{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14417531718569782,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014417531718569781,
      "grad_norm": 1584.0,
      "kd_loss": 1.4788804054260254,
      "learning_rate": 4.444444444444445e-07,
      "loss": 2.2647,
      "step": 5,
      "student_loss": 0.12291660904884338,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0028835063437139563,
      "grad_norm": 796.0,
      "kd_loss": 1.487825870513916,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.9392,
      "step": 10,
      "student_loss": 0.198484867811203,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.004325259515570935,
      "grad_norm": 260.0,
      "kd_loss": 0.07314793765544891,
      "learning_rate": 1.5555555555555558e-06,
      "loss": 1.2376,
      "step": 15,
      "student_loss": 0.08613421022891998,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0057670126874279125,
      "grad_norm": 85.0,
      "kd_loss": 0.023559529334306717,
      "learning_rate": 2.1111111111111114e-06,
      "loss": 0.6343,
      "step": 20,
      "student_loss": 0.23392575979232788,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.00720876585928489,
      "grad_norm": 33.75,
      "kd_loss": 0.0026166969910264015,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.6107,
      "step": 25,
      "student_loss": 0.2554866075515747,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.00865051903114187,
      "grad_norm": 24.125,
      "kd_loss": 0.022094376385211945,
      "learning_rate": 3.2222222222222227e-06,
      "loss": 0.498,
      "step": 30,
      "student_loss": 0.2493494749069214,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.010092272202998846,
      "grad_norm": 39.0,
      "kd_loss": 0.04670819640159607,
      "learning_rate": 3.777777777777778e-06,
      "loss": 0.3781,
      "step": 35,
      "student_loss": 0.13782167434692383,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.011534025374855825,
      "grad_norm": 18.125,
      "kd_loss": 0.24180860817432404,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.3341,
      "step": 40,
      "student_loss": 0.09410303086042404,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.012975778546712802,
      "grad_norm": 20.25,
      "kd_loss": 0.4184195101261139,
      "learning_rate": 4.888888888888889e-06,
      "loss": 0.2388,
      "step": 45,
      "student_loss": 0.09438568353652954,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.01441753171856978,
      "grad_norm": 32.75,
      "kd_loss": 0.8934061527252197,
      "learning_rate": 5.444444444444445e-06,
      "loss": 0.3727,
      "step": 50,
      "student_loss": 0.020176472142338753,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.015859284890426758,
      "grad_norm": 28.5,
      "kd_loss": 0.018707511946558952,
      "learning_rate": 6e-06,
      "loss": 0.2167,
      "step": 55,
      "student_loss": 0.0011619763681665063,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.01730103806228374,
      "grad_norm": 27.25,
      "kd_loss": 0.007137665059417486,
      "learning_rate": 6.555555555555556e-06,
      "loss": 0.1682,
      "step": 60,
      "student_loss": 0.001694640377536416,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.018742791234140715,
      "grad_norm": 15.75,
      "kd_loss": 0.0016208974411711097,
      "learning_rate": 7.111111111111112e-06,
      "loss": 0.1815,
      "step": 65,
      "student_loss": 0.029718520119786263,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.020184544405997693,
      "grad_norm": 12.1875,
      "kd_loss": 0.2541334331035614,
      "learning_rate": 7.666666666666667e-06,
      "loss": 0.1369,
      "step": 70,
      "student_loss": 0.010810595005750656,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02162629757785467,
      "grad_norm": 18.375,
      "kd_loss": 0.007482057902961969,
      "learning_rate": 8.222222222222222e-06,
      "loss": 0.2322,
      "step": 75,
      "student_loss": 0.00097510009072721,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02306805074971165,
      "grad_norm": 10.3125,
      "kd_loss": 0.006171244662255049,
      "learning_rate": 8.777777777777778e-06,
      "loss": 0.1828,
      "step": 80,
      "student_loss": 0.000972377136349678,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.024509803921568627,
      "grad_norm": 18.125,
      "kd_loss": 0.005768964998424053,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.1856,
