{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.765655130417132,
  "eval_steps": 500,
  "global_step": 2175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008119354511316351,
      "grad_norm": 1.192345380783081,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.3216888427734375,
      "step": 10
    },
    {
      "epoch": 0.016238709022632702,
      "grad_norm": 1.2548257112503052,
      "learning_rate": 5.757575757575758e-05,
      "loss": 1.0566269874572753,
      "step": 20
    },
    {
      "epoch": 0.02435806353394905,
      "grad_norm": 0.30806204676628113,
      "learning_rate": 8.787878787878789e-05,
      "loss": 0.6396953582763671,
      "step": 30
    },
    {
      "epoch": 0.032477418045265403,
      "grad_norm": 0.25909167528152466,
      "learning_rate": 0.0001181818181818182,
      "loss": 0.5402174472808838,
      "step": 40
    },
    {
      "epoch": 0.04059677255658175,
      "grad_norm": 0.21031738817691803,
      "learning_rate": 0.00014848484848484849,
      "loss": 0.5005859375,
      "step": 50
    },
    {
      "epoch": 0.0487161270678981,
      "grad_norm": 0.18716108798980713,
      "learning_rate": 0.0001787878787878788,
      "loss": 0.537840461730957,
      "step": 60
    },
    {
      "epoch": 0.056835481579214454,
      "grad_norm": 0.1792488396167755,
      "learning_rate": 0.0001999990247348105,
      "loss": 0.4450899600982666,
      "step": 70
    },
    {
      "epoch": 0.06495483609053081,
      "grad_norm": 0.21492543816566467,
      "learning_rate": 0.00019998168721618701,
      "loss": 0.4202279090881348,
      "step": 80
    },
    {
      "epoch": 0.07307419060184715,
      "grad_norm": 0.16661711037158966,
      "learning_rate": 0.00019994268146276777,
      "loss": 0.4485616207122803,
      "step": 90
    },
    {
      "epoch": 0.0811935451131635,
      "grad_norm": 0.24056391417980194,
      "learning_rate": 0.0001998820159279591,
      "loss": 0.44878439903259276,
      "step": 100
    },
    {
      "epoch": 0.08931289962447986,
      "grad_norm": 0.20612840354442596,
      "learning_rate": 0.00019979970375931912,
      "loss": 0.4974456787109375,
      "step": 110
    },
    {
      "epoch": 0.0974322541357962,
      "grad_norm": 0.17296524345874786,
      "learning_rate": 0.00019969576279570866,
      "loss": 0.4231257438659668,
      "step": 120
    },
    {
      "epoch": 0.10555160864711255,
      "grad_norm": 0.20717096328735352,
      "learning_rate": 0.00019957021556342495,
      "loss": 0.4275392532348633,
      "step": 130
    },
    {
      "epoch": 0.11367096315842891,
      "grad_norm": 0.20023062825202942,
      "learning_rate": 0.00019942308927131972,
      "loss": 0.41733384132385254,
      "step": 140
    },
    {
      "epoch": 0.12179031766974525,
      "grad_norm": 0.17242860794067383,
      "learning_rate": 0.00019925441580490255,
      "loss": 0.41766815185546874,
      "step": 150
    },
    {
      "epoch": 0.12990967218106161,
      "grad_norm": 0.17718906700611115,
      "learning_rate": 0.00019906423171943047,
      "loss": 0.43944649696350097,
      "step": 160
    },
    {
      "epoch": 0.13802902669237796,
      "grad_norm": 0.1699272096157074,
      "learning_rate": 0.0001988525782319856,
      "loss": 0.4246710777282715,
      "step": 170
    },
    {
      "epoch": 0.1461483812036943,
      "grad_norm": 0.18154670298099518,
      "learning_rate": 0.00019861950121254275,
      "loss": 0.40392107963562013,
      "step": 180
    },
    {
      "epoch": 0.15426773571501065,
      "grad_norm": 0.18973930180072784,
      "learning_rate": 0.00019836505117402792,
      "loss": 0.4155430316925049,
      "step": 190
    },
    {
      "epoch": 0.162387090226327,
      "grad_norm": 0.15529297292232513,
      "learning_rate": 0.00019808928326137156,
      "loss": 0.430379581451416,
      "step": 200
    },
    {
      "epoch": 0.17050644473764337,
      "grad_norm": 0.20729880034923553,
      "learning_rate": 0.00019779225723955707,
      "loss": 0.42681236267089845,
      "step": 210
    },
    {
      "epoch": 0.17862579924895972,
      "grad_norm": 0.17007844150066376,
      "learning_rate": 0.0001974740374806686,
      "loss": 0.3926879644393921,
      "step": 220
    },
    {
      "epoch": 0.18674515376027606,
      "grad_norm": 0.1643807291984558,
      "learning_rate": 0.00019713469294994012,
      "loss": 0.41318230628967284,
      "step": 230
    },
    {
      "epoch": 0.1948645082715924,
      "grad_norm": 0.1504553258419037,
      "learning_rate": 0.00019677429719080916,
      "loss": 0.443330192565918,
      "step": 240
    },
    {
      "epoch": 0.20298386278290875,
      "grad_norm": 0.17451228201389313,
      "learning_rate": 0.00019639292830897837,
      "loss": 0.4365452766418457,
      "step": 250
    },
    {
      "epoch": 0.2111032172942251,
      "grad_norm": 0.16454367339611053,
      "learning_rate": 0.0001959906689554881,
      "loss": 0.45282588005065916,
      "step": 260
    },
    {
      "epoch": 0.21922257180554147,
      "grad_norm": 0.15446598827838898,
      "learning_rate": 0.0001955676063088045,
