{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.002,
  "eval_steps": 500,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002,
      "grad_norm": 226.5673828125,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 67.51285400390626,
      "step": 10
    },
    {
      "epoch": 0.0004,
      "grad_norm": 30.177888870239258,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 29.44110107421875,
      "step": 20
    },
    {
      "epoch": 0.0006,
      "grad_norm": 7.557392120361328,
      "learning_rate": 8.699999999999999e-05,
      "loss": 16.708602905273438,
      "step": 30
    },
    {
      "epoch": 0.0008,
      "grad_norm": 4.4042744636535645,
      "learning_rate": 0.000117,
      "loss": 16.181797790527344,
      "step": 40
    },
    {
      "epoch": 0.001,
      "grad_norm": 2.3703675270080566,
      "learning_rate": 0.000147,
      "loss": 13.265884399414062,
      "step": 50
    },
    {
      "epoch": 0.0012,
      "grad_norm": 0.868837296962738,
      "learning_rate": 0.00017699999999999997,
      "loss": 11.693977355957031,
      "step": 60
    },
    {
      "epoch": 0.0014,
      "grad_norm": 1.1192706823349,
      "learning_rate": 0.00020699999999999996,
      "loss": 12.454998016357422,
      "step": 70
    },
    {
      "epoch": 0.0016,
      "grad_norm": 1.4453760385513306,
      "learning_rate": 0.000237,
      "loss": 13.03106231689453,
      "step": 80
    },
    {
      "epoch": 0.0018,
      "grad_norm": 1.499172568321228,
      "learning_rate": 0.000267,
      "loss": 10.518834686279297,
      "step": 90
    },
    {
      "epoch": 0.002,
      "grad_norm": 2.132214069366455,
      "learning_rate": 0.00029699999999999996,
      "loss": 12.466087341308594,
      "step": 100
    },
    {
      "epoch": 0.0022,
      "grad_norm": 0.9064206480979919,
      "learning_rate": 0.0002999458917835671,
      "loss": 12.170447540283202,
      "step": 110
    },
    {
      "epoch": 0.0024,
      "grad_norm": 4.273526191711426,
      "learning_rate": 0.00029988577154308615,
      "loss": 10.753311157226562,
      "step": 120
    },
    {
      "epoch": 0.0026,
      "grad_norm": 1.101340889930725,
      "learning_rate": 0.0002998256513026052,
      "loss": 12.582955932617187,
      "step": 130
    },
    {
      "epoch": 0.0028,
      "grad_norm": 0.7963618040084839,
      "learning_rate": 0.0002997655310621242,
      "loss": 12.283400726318359,
      "step": 140
    },
    {
      "epoch": 0.003,
      "grad_norm": 1.5654473304748535,
      "learning_rate": 0.00029970541082164324,
      "loss": 11.285658264160157,
      "step": 150
    },
    {
      "epoch": 0.0032,
      "grad_norm": 1.8542180061340332,
      "learning_rate": 0.0002996452905811623,
      "loss": 10.847380065917969,
      "step": 160
    },
    {
      "epoch": 0.0034,
      "grad_norm": 2.580841302871704,
      "learning_rate": 0.00029958517034068134,
      "loss": 9.636419677734375,
      "step": 170
    },
    {
      "epoch": 0.0036,
      "grad_norm": 1.7422585487365723,
      "learning_rate": 0.0002995250501002004,
      "loss": 12.142258453369141,
      "step": 180
    },
    {
      "epoch": 0.0038,
      "grad_norm": 1.7994998693466187,
      "learning_rate": 0.00029946492985971943,
      "loss": 11.316072845458985,
      "step": 190
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.8520310521125793,
      "learning_rate": 0.0002994048096192384,
      "loss": 9.44781723022461,