      "step": 85,
      "student_loss": 0.0005292362766340375,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.025951557093425604,
      "grad_norm": 5.65625,
      "kd_loss": 0.060487739741802216,
      "learning_rate": 9.88888888888889e-06,
      "loss": 0.1726,
      "step": 90,
      "student_loss": 0.007604286074638367,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.027393310265282585,
      "grad_norm": 13.5625,
      "kd_loss": 0.01542923878878355,
      "learning_rate": 9.99995337991255e-06,
      "loss": 0.1586,
      "step": 95,
      "student_loss": 0.015073101036250591,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02883506343713956,
      "grad_norm": 15.8125,
      "kd_loss": 0.0029005378019064665,
      "learning_rate": 9.999763987297266e-06,
      "loss": 0.1247,
      "step": 100,
      "student_loss": 0.0006029795622453094,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03027681660899654,
      "grad_norm": 15.375,
      "kd_loss": 0.007598078344017267,
      "learning_rate": 9.999428913912876e-06,
      "loss": 0.1266,
      "step": 105,
      "student_loss": 0.003934374079108238,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.031718569780853516,
      "grad_norm": 16.0,
      "kd_loss": 0.00252303434535861,
      "learning_rate": 9.998948169522587e-06,
      "loss": 0.1767,
      "step": 110,
      "student_loss": 0.04128251224756241,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03316032295271049,
      "grad_norm": 13.3125,
      "kd_loss": 0.19726258516311646,
      "learning_rate": 9.998321768134101e-06,
      "loss": 0.1655,
      "step": 115,
      "student_loss": 0.001500162878073752,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03460207612456748,
      "grad_norm": 5.875,
      "kd_loss": 0.008542308583855629,
      "learning_rate": 9.997549727999212e-06,
      "loss": 0.0858,
      "step": 120,
      "student_loss": 0.0007994729094207287,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.036043829296424454,
      "grad_norm": 14.875,
      "kd_loss": 0.7844982743263245,
      "learning_rate": 9.996632071613257e-06,
      "loss": 0.1328,
      "step": 125,
      "student_loss": 0.029885753989219666,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03748558246828143,
      "grad_norm": 14.0625,
      "kd_loss": 0.011637737974524498,
      "learning_rate": 9.995568825714479e-06,
      "loss": 0.1454,
      "step": 130,
      "student_loss": 0.0005009593442082405,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03892733564013841,
      "grad_norm": 19.5,
      "kd_loss": 0.12578554451465607,
      "learning_rate": 9.994360021283235e-06,
      "loss": 0.1434,
      "step": 135,
      "student_loss": 0.0007728396449238062,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.040369088811995385,
      "grad_norm": 4.0625,
      "kd_loss": 0.0028691363986581564,
      "learning_rate": 9.993005693541098e-06,
      "loss": 0.1367,
      "step": 140,
      "student_loss": 0.0006042163586243987,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04181084198385236,
      "grad_norm": 11.0,
      "kd_loss": 1.0329420566558838,
      "learning_rate": 9.991505881949837e-06,
      "loss": 0.1066,
      "step": 145,
      "student_loss": 0.041140101850032806,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04325259515570934,
      "grad_norm": 7.71875,
      "kd_loss": 0.013778705149888992,
      "learning_rate": 9.989860630210251e-06,
      "loss": 0.1259,
      "step": 150,
      "student_loss": 0.0009030756773427129,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04469434832756632,
      "grad_norm": 4.15625,
      "kd_loss": 0.028440266847610474,
      "learning_rate": 9.98806998626091e-06,
      "loss": 0.1208,
      "step": 155,
      "student_loss": 0.0017314451979473233,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0461361014994233,
      "grad_norm": 20.75,
      "kd_loss": 0.005404896102845669,
      "learning_rate": 9.98613400227676e-06,
      "loss": 0.1872,
      "step": 160,
      "student_loss": 0.10157372802495956,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04757785467128028,
      "grad_norm": 26.25,
      "kd_loss": 0.008982345461845398,
      "learning_rate": 9.984052734667586e-06,
      "loss": 0.1018,
      "step": 165,
      "student_loss": 0.00033849035389721394,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": 18.125,
