{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999829030603522,
  "eval_steps": 100,
  "global_step": 731,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006838775859121217,
      "grad_norm": 4.283134460449219,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 1.3383,
      "mean_token_accuracy": 0.6803730711340904,
      "step": 5
    },
    {
      "epoch": 0.013677551718242434,
      "grad_norm": 2.8879575729370117,
      "learning_rate": 2.702702702702703e-06,
      "loss": 1.2973,
      "mean_token_accuracy": 0.6889803171157837,
      "step": 10
    },
    {
      "epoch": 0.02051632757736365,
      "grad_norm": 1.4510750770568848,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 1.2647,
      "mean_token_accuracy": 0.6867526054382325,
      "step": 15
    },
    {
      "epoch": 0.027355103436484868,
      "grad_norm": 2.0351901054382324,
      "learning_rate": 5.405405405405406e-06,
      "loss": 1.1765,
      "mean_token_accuracy": 0.7007667943835258,
      "step": 20
    },
    {
      "epoch": 0.034193879295606085,
      "grad_norm": 1.0107135772705078,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 1.1098,
      "mean_token_accuracy": 0.7095919325947762,
      "step": 25
    },
    {
      "epoch": 0.0410326551547273,
      "grad_norm": 0.7789012789726257,
      "learning_rate": 8.108108108108109e-06,
      "loss": 1.0612,
      "mean_token_accuracy": 0.717575378715992,
      "step": 30
    },
    {
      "epoch": 0.04787143101384852,
      "grad_norm": 0.6472299098968506,
      "learning_rate": 9.45945945945946e-06,
      "loss": 1.0272,
      "mean_token_accuracy": 0.7225469693541526,
      "step": 35
    },
    {
      "epoch": 0.054710206872969736,
      "grad_norm": 0.5901947021484375,
      "learning_rate": 1.0810810810810812e-05,
      "loss": 0.9874,
      "mean_token_accuracy": 0.7313357755541802,
      "step": 40
    },
    {
      "epoch": 0.06154898273209095,
      "grad_norm": 0.6146127581596375,
      "learning_rate": 1.2162162162162164e-05,
      "loss": 0.9738,
      "mean_token_accuracy": 0.7330265626311302,
      "step": 45
    },
    {
      "epoch": 0.06838775859121217,
      "grad_norm": 0.6039953827857971,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 0.9604,
      "mean_token_accuracy": 0.7354672074317932,
      "step": 50
    },
    {
      "epoch": 0.0752265344503334,
      "grad_norm": 0.5497832894325256,
      "learning_rate": 1.4864864864864865e-05,
      "loss": 0.9501,
      "mean_token_accuracy": 0.7374408826231956,
      "step": 55
    },
    {
      "epoch": 0.0820653103094546,
      "grad_norm": 0.5113657712936401,
      "learning_rate": 1.6216216216216218e-05,
      "loss": 0.9237,
      "mean_token_accuracy": 0.7434996381402016,
      "step": 60
    },
    {
      "epoch": 0.08890408616857583,
      "grad_norm": 0.5408641695976257,
      "learning_rate": 1.756756756756757e-05,
      "loss": 0.9378,
      "mean_token_accuracy": 0.7394065439701081,
      "step": 65
    },
    {
      "epoch": 0.09574286202769704,
      "grad_norm": 0.5544885396957397,
      "learning_rate": 1.891891891891892e-05,
      "loss": 0.9347,
      "mean_token_accuracy": 0.739613801240921,
      "step": 70
    },
    {
      "epoch": 0.10258163788681826,
      "grad_norm": 0.5568746328353882,
      "learning_rate": 1.9999885675796825e-05,
      "loss": 0.9144,
      "mean_token_accuracy": 0.7448009416460991,
      "step": 75
    },
    {
      "epoch": 0.10942041374593947,
      "grad_norm": 0.5509134531021118,
      "learning_rate": 1.9995884603149403e-05,
      "loss": 0.9181,
      "mean_token_accuracy": 0.7419906392693519,
      "step": 80
    },
    {
      "epoch": 0.1162591896050607,
      "grad_norm": 0.548611044883728,
      "learning_rate": 1.9986169934079135e-05,
      "loss": 0.9106,
      "mean_token_accuracy": 0.7441679835319519,
      "step": 85
    },
    {
      "epoch": 0.1230979654641819,
      "grad_norm": 0.5514124631881714,
      "learning_rate": 1.9970747221441084e-05,
      "loss": 0.9151,
      "mean_token_accuracy": 0.7427051544189454,
      "step": 90
    },
    {
