{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 100.0,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025,
      "grad_norm": 0.09379793703556061,
      "learning_rate": 5.999999999999999e-06,
      "loss": 0.6799,
      "step": 5
    },
    {
      "epoch": 0.005,
      "grad_norm": 0.1399833709001541,
      "learning_rate": 1.3499999999999998e-05,
      "loss": 0.6954,
      "step": 10
    },
    {
      "epoch": 0.0075,
      "grad_norm": 0.08632303029298782,
      "learning_rate": 2.1e-05,
      "loss": 0.6921,
      "step": 15
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.10006701201200485,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 0.69,
      "step": 20
    },
    {
      "epoch": 0.0125,
      "grad_norm": 0.07633858919143677,
      "learning_rate": 3.5999999999999994e-05,
      "loss": 0.6722,
      "step": 25
    },
    {
      "epoch": 0.015,
      "grad_norm": 0.09399061650037766,
      "learning_rate": 4.3499999999999993e-05,
      "loss": 0.6453,
      "step": 30
    },
    {
      "epoch": 0.0175,
      "grad_norm": 0.0843738541007042,
      "learning_rate": 5.1e-05,
      "loss": 0.6276,
      "step": 35
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.08583351224660873,
      "learning_rate": 5.85e-05,
      "loss": 0.58,
      "step": 40
    },
    {
      "epoch": 0.0225,
      "grad_norm": 0.09571370482444763,
      "learning_rate": 6.599999999999999e-05,
      "loss": 0.6355,
      "step": 45
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.1083935871720314,
      "learning_rate": 7.35e-05,
      "loss": 0.589,
      "step": 50
    },
    {
      "epoch": 0.0275,
      "grad_norm": 0.10387319326400757,
      "learning_rate": 8.1e-05,
      "loss": 0.6061,
      "step": 55
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.11083361506462097,
      "learning_rate": 8.849999999999998e-05,
      "loss": 0.572,
      "step": 60
    },
    {
      "epoch": 0.0325,
      "grad_norm": 0.12665686011314392,
      "learning_rate": 9.599999999999999e-05,
      "loss": 0.5442,
      "step": 65
    },
    {
      "epoch": 0.035,
      "grad_norm": 0.1308053582906723,
      "learning_rate": 0.00010349999999999998,
      "loss": 0.6524,
      "step": 70
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.13535510003566742,
      "learning_rate": 0.00011099999999999999,
      "loss": 0.6404,
      "step": 75
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.12833671271800995,
      "learning_rate": 0.0001185,
      "loss": 0.5717,
      "step": 80
    },
    {
      "epoch": 0.0425,
      "grad_norm": 0.11962099373340607,
      "learning_rate": 0.00012599999999999997,
      "loss": 0.6098,
      "step": 85
    },
    {
      "epoch": 0.045,
      "grad_norm": 0.13898271322250366,
      "learning_rate": 0.0001335,
      "loss": 0.6099,
      "step": 90
    },
    {
      "epoch": 0.0475,
      "grad_norm": 0.14486610889434814,
      "learning_rate": 0.00014099999999999998,
      "loss": 0.5744,
      "step": 95
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.1432138830423355,
      "learning_rate": 0.00014849999999999998,
      "loss": 0.5659,
      "step": 100
    },
    {
      "epoch": 0.0525,
      "grad_norm": 0.13487878441810608,
      "learning_rate": 0.000156,
      "loss": 0.5622,
      "step": 105
    },
    {
      "epoch": 0.055,
      "grad_norm": 0.12495309859514236,
      "learning_rate": 0.0001635,
      "loss": 0.5951,
      "step": 110
    },
    {
      "epoch": 0.0575,
      "grad_norm": 0.13011734187602997,
      "learning_rate": 0.00017099999999999998,
      "loss": 0.6249,
      "step": 115
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.13987745344638824,
      "learning_rate": 0.00017849999999999997,
      "loss": 0.559,
      "step": 120
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.13373605906963348,
      "learning_rate": 0.000186,
      "loss": 0.5475,
      "step": 125
    },
    {
      "epoch": 0.065,
      "grad_norm": 0.12433867901563644,
