{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 945,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.2536803647875785,
      "epoch": 0.05291005291005291,
      "grad_norm": 8.8125,
      "learning_rate": 3.2142857142857147e-06,
      "loss": 1.1722795486450195,
      "mean_token_accuracy": 0.7258133076131343,
      "num_tokens": 710093.0,
      "step": 10
    },
    {
      "entropy": 0.9760579235851765,
      "epoch": 0.10582010582010581,
      "grad_norm": 2.65625,
      "learning_rate": 6.785714285714287e-06,
      "loss": 0.9763177871704102,
      "mean_token_accuracy": 0.7567757397890091,
      "num_tokens": 1429271.0,
      "step": 20
    },
    {
      "entropy": 0.794147289544344,
      "epoch": 0.15873015873015872,
      "grad_norm": 2.46875,
      "learning_rate": 1.0357142857142859e-05,
      "loss": 0.8046525001525879,
      "mean_token_accuracy": 0.7873034350574016,
      "num_tokens": 2149735.0,
      "step": 30
    },
    {
      "entropy": 0.7088500954210758,
      "epoch": 0.21164021164021163,
      "grad_norm": 1.4609375,
      "learning_rate": 1.3928571428571429e-05,
      "loss": 0.7121071815490723,
      "mean_token_accuracy": 0.8070594437420369,
      "num_tokens": 2868867.0,
      "step": 40
    },
    {
      "entropy": 0.683020292967558,
      "epoch": 0.26455026455026454,
      "grad_norm": 1.46875,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 0.68443603515625,
      "mean_token_accuracy": 0.8138657048344612,
      "num_tokens": 3582476.0,
      "step": 50
    },
    {
      "entropy": 0.6564815938472748,
      "epoch": 0.31746031746031744,
      "grad_norm": 1.4296875,
      "learning_rate": 1.999986795783372e-05,
      "loss": 0.6578450202941895,
      "mean_token_accuracy": 0.8192978233098984,
      "num_tokens": 4287689.0,
      "step": 60
    },
    {
      "entropy": 0.6446133196353913,
      "epoch": 0.37037037037037035,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9997520638548385e-05,
      "loss": 0.651158332824707,
      "mean_token_accuracy": 0.8207244381308556,
      "num_tokens": 5011191.0,
      "step": 70
    },
    {
      "entropy": 0.6360202118754387,
      "epoch": 0.42328042328042326,
      "grad_norm": 1.3984375,
      "learning_rate": 1.9992239841688418e-05,
      "loss": 0.6350794792175293,
      "mean_token_accuracy": 0.8251068785786628,
      "num_tokens": 5714842.0,
      "step": 80
    },
    {
      "entropy": 0.6189912840723991,
      "epoch": 0.47619047619047616,
      "grad_norm": 1.328125,
      "learning_rate": 1.9984027116747914e-05,
      "loss": 0.622182559967041,
      "mean_token_accuracy": 0.8279523886740208,
      "num_tokens": 6424614.0,
      "step": 90
    },
    {
      "entropy": 0.6159785229712724,
      "epoch": 0.5291005291005291,
      "grad_norm": 1.3671875,
      "learning_rate": 1.997288487350878e-05,
      "loss": 0.617555046081543,
      "mean_token_accuracy": 0.8284852005541324,
      "num_tokens": 7139778.0,
      "step": 100
    },
    {
      "entropy": 0.6129939660429955,
      "epoch": 0.582010582010582,
      "grad_norm": 1.328125,
      "learning_rate": 1.9958816381333684e-05,
      "loss": 0.6128347873687744,
      "mean_token_accuracy": 0.8294584318995476,
      "num_tokens": 7852540.0,
      "step": 110
    },
    {
      "entropy": 0.6052542962133884,
      "epoch": 0.6349206349206349,
      "grad_norm": 1.3359375,
      "learning_rate": 1.994182576820673e-05,
      "loss": 0.6046356201171875,