      "epoch": 0.12993674132330313,
      "grad_norm": 0.549062967300415,
      "learning_rate": 1.994962528077878e-05,
      "loss": 0.9029,
      "mean_token_accuracy": 0.7451761096715928,
      "step": 95
    },
    {
      "epoch": 0.13677551718242434,
      "grad_norm": 0.573813796043396,
      "learning_rate": 1.9922816185285264e-05,
      "loss": 0.8884,
      "mean_token_accuracy": 0.7493397817015648,
      "step": 100
    },
    {
      "epoch": 0.14361429304154558,
      "grad_norm": 0.5562133193016052,
      "learning_rate": 1.9890335258902177e-05,
      "loss": 0.8855,
      "mean_token_accuracy": 0.7493105083703995,
      "step": 105
    },
    {
      "epoch": 0.1504530689006668,
      "grad_norm": 0.5802770853042603,
      "learning_rate": 1.9852201067560607e-05,
      "loss": 0.9027,
      "mean_token_accuracy": 0.7449040159583091,
      "step": 110
    },
    {
      "epoch": 0.157291844759788,
      "grad_norm": 0.5636809468269348,
      "learning_rate": 1.9808435408568938e-05,
      "loss": 0.8876,
      "mean_token_accuracy": 0.7495187863707542,
      "step": 115
    },
    {
      "epoch": 0.1641306206189092,
      "grad_norm": 0.5830625891685486,
      "learning_rate": 1.97590632981536e-05,
      "loss": 0.8871,
      "mean_token_accuracy": 0.7475770503282547,
      "step": 120
    },
    {
      "epoch": 0.17096939647803044,
      "grad_norm": 0.5543267726898193,
      "learning_rate": 1.970411295715994e-05,
      "loss": 0.8918,
      "mean_token_accuracy": 0.7472289979457856,
      "step": 125
    },
    {
      "epoch": 0.17780817233715165,
      "grad_norm": 0.5292794704437256,
      "learning_rate": 1.964361579492132e-05,
      "loss": 0.8764,
      "mean_token_accuracy": 0.7520371958613395,
      "step": 130
    },
    {
      "epoch": 0.18464694819627286,
      "grad_norm": 0.5680862069129944,
      "learning_rate": 1.9577606391305705e-05,
      "loss": 0.8934,
      "mean_token_accuracy": 0.7469688639044761,
      "step": 135
    },
    {
      "epoch": 0.19148572405539407,
      "grad_norm": 0.5672624111175537,
      "learning_rate": 1.950612247694998e-05,
      "loss": 0.889,
      "mean_token_accuracy": 0.7479311898350716,
      "step": 140
    },
    {
      "epoch": 0.1983244999145153,
      "grad_norm": 0.5509658455848694,
      "learning_rate": 1.9429204911693333e-05,
      "loss": 0.8708,
      "mean_token_accuracy": 0.7525908648967743,
      "step": 145
    },
    {
      "epoch": 0.20516327577363652,
      "grad_norm": 0.573887825012207,
      "learning_rate": 1.9346897661221957e-05,
      "loss": 0.8748,
      "mean_token_accuracy": 0.7516056269407272,
      "step": 150
    },
    {
      "epoch": 0.21200205163275773,
      "grad_norm": 0.5755806565284729,
      "learning_rate": 1.92592477719385e-05,
      "loss": 0.88,
      "mean_token_accuracy": 0.7498792737722397,
      "step": 155
    },
    {
      "epoch": 0.21884082749187894,
      "grad_norm": 0.5494788885116577,
      "learning_rate": 1.916630534407058e-05,
      "loss": 0.8739,
      "mean_token_accuracy": 0.7512936532497406,
      "step": 160
    },
    {
      "epoch": 0.22567960335100018,
      "grad_norm": 0.543487548828125,
      "learning_rate": 1.9068123503033752e-05,
      "loss": 0.8587,
      "mean_token_accuracy": 0.7555688112974167,
      "step": 165
    },
    {
      "epoch": 0.2325183792101214,
      "grad_norm": 0.5982221364974976,
      "learning_rate": 1.8964758369065303e-05,
      "loss": 0.8923,
      "mean_token_accuracy": 0.7462443545460701,
      "step": 170
    },
    {
      "epoch": 0.2393571550692426,
      "grad_norm": 0.5857303142547607,
      "learning_rate": 1.8856269025146182e-05,
      "loss": 0.8738,
      "mean_token_accuracy": 0.750712414085865,
      "step": 175
    },
    {
      "epoch": 0.2461959309283638,
      "grad_norm": 0.5462734699249268,
      "learning_rate": 1.874271748322951e-05,
      "loss": 0.8523,
      "mean_token_accuracy": 0.7573387727141381,
      "step": 180
    },
    {
      "epoch": 0.253034706787485,
      "grad_norm": 0.5329501032829285,
      "learning_rate": 1.8624168648794833e-05,
      "loss": 0.8671,
