{
  "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": 106.5,
      "kd_loss": 1.1900196075439453,
      "learning_rate": 4.444444444444445e-07,
      "loss": 1.389,
      "step": 5,
      "student_loss": 0.1422676295042038,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0028835063437139563,
      "grad_norm": 75.5,
      "kd_loss": 1.0197750329971313,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.3585,
      "step": 10,
      "student_loss": 0.20726262032985687,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.004325259515570935,
      "grad_norm": 67.0,
      "kd_loss": 0.8719732165336609,
      "learning_rate": 1.5555555555555558e-06,
      "loss": 1.2979,
      "step": 15,
      "student_loss": 0.07172369956970215,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0057670126874279125,
      "grad_norm": 88.0,
      "kd_loss": 0.7114419341087341,
      "learning_rate": 2.1111111111111114e-06,
      "loss": 1.1904,
      "step": 20,
      "student_loss": 0.13332775235176086,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.00720876585928489,
      "grad_norm": 40.5,
      "kd_loss": 0.6378957033157349,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.0315,
      "step": 25,
      "student_loss": 0.1825275719165802,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.00865051903114187,
      "grad_norm": 36.0,
      "kd_loss": 0.48297253251075745,
      "learning_rate": 3.2222222222222227e-06,
      "loss": 0.8442,
      "step": 30,
      "student_loss": 0.16044040024280548,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.010092272202998846,
      "grad_norm": 30.375,
      "kd_loss": 0.4690523147583008,
      "learning_rate": 3.777777777777778e-06,
      "loss": 0.7189,
      "step": 35,
      "student_loss": 0.02417413890361786,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.011534025374855825,
      "grad_norm": 10.75,
      "kd_loss": 0.3731468915939331,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.5653,
      "step": 40,
      "student_loss": 0.07280340045690536,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.012975778546712802,
      "grad_norm": 9.25,
      "kd_loss": 0.7187333703041077,
      "learning_rate": 4.888888888888889e-06,
      "loss": 0.463,
      "step": 45,
      "student_loss": 0.10900051146745682,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.01441753171856978,
      "grad_norm": 8.875,
      "kd_loss": 0.39285412430763245,
      "learning_rate": 5.444444444444445e-06,
      "loss": 0.4475,
      "step": 50,
      "student_loss": 0.019839322194457054,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.015859284890426758,
      "grad_norm": 11.5,
      "kd_loss": 0.19283825159072876,
      "learning_rate": 6e-06,
      "loss": 0.3823,
      "step": 55,
      "student_loss": 0.0010118820937350392,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.01730103806228374,
      "grad_norm": 12.9375,
      "kd_loss": 0.16523021459579468,
      "learning_rate": 6.555555555555556e-06,
      "loss": 0.3287,
      "step": 60,
      "student_loss": 0.0016304850578308105,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.018742791234140715,
      "grad_norm": 7.34375,
      "kd_loss": 0.14898601174354553,
      "learning_rate": 7.111111111111112e-06,
      "loss": 0.3321,
      "step": 65,
      "student_loss": 0.027957376092672348,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.020184544405997693,
      "grad_norm": 6.96875,
      "kd_loss": 0.34543901681900024,
      "learning_rate": 7.666666666666667e-06,
      "loss": 0.3072,
      "step": 70,
      "student_loss": 0.013891056180000305,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02162629757785467,
      "grad_norm": 10.875,
      "kd_loss": 0.11955085396766663,
      "learning_rate": 8.222222222222222e-06,
      "loss": 0.2997,
      "step": 75,
      "student_loss": 0.001077663735486567,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02306805074971165,
      "grad_norm": 8.125,
      "kd_loss": 0.10641466826200485,
      "learning_rate": 8.777777777777778e-06,
      "loss": 0.274,
      "step": 80,
      "student_loss": 0.0010437737219035625,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.024509803921568627,
      "grad_norm": 10.0625,
      "kd_loss": 0.06137283146381378,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.2777,
      "step": 85,
