{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2917,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003428914320003429,
      "grad_norm": 1.3298883438110352,
      "learning_rate": 2.054794520547945e-06,
      "loss": 0.8432891845703125,
      "step": 10
    },
    {
      "epoch": 0.006857828640006858,
      "grad_norm": 1.4883699417114258,
      "learning_rate": 4.337899543378996e-06,
      "loss": 0.8494134902954101,
      "step": 20
    },
    {
      "epoch": 0.010286742960010286,
      "grad_norm": 1.569236159324646,
      "learning_rate": 6.621004566210046e-06,
      "loss": 0.7930152893066407,
      "step": 30
    },
    {
      "epoch": 0.013715657280013716,
      "grad_norm": 1.444800853729248,
      "learning_rate": 8.904109589041095e-06,
      "loss": 0.6452465534210206,
      "step": 40
    },
    {
      "epoch": 0.017144571600017144,
      "grad_norm": 0.634009838104248,
      "learning_rate": 1.1187214611872146e-05,
      "loss": 0.47983288764953613,
      "step": 50
    },
    {
      "epoch": 0.020573485920020573,
      "grad_norm": 0.35944080352783203,
      "learning_rate": 1.3470319634703196e-05,
      "loss": 0.38299362659454345,
      "step": 60
    },
    {
      "epoch": 0.024002400240024,
      "grad_norm": 0.2663295567035675,
      "learning_rate": 1.5753424657534248e-05,
      "loss": 0.3400583028793335,
      "step": 70
    },
    {
      "epoch": 0.027431314560027432,
      "grad_norm": 0.1992281973361969,
      "learning_rate": 1.80365296803653e-05,
      "loss": 0.3030625104904175,
      "step": 80
    },
    {
      "epoch": 0.03086022888003086,
      "grad_norm": 0.1845274269580841,
      "learning_rate": 2.0319634703196345e-05,
      "loss": 0.283364462852478,
      "step": 90
    },
    {
      "epoch": 0.03428914320003429,
      "grad_norm": 0.15725447237491608,
      "learning_rate": 2.2602739726027396e-05,
      "loss": 0.27444844245910643,
      "step": 100
    },
    {
      "epoch": 0.03771805752003772,
      "grad_norm": 0.1385478377342224,
      "learning_rate": 2.4885844748858446e-05,
      "loss": 0.2594951391220093,
      "step": 110
    },
    {
      "epoch": 0.041146971840041145,
      "grad_norm": 0.1409701704978943,
      "learning_rate": 2.71689497716895e-05,
      "loss": 0.25205914974212645,
      "step": 120
    },
    {
      "epoch": 0.04457588616004458,
      "grad_norm": 0.12514901161193848,
      "learning_rate": 2.945205479452055e-05,
      "loss": 0.23389830589294433,
      "step": 130
    },
    {
      "epoch": 0.048004800480048,
      "grad_norm": 0.20258280634880066,
      "learning_rate": 3.17351598173516e-05,
      "loss": 0.22158000469207764,
      "step": 140
    },
    {
      "epoch": 0.05143371480005143,
      "grad_norm": 0.14751552045345306,
      "learning_rate": 3.4018264840182654e-05,
      "loss": 0.2103422164916992,
      "step": 150
    },
    {
      "epoch": 0.054862629120054865,
      "grad_norm": 0.1548272967338562,
      "learning_rate": 3.63013698630137e-05,
      "loss": 0.1952539324760437,
      "step": 160
    },
    {
      "epoch": 0.05829154344005829,
      "grad_norm": 0.12594084441661835,
      "learning_rate": 3.8584474885844754e-05,
      "loss": 0.19135934114456177,
      "step": 170
    },
    {
      "epoch": 0.06172045776006172,
      "grad_norm": 0.14258800446987152,
      "learning_rate": 4.08675799086758e-05,
      "loss": 0.17143574953079224,
      "step": 180
    },
    {
      "epoch": 0.06514937208006515,
      "grad_norm": 0.1194511353969574,
      "learning_rate": 4.3150684931506855e-05,
      "loss": 0.15910775661468507,
      "step": 190
    },
    {
      "epoch": 0.06857828640006858,
      "grad_norm": 0.16704410314559937,
      "learning_rate": 4.54337899543379e-05,
      "loss": 0.1537066102027893,
      "step": 200
    },
    {
      "epoch": 0.07200720072007201,
      "grad_norm": 0.12291927635669708,
      "learning_rate": 4.7716894977168955e-05,
      "loss": 0.1391252398490906,
      "step": 210
    },
    {
      "epoch": 0.07543611504007544,
      "grad_norm": 0.12858909368515015,
      "learning_rate": 5e-05,
      "loss": 0.1354471802711487,
      "step": 220
    },
    {
      "epoch": 0.07886502936007886,
      "grad_norm": 0.12648724019527435,
      "learning_rate": 5.2283105022831056e-05,
      "loss": 0.12894512414932252,
      "step": 230
    },
    {
      "epoch": 0.08229394368008229,
      "grad_norm": 0.12357676029205322,
      "learning_rate": 5.45662100456621e-05,
      "loss": 0.12626115083694459,
      "step": 240
    },
    {
      "epoch": 0.08572285800008572,
      "grad_norm": 0.1405642181634903,
      "learning_rate": 5.684931506849316e-05,
      "loss": 0.11540137529373169,
      "step": 250
    },
    {
      "epoch": 0.08915177232008915,
      "grad_norm": 0.17321588099002838,
      "learning_rate": 5.9132420091324204e-05,
      "loss": 0.11650693416595459,
      "step": 260
    },
    {
      "epoch": 0.09258068664009259,
      "grad_norm": 0.13030178844928741,
      "learning_rate": 6.141552511415526e-05,
      "loss": 0.11383731365203857,
      "step": 270
    },
    {
      "epoch": 0.096009600960096,
      "grad_norm": 0.20526033639907837,
      "learning_rate": 6.36986301369863e-05,
      "loss": 0.11148416996002197,
      "step": 280
    },
    {
      "epoch": 0.09943851528009943,
      "grad_norm": 0.12799160182476044,
      "learning_rate": 6.598173515981736e-05,
      "loss": 0.10550851821899414,
      "step": 290
    },
    {
      "epoch": 0.10286742960010287,
      "grad_norm": 0.10688431560993195,
      "learning_rate": 6.82648401826484e-05,
      "loss": 0.09785101413726807,
      "step": 300
    },
    {
      "epoch": 0.1062963439201063,
      "grad_norm": 0.1471128910779953,
      "learning_rate": 7.054794520547947e-05,
      "loss": 0.10035187005996704,
      "step": 310
    },
    {
      "epoch": 0.10972525824010973,
      "grad_norm": 0.15709125995635986,
      "learning_rate": 7.28310502283105e-05,
      "loss": 0.09798988699913025,
      "step": 320
    },
    {
      "epoch": 0.11315417256011315,
      "grad_norm": 0.17999057471752167,
      "learning_rate": 7.511415525114156e-05,
      "loss": 0.1036344051361084,
      "step": 330
    },
    {
      "epoch": 0.11658308688011658,
      "grad_norm": 0.13842232525348663,
      "learning_rate": 7.73972602739726e-05,
      "loss": 0.09758269786834717,
      "step": 340
    },
    {
      "epoch": 0.12001200120012001,
      "grad_norm": 0.26885131001472473,
      "learning_rate": 7.968036529680367e-05,
      "loss": 0.09586278200149537,
      "step": 350
    },
    {
      "epoch": 0.12344091552012344,
      "grad_norm": 0.19039925932884216,
      "learning_rate": 8.19634703196347e-05,
      "loss": 0.0976291537284851,
      "step": 360
    },
    {
      "epoch": 0.12686982984012687,
      "grad_norm": 0.1937050223350525,