      "mean_token_accuracy": 0.831394524872303,
      "num_tokens": 8568056.0,
      "step": 120
    },
    {
      "entropy": 0.6013224326074124,
      "epoch": 0.6878306878306878,
      "grad_norm": 1.3203125,
      "learning_rate": 1.9921918019522238e-05,
      "loss": 0.6063410758972168,
      "mean_token_accuracy": 0.8313738636672496,
      "num_tokens": 9276742.0,
      "step": 130
    },
    {
      "entropy": 0.5983927462249994,
      "epoch": 0.7407407407407407,
      "grad_norm": 1.3125,
      "learning_rate": 1.9899098976621922e-05,
      "loss": 0.5977112770080566,
      "mean_token_accuracy": 0.8335464030504227,
      "num_tokens": 9990163.0,
      "step": 140
    },
    {
      "entropy": 0.5922725383192301,
      "epoch": 0.7936507936507936,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9873375335080915e-05,
      "loss": 0.5917873382568359,
      "mean_token_accuracy": 0.8347524181008339,
      "num_tokens": 10710006.0,
      "step": 150
    },
    {
      "entropy": 0.5920293003320694,
      "epoch": 0.8465608465608465,
      "grad_norm": 1.3046875,
      "learning_rate": 1.9844754642743164e-05,
      "loss": 0.5962053298950195,
      "mean_token_accuracy": 0.8335559628903866,
      "num_tokens": 11416822.0,
      "step": 160
    },
    {
      "entropy": 0.5966673269867897,
      "epoch": 0.8994708994708994,
      "grad_norm": 1.3828125,
      "learning_rate": 1.981324529750672e-05,
      "loss": 0.6019061088562012,
      "mean_token_accuracy": 0.83258865326643,
      "num_tokens": 12123118.0,
      "step": 170
    },
    {
      "entropy": 0.5854565776884556,
      "epoch": 0.9523809523809523,
      "grad_norm": 1.359375,
      "learning_rate": 1.9778856544859647e-05,
      "loss": 0.5845203399658203,
      "mean_token_accuracy": 0.8360438510775566,
      "num_tokens": 12831058.0,
      "step": 180
    },
    {
      "entropy": 0.5759805988520383,
      "epoch": 1.0052910052910053,
      "grad_norm": 1.3046875,
      "learning_rate": 1.9741598475167173e-05,
      "loss": 0.5696067810058594,
      "mean_token_accuracy": 0.839682175219059,
      "num_tokens": 13547943.0,
      "step": 190
    },
    {
      "entropy": 0.5275494448840619,
      "epoch": 1.0582010582010581,
      "grad_norm": 1.3984375,
      "learning_rate": 1.9701482020711004e-05,
      "loss": 0.5299928665161133,
      "mean_token_accuracy": 0.8484233327209949,
      "num_tokens": 14264772.0,
      "step": 200
    },
    {
      "entropy": 0.5196751751005649,
      "epoch": 1.1111111111111112,
      "grad_norm": 1.2109375,
      "learning_rate": 1.9658518952481543e-05,
      "loss": 0.5208037853240967,
      "mean_token_accuracy": 0.8509362854063511,
      "num_tokens": 14985565.0,
      "step": 210
    },
    {
      "entropy": 0.5303940393030644,
      "epoch": 1.164021164021164,
      "grad_norm": 1.3359375,
      "learning_rate": 1.9612721876724054e-05,
      "loss": 0.5318955421447754,
      "mean_token_accuracy": 0.8480072498321534,
      "num_tokens": 15701796.0,
      "step": 220
    },
    {
      "entropy": 0.5232694145292044,
      "epoch": 1.216931216931217,
      "grad_norm": 1.359375,
      "learning_rate": 1.9564104231239726e-05,
      "loss": 0.5231654167175293,
      "mean_token_accuracy": 0.8490844376385212,
      "num_tokens": 16412522.0,
      "step": 230
    },
    {
      "entropy": 0.529466836899519,
      "epoch": 1.2698412698412698,
      "grad_norm": 1.3046875,
      "learning_rate": 1.9512680281442745e-05,