      "loss": 0.46193952560424806,
      "step": 270
    },
    {
      "epoch": 0.22734192631685782,
      "grad_norm": 0.17489995062351227,
      "learning_rate": 0.00019512383205592552,
      "loss": 0.46073436737060547,
      "step": 280
    },
    {
      "epoch": 0.23546128082817416,
      "grad_norm": 0.1772591769695282,
      "learning_rate": 0.00019465944237251071,
      "loss": 0.38799960613250734,
      "step": 290
    },
    {
      "epoch": 0.2435806353394905,
      "grad_norm": 0.11530005931854248,
      "learning_rate": 0.00019417453790203772,
      "loss": 0.4481969833374023,
      "step": 300
    },
    {
      "epoch": 0.2516999898508069,
      "grad_norm": 0.1683167964220047,
      "learning_rate": 0.0001936692237339905,
      "loss": 0.41562438011169434,
      "step": 310
    },
    {
      "epoch": 0.25981934436212323,
      "grad_norm": 0.16425232589244843,
      "learning_rate": 0.00019314360938108425,
      "loss": 0.40752553939819336,
      "step": 320
    },
    {
      "epoch": 0.2679386988734396,
      "grad_norm": 0.16231301426887512,
      "learning_rate": 0.0001925978087555316,
      "loss": 0.3947896480560303,
      "step": 330
    },
    {
      "epoch": 0.2760580533847559,
      "grad_norm": 0.17653369903564453,
      "learning_rate": 0.00019203194014435525,
      "loss": 0.4535045146942139,
      "step": 340
    },
    {
      "epoch": 0.28417740789607226,
      "grad_norm": 0.15756867825984955,
      "learning_rate": 0.0001914461261837526,
      "loss": 0.4795684814453125,
      "step": 350
    },
    {
      "epoch": 0.2922967624073886,
      "grad_norm": 0.1505475640296936,
      "learning_rate": 0.00019084049383251783,
      "loss": 0.4024923324584961,
      "step": 360
    },
    {
      "epoch": 0.30041611691870496,
      "grad_norm": 0.16846773028373718,
      "learning_rate": 0.00019021517434452702,
      "loss": 0.42346930503845215,
      "step": 370
    },
    {
      "epoch": 0.3085354714300213,
      "grad_norm": 0.17196664214134216,
      "learning_rate": 0.0001895703032402926,
      "loss": 0.38081505298614504,
      "step": 380
    },
    {
      "epoch": 0.31665482594133765,
      "grad_norm": 0.18256904184818268,
      "learning_rate": 0.00018890602027759313,
      "loss": 0.37936599254608155,
      "step": 390
    },
    {
      "epoch": 0.324774180452654,
      "grad_norm": 0.1385713666677475,
      "learning_rate": 0.00018822246942118466,
      "loss": 0.3991415977478027,
      "step": 400
    },
    {
      "epoch": 0.33289353496397034,
      "grad_norm": 0.15789403021335602,
      "learning_rate": 0.00018751979881160029,
      "loss": 0.40332279205322263,
      "step": 410
    },
    {
      "epoch": 0.34101288947528674,
      "grad_norm": 0.15686365962028503,
      "learning_rate": 0.0001867981607330451,
      "loss": 0.3878762722015381,
      "step": 420
    },
    {
      "epoch": 0.3491322439866031,
      "grad_norm": 0.15789690613746643,
      "learning_rate": 0.00018605771158039253,
      "loss": 0.3754732131958008,
      "step": 430
    },
    {
      "epoch": 0.35725159849791943,
      "grad_norm": 0.14583982527256012,
      "learning_rate": 0.00018529861182529036,
      "loss": 0.4119413375854492,
      "step": 440
    },
    {
      "epoch": 0.3653709530092358,
      "grad_norm": 0.16271716356277466,
      "learning_rate": 0.0001845210259813829,
      "loss": 0.4371773719787598,
      "step": 450
    },
    {
      "epoch": 0.3734903075205521,
      "grad_norm": 0.15252803266048431,
      "learning_rate": 0.00018372512256865724,
      "loss": 0.3985795021057129,
      "step": 460
    },
    {
      "epoch": 0.38160966203186847,
      "grad_norm": 0.17694011330604553,
      "learning_rate": 0.00018291107407692128,
      "loss": 0.40482492446899415,
      "step": 470
    },
    {
      "epoch": 0.3897290165431848,
      "grad_norm": 0.15677419304847717,
      "learning_rate": 0.00018207905692842134,
      "loss": 0.3925381898880005,
      "step": 480
    },
    {
      "epoch": 0.39784837105450116,
      "grad_norm": 0.15828488767147064,
      "learning_rate": 0.00018122925143960775,
      "loss": 0.3869333028793335,
      "step": 490
    },
    {
      "epoch": 0.4059677255658175,
      "grad_norm": 0.13660173118114471,
      "learning_rate": 0.000180361841782056,
      "loss": 0.4138071060180664,
      "step": 500
    },
    {
      "epoch": 0.41408708007713385,
      "grad_norm": 0.164328932762146,
      "learning_rate": 0.00017947701594255299,
      "loss": 0.4766359806060791,
      "step": 510
    },
    {
      "epoch": 0.4222064345884502,
      "grad_norm": 0.13619564473628998,
      "learning_rate": 0.00017857496568235597,
      "loss": 0.3740208625793457,
      "step": 520
    },
    {
      "epoch": 0.43032578909976654,
      "grad_norm": 0.1389133632183075,
      "learning_rate": 0.00017765588649563372,
      "loss": 0.4194491386413574,
      "step": 530
    },
    {
      "epoch": 0.43844514361108294,
      "grad_norm": 0.16105148196220398,
      "learning_rate": 0.00017671997756709863,
      "loss": 0.37844417095184324,
