{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1282,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0078003120124804995,
      "grad_norm": 2.144841432571411,
      "learning_rate": 0.0009989971027412525,
      "loss": 1.1174,
      "step": 10
    },
    {
      "epoch": 0.015600624024960999,
      "grad_norm": 1.0625462532043457,
      "learning_rate": 0.0009978827724537553,
      "loss": 0.5035,
      "step": 20
    },
    {
      "epoch": 0.0234009360374415,
      "grad_norm": 1.619573950767517,
      "learning_rate": 0.0009967684421662581,
      "loss": 0.3841,
      "step": 30
    },
    {
      "epoch": 0.031201248049921998,
      "grad_norm": 3.2681403160095215,
      "learning_rate": 0.000995654111878761,
      "loss": 0.4974,
      "step": 40
    },
    {
      "epoch": 0.0390015600624025,
      "grad_norm": 1.5944786071777344,
      "learning_rate": 0.0009945397815912637,
      "loss": 0.4797,
      "step": 50
    },
    {
      "epoch": 0.046801872074883,
      "grad_norm": 1.8234444856643677,
      "learning_rate": 0.0009934254513037665,
      "loss": 0.637,
      "step": 60
    },
    {
      "epoch": 0.054602184087363496,
      "grad_norm": 3.790844440460205,
      "learning_rate": 0.0009923111210162691,
      "loss": 0.4479,
      "step": 70
    },
    {
      "epoch": 0.062402496099843996,
      "grad_norm": 2.9351046085357666,
      "learning_rate": 0.000991196790728772,
      "loss": 0.4332,
      "step": 80
    },
    {
      "epoch": 0.07020280811232449,
      "grad_norm": 2.2770025730133057,
      "learning_rate": 0.0009900824604412747,
      "loss": 0.4399,
      "step": 90
    },
    {
      "epoch": 0.078003120124805,
      "grad_norm": 1.86591637134552,
      "learning_rate": 0.0009889681301537775,
      "loss": 0.407,
      "step": 100
    },
    {
      "epoch": 0.08580343213728549,
      "grad_norm": 1.6851640939712524,
      "learning_rate": 0.0009878537998662805,
      "loss": 0.3862,
      "step": 110
    },
    {
      "epoch": 0.093603744149766,
      "grad_norm": 2.5469818115234375,
      "learning_rate": 0.0009867394695787831,
      "loss": 0.4166,
      "step": 120
    },
    {
      "epoch": 0.10140405616224649,
      "grad_norm": 1.8210259675979614,
      "learning_rate": 0.000985625139291286,
      "loss": 0.3785,
      "step": 130
    },
    {
      "epoch": 0.10920436817472699,
      "grad_norm": 2.031057119369507,
      "learning_rate": 0.0009845108090037887,
      "loss": 0.4177,
      "step": 140
    },
    {
      "epoch": 0.11700468018720749,
      "grad_norm": 1.6646612882614136,
      "learning_rate": 0.0009833964787162915,
      "loss": 0.402,
      "step": 150
    },
    {
      "epoch": 0.12480499219968799,
      "grad_norm": 1.8680285215377808,
      "learning_rate": 0.0009822821484287943,
      "loss": 0.3282,
      "step": 160
    },
    {
      "epoch": 0.13260530421216848,
      "grad_norm": 1.8039604425430298,
      "learning_rate": 0.0009811678181412971,
      "loss": 0.3536,
      "step": 170
    },
    {
      "epoch": 0.14040561622464898,
      "grad_norm": 3.3018901348114014,
      "learning_rate": 0.0009800534878538,
      "loss": 0.4595,
      "step": 180
    },
    {
      "epoch": 0.1482059282371295,
      "grad_norm": 3.684013843536377,
      "learning_rate": 0.0009789391575663027,
      "loss": 0.4288,
      "step": 190
    },
    {
