{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01599987200102399,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.999936000511996e-05,
      "grad_norm": 4.414881453815827,
      "learning_rate": 7.199424046076314e-09,
      "loss": 0.5441,
      "step": 10
    },
    {
      "epoch": 0.00015999872001023991,
      "grad_norm": 4.004957247533114,
      "learning_rate": 1.519878409727222e-08,
      "loss": 0.5353,
      "step": 20
    },
    {
      "epoch": 0.00023999808001535987,
      "grad_norm": 4.889790729834478,
      "learning_rate": 2.3198144148468124e-08,
      "loss": 0.537,
      "step": 30
    },
    {
      "epoch": 0.00031999744002047983,
      "grad_norm": 3.7138301639437508,
      "learning_rate": 3.119750419966403e-08,
      "loss": 0.5488,
      "step": 40
    },
    {
      "epoch": 0.0003999968000255998,
      "grad_norm": 4.208028943214464,
      "learning_rate": 3.919686425085993e-08,
      "loss": 0.5557,
      "step": 50
    },
    {
      "epoch": 0.00047999616003071974,
      "grad_norm": 4.326896533998126,
      "learning_rate": 4.719622430205584e-08,
      "loss": 0.5061,
      "step": 60
    },
    {
      "epoch": 0.0005599955200358397,
      "grad_norm": 7.1723877700496415,
      "learning_rate": 5.519558435325175e-08,
      "loss": 0.5193,
      "step": 70
    },
    {
      "epoch": 0.0006399948800409597,
      "grad_norm": 3.892238785520058,
      "learning_rate": 6.319494440444764e-08,
      "loss": 0.5311,
      "step": 80
    },
    {
      "epoch": 0.0007199942400460796,
      "grad_norm": 3.4517472540795513,
      "learning_rate": 7.119430445564356e-08,
      "loss": 0.5232,
      "step": 90
    },
    {
      "epoch": 0.0007999936000511996,
      "grad_norm": 4.094057558667446,
      "learning_rate": 7.919366450683946e-08,
      "loss": 0.5225,
      "step": 100
    },
    {
      "epoch": 0.0008799929600563195,
      "grad_norm": 3.4395682865399144,
      "learning_rate": 8.719302455803536e-08,
      "loss": 0.5371,
      "step": 110
    },
    {
      "epoch": 0.0009599923200614395,
      "grad_norm": 3.7029712275218682,
      "learning_rate": 9.519238460923127e-08,
      "loss": 0.5305,
      "step": 120
    },
    {
      "epoch": 0.0010399916800665594,
      "grad_norm": 3.493027269180126,
      "learning_rate": 1.0319174466042718e-07,
      "loss": 0.5167,
      "step": 130
    },
    {
      "epoch": 0.0011199910400716794,
      "grad_norm": 3.480790725115363,
      "learning_rate": 1.1119110471162308e-07,
      "loss": 0.5543,
      "step": 140
    },
    {
      "epoch": 0.0011999904000767993,
      "grad_norm": 3.0350778792458564,
      "learning_rate": 1.1919046476281897e-07,
      "loss": 0.5188,
      "step": 150
    },
    {
      "epoch": 0.0012799897600819193,
      "grad_norm": 2.7703962024693216,
      "learning_rate": 1.271898248140149e-07,
      "loss": 0.5176,
      "step": 160
    },
    {
      "epoch": 0.0013599891200870393,
      "grad_norm": 2.7312812150288277,
      "learning_rate": 1.351891848652108e-07,
      "loss": 0.5206,
      "step": 170
    },
    {
      "epoch": 0.0014399884800921593,
      "grad_norm": 2.6772442085163837,
      "learning_rate": 1.431885449164067e-07,
      "loss": 0.5187,
      "step": 180
    },
    {
      "epoch": 0.0015199878400972793,
      "grad_norm": 2.6017371604025503,
      "learning_rate": 1.5118790496760262e-07,
      "loss": 0.4858,
      "step": 190
    },
    {
      "epoch": 0.0015999872001023993,
      "grad_norm": 2.361921882047865,
      "learning_rate": 1.5918726501879854e-07,
      "loss": 0.4965,
      "step": 200
    },
    {
      "epoch": 0.0016799865601075192,
      "grad_norm": 1.9949603945902301,
      "learning_rate": 1.6718662506999443e-07,
      "loss": 0.49,
      "step": 210
    },
    {
      "epoch": 0.001759985920112639,
      "grad_norm": 1.689017850332906,
      "learning_rate": 1.7518598512119031e-07,
      "loss": 0.4474,
      "step": 220
    },
    {
      "epoch": 0.001839985280117759,
      "grad_norm": 1.7526108484730667,
      "learning_rate": 1.8318534517238623e-07,
      "loss": 0.4758,
      "step": 230
    },
    {
      "epoch": 0.001919984640122879,
      "grad_norm": 1.6619250196852287,
      "learning_rate": 1.9118470522358212e-07,
      "loss": 0.4551,
      "step": 240
    },
    {
      "epoch": 0.001999984000127999,
      "grad_norm": 1.4244411983222107,
      "learning_rate": 1.9918406527477803e-07,