      "kd_loss": 0.005132909398525953,
      "learning_rate": 9.981826244076387e-06,
      "loss": 0.1339,
      "step": 170,
      "student_loss": 0.0005440761451609433,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05046136101499423,
      "grad_norm": 18.0,
      "kd_loss": 0.021587209776043892,
      "learning_rate": 9.979454595377594e-06,
      "loss": 0.1247,
      "step": 175,
      "student_loss": 0.014186372049152851,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05190311418685121,
      "grad_norm": 8.5,
      "kd_loss": 0.011625917628407478,
      "learning_rate": 9.97693785767519e-06,
      "loss": 0.0741,
      "step": 180,
      "student_loss": 0.0005693296552635729,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05334486735870819,
      "grad_norm": 7.21875,
      "kd_loss": 0.0012370528420433402,
      "learning_rate": 9.9742761043007e-06,
      "loss": 0.1795,
      "step": 185,
      "student_loss": 0.043101612478494644,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05478662053056517,
      "grad_norm": 7.34375,
      "kd_loss": 0.1722288429737091,
      "learning_rate": 9.971469412811032e-06,
      "loss": 0.093,
      "step": 190,
      "student_loss": 0.006316277664154768,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.056228373702422146,
      "grad_norm": 44.25,
      "kd_loss": 0.6569585800170898,
      "learning_rate": 9.968517864986247e-06,
      "loss": 0.1118,
      "step": 195,
      "student_loss": 0.023583440110087395,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05767012687427912,
      "grad_norm": 4.9375,
      "kd_loss": 0.0010104529792442918,
      "learning_rate": 9.965421546827153e-06,
      "loss": 0.1094,
      "step": 200,
      "student_loss": 0.0004585790156852454,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0591118800461361,
      "grad_norm": 4.59375,
      "kd_loss": 0.0006818274850957096,
      "learning_rate": 9.962180548552812e-06,
      "loss": 0.0885,
      "step": 205,
      "student_loss": 0.046175092458724976,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06055363321799308,
      "grad_norm": 58.0,
      "kd_loss": 0.4983484745025635,
      "learning_rate": 9.958794964597906e-06,
      "loss": 0.1317,
      "step": 210,
      "student_loss": 0.007553795352578163,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.061995386389850055,
      "grad_norm": 6.46875,
      "kd_loss": 0.0009208342526108027,
      "learning_rate": 9.955264893609986e-06,
      "loss": 0.1522,
      "step": 215,
      "student_loss": 0.00047464462113566697,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06343713956170703,
      "grad_norm": 18.125,
      "kd_loss": 0.0944160670042038,
      "learning_rate": 9.951590438446597e-06,
      "loss": 0.0774,
      "step": 220,
      "student_loss": 0.03491729497909546,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06487889273356401,
      "grad_norm": 10.25,
      "kd_loss": 0.001832562847994268,
      "learning_rate": 9.947771706172285e-06,
      "loss": 0.0976,
      "step": 225,
      "student_loss": 0.05962345376610756,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06632064590542099,
      "grad_norm": 21.75,
      "kd_loss": 0.10277731716632843,
      "learning_rate": 9.943808808055472e-06,
      "loss": 0.0911,
      "step": 230,
      "student_loss": 0.0012677249033004045,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06776239907727798,
      "grad_norm": 17.25,
      "kd_loss": 0.4876050353050232,
      "learning_rate": 9.93970185956522e-06,
      "loss": 0.1077,
      "step": 235,
      "student_loss": 0.006362705025821924,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 1.46875,
      "kd_loss": 0.010914070531725883,
      "learning_rate": 9.93545098036786e-06,
      "loss": 0.1107,
      "step": 240,
      "student_loss": 0.0032385734375566244,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07064590542099193,
      "grad_norm": 10.3125,
      "kd_loss": 0.02172888070344925,
      "learning_rate": 9.931056294323507e-06,
      "loss": 0.081,
      "step": 245,
      "student_loss": 0.0005711687845177948,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07208765859284891,
      "grad_norm": 5.125,
      "kd_loss": 0.005143388640135527,
      "learning_rate": 9.926517929482454e-06,
      "loss": 0.1052,
      "step": 250,
      "student_loss": 0.0005271504633128643,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 6.5,