      "student_loss": 0.0004318205174058676,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.025951557093425604,
      "grad_norm": 7.5,
      "kd_loss": 0.3231976330280304,
      "learning_rate": 9.88888888888889e-06,
      "loss": 0.2554,
      "step": 90,
      "student_loss": 0.010668772272765636,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.027393310265282585,
      "grad_norm": 7.8125,
      "kd_loss": 0.2638072371482849,
      "learning_rate": 9.99995337991255e-06,
      "loss": 0.2571,
      "step": 95,
      "student_loss": 0.013187691569328308,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02883506343713956,
      "grad_norm": 7.15625,
      "kd_loss": 0.08886470645666122,
      "learning_rate": 9.999763987297266e-06,
      "loss": 0.2321,
      "step": 100,
      "student_loss": 0.0006429512286558747,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03027681660899654,
      "grad_norm": 6.5625,
      "kd_loss": 0.24982710182666779,
      "learning_rate": 9.999428913912876e-06,
      "loss": 0.2416,
      "step": 105,
      "student_loss": 0.0025494606234133244,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.031718569780853516,
      "grad_norm": 5.875,
      "kd_loss": 0.26601096987724304,
      "learning_rate": 9.998948169522587e-06,
      "loss": 0.2443,
      "step": 110,
      "student_loss": 0.036904845386743546,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03316032295271049,
      "grad_norm": 6.34375,
      "kd_loss": 0.3104342222213745,
      "learning_rate": 9.998321768134101e-06,
      "loss": 0.237,
      "step": 115,
      "student_loss": 0.0034773952793329954,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03460207612456748,
      "grad_norm": 5.4375,
      "kd_loss": 0.13216911256313324,
      "learning_rate": 9.997549727999212e-06,
      "loss": 0.2046,
      "step": 120,
      "student_loss": 0.0008047327864915133,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.036043829296424454,
      "grad_norm": 10.9375,
      "kd_loss": 0.39640313386917114,
      "learning_rate": 9.996632071613257e-06,
      "loss": 0.2315,
      "step": 125,
      "student_loss": 0.055598437786102295,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03748558246828143,
      "grad_norm": 7.375,
      "kd_loss": 0.15535855293273926,
      "learning_rate": 9.995568825714479e-06,
      "loss": 0.2439,
      "step": 130,
      "student_loss": 0.0005180384614504874,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03892733564013841,
      "grad_norm": 8.875,
      "kd_loss": 0.2404610514640808,
      "learning_rate": 9.994360021283235e-06,
      "loss": 0.2227,
      "step": 135,
      "student_loss": 0.0007398177986033261,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.040369088811995385,
      "grad_norm": 6.65625,
      "kd_loss": 0.11759798973798752,
      "learning_rate": 9.993005693541098e-06,
      "loss": 0.2056,
      "step": 140,
      "student_loss": 0.0005030568572692573,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04181084198385236,
      "grad_norm": 10.1875,
      "kd_loss": 0.495441734790802,
      "learning_rate": 9.991505881949837e-06,
      "loss": 0.2072,
      "step": 145,
      "student_loss": 0.04584295675158501,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04325259515570934,
      "grad_norm": 7.5625,
      "kd_loss": 0.06494709104299545,
      "learning_rate": 9.989860630210251e-06,
      "loss": 0.208,
      "step": 150,
      "student_loss": 0.0006991412374190986,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04469434832756632,
      "grad_norm": 6.34375,
      "kd_loss": 0.11540775746107101,
      "learning_rate": 9.98806998626091e-06,
      "loss": 0.2123,
      "step": 155,
      "student_loss": 0.0013254352379590273,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0461361014994233,
      "grad_norm": 7.78125,
      "kd_loss": 0.20968985557556152,
      "learning_rate": 9.98613400227676e-06,
      "loss": 0.2308,
      "step": 160,
      "student_loss": 0.07876866310834885,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04757785467128028,
      "grad_norm": 5.125,
      "kd_loss": 0.19647686183452606,
      "learning_rate": 9.984052734667586e-06,
      "loss": 0.2057,
      "step": 165,
      "student_loss": 0.00031577967456541955,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": 6.0625,
      "kd_loss": 0.0746464729309082,