      "loss": 0.5309067726135254,
      "mean_token_accuracy": 0.8485323786735535,
      "num_tokens": 17126523.0,
      "step": 240
    },
    {
      "entropy": 0.527790617197752,
      "epoch": 1.3227513227513228,
      "grad_norm": 1.3125,
      "learning_rate": 1.9458465116174534e-05,
      "loss": 0.5262090682983398,
      "mean_token_accuracy": 0.8493455089628696,
      "num_tokens": 17834934.0,
      "step": 250
    },
    {
      "entropy": 0.528411227837205,
      "epoch": 1.3756613756613756,
      "grad_norm": 1.265625,
      "learning_rate": 1.940147464327637e-05,
      "loss": 0.529714298248291,
      "mean_token_accuracy": 0.8480914957821369,
      "num_tokens": 18553413.0,
      "step": 260
    },
    {
      "entropy": 0.516933124884963,
      "epoch": 1.4285714285714286,
      "grad_norm": 1.296875,
      "learning_rate": 1.9341725584921712e-05,
      "loss": 0.5172879219055175,
      "mean_token_accuracy": 0.8517736725509166,
      "num_tokens": 19270191.0,
      "step": 270
    },
    {
      "entropy": 0.5223661050200462,
      "epoch": 1.4814814814814814,
      "grad_norm": 1.2421875,
      "learning_rate": 1.9279235472709554e-05,
      "loss": 0.5231949329376221,
      "mean_token_accuracy": 0.8496842503547668,
      "num_tokens": 19976552.0,
      "step": 280
    },
    {
      "entropy": 0.5293067336082459,
      "epoch": 1.5343915343915344,
      "grad_norm": 1.2421875,
      "learning_rate": 1.92140226425203e-05,
      "loss": 0.5295753479003906,
      "mean_token_accuracy": 0.8479710258543491,
      "num_tokens": 20676613.0,
      "step": 290
    },
    {
      "entropy": 0.5302139949053526,
      "epoch": 1.5873015873015874,
      "grad_norm": 1.28125,
      "learning_rate": 1.914610622913566e-05,
      "loss": 0.530374813079834,
      "mean_token_accuracy": 0.8484688423573971,
      "num_tokens": 21385978.0,
      "step": 300
    },
    {
      "entropy": 0.5183596257120371,
      "epoch": 1.6402116402116402,
      "grad_norm": 1.1953125,
      "learning_rate": 1.9075506160624068e-05,
      "loss": 0.519154167175293,
      "mean_token_accuracy": 0.8509341597557067,
      "num_tokens": 22094336.0,
      "step": 310
    },
    {
      "entropy": 0.5201449614018202,
      "epoch": 1.693121693121693,
      "grad_norm": 1.328125,
      "learning_rate": 1.900224315249343e-05,
      "loss": 0.5171724796295166,
      "mean_token_accuracy": 0.8508495308458806,
      "num_tokens": 22798906.0,
      "step": 320
    },
    {
      "entropy": 0.5111908499151468,
      "epoch": 1.746031746031746,
      "grad_norm": 1.2265625,
      "learning_rate": 1.8926338701612738e-05,
      "loss": 0.511273717880249,
      "mean_token_accuracy": 0.8524932019412518,
      "num_tokens": 23511239.0,
      "step": 330
    },
    {
      "entropy": 0.5265866108238697,
      "epoch": 1.798941798941799,
      "grad_norm": 1.265625,
      "learning_rate": 1.884781507990445e-05,
      "loss": 0.5289421558380127,
      "mean_token_accuracy": 0.8486531592905522,
      "num_tokens": 24231185.0,
      "step": 340
    },
    {
      "entropy": 0.5189403794705868,
      "epoch": 1.8518518518518519,
      "grad_norm": 1.2578125,
      "learning_rate": 1.8766695327809463e-05,
      "loss": 0.5158460140228271,
      "mean_token_accuracy": 0.8517816573381424,
      "num_tokens": 24944285.0,
      "step": 350
    },
    {
      "entropy": 0.5055529039353133,
      "epoch": 1.9047619047619047,
      "grad_norm": 1.1953125,