      "epoch": 0.15600624024961,
      "grad_norm": 1.4512592554092407,
      "learning_rate": 0.0009778248272788055,
      "loss": 0.5086,
      "step": 200
    },
    {
      "epoch": 0.16380655226209048,
      "grad_norm": 2.3981761932373047,
      "learning_rate": 0.0009767104969913081,
      "loss": 0.4084,
      "step": 210
    },
    {
      "epoch": 0.17160686427457097,
      "grad_norm": 3.7943010330200195,
      "learning_rate": 0.000975596166703811,
      "loss": 0.4524,
      "step": 220
    },
    {
      "epoch": 0.1794071762870515,
      "grad_norm": 2.657606840133667,
      "learning_rate": 0.0009744818364163138,
      "loss": 0.3592,
      "step": 230
    },
    {
      "epoch": 0.187207488299532,
      "grad_norm": 2.7629363536834717,
      "learning_rate": 0.0009733675061288166,
      "loss": 0.4263,
      "step": 240
    },
    {
      "epoch": 0.19500780031201248,
      "grad_norm": 1.3749983310699463,
      "learning_rate": 0.0009722531758413193,
      "loss": 0.48,
      "step": 250
    },
    {
      "epoch": 0.20280811232449297,
      "grad_norm": 2.648716449737549,
      "learning_rate": 0.0009711388455538221,
      "loss": 0.416,
      "step": 260
    },
    {
      "epoch": 0.21060842433697347,
      "grad_norm": 1.5672308206558228,
      "learning_rate": 0.0009700245152663249,
      "loss": 0.4223,
      "step": 270
    },
    {
      "epoch": 0.21840873634945399,
      "grad_norm": 2.618163585662842,
      "learning_rate": 0.0009689101849788277,
      "loss": 0.4172,
      "step": 280
    },
    {
      "epoch": 0.22620904836193448,
      "grad_norm": 3.6365268230438232,
      "learning_rate": 0.0009677958546913305,
      "loss": 0.5501,
      "step": 290
    },
    {
      "epoch": 0.23400936037441497,
      "grad_norm": 2.740039825439453,
      "learning_rate": 0.0009666815244038332,
      "loss": 0.3553,
      "step": 300
    },
    {
      "epoch": 0.24180967238689546,
      "grad_norm": 3.406210422515869,
      "learning_rate": 0.000965567194116336,
      "loss": 0.3518,
      "step": 310
    },
    {
      "epoch": 0.24960998439937598,
      "grad_norm": 1.4707075357437134,
      "learning_rate": 0.000964452863828839,
      "loss": 0.3452,
      "step": 320
    },
    {
      "epoch": 0.2574102964118565,
      "grad_norm": 1.608324408531189,
      "learning_rate": 0.0009633385335413417,
      "loss": 0.4908,
      "step": 330
    },
    {
      "epoch": 0.26521060842433697,
      "grad_norm": 4.090480327606201,
      "learning_rate": 0.0009622242032538444,
      "loss": 0.4597,
      "step": 340
    },
    {
      "epoch": 0.27301092043681746,
      "grad_norm": 2.2214395999908447,
      "learning_rate": 0.0009611098729663472,
      "loss": 0.4552,
      "step": 350
    },
    {
      "epoch": 0.28081123244929795,
      "grad_norm": 1.9134166240692139,
      "learning_rate": 0.00095999554267885,
      "loss": 0.3571,
      "step": 360
    },
    {
      "epoch": 0.28861154446177845,
      "grad_norm": 1.8127851486206055,
      "learning_rate": 0.0009588812123913528,
      "loss": 0.3808,
      "step": 370
    },
    {
      "epoch": 0.296411856474259,
      "grad_norm": 2.2262885570526123,
      "learning_rate": 0.0009577668821038556,
      "loss": 0.4099,
      "step": 380
    },
    {
      "epoch": 0.3042121684867395,
      "grad_norm": 2.8041303157806396,
      "learning_rate": 0.0009566525518163583,