      "loss": 0.4666,
      "step": 250
    },
    {
      "epoch": 0.0020799833601331187,
      "grad_norm": 1.4091371713945773,
      "learning_rate": 2.0718342532597392e-07,
      "loss": 0.4744,
      "step": 260
    },
    {
      "epoch": 0.002159982720138239,
      "grad_norm": 1.4037698231377602,
      "learning_rate": 2.1518278537716986e-07,
      "loss": 0.4577,
      "step": 270
    },
    {
      "epoch": 0.0022399820801433587,
      "grad_norm": 1.1233973407058262,
      "learning_rate": 2.2318214542836575e-07,
      "loss": 0.4442,
      "step": 280
    },
    {
      "epoch": 0.002319981440148479,
      "grad_norm": 1.0934034827825632,
      "learning_rate": 2.3118150547956164e-07,
      "loss": 0.4746,
      "step": 290
    },
    {
      "epoch": 0.0023999808001535987,
      "grad_norm": 0.9547032856231036,
      "learning_rate": 2.3918086553075753e-07,
      "loss": 0.4631,
      "step": 300
    },
    {
      "epoch": 0.002479980160158719,
      "grad_norm": 1.011447249716743,
      "learning_rate": 2.4718022558195345e-07,
      "loss": 0.4359,
      "step": 310
    },
    {
      "epoch": 0.0025599795201638386,
      "grad_norm": 0.7506687829382205,
      "learning_rate": 2.5517958563314936e-07,
      "loss": 0.4554,
      "step": 320
    },
    {
      "epoch": 0.002639978880168959,
      "grad_norm": 0.8268141903301145,
      "learning_rate": 2.631789456843453e-07,
      "loss": 0.4444,
      "step": 330
    },
    {
      "epoch": 0.0027199782401740786,
      "grad_norm": 0.9120933866995852,
      "learning_rate": 2.711783057355412e-07,
      "loss": 0.4662,
      "step": 340
    },
    {
      "epoch": 0.0027999776001791984,
      "grad_norm": 0.9481570868182263,
      "learning_rate": 2.791776657867371e-07,
      "loss": 0.4677,
      "step": 350
    },
    {
      "epoch": 0.0028799769601843186,
      "grad_norm": 0.8010445040150771,
      "learning_rate": 2.8717702583793297e-07,
      "loss": 0.4196,
      "step": 360
    },
    {
      "epoch": 0.0029599763201894383,
      "grad_norm": 0.8670839473253033,
      "learning_rate": 2.951763858891289e-07,
      "loss": 0.4492,
      "step": 370
    },
    {
      "epoch": 0.0030399756801945585,
      "grad_norm": 0.8536232676044045,
      "learning_rate": 3.031757459403248e-07,
      "loss": 0.4375,
      "step": 380
    },
    {
      "epoch": 0.0031199750401996783,
      "grad_norm": 0.8135677817452803,
      "learning_rate": 3.111751059915207e-07,
      "loss": 0.438,
      "step": 390
    },
    {
      "epoch": 0.0031999744002047985,
      "grad_norm": 0.9667962048008838,
      "learning_rate": 3.191744660427166e-07,
      "loss": 0.4348,
      "step": 400
    },
    {
      "epoch": 0.0032799737602099183,
      "grad_norm": 0.885059264680228,
      "learning_rate": 3.271738260939125e-07,
      "loss": 0.4295,
      "step": 410
    },
    {
      "epoch": 0.0033599731202150385,
      "grad_norm": 0.7112007856245484,
      "learning_rate": 3.3517318614510846e-07,
      "loss": 0.4412,
      "step": 420
    },
    {
      "epoch": 0.0034399724802201583,
      "grad_norm": 0.9486242885147141,
      "learning_rate": 3.431725461963043e-07,
      "loss": 0.4357,
      "step": 430
    },
    {
      "epoch": 0.003519971840225278,
      "grad_norm": 0.7792187180449996,
      "learning_rate": 3.5117190624750024e-07,
      "loss": 0.4053,
      "step": 440
    },
    {
      "epoch": 0.0035999712002303982,
      "grad_norm": 0.8013118911013118,
      "learning_rate": 3.591712662986961e-07,
      "loss": 0.4526,
      "step": 450
    },
    {
      "epoch": 0.003679970560235518,
      "grad_norm": 0.9290353407648725,
      "learning_rate": 3.6717062634989207e-07,
      "loss": 0.4394,
      "step": 460
    },
    {
      "epoch": 0.003759969920240638,
      "grad_norm": 0.7440275824040646,
      "learning_rate": 3.7516998640108793e-07,
      "loss": 0.4354,
      "step": 470
    },
    {
      "epoch": 0.003839969280245758,
      "grad_norm": 0.6661735557442742,
      "learning_rate": 3.8316934645228385e-07,
      "loss": 0.4132,
      "step": 480
    },
    {
      "epoch": 0.003919968640250878,
      "grad_norm": 0.80714967397643,
      "learning_rate": 3.9116870650347976e-07,
      "loss": 0.4247,
      "step": 490
    },
    {
      "epoch": 0.003999968000255998,
      "grad_norm": 0.7269691108846945,
      "learning_rate": 3.9916806655467563e-07,