      "learning_rate": 1.8683003247526567e-05,
      "loss": 0.5064782619476318,
      "mean_token_accuracy": 0.8533773042261601,
      "num_tokens": 25670441.0,
      "step": 360
    },
    {
      "entropy": 0.5245815236121416,
      "epoch": 1.9576719576719577,
      "grad_norm": 1.2421875,
      "learning_rate": 1.8596763396028384e-05,
      "loss": 0.5262872219085694,
      "mean_token_accuracy": 0.8492341041564941,
      "num_tokens": 26379786.0,
      "step": 370
    },
    {
      "entropy": 0.5117530789226293,
      "epoch": 2.0105820105820107,
      "grad_norm": 1.390625,
      "learning_rate": 1.8508001077855876e-05,
      "loss": 0.5020773887634278,
      "mean_token_accuracy": 0.854968623816967,
      "num_tokens": 27097166.0,
      "step": 380
    },
    {
      "entropy": 0.44686204604804514,
      "epoch": 2.0634920634920633,
      "grad_norm": 1.3046875,
      "learning_rate": 1.8416742337693436e-05,
      "loss": 0.4472813606262207,
      "mean_token_accuracy": 0.8682501375675201,
      "num_tokens": 27818991.0,
      "step": 390
    },
    {
      "entropy": 0.4516366470605135,
      "epoch": 2.1164021164021163,
      "grad_norm": 1.484375,
      "learning_rate": 1.8323013952726877e-05,
      "loss": 0.45279760360717775,
      "mean_token_accuracy": 0.8667486943304539,
      "num_tokens": 28524822.0,
      "step": 400
    },
    {
      "entropy": 0.44368173032999036,
      "epoch": 2.1693121693121693,
      "grad_norm": 1.328125,
      "learning_rate": 1.8226843424786434e-05,
      "loss": 0.4443831443786621,
      "mean_token_accuracy": 0.8681288480758667,
      "num_tokens": 29245634.0,
      "step": 410
    },
    {
      "entropy": 0.44680118896067145,
      "epoch": 2.2222222222222223,
      "grad_norm": 1.3046875,
      "learning_rate": 1.8128258972277176e-05,
      "loss": 0.4440959930419922,
      "mean_token_accuracy": 0.8689466655254364,
      "num_tokens": 29967135.0,
      "step": 420
    },
    {
      "entropy": 0.4494645904749632,
      "epoch": 2.2751322751322753,
      "grad_norm": 1.328125,
      "learning_rate": 1.8027289521899143e-05,
      "loss": 0.45146980285644533,
      "mean_token_accuracy": 0.8666525632143021,
      "num_tokens": 30680274.0,
      "step": 430
    },
    {
      "entropy": 0.4557589769363403,
      "epoch": 2.328042328042328,
      "grad_norm": 1.2734375,
      "learning_rate": 1.7923964700159658e-05,
      "loss": 0.45585927963256834,
      "mean_token_accuracy": 0.8663338787853718,
      "num_tokens": 31386859.0,
      "step": 440
    },
    {
      "entropy": 0.46223078556358815,
      "epoch": 2.380952380952381,
      "grad_norm": 1.390625,
      "learning_rate": 1.78183148246803e-05,
      "loss": 0.4587599754333496,
      "mean_token_accuracy": 0.86525354757905,
      "num_tokens": 32111007.0,
      "step": 450
    },
    {
      "entropy": 0.4548660650849342,
      "epoch": 2.433862433862434,
      "grad_norm": 1.265625,
      "learning_rate": 1.77103708953011e-05,
      "loss": 0.4531528949737549,
      "mean_token_accuracy": 0.8663033962249755,
      "num_tokens": 32819180.0,
      "step": 460
    },
    {
      "entropy": 0.4630272053182125,
      "epoch": 2.4867724867724865,
      "grad_norm": 1.28125,
      "learning_rate": 1.7600164584984548e-05,
      "loss": 0.4610149383544922,
      "mean_token_accuracy": 0.8639790855348111,
      "num_tokens": 33523113.0,
      "step": 470
    },
    {
      "entropy": 0.4509055320173502,
      "epoch": 2.5396825396825395,