      "learning_rate": 9.981826244076387e-06,
      "loss": 0.2068,
      "step": 170,
      "student_loss": 0.0005107919569127262,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05046136101499423,
      "grad_norm": 9.5,
      "kd_loss": 0.13447396457195282,
      "learning_rate": 9.979454595377594e-06,
      "loss": 0.1983,
      "step": 175,
      "student_loss": 0.012695364654064178,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05190311418685121,
      "grad_norm": 7.09375,
      "kd_loss": 0.2970976233482361,
      "learning_rate": 9.97693785767519e-06,
      "loss": 0.1904,
      "step": 180,
      "student_loss": 0.0004823607159778476,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05334486735870819,
      "grad_norm": 6.5,
      "kd_loss": 0.16425344347953796,
      "learning_rate": 9.9742761043007e-06,
      "loss": 0.2085,
      "step": 185,
      "student_loss": 0.04301092401146889,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05478662053056517,
      "grad_norm": 7.96875,
      "kd_loss": 0.2780059278011322,
      "learning_rate": 9.971469412811032e-06,
      "loss": 0.1921,
      "step": 190,
      "student_loss": 0.011953173205256462,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.056228373702422146,
      "grad_norm": 5.625,
      "kd_loss": 0.3551367223262787,
      "learning_rate": 9.968517864986247e-06,
      "loss": 0.1926,
      "step": 195,
      "student_loss": 0.0191096980124712,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05767012687427912,
      "grad_norm": 8.0625,
      "kd_loss": 0.13143359124660492,
      "learning_rate": 9.965421546827153e-06,
      "loss": 0.2061,
      "step": 200,
      "student_loss": 0.0003951227408833802,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0591118800461361,
      "grad_norm": 5.4375,
      "kd_loss": 0.17285136878490448,
      "learning_rate": 9.962180548552812e-06,
      "loss": 0.1878,
      "step": 205,
      "student_loss": 0.04404015466570854,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06055363321799308,
      "grad_norm": 5.8125,
      "kd_loss": 0.21570773422718048,
      "learning_rate": 9.958794964597906e-06,
      "loss": 0.1884,
      "step": 210,
      "student_loss": 0.0004762043245136738,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.061995386389850055,
      "grad_norm": 6.3125,
      "kd_loss": 0.14821867644786835,
      "learning_rate": 9.955264893609986e-06,
      "loss": 0.2088,
      "step": 215,
      "student_loss": 0.00042462380952201784,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06343713956170703,
      "grad_norm": 5.53125,
      "kd_loss": 0.21854154765605927,
      "learning_rate": 9.951590438446597e-06,
      "loss": 0.1834,
      "step": 220,
      "student_loss": 0.034548722207546234,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06487889273356401,
      "grad_norm": 5.375,
      "kd_loss": 0.09108870476484299,
      "learning_rate": 9.947771706172285e-06,
      "loss": 0.1893,
      "step": 225,
      "student_loss": 0.03484133258461952,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06632064590542099,
      "grad_norm": 9.75,
      "kd_loss": 0.23377805948257446,
      "learning_rate": 9.943808808055472e-06,
      "loss": 0.182,
      "step": 230,
      "student_loss": 0.0028649731539189816,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06776239907727798,
      "grad_norm": 7.4375,
      "kd_loss": 0.4445033073425293,
      "learning_rate": 9.93970185956522e-06,
      "loss": 0.1916,
      "step": 235,
      "student_loss": 0.016616689041256905,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 8.9375,
      "kd_loss": 0.1569254994392395,
      "learning_rate": 9.93545098036786e-06,
      "loss": 0.1856,
      "step": 240,
      "student_loss": 0.005397707223892212,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07064590542099193,
      "grad_norm": 10.0,
      "kd_loss": 0.05294733867049217,
      "learning_rate": 9.931056294323507e-06,
      "loss": 0.1755,
      "step": 245,
      "student_loss": 0.0006755735375918448,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07208765859284891,
      "grad_norm": 11.9375,
      "kd_loss": 0.06715790927410126,
      "learning_rate": 9.926517929482454e-06,
      "loss": 0.1881,
      "step": 250,
      "student_loss": 0.0005509246839210391,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 9.75,