      "learning_rate": 8.424657534246576e-05,
      "loss": 0.09275003671646118,
      "step": 370
    },
    {
      "epoch": 0.1302987441601303,
      "grad_norm": 0.18121008574962616,
      "learning_rate": 8.65296803652968e-05,
      "loss": 0.09187136888504029,
      "step": 380
    },
    {
      "epoch": 0.13372765848013374,
      "grad_norm": 0.1285638064146042,
      "learning_rate": 8.881278538812787e-05,
      "loss": 0.09056932926177978,
      "step": 390
    },
    {
      "epoch": 0.13715657280013716,
      "grad_norm": 0.10619012266397476,
      "learning_rate": 9.109589041095891e-05,
      "loss": 0.08771317005157471,
      "step": 400
    },
    {
      "epoch": 0.14058548712014057,
      "grad_norm": 0.13739266991615295,
      "learning_rate": 9.337899543378996e-05,
      "loss": 0.08628376722335815,
      "step": 410
    },
    {
      "epoch": 0.14401440144014402,
      "grad_norm": 0.11956508457660675,
      "learning_rate": 9.5662100456621e-05,
      "loss": 0.0913696527481079,
      "step": 420
    },
    {
      "epoch": 0.14744331576014744,
      "grad_norm": 0.13098114728927612,
      "learning_rate": 9.794520547945207e-05,
      "loss": 0.09056272506713867,
      "step": 430
    },
    {
      "epoch": 0.15087223008015088,
      "grad_norm": 0.14199639856815338,
      "learning_rate": 0.00010022831050228312,
      "loss": 0.08974846601486205,
      "step": 440
    },
    {
      "epoch": 0.1543011444001543,
      "grad_norm": 0.12583988904953003,
      "learning_rate": 0.00010251141552511416,
      "loss": 0.08946011662483215,
      "step": 450
    },
    {
      "epoch": 0.15773005872015772,
      "grad_norm": 0.11818652600049973,
      "learning_rate": 0.0001047945205479452,
      "loss": 0.0851108729839325,
      "step": 460
    },
    {
      "epoch": 0.16115897304016116,
      "grad_norm": 0.12538324296474457,
      "learning_rate": 0.00010707762557077626,
      "loss": 0.08938277363777161,
      "step": 470
    },
    {
      "epoch": 0.16458788736016458,
      "grad_norm": 0.12186136096715927,
      "learning_rate": 0.00010936073059360732,
      "loss": 0.08132482171058655,
      "step": 480
    },
    {
      "epoch": 0.16801680168016803,
      "grad_norm": 0.13485857844352722,
      "learning_rate": 0.00011164383561643836,
      "loss": 0.08109607100486756,
      "step": 490
    },
    {
      "epoch": 0.17144571600017144,
      "grad_norm": 0.11099082231521606,
      "learning_rate": 0.0001139269406392694,
      "loss": 0.0870327353477478,
      "step": 500
    },
    {
      "epoch": 0.17487463032017486,
      "grad_norm": 0.1529977172613144,
      "learning_rate": 0.00011621004566210046,
      "loss": 0.08298802971839905,
      "step": 510
    },
    {
      "epoch": 0.1783035446401783,
      "grad_norm": 0.12247070670127869,
      "learning_rate": 0.00011849315068493152,
      "loss": 0.08257973790168763,
      "step": 520
    },
    {
      "epoch": 0.18173245896018173,
      "grad_norm": 0.09750987589359283,
      "learning_rate": 0.00012077625570776256,
      "loss": 0.08538851737976075,
      "step": 530
    },
    {
      "epoch": 0.18516137328018517,
      "grad_norm": 0.1477072685956955,
      "learning_rate": 0.0001230593607305936,
      "loss": 0.07966969013214112,
      "step": 540
    },
    {
      "epoch": 0.1885902876001886,
      "grad_norm": 0.1115131676197052,
      "learning_rate": 0.00012534246575342465,
      "loss": 0.0803002655506134,
      "step": 550
    },
    {
      "epoch": 0.192019201920192,
      "grad_norm": 0.11209847778081894,
      "learning_rate": 0.0001276255707762557,
      "loss": 0.08299272656440734,
      "step": 560
    },
    {
      "epoch": 0.19544811624019545,
      "grad_norm": 0.10297664999961853,
      "learning_rate": 0.00012990867579908675,
      "loss": 0.07735013961791992,
      "step": 570
    },
    {
      "epoch": 0.19887703056019887,
      "grad_norm": 0.1319982260465622,
      "learning_rate": 0.00013219178082191782,
      "loss": 0.07743288278579712,
      "step": 580
    },
    {
      "epoch": 0.20230594488020232,
      "grad_norm": 0.11637051403522491,
      "learning_rate": 0.00013447488584474886,
      "loss": 0.0807669997215271,
      "step": 590
    },
    {
      "epoch": 0.20573485920020573,
      "grad_norm": 0.11369775235652924,
      "learning_rate": 0.00013675799086757993,
      "loss": 0.07854493260383606,
      "step": 600
    },
    {
      "epoch": 0.20916377352020915,
      "grad_norm": 0.1144910454750061,
      "learning_rate": 0.00013904109589041097,
      "loss": 0.07866560816764831,
      "step": 610
    },
    {
      "epoch": 0.2125926878402126,
      "grad_norm": 0.12000512331724167,
      "learning_rate": 0.000141324200913242,
      "loss": 0.08003532290458679,
      "step": 620
    },
    {
      "epoch": 0.21602160216021601,
      "grad_norm": 0.13864439725875854,
      "learning_rate": 0.00014360730593607305,
      "loss": 0.07690358757972718,
      "step": 630
    },
    {
      "epoch": 0.21945051648021946,
      "grad_norm": 0.11890323460102081,
      "learning_rate": 0.00014589041095890411,
      "loss": 0.08117523193359374,
      "step": 640
    },
    {
      "epoch": 0.22287943080022288,
      "grad_norm": 0.10761404037475586,
      "learning_rate": 0.00014817351598173515,
      "loss": 0.07784844636917114,
      "step": 650
    },
    {
      "epoch": 0.2263083451202263,
      "grad_norm": 0.1405085325241089,
      "learning_rate": 0.00015045662100456622,
      "loss": 0.07747803926467896,
      "step": 660
    },
    {
      "epoch": 0.22973725944022974,
      "grad_norm": 0.12741142511367798,
      "learning_rate": 0.0001527397260273973,
      "loss": 0.08193380236625672,
      "step": 670
    },
    {
      "epoch": 0.23316617376023316,
      "grad_norm": 0.11028678715229034,
      "learning_rate": 0.00015502283105022833,
      "loss": 0.08220186829566956,
      "step": 680
    },
    {
      "epoch": 0.2365950880802366,
      "grad_norm": 0.09016034752130508,
      "learning_rate": 0.00015730593607305937,
      "loss": 0.07895171046257018,
      "step": 690
    },
    {
      "epoch": 0.24002400240024002,
      "grad_norm": 0.12008935213088989,
      "learning_rate": 0.0001595890410958904,
      "loss": 0.07650137543678284,
      "step": 700
    },
    {
      "epoch": 0.24345291672024344,
      "grad_norm": 0.08145634084939957,
      "learning_rate": 0.00016187214611872148,
      "loss": 0.07745814323425293,
      "step": 710
    },
    {
      "epoch": 0.24688183104024689,
      "grad_norm": 0.08875567466020584,
      "learning_rate": 0.00016415525114155252,
      "loss": 0.0772017478942871,
      "step": 720
    },
    {
      "epoch": 0.25031074536025033,
      "grad_norm": 0.08266468346118927,
      "learning_rate": 0.00016643835616438356,
      "loss": 0.07902273535728455,
      "step": 730