      "mean_token_accuracy": 0.7528049916028976,
      "step": 185
    },
    {
      "epoch": 0.25987348264660626,
      "grad_norm": 0.516778290271759,
      "learning_rate": 1.8500690283748502e-05,
      "loss": 0.8363,
      "mean_token_accuracy": 0.7607189759612083,
      "step": 190
    },
    {
      "epoch": 0.2667122585057275,
      "grad_norm": 0.5503281354904175,
      "learning_rate": 1.837235296769131e-05,
      "loss": 0.8646,
      "mean_token_accuracy": 0.7525520265102387,
      "step": 195
    },
    {
      "epoch": 0.2735510343648487,
      "grad_norm": 0.5709648728370667,
      "learning_rate": 1.8239230057575542e-05,
      "loss": 0.8547,
      "mean_token_accuracy": 0.7552181035280228,
      "step": 200
    },
    {
      "epoch": 0.2803898102239699,
      "grad_norm": 0.5268268585205078,
      "learning_rate": 1.810139764577454e-05,
      "loss": 0.8569,
      "mean_token_accuracy": 0.7549711287021637,
      "step": 205
    },
    {
      "epoch": 0.28722858608309115,
      "grad_norm": 0.5442251563072205,
      "learning_rate": 1.7958934516588665e-05,
      "loss": 0.8596,
      "mean_token_accuracy": 0.7541473567485809,
      "step": 210
    },
    {
      "epoch": 0.29406736194221234,
      "grad_norm": 0.5293693542480469,
      "learning_rate": 1.7811922101212622e-05,
      "loss": 0.8692,
      "mean_token_accuracy": 0.7512467160820961,
      "step": 215
    },
    {
      "epoch": 0.3009061378013336,
      "grad_norm": 0.5479506850242615,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.8619,
      "mean_token_accuracy": 0.7537136003375053,
      "step": 220
    },
    {
      "epoch": 0.30774491366045476,
      "grad_norm": 0.5542939901351929,
      "learning_rate": 1.75045880903802e-05,
      "loss": 0.8419,
      "mean_token_accuracy": 0.7578989654779434,
      "step": 225
    },
    {
      "epoch": 0.314583689519576,
      "grad_norm": 0.5070068836212158,
      "learning_rate": 1.7344442165469714e-05,
      "loss": 0.8448,
      "mean_token_accuracy": 0.7581931978464127,
      "step": 230
    },
    {
      "epoch": 0.32142246537869723,
      "grad_norm": 0.5048102140426636,
      "learning_rate": 1.7180098195048458e-05,
      "loss": 0.8317,
      "mean_token_accuracy": 0.7602518483996391,
      "step": 235
    },
    {
      "epoch": 0.3282612412378184,
      "grad_norm": 0.5216901302337646,
      "learning_rate": 1.7011650117287868e-05,
      "loss": 0.8427,
      "mean_token_accuracy": 0.7580358654260635,
      "step": 240
    },
    {
      "epoch": 0.33510001709693965,
      "grad_norm": 0.5171140432357788,
      "learning_rate": 1.683919421624611e-05,
      "loss": 0.8286,
      "mean_token_accuracy": 0.7620488360524178,
      "step": 245
    },
    {
      "epoch": 0.3419387929560609,
      "grad_norm": 0.5429340600967407,
      "learning_rate": 1.6662829066832595e-05,
      "loss": 0.8452,
      "mean_token_accuracy": 0.7569812595844269,
      "step": 250
    },
    {
      "epoch": 0.34877756881518207,
      "grad_norm": 0.5294564962387085,
      "learning_rate": 1.648265547846308e-05,
      "loss": 0.8478,
      "mean_token_accuracy": 0.756881557404995,
      "step": 255
    },
    {
      "epoch": 0.3556163446743033,
      "grad_norm": 0.530605137348175,
      "learning_rate": 1.6298776437437526e-05,
      "loss": 0.8495,
      "mean_token_accuracy": 0.7560626447200776,
      "step": 260
    },
    {
      "epoch": 0.3624551205334245,
      "grad_norm": 0.5185920000076294,
      "learning_rate": 1.611129704807362e-05,
      "loss": 0.8438,
      "mean_token_accuracy": 0.7576473146677017,
      "step": 265
    },
    {
      "epoch": 0.36929389639254573,
      "grad_norm": 0.5438268184661865,
      "learning_rate": 1.592032447262973e-05,
      "loss": 0.8481,
      "mean_token_accuracy": 0.7563759610056877,
      "step": 270
    },
    {
      "epoch": 0.37613267225166697,
      "grad_norm": 0.5615527033805847,
      "learning_rate": 1.572596787005149e-05,
      "loss": 0.8418,
      "mean_token_accuracy": 0.757819227874279,
      "step": 275
    },
    {
      "epoch": 0.38297144811078815,