      "learning_rate": 0.0001935,
      "loss": 0.5274,
      "step": 130
    },
    {
      "epoch": 0.0675,
      "grad_norm": 0.11097615957260132,
      "learning_rate": 0.000201,
      "loss": 0.678,
      "step": 135
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.1155027225613594,
      "learning_rate": 0.00020849999999999997,
      "loss": 0.5611,
      "step": 140
    },
    {
      "epoch": 0.0725,
      "grad_norm": 0.11431068181991577,
      "learning_rate": 0.00021599999999999996,
      "loss": 0.6054,
      "step": 145
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.09796140342950821,
      "learning_rate": 0.00022349999999999998,
      "loss": 0.5472,
      "step": 150
    },
    {
      "epoch": 0.0775,
      "grad_norm": 0.09489257633686066,
      "learning_rate": 0.00023099999999999998,
      "loss": 0.4636,
      "step": 155
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.10787788033485413,
      "learning_rate": 0.0002385,
      "loss": 0.6164,
      "step": 160
    },
    {
      "epoch": 0.0825,
      "grad_norm": 0.10261733084917068,
      "learning_rate": 0.00024599999999999996,
      "loss": 0.5408,
      "step": 165
    },
    {
      "epoch": 0.085,
      "grad_norm": 0.11870352178812027,
      "learning_rate": 0.0002535,
      "loss": 0.5268,
      "step": 170
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.11910569667816162,
      "learning_rate": 0.000261,
      "loss": 0.5461,
      "step": 175
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.10083702206611633,
      "learning_rate": 0.00026849999999999997,
      "loss": 0.4794,
      "step": 180
    },
    {
      "epoch": 0.0925,
      "grad_norm": 0.10453511029481888,
      "learning_rate": 0.000276,
      "loss": 0.5539,
      "step": 185
    },
    {
      "epoch": 0.095,
      "grad_norm": 0.101403146982193,
      "learning_rate": 0.00028349999999999995,
      "loss": 0.5346,
      "step": 190
    },
    {
      "epoch": 0.0975,
      "grad_norm": 0.10724789649248123,
      "learning_rate": 0.00029099999999999997,
      "loss": 0.6026,
      "step": 195
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.1140277311205864,
      "learning_rate": 0.0002985,
      "loss": 0.5193,
      "step": 200
    },
    {
      "epoch": 0.1025,
      "grad_norm": 0.09706108272075653,
      "learning_rate": 0.0002999963446058092,
      "loss": 0.54,
      "step": 205
    },
    {
      "epoch": 0.105,
      "grad_norm": 0.10003062337636948,
      "learning_rate": 0.0002999814948722491,
      "loss": 0.5365,
      "step": 210
    },
    {
      "epoch": 0.1075,
      "grad_norm": 0.1078687533736229,
      "learning_rate": 0.00029995522346717746,
      "loss": 0.5889,
      "step": 215
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.10538115352392197,
      "learning_rate": 0.0002999175323912636,
      "loss": 0.5611,
      "step": 220
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.1020808294415474,
      "learning_rate": 0.00029986842451482874,
      "loss": 0.6103,
      "step": 225
    },
    {
      "epoch": 0.115,
      "grad_norm": 0.09635835886001587,
      "learning_rate": 0.0002998079035776279,
      "loss": 0.5229,
      "step": 230
    },
    {
      "epoch": 0.1175,
      "grad_norm": 0.10287190228700638,
      "learning_rate": 0.0002997359741885648,
      "loss": 0.5312,
      "step": 235
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.09160075336694717,
      "learning_rate": 0.0002996526418253408,
      "loss": 0.5673,
      "step": 240
    },
    {
      "epoch": 0.1225,
      "grad_norm": 0.08691006153821945,
      "learning_rate": 0.000299557912834038,
      "loss": 0.5326,
      "step": 245
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.10096988826990128,
      "learning_rate": 0.00029945179442863594,
      "loss": 0.6004,
      "step": 250
    },
    {
      "epoch": 0.1275,
      "grad_norm": 0.09594204276800156,
      "learning_rate": 0.000299334294690462,
      "loss": 0.5516,
      "step": 255