    },
    {
      "epoch": 0.25373965968025375,
      "grad_norm": 0.12261392921209335,
      "learning_rate": 0.00016872146118721462,
      "loss": 0.07991406917572022,
      "step": 740
    },
    {
      "epoch": 0.25716857400025717,
      "grad_norm": 0.15539783239364624,
      "learning_rate": 0.0001710045662100457,
      "loss": 0.0717797577381134,
      "step": 750
    },
    {
      "epoch": 0.2605974883202606,
      "grad_norm": 0.12941250205039978,
      "learning_rate": 0.00017328767123287673,
      "loss": 0.07801813483238221,
      "step": 760
    },
    {
      "epoch": 0.264026402640264,
      "grad_norm": 0.10697443783283234,
      "learning_rate": 0.00017557077625570777,
      "loss": 0.08085813522338867,
      "step": 770
    },
    {
      "epoch": 0.2674553169602675,
      "grad_norm": 0.1086842268705368,
      "learning_rate": 0.0001778538812785388,
      "loss": 0.07432876825332642,
      "step": 780
    },
    {
      "epoch": 0.2708842312802709,
      "grad_norm": 0.12223174422979355,
      "learning_rate": 0.00018013698630136988,
      "loss": 0.08123633861541749,
      "step": 790
    },
    {
      "epoch": 0.2743131456002743,
      "grad_norm": 0.09192939847707748,
      "learning_rate": 0.00018242009132420092,
      "loss": 0.07588958740234375,
      "step": 800
    },
    {
      "epoch": 0.27774205992027773,
      "grad_norm": 0.10211896896362305,
      "learning_rate": 0.00018470319634703196,
      "loss": 0.0751219093799591,
      "step": 810
    },
    {
      "epoch": 0.28117097424028115,
      "grad_norm": 0.09135781228542328,
      "learning_rate": 0.00018698630136986303,
      "loss": 0.07519081234931946,
      "step": 820
    },
    {
      "epoch": 0.2845998885602846,
      "grad_norm": 0.0870634913444519,
      "learning_rate": 0.0001892694063926941,
      "loss": 0.07777546644210816,
      "step": 830
    },
    {
      "epoch": 0.28802880288028804,
      "grad_norm": 0.10131728649139404,
      "learning_rate": 0.00019155251141552513,
      "loss": 0.07261776924133301,
      "step": 840
    },
    {
      "epoch": 0.29145771720029146,
      "grad_norm": 0.07320058345794678,
      "learning_rate": 0.00019383561643835617,
      "loss": 0.07279639840126037,
      "step": 850
    },
    {
      "epoch": 0.2948866315202949,
      "grad_norm": 0.08462163805961609,
      "learning_rate": 0.00019611872146118721,
      "loss": 0.07540533542633057,
      "step": 860
    },
    {
      "epoch": 0.2983155458402983,
      "grad_norm": 0.07783285528421402,
      "learning_rate": 0.00019840182648401828,
      "loss": 0.07547606229782104,
      "step": 870
    },
    {
      "epoch": 0.30174446016030176,
      "grad_norm": 0.08769109100103378,
      "learning_rate": 0.00019999999445216476,
      "loss": 0.07635555267333985,
      "step": 880
    },
    {
      "epoch": 0.3051733744803052,
      "grad_norm": 0.09398491680622101,
      "learning_rate": 0.0001999998958239994,
      "loss": 0.07587789893150329,
      "step": 890
    },
    {
      "epoch": 0.3086022888003086,
      "grad_norm": 0.10255398601293564,
      "learning_rate": 0.0001999996739107459,
      "loss": 0.0769170880317688,
      "step": 900
    },
    {
      "epoch": 0.312031203120312,
      "grad_norm": 0.07438833266496658,
      "learning_rate": 0.00019999932871267792,
      "loss": 0.07230271697044373,
      "step": 910
    },
    {
      "epoch": 0.31546011744031544,
      "grad_norm": 0.12263499200344086,
      "learning_rate": 0.0001999988602302209,
      "loss": 0.0734669029712677,
      "step": 920
    },
    {
      "epoch": 0.3188890317603189,
      "grad_norm": 0.07665298879146576,
      "learning_rate": 0.00019999826846395254,
      "loss": 0.07372477054595947,
      "step": 930
    },
    {
      "epoch": 0.3223179460803223,
      "grad_norm": 0.1038631722331047,
      "learning_rate": 0.00019999755341460236,
      "loss": 0.07595999836921692,
      "step": 940
    },
    {
      "epoch": 0.32574686040032574,
      "grad_norm": 0.08356453478336334,
      "learning_rate": 0.00019999671508305185,
      "loss": 0.07429630756378174,
      "step": 950
    },
    {
      "epoch": 0.32917577472032916,
      "grad_norm": 0.09604129195213318,
      "learning_rate": 0.0001999957534703346,
      "loss": 0.07514963746070862,
      "step": 960
    },
    {
      "epoch": 0.3326046890403326,
      "grad_norm": 0.07055286318063736,
      "learning_rate": 0.00019999466857763615,
      "loss": 0.06938321590423584,
      "step": 970
    },
    {
      "epoch": 0.33603360336033605,
      "grad_norm": 0.09927641600370407,
      "learning_rate": 0.000199993460406294,
      "loss": 0.07581758499145508,
      "step": 980
    },
    {
      "epoch": 0.33946251768033947,
      "grad_norm": 0.1004660576581955,
      "learning_rate": 0.0001999921289577976,
      "loss": 0.07313386201858521,
      "step": 990
    },
    {
      "epoch": 0.3428914320003429,
      "grad_norm": 0.07290191948413849,
      "learning_rate": 0.00019999067423378853,
      "loss": 0.07103977799415588,
      "step": 1000
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 0.08976606279611588,
      "learning_rate": 0.00019998909623606014,
      "loss": 0.07495319843292236,
      "step": 1010
    },
    {
      "epoch": 0.3497492606403497,
      "grad_norm": 0.08071667701005936,
      "learning_rate": 0.0001999873949665579,
      "loss": 0.06945164203643799,
      "step": 1020
    },
    {
      "epoch": 0.3531781749603532,
      "grad_norm": 0.07254912704229355,
      "learning_rate": 0.0001999855704273793,
      "loss": 0.0715824842453003,
      "step": 1030
    },
    {
      "epoch": 0.3566070892803566,
      "grad_norm": 0.07526320964097977,
      "learning_rate": 0.00019998362262077364,
      "loss": 0.07164299488067627,
      "step": 1040
    },
    {
      "epoch": 0.36003600360036003,
      "grad_norm": 0.09813207387924194,
      "learning_rate": 0.0001999815515491423,
      "loss": 0.07462467551231385,
      "step": 1050
    },
    {
      "epoch": 0.36346491792036345,
      "grad_norm": 0.08068419992923737,
      "learning_rate": 0.0001999793572150386,
      "loss": 0.07437445521354676,
      "step": 1060
    },
    {
      "epoch": 0.36689383224036687,
      "grad_norm": 0.08591397106647491,
      "learning_rate": 0.0001999770396211679,
      "loss": 0.07437514662742614,
      "step": 1070
    },
    {
      "epoch": 0.37032274656037034,
      "grad_norm": 0.11709548532962799,
      "learning_rate": 0.00019997459877038734,
      "loss": 0.0700849175453186,
      "step": 1080
    },
    {
      "epoch": 0.37375166088037376,
      "grad_norm": 0.09189271181821823,
      "learning_rate": 0.00019997203466570618,
      "loss": 0.07723066210746765,
      "step": 1090
    },
    {
      "epoch": 0.3771805752003772,
      "grad_norm": 0.1487947404384613,
      "learning_rate": 0.00019996934731028558,
