{
  "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": 1952.0,
      "kd_loss": 1.354009985923767,
      "learning_rate": 4.444444444444445e-07,
      "loss": 4.4194,
      "step": 5,
      "student_loss": 0.10154028236865997,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0028835063437139563,
      "grad_norm": 768.0,
      "kd_loss": 2.1859679222106934,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 4.072,
      "step": 10,
      "student_loss": 0.23161625862121582,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.004325259515570935,
      "grad_norm": 676.0,
      "kd_loss": 0.8974658250808716,
      "learning_rate": 1.5555555555555558e-06,
      "loss": 3.0092,
      "step": 15,
      "student_loss": 0.07354968786239624,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0057670126874279125,
      "grad_norm": 784.0,
      "kd_loss": 5.459206581115723,
      "learning_rate": 2.1111111111111114e-06,
      "loss": 2.0182,
      "step": 20,
      "student_loss": 0.24417075514793396,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.00720876585928489,
      "grad_norm": 132.0,
      "kd_loss": 0.039198435842990875,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.9093,
      "step": 25,
      "student_loss": 0.3775336444377899,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.00865051903114187,
      "grad_norm": 82.0,
      "kd_loss": 0.01129975076764822,
      "learning_rate": 3.2222222222222227e-06,
      "loss": 0.6102,
      "step": 30,
      "student_loss": 0.48634102940559387,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.010092272202998846,
      "grad_norm": 67.5,
      "kd_loss": 0.01766686514019966,
      "learning_rate": 3.777777777777778e-06,
      "loss": 0.5753,
      "step": 35,
      "student_loss": 0.16448530554771423,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.011534025374855825,
      "grad_norm": 66.0,
      "kd_loss": 0.02908974140882492,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.441,
      "step": 40,
      "student_loss": 0.11244617402553558,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.012975778546712802,
      "grad_norm": 68.0,
      "kd_loss": 0.2916097640991211,
      "learning_rate": 4.888888888888889e-06,
      "loss": 0.2934,
      "step": 45,
      "student_loss": 0.07623665779829025,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.01441753171856978,
      "grad_norm": 88.5,
      "kd_loss": 0.19340172410011292,
      "learning_rate": 5.444444444444445e-06,
      "loss": 0.3841,
      "step": 50,
      "student_loss": 0.009455127641558647,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.015859284890426758,
      "grad_norm": 115.0,
      "kd_loss": 0.01024007610976696,
      "learning_rate": 6e-06,
      "loss": 0.2854,
      "step": 55,
      "student_loss": 0.0043172105215489864,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.01730103806228374,
      "grad_norm": 57.75,
      "kd_loss": 0.0018813807982951403,
      "learning_rate": 6.555555555555556e-06,
      "loss": 0.2133,
      "step": 60,
      "student_loss": 0.012564695440232754,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.018742791234140715,
      "grad_norm": 56.0,
      "kd_loss": 0.0018871173961088061,
      "learning_rate": 7.111111111111112e-06,
      "loss": 0.2158,
      "step": 65,
      "student_loss": 0.050387192517519,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.020184544405997693,
      "grad_norm": 28.625,
      "kd_loss": 0.4643922448158264,
      "learning_rate": 7.666666666666667e-06,
      "loss": 0.1818,
      "step": 70,
      "student_loss": 0.023501692339777946,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02162629757785467,
      "grad_norm": 43.0,
      "kd_loss": 0.010926949791610241,
      "learning_rate": 8.222222222222222e-06,
      "loss": 0.3426,
      "step": 75,
      "student_loss": 0.0022108303382992744,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02306805074971165,
      "grad_norm": 13.4375,
      "kd_loss": 0.004479927476495504,
      "learning_rate": 8.777777777777778e-06,
      "loss": 0.3733,
      "step": 80,
      "student_loss": 0.0041625467129051685,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.024509803921568627,
      "grad_norm": 19.5,
      "kd_loss": 0.003717327257618308,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.2466,
      "step": 85,