      "loss": 0.4308,
      "step": 500
    },
    {
      "epoch": 0.004079967360261118,
      "grad_norm": 0.8112092339496537,
      "learning_rate": 4.071674266058716e-07,
      "loss": 0.4215,
      "step": 510
    },
    {
      "epoch": 0.0041599667202662375,
      "grad_norm": 0.8465738727092779,
      "learning_rate": 4.1516678665706746e-07,
      "loss": 0.4438,
      "step": 520
    },
    {
      "epoch": 0.004239966080271358,
      "grad_norm": 0.7947114246478345,
      "learning_rate": 4.2316614670826337e-07,
      "loss": 0.402,
      "step": 530
    },
    {
      "epoch": 0.004319965440276478,
      "grad_norm": 0.771445835897062,
      "learning_rate": 4.311655067594593e-07,
      "loss": 0.4434,
      "step": 540
    },
    {
      "epoch": 0.004399964800281598,
      "grad_norm": 0.7143580000434352,
      "learning_rate": 4.3916486681065515e-07,
      "loss": 0.4227,
      "step": 550
    },
    {
      "epoch": 0.004479964160286717,
      "grad_norm": 0.7487773075552359,
      "learning_rate": 4.471642268618511e-07,
      "loss": 0.438,
      "step": 560
    },
    {
      "epoch": 0.004559963520291838,
      "grad_norm": 0.7373810653849879,
      "learning_rate": 4.55163586913047e-07,
      "loss": 0.4288,
      "step": 570
    },
    {
      "epoch": 0.004639962880296958,
      "grad_norm": 0.7104505393064982,
      "learning_rate": 4.631629469642429e-07,
      "loss": 0.4462,
      "step": 580
    },
    {
      "epoch": 0.004719962240302078,
      "grad_norm": 0.6996674322090365,
      "learning_rate": 4.7116230701543876e-07,
      "loss": 0.4263,
      "step": 590
    },
    {
      "epoch": 0.004799961600307197,
      "grad_norm": 0.779468888606517,
      "learning_rate": 4.791616670666347e-07,
      "loss": 0.4378,
      "step": 600
    },
    {
      "epoch": 0.0048799609603123175,
      "grad_norm": 0.6348456379271163,
      "learning_rate": 4.871610271178306e-07,
      "loss": 0.4098,
      "step": 610
    },
    {
      "epoch": 0.004959960320317438,
      "grad_norm": 0.6384341588537313,
      "learning_rate": 4.951603871690265e-07,
      "loss": 0.4489,
      "step": 620
    },
    {
      "epoch": 0.005039959680322557,
      "grad_norm": 0.6779051066808497,
      "learning_rate": 5.031597472202224e-07,
      "loss": 0.4522,
      "step": 630
    },
    {
      "epoch": 0.005119959040327677,
      "grad_norm": 0.7405337420145796,
      "learning_rate": 5.111591072714183e-07,
      "loss": 0.4248,
      "step": 640
    },
    {
      "epoch": 0.0051999584003327975,
      "grad_norm": 0.6915688533513078,
      "learning_rate": 5.191584673226143e-07,
      "loss": 0.4129,
      "step": 650
    },
    {
      "epoch": 0.005279957760337918,
      "grad_norm": 0.6044444399034763,
      "learning_rate": 5.271578273738101e-07,
      "loss": 0.4237,
      "step": 660
    },
    {
      "epoch": 0.005359957120343037,
      "grad_norm": 0.7401624173362278,
      "learning_rate": 5.351571874250061e-07,
      "loss": 0.4216,
      "step": 670
    },
    {
      "epoch": 0.005439956480348157,
      "grad_norm": 0.7496141168534413,
      "learning_rate": 5.43156547476202e-07,
      "loss": 0.4268,
      "step": 680
    },
    {
      "epoch": 0.005519955840353277,
      "grad_norm": 0.730614366570662,
      "learning_rate": 5.511559075273978e-07,
      "loss": 0.4589,
      "step": 690
    },
    {
      "epoch": 0.005599955200358397,
      "grad_norm": 0.7836211351094068,
      "learning_rate": 5.591552675785937e-07,
      "loss": 0.4176,
      "step": 700
    },
    {
      "epoch": 0.005679954560363517,
      "grad_norm": 0.6648189022606215,
      "learning_rate": 5.671546276297896e-07,
      "loss": 0.4274,
      "step": 710
    },
    {
      "epoch": 0.005759953920368637,
      "grad_norm": 0.6607901995290275,
      "learning_rate": 5.751539876809856e-07,
      "loss": 0.428,
      "step": 720
    },
    {
      "epoch": 0.005839953280373757,
      "grad_norm": 0.8422142881250906,
      "learning_rate": 5.831533477321815e-07,
      "loss": 0.4206,
      "step": 730
    },
    {
      "epoch": 0.005919952640378877,
      "grad_norm": 0.8636103630308042,
      "learning_rate": 5.911527077833774e-07,
      "loss": 0.4384,
      "step": 740
    },
    {
      "epoch": 0.005999952000383997,
      "grad_norm": 0.7020283376881055,
      "learning_rate": 5.991520678345733e-07,
      "loss": 0.4336,
      "step": 750
    },
    {
