad_norm": 0.5384700298309326, "learning_rate": 1.2295244814996e-07, "loss": 4.1972, "step": 31706 }, { "epoch": 0.9684483811850947, "grad_norm": 0.5435585379600525, "learning_rate": 1.227149387578036e-07, "loss": 4.1761, "step": 31707 }, { "epoch": 0.9684789248625535, "grad_norm": 0.5388786792755127, "learning_rate": 1.2247765842360038e-07, "loss": 4.2619, "step": 31708 }, { "epoch": 0.9685094685400122, "grad_norm": 0.5665441155433655, "learning_rate": 1.2224060714954022e-07, "loss": 4.307, "step": 31709 }, { "epoch": 0.968540012217471, "grad_norm": 0.5390577912330627, "learning_rate": 1.2200378493779641e-07, "loss": 4.152, "step": 31710 }, { "epoch": 0.9685705558949298, "grad_norm": 0.5345250964164734, "learning_rate": 1.2176719179055606e-07, "loss": 4.2507, "step": 31711 }, { "epoch": 0.9686010995723885, "grad_norm": 0.5428541302680969, "learning_rate": 1.21530827709998e-07, "loss": 4.258, "step": 31712 }, { "epoch": 0.9686316432498473, "grad_norm": 0.5453068017959595, "learning_rate": 1.2129469269829552e-07, "loss": 4.3186, "step": 31713 }, { "epoch": 0.9686621869273061, "grad_norm": 0.5379244089126587, "learning_rate": 1.210587867576274e-07, "loss": 4.2595, "step": 31714 }, { "epoch": 0.9686927306047648, "grad_norm": 0.5455182790756226, "learning_rate": 1.2082310989015854e-07, "loss": 4.2281, "step": 31715 }, { "epoch": 0.9687232742822236, "grad_norm": 0.538497269153595, "learning_rate": 1.2058766209806504e-07, "loss": 4.2812, "step": 31716 }, { "epoch": 0.9687538179596823, "grad_norm": 0.550862729549408, "learning_rate": 1.203524433835118e-07, "loss": 4.2022, "step": 31717 }, { "epoch": 0.9687843616371411, "grad_norm": 0.5411646962165833, "learning_rate": 1.201174537486638e-07, "loss": 4.2093, "step": 31718 }, { "epoch": 0.9688149053145999, "grad_norm": 0.5378401279449463, "learning_rate": 1.1988269319568869e-07, "loss": 4.217, "step": 31719 }, { "epoch": 0.9688454489920586, "grad_norm": 0.5424426198005676, "learning_rate": 1.1964816172674587e-07, "loss": 4.3204, "step": 31720 }, { "epoch": 0.9688759926695174, "grad_norm": 0.5520089864730835, "learning_rate": 1.1941385934399475e-07, "loss": 4.2559, "step": 31721 }, { "epoch": 0.9689065363469762, "grad_norm": 0.5406882166862488, "learning_rate": 1.1917978604958912e-07, "loss": 4.2287, "step": 31722 }, { "epoch": 0.9689370800244349, "grad_norm": 0.5421537160873413, "learning_rate": 1.1894594184569119e-07, "loss": 4.1846, "step": 31723 }, { "epoch": 0.9689676237018937, "grad_norm": 0.5448704361915588, "learning_rate": 1.1871232673444921e-07, "loss": 4.1753, "step": 31724 }, { "epoch": 0.9689981673793525, "grad_norm": 0.5470408797264099, "learning_rate": 1.1847894071801424e-07, "loss": 4.304, "step": 31725 }, { "epoch": 0.9690287110568112, "grad_norm": 0.5443937182426453, "learning_rate": 1.1824578379854012e-07, "loss": 4.1091, "step": 31726 }, { "epoch": 0.96905925473427, "grad_norm": 0.5401765704154968, "learning_rate": 1.180128559781668e-07, "loss": 4.2592, "step": 31727 }, { "epoch": 0.9690897984117288, "grad_norm": 0.546089231967926, "learning_rate": 1.1778015725904257e-07, "loss": 4.2204, "step": 31728 }, { "epoch": 0.9691203420891875, "grad_norm": 0.5395445227622986, "learning_rate": 1.1754768764331293e-07, "loss": 4.3086, "step": 31729 }, { "epoch": 0.9691508857666463, "grad_norm": 0.5471151471138, "learning_rate": 1.1731544713311227e-07, "loss": 4.2702, "step": 31730 }, { "epoch": 0.9691814294441051, "grad_norm": 0.5448738932609558, "learning_rate": 1.1708343573058056e-07, "loss": 4.2558, "step": 31731 }, { "epoch": 0.9692119731215638, "grad_norm": 0.5375982522964478, "learning_rate": 1.1685165343785775e-07, "loss": 4.2828, "step": 31732 }, { "epoch": 0.9692425167990226, "grad_norm": 0.5333684086799622, "learning_rate": 1.1662010025707271e-07, "loss": 4.2649, "step": 31733 }, { "epoch": 0.9692730604764813, "grad_norm": 0.5462832450866699, "learning_rate": 1.1638877619036259e-07, "loss": 4.262, "step": 31734 }, { "epoch": 0.9693036041539401, "grad_norm": 0.5437778830528259, "learning_rate": 1.161576812398535e-07, "loss": 4.1998, "step": 31735 }, { "epoch": 0.9693341478313989, "grad_norm": 0.5571187734603882, "learning_rate": 1.1592681540767425e-07, "loss": 4.2814, "step": 31736 }, { "epoch": 0.9693646915088576, "grad_norm": 0.5408465266227722, "learning_rate": 1.1569617869595373e-07, "loss": 4.2776, "step": 31737 }, { "epoch": 0.9693952351863164, "grad_norm": 0.5407027006149292, "learning_rate": 1.1546577110680968e-07, "loss": 4.2125, "step": 31738 }, { "epoch": 0.9694257788637752, "grad_norm": 0.5396227836608887, "learning_rate": 1.1523559264236816e-07, "loss": 4.2102, "step": 31739 }, { "epoch": 0.9694563225412339, "grad_norm": 0.5469169616699219, "learning_rate": 1.1500564330474695e-07, "loss": 4.2461, "step": 31740 }, { "epoch": 0.9694868662186927, "grad_norm": 0.5376390814781189, "learning_rate": 1.14775923096061e-07, "loss": 4.2562, "step": 31741 }, { "epoch": 0.9695174098961515, "grad_norm": 0.5352964997291565, "learning_rate": 1.1454643201843085e-07, "loss": 4.1849, "step": 31742 }, { "epoch": 0.9695479535736102, "grad_norm": 0.5462413430213928, "learning_rate": 1.1431717007396592e-07, "loss": 4.2724, "step": 31743 }, { "epoch": 0.969578497251069, "grad_norm": 0.5465602874755859, "learning_rate": 1.1408813726477563e-07, "loss": 4.223, "step": 31744 }, { "epoch": 0.9696090409285278, "grad_norm": 0.5494479537010193, "learning_rate": 1.1385933359297496e-07, "loss": 4.2071, "step": 31745 }, { "epoch": 0.9696395846059865, "grad_norm": 0.5432590246200562, "learning_rate": 1.1363075906066223e-07, "loss": 4.233, "step": 31746 }, { "epoch": 0.9696701282834453, "grad_norm": 0.5439760684967041, "learning_rate": 1.1340241366994963e-07, "loss": 4.1617, "step": 31747 }, { "epoch": 0.9697006719609041, "grad_norm": 0.53471440076828, "learning_rate": 1.131742974229355e-07, "loss": 4.2064, "step": 31748 }, { "epoch": 0.9697312156383628, "grad_norm": 0.5378453135490417, "learning_rate": 1.1294641032172093e-07, "loss": 4.2821, "step": 31749 }, { "epoch": 0.9697617593158216, "grad_norm": 0.5393425822257996, "learning_rate": 1.1271875236840424e-07, "loss": 4.2406, "step": 31750 }, { "epoch": 0.9697923029932803, "grad_norm": 0.5365400314331055, "learning_rate": 1.1249132356508374e-07, "loss": 4.2307, "step": 31751 }, { "epoch": 0.9698228466707391, "grad_norm": 0.5352050065994263, "learning_rate": 1.1226412391384944e-07, "loss": 4.1926, "step": 31752 }, { "epoch": 0.969853390348198, "grad_norm": 0.5349563360214233, "learning_rate": 1.120371534167941e-07, "loss": 4.1937, "step": 31753 }, { "epoch": 0.9698839340256566, "grad_norm": 0.5433503985404968, "learning_rate": 1.118104120760105e-07, "loss": 4.2513, "step": 31754 }, { "epoch": 0.9699144777031155, "grad_norm": 0.536825954914093, "learning_rate": 1.1158389989358586e-07, "loss": 4.2063, "step": 31755 }, { "epoch": 0.9699450213805743, "grad_norm": 0.5461567640304565, "learning_rate": 1.1135761687160185e-07, "loss": 4.2456, "step": 31756 }, { "epoch": 0.969975565058033, "grad_norm": 0.5517445206642151, "learning_rate": 1.1113156301214567e-07, "loss": 4.2234, "step": 31757 }, { "epoch": 0.9700061087354918, "grad_norm": 0.5368888974189758, "learning_rate": 1.10905738317299e-07, "loss": 4.258, "step": 31758 }, { "epoch": 0.9700366524129506, "grad_norm": 0.5492954254150391, "learning_rate": 1.1068014278913796e-07, "loss": 4.2999, "step": 31759 }, { "epoch": 0.9700671960904093, "grad_norm": 0.5364285707473755, "learning_rate": 1.1045477642974422e-07, "loss": 4.2399, "step": 31760 }, { "epoch": 0.9700977397678681, "grad_norm": 0.5462208986282349, "learning_rate": 1.1022963924118835e-07, "loss": 4.2861, "step": 31761 }, { "epoch": 0.9701282834453269, "grad_norm": 0.5498844385147095, "learning_rate": 1.1000473122554644e-07, "loss": 4.2648, "step": 31762 }, { "epoch": 0.9701588271227856, "grad_norm": 0.5557608008384705, "learning_rate": 1.0978005238488908e-07, "loss": 4.2324, "step": 31763 }, { "epoch": 0.9701893708002444, "grad_norm": 0.5424261093139648, "learning_rate": 1.0955560272128129e-07, "loss": 4.2717, "step": 31764 }, { "epoch": 0.9702199144777031, "grad_norm": 0.5502727627754211, "learning_rate": 1.0933138223679362e-07, "loss": 4.2818, "step": 31765 }, { "epoch": 0.9702504581551619, "grad_norm": 0.5438538789749146, "learning_rate": 1.0910739093348831e-07, "loss": 4.1955, "step": 31766 }, { "epoch": 0.9702810018326207, "grad_norm": 0.5554239749908447, "learning_rate": 1.088836288134304e-07, "loss": 4.2915, "step": 31767 }, { "epoch": 0.9703115455100794, "grad_norm": 0.5411609411239624, "learning_rate": 1.0866009587867931e-07, "loss": 4.2041, "step": 31768 }, { "epoch": 0.9703420891875382, "grad_norm": 0.5441834926605225, "learning_rate": 1.0843679213129177e-07, "loss": 4.209, "step": 31769 }, { "epoch": 0.970372632864997, "grad_norm": 0.5391780138015747, "learning_rate": 1.0821371757332444e-07, "loss": 4.3058, "step": 31770 }, { "epoch": 0.9704031765424557, "grad_norm": 0.5384134650230408, "learning_rate": 1.0799087220683123e-07, "loss": 4.2268, "step": 31771 }, { "epoch": 0.9704337202199145, "grad_norm": 0.5425176620483398, "learning_rate": 1.0776825603386331e-07, "loss": 4.0312, "step": 31772 }, { "epoch": 0.9704642638973733, "grad_norm": 0.5370875597000122, "learning_rate": 1.075458690564718e-07, "loss": 4.2286, "step": 31773 }, { "epoch": 0.970494807574832, "grad_norm": 0.5367571711540222, "learning_rate": 1.0732371127670782e-07, "loss": 4.2574, "step": 31774 }, { "epoch": 0.9705253512522908, "grad_norm": 0.5463330745697021, "learning_rate": 1.0710178269660865e-07, "loss": 4.2694, "step": 31775 }, { "epoch": 0.9705558949297496, "grad_norm": 0.5475325584411621, "learning_rate": 1.0688008331822264e-07, "loss": 4.139, "step": 31776 }, { "epoch": 0.9705864386072083, "grad_norm": 0.5487565994262695, "learning_rate": 1.066586131435926e-07, "loss": 4.2361, "step": 31777 }, { "epoch": 0.9706169822846671, "grad_norm": 0.5492107272148132, "learning_rate": 1.0643737217475302e-07, "loss": 4.2795, "step": 31778 }, { "epoch": 0.9706475259621259, "grad_norm": 0.541998028755188, "learning_rate": 1.0621636041374395e-07, "loss": 4.2771, "step": 31779 }, { "epoch": 0.9706780696395846, "grad_norm": 0.5444563031196594, "learning_rate": 1.0599557786260261e-07, "loss": 4.2836, "step": 31780 }, { "epoch": 0.9707086133170434, "grad_norm": 0.5486419200897217, "learning_rate": 1.0577502452335519e-07, "loss": 4.2619, "step": 31781 }, { "epoch": 0.9707391569945021, "grad_norm": 0.5481506586074829, "learning_rate": 1.0555470039804171e-07, "loss": 4.3538, "step": 31782 }, { "epoch": 0.9707697006719609, "grad_norm": 0.5360015034675598, "learning_rate": 1.0533460548868002e-07, "loss": 4.1689, "step": 31783 }, { "epoch": 0.9708002443494197, "grad_norm": 0.5387094616889954, "learning_rate": 1.0511473979730457e-07, "loss": 4.2292, "step": 31784 }, { "epoch": 0.9708307880268784, "grad_norm": 0.5440080165863037, "learning_rate": 1.0489510332593877e-07, "loss": 4.2381, "step": 31785 }, { "epoch": 0.9708613317043372, "grad_norm": 0.5519579648971558, "learning_rate": 1.0467569607660043e-07, "loss": 4.334, "step": 31786 }, { "epoch": 0.970891875381796, "grad_norm": 0.5460531115531921, "learning_rate": 1.0445651805131574e-07, "loss": 4.2631, "step": 31787 }, { "epoch": 0.9709224190592547, "grad_norm": 0.5455981492996216, "learning_rate": 1.0423756925209971e-07, "loss": 4.2348, "step": 31788 }, { "epoch": 0.9709529627367135, "grad_norm": 0.5473607778549194, "learning_rate": 1.0401884968096464e-07, "loss": 4.2206, "step": 31789 }, { "epoch": 0.9709835064141723, "grad_norm": 0.5375229120254517, "learning_rate": 1.0380035933993115e-07, "loss": 4.2321, "step": 31790 }, { "epoch": 0.971014050091631, "grad_norm": 0.5331416726112366, "learning_rate": 1.0358209823100873e-07, "loss": 4.2007, "step": 31791 }, { "epoch": 0.9710445937690898, "grad_norm": 0.5408132672309875, "learning_rate": 1.0336406635620688e-07, "loss": 4.2608, "step": 31792 }, { "epoch": 0.9710751374465486, "grad_norm": 0.5508174300193787, "learning_rate": 1.0314626371753233e-07, "loss": 4.257, "step": 31793 }, { "epoch": 0.9711056811240073, "grad_norm": 0.5494740009307861, "learning_rate": 1.0292869031698904e-07, "loss": 4.2128, "step": 31794 }, { "epoch": 0.9711362248014661, "grad_norm": 0.5411782264709473, "learning_rate": 1.0271134615658374e-07, "loss": 4.2964, "step": 31795 }, { "epoch": 0.9711667684789249, "grad_norm": 0.540103018283844, "learning_rate": 1.024942312383148e-07, "loss": 4.2377, "step": 31796 }, { "epoch": 0.9711973121563836, "grad_norm": 0.5333266258239746, "learning_rate": 1.0227734556418345e-07, "loss": 4.1819, "step": 31797 }, { "epoch": 0.9712278558338424, "grad_norm": 0.550325870513916, "learning_rate": 1.0206068913618527e-07, "loss": 4.1482, "step": 31798 }, { "epoch": 0.9712583995113011, "grad_norm": 0.5381484627723694, "learning_rate": 1.0184426195631591e-07, "loss": 4.2032, "step": 31799 }, { "epoch": 0.9712889431887599, "grad_norm": 0.5359317660331726, "learning_rate": 1.0162806402656822e-07, "loss": 4.2265, "step": 31800 }, { "epoch": 0.9713194868662187, "grad_norm": 0.5454024076461792, "learning_rate": 1.0141209534893225e-07, "loss": 4.1603, "step": 31801 }, { "epoch": 0.9713500305436774, "grad_norm": 0.533126950263977, "learning_rate": 1.0119635592539533e-07, "loss": 4.2229, "step": 31802 }, { "epoch": 0.9713805742211362, "grad_norm": 0.5434475541114807, "learning_rate": 1.0098084575794475e-07, "loss": 4.2697, "step": 31803 }, { "epoch": 0.971411117898595, "grad_norm": 0.5411009192466736, "learning_rate": 1.0076556484856781e-07, "loss": 4.2239, "step": 31804 }, { "epoch": 0.9714416615760537, "grad_norm": 0.5430522561073303, "learning_rate": 1.0055051319924346e-07, "loss": 4.3067, "step": 31805 }, { "epoch": 0.9714722052535125, "grad_norm": 0.5386737585067749, "learning_rate": 1.0033569081195072e-07, "loss": 4.2626, "step": 31806 }, { "epoch": 0.9715027489309713, "grad_norm": 0.5469550490379333, "learning_rate": 1.0012109768867128e-07, "loss": 4.3075, "step": 31807 }, { "epoch": 0.97153329260843, "grad_norm": 0.5405794382095337, "learning_rate": 9.990673383137861e-08, "loss": 4.184, "step": 31808 }, { "epoch": 0.9715638362858888, "grad_norm": 0.5425795316696167, "learning_rate": 9.969259924204888e-08, "loss": 4.2686, "step": 31809 }, { "epoch": 0.9715943799633476, "grad_norm": 0.5450062155723572, "learning_rate": 9.947869392264997e-08, "loss": 4.3004, "step": 31810 }, { "epoch": 0.9716249236408063, "grad_norm": 0.5420103669166565, "learning_rate": 9.926501787515529e-08, "loss": 4.2756, "step": 31811 }, { "epoch": 0.9716554673182651, "grad_norm": 0.5432336330413818, "learning_rate": 9.905157110152718e-08, "loss": 4.3287, "step": 31812 }, { "epoch": 0.9716860109957239, "grad_norm": 0.5432475209236145, "learning_rate": 9.883835360373628e-08, "loss": 4.3248, "step": 31813 }, { "epoch": 0.9717165546731826, "grad_norm": 0.538497269153595, "learning_rate": 9.862536538374212e-08, "loss": 4.1023, "step": 31814 }, { "epoch": 0.9717470983506414, "grad_norm": 0.5518795847892761, "learning_rate": 9.841260644350703e-08, "loss": 4.2948, "step": 31815 }, { "epoch": 0.9717776420281001, "grad_norm": 0.548895001411438, "learning_rate": 9.820007678499054e-08, "loss": 4.2887, "step": 31816 }, { "epoch": 0.9718081857055589, "grad_norm": 0.5430777668952942, "learning_rate": 9.798777641014945e-08, "loss": 4.2577, "step": 31817 }, { "epoch": 0.9718387293830177, "grad_norm": 0.5364472270011902, "learning_rate": 9.777570532093772e-08, "loss": 4.2445, "step": 31818 }, { "epoch": 0.9718692730604764, "grad_norm": 0.5435846447944641, "learning_rate": 9.756386351931212e-08, "loss": 4.142, "step": 31819 }, { "epoch": 0.9718998167379352, "grad_norm": 0.5437873005867004, "learning_rate": 9.735225100721556e-08, "loss": 4.2641, "step": 31820 }, { "epoch": 0.971930360415394, "grad_norm": 0.5377184152603149, "learning_rate": 9.714086778660203e-08, "loss": 4.2631, "step": 31821 }, { "epoch": 0.9719609040928527, "grad_norm": 0.5419577956199646, "learning_rate": 9.692971385941441e-08, "loss": 4.3078, "step": 31822 }, { "epoch": 0.9719914477703115, "grad_norm": 0.5332276225090027, "learning_rate": 9.671878922760114e-08, "loss": 4.228, "step": 31823 }, { "epoch": 0.9720219914477704, "grad_norm": 0.5463456511497498, "learning_rate": 9.650809389310234e-08, "loss": 4.1189, "step": 31824 }, { "epoch": 0.972052535125229, "grad_norm": 0.5365262031555176, "learning_rate": 9.629762785785534e-08, "loss": 4.1416, "step": 31825 }, { "epoch": 0.9720830788026878, "grad_norm": 0.5529763698577881, "learning_rate": 9.608739112380304e-08, "loss": 4.259, "step": 31826 }, { "epoch": 0.9721136224801467, "grad_norm": 0.540632963180542, "learning_rate": 9.587738369287446e-08, "loss": 4.2896, "step": 31827 }, { "epoch": 0.9721441661576053, "grad_norm": 0.5404080748558044, "learning_rate": 9.566760556700971e-08, "loss": 4.209, "step": 31828 }, { "epoch": 0.9721747098350642, "grad_norm": 0.556201696395874, "learning_rate": 9.545805674813779e-08, "loss": 4.2876, "step": 31829 }, { "epoch": 0.972205253512523, "grad_norm": 0.5549717545509338, "learning_rate": 9.524873723818772e-08, "loss": 4.1247, "step": 31830 }, { "epoch": 0.9722357971899817, "grad_norm": 0.5371652841567993, "learning_rate": 9.503964703908852e-08, "loss": 4.2559, "step": 31831 }, { "epoch": 0.9722663408674405, "grad_norm": 0.5481299161911011, "learning_rate": 9.483078615276364e-08, "loss": 4.3176, "step": 31832 }, { "epoch": 0.9722968845448992, "grad_norm": 0.5404033064842224, "learning_rate": 9.462215458113655e-08, "loss": 4.2726, "step": 31833 }, { "epoch": 0.972327428222358, "grad_norm": 0.5415763854980469, "learning_rate": 9.441375232612792e-08, "loss": 4.1348, "step": 31834 }, { "epoch": 0.9723579718998168, "grad_norm": 0.536869466304779, "learning_rate": 