      "grad_norm": 0.48962655663490295,
      "learning_rate": 1.55283383335771e-05,
      "loss": 0.8406,
      "mean_token_accuracy": 0.7577673494815826,
      "step": 280
    },
    {
      "epoch": 0.3898102239699094,
      "grad_norm": 0.4873958230018616,
      "learning_rate": 1.5327548827237008e-05,
      "loss": 0.8389,
      "mean_token_accuracy": 0.7587939977645874,
      "step": 285
    },
    {
      "epoch": 0.3966489998290306,
      "grad_norm": 0.49630922079086304,
      "learning_rate": 1.512371412128424e-05,
      "loss": 0.8501,
      "mean_token_accuracy": 0.7546382084488868,
      "step": 290
    },
    {
      "epoch": 0.4034877756881518,
      "grad_norm": 0.4898976683616638,
      "learning_rate": 1.4916950726592322e-05,
      "loss": 0.8335,
      "mean_token_accuracy": 0.7595216274261475,
      "step": 295
    },
    {
      "epoch": 0.41032655154727304,
      "grad_norm": 0.486189603805542,
      "learning_rate": 1.4707376828058264e-05,
      "loss": 0.8334,
      "mean_token_accuracy": 0.7587142795324325,
      "step": 300
    },
    {
      "epoch": 0.4171653274063943,
      "grad_norm": 0.4933895170688629,
      "learning_rate": 1.449511221704866e-05,
      "loss": 0.8543,
      "mean_token_accuracy": 0.7549725160002708,
      "step": 305
    },
    {
      "epoch": 0.42400410326551546,
      "grad_norm": 0.4862573444843292,
      "learning_rate": 1.428027822292758e-05,
      "loss": 0.8328,
      "mean_token_accuracy": 0.7595344498753548,
      "step": 310
    },
    {
      "epoch": 0.4308428791246367,
      "grad_norm": 0.48415231704711914,
      "learning_rate": 1.4062997643705308e-05,
      "loss": 0.8282,
      "mean_token_accuracy": 0.7610621720552444,
      "step": 315
    },
    {
      "epoch": 0.4376816549837579,
      "grad_norm": 0.5168640613555908,
      "learning_rate": 1.3843394675847635e-05,
      "loss": 0.8472,
      "mean_token_accuracy": 0.7552296608686447,
      "step": 320
    },
    {
      "epoch": 0.4445204308428791,
      "grad_norm": 0.5019128918647766,
      "learning_rate": 1.3621594843285801e-05,
      "loss": 0.8287,
      "mean_token_accuracy": 0.7620115980505944,
      "step": 325
    },
    {
      "epoch": 0.45135920670200036,
      "grad_norm": 0.5697439312934875,
      "learning_rate": 1.3397724925667657e-05,
      "loss": 0.8361,
      "mean_token_accuracy": 0.7582670867443084,
      "step": 330
    },
    {
      "epoch": 0.45819798256112154,
      "grad_norm": 0.5009385943412781,
      "learning_rate": 1.3171912885891063e-05,
      "loss": 0.8402,
      "mean_token_accuracy": 0.756958456337452,
      "step": 335
    },
    {
      "epoch": 0.4650367584202428,
      "grad_norm": 0.5170038938522339,
      "learning_rate": 1.2944287796960949e-05,
      "loss": 0.8277,
      "mean_token_accuracy": 0.7602688521146774,
      "step": 340
    },
    {
      "epoch": 0.471875534279364,
      "grad_norm": 0.500216007232666,
      "learning_rate": 1.2714979768211854e-05,
      "loss": 0.8267,
      "mean_token_accuracy": 0.760731266438961,
      "step": 345
    },
    {
      "epoch": 0.4787143101384852,
      "grad_norm": 0.5052452683448792,
      "learning_rate": 1.2484119870938102e-05,
      "loss": 0.8289,
      "mean_token_accuracy": 0.760765828192234,
      "step": 350
    },
    {
      "epoch": 0.48555308599760644,
      "grad_norm": 0.47336429357528687,
      "learning_rate": 1.2251840063474108e-05,
      "loss": 0.8225,
      "mean_token_accuracy": 0.7622879460453987,
      "step": 355
    },
    {
      "epoch": 0.4923918618567276,
      "grad_norm": 0.4850134551525116,
      "learning_rate": 1.2018273115767673e-05,
      "loss": 0.8289,
      "mean_token_accuracy": 0.7606528863310814,
      "step": 360
    },
    {
      "epoch": 0.49923063771584886,
      "grad_norm": 0.49699971079826355,
      "learning_rate": 1.1783552533489372e-05,
      "loss": 0.8221,
      "mean_token_accuracy": 0.762169836461544,
      "step": 365
    },
    {
      "epoch": 0.50606941357497,
      "grad_norm": 0.5126599073410034,
      "learning_rate": 1.1547812481721387e-05,
      "loss": 0.8363,