      "student_loss": 0.0008013551123440266,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.025951557093425604,
      "grad_norm": 8.4375,
      "kd_loss": 0.3134710490703583,
      "learning_rate": 9.88888888888889e-06,
      "loss": 0.2059,
      "step": 90,
      "student_loss": 0.016512297093868256,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.027393310265282585,
      "grad_norm": 42.0,
      "kd_loss": 0.0037511922419071198,
      "learning_rate": 9.99995337991255e-06,
      "loss": 0.1824,
      "step": 95,
      "student_loss": 0.014032241888344288,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.02883506343713956,
      "grad_norm": 42.75,
      "kd_loss": 0.0027243352960795164,
      "learning_rate": 9.999763987297266e-06,
      "loss": 0.1423,
      "step": 100,
      "student_loss": 0.0006586164236068726,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03027681660899654,
      "grad_norm": 22.75,
      "kd_loss": 0.007741209119558334,
      "learning_rate": 9.999428913912876e-06,
      "loss": 0.1432,
      "step": 105,
      "student_loss": 0.006049849092960358,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.031718569780853516,
      "grad_norm": 8.0,
      "kd_loss": 0.002043877262622118,
      "learning_rate": 9.998948169522587e-06,
      "loss": 0.2012,
      "step": 110,
      "student_loss": 0.03380074352025986,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03316032295271049,
      "grad_norm": 12.9375,
      "kd_loss": 0.13418245315551758,
      "learning_rate": 9.998321768134101e-06,
      "loss": 0.1955,
      "step": 115,
      "student_loss": 0.0011221985332667828,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03460207612456748,
      "grad_norm": 5.5,
      "kd_loss": 0.00385228986851871,
      "learning_rate": 9.997549727999212e-06,
      "loss": 0.1011,
      "step": 120,
      "student_loss": 0.0008886058931238949,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.036043829296424454,
      "grad_norm": 21.75,
      "kd_loss": 0.8833059072494507,
      "learning_rate": 9.996632071613257e-06,
      "loss": 0.1431,
      "step": 125,
      "student_loss": 0.037908557802438736,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03748558246828143,
      "grad_norm": 22.75,
      "kd_loss": 0.0020795725286006927,
      "learning_rate": 9.995568825714479e-06,
      "loss": 0.2122,
      "step": 130,
      "student_loss": 0.0007846044027246535,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.03892733564013841,
      "grad_norm": 27.5,
      "kd_loss": 0.6685954928398132,
      "learning_rate": 9.994360021283235e-06,
      "loss": 0.1744,
      "step": 135,
      "student_loss": 0.03987047076225281,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.040369088811995385,
      "grad_norm": 6.34375,
      "kd_loss": 0.0027170090470463037,
      "learning_rate": 9.993005693541098e-06,
      "loss": 0.1217,
      "step": 140,
      "student_loss": 0.0007884247461333871,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04181084198385236,
      "grad_norm": 15.625,
      "kd_loss": 0.7305672764778137,
      "learning_rate": 9.991505881949837e-06,
      "loss": 0.1177,
      "step": 145,
      "student_loss": 0.032465774565935135,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04325259515570934,
      "grad_norm": 11.9375,
      "kd_loss": 0.0009196309256367385,
      "learning_rate": 9.989860630210251e-06,
      "loss": 0.1145,
      "step": 150,
      "student_loss": 0.0006800334667786956,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04469434832756632,
      "grad_norm": 3.75,
      "kd_loss": 0.0008867154247127473,
      "learning_rate": 9.98806998626091e-06,
      "loss": 0.1703,
      "step": 155,
      "student_loss": 0.000513731618411839,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0461361014994233,
      "grad_norm": 13.5625,
      "kd_loss": 0.0031801851000636816,
      "learning_rate": 9.98613400227676e-06,
      "loss": 0.1881,
      "step": 160,
      "student_loss": 0.095796138048172,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.04757785467128028,
      "grad_norm": 8.75,
      "kd_loss": 0.009066148661077023,
      "learning_rate": 9.984052734667586e-06,
      "loss": 0.147,
      "step": 165,
      "student_loss": 0.00036973567330278456,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.049019607843137254,
      "grad_norm": 19.875,
      "kd_loss": 0.0007732495432719588,
