{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019517030517964842,
  "eval_steps": 1000,
  "global_step": 1457,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013395353821527004,
      "grad_norm": 4.978700160980225,
      "learning_rate": 8.035714285714286e-07,
      "loss": 1.4198334693908692,
      "step": 10
    },
    {
      "epoch": 0.0002679070764305401,
      "grad_norm": 3.940929412841797,
      "learning_rate": 1.6964285714285713e-06,
      "loss": 1.3955652236938476,
      "step": 20
    },
    {
      "epoch": 0.0004018606146458101,
      "grad_norm": 2.915323495864868,
      "learning_rate": 2.5892857142857148e-06,
      "loss": 1.3398881912231446,
      "step": 30
    },
    {
      "epoch": 0.0005358141528610801,
      "grad_norm": 2.512028932571411,
      "learning_rate": 3.4821428571428576e-06,
      "loss": 1.2956685066223144,
      "step": 40
    },
    {
      "epoch": 0.0006697676910763502,
      "grad_norm": 2.561004161834717,
      "learning_rate": 4.375e-06,
      "loss": 1.2670017242431642,
      "step": 50
    },
    {
      "epoch": 0.0008037212292916202,
      "grad_norm": 2.296826124191284,
      "learning_rate": 5.267857142857143e-06,
      "loss": 1.2354182243347167,
      "step": 60
    },
    {
      "epoch": 0.0009376747675068903,
      "grad_norm": 2.3733971118927,
      "learning_rate": 6.160714285714286e-06,
      "loss": 1.1916924476623536,
      "step": 70
    },
    {
      "epoch": 0.0010716283057221603,
      "grad_norm": 2.520475387573242,
      "learning_rate": 7.0535714285714286e-06,
      "loss": 1.1873969078063964,
      "step": 80
    },
    {
      "epoch": 0.0012055818439374302,
      "grad_norm": 2.4990739822387695,
      "learning_rate": 7.946428571428571e-06,
      "loss": 1.1627039909362793,
      "step": 90
    },
    {
      "epoch": 0.0013395353821527003,
      "grad_norm": 2.3932080268859863,
      "learning_rate": 8.839285714285716e-06,
      "loss": 1.1169233322143555,
      "step": 100
    },
    {
      "epoch": 0.0014734889203679704,
      "grad_norm": 2.6543712615966797,
      "learning_rate": 9.732142857142858e-06,
      "loss": 1.1316115379333496,
      "step": 110
    },
    {
      "epoch": 0.0016074424585832403,
      "grad_norm": 2.6352458000183105,
      "learning_rate": 1.0625e-05,
      "loss": 1.0918511390686034,
      "step": 120
    },
    {
      "epoch": 0.0017413959967985105,
      "grad_norm": 2.4628708362579346,
      "learning_rate": 1.1517857142857142e-05,
      "loss": 1.1151651382446288,
      "step": 130
    },
    {
      "epoch": 0.0018753495350137806,
      "grad_norm": 2.482074737548828,
      "learning_rate": 1.2410714285714287e-05,
      "loss": 1.094371223449707,
      "step": 140
    },
    {
      "epoch": 0.0020093030732290505,
      "grad_norm": 2.431954860687256,
      "learning_rate": 1.3303571428571429e-05,
      "loss": 1.0961938858032227,
      "step": 150
    },
    {
      "epoch": 0.0021432566114443206,
      "grad_norm": 2.8230552673339844,
      "learning_rate": 1.4196428571428572e-05,
      "loss": 1.083104705810547,
      "step": 160
    },
    {
      "epoch": 0.0022772101496595907,
      "grad_norm": 2.721494436264038,
      "learning_rate": 1.5089285714285714e-05,
      "loss": 1.0713379859924317,
      "step": 170
    },
    {
      "epoch": 0.0024111636878748604,
      "grad_norm": 2.3565499782562256,
      "learning_rate": 1.5982142857142857e-05,