9.420557938965846e-08, "loss": 4.2676, "step": 31835 }, { "epoch": 0.9723885155772755, "grad_norm": 0.5496411919593811, "learning_rate": 9.399763577364051e-08, "loss": 4.2379, "step": 31836 }, { "epoch": 0.9724190592547343, "grad_norm": 0.5406626462936401, "learning_rate": 9.378992147999476e-08, "loss": 4.123, "step": 31837 }, { "epoch": 0.9724496029321931, "grad_norm": 0.5339988470077515, "learning_rate": 9.358243651062803e-08, "loss": 4.2772, "step": 31838 }, { "epoch": 0.9724801466096518, "grad_norm": 0.5460781455039978, "learning_rate": 9.337518086745545e-08, "loss": 4.3154, "step": 31839 }, { "epoch": 0.9725106902871106, "grad_norm": 0.5385400056838989, "learning_rate": 9.316815455238381e-08, "loss": 4.2631, "step": 31840 }, { "epoch": 0.9725412339645694, "grad_norm": 0.5378940105438232, "learning_rate": 9.296135756731717e-08, "loss": 4.2187, "step": 31841 }, { "epoch": 0.9725717776420281, "grad_norm": 0.5454562306404114, "learning_rate": 9.275478991416231e-08, "loss": 4.2456, "step": 31842 }, { "epoch": 0.9726023213194869, "grad_norm": 0.5380887985229492, "learning_rate": 9.254845159482051e-08, "loss": 4.1038, "step": 31843 }, { "epoch": 0.9726328649969457, "grad_norm": 0.5416015982627869, "learning_rate": 9.234234261119023e-08, "loss": 4.2236, "step": 31844 }, { "epoch": 0.9726634086744044, "grad_norm": 0.5326213240623474, "learning_rate": 9.213646296516998e-08, "loss": 4.1818, "step": 31845 }, { "epoch": 0.9726939523518632, "grad_norm": 0.539833128452301, "learning_rate": 9.193081265865544e-08, "loss": 4.3105, "step": 31846 }, { "epoch": 0.972724496029322, "grad_norm": 0.5493593215942383, "learning_rate": 9.172539169354233e-08, "loss": 4.2266, "step": 31847 }, { "epoch": 0.9727550397067807, "grad_norm": 0.5560773015022278, "learning_rate": 9.152020007171803e-08, "loss": 4.1114, "step": 31848 }, { "epoch": 0.9727855833842395, "grad_norm": 0.5455468893051147, "learning_rate": 9.131523779507545e-08, "loss": 4.1892, "step": 31849 }, { "epoch": 0.9728161270616982, "grad_norm": 0.5531373023986816, "learning_rate": 9.111050486549921e-08, "loss": 4.0427, "step": 31850 }, { "epoch": 0.972846670739157, "grad_norm": 0.5404198169708252, "learning_rate": 9.09060012848767e-08, "loss": 4.2745, "step": 31851 }, { "epoch": 0.9728772144166158, "grad_norm": 0.5539830923080444, "learning_rate": 9.070172705508695e-08, "loss": 4.2578, "step": 31852 }, { "epoch": 0.9729077580940745, "grad_norm": 0.5581210255622864, "learning_rate": 9.049768217801458e-08, "loss": 4.2934, "step": 31853 }, { "epoch": 0.9729383017715333, "grad_norm": 0.5498589873313904, "learning_rate": 9.029386665553863e-08, "loss": 4.2741, "step": 31854 }, { "epoch": 0.9729688454489921, "grad_norm": 0.5392913818359375, "learning_rate": 9.009028048953538e-08, "loss": 4.3032, "step": 31855 }, { "epoch": 0.9729993891264508, "grad_norm": 0.5332508683204651, "learning_rate": 8.988692368187557e-08, "loss": 4.2502, "step": 31856 }, { "epoch": 0.9730299328039096, "grad_norm": 0.541194498538971, "learning_rate": 8.968379623443545e-08, "loss": 4.2148, "step": 31857 }, { "epoch": 0.9730604764813684, "grad_norm": 0.5347804427146912, "learning_rate": 8.9480898149083e-08, "loss": 4.2515, "step": 31858 }, { "epoch": 0.9730910201588271, "grad_norm": 0.5479819774627686, "learning_rate": 8.927822942768893e-08, "loss": 4.3176, "step": 31859 }, { "epoch": 0.9731215638362859, "grad_norm": 0.5456337928771973, "learning_rate": 8.907579007211841e-08, "loss": 4.2478, "step": 31860 }, { "epoch": 0.9731521075137447, "grad_norm": 0.5495847463607788, "learning_rate": 8.887358008423386e-08, "loss": 4.2726, "step": 31861 }, { "epoch": 0.9731826511912034, "grad_norm": 0.5572108030319214, "learning_rate": 8.867159946590042e-08, "loss": 4.2396, "step": 31862 }, { "epoch": 0.9732131948686622, "grad_norm": 0.5581045150756836, "learning_rate": 8.846984821897219e-08, "loss": 4.3025, "step": 31863 }, { "epoch": 0.973243738546121, "grad_norm": 0.5446129441261292, "learning_rate": 8.826832634531434e-08, "loss": 4.2653, "step": 31864 }, { "epoch": 0.9732742822235797, "grad_norm": 0.5465911626815796, "learning_rate": 8.806703384677539e-08, "loss": 4.2816, "step": 31865 }, { "epoch": 0.9733048259010385, "grad_norm": 0.5493743419647217, "learning_rate": 8.786597072521219e-08, "loss": 4.2136, "step": 31866 }, { "epoch": 0.9733353695784972, "grad_norm": 0.5574077367782593, "learning_rate": 8.766513698247603e-08, "loss": 4.371, "step": 31867 }, { "epoch": 0.973365913255956, "grad_norm": 0.5541849732398987, "learning_rate": 8.746453262041543e-08, "loss": 4.1685, "step": 31868 }, { "epoch": 0.9733964569334148, "grad_norm": 0.5413094162940979, "learning_rate": 8.726415764087891e-08, "loss": 4.2495, "step": 31869 }, { "epoch": 0.9734270006108735, "grad_norm": 0.5398074984550476, "learning_rate": 8.706401204570947e-08, "loss": 4.1687, "step": 31870 }, { "epoch": 0.9734575442883323, "grad_norm": 0.5598376393318176, "learning_rate": 8.686409583675004e-08, "loss": 4.1847, "step": 31871 }, { "epoch": 0.9734880879657911, "grad_norm": 0.5476230382919312, "learning_rate": 8.666440901584083e-08, "loss": 4.2857, "step": 31872 }, { "epoch": 0.9735186316432498, "grad_norm": 0.5319695472717285, "learning_rate": 8.646495158482481e-08, "loss": 4.1843, "step": 31873 }, { "epoch": 0.9735491753207086, "grad_norm": 0.5375962257385254, "learning_rate": 8.626572354553108e-08, "loss": 4.2452, "step": 31874 }, { "epoch": 0.9735797189981674, "grad_norm": 0.5474733114242554, "learning_rate": 8.606672489980261e-08, "loss": 4.2956, "step": 31875 }, { "epoch": 0.9736102626756261, "grad_norm": 0.5362688899040222, "learning_rate": 8.586795564946293e-08, "loss": 4.1595, "step": 31876 }, { "epoch": 0.9736408063530849, "grad_norm": 0.5485652089118958, "learning_rate": 8.566941579634947e-08, "loss": 4.2646, "step": 31877 }, { "epoch": 0.9736713500305437, "grad_norm": 0.5427928566932678, "learning_rate": 8.547110534228574e-08, "loss": 4.1619, "step": 31878 }, { "epoch": 0.9737018937080024, "grad_norm": 0.5425037741661072, "learning_rate": 8.527302428910089e-08, "loss": 4.2876, "step": 31879 }, { "epoch": 0.9737324373854612, "grad_norm": 0.5417330861091614, "learning_rate": 8.507517263861565e-08, "loss": 4.2515, "step": 31880 }, { "epoch": 0.97376298106292, "grad_norm": 0.5380128622055054, "learning_rate": 8.487755039265355e-08, "loss": 4.2066, "step": 31881 }, { "epoch": 0.9737935247403787, "grad_norm": 0.5448879599571228, "learning_rate": 8.468015755303538e-08, "loss": 4.3189, "step": 31882 }, { "epoch": 0.9738240684178375, "grad_norm": 0.5362061858177185, "learning_rate": 8.448299412157634e-08, "loss": 4.2871, "step": 31883 }, { "epoch": 0.9738546120952962, "grad_norm": 0.5394042134284973, "learning_rate": 8.428606010009444e-08, "loss": 4.2462, "step": 31884 }, { "epoch": 0.973885155772755, "grad_norm": 0.5502734184265137, "learning_rate": 8.408935549039932e-08, "loss": 4.1461, "step": 31885 }, { "epoch": 0.9739156994502138, "grad_norm": 0.5289720892906189, "learning_rate": 8.389288029430342e-08, "loss": 4.1476, "step": 31886 }, { "epoch": 0.9739462431276725, "grad_norm": 0.550084114074707, "learning_rate": 8.369663451361642e-08, "loss": 4.2449, "step": 31887 }, { "epoch": 0.9739767868051313, "grad_norm": 0.5468040704727173, "learning_rate": 8.350061815014798e-08, "loss": 4.3089, "step": 31888 }, { "epoch": 0.9740073304825901, "grad_norm": 0.545708417892456, "learning_rate": 8.330483120569666e-08, "loss": 4.2706, "step": 31889 }, { "epoch": 0.9740378741600488, "grad_norm": 0.5463305115699768, "learning_rate": 8.310927368206933e-08, "loss": 4.3746, "step": 31890 }, { "epoch": 0.9740684178375076, "grad_norm": 0.5496059060096741, "learning_rate": 8.291394558106735e-08, "loss": 4.1738, "step": 31891 }, { "epoch": 0.9740989615149664, "grad_norm": 0.5370641350746155, "learning_rate": 8.27188469044865e-08, "loss": 4.1218, "step": 31892 }, { "epoch": 0.9741295051924251, "grad_norm": 0.5415517687797546, "learning_rate": 8.252397765412534e-08, "loss": 4.2707, "step": 31893 }, { "epoch": 0.9741600488698839, "grad_norm": 0.5438118577003479, "learning_rate": 8.232933783177688e-08, "loss": 4.3386, "step": 31894 }, { "epoch": 0.9741905925473427, "grad_norm": 0.5488045811653137, "learning_rate": 8.213492743923134e-08, "loss": 4.2271, "step": 31895 }, { "epoch": 0.9742211362248014, "grad_norm": 0.5333805680274963, "learning_rate": 8.194074647828454e-08, "loss": 4.182, "step": 31896 }, { "epoch": 0.9742516799022602, "grad_norm": 0.5490120649337769, "learning_rate": 8.174679495071835e-08, "loss": 4.2367, "step": 31897 }, { "epoch": 0.974282223579719, "grad_norm": 0.5407941341400146, "learning_rate": 8.155307285832304e-08, "loss": 4.1803, "step": 31898 }, { "epoch": 0.9743127672571777, "grad_norm": 0.548362135887146, "learning_rate": 8.135958020288048e-08, "loss": 4.269, "step": 31899 }, { "epoch": 0.9743433109346366, "grad_norm": 0.5381620526313782, "learning_rate": 8.116631698616983e-08, "loss": 4.27, "step": 31900 }, { "epoch": 0.9743738546120952, "grad_norm": 0.5498575568199158, "learning_rate": 8.097328320997578e-08, "loss": 4.3114, "step": 31901 }, { "epoch": 0.974404398289554, "grad_norm": 0.5491060614585876, "learning_rate": 8.078047887607187e-08, "loss": 4.4025, "step": 31902 }, { "epoch": 0.9744349419670129, "grad_norm": 0.5514997243881226, "learning_rate": 8.05879039862345e-08, "loss": 4.248, "step": 31903 }, { "epoch": 0.9744654856444716, "grad_norm": 0.5462926626205444, "learning_rate": 8.039555854223447e-08, "loss": 4.1967, "step": 31904 }, { "epoch": 0.9744960293219304, "grad_norm": 0.5467098355293274, "learning_rate": 8.02034425458481e-08, "loss": 4.2069, "step": 31905 }, { "epoch": 0.9745265729993892, "grad_norm": 0.5521351099014282, "learning_rate": 8.001155599883792e-08, "loss": 4.2619, "step": 31906 }, { "epoch": 0.9745571166768479, "grad_norm": 0.5377628207206726, "learning_rate": 7.98198989029747e-08, "loss": 4.3152, "step": 31907 }, { "epoch": 0.9745876603543067, "grad_norm": 0.542168140411377, "learning_rate": 7.96284712600237e-08, "loss": 4.2059, "step": 31908 }, { "epoch": 0.9746182040317655, "grad_norm": 0.552277684211731, "learning_rate": 7.943727307174464e-08, "loss": 4.1558, "step": 31909 }, { "epoch": 0.9746487477092242, "grad_norm": 0.5439386367797852, "learning_rate": 7.924630433989999e-08, "loss": 4.2727, "step": 31910 }, { "epoch": 0.974679291386683, "grad_norm": 0.5542514324188232, "learning_rate": 7.905556506624945e-08, "loss": 4.1984, "step": 31911 }, { "epoch": 0.9747098350641418, "grad_norm": 0.5488602519035339, "learning_rate": 7.88650552525444e-08, "loss": 4.1289, "step": 31912 }, { "epoch": 0.9747403787416005, "grad_norm": 0.532967209815979, "learning_rate": 7.867477490054454e-08, "loss": 4.1573, "step": 31913 }, { "epoch": 0.9747709224190593, "grad_norm": 0.5389257073402405, "learning_rate": 7.848472401199847e-08, "loss": 4.2249, "step": 31914 }, { "epoch": 0.974801466096518, "grad_norm": 0.5348942875862122, "learning_rate": 7.829490258865757e-08, "loss": 4.2906, "step": 31915 }, { "epoch": 0.9748320097739768, "grad_norm": 0.5490289926528931, "learning_rate": 7.810531063226767e-08, "loss": 4.2511, "step": 31916 }, { "epoch": 0.9748625534514356, "grad_norm": 0.5461191534996033, "learning_rate": 7.791594814457459e-08, "loss": 4.178, "step": 31917 }, { "epoch": 0.9748930971288943, "grad_norm": 0.5466051697731018, "learning_rate": 7.772681512732416e-08, "loss": 4.2014, "step": 31918 }, { "epoch": 0.9749236408063531, "grad_norm": 0.5429598689079285, "learning_rate": 7.753791158225943e-08, "loss": 4.2753, "step": 31919 }, { "epoch": 0.9749541844838119, "grad_norm": 0.5345268845558167, "learning_rate": 7.734923751111511e-08, "loss": 4.2068, "step": 31920 }, { "epoch": 0.9749847281612706, "grad_norm": 0.5501502752304077, "learning_rate": 7.716079291562872e-08, "loss": 4.2798, "step": 31921 }, { "epoch": 0.9750152718387294, "grad_norm": 0.5486342310905457, "learning_rate": 7.697257779753775e-08, "loss": 4.1967, "step": 31922 }, { "epoch": 0.9750458155161882, "grad_norm": 0.5414403676986694, "learning_rate": 7.678459215857415e-08, "loss": 4.1903, "step": 31923 }, { "epoch": 0.9750763591936469, "grad_norm": 0.5499349236488342, "learning_rate": 7.659683600047263e-08, "loss": 4.1772, "step": 31924 }, { "epoch": 0.9751069028711057, "grad_norm": 0.5427389740943909, "learning_rate": 7.640930932495405e-08, "loss": 4.2667, "step": 31925 }, { "epoch": 0.9751374465485645, "grad_norm": 0.5446215271949768, "learning_rate": 7.622201213375035e-08, "loss": 4.3123, "step": 31926 }, { "epoch": 0.9751679902260232, "grad_norm": 0.5399439930915833, "learning_rate": 7.603494442858516e-08, "loss": 4.1428, "step": 31927 }, { "epoch": 0.975198533903482, "grad_norm": 0.5449823141098022, "learning_rate": 7.58481062111821e-08, "loss": 4.3497, "step": 31928 }, { "epoch": 0.9752290775809408, "grad_norm": 0.5398023724555969, "learning_rate": 7.566149748325924e-08, "loss": 4.2169, "step": 31929 }, { "epoch": 0.9752596212583995, "grad_norm": 0.5436956882476807, "learning_rate": 7.547511824653741e-08, "loss": 4.3263, "step": 31930 }, { "epoch": 0.9752901649358583, "grad_norm": 0.5509716868400574, "learning_rate": 7.528896850272915e-08, "loss": 4.2755, "step": 31931 }, { "epoch": 0.975320708613317, "grad_norm": 0.5389108657836914, "learning_rate": 7.510304825354974e-08, "loss": 4.2852, "step": 31932 }, { "epoch": 0.9753512522907758, "grad_norm": 0.5484406352043152, "learning_rate": 7.49173575007145e-08, "loss": 4.2529, "step": 31933 }, { "epoch": 0.9753817959682346, "grad_norm": 0.5512726902961731, "learning_rate": 7.473189624592758e-08, "loss": 4.2101, "step": 31934 }, { "epoch": 0.9754123396456933, "grad_norm": 0.5412830114364624, "learning_rate": 7.454666449090153e-08, "loss": 4.2567, "step": 31935 }, { "epoch": 0.9754428833231521, "grad_norm": 0.5326639413833618, "learning_rate": 7.436166223733776e-08, "loss": 4.142, "step": 31936 }, { "epoch": 0.9754734270006109, "grad_norm": 0.5583691596984863, "learning_rate": 7.417688948694324e-08, "loss": 4.3138, "step": 31937 }, { "epoch": 0.9755039706780696, "grad_norm": 0.5450142025947571, "learning_rate": 7.39923462414166e-08, "loss": 4.2378, "step": 31938 }, { "epoch": 0.9755345143555284, "grad_norm": 0.546263575553894, "learning_rate": 7.380803250245926e-08, "loss": 4.2232, "step": 31939 }, { "epoch": 0.9755650580329872, "grad_norm": 0.54035884141922, "learning_rate": 7.36239482717671e-08, "loss": 4.1848, "step": 31940 }, { "epoch": 0.9755956017104459, "grad_norm": 0.5329445004463196, "learning_rate": 7.34400935510332e-08, "loss": 4.2729, "step": 31941 }, { "epoch": 0.9756261453879047, "grad_norm": 0.525862991809845, "learning_rate": 7.325646834195343e-08, "loss": 4.1388, "step": 31942 }, { "epoch": 0.9756566890653635, "grad_norm": 0.5523228645324707, "learning_rate": 7.30730726462181e-08, "loss": 4.2381, "step": 31943 }, { "epoch": 0.9756872327428222, "grad_norm": 0.5371569395065308, "learning_rate": 7.288990646551475e-08, "loss": 4.2522, "step": 31944 }, { "epoch": 0.975717776420281, "grad_norm": 0.536071240901947, "learning_rate": 7.270696980153092e-08, "loss": 4.2341, "step": 31945 }, { "epoch": 0.9757483200977398, "grad_norm": 0.5434842109680176, "learning_rate": 7.252426265594858e-08, "loss": 4.1147, "step": 31946 }, { "epoch": 0.9757788637751985, "grad_norm": 0.5447087287902832, "learning_rate": 7.23417850304553e-08, "loss": 4.2751, "step": 31947 }, { "epoch": 0.9758094074526573, "grad_norm": 0.5473383069038391, "learning_rate": 7.215953692672472e-08, "loss": 4.3048, "step": 31948 }, { "epoch": 0.975839951130116, "grad_norm": 0.5475967526435852, "learning_rate": 7.197751834643884e-08, "loss": 4.1977, "step": 31949 }, { "epoch": 0.9758704948075748, "grad_norm": 0.5533168315887451, "learning_rate": 7.179572929127132e-08, "loss": 4.223, "step": 31950 }, { "epoch": 0.9759010384850336, "grad_norm": 0.5423659682273865, "learning_rate": 7.161416976289858e-08, "loss": 4.2735, "step": 31951 }, { "epoch": 0.9759315821624923, "grad_norm": 0.5503675937652588, "learning_rate": 7.143283976299153e-08, "loss": 4.2694, "step": 31952 }, { "epoch": 0.9759621258399511, "grad_norm": 0.5524708032608032, "learning_rate": 7.125173929321827e-08, "loss": 4.2356, "step": 31953 }, { "epoch": 0.9759926695174099, "grad_norm": 0.5406578183174133, "learning_rate": 7.10708683552469e-08, "loss": 4.2779, "step": 31954 }, { "epoch": 0.9760232131948686, "grad_norm": 0.5508753657341003, "learning_rate": 7.089022695074555e-08, "loss": 4.2142, "step": 31955 }, { "epoch": 0.9760537568723274, "grad_norm": 0.549037516117096, "learning_rate": 7.070981508137397e-08, "loss": 4.1951, "step": 31956 }, { "epoch": 0.9760843005497862, "grad_norm": 0.5457966923713684, "learning_rate": 7.052963274879199e-08, "loss": 4.2519, "step": 31957 }, { "epoch": 0.9761148442272449, "grad_norm": 0.5402691960334778, "learning_rate": 7.03496799546649e-08, "loss": 4.2908, "step": 31958 }, { "epoch": 0.9761453879047037, "grad_norm": 0.5357896685600281, "learning_rate": 7.016995670064419e-08, "loss": 4.1625, "step": 31959 }, { "epoch": 0.9761759315821625, "grad_norm": 0.5353471636772156, "learning_rate": 6.999046298838685e-08, "loss": 4.2066, "step": 31960 }, { "epoch": 0.9762064752596212, "grad_norm": 0.5351005792617798, "learning_rate": 6.981119881954434e-08, "loss": 4.1661, "step": 31961 }, { "epoch": 0.97623701893708, "grad_norm": 0.5421670079231262, "learning_rate": 6.963216419576812e-08, "loss": 4.2196, "step": 31962 }, { "epoch": 0.9762675626145388, "grad_norm": 0.5470213890075684, "learning_rate": 6.945335911870688e-08, "loss": 4.3244, "step": 31963 }, { "epoch": 0.9762981062919975, "grad_norm": 0.5402565002441406, "learning_rate": 6.92747835900065e-08, "loss": 4.1755, "step": 31964 }, { "epoch": 0.9763286499694563, "grad_norm": 0.5409813523292542, "learning_rate": 