      "loss": 0.06955035328865052,
      "step": 1100
    },
    {
      "epoch": 0.3806094895203806,
      "grad_norm": 0.06110523268580437,
      "learning_rate": 0.00019996653670743868,
      "loss": 0.07219574451446534,
      "step": 1110
    },
    {
      "epoch": 0.384038403840384,
      "grad_norm": 0.09093336760997772,
      "learning_rate": 0.00019996360286063047,
      "loss": 0.07197158336639405,
      "step": 1120
    },
    {
      "epoch": 0.3874673181603875,
      "grad_norm": 0.07465828955173492,
      "learning_rate": 0.00019996054577347804,
      "loss": 0.06595431566238404,
      "step": 1130
    },
    {
      "epoch": 0.3908962324803909,
      "grad_norm": 0.06949753314256668,
      "learning_rate": 0.00019995736544975022,
      "loss": 0.06800097823143006,
      "step": 1140
    },
    {
      "epoch": 0.3943251468003943,
      "grad_norm": 0.06402743607759476,
      "learning_rate": 0.00019995406189336797,
      "loss": 0.06762506961822509,
      "step": 1150
    },
    {
      "epoch": 0.39775406112039774,
      "grad_norm": 0.07319864630699158,
      "learning_rate": 0.00019995063510840403,
      "loss": 0.06694105267524719,
      "step": 1160
    },
    {
      "epoch": 0.40118297544040116,
      "grad_norm": 0.07902734726667404,
      "learning_rate": 0.00019994708509908318,
      "loss": 0.07268706560134888,
      "step": 1170
    },
    {
      "epoch": 0.40461188976040463,
      "grad_norm": 0.08665812760591507,
      "learning_rate": 0.000199943411869782,
      "loss": 0.07282707095146179,
      "step": 1180
    },
    {
      "epoch": 0.40804080408040805,
      "grad_norm": 0.06259504705667496,
      "learning_rate": 0.00019993961542502902,
      "loss": 0.07454213500022888,
      "step": 1190
    },
    {
      "epoch": 0.41146971840041147,
      "grad_norm": 0.09083051979541779,
      "learning_rate": 0.0001999356957695048,
      "loss": 0.070106840133667,
      "step": 1200
    },
    {
      "epoch": 0.4148986327204149,
      "grad_norm": 0.07197695225477219,
      "learning_rate": 0.00019993165290804158,
      "loss": 0.07483985424041747,
      "step": 1210
    },
    {
      "epoch": 0.4183275470404183,
      "grad_norm": 0.0816626250743866,
      "learning_rate": 0.00019992748684562366,
      "loss": 0.07281675934791565,
      "step": 1220
    },
    {
      "epoch": 0.4217564613604218,
      "grad_norm": 0.09566456824541092,
      "learning_rate": 0.0001999231975873872,
      "loss": 0.07552507519721985,
      "step": 1230
    },
    {
      "epoch": 0.4251853756804252,
      "grad_norm": 0.07115880399942398,
      "learning_rate": 0.00019991878513862018,
      "loss": 0.0698797047138214,
      "step": 1240
    },
    {
      "epoch": 0.4286142900004286,
      "grad_norm": 0.06638191640377045,
      "learning_rate": 0.0001999142495047625,
      "loss": 0.07549352645874023,
      "step": 1250
    },
    {
      "epoch": 0.43204320432043203,
      "grad_norm": 0.08422329276800156,
      "learning_rate": 0.000199909590691406,
      "loss": 0.06987190246582031,
      "step": 1260
    },
    {
      "epoch": 0.43547211864043545,
      "grad_norm": 0.06643088161945343,
      "learning_rate": 0.0001999048087042942,
      "loss": 0.0773307740688324,
      "step": 1270
    },
    {
      "epoch": 0.4389010329604389,
      "grad_norm": 0.07236617058515549,
      "learning_rate": 0.00019989990354932265,
      "loss": 0.06638508439064025,
      "step": 1280
    },
    {
      "epoch": 0.44232994728044234,
      "grad_norm": 0.09377867728471756,
      "learning_rate": 0.00019989487523253865,
      "loss": 0.07471420168876648,
      "step": 1290
    },
    {
      "epoch": 0.44575886160044575,
      "grad_norm": 0.07945447415113449,
      "learning_rate": 0.00019988972376014142,
      "loss": 0.07506393194198609,
      "step": 1300
    },
    {
      "epoch": 0.4491877759204492,
      "grad_norm": 0.06589485704898834,
      "learning_rate": 0.00019988444913848188,
      "loss": 0.06664330363273621,
      "step": 1310
    },
    {
      "epoch": 0.4526166902404526,
      "grad_norm": 0.07233788818120956,
      "learning_rate": 0.00019987905137406294,
      "loss": 0.07118790149688721,
      "step": 1320
    },
    {
      "epoch": 0.45604560456045606,
      "grad_norm": 0.08887393772602081,
      "learning_rate": 0.00019987353047353922,
      "loss": 0.0676496684551239,
      "step": 1330
    },
    {
      "epoch": 0.4594745188804595,
      "grad_norm": 0.07033324986696243,
      "learning_rate": 0.00019986788644371715,
      "loss": 0.07179500460624695,
      "step": 1340
    },
    {
      "epoch": 0.4629034332004629,
      "grad_norm": 0.07686027884483337,
      "learning_rate": 0.000199862119291555,
      "loss": 0.07234726548194885,
      "step": 1350
    },
    {
      "epoch": 0.4663323475204663,
      "grad_norm": 0.08190786093473434,
      "learning_rate": 0.00019985622902416283,
      "loss": 0.07036671042442322,
      "step": 1360
    },
    {
      "epoch": 0.46976126184046973,
      "grad_norm": 0.07698442786931992,
      "learning_rate": 0.00019985021564880245,
      "loss": 0.06707795858383178,
      "step": 1370
    },
    {
      "epoch": 0.4731901761604732,
      "grad_norm": 0.08871393650770187,
      "learning_rate": 0.00019984407917288745,
      "loss": 0.06883646249771118,
      "step": 1380
    },
    {
      "epoch": 0.4766190904804766,
      "grad_norm": 0.08392845839262009,
      "learning_rate": 0.00019983781960398325,
      "loss": 0.07154896259307861,
      "step": 1390
    },
    {
      "epoch": 0.48004800480048004,
      "grad_norm": 0.07391165941953659,
      "learning_rate": 0.00019983143694980694,
      "loss": 0.06980017423629761,
      "step": 1400
    },
    {
      "epoch": 0.48347691912048346,
      "grad_norm": 0.0696796178817749,
      "learning_rate": 0.00019982493121822737,
      "loss": 0.07289748191833496,
      "step": 1410
    },
    {
      "epoch": 0.4869058334404869,
      "grad_norm": 0.057650376111269,
      "learning_rate": 0.00019981830241726516,
      "loss": 0.06804858446121216,
      "step": 1420
    },
    {
      "epoch": 0.49033474776049035,
      "grad_norm": 0.08872418850660324,
      "learning_rate": 0.00019981155055509266,
      "loss": 0.0683191955089569,
      "step": 1430
    },
    {
      "epoch": 0.49376366208049377,
      "grad_norm": 0.06679575145244598,
      "learning_rate": 0.0001998046756400339,
      "loss": 0.07029005289077758,
      "step": 1440
    },
    {
      "epoch": 0.4971925764004972,
      "grad_norm": 0.07526200264692307,
      "learning_rate": 0.00019979767768056464,
      "loss": 0.07121672034263611,
      "step": 1450
    },
    {
      "epoch": 0.5006214907205007,
      "grad_norm": 0.13412092626094818,
      "learning_rate": 0.00019979055668531236,
      "loss": 0.07710989117622376,
      "step": 1460