      "loss": 1.099677276611328,
      "step": 180
    },
    {
      "epoch": 0.0025451172260901305,
      "grad_norm": 2.345555543899536,
      "learning_rate": 1.6875000000000004e-05,
      "loss": 1.0562498092651367,
      "step": 190
    },
    {
      "epoch": 0.0026790707643054006,
      "grad_norm": 2.381127119064331,
      "learning_rate": 1.7767857142857143e-05,
      "loss": 1.0502027511596679,
      "step": 200
    },
    {
      "epoch": 0.0028130243025206707,
      "grad_norm": 2.4133875370025635,
      "learning_rate": 1.8660714285714287e-05,
      "loss": 1.0681496620178224,
      "step": 210
    },
    {
      "epoch": 0.002946977840735941,
      "grad_norm": 2.5238466262817383,
      "learning_rate": 1.955357142857143e-05,
      "loss": 1.0440272331237792,
      "step": 220
    },
    {
      "epoch": 0.003080931378951211,
      "grad_norm": 2.7593183517456055,
      "learning_rate": 2.0446428571428573e-05,
      "loss": 1.0714456558227539,
      "step": 230
    },
    {
      "epoch": 0.0032148849171664807,
      "grad_norm": 2.5562100410461426,
      "learning_rate": 2.1339285714285713e-05,
      "loss": 1.0298255920410155,
      "step": 240
    },
    {
      "epoch": 0.003348838455381751,
      "grad_norm": 2.6205103397369385,
      "learning_rate": 2.2232142857142856e-05,
      "loss": 1.050998592376709,
      "step": 250
    },
    {
      "epoch": 0.003482791993597021,
      "grad_norm": 2.5965018272399902,
      "learning_rate": 2.3125000000000003e-05,
      "loss": 1.0283641815185547,
      "step": 260
    },
    {
      "epoch": 0.003616745531812291,
      "grad_norm": 2.3729209899902344,
      "learning_rate": 2.4017857142857146e-05,
      "loss": 1.0502397537231445,
      "step": 270
    },
    {
      "epoch": 0.003750699070027561,
      "grad_norm": 2.378077983856201,
      "learning_rate": 2.4910714285714286e-05,
      "loss": 1.0391980171203614,
      "step": 280
    },
    {
      "epoch": 0.003884652608242831,
      "grad_norm": 2.4107515811920166,
      "learning_rate": 2.5803571428571433e-05,
      "loss": 1.0300152778625489,
      "step": 290
    },
    {
      "epoch": 0.004018606146458101,
      "grad_norm": 2.4866559505462646,
      "learning_rate": 2.6696428571428573e-05,
      "loss": 1.0498000144958497,
      "step": 300
    },
    {
      "epoch": 0.004152559684673371,
      "grad_norm": 2.3568379878997803,
      "learning_rate": 2.7589285714285716e-05,
      "loss": 1.0401558876037598,
      "step": 310
    },
    {
      "epoch": 0.004286513222888641,
      "grad_norm": 2.456519603729248,
      "learning_rate": 2.8482142857142856e-05,
      "loss": 1.0105724334716797,
      "step": 320
    },
    {
      "epoch": 0.004420466761103911,
      "grad_norm": 2.8484723567962646,
      "learning_rate": 2.9375000000000003e-05,
      "loss": 1.0271486282348632,
      "step": 330
    },
    {
      "epoch": 0.004554420299319181,
      "grad_norm": 2.829651117324829,
      "learning_rate": 3.0267857142857142e-05,
      "loss": 1.0125882148742675,
      "step": 340
    },
    {
      "epoch": 0.0046883738375344515,
      "grad_norm": 1.9819118976593018,
      "learning_rate": 3.116071428571429e-05,
      "loss": 1.0134092330932618,
      "step": 350
    },
    {
      "epoch": 0.004822327375749721,
      "grad_norm": 2.5545337200164795,
      "learning_rate": 3.205357142857143e-05,
      "loss": 1.006214714050293,
      "step": 360
    },
    {