      "kd_loss": 0.0008525780867785215,
      "learning_rate": 9.921836018081438e-06,
      "loss": 0.0589,
      "step": 255,
      "student_loss": 0.0003723589761648327,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07497116493656286,
      "grad_norm": 17.0,
      "kd_loss": 0.0010641744593158364,
      "learning_rate": 9.917010696539793e-06,
      "loss": 0.1453,
      "step": 260,
      "student_loss": 0.0432959608733654,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07641291810841984,
      "grad_norm": 16.0,
      "kd_loss": 0.001827583066187799,
      "learning_rate": 9.912042105455462e-06,
      "loss": 0.0908,
      "step": 265,
      "student_loss": 0.00034234311897307634,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07785467128027682,
      "grad_norm": 14.0,
      "kd_loss": 0.000661063939332962,
      "learning_rate": 9.906930389600917e-06,
      "loss": 0.0894,
      "step": 270,
      "student_loss": 0.0010115442564710975,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07929642445213379,
      "grad_norm": 13.0,
      "kd_loss": 0.0016069641569629312,
      "learning_rate": 9.901675697918925e-06,
      "loss": 0.1173,
      "step": 275,
      "student_loss": 0.05398955196142197,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08073817762399077,
      "grad_norm": 29.0,
      "kd_loss": 0.0010736712720245123,
      "learning_rate": 9.896278183518216e-06,
      "loss": 0.1427,
      "step": 280,
      "student_loss": 0.0005599395371973515,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08217993079584775,
      "grad_norm": 17.5,
      "kd_loss": 0.017228417098522186,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.1333,
      "step": 285,
      "student_loss": 0.0005250528338365257,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08362168396770472,
      "grad_norm": 35.5,
      "kd_loss": 0.0026075318455696106,
      "learning_rate": 9.885055319798514e-06,
      "loss": 0.1752,
      "step": 290,
      "student_loss": 0.0017553431680426002,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0850634371395617,
      "grad_norm": 26.25,
      "kd_loss": 0.004095411393791437,
      "learning_rate": 9.879230297486034e-06,
      "loss": 0.158,
      "step": 295,
      "student_loss": 0.0005752203287556767,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08650519031141868,
      "grad_norm": 4.96875,
      "kd_loss": 0.2717151343822479,
      "learning_rate": 9.873263106458353e-06,
      "loss": 0.0941,
      "step": 300,
      "student_loss": 0.023448897525668144,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08794694348327567,
      "grad_norm": 6.65625,
      "kd_loss": 0.019775602966547012,
      "learning_rate": 9.86715392058467e-06,
      "loss": 0.1302,
      "step": 305,
      "student_loss": 0.0025525283999741077,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08938869665513265,
      "grad_norm": 7.0,
      "kd_loss": 0.0005424432456493378,
      "learning_rate": 9.860902917871566e-06,
      "loss": 0.1096,
      "step": 310,
      "student_loss": 0.000471778039354831,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09083044982698962,
      "grad_norm": 10.25,
      "kd_loss": 0.021720539778470993,
      "learning_rate": 9.854510280457819e-06,
      "loss": 0.0897,
      "step": 315,
      "student_loss": 0.015475576743483543,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0922722029988466,
      "grad_norm": 6.40625,
      "kd_loss": 0.0012843874283134937,
      "learning_rate": 9.847976194609083e-06,
      "loss": 0.091,
      "step": 320,
      "student_loss": 0.0004686483880504966,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09371395617070358,
      "grad_norm": 26.375,
      "kd_loss": 0.6982781887054443,
      "learning_rate": 9.841300850712479e-06,
      "loss": 0.103,
      "step": 325,
      "student_loss": 0.017696071416139603,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09515570934256055,
      "grad_norm": 8.6875,
      "kd_loss": 0.15215124189853668,
      "learning_rate": 9.834484443271035e-06,
      "loss": 0.0715,
      "step": 330,
      "student_loss": 0.005886889062821865,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09659746251441753,
      "grad_norm": 2.875,
      "kd_loss": 0.0015391090419143438,
      "learning_rate": 9.827527170898019e-06,
      "loss": 0.0852,
      "step": 335,
      "student_loss": 0.0005516717210412025,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 15.0,