      "step": 540
    },
    {
      "epoch": 0.4465644981223993,
      "grad_norm": 0.1176551878452301,
      "learning_rate": 0.00017576744172883899,
      "loss": 0.3884027719497681,
      "step": 550
    },
    {
      "epoch": 0.45468385263371563,
      "grad_norm": 0.15062262117862701,
      "learning_rate": 0.0001747984854163609,
      "loss": 0.4128002643585205,
      "step": 560
    },
    {
      "epoch": 0.462803207145032,
      "grad_norm": 0.14474593102931976,
      "learning_rate": 0.00017381331862384894,
      "loss": 0.37835040092468264,
      "step": 570
    },
    {
      "epoch": 0.4709225616563483,
      "grad_norm": 0.11984218657016754,
      "learning_rate": 0.00017281215485865603,
      "loss": 0.3885404109954834,
      "step": 580
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 0.11157386004924774,
      "learning_rate": 0.00017179521109503146,
      "loss": 0.41469721794128417,
      "step": 590
    },
    {
      "epoch": 0.487161270678981,
      "grad_norm": 0.15861837565898895,
      "learning_rate": 0.00017076270772709807,
      "loss": 0.40916032791137696,
      "step": 600
    },
    {
      "epoch": 0.49528062519029736,
      "grad_norm": 0.16919773817062378,
      "learning_rate": 0.00016971486852108763,
      "loss": 0.38907546997070314,
      "step": 610
    },
    {
      "epoch": 0.5033999797016138,
      "grad_norm": 0.1534120887517929,
      "learning_rate": 0.00016865192056684605,
      "loss": 0.3835587978363037,
      "step": 620
    },
    {
      "epoch": 0.51151933421293,
      "grad_norm": 0.1444127857685089,
      "learning_rate": 0.00016757409422861802,
      "loss": 0.41408615112304686,
      "step": 630
    },
    {
      "epoch": 0.5196386887242465,
      "grad_norm": 0.16517969965934753,
      "learning_rate": 0.00016648162309512173,
      "loss": 0.3881347179412842,
      "step": 640
    },
    {
      "epoch": 0.5277580432355627,
      "grad_norm": 0.16764643788337708,
      "learning_rate": 0.00016537474392892528,
      "loss": 0.36968770027160647,
      "step": 650
    },
    {
      "epoch": 0.5358773977468791,
      "grad_norm": 0.15984776616096497,
      "learning_rate": 0.0001642536966151349,
      "loss": 0.4436800003051758,
      "step": 660
    },
    {
      "epoch": 0.5439967522581954,
      "grad_norm": 0.15119516849517822,
      "learning_rate": 0.00016311872410940676,
      "loss": 0.36648738384246826,
      "step": 670
    },
    {
      "epoch": 0.5521161067695118,
      "grad_norm": 0.17760701477527618,
      "learning_rate": 0.00016197007238529277,
      "loss": 0.43828520774841306,
      "step": 680
    },
    {
      "epoch": 0.5602354612808281,
      "grad_norm": 0.15702351927757263,
      "learning_rate": 0.00016080799038093311,
      "loss": 0.39908370971679685,
      "step": 690
    },
    {
      "epoch": 0.5683548157921445,
      "grad_norm": 0.16063162684440613,
      "learning_rate": 0.0001596327299451054,
      "loss": 0.3547415256500244,
      "step": 700
    },
    {
      "epoch": 0.5764741703034608,
      "grad_norm": 0.15705077350139618,
      "learning_rate": 0.000158444545782644,
      "loss": 0.38064041137695315,
      "step": 710
    },
    {
      "epoch": 0.5845935248147772,
      "grad_norm": 0.2802039086818695,
      "learning_rate": 0.0001572436953992394,
      "loss": 0.34356114864349363,
      "step": 720
    },
    {
      "epoch": 0.5927128793260936,
      "grad_norm": 0.14802053570747375,
      "learning_rate": 0.00015603043904563148,
      "loss": 0.44878721237182617,
      "step": 730
    },
    {
      "epoch": 0.6008322338374099,
      "grad_norm": 0.15852048993110657,
      "learning_rate": 0.00015480503966120704,
      "loss": 0.40053658485412597,
      "step": 740
    },
    {
      "epoch": 0.6089515883487263,
      "grad_norm": 0.15426747500896454,
      "learning_rate": 0.00015356776281701538,
      "loss": 0.404225492477417,
      "step": 750
    },
    {
      "epoch": 0.6170709428600426,
      "grad_norm": 0.1420115828514099,
      "learning_rate": 0.000152318876658213,
      "loss": 0.37903261184692383,
      "step": 760
    },
    {
      "epoch": 0.625190297371359,
      "grad_norm": 0.13923387229442596,
      "learning_rate": 0.00015105865184595073,
      "loss": 0.35583546161651614,
      "step": 770
    },
    {
      "epoch": 0.6333096518826753,
      "grad_norm": 0.14876466989517212,
      "learning_rate": 0.00014978736149871545,
      "loss": 0.3251772165298462,
      "step": 780
    },
    {
      "epoch": 0.6414290063939917,
      "grad_norm": 0.17565123736858368,
      "learning_rate": 0.0001485052811331393,
      "loss": 0.39765985012054444,
      "step": 790
    },
    {
      "epoch": 0.649548360905308,
      "grad_norm": 0.15443134307861328,
      "learning_rate": 0.00014721268860428912,
      "loss": 0.3529685020446777,
      "step": 800
    },
    {
      "epoch": 0.6576677154166244,
      "grad_norm": 0.15266218781471252,
      "learning_rate": 0.00014590986404544923,
      "loss": 0.4115382194519043,
      "step": 810
    },
    {
      "epoch": 0.6657870699279407,