      "mean_token_accuracy": 0.757779236137867,
      "step": 370
    },
    {
      "epoch": 0.5129081894340913,
      "grad_norm": 0.5152341723442078,
      "learning_rate": 1.1311187708269442e-05,
      "loss": 0.8414,
      "mean_token_accuracy": 0.756208673119545,
      "step": 375
    },
    {
      "epoch": 0.5197469652932125,
      "grad_norm": 0.47980859875679016,
      "learning_rate": 1.1073813466641633e-05,
      "loss": 0.8262,
      "mean_token_accuracy": 0.7605276107788086,
      "step": 380
    },
    {
      "epoch": 0.5265857411523337,
      "grad_norm": 0.5068893432617188,
      "learning_rate": 1.0835825438738232e-05,
      "loss": 0.8334,
      "mean_token_accuracy": 0.7591528907418251,
      "step": 385
    },
    {
      "epoch": 0.533424517011455,
      "grad_norm": 0.4852905571460724,
      "learning_rate": 1.0597359657296602e-05,
      "loss": 0.8242,
      "mean_token_accuracy": 0.7600131437182427,
      "step": 390
    },
    {
      "epoch": 0.5402632928705762,
      "grad_norm": 0.4789692461490631,
      "learning_rate": 1.0358552428135576e-05,
      "loss": 0.8224,
      "mean_token_accuracy": 0.7617440149188042,
      "step": 395
    },
    {
      "epoch": 0.5471020687296974,
      "grad_norm": 0.5026122331619263,
      "learning_rate": 1.0119540252243755e-05,
      "loss": 0.8374,
      "mean_token_accuracy": 0.7577085196971893,
      "step": 400
    },
    {
      "epoch": 0.5539408445888186,
      "grad_norm": 0.5124115347862244,
      "learning_rate": 9.880459747756247e-06,
      "loss": 0.8158,
      "mean_token_accuracy": 0.7633502900600433,
      "step": 405
    },
    {
      "epoch": 0.5607796204479398,
      "grad_norm": 0.46995291113853455,
      "learning_rate": 9.641447571864429e-06,
      "loss": 0.8309,
      "mean_token_accuracy": 0.7596037566661835,
      "step": 410
    },
    {
      "epoch": 0.567618396307061,
      "grad_norm": 0.4657708704471588,
      "learning_rate": 9.402640342703401e-06,
      "loss": 0.8258,
      "mean_token_accuracy": 0.7604287952184677,
      "step": 415
    },
    {
      "epoch": 0.5744571721661823,
      "grad_norm": 0.4966000020503998,
      "learning_rate": 9.164174561261771e-06,
      "loss": 0.8191,
      "mean_token_accuracy": 0.7622967541217804,
      "step": 420
    },
    {
      "epoch": 0.5812959480253035,
      "grad_norm": 0.5118598937988281,
      "learning_rate": 8.92618653335837e-06,
      "loss": 0.8145,
      "mean_token_accuracy": 0.7636432871222496,
      "step": 425
    },
    {
      "epoch": 0.5881347238844247,
      "grad_norm": 0.47218063473701477,
      "learning_rate": 8.688812291730565e-06,
      "loss": 0.8175,
      "mean_token_accuracy": 0.7625760570168495,
      "step": 430
    },
    {
      "epoch": 0.5949734997435459,
      "grad_norm": 0.4943382441997528,
      "learning_rate": 8.452187518278615e-06,
      "loss": 0.8282,
      "mean_token_accuracy": 0.7598957225680352,
      "step": 435
    },
    {
      "epoch": 0.6018122756026671,
      "grad_norm": 0.4632488489151001,
      "learning_rate": 8.216447466510633e-06,
      "loss": 0.8166,
      "mean_token_accuracy": 0.7627444177865982,
      "step": 440
    },
    {
      "epoch": 0.6086510514617883,
      "grad_norm": 0.46436184644699097,
      "learning_rate": 7.981726884232328e-06,
      "loss": 0.8141,
      "mean_token_accuracy": 0.7631665468215942,
      "step": 445
    },
    {
      "epoch": 0.6154898273209095,
      "grad_norm": 0.4806179702281952,
      "learning_rate": 7.748159936525896e-06,
      "loss": 0.8158,
      "mean_token_accuracy": 0.762781310081482,
      "step": 450
    },
    {
      "epoch": 0.6223286031800308,
      "grad_norm": 0.4713290333747864,
      "learning_rate": 7.5158801290619e-06,
      "loss": 0.8197,
      "mean_token_accuracy": 0.7615951552987099,
      "step": 455
    },
    {
      "epoch": 0.629167379039152,
      "grad_norm": 0.46885767579078674,
      "learning_rate": 7.285020231788149e-06,
      "loss": 0.8073,
      "mean_token_accuracy": 0.7656721040606499,
      "step": 460
    },
    {
      "epoch": 0.6360061548982732,
      "grad_norm": 0.495272159576416,