      "epoch": 0.004956280913964991,
      "grad_norm": 2.3971850872039795,
      "learning_rate": 3.2946428571428576e-05,
      "loss": 1.014259147644043,
      "step": 370
    },
    {
      "epoch": 0.005090234452180261,
      "grad_norm": 2.188464641571045,
      "learning_rate": 3.383928571428572e-05,
      "loss": 1.0164517402648925,
      "step": 380
    },
    {
      "epoch": 0.005224187990395531,
      "grad_norm": 2.607635021209717,
      "learning_rate": 3.4732142857142855e-05,
      "loss": 1.0006816864013672,
      "step": 390
    },
    {
      "epoch": 0.005358141528610801,
      "grad_norm": 1.9828215837478638,
      "learning_rate": 3.5625000000000005e-05,
      "loss": 0.994498348236084,
      "step": 400
    },
    {
      "epoch": 0.005492095066826071,
      "grad_norm": 2.0254552364349365,
      "learning_rate": 3.651785714285714e-05,
      "loss": 1.0143715858459472,
      "step": 410
    },
    {
      "epoch": 0.0056260486050413415,
      "grad_norm": 2.088826894760132,
      "learning_rate": 3.7410714285714285e-05,
      "loss": 1.003225040435791,
      "step": 420
    },
    {
      "epoch": 0.005760002143256612,
      "grad_norm": 2.4125075340270996,
      "learning_rate": 3.8303571428571435e-05,
      "loss": 0.9795364379882813,
      "step": 430
    },
    {
      "epoch": 0.005893955681471882,
      "grad_norm": 2.0874435901641846,
      "learning_rate": 3.919642857142857e-05,
      "loss": 0.9827790260314941,
      "step": 440
    },
    {
      "epoch": 0.006027909219687152,
      "grad_norm": 1.7993626594543457,
      "learning_rate": 4.0089285714285715e-05,
      "loss": 0.992791748046875,
      "step": 450
    },
    {
      "epoch": 0.006161862757902422,
      "grad_norm": 2.1616885662078857,
      "learning_rate": 4.098214285714286e-05,
      "loss": 0.9879550933837891,
      "step": 460
    },
    {
      "epoch": 0.006295816296117691,
      "grad_norm": 2.0187010765075684,
      "learning_rate": 4.1875e-05,
      "loss": 0.9812018394470214,
      "step": 470
    },
    {
      "epoch": 0.006429769834332961,
      "grad_norm": 2.0268852710723877,
      "learning_rate": 4.2767857142857145e-05,
      "loss": 1.017441749572754,
      "step": 480
    },
    {
      "epoch": 0.0065637233725482315,
      "grad_norm": 2.1466526985168457,
      "learning_rate": 4.366071428571429e-05,
      "loss": 0.9769362449645996,
      "step": 490
    },
    {
      "epoch": 0.006697676910763502,
      "grad_norm": 2.0106499195098877,
      "learning_rate": 4.455357142857143e-05,
      "loss": 0.9902260780334473,
      "step": 500
    },
    {
      "epoch": 0.006831630448978772,
      "grad_norm": 1.843783974647522,
      "learning_rate": 4.5446428571428574e-05,
      "loss": 1.0007816314697267,
      "step": 510
    },
    {
      "epoch": 0.006965583987194042,
      "grad_norm": 1.8174176216125488,
      "learning_rate": 4.633928571428572e-05,
      "loss": 0.9792203903198242,
      "step": 520
    },
    {
      "epoch": 0.007099537525409312,
      "grad_norm": 1.8151051998138428,
      "learning_rate": 4.723214285714286e-05,
      "loss": 0.992054557800293,
      "step": 530
    },
    {
      "epoch": 0.007233491063624582,
      "grad_norm": 1.7471234798431396,
      "learning_rate": 4.8125000000000004e-05,
      "loss": 0.9979231834411622,
      "step": 540
    },
    {
      "epoch": 0.007367444601839852,
      "grad_norm": 1.7692842483520508,
      "learning_rate": 4.901785714285714e-05,