      "grad_norm": 0.14183001220226288,
      "learning_rate": 0.00014459708980741037,
      "loss": 0.4038706302642822,
      "step": 820
    },
    {
      "epoch": 0.6739064244392571,
      "grad_norm": 0.20107750594615936,
      "learning_rate": 0.00014327465039727785,
      "loss": 0.42904024124145507,
      "step": 830
    },
    {
      "epoch": 0.6820257789505735,
      "grad_norm": 0.15056397020816803,
      "learning_rate": 0.00014194283241681293,
      "loss": 0.3807892084121704,
      "step": 840
    },
    {
      "epoch": 0.6901451334618898,
      "grad_norm": 0.16432157158851624,
      "learning_rate": 0.00014060192450031958,
      "loss": 0.40647153854370116,
      "step": 850
    },
    {
      "epoch": 0.6982644879732062,
      "grad_norm": 0.14384903013706207,
      "learning_rate": 0.0001392522172520913,
      "loss": 0.400847864151001,
      "step": 860
    },
    {
      "epoch": 0.7063838424845225,
      "grad_norm": 0.16257992386817932,
      "learning_rate": 0.00013789400318343068,
      "loss": 0.4034707069396973,
      "step": 870
    },
    {
      "epoch": 0.7145031969958389,
      "grad_norm": 0.1456725299358368,
      "learning_rate": 0.00013652757664925572,
      "loss": 0.3958974123001099,
      "step": 880
    },
    {
      "epoch": 0.7226225515071552,
      "grad_norm": 0.1645933985710144,
      "learning_rate": 0.00013515323378430664,
      "loss": 0.39889843463897706,
      "step": 890
    },
    {
      "epoch": 0.7307419060184716,
      "grad_norm": 0.14808154106140137,
      "learning_rate": 0.00013377127243896706,
      "loss": 0.39709608554840087,
      "step": 900
    },
    {
      "epoch": 0.7388612605297878,
      "grad_norm": 0.15682613849639893,
      "learning_rate": 0.00013238199211471305,
      "loss": 0.3838841199874878,
      "step": 910
    },
    {
      "epoch": 0.7469806150411042,
      "grad_norm": 0.15188175439834595,
      "learning_rate": 0.00013098569389920488,
      "loss": 0.4285408973693848,
      "step": 920
    },
    {
      "epoch": 0.7550999695524205,
      "grad_norm": 0.16449961066246033,
      "learning_rate": 0.00012958268040103434,
      "loss": 0.37526252269744875,
      "step": 930
    },
    {
      "epoch": 0.7632193240637369,
      "grad_norm": 0.1517837643623352,
      "learning_rate": 0.00012817325568414297,
      "loss": 0.40034284591674807,
      "step": 940
    },
    {
      "epoch": 0.7713386785750533,
      "grad_norm": 0.18229644000530243,
      "learning_rate": 0.00012675772520192476,
      "loss": 0.37904250621795654,
      "step": 950
    },
    {
      "epoch": 0.7794580330863696,
      "grad_norm": 0.15189775824546814,
      "learning_rate": 0.00012533639573102754,
      "loss": 0.4246711254119873,
      "step": 960
    },
    {
      "epoch": 0.787577387597686,
      "grad_norm": 0.15175221860408783,
      "learning_rate": 0.0001239095753048678,
      "loss": 0.3818449735641479,
      "step": 970
    },
    {
      "epoch": 0.7956967421090023,
      "grad_norm": 0.14126037061214447,
      "learning_rate": 0.00012247757314687297,
      "loss": 0.3847095251083374,
      "step": 980
    },
    {
      "epoch": 0.8038160966203187,
      "grad_norm": 0.17514625191688538,
      "learning_rate": 0.00012104069960346596,
      "loss": 0.40877785682678225,
      "step": 990
    },
    {
      "epoch": 0.811935451131635,
      "grad_norm": 0.1650720089673996,
      "learning_rate": 0.00011959926607680639,
      "loss": 0.40711078643798826,
      "step": 1000
    },
    {
      "epoch": 0.8200548056429514,
      "grad_norm": 0.15258049964904785,
      "learning_rate": 0.00011815358495730253,
      "loss": 0.40592288970947266,
      "step": 1010
    },
    {
      "epoch": 0.8281741601542677,
      "grad_norm": 0.14057976007461548,
      "learning_rate": 0.00011670396955590974,
      "loss": 0.3216592073440552,
      "step": 1020
    },
    {
      "epoch": 0.8362935146655841,
      "grad_norm": 0.16660679876804352,
      "learning_rate": 0.00011525073403622894,
      "loss": 0.40019774436950684,
      "step": 1030
    },
    {
      "epoch": 0.8444128691769004,
      "grad_norm": 0.17680172622203827,
      "learning_rate": 0.0001137941933464204,
      "loss": 0.4132580280303955,
      "step": 1040
    },
    {
      "epoch": 0.8525322236882168,
      "grad_norm": 0.17041870951652527,
      "learning_rate": 0.0001123346631509477,
      "loss": 0.3415886878967285,
      "step": 1050
    },
    {
      "epoch": 0.8606515781995331,
      "grad_norm": 0.15096868574619293,
      "learning_rate": 0.00011087245976216607,
      "loss": 0.4133938789367676,
      "step": 1060
    },
    {
      "epoch": 0.8687709327108495,
      "grad_norm": 0.15110765397548676,
      "learning_rate": 0.00010940790007177069,
      "loss": 0.38502039909362795,
      "step": 1070
    },
    {
      "epoch": 0.8768902872221659,
      "grad_norm": 0.1299409419298172,
      "learning_rate": 0.00010794130148211918,
      "loss": 0.36754612922668456,
      "step": 1080
    },
    {
      "epoch": 0.8850096417334822,
      "grad_norm": 0.16098879277706146,
      "learning_rate": 0.00010647298183744359,