6.909643761131013e-08, "loss": 4.1244, "step": 31965 }, { "epoch": 0.976359193646915, "grad_norm": 0.5434737801551819, "learning_rate": 6.891832118426366e-08, "loss": 4.2242, "step": 31966 }, { "epoch": 0.9763897373243738, "grad_norm": 0.5367753505706787, "learning_rate": 6.874043431050193e-08, "loss": 4.2215, "step": 31967 }, { "epoch": 0.9764202810018326, "grad_norm": 0.5443695783615112, "learning_rate": 6.856277699166802e-08, "loss": 4.2255, "step": 31968 }, { "epoch": 0.9764508246792913, "grad_norm": 0.5322675704956055, "learning_rate": 6.838534922939399e-08, "loss": 4.0774, "step": 31969 }, { "epoch": 0.9764813683567501, "grad_norm": 0.5449807643890381, "learning_rate": 6.820815102531186e-08, "loss": 4.3246, "step": 31970 }, { "epoch": 0.976511912034209, "grad_norm": 0.5375898480415344, "learning_rate": 6.80311823810592e-08, "loss": 4.1993, "step": 31971 }, { "epoch": 0.9765424557116676, "grad_norm": 0.5373116135597229, "learning_rate": 6.785444329825974e-08, "loss": 4.2307, "step": 31972 }, { "epoch": 0.9765729993891265, "grad_norm": 0.5465956926345825, "learning_rate": 6.767793377854548e-08, "loss": 4.2816, "step": 31973 }, { "epoch": 0.9766035430665853, "grad_norm": 0.540966272354126, "learning_rate": 6.750165382353734e-08, "loss": 4.2896, "step": 31974 }, { "epoch": 0.976634086744044, "grad_norm": 0.5454344153404236, "learning_rate": 6.73256034348646e-08, "loss": 4.2943, "step": 31975 }, { "epoch": 0.9766646304215028, "grad_norm": 0.5388211607933044, "learning_rate": 6.714978261413984e-08, "loss": 4.2681, "step": 31976 }, { "epoch": 0.9766951740989616, "grad_norm": 0.5417342782020569, "learning_rate": 6.697419136298678e-08, "loss": 4.1913, "step": 31977 }, { "epoch": 0.9767257177764203, "grad_norm": 0.555343508720398, "learning_rate": 6.679882968302354e-08, "loss": 4.3231, "step": 31978 }, { "epoch": 0.9767562614538791, "grad_norm": 0.5474591255187988, "learning_rate": 6.662369757586274e-08, "loss": 4.0742, "step": 31979 }, { "epoch": 0.9767868051313379, "grad_norm": 0.5364439487457275, "learning_rate": 6.644879504311697e-08, "loss": 4.2772, "step": 31980 }, { "epoch": 0.9768173488087966, "grad_norm": 0.5435170531272888, "learning_rate": 6.627412208639328e-08, "loss": 4.2316, "step": 31981 }, { "epoch": 0.9768478924862554, "grad_norm": 0.5382710695266724, "learning_rate": 6.609967870730704e-08, "loss": 4.2262, "step": 31982 }, { "epoch": 0.9768784361637141, "grad_norm": 0.5378017425537109, "learning_rate": 6.592546490745977e-08, "loss": 4.279, "step": 31983 }, { "epoch": 0.9769089798411729, "grad_norm": 0.5473552942276001, "learning_rate": 6.575148068845849e-08, "loss": 4.2494, "step": 31984 }, { "epoch": 0.9769395235186317, "grad_norm": 0.5440387725830078, "learning_rate": 6.557772605189916e-08, "loss": 4.2929, "step": 31985 }, { "epoch": 0.9769700671960904, "grad_norm": 0.5523157119750977, "learning_rate": 6.540420099938882e-08, "loss": 4.2021, "step": 31986 }, { "epoch": 0.9770006108735492, "grad_norm": 0.5458299517631531, "learning_rate": 6.523090553252065e-08, "loss": 4.1891, "step": 31987 }, { "epoch": 0.977031154551008, "grad_norm": 0.5411607027053833, "learning_rate": 6.505783965289336e-08, "loss": 4.2535, "step": 31988 }, { "epoch": 0.9770616982284667, "grad_norm": 0.5474498271942139, "learning_rate": 6.488500336209735e-08, "loss": 4.352, "step": 31989 }, { "epoch": 0.9770922419059255, "grad_norm": 0.537473201751709, "learning_rate": 6.47123966617258e-08, "loss": 4.1692, "step": 31990 }, { "epoch": 0.9771227855833843, "grad_norm": 0.5349568724632263, "learning_rate": 6.45400195533663e-08, "loss": 4.2542, "step": 31991 }, { "epoch": 0.977153329260843, "grad_norm": 0.5538502931594849, "learning_rate": 6.436787203860928e-08, "loss": 4.3146, "step": 31992 }, { "epoch": 0.9771838729383018, "grad_norm": 0.5389499664306641, "learning_rate": 6.419595411903956e-08, "loss": 4.2182, "step": 31993 }, { "epoch": 0.9772144166157606, "grad_norm": 0.5381923913955688, "learning_rate": 6.402426579623367e-08, "loss": 4.1464, "step": 31994 }, { "epoch": 0.9772449602932193, "grad_norm": 0.5438488721847534, "learning_rate": 6.385280707178199e-08, "loss": 4.2993, "step": 31995 }, { "epoch": 0.9772755039706781, "grad_norm": 0.5422479510307312, "learning_rate": 6.368157794725549e-08, "loss": 4.2738, "step": 31996 }, { "epoch": 0.9773060476481369, "grad_norm": 0.5403241515159607, "learning_rate": 6.351057842423347e-08, "loss": 4.2828, "step": 31997 }, { "epoch": 0.9773365913255956, "grad_norm": 0.5469111800193787, "learning_rate": 6.333980850429244e-08, "loss": 4.2912, "step": 31998 }, { "epoch": 0.9773671350030544, "grad_norm": 0.5584810376167297, "learning_rate": 6.316926818900337e-08, "loss": 4.2446, "step": 31999 }, { "epoch": 0.9773976786805131, "grad_norm": 0.541620671749115, "learning_rate": 6.299895747993445e-08, "loss": 4.295, "step": 32000 }, { "epoch": 0.9774282223579719, "grad_norm": 0.5478538274765015, "learning_rate": 6.282887637865664e-08, "loss": 4.1834, "step": 32001 }, { "epoch": 0.9774587660354307, "grad_norm": 0.5440146923065186, "learning_rate": 6.265902488673259e-08, "loss": 4.2438, "step": 32002 }, { "epoch": 0.9774893097128894, "grad_norm": 0.5393646955490112, "learning_rate": 6.248940300573047e-08, "loss": 4.265, "step": 32003 }, { "epoch": 0.9775198533903482, "grad_norm": 0.5399725437164307, "learning_rate": 6.232001073721016e-08, "loss": 4.2304, "step": 32004 }, { "epoch": 0.977550397067807, "grad_norm": 0.5470872521400452, "learning_rate": 6.215084808272876e-08, "loss": 4.346, "step": 32005 }, { "epoch": 0.9775809407452657, "grad_norm": 0.5360822677612305, "learning_rate": 6.198191504384887e-08, "loss": 4.1274, "step": 32006 }, { "epoch": 0.9776114844227245, "grad_norm": 0.5447620153427124, "learning_rate": 6.181321162212206e-08, "loss": 4.2915, "step": 32007 }, { "epoch": 0.9776420281001833, "grad_norm": 0.5372705459594727, "learning_rate": 6.164473781910262e-08, "loss": 4.2358, "step": 32008 }, { "epoch": 0.977672571777642, "grad_norm": 0.5439798831939697, "learning_rate": 6.147649363634212e-08, "loss": 4.2891, "step": 32009 }, { "epoch": 0.9777031154551008, "grad_norm": 0.5541260242462158, "learning_rate": 6.130847907539206e-08, "loss": 4.2841, "step": 32010 }, { "epoch": 0.9777336591325596, "grad_norm": 0.537132740020752, "learning_rate": 6.114069413779566e-08, "loss": 4.2284, "step": 32011 }, { "epoch": 0.9777642028100183, "grad_norm": 0.5449116826057434, "learning_rate": 6.097313882509614e-08, "loss": 4.2334, "step": 32012 }, { "epoch": 0.9777947464874771, "grad_norm": 0.5439637303352356, "learning_rate": 6.080581313884504e-08, "loss": 4.238, "step": 32013 }, { "epoch": 0.9778252901649359, "grad_norm": 0.5430607795715332, "learning_rate": 6.063871708057168e-08, "loss": 4.0866, "step": 32014 }, { "epoch": 0.9778558338423946, "grad_norm": 0.542843759059906, "learning_rate": 6.047185065182481e-08, "loss": 4.2238, "step": 32015 }, { "epoch": 0.9778863775198534, "grad_norm": 0.5454525947570801, "learning_rate": 6.030521385413378e-08, "loss": 4.2935, "step": 32016 }, { "epoch": 0.9779169211973121, "grad_norm": 0.5453518629074097, "learning_rate": 6.013880668903627e-08, "loss": 4.2415, "step": 32017 }, { "epoch": 0.9779474648747709, "grad_norm": 0.5583998560905457, "learning_rate": 5.997262915806157e-08, "loss": 4.2061, "step": 32018 }, { "epoch": 0.9779780085522297, "grad_norm": 0.5538092255592346, "learning_rate": 5.980668126274457e-08, "loss": 4.3277, "step": 32019 }, { "epoch": 0.9780085522296884, "grad_norm": 0.542945146560669, "learning_rate": 5.964096300460909e-08, "loss": 4.3148, "step": 32020 }, { "epoch": 0.9780390959071472, "grad_norm": 0.5371029376983643, "learning_rate": 5.947547438518164e-08, "loss": 4.1937, "step": 32021 }, { "epoch": 0.978069639584606, "grad_norm": 0.5480057001113892, "learning_rate": 5.931021540598603e-08, "loss": 4.1735, "step": 32022 }, { "epoch": 0.9781001832620647, "grad_norm": 0.5392062067985535, "learning_rate": 5.914518606854602e-08, "loss": 4.1801, "step": 32023 }, { "epoch": 0.9781307269395235, "grad_norm": 0.5468050241470337, "learning_rate": 5.898038637437986e-08, "loss": 4.2055, "step": 32024 }, { "epoch": 0.9781612706169823, "grad_norm": 0.5548871755599976, "learning_rate": 5.881581632500577e-08, "loss": 4.2416, "step": 32025 }, { "epoch": 0.978191814294441, "grad_norm": 0.5398991703987122, "learning_rate": 5.8651475921936424e-08, "loss": 4.2573, "step": 32026 }, { "epoch": 0.9782223579718998, "grad_norm": 0.5384154915809631, "learning_rate": 5.848736516668452e-08, "loss": 4.1679, "step": 32027 }, { "epoch": 0.9782529016493586, "grad_norm": 0.5435892939567566, "learning_rate": 5.832348406076549e-08, "loss": 4.249, "step": 32028 }, { "epoch": 0.9782834453268173, "grad_norm": 0.5448693037033081, "learning_rate": 5.815983260568647e-08, "loss": 4.1775, "step": 32029 }, { "epoch": 0.9783139890042761, "grad_norm": 0.5445963144302368, "learning_rate": 5.7996410802951814e-08, "loss": 4.2799, "step": 32030 }, { "epoch": 0.9783445326817349, "grad_norm": 0.5340720415115356, "learning_rate": 5.7833218654068653e-08, "loss": 4.2218, "step": 32031 }, { "epoch": 0.9783750763591936, "grad_norm": 0.5461506247520447, "learning_rate": 5.767025616054134e-08, "loss": 4.2332, "step": 32032 }, { "epoch": 0.9784056200366524, "grad_norm": 0.5357884168624878, "learning_rate": 5.7507523323865884e-08, "loss": 4.2535, "step": 32033 }, { "epoch": 0.9784361637141111, "grad_norm": 0.5507866144180298, "learning_rate": 5.734502014554388e-08, "loss": 4.2035, "step": 32034 }, { "epoch": 0.9784667073915699, "grad_norm": 0.5544690489768982, "learning_rate": 5.718274662706857e-08, "loss": 4.2965, "step": 32035 }, { "epoch": 0.9784972510690287, "grad_norm": 0.5503145456314087, "learning_rate": 5.7020702769935984e-08, "loss": 4.2515, "step": 32036 }, { "epoch": 0.9785277947464874, "grad_norm": 0.5407360196113586, "learning_rate": 5.6858888575639366e-08, "loss": 4.2402, "step": 32037 }, { "epoch": 0.9785583384239462, "grad_norm": 0.5301306843757629, "learning_rate": 5.6697304045669197e-08, "loss": 4.1859, "step": 32038 }, { "epoch": 0.978588882101405, "grad_norm": 0.5435380935668945, "learning_rate": 5.653594918150762e-08, "loss": 4.205, "step": 32039 }, { "epoch": 0.9786194257788637, "grad_norm": 0.5426672697067261, "learning_rate": 5.637482398464788e-08, "loss": 4.2937, "step": 32040 }, { "epoch": 0.9786499694563225, "grad_norm": 0.5485815405845642, "learning_rate": 5.6213928456569367e-08, "loss": 4.2815, "step": 32041 }, { "epoch": 0.9786805131337813, "grad_norm": 0.5568462610244751, "learning_rate": 5.6053262598751434e-08, "loss": 4.3053, "step": 32042 }, { "epoch": 0.97871105681124, "grad_norm": 0.5433337092399597, "learning_rate": 5.589282641267901e-08, "loss": 4.2297, "step": 32043 }, { "epoch": 0.9787416004886988, "grad_norm": 0.5429636240005493, "learning_rate": 5.5732619899823145e-08, "loss": 4.2336, "step": 32044 }, { "epoch": 0.9787721441661577, "grad_norm": 0.5348478555679321, "learning_rate": 5.557264306166598e-08, "loss": 4.2015, "step": 32045 }, { "epoch": 0.9788026878436163, "grad_norm": 0.5445052981376648, "learning_rate": 5.5412895899673025e-08, "loss": 4.2586, "step": 32046 }, { "epoch": 0.9788332315210752, "grad_norm": 0.5424984693527222, "learning_rate": 5.5253378415320854e-08, "loss": 4.2391, "step": 32047 }, { "epoch": 0.978863775198534, "grad_norm": 0.5401051640510559, "learning_rate": 5.5094090610074976e-08, "loss": 4.2051, "step": 32048 }, { "epoch": 0.9788943188759927, "grad_norm": 0.5308282971382141, "learning_rate": 5.493503248540366e-08, "loss": 4.2029, "step": 32049 }, { "epoch": 0.9789248625534515, "grad_norm": 0.5541139245033264, "learning_rate": 5.47762040427724e-08, "loss": 4.3366, "step": 32050 }, { "epoch": 0.9789554062309102, "grad_norm": 0.5455759167671204, "learning_rate": 5.461760528364113e-08, "loss": 4.1596, "step": 32051 }, { "epoch": 0.978985949908369, "grad_norm": 0.5461428761482239, "learning_rate": 5.44592362094698e-08, "loss": 4.2456, "step": 32052 }, { "epoch": 0.9790164935858278, "grad_norm": 0.5412176251411438, "learning_rate": 5.430109682172113e-08, "loss": 4.291, "step": 32053 }, { "epoch": 0.9790470372632865, "grad_norm": 0.5514407157897949, "learning_rate": 5.414318712184674e-08, "loss": 4.2324, "step": 32054 }, { "epoch": 0.9790775809407453, "grad_norm": 0.5357719659805298, "learning_rate": 5.398550711130101e-08, "loss": 4.2502, "step": 32055 }, { "epoch": 0.9791081246182041, "grad_norm": 0.5546352863311768, "learning_rate": 5.3828056791535575e-08, "loss": 4.2669, "step": 32056 }, { "epoch": 0.9791386682956628, "grad_norm": 0.5375304818153381, "learning_rate": 5.3670836164002035e-08, "loss": 4.2216, "step": 32057 }, { "epoch": 0.9791692119731216, "grad_norm": 0.5358065962791443, "learning_rate": 5.351384523014924e-08, "loss": 4.1993, "step": 32058 }, { "epoch": 0.9791997556505804, "grad_norm": 0.5435459613800049, "learning_rate": 5.3357083991420476e-08, "loss": 4.262, "step": 32059 }, { "epoch": 0.9792302993280391, "grad_norm": 0.5372471809387207, "learning_rate": 5.320055244925626e-08, "loss": 4.2441, "step": 32060 }, { "epoch": 0.9792608430054979, "grad_norm": 0.5332433581352234, "learning_rate": 5.304425060510265e-08, "loss": 4.254, "step": 32061 }, { "epoch": 0.9792913866829567, "grad_norm": 0.5401431322097778, "learning_rate": 5.28881784603974e-08, "loss": 4.2365, "step": 32062 }, { "epoch": 0.9793219303604154, "grad_norm": 0.5360552072525024, "learning_rate": 5.2732336016578235e-08, "loss": 4.2224, "step": 32063 }, { "epoch": 0.9793524740378742, "grad_norm": 0.5397379398345947, "learning_rate": 5.257672327507735e-08, "loss": 4.174, "step": 32064 }, { "epoch": 0.9793830177153329, "grad_norm": 0.540459394454956, "learning_rate": 5.242134023733247e-08, "loss": 4.3185, "step": 32065 }, { "epoch": 0.9794135613927917, "grad_norm": 0.5451126098632812, "learning_rate": 5.226618690476748e-08, "loss": 4.3413, "step": 32066 }, { "epoch": 0.9794441050702505, "grad_norm": 0.5467239618301392, "learning_rate": 5.211126327881455e-08, "loss": 4.3096, "step": 32067 }, { "epoch": 0.9794746487477092, "grad_norm": 0.5494194626808167, "learning_rate": 5.1956569360903095e-08, "loss": 4.2398, "step": 32068 }, { "epoch": 0.979505192425168, "grad_norm": 0.5379214286804199, "learning_rate": 5.180210515245143e-08, "loss": 4.1538, "step": 32069 }, { "epoch": 0.9795357361026268, "grad_norm": 0.5511438846588135, "learning_rate": 5.164787065488619e-08, "loss": 4.3314, "step": 32070 }, { "epoch": 0.9795662797800855, "grad_norm": 0.531179666519165, "learning_rate": 5.1493865869625676e-08, "loss": 4.2664, "step": 32071 }, { "epoch": 0.9795968234575443, "grad_norm": 0.542750895023346, "learning_rate": 5.134009079808821e-08, "loss": 4.2382, "step": 32072 }, { "epoch": 0.9796273671350031, "grad_norm": 0.533886730670929, "learning_rate": 5.1186545441692104e-08, "loss": 4.2097, "step": 32073 }, { "epoch": 0.9796579108124618, "grad_norm": 0.548926591873169, "learning_rate": 5.103322980184733e-08, "loss": 4.3186, "step": 32074 }, { "epoch": 0.9796884544899206, "grad_norm": 0.5348851084709167, "learning_rate": 5.0880143879966646e-08, "loss": 4.1842, "step": 32075 }, { "epoch": 0.9797189981673794, "grad_norm": 0.54319828748703, "learning_rate": 5.0727287677460045e-08, "loss": 4.2886, "step": 32076 }, { "epoch": 0.9797495418448381, "grad_norm": 0.5463808178901672, "learning_rate": 5.057466119573473e-08, "loss": 4.2724, "step": 32077 }, { "epoch": 0.9797800855222969, "grad_norm": 0.5410523414611816, "learning_rate": 5.0422264436197905e-08, "loss": 4.2368, "step": 32078 }, { "epoch": 0.9798106291997557, "grad_norm": 0.5424789786338806, "learning_rate": 5.027009740024846e-08, "loss": 4.3175, "step": 32079 }, { "epoch": 0.9798411728772144, "grad_norm": 0.5496876239776611, "learning_rate": 5.0118160089293595e-08, "loss": 4.1907, "step": 32080 }, { "epoch": 0.9798717165546732, "grad_norm": 0.5404130816459656, "learning_rate": 4.996645250472665e-08, "loss": 4.1796, "step": 32081 }, { "epoch": 0.9799022602321319, "grad_norm": 0.5433064103126526, "learning_rate": 4.981497464794649e-08, "loss": 4.3131, "step": 32082 }, { "epoch": 0.9799328039095907, "grad_norm": 0.5345633625984192, "learning_rate": 4.9663726520349226e-08, "loss": 4.2468, "step": 32083 }, { "epoch": 0.9799633475870495, "grad_norm": 0.5466643571853638, "learning_rate": 4.951270812332265e-08, "loss": 4.3193, "step": 32084 }, { "epoch": 0.9799938912645082, "grad_norm": 0.5447745323181152, "learning_rate": 4.936191945826563e-08, "loss": 4.1482, "step": 32085 }, { "epoch": 0.980024434941967, "grad_norm": 0.5427419543266296, "learning_rate": 4.9211360526557613e-08, "loss": 4.2183, "step": 32086 }, { "epoch": 0.9800549786194258, "grad_norm": 0.541888415813446, "learning_rate": 4.9061031329591946e-08, "loss": 4.2848, "step": 32087 }, { "epoch": 0.9800855222968845, "grad_norm": 0.5408840775489807, "learning_rate": 4.891093186875084e-08, "loss": 4.2284, "step": 32088 }, { "epoch": 0.9801160659743433, "grad_norm": 0.5431108474731445, "learning_rate": 4.876106214541098e-08, "loss": 4.2329, "step": 32089 }, { "epoch": 0.9801466096518021, "grad_norm": 0.543495774269104, "learning_rate": 4.861142216096015e-08, "loss": 4.3167, "step": 32090 }, { "epoch": 0.9801771533292608, "grad_norm": 0.5349050760269165, "learning_rate": 4.846201191677224e-08, "loss": 4.2332, "step": 32091 }, { "epoch": 0.9802076970067196, "grad_norm": 0.541678786277771, "learning_rate": 4.831283141422393e-08, "loss": 4.1927, "step": 32092 }, { "epoch": 0.9802382406841784, "grad_norm": 0.5579763054847717, "learning_rate": 4.816388065468636e-08, "loss": 4.2343, "step": 32093 }, { "epoch": 0.9802687843616371, "grad_norm": 0.551734983921051, "learning_rate": 4.8015159639533405e-08, "loss": 4.229, "step": 32094 }, { "epoch": 