      "learning_rate": 7.0557122030390545e-06,
      "loss": 0.8063,
      "mean_token_accuracy": 0.765167286992073,
      "step": 465
    },
    {
      "epoch": 0.6428449307573945,
      "grad_norm": 0.47429198026657104,
      "learning_rate": 6.8280871141089415e-06,
      "loss": 0.8026,
      "mean_token_accuracy": 0.7673456132411957,
      "step": 470
    },
    {
      "epoch": 0.6496837066165156,
      "grad_norm": 0.48846620321273804,
      "learning_rate": 6.602275074332345e-06,
      "loss": 0.8201,
      "mean_token_accuracy": 0.7618905574083328,
      "step": 475
    },
    {
      "epoch": 0.6565224824756368,
      "grad_norm": 0.5203046798706055,
      "learning_rate": 6.378405156714202e-06,
      "loss": 0.8054,
      "mean_token_accuracy": 0.7656926274299621,
      "step": 480
    },
    {
      "epoch": 0.6633612583347581,
      "grad_norm": 0.481134295463562,
      "learning_rate": 6.156605324152369e-06,
      "loss": 0.7985,
      "mean_token_accuracy": 0.7675068721175193,
      "step": 485
    },
    {
      "epoch": 0.6702000341938793,
      "grad_norm": 0.465944766998291,
      "learning_rate": 5.937002356294699e-06,
      "loss": 0.8082,
      "mean_token_accuracy": 0.7647843450307846,
      "step": 490
    },
    {
      "epoch": 0.6770388100530005,
      "grad_norm": 0.4643535614013672,
      "learning_rate": 5.719721777072425e-06,
      "loss": 0.8081,
      "mean_token_accuracy": 0.7649053990840912,
      "step": 495
    },
    {
      "epoch": 0.6838775859121218,
      "grad_norm": 0.48063191771507263,
      "learning_rate": 5.504887782951343e-06,
      "loss": 0.8067,
      "mean_token_accuracy": 0.765461964905262,
      "step": 500
    },
    {
      "epoch": 0.690716361771243,
      "grad_norm": 0.47620853781700134,
      "learning_rate": 5.29262317194174e-06,
      "loss": 0.8017,
      "mean_token_accuracy": 0.7668887257575989,
      "step": 505
    },
    {
      "epoch": 0.6975551376303641,
      "grad_norm": 0.46232712268829346,
      "learning_rate": 5.083049273407681e-06,
      "loss": 0.8034,
      "mean_token_accuracy": 0.7657584965229034,
      "step": 510
    },
    {
      "epoch": 0.7043939134894854,
      "grad_norm": 0.45751717686653137,
      "learning_rate": 4.876285878715764e-06,
      "loss": 0.8035,
      "mean_token_accuracy": 0.766502857208252,
      "step": 515
    },
    {
      "epoch": 0.7112326893486066,
      "grad_norm": 0.4558106064796448,
      "learning_rate": 4.672451172762998e-06,
      "loss": 0.8103,
      "mean_token_accuracy": 0.7645265579223632,
      "step": 520
    },
    {
      "epoch": 0.7180714652077278,
      "grad_norm": 0.4815528988838196,
      "learning_rate": 4.471661666422899e-06,
      "loss": 0.814,
      "mean_token_accuracy": 0.7626894161105156,
      "step": 525
    },
    {
      "epoch": 0.724910241066849,
      "grad_norm": 0.4826851189136505,
      "learning_rate": 4.274032129948512e-06,
      "loss": 0.8078,
      "mean_token_accuracy": 0.7646446511149406,
      "step": 530
    },
    {
      "epoch": 0.7317490169259703,
      "grad_norm": 0.4646717309951782,
      "learning_rate": 4.079675527370273e-06,
      "loss": 0.8139,
      "mean_token_accuracy": 0.7622727945446968,
      "step": 535
    },
    {
      "epoch": 0.7385877927850915,
      "grad_norm": 0.48112139105796814,
      "learning_rate": 3.888702951926384e-06,
      "loss": 0.7982,
      "mean_token_accuracy": 0.7667050585150719,
      "step": 540
    },
    {
      "epoch": 0.7454265686442126,
      "grad_norm": 0.47457870841026306,
      "learning_rate": 3.701223562562478e-06,
      "loss": 0.8082,
      "mean_token_accuracy": 0.7652096658945083,
      "step": 545
    },
    {
      "epoch": 0.7522653445033339,
      "grad_norm": 0.48485058546066284,
      "learning_rate": 3.5173445215369183e-06,
      "loss": 0.8027,
      "mean_token_accuracy": 0.7657500252127647,
      "step": 550
    },
    {
      "epoch": 0.7591041203624551,
      "grad_norm": 0.49953824281692505,
      "learning_rate": 3.3371709331674075e-06,
      "loss": 0.8036,
      "mean_token_accuracy": 0.7657319813966751,