      "loss": 0.3988,
      "step": 390
    },
    {
      "epoch": 0.31201248049922,
      "grad_norm": 6.797432899475098,
      "learning_rate": 0.0009555382215288611,
      "loss": 0.4728,
      "step": 400
    },
    {
      "epoch": 0.31981279251170047,
      "grad_norm": 3.1861369609832764,
      "learning_rate": 0.000954423891241364,
      "loss": 0.3502,
      "step": 410
    },
    {
      "epoch": 0.32761310452418096,
      "grad_norm": 2.9223642349243164,
      "learning_rate": 0.0009533095609538667,
      "loss": 0.4215,
      "step": 420
    },
    {
      "epoch": 0.33541341653666146,
      "grad_norm": 6.848895072937012,
      "learning_rate": 0.0009521952306663694,
      "loss": 0.415,
      "step": 430
    },
    {
      "epoch": 0.34321372854914195,
      "grad_norm": 9.054282188415527,
      "learning_rate": 0.0009510809003788722,
      "loss": 0.4667,
      "step": 440
    },
    {
      "epoch": 0.35101404056162244,
      "grad_norm": 2.3005900382995605,
      "learning_rate": 0.0009499665700913752,
      "loss": 0.6565,
      "step": 450
    },
    {
      "epoch": 0.358814352574103,
      "grad_norm": 2.9467573165893555,
      "learning_rate": 0.000948852239803878,
      "loss": 0.3837,
      "step": 460
    },
    {
      "epoch": 0.3666146645865835,
      "grad_norm": 1.5977652072906494,
      "learning_rate": 0.0009477379095163808,
      "loss": 0.407,
      "step": 470
    },
    {
      "epoch": 0.374414976599064,
      "grad_norm": 2.8274600505828857,
      "learning_rate": 0.0009466235792288835,
      "loss": 0.4501,
      "step": 480
    },
    {
      "epoch": 0.38221528861154447,
      "grad_norm": 1.8566502332687378,
      "learning_rate": 0.0009455092489413863,
      "loss": 0.3146,
      "step": 490
    },
    {
      "epoch": 0.39001560062402496,
      "grad_norm": 2.5871951580047607,
      "learning_rate": 0.0009443949186538891,
      "loss": 0.3335,
      "step": 500
    },
    {
      "epoch": 0.39781591263650545,
      "grad_norm": 2.0552711486816406,
      "learning_rate": 0.0009432805883663919,
      "loss": 0.3698,
      "step": 510
    },
    {
      "epoch": 0.40561622464898595,
      "grad_norm": 1.5244548320770264,
      "learning_rate": 0.0009421662580788946,
      "loss": 0.581,
      "step": 520
    },
    {
      "epoch": 0.41341653666146644,
      "grad_norm": 1.5146633386611938,
      "learning_rate": 0.0009410519277913974,
      "loss": 0.3634,
      "step": 530
    },
    {
      "epoch": 0.42121684867394693,
      "grad_norm": 2.394819736480713,
      "learning_rate": 0.0009399375975039002,
      "loss": 0.338,
      "step": 540
    },
    {
      "epoch": 0.4290171606864275,
      "grad_norm": 2.3500325679779053,
      "learning_rate": 0.000938823267216403,
      "loss": 0.4025,
      "step": 550
    },
    {
      "epoch": 0.43681747269890797,
      "grad_norm": 2.4186370372772217,
      "learning_rate": 0.0009377089369289058,
      "loss": 0.4095,
      "step": 560
    },
    {
      "epoch": 0.44461778471138846,
      "grad_norm": 1.9770065546035767,
      "learning_rate": 0.0009365946066414085,
      "loss": 0.4275,
      "step": 570
    },
    {
      "epoch": 0.45241809672386896,
      "grad_norm": 1.7679632902145386,
      "learning_rate": 0.0009354802763539114,
      "loss": 0.3949,
      "step": 580
    },
    {
      "epoch": 0.46021840873634945,