      "loss": 0.9751591682434082,
      "step": 550
    },
    {
      "epoch": 0.007501398140055122,
      "grad_norm": 1.6787338256835938,
      "learning_rate": 4.991071428571429e-05,
      "loss": 0.9884813308715821,
      "step": 560
    },
    {
      "epoch": 0.0076353516782703915,
      "grad_norm": 1.7012407779693604,
      "learning_rate": 5.080357142857143e-05,
      "loss": 0.9855763435363769,
      "step": 570
    },
    {
      "epoch": 0.007769305216485662,
      "grad_norm": 1.915123701095581,
      "learning_rate": 5.169642857142858e-05,
      "loss": 0.9511891365051269,
      "step": 580
    },
    {
      "epoch": 0.007903258754700932,
      "grad_norm": 1.833243727684021,
      "learning_rate": 5.258928571428572e-05,
      "loss": 0.9984745025634766,
      "step": 590
    },
    {
      "epoch": 0.008037212292916202,
      "grad_norm": 1.450955867767334,
      "learning_rate": 5.348214285714286e-05,
      "loss": 0.9740289688110352,
      "step": 600
    },
    {
      "epoch": 0.008171165831131472,
      "grad_norm": 1.7209330797195435,
      "learning_rate": 5.4375e-05,
      "loss": 0.9547987937927246,
      "step": 610
    },
    {
      "epoch": 0.008305119369346742,
      "grad_norm": 1.7298052310943604,
      "learning_rate": 5.526785714285715e-05,
      "loss": 0.9855975151062012,
      "step": 620
    },
    {
      "epoch": 0.008439072907562012,
      "grad_norm": 1.6286202669143677,
      "learning_rate": 5.616071428571429e-05,
      "loss": 0.9657292366027832,
      "step": 630
    },
    {
      "epoch": 0.008573026445777282,
      "grad_norm": 2.2121224403381348,
      "learning_rate": 5.705357142857143e-05,
      "loss": 0.9826187133789063,
      "step": 640
    },
    {
      "epoch": 0.008706979983992552,
      "grad_norm": 1.4359034299850464,
      "learning_rate": 5.794642857142858e-05,
      "loss": 0.9880683898925782,
      "step": 650
    },
    {
      "epoch": 0.008840933522207823,
      "grad_norm": 1.8250757455825806,
      "learning_rate": 5.883928571428572e-05,
      "loss": 0.9728729248046875,
      "step": 660
    },
    {
      "epoch": 0.008974887060423093,
      "grad_norm": 1.6160730123519897,
      "learning_rate": 5.973214285714286e-05,
      "loss": 0.9673951148986817,
      "step": 670
    },
    {
      "epoch": 0.009108840598638363,
      "grad_norm": 1.623353362083435,
      "learning_rate": 6.0624999999999996e-05,
      "loss": 0.9910868644714356,
      "step": 680
    },
    {
      "epoch": 0.009242794136853633,
      "grad_norm": 1.7099947929382324,
      "learning_rate": 6.151785714285715e-05,
      "loss": 0.9758204460144043,
      "step": 690
    },
    {
      "epoch": 0.009376747675068903,
      "grad_norm": 1.6103285551071167,
      "learning_rate": 6.241071428571428e-05,
      "loss": 0.9683603286743164,
      "step": 700
    },
    {
      "epoch": 0.009510701213284173,
      "grad_norm": 1.703170895576477,
      "learning_rate": 6.330357142857143e-05,
      "loss": 0.959897232055664,
      "step": 710
    },
    {
      "epoch": 0.009644654751499442,
      "grad_norm": 1.662630319595337,
      "learning_rate": 6.419642857142858e-05,
      "loss": 0.9767607688903809,
      "step": 720
    },
    {
      "epoch": 0.009778608289714712,
      "grad_norm": 1.5833293199539185,
      "learning_rate": 6.508928571428571e-05,
      "loss": 0.9608363151550293,
      "step": 730
    },
    {