      "kd_loss": 0.06327904760837555,
      "learning_rate": 9.921836018081438e-06,
      "loss": 0.1683,
      "step": 255,
      "student_loss": 0.00027642049826681614,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07497116493656286,
      "grad_norm": 7.59375,
      "kd_loss": 0.12199637293815613,
      "learning_rate": 9.917010696539793e-06,
      "loss": 0.2046,
      "step": 260,
      "student_loss": 0.042497601360082626,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07641291810841984,
      "grad_norm": 7.65625,
      "kd_loss": 0.052612222731113434,
      "learning_rate": 9.912042105455462e-06,
      "loss": 0.1824,
      "step": 265,
      "student_loss": 0.00036533031379804015,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07785467128027682,
      "grad_norm": 4.84375,
      "kd_loss": 0.050872161984443665,
      "learning_rate": 9.906930389600917e-06,
      "loss": 0.1905,
      "step": 270,
      "student_loss": 0.0008181569282896817,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07929642445213379,
      "grad_norm": 7.34375,
      "kd_loss": 0.13403832912445068,
      "learning_rate": 9.901675697918925e-06,
      "loss": 0.1834,
      "step": 275,
      "student_loss": 0.050149545073509216,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08073817762399077,
      "grad_norm": 6.78125,
      "kd_loss": 0.10233883559703827,
      "learning_rate": 9.896278183518216e-06,
      "loss": 0.1848,
      "step": 280,
      "student_loss": 0.0005086572491563857,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08217993079584775,
      "grad_norm": 5.625,
      "kd_loss": 0.09045373648405075,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.2056,
      "step": 285,
      "student_loss": 0.0005186001653783023,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08362168396770472,
      "grad_norm": 10.4375,
      "kd_loss": 0.07550664991140366,
      "learning_rate": 9.885055319798514e-06,
      "loss": 0.1994,
      "step": 290,
      "student_loss": 0.0020688113290816545,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0850634371395617,
      "grad_norm": 5.375,
      "kd_loss": 0.07470615953207016,
      "learning_rate": 9.879230297486034e-06,
      "loss": 0.2036,
      "step": 295,
      "student_loss": 0.0005224258056841791,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08650519031141868,
      "grad_norm": 4.96875,
      "kd_loss": 0.254043310880661,
      "learning_rate": 9.873263106458353e-06,
      "loss": 0.1766,
      "step": 300,
      "student_loss": 0.022904984652996063,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08794694348327567,
      "grad_norm": 8.625,
      "kd_loss": 0.12328250706195831,
      "learning_rate": 9.86715392058467e-06,
      "loss": 0.1687,
      "step": 305,
      "student_loss": 0.0030305401887744665,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08938869665513265,
      "grad_norm": 8.5625,
      "kd_loss": 0.08438524603843689,
      "learning_rate": 9.860902917871566e-06,
      "loss": 0.179,
      "step": 310,
      "student_loss": 0.0004664761363528669,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09083044982698962,
      "grad_norm": 5.84375,
      "kd_loss": 0.21459946036338806,
      "learning_rate": 9.854510280457819e-06,
      "loss": 0.1756,
      "step": 315,
      "student_loss": 0.00737906526774168,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0922722029988466,
      "grad_norm": 7.28125,
      "kd_loss": 0.07853322476148605,
      "learning_rate": 9.847976194609083e-06,
      "loss": 0.1793,
      "step": 320,
      "student_loss": 0.0004535326734185219,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09371395617070358,
      "grad_norm": 7.0625,
      "kd_loss": 0.36134564876556396,
      "learning_rate": 9.841300850712479e-06,
      "loss": 0.1574,
      "step": 325,
      "student_loss": 0.0006651441799476743,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09515570934256055,
      "grad_norm": 5.59375,
      "kd_loss": 0.2662656009197235,
      "learning_rate": 9.834484443271035e-06,
      "loss": 0.1744,
      "step": 330,
      "student_loss": 0.0028211227618157864,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09659746251441753,
      "grad_norm": 8.0625,
      "kd_loss": 0.09443436563014984,
      "learning_rate": 9.827527170898019e-06,
      "loss": 0.1489,
      "step": 335,