      "step": 200
    },
    {
      "epoch": 0.0042,
      "grad_norm": 1.9302258491516113,
      "learning_rate": 0.0002993446893787575,
      "loss": 11.585807800292969,
      "step": 210
    },
    {
      "epoch": 0.0044,
      "grad_norm": 1.4165903329849243,
      "learning_rate": 0.0002992845691382765,
      "loss": 10.411253356933594,
      "step": 220
    },
    {
      "epoch": 0.0046,
      "grad_norm": 2.6108484268188477,
      "learning_rate": 0.00029922444889779557,
      "loss": 13.10027618408203,
      "step": 230
    },
    {
      "epoch": 0.0048,
      "grad_norm": 2.317113161087036,
      "learning_rate": 0.00029916432865731456,
      "loss": 10.390520477294922,
      "step": 240
    },
    {
      "epoch": 0.005,
      "grad_norm": 2.3662290573120117,
      "learning_rate": 0.00029910420841683367,
      "loss": 11.516622924804688,
      "step": 250
    },
    {
      "epoch": 0.0052,
      "grad_norm": 1.1160132884979248,
      "learning_rate": 0.0002990440881763527,
      "loss": 10.796371459960938,
      "step": 260
    },
    {
      "epoch": 0.0054,
      "grad_norm": 2.113326072692871,
      "learning_rate": 0.0002989839679358717,
      "loss": 12.288037109375,
      "step": 270
    },
    {
      "epoch": 0.0056,
      "grad_norm": 1.6802517175674438,
      "learning_rate": 0.00029892384769539075,
      "loss": 9.989302062988282,
      "step": 280
    },
    {
      "epoch": 0.0058,
      "grad_norm": 0.667611300945282,
      "learning_rate": 0.0002988637274549098,
      "loss": 10.866537475585938,
      "step": 290
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.9238641858100891,
      "learning_rate": 0.00029880360721442885,
      "loss": 10.386916351318359,
      "step": 300
    },
    {
      "epoch": 0.0062,
      "grad_norm": 2.5315372943878174,
      "learning_rate": 0.00029874348697394784,
      "loss": 8.981736755371093,
      "step": 310
    },
    {
      "epoch": 0.0064,
      "grad_norm": 1.1698753833770752,
      "learning_rate": 0.0002986833667334669,
      "loss": 8.788543701171875,
      "step": 320
    },
    {
      "epoch": 0.0066,
      "grad_norm": 1.353128433227539,
      "learning_rate": 0.00029862324649298594,
      "loss": 9.83536148071289,
      "step": 330
    },
    {
      "epoch": 0.0068,
      "grad_norm": 1.1758288145065308,
      "learning_rate": 0.000298563126252505,
      "loss": 11.545357513427735,
      "step": 340
    },
    {
      "epoch": 0.007,
      "grad_norm": 1.2862794399261475,
      "learning_rate": 0.00029850300601202403,
      "loss": 9.087370300292969,
      "step": 350
    },
    {
      "epoch": 0.0072,
      "grad_norm": 1.449062466621399,
      "learning_rate": 0.0002984428857715431,
      "loss": 11.168739318847656,
      "step": 360
    },
    {
      "epoch": 0.0074,
      "grad_norm": 0.5698562264442444,
      "learning_rate": 0.00029838276553106213,
      "loss": 7.454578399658203,
      "step": 370
    },
    {
      "epoch": 0.0076,
      "grad_norm": 0.9205979108810425,
      "learning_rate": 0.0002983226452905811,
      "loss": 11.321672058105468,
      "step": 380
    },
    {
      "epoch": 0.0078,
      "grad_norm": 0.8094843626022339,
      "learning_rate": 0.00029826252505010017,
      "loss": 9.661857604980469,
      "step": 390
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.9517568945884705,
      "learning_rate": 0.0002982024048096192,
      "loss": 7.4337646484375,