0.9802993280390959, "grad_norm": 0.5425043702125549, "learning_rate": 4.786666837013343e-08, "loss": 4.2708, "step": 32095 }, { "epoch": 0.9803298717165547, "grad_norm": 0.5344297885894775, "learning_rate": 4.771840684785478e-08, "loss": 4.2591, "step": 32096 }, { "epoch": 0.9803604153940134, "grad_norm": 0.5507059097290039, "learning_rate": 4.757037507406303e-08, "loss": 4.2293, "step": 32097 }, { "epoch": 0.9803909590714722, "grad_norm": 0.540465235710144, "learning_rate": 4.742257305011821e-08, "loss": 4.2428, "step": 32098 }, { "epoch": 0.9804215027489309, "grad_norm": 0.5407493114471436, "learning_rate": 4.727500077738589e-08, "loss": 4.2302, "step": 32099 }, { "epoch": 0.9804520464263897, "grad_norm": 0.5401201248168945, "learning_rate": 4.712765825722054e-08, "loss": 4.2491, "step": 32100 }, { "epoch": 0.9804825901038485, "grad_norm": 0.5441713333129883, "learning_rate": 4.698054549097941e-08, "loss": 4.3234, "step": 32101 }, { "epoch": 0.9805131337813072, "grad_norm": 0.5390957593917847, "learning_rate": 4.6833662480019744e-08, "loss": 4.225, "step": 32102 }, { "epoch": 0.980543677458766, "grad_norm": 0.5489734411239624, "learning_rate": 4.668700922569047e-08, "loss": 4.1827, "step": 32103 }, { "epoch": 0.9805742211362248, "grad_norm": 0.539317786693573, "learning_rate": 4.654058572934328e-08, "loss": 4.3129, "step": 32104 }, { "epoch": 0.9806047648136835, "grad_norm": 0.5358920693397522, "learning_rate": 4.639439199232709e-08, "loss": 4.2372, "step": 32105 }, { "epoch": 0.9806353084911423, "grad_norm": 0.5443054437637329, "learning_rate": 4.6248428015988054e-08, "loss": 4.2391, "step": 32106 }, { "epoch": 0.9806658521686011, "grad_norm": 0.5500613451004028, "learning_rate": 4.610269380167231e-08, "loss": 4.2905, "step": 32107 }, { "epoch": 0.9806963958460598, "grad_norm": 0.5560263991355896, "learning_rate": 4.5957189350714915e-08, "loss": 4.3374, "step": 32108 }, { "epoch": 0.9807269395235186, "grad_norm": 0.5371687412261963, "learning_rate": 4.5811914664461996e-08, "loss": 4.2449, "step": 32109 }, { "epoch": 0.9807574832009774, "grad_norm": 0.5384222865104675, "learning_rate": 4.5666869744248605e-08, "loss": 4.2394, "step": 32110 }, { "epoch": 0.9807880268784361, "grad_norm": 0.545928418636322, "learning_rate": 4.552205459140979e-08, "loss": 4.2157, "step": 32111 }, { "epoch": 0.9808185705558949, "grad_norm": 0.5340307354927063, "learning_rate": 4.5377469207280586e-08, "loss": 4.228, "step": 32112 }, { "epoch": 0.9808491142333537, "grad_norm": 0.5422952175140381, "learning_rate": 4.523311359319049e-08, "loss": 4.3072, "step": 32113 }, { "epoch": 0.9808796579108124, "grad_norm": 0.5399478077888489, "learning_rate": 4.508898775047177e-08, "loss": 4.2559, "step": 32114 }, { "epoch": 0.9809102015882712, "grad_norm": 0.5418354868888855, "learning_rate": 4.4945091680448356e-08, "loss": 4.2977, "step": 32115 }, { "epoch": 0.9809407452657299, "grad_norm": 0.5358706712722778, "learning_rate": 4.4801425384444205e-08, "loss": 4.2216, "step": 32116 }, { "epoch": 0.9809712889431887, "grad_norm": 0.5415072441101074, "learning_rate": 4.4657988863786026e-08, "loss": 4.2282, "step": 32117 }, { "epoch": 0.9810018326206476, "grad_norm": 0.5377028584480286, "learning_rate": 4.4514782119792206e-08, "loss": 4.2941, "step": 32118 }, { "epoch": 0.9810323762981062, "grad_norm": 0.5544689893722534, "learning_rate": 4.4371805153781144e-08, "loss": 4.1249, "step": 32119 }, { "epoch": 0.981062919975565, "grad_norm": 0.5373596549034119, "learning_rate": 4.422905796706844e-08, "loss": 4.1947, "step": 32120 }, { "epoch": 0.9810934636530239, "grad_norm": 0.5475280284881592, "learning_rate": 4.40865405609725e-08, "loss": 4.2893, "step": 32121 }, { "epoch": 0.9811240073304826, "grad_norm": 0.5376316905021667, "learning_rate": 4.39442529368006e-08, "loss": 4.2665, "step": 32122 }, { "epoch": 0.9811545510079414, "grad_norm": 0.5365267992019653, "learning_rate": 4.380219509586836e-08, "loss": 4.2835, "step": 32123 }, { "epoch": 0.9811850946854002, "grad_norm": 0.5490176677703857, "learning_rate": 4.3660367039477515e-08, "loss": 4.3021, "step": 32124 }, { "epoch": 0.9812156383628589, "grad_norm": 0.5416646003723145, "learning_rate": 4.3518768768938124e-08, "loss": 4.2621, "step": 32125 }, { "epoch": 0.9812461820403177, "grad_norm": 0.5422686338424683, "learning_rate": 4.3377400285551926e-08, "loss": 4.2169, "step": 32126 }, { "epoch": 0.9812767257177765, "grad_norm": 0.5470463037490845, "learning_rate": 4.323626159062067e-08, "loss": 4.238, "step": 32127 }, { "epoch": 0.9813072693952352, "grad_norm": 0.5454206466674805, "learning_rate": 4.309535268544607e-08, "loss": 4.2173, "step": 32128 }, { "epoch": 0.981337813072694, "grad_norm": 0.5453397631645203, "learning_rate": 4.295467357132432e-08, "loss": 4.3083, "step": 32129 }, { "epoch": 0.9813683567501528, "grad_norm": 0.5575116872787476, "learning_rate": 4.281422424955162e-08, "loss": 4.2662, "step": 32130 }, { "epoch": 0.9813989004276115, "grad_norm": 0.5507981181144714, "learning_rate": 4.267400472141858e-08, "loss": 4.2621, "step": 32131 }, { "epoch": 0.9814294441050703, "grad_norm": 0.5418187379837036, "learning_rate": 4.2534014988215856e-08, "loss": 4.2998, "step": 32132 }, { "epoch": 0.981459987782529, "grad_norm": 0.5372570157051086, "learning_rate": 4.2394255051236845e-08, "loss": 4.2752, "step": 32133 }, { "epoch": 0.9814905314599878, "grad_norm": 0.5376075506210327, "learning_rate": 4.225472491176663e-08, "loss": 4.3191, "step": 32134 }, { "epoch": 0.9815210751374466, "grad_norm": 0.5460808873176575, "learning_rate": 4.2115424571087526e-08, "loss": 4.2378, "step": 32135 }, { "epoch": 0.9815516188149053, "grad_norm": 0.5424284338951111, "learning_rate": 4.197635403048461e-08, "loss": 4.2473, "step": 32136 }, { "epoch": 0.9815821624923641, "grad_norm": 0.5373291969299316, "learning_rate": 4.1837513291234644e-08, "loss": 4.2335, "step": 32137 }, { "epoch": 0.9816127061698229, "grad_norm": 0.547227680683136, "learning_rate": 4.16989023546227e-08, "loss": 4.1887, "step": 32138 }, { "epoch": 0.9816432498472816, "grad_norm": 0.5539701581001282, "learning_rate": 4.156052122192e-08, "loss": 4.1771, "step": 32139 }, { "epoch": 0.9816737935247404, "grad_norm": 0.530977725982666, "learning_rate": 4.142236989440051e-08, "loss": 4.2262, "step": 32140 }, { "epoch": 0.9817043372021992, "grad_norm": 0.5368709564208984, "learning_rate": 4.1284448373341e-08, "loss": 4.2594, "step": 32141 }, { "epoch": 0.9817348808796579, "grad_norm": 0.5489108562469482, "learning_rate": 4.114675666000434e-08, "loss": 4.2089, "step": 32142 }, { "epoch": 0.9817654245571167, "grad_norm": 0.5401860475540161, "learning_rate": 4.1009294755664504e-08, "loss": 4.1823, "step": 32143 }, { "epoch": 0.9817959682345755, "grad_norm": 0.5342718958854675, "learning_rate": 4.0872062661584384e-08, "loss": 4.2402, "step": 32144 }, { "epoch": 0.9818265119120342, "grad_norm": 0.5433944463729858, "learning_rate": 4.0735060379026855e-08, "loss": 4.2657, "step": 32145 }, { "epoch": 0.981857055589493, "grad_norm": 0.5401697158813477, "learning_rate": 4.0598287909254796e-08, "loss": 4.1875, "step": 32146 }, { "epoch": 0.9818875992669518, "grad_norm": 0.5400201082229614, "learning_rate": 4.046174525352831e-08, "loss": 4.24, "step": 32147 }, { "epoch": 0.9819181429444105, "grad_norm": 0.5394032597541809, "learning_rate": 4.0325432413101936e-08, "loss": 4.2735, "step": 32148 }, { "epoch": 0.9819486866218693, "grad_norm": 0.5404385924339294, "learning_rate": 4.018934938923302e-08, "loss": 4.2314, "step": 32149 }, { "epoch": 0.981979230299328, "grad_norm": 0.5422081351280212, "learning_rate": 4.005349618317333e-08, "loss": 4.1975, "step": 32150 }, { "epoch": 0.9820097739767868, "grad_norm": 0.5430604219436646, "learning_rate": 3.9917872796174647e-08, "loss": 4.2818, "step": 32151 }, { "epoch": 0.9820403176542456, "grad_norm": 0.5432683229446411, "learning_rate": 3.978247922948597e-08, "loss": 4.278, "step": 32152 }, { "epoch": 0.9820708613317043, "grad_norm": 0.5440675616264343, "learning_rate": 3.9647315484350746e-08, "loss": 4.2765, "step": 32153 }, { "epoch": 0.9821014050091631, "grad_norm": 0.549324095249176, "learning_rate": 3.9512381562017976e-08, "loss": 4.2566, "step": 32154 }, { "epoch": 0.9821319486866219, "grad_norm": 0.5642391443252563, "learning_rate": 3.9377677463728334e-08, "loss": 4.2774, "step": 32155 }, { "epoch": 0.9821624923640806, "grad_norm": 0.5617099404335022, "learning_rate": 3.92432031907225e-08, "loss": 4.3118, "step": 32156 }, { "epoch": 0.9821930360415394, "grad_norm": 0.5429649353027344, "learning_rate": 3.910895874423559e-08, "loss": 4.2321, "step": 32157 }, { "epoch": 0.9822235797189982, "grad_norm": 0.5407713651657104, "learning_rate": 3.8974944125508285e-08, "loss": 4.2173, "step": 32158 }, { "epoch": 0.9822541233964569, "grad_norm": 0.544147789478302, "learning_rate": 3.8841159335772924e-08, "loss": 4.1948, "step": 32159 }, { "epoch": 0.9822846670739157, "grad_norm": 0.543140172958374, "learning_rate": 3.870760437625909e-08, "loss": 4.227, "step": 32160 }, { "epoch": 0.9823152107513745, "grad_norm": 0.5363914370536804, "learning_rate": 3.857427924819912e-08, "loss": 4.2318, "step": 32161 }, { "epoch": 0.9823457544288332, "grad_norm": 0.5436073541641235, "learning_rate": 3.844118395281704e-08, "loss": 4.304, "step": 32162 }, { "epoch": 0.982376298106292, "grad_norm": 0.5436059236526489, "learning_rate": 3.8308318491345195e-08, "loss": 4.2249, "step": 32163 }, { "epoch": 0.9824068417837508, "grad_norm": 0.5405842065811157, "learning_rate": 3.8175682864999285e-08, "loss": 4.2798, "step": 32164 }, { "epoch": 0.9824373854612095, "grad_norm": 0.5591988563537598, "learning_rate": 3.80432770750061e-08, "loss": 4.2148, "step": 32165 }, { "epoch": 0.9824679291386683, "grad_norm": 0.541042149066925, "learning_rate": 3.791110112258134e-08, "loss": 4.28, "step": 32166 }, { "epoch": 0.982498472816127, "grad_norm": 0.5619746446609497, "learning_rate": 3.777915500894347e-08, "loss": 4.2146, "step": 32167 }, { "epoch": 0.9825290164935858, "grad_norm": 0.5356637835502625, "learning_rate": 3.7647438735308183e-08, "loss": 4.147, "step": 32168 }, { "epoch": 0.9825595601710446, "grad_norm": 0.5458183884620667, "learning_rate": 3.751595230288563e-08, "loss": 4.2073, "step": 32169 }, { "epoch": 0.9825901038485033, "grad_norm": 0.5397166013717651, "learning_rate": 3.7384695712888716e-08, "loss": 4.264, "step": 32170 }, { "epoch": 0.9826206475259621, "grad_norm": 0.5546014308929443, "learning_rate": 3.72536689665276e-08, "loss": 4.279, "step": 32171 }, { "epoch": 0.9826511912034209, "grad_norm": 0.5454757809638977, "learning_rate": 3.712287206500409e-08, "loss": 4.2541, "step": 32172 }, { "epoch": 0.9826817348808796, "grad_norm": 0.5451055765151978, "learning_rate": 3.699230500952555e-08, "loss": 4.1504, "step": 32173 }, { "epoch": 0.9827122785583384, "grad_norm": 0.5464561581611633, "learning_rate": 3.6861967801293806e-08, "loss": 4.1936, "step": 32174 }, { "epoch": 0.9827428222357972, "grad_norm": 0.5344406962394714, "learning_rate": 3.673186044150789e-08, "loss": 4.2065, "step": 32175 }, { "epoch": 0.9827733659132559, "grad_norm": 0.5420566201210022, "learning_rate": 3.660198293136685e-08, "loss": 4.2798, "step": 32176 }, { "epoch": 0.9828039095907147, "grad_norm": 0.5417743921279907, "learning_rate": 3.647233527206695e-08, "loss": 4.24, "step": 32177 }, { "epoch": 0.9828344532681735, "grad_norm": 0.5338996052742004, "learning_rate": 3.6342917464801673e-08, "loss": 4.2158, "step": 32178 }, { "epoch": 0.9828649969456322, "grad_norm": 0.539648175239563, "learning_rate": 3.621372951076174e-08, "loss": 4.2106, "step": 32179 }, { "epoch": 0.982895540623091, "grad_norm": 0.5412174463272095, "learning_rate": 3.608477141113509e-08, "loss": 4.2932, "step": 32180 }, { "epoch": 0.9829260843005498, "grad_norm": 0.5445961356163025, "learning_rate": 3.595604316711243e-08, "loss": 4.319, "step": 32181 }, { "epoch": 0.9829566279780085, "grad_norm": 0.5387054681777954, "learning_rate": 3.582754477987893e-08, "loss": 4.2721, "step": 32182 }, { "epoch": 0.9829871716554673, "grad_norm": 0.5403825044631958, "learning_rate": 3.5699276250616975e-08, "loss": 4.1489, "step": 32183 }, { "epoch": 0.983017715332926, "grad_norm": 0.53786700963974, "learning_rate": 3.5571237580506176e-08, "loss": 4.2749, "step": 32184 }, { "epoch": 0.9830482590103848, "grad_norm": 0.544837474822998, "learning_rate": 3.544342877072615e-08, "loss": 4.1809, "step": 32185 }, { "epoch": 0.9830788026878436, "grad_norm": 0.5479652881622314, "learning_rate": 3.531584982245373e-08, "loss": 4.2838, "step": 32186 }, { "epoch": 0.9831093463653023, "grad_norm": 0.5404512286186218, "learning_rate": 3.518850073686297e-08, "loss": 4.2253, "step": 32187 }, { "epoch": 0.9831398900427611, "grad_norm": 0.5514581203460693, "learning_rate": 3.506138151512794e-08, "loss": 4.2124, "step": 32188 }, { "epoch": 0.98317043372022, "grad_norm": 0.545109212398529, "learning_rate": 3.493449215841993e-08, "loss": 4.222, "step": 32189 }, { "epoch": 0.9832009773976786, "grad_norm": 0.5470882058143616, "learning_rate": 3.480783266790466e-08, "loss": 4.3042, "step": 32190 }, { "epoch": 0.9832315210751374, "grad_norm": 0.5386310815811157, "learning_rate": 3.468140304475065e-08, "loss": 4.2315, "step": 32191 }, { "epoch": 0.9832620647525963, "grad_norm": 0.5349675416946411, "learning_rate": 3.455520329011808e-08, "loss": 4.1865, "step": 32192 }, { "epoch": 0.983292608430055, "grad_norm": 0.5458489060401917, "learning_rate": 3.442923340517545e-08, "loss": 4.2858, "step": 32193 }, { "epoch": 0.9833231521075138, "grad_norm": 0.5458115935325623, "learning_rate": 3.4303493391074636e-08, "loss": 4.1122, "step": 32194 }, { "epoch": 0.9833536957849726, "grad_norm": 0.5405676364898682, "learning_rate": 3.417798324898136e-08, "loss": 4.2671, "step": 32195 }, { "epoch": 0.9833842394624313, "grad_norm": 0.5336143374443054, "learning_rate": 3.4052702980044706e-08, "loss": 4.2783, "step": 32196 }, { "epoch": 0.9834147831398901, "grad_norm": 0.5563355684280396, "learning_rate": 3.3927652585422076e-08, "loss": 4.2248, "step": 32197 }, { "epoch": 0.9834453268173489, "grad_norm": 0.5472139716148376, "learning_rate": 3.3802832066265334e-08, "loss": 4.2307, "step": 32198 }, { "epoch": 0.9834758704948076, "grad_norm": 0.5437528491020203, "learning_rate": 3.367824142372078e-08, "loss": 4.2496, "step": 32199 }, { "epoch": 0.9835064141722664, "grad_norm": 0.5509291291236877, "learning_rate": 3.35538806589375e-08, "loss": 4.2974, "step": 32200 }, { "epoch": 0.9835369578497251, "grad_norm": 0.5505026578903198, "learning_rate": 3.342974977306179e-08, "loss": 4.3067, "step": 32201 }, { "epoch": 0.9835675015271839, "grad_norm": 0.5385098457336426, "learning_rate": 3.330584876723164e-08, "loss": 4.2, "step": 32202 }, { "epoch": 0.9835980452046427, "grad_norm": 0.5482808351516724, "learning_rate": 3.3182177642593346e-08, "loss": 4.1621, "step": 32203 }, { "epoch": 0.9836285888821014, "grad_norm": 0.5449146628379822, "learning_rate": 3.305873640028212e-08, "loss": 4.1395, "step": 32204 }, { "epoch": 0.9836591325595602, "grad_norm": 0.5398402810096741, "learning_rate": 3.293552504143871e-08, "loss": 4.2439, "step": 32205 }, { "epoch": 0.983689676237019, "grad_norm": 0.5415880680084229, "learning_rate": 3.281254356718999e-08, "loss": 4.2076, "step": 32206 }, { "epoch": 0.9837202199144777, "grad_norm": 0.5410006642341614, "learning_rate": 3.268979197867672e-08, "loss": 4.221, "step": 32207 }, { "epoch": 0.9837507635919365, "grad_norm": 0.5391185879707336, "learning_rate": 3.2567270277023e-08, "loss": 4.2669, "step": 32208 }, { "epoch": 0.9837813072693953, "grad_norm": 0.5394450426101685, "learning_rate": 3.244497846336125e-08, "loss": 4.2105, "step": 32209 }, { "epoch": 0.983811850946854, "grad_norm": 0.5468024611473083, "learning_rate": 3.232291653881558e-08, "loss": 4.3426, "step": 32210 }, { "epoch": 0.9838423946243128, "grad_norm": 0.5396625399589539, "learning_rate": 3.2201084504510094e-08, "loss": 4.3062, "step": 32211 }, { "epoch": 0.9838729383017716, "grad_norm": 0.5418605804443359, "learning_rate": 3.2079482361566106e-08, "loss": 4.2534, "step": 32212 }, { "epoch": 0.9839034819792303, "grad_norm": 0.5477207899093628, "learning_rate": 3.195811011110217e-08, "loss": 4.3081, "step": 32213 }, { "epoch": 0.9839340256566891, "grad_norm": 0.5438969731330872, "learning_rate": 3.183696775423961e-08, "loss": 4.223, "step": 32214 }, { "epoch": 0.9839645693341478, "grad_norm": 0.5438283681869507, "learning_rate": 3.1716055292088656e-08, "loss": 4.1743, "step": 32215 }, { "epoch": 0.9839951130116066, "grad_norm": 0.5445919036865234, "learning_rate": 3.1595372725767845e-08, "loss": 4.2177, "step": 32216 }, { "epoch": 0.9840256566890654, "grad_norm": 0.5438566207885742, "learning_rate": 3.147492005638464e-08, "loss": 4.2069, "step": 32217 }, { "epoch": 0.9840562003665241, "grad_norm": 0.5440845489501953, "learning_rate": 3.135469728504925e-08, "loss": 4.2919, "step": 32218 }, { "epoch": 0.9840867440439829, "grad_norm": 0.5506601333618164, "learning_rate": 3.123470441286913e-08, "loss": 4.2588, "step": 32219 }, { "epoch": 0.9841172877214417, "grad_norm": 0.5453419089317322, "learning_rate": 3.111494144094895e-08, "loss": 4.2234, "step": 32220 }, { "epoch": 0.9841478313989004, "grad_norm": 0.552818238735199, "learning_rate": 3.099540837039061e-08, "loss": 4.3024, "step": 32221 }, { "epoch": 0.9841783750763592, "grad_norm": 0.5403199195861816, "learning_rate": 3.0876105202296e-08, "loss": 4.2418, "step": 32222 }, { "epoch": 0.984208918753818, "grad_norm": 0.5350632071495056, "learning_rate": 3.0757031937761474e-08, "loss": 4.2098, "step": 32223 }, { "epoch": 0.9842394624312767, "grad_norm": 0.5364093780517578, "learning_rate": 3.063818857788614e-08, "loss": 