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.10281919687986374,
      "learning_rate": 0.00029920542256757607,
      "loss": 0.5515,
      "step": 260
    },
    {
      "epoch": 0.1325,
      "grad_norm": 0.08547840267419815,
      "learning_rate": 0.00029906518787408944,
      "loss": 0.5243,
      "step": 265
    },
    {
      "epoch": 0.135,
      "grad_norm": 0.10161560773849487,
      "learning_rate": 0.0002989136012894168,
      "loss": 0.5096,
      "step": 270
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.09101904183626175,
      "learning_rate": 0.0002987506743574635,
      "loss": 0.553,
      "step": 275
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.09769442677497864,
      "learning_rate": 0.0002985764194857463,
      "loss": 0.4953,
      "step": 280
    },
    {
      "epoch": 0.1425,
      "grad_norm": 0.10991579294204712,
      "learning_rate": 0.00029839084994444826,
      "loss": 0.5152,
      "step": 285
    },
    {
      "epoch": 0.145,
      "grad_norm": 0.09450916200876236,
      "learning_rate": 0.00029819397986540836,
      "loss": 0.5397,
      "step": 290
    },
    {
      "epoch": 0.1475,
      "grad_norm": 0.10876069217920303,
      "learning_rate": 0.0002979858242410454,
      "loss": 0.4858,
      "step": 295
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.097995825111866,
      "learning_rate": 0.00029776639892321606,
      "loss": 0.5566,
      "step": 300
    },
    {
      "epoch": 0.1525,
      "grad_norm": 0.1145048514008522,
      "learning_rate": 0.0002975357206220079,
      "loss": 0.4531,
      "step": 305
    },
    {
      "epoch": 0.155,
      "grad_norm": 0.10271880775690079,
      "learning_rate": 0.00029729380690446654,
      "loss": 0.5199,
      "step": 310
    },
    {
      "epoch": 0.1575,
      "grad_norm": 0.11095371842384338,
      "learning_rate": 0.0002970406761932583,
      "loss": 0.5416,
      "step": 315
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09949438273906708,
      "learning_rate": 0.00029677634776526673,
      "loss": 0.4841,
      "step": 320
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.1163724958896637,
      "learning_rate": 0.00029650084175012517,
      "loss": 0.4913,
      "step": 325
    },
    {
      "epoch": 0.165,
      "grad_norm": 0.10726840049028397,
      "learning_rate": 0.00029621417912868323,
      "loss": 0.5203,
      "step": 330
    },
    {
      "epoch": 0.1675,
      "grad_norm": 0.09609931707382202,
      "learning_rate": 0.00029591638173140947,
      "loss": 0.5607,
      "step": 335
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.10824442654848099,
      "learning_rate": 0.0002956074722367286,
      "loss": 0.6004,
      "step": 340
    },
    {
      "epoch": 0.1725,
      "grad_norm": 0.10465679317712784,
      "learning_rate": 0.00029528747416929463,
      "loss": 0.5216,
      "step": 345
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.10518354922533035,
      "learning_rate": 0.0002949564118981994,
      "loss": 0.499,
      "step": 350
    },
    {
      "epoch": 0.1775,
      "grad_norm": 0.0955279991030693,
      "learning_rate": 0.0002946143106351165,
      "loss": 0.5607,
      "step": 355
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.11159654706716537,
      "learning_rate": 0.0002942611964323817,
      "loss": 0.5204,
      "step": 360
    },
    {
      "epoch": 0.1825,
      "grad_norm": 0.09571187198162079,
      "learning_rate": 0.0002938970961810086,
      "loss": 0.6113,
      "step": 365
    },
    {
      "epoch": 0.185,
      "grad_norm": 0.11854679882526398,
      "learning_rate": 0.0002935220376086411,
      "loss": 0.5639,
      "step": 370
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.1050512045621872,
      "learning_rate": 0.0002931360492774415,
      "loss": 0.548,
      "step": 375
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.1053968220949173,
      "learning_rate": 0.0002927391605819157,
      "loss": 0.5507,
      "step": 380
    },
    {