      "learning_rate": 9.981826244076387e-06,
      "loss": 0.1159,
      "step": 170,
      "student_loss": 0.0006115734577178955,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05046136101499423,
      "grad_norm": 17.75,
      "kd_loss": 0.001440449501387775,
      "learning_rate": 9.979454595377594e-06,
      "loss": 0.1439,
      "step": 175,
      "student_loss": 0.0018107936484739184,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05190311418685121,
      "grad_norm": 12.6875,
      "kd_loss": 0.003575589507818222,
      "learning_rate": 9.97693785767519e-06,
      "loss": 0.0823,
      "step": 180,
      "student_loss": 0.0005937832174822688,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05334486735870819,
      "grad_norm": 13.8125,
      "kd_loss": 0.002183184027671814,
      "learning_rate": 9.9742761043007e-06,
      "loss": 0.2085,
      "step": 185,
      "student_loss": 0.058680690824985504,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05478662053056517,
      "grad_norm": 7.9375,
      "kd_loss": 0.13934114575386047,
      "learning_rate": 9.971469412811032e-06,
      "loss": 0.1039,
      "step": 190,
      "student_loss": 0.003180636093020439,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.056228373702422146,
      "grad_norm": 14.5625,
      "kd_loss": 0.2642575800418854,
      "learning_rate": 9.968517864986247e-06,
      "loss": 0.0963,
      "step": 195,
      "student_loss": 0.023328492417931557,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.05767012687427912,
      "grad_norm": 6.1875,
      "kd_loss": 0.0009822066640481353,
      "learning_rate": 9.965421546827153e-06,
      "loss": 0.1046,
      "step": 200,
      "student_loss": 0.000694891030434519,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0591118800461361,
      "grad_norm": 13.5,
      "kd_loss": 0.0020439866930246353,
      "learning_rate": 9.962180548552812e-06,
      "loss": 0.0897,
      "step": 205,
      "student_loss": 0.042425841093063354,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06055363321799308,
      "grad_norm": 5.6875,
      "kd_loss": 0.06946802884340286,
      "learning_rate": 9.958794964597906e-06,
      "loss": 0.0994,
      "step": 210,
      "student_loss": 0.0007058735354803503,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.061995386389850055,
      "grad_norm": 8.75,
      "kd_loss": 0.0022037022281438112,
      "learning_rate": 9.955264893609986e-06,
      "loss": 0.1323,
      "step": 215,
      "student_loss": 0.0006759354146197438,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06343713956170703,
      "grad_norm": 23.5,
      "kd_loss": 0.11546128988265991,
      "learning_rate": 9.951590438446597e-06,
      "loss": 0.108,
      "step": 220,
      "student_loss": 0.04613906517624855,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06487889273356401,
      "grad_norm": 11.0,
      "kd_loss": 0.006272319238632917,
      "learning_rate": 9.947771706172285e-06,
      "loss": 0.1205,
      "step": 225,
      "student_loss": 0.03350772336125374,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06632064590542099,
      "grad_norm": 24.25,
      "kd_loss": 0.26141810417175293,
      "learning_rate": 9.943808808055472e-06,
      "loss": 0.0788,
      "step": 230,
      "student_loss": 0.003604925936087966,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06776239907727798,
      "grad_norm": 15.6875,
      "kd_loss": 0.6798978447914124,
      "learning_rate": 9.93970185956522e-06,
      "loss": 0.0869,
      "step": 235,
      "student_loss": 0.015447350218892097,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 1.71875,
      "kd_loss": 0.003386611584573984,
      "learning_rate": 9.93545098036786e-06,
      "loss": 0.1246,
      "step": 240,
      "student_loss": 0.0006252449820749462,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07064590542099193,
      "grad_norm": 21.25,
      "kd_loss": 0.2356187403202057,
      "learning_rate": 9.931056294323507e-06,
      "loss": 0.146,
      "step": 245,
      "student_loss": 0.0012863262090831995,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07208765859284891,
      "grad_norm": 12.9375,
      "kd_loss": 0.0037490571849048138,
      "learning_rate": 9.926517929482454e-06,
      "loss": 0.1485,
      "step": 250,
      "student_loss": 0.00040524674113839865,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 21.125,