      "grad_norm": 1.34375,
      "learning_rate": 1.7487728230522085e-05,
      "loss": 0.44989833831787107,
      "mean_token_accuracy": 0.8673267938196659,
      "num_tokens": 34240357.0,
      "step": 480
    },
    {
      "entropy": 0.455976203456521,
      "epoch": 2.5925925925925926,
      "grad_norm": 1.2265625,
      "learning_rate": 1.737309482304585e-05,
      "loss": 0.4550386905670166,
      "mean_token_accuracy": 0.8660441562533379,
      "num_tokens": 34958032.0,
      "step": 490
    },
    {
      "entropy": 0.4540476597845554,
      "epoch": 2.6455026455026456,
      "grad_norm": 1.328125,
      "learning_rate": 1.7256297998348388e-05,
      "loss": 0.45427827835083007,
      "mean_token_accuracy": 0.866205920279026,
      "num_tokens": 35658658.0,
      "step": 500
    },
    {
      "entropy": 0.45439887307584287,
      "epoch": 2.6984126984126986,
      "grad_norm": 1.3203125,
      "learning_rate": 1.7137372027013212e-05,
      "loss": 0.45563058853149413,
      "mean_token_accuracy": 0.865429712831974,
      "num_tokens": 36364754.0,
      "step": 510
    },
    {
      "entropy": 0.46197318099439144,
      "epoch": 2.751322751322751,
      "grad_norm": 1.296875,
      "learning_rate": 1.7016351804359134e-05,
      "loss": 0.46036925315856936,
      "mean_token_accuracy": 0.8651507623493672,
      "num_tokens": 37074678.0,
      "step": 520
    },
    {
      "entropy": 0.47125925347208975,
      "epoch": 2.804232804232804,
      "grad_norm": 1.296875,
      "learning_rate": 1.6893272840201243e-05,
      "loss": 0.4696796417236328,
      "mean_token_accuracy": 0.862788101285696,
      "num_tokens": 37787128.0,
      "step": 530
    },
    {
      "entropy": 0.4597961250692606,
      "epoch": 2.857142857142857,
      "grad_norm": 1.3203125,
      "learning_rate": 1.6768171248431603e-05,
      "loss": 0.45906572341918944,
      "mean_token_accuracy": 0.8650128476321697,
      "num_tokens": 38504013.0,
      "step": 540
    },
    {
      "entropy": 0.4489801775664091,
      "epoch": 2.91005291005291,
      "grad_norm": 1.3046875,
      "learning_rate": 1.66410837364227e-05,
      "loss": 0.4477699279785156,
      "mean_token_accuracy": 0.8676867328584195,
      "num_tokens": 39212782.0,
      "step": 550
    },
    {
      "entropy": 0.4513770941644907,
      "epoch": 2.962962962962963,
      "grad_norm": 1.2734375,
      "learning_rate": 1.651204759425674e-05,
      "loss": 0.4503082275390625,
      "mean_token_accuracy": 0.8672237955033779,
      "num_tokens": 39931947.0,
      "step": 560
    },
    {
      "entropy": 0.4483271919190884,
      "epoch": 3.015873015873016,
      "grad_norm": 1.34375,
      "learning_rate": 1.6381100683783984e-05,
      "loss": 0.4379873275756836,
      "mean_token_accuracy": 0.8702801637351513,
      "num_tokens": 40643225.0,
      "step": 570
    },
    {
      "entropy": 0.3994087837636471,
      "epoch": 3.068783068783069,
      "grad_norm": 1.375,
      "learning_rate": 1.6248281427513293e-05,
      "loss": 0.40430545806884766,
      "mean_token_accuracy": 0.8792076490819454,
      "num_tokens": 41359577.0,
      "step": 580
    },
    {
      "entropy": 0.40569392777979374,
      "epoch": 3.121693121693122,
      "grad_norm": 1.46875,
      "learning_rate": 1.6113628797338182e-05,
      "loss": 0.40410671234130857,
      "mean_token_accuracy": 0.8795830741524696,
      "num_tokens": 42068599.0,
      "step": 590
    },
    {
      "entropy": 0.39706668704748155,