      "step": 400
    },
    {
      "epoch": 0.0082,
      "grad_norm": 28.707782745361328,
      "learning_rate": 0.00029814228456913827,
      "loss": 103.1381591796875,
      "step": 410
    },
    {
      "epoch": 0.0084,
      "grad_norm": 12.400252342224121,
      "learning_rate": 0.00029808216432865726,
      "loss": 83.130029296875,
      "step": 420
    },
    {
      "epoch": 0.0086,
      "grad_norm": 7.325169563293457,
      "learning_rate": 0.0002980220440881763,
      "loss": 73.54479370117187,
      "step": 430
    },
    {
      "epoch": 0.0088,
      "grad_norm": 11.358526229858398,
      "learning_rate": 0.00029796192384769535,
      "loss": 77.26640625,
      "step": 440
    },
    {
      "epoch": 0.009,
      "grad_norm": 8.655184745788574,
      "learning_rate": 0.0002979018036072144,
      "loss": 77.83007202148437,
      "step": 450
    },
    {
      "epoch": 0.0092,
      "grad_norm": 10.999149322509766,
      "learning_rate": 0.00029784168336673345,
      "loss": 78.61140747070313,
      "step": 460
    },
    {
      "epoch": 0.0094,
      "grad_norm": 9.994011878967285,
      "learning_rate": 0.0002977815631262525,
      "loss": 71.70507202148437,
      "step": 470
    },
    {
      "epoch": 0.0096,
      "grad_norm": 7.690250873565674,
      "learning_rate": 0.00029772144288577155,
      "loss": 73.41466674804687,
      "step": 480
    },
    {
      "epoch": 0.0098,
      "grad_norm": 9.543883323669434,
      "learning_rate": 0.00029766132264529054,
      "loss": 75.77626953125,
      "step": 490
    },
    {
      "epoch": 0.01,
      "grad_norm": 11.137728691101074,
      "learning_rate": 0.0002976012024048096,
      "loss": 78.9918212890625,
      "step": 500
    },
    {
      "epoch": 0.0102,
      "grad_norm": 15.467362403869629,
      "learning_rate": 0.00029754108216432863,
      "loss": 124.401513671875,
      "step": 510
    },
    {
      "epoch": 0.0104,
      "grad_norm": 13.991318702697754,
      "learning_rate": 0.0002974809619238477,
      "loss": 110.567431640625,
      "step": 520
    },
    {
      "epoch": 0.0106,
      "grad_norm": 17.036069869995117,
      "learning_rate": 0.0002974208416833667,
      "loss": 104.7319580078125,
      "step": 530
    },
    {
      "epoch": 0.0108,
      "grad_norm": 13.922304153442383,
      "learning_rate": 0.0002973607214428857,
      "loss": 100.63988647460937,
      "step": 540
    },
    {
      "epoch": 0.011,
      "grad_norm": 13.223531723022461,
      "learning_rate": 0.0002973006012024048,
      "loss": 99.96443481445313,
      "step": 550
    },
    {
      "epoch": 0.0112,
      "grad_norm": 14.53707504272461,
      "learning_rate": 0.0002972404809619238,
      "loss": 95.74251098632813,
      "step": 560
    },
    {
      "epoch": 0.0114,
      "grad_norm": 14.91770076751709,
      "learning_rate": 0.00029718036072144287,
      "loss": 94.661767578125,
      "step": 570
    },
    {
      "epoch": 0.0116,
      "grad_norm": 13.45614242553711,
      "learning_rate": 0.0002971202404809619,
      "loss": 90.941796875,
      "step": 580
    },
    {
      "epoch": 0.0118,
      "grad_norm": 13.695131301879883,
      "learning_rate": 0.00029706012024048096,
      "loss": 92.9096923828125,
      "step": 590
    },
    {
      "epoch": 0.012,
      "grad_norm": 16.406902313232422,
      "learning_rate": 0.00029699999999999996,
      "loss": 90.14566650390626,
      "step": 600