      "epoch": 0.1925,
      "grad_norm": 0.10567320138216019,
      "learning_rate": 0.00029233140174667445,
      "loss": 0.5312,
      "step": 385
    },
    {
      "epoch": 0.195,
      "grad_norm": 0.11914283782243729,
      "learning_rate": 0.0002919128038241318,
      "loss": 0.5961,
      "step": 390
    },
    {
      "epoch": 0.1975,
      "grad_norm": 0.09915795922279358,
      "learning_rate": 0.0002914833986921401,
      "loss": 0.5086,
      "step": 395
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.10796502232551575,
      "learning_rate": 0.0002910432190515628,
      "loss": 0.5585,
      "step": 400
    },
    {
      "epoch": 0.2025,
      "grad_norm": 0.10748997330665588,
      "learning_rate": 0.00029059229842378373,
      "loss": 0.5466,
      "step": 405
    },
    {
      "epoch": 0.205,
      "grad_norm": 0.10696308314800262,
      "learning_rate": 0.0002901306711481544,
      "loss": 0.5513,
      "step": 410
    },
    {
      "epoch": 0.2075,
      "grad_norm": 0.10418657958507538,
      "learning_rate": 0.0002896583723793792,
      "loss": 0.5391,
      "step": 415
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.16421550512313843,
      "learning_rate": 0.00028917543808483796,
      "loss": 0.4699,
      "step": 420
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.12929962575435638,
      "learning_rate": 0.00028868190504184696,
      "loss": 0.4984,
      "step": 425
    },
    {
      "epoch": 0.215,
      "grad_norm": 0.10469454526901245,
      "learning_rate": 0.00028817781083485816,
      "loss": 0.5119,
      "step": 430
    },
    {
      "epoch": 0.2175,
      "grad_norm": 0.0964970663189888,
      "learning_rate": 0.00028766319385259713,
      "loss": 0.5167,
      "step": 435
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.12395574152469635,
      "learning_rate": 0.00028713809328513953,
      "loss": 0.5692,
      "step": 440
    },
    {
      "epoch": 0.2225,
      "grad_norm": 0.10189738124608994,
      "learning_rate": 0.0002866025491209265,
      "loss": 0.4628,
      "step": 445
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.10433454066514969,
      "learning_rate": 0.0002860566021437197,
      "loss": 0.4869,
      "step": 450
    },
    {
      "epoch": 0.2275,
      "grad_norm": 0.13003456592559814,
      "learning_rate": 0.0002855002939294951,
      "loss": 0.5291,
      "step": 455
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.11692202836275101,
      "learning_rate": 0.000284933666843277,
      "loss": 0.5229,
      "step": 460
    },
    {
      "epoch": 0.2325,
      "grad_norm": 0.10757846385240555,
      "learning_rate": 0.0002843567640359119,
      "loss": 0.435,
      "step": 465
    },
    {
      "epoch": 0.235,
      "grad_norm": 0.10775501281023026,
      "learning_rate": 0.00028376962944078206,
      "loss": 0.4418,
      "step": 470
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.11543692648410797,
      "learning_rate": 0.00028317230777046015,
      "loss": 0.4204,
      "step": 475
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.10946698486804962,
      "learning_rate": 0.00028256484451330403,
      "loss": 0.49,
      "step": 480
    },
    {
      "epoch": 0.2425,
      "grad_norm": 0.11528221517801285,
      "learning_rate": 0.00028194728592999247,
      "loss": 0.4752,
      "step": 485
    },
    {
      "epoch": 0.245,
      "grad_norm": 0.10474205762147903,
      "learning_rate": 0.0002813196790500027,
      "loss": 0.4847,
      "step": 490
    },
    {
      "epoch": 0.2475,
      "grad_norm": 0.10768820345401764,
      "learning_rate": 0.00028068207166802837,
      "loss": 0.4664,
      "step": 495
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.12158560007810593,
      "learning_rate": 0.00028003451234034037,
      "loss": 0.4741,
      "step": 500
    },
    {
      "epoch": 0.2525,
      "grad_norm": 0.11635497957468033,
      "learning_rate": 0.0002793770503810886,
      "loss": 0.4969,
      "step": 505
    },
    {