      "epoch": 3.1746031746031744,
      "grad_norm": 1.453125,
      "learning_rate": 1.597718230310167e-05,
      "loss": 0.39309277534484866,
      "mean_token_accuracy": 0.8820179499685764,
      "num_tokens": 42785175.0,
      "step": 600
    },
    {
      "entropy": 0.3929748997092247,
      "epoch": 3.2275132275132274,
      "grad_norm": 1.3515625,
      "learning_rate": 1.5838981981003273e-05,
      "loss": 0.391530179977417,
      "mean_token_accuracy": 0.8828775212168694,
      "num_tokens": 43504295.0,
      "step": 610
    },
    {
      "entropy": 0.4006485942751169,
      "epoch": 3.2804232804232805,
      "grad_norm": 1.3359375,
      "learning_rate": 1.5699068381851576e-05,
      "loss": 0.39961411952972414,
      "mean_token_accuracy": 0.8799484111368656,
      "num_tokens": 44210262.0,
      "step": 620
    },
    {
      "entropy": 0.40273183323442935,
      "epoch": 3.3333333333333335,
      "grad_norm": 1.296875,
      "learning_rate": 1.5557482559165777e-05,
      "loss": 0.3995194435119629,
      "mean_token_accuracy": 0.8803919807076455,
      "num_tokens": 44921899.0,
      "step": 630
    },
    {
      "entropy": 0.39858098365366457,
      "epoch": 3.386243386243386,
      "grad_norm": 1.359375,
      "learning_rate": 1.541426605712975e-05,
      "loss": 0.39831721782684326,
      "mean_token_accuracy": 0.8801213204860687,
      "num_tokens": 45631735.0,
      "step": 640
    },
    {
      "entropy": 0.40417286232113836,
      "epoch": 3.439153439153439,
      "grad_norm": 1.390625,
      "learning_rate": 1.526946089840214e-05,
      "loss": 0.4012503147125244,
      "mean_token_accuracy": 0.8794990263879299,
      "num_tokens": 46339604.0,
      "step": 650
    },
    {
      "entropy": 0.4001857254654169,
      "epoch": 3.492063492063492,
      "grad_norm": 1.359375,
      "learning_rate": 1.5123109571786034e-05,
      "loss": 0.3985880374908447,
      "mean_token_accuracy": 0.8811507351696491,
      "num_tokens": 47060193.0,
      "step": 660
    },
    {
      "entropy": 0.40479574501514437,
      "epoch": 3.544973544973545,
      "grad_norm": 1.3515625,
      "learning_rate": 1.4975255019761896e-05,
      "loss": 0.40291218757629393,
      "mean_token_accuracy": 0.8791408479213715,
      "num_tokens": 47768090.0,
      "step": 670
    },
    {
      "entropy": 0.4033591251820326,
      "epoch": 3.597883597883598,
      "grad_norm": 1.3828125,
      "learning_rate": 1.4825940625887343e-05,
      "loss": 0.4013660430908203,
      "mean_token_accuracy": 0.8803223237395287,
      "num_tokens": 48486016.0,
      "step": 680
    },
    {
      "entropy": 0.40111338496208193,
      "epoch": 3.6507936507936507,
      "grad_norm": 1.3203125,
      "learning_rate": 1.467521020206753e-05,
      "loss": 0.4004556655883789,
      "mean_token_accuracy": 0.8803155072033405,
      "num_tokens": 49196144.0,
      "step": 690
    },
    {
      "entropy": 0.4051408216357231,
      "epoch": 3.7037037037037037,
      "grad_norm": 1.4453125,
      "learning_rate": 1.4523107975699833e-05,
      "loss": 0.40234980583190916,
      "mean_token_accuracy": 0.8797906585037708,
      "num_tokens": 49912021.0,
      "step": 700
    },
    {
      "entropy": 0.40589384697377684,
      "epoch": 3.7566137566137567,
      "grad_norm": 1.3828125,
      "learning_rate": 1.4369678576696633e-05,
      "loss": 0.40387759208679197,
      "mean_token_accuracy": 0.8787553466856479,
      "num_tokens": 50634262.0,