4.0855, "step": 32224 }, { "epoch": 0.9842700061087355, "grad_norm": 0.5409694314002991, "learning_rate": 3.0519575123763575e-08, "loss": 4.2237, "step": 32225 }, { "epoch": 0.9843005497861943, "grad_norm": 0.5384907126426697, "learning_rate": 3.0401191576484576e-08, "loss": 4.247, "step": 32226 }, { "epoch": 0.984331093463653, "grad_norm": 0.5417336225509644, "learning_rate": 3.028303793713994e-08, "loss": 4.22, "step": 32227 }, { "epoch": 0.9843616371411118, "grad_norm": 0.5405024290084839, "learning_rate": 3.016511420681767e-08, "loss": 4.2021, "step": 32228 }, { "epoch": 0.9843921808185706, "grad_norm": 0.5366271734237671, "learning_rate": 3.004742038660302e-08, "loss": 4.2488, "step": 32229 }, { "epoch": 0.9844227244960293, "grad_norm": 0.5468950271606445, "learning_rate": 2.992995647758123e-08, "loss": 4.2703, "step": 32230 }, { "epoch": 0.9844532681734881, "grad_norm": 0.5556163787841797, "learning_rate": 2.9812722480832e-08, "loss": 4.2498, "step": 32231 }, { "epoch": 0.9844838118509468, "grad_norm": 0.5389062762260437, "learning_rate": 2.9695718397435012e-08, "loss": 4.1704, "step": 32232 }, { "epoch": 0.9845143555284056, "grad_norm": 0.5374857187271118, "learning_rate": 2.9578944228469964e-08, "loss": 4.2984, "step": 32233 }, { "epoch": 0.9845448992058644, "grad_norm": 0.5418519973754883, "learning_rate": 2.9462399975008215e-08, "loss": 4.2047, "step": 32234 }, { "epoch": 0.9845754428833231, "grad_norm": 0.5374511480331421, "learning_rate": 2.9346085638123912e-08, "loss": 4.2145, "step": 32235 }, { "epoch": 0.9846059865607819, "grad_norm": 0.5425575971603394, "learning_rate": 2.9230001218888413e-08, "loss": 4.249, "step": 32236 }, { "epoch": 0.9846365302382407, "grad_norm": 0.5361958742141724, "learning_rate": 2.911414671837309e-08, "loss": 4.1577, "step": 32237 }, { "epoch": 0.9846670739156994, "grad_norm": 0.5407875776290894, "learning_rate": 2.8998522137643758e-08, "loss": 4.223, "step": 32238 }, { "epoch": 0.9846976175931582, "grad_norm": 0.5405350923538208, "learning_rate": 2.8883127477760674e-08, "loss": 4.2703, "step": 32239 }, { "epoch": 0.984728161270617, "grad_norm": 0.5500454902648926, "learning_rate": 2.8767962739789657e-08, "loss": 4.3005, "step": 32240 }, { "epoch": 0.9847587049480757, "grad_norm": 0.5438408851623535, "learning_rate": 2.8653027924793742e-08, "loss": 4.3073, "step": 32241 }, { "epoch": 0.9847892486255345, "grad_norm": 0.5392075777053833, "learning_rate": 2.8538323033824865e-08, "loss": 4.2156, "step": 32242 }, { "epoch": 0.9848197923029933, "grad_norm": 0.5356596112251282, "learning_rate": 2.842384806794607e-08, "loss": 4.0527, "step": 32243 }, { "epoch": 0.984850335980452, "grad_norm": 0.5330551266670227, "learning_rate": 2.830960302820651e-08, "loss": 4.2439, "step": 32244 }, { "epoch": 0.9848808796579108, "grad_norm": 0.540677547454834, "learning_rate": 2.8195587915658128e-08, "loss": 4.2032, "step": 32245 }, { "epoch": 0.9849114233353696, "grad_norm": 0.5302192568778992, "learning_rate": 2.8081802731355632e-08, "loss": 4.1573, "step": 32246 }, { "epoch": 0.9849419670128283, "grad_norm": 0.5471441745758057, "learning_rate": 2.796824747633986e-08, "loss": 4.3595, "step": 32247 }, { "epoch": 0.9849725106902871, "grad_norm": 0.5422666072845459, "learning_rate": 2.7854922151662743e-08, "loss": 4.201, "step": 32248 }, { "epoch": 0.9850030543677458, "grad_norm": 0.5416178107261658, "learning_rate": 2.7741826758362344e-08, "loss": 4.2851, "step": 32249 }, { "epoch": 0.9850335980452046, "grad_norm": 0.5374509692192078, "learning_rate": 2.7628961297485045e-08, "loss": 4.2803, "step": 32250 }, { "epoch": 0.9850641417226634, "grad_norm": 0.5444687604904175, "learning_rate": 2.7516325770063355e-08, "loss": 4.2009, "step": 32251 }, { "epoch": 0.9850946854001221, "grad_norm": 0.5405475497245789, "learning_rate": 2.7403920177140886e-08, "loss": 4.2475, "step": 32252 }, { "epoch": 0.9851252290775809, "grad_norm": 0.5520322918891907, "learning_rate": 2.7291744519750138e-08, "loss": 4.3203, "step": 32253 }, { "epoch": 0.9851557727550397, "grad_norm": 0.5442022085189819, "learning_rate": 2.7179798798923628e-08, "loss": 4.1715, "step": 32254 }, { "epoch": 0.9851863164324984, "grad_norm": 0.5424264073371887, "learning_rate": 2.7068083015693857e-08, "loss": 4.3047, "step": 32255 }, { "epoch": 0.9852168601099572, "grad_norm": 0.540698766708374, "learning_rate": 2.6956597171087783e-08, "loss": 4.2595, "step": 32256 }, { "epoch": 0.985247403787416, "grad_norm": 0.5447843670845032, "learning_rate": 2.6845341266129585e-08, "loss": 4.1979, "step": 32257 }, { "epoch": 0.9852779474648747, "grad_norm": 0.5425876379013062, "learning_rate": 2.6734315301849e-08, "loss": 4.3507, "step": 32258 }, { "epoch": 0.9853084911423335, "grad_norm": 0.5481268167495728, "learning_rate": 2.662351927926465e-08, "loss": 4.2199, "step": 32259 }, { "epoch": 0.9853390348197923, "grad_norm": 0.547026515007019, "learning_rate": 2.651295319939795e-08, "loss": 4.2704, "step": 32260 }, { "epoch": 0.985369578497251, "grad_norm": 0.5356020927429199, "learning_rate": 2.6402617063264744e-08, "loss": 4.2351, "step": 32261 }, { "epoch": 0.9854001221747098, "grad_norm": 0.5461746454238892, "learning_rate": 2.6292510871883668e-08, "loss": 4.3727, "step": 32262 }, { "epoch": 0.9854306658521687, "grad_norm": 0.5379568338394165, "learning_rate": 2.6182634626270574e-08, "loss": 4.1767, "step": 32263 }, { "epoch": 0.9854612095296273, "grad_norm": 0.5381967425346375, "learning_rate": 2.6072988327430215e-08, "loss": 4.1422, "step": 32264 }, { "epoch": 0.9854917532070862, "grad_norm": 0.5281660556793213, "learning_rate": 2.596357197637844e-08, "loss": 4.2194, "step": 32265 }, { "epoch": 0.9855222968845448, "grad_norm": 0.5387130975723267, "learning_rate": 2.5854385574120012e-08, "loss": 4.2856, "step": 32266 }, { "epoch": 0.9855528405620037, "grad_norm": 0.5333083271980286, "learning_rate": 2.574542912165967e-08, "loss": 4.256, "step": 32267 }, { "epoch": 0.9855833842394625, "grad_norm": 0.5392507314682007, "learning_rate": 2.5636702620002175e-08, "loss": 4.2594, "step": 32268 }, { "epoch": 0.9856139279169212, "grad_norm": 0.5432342290878296, "learning_rate": 2.5528206070149497e-08, "loss": 4.1692, "step": 32269 }, { "epoch": 0.98564447159438, "grad_norm": 0.5458505749702454, "learning_rate": 2.5419939473098066e-08, "loss": 4.2279, "step": 32270 }, { "epoch": 0.9856750152718388, "grad_norm": 0.5461249947547913, "learning_rate": 2.531190282984708e-08, "loss": 4.2324, "step": 32271 }, { "epoch": 0.9857055589492975, "grad_norm": 0.5429444313049316, "learning_rate": 2.520409614138741e-08, "loss": 4.276, "step": 32272 }, { "epoch": 0.9857361026267563, "grad_norm": 0.5416187644004822, "learning_rate": 2.509651940871549e-08, "loss": 4.2316, "step": 32273 }, { "epoch": 0.9857666463042151, "grad_norm": 0.5587183237075806, "learning_rate": 2.4989172632822188e-08, "loss": 4.195, "step": 32274 }, { "epoch": 0.9857971899816738, "grad_norm": 0.5354174375534058, "learning_rate": 2.4882055814692827e-08, "loss": 4.1181, "step": 32275 }, { "epoch": 0.9858277336591326, "grad_norm": 0.5407021045684814, "learning_rate": 2.4775168955315508e-08, "loss": 4.2951, "step": 32276 }, { "epoch": 0.9858582773365914, "grad_norm": 0.5345343351364136, "learning_rate": 2.4668512055675552e-08, "loss": 4.2006, "step": 32277 }, { "epoch": 0.9858888210140501, "grad_norm": 0.5517444610595703, "learning_rate": 2.456208511675273e-08, "loss": 4.2339, "step": 32278 }, { "epoch": 0.9859193646915089, "grad_norm": 0.535225510597229, "learning_rate": 2.445588813952959e-08, "loss": 4.2229, "step": 32279 }, { "epoch": 0.9859499083689677, "grad_norm": 0.5460790395736694, "learning_rate": 2.4349921124980358e-08, "loss": 4.2513, "step": 32280 }, { "epoch": 0.9859804520464264, "grad_norm": 0.533305823802948, "learning_rate": 2.4244184074082022e-08, "loss": 4.1891, "step": 32281 }, { "epoch": 0.9860109957238852, "grad_norm": 0.5487325191497803, "learning_rate": 2.4138676987808805e-08, "loss": 4.2248, "step": 32282 }, { "epoch": 0.9860415394013439, "grad_norm": 0.5401039719581604, "learning_rate": 2.403339986713493e-08, "loss": 4.2222, "step": 32283 }, { "epoch": 0.9860720830788027, "grad_norm": 0.5427893400192261, "learning_rate": 2.3928352713023518e-08, "loss": 4.1917, "step": 32284 }, { "epoch": 0.9861026267562615, "grad_norm": 0.5421006083488464, "learning_rate": 2.3823535526446004e-08, "loss": 4.207, "step": 32285 }, { "epoch": 0.9861331704337202, "grad_norm": 0.5352987051010132, "learning_rate": 2.3718948308368292e-08, "loss": 4.1923, "step": 32286 }, { "epoch": 0.986163714111179, "grad_norm": 0.5324806571006775, "learning_rate": 2.3614591059750725e-08, "loss": 4.2641, "step": 32287 }, { "epoch": 0.9861942577886378, "grad_norm": 0.5421547889709473, "learning_rate": 2.3510463781553636e-08, "loss": 4.229, "step": 32288 }, { "epoch": 0.9862248014660965, "grad_norm": 0.5331491827964783, "learning_rate": 2.3406566474740156e-08, "loss": 4.216, "step": 32289 }, { "epoch": 0.9862553451435553, "grad_norm": 0.5463569760322571, "learning_rate": 2.330289914026229e-08, "loss": 4.3226, "step": 32290 }, { "epoch": 0.9862858888210141, "grad_norm": 0.5324448347091675, "learning_rate": 2.3199461779077614e-08, "loss": 4.257, "step": 32291 }, { "epoch": 0.9863164324984728, "grad_norm": 0.5349125862121582, "learning_rate": 2.3096254392135364e-08, "loss": 4.167, "step": 32292 }, { "epoch": 0.9863469761759316, "grad_norm": 0.540890097618103, "learning_rate": 2.2993276980390332e-08, "loss": 4.1612, "step": 32293 }, { "epoch": 0.9863775198533904, "grad_norm": 0.5407413840293884, "learning_rate": 2.289052954478621e-08, "loss": 4.2015, "step": 32294 }, { "epoch": 0.9864080635308491, "grad_norm": 0.5438876748085022, "learning_rate": 2.2788012086272237e-08, "loss": 4.3542, "step": 32295 }, { "epoch": 0.9864386072083079, "grad_norm": 0.5454908013343811, "learning_rate": 2.2685724605789328e-08, "loss": 4.2427, "step": 32296 }, { "epoch": 0.9864691508857667, "grad_norm": 0.5390033721923828, "learning_rate": 2.258366710428117e-08, "loss": 4.2682, "step": 32297 }, { "epoch": 0.9864996945632254, "grad_norm": 0.5468237996101379, "learning_rate": 2.248183958268868e-08, "loss": 4.247, "step": 32298 }, { "epoch": 0.9865302382406842, "grad_norm": 0.5329567193984985, "learning_rate": 2.238024204194722e-08, "loss": 4.2297, "step": 32299 }, { "epoch": 0.9865607819181429, "grad_norm": 0.551260232925415, "learning_rate": 2.2278874482994925e-08, "loss": 4.1859, "step": 32300 }, { "epoch": 0.9865913255956017, "grad_norm": 0.5361964106559753, "learning_rate": 2.2177736906761615e-08, "loss": 4.2868, "step": 32301 }, { "epoch": 0.9866218692730605, "grad_norm": 0.5480878353118896, "learning_rate": 2.207682931417987e-08, "loss": 4.2821, "step": 32302 }, { "epoch": 0.9866524129505192, "grad_norm": 0.5415011048316956, "learning_rate": 2.1976151706179504e-08, "loss": 4.2769, "step": 32303 }, { "epoch": 0.986682956627978, "grad_norm": 0.5525233745574951, "learning_rate": 2.1875704083687555e-08, "loss": 4.2754, "step": 32304 }, { "epoch": 0.9867135003054368, "grad_norm": 0.5340811014175415, "learning_rate": 2.177548644762828e-08, "loss": 4.2384, "step": 32305 }, { "epoch": 0.9867440439828955, "grad_norm": 0.5493931174278259, "learning_rate": 2.1675498798923167e-08, "loss": 4.2502, "step": 32306 }, { "epoch": 0.9867745876603543, "grad_norm": 0.5496225357055664, "learning_rate": 2.1575741138496475e-08, "loss": 4.2563, "step": 32307 }, { "epoch": 0.9868051313378131, "grad_norm": 0.538792610168457, "learning_rate": 2.147621346726414e-08, "loss": 4.278, "step": 32308 }, { "epoch": 0.9868356750152718, "grad_norm": 0.5573070645332336, "learning_rate": 2.1376915786142094e-08, "loss": 4.2762, "step": 32309 }, { "epoch": 0.9868662186927306, "grad_norm": 0.5380181670188904, "learning_rate": 2.1277848096046272e-08, "loss": 4.2031, "step": 32310 }, { "epoch": 0.9868967623701894, "grad_norm": 0.5421412587165833, "learning_rate": 2.1179010397887057e-08, "loss": 4.2737, "step": 32311 }, { "epoch": 0.9869273060476481, "grad_norm": 0.5377330183982849, "learning_rate": 2.1080402692577604e-08, "loss": 4.2413, "step": 32312 }, { "epoch": 0.9869578497251069, "grad_norm": 0.5416501760482788, "learning_rate": 2.0982024981022753e-08, "loss": 4.1934, "step": 32313 }, { "epoch": 0.9869883934025657, "grad_norm": 0.5400877594947815, "learning_rate": 2.0883877264127327e-08, "loss": 4.1242, "step": 32314 }, { "epoch": 0.9870189370800244, "grad_norm": 0.5466192364692688, "learning_rate": 2.0785959542798937e-08, "loss": 4.229, "step": 32315 }, { "epoch": 0.9870494807574832, "grad_norm": 0.538909912109375, "learning_rate": 2.0688271817936866e-08, "loss": 4.2265, "step": 32316 }, { "epoch": 0.9870800244349419, "grad_norm": 0.547718346118927, "learning_rate": 2.0590814090443166e-08, "loss": 4.2874, "step": 32317 }, { "epoch": 0.9871105681124007, "grad_norm": 0.5463293194770813, "learning_rate": 2.0493586361208795e-08, "loss": 4.1964, "step": 32318 }, { "epoch": 0.9871411117898595, "grad_norm": 0.533663272857666, "learning_rate": 2.0396588631135805e-08, "loss": 4.1888, "step": 32319 }, { "epoch": 0.9871716554673182, "grad_norm": 0.5440580248832703, "learning_rate": 2.0299820901115153e-08, "loss": 4.2626, "step": 32320 }, { "epoch": 0.987202199144777, "grad_norm": 0.5352540016174316, "learning_rate": 2.0203283172035015e-08, "loss": 4.2399, "step": 32321 }, { "epoch": 0.9872327428222358, "grad_norm": 0.5442578792572021, "learning_rate": 2.0106975444789122e-08, "loss": 4.4019, "step": 32322 }, { "epoch": 0.9872632864996945, "grad_norm": 0.5439690351486206, "learning_rate": 2.0010897720260103e-08, "loss": 4.2742, "step": 32323 }, { "epoch": 0.9872938301771533, "grad_norm": 0.5445601940155029, "learning_rate": 1.9915049999336134e-08, "loss": 4.2524, "step": 32324 }, { "epoch": 0.9873243738546121, "grad_norm": 0.5430193543434143, "learning_rate": 1.9819432282897066e-08, "loss": 4.1937, "step": 32325 }, { "epoch": 0.9873549175320708, "grad_norm": 0.5475872755050659, "learning_rate": 1.9724044571822754e-08, "loss": 4.2671, "step": 32326 }, { "epoch": 0.9873854612095296, "grad_norm": 0.5485712289810181, "learning_rate": 1.9628886866993047e-08, "loss": 4.2337, "step": 32327 }, { "epoch": 0.9874160048869884, "grad_norm": 0.5379061102867126, "learning_rate": 1.9533959169282246e-08, "loss": 4.1678, "step": 32328 }, { "epoch": 0.9874465485644471, "grad_norm": 0.5429950952529907, "learning_rate": 1.9439261479570202e-08, "loss": 4.3139, "step": 32329 }, { "epoch": 0.9874770922419059, "grad_norm": 0.5369104146957397, "learning_rate": 1.934479379872012e-08, "loss": 4.3239, "step": 32330 }, { "epoch": 0.9875076359193647, "grad_norm": 0.5448840260505676, "learning_rate": 1.9250556127609066e-08, "loss": 4.3214, "step": 32331 }, { "epoch": 0.9875381795968234, "grad_norm": 0.5443494915962219, "learning_rate": 1.9156548467100245e-08, "loss": 4.2566, "step": 32332 }, { "epoch": 0.9875687232742822, "grad_norm": 0.5445163249969482, "learning_rate": 1.90627708180624e-08, "loss": 4.2994, "step": 32333 }, { "epoch": 0.9875992669517409, "grad_norm": 0.5406241416931152, "learning_rate": 1.896922318135874e-08, "loss": 4.2503, "step": 32334 }, { "epoch": 0.9876298106291997, "grad_norm": 0.5386080145835876, "learning_rate": 1.8875905557846905e-08, "loss": 4.1829, "step": 32335 }, { "epoch": 0.9876603543066585, "grad_norm": 0.5461429357528687, "learning_rate": 1.8782817948390096e-08, "loss": 4.3087, "step": 32336 }, { "epoch": 0.9876908979841172, "grad_norm": 0.5387842059135437, "learning_rate": 1.8689960353843184e-08, "loss": 4.143, "step": 32337 }, { "epoch": 0.987721441661576, "grad_norm": 0.5481722950935364, "learning_rate": 1.859733277506104e-08, "loss": 4.2534, "step": 32338 }, { "epoch": 0.9877519853390349, "grad_norm": 0.5448875427246094, "learning_rate": 1.8504935212898533e-08, "loss": 4.2751, "step": 32339 }, { "epoch": 0.9877825290164935, "grad_norm": 0.539884090423584, "learning_rate": 1.841276766820499e-08, "loss": 4.3053, "step": 32340 }, { "epoch": 0.9878130726939524, "grad_norm": 0.5381389856338501, "learning_rate": 1.8320830141829726e-08, "loss": 4.2126, "step": 32341 }, { "epoch": 0.9878436163714112, "grad_norm": 0.5581790208816528, "learning_rate": 1.822912263461929e-08, "loss": 4.2346, "step": 32342 }, { "epoch": 0.9878741600488699, "grad_norm": 0.5334008932113647, "learning_rate": 1.8137645147417448e-08, "loss": 4.1673, "step": 32343 }, { "epoch": 0.9879047037263287, "grad_norm": 0.5326122641563416, "learning_rate": 1.8046397681065198e-08, "loss": 4.2479, "step": 32344 }, { "epoch": 0.9879352474037875, "grad_norm": 0.5360957980155945, "learning_rate": 1.7955380236406306e-08, "loss": 4.1899, "step": 32345 }, { "epoch": 0.9879657910812462, "grad_norm": 0.5363016128540039, "learning_rate": 1.7864592814276215e-08, "loss": 4.1993, "step": 32346 }, { "epoch": 0.987996334758705, "grad_norm": 0.5478043556213379, "learning_rate": 1.777403541551037e-08, "loss": 4.2324, "step": 32347 }, { "epoch": 0.9880268784361638, "grad_norm": 0.549139142036438, "learning_rate": 1.7683708040944214e-08, "loss": 4.1805, "step": 32348 }, { "epoch": 0.9880574221136225, "grad_norm": 0.5513960719108582, "learning_rate": 1.7593610691410413e-08, "loss": 4.1576, "step": 32349 }, { "epoch": 0.9880879657910813, "grad_norm": 0.5423205494880676, "learning_rate": 1.7503743367733306e-08, "loss": 4.2801, "step": 32350 }, { "epoch": 0.98811850946854, "grad_norm": 0.546481728553772, "learning_rate": 1.7414106070748338e-08, "loss": 4.2698, "step": 32351 }, { "epoch": 0.9881490531459988, "grad_norm": 0.5411642789840698, "learning_rate": 1.732469880127152e-08, "loss": 4.2396, "step": 32352 }, { "epoch": 0.9881795968234576, "grad_norm": 0.5372747778892517, "learning_rate": 1.7235521560135525e-08, "loss": 4.2642, "step": 32353 }, { "epoch": 