      "epoch": 0.006079951360389117,
      "grad_norm": 0.6637768636661737,
      "learning_rate": 6.071514278857692e-07,
      "loss": 0.421,
      "step": 760
    },
    {
      "epoch": 0.006159950720394236,
      "grad_norm": 0.6720228370970702,
      "learning_rate": 6.151507879369651e-07,
      "loss": 0.4425,
      "step": 770
    },
    {
      "epoch": 0.006239950080399357,
      "grad_norm": 0.7915308024009126,
      "learning_rate": 6.231501479881609e-07,
      "loss": 0.4665,
      "step": 780
    },
    {
      "epoch": 0.006319949440404477,
      "grad_norm": 0.7005483141808596,
      "learning_rate": 6.311495080393569e-07,
      "loss": 0.4371,
      "step": 790
    },
    {
      "epoch": 0.006399948800409597,
      "grad_norm": 0.7085842808188052,
      "learning_rate": 6.391488680905528e-07,
      "loss": 0.4481,
      "step": 800
    },
    {
      "epoch": 0.006479948160414716,
      "grad_norm": 0.797364113205394,
      "learning_rate": 6.471482281417488e-07,
      "loss": 0.43,
      "step": 810
    },
    {
      "epoch": 0.0065599475204198366,
      "grad_norm": 0.7769920944189029,
      "learning_rate": 6.551475881929446e-07,
      "loss": 0.4421,
      "step": 820
    },
    {
      "epoch": 0.006639946880424957,
      "grad_norm": 0.7190098449382926,
      "learning_rate": 6.631469482441405e-07,
      "loss": 0.4524,
      "step": 830
    },
    {
      "epoch": 0.006719946240430077,
      "grad_norm": 0.8999089940382301,
      "learning_rate": 6.711463082953363e-07,
      "loss": 0.4327,
      "step": 840
    },
    {
      "epoch": 0.006799945600435196,
      "grad_norm": 0.8071258672281636,
      "learning_rate": 6.791456683465323e-07,
      "loss": 0.3999,
      "step": 850
    },
    {
      "epoch": 0.0068799449604403165,
      "grad_norm": 0.9718244104757909,
      "learning_rate": 6.871450283977283e-07,
      "loss": 0.4109,
      "step": 860
    },
    {
      "epoch": 0.006959944320445437,
      "grad_norm": 0.7260805899057289,
      "learning_rate": 6.951443884489241e-07,
      "loss": 0.4254,
      "step": 870
    },
    {
      "epoch": 0.007039943680450556,
      "grad_norm": 0.6793848246836304,
      "learning_rate": 7.031437485001201e-07,
      "loss": 0.4168,
      "step": 880
    },
    {
      "epoch": 0.007119943040455676,
      "grad_norm": 0.8220405330990818,
      "learning_rate": 7.11143108551316e-07,
      "loss": 0.4368,
      "step": 890
    },
    {
      "epoch": 0.0071999424004607964,
      "grad_norm": 0.8650021092848164,
      "learning_rate": 7.191424686025118e-07,
      "loss": 0.4336,
      "step": 900
    },
    {
      "epoch": 0.007279941760465917,
      "grad_norm": 0.6667689577948444,
      "learning_rate": 7.271418286537078e-07,
      "loss": 0.4325,
      "step": 910
    },
    {
      "epoch": 0.007359941120471036,
      "grad_norm": 0.6443211014509481,
      "learning_rate": 7.351411887049036e-07,
      "loss": 0.443,
      "step": 920
    },
    {
      "epoch": 0.007439940480476156,
      "grad_norm": 0.6067913066251965,
      "learning_rate": 7.431405487560996e-07,
      "loss": 0.4095,
      "step": 930
    },
    {
      "epoch": 0.007519939840481276,
      "grad_norm": 0.6935512372810877,
      "learning_rate": 7.511399088072954e-07,
      "loss": 0.4272,
      "step": 940
    },
    {
      "epoch": 0.007599939200486396,
      "grad_norm": 0.6599113657719949,
      "learning_rate": 7.591392688584914e-07,
      "loss": 0.3942,
      "step": 950
    },
    {
      "epoch": 0.007679938560491516,
      "grad_norm": 0.611225655896161,
      "learning_rate": 7.671386289096873e-07,
      "loss": 0.4451,
      "step": 960
    },
    {
      "epoch": 0.007759937920496636,
      "grad_norm": 0.757015652343119,
      "learning_rate": 7.751379889608831e-07,
      "loss": 0.4059,
      "step": 970
    },
    {
      "epoch": 0.007839937280501755,
      "grad_norm": 0.8456384517410107,
      "learning_rate": 7.831373490120791e-07,
      "loss": 0.4278,
      "step": 980
    },
    {
      "epoch": 0.007919936640506876,
      "grad_norm": 0.7996016208371923,
      "learning_rate": 7.911367090632751e-07,
      "loss": 0.4536,
      "step": 990
    },
    {
      "epoch": 0.007999936000511996,
      "grad_norm": 0.6228736248515305,
      "learning_rate": 7.991360691144709e-07,
      "loss": 0.3969,
      "step": 1000
    },
    {
      "epoch": 0.008079935360517116,
      "grad_norm": 0.6440105424946402,