    },
    {
      "epoch": 0.504050405040504,
      "grad_norm": 0.10995283722877502,
      "learning_rate": 0.0001997833126630561,
      "loss": 0.07113178968429565,
      "step": 1470
    },
    {
      "epoch": 0.5074793193605075,
      "grad_norm": 0.07785722613334656,
      "learning_rate": 0.00019977594562272676,
      "loss": 0.07184987664222717,
      "step": 1480
    },
    {
      "epoch": 0.5109082336805109,
      "grad_norm": 0.061964794993400574,
      "learning_rate": 0.0001997684555734068,
      "loss": 0.0705429494380951,
      "step": 1490
    },
    {
      "epoch": 0.5143371480005143,
      "grad_norm": 0.0596599318087101,
      "learning_rate": 0.0001997608425243303,
      "loss": 0.06806035041809082,
      "step": 1500
    },
    {
      "epoch": 0.5177660623205178,
      "grad_norm": 0.07160928100347519,
      "learning_rate": 0.00019975310648488306,
      "loss": 0.0710654079914093,
      "step": 1510
    },
    {
      "epoch": 0.5211949766405212,
      "grad_norm": 0.06318478286266327,
      "learning_rate": 0.00019974524746460245,
      "loss": 0.06881251335144042,
      "step": 1520
    },
    {
      "epoch": 0.5246238909605246,
      "grad_norm": 0.06995552778244019,
      "learning_rate": 0.0001997372654731775,
      "loss": 0.07101587653160095,
      "step": 1530
    },
    {
      "epoch": 0.528052805280528,
      "grad_norm": 0.0636630430817604,
      "learning_rate": 0.00019972916052044882,
      "loss": 0.06702117919921875,
      "step": 1540
    },
    {
      "epoch": 0.5314817196005315,
      "grad_norm": 0.06165006011724472,
      "learning_rate": 0.00019972093261640863,
      "loss": 0.06591456532478332,
      "step": 1550
    },
    {
      "epoch": 0.534910633920535,
      "grad_norm": 0.06443383544683456,
      "learning_rate": 0.00019971258177120071,
      "loss": 0.07227083444595336,
      "step": 1560
    },
    {
      "epoch": 0.5383395482405383,
      "grad_norm": 0.07027114182710648,
      "learning_rate": 0.00019970410799512037,
      "loss": 0.062342596054077146,
      "step": 1570
    },
    {
      "epoch": 0.5417684625605418,
      "grad_norm": 0.046684492379426956,
      "learning_rate": 0.00019969551129861462,
      "loss": 0.06642588973045349,
      "step": 1580
    },
    {
      "epoch": 0.5451973768805451,
      "grad_norm": 0.06529752910137177,
      "learning_rate": 0.00019968679169228183,
      "loss": 0.06675980091094971,
      "step": 1590
    },
    {
      "epoch": 0.5486262912005486,
      "grad_norm": 0.06308460235595703,
      "learning_rate": 0.00019967794918687202,
      "loss": 0.0655122697353363,
      "step": 1600
    },
    {
      "epoch": 0.5520552055205521,
      "grad_norm": 0.060192737728357315,
      "learning_rate": 0.0001996689837932867,
      "loss": 0.06651552319526673,
      "step": 1610
    },
    {
      "epoch": 0.5554841198405555,
      "grad_norm": 0.056659456342458725,
      "learning_rate": 0.00019965989552257887,
      "loss": 0.06584551334381103,
      "step": 1620
    },
    {
      "epoch": 0.5589130341605589,
      "grad_norm": 0.054737452417612076,
      "learning_rate": 0.000199650684385953,
      "loss": 0.06906264424324035,
      "step": 1630
    },
    {
      "epoch": 0.5623419484805623,
      "grad_norm": 0.06594469398260117,
      "learning_rate": 0.0001996413503947651,
      "loss": 0.06982675790786744,
      "step": 1640
    },
    {
      "epoch": 0.5657708628005658,
      "grad_norm": 0.06081661209464073,
      "learning_rate": 0.00019963189356052259,
      "loss": 0.0662455141544342,
      "step": 1650
    },
    {
      "epoch": 0.5691997771205692,
      "grad_norm": 0.05774581804871559,
      "learning_rate": 0.0001996223138948843,
      "loss": 0.06652381420135497,
      "step": 1660
    },
    {
      "epoch": 0.5726286914405726,
      "grad_norm": 0.062362875789403915,
      "learning_rate": 0.0001996126114096606,
      "loss": 0.06487467885017395,
      "step": 1670
    },
    {
      "epoch": 0.5760576057605761,
      "grad_norm": 0.06780681014060974,
      "learning_rate": 0.00019960278611681322,
      "loss": 0.06824981570243835,
      "step": 1680
    },
    {
      "epoch": 0.5794865200805794,
      "grad_norm": 0.06902427971363068,
      "learning_rate": 0.00019959283802845526,
      "loss": 0.06992611885070801,
      "step": 1690
    },
    {
      "epoch": 0.5829154344005829,
      "grad_norm": 0.06338348239660263,
      "learning_rate": 0.00019958276715685124,
      "loss": 0.0669023871421814,
      "step": 1700
    },
    {
      "epoch": 0.5863443487205864,
      "grad_norm": 0.06664100289344788,
      "learning_rate": 0.0001995725735144171,
      "loss": 0.07338454723358154,
      "step": 1710
    },
    {
      "epoch": 0.5897732630405897,
      "grad_norm": 0.0678853988647461,
      "learning_rate": 0.00019956225711372004,
      "loss": 0.06788999438285828,
      "step": 1720
    },
    {
      "epoch": 0.5932021773605932,
      "grad_norm": 0.07547562569379807,
      "learning_rate": 0.00019955181796747868,
      "loss": 0.06702386736869811,
      "step": 1730
    },
    {
      "epoch": 0.5966310916805966,
      "grad_norm": 0.054227564483881,
      "learning_rate": 0.00019954125608856297,
      "loss": 0.06447795629501343,
      "step": 1740
    },
    {
      "epoch": 0.6000600060006,
      "grad_norm": 0.06533336639404297,
      "learning_rate": 0.00019953057148999412,
      "loss": 0.06636461615562439,
      "step": 1750
    },
    {
      "epoch": 0.6034889203206035,
      "grad_norm": 0.06058265641331673,
      "learning_rate": 0.00019951976418494468,
      "loss": 0.0677622377872467,
      "step": 1760
    },
    {
      "epoch": 0.6069178346406069,
      "grad_norm": 0.06041079759597778,
      "learning_rate": 0.0001995088341867384,
      "loss": 0.06635680794715881,
      "step": 1770
    },
    {
      "epoch": 0.6103467489606104,
      "grad_norm": 0.05961493402719498,
      "learning_rate": 0.00019949778150885042,
      "loss": 0.06692826151847839,
      "step": 1780
    },
    {
      "epoch": 0.6137756632806137,
      "grad_norm": 0.07581457495689392,
      "learning_rate": 0.00019948660616490703,
      "loss": 0.06609666347503662,
      "step": 1790
    },
    {
      "epoch": 0.6172045776006172,
      "grad_norm": 0.05494590476155281,
      "learning_rate": 0.00019947530816868576,
      "loss": 0.06787877082824707,
      "step": 1800
    },
    {
      "epoch": 0.6206334919206207,
      "grad_norm": 0.07579834014177322,
      "learning_rate": 0.0001994638875341154,
      "loss": 0.06385068893432617,
      "step": 1810
    },
    {
      "epoch": 0.624062406240624,
      "grad_norm": 0.06341655552387238,
      "learning_rate": 0.0001994523442752759,
      "loss": 0.06808843016624451,
      "step": 1820
    },
    {
      "epoch": 0.6274913205606275,
      "grad_norm": 0.05943651869893074,