0.9882101405009163, "grad_norm": 0.5501464605331421, "learning_rate": 1.7146574348153588e-08, "loss": 4.3236, "step": 32354 }, { "epoch": 0.9882406841783751, "grad_norm": 0.5405781865119934, "learning_rate": 1.705785716615005e-08, "loss": 4.2315, "step": 32355 }, { "epoch": 0.9882712278558339, "grad_norm": 0.5482333898544312, "learning_rate": 1.6969370014938147e-08, "loss": 4.2848, "step": 32356 }, { "epoch": 0.9883017715332926, "grad_norm": 0.5342289209365845, "learning_rate": 1.6881112895336672e-08, "loss": 4.1851, "step": 32357 }, { "epoch": 0.9883323152107514, "grad_norm": 0.5385939478874207, "learning_rate": 1.679308580815331e-08, "loss": 4.2639, "step": 32358 }, { "epoch": 0.9883628588882102, "grad_norm": 0.5456063151359558, "learning_rate": 1.6705288754204074e-08, "loss": 4.2853, "step": 32359 }, { "epoch": 0.9883934025656689, "grad_norm": 0.5428072214126587, "learning_rate": 1.6617721734291102e-08, "loss": 4.1094, "step": 32360 }, { "epoch": 0.9884239462431277, "grad_norm": 0.541743278503418, "learning_rate": 1.6530384749224858e-08, "loss": 4.2684, "step": 32361 }, { "epoch": 0.9884544899205865, "grad_norm": 0.5441136956214905, "learning_rate": 1.6443277799810254e-08, "loss": 4.361, "step": 32362 }, { "epoch": 0.9884850335980452, "grad_norm": 0.5384061336517334, "learning_rate": 1.6356400886846645e-08, "loss": 4.2493, "step": 32363 }, { "epoch": 0.988515577275504, "grad_norm": 0.5446447730064392, "learning_rate": 1.6269754011136174e-08, "loss": 4.3588, "step": 32364 }, { "epoch": 0.9885461209529627, "grad_norm": 0.5528640747070312, "learning_rate": 1.6183337173472647e-08, "loss": 4.1602, "step": 32365 }, { "epoch": 0.9885766646304215, "grad_norm": 0.5453195571899414, "learning_rate": 1.6097150374655424e-08, "loss": 4.2694, "step": 32366 }, { "epoch": 0.9886072083078803, "grad_norm": 0.5471076369285583, "learning_rate": 1.6011193615478315e-08, "loss": 4.0954, "step": 32367 }, { "epoch": 0.988637751985339, "grad_norm": 0.54205322265625, "learning_rate": 1.5925466896732356e-08, "loss": 4.3225, "step": 32368 }, { "epoch": 0.9886682956627978, "grad_norm": 0.5340805053710938, "learning_rate": 1.5839970219203026e-08, "loss": 4.168, "step": 32369 }, { "epoch": 0.9886988393402566, "grad_norm": 0.5355543494224548, "learning_rate": 1.575470358368414e-08, "loss": 4.2365, "step": 32370 }, { "epoch": 0.9887293830177153, "grad_norm": 0.5352990627288818, "learning_rate": 1.5669666990955624e-08, "loss": 4.23, "step": 32371 }, { "epoch": 0.9887599266951741, "grad_norm": 0.5506138205528259, "learning_rate": 1.558486044180296e-08, "loss": 4.1809, "step": 32372 }, { "epoch": 0.9887904703726329, "grad_norm": 0.5450232625007629, "learning_rate": 1.5500283937006088e-08, "loss": 4.2576, "step": 32373 }, { "epoch": 0.9888210140500916, "grad_norm": 0.5429534316062927, "learning_rate": 1.541593747734216e-08, "loss": 4.1526, "step": 32374 }, { "epoch": 0.9888515577275504, "grad_norm": 0.5422145128250122, "learning_rate": 1.53318210635911e-08, "loss": 4.2467, "step": 32375 }, { "epoch": 0.9888821014050092, "grad_norm": 0.5443995594978333, "learning_rate": 1.5247934696524524e-08, "loss": 4.3176, "step": 32376 }, { "epoch": 0.9889126450824679, "grad_norm": 0.5397708415985107, "learning_rate": 1.5164278376916806e-08, "loss": 4.3081, "step": 32377 }, { "epoch": 0.9889431887599267, "grad_norm": 0.5355463027954102, "learning_rate": 1.5080852105536782e-08, "loss": 4.2358, "step": 32378 }, { "epoch": 0.9889737324373855, "grad_norm": 0.5422785878181458, "learning_rate": 1.499765588315605e-08, "loss": 4.2536, "step": 32379 }, { "epoch": 0.9890042761148442, "grad_norm": 0.5550374388694763, "learning_rate": 1.491468971053511e-08, "loss": 4.3203, "step": 32380 }, { "epoch": 0.989034819792303, "grad_norm": 0.5433079600334167, "learning_rate": 1.4831953588442805e-08, "loss": 4.3239, "step": 32381 }, { "epoch": 0.9890653634697617, "grad_norm": 0.5442589521408081, "learning_rate": 1.474944751763685e-08, "loss": 4.3287, "step": 32382 }, { "epoch": 0.9890959071472205, "grad_norm": 0.5330585241317749, "learning_rate": 1.4667171498880527e-08, "loss": 4.191, "step": 32383 }, { "epoch": 0.9891264508246793, "grad_norm": 0.5485821962356567, "learning_rate": 1.458512553292879e-08, "loss": 4.229, "step": 32384 }, { "epoch": 0.989156994502138, "grad_norm": 0.5421162247657776, "learning_rate": 1.4503309620536587e-08, "loss": 4.2669, "step": 32385 }, { "epoch": 0.9891875381795968, "grad_norm": 0.5608871579170227, "learning_rate": 1.4421723762461647e-08, "loss": 4.2434, "step": 32386 }, { "epoch": 0.9892180818570556, "grad_norm": 0.5577396750450134, "learning_rate": 1.4340367959450595e-08, "loss": 4.1913, "step": 32387 }, { "epoch": 0.9892486255345143, "grad_norm": 0.5427765250205994, "learning_rate": 1.4259242212252833e-08, "loss": 4.289, "step": 32388 }, { "epoch": 0.9892791692119731, "grad_norm": 0.5442230105400085, "learning_rate": 1.4178346521617757e-08, "loss": 4.2458, "step": 32389 }, { "epoch": 0.9893097128894319, "grad_norm": 0.5327423214912415, "learning_rate": 1.4097680888289223e-08, "loss": 4.2638, "step": 32390 }, { "epoch": 0.9893402565668906, "grad_norm": 0.5418465733528137, "learning_rate": 1.4017245313011074e-08, "loss": 4.141, "step": 32391 }, { "epoch": 0.9893708002443494, "grad_norm": 0.5447657704353333, "learning_rate": 1.3937039796521612e-08, "loss": 4.2817, "step": 32392 }, { "epoch": 0.9894013439218082, "grad_norm": 0.5589021444320679, "learning_rate": 1.385706433956191e-08, "loss": 4.2649, "step": 32393 }, { "epoch": 0.9894318875992669, "grad_norm": 0.5500265955924988, "learning_rate": 1.3777318942864715e-08, "loss": 4.2597, "step": 32394 }, { "epoch": 0.9894624312767257, "grad_norm": 0.5382109880447388, "learning_rate": 1.369780360716555e-08, "loss": 4.2184, "step": 32395 }, { "epoch": 0.9894929749541845, "grad_norm": 0.5305317640304565, "learning_rate": 1.3618518333199936e-08, "loss": 4.238, "step": 32396 }, { "epoch": 0.9895235186316432, "grad_norm": 0.5433033108711243, "learning_rate": 1.3539463121695073e-08, "loss": 4.2869, "step": 32397 }, { "epoch": 0.989554062309102, "grad_norm": 0.553855299949646, "learning_rate": 1.3460637973378154e-08, "loss": 4.3242, "step": 32398 }, { "epoch": 0.9895846059865607, "grad_norm": 0.5513632893562317, "learning_rate": 1.3382042888976376e-08, "loss": 4.116, "step": 32399 }, { "epoch": 0.9896151496640195, "grad_norm": 0.5571274161338806, "learning_rate": 1.3303677869211384e-08, "loss": 4.238, "step": 32400 }, { "epoch": 0.9896456933414783, "grad_norm": 0.5611317753791809, "learning_rate": 1.3225542914807599e-08, "loss": 4.2268, "step": 32401 }, { "epoch": 0.989676237018937, "grad_norm": 0.5417979955673218, "learning_rate": 1.3147638026483888e-08, "loss": 4.2236, "step": 32402 }, { "epoch": 0.9897067806963958, "grad_norm": 0.542323112487793, "learning_rate": 1.3069963204956348e-08, "loss": 4.2823, "step": 32403 }, { "epoch": 0.9897373243738546, "grad_norm": 0.538357675075531, "learning_rate": 1.2992518450938296e-08, "loss": 4.2498, "step": 32404 }, { "epoch": 0.9897678680513133, "grad_norm": 0.5511847734451294, "learning_rate": 1.29153037651486e-08, "loss": 4.1644, "step": 32405 }, { "epoch": 0.9897984117287721, "grad_norm": 0.5431770086288452, "learning_rate": 1.2838319148292255e-08, "loss": 4.3431, "step": 32406 }, { "epoch": 0.989828955406231, "grad_norm": 0.5383443832397461, "learning_rate": 1.2761564601082576e-08, "loss": 4.2194, "step": 32407 }, { "epoch": 0.9898594990836896, "grad_norm": 0.5476018786430359, "learning_rate": 1.2685040124224557e-08, "loss": 4.158, "step": 32408 }, { "epoch": 0.9898900427611484, "grad_norm": 0.5431240200996399, "learning_rate": 1.2608745718420411e-08, "loss": 4.28, "step": 32409 }, { "epoch": 0.9899205864386073, "grad_norm": 0.5520091652870178, "learning_rate": 1.253268138437791e-08, "loss": 4.2293, "step": 32410 }, { "epoch": 0.989951130116066, "grad_norm": 0.5378217697143555, "learning_rate": 1.2456847122790938e-08, "loss": 4.2283, "step": 32411 }, { "epoch": 0.9899816737935248, "grad_norm": 0.5412110090255737, "learning_rate": 1.2381242934361714e-08, "loss": 4.2356, "step": 32412 }, { "epoch": 0.9900122174709836, "grad_norm": 0.529691755771637, "learning_rate": 1.2305868819786904e-08, "loss": 4.0781, "step": 32413 }, { "epoch": 0.9900427611484423, "grad_norm": 0.5433122515678406, "learning_rate": 1.2230724779760395e-08, "loss": 4.1802, "step": 32414 }, { "epoch": 0.9900733048259011, "grad_norm": 0.5418757796287537, "learning_rate": 1.2155810814970526e-08, "loss": 4.1833, "step": 32415 }, { "epoch": 0.9901038485033598, "grad_norm": 0.5341151356697083, "learning_rate": 1.2081126926111185e-08, "loss": 4.2514, "step": 32416 }, { "epoch": 0.9901343921808186, "grad_norm": 0.5433660745620728, "learning_rate": 1.2006673113867939e-08, "loss": 4.2701, "step": 32417 }, { "epoch": 0.9901649358582774, "grad_norm": 0.5515547394752502, "learning_rate": 1.1932449378926346e-08, "loss": 4.1505, "step": 32418 }, { "epoch": 0.9901954795357361, "grad_norm": 0.5462126135826111, "learning_rate": 1.1858455721971972e-08, "loss": 4.2159, "step": 32419 }, { "epoch": 0.9902260232131949, "grad_norm": 0.5327140688896179, "learning_rate": 1.1784692143684828e-08, "loss": 4.2715, "step": 32420 }, { "epoch": 0.9902565668906537, "grad_norm": 0.5458861589431763, "learning_rate": 1.1711158644742149e-08, "loss": 4.1663, "step": 32421 }, { "epoch": 0.9902871105681124, "grad_norm": 0.5405701994895935, "learning_rate": 1.163785522582117e-08, "loss": 4.2148, "step": 32422 }, { "epoch": 0.9903176542455712, "grad_norm": 0.5307318568229675, "learning_rate": 1.156478188759913e-08, "loss": 4.2312, "step": 32423 }, { "epoch": 0.99034819792303, "grad_norm": 0.5496101379394531, "learning_rate": 1.1491938630747711e-08, "loss": 4.2607, "step": 32424 }, { "epoch": 0.9903787416004887, "grad_norm": 0.5323073863983154, "learning_rate": 1.1419325455938601e-08, "loss": 4.1989, "step": 32425 }, { "epoch": 0.9904092852779475, "grad_norm": 0.5385541319847107, "learning_rate": 1.1346942363840707e-08, "loss": 4.2352, "step": 32426 }, { "epoch": 0.9904398289554063, "grad_norm": 0.5327857732772827, "learning_rate": 1.1274789355117387e-08, "loss": 4.2789, "step": 32427 }, { "epoch": 0.990470372632865, "grad_norm": 0.5432462692260742, "learning_rate": 1.1202866430437553e-08, "loss": 4.2646, "step": 32428 }, { "epoch": 0.9905009163103238, "grad_norm": 0.549659252166748, "learning_rate": 1.1131173590459009e-08, "loss": 4.3128, "step": 32429 }, { "epoch": 0.9905314599877826, "grad_norm": 0.5415797233581543, "learning_rate": 1.1059710835842341e-08, "loss": 4.2201, "step": 32430 }, { "epoch": 0.9905620036652413, "grad_norm": 0.5344588160514832, "learning_rate": 1.0988478167248129e-08, "loss": 4.265, "step": 32431 }, { "epoch": 0.9905925473427001, "grad_norm": 0.5397946238517761, "learning_rate": 1.0917475585331405e-08, "loss": 4.2647, "step": 32432 }, { "epoch": 0.9906230910201588, "grad_norm": 0.5329254865646362, "learning_rate": 1.0846703090747201e-08, "loss": 4.2227, "step": 32433 }, { "epoch": 0.9906536346976176, "grad_norm": 0.5481454133987427, "learning_rate": 1.0776160684142223e-08, "loss": 4.2477, "step": 32434 }, { "epoch": 0.9906841783750764, "grad_norm": 0.5377762317657471, "learning_rate": 1.07058483661715e-08, "loss": 4.2353, "step": 32435 }, { "epoch": 0.9907147220525351, "grad_norm": 0.548944354057312, "learning_rate": 1.0635766137481739e-08, "loss": 4.2678, "step": 32436 }, { "epoch": 0.9907452657299939, "grad_norm": 0.5514004826545715, "learning_rate": 1.0565913998714094e-08, "loss": 4.2377, "step": 32437 }, { "epoch": 0.9907758094074527, "grad_norm": 0.5411518812179565, "learning_rate": 1.0496291950515269e-08, "loss": 4.1636, "step": 32438 }, { "epoch": 0.9908063530849114, "grad_norm": 0.5396931767463684, "learning_rate": 1.0426899993526418e-08, "loss": 4.1032, "step": 32439 }, { "epoch": 0.9908368967623702, "grad_norm": 0.5507844686508179, "learning_rate": 1.0357738128383143e-08, "loss": 4.2643, "step": 32440 }, { "epoch": 0.990867440439829, "grad_norm": 0.5389758944511414, "learning_rate": 1.0288806355726599e-08, "loss": 4.2255, "step": 32441 }, { "epoch": 0.9908979841172877, "grad_norm": 0.54487544298172, "learning_rate": 1.0220104676186837e-08, "loss": 4.3041, "step": 32442 }, { "epoch": 0.9909285277947465, "grad_norm": 0.5482224225997925, "learning_rate": 1.0151633090402234e-08, "loss": 4.3102, "step": 32443 }, { "epoch": 0.9909590714722053, "grad_norm": 0.537799060344696, "learning_rate": 1.0083391598997294e-08, "loss": 4.1287, "step": 32444 }, { "epoch": 0.990989615149664, "grad_norm": 0.544572114944458, "learning_rate": 1.0015380202604841e-08, "loss": 4.3169, "step": 32445 }, { "epoch": 0.9910201588271228, "grad_norm": 0.5407410264015198, "learning_rate": 9.947598901849376e-09, "loss": 4.2954, "step": 32446 }, { "epoch": 0.9910507025045816, "grad_norm": 0.5390342473983765, "learning_rate": 9.8800476973554e-09, "loss": 4.2968, "step": 32447 }, { "epoch": 0.9910812461820403, "grad_norm": 0.5413105487823486, "learning_rate": 9.81272658974186e-09, "loss": 4.2394, "step": 32448 }, { "epoch": 0.9911117898594991, "grad_norm": 0.5402113199234009, "learning_rate": 9.745635579633261e-09, "loss": 4.3452, "step": 32449 }, { "epoch": 0.9911423335369578, "grad_norm": 0.5325607061386108, "learning_rate": 9.678774667645773e-09, "loss": 4.2255, "step": 32450 }, { "epoch": 0.9911728772144166, "grad_norm": 0.5488717555999756, "learning_rate": 9.612143854395572e-09, "loss": 4.3143, "step": 32451 }, { "epoch": 0.9912034208918754, "grad_norm": 0.5417110919952393, "learning_rate": 9.54574314049328e-09, "loss": 4.2842, "step": 32452 }, { "epoch": 0.9912339645693341, "grad_norm": 0.5512992143630981, "learning_rate": 9.479572526552293e-09, "loss": 4.2829, "step": 32453 }, { "epoch": 0.9912645082467929, "grad_norm": 0.5432347655296326, "learning_rate": 9.413632013180462e-09, "loss": 4.2513, "step": 32454 }, { "epoch": 0.9912950519242517, "grad_norm": 0.5311964750289917, "learning_rate": 9.347921600988407e-09, "loss": 4.1781, "step": 32455 }, { "epoch": 0.9913255956017104, "grad_norm": 0.5344493389129639, "learning_rate": 9.282441290578424e-09, "loss": 4.1586, "step": 32456 }, { "epoch": 0.9913561392791692, "grad_norm": 0.5432980060577393, "learning_rate": 9.217191082552812e-09, "loss": 4.298, "step": 32457 }, { "epoch": 0.991386682956628, "grad_norm": 0.5300225615501404, "learning_rate": 9.152170977513862e-09, "loss": 4.1979, "step": 32458 }, { "epoch": 0.9914172266340867, "grad_norm": 0.5400630235671997, "learning_rate": 9.0873809760611e-09, "loss": 4.2908, "step": 32459 }, { "epoch": 0.9914477703115455, "grad_norm": 0.5407184958457947, "learning_rate": 9.02282107878849e-09, "loss": 4.1914, "step": 32460 }, { "epoch": 0.9914783139890043, "grad_norm": 0.5484578609466553, "learning_rate": 8.958491286292781e-09, "loss": 4.1845, "step": 32461 }, { "epoch": 0.991508857666463, "grad_norm": 0.5336156487464905, "learning_rate": 8.894391599165164e-09, "loss": 4.1707, "step": 32462 }, { "epoch": 0.9915394013439218, "grad_norm": 0.5480175018310547, "learning_rate": 8.830522017994058e-09, "loss": 4.2776, "step": 32463 }, { "epoch": 0.9915699450213806, "grad_norm": 0.5424970984458923, "learning_rate": 8.766882543373434e-09, "loss": 4.2689, "step": 32464 }, { "epoch": 0.9916004886988393, "grad_norm": 0.548251211643219, "learning_rate": 8.703473175883381e-09, "loss": 4.2265, "step": 32465 }, { "epoch": 0.9916310323762981, "grad_norm": 0.5427120327949524, "learning_rate": 8.640293916109544e-09, "loss": 4.188, "step": 32466 }, { "epoch": 0.9916615760537568, "grad_norm": 0.5418068766593933, "learning_rate": 8.577344764632012e-09, "loss": 4.1528, "step": 32467 }, { "epoch": 0.9916921197312156, "grad_norm": 0.5472716689109802, "learning_rate": 8.51462572203643e-09, "loss": 4.2511, "step": 32468 }, { "epoch": 0.9917226634086744, "grad_norm": 0.5590322017669678, "learning_rate": 8.452136788891784e-09, "loss": 4.1819, "step": 32469 }, { "epoch": 0.9917532070861331, "grad_norm": 0.5415220260620117, "learning_rate": 8.389877965780946e-09, "loss": 4.149, "step": 32470 }, { "epoch": 0.9917837507635919, "grad_norm": 0.5403238534927368, "learning_rate": 8.327849253272902e-09, "loss": 4.1476, "step": 32471 }, { "epoch": 0.9918142944410507, "grad_norm": 0.5390871167182922, "learning_rate": 8.266050651939416e-09, "loss": 4.2217, "step": 32472 }, { "epoch": 0.9918448381185094, "grad_norm": 0.5463714003562927, "learning_rate": 8.20448216234948e-09, "loss": 4.1709, "step": 32473 }, { "epoch": 0.9918753817959682, "grad_norm": 0.5383853912353516, "learning_rate": 8.143143785069307e-09, "loss": 4.154, "step": 32474 }, { "epoch": 0.991905925473427, "grad_norm": 0.5493888258934021, "learning_rate": 8.082035520667886e-09, "loss": 4.2197, "step": 32475 }, { "epoch": 0.9919364691508857, "grad_norm": 0.5436722040176392, "learning_rate": 8.021157369703102e-09, "loss": 4.2656, "step": 32476 }, { "epoch": 0.9919670128283445, "grad_norm": 0.5403783917427063, "learning_rate": 7.960509332735621e-09, "loss": 4.2862, "step": 32477 }, { "epoch": 0.9919975565058033, "grad_norm": 0.5539766550064087, "learning_rate": 7.900091410326105e-09, "loss": 4.2916, "step": 32478 }, { "epoch": 0.992028100183262, "grad_norm": 0.5421238541603088, "learning_rate": 7.83990360303244e-09, "loss": 4.1958, "step": 32479 }, { "epoch": 0.9920586438607208, "grad_norm": 0.5416231155395508, "learning_rate": 7.779945911404185e-09, "loss": 4.2713, "step": 32480 }, { "epoch": 0.9920891875381797, "grad_norm": 0.5502098798751831, "learning_rate": 7.720218335996454e-09, "loss": 4.1671, "step": 32481 }, { "epoch": 0.9921197312156383, "grad_norm": 0.5470168590545654, "learning_rate": 7.660720877358806e-09, "loss": 4.275, "step": 32482 }, { "epoch": 0.9921502748930972, "grad_norm": 0.5381004214286804, "learning_rate": 