      "kd_loss": 0.0018789542373269796,
      "learning_rate": 9.921836018081438e-06,
      "loss": 0.056,
      "step": 255,
      "student_loss": 0.0003012118686456233,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07497116493656286,
      "grad_norm": 10.25,
      "kd_loss": 0.008267119526863098,
      "learning_rate": 9.917010696539793e-06,
      "loss": 0.2125,
      "step": 260,
      "student_loss": 0.04526061564683914,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07641291810841984,
      "grad_norm": 4.8125,
      "kd_loss": 0.0011836340418085456,
      "learning_rate": 9.912042105455462e-06,
      "loss": 0.1144,
      "step": 265,
      "student_loss": 0.00038986533763818443,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07785467128027682,
      "grad_norm": 12.875,
      "kd_loss": 0.0008742965874262154,
      "learning_rate": 9.906930389600917e-06,
      "loss": 0.1514,
      "step": 270,
      "student_loss": 0.0005801369552500546,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.07929642445213379,
      "grad_norm": 17.75,
      "kd_loss": 0.0008876683423295617,
      "learning_rate": 9.901675697918925e-06,
      "loss": 0.1775,
      "step": 275,
      "student_loss": 0.053293921053409576,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08073817762399077,
      "grad_norm": 26.75,
      "kd_loss": 0.002074585296213627,
      "learning_rate": 9.896278183518216e-06,
      "loss": 0.1494,
      "step": 280,
      "student_loss": 0.004262140020728111,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08217993079584775,
      "grad_norm": 7.65625,
      "kd_loss": 0.0025187216233462095,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.1171,
      "step": 285,
      "student_loss": 0.0007169336313381791,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08362168396770472,
      "grad_norm": 21.375,
      "kd_loss": 0.007369345054030418,
      "learning_rate": 9.885055319798514e-06,
      "loss": 0.1821,
      "step": 290,
      "student_loss": 0.0005684102652594447,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0850634371395617,
      "grad_norm": 16.0,
      "kd_loss": 0.006104703992605209,
      "learning_rate": 9.879230297486034e-06,
      "loss": 0.1704,
      "step": 295,
      "student_loss": 0.0010396749712526798,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08650519031141868,
      "grad_norm": 23.375,
      "kd_loss": 0.08903778344392776,
      "learning_rate": 9.873263106458353e-06,
      "loss": 0.1398,
      "step": 300,
      "student_loss": 0.014311299659311771,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08794694348327567,
      "grad_norm": 21.125,
      "kd_loss": 0.003498164936900139,
      "learning_rate": 9.86715392058467e-06,
      "loss": 0.1304,
      "step": 305,
      "student_loss": 0.018731793388724327,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.08938869665513265,
      "grad_norm": 22.25,
      "kd_loss": 0.0002319709019502625,
      "learning_rate": 9.860902917871566e-06,
      "loss": 0.1595,
      "step": 310,
      "student_loss": 0.0005537475226446986,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09083044982698962,
      "grad_norm": 28.125,
      "kd_loss": 0.012743989005684853,
      "learning_rate": 9.854510280457819e-06,
      "loss": 0.1062,
      "step": 315,
      "student_loss": 0.012689951807260513,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.0922722029988466,
      "grad_norm": 18.625,
      "kd_loss": 0.0014882351970300078,
      "learning_rate": 9.847976194609083e-06,
      "loss": 0.1479,
      "step": 320,
      "student_loss": 0.0005163275054655969,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09371395617070358,
      "grad_norm": 22.625,
      "kd_loss": 0.3226740062236786,
      "learning_rate": 9.841300850712479e-06,
      "loss": 0.1206,
      "step": 325,
      "student_loss": 0.005041609983891249,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09515570934256055,
      "grad_norm": 10.125,
      "kd_loss": 0.4770796298980713,
      "learning_rate": 9.834484443271035e-06,
      "loss": 0.0984,
      "step": 330,
      "student_loss": 0.015074173919856548,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09659746251441753,
      "grad_norm": 13.25,
      "kd_loss": 0.000536711944732815,
      "learning_rate": 9.827527170898019e-06,
      "loss": 0.0722,
      "step": 335,