      "epoch": 0.009912561827929982,
      "grad_norm": 1.7040482759475708,
      "learning_rate": 6.598214285714286e-05,
      "loss": 0.9693010330200196,
      "step": 740
    },
    {
      "epoch": 0.010046515366145252,
      "grad_norm": 1.505820393562317,
      "learning_rate": 6.6875e-05,
      "loss": 0.9575628280639649,
      "step": 750
    },
    {
      "epoch": 0.010180468904360522,
      "grad_norm": 1.812294602394104,
      "learning_rate": 6.776785714285716e-05,
      "loss": 0.9544397354125976,
      "step": 760
    },
    {
      "epoch": 0.010314422442575792,
      "grad_norm": 1.6276874542236328,
      "learning_rate": 6.866071428571429e-05,
      "loss": 0.9317039489746094,
      "step": 770
    },
    {
      "epoch": 0.010448375980791062,
      "grad_norm": 1.6243042945861816,
      "learning_rate": 6.955357142857143e-05,
      "loss": 0.9851680755615234,
      "step": 780
    },
    {
      "epoch": 0.010582329519006332,
      "grad_norm": 1.5983399152755737,
      "learning_rate": 7.044642857142859e-05,
      "loss": 0.9748747825622559,
      "step": 790
    },
    {
      "epoch": 0.010716283057221603,
      "grad_norm": 1.7678436040878296,
      "learning_rate": 7.133928571428572e-05,
      "loss": 0.9590046882629395,
      "step": 800
    },
    {
      "epoch": 0.010850236595436873,
      "grad_norm": 1.5059410333633423,
      "learning_rate": 7.223214285714286e-05,
      "loss": 0.9823746681213379,
      "step": 810
    },
    {
      "epoch": 0.010984190133652143,
      "grad_norm": 1.4575616121292114,
      "learning_rate": 7.3125e-05,
      "loss": 0.9733425140380859,
      "step": 820
    },
    {
      "epoch": 0.011118143671867413,
      "grad_norm": 1.6164171695709229,
      "learning_rate": 7.401785714285715e-05,
      "loss": 0.927185344696045,
      "step": 830
    },
    {
      "epoch": 0.011252097210082683,
      "grad_norm": 1.512903094291687,
      "learning_rate": 7.491071428571429e-05,
      "loss": 0.9673010826110839,
      "step": 840
    },
    {
      "epoch": 0.011386050748297953,
      "grad_norm": 1.4509457349777222,
      "learning_rate": 7.580357142857143e-05,
      "loss": 0.9444644927978516,
      "step": 850
    },
    {
      "epoch": 0.011520004286513223,
      "grad_norm": 1.3291261196136475,
      "learning_rate": 7.669642857142858e-05,
      "loss": 0.9484622001647949,
      "step": 860
    },
    {
      "epoch": 0.011653957824728493,
      "grad_norm": 1.6370415687561035,
      "learning_rate": 7.758928571428572e-05,
      "loss": 0.9409455299377442,
      "step": 870
    },
    {
      "epoch": 0.011787911362943763,
      "grad_norm": 1.5580850839614868,
      "learning_rate": 7.848214285714286e-05,
      "loss": 0.9556178092956543,
      "step": 880
    },
    {
      "epoch": 0.011921864901159034,
      "grad_norm": 1.4624580144882202,
      "learning_rate": 7.9375e-05,
      "loss": 0.9679806709289551,
      "step": 890
    },
    {
      "epoch": 0.012055818439374304,
      "grad_norm": 1.5962079763412476,
      "learning_rate": 8.026785714285715e-05,
      "loss": 0.9726933479309082,
      "step": 900
    },
    {
      "epoch": 0.012189771977589574,
      "grad_norm": 1.3573912382125854,
      "learning_rate": 8.116071428571429e-05,
      "loss": 0.9682340621948242,
      "step": 910
    },
    {
      "epoch": 0.012323725515804844,
      "grad_norm": 1.5596022605895996,
      "learning_rate": 8.205357142857143e-05,