      "learning_rate": 0.0001994406784063984,
      "loss": 0.06618317365646362,
      "step": 1830
    },
    {
      "epoch": 0.6309202348806309,
      "grad_norm": 0.05437728762626648,
      "learning_rate": 0.00019942888994186518,
      "loss": 0.07004727125167846,
      "step": 1840
    },
    {
      "epoch": 0.6343491492006343,
      "grad_norm": 0.0638783648610115,
      "learning_rate": 0.00019941697889620962,
      "loss": 0.0705324113368988,
      "step": 1850
    },
    {
      "epoch": 0.6377780635206378,
      "grad_norm": 0.06645606458187103,
      "learning_rate": 0.00019940494528411637,
      "loss": 0.06418377161026001,
      "step": 1860
    },
    {
      "epoch": 0.6412069778406412,
      "grad_norm": 0.06460703909397125,
      "learning_rate": 0.00019939278912042103,
      "loss": 0.06468948721885681,
      "step": 1870
    },
    {
      "epoch": 0.6446358921606447,
      "grad_norm": 0.05361228436231613,
      "learning_rate": 0.0001993805104201104,
      "loss": 0.06462889313697814,
      "step": 1880
    },
    {
      "epoch": 0.648064806480648,
      "grad_norm": 0.09618914872407913,
      "learning_rate": 0.00019936810919832224,
      "loss": 0.06841772198677062,
      "step": 1890
    },
    {
      "epoch": 0.6514937208006515,
      "grad_norm": 0.0680570900440216,
      "learning_rate": 0.0001993555854703455,
      "loss": 0.07115979194641113,
      "step": 1900
    },
    {
      "epoch": 0.654922635120655,
      "grad_norm": 0.07154513150453568,
      "learning_rate": 0.00019934293925162003,
      "loss": 0.06491658687591553,
      "step": 1910
    },
    {
      "epoch": 0.6583515494406583,
      "grad_norm": 0.05888069421052933,
      "learning_rate": 0.00019933017055773675,
      "loss": 0.06860610246658325,
      "step": 1920
    },
    {
      "epoch": 0.6617804637606618,
      "grad_norm": 0.06386138498783112,
      "learning_rate": 0.00019931727940443762,
      "loss": 0.06297200322151184,
      "step": 1930
    },
    {
      "epoch": 0.6652093780806652,
      "grad_norm": 0.0675712302327156,
      "learning_rate": 0.00019930426580761545,
      "loss": 0.0634054958820343,
      "step": 1940
    },
    {
      "epoch": 0.6686382924006686,
      "grad_norm": 0.06546768546104431,
      "learning_rate": 0.00019929112978331415,
      "loss": 0.07228370308876038,
      "step": 1950
    },
    {
      "epoch": 0.6720672067206721,
      "grad_norm": 0.0673958882689476,
      "learning_rate": 0.0001992778713477285,
      "loss": 0.0674474835395813,
      "step": 1960
    },
    {
      "epoch": 0.6754961210406755,
      "grad_norm": 0.11614768952131271,
      "learning_rate": 0.00019926449051720413,
      "loss": 0.06380310654640198,
      "step": 1970
    },
    {
      "epoch": 0.6789250353606789,
      "grad_norm": 0.07336936891078949,
      "learning_rate": 0.00019925098730823763,
      "loss": 0.06617136597633362,
      "step": 1980
    },
    {
      "epoch": 0.6823539496806823,
      "grad_norm": 0.048847053200006485,
      "learning_rate": 0.00019923736173747654,
      "loss": 0.06561228036880493,
      "step": 1990
    },
    {
      "epoch": 0.6857828640006858,
      "grad_norm": 0.07655756920576096,
      "learning_rate": 0.00019922361382171907,
      "loss": 0.06520624160766601,
      "step": 2000
    },
    {
      "epoch": 0.6892117783206893,
      "grad_norm": 0.06696760654449463,
      "learning_rate": 0.00019920974357791446,
      "loss": 0.0701349914073944,
      "step": 2010
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 0.06227932125329971,
      "learning_rate": 0.00019919575102316262,
      "loss": 0.0680422067642212,
      "step": 2020
    },
    {
      "epoch": 0.6960696069606961,
      "grad_norm": 0.061125896871089935,
      "learning_rate": 0.00019918163617471427,
      "loss": 0.06432726383209228,
      "step": 2030
    },
    {
      "epoch": 0.6994985212806994,
      "grad_norm": 0.07095475494861603,
      "learning_rate": 0.00019916739904997103,
      "loss": 0.06661240458488464,
      "step": 2040
    },
    {
      "epoch": 0.7029274356007029,
      "grad_norm": 0.0691307857632637,
      "learning_rate": 0.00019915303966648509,
      "loss": 0.05807797908782959,
      "step": 2050
    },
    {
      "epoch": 0.7063563499207064,
      "grad_norm": 0.05840357765555382,
      "learning_rate": 0.00019913855804195945,
      "loss": 0.06822753548622132,
      "step": 2060
    },
    {
      "epoch": 0.7097852642407098,
      "grad_norm": 0.07420432567596436,
      "learning_rate": 0.00019912395419424786,
      "loss": 0.06311638951301575,
      "step": 2070
    },
    {
      "epoch": 0.7132141785607132,
      "grad_norm": 0.06721077114343643,
      "learning_rate": 0.00019910922814135465,
      "loss": 0.06664948463439942,
      "step": 2080
    },
    {
      "epoch": 0.7166430928807166,
      "grad_norm": 0.05893215909600258,
      "learning_rate": 0.0001990943799014349,
      "loss": 0.06596503853797912,
      "step": 2090
    },
    {
      "epoch": 0.7200720072007201,
      "grad_norm": 0.06285710632801056,
      "learning_rate": 0.0001990794094927943,
      "loss": 0.06053690910339356,
      "step": 2100
    },
    {
      "epoch": 0.7235009215207235,
      "grad_norm": 0.06883195042610168,
      "learning_rate": 0.00019906431693388914,
      "loss": 0.06739038228988647,
      "step": 2110
    },
    {
      "epoch": 0.7269298358407269,
      "grad_norm": 0.06060967966914177,
      "learning_rate": 0.00019904910224332632,
      "loss": 0.06340742111206055,
      "step": 2120
    },
    {
      "epoch": 0.7303587501607304,
      "grad_norm": 0.06806771457195282,
      "learning_rate": 0.00019903376543986328,
      "loss": 0.06537085771560669,
      "step": 2130
    },
    {
      "epoch": 0.7337876644807337,
      "grad_norm": 0.05098235607147217,
      "learning_rate": 0.00019901830654240805,
      "loss": 0.061222386360168454,
      "step": 2140
    },
    {
      "epoch": 0.7372165788007372,
      "grad_norm": 0.05651809275150299,
      "learning_rate": 0.00019900272557001918,
      "loss": 0.06748454570770264,
      "step": 2150
    },
    {
      "epoch": 0.7406454931207407,
      "grad_norm": 0.07300875335931778,
      "learning_rate": 0.00019898702254190568,
      "loss": 0.06485098600387573,
      "step": 2160
    },
    {
      "epoch": 0.744074407440744,
      "grad_norm": 0.06163975968956947,
      "learning_rate": 0.00019897119747742706,
      "loss": 0.06237448453903198,
      "step": 2170
    },
    {
      "epoch": 0.7475033217607475,
      "grad_norm": 0.06156700477004051,
      "learning_rate": 0.00019895525039609327,
      "loss": 0.06336918473243713,
      "step": 2180
    },
    {
      "epoch": 0.7509322360807509,
      "grad_norm": 0.05241743102669716,
      "learning_rate": 0.00019893918131756478,
      "loss": 0.06216521263122558,
      "step": 2190