      "kd_loss": 0.07792548835277557,
      "learning_rate": 9.820429236311158e-06,
      "loss": 0.1289,
      "step": 340,
      "student_loss": 0.010181530378758907,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09948096885813149,
      "grad_norm": 6.0625,
      "kd_loss": 0.013684757985174656,
      "learning_rate": 9.81319084632673e-06,
      "loss": 0.093,
      "step": 345,
      "student_loss": 0.01164299063384533,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10092272202998846,
      "grad_norm": 5.3125,
      "kd_loss": 0.0955321341753006,
      "learning_rate": 9.805812211853534e-06,
      "loss": 0.0668,
      "step": 350,
      "student_loss": 0.0006315007922239602,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10236447520184544,
      "grad_norm": 15.75,
      "kd_loss": 0.000853118603117764,
      "learning_rate": 9.798293547886748e-06,
      "loss": 0.1354,
      "step": 355,
      "student_loss": 0.00041306763887405396,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10380622837370242,
      "grad_norm": 4.125,
      "kd_loss": 0.0023229331709444523,
      "learning_rate": 9.790635073501662e-06,
      "loss": 0.0929,
      "step": 360,
      "student_loss": 0.0004519273934420198,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1052479815455594,
      "grad_norm": 12.875,
      "kd_loss": 0.004534870386123657,
      "learning_rate": 9.782837011847294e-06,
      "loss": 0.177,
      "step": 365,
      "student_loss": 0.048408832401037216,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10668973471741638,
      "grad_norm": 5.75,
      "kd_loss": 0.5334176421165466,
      "learning_rate": 9.774899590139897e-06,
      "loss": 0.0711,
      "step": 370,
      "student_loss": 0.0273645780980587,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10813148788927336,
      "grad_norm": 12.25,
      "kd_loss": 0.006150795612484217,
      "learning_rate": 9.766823039656328e-06,
      "loss": 0.1286,
      "step": 375,
      "student_loss": 0.03481242433190346,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10957324106113034,
      "grad_norm": 0.69140625,
      "kd_loss": 0.0020576389506459236,
      "learning_rate": 9.758607595727309e-06,
      "loss": 0.0763,
      "step": 380,
      "student_loss": 0.0004342672764323652,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11101499423298732,
      "grad_norm": 3.375,
      "kd_loss": 0.01198313757777214,
      "learning_rate": 9.75025349773058e-06,
      "loss": 0.0684,
      "step": 385,
      "student_loss": 0.00040114219882525504,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11245674740484429,
      "grad_norm": 42.25,
      "kd_loss": 0.0029099821113049984,
      "learning_rate": 9.741760989083914e-06,
      "loss": 0.0966,
      "step": 390,
      "student_loss": 0.00024992373073473573,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11389850057670127,
      "grad_norm": 10.4375,
      "kd_loss": 0.0029170780908316374,
      "learning_rate": 9.73313031723803e-06,
      "loss": 0.0846,
      "step": 395,
      "student_loss": 0.0004683209699578583,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11534025374855825,
      "grad_norm": 2.390625,
      "kd_loss": 0.002679860917851329,
      "learning_rate": 9.724361733669383e-06,
      "loss": 0.0425,
      "step": 400,
      "student_loss": 0.002333736512809992,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11678200692041522,
      "grad_norm": 11.6875,
      "kd_loss": 0.0017421097727492452,
      "learning_rate": 9.715455493872827e-06,
      "loss": 0.1317,
      "step": 405,
      "student_loss": 0.011753321625292301,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1182237600922722,
      "grad_norm": 5.96875,
      "kd_loss": 0.0038202686700969934,
      "learning_rate": 9.70641185735419e-06,
      "loss": 0.0947,
      "step": 410,
      "student_loss": 0.015384526923298836,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11966551326412918,
      "grad_norm": 15.625,
      "kd_loss": 0.007967401295900345,
      "learning_rate": 9.697231087622691e-06,
      "loss": 0.1609,
      "step": 415,
      "student_loss": 0.003767178161069751,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12110726643598616,
      "grad_norm": 7.78125,
      "kd_loss": 0.3626428246498108,
      "learning_rate": 9.687913452183277e-06,
      "loss": 0.0883,
      "step": 420,