    },
    {
      "epoch": 0.0122,
      "grad_norm": 11.779080390930176,
      "learning_rate": 0.000296939879759519,
      "loss": 86.8746826171875,
      "step": 610
    },
    {
      "epoch": 0.0124,
      "grad_norm": 13.758212089538574,
      "learning_rate": 0.00029687975951903805,
      "loss": 87.3355224609375,
      "step": 620
    },
    {
      "epoch": 0.0126,
      "grad_norm": 12.833357810974121,
      "learning_rate": 0.0002968196392785571,
      "loss": 89.81148071289063,
      "step": 630
    },
    {
      "epoch": 0.0128,
      "grad_norm": 14.684094429016113,
      "learning_rate": 0.0002967595190380761,
      "loss": 89.44540405273438,
      "step": 640
    },
    {
      "epoch": 0.013,
      "grad_norm": 10.780083656311035,
      "learning_rate": 0.0002966993987975952,
      "loss": 88.07953491210938,
      "step": 650
    },
    {
      "epoch": 0.0132,
      "grad_norm": 11.908385276794434,
      "learning_rate": 0.0002966392785571142,
      "loss": 87.04054565429688,
      "step": 660
    },
    {
      "epoch": 0.0134,
      "grad_norm": 15.518954277038574,
      "learning_rate": 0.00029657915831663323,
      "loss": 85.9423583984375,
      "step": 670
    },
    {
      "epoch": 0.0136,
      "grad_norm": 10.570508003234863,
      "learning_rate": 0.0002965190380761523,
      "loss": 86.79979858398437,
      "step": 680
    },
    {
      "epoch": 0.0138,
      "grad_norm": 14.696393013000488,
      "learning_rate": 0.00029645891783567133,
      "loss": 79.76475219726562,
      "step": 690
    },
    {
      "epoch": 0.014,
      "grad_norm": 12.92392349243164,
      "learning_rate": 0.0002963987975951904,
      "loss": 87.0448974609375,
      "step": 700
    },
    {
      "epoch": 0.0142,
      "grad_norm": 13.465226173400879,
      "learning_rate": 0.00029633867735470937,
      "loss": 90.22592163085938,
      "step": 710
    },
    {
      "epoch": 0.0144,
      "grad_norm": 12.435464859008789,
      "learning_rate": 0.0002962785571142284,
      "loss": 86.32198486328124,
      "step": 720
    },
    {
      "epoch": 0.0146,
      "grad_norm": 12.340784072875977,
      "learning_rate": 0.00029621843687374747,
      "loss": 89.89630737304688,
      "step": 730
    },
    {
      "epoch": 0.0148,
      "grad_norm": 14.63569164276123,
      "learning_rate": 0.0002961583166332665,
      "loss": 86.31669921875,
      "step": 740
    },
    {
      "epoch": 0.015,
      "grad_norm": 10.646244049072266,
      "learning_rate": 0.00029609819639278556,
      "loss": 85.20569458007813,
      "step": 750
    },
    {
      "epoch": 0.0152,
      "grad_norm": 8.930062294006348,
      "learning_rate": 0.0002960380761523046,
      "loss": 86.44678955078125,
      "step": 760
    },
    {
      "epoch": 0.0154,
      "grad_norm": 12.228261947631836,
      "learning_rate": 0.0002959779559118236,
      "loss": 84.96986083984375,
      "step": 770
    },
    {
      "epoch": 0.0156,
      "grad_norm": 9.189741134643555,
      "learning_rate": 0.00029591783567134265,
      "loss": 86.03868408203125,
      "step": 780
    },
    {
      "epoch": 0.0158,
      "grad_norm": 12.331954956054688,
      "learning_rate": 0.0002958577154308617,
      "loss": 85.13253784179688,
      "step": 790
    },
    {
      "epoch": 0.016,
      "grad_norm": 14.345333099365234,
      "learning_rate": 0.00029579759519038075,
      "loss": 86.58322143554688,
      "step": 800
    },