7.601453536038028e-09, "loss": 4.2609, "step": 32483 }, { "epoch": 0.9921808185705558, "grad_norm": 0.5453941822052002, "learning_rate": 7.542416312580902e-09, "loss": 4.2484, "step": 32484 }, { "epoch": 0.9922113622480146, "grad_norm": 0.5364117622375488, "learning_rate": 7.483609207531439e-09, "loss": 4.2568, "step": 32485 }, { "epoch": 0.9922419059254735, "grad_norm": 0.5424348711967468, "learning_rate": 7.425032221428096e-09, "loss": 4.1223, "step": 32486 }, { "epoch": 0.9922724496029321, "grad_norm": 0.5346983075141907, "learning_rate": 7.366685354814884e-09, "loss": 4.2342, "step": 32487 }, { "epoch": 0.992302993280391, "grad_norm": 0.5487028360366821, "learning_rate": 7.308568608224708e-09, "loss": 4.3614, "step": 32488 }, { "epoch": 0.9923335369578498, "grad_norm": 0.5312263369560242, "learning_rate": 7.250681982196028e-09, "loss": 4.2972, "step": 32489 }, { "epoch": 0.9923640806353085, "grad_norm": 0.537367582321167, "learning_rate": 7.1930254772589746e-09, "loss": 4.2707, "step": 32490 }, { "epoch": 0.9923946243127673, "grad_norm": 0.5357579588890076, "learning_rate": 7.135599093946455e-09, "loss": 4.2646, "step": 32491 }, { "epoch": 0.9924251679902261, "grad_norm": 0.5425340533256531, "learning_rate": 7.078402832785825e-09, "loss": 4.2975, "step": 32492 }, { "epoch": 0.9924557116676848, "grad_norm": 0.5401874780654907, "learning_rate": 7.0214366943044395e-09, "loss": 4.2541, "step": 32493 }, { "epoch": 0.9924862553451436, "grad_norm": 0.5316372513771057, "learning_rate": 6.964700679026881e-09, "loss": 4.172, "step": 32494 }, { "epoch": 0.9925167990226024, "grad_norm": 0.5330803990364075, "learning_rate": 6.908194787474953e-09, "loss": 4.1749, "step": 32495 }, { "epoch": 0.9925473427000611, "grad_norm": 0.5420330166816711, "learning_rate": 6.851919020170461e-09, "loss": 4.2388, "step": 32496 }, { "epoch": 0.9925778863775199, "grad_norm": 0.5483307242393494, "learning_rate": 6.795873377629658e-09, "loss": 4.2811, "step": 32497 }, { "epoch": 0.9926084300549787, "grad_norm": 0.5480972528457642, "learning_rate": 6.740057860371573e-09, "loss": 4.3152, "step": 32498 }, { "epoch": 0.9926389737324374, "grad_norm": 0.5456258058547974, "learning_rate": 6.684472468906911e-09, "loss": 4.2095, "step": 32499 }, { "epoch": 0.9926695174098962, "grad_norm": 0.5355205535888672, "learning_rate": 6.629117203746371e-09, "loss": 4.205, "step": 32500 }, { "epoch": 0.9927000610873549, "grad_norm": 0.5428798794746399, "learning_rate": 6.573992065406209e-09, "loss": 4.2659, "step": 32501 }, { "epoch": 0.9927306047648137, "grad_norm": 0.5460379719734192, "learning_rate": 6.519097054386025e-09, "loss": 4.2227, "step": 32502 }, { "epoch": 0.9927611484422725, "grad_norm": 0.5498731136322021, "learning_rate": 6.464432171196522e-09, "loss": 4.2867, "step": 32503 }, { "epoch": 0.9927916921197312, "grad_norm": 0.5445359945297241, "learning_rate": 6.4099974163372985e-09, "loss": 4.2989, "step": 32504 }, { "epoch": 0.99282223579719, "grad_norm": 0.5473845601081848, "learning_rate": 6.355792790313508e-09, "loss": 4.2955, "step": 32505 }, { "epoch": 0.9928527794746488, "grad_norm": 0.5487673878669739, "learning_rate": 6.301818293621975e-09, "loss": 4.354, "step": 32506 }, { "epoch": 0.9928833231521075, "grad_norm": 0.5349521636962891, "learning_rate": 6.248073926762299e-09, "loss": 4.2287, "step": 32507 }, { "epoch": 0.9929138668295663, "grad_norm": 0.5548239946365356, "learning_rate": 6.194559690225754e-09, "loss": 4.2651, "step": 32508 }, { "epoch": 0.9929444105070251, "grad_norm": 0.5416533946990967, "learning_rate": 6.141275584503614e-09, "loss": 4.2701, "step": 32509 }, { "epoch": 0.9929749541844838, "grad_norm": 0.5341911315917969, "learning_rate": 6.088221610092704e-09, "loss": 4.2567, "step": 32510 }, { "epoch": 0.9930054978619426, "grad_norm": 0.5423837900161743, "learning_rate": 6.03539776747597e-09, "loss": 4.2422, "step": 32511 }, { "epoch": 0.9930360415394014, "grad_norm": 0.5414524674415588, "learning_rate": 5.982804057144687e-09, "loss": 4.2345, "step": 32512 }, { "epoch": 0.9930665852168601, "grad_norm": 0.5361393690109253, "learning_rate": 5.9304404795762496e-09, "loss": 4.1863, "step": 32513 }, { "epoch": 0.9930971288943189, "grad_norm": 0.5484894514083862, "learning_rate": 5.878307035261932e-09, "loss": 4.2422, "step": 32514 }, { "epoch": 0.9931276725717776, "grad_norm": 0.5418072938919067, "learning_rate": 5.826403724673579e-09, "loss": 4.1164, "step": 32515 }, { "epoch": 0.9931582162492364, "grad_norm": 0.544004499912262, "learning_rate": 5.774730548291363e-09, "loss": 4.3427, "step": 32516 }, { "epoch": 0.9931887599266952, "grad_norm": 0.5418097376823425, "learning_rate": 5.7232875065954535e-09, "loss": 4.2952, "step": 32517 }, { "epoch": 0.9932193036041539, "grad_norm": 0.5414495468139648, "learning_rate": 5.672074600052146e-09, "loss": 4.2272, "step": 32518 }, { "epoch": 0.9932498472816127, "grad_norm": 0.5298752784729004, "learning_rate": 5.621091829138836e-09, "loss": 4.1045, "step": 32519 }, { "epoch": 0.9932803909590715, "grad_norm": 0.5452625155448914, "learning_rate": 5.5703391943245916e-09, "loss": 4.3081, "step": 32520 }, { "epoch": 0.9933109346365302, "grad_norm": 0.5480661392211914, "learning_rate": 5.519816696072932e-09, "loss": 4.2257, "step": 32521 }, { "epoch": 0.993341478313989, "grad_norm": 0.5453289747238159, "learning_rate": 5.469524334850152e-09, "loss": 4.1697, "step": 32522 }, { "epoch": 0.9933720219914478, "grad_norm": 0.5605136752128601, "learning_rate": 5.4194621111225415e-09, "loss": 4.2576, "step": 32523 }, { "epoch": 0.9934025656689065, "grad_norm": 0.5419448018074036, "learning_rate": 5.369630025348071e-09, "loss": 4.2294, "step": 32524 }, { "epoch": 0.9934331093463653, "grad_norm": 0.5405228137969971, "learning_rate": 5.320028077987482e-09, "loss": 4.331, "step": 32525 }, { "epoch": 0.9934636530238241, "grad_norm": 0.5405299067497253, "learning_rate": 5.27065626949319e-09, "loss": 4.2525, "step": 32526 }, { "epoch": 0.9934941967012828, "grad_norm": 0.5356466174125671, "learning_rate": 5.2215146003259384e-09, "loss": 4.2117, "step": 32527 }, { "epoch": 0.9935247403787416, "grad_norm": 0.545049786567688, "learning_rate": 5.172603070935367e-09, "loss": 4.2821, "step": 32528 }, { "epoch": 0.9935552840562004, "grad_norm": 0.5429689884185791, "learning_rate": 5.1239216817711156e-09, "loss": 4.231, "step": 32529 }, { "epoch": 0.9935858277336591, "grad_norm": 0.5324009656906128, "learning_rate": 5.0754704332800496e-09, "loss": 4.2171, "step": 32530 }, { "epoch": 0.9936163714111179, "grad_norm": 0.5416842699050903, "learning_rate": 5.027249325911809e-09, "loss": 4.2472, "step": 32531 }, { "epoch": 0.9936469150885766, "grad_norm": 0.5367780923843384, "learning_rate": 4.979258360110484e-09, "loss": 4.2141, "step": 32532 }, { "epoch": 0.9936774587660354, "grad_norm": 0.5531193614006042, "learning_rate": 4.931497536314611e-09, "loss": 4.2013, "step": 32533 }, { "epoch": 0.9937080024434942, "grad_norm": 0.543888509273529, "learning_rate": 4.883966854965505e-09, "loss": 4.2591, "step": 32534 }, { "epoch": 0.9937385461209529, "grad_norm": 0.541618824005127, "learning_rate": 4.836666316501703e-09, "loss": 4.3325, "step": 32535 }, { "epoch": 0.9937690897984117, "grad_norm": 0.5502912998199463, "learning_rate": 4.789595921356193e-09, "loss": 4.2718, "step": 32536 }, { "epoch": 0.9937996334758705, "grad_norm": 0.542998731136322, "learning_rate": 4.7427556699675135e-09, "loss": 4.3346, "step": 32537 }, { "epoch": 0.9938301771533292, "grad_norm": 0.5372114181518555, "learning_rate": 4.6961455627603235e-09, "loss": 4.2533, "step": 32538 }, { "epoch": 0.993860720830788, "grad_norm": 0.5364814400672913, "learning_rate": 4.649765600167611e-09, "loss": 4.1601, "step": 32539 }, { "epoch": 0.9938912645082468, "grad_norm": 0.5514428615570068, "learning_rate": 4.60361578261681e-09, "loss": 4.2884, "step": 32540 }, { "epoch": 0.9939218081857055, "grad_norm": 0.5400792956352234, "learning_rate": 4.5576961105325835e-09, "loss": 4.1863, "step": 32541 }, { "epoch": 0.9939523518631643, "grad_norm": 1.2848224639892578, "learning_rate": 4.5120065843340385e-09, "loss": 4.1925, "step": 32542 }, { "epoch": 0.9939828955406231, "grad_norm": 0.5715493559837341, "learning_rate": 4.466547204448612e-09, "loss": 4.2413, "step": 32543 }, { "epoch": 0.9940134392180818, "grad_norm": 0.5377115607261658, "learning_rate": 4.421317971287087e-09, "loss": 4.287, "step": 32544 }, { "epoch": 0.9940439828955406, "grad_norm": 0.5355444550514221, "learning_rate": 4.376318885274122e-09, "loss": 4.1923, "step": 32545 }, { "epoch": 0.9940745265729994, "grad_norm": 0.5457675457000732, "learning_rate": 4.331549946817725e-09, "loss": 4.3091, "step": 32546 }, { "epoch": 0.9941050702504581, "grad_norm": 0.5403586626052856, "learning_rate": 4.2870111563314555e-09, "loss": 4.2925, "step": 32547 }, { "epoch": 0.9941356139279169, "grad_norm": 0.5423441529273987, "learning_rate": 4.2427025142260935e-09, "loss": 4.1229, "step": 32548 }, { "epoch": 0.9941661576053756, "grad_norm": 0.5378155708312988, "learning_rate": 4.198624020912423e-09, "loss": 4.1603, "step": 32549 }, { "epoch": 0.9941967012828344, "grad_norm": 0.5406339168548584, "learning_rate": 4.154775676790124e-09, "loss": 4.2566, "step": 32550 }, { "epoch": 0.9942272449602932, "grad_norm": 0.5482601523399353, "learning_rate": 4.1111574822699784e-09, "loss": 4.1414, "step": 32551 }, { "epoch": 0.9942577886377519, "grad_norm": 0.5365251898765564, "learning_rate": 4.0677694377488915e-09, "loss": 4.3169, "step": 32552 }, { "epoch": 0.9942883323152107, "grad_norm": 0.5443477034568787, "learning_rate": 4.024611543626544e-09, "loss": 4.3327, "step": 32553 }, { "epoch": 0.9943188759926695, "grad_norm": 0.5451380610466003, "learning_rate": 3.98168380029984e-09, "loss": 4.3219, "step": 32554 }, { "epoch": 0.9943494196701282, "grad_norm": 0.5546793341636658, "learning_rate": 3.93898620816846e-09, "loss": 4.2496, "step": 32555 }, { "epoch": 0.994379963347587, "grad_norm": 0.5449600219726562, "learning_rate": 3.8965187676209824e-09, "loss": 4.2242, "step": 32556 }, { "epoch": 0.9944105070250459, "grad_norm": 0.5460498929023743, "learning_rate": 3.8542814790487605e-09, "loss": 4.217, "step": 32557 }, { "epoch": 0.9944410507025045, "grad_norm": 0.5329766273498535, "learning_rate": 3.8122743428431476e-09, "loss": 4.2445, "step": 32558 }, { "epoch": 0.9944715943799634, "grad_norm": 0.5408878326416016, "learning_rate": 3.7704973593899464e-09, "loss": 4.2882, "step": 32559 }, { "epoch": 0.9945021380574222, "grad_norm": 0.5459732413291931, "learning_rate": 3.728950529074959e-09, "loss": 4.2154, "step": 32560 }, { "epoch": 0.9945326817348809, "grad_norm": 0.5370294451713562, "learning_rate": 3.687633852278438e-09, "loss": 4.281, "step": 32561 }, { "epoch": 0.9945632254123397, "grad_norm": 0.5344735980033875, "learning_rate": 3.646547329380634e-09, "loss": 4.2788, "step": 32562 }, { "epoch": 0.9945937690897985, "grad_norm": 0.5444332957267761, "learning_rate": 3.6056909607617985e-09, "loss": 4.1587, "step": 32563 }, { "epoch": 0.9946243127672572, "grad_norm": 0.5394106507301331, "learning_rate": 3.5650647467966314e-09, "loss": 4.2646, "step": 32564 }, { "epoch": 0.994654856444716, "grad_norm": 0.5377840995788574, "learning_rate": 3.5246686878598333e-09, "loss": 4.2195, "step": 32565 }, { "epoch": 0.9946854001221747, "grad_norm": 0.54173344373703, "learning_rate": 3.484502784323329e-09, "loss": 4.2449, "step": 32566 }, { "epoch": 0.9947159437996335, "grad_norm": 0.5433860421180725, "learning_rate": 3.4445670365562675e-09, "loss": 4.1451, "step": 32567 }, { "epoch": 0.9947464874770923, "grad_norm": 0.5443411469459534, "learning_rate": 3.404861444927798e-09, "loss": 4.2606, "step": 32568 }, { "epoch": 0.994777031154551, "grad_norm": 0.5405430197715759, "learning_rate": 3.3653860098042943e-09, "loss": 4.1141, "step": 32569 }, { "epoch": 0.9948075748320098, "grad_norm": 0.5465214848518372, "learning_rate": 3.3261407315465788e-09, "loss": 4.284, "step": 32570 }, { "epoch": 0.9948381185094686, "grad_norm": 0.5363882184028625, "learning_rate": 3.2871256105154734e-09, "loss": 4.3078, "step": 32571 }, { "epoch": 0.9948686621869273, "grad_norm": 0.5535841584205627, "learning_rate": 3.248340647074577e-09, "loss": 4.2652, "step": 32572 }, { "epoch": 0.9948992058643861, "grad_norm": 0.5370330810546875, "learning_rate": 3.209785841576385e-09, "loss": 4.2785, "step": 32573 }, { "epoch": 0.9949297495418449, "grad_norm": 0.5396561026573181, "learning_rate": 3.171461194378944e-09, "loss": 4.2382, "step": 32574 }, { "epoch": 0.9949602932193036, "grad_norm": 0.5350757241249084, "learning_rate": 3.133366705831975e-09, "loss": 4.2579, "step": 32575 }, { "epoch": 0.9949908368967624, "grad_norm": 0.5308182835578918, "learning_rate": 3.0955023762907486e-09, "loss": 4.1712, "step": 32576 }, { "epoch": 0.9950213805742212, "grad_norm": 0.5389006733894348, "learning_rate": 3.0578682060994348e-09, "loss": 4.2241, "step": 32577 }, { "epoch": 0.9950519242516799, "grad_norm": 0.5409271121025085, "learning_rate": 3.0204641956077527e-09, "loss": 4.2862, "step": 32578 }, { "epoch": 0.9950824679291387, "grad_norm": 0.5398676991462708, "learning_rate": 2.983290345157097e-09, "loss": 4.2827, "step": 32579 }, { "epoch": 0.9951130116065975, "grad_norm": 0.5367521047592163, "learning_rate": 2.946346655094412e-09, "loss": 4.2201, "step": 32580 }, { "epoch": 0.9951435552840562, "grad_norm": 0.5412187576293945, "learning_rate": 2.9096331257527643e-09, "loss": 4.2446, "step": 32581 }, { "epoch": 0.995174098961515, "grad_norm": 0.5460236072540283, "learning_rate": 2.8731497574790988e-09, "loss": 4.2443, "step": 32582 }, { "epoch": 0.9952046426389737, "grad_norm": 0.5501893162727356, "learning_rate": 2.8368965506009315e-09, "loss": 4.2631, "step": 32583 }, { "epoch": 0.9952351863164325, "grad_norm": 0.5414931178092957, "learning_rate": 2.8008735054568803e-09, "loss": 4.2275, "step": 32584 }, { "epoch": 0.9952657299938913, "grad_norm": 0.5423043370246887, "learning_rate": 2.7650806223772364e-09, "loss": 4.2046, "step": 32585 }, { "epoch": 0.99529627367135, "grad_norm": 0.5445241332054138, "learning_rate": 2.7295179016922912e-09, "loss": 4.2841, "step": 32586 }, { "epoch": 0.9953268173488088, "grad_norm": 0.5462916493415833, "learning_rate": 2.6941853437295606e-09, "loss": 4.2703, "step": 32587 }, { "epoch": 0.9953573610262676, "grad_norm": 0.5424567461013794, "learning_rate": 2.6590829488137845e-09, "loss": 4.2464, "step": 32588 }, { "epoch": 0.9953879047037263, "grad_norm": 0.5469291806221008, "learning_rate": 2.6242107172669285e-09, "loss": 4.217, "step": 32589 }, { "epoch": 0.9954184483811851, "grad_norm": 0.5425596237182617, "learning_rate": 2.589568649410956e-09, "loss": 4.272, "step": 32590 }, { "epoch": 0.9954489920586439, "grad_norm": 0.5331712961196899, "learning_rate": 2.5551567455678326e-09, "loss": 4.2383, "step": 32591 }, { "epoch": 0.9954795357361026, "grad_norm": 0.5522869229316711, "learning_rate": 2.5209750060484205e-09, "loss": 4.1979, "step": 32592 }, { "epoch": 0.9955100794135614, "grad_norm": 0.5472468137741089, "learning_rate": 2.4870234311746843e-09, "loss": 4.3048, "step": 32593 }, { "epoch": 0.9955406230910202, "grad_norm": 0.53632652759552, "learning_rate": 2.4533020212519355e-09, "loss": 4.2875, "step": 32594 }, { "epoch": 0.9955711667684789, "grad_norm": 0.5410551428794861, "learning_rate": 2.419810776596587e-09, "loss": 4.2638, "step": 32595 }, { "epoch": 0.9956017104459377, "grad_norm": 0.5489333868026733, "learning_rate": 2.3865496975111758e-09, "loss": 4.2562, "step": 32596 }, { "epoch": 0.9956322541233965, "grad_norm": 0.5322604179382324, "learning_rate": 2.3535187843093387e-09, "loss": 4.1422, "step": 32597 }, { "epoch": 0.9956627978008552, "grad_norm": 0.5394793152809143, "learning_rate": 2.320718037288061e-09, "loss": 4.1675, "step": 32598 }, { "epoch": 0.995693341478314, "grad_norm": 0.5430273413658142, "learning_rate": 2.2881474567554296e-09, "loss": 4.2179, "step": 32599 }, { "epoch": 0.9957238851557727, "grad_norm": 0.5353436470031738, "learning_rate": 2.2558070430056533e-09, "loss": 4.0835, "step": 32600 }, { "epoch": 0.9957544288332315, "grad_norm": 0.5380871295928955, "learning_rate": 2.223696796341268e-09, "loss": 4.3078, "step": 32601 }, { "epoch": 0.9957849725106903, "grad_norm": 0.5361379384994507, "learning_rate": 2.1918167170537074e-09, "loss": 4.272, "step": 32602 }, { "epoch": 0.995815516188149, "grad_norm": 0.5466609597206116, "learning_rate": 2.160166805439956e-09, "loss": 4.1454, "step": 32603 }, { "epoch": 0.9958460598656078, "grad_norm": 0.5485112071037292, "learning_rate": 2.1287470617886716e-09, "loss": 4.1804, "step": 32604 }, { "epoch": 0.9958766035430666, "grad_norm": 0.5437322854995728, "learning_rate": 2.097557486394064e-09, "loss": 4.332, "step": 32605 }, { "epoch": 0.9959071472205253, "grad_norm": 0.5391164422035217, "learning_rate": 2.0665980795364637e-09, "loss": 4.2443, "step": 32606 }, { "epoch": 0.9959376908979841, "grad_norm": 0.5434402823448181, "learning_rate": 2.0358688415073048e-09, "loss": 4.2389, "step": 32607 }, { "epoch": 0.9959682345754429, "grad_norm": 0.5440785884857178, "learning_rate": 2.0053697725841425e-09, "loss": 4.2802, "step": 32608 }, { "epoch": 0.9959987782529016, "grad_norm": 0.5441839098930359, "learning_rate": 1.975100873050084e-09, "loss": 4.2351, "step": 32609 }, { "epoch": 0.9960293219303604, "grad_norm": 0.54057776927948, "learning_rate": 1.945062143185461e-09, "loss": 4.2227, "step": 32610 }, { "epoch": 0.9960598656078192, "grad_norm": 0.5376168489456177, "learning_rate": 1.9152535832650533e-09, "loss": 4.0847, "step": 32611 }, { "epoch": 0.9960904092852779, "grad_norm": 0.5402939319610596, "learning_rate": 1.885675193563641e-09, "loss": 4.2016, "step": 