      "step": 555
    },
    {
      "epoch": 0.7659428962215763,
      "grad_norm": 0.45230066776275635,
      "learning_rate": 3.1608057837538976e-06,
      "loss": 0.8029,
      "mean_token_accuracy": 0.7664909601211548,
      "step": 560
    },
    {
      "epoch": 0.7727816720806976,
      "grad_norm": 0.4862216114997864,
      "learning_rate": 2.988349882712135e-06,
      "loss": 0.82,
      "mean_token_accuracy": 0.7606521427631379,
      "step": 565
    },
    {
      "epoch": 0.7796204479398188,
      "grad_norm": 0.4636688232421875,
      "learning_rate": 2.819901804951547e-06,
      "loss": 0.7885,
      "mean_token_accuracy": 0.7696284845471382,
      "step": 570
    },
    {
      "epoch": 0.78645922379894,
      "grad_norm": 0.46034541726112366,
      "learning_rate": 2.655557834530288e-06,
      "loss": 0.8148,
      "mean_token_accuracy": 0.7626620322465897,
      "step": 575
    },
    {
      "epoch": 0.7932979996580612,
      "grad_norm": 0.46980300545692444,
      "learning_rate": 2.495411909619804e-06,
      "loss": 0.8209,
      "mean_token_accuracy": 0.760961389541626,
      "step": 580
    },
    {
      "epoch": 0.8001367755171824,
      "grad_norm": 0.4673324227333069,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.8131,
      "mean_token_accuracy": 0.7633547097444534,
      "step": 585
    },
    {
      "epoch": 0.8069755513763036,
      "grad_norm": 0.46234130859375,
      "learning_rate": 2.1880778987873806e-06,
      "loss": 0.7929,
      "mean_token_accuracy": 0.7690023958683014,
      "step": 590
    },
    {
      "epoch": 0.8138143272354249,
      "grad_norm": 0.4616515338420868,
      "learning_rate": 2.0410654834113362e-06,
      "loss": 0.7883,
      "mean_token_accuracy": 0.7698821023106575,
      "step": 595
    },
    {
      "epoch": 0.8206531030945461,
      "grad_norm": 0.4555530548095703,
      "learning_rate": 1.8986023542254617e-06,
      "loss": 0.7933,
      "mean_token_accuracy": 0.7684802070260048,
      "step": 600
    },
    {
      "epoch": 0.8274918789536673,
      "grad_norm": 0.45201539993286133,
      "learning_rate": 1.7607699424244583e-06,
      "loss": 0.8116,
      "mean_token_accuracy": 0.7643455028533935,
      "step": 605
    },
    {
      "epoch": 0.8343306548127886,
      "grad_norm": 0.47511157393455505,
      "learning_rate": 1.6276470323086936e-06,
      "loss": 0.798,
      "mean_token_accuracy": 0.7679879561066627,
      "step": 610
    },
    {
      "epoch": 0.8411694306719097,
      "grad_norm": 0.443029522895813,
      "learning_rate": 1.499309716251498e-06,
      "loss": 0.8061,
      "mean_token_accuracy": 0.7647668555378914,
      "step": 615
    },
    {
      "epoch": 0.8480082065310309,
      "grad_norm": 0.4504885673522949,
      "learning_rate": 1.3758313512051702e-06,
      "loss": 0.7991,
      "mean_token_accuracy": 0.7665026307106018,
      "step": 620
    },
    {
      "epoch": 0.8548469823901521,
      "grad_norm": 0.4775781035423279,
      "learning_rate": 1.257282516770494e-06,
      "loss": 0.8099,
      "mean_token_accuracy": 0.7643145814538002,
      "step": 625
    },
    {
      "epoch": 0.8616857582492734,
      "grad_norm": 0.4560346305370331,
      "learning_rate": 1.1437309748538205e-06,
      "loss": 0.788,
      "mean_token_accuracy": 0.7699791714549065,
      "step": 630
    },
    {
      "epoch": 0.8685245341083946,
      "grad_norm": 0.46563640236854553,
      "learning_rate": 1.0352416309347003e-06,
      "loss": 0.7882,
      "mean_token_accuracy": 0.7693348750472069,
      "step": 635
    },
    {
      "epoch": 0.8753633099675158,
      "grad_norm": 0.4712006449699402,
      "learning_rate": 9.318764969662475e-07,
      "loss": 0.7948,
      "mean_token_accuracy": 0.7693790286779404,
      "step": 640
    },
    {
      "epoch": 0.8822020858266371,
      "grad_norm": 0.4499385952949524,
      "learning_rate": 8.336946559294223e-07,
      "loss": 0.7904,
      "mean_token_accuracy": 0.7691716372966766,
      "step": 645
    },
    {
      "epoch": 0.8890408616857582,
      "grad_norm": 0.46574312448501587,
      "learning_rate": 7.40752228061502e-07,