    {
      "epoch": 0.0162,
      "grad_norm": 10.961579322814941,
      "learning_rate": 0.00029573747494989974,
      "loss": 84.83054809570312,
      "step": 810
    },
    {
      "epoch": 0.0164,
      "grad_norm": 11.578486442565918,
      "learning_rate": 0.0002956773547094188,
      "loss": 87.94888305664062,
      "step": 820
    },
    {
      "epoch": 0.0166,
      "grad_norm": 13.537806510925293,
      "learning_rate": 0.00029561723446893784,
      "loss": 87.522900390625,
      "step": 830
    },
    {
      "epoch": 0.0168,
      "grad_norm": 10.907570838928223,
      "learning_rate": 0.0002955571142284569,
      "loss": 84.80013427734374,
      "step": 840
    },
    {
      "epoch": 0.017,
      "grad_norm": 13.713836669921875,
      "learning_rate": 0.00029549699398797593,
      "loss": 86.79594116210937,
      "step": 850
    },
    {
      "epoch": 0.0172,
      "grad_norm": 12.571099281311035,
      "learning_rate": 0.000295436873747495,
      "loss": 84.85569458007812,
      "step": 860
    },
    {
      "epoch": 0.0174,
      "grad_norm": 9.433479309082031,
      "learning_rate": 0.000295376753507014,
      "loss": 85.20677490234375,
      "step": 870
    },
    {
      "epoch": 0.0176,
      "grad_norm": 12.85809326171875,
      "learning_rate": 0.000295316633266533,
      "loss": 79.00835571289062,
      "step": 880
    },
    {
      "epoch": 0.0178,
      "grad_norm": 11.075084686279297,
      "learning_rate": 0.00029525651302605207,
      "loss": 80.06212158203125,
      "step": 890
    },
    {
      "epoch": 0.018,
      "grad_norm": 14.64054012298584,
      "learning_rate": 0.0002951963927855711,
      "loss": 83.31229248046876,
      "step": 900
    },
    {
      "epoch": 0.0182,
      "grad_norm": 11.558423042297363,
      "learning_rate": 0.00029513627254509016,
      "loss": 78.82657470703126,
      "step": 910
    },
    {
      "epoch": 0.0184,
      "grad_norm": 22.44339942932129,
      "learning_rate": 0.00029507615230460916,
      "loss": 81.31973266601562,
      "step": 920
    },
    {
      "epoch": 0.0186,
      "grad_norm": 10.331223487854004,
      "learning_rate": 0.0002950160320641282,
      "loss": 83.343115234375,
      "step": 930
    },
    {
      "epoch": 0.0188,
      "grad_norm": 9.869694709777832,
      "learning_rate": 0.0002949559118236473,
      "loss": 79.85993041992188,
      "step": 940
    },
    {
      "epoch": 0.019,
      "grad_norm": 10.701475143432617,
      "learning_rate": 0.0002948957915831663,
      "loss": 84.02029418945312,
      "step": 950
    },
    {
      "epoch": 0.0192,
      "grad_norm": 12.234188079833984,
      "learning_rate": 0.00029483567134268535,
      "loss": 83.42827758789062,
      "step": 960
    },
    {
      "epoch": 0.0194,
      "grad_norm": 11.610219955444336,
      "learning_rate": 0.0002947755511022044,
      "loss": 80.161669921875,
      "step": 970
    },
    {
      "epoch": 0.0196,
      "grad_norm": 8.672530174255371,
      "learning_rate": 0.00029471543086172344,
      "loss": 81.43499145507812,
      "step": 980
    },
    {
      "epoch": 0.0198,
      "grad_norm": 11.546252250671387,
      "learning_rate": 0.00029465531062124244,
      "loss": 79.0343017578125,
      "step": 990
    },
    {
      "epoch": 0.02,
      "grad_norm": 11.632270812988281,
      "learning_rate": 0.0002945951903807615,
      "loss": 80.40287475585937,
      "step": 1000
    },
    {