      "loss": 0.9629892349243164,
      "step": 920
    },
    {
      "epoch": 0.012457679054020112,
      "grad_norm": 1.730648398399353,
      "learning_rate": 8.294642857142858e-05,
      "loss": 0.9566517829895019,
      "step": 930
    },
    {
      "epoch": 0.012591632592235382,
      "grad_norm": 1.5507956743240356,
      "learning_rate": 8.383928571428572e-05,
      "loss": 0.9654373168945313,
      "step": 940
    },
    {
      "epoch": 0.012725586130450653,
      "grad_norm": 1.4160267114639282,
      "learning_rate": 8.473214285714286e-05,
      "loss": 0.9531091690063477,
      "step": 950
    },
    {
      "epoch": 0.012859539668665923,
      "grad_norm": 1.617100477218628,
      "learning_rate": 8.5625e-05,
      "loss": 0.9591686248779296,
      "step": 960
    },
    {
      "epoch": 0.012993493206881193,
      "grad_norm": 1.296432375907898,
      "learning_rate": 8.651785714285715e-05,
      "loss": 0.971707534790039,
      "step": 970
    },
    {
      "epoch": 0.013127446745096463,
      "grad_norm": 1.402993083000183,
      "learning_rate": 8.74107142857143e-05,
      "loss": 0.9584191322326661,
      "step": 980
    },
    {
      "epoch": 0.013261400283311733,
      "grad_norm": 1.4196568727493286,
      "learning_rate": 8.830357142857142e-05,
      "loss": 0.9672185897827148,
      "step": 990
    },
    {
      "epoch": 0.013395353821527003,
      "grad_norm": 1.3073877096176147,
      "learning_rate": 8.919642857142858e-05,
      "loss": 0.9563102722167969,
      "step": 1000
    },
    {
      "epoch": 0.013395353821527003,
      "eval_loss": 0.9335520267486572,
      "eval_runtime": 282.864,
      "eval_samples_per_second": 10.652,
      "eval_steps_per_second": 10.652,
      "step": 1000
    },
    {
      "epoch": 0.013529307359742273,
      "grad_norm": 1.2876602411270142,
      "learning_rate": 9.008928571428572e-05,
      "loss": 0.9841785430908203,
      "step": 1010
    },
    {
      "epoch": 0.013663260897957543,
      "grad_norm": 1.302293062210083,
      "learning_rate": 9.098214285714285e-05,
      "loss": 0.9624536514282227,
      "step": 1020
    },
    {
      "epoch": 0.013797214436172813,
      "grad_norm": 1.4643065929412842,
      "learning_rate": 9.1875e-05,
      "loss": 0.9604171752929688,
      "step": 1030
    },
    {
      "epoch": 0.013931167974388084,
      "grad_norm": 1.5588184595108032,
      "learning_rate": 9.276785714285715e-05,
      "loss": 0.9482678413391114,
      "step": 1040
    },
    {
      "epoch": 0.014065121512603354,
      "grad_norm": 1.3061965703964233,
      "learning_rate": 9.36607142857143e-05,
      "loss": 0.9968178749084473,
      "step": 1050
    },
    {
      "epoch": 0.014199075050818624,
      "grad_norm": 1.49628746509552,
      "learning_rate": 9.455357142857143e-05,
      "loss": 0.965756893157959,
      "step": 1060
    },
    {
      "epoch": 0.014333028589033894,
      "grad_norm": 1.5427523851394653,
      "learning_rate": 9.544642857142858e-05,
      "loss": 0.9401347160339355,
      "step": 1070
    },
    {
      "epoch": 0.014466982127249164,
      "grad_norm": 1.44222891330719,
      "learning_rate": 9.633928571428573e-05,
      "loss": 0.9700592994689942,
      "step": 1080
    },
    {
      "epoch": 0.014600935665464434,
      "grad_norm": 1.2180535793304443,
      "learning_rate": 9.723214285714286e-05,
      "loss": 0.9597712516784668,
      "step": 1090
    },
    {