      "loss": 0.8119,
      "mean_token_accuracy": 0.7633272022008896,
      "step": 650
    },
    {
      "epoch": 0.8958796375448794,
      "grad_norm": 0.4548204243183136,
      "learning_rate": 6.531023387780433e-07,
      "loss": 0.7967,
      "mean_token_accuracy": 0.7682895168662072,
      "step": 655
    },
    {
      "epoch": 0.9027184134040007,
      "grad_norm": 0.475398987531662,
      "learning_rate": 5.707950883066681e-07,
      "loss": 0.8046,
      "mean_token_accuracy": 0.7655658751726151,
      "step": 660
    },
    {
      "epoch": 0.9095571892631219,
      "grad_norm": 0.4481120705604553,
      "learning_rate": 4.938775230500192e-07,
      "loss": 0.7998,
      "mean_token_accuracy": 0.7667894646525383,
      "step": 665
    },
    {
      "epoch": 0.9163959651222431,
      "grad_norm": 0.46256303787231445,
      "learning_rate": 4.223936086942981e-07,
      "loss": 0.7981,
      "mean_token_accuracy": 0.7671072691679001,
      "step": 670
    },
    {
      "epoch": 0.9232347409813644,
      "grad_norm": 0.45697101950645447,
      "learning_rate": 3.5638420507868145e-07,
      "loss": 0.7947,
      "mean_token_accuracy": 0.7680518299341201,
      "step": 675
    },
    {
      "epoch": 0.9300735168404856,
      "grad_norm": 0.44780802726745605,
      "learning_rate": 2.9588704284006176e-07,
      "loss": 0.7935,
      "mean_token_accuracy": 0.7683573782444,
      "step": 680
    },
    {
      "epoch": 0.9369122926996067,
      "grad_norm": 0.4538120925426483,
      "learning_rate": 2.4093670184640263e-07,
      "loss": 0.8087,
      "mean_token_accuracy": 0.7649404585361481,
      "step": 685
    },
    {
      "epoch": 0.943751068558728,
      "grad_norm": 0.44170472025871277,
      "learning_rate": 1.9156459143106598e-07,
      "loss": 0.8082,
      "mean_token_accuracy": 0.764902551472187,
      "step": 690
    },
    {
      "epoch": 0.9505898444178492,
      "grad_norm": 0.450748473405838,
      "learning_rate": 1.4779893243939358e-07,
      "loss": 0.7977,
      "mean_token_accuracy": 0.7670714050531388,
      "step": 695
    },
    {
      "epoch": 0.9574286202769704,
      "grad_norm": 0.4557766020298004,
      "learning_rate": 1.0966474109782354e-07,
      "loss": 0.794,
      "mean_token_accuracy": 0.7679675281047821,
      "step": 700
    },
    {
      "epoch": 0.9642673961360917,
      "grad_norm": 0.4443546533584595,
      "learning_rate": 7.718381471473524e-08,
      "loss": 0.7979,
      "mean_token_accuracy": 0.7666744440793991,
      "step": 705
    },
    {
      "epoch": 0.9711061719952129,
      "grad_norm": 0.4413938522338867,
      "learning_rate": 5.037471922122561e-08,
      "loss": 0.8083,
      "mean_token_accuracy": 0.7643239527940751,
      "step": 710
    },
    {
      "epoch": 0.9779449478543341,
      "grad_norm": 0.4516150653362274,
      "learning_rate": 2.925277855891695e-08,
      "loss": 0.8064,
      "mean_token_accuracy": 0.7641888409852982,
      "step": 715
    },
    {
      "epoch": 0.9847837237134552,
      "grad_norm": 0.4401575028896332,
      "learning_rate": 1.3830065920867886e-08,
      "loss": 0.8108,
      "mean_token_accuracy": 0.7633798211812973,
      "step": 720
    },
    {
      "epoch": 0.9916224995725765,
      "grad_norm": 0.4507163465023041,
      "learning_rate": 4.11539685059914e-09,
      "loss": 0.7984,
      "mean_token_accuracy": 0.7672414898872375,
      "step": 725
    },
    {
      "epoch": 0.9984612754316977,
      "grad_norm": 0.4516432285308838,
      "learning_rate": 1.1432420317758486e-10,
      "loss": 0.7992,
      "mean_token_accuracy": 0.7661866798996926,
      "step": 730
    },
    {
      "epoch": 0.999829030603522,
      "mean_token_accuracy": 0.7705116346478462,
      "step": 731,
      "total_flos": 72689419026432.0,
      "train_loss": 0.8537281411617138,
      "train_runtime": 90647.457,
      "train_samples_per_second": 1.032,
      "train_steps_per_second": 0.008
    }
  ],
  "logging_steps": 5,
  "max_steps": 731,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 72689419026432.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}