      "learning_rate": 8.071354291656668e-07,
      "loss": 0.4307,
      "step": 1010
    },
    {
      "epoch": 0.008159934720522236,
      "grad_norm": 0.6636370756757088,
      "learning_rate": 8.151347892168628e-07,
      "loss": 0.4019,
      "step": 1020
    },
    {
      "epoch": 0.008239934080527356,
      "grad_norm": 0.6534728964626215,
      "learning_rate": 8.231341492680586e-07,
      "loss": 0.4357,
      "step": 1030
    },
    {
      "epoch": 0.008319933440532475,
      "grad_norm": 0.6854238349847609,
      "learning_rate": 8.311335093192545e-07,
      "loss": 0.4156,
      "step": 1040
    },
    {
      "epoch": 0.008399932800537595,
      "grad_norm": 0.7692797686595098,
      "learning_rate": 8.391328693704504e-07,
      "loss": 0.4364,
      "step": 1050
    },
    {
      "epoch": 0.008479932160542715,
      "grad_norm": 0.6892139807862941,
      "learning_rate": 8.471322294216464e-07,
      "loss": 0.4595,
      "step": 1060
    },
    {
      "epoch": 0.008559931520547836,
      "grad_norm": 0.6786670330601587,
      "learning_rate": 8.551315894728423e-07,
      "loss": 0.4207,
      "step": 1070
    },
    {
      "epoch": 0.008639930880552956,
      "grad_norm": 0.6118366771253826,
      "learning_rate": 8.631309495240381e-07,
      "loss": 0.4186,
      "step": 1080
    },
    {
      "epoch": 0.008719930240558076,
      "grad_norm": 0.7157718863255984,
      "learning_rate": 8.711303095752341e-07,
      "loss": 0.4412,
      "step": 1090
    },
    {
      "epoch": 0.008799929600563196,
      "grad_norm": 0.7102096103999658,
      "learning_rate": 8.791296696264299e-07,
      "loss": 0.4205,
      "step": 1100
    },
    {
      "epoch": 0.008879928960568315,
      "grad_norm": 0.6326552697725677,
      "learning_rate": 8.871290296776258e-07,
      "loss": 0.4161,
      "step": 1110
    },
    {
      "epoch": 0.008959928320573435,
      "grad_norm": 0.7455469536196851,
      "learning_rate": 8.951283897288219e-07,
      "loss": 0.4259,
      "step": 1120
    },
    {
      "epoch": 0.009039927680578555,
      "grad_norm": 0.8219540514047248,
      "learning_rate": 9.031277497800177e-07,
      "loss": 0.4423,
      "step": 1130
    },
    {
      "epoch": 0.009119927040583675,
      "grad_norm": 0.6428846698552027,
      "learning_rate": 9.111271098312136e-07,
      "loss": 0.432,
      "step": 1140
    },
    {
      "epoch": 0.009199926400588795,
      "grad_norm": 0.7959015617833209,
      "learning_rate": 9.191264698824094e-07,
      "loss": 0.4374,
      "step": 1150
    },
    {
      "epoch": 0.009279925760593916,
      "grad_norm": 0.722690696817927,
      "learning_rate": 9.271258299336054e-07,
      "loss": 0.4177,
      "step": 1160
    },
    {
      "epoch": 0.009359925120599036,
      "grad_norm": 0.7583146312532495,
      "learning_rate": 9.351251899848013e-07,
      "loss": 0.4349,
      "step": 1170
    },
    {
      "epoch": 0.009439924480604156,
      "grad_norm": 0.8841341873240007,
      "learning_rate": 9.431245500359971e-07,
      "loss": 0.4323,
      "step": 1180
    },
    {
      "epoch": 0.009519923840609274,
      "grad_norm": 0.6844990736142492,
      "learning_rate": 9.511239100871932e-07,
      "loss": 0.4195,
      "step": 1190
    },
    {
      "epoch": 0.009599923200614395,
      "grad_norm": 0.7129122863481299,
      "learning_rate": 9.59123270138389e-07,
      "loss": 0.4088,
      "step": 1200
    },
    {
      "epoch": 0.009679922560619515,
      "grad_norm": 0.6532760834208395,
      "learning_rate": 9.67122630189585e-07,
      "loss": 0.3969,
      "step": 1210
    },
    {
      "epoch": 0.009759921920624635,
      "grad_norm": 0.7563260927255472,
      "learning_rate": 9.75121990240781e-07,
      "loss": 0.4075,
      "step": 1220
    },
    {
      "epoch": 0.009839921280629755,
      "grad_norm": 0.7704505024635662,
      "learning_rate": 9.831213502919768e-07,
      "loss": 0.3981,
      "step": 1230
    },
    {
      "epoch": 0.009919920640634875,
      "grad_norm": 0.7056792723024738,
      "learning_rate": 9.911207103431725e-07,
      "loss": 0.4223,
      "step": 1240
    },
    {
      "epoch": 0.009999920000639996,
      "grad_norm": 0.750390399783068,
      "learning_rate": 9.991200703943684e-07,
      "loss": 0.4102,
      "step": 1250
    },
    {
      "epoch": 0.010079919360645114,
      "grad_norm": 0.7529460057363149,
      "learning_rate": 1.0071194304455646e-06,
      "loss": 0.4278,
      "step": 1260
    },
    {
      "epoch": 0.010159918720650234,
      "grad_norm": 1.041695148553965,
      "learning_rate": 1.0151187904967603e-06,
      "loss": 0.4261,
      "step": 1270
    },
    {
      "epoch": 0.010239918080655355,
      "grad_norm": 0.8098838670880232,
      "learning_rate": 1.0231181505479562e-06,
      "loss": 0.4163,
      "step": 1280
    },
    {
      "epoch": 0.010319917440660475,
      "grad_norm": 0.7139180273227849,
      "learning_rate": 1.0311175105991523e-06,
      "loss": 0.4139,
      "step": 1290
    },
    {
      "epoch": 0.010399916800665595,
      "grad_norm": 0.7293628900497775,
      "learning_rate": 1.039116870650348e-06,
      "loss": 0.4139,
      "step": 1300
    },
    {
      "epoch": 0.010479916160670715,
      "grad_norm": 3.9899125178456276,
      "learning_rate": 1.047116230701544e-06,
      "loss": 0.4352,
      "step": 1310
    },
    {
      "epoch": 0.010559915520675835,
      "grad_norm": 0.741428608083807,
      "learning_rate": 1.0551155907527398e-06,
      "loss": 0.4487,
      "step": 1320
    },
    {
      "epoch": 0.010639914880680954,
      "grad_norm": 0.7645959836257802,
      "learning_rate": 1.0631149508039358e-06,
      "loss": 0.4509,
      "step": 1330
    },
    {
      "epoch": 0.010719914240686074,
      "grad_norm": 0.6630163901596575,
      "learning_rate": 1.0711143108551317e-06,
      "loss": 0.422,
      "step": 1340
    },
    {
      "epoch": 0.010799913600691194,
      "grad_norm": 0.7653242364061862,
      "learning_rate": 1.0791136709063276e-06,
      "loss": 0.4047,
      "step": 1350
    },
    {
      "epoch": 0.010879912960696314,
      "grad_norm": 0.6952138151449674,
      "learning_rate": 1.0871130309575235e-06,
      "loss": 0.424,
      "step": 1360
    },
    {
      "epoch": 0.010959912320701435,
      "grad_norm": 0.8400358998787617,
      "learning_rate": 1.0951123910087194e-06,
      "loss": 0.4329,
      "step": 1370
    },
    {
      "epoch": 0.011039911680706555,
      "grad_norm": 0.7959368745719518,
      "learning_rate": 1.1031117510599153e-06,
      "loss": 0.4296,
      "step": 1380
    },
    {
      "epoch": 0.011119911040711675,
      "grad_norm": 0.7182831330712102,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.4053,
      "step": 1390
    },
    {
      "epoch": 0.011199910400716794,
      "grad_norm": 0.7631459457678664,
      "learning_rate": 1.1191104711623072e-06,
      "loss": 0.4174,
      "step": 1400
    },
    {
      "epoch": 0.011279909760721914,
      "grad_norm": 0.6904060292491346,
      "learning_rate": 1.127109831213503e-06,
      "loss": 0.4262,
      "step": 1410
    },
    {
      "epoch": 0.011359909120727034,
      "grad_norm": 0.7154968430224656,
      "learning_rate": 1.1351091912646988e-06,
      "loss": 0.4116,
      "step": 1420
    },
    {
      "epoch": 0.011439908480732154,
      "grad_norm": 0.6430506977204669,
      "learning_rate": 1.143108551315895e-06,
      "loss": 0.3985,
      "step": 1430
    },
    {
      "epoch": 0.011519907840737274,
      "grad_norm": 0.6060536937789834,
      "learning_rate": 1.1511079113670908e-06,
      "loss": 0.4366,
      "step": 1440
    },
    {
      "epoch": 0.011599907200742395,
      "grad_norm": 0.7070045694797042,
      "learning_rate": 1.1591072714182865e-06,
      "loss": 0.3951,
      "step": 1450
    },
    {
      "epoch": 0.011679906560747515,
      "grad_norm": 0.6799481270205386,
      "learning_rate": 1.1671066314694824e-06,
      "loss": 0.4277,
      "step": 1460
    },
    {
      "epoch": 0.011759905920752633,
      "grad_norm": 0.7706688131579046,
      "learning_rate": 1.1751059915206786e-06,
      "loss": 0.4106,
      "step": 1470
    },
    {
      "epoch": 0.011839905280757753,
      "grad_norm": 0.7659401655636618,
      "learning_rate": 1.1831053515718743e-06,
      "loss": 0.4147,
      "step": 1480
    },
    {
      "epoch": 0.011919904640762874,
      "grad_norm": 0.7880351649260696,
      "learning_rate": 1.1911047116230702e-06,
      "loss": 0.4018,
      "step": 1490
    },
    {
      "epoch": 0.011999904000767994,
      "grad_norm": 0.6643952514129879,
      "learning_rate": 1.1991040716742661e-06,
      "loss": 0.4225,
      "step": 1500
    },
    {
      "epoch": 0.012079903360773114,
      "grad_norm": 0.7410891062680932,
      "learning_rate": 1.207103431725462e-06,
      "loss": 0.4235,
      "step": 1510
    },
    {
      "epoch": 0.012159902720778234,
      "grad_norm": 0.6702465025094532,
      "learning_rate": 1.215102791776658e-06,
      "loss": 0.4485,
      "step": 1520
    },
    {
      "epoch": 0.012239902080783354,
      "grad_norm": 0.72511805103151,
      "learning_rate": 1.2231021518278539e-06,
      "loss": 0.4075,
      "step": 1530
    },
    {
      "epoch": 0.012319901440788473,
      "grad_norm": 0.7364457263640842,
      "learning_rate": 1.2311015118790498e-06,
      "loss": 0.4209,
      "step": 1540
    },
    {
      "epoch": 0.012399900800793593,
      "grad_norm": 0.6760801533876919,
      "learning_rate": 1.2391008719302457e-06,
      "loss": 0.4153,
      "step": 1550
    },
    {
      "epoch": 0.012479900160798713,
      "grad_norm": 1.329240774622819,
      "learning_rate": 1.2471002319814416e-06,
      "loss": 0.4569,
      "step": 1560
    },
    {
      "epoch": 0.012559899520803833,
      "grad_norm": 0.7197695590369367,
      "learning_rate": 1.2550995920326375e-06,
      "loss": 0.4148,
      "step": 1570
    },
    {
      "epoch": 0.012639898880808954,
      "grad_norm": 0.7197146321929337,
      "learning_rate": 1.2630989520838332e-06,
      "loss": 0.4309,
      "step": 1580
    },
    {
      "epoch": 0.012719898240814074,
      "grad_norm": 0.6941046794760515,
      "learning_rate": 1.2710983121350293e-06,
      "loss": 0.4266,
      "step": 1590
    },
    {
      "epoch": 0.012799897600819194,
      "grad_norm": 0.6685733935987979,
      "learning_rate": 1.2790976721862253e-06,
      "loss": 0.4148,
      "step": 1600
    },
    {
      "epoch": 0.012879896960824314,
      "grad_norm": 0.829963069106683,
      "learning_rate": 1.287097032237421e-06,
      "loss": 0.438,
      "step": 1610
    },
    {
      "epoch": 0.012959896320829433,
      "grad_norm": 0.8772001383565942,
      "learning_rate": 1.295096392288617e-06,
      "loss": 0.4167,
      "step": 1620
    },
    {
      "epoch": 0.013039895680834553,
      "grad_norm": 0.7693529714105686,
      "learning_rate": 1.303095752339813e-06,
      "loss": 0.4465,
      "step": 1630
    },
    {
      "epoch": 0.013119895040839673,
      "grad_norm": 0.6969819161826472,
      "learning_rate": 1.3110951123910087e-06,
      "loss": 0.4374,
      "step": 1640
    },
    {
      "epoch": 0.013199894400844793,
      "grad_norm": 0.7245418409893126,
      "learning_rate": 1.3190944724422048e-06,
      "loss": 0.4375,
      "step": 1650
    },
    {
      "epoch": 0.013279893760849914,
      "grad_norm": 0.6704658854506884,
      "learning_rate": 1.3270938324934008e-06,
      "loss": 0.4144,
      "step": 1660
    },
    {
      "epoch": 0.013359893120855034,
      "grad_norm": 0.7596780468310279,
      "learning_rate": 1.3350931925445965e-06,
      "loss": 0.4142,
      "step": 1670
    },
    {
      "epoch": 0.013439892480860154,
      "grad_norm": 0.799033496950235,
      "learning_rate": 1.3430925525957924e-06,
      "loss": 0.424,
      "step": 1680
    },
    {
      "epoch": 0.013519891840865272,
      "grad_norm": 0.8360146268303155,
      "learning_rate": 1.3510919126469885e-06,
      "loss": 0.4104,
      "step": 1690
    },
    {
      "epoch": 0.013599891200870393,
      "grad_norm": 0.7830381641790578,
      "learning_rate": 1.3590912726981842e-06,
      "loss": 0.4067,
      "step": 1700
    },
    {
      "epoch": 0.013679890560875513,
      "grad_norm": 0.7376045815830132,
      "learning_rate": 1.3670906327493801e-06,
      "loss": 0.4232,
      "step": 1710
    },
    {
      "epoch": 0.013759889920880633,
      "grad_norm": 0.7780257393234633,
      "learning_rate": 1.3750899928005762e-06,
      "loss": 0.4001,
      "step": 1720
    },
    {
      "epoch": 0.013839889280885753,
      "grad_norm": 0.7400853428241427,
      "learning_rate": 1.383089352851772e-06,
      "loss": 0.4283,
      "step": 1730
    },
    {
      "epoch": 0.013919888640890873,
      "grad_norm": 0.6301335389858812,
      "learning_rate": 1.3910887129029679e-06,
      "loss": 0.4315,
      "step": 1740
    },
    {
      "epoch": 0.013999888000895994,
      "grad_norm": 0.6873058205506691,
      "learning_rate": 1.3990880729541636e-06,
      "loss": 0.4294,
      "step": 1750
    },
    {
      "epoch": 0.014079887360901112,
      "grad_norm": 0.6118849450571252,
      "learning_rate": 1.4070874330053597e-06,
      "loss": 0.4116,
      "step": 1760
    },
    {
      "epoch": 0.014159886720906232,
      "grad_norm": 0.8643963519063279,
      "learning_rate": 1.4150867930565556e-06,
      "loss": 0.4189,
      "step": 1770
    },
    {
      "epoch": 0.014239886080911352,
      "grad_norm": 0.6986286668684888,
      "learning_rate": 1.4230861531077513e-06,
      "loss": 0.4393,
      "step": 1780
    },
    {
      "epoch": 0.014319885440916473,
      "grad_norm": 0.7361554237470329,
      "learning_rate": 1.4310855131589474e-06,
      "loss": 0.4048,
      "step": 1790
    },
    {
      "epoch": 0.014399884800921593,
      "grad_norm": 0.7526595512221772,
      "learning_rate": 1.4390848732101434e-06,
      "loss": 0.4434,
      "step": 1800
    },
    {
      "epoch": 0.014479884160926713,
      "grad_norm": 0.6793121490590498,
      "learning_rate": 1.447084233261339e-06,
      "loss": 0.4313,
      "step": 1810
    },
    {
      "epoch": 0.014559883520931833,
      "grad_norm": 0.7503593630371851,
      "learning_rate": 1.4550835933125352e-06,
      "loss": 0.4363,
      "step": 1820
    },
    {
      "epoch": 0.014639882880936952,
      "grad_norm": 0.6631126747097913,
      "learning_rate": 1.463082953363731e-06,
      "loss": 0.4172,
      "step": 1830
    },
    {
      "epoch": 0.014719882240942072,
      "grad_norm": 0.6201041671912539,
      "learning_rate": 1.4710823134149268e-06,
      "loss": 0.426,
      "step": 1840
    },
    {
      "epoch": 0.014799881600947192,
      "grad_norm": 0.7986575840999489,
      "learning_rate": 1.479081673466123e-06,
      "loss": 0.4418,
      "step": 1850
    },
    {
      "epoch": 0.014879880960952312,
      "grad_norm": 0.7485644191714067,
      "learning_rate": 1.4870810335173188e-06,
      "loss": 0.4315,
      "step": 1860
    },
    {
      "epoch": 0.014959880320957433,
      "grad_norm": 0.767180980787683,
      "learning_rate": 1.4950803935685146e-06,
      "loss": 0.44,
      "step": 1870
    },
    {
      "epoch": 0.015039879680962553,
      "grad_norm": 0.7085244935047633,
      "learning_rate": 1.5030797536197107e-06,
      "loss": 0.4197,
      "step": 1880
    },
    {
      "epoch": 0.015119879040967673,
      "grad_norm": 0.9096558305501717,
      "learning_rate": 1.5110791136709064e-06,
      "loss": 0.4276,
      "step": 1890
    },
    {
      "epoch": 0.015199878400972791,
      "grad_norm": 0.7782449144127891,
      "learning_rate": 1.5190784737221023e-06,
      "loss": 0.4433,
      "step": 1900
    },
    {
      "epoch": 0.015279877760977912,
      "grad_norm": 0.6784288997728832,
      "learning_rate": 1.5270778337732984e-06,
      "loss": 0.408,
      "step": 1910
    },
    {
      "epoch": 0.015359877120983032,
      "grad_norm": 0.7394160138728095,
      "learning_rate": 1.5350771938244941e-06,
      "loss": 0.427,
      "step": 1920
    },
    {
      "epoch": 0.015439876480988152,
      "grad_norm": 0.7020184796096351,
      "learning_rate": 1.54307655387569e-06,
      "loss": 0.4585,
      "step": 1930
    },
    {
      "epoch": 0.015519875840993272,
      "grad_norm": 0.6570216742745165,
      "learning_rate": 1.551075913926886e-06,
      "loss": 0.4203,
      "step": 1940
    },
    {
      "epoch": 0.015599875200998392,
      "grad_norm": 0.6492915506893296,
      "learning_rate": 1.5590752739780819e-06,
      "loss": 0.4225,
      "step": 1950
    },
    {
      "epoch": 0.01567987456100351,
      "grad_norm": 0.6404207960330748,
      "learning_rate": 1.5670746340292778e-06,
      "loss": 0.4155,
      "step": 1960
    },
    {
      "epoch": 0.01575987392100863,
      "grad_norm": 0.7069937527425317,
      "learning_rate": 1.5750739940804737e-06,
      "loss": 0.4017,
      "step": 1970
    },
    {
      "epoch": 0.01583987328101375,
      "grad_norm": 0.7497814910327999,
      "learning_rate": 1.5830733541316694e-06,
      "loss": 0.4336,
      "step": 1980
    },
    {
      "epoch": 0.01591987264101887,
      "grad_norm": 0.997502334828043,
      "learning_rate": 1.5910727141828655e-06,
      "loss": 0.4252,
      "step": 1990
    },
    {
      "epoch": 0.01599987200102399,
      "grad_norm": 0.7051737520195863,
      "learning_rate": 1.5990720742340615e-06,
      "loss": 0.4136,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 125001,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 115736344297472.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}