      "loss": 0.4300854206085205,
      "step": 1090
    },
    {
      "epoch": 0.8931289962447986,
      "grad_norm": 0.18567131459712982,
      "learning_rate": 0.00010500325935496654,
      "loss": 0.4555531978607178,
      "step": 1100
    },
    {
      "epoch": 0.9012483507561149,
      "grad_norm": 0.15725167095661163,
      "learning_rate": 0.00010353245255593645,
      "loss": 0.40347743034362793,
      "step": 1110
    },
    {
      "epoch": 0.9093677052674313,
      "grad_norm": 0.18014128506183624,
      "learning_rate": 0.0001020608801965971,
      "loss": 0.43356914520263673,
      "step": 1120
    },
    {
      "epoch": 0.9174870597787476,
      "grad_norm": 0.14646700024604797,
      "learning_rate": 0.00010058886119910603,
      "loss": 0.3579983949661255,
      "step": 1130
    },
    {
      "epoch": 0.925606414290064,
      "grad_norm": 0.15054835379123688,
      "learning_rate": 9.911671458241707e-05,
      "loss": 0.412873363494873,
      "step": 1140
    },
    {
      "epoch": 0.9337257688013803,
      "grad_norm": 0.1782434582710266,
      "learning_rate": 9.764475939314199e-05,
      "loss": 0.3661553144454956,
      "step": 1150
    },
    {
      "epoch": 0.9418451233126967,
      "grad_norm": 0.14244233071804047,
      "learning_rate": 9.6173314636406e-05,
      "loss": 0.33595120906829834,
      "step": 1160
    },
    {
      "epoch": 0.9499644778240129,
      "grad_norm": 0.15346868336200714,
      "learning_rate": 9.470269920671242e-05,
      "loss": 0.35301713943481444,
      "step": 1170
    },
    {
      "epoch": 0.9580838323353293,
      "grad_norm": 0.17095577716827393,
      "learning_rate": 9.323323181883093e-05,
      "loss": 0.46831064224243163,
      "step": 1180
    },
    {
      "epoch": 0.9662031868466457,
      "grad_norm": 0.16479066014289856,
      "learning_rate": 9.176523093872545e-05,
      "loss": 0.35177159309387207,
      "step": 1190
    },
    {
      "epoch": 0.974322541357962,
      "grad_norm": 0.15938977897167206,
      "learning_rate": 9.02990147145352e-05,
      "loss": 0.40160298347473145,
      "step": 1200
    },
    {
      "epoch": 0.9824418958692784,
      "grad_norm": 0.15273737907409668,
      "learning_rate": 8.883490090762524e-05,
      "loss": 0.3344574451446533,
      "step": 1210
    },
    {
      "epoch": 0.9905612503805947,
      "grad_norm": 0.17632175981998444,
      "learning_rate": 8.737320682372048e-05,
      "loss": 0.3946251392364502,
      "step": 1220
    },
    {
      "epoch": 0.9986806048919111,
      "grad_norm": 0.1546667516231537,
      "learning_rate": 8.59142492441384e-05,
      "loss": 0.38449108600616455,
      "step": 1230
    },
    {
      "epoch": 1.0064954836090532,
      "grad_norm": 0.1582242101430893,
      "learning_rate": 8.445834435713589e-05,
      "loss": 0.35192313194274905,
      "step": 1240
    },
    {
      "epoch": 1.0146148381203695,
      "grad_norm": 0.16060605645179749,
      "learning_rate": 8.300580768938389e-05,
      "loss": 0.3984487295150757,
      "step": 1250
    },
    {
      "epoch": 1.0227341926316857,
      "grad_norm": 0.15913701057434082,
      "learning_rate": 8.155695403758614e-05,
      "loss": 0.3666527271270752,
      "step": 1260
    },
    {
      "epoch": 1.030853547143002,
      "grad_norm": 0.2222735434770584,
      "learning_rate": 8.011209740025568e-05,
      "loss": 0.39426436424255373,
      "step": 1270
    },
    {
      "epoch": 1.0389729016543185,
      "grad_norm": 0.14628788828849792,
      "learning_rate": 7.867155090966429e-05,
      "loss": 0.3448423147201538,
      "step": 1280
    },
    {
      "epoch": 1.0470922561656348,
      "grad_norm": 0.1674235761165619,
      "learning_rate": 7.723562676398017e-05,
      "loss": 0.3735038280487061,
      "step": 1290
    },
    {
      "epoch": 1.0552116106769511,
      "grad_norm": 0.1577482521533966,
      "learning_rate": 7.580463615960731e-05,
      "loss": 0.36143453121185304,
      "step": 1300
    },
    {
      "epoch": 1.0633309651882676,
      "grad_norm": 0.15055105090141296,
      "learning_rate": 7.437888922374276e-05,
      "loss": 0.3465540647506714,
      "step": 1310
    },
    {
      "epoch": 1.071450319699584,
      "grad_norm": 0.16190367937088013,
      "learning_rate": 7.2958694947165e-05,
      "loss": 0.3162075519561768,
      "step": 1320
    },
    {
      "epoch": 1.0795696742109002,
      "grad_norm": 0.13373522460460663,
      "learning_rate": 7.154436111726885e-05,
      "loss": 0.2877171516418457,
      "step": 1330
    },
    {
      "epoch": 1.0876890287222165,
      "grad_norm": 0.1537173092365265,
      "learning_rate": 7.013619425136125e-05,
      "loss": 0.371155834197998,
      "step": 1340
    },
    {
      "epoch": 1.095808383233533,
      "grad_norm": 0.153018981218338,
      "learning_rate": 6.873449953023205e-05,
      "loss": 0.3403003454208374,
      "step": 1350
    },
    {
      "epoch": 1.1039277377448493,
      "grad_norm": 0.14698824286460876,
      "learning_rate": 6.733958073201484e-05,
      "loss": 0.3563337802886963,
      "step": 1360