      "step": 710
    },
    {
      "entropy": 0.40110721029341223,
      "epoch": 3.8095238095238093,
      "grad_norm": 1.375,
      "learning_rate": 1.4214967024389978e-05,
      "loss": 0.3980360269546509,
      "mean_token_accuracy": 0.8805328562855721,
      "num_tokens": 51343452.0,
      "step": 720
    },
    {
      "entropy": 0.40014385208487513,
      "epoch": 3.8624338624338623,
      "grad_norm": 1.3671875,
      "learning_rate": 1.4059018714321986e-05,
      "loss": 0.39777488708496095,
      "mean_token_accuracy": 0.8803488783538341,
      "num_tokens": 52046363.0,
      "step": 730
    },
    {
      "entropy": 0.39626855254173277,
      "epoch": 3.9153439153439153,
      "grad_norm": 1.3671875,
      "learning_rate": 1.390187940492486e-05,
      "loss": 0.39633784294128416,
      "mean_token_accuracy": 0.8808404296636582,
      "num_tokens": 52755135.0,
      "step": 740
    },
    {
      "entropy": 0.39399982392787936,
      "epoch": 3.9682539682539684,
      "grad_norm": 1.3125,
      "learning_rate": 1.3743595204094442e-05,
      "loss": 0.3921464443206787,
      "mean_token_accuracy": 0.8814935088157654,
      "num_tokens": 53473566.0,
      "step": 750
    },
    {
      "entropy": 0.38536344952881335,
      "epoch": 4.021164021164021,
      "grad_norm": 1.3515625,
      "learning_rate": 1.3584212555661187e-05,
      "loss": 0.37671327590942383,
      "mean_token_accuracy": 0.8863395161926746,
      "num_tokens": 54190492.0,
      "step": 760
    },
    {
      "entropy": 0.353043582290411,
      "epoch": 4.074074074074074,
      "grad_norm": 1.375,
      "learning_rate": 1.3423778225762609e-05,
      "loss": 0.35420970916748046,
      "mean_token_accuracy": 0.8928504519164562,
      "num_tokens": 54897936.0,
      "step": 770
    },
    {
      "entropy": 0.36162243895232676,
      "epoch": 4.1269841269841265,
      "grad_norm": 1.5234375,
      "learning_rate": 1.3262339289121129e-05,
      "loss": 0.3595908164978027,
      "mean_token_accuracy": 0.8911875270307064,
      "num_tokens": 55609388.0,
      "step": 780
    },
    {
      "entropy": 0.35968837030231954,
      "epoch": 4.1798941798941796,
      "grad_norm": 1.5546875,
      "learning_rate": 1.3099943115231386e-05,
      "loss": 0.3570686101913452,
      "mean_token_accuracy": 0.8919634193181991,
      "num_tokens": 56329299.0,
      "step": 790
    },
    {
      "entropy": 0.3573555305600166,
      "epoch": 4.232804232804233,
      "grad_norm": 1.453125,
      "learning_rate": 1.2936637354461064e-05,
      "loss": 0.35538694858551023,
      "mean_token_accuracy": 0.891864238679409,
      "num_tokens": 57042704.0,
      "step": 800
    },
    {
      "entropy": 0.3631866227835417,
      "epoch": 4.285714285714286,
      "grad_norm": 1.453125,
      "learning_rate": 1.2772469924069285e-05,
      "loss": 0.36122586727142336,
      "mean_token_accuracy": 0.8907185509800911,
      "num_tokens": 57755769.0,
      "step": 810
    },
    {
      "entropy": 0.35537443719804285,
      "epoch": 4.338624338624339,
      "grad_norm": 1.3515625,
      "learning_rate": 1.2607488994146703e-05,
      "loss": 0.3507373809814453,
      "mean_token_accuracy": 0.8932205140590668,
      "num_tokens": 58467967.0,
      "step": 820
    },
    {
      "entropy": 0.36577242650091646,
      "epoch": 4.391534391534392,
      "grad_norm": 1.421875,
      "learning_rate": 1.2441742973481432e-05,
      "loss": 0.36283602714538576,
      "mean_token_accuracy": 0.8900898195803165,