      "epoch": 0.014734889203679704,
      "grad_norm": 1.4644688367843628,
      "learning_rate": 9.8125e-05,
      "loss": 0.9620055198669434,
      "step": 1100
    },
    {
      "epoch": 0.014868842741894974,
      "grad_norm": 1.4942972660064697,
      "learning_rate": 9.901785714285716e-05,
      "loss": 0.9615335464477539,
      "step": 1110
    },
    {
      "epoch": 0.015002796280110245,
      "grad_norm": 1.1068652868270874,
      "learning_rate": 9.991071428571429e-05,
      "loss": 0.9622197151184082,
      "step": 1120
    },
    {
      "epoch": 0.015136749818325513,
      "grad_norm": 1.283275842666626,
      "learning_rate": 0.00010080357142857144,
      "loss": 0.9707681655883789,
      "step": 1130
    },
    {
      "epoch": 0.015270703356540783,
      "grad_norm": 1.197508454322815,
      "learning_rate": 0.00010169642857142859,
      "loss": 0.9689389228820801,
      "step": 1140
    },
    {
      "epoch": 0.015404656894756053,
      "grad_norm": 1.2500603199005127,
      "learning_rate": 0.00010258928571428572,
      "loss": 0.9651185035705566,
      "step": 1150
    },
    {
      "epoch": 0.015538610432971323,
      "grad_norm": 1.6802270412445068,
      "learning_rate": 0.00010348214285714286,
      "loss": 0.9665432929992676,
      "step": 1160
    },
    {
      "epoch": 0.015672563971186593,
      "grad_norm": 1.4018360376358032,
      "learning_rate": 0.000104375,
      "loss": 0.9392754554748535,
      "step": 1170
    },
    {
      "epoch": 0.015806517509401864,
      "grad_norm": 1.5453063249588013,
      "learning_rate": 0.00010526785714285715,
      "loss": 0.9618069648742675,
      "step": 1180
    },
    {
      "epoch": 0.015940471047617134,
      "grad_norm": 1.2306983470916748,
      "learning_rate": 0.00010616071428571428,
      "loss": 0.940494441986084,
      "step": 1190
    },
    {
      "epoch": 0.016074424585832404,
      "grad_norm": 1.1923718452453613,
      "learning_rate": 0.00010705357142857145,
      "loss": 0.9696602821350098,
      "step": 1200
    },
    {
      "epoch": 0.016208378124047674,
      "grad_norm": 1.3687347173690796,
      "learning_rate": 0.00010794642857142858,
      "loss": 0.9562197685241699,
      "step": 1210
    },
    {
      "epoch": 0.016342331662262944,
      "grad_norm": 1.3242262601852417,
      "learning_rate": 0.00010883928571428572,
      "loss": 0.941429328918457,
      "step": 1220
    },
    {
      "epoch": 0.016476285200478214,
      "grad_norm": 1.2945473194122314,
      "learning_rate": 0.00010973214285714286,
      "loss": 0.9632730484008789,
      "step": 1230
    },
    {
      "epoch": 0.016610238738693484,
      "grad_norm": 1.1794791221618652,
      "learning_rate": 0.000110625,
      "loss": 0.9528386116027832,
      "step": 1240
    },
    {
      "epoch": 0.016744192276908754,
      "grad_norm": 1.261305570602417,
      "learning_rate": 0.00011151785714285714,
      "loss": 0.945485782623291,
      "step": 1250
    },
    {
      "epoch": 0.016878145815124024,
      "grad_norm": 1.310412883758545,
      "learning_rate": 0.00011241071428571428,
      "loss": 0.9500171661376953,
      "step": 1260
    },
    {
      "epoch": 0.017012099353339295,
      "grad_norm": 1.4417651891708374,
      "learning_rate": 0.00011330357142857145,
      "loss": 0.965580940246582,
      "step": 1270
    },
    {
      "epoch": 0.017146052891554565,
      "grad_norm": 1.2227723598480225,