    },
    {
      "epoch": 1.1120470922561656,
      "grad_norm": 0.17373280227184296,
      "learning_rate": 6.595174016635132e-05,
      "loss": 0.36922128200531007,
      "step": 1370
    },
    {
      "epoch": 1.120166446767482,
      "grad_norm": 0.1971225142478943,
      "learning_rate": 6.457127860887424e-05,
      "loss": 0.40238251686096194,
      "step": 1380
    },
    {
      "epoch": 1.1282858012787984,
      "grad_norm": 0.1588146984577179,
      "learning_rate": 6.319849523602271e-05,
      "loss": 0.38647644519805907,
      "step": 1390
    },
    {
      "epoch": 1.1364051557901147,
      "grad_norm": 0.1998201310634613,
      "learning_rate": 6.18336875602039e-05,
      "loss": 0.3392190933227539,
      "step": 1400
    },
    {
      "epoch": 1.144524510301431,
      "grad_norm": 0.1279604434967041,
      "learning_rate": 6.047715136531587e-05,
      "loss": 0.29073169231414797,
      "step": 1410
    },
    {
      "epoch": 1.1526438648127475,
      "grad_norm": 0.17609012126922607,
      "learning_rate": 5.9129180642644414e-05,
      "loss": 0.3901878118515015,
      "step": 1420
    },
    {
      "epoch": 1.1607632193240638,
      "grad_norm": 0.1663195639848709,
      "learning_rate": 5.779006752714868e-05,
      "loss": 0.3095200300216675,
      "step": 1430
    },
    {
      "epoch": 1.16888257383538,
      "grad_norm": 0.14723604917526245,
      "learning_rate": 5.646010223414924e-05,
      "loss": 0.3879781007766724,
      "step": 1440
    },
    {
      "epoch": 1.1770019283466964,
      "grad_norm": 0.19692786037921906,
      "learning_rate": 5.513957299643194e-05,
      "loss": 0.3436476469039917,
      "step": 1450
    },
    {
      "epoch": 1.1851212828580129,
      "grad_norm": 0.14053191244602203,
      "learning_rate": 5.382876600178155e-05,
      "loss": 0.32699582576751707,
      "step": 1460
    },
    {
      "epoch": 1.1932406373693292,
      "grad_norm": 0.18614161014556885,
      "learning_rate": 5.25279653309584e-05,
      "loss": 0.3756012201309204,
      "step": 1470
    },
    {
      "epoch": 1.2013599918806455,
      "grad_norm": 0.17593547701835632,
      "learning_rate": 5.1237452896132067e-05,
      "loss": 0.4036771297454834,
      "step": 1480
    },
    {
      "epoch": 1.2094793463919618,
      "grad_norm": 0.1469552218914032,
      "learning_rate": 4.9957508379784704e-05,
      "loss": 0.35532774925231936,
      "step": 1490
    },
    {
      "epoch": 1.2175987009032783,
      "grad_norm": 0.1465003490447998,
      "learning_rate": 4.86884091740975e-05,
      "loss": 0.3272955656051636,
      "step": 1500
    },
    {
      "epoch": 1.2257180554145946,
      "grad_norm": 0.16992369294166565,
      "learning_rate": 4.7430430320834e-05,
      "loss": 0.3861941576004028,
      "step": 1510
    },
    {
      "epoch": 1.2338374099259108,
      "grad_norm": 0.19381046295166016,
      "learning_rate": 4.618384445173228e-05,
      "loss": 0.36703226566314695,
      "step": 1520
    },
    {
      "epoch": 1.2419567644372274,
      "grad_norm": 0.1563887596130371,
      "learning_rate": 4.494892172941965e-05,
      "loss": 0.40213809013366697,
      "step": 1530
    },
    {
      "epoch": 1.2500761189485436,
      "grad_norm": 0.145489901304245,
      "learning_rate": 4.372592978886254e-05,
      "loss": 0.344010591506958,
      "step": 1540
    },
    {
      "epoch": 1.25819547345986,
      "grad_norm": 0.16564379632472992,
      "learning_rate": 4.2515133679364116e-05,
      "loss": 0.3600982904434204,
      "step": 1550
    },
    {
      "epoch": 1.2663148279711762,
      "grad_norm": 0.12342356890439987,
      "learning_rate": 4.13167958071221e-05,
      "loss": 0.32795798778533936,
      "step": 1560
    },
    {
      "epoch": 1.2744341824824925,
      "grad_norm": 0.18176662921905518,
      "learning_rate": 4.013117587835978e-05,
      "loss": 0.36577463150024414,
      "step": 1570
    },
    {
      "epoch": 1.282553536993809,
      "grad_norm": 0.1916268765926361,
      "learning_rate": 3.895853084304176e-05,
      "loss": 0.39234256744384766,
      "step": 1580
    },
    {
      "epoch": 1.2906728915051253,
      "grad_norm": 0.1897222399711609,
      "learning_rate": 3.779911483918739e-05,
      "loss": 0.41258983612060546,
      "step": 1590
    },
    {
      "epoch": 1.2987922460164416,
      "grad_norm": 0.15678349137306213,
      "learning_rate": 3.665317913779337e-05,
      "loss": 0.3665084600448608,
      "step": 1600
    },
    {
      "epoch": 1.3069116005277581,
      "grad_norm": 0.16308161616325378,
      "learning_rate": 3.552097208837775e-05,
      "loss": 0.3931357622146606,
      "step": 1610
    },
    {
      "epoch": 1.3150309550390744,
      "grad_norm": 0.1778445839881897,
      "learning_rate": 3.4402739065157266e-05,
      "loss": 0.3759305477142334,
      "step": 1620
    },
    {
      "epoch": 1.3231503095503907,
      "grad_norm": 0.1780257523059845,
      "learning_rate": 3.3298722413869155e-05,
      "loss": 0.3472525358200073,
      "step": 1630
    },
    {
      "epoch": 1.3312696640617072,
      "grad_norm": 0.14955449104309082,