      "epoch": 0.0202,
      "grad_norm": 10.527654647827148,
      "learning_rate": 0.00029453507014028053,
      "loss": 80.63410034179688,
      "step": 1010
    },
    {
      "epoch": 0.0204,
      "grad_norm": 15.636934280395508,
      "learning_rate": 0.0002944749498997996,
      "loss": 81.25313720703124,
      "step": 1020
    },
    {
      "epoch": 0.0206,
      "grad_norm": 8.874528884887695,
      "learning_rate": 0.00029441482965931857,
      "loss": 82.75345458984376,
      "step": 1030
    },
    {
      "epoch": 0.0208,
      "grad_norm": 9.90005874633789,
      "learning_rate": 0.0002943547094188377,
      "loss": 82.091015625,
      "step": 1040
    },
    {
      "epoch": 0.021,
      "grad_norm": 13.979220390319824,
      "learning_rate": 0.0002942945891783567,
      "loss": 78.61309814453125,
      "step": 1050
    },
    {
      "epoch": 0.0212,
      "grad_norm": 12.40916919708252,
      "learning_rate": 0.0002942344689378757,
      "loss": 77.57515258789063,
      "step": 1060
    },
    {
      "epoch": 0.0214,
      "grad_norm": 10.719722747802734,
      "learning_rate": 0.00029417434869739476,
      "loss": 81.308154296875,
      "step": 1070
    },
    {
      "epoch": 0.0216,
      "grad_norm": 11.862334251403809,
      "learning_rate": 0.0002941142284569138,
      "loss": 82.37334594726562,
      "step": 1080
    },
    {
      "epoch": 0.0218,
      "grad_norm": 9.369874954223633,
      "learning_rate": 0.00029405410821643286,
      "loss": 83.06602783203125,
      "step": 1090
    },
    {
      "epoch": 0.022,
      "grad_norm": 12.45842456817627,
      "learning_rate": 0.00029399398797595185,
      "loss": 80.74660034179688,
      "step": 1100
    },
    {
      "epoch": 0.0222,
      "grad_norm": 10.802011489868164,
      "learning_rate": 0.0002939338677354709,
      "loss": 82.18253784179687,
      "step": 1110
    },
    {
      "epoch": 0.0224,
      "grad_norm": 11.504124641418457,
      "learning_rate": 0.00029387374749498995,
      "loss": 82.32182006835937,
      "step": 1120
    },
    {
      "epoch": 0.0226,
      "grad_norm": 11.662162780761719,
      "learning_rate": 0.000293813627254509,
      "loss": 77.90712890625,
      "step": 1130
    },
    {
      "epoch": 0.0228,
      "grad_norm": 10.139030456542969,
      "learning_rate": 0.00029375350701402804,
      "loss": 80.47349853515625,
      "step": 1140
    },
    {
      "epoch": 0.023,
      "grad_norm": 10.677655220031738,
      "learning_rate": 0.0002936933867735471,
      "loss": 83.250830078125,
      "step": 1150
    },
    {
      "epoch": 0.0232,
      "grad_norm": 9.329009056091309,
      "learning_rate": 0.00029363326653306614,
      "loss": 78.31179809570312,
      "step": 1160
    },
    {
      "epoch": 0.0234,
      "grad_norm": 11.546579360961914,
      "learning_rate": 0.00029357314629258513,
      "loss": 84.429248046875,
      "step": 1170
    },
    {
      "epoch": 0.0236,
      "grad_norm": 11.815690040588379,
      "learning_rate": 0.0002935130260521042,
      "loss": 81.21365966796876,
      "step": 1180
    },
    {
      "epoch": 0.0238,
      "grad_norm": 11.184410095214844,
      "learning_rate": 0.0002934529058116232,
      "loss": 79.05919189453125,
      "step": 1190
    },
    {
      "epoch": 0.024,
      "grad_norm": 10.736798286437988,
      "learning_rate": 0.0002933927855711423,
      "loss": 80.73649291992187,
      "step": 1200
    },
    {