      "epoch": 0.255,
      "grad_norm": 0.12205849587917328,
      "learning_rate": 0.00027870973585854665,
      "loss": 0.4798,
      "step": 510
    },
    {
      "epoch": 0.2575,
      "grad_norm": 0.10270871222019196,
      "learning_rate": 0.00027803261959129905,
      "loss": 0.3888,
      "step": 515
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.11313367635011673,
      "learning_rate": 0.0002773457531443712,
      "loss": 0.4759,
      "step": 520
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.12905193865299225,
      "learning_rate": 0.00027664918882530225,
      "loss": 0.4442,
      "step": 525
    },
    {
      "epoch": 0.265,
      "grad_norm": 0.11690939962863922,
      "learning_rate": 0.00027594297968016197,
      "loss": 0.5535,
      "step": 530
    },
    {
      "epoch": 0.2675,
      "grad_norm": 0.10021405667066574,
      "learning_rate": 0.00027522717948951094,
      "loss": 0.4717,
      "step": 535
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.10104178637266159,
      "learning_rate": 0.0002745018427643051,
      "loss": 0.4906,
      "step": 540
    },
    {
      "epoch": 0.2725,
      "grad_norm": 0.12113891541957855,
      "learning_rate": 0.00027376702474174425,
      "loss": 0.5674,
      "step": 545
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.11330476403236389,
      "learning_rate": 0.0002730227813810658,
      "loss": 0.5184,
      "step": 550
    },
    {
      "epoch": 0.2775,
      "grad_norm": 0.1025850847363472,
      "learning_rate": 0.0002722691693592831,
      "loss": 0.4395,
      "step": 555
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.11591499298810959,
      "learning_rate": 0.0002715062460668694,
      "loss": 0.5003,
      "step": 560
    },
    {
      "epoch": 0.2825,
      "grad_norm": 0.11281153559684753,
      "learning_rate": 0.0002707340696033871,
      "loss": 0.4672,
      "step": 565
    },
    {
      "epoch": 0.285,
      "grad_norm": 0.1123538464307785,
      "learning_rate": 0.00026995269877306356,
      "loss": 0.513,
      "step": 570
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.10776390135288239,
      "learning_rate": 0.0002691621930803127,
      "loss": 0.4572,
      "step": 575
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.10008667409420013,
      "learning_rate": 0.0002683626127252036,
      "loss": 0.4618,
      "step": 580
    },
    {
      "epoch": 0.2925,
      "grad_norm": 0.13961340487003326,
      "learning_rate": 0.00026755401859887595,
      "loss": 0.4819,
      "step": 585
    },
    {
      "epoch": 0.295,
      "grad_norm": 0.1476685106754303,
      "learning_rate": 0.00026673647227890316,
      "loss": 0.4964,
      "step": 590
    },
    {
      "epoch": 0.2975,
      "grad_norm": 0.09795507788658142,
      "learning_rate": 0.00026591003602460263,
      "loss": 0.4796,
      "step": 595
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.10903532058000565,
      "learning_rate": 0.00026507477277229496,
      "loss": 0.4775,
      "step": 600
    },
    {
      "epoch": 0.3025,
      "grad_norm": 0.10258448123931885,
      "learning_rate": 0.0002642307461305105,
      "loss": 0.4519,
      "step": 605
    },
    {
      "epoch": 0.305,
      "grad_norm": 0.11204435676336288,
      "learning_rate": 0.0002633780203751459,
      "loss": 0.4451,
      "step": 610
    },
    {
      "epoch": 0.3075,
      "grad_norm": 0.10147629678249359,
      "learning_rate": 0.0002625166604445689,
      "loss": 0.4256,
      "step": 615
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.10481107234954834,
      "learning_rate": 0.00026164673193467306,
      "loss": 0.4381,
      "step": 620
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.10856641829013824,
      "learning_rate": 0.00026076830109388255,
      "loss": 0.4958,
      "step": 625
    },
    {
      "epoch": 0.315,
      "grad_norm": 0.09918677806854248,
      "learning_rate": 0.0002598814348181068,
      "loss": 0.4335,
      "step": 630
    },
    {
      "epoch": 0.3175,
      "grad_norm": 0.10417389869689941,
      "learning_rate": 0.00025898620064564637,
      "loss": 0.4603,
      "step": 635
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.0903329998254776,
      "learning_rate": 0.00025808266675204954,
      "loss": 0.3932,
      "step": 640
    },
    {
      "epoch": 0.3225,
      "grad_norm": 0.11511855572462082,
      "learning_rate": 0.0002571709019449205,
      "loss": 0.4169,
      "step": 645
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.11355557292699814,
      "learning_rate": 0.0002562509756586793,
      "loss": 0.4455,
      "step": 650
    },
    {
      "epoch": 0.3275,
      "grad_norm": 0.1271187961101532,
      "learning_rate": 0.00025532295794927437,
      "loss": 0.4902,
      "step": 655
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.11936645954847336,
      "learning_rate": 0.0002543869194888471,
      "loss": 0.4843,
      "step": 660
    },
    {
      "epoch": 0.3325,
      "grad_norm": 0.11935465037822723,
      "learning_rate": 0.00025344293156035044,
      "loss": 0.4402,
      "step": 665
    },
    {
      "epoch": 0.335,
      "grad_norm": 0.13073407113552094,
      "learning_rate": 0.00025249106605211986,
      "loss": 0.467,
      "step": 670
    },
    {
      "epoch": 0.3375,
      "grad_norm": 0.10340435802936554,
      "learning_rate": 0.0002515313954523991,
      "loss": 0.4827,
      "step": 675
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.11634550243616104,
      "learning_rate": 0.00025056399284381983,
      "loss": 0.466,
      "step": 680
    },
    {
      "epoch": 0.3425,
      "grad_norm": 0.10582319647073746,
      "learning_rate": 0.0002495889318978362,
      "loss": 0.4751,
      "step": 685
    },
    {
      "epoch": 0.345,
      "grad_norm": 0.16781780123710632,
      "learning_rate": 0.00024860628686911436,
      "loss": 0.4717,
      "step": 690
    },
    {
      "epoch": 0.3475,
      "grad_norm": 0.11522196233272552,
      "learning_rate": 0.0002476161325898776,
      "loss": 0.4687,
      "step": 695
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.11830449104309082,
      "learning_rate": 0.000246618544464208,
      "loss": 0.436,
      "step": 700
    },
    {
      "epoch": 0.3525,
      "grad_norm": 0.17485427856445312,
      "learning_rate": 0.0002456135984623034,
      "loss": 0.4284,
      "step": 705
    },
    {
      "epoch": 0.355,
      "grad_norm": 0.12288108468055725,
      "learning_rate": 0.00024460137111469296,
      "loss": 0.4261,
      "step": 710
    },
    {
      "epoch": 0.3575,
      "grad_norm": 0.11587081104516983,
      "learning_rate": 0.0002435819395064079,
      "loss": 0.4493,
      "step": 715
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.10690271109342575,
      "learning_rate": 0.0002425553812711123,
      "loss": 0.4648,
      "step": 720
    },
    {
      "epoch": 0.3625,
      "grad_norm": 0.10404397547245026,
      "learning_rate": 0.00024152177458519014,
      "loss": 0.4634,
      "step": 725
    },
    {
      "epoch": 0.365,
      "grad_norm": 0.11986954510211945,
      "learning_rate": 0.00024048119816179236,
      "loss": 0.4525,
      "step": 730
    },
    {
      "epoch": 0.3675,
      "grad_norm": 0.10243026167154312,
      "learning_rate": 0.00023943373124484234,
      "loss": 0.4572,
      "step": 735
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.10386748611927032,
      "learning_rate": 0.00023837945360300129,
      "loss": 0.3884,
      "step": 740
    },
    {
      "epoch": 0.3725,
      "grad_norm": 0.11165735125541687,
      "learning_rate": 0.0002373184455235934,
      "loss": 0.4902,
      "step": 745
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.09951601922512054,
      "learning_rate": 0.00023625078780649178,
      "loss": 0.4541,
      "step": 750
    },
    {
      "epoch": 0.3775,
      "grad_norm": 0.10347504913806915,
      "learning_rate": 0.00023517656175796518,
      "loss": 0.3871,
      "step": 755
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.10478132963180542,
      "learning_rate": 0.00023409584918448627,
      "loss": 0.4329,
      "step": 760
    },
    {
      "epoch": 0.3825,
      "grad_norm": 0.1198212131857872,
      "learning_rate": 0.00023300873238650159,
      "loss": 0.425,
      "step": 765
    },
    {
      "epoch": 0.385,
      "grad_norm": 0.1103711724281311,
      "learning_rate": 0.00023191529415216434,
      "loss": 0.4274,
      "step": 770
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.09940385073423386,
      "learning_rate": 0.00023081561775102944,
      "loss": 0.4368,
      "step": 775
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.11599268019199371,
      "learning_rate": 0.00022970978692771242,
      "loss": 0.4386,
      "step": 780
    },
    {
      "epoch": 0.3925,
      "grad_norm": 0.10101296752691269,
      "learning_rate": 0.00022859788589551188,
      "loss": 0.4696,
      "step": 785
    },
    {
      "epoch": 0.395,
      "grad_norm": 0.10112808644771576,
      "learning_rate": 0.00022747999932999624,
      "loss": 0.4066,
      "step": 790
    },
    {
      "epoch": 0.3975,
      "grad_norm": 0.09595459699630737,
      "learning_rate": 0.00022635621236255567,
      "loss": 0.4837,
      "step": 795
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.10761380940675735,
      "learning_rate": 0.00022522661057391857,
      "loss": 0.5446,
      "step": 800
    },
    {
      "epoch": 0.4025,
      "grad_norm": 0.11919954419136047,
      "learning_rate": 0.00022409127998763463,
      "loss": 0.5027,
      "step": 805
    },
    {
      "epoch": 0.405,
      "grad_norm": 0.10851597785949707,
      "learning_rate": 0.00022295030706352356,
      "loss": 0.4481,
      "step": 810
    },
    {
      "epoch": 0.4075,
      "grad_norm": 0.10030311346054077,
      "learning_rate": 0.00022180377869109104,
      "loss": 0.4709,
      "step": 815
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.111280657351017,
      "learning_rate": 0.00022065178218291147,
      "loss": 0.4423,
      "step": 820
    },
    {
      "epoch": 0.4125,
      "grad_norm": 0.11253602802753448,
      "learning_rate": 0.00021949440526797926,
      "loss": 0.4136,
      "step": 825
    },
    {
      "epoch": 0.415,
      "grad_norm": 0.10805424302816391,
      "learning_rate": 0.00021833173608502732,
      "loss": 0.4656,
      "step": 830
    },
    {
      "epoch": 0.4175,
      "grad_norm": 0.10983198881149292,
      "learning_rate": 0.00021716386317581542,
      "loss": 0.3687,
      "step": 835
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.10653118044137955,
      "learning_rate": 0.00021599087547838727,
      "loss": 0.4654,
      "step": 840
    },
    {
      "epoch": 0.4225,
      "grad_norm": 0.10856354981660843,
      "learning_rate": 0.00021481286232029735,
      "loss": 0.4298,
      "step": 845
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.11233706772327423,
      "learning_rate": 0.0002136299134118085,
      "loss": 0.4484,
      "step": 850
    },
    {
      "epoch": 0.4275,
      "grad_norm": 0.1085442528128624,
      "learning_rate": 0.00021244211883906017,
      "loss": 0.4776,
      "step": 855
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.12297824025154114,
      "learning_rate": 0.0002112495690572077,
      "loss": 0.4029,
      "step": 860
    },
    {
      "epoch": 0.4325,
      "grad_norm": 0.10838114470243454,
      "learning_rate": 0.00021005235488353428,
      "loss": 0.4848,
      "step": 865
    },
    {
      "epoch": 0.435,
      "grad_norm": 0.10273341834545135,
      "learning_rate": 0.0002088505674905342,
      "loss": 0.3989,
      "step": 870
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.11189126968383789,
      "learning_rate": 0.0002076442983989705,
      "loss": 0.438,
      "step": 875
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.11592905968427658,
      "learning_rate": 0.0002064336394709048,
      "loss": 0.4786,
      "step": 880
    },