      "student_loss": 0.0006227240664884448,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 26.0,
      "kd_loss": 0.12674546241760254,
      "learning_rate": 9.820429236311158e-06,
      "loss": 0.1458,
      "step": 340,
      "student_loss": 0.012428171001374722,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.09948096885813149,
      "grad_norm": 8.375,
      "kd_loss": 0.0027160593308508396,
      "learning_rate": 9.81319084632673e-06,
      "loss": 0.1197,
      "step": 345,
      "student_loss": 0.01698848232626915,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10092272202998846,
      "grad_norm": 25.5,
      "kd_loss": 0.2688156068325043,
      "learning_rate": 9.805812211853534e-06,
      "loss": 0.0684,
      "step": 350,
      "student_loss": 0.006060065235942602,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10236447520184544,
      "grad_norm": 26.0,
      "kd_loss": 0.0023566237650811672,
      "learning_rate": 9.798293547886748e-06,
      "loss": 0.1159,
      "step": 355,
      "student_loss": 0.0004638656973838806,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10380622837370242,
      "grad_norm": 9.125,
      "kd_loss": 0.004494955763220787,
      "learning_rate": 9.790635073501662e-06,
      "loss": 0.082,
      "step": 360,
      "student_loss": 0.0004987778957001865,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1052479815455594,
      "grad_norm": 10.375,
      "kd_loss": 0.0029149462934583426,
      "learning_rate": 9.782837011847294e-06,
      "loss": 0.1926,
      "step": 365,
      "student_loss": 0.043784309178590775,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10668973471741638,
      "grad_norm": 24.625,
      "kd_loss": 0.07756392657756805,
      "learning_rate": 9.774899590139897e-06,
      "loss": 0.0849,
      "step": 370,
      "student_loss": 0.01941766031086445,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10813148788927336,
      "grad_norm": 13.125,
      "kd_loss": 0.00261987978592515,
      "learning_rate": 9.766823039656328e-06,
      "loss": 0.1517,
      "step": 375,
      "student_loss": 0.03552848473191261,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.10957324106113034,
      "grad_norm": 6.28125,
      "kd_loss": 0.0021297987550497055,
      "learning_rate": 9.758607595727309e-06,
      "loss": 0.1632,
      "step": 380,
      "student_loss": 0.0005093910149298608,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11101499423298732,
      "grad_norm": 28.125,
      "kd_loss": 0.012473474256694317,
      "learning_rate": 9.75025349773058e-06,
      "loss": 0.1271,
      "step": 385,
      "student_loss": 0.00041385076474398375,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11245674740484429,
      "grad_norm": 24.375,
      "kd_loss": 0.0008915087673813105,
      "learning_rate": 9.741760989083914e-06,
      "loss": 0.0936,
      "step": 390,
      "student_loss": 0.00028736997046507895,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11389850057670127,
      "grad_norm": 12.875,
      "kd_loss": 0.007614473812282085,
      "learning_rate": 9.73313031723803e-06,
      "loss": 0.0901,
      "step": 395,
      "student_loss": 0.0005106693133711815,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11534025374855825,
      "grad_norm": 11.25,
      "kd_loss": 0.00347925559617579,
      "learning_rate": 9.724361733669383e-06,
      "loss": 0.0546,
      "step": 400,
      "student_loss": 0.0008912020130082965,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11678200692041522,
      "grad_norm": 8.0625,
      "kd_loss": 0.0011954058427363634,
      "learning_rate": 9.715455493872827e-06,
      "loss": 0.1324,
      "step": 405,
      "student_loss": 0.004991908557713032,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1182237600922722,
      "grad_norm": 9.1875,
      "kd_loss": 0.0025417145807296038,
      "learning_rate": 9.70641185735419e-06,
      "loss": 0.1483,
      "step": 410,
      "student_loss": 0.01691470481455326,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.11966551326412918,
      "grad_norm": 13.3125,
      "kd_loss": 0.003752017393708229,
      "learning_rate": 9.697231087622691e-06,
      "loss": 0.1511,
      "step": 415,
      "student_loss": 0.0010631532641127706,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12110726643598616,
      "grad_norm": 10.9375,
      "kd_loss": 0.2554698586463928,