32612 }, { "epoch": 0.9961209529627367, "grad_norm": 0.544700026512146, "learning_rate": 1.8563269743532285e-09, "loss": 4.3023, "step": 32613 }, { "epoch": 0.9961514966401955, "grad_norm": 0.5335965752601624, "learning_rate": 1.827208925905821e-09, "loss": 4.2368, "step": 32614 }, { "epoch": 0.9961820403176542, "grad_norm": 0.5372351408004761, "learning_rate": 1.7983210484850964e-09, "loss": 4.198, "step": 32615 }, { "epoch": 0.996212583995113, "grad_norm": 0.5503082871437073, "learning_rate": 1.7696633423630592e-09, "loss": 4.2558, "step": 32616 }, { "epoch": 0.9962431276725717, "grad_norm": 0.5351253747940063, "learning_rate": 1.741235807800612e-09, "loss": 4.1816, "step": 32617 }, { "epoch": 0.9962736713500305, "grad_norm": 0.5422622561454773, "learning_rate": 1.7130384450558811e-09, "loss": 4.2601, "step": 32618 }, { "epoch": 0.9963042150274893, "grad_norm": 0.5339477062225342, "learning_rate": 1.6850712543953206e-09, "loss": 4.258, "step": 32619 }, { "epoch": 0.996334758704948, "grad_norm": 0.5351950526237488, "learning_rate": 1.657334236071506e-09, "loss": 4.1776, "step": 32620 }, { "epoch": 0.9963653023824068, "grad_norm": 0.5395336747169495, "learning_rate": 1.6298273903425643e-09, "loss": 4.2252, "step": 32621 }, { "epoch": 0.9963958460598656, "grad_norm": 0.5403858423233032, "learning_rate": 1.602550717461071e-09, "loss": 4.1108, "step": 32622 }, { "epoch": 0.9964263897373243, "grad_norm": 0.5423550605773926, "learning_rate": 1.5755042176768264e-09, "loss": 4.3221, "step": 32623 }, { "epoch": 0.9964569334147831, "grad_norm": 0.5433358550071716, "learning_rate": 1.5486878912396307e-09, "loss": 4.2316, "step": 32624 }, { "epoch": 0.996487477092242, "grad_norm": 0.551796555519104, "learning_rate": 1.5221017383965086e-09, "loss": 4.1759, "step": 32625 }, { "epoch": 0.9965180207697006, "grad_norm": 0.5408788919448853, "learning_rate": 1.4957457593944846e-09, "loss": 4.2007, "step": 32626 }, { "epoch": 0.9965485644471594, "grad_norm": 0.5463103652000427, "learning_rate": 1.4696199544722567e-09, "loss": 4.2375, "step": 32627 }, { "epoch": 0.9965791081246183, "grad_norm": 0.5365496277809143, "learning_rate": 1.4437243238712984e-09, "loss": 4.2978, "step": 32628 }, { "epoch": 0.996609651802077, "grad_norm": 0.5388103127479553, "learning_rate": 1.418058867833083e-09, "loss": 4.2303, "step": 32629 }, { "epoch": 0.9966401954795358, "grad_norm": 0.5421556830406189, "learning_rate": 1.3926235865907577e-09, "loss": 4.236, "step": 32630 }, { "epoch": 0.9966707391569946, "grad_norm": 0.5285962820053101, "learning_rate": 1.3674184803774693e-09, "loss": 4.1961, "step": 32631 }, { "epoch": 0.9967012828344533, "grad_norm": 0.5459372401237488, "learning_rate": 1.3424435494319154e-09, "loss": 4.3065, "step": 32632 }, { "epoch": 0.9967318265119121, "grad_norm": 0.5452320575714111, "learning_rate": 1.3176987939761409e-09, "loss": 4.2852, "step": 32633 }, { "epoch": 0.9967623701893707, "grad_norm": 0.5365524888038635, "learning_rate": 1.2931842142432926e-09, "loss": 4.265, "step": 32634 }, { "epoch": 0.9967929138668296, "grad_norm": 0.5414062738418579, "learning_rate": 1.268899810455415e-09, "loss": 4.3095, "step": 32635 }, { "epoch": 0.9968234575442884, "grad_norm": 0.5456399321556091, "learning_rate": 1.2448455828373284e-09, "loss": 4.162, "step": 32636 }, { "epoch": 0.996854001221747, "grad_norm": 0.5427981019020081, "learning_rate": 1.221021531613853e-09, "loss": 4.1715, "step": 32637 }, { "epoch": 0.9968845448992059, "grad_norm": 0.5365437865257263, "learning_rate": 1.1974276569987065e-09, "loss": 4.29, "step": 32638 }, { "epoch": 0.9969150885766647, "grad_norm": 0.546474039554596, "learning_rate": 1.1740639592139336e-09, "loss": 4.3102, "step": 32639 }, { "epoch": 0.9969456322541234, "grad_norm": 0.5456947684288025, "learning_rate": 1.1509304384704766e-09, "loss": 4.2344, "step": 32640 }, { "epoch": 0.9969761759315822, "grad_norm": 0.5421507954597473, "learning_rate": 1.1280270949876048e-09, "loss": 4.2927, "step": 32641 }, { "epoch": 0.997006719609041, "grad_norm": 0.5323403477668762, "learning_rate": 1.1053539289679338e-09, "loss": 4.1802, "step": 32642 }, { "epoch": 0.9970372632864997, "grad_norm": 0.5486793518066406, "learning_rate": 1.0829109406251814e-09, "loss": 4.2869, "step": 32643 }, { "epoch": 0.9970678069639585, "grad_norm": 0.5439022183418274, "learning_rate": 1.0606981301675144e-09, "loss": 4.3147, "step": 32644 }, { "epoch": 0.9970983506414173, "grad_norm": 0.5444372892379761, "learning_rate": 1.0387154977947732e-09, "loss": 4.3319, "step": 32645 }, { "epoch": 0.997128894318876, "grad_norm": 0.5415830612182617, "learning_rate": 1.016963043712349e-09, "loss": 4.1969, "step": 32646 }, { "epoch": 0.9971594379963348, "grad_norm": 0.5362542867660522, "learning_rate": 9.954407681228573e-10, "loss": 4.203, "step": 32647 }, { "epoch": 0.9971899816737936, "grad_norm": 0.5431903004646301, "learning_rate": 9.741486712178116e-10, "loss": 4.1948, "step": 32648 }, { "epoch": 0.9972205253512523, "grad_norm": 0.552909791469574, "learning_rate": 9.530867531970523e-10, "loss": 4.1829, "step": 32649 }, { "epoch": 0.9972510690287111, "grad_norm": 0.5574637055397034, "learning_rate": 9.322550142576435e-10, "loss": 4.1338, "step": 32650 }, { "epoch": 0.9972816127061698, "grad_norm": 0.5403703451156616, "learning_rate": 9.116534545855482e-10, "loss": 4.156, "step": 32651 }, { "epoch": 0.9973121563836286, "grad_norm": 0.5467530488967896, "learning_rate": 8.91282074375055e-10, "loss": 4.2114, "step": 32652 }, { "epoch": 0.9973427000610874, "grad_norm": 0.5455836057662964, "learning_rate": 8.711408738093508e-10, "loss": 4.2944, "step": 32653 }, { "epoch": 0.9973732437385461, "grad_norm": 0.5407625436782837, "learning_rate": 8.512298530771734e-10, "loss": 4.3111, "step": 32654 }, { "epoch": 0.9974037874160049, "grad_norm": 0.5524365305900574, "learning_rate": 8.315490123617098e-10, "loss": 4.2862, "step": 32655 }, { "epoch": 0.9974343310934637, "grad_norm": 0.5412649512290955, "learning_rate": 8.120983518433712e-10, "loss": 4.2852, "step": 32656 }, { "epoch": 0.9974648747709224, "grad_norm": 0.5465620160102844, "learning_rate": 7.928778716997931e-10, "loss": 4.2752, "step": 32657 }, { "epoch": 0.9974954184483812, "grad_norm": 0.5459195971488953, "learning_rate": 7.738875721113869e-10, "loss": 4.284, "step": 32658 }, { "epoch": 0.99752596212584, "grad_norm": 0.548629879951477, "learning_rate": 7.551274532502372e-10, "loss": 4.225, "step": 32659 }, { "epoch": 0.9975565058032987, "grad_norm": 0.5525393486022949, "learning_rate": 7.365975152912041e-10, "loss": 4.3349, "step": 32660 }, { "epoch": 0.9975870494807575, "grad_norm": 0.5423112511634827, "learning_rate": 7.182977584035966e-10, "loss": 4.1897, "step": 32661 }, { "epoch": 0.9976175931582163, "grad_norm": 0.5389964580535889, "learning_rate": 7.002281827539481e-10, "loss": 4.2742, "step": 32662 }, { "epoch": 0.997648136835675, "grad_norm": 0.53514564037323, "learning_rate": 6.823887885115676e-10, "loss": 4.2791, "step": 32663 }, { "epoch": 0.9976786805131338, "grad_norm": 0.5499048829078674, "learning_rate": 6.647795758402131e-10, "loss": 4.2942, "step": 32664 }, { "epoch": 0.9977092241905925, "grad_norm": 0.5501970052719116, "learning_rate": 6.474005449008669e-10, "loss": 4.2287, "step": 32665 }, { "epoch": 0.9977397678680513, "grad_norm": 0.5541762709617615, "learning_rate": 6.302516958572869e-10, "loss": 4.3015, "step": 32666 }, { "epoch": 0.9977703115455101, "grad_norm": 0.5435750484466553, "learning_rate": 6.133330288621286e-10, "loss": 4.2023, "step": 32667 }, { "epoch": 0.9978008552229688, "grad_norm": 0.5450738072395325, "learning_rate": 5.966445440735991e-10, "loss": 4.2931, "step": 32668 }, { "epoch": 0.9978313989004276, "grad_norm": 0.5376171469688416, "learning_rate": 5.801862416443537e-10, "loss": 4.21, "step": 32669 }, { "epoch": 0.9978619425778864, "grad_norm": 0.5484237670898438, "learning_rate": 5.639581217270485e-10, "loss": 4.1827, "step": 32670 }, { "epoch": 0.9978924862553451, "grad_norm": 0.5441884994506836, "learning_rate": 5.479601844715631e-10, "loss": 4.2513, "step": 32671 }, { "epoch": 0.9979230299328039, "grad_norm": 0.5360386371612549, "learning_rate": 5.321924300222269e-10, "loss": 4.2756, "step": 32672 }, { "epoch": 0.9979535736102627, "grad_norm": 0.5702599287033081, "learning_rate": 5.166548585289199e-10, "loss": 4.2203, "step": 32673 }, { "epoch": 0.9979841172877214, "grad_norm": 0.5486243367195129, "learning_rate": 5.013474701304199e-10, "loss": 4.2641, "step": 32674 }, { "epoch": 0.9980146609651802, "grad_norm": 0.5359280109405518, "learning_rate": 4.86270264971056e-10, "loss": 4.2376, "step": 32675 }, { "epoch": 0.998045204642639, "grad_norm": 0.5529439449310303, "learning_rate": 4.714232431896059e-10, "loss": 4.3235, "step": 32676 }, { "epoch": 0.9980757483200977, "grad_norm": 0.5408813953399658, "learning_rate": 4.568064049192966e-10, "loss": 4.2113, "step": 32677 }, { "epoch": 0.9981062919975565, "grad_norm": 0.5324466824531555, "learning_rate": 4.424197502961303e-10, "loss": 4.2106, "step": 32678 }, { "epoch": 0.9981368356750153, "grad_norm": 0.5497049689292908, "learning_rate": 4.2826327945333366e-10, "loss": 4.1196, "step": 32679 }, { "epoch": 0.998167379352474, "grad_norm": 0.5422528386116028, "learning_rate": 4.1433699252135804e-10, "loss": 4.2497, "step": 32680 }, { "epoch": 0.9981979230299328, "grad_norm": 0.5512937903404236, "learning_rate": 4.0064088962787906e-10, "loss": 4.2438, "step": 32681 }, { "epoch": 0.9982284667073915, "grad_norm": 0.5428279042243958, "learning_rate": 3.8717497089779674e-10, "loss": 4.3321, "step": 32682 }, { "epoch": 0.9982590103848503, "grad_norm": 0.5424405932426453, "learning_rate": 3.7393923645878684e-10, "loss": 4.2673, "step": 32683 }, { "epoch": 0.9982895540623091, "grad_norm": 0.5464704632759094, "learning_rate": 3.609336864301982e-10, "loss": 4.2327, "step": 32684 }, { "epoch": 0.9983200977397678, "grad_norm": 0.5458129048347473, "learning_rate": 3.481583209313799e-10, "loss": 4.1688, "step": 32685 }, { "epoch": 0.9983506414172266, "grad_norm": 0.5429912209510803, "learning_rate": 3.356131400816809e-10, "loss": 4.1294, "step": 32686 }, { "epoch": 0.9983811850946854, "grad_norm": 0.5460450053215027, "learning_rate": 3.23298143994899e-10, "loss": 4.1931, "step": 32687 }, { "epoch": 0.9984117287721441, "grad_norm": 0.539237916469574, "learning_rate": 3.112133327848321e-10, "loss": 4.1822, "step": 32688 }, { "epoch": 0.9984422724496029, "grad_norm": 0.5299618244171143, "learning_rate": 2.993587065625025e-10, "loss": 4.2393, "step": 32689 }, { "epoch": 0.9984728161270617, "grad_norm": 0.5478833317756653, "learning_rate": 2.8773426543893256e-10, "loss": 4.2789, "step": 32690 }, { "epoch": 0.9985033598045204, "grad_norm": 0.5617871880531311, "learning_rate": 2.7634000951681784e-10, "loss": 4.2206, "step": 32691 }, { "epoch": 0.9985339034819792, "grad_norm": 0.5413055419921875, "learning_rate": 2.6517593890718064e-10, "loss": 4.2792, "step": 32692 }, { "epoch": 0.998564447159438, "grad_norm": 0.5418848991394043, "learning_rate": 2.5424205370994106e-10, "loss": 4.2531, "step": 32693 }, { "epoch": 0.9985949908368967, "grad_norm": 0.5387137532234192, "learning_rate": 2.4353835402224355e-10, "loss": 4.2117, "step": 32694 }, { "epoch": 0.9986255345143555, "grad_norm": 0.5293691754341125, "learning_rate": 2.3306483994955943e-10, "loss": 4.2752, "step": 32695 }, { "epoch": 0.9986560781918143, "grad_norm": 0.5421976447105408, "learning_rate": 2.2282151158070642e-10, "loss": 4.2469, "step": 32696 }, { "epoch": 0.998686621869273, "grad_norm": 0.553848385810852, "learning_rate": 2.1280836901838018e-10, "loss": 4.2561, "step": 32697 }, { "epoch": 0.9987171655467318, "grad_norm": 0.5481463670730591, "learning_rate": 2.0302541234584748e-10, "loss": 4.236, "step": 32698 }, { "epoch": 0.9987477092241905, "grad_norm": 0.543698251247406, "learning_rate": 1.934726416602528e-10, "loss": 4.2989, "step": 32699 }, { "epoch": 0.9987782529016493, "grad_norm": 0.55169677734375, "learning_rate": 1.8415005704763842e-10, "loss": 4.1897, "step": 32700 }, { "epoch": 0.9988087965791081, "grad_norm": 0.5395405292510986, "learning_rate": 1.750576585912711e-10, "loss": 4.2321, "step": 32701 }, { "epoch": 0.9988393402565668, "grad_norm": 0.5448697805404663, "learning_rate": 1.6619544637996865e-10, "loss": 4.1605, "step": 32702 }, { "epoch": 0.9988698839340256, "grad_norm": 0.533403754234314, "learning_rate": 1.5756342048867112e-10, "loss": 4.2475, "step": 32703 }, { "epoch": 0.9989004276114845, "grad_norm": 0.5374626517295837, "learning_rate": 1.4916158100064526e-10, "loss": 4.2376, "step": 32704 }, { "epoch": 0.9989309712889431, "grad_norm": 0.5546663403511047, "learning_rate": 1.4098992799360668e-10, "loss": 4.171, "step": 32705 }, { "epoch": 0.998961514966402, "grad_norm": 0.5384698510169983, "learning_rate": 1.330484615424954e-10, "loss": 4.2156, "step": 32706 }, { "epoch": 0.9989920586438608, "grad_norm": 0.5439882278442383, "learning_rate": 1.253371817222515e-10, "loss": 4.2177, "step": 32707 }, { "epoch": 0.9990226023213195, "grad_norm": 0.5435536503791809, "learning_rate": 1.1785608859948838e-10, "loss": 4.2706, "step": 32708 }, { "epoch": 0.9990531459987783, "grad_norm": 0.5389096736907959, "learning_rate": 1.1060518224359495e-10, "loss": 4.1927, "step": 32709 }, { "epoch": 0.9990836896762371, "grad_norm": 0.5355575084686279, "learning_rate": 1.0358446272396017e-10, "loss": 4.2569, "step": 32710 }, { "epoch": 0.9991142333536958, "grad_norm": 0.538880467414856, "learning_rate": 9.679393010719739e-11, "loss": 4.1549, "step": 32711 }, { "epoch": 0.9991447770311546, "grad_norm": 0.5437731146812439, "learning_rate": 9.023358444881779e-11, "loss": 4.2648, "step": 32712 }, { "epoch": 0.9991753207086134, "grad_norm": 0.5431472063064575, "learning_rate": 8.390342581543476e-11, "loss": 4.2042, "step": 32713 }, { "epoch": 0.9992058643860721, "grad_norm": 0.5447849631309509, "learning_rate": 7.780345426255941e-11, "loss": 4.2599, "step": 32714 }, { "epoch": 0.9992364080635309, "grad_norm": 0.5316182971000671, "learning_rate": 7.193366984847849e-11, "loss": 4.2505, "step": 32715 }, { "epoch": 0.9992669517409896, "grad_norm": 0.5530226826667786, "learning_rate": 6.629407262592758e-11, "loss": 4.2238, "step": 32716 }, { "epoch": 0.9992974954184484, "grad_norm": 0.5393067002296448, "learning_rate": 6.08846626448667e-11, "loss": 4.1013, "step": 32717 }, { "epoch": 0.9993280390959072, "grad_norm": 0.5500429272651672, "learning_rate": 5.570543995803146e-11, "loss": 4.2825, "step": 32718 }, { "epoch": 0.9993585827733659, "grad_norm": 0.5433575510978699, "learning_rate": 5.0756404609830777e-11, "loss": 4.3167, "step": 32719 }, { "epoch": 0.9993891264508247, "grad_norm": 0.5405966639518738, "learning_rate": 4.603755665022469e-11, "loss": 4.221, "step": 32720 }, { "epoch": 0.9994196701282835, "grad_norm": 0.5362282395362854, "learning_rate": 4.154889612084656e-11, "loss": 4.2203, "step": 32721 }, { "epoch": 0.9994502138057422, "grad_norm": 0.5444602966308594, "learning_rate": 3.729042306055419e-11, "loss": 4.3133, "step": 32722 }, { "epoch": 0.999480757483201, "grad_norm": 0.5443046689033508, "learning_rate": 3.326213751375651e-11, "loss": 4.2125, "step": 32723 }, { "epoch": 0.9995113011606598, "grad_norm": 0.5440806746482849, "learning_rate": 2.9464039510984645e-11, "loss": 4.2204, "step": 32724 }, { "epoch": 0.9995418448381185, "grad_norm": 0.5457210540771484, "learning_rate": 2.5896129093871956e-11, "loss": 4.2112, "step": 32725 }, { "epoch": 0.9995723885155773, "grad_norm": 0.5483845472335815, "learning_rate": 2.2558406290174027e-11, "loss": 4.2966, "step": 32726 }, { "epoch": 0.9996029321930361, "grad_norm": 0.5411496758460999, "learning_rate": 1.9450871133197547e-11, "loss": 4.2242, "step": 32727 }, { "epoch": 0.9996334758704948, "grad_norm": 0.5394891500473022, "learning_rate": 1.6573523650698086e-11, "loss": 4.2327, "step": 32728 }, { "epoch": 0.9996640195479536, "grad_norm": 0.5688003897666931, "learning_rate": 1.3926363867655668e-11, "loss": 4.269, "step": 32729 }, { "epoch": 0.9996945632254124, "grad_norm": 0.5397461652755737, "learning_rate": 1.1509391811825866e-11, "loss": 4.2269, "step": 32730 }, { "epoch": 0.9997251069028711, "grad_norm": 0.5465231537818909, "learning_rate": 9.322607502637581e-12, "loss": 4.1615, "step": 32731 }, { "epoch": 0.9997556505803299, "grad_norm": 0.5428950786590576, "learning_rate": 7.366010962295278e-12, "loss": 4.2882, "step": 32732 }, { "epoch": 0.9997861942577886, "grad_norm": 0.5459716320037842, "learning_rate": 5.6396022074522995e-12, "loss": 4.1804, "step": 32733 }, { "epoch": 0.9998167379352474, "grad_norm": 0.542272686958313, "learning_rate": 4.143381254761991e-12, "loss": 4.205, "step": 32734 }, { "epoch": 0.9998472816127062, "grad_norm": 0.5343611836433411, "learning_rate": 2.877348118102141e-12, "loss": 4.1633, "step": 32735 }, { "epoch": 0.9998778252901649, "grad_norm": 0.5393187999725342, "learning_rate": 1.8415028085749797e-12, "loss": 4.273, "step": 32736 }, { "epoch": 0.9999083689676237, "grad_norm": 0.5446283221244812, "learning_rate": 1.0358453345071794e-12, "loss": 4.175, "step": 32737 }, { "epoch": 0.9999389126450825, "grad_norm": 0.5302468538284302, "learning_rate": 4.603757070009707e-13, "loss": 4.2226, "step": 32738 }, { "epoch": 0.9999694563225412, "grad_norm": 0.5402398705482483, "learning_rate": 1.1509392605635327e-13, "loss": 4.224, "step": 32739 }, { "epoch": 1.0, "grad_norm": 0.5451114177703857, "learning_rate": 0.0, "loss": 4.2501, "step": 32740 } ], "logging_steps": 1, "max_steps": 32740, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 12000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.53603113111126e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }