{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32647730982696704,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010882576994232234,
      "grad_norm": 0.5460862517356873,
      "learning_rate": 1.8e-05,
      "loss": 4.743990707397461,
      "step": 10
    },
    {
      "epoch": 0.0021765153988464467,
      "grad_norm": 0.40822282433509827,
      "learning_rate": 3.8e-05,
      "loss": 4.506277847290039,
      "step": 20
    },
    {
      "epoch": 0.00326477309826967,
      "grad_norm": 0.5533190965652466,
      "learning_rate": 5.8e-05,
      "loss": 4.476789474487305,
      "step": 30
    },
    {
      "epoch": 0.004353030797692893,
      "grad_norm": 0.5098243951797485,
      "learning_rate": 7.800000000000001e-05,
      "loss": 4.173786926269531,
      "step": 40
    },
    {
      "epoch": 0.005441288497116117,
      "grad_norm": 0.46193602681159973,
      "learning_rate": 9.8e-05,
      "loss": 3.8873260498046873,
      "step": 50
    },
    {
      "epoch": 0.00652954619653934,
      "grad_norm": 0.6326547861099243,
      "learning_rate": 0.000118,
      "loss": 3.690767288208008,
      "step": 60
    },
    {
      "epoch": 0.007617803895962564,
      "grad_norm": 0.5634731650352478,
      "learning_rate": 0.000138,
      "loss": 3.532633590698242,
      "step": 70
    },
    {
      "epoch": 0.008706061595385787,
      "grad_norm": 0.7146243453025818,
      "learning_rate": 0.00015800000000000002,
      "loss": 3.369486999511719,
      "step": 80
    },
    {
      "epoch": 0.009794319294809012,
      "grad_norm": 0.7313923239707947,
      "learning_rate": 0.00017800000000000002,
      "loss": 3.3079143524169923,
      "step": 90
    },
    {
      "epoch": 0.010882576994232234,
      "grad_norm": 0.8027234077453613,
      "learning_rate": 0.00019800000000000002,
      "loss": 3.2139404296875,
      "step": 100
    },
    {
      "epoch": 0.011970834693655457,
      "grad_norm": 0.7909902930259705,
      "learning_rate": 0.00019999951613722537,
      "loss": 3.099309539794922,
      "step": 110
    },
    {
      "epoch": 0.01305909239307868,
      "grad_norm": 0.8192159533500671,
      "learning_rate": 0.00019999784353117638,
      "loss": 3.0375497817993162,
      "step": 120
    },
    {
      "epoch": 0.014147350092501905,
      "grad_norm": 0.7443103790283203,
      "learning_rate": 0.0001999949762282168,
      "loss": 2.978965950012207,
      "step": 130
    },
    {
      "epoch": 0.015235607791925128,
      "grad_norm": 0.7991694808006287,
      "learning_rate": 0.000199990914262603,
      "loss": 2.9791082382202148,
      "step": 140
    },
    {
      "epoch": 0.01632386549134835,
      "grad_norm": 0.6008569002151489,
      "learning_rate": 0.00019998565768286416,
      "loss": 2.950560188293457,
      "step": 150
    },
    {
      "epoch": 0.017412123190771574,
      "grad_norm": 0.7995827794075012,
      "learning_rate": 0.00019997920655180184,
      "loss": 3.0215282440185547,
      "step": 160
    },
    {
      "epoch": 0.018500380890194797,
      "grad_norm": 0.7619604468345642,
      "learning_rate": 0.00019997156094648917,
      "loss": 2.7942909240722655,
      "step": 170
    },
    {
      "epoch": 0.019588638589618023,
      "grad_norm": 0.7879506349563599,
      "learning_rate": 0.0001999627209582699,
      "loss": 2.9927343368530273,
      "step": 180
    },
    {
      "epoch": 0.020676896289041246,
      "grad_norm": 0.6188663840293884,
      "learning_rate": 0.0001999526866927574,
      "loss": 2.996811866760254,
      "step": 190
    },
    {
      "epoch": 0.02176515398846447,
      "grad_norm": 0.8291100263595581,
      "learning_rate": 0.00019994145826983335,
      "loss": 2.8538694381713867,
      "step": 200
    },
    {
      "epoch": 0.022853411687887692,
      "grad_norm": 0.7064241766929626,
      "learning_rate": 0.00019992903582364616,
      "loss": 2.9169912338256836,
      "step": 210
    },
    {
      "epoch": 0.023941669387310915,
      "grad_norm": 0.7565109133720398,
      "learning_rate": 0.00019991541950260976,
      "loss": 2.8318023681640625,
      "step": 220
    },
    {
      "epoch": 0.025029927086734138,
      "grad_norm": 0.8033138513565063,
      "learning_rate": 0.00019990060946940128,
      "loss": 2.9133060455322264,
      "step": 230
    },
    {
      "epoch": 0.02611818478615736,
      "grad_norm": 0.6850875020027161,
      "learning_rate": 0.00019988460590095964,
      "loss": 2.8186214447021483,
      "step": 240
    },
    {
      "epoch": 0.027206442485580587,
      "grad_norm": 0.822592556476593,
      "learning_rate": 0.00019986740898848306,
      "loss": 2.751984214782715,
      "step": 250
    },
    {
      "epoch": 0.02829470018500381,
      "grad_norm": 0.7135462164878845,
      "learning_rate": 0.00019984901893742695,
      "loss": 2.845341682434082,
      "step": 260
    },
    {
      "epoch": 0.029382957884427033,
      "grad_norm": 0.7428542971611023,
      "learning_rate": 0.00019982943596750147,
      "loss": 2.760402488708496,
      "step": 270
    },
    {
      "epoch": 0.030471215583850256,
      "grad_norm": 0.6774494051933289,
      "learning_rate": 0.00019980866031266871,
      "loss": 2.7369028091430665,
      "step": 280
    },
    {
      "epoch": 0.03155947328327348,
      "grad_norm": 0.5907191038131714,
      "learning_rate": 0.00019978669222114022,
      "loss": 2.6875715255737305,
      "step": 290
    },
    {
      "epoch": 0.0326477309826967,
      "grad_norm": 0.604983925819397,
      "learning_rate": 0.00019976353195537373,
      "loss": 2.7130207061767577,
      "step": 300
    },
    {
      "epoch": 0.033735988682119925,
      "grad_norm": 0.6687904596328735,
      "learning_rate": 0.0001997391797920702,
      "loss": 2.6797380447387695,
      "step": 310
    },
    {
      "epoch": 0.03482424638154315,
      "grad_norm": 0.7419909834861755,
      "learning_rate": 0.00019971363602217039,
      "loss": 2.7096893310546877,
      "step": 320
    },
    {
      "epoch": 0.03591250408096637,
      "grad_norm": 0.7090854644775391,
      "learning_rate": 0.0001996869009508516,
      "loss": 2.635569953918457,
      "step": 330
    },
    {
      "epoch": 0.03700076178038959,
      "grad_norm": 0.7182894945144653,
      "learning_rate": 0.00019965897489752373,
      "loss": 2.6656593322753905,
      "step": 340
    },
    {
      "epoch": 0.038089019479812816,
      "grad_norm": 0.7110818028450012,
      "learning_rate": 0.0001996298581958257,
      "loss": 2.6308521270751952,
      "step": 350
    },
    {
      "epoch": 0.039177277179236046,
      "grad_norm": 0.5732347965240479,
      "learning_rate": 0.00019959955119362133,
      "loss": 2.6709070205688477,
      "step": 360
    },
    {
      "epoch": 0.04026553487865927,
      "grad_norm": 0.6702016592025757,
      "learning_rate": 0.00019956805425299526,
      "loss": 2.531391906738281,
      "step": 370
    },
    {
      "epoch": 0.04135379257808249,
      "grad_norm": 0.6591757535934448,
      "learning_rate": 0.00019953536775024855,
      "loss": 2.5455032348632813,
      "step": 380
    },
    {
      "epoch": 0.042442050277505715,
      "grad_norm": 0.5890617966651917,
      "learning_rate": 0.0001995014920758943,
      "loss": 2.5943485260009767,
      "step": 390
    },
    {
      "epoch": 0.04353030797692894,
      "grad_norm": 0.597907304763794,
      "learning_rate": 0.00019946642763465287,
      "loss": 2.5355979919433596,
      "step": 400
    },
    {
      "epoch": 0.04461856567635216,
      "grad_norm": 0.5858283638954163,
      "learning_rate": 0.00019943017484544705,
      "loss": 2.5751579284667967,
      "step": 410
    },
    {
      "epoch": 0.045706823375775384,
      "grad_norm": 0.6279524564743042,
      "learning_rate": 0.00019939273414139717,
      "loss": 2.5788373947143555,
      "step": 420
    },
    {
      "epoch": 0.04679508107519861,
      "grad_norm": 0.6761276721954346,
      "learning_rate": 0.0001993541059698158,
      "loss": 2.638111686706543,
      "step": 430
    },
    {
      "epoch": 0.04788333877462183,
      "grad_norm": 0.7934256196022034,
      "learning_rate": 0.00019931429079220246,
      "loss": 2.597989082336426,
      "step": 440
    },
    {
      "epoch": 0.04897159647404505,
      "grad_norm": 0.614450216293335,
      "learning_rate": 0.0001992732890842381,
      "loss": 2.6165655136108397,
      "step": 450
    },
    {
      "epoch": 0.050059854173468275,
      "grad_norm": 0.6322848796844482,
      "learning_rate": 0.00019923110133577944,
      "loss": 2.618748664855957,
      "step": 460
    },
    {
      "epoch": 0.0511481118728915,
      "grad_norm": 0.7874864339828491,
      "learning_rate": 0.0001991877280508531,
      "loss": 2.5130441665649412,
      "step": 470
    },
    {
      "epoch": 0.05223636957231472,
      "grad_norm": 0.6739583611488342,
      "learning_rate": 0.0001991431697476495,
      "loss": 2.512283134460449,
      "step": 480
    },
    {
      "epoch": 0.053324627271737944,
      "grad_norm": 0.6174733638763428,
      "learning_rate": 0.00019909742695851677,
      "loss": 2.513458824157715,
      "step": 490
    },
    {
      "epoch": 0.054412884971161174,
      "grad_norm": 0.7092267274856567,
      "learning_rate": 0.00019905050022995445,
      "loss": 2.504042053222656,
      "step": 500
    },
    {
      "epoch": 0.054412884971161174,
      "eval_loss": 2.5402708053588867,
      "eval_runtime": 586.9756,
      "eval_samples_per_second": 52.731,
      "eval_steps_per_second": 1.649,
      "step": 500
    },
    {
      "epoch": 0.0555011426705844,
      "grad_norm": 0.6926353573799133,
      "learning_rate": 0.00019900239012260676,
      "loss": 2.526125907897949,
      "step": 510
    },
    {
      "epoch": 0.05658940037000762,
      "grad_norm": 0.677131175994873,
      "learning_rate": 0.0001989530972112561,
      "loss": 2.5419589996337892,
      "step": 520
    },
    {
      "epoch": 0.05767765806943084,
      "grad_norm": 0.6061253547668457,
      "learning_rate": 0.00019890262208481607,
      "loss": 2.4368318557739257,
      "step": 530
    },
    {
      "epoch": 0.058765915768854066,
      "grad_norm": 0.759306013584137,
      "learning_rate": 0.00019885096534632437,
      "loss": 2.5052522659301757,
      "step": 540
    },
    {
      "epoch": 0.05985417346827729,
      "grad_norm": 0.6426571011543274,
      "learning_rate": 0.00019879812761293585,
      "loss": 2.500101089477539,
      "step": 550
    },
    {
      "epoch": 0.06094243116770051,
      "grad_norm": 0.6019865274429321,
      "learning_rate": 0.00019874410951591483,
      "loss": 2.5190673828125,
      "step": 560
    },
    {
      "epoch": 0.062030688867123734,
      "grad_norm": 0.6041361093521118,
      "learning_rate": 0.0001986889117006278,
      "loss": 2.441026496887207,
      "step": 570
    },
    {
      "epoch": 0.06311894656654696,
      "grad_norm": 0.5995342135429382,
      "learning_rate": 0.0001986325348265356,
      "loss": 2.5326648712158204,
      "step": 580
    },
    {
      "epoch": 0.06420720426597018,
      "grad_norm": 0.6185106039047241,
      "learning_rate": 0.00019857497956718545,
      "loss": 2.556035041809082,
      "step": 590
    },
    {
      "epoch": 0.0652954619653934,
      "grad_norm": 0.5220043659210205,
      "learning_rate": 0.00019851624661020316,
      "loss": 2.4316898345947267,
      "step": 600
    },
    {
      "epoch": 0.06638371966481663,
      "grad_norm": 0.6268026828765869,
      "learning_rate": 0.00019845633665728464,
      "loss": 2.5950042724609377,
      "step": 610
    },
    {
      "epoch": 0.06747197736423985,
      "grad_norm": 0.6248210072517395,
      "learning_rate": 0.00019839525042418768,
      "loss": 2.441714859008789,
      "step": 620
    },
    {
      "epoch": 0.06856023506366307,
      "grad_norm": 0.5517216920852661,
      "learning_rate": 0.0001983329886407234,
      "loss": 2.4361038208007812,
      "step": 630
    },
    {
      "epoch": 0.0696484927630863,
      "grad_norm": 0.6257575154304504,
      "learning_rate": 0.0001982695520507474,
      "loss": 2.3455841064453127,
      "step": 640
    },
    {
      "epoch": 0.07073675046250952,
      "grad_norm": 0.713700532913208,
      "learning_rate": 0.00019820494141215104,
      "loss": 2.5119384765625,
      "step": 650
    },
    {
      "epoch": 0.07182500816193274,
      "grad_norm": 0.6029644012451172,
      "learning_rate": 0.0001981391574968522,
      "loss": 2.433802604675293,
      "step": 660
    },
    {
      "epoch": 0.07291326586135596,
      "grad_norm": 0.5936899185180664,
      "learning_rate": 0.00019807220109078634,
      "loss": 2.429648590087891,
      "step": 670
    },
    {
      "epoch": 0.07400152356077919,
      "grad_norm": 0.6892074346542358,
      "learning_rate": 0.00019800407299389676,
      "loss": 2.4622060775756838,
      "step": 680
    },
    {
      "epoch": 0.07508978126020241,
      "grad_norm": 0.5444376468658447,
      "learning_rate": 0.0001979347740201253,
      "loss": 2.443063163757324,
      "step": 690
    },
    {
      "epoch": 0.07617803895962563,
      "grad_norm": 0.5775953531265259,
      "learning_rate": 0.00019786430499740246,
      "loss": 2.432481575012207,
      "step": 700
    },
    {
      "epoch": 0.07726629665904887,
      "grad_norm": 0.5795350074768066,
      "learning_rate": 0.0001977926667676377,
      "loss": 2.4973833084106447,
      "step": 710
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.5367754101753235,
      "learning_rate": 0.00019771986018670917,
      "loss": 2.3666255950927733,
      "step": 720
    },
    {
      "epoch": 0.07944281205789532,
      "grad_norm": 0.5822617411613464,
      "learning_rate": 0.00019764588612445358,
      "loss": 2.385586738586426,
      "step": 730
    },
    {
      "epoch": 0.08053106975731854,
      "grad_norm": 0.5901954770088196,
      "learning_rate": 0.00019757074546465587,
      "loss": 2.370471954345703,
      "step": 740
    },
    {
      "epoch": 0.08161932745674176,
      "grad_norm": 0.6353778839111328,
      "learning_rate": 0.00019749443910503848,
      "loss": 2.396226692199707,
      "step": 750
    },
    {
      "epoch": 0.08270758515616498,
      "grad_norm": 0.6343770623207092,
      "learning_rate": 0.00019741696795725087,
      "loss": 2.401010513305664,
      "step": 760
    },
    {
      "epoch": 0.0837958428555882,
      "grad_norm": 0.5598312020301819,
      "learning_rate": 0.00019733833294685834,
      "loss": 2.2786861419677735,
      "step": 770
    },
    {
      "epoch": 0.08488410055501143,
      "grad_norm": 0.5484779477119446,
      "learning_rate": 0.00019725853501333123,
      "loss": 2.3955661773681642,
      "step": 780
    },
    {
      "epoch": 0.08597235825443465,
      "grad_norm": 0.6644891500473022,
      "learning_rate": 0.00019717757511003353,
      "loss": 2.3859668731689454,
      "step": 790
    },
    {
      "epoch": 0.08706061595385788,
      "grad_norm": 0.6514454483985901,
      "learning_rate": 0.00019709545420421156,
      "loss": 2.2458009719848633,
      "step": 800
    },
    {
      "epoch": 0.0881488736532811,
      "grad_norm": 0.5960633158683777,
      "learning_rate": 0.00019701217327698238,
      "loss": 2.3914718627929688,
      "step": 810
    },
    {
      "epoch": 0.08923713135270432,
      "grad_norm": 0.6240096688270569,
      "learning_rate": 0.00019692773332332216,
      "loss": 2.3869680404663085,
      "step": 820
    },
    {
      "epoch": 0.09032538905212754,
      "grad_norm": 0.5594795346260071,
      "learning_rate": 0.00019684213535205413,
      "loss": 2.3711660385131834,
      "step": 830
    },
    {
      "epoch": 0.09141364675155077,
      "grad_norm": 0.6088646650314331,
      "learning_rate": 0.0001967553803858367,
      "loss": 2.3576807022094726,
      "step": 840
    },
    {
      "epoch": 0.09250190445097399,
      "grad_norm": 0.46641722321510315,
      "learning_rate": 0.00019666746946115108,
      "loss": 2.2290084838867186,
      "step": 850
    },
    {
      "epoch": 0.09359016215039721,
      "grad_norm": 0.548875093460083,
      "learning_rate": 0.00019657840362828906,
      "loss": 2.327008056640625,
      "step": 860
    },
    {
      "epoch": 0.09467841984982044,
      "grad_norm": 0.5243982672691345,
      "learning_rate": 0.0001964881839513403,
      "loss": 2.3408859252929686,
      "step": 870
    },
    {
      "epoch": 0.09576667754924366,
      "grad_norm": 0.6235495209693909,
      "learning_rate": 0.0001963968115081798,
      "loss": 2.263168525695801,
      "step": 880
    },
    {
      "epoch": 0.09685493524866688,
      "grad_norm": 0.6063691973686218,
      "learning_rate": 0.00019630428739045476,
      "loss": 2.3421646118164063,
      "step": 890
    },
    {
      "epoch": 0.0979431929480901,
      "grad_norm": 0.5557937622070312,
      "learning_rate": 0.00019621061270357187,
      "loss": 2.3258382797241213,
      "step": 900
    },
    {
      "epoch": 0.09903145064751333,
      "grad_norm": 0.6151397228240967,
      "learning_rate": 0.00019611578856668386,
      "loss": 2.3854576110839845,
      "step": 910
    },
    {
      "epoch": 0.10011970834693655,
      "grad_norm": 0.644874095916748,
      "learning_rate": 0.00019601981611267616,
      "loss": 2.289360237121582,
      "step": 920
    },
    {
      "epoch": 0.10120796604635977,
      "grad_norm": 0.5509300827980042,
      "learning_rate": 0.00019592269648815346,
      "loss": 2.295314598083496,
      "step": 930
    },
    {
      "epoch": 0.102296223745783,
      "grad_norm": 0.5932837724685669,
      "learning_rate": 0.00019582443085342587,
      "loss": 2.3362094879150392,
      "step": 940
    },
    {
      "epoch": 0.10338448144520622,
      "grad_norm": 0.5630385279655457,
      "learning_rate": 0.0001957250203824953,
      "loss": 2.300915336608887,
      "step": 950
    },
    {
      "epoch": 0.10447273914462944,
      "grad_norm": 0.6143785715103149,
      "learning_rate": 0.00019562446626304115,
      "loss": 2.283652496337891,
      "step": 960
    },
    {
      "epoch": 0.10556099684405267,
      "grad_norm": 0.5924747586250305,
      "learning_rate": 0.00019552276969640628,
      "loss": 2.36254768371582,
      "step": 970
    },
    {
      "epoch": 0.10664925454347589,
      "grad_norm": 0.6027070879936218,
      "learning_rate": 0.00019541993189758263,
      "loss": 2.3686290740966798,
      "step": 980
    },
    {
      "epoch": 0.10773751224289912,
      "grad_norm": 0.5071986317634583,
      "learning_rate": 0.00019531595409519672,
      "loss": 2.310688591003418,
      "step": 990
    },
    {
      "epoch": 0.10882576994232235,
      "grad_norm": 0.6230975985527039,
      "learning_rate": 0.0001952108375314949,
      "loss": 2.1661685943603515,
      "step": 1000
    },
    {
      "epoch": 0.10882576994232235,
      "eval_loss": 2.3169119358062744,
      "eval_runtime": 587.2932,
      "eval_samples_per_second": 52.703,
      "eval_steps_per_second": 1.648,
      "step": 1000
    },
    {
      "epoch": 0.10991402764174557,
      "grad_norm": 0.6722395420074463,
      "learning_rate": 0.00019510458346232862,
      "loss": 2.205127143859863,
      "step": 1010
    },
    {
      "epoch": 0.1110022853411688,
      "grad_norm": 0.5277002453804016,
      "learning_rate": 0.00019499719315713932,
      "loss": 2.1974628448486326,
      "step": 1020
    },
    {
      "epoch": 0.11209054304059202,
      "grad_norm": 0.5719823241233826,
      "learning_rate": 0.0001948886678989433,
      "loss": 2.3115985870361326,
      "step": 1030
    },
    {
      "epoch": 0.11317880074001524,
      "grad_norm": 0.5792841911315918,
      "learning_rate": 0.00019477900898431648,
      "loss": 2.2694074630737306,
      "step": 1040
    },
    {
      "epoch": 0.11426705843943846,
      "grad_norm": 0.5490453839302063,
      "learning_rate": 0.00019466821772337877,
      "loss": 2.231657791137695,
      "step": 1050
    },
    {
      "epoch": 0.11535531613886169,
      "grad_norm": 0.5345600843429565,
      "learning_rate": 0.00019455629543977846,
      "loss": 2.334513282775879,
      "step": 1060
    },
    {
      "epoch": 0.11644357383828491,
      "grad_norm": 0.6602033972740173,
      "learning_rate": 0.0001944432434706765,
      "loss": 2.3895183563232423,
      "step": 1070
    },
    {
      "epoch": 0.11753183153770813,
      "grad_norm": 0.5924275517463684,
      "learning_rate": 0.0001943290631667303,
      "loss": 2.351070022583008,
      "step": 1080
    },
    {
      "epoch": 0.11862008923713135,
      "grad_norm": 0.5626043081283569,
      "learning_rate": 0.00019421375589207793,
      "loss": 2.3270200729370116,
      "step": 1090
    },
    {
      "epoch": 0.11970834693655458,
      "grad_norm": 0.5710933804512024,
      "learning_rate": 0.00019409732302432152,
      "loss": 2.308769416809082,
      "step": 1100
    },
    {
      "epoch": 0.1207966046359778,
      "grad_norm": 0.6023140549659729,
      "learning_rate": 0.00019397976595451094,
      "loss": 2.2540557861328123,
      "step": 1110
    },
    {
      "epoch": 0.12188486233540102,
      "grad_norm": 0.6819802522659302,
      "learning_rate": 0.00019386108608712715,
      "loss": 2.2449235916137695,
      "step": 1120
    },
    {
      "epoch": 0.12297312003482425,
      "grad_norm": 0.6211457252502441,
      "learning_rate": 0.00019374128484006545,
      "loss": 2.258294105529785,
      "step": 1130
    },
    {
      "epoch": 0.12406137773424747,
      "grad_norm": 0.520028293132782,
      "learning_rate": 0.00019362036364461847,
      "loss": 2.187278938293457,
      "step": 1140
    },
    {
      "epoch": 0.1251496354336707,
      "grad_norm": 0.5941503047943115,
      "learning_rate": 0.0001934983239454592,
      "loss": 2.2918350219726564,
      "step": 1150
    },
    {
      "epoch": 0.12623789313309391,
      "grad_norm": 0.5812289714813232,
      "learning_rate": 0.00019337516720062357,
      "loss": 2.255027961730957,
      "step": 1160
    },
    {
      "epoch": 0.12732615083251714,
      "grad_norm": 0.505490779876709,
      "learning_rate": 0.00019325089488149313,
      "loss": 2.242863655090332,
      "step": 1170
    },
    {
      "epoch": 0.12841440853194036,
      "grad_norm": 0.6723229289054871,
      "learning_rate": 0.00019312550847277744,
      "loss": 2.3193592071533202,
      "step": 1180
    },
    {
      "epoch": 0.12950266623136358,
      "grad_norm": 0.535140872001648,
      "learning_rate": 0.0001929990094724964,
      "loss": 2.256319046020508,
      "step": 1190
    },
    {
      "epoch": 0.1305909239307868,
      "grad_norm": 0.4813484847545624,
      "learning_rate": 0.00019287139939196224,
      "loss": 2.2660842895507813,
      "step": 1200
    },
    {
      "epoch": 0.13167918163021003,
      "grad_norm": 0.570446252822876,
      "learning_rate": 0.00019274267975576153,
      "loss": 2.2892129898071287,
      "step": 1210
    },
    {
      "epoch": 0.13276743932963325,
      "grad_norm": 0.6873188614845276,
      "learning_rate": 0.0001926128521017369,
      "loss": 2.3654247283935548,
      "step": 1220
    },
    {
      "epoch": 0.13385569702905648,
      "grad_norm": 0.48321738839149475,
      "learning_rate": 0.0001924819179809688,
      "loss": 2.224453353881836,
      "step": 1230
    },
    {
      "epoch": 0.1349439547284797,
      "grad_norm": 0.5957618355751038,
      "learning_rate": 0.00019234987895775686,
      "loss": 2.285516548156738,
      "step": 1240
    },
    {
      "epoch": 0.13603221242790292,
      "grad_norm": 0.6557724475860596,
      "learning_rate": 0.00019221673660960127,
      "loss": 2.3456472396850585,
      "step": 1250
    },
    {
      "epoch": 0.13712047012732614,
      "grad_norm": 0.560992956161499,
      "learning_rate": 0.0001920824925271838,
      "loss": 2.2950157165527343,
      "step": 1260
    },
    {
      "epoch": 0.13820872782674937,
      "grad_norm": 0.5748006105422974,
      "learning_rate": 0.00019194714831434896,
      "loss": 2.2706621170043944,
      "step": 1270
    },
    {
      "epoch": 0.1392969855261726,
      "grad_norm": 0.6105372309684753,
      "learning_rate": 0.00019181070558808475,
      "loss": 2.3399494171142576,
      "step": 1280
    },
    {
      "epoch": 0.1403852432255958,
      "grad_norm": 0.5753287672996521,
      "learning_rate": 0.00019167316597850333,
      "loss": 2.2844791412353516,
      "step": 1290
    },
    {
      "epoch": 0.14147350092501904,
      "grad_norm": 0.5580806136131287,
      "learning_rate": 0.00019153453112882166,
      "loss": 2.2780637741088867,
      "step": 1300
    },
    {
      "epoch": 0.14256175862444226,
      "grad_norm": 0.6475474238395691,
      "learning_rate": 0.00019139480269534168,
      "loss": 2.1635242462158204,
      "step": 1310
    },
    {
      "epoch": 0.14365001632386548,
      "grad_norm": 0.5461703538894653,
      "learning_rate": 0.00019125398234743067,
      "loss": 2.1374628067016603,
      "step": 1320
    },
    {
      "epoch": 0.1447382740232887,
      "grad_norm": 0.6155250668525696,
      "learning_rate": 0.00019111207176750127,
      "loss": 2.18671875,
      "step": 1330
    },
    {
      "epoch": 0.14582653172271193,
      "grad_norm": 0.5225923657417297,
      "learning_rate": 0.00019096907265099135,
      "loss": 2.2136383056640625,
      "step": 1340
    },
    {
      "epoch": 0.14691478942213515,
      "grad_norm": 0.5861334204673767,
      "learning_rate": 0.0001908249867063438,
      "loss": 2.2212467193603516,
      "step": 1350
    },
    {
      "epoch": 0.14800304712155837,
      "grad_norm": 0.4927869439125061,
      "learning_rate": 0.000190679815654986,
      "loss": 2.1569862365722656,
      "step": 1360
    },
    {
      "epoch": 0.1490913048209816,
      "grad_norm": 0.6709020733833313,
      "learning_rate": 0.00019053356123130953,
      "loss": 2.2681760787963867,
      "step": 1370
    },
    {
      "epoch": 0.15017956252040482,
      "grad_norm": 0.5057207942008972,
      "learning_rate": 0.00019038622518264905,
      "loss": 2.2577709197998046,
      "step": 1380
    },
    {
      "epoch": 0.15126782021982804,
      "grad_norm": 0.5065057873725891,
      "learning_rate": 0.00019023780926926177,
      "loss": 2.142281341552734,
      "step": 1390
    },
    {
      "epoch": 0.15235607791925126,
      "grad_norm": 0.5002779364585876,
      "learning_rate": 0.0001900883152643063,
      "loss": 2.325468826293945,
      "step": 1400
    },
    {
      "epoch": 0.15344433561867452,
      "grad_norm": 0.6079955697059631,
      "learning_rate": 0.0001899377449538214,
      "loss": 2.170610237121582,
      "step": 1410
    },
    {
      "epoch": 0.15453259331809774,
      "grad_norm": 0.5860960483551025,
      "learning_rate": 0.00018978610013670468,
      "loss": 2.1679641723632814,
      "step": 1420
    },
    {
      "epoch": 0.15562085101752096,
      "grad_norm": 0.5875873565673828,
      "learning_rate": 0.00018963338262469116,
      "loss": 2.2343332290649416,
      "step": 1430
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.5325888991355896,
      "learning_rate": 0.0001894795942423316,
      "loss": 2.2183040618896483,
      "step": 1440
    },
    {
      "epoch": 0.1577973664163674,
      "grad_norm": 0.5409967303276062,
      "learning_rate": 0.00018932473682697066,
      "loss": 2.17867374420166,
      "step": 1450
    },
    {
      "epoch": 0.15888562411579063,
      "grad_norm": 0.5937164425849915,
      "learning_rate": 0.00018916881222872504,
      "loss": 2.220071220397949,
      "step": 1460
    },
    {
      "epoch": 0.15997388181521385,
      "grad_norm": 0.6509461402893066,
      "learning_rate": 0.0001890118223104612,
      "loss": 2.2115047454833983,
      "step": 1470
    },
    {
      "epoch": 0.16106213951463708,
      "grad_norm": 0.6225976347923279,
      "learning_rate": 0.00018885376894777332,
      "loss": 2.241412544250488,
      "step": 1480
    },
    {
      "epoch": 0.1621503972140603,
      "grad_norm": 0.5052709579467773,
      "learning_rate": 0.00018869465402896076,
      "loss": 2.1810253143310545,
      "step": 1490
    },
    {
      "epoch": 0.16323865491348352,
      "grad_norm": 0.6119481325149536,
      "learning_rate": 0.00018853447945500556,
      "loss": 2.2947011947631837,
      "step": 1500
    },
    {
      "epoch": 0.16323865491348352,
      "eval_loss": 2.20023512840271,
      "eval_runtime": 587.0529,
      "eval_samples_per_second": 52.724,
      "eval_steps_per_second": 1.649,
      "step": 1500
    },
    {
      "epoch": 0.16432691261290674,
      "grad_norm": 0.5992363691329956,
      "learning_rate": 0.00018837324713954964,
      "loss": 2.2904293060302736,
      "step": 1510
    },
    {
      "epoch": 0.16541517031232997,
      "grad_norm": 0.66703200340271,
      "learning_rate": 0.00018821095900887203,
      "loss": 2.1766429901123048,
      "step": 1520
    },
    {
      "epoch": 0.1665034280117532,
      "grad_norm": 0.6062861084938049,
      "learning_rate": 0.00018804761700186586,
      "loss": 2.141710090637207,
      "step": 1530
    },
    {
      "epoch": 0.1675916857111764,
      "grad_norm": 0.6298074126243591,
      "learning_rate": 0.0001878832230700151,
      "loss": 2.130615997314453,
      "step": 1540
    },
    {
      "epoch": 0.16867994341059964,
      "grad_norm": 0.5489169955253601,
      "learning_rate": 0.0001877177791773713,
      "loss": 2.1672636032104493,
      "step": 1550
    },
    {
      "epoch": 0.16976820111002286,
      "grad_norm": 0.5847949981689453,
      "learning_rate": 0.00018755128730053023,
      "loss": 2.156511688232422,
      "step": 1560
    },
    {
      "epoch": 0.17085645880944608,
      "grad_norm": 0.5692253708839417,
      "learning_rate": 0.00018738374942860807,
      "loss": 2.0986377716064455,
      "step": 1570
    },
    {
      "epoch": 0.1719447165088693,
      "grad_norm": 0.5773114562034607,
      "learning_rate": 0.0001872151675632177,
      "loss": 2.1211204528808594,
      "step": 1580
    },
    {
      "epoch": 0.17303297420829253,
      "grad_norm": 0.569576621055603,
      "learning_rate": 0.00018704554371844496,
      "loss": 2.1663122177124023,
      "step": 1590
    },
    {
      "epoch": 0.17412123190771575,
      "grad_norm": 0.5821296572685242,
      "learning_rate": 0.00018687487992082437,
      "loss": 2.25234317779541,
      "step": 1600
    },
    {
      "epoch": 0.17520948960713897,
      "grad_norm": 0.6224921345710754,
      "learning_rate": 0.000186703178209315,
      "loss": 2.08530216217041,
      "step": 1610
    },
    {
      "epoch": 0.1762977473065622,
      "grad_norm": 0.7561960816383362,
      "learning_rate": 0.00018653044063527614,
      "loss": 2.2214725494384764,
      "step": 1620
    },
    {
      "epoch": 0.17738600500598542,
      "grad_norm": 0.6512922048568726,
      "learning_rate": 0.00018635666926244276,
      "loss": 2.1064992904663087,
      "step": 1630
    },
    {
      "epoch": 0.17847426270540864,
      "grad_norm": 0.6448703408241272,
      "learning_rate": 0.00018618186616690084,
      "loss": 2.238378715515137,
      "step": 1640
    },
    {
      "epoch": 0.17956252040483187,
      "grad_norm": 0.6052150130271912,
      "learning_rate": 0.00018600603343706262,
      "loss": 2.1941831588745115,
      "step": 1650
    },
    {
      "epoch": 0.1806507781042551,
      "grad_norm": 0.49514251947402954,
      "learning_rate": 0.0001858291731736416,
      "loss": 2.058866500854492,
      "step": 1660
    },
    {
      "epoch": 0.1817390358036783,
      "grad_norm": 0.6906781196594238,
      "learning_rate": 0.00018565128748962738,
      "loss": 2.212385559082031,
      "step": 1670
    },
    {
      "epoch": 0.18282729350310153,
      "grad_norm": 0.6092531681060791,
      "learning_rate": 0.00018547237851026063,
      "loss": 2.2459482192993163,
      "step": 1680
    },
    {
      "epoch": 0.18391555120252476,
      "grad_norm": 0.6431053280830383,
      "learning_rate": 0.00018529244837300746,
      "loss": 2.121844673156738,
      "step": 1690
    },
    {
      "epoch": 0.18500380890194798,
      "grad_norm": 0.5417641997337341,
      "learning_rate": 0.00018511149922753402,
      "loss": 2.143844413757324,
      "step": 1700
    },
    {
      "epoch": 0.1860920666013712,
      "grad_norm": 0.5495652556419373,
      "learning_rate": 0.00018492953323568083,
      "loss": 2.1220401763916015,
      "step": 1710
    },
    {
      "epoch": 0.18718032430079443,
      "grad_norm": 0.7368461489677429,
      "learning_rate": 0.00018474655257143678,
      "loss": 2.112496566772461,
      "step": 1720
    },
    {
      "epoch": 0.18826858200021765,
      "grad_norm": 0.5933881998062134,
      "learning_rate": 0.00018456255942091341,
      "loss": 2.2545331954956054,
      "step": 1730
    },
    {
      "epoch": 0.18935683969964087,
      "grad_norm": 0.5794192552566528,
      "learning_rate": 0.00018437755598231856,
      "loss": 2.171444320678711,
      "step": 1740
    },
    {
      "epoch": 0.1904450973990641,
      "grad_norm": 0.5667774677276611,
      "learning_rate": 0.00018419154446593032,
      "loss": 2.1689022064208983,
      "step": 1750
    },
    {
      "epoch": 0.19153335509848732,
      "grad_norm": 0.589802086353302,
      "learning_rate": 0.0001840045270940704,
      "loss": 2.116688346862793,
      "step": 1760
    },
    {
      "epoch": 0.19262161279791054,
      "grad_norm": 0.5414043664932251,
      "learning_rate": 0.0001838165061010778,
      "loss": 2.206948471069336,
      "step": 1770
    },
    {
      "epoch": 0.19370987049733376,
      "grad_norm": 0.5901210308074951,
      "learning_rate": 0.00018362748373328187,
      "loss": 2.0587100982666016,
      "step": 1780
    },
    {
      "epoch": 0.194798128196757,
      "grad_norm": 0.6130768060684204,
      "learning_rate": 0.0001834374622489758,
      "loss": 2.1653223037719727,
      "step": 1790
    },
    {
      "epoch": 0.1958863858961802,
      "grad_norm": 0.4660082459449768,
      "learning_rate": 0.00018324644391838927,
      "loss": 2.149919319152832,
      "step": 1800
    },
    {
      "epoch": 0.19697464359560343,
      "grad_norm": 0.48946431279182434,
      "learning_rate": 0.00018305443102366163,
      "loss": 2.166761016845703,
      "step": 1810
    },
    {
      "epoch": 0.19806290129502666,
      "grad_norm": 0.5410107374191284,
      "learning_rate": 0.00018286142585881445,
      "loss": 2.2590333938598635,
      "step": 1820
    },
    {
      "epoch": 0.19915115899444988,
      "grad_norm": 0.6120771765708923,
      "learning_rate": 0.0001826674307297242,
      "loss": 2.1067811965942385,
      "step": 1830
    },
    {
      "epoch": 0.2002394166938731,
      "grad_norm": 0.6054511070251465,
      "learning_rate": 0.00018247244795409467,
      "loss": 2.117809295654297,
      "step": 1840
    },
    {
      "epoch": 0.20132767439329632,
      "grad_norm": 0.5898885130882263,
      "learning_rate": 0.00018227647986142936,
      "loss": 2.1442087173461912,
      "step": 1850
    },
    {
      "epoch": 0.20241593209271955,
      "grad_norm": 0.551909863948822,
      "learning_rate": 0.00018207952879300342,
      "loss": 2.1360584259033204,
      "step": 1860
    },
    {
      "epoch": 0.20350418979214277,
      "grad_norm": 0.5962231159210205,
      "learning_rate": 0.00018188159710183594,
      "loss": 2.0945831298828126,
      "step": 1870
    },
    {
      "epoch": 0.204592447491566,
      "grad_norm": 0.5748026371002197,
      "learning_rate": 0.00018168268715266172,
      "loss": 2.149133491516113,
      "step": 1880
    },
    {
      "epoch": 0.20568070519098922,
      "grad_norm": 0.6263651251792908,
      "learning_rate": 0.00018148280132190302,
      "loss": 2.1301254272460937,
      "step": 1890
    },
    {
      "epoch": 0.20676896289041244,
      "grad_norm": 0.5330021977424622,
      "learning_rate": 0.00018128194199764126,
      "loss": 2.169965934753418,
      "step": 1900
    },
    {
      "epoch": 0.20785722058983566,
      "grad_norm": 0.5281866192817688,
      "learning_rate": 0.0001810801115795882,
      "loss": 2.0392730712890623,
      "step": 1910
    },
    {
      "epoch": 0.20894547828925888,
      "grad_norm": 0.522429347038269,
      "learning_rate": 0.0001808773124790577,
      "loss": 2.2333887100219725,
      "step": 1920
    },
    {
      "epoch": 0.2100337359886821,
      "grad_norm": 0.5848979949951172,
      "learning_rate": 0.00018067354711893656,
      "loss": 2.097432327270508,
      "step": 1930
    },
    {
      "epoch": 0.21112199368810533,
      "grad_norm": 0.6055752038955688,
      "learning_rate": 0.00018046881793365574,
      "loss": 2.1793869018554686,
      "step": 1940
    },
    {
      "epoch": 0.21221025138752855,
      "grad_norm": 0.6010363698005676,
      "learning_rate": 0.00018026312736916126,
      "loss": 2.124331474304199,
      "step": 1950
    },
    {
      "epoch": 0.21329850908695178,
      "grad_norm": 0.5671064853668213,
      "learning_rate": 0.00018005647788288493,
      "loss": 2.162104606628418,
      "step": 1960
    },
    {
      "epoch": 0.21438676678637503,
      "grad_norm": 0.5831570625305176,
      "learning_rate": 0.00017984887194371501,
      "loss": 2.1268938064575194,
      "step": 1970
    },
    {
      "epoch": 0.21547502448579825,
      "grad_norm": 0.5373016595840454,
      "learning_rate": 0.0001796403120319667,
      "loss": 2.1061019897460938,
      "step": 1980
    },
    {
      "epoch": 0.21656328218522147,
      "grad_norm": 0.5929492115974426,
      "learning_rate": 0.0001794308006393526,
      "loss": 2.1705223083496095,
      "step": 1990
    },
    {
      "epoch": 0.2176515398846447,
      "grad_norm": 0.4705328941345215,
      "learning_rate": 0.00017922034026895283,
      "loss": 2.074695587158203,
      "step": 2000
    },
    {
      "epoch": 0.2176515398846447,
      "eval_loss": 2.109147071838379,
      "eval_runtime": 586.9376,
      "eval_samples_per_second": 52.735,
      "eval_steps_per_second": 1.649,
      "step": 2000
    },
    {
      "epoch": 0.21873979758406792,
      "grad_norm": 0.5088332295417786,
      "learning_rate": 0.0001790089334351851,
      "loss": 2.1133037567138673,
      "step": 2010
    },
    {
      "epoch": 0.21982805528349114,
      "grad_norm": 0.5302846431732178,
      "learning_rate": 0.00017879658266377484,
      "loss": 2.1055421829223633,
      "step": 2020
    },
    {
      "epoch": 0.22091631298291436,
      "grad_norm": 0.512309730052948,
      "learning_rate": 0.00017858329049172484,
      "loss": 2.034654998779297,
      "step": 2030
    },
    {
      "epoch": 0.2220045706823376,
      "grad_norm": 0.5561679601669312,
      "learning_rate": 0.00017836905946728505,
      "loss": 2.1128475189208986,
      "step": 2040
    },
    {
      "epoch": 0.2230928283817608,
      "grad_norm": 0.5545385479927063,
      "learning_rate": 0.0001781538921499221,
      "loss": 2.051860809326172,
      "step": 2050
    },
    {
      "epoch": 0.22418108608118403,
      "grad_norm": 0.5441116094589233,
      "learning_rate": 0.0001779377911102887,
      "loss": 1.969563865661621,
      "step": 2060
    },
    {
      "epoch": 0.22526934378060726,
      "grad_norm": 0.5807257890701294,
      "learning_rate": 0.00017772075893019297,
      "loss": 2.0863178253173826,
      "step": 2070
    },
    {
      "epoch": 0.22635760148003048,
      "grad_norm": 0.634229302406311,
      "learning_rate": 0.00017750279820256756,
      "loss": 2.0736406326293944,
      "step": 2080
    },
    {
      "epoch": 0.2274458591794537,
      "grad_norm": 0.5438808798789978,
      "learning_rate": 0.0001772839115314388,
      "loss": 2.006355857849121,
      "step": 2090
    },
    {
      "epoch": 0.22853411687887693,
      "grad_norm": 0.6062809228897095,
      "learning_rate": 0.00017706410153189527,
      "loss": 2.0591571807861326,
      "step": 2100
    },
    {
      "epoch": 0.22962237457830015,
      "grad_norm": 0.5494603514671326,
      "learning_rate": 0.00017684337083005694,
      "loss": 2.143521308898926,
      "step": 2110
    },
    {
      "epoch": 0.23071063227772337,
      "grad_norm": 0.5180804133415222,
      "learning_rate": 0.00017662172206304351,
      "loss": 2.0645524978637697,
      "step": 2120
    },
    {
      "epoch": 0.2317988899771466,
      "grad_norm": 0.5837594866752625,
      "learning_rate": 0.0001763991578789431,
      "loss": 1.9541698455810548,
      "step": 2130
    },
    {
      "epoch": 0.23288714767656982,
      "grad_norm": 0.6127448678016663,
      "learning_rate": 0.00017617568093678044,
      "loss": 2.17177791595459,
      "step": 2140
    },
    {
      "epoch": 0.23397540537599304,
      "grad_norm": 0.5226433277130127,
      "learning_rate": 0.00017595129390648531,
      "loss": 2.0547914505004883,
      "step": 2150
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.5894423127174377,
      "learning_rate": 0.00017572599946886032,
      "loss": 2.0524356842041014,
      "step": 2160
    },
    {
      "epoch": 0.23615192077483949,
      "grad_norm": 0.6199406385421753,
      "learning_rate": 0.0001754998003155493,
      "loss": 2.0789115905761717,
      "step": 2170
    },
    {
      "epoch": 0.2372401784742627,
      "grad_norm": 0.5394810438156128,
      "learning_rate": 0.00017527269914900475,
      "loss": 2.0597148895263673,
      "step": 2180
    },
    {
      "epoch": 0.23832843617368593,
      "grad_norm": 0.49846354126930237,
      "learning_rate": 0.00017504469868245584,
      "loss": 2.0944677352905274,
      "step": 2190
    },
    {
      "epoch": 0.23941669387310915,
      "grad_norm": 0.47657492756843567,
      "learning_rate": 0.00017481580163987589,
      "loss": 2.122162437438965,
      "step": 2200
    },
    {
      "epoch": 0.24050495157253238,
      "grad_norm": 0.6801338195800781,
      "learning_rate": 0.00017458601075594964,
      "loss": 2.1052452087402345,
      "step": 2210
    },
    {
      "epoch": 0.2415932092719556,
      "grad_norm": 0.5712375044822693,
      "learning_rate": 0.000174355328776041,
      "loss": 2.0954410552978517,
      "step": 2220
    },
    {
      "epoch": 0.24268146697137882,
      "grad_norm": 0.5341486930847168,
      "learning_rate": 0.00017412375845615987,
      "loss": 2.1599788665771484,
      "step": 2230
    },
    {
      "epoch": 0.24376972467080205,
      "grad_norm": 0.5819491744041443,
      "learning_rate": 0.00017389130256292932,
      "loss": 2.115601921081543,
      "step": 2240
    },
    {
      "epoch": 0.24485798237022527,
      "grad_norm": 0.527596116065979,
      "learning_rate": 0.00017365796387355266,
      "loss": 2.1216785430908205,
      "step": 2250
    },
    {
      "epoch": 0.2459462400696485,
      "grad_norm": 0.532425582408905,
      "learning_rate": 0.00017342374517578007,
      "loss": 2.141047477722168,
      "step": 2260
    },
    {
      "epoch": 0.24703449776907171,
      "grad_norm": 0.5290660858154297,
      "learning_rate": 0.0001731886492678755,
      "loss": 2.042479705810547,
      "step": 2270
    },
    {
      "epoch": 0.24812275546849494,
      "grad_norm": 0.5581395626068115,
      "learning_rate": 0.00017295267895858305,
      "loss": 2.1573259353637697,
      "step": 2280
    },
    {
      "epoch": 0.24921101316791816,
      "grad_norm": 0.6137312650680542,
      "learning_rate": 0.0001727158370670935,
      "loss": 2.1984088897705076,
      "step": 2290
    },
    {
      "epoch": 0.2502992708673414,
      "grad_norm": 0.4954657554626465,
      "learning_rate": 0.00017247812642301062,
      "loss": 1.9827383041381836,
      "step": 2300
    },
    {
      "epoch": 0.2513875285667646,
      "grad_norm": 0.551364004611969,
      "learning_rate": 0.0001722395498663174,
      "loss": 2.064924621582031,
      "step": 2310
    },
    {
      "epoch": 0.25247578626618783,
      "grad_norm": 0.5545063018798828,
      "learning_rate": 0.00017200011024734205,
      "loss": 1.9985237121582031,
      "step": 2320
    },
    {
      "epoch": 0.25356404396561105,
      "grad_norm": 0.5492304563522339,
      "learning_rate": 0.00017175981042672395,
      "loss": 2.0118520736694334,
      "step": 2330
    },
    {
      "epoch": 0.2546523016650343,
      "grad_norm": 0.46815717220306396,
      "learning_rate": 0.0001715186532753796,
      "loss": 2.0273427963256836,
      "step": 2340
    },
    {
      "epoch": 0.2557405593644575,
      "grad_norm": 0.5318409204483032,
      "learning_rate": 0.00017127664167446814,
      "loss": 2.0612958908081054,
      "step": 2350
    },
    {
      "epoch": 0.2568288170638807,
      "grad_norm": 0.589786171913147,
      "learning_rate": 0.00017103377851535704,
      "loss": 2.0560323715209963,
      "step": 2360
    },
    {
      "epoch": 0.25791707476330394,
      "grad_norm": 0.5954175591468811,
      "learning_rate": 0.00017079006669958754,
      "loss": 2.025723457336426,
      "step": 2370
    },
    {
      "epoch": 0.25900533246272717,
      "grad_norm": 0.6750893592834473,
      "learning_rate": 0.00017054550913883998,
      "loss": 2.0966495513916015,
      "step": 2380
    },
    {
      "epoch": 0.2600935901621504,
      "grad_norm": 0.48345836997032166,
      "learning_rate": 0.00017030010875489896,
      "loss": 2.0325756072998047,
      "step": 2390
    },
    {
      "epoch": 0.2611818478615736,
      "grad_norm": 0.6194612383842468,
      "learning_rate": 0.0001700538684796185,
      "loss": 2.095437240600586,
      "step": 2400
    },
    {
      "epoch": 0.26227010556099684,
      "grad_norm": 0.6276369094848633,
      "learning_rate": 0.00016980679125488704,
      "loss": 2.0224342346191406,
      "step": 2410
    },
    {
      "epoch": 0.26335836326042006,
      "grad_norm": 0.6124218702316284,
      "learning_rate": 0.0001695588800325922,
      "loss": 2.0889892578125,
      "step": 2420
    },
    {
      "epoch": 0.2644466209598433,
      "grad_norm": 0.6168131828308105,
      "learning_rate": 0.00016931013777458554,
      "loss": 2.086269760131836,
      "step": 2430
    },
    {
      "epoch": 0.2655348786592665,
      "grad_norm": 0.5778802633285522,
      "learning_rate": 0.00016906056745264722,
      "loss": 2.06359977722168,
      "step": 2440
    },
    {
      "epoch": 0.2666231363586897,
      "grad_norm": 0.50979083776474,
      "learning_rate": 0.0001688101720484505,
      "loss": 2.0644145965576173,
      "step": 2450
    },
    {
      "epoch": 0.26771139405811295,
      "grad_norm": 0.6815667748451233,
      "learning_rate": 0.000168558954553526,
      "loss": 1.9590221405029298,
      "step": 2460
    },
    {
      "epoch": 0.2687996517575362,
      "grad_norm": 0.5399974584579468,
      "learning_rate": 0.00016830691796922614,
      "loss": 2.044365882873535,
      "step": 2470
    },
    {
      "epoch": 0.2698879094569594,
      "grad_norm": 0.5563638806343079,
      "learning_rate": 0.0001680540653066891,
      "loss": 1.989365577697754,
      "step": 2480
    },
    {
      "epoch": 0.2709761671563826,
      "grad_norm": 0.5071965456008911,
      "learning_rate": 0.000167800399586803,
      "loss": 2.1890398025512696,
      "step": 2490
    },
    {
      "epoch": 0.27206442485580584,
      "grad_norm": 0.5304718613624573,
      "learning_rate": 0.0001675459238401697,
      "loss": 1.9666751861572265,
      "step": 2500
    },
    {
      "epoch": 0.27206442485580584,
      "eval_loss": 2.052706718444824,
      "eval_runtime": 587.1428,
      "eval_samples_per_second": 52.716,
      "eval_steps_per_second": 1.649,
      "step": 2500
    },
    {
      "epoch": 0.27315268255522906,
      "grad_norm": 0.5595816969871521,
      "learning_rate": 0.0001672906411070687,
      "loss": 2.0600120544433596,
      "step": 2510
    },
    {
      "epoch": 0.2742409402546523,
      "grad_norm": 0.5852010846138,
      "learning_rate": 0.0001670345544374206,
      "loss": 2.028826904296875,
      "step": 2520
    },
    {
      "epoch": 0.2753291979540755,
      "grad_norm": 0.5964128375053406,
      "learning_rate": 0.00016677766689075096,
      "loss": 1.9598331451416016,
      "step": 2530
    },
    {
      "epoch": 0.27641745565349873,
      "grad_norm": 0.571686863899231,
      "learning_rate": 0.00016651998153615353,
      "loss": 1.9748113632202149,
      "step": 2540
    },
    {
      "epoch": 0.27750571335292196,
      "grad_norm": 0.6193922162055969,
      "learning_rate": 0.0001662615014522537,
      "loss": 2.085162353515625,
      "step": 2550
    },
    {
      "epoch": 0.2785939710523452,
      "grad_norm": 0.5795553922653198,
      "learning_rate": 0.00016600222972717164,
      "loss": 2.175711250305176,
      "step": 2560
    },
    {
      "epoch": 0.2796822287517684,
      "grad_norm": 0.5491994023323059,
      "learning_rate": 0.00016574216945848538,
      "loss": 2.1317411422729493,
      "step": 2570
    },
    {
      "epoch": 0.2807704864511916,
      "grad_norm": 0.5458104610443115,
      "learning_rate": 0.000165481323753194,
      "loss": 2.068903923034668,
      "step": 2580
    },
    {
      "epoch": 0.28185874415061485,
      "grad_norm": 0.6222167611122131,
      "learning_rate": 0.00016521969572768022,
      "loss": 1.999159049987793,
      "step": 2590
    },
    {
      "epoch": 0.28294700185003807,
      "grad_norm": 0.5796995759010315,
      "learning_rate": 0.00016495728850767343,
      "loss": 2.0736717224121093,
      "step": 2600
    },
    {
      "epoch": 0.2840352595494613,
      "grad_norm": 0.5838117003440857,
      "learning_rate": 0.00016469410522821214,
      "loss": 1.9951139450073243,
      "step": 2610
    },
    {
      "epoch": 0.2851235172488845,
      "grad_norm": 0.6098240613937378,
      "learning_rate": 0.0001644301490336067,
      "loss": 2.0833147048950194,
      "step": 2620
    },
    {
      "epoch": 0.28621177494830774,
      "grad_norm": 0.6246470212936401,
      "learning_rate": 0.00016416542307740161,
      "loss": 2.060029983520508,
      "step": 2630
    },
    {
      "epoch": 0.28730003264773096,
      "grad_norm": 0.5276803970336914,
      "learning_rate": 0.00016389993052233793,
      "loss": 2.019278144836426,
      "step": 2640
    },
    {
      "epoch": 0.2883882903471542,
      "grad_norm": 0.6400175094604492,
      "learning_rate": 0.0001636336745403153,
      "loss": 2.046988677978516,
      "step": 2650
    },
    {
      "epoch": 0.2894765480465774,
      "grad_norm": 0.5165756344795227,
      "learning_rate": 0.00016336665831235444,
      "loss": 1.9314437866210938,
      "step": 2660
    },
    {
      "epoch": 0.29056480574600063,
      "grad_norm": 0.5371330380439758,
      "learning_rate": 0.0001630988850285587,
      "loss": 1.9953683853149413,
      "step": 2670
    },
    {
      "epoch": 0.29165306344542385,
      "grad_norm": 0.5350714921951294,
      "learning_rate": 0.0001628303578880762,
      "loss": 2.0260534286499023,
      "step": 2680
    },
    {
      "epoch": 0.2927413211448471,
      "grad_norm": 0.5653142333030701,
      "learning_rate": 0.00016256108009906167,
      "loss": 1.9526407241821289,
      "step": 2690
    },
    {
      "epoch": 0.2938295788442703,
      "grad_norm": 0.5415879487991333,
      "learning_rate": 0.00016229105487863778,
      "loss": 2.050252342224121,
      "step": 2700
    },
    {
      "epoch": 0.2949178365436935,
      "grad_norm": 0.4817979633808136,
      "learning_rate": 0.00016202028545285718,
      "loss": 2.0294048309326174,
      "step": 2710
    },
    {
      "epoch": 0.29600609424311675,
      "grad_norm": 0.5869520902633667,
      "learning_rate": 0.00016174877505666357,
      "loss": 1.948918342590332,
      "step": 2720
    },
    {
      "epoch": 0.29709435194253997,
      "grad_norm": 0.5371376276016235,
      "learning_rate": 0.00016147652693385313,
      "loss": 2.028607177734375,
      "step": 2730
    },
    {
      "epoch": 0.2981826096419632,
      "grad_norm": 0.608590304851532,
      "learning_rate": 0.000161203544337036,
      "loss": 2.0580350875854494,
      "step": 2740
    },
    {
      "epoch": 0.2992708673413864,
      "grad_norm": 0.5166542530059814,
      "learning_rate": 0.0001609298305275972,
      "loss": 2.1726612091064452,
      "step": 2750
    },
    {
      "epoch": 0.30035912504080964,
      "grad_norm": 0.4902857840061188,
      "learning_rate": 0.00016065538877565753,
      "loss": 1.945541763305664,
      "step": 2760
    },
    {
      "epoch": 0.30144738274023286,
      "grad_norm": 0.5767205953598022,
      "learning_rate": 0.00016038022236003499,
      "loss": 1.8922840118408204,
      "step": 2770
    },
    {
      "epoch": 0.3025356404396561,
      "grad_norm": 0.5173133611679077,
      "learning_rate": 0.000160104334568205,
      "loss": 1.9178089141845702,
      "step": 2780
    },
    {
      "epoch": 0.3036238981390793,
      "grad_norm": 0.5458312630653381,
      "learning_rate": 0.00015982772869626167,
      "loss": 1.9625509262084961,
      "step": 2790
    },
    {
      "epoch": 0.30471215583850253,
      "grad_norm": 0.6096794605255127,
      "learning_rate": 0.00015955040804887803,
      "loss": 1.9656063079833985,
      "step": 2800
    },
    {
      "epoch": 0.3058004135379258,
      "grad_norm": 0.5105905532836914,
      "learning_rate": 0.00015927237593926668,
      "loss": 1.9899227142333984,
      "step": 2810
    },
    {
      "epoch": 0.30688867123734903,
      "grad_norm": 0.4678819477558136,
      "learning_rate": 0.0001589936356891404,
      "loss": 2.026172065734863,
      "step": 2820
    },
    {
      "epoch": 0.30797692893677225,
      "grad_norm": 0.6311321258544922,
      "learning_rate": 0.00015871419062867207,
      "loss": 1.9687185287475586,
      "step": 2830
    },
    {
      "epoch": 0.3090651866361955,
      "grad_norm": 0.5898714661598206,
      "learning_rate": 0.00015843404409645516,
      "loss": 2.0452117919921875,
      "step": 2840
    },
    {
      "epoch": 0.3101534443356187,
      "grad_norm": 0.4785173833370209,
      "learning_rate": 0.00015815319943946393,
      "loss": 1.920002555847168,
      "step": 2850
    },
    {
      "epoch": 0.3112417020350419,
      "grad_norm": 0.5722597241401672,
      "learning_rate": 0.00015787166001301307,
      "loss": 1.980157470703125,
      "step": 2860
    },
    {
      "epoch": 0.31232995973446515,
      "grad_norm": 0.6049121618270874,
      "learning_rate": 0.00015758942918071798,
      "loss": 2.0541561126708983,
      "step": 2870
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.6247254014015198,
      "learning_rate": 0.00015730651031445442,
      "loss": 2.0732309341430666,
      "step": 2880
    },
    {
      "epoch": 0.3145064751333116,
      "grad_norm": 0.5216240286827087,
      "learning_rate": 0.00015702290679431825,
      "loss": 2.015762710571289,
      "step": 2890
    },
    {
      "epoch": 0.3155947328327348,
      "grad_norm": 0.6961284875869751,
      "learning_rate": 0.000156738622008585,
      "loss": 2.052688980102539,
      "step": 2900
    },
    {
      "epoch": 0.31668299053215804,
      "grad_norm": 0.6234159469604492,
      "learning_rate": 0.00015645365935366946,
      "loss": 2.010626220703125,
      "step": 2910
    },
    {
      "epoch": 0.31777124823158126,
      "grad_norm": 0.5455389022827148,
      "learning_rate": 0.0001561680222340851,
      "loss": 2.1055572509765623,
      "step": 2920
    },
    {
      "epoch": 0.3188595059310045,
      "grad_norm": 0.6326649785041809,
      "learning_rate": 0.00015588171406240338,
      "loss": 1.915243911743164,
      "step": 2930
    },
    {
      "epoch": 0.3199477636304277,
      "grad_norm": 0.56302410364151,
      "learning_rate": 0.00015559473825921288,
      "loss": 1.885507583618164,
      "step": 2940
    },
    {
      "epoch": 0.32103602132985093,
      "grad_norm": 0.587032675743103,
      "learning_rate": 0.00015530709825307862,
      "loss": 1.9598285675048828,
      "step": 2950
    },
    {
      "epoch": 0.32212427902927415,
      "grad_norm": 0.5396708846092224,
      "learning_rate": 0.000155018797480501,
      "loss": 1.9466554641723632,
      "step": 2960
    },
    {
      "epoch": 0.3232125367286974,
      "grad_norm": 0.5461894869804382,
      "learning_rate": 0.00015472983938587468,
      "loss": 1.9678598403930665,
      "step": 2970
    },
    {
      "epoch": 0.3243007944281206,
      "grad_norm": 0.5173971652984619,
      "learning_rate": 0.00015444022742144758,
      "loss": 2.0659557342529298,
      "step": 2980
    },
    {
      "epoch": 0.3253890521275438,
      "grad_norm": 0.6960553526878357,
      "learning_rate": 0.00015414996504727947,
      "loss": 2.006389045715332,
      "step": 2990
    },
    {
      "epoch": 0.32647730982696704,
      "grad_norm": 0.5320561528205872,
      "learning_rate": 0.00015385905573120075,
      "loss": 1.9795562744140625,
      "step": 3000
    },
    {
      "epoch": 0.32647730982696704,
      "eval_loss": 2.002763032913208,
      "eval_runtime": 587.3305,
      "eval_samples_per_second": 52.699,
      "eval_steps_per_second": 1.648,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 9189,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.654283695030272e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}