      "learning_rate": 9.687913452183277e-06,
      "loss": 0.1095,
      "step": 420,
      "student_loss": 0.06524818390607834,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12254901960784313,
      "grad_norm": 9.125,
      "kd_loss": 0.0005501045961864293,
      "learning_rate": 9.678459222528825e-06,
      "loss": 0.0577,
      "step": 425,
      "student_loss": 0.0013150365557521582,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12399077277970011,
      "grad_norm": 10.0625,
      "kd_loss": 0.00420792680233717,
      "learning_rate": 9.668868674132224e-06,
      "loss": 0.1381,
      "step": 430,
      "student_loss": 0.05358680710196495,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1254325259515571,
      "grad_norm": 14.625,
      "kd_loss": 0.0016143789980560541,
      "learning_rate": 9.65914208643836e-06,
      "loss": 0.0654,
      "step": 435,
      "student_loss": 0.000772066181525588,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12687427912341406,
      "grad_norm": 7.15625,
      "kd_loss": 0.0023973328061401844,
      "learning_rate": 9.649279742855964e-06,
      "loss": 0.1371,
      "step": 440,
      "student_loss": 0.025605041533708572,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12831603229527105,
      "grad_norm": 23.0,
      "kd_loss": 0.0013417273294180632,
      "learning_rate": 9.639281930749363e-06,
      "loss": 0.0814,
      "step": 445,
      "student_loss": 0.03157199174165726,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.12975778546712802,
      "grad_norm": 13.25,
      "kd_loss": 0.0016620807582512498,
      "learning_rate": 9.629148941430096e-06,
      "loss": 0.1442,
      "step": 450,
      "student_loss": 0.0006721625686623156,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.131199538638985,
      "grad_norm": 28.0,
      "kd_loss": 0.0016946454998105764,
      "learning_rate": 9.618881070148436e-06,
      "loss": 0.1405,
      "step": 455,
      "student_loss": 0.0009172292775474489,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13264129181084197,
      "grad_norm": 10.125,
      "kd_loss": 0.027760690078139305,
      "learning_rate": 9.608478616084784e-06,
      "loss": 0.0505,
      "step": 460,
      "student_loss": 0.0005534313968382776,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13408304498269896,
      "grad_norm": 14.25,
      "kd_loss": 0.008209657855331898,
      "learning_rate": 9.597941882340947e-06,
      "loss": 0.1803,
      "step": 465,
      "student_loss": 0.000469625141704455,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13552479815455595,
      "grad_norm": 13.4375,
      "kd_loss": 0.0006104095955379307,
      "learning_rate": 9.587271175931313e-06,
      "loss": 0.1148,
      "step": 470,
      "student_loss": 0.00037698415690101683,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13696655132641292,
      "grad_norm": 6.5625,
      "kd_loss": 0.012027841061353683,
      "learning_rate": 9.5764668077739e-06,
      "loss": 0.0626,
      "step": 475,
      "student_loss": 0.0005685262149199843,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 9.0625,
      "kd_loss": 0.0022413916885852814,
      "learning_rate": 9.5655290926813e-06,
      "loss": 0.099,
      "step": 480,
      "student_loss": 0.012239435687661171,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.13985005767012687,
      "grad_norm": 25.75,
      "kd_loss": 0.0016755703836679459,
      "learning_rate": 9.554458349351507e-06,
      "loss": 0.0891,
      "step": 485,
      "student_loss": 0.027401834726333618,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14129181084198386,
      "grad_norm": 29.875,
      "kd_loss": 0.46647658944129944,
      "learning_rate": 9.54325490035863e-06,
      "loss": 0.1581,
      "step": 490,
      "student_loss": 0.0034644226543605328,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14273356401384082,
      "grad_norm": 12.0,
      "kd_loss": 0.10091336816549301,
      "learning_rate": 9.531919072143488e-06,
      "loss": 0.1283,
      "step": 495,
      "student_loss": 0.0010429032845422626,
      "teacher_loss": 0.0
    },
    {
      "epoch": 0.14417531718569782,
      "grad_norm": 18.125,
      "kd_loss": 0.25293171405792236,
      "learning_rate": 9.520451195004107e-06,
      "loss": 0.0874,
      "step": 500,
      "student_loss": 0.0008772966684773564,
      "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
}