      "student_loss": 0.0005554864183068275,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 5.71875,
      "kd_loss": 0.10154180973768234,
      "learning_rate": 9.820429236311158e-06,
      "loss": 0.1851,
      "step": 340,
      "student_loss": 0.009886357001960278,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09948096885813149,
      "grad_norm": 3.40625,
      "kd_loss": 0.13887977600097656,
      "learning_rate": 9.81319084632673e-06,
      "loss": 0.1744,
      "step": 345,
      "student_loss": 0.006124563980847597,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10092272202998846,
      "grad_norm": 4.71875,
      "kd_loss": 0.2847428023815155,
      "learning_rate": 9.805812211853534e-06,
      "loss": 0.1624,
      "step": 350,
      "student_loss": 0.00044082352542318404,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10236447520184544,
      "grad_norm": 7.0,
      "kd_loss": 0.0902910828590393,
      "learning_rate": 9.798293547886748e-06,
      "loss": 0.1686,
      "step": 355,
      "student_loss": 0.00043379762792028487,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10380622837370242,
      "grad_norm": 7.46875,
      "kd_loss": 0.05925482511520386,
      "learning_rate": 9.790635073501662e-06,
      "loss": 0.1726,
      "step": 360,
      "student_loss": 0.0004483895900193602,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1052479815455594,
      "grad_norm": 9.75,
      "kd_loss": 0.1501902937889099,
      "learning_rate": 9.782837011847294e-06,
      "loss": 0.1935,
      "step": 365,
      "student_loss": 0.04511932656168938,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10668973471741638,
      "grad_norm": 5.5,
      "kd_loss": 0.2575005292892456,
      "learning_rate": 9.774899590139897e-06,
      "loss": 0.1727,
      "step": 370,
      "student_loss": 0.033754754811525345,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10813148788927336,
      "grad_norm": 7.0,
      "kd_loss": 0.1478898823261261,
      "learning_rate": 9.766823039656328e-06,
      "loss": 0.1646,
      "step": 375,
      "student_loss": 0.031900398433208466,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10957324106113034,
      "grad_norm": 4.0625,
      "kd_loss": 0.05213665962219238,
      "learning_rate": 9.758607595727309e-06,
      "loss": 0.1731,
      "step": 380,
      "student_loss": 0.00042764144018292427,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11101499423298732,
      "grad_norm": 7.4375,
      "kd_loss": 0.1557849943637848,
      "learning_rate": 9.75025349773058e-06,
      "loss": 0.1576,
      "step": 385,
      "student_loss": 0.00038361549377441406,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11245674740484429,
      "grad_norm": 7.34375,
      "kd_loss": 0.04977763444185257,
      "learning_rate": 9.741760989083914e-06,
      "loss": 0.1599,
      "step": 390,
      "student_loss": 0.00024680295609869063,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11389850057670127,
      "grad_norm": 5.5,
      "kd_loss": 0.09320851415395737,
      "learning_rate": 9.73313031723803e-06,
      "loss": 0.1557,
      "step": 395,
      "student_loss": 0.00043702221591956913,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11534025374855825,
      "grad_norm": 4.0625,
      "kd_loss": 0.0984533280134201,
      "learning_rate": 9.724361733669383e-06,
      "loss": 0.1313,
      "step": 400,
      "student_loss": 0.002326528076082468,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11678200692041522,
      "grad_norm": 5.6875,
      "kd_loss": 0.08723900467157364,
      "learning_rate": 9.715455493872827e-06,
      "loss": 0.1661,
      "step": 405,
      "student_loss": 0.011903912760317326,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1182237600922722,
      "grad_norm": 6.84375,
      "kd_loss": 0.20244774222373962,
      "learning_rate": 9.70641185735419e-06,
      "loss": 0.1729,
      "step": 410,
      "student_loss": 0.01531198713928461,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11966551326412918,
      "grad_norm": 5.90625,
      "kd_loss": 0.08771727979183197,
      "learning_rate": 9.697231087622691e-06,
      "loss": 0.1872,
      "step": 415,
      "student_loss": 0.0038373665884137154,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12110726643598616,
      "grad_norm": 6.03125,
      "kd_loss": 0.23439179360866547,