      "epoch": 0.0242,
      "grad_norm": 8.631206512451172,
      "learning_rate": 0.00029333266533066127,
      "loss": 78.77828979492188,
      "step": 1210
    },
    {
      "epoch": 0.0244,
      "grad_norm": 10.169127464294434,
      "learning_rate": 0.0002932725450901803,
      "loss": 75.32427978515625,
      "step": 1220
    },
    {
      "epoch": 0.0246,
      "grad_norm": 9.112273216247559,
      "learning_rate": 0.00029321242484969936,
      "loss": 80.11078491210938,
      "step": 1230
    },
    {
      "epoch": 0.0248,
      "grad_norm": 12.80979061126709,
      "learning_rate": 0.0002931523046092184,
      "loss": 80.26668090820313,
      "step": 1240
    },
    {
      "epoch": 0.025,
      "grad_norm": 11.88176155090332,
      "learning_rate": 0.00029309218436873746,
      "loss": 76.81950073242187,
      "step": 1250
    },
    {
      "epoch": 0.0252,
      "grad_norm": 9.650444984436035,
      "learning_rate": 0.0002930320641282565,
      "loss": 79.194091796875,
      "step": 1260
    },
    {
      "epoch": 0.0254,
      "grad_norm": 14.309748649597168,
      "learning_rate": 0.00029297194388777555,
      "loss": 76.17477416992188,
      "step": 1270
    },
    {
      "epoch": 0.0256,
      "grad_norm": 8.881438255310059,
      "learning_rate": 0.00029291182364729455,
      "loss": 76.45478515625,
      "step": 1280
    },
    {
      "epoch": 0.0258,
      "grad_norm": 13.313039779663086,
      "learning_rate": 0.0002928517034068136,
      "loss": 82.49783325195312,
      "step": 1290
    },
    {
      "epoch": 0.026,
      "grad_norm": 10.125815391540527,
      "learning_rate": 0.00029279158316633264,
      "loss": 74.025732421875,
      "step": 1300
    },
    {
      "epoch": 0.0262,
      "grad_norm": 9.924642562866211,
      "learning_rate": 0.0002927314629258517,
      "loss": 78.94208374023438,
      "step": 1310
    },
    {
      "epoch": 0.0264,
      "grad_norm": 12.754880905151367,
      "learning_rate": 0.0002926713426853707,
      "loss": 77.15728759765625,
      "step": 1320
    },
    {
      "epoch": 0.0266,
      "grad_norm": 10.190311431884766,
      "learning_rate": 0.0002926112224448898,
      "loss": 80.74267578125,
      "step": 1330
    },
    {
      "epoch": 0.0268,
      "grad_norm": 11.177680969238281,
      "learning_rate": 0.0002925511022044088,
      "loss": 76.56298828125,
      "step": 1340
    },
    {
      "epoch": 0.027,
      "grad_norm": 10.974754333496094,
      "learning_rate": 0.00029249098196392783,
      "loss": 77.54933471679688,
      "step": 1350
    },
    {
      "epoch": 0.0272,
      "grad_norm": 10.333001136779785,
      "learning_rate": 0.0002924308617234469,
      "loss": 76.95223999023438,
      "step": 1360
    },
    {
      "epoch": 0.0274,
      "grad_norm": 9.6028470993042,
      "learning_rate": 0.0002923707414829659,
      "loss": 76.2347900390625,
      "step": 1370
    },
    {
      "epoch": 0.0276,
      "grad_norm": 9.229351997375488,
      "learning_rate": 0.00029231062124248497,
      "loss": 84.37387084960938,
      "step": 1380
    },
    {
      "epoch": 0.0278,
      "grad_norm": 11.785066604614258,
      "learning_rate": 0.00029225050100200396,
      "loss": 77.95558471679688,
      "step": 1390
    },
    {
      "epoch": 0.028,
      "grad_norm": 8.809196472167969,
      "learning_rate": 0.000292190380761523,
      "loss": 75.076611328125,
      "step": 1400
    },
    {
      "epoch": 0.0282,