    {
      "epoch": 0.4425,
      "grad_norm": 0.11230389773845673,
      "learning_rate": 0.0002052186829027017,
      "loss": 0.3999,
      "step": 885
    },
    {
      "epoch": 0.445,
      "grad_norm": 0.12455113977193832,
      "learning_rate": 0.00020399952121800767,
      "loss": 0.4856,
      "step": 890
    },
    {
      "epoch": 0.4475,
      "grad_norm": 0.1001812294125557,
      "learning_rate": 0.00020277624726070526,
      "loss": 0.4689,
      "step": 895
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.11319112777709961,
      "learning_rate": 0.00020154895418784242,
      "loss": 0.3998,
      "step": 900
    },
    {
      "epoch": 0.4525,
      "grad_norm": 0.11322236061096191,
      "learning_rate": 0.00020031773546253824,
      "loss": 0.4321,
      "step": 905
    },
    {
      "epoch": 0.455,
      "grad_norm": 0.12924689054489136,
      "learning_rate": 0.00019908268484686558,
      "loss": 0.4208,
      "step": 910
    },
    {
      "epoch": 0.4575,
      "grad_norm": 0.11435618251562119,
      "learning_rate": 0.00019784389639471048,
      "loss": 0.4682,
      "step": 915
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.10801081359386444,
      "learning_rate": 0.00019660146444460975,
      "loss": 0.428,
      "step": 920
    },
    {
      "epoch": 0.4625,
      "grad_norm": 0.10906939953565598,
      "learning_rate": 0.0001953554836125667,
      "loss": 0.4455,
      "step": 925
    },
    {
      "epoch": 0.465,
      "grad_norm": 0.10790123790502548,
      "learning_rate": 0.00019410604878484556,
      "loss": 0.4544,
      "step": 930
    },
    {
      "epoch": 0.4675,
      "grad_norm": 0.10536376386880875,
      "learning_rate": 0.000192853255110746,
      "loss": 0.376,
      "step": 935
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.11744682490825653,
      "learning_rate": 0.00019159719799535668,
      "loss": 0.3887,
      "step": 940
    },
    {
      "epoch": 0.4725,
      "grad_norm": 0.12954068183898926,
      "learning_rate": 0.00019033797309228983,
      "loss": 0.4075,
      "step": 945
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.1401606798171997,
      "learning_rate": 0.00018907567629639725,
      "loss": 0.4454,
      "step": 950
    },
    {
      "epoch": 0.4775,
      "grad_norm": 0.12059322744607925,
      "learning_rate": 0.00018781040373646706,
      "loss": 0.4339,
      "step": 955
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.11798987537622452,
      "learning_rate": 0.00018654225176790336,
      "loss": 0.4405,
      "step": 960
    },
    {
      "epoch": 0.4825,
      "grad_norm": 0.11344211548566818,
      "learning_rate": 0.00018527131696538846,
      "loss": 0.4124,
      "step": 965
    },
    {
      "epoch": 0.485,
      "grad_norm": 0.10373330116271973,
      "learning_rate": 0.00018399769611552824,
      "loss": 0.4329,
      "step": 970
    },
    {
      "epoch": 0.4875,
      "grad_norm": 0.12053704261779785,
      "learning_rate": 0.0001827214862094814,
      "loss": 0.4944,
      "step": 975
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.141033336520195,
      "learning_rate": 0.00018144278443557328,
      "loss": 0.4569,
      "step": 980
    },
    {
      "epoch": 0.4925,
      "grad_norm": 0.10922867804765701,
      "learning_rate": 0.0001801616881718947,
      "loss": 0.3879,
      "step": 985
    },
    {
      "epoch": 0.495,
      "grad_norm": 0.09843657910823822,
      "learning_rate": 0.00017887829497888612,
      "loss": 0.4106,
      "step": 990
    },
    {
      "epoch": 0.4975,
      "grad_norm": 0.12131062150001526,
      "learning_rate": 0.000177592702591908,
      "loss": 0.4023,
      "step": 995
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.11343283206224442,
      "learning_rate": 0.00017630500891379806,
      "loss": 0.4824,
      "step": 1000
    }
  ],
  "logging_steps": 5,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 1.314789078859776e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}