      "learning_rate": 9.687913452183277e-06,
      "loss": 0.1579,
      "step": 420,
      "student_loss": 0.06521515548229218,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12254901960784313,
      "grad_norm": 10.25,
      "kd_loss": 0.02720467746257782,
      "learning_rate": 9.678459222528825e-06,
      "loss": 0.1542,
      "step": 425,
      "student_loss": 0.0021591742988675833,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12399077277970011,
      "grad_norm": 4.625,
      "kd_loss": 0.26806876063346863,
      "learning_rate": 9.668868674132224e-06,
      "loss": 0.1984,
      "step": 430,
      "student_loss": 0.06153964251279831,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1254325259515571,
      "grad_norm": 5.875,
      "kd_loss": 0.0505138635635376,
      "learning_rate": 9.65914208643836e-06,
      "loss": 0.1399,
      "step": 435,
      "student_loss": 0.0006324865389615297,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12687427912341406,
      "grad_norm": 5.6875,
      "kd_loss": 0.25690194964408875,
      "learning_rate": 9.649279742855964e-06,
      "loss": 0.1766,
      "step": 440,
      "student_loss": 0.014252256602048874,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12831603229527105,
      "grad_norm": 13.9375,
      "kd_loss": 0.16726160049438477,
      "learning_rate": 9.639281930749363e-06,
      "loss": 0.1683,
      "step": 445,
      "student_loss": 0.030716991052031517,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12975778546712802,
      "grad_norm": 5.875,
      "kd_loss": 0.14118966460227966,
      "learning_rate": 9.629148941430096e-06,
      "loss": 0.1852,
      "step": 450,
      "student_loss": 0.0006644712993875146,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.131199538638985,
      "grad_norm": 5.71875,
      "kd_loss": 0.0657167136669159,
      "learning_rate": 9.618881070148436e-06,
      "loss": 0.1697,
      "step": 455,
      "student_loss": 0.0011592389782890677,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13264129181084197,
      "grad_norm": 8.625,
      "kd_loss": 0.2250318080186844,
      "learning_rate": 9.608478616084784e-06,
      "loss": 0.1424,
      "step": 460,
      "student_loss": 0.009063606150448322,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13408304498269896,
      "grad_norm": 4.96875,
      "kd_loss": 0.23261451721191406,
      "learning_rate": 9.597941882340947e-06,
      "loss": 0.19,
      "step": 465,
      "student_loss": 0.00037093457649461925,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13552479815455595,
      "grad_norm": 5.65625,
      "kd_loss": 0.06862400472164154,
      "learning_rate": 9.587271175931313e-06,
      "loss": 0.1546,
      "step": 470,
      "student_loss": 0.0003174058219883591,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13696655132641292,
      "grad_norm": 6.9375,
      "kd_loss": 0.1504378765821457,
      "learning_rate": 9.5764668077739e-06,
      "loss": 0.137,
      "step": 475,
      "student_loss": 0.00043892176472581923,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 9.5,
      "kd_loss": 0.19803652167320251,
      "learning_rate": 9.5655290926813e-06,
      "loss": 0.1684,
      "step": 480,
      "student_loss": 0.03657232224941254,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13985005767012687,
      "grad_norm": 10.6875,
      "kd_loss": 0.042275670915842056,
      "learning_rate": 9.554458349351507e-06,
      "loss": 0.1598,
      "step": 485,
      "student_loss": 0.0004415225994307548,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14129181084198386,
      "grad_norm": 5.25,
      "kd_loss": 0.08490484207868576,
      "learning_rate": 9.54325490035863e-06,
      "loss": 0.1747,
      "step": 490,
      "student_loss": 0.0003650383441708982,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14273356401384082,
      "grad_norm": 9.125,
      "kd_loss": 0.22001218795776367,
      "learning_rate": 9.531919072143488e-06,
      "loss": 0.1684,
      "step": 495,
      "student_loss": 0.0004516220942605287,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14417531718569782,
      "grad_norm": 7.5625,
      "kd_loss": 0.1156071275472641,
      "learning_rate": 9.520451195004107e-06,
      "loss": 0.1612,
      "step": 500,
      "student_loss": 0.0002619729784782976,
      "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
}