      "grad_norm": 13.894006729125977,
      "learning_rate": 0.00029213026052104206,
      "loss": 74.74369506835937,
      "step": 1410
    },
    {
      "epoch": 0.0284,
      "grad_norm": 11.996317863464355,
      "learning_rate": 0.0002920701402805611,
      "loss": 80.37234497070312,
      "step": 1420
    },
    {
      "epoch": 0.0286,
      "grad_norm": 9.478863716125488,
      "learning_rate": 0.00029201002004008015,
      "loss": 76.234619140625,
      "step": 1430
    },
    {
      "epoch": 0.0288,
      "grad_norm": 11.88571834564209,
      "learning_rate": 0.0002919498997995992,
      "loss": 82.56802368164062,
      "step": 1440
    },
    {
      "epoch": 0.029,
      "grad_norm": 10.63763427734375,
      "learning_rate": 0.0002918897795591182,
      "loss": 80.0512939453125,
      "step": 1450
    },
    {
      "epoch": 0.0292,
      "grad_norm": 12.671412467956543,
      "learning_rate": 0.00029182965931863724,
      "loss": 76.4797607421875,
      "step": 1460
    },
    {
      "epoch": 0.0294,
      "grad_norm": 11.89295482635498,
      "learning_rate": 0.0002917695390781563,
      "loss": 81.70416259765625,
      "step": 1470
    },
    {
      "epoch": 0.0296,
      "grad_norm": 10.384812355041504,
      "learning_rate": 0.00029170941883767534,
      "loss": 76.416650390625,
      "step": 1480
    },
    {
      "epoch": 0.0298,
      "grad_norm": 12.619583129882812,
      "learning_rate": 0.00029164929859719433,
      "loss": 82.743701171875,
      "step": 1490
    },
    {
      "epoch": 0.03,
      "grad_norm": 10.555590629577637,
      "learning_rate": 0.0002915891783567134,
      "loss": 77.63518676757812,
      "step": 1500
    },
    {
      "epoch": 1.0002,
      "grad_norm": NaN,
      "learning_rate": 0.00029152905811623243,
      "loss": 107136583467008.0,
      "step": 1510
    },
    {
      "epoch": 1.0004,
      "grad_norm": NaN,
      "learning_rate": 0.0002914689378757515,
      "loss": 3583383070310.4,
      "step": 1520
    },
    {
      "epoch": 1.0006,
      "grad_norm": NaN,
      "learning_rate": 0.0002914088176352705,
      "loss": 36528589478297.6,
      "step": 1530
    },
    {
      "epoch": 1.0008,
      "grad_norm": NaN,
      "learning_rate": 0.00029134869739478957,
      "loss": 1132657744281.6,
      "step": 1540
    },
    {
      "epoch": 1.001,
      "grad_norm": NaN,
      "learning_rate": 0.0002912885771543086,
      "loss": 9138627379.2,
      "step": 1550
    },
    {
      "epoch": 1.0012,
      "grad_norm": NaN,
      "learning_rate": 0.0002912284569138276,
      "loss": 1681122891975884.8,
      "step": 1560
    },
    {
      "epoch": 1.0014,
      "grad_norm": NaN,
      "learning_rate": 0.00029116833667334666,
      "loss": 929300570596966.4,
      "step": 1570
    },
    {
      "epoch": 1.0016,
      "grad_norm": NaN,
      "learning_rate": 0.0002911082164328657,
      "loss": 9330961573478.4,
      "step": 1580
    },
    {
      "epoch": 1.0018,
      "grad_norm": NaN,
      "learning_rate": 0.00029104809619238476,
      "loss": 63892658271027.2,
      "step": 1590
    },
    {
      "epoch": 1.002,
      "grad_norm": NaN,
      "learning_rate": 0.00029098797595190375,
      "loss": 3103321489408.0,
      "step": 1600
    }
  ],
  "logging_steps": 10,
  "max_steps": 50000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.66012131885056e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}