      "learning_rate": 0.00011419642857142858,
      "loss": 0.9576460838317871,
      "step": 1280
    },
    {
      "epoch": 0.017280006429769835,
      "grad_norm": 1.278008222579956,
      "learning_rate": 0.00011508928571428572,
      "loss": 0.9216486930847168,
      "step": 1290
    },
    {
      "epoch": 0.017413959967985105,
      "grad_norm": 1.2406392097473145,
      "learning_rate": 0.00011598214285714287,
      "loss": 0.9882441520690918,
      "step": 1300
    },
    {
      "epoch": 0.017547913506200375,
      "grad_norm": 1.2370669841766357,
      "learning_rate": 0.000116875,
      "loss": 0.9419057846069336,
      "step": 1310
    },
    {
      "epoch": 0.017681867044415645,
      "grad_norm": 1.1850550174713135,
      "learning_rate": 0.00011776785714285714,
      "loss": 0.976494026184082,
      "step": 1320
    },
    {
      "epoch": 0.017815820582630915,
      "grad_norm": 1.1672782897949219,
      "learning_rate": 0.00011866071428571428,
      "loss": 0.9599658012390136,
      "step": 1330
    },
    {
      "epoch": 0.017949774120846185,
      "grad_norm": 1.2031351327896118,
      "learning_rate": 0.00011955357142857144,
      "loss": 0.9466784477233887,
      "step": 1340
    },
    {
      "epoch": 0.018083727659061456,
      "grad_norm": 1.423079013824463,
      "learning_rate": 0.00012044642857142858,
      "loss": 0.9467257499694824,
      "step": 1350
    },
    {
      "epoch": 0.018217681197276726,
      "grad_norm": 1.3132128715515137,
      "learning_rate": 0.00012133928571428572,
      "loss": 0.95529203414917,
      "step": 1360
    },
    {
      "epoch": 0.018351634735491996,
      "grad_norm": 1.3859386444091797,
      "learning_rate": 0.00012223214285714287,
      "loss": 0.9389223098754883,
      "step": 1370
    },
    {
      "epoch": 0.018485588273707266,
      "grad_norm": 1.1685659885406494,
      "learning_rate": 0.000123125,
      "loss": 0.94387845993042,
      "step": 1380
    },
    {
      "epoch": 0.018619541811922536,
      "grad_norm": 1.2127257585525513,
      "learning_rate": 0.00012401785714285715,
      "loss": 0.918062400817871,
      "step": 1390
    },
    {
      "epoch": 0.018753495350137806,
      "grad_norm": 1.1995147466659546,
      "learning_rate": 0.00012491071428571428,
      "loss": 0.9396192550659179,
      "step": 1400
    },
    {
      "epoch": 0.018887448888353076,
      "grad_norm": 1.2880109548568726,
      "learning_rate": 0.00012580357142857144,
      "loss": 0.9649562835693359,
      "step": 1410
    },
    {
      "epoch": 0.019021402426568346,
      "grad_norm": 1.2551807165145874,
      "learning_rate": 0.00012669642857142857,
      "loss": 0.9511116027832032,
      "step": 1420
    },
    {
      "epoch": 0.019155355964783616,
      "grad_norm": 1.184615135192871,
      "learning_rate": 0.00012758928571428573,
      "loss": 0.9791507720947266,
      "step": 1430
    },
    {
      "epoch": 0.019289309502998883,
      "grad_norm": 1.1787488460540771,
      "learning_rate": 0.00012848214285714286,
      "loss": 0.9635199546813965,
      "step": 1440
    },
    {
      "epoch": 0.019423263041214153,
      "grad_norm": 1.0999921560287476,
      "learning_rate": 0.00012937500000000001,
      "loss": 0.9462879180908204,
      "step": 1450
    }
  ],
  "logging_steps": 10,
  "max_steps": 74653,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1231563344972826e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}