    },
    {
      "epoch": 0.7543611504007544,
      "grad_norm": 0.06804622709751129,
      "learning_rate": 0.00019892299026165233,
      "loss": 0.06613343954086304,
      "step": 2200
    },
    {
      "epoch": 0.7577900647207578,
      "grad_norm": 0.08165010064840317,
      "learning_rate": 0.00019890667724831707,
      "loss": 0.06366372108459473,
      "step": 2210
    },
    {
      "epoch": 0.7612189790407612,
      "grad_norm": 0.06307308375835419,
      "learning_rate": 0.0001988902422976706,
      "loss": 0.06628135442733765,
      "step": 2220
    },
    {
      "epoch": 0.7646478933607647,
      "grad_norm": 0.0657610297203064,
      "learning_rate": 0.00019887368542997476,
      "loss": 0.06268489360809326,
      "step": 2230
    },
    {
      "epoch": 0.768076807680768,
      "grad_norm": 0.0674707219004631,
      "learning_rate": 0.0001988570066656417,
      "loss": 0.06617584228515624,
      "step": 2240
    },
    {
      "epoch": 0.7715057220007715,
      "grad_norm": 0.05486510321497917,
      "learning_rate": 0.0001988402060252339,
      "loss": 0.06360874176025391,
      "step": 2250
    },
    {
      "epoch": 0.774934636320775,
      "grad_norm": 0.05392001196742058,
      "learning_rate": 0.00019882328352946403,
      "loss": 0.06193780303001404,
      "step": 2260
    },
    {
      "epoch": 0.7783635506407783,
      "grad_norm": 0.05386793240904808,
      "learning_rate": 0.00019880623919919506,
      "loss": 0.06729251742362977,
      "step": 2270
    },
    {
      "epoch": 0.7817924649607818,
      "grad_norm": 0.05438312143087387,
      "learning_rate": 0.0001987890730554401,
      "loss": 0.06320361495018005,
      "step": 2280
    },
    {
      "epoch": 0.7852213792807852,
      "grad_norm": 0.050483524799346924,
      "learning_rate": 0.0001987717851193625,
      "loss": 0.06522406339645385,
      "step": 2290
    },
    {
      "epoch": 0.7886502936007886,
      "grad_norm": 0.05501532927155495,
      "learning_rate": 0.00019875437541227572,
      "loss": 0.06552278399467468,
      "step": 2300
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.06172218918800354,
      "learning_rate": 0.00019873684395564333,
      "loss": 0.06915403008460999,
      "step": 2310
    },
    {
      "epoch": 0.7955081222407955,
      "grad_norm": 0.051952604204416275,
      "learning_rate": 0.0001987191907710791,
      "loss": 0.06277130246162414,
      "step": 2320
    },
    {
      "epoch": 0.798937036560799,
      "grad_norm": 0.05152563005685806,
      "learning_rate": 0.00019870141588034665,
      "loss": 0.06619568467140198,
      "step": 2330
    },
    {
      "epoch": 0.8023659508808023,
      "grad_norm": 0.0674680843949318,
      "learning_rate": 0.00019868351930535993,
      "loss": 0.06798242330551148,
      "step": 2340
    },
    {
      "epoch": 0.8057948652008058,
      "grad_norm": 0.06978574395179749,
      "learning_rate": 0.0001986655010681827,
      "loss": 0.06347747445106507,
      "step": 2350
    },
    {
      "epoch": 0.8092237795208093,
      "grad_norm": 0.05963709577918053,
      "learning_rate": 0.00019864736119102884,
      "loss": 0.06163069009780884,
      "step": 2360
    },
    {
      "epoch": 0.8126526938408126,
      "grad_norm": 0.04883351922035217,
      "learning_rate": 0.0001986290996962621,
      "loss": 0.05950311422348022,
      "step": 2370
    },
    {
      "epoch": 0.8160816081608161,
      "grad_norm": 0.3814024031162262,
      "learning_rate": 0.00019861071660639618,
      "loss": 0.06604605913162231,
      "step": 2380
    },
    {
      "epoch": 0.8195105224808195,
      "grad_norm": 0.1023794636130333,
      "learning_rate": 0.00019859221194409475,
      "loss": 0.064841890335083,
      "step": 2390
    },
    {
      "epoch": 0.8229394368008229,
      "grad_norm": 0.0649971291422844,
      "learning_rate": 0.00019857358573217133,
      "loss": 0.0684207558631897,
      "step": 2400
    },
    {
      "epoch": 0.8263683511208264,
      "grad_norm": 0.06579799205064774,
      "learning_rate": 0.00019855483799358922,
      "loss": 0.06325002908706664,
      "step": 2410
    },
    {
      "epoch": 0.8297972654408298,
      "grad_norm": 0.05028271675109863,
      "learning_rate": 0.0001985359687514617,
      "loss": 0.06539126038551331,
      "step": 2420
    },
    {
      "epoch": 0.8332261797608332,
      "grad_norm": 0.05256115645170212,
      "learning_rate": 0.00019851697802905172,
      "loss": 0.0646961510181427,
      "step": 2430
    },
    {
      "epoch": 0.8366550940808366,
      "grad_norm": 0.060003966093063354,
      "learning_rate": 0.000198497865849772,
      "loss": 0.06308870911598205,
      "step": 2440
    },
    {
      "epoch": 0.8400840084008401,
      "grad_norm": 0.06799912452697754,
      "learning_rate": 0.00019847863223718506,
      "loss": 0.0649224042892456,
      "step": 2450
    },
    {
      "epoch": 0.8435129227208435,
      "grad_norm": 0.07937843352556229,
      "learning_rate": 0.0001984592772150031,
      "loss": 0.0636534869670868,
      "step": 2460
    },
    {
      "epoch": 0.8469418370408469,
      "grad_norm": 0.05219930782914162,
      "learning_rate": 0.00019843980080708803,
      "loss": 0.06010836958885193,
      "step": 2470
    },
    {
      "epoch": 0.8503707513608504,
      "grad_norm": 0.0586070753633976,
      "learning_rate": 0.00019842020303745131,
      "loss": 0.06380678415298462,
      "step": 2480
    },
    {
      "epoch": 0.8537996656808537,
      "grad_norm": 0.058439116925001144,
      "learning_rate": 0.00019840048393025416,
      "loss": 0.06640804409980774,
      "step": 2490
    },
    {
      "epoch": 0.8572285800008572,
      "grad_norm": 0.06139601767063141,
      "learning_rate": 0.00019838064350980727,
      "loss": 0.05971125960350036,
      "step": 2500
    },
    {
      "epoch": 0.8606574943208607,
      "grad_norm": 0.06821685284376144,
      "learning_rate": 0.000198360681800571,
      "loss": 0.06303138732910156,
      "step": 2510
    },
    {
      "epoch": 0.8640864086408641,
      "grad_norm": 0.06389456242322922,
      "learning_rate": 0.00019834059882715516,
      "loss": 0.06540479063987732,
      "step": 2520
    },
    {
      "epoch": 0.8675153229608675,
      "grad_norm": 0.04554591700434685,
      "learning_rate": 0.00019832039461431907,
      "loss": 0.058097350597381595,
      "step": 2530
    },
    {
      "epoch": 0.8709442372808709,
      "grad_norm": 0.06274914741516113,
      "learning_rate": 0.00019830006918697155,
      "loss": 0.06443666219711304,
      "step": 2540
    },
    {
      "epoch": 0.8743731516008744,
      "grad_norm": 0.058880288153886795,
      "learning_rate": 0.0001982796225701709,
      "loss": 0.06162167191505432,
      "step": 2550
    },
    {
      "epoch": 0.8778020659208778,
      "grad_norm": 0.05205392837524414,