      "learning_rate": 3.2209161399249674e-05,
      "loss": 0.34793896675109864,
      "step": 1640
    },
    {
      "epoch": 1.3393890185730235,
      "grad_norm": 0.20207709074020386,
      "learning_rate": 3.1134292153180056e-05,
      "loss": 0.3454656362533569,
      "step": 1650
    },
    {
      "epoch": 1.3475083730843398,
      "grad_norm": 0.18875418603420258,
      "learning_rate": 3.007434762351147e-05,
      "loss": 0.3456529140472412,
      "step": 1660
    },
    {
      "epoch": 1.355627727595656,
      "grad_norm": 0.18712455034255981,
      "learning_rate": 2.9029557523580253e-05,
      "loss": 0.33401539325714114,
      "step": 1670
    },
    {
      "epoch": 1.3637470821069724,
      "grad_norm": 0.16952762007713318,
      "learning_rate": 2.800014828242381e-05,
      "loss": 0.3649503231048584,
      "step": 1680
    },
    {
      "epoch": 1.3718664366182889,
      "grad_norm": 0.19082432985305786,
      "learning_rate": 2.698634299570857e-05,
      "loss": 0.3909872770309448,
      "step": 1690
    },
    {
      "epoch": 1.3799857911296052,
      "grad_norm": 0.16776010394096375,
      "learning_rate": 2.5988361377380188e-05,
      "loss": 0.3379994869232178,
      "step": 1700
    },
    {
      "epoch": 1.3881051456409215,
      "grad_norm": 0.19785159826278687,
      "learning_rate": 2.5006419712046636e-05,
      "loss": 0.3403695821762085,
      "step": 1710
    },
    {
      "epoch": 1.396224500152238,
      "grad_norm": 0.12651121616363525,
      "learning_rate": 2.4040730808104706e-05,
      "loss": 0.37059574127197265,
      "step": 1720
    },
    {
      "epoch": 1.4043438546635543,
      "grad_norm": 0.18700380623340607,
      "learning_rate": 2.3091503951619543e-05,
      "loss": 0.4034583568572998,
      "step": 1730
    },
    {
      "epoch": 1.4124632091748706,
      "grad_norm": 0.1756463646888733,
      "learning_rate": 2.2158944860967946e-05,
      "loss": 0.3308366060256958,
      "step": 1740
    },
    {
      "epoch": 1.420582563686187,
      "grad_norm": 0.19831162691116333,
      "learning_rate": 2.1243255642254578e-05,
      "loss": 0.3691343069076538,
      "step": 1750
    },
    {
      "epoch": 1.4287019181975034,
      "grad_norm": 0.1685105711221695,
      "learning_rate": 2.0344634745511015e-05,
      "loss": 0.3646685600280762,
      "step": 1760
    },
    {
      "epoch": 1.4368212727088197,
      "grad_norm": 0.1513417512178421,
      "learning_rate": 1.9463276921687458e-05,
      "loss": 0.3358032464981079,
      "step": 1770
    },
    {
      "epoch": 1.444940627220136,
      "grad_norm": 0.21079151332378387,
      "learning_rate": 1.8599373180445688e-05,
      "loss": 0.38408379554748534,
      "step": 1780
    },
    {
      "epoch": 1.4530599817314522,
      "grad_norm": 0.1852787733078003,
      "learning_rate": 1.775311074876329e-05,
      "loss": 0.3572732925415039,
      "step": 1790
    },
    {
      "epoch": 1.4611793362427687,
      "grad_norm": 0.18594121932983398,
      "learning_rate": 1.6924673030357285e-05,
      "loss": 0.34491288661956787,
      "step": 1800
    },
    {
      "epoch": 1.469298690754085,
      "grad_norm": 0.16469211876392365,
      "learning_rate": 1.6114239565936484e-05,
      "loss": 0.3106041193008423,
      "step": 1810
    },
    {
      "epoch": 1.4774180452654013,
      "grad_norm": 0.146048441529274,
      "learning_rate": 1.532198599429122e-05,
      "loss": 0.3674412965774536,
      "step": 1820
    },
    {
      "epoch": 1.4855373997767178,
      "grad_norm": 0.18818271160125732,
      "learning_rate": 1.454808401422837e-05,
      "loss": 0.3938064336776733,
      "step": 1830
    },
    {
      "epoch": 1.4936567542880341,
      "grad_norm": 0.20953674614429474,
      "learning_rate": 1.379270134736057e-05,
      "loss": 0.30992081165313723,
      "step": 1840
    },
    {
      "epoch": 1.5017761087993504,
      "grad_norm": 0.21023158729076385,
      "learning_rate": 1.3056001701757226e-05,
      "loss": 0.3922957181930542,
      "step": 1850
    },
    {
      "epoch": 1.509895463310667,
      "grad_norm": 0.18391859531402588,
      "learning_rate": 1.233814473646524e-05,
      "loss": 0.3312171459197998,
      "step": 1860
    },
    {
      "epoch": 1.518014817821983,
      "grad_norm": 0.20905567705631256,
      "learning_rate": 1.1639286026907581e-05,
      "loss": 0.33843116760253905,
      "step": 1870
    },
    {
      "epoch": 1.5261341723332995,
      "grad_norm": 0.2057563066482544,
      "learning_rate": 1.0959577031166513e-05,
      "loss": 0.32880287170410155,
      "step": 1880
    },
    {
      "epoch": 1.5342535268446158,
      "grad_norm": 0.16004444658756256,
      "learning_rate": 1.0299165057159332e-05,
      "loss": 0.3609264850616455,
      "step": 1890
    },
    {
      "epoch": 1.542372881355932,
      "grad_norm": 0.18283307552337646,
      "learning_rate": 9.658193230713509e-06,
      "loss": 0.36747682094573975,
      "step": 1900
    },
    {
      "epoch": 1.5504922358672486,
      "grad_norm": 0.13987980782985687,
      "learning_rate": 9.036800464548157e-06,