      "student_loss": 0.06143607571721077,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12254901960784313,
      "grad_norm": 9.1875,
      "kd_loss": 0.0016940389759838581,
      "learning_rate": 9.678459222528825e-06,
      "loss": 0.0493,
      "step": 425,
      "student_loss": 0.002240637084469199,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12399077277970011,
      "grad_norm": 19.75,
      "kd_loss": 0.9260356426239014,
      "learning_rate": 9.668868674132224e-06,
      "loss": 0.1153,
      "step": 430,
      "student_loss": 0.0827086940407753,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1254325259515571,
      "grad_norm": 12.8125,
      "kd_loss": 0.0019437845330685377,
      "learning_rate": 9.65914208643836e-06,
      "loss": 0.0634,
      "step": 435,
      "student_loss": 0.0006262208335101604,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12687427912341406,
      "grad_norm": 4.25,
      "kd_loss": 0.00489834975451231,
      "learning_rate": 9.649279742855964e-06,
      "loss": 0.103,
      "step": 440,
      "student_loss": 0.013814084231853485,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12831603229527105,
      "grad_norm": 22.375,
      "kd_loss": 0.0016376337734982371,
      "learning_rate": 9.639281930749363e-06,
      "loss": 0.079,
      "step": 445,
      "student_loss": 0.03539160266518593,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12975778546712802,
      "grad_norm": 7.375,
      "kd_loss": 0.0012233811430633068,
      "learning_rate": 9.629148941430096e-06,
      "loss": 0.1054,
      "step": 450,
      "student_loss": 0.0006881144363433123,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.131199538638985,
      "grad_norm": 6.0,
      "kd_loss": 0.0003836078103631735,
      "learning_rate": 9.618881070148436e-06,
      "loss": 0.1035,
      "step": 455,
      "student_loss": 0.001039310242049396,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13264129181084197,
      "grad_norm": 7.15625,
      "kd_loss": 0.039876699447631836,
      "learning_rate": 9.608478616084784e-06,
      "loss": 0.0547,
      "step": 460,
      "student_loss": 0.008442185819149017,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13408304498269896,
      "grad_norm": 15.4375,
      "kd_loss": 0.08534516394138336,
      "learning_rate": 9.597941882340947e-06,
      "loss": 0.1407,
      "step": 465,
      "student_loss": 0.00036318166530691087,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13552479815455595,
      "grad_norm": 9.125,
      "kd_loss": 0.000860957894474268,
      "learning_rate": 9.587271175931313e-06,
      "loss": 0.0872,
      "step": 470,
      "student_loss": 0.00031289560138247907,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13696655132641292,
      "grad_norm": 3.21875,
      "kd_loss": 0.021515244618058205,
      "learning_rate": 9.5764668077739e-06,
      "loss": 0.0627,
      "step": 475,
      "student_loss": 0.0004178633389528841,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 11.5625,
      "kd_loss": 0.01755513623356819,
      "learning_rate": 9.5655290926813e-06,
      "loss": 0.0742,
      "step": 480,
      "student_loss": 0.041500866413116455,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13985005767012687,
      "grad_norm": 18.875,
      "kd_loss": 0.0021918262355029583,
      "learning_rate": 9.554458349351507e-06,
      "loss": 0.0853,
      "step": 485,
      "student_loss": 0.0005753549048677087,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14129181084198386,
      "grad_norm": 16.0,
      "kd_loss": 0.005263358820229769,
      "learning_rate": 9.54325490035863e-06,
      "loss": 0.1613,
      "step": 490,
      "student_loss": 0.0003423037414904684,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14273356401384082,
      "grad_norm": 6.75,
      "kd_loss": 0.0663486197590828,
      "learning_rate": 9.531919072143488e-06,
      "loss": 0.0925,
      "step": 495,
      "student_loss": 0.0005914232460781932,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14417531718569782,
      "grad_norm": 7.40625,
      "kd_loss": 0.032540202140808105,
      "learning_rate": 9.520451195004107e-06,
      "loss": 0.0773,
      "step": 500,
      "student_loss": 0.00025544269010424614,
      "teacher_loss": 0.0
    }
  ],
  "logging_steps": 5,
  "max_steps": 3000,
  "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": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}