      "num_tokens": 59188579.0,
      "step": 830
    },
    {
      "entropy": 0.3536319576203823,
      "epoch": 4.444444444444445,
      "grad_norm": 1.453125,
      "learning_rate": 1.2275280495354889e-05,
      "loss": 0.3507254123687744,
      "mean_token_accuracy": 0.8936197653412818,
      "num_tokens": 59899589.0,
      "step": 840
    },
    {
      "entropy": 0.35393124222755434,
      "epoch": 4.497354497354498,
      "grad_norm": 1.390625,
      "learning_rate": 1.21081504032718e-05,
      "loss": 0.35221099853515625,
      "mean_token_accuracy": 0.8937442168593407,
      "num_tokens": 60620913.0,
      "step": 850
    },
    {
      "entropy": 0.3644785340875387,
      "epoch": 4.550264550264551,
      "grad_norm": 1.4296875,
      "learning_rate": 1.1940401736628524e-05,
      "loss": 0.36148934364318847,
      "mean_token_accuracy": 0.8908700153231621,
      "num_tokens": 61330675.0,
      "step": 860
    },
    {
      "entropy": 0.36559525281190874,
      "epoch": 4.603174603174603,
      "grad_norm": 1.546875,
      "learning_rate": 1.1772083716323878e-05,
      "loss": 0.36388137340545657,
      "mean_token_accuracy": 0.8894597724080086,
      "num_tokens": 62041645.0,
      "step": 870
    },
    {
      "entropy": 0.3636305950582027,
      "epoch": 4.656084656084656,
      "grad_norm": 1.3671875,
      "learning_rate": 1.1603245730316724e-05,
      "loss": 0.35996088981628416,
      "mean_token_accuracy": 0.8900512047111988,
      "num_tokens": 62750446.0,
      "step": 880
    },
    {
      "entropy": 0.35667852535843847,
      "epoch": 4.708994708994709,
      "grad_norm": 1.4296875,
      "learning_rate": 1.1433937319134512e-05,
      "loss": 0.3551082372665405,
      "mean_token_accuracy": 0.8923696964979172,
      "num_tokens": 63460008.0,
      "step": 890
    },
    {
      "entropy": 0.35801570676267147,
      "epoch": 4.761904761904762,
      "grad_norm": 1.4375,
      "learning_rate": 1.1264208161337091e-05,
      "loss": 0.3563329458236694,
      "mean_token_accuracy": 0.8912324517965317,
      "num_tokens": 64164803.0,
      "step": 900
    },
    {
      "entropy": 0.36424682177603246,
      "epoch": 4.814814814814815,
      "grad_norm": 1.4140625,
      "learning_rate": 1.1094108058940005e-05,
      "loss": 0.3606156826019287,
      "mean_token_accuracy": 0.8901903286576272,
      "num_tokens": 64878163.0,
      "step": 910
    },
    {
      "entropy": 0.3541768804192543,
      "epoch": 4.867724867724868,
      "grad_norm": 1.4296875,
      "learning_rate": 1.0923686922801537e-05,
      "loss": 0.34981212615966795,
      "mean_token_accuracy": 0.893631624430418,
      "num_tokens": 65599878.0,
      "step": 920
    },
    {
      "entropy": 0.35314388051629064,
      "epoch": 4.920634920634921,
      "grad_norm": 1.40625,
      "learning_rate": 1.0752994757977862e-05,
      "loss": 0.3507479190826416,
      "mean_token_accuracy": 0.8934470795094966,
      "num_tokens": 66312478.0,
      "step": 930
    },
    {
      "entropy": 0.36552518904209136,
      "epoch": 4.973544973544973,
      "grad_norm": 1.40625,
      "learning_rate": 1.058208164905052e-05,
      "loss": 0.364410400390625,
      "mean_token_accuracy": 0.8898321248590946,
      "num_tokens": 67026652.0,
      "step": 940
    }
  ],
  "logging_steps": 10,
  "max_steps": 1890,
  "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": 1.2167874952917156e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}