      "loss": 0.3149809598922729,
      "step": 1910
    },
    {
      "epoch": 1.558611590378565,
      "grad_norm": 0.20485147833824158,
      "learning_rate": 8.435121428168613e-06,
      "loss": 0.3814858436584473,
      "step": 1920
    },
    {
      "epoch": 1.5667309448898812,
      "grad_norm": 0.19381378591060638,
      "learning_rate": 7.853286518680503e-06,
      "loss": 0.3389918565750122,
      "step": 1930
    },
    {
      "epoch": 1.5748502994011977,
      "grad_norm": 0.1762656271457672,
      "learning_rate": 7.291421832529921e-06,
      "loss": 0.3758829355239868,
      "step": 1940
    },
    {
      "epoch": 1.582969653912514,
      "grad_norm": 0.18566051125526428,
      "learning_rate": 6.749649138175518e-06,
      "loss": 0.361565375328064,
      "step": 1950
    },
    {
      "epoch": 1.5910890084238303,
      "grad_norm": 0.1679965704679489,
      "learning_rate": 6.228085849698495e-06,
      "loss": 0.3467693567276001,
      "step": 1960
    },
    {
      "epoch": 1.5992083629351468,
      "grad_norm": 0.19734881818294525,
      "learning_rate": 5.726845001356573e-06,
      "loss": 0.41715250015258787,
      "step": 1970
    },
    {
      "epoch": 1.6073277174464629,
      "grad_norm": 0.20948296785354614,
      "learning_rate": 5.246035223086821e-06,
      "loss": 0.3086181879043579,
      "step": 1980
    },
    {
      "epoch": 1.6154470719577794,
      "grad_norm": 0.2349746823310852,
      "learning_rate": 4.785760716963205e-06,
      "loss": 0.2819353580474854,
      "step": 1990
    },
    {
      "epoch": 1.6235664264690957,
      "grad_norm": 0.15716052055358887,
      "learning_rate": 4.346121234613732e-06,
      "loss": 0.4032479763031006,
      "step": 2000
    },
    {
      "epoch": 1.631685780980412,
      "grad_norm": 0.1870564967393875,
      "learning_rate": 3.927212055602003e-06,
      "loss": 0.3259021759033203,
      "step": 2010
    },
    {
      "epoch": 1.6398051354917285,
      "grad_norm": 0.1917184740304947,
      "learning_rate": 3.5291239667781253e-06,
      "loss": 0.3619376182556152,
      "step": 2020
    },
    {
      "epoch": 1.6479244900030448,
      "grad_norm": 0.15155203640460968,
      "learning_rate": 3.1519432426031504e-06,
      "loss": 0.3836283445358276,
      "step": 2030
    },
    {
      "epoch": 1.656043844514361,
      "grad_norm": 0.18562212586402893,
      "learning_rate": 2.7957516264514593e-06,
      "loss": 0.35469727516174315,
      "step": 2040
    },
    {
      "epoch": 1.6641631990256776,
      "grad_norm": 0.23471137881278992,
      "learning_rate": 2.4606263128952646e-06,
      "loss": 0.4092714309692383,
      "step": 2050
    },
    {
      "epoch": 1.6722825535369938,
      "grad_norm": 0.19046807289123535,
      "learning_rate": 2.1466399309747364e-06,
      "loss": 0.37486720085144043,
      "step": 2060
    },
    {
      "epoch": 1.6804019080483101,
      "grad_norm": 0.18093442916870117,
      "learning_rate": 1.8538605284577848e-06,
      "loss": 0.3519495248794556,
      "step": 2070
    },
    {
      "epoch": 1.6885212625596266,
      "grad_norm": 0.17989413440227509,
      "learning_rate": 1.5823515570925763e-06,
      "loss": 0.36248462200164794,
      "step": 2080
    },
    {
      "epoch": 1.6966406170709427,
      "grad_norm": 0.18000203371047974,
      "learning_rate": 1.3321718588561128e-06,
      "loss": 0.377717113494873,
      "step": 2090
    },
    {
      "epoch": 1.7047599715822592,
      "grad_norm": 0.1857496201992035,
      "learning_rate": 1.1033756532019102e-06,
      "loss": 0.3373147964477539,
      "step": 2100
    },
    {
      "epoch": 1.7128793260935755,
      "grad_norm": 0.15915660560131073,
      "learning_rate": 8.96012525309442e-07,
      "loss": 0.35358049869537356,
      "step": 2110
    },
    {
      "epoch": 1.7209986806048918,
      "grad_norm": 0.18095794320106506,
      "learning_rate": 7.101274153379244e-07,
      "loss": 0.34168615341186526,
      "step": 2120
    },
    {
      "epoch": 1.7291180351162083,
      "grad_norm": 0.13066989183425903,
      "learning_rate": 5.457606086868406e-07,
      "loss": 0.31731865406036375,
      "step": 2130
    },
    {
      "epoch": 1.7372373896275246,
      "grad_norm": 0.15085873007774353,
      "learning_rate": 4.0294772726511274e-07,
      "loss": 0.3172720193862915,
      "step": 2140
    },
    {
      "epoch": 1.745356744138841,
      "grad_norm": 0.1692853718996048,
      "learning_rate": 2.817197217711565e-07,
      "loss": 0.3663973808288574,
      "step": 2150
    },
    {
      "epoch": 1.7534760986501574,
      "grad_norm": 0.1765965223312378,
      "learning_rate": 1.8210286498512307e-07,
      "loss": 0.3134049415588379,
      "step": 2160
    },
    {
      "epoch": 1.7615954531614737,
      "grad_norm": 0.17754477262496948,
      "learning_rate": 1.0411874607501038e-07,
      "loss": 0.32787179946899414,
      "step": 2170
    }
  ],
  "logging_steps": 10,
  "max_steps": 2200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.388922511336653e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}