      "learning_rate": 0.00019825905478912468,
      "loss": 0.055066394805908206,
      "step": 2560
    },
    {
      "epoch": 0.8812309802408812,
      "grad_norm": 0.0545465461909771,
      "learning_rate": 0.00019823836586918997,
      "loss": 0.06011802554130554,
      "step": 2570
    },
    {
      "epoch": 0.8846598945608847,
      "grad_norm": 0.05792587995529175,
      "learning_rate": 0.00019821755583587317,
      "loss": 0.058178257942199704,
      "step": 2580
    },
    {
      "epoch": 0.888088808880888,
      "grad_norm": 0.06038236618041992,
      "learning_rate": 0.00019819662471482995,
      "loss": 0.061930137872695926,
      "step": 2590
    },
    {
      "epoch": 0.8915177232008915,
      "grad_norm": 0.06363194435834885,
      "learning_rate": 0.00019817557253186532,
      "loss": 0.06379579305648804,
      "step": 2600
    },
    {
      "epoch": 0.894946637520895,
      "grad_norm": 0.07369779050350189,
      "learning_rate": 0.00019815439931293347,
      "loss": 0.060153383016586306,
      "step": 2610
    },
    {
      "epoch": 0.8983755518408983,
      "grad_norm": 0.062007270753383636,
      "learning_rate": 0.00019813310508413784,
      "loss": 0.0662104070186615,
      "step": 2620
    },
    {
      "epoch": 0.9018044661609018,
      "grad_norm": 0.06512269377708435,
      "learning_rate": 0.00019811168987173109,
      "loss": 0.06587219834327698,
      "step": 2630
    },
    {
      "epoch": 0.9052333804809052,
      "grad_norm": 0.05178048089146614,
      "learning_rate": 0.00019809015370211502,
      "loss": 0.06476051211357117,
      "step": 2640
    },
    {
      "epoch": 0.9086622948009087,
      "grad_norm": 0.05599229782819748,
      "learning_rate": 0.00019806849660184054,
      "loss": 0.06642783880233764,
      "step": 2650
    },
    {
      "epoch": 0.9120912091209121,
      "grad_norm": 0.06416797637939453,
      "learning_rate": 0.00019804671859760764,
      "loss": 0.06604329347610474,
      "step": 2660
    },
    {
      "epoch": 0.9155201234409155,
      "grad_norm": 0.05304501950740814,
      "learning_rate": 0.0001980248197162654,
      "loss": 0.0627303421497345,
      "step": 2670
    },
    {
      "epoch": 0.918949037760919,
      "grad_norm": 0.05713188648223877,
      "learning_rate": 0.00019800279998481187,
      "loss": 0.06577149033546448,
      "step": 2680
    },
    {
      "epoch": 0.9223779520809223,
      "grad_norm": 0.06850962340831757,
      "learning_rate": 0.00019798065943039413,
      "loss": 0.061149966716766355,
      "step": 2690
    },
    {
      "epoch": 0.9258068664009258,
      "grad_norm": 0.06360381096601486,
      "learning_rate": 0.00019795839808030822,
      "loss": 0.0627046525478363,
      "step": 2700
    },
    {
      "epoch": 0.9292357807209293,
      "grad_norm": 0.046474043279886246,
      "learning_rate": 0.00019793601596199912,
      "loss": 0.06419117450714111,
      "step": 2710
    },
    {
      "epoch": 0.9326646950409326,
      "grad_norm": 0.0652134045958519,
      "learning_rate": 0.00019791351310306064,
      "loss": 0.06440665125846863,
      "step": 2720
    },
    {
      "epoch": 0.9360936093609361,
      "grad_norm": 0.05071209743618965,
      "learning_rate": 0.0001978908895312355,
      "loss": 0.06100277304649353,
      "step": 2730
    },
    {
      "epoch": 0.9395225236809395,
      "grad_norm": 0.08431413769721985,
      "learning_rate": 0.0001978681452744152,
      "loss": 0.06571382284164429,
      "step": 2740
    },
    {
      "epoch": 0.9429514380009429,
      "grad_norm": 0.06639470160007477,
      "learning_rate": 0.00019784528036064005,
      "loss": 0.06303996443748475,
      "step": 2750
    },
    {
      "epoch": 0.9463803523209464,
      "grad_norm": 0.06278301030397415,
      "learning_rate": 0.00019782229481809908,
      "loss": 0.060810595750808716,
      "step": 2760
    },
    {
      "epoch": 0.9498092666409498,
      "grad_norm": 0.05751429498195648,
      "learning_rate": 0.00019779918867513015,
      "loss": 0.06521624922752381,
      "step": 2770
    },
    {
      "epoch": 0.9532381809609533,
      "grad_norm": 0.05640877038240433,
      "learning_rate": 0.00019777596196021965,
      "loss": 0.06350036263465882,
      "step": 2780
    },
    {
      "epoch": 0.9566670952809566,
      "grad_norm": 0.0672905445098877,
      "learning_rate": 0.0001977526147020027,
      "loss": 0.06559882164001465,
      "step": 2790
    },
    {
      "epoch": 0.9600960096009601,
      "grad_norm": 0.061227139085531235,
      "learning_rate": 0.00019772914692926298,
      "loss": 0.0647310495376587,
      "step": 2800
    },
    {
      "epoch": 0.9635249239209636,
      "grad_norm": 0.04840533435344696,
      "learning_rate": 0.00019770555867093287,
      "loss": 0.06300787925720215,
      "step": 2810
    },
    {
      "epoch": 0.9669538382409669,
      "grad_norm": 0.04809625446796417,
      "learning_rate": 0.00019768184995609314,
      "loss": 0.060482186079025266,
      "step": 2820
    },
    {
      "epoch": 0.9703827525609704,
      "grad_norm": 0.0634710043668747,
      "learning_rate": 0.00019765802081397315,
      "loss": 0.06123342514038086,
      "step": 2830
    },
    {
      "epoch": 0.9738116668809738,
      "grad_norm": 0.06208731234073639,
      "learning_rate": 0.00019763407127395074,
      "loss": 0.06303659081459045,
      "step": 2840
    },
    {
      "epoch": 0.9772405812009772,
      "grad_norm": 0.05797295272350311,
      "learning_rate": 0.0001976100013655521,
      "loss": 0.06181204319000244,
      "step": 2850
    },
    {
      "epoch": 0.9806694955209807,
      "grad_norm": 0.047497738152742386,
      "learning_rate": 0.00019758581111845188,
      "loss": 0.06843062043190003,
      "step": 2860
    },
    {
      "epoch": 0.9840984098409841,
      "grad_norm": 0.07195553183555603,
      "learning_rate": 0.00019756150056247308,
      "loss": 0.057436692714691165,
      "step": 2870
    },
    {
      "epoch": 0.9875273241609875,
      "grad_norm": 0.05397411808371544,
      "learning_rate": 0.00019753706972758708,
      "loss": 0.06481915712356567,
      "step": 2880
    },
    {
      "epoch": 0.9909562384809909,
      "grad_norm": 0.07122443616390228,
      "learning_rate": 0.00019751251864391338,
      "loss": 0.06128339171409607,
      "step": 2890
    },
    {
      "epoch": 0.9943851528009944,
      "grad_norm": 0.05404914170503616,
      "learning_rate": 0.00019748784734171992,
      "loss": 0.06380388736724854,
      "step": 2900
    },
    {
      "epoch": 0.9978140671209978,
      "grad_norm": 0.05884242057800293,
      "learning_rate": 0.00019746305585142276,
      "loss": 0.062488919496536253,
      "step": 2910
    }
  ],
  "logging_steps": 10,
  "max_steps": 29170,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 2.6570827015387837e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}