      "grad_norm": 2.0794620513916016,
      "learning_rate": 0.0009343659460664142,
      "loss": 0.4208,
      "step": 590
    },
    {
      "epoch": 0.46801872074882994,
      "grad_norm": 2.677424192428589,
      "learning_rate": 0.000933251615778917,
      "loss": 0.4089,
      "step": 600
    },
    {
      "epoch": 0.47581903276131043,
      "grad_norm": 1.526112675666809,
      "learning_rate": 0.0009321372854914197,
      "loss": 0.4196,
      "step": 610
    },
    {
      "epoch": 0.4836193447737909,
      "grad_norm": 1.8656370639801025,
      "learning_rate": 0.0009310229552039225,
      "loss": 0.3732,
      "step": 620
    },
    {
      "epoch": 0.4914196567862715,
      "grad_norm": 3.3338847160339355,
      "learning_rate": 0.0009299086249164253,
      "loss": 0.4231,
      "step": 630
    },
    {
      "epoch": 0.49921996879875197,
      "grad_norm": 2.1057350635528564,
      "learning_rate": 0.0009287942946289281,
      "loss": 0.3921,
      "step": 640
    },
    {
      "epoch": 0.5070202808112324,
      "grad_norm": 1.544977068901062,
      "learning_rate": 0.0009276799643414309,
      "loss": 0.3748,
      "step": 650
    },
    {
      "epoch": 0.514820592823713,
      "grad_norm": 3.4070258140563965,
      "learning_rate": 0.0009265656340539336,
      "loss": 0.4027,
      "step": 660
    },
    {
      "epoch": 0.5226209048361935,
      "grad_norm": 5.5486931800842285,
      "learning_rate": 0.0009254513037664364,
      "loss": 0.4326,
      "step": 670
    },
    {
      "epoch": 0.5304212168486739,
      "grad_norm": 3.6824769973754883,
      "learning_rate": 0.0009243369734789392,
      "loss": 0.4809,
      "step": 680
    },
    {
      "epoch": 0.5382215288611545,
      "grad_norm": 6.3154778480529785,
      "learning_rate": 0.000923222643191442,
      "loss": 0.3588,
      "step": 690
    },
    {
      "epoch": 0.5460218408736349,
      "grad_norm": 3.133465528488159,
      "learning_rate": 0.0009221083129039447,
      "loss": 0.4712,
      "step": 700
    },
    {
      "epoch": 0.5538221528861155,
      "grad_norm": 4.222598552703857,
      "learning_rate": 0.0009209939826164475,
      "loss": 0.4135,
      "step": 710
    },
    {
      "epoch": 0.5616224648985959,
      "grad_norm": 4.6125078201293945,
      "learning_rate": 0.0009198796523289504,
      "loss": 0.393,
      "step": 720
    },
    {
      "epoch": 0.5694227769110765,
      "grad_norm": 6.543318748474121,
      "learning_rate": 0.0009187653220414532,
      "loss": 0.6138,
      "step": 730
    },
    {
      "epoch": 0.5772230889235569,
      "grad_norm": 2.596463680267334,
      "learning_rate": 0.000917650991753956,
      "loss": 0.3694,
      "step": 740
    },
    {
      "epoch": 0.5850234009360374,
      "grad_norm": 2.428490161895752,
      "learning_rate": 0.0009165366614664587,
      "loss": 0.4535,
      "step": 750
    },
    {
      "epoch": 0.592823712948518,
      "grad_norm": 1.8790688514709473,
      "learning_rate": 0.0009154223311789615,
      "loss": 0.3986,
      "step": 760
    },
    {
      "epoch": 0.6006240249609984,
      "grad_norm": 3.141587734222412,
      "learning_rate": 0.0009143080008914643,
      "loss": 0.3881,
      "step": 770
    },
    {
      "epoch": 0.608424336973479,
      "grad_norm": 2.125810146331787,
      "learning_rate": 0.0009131936706039671,
      "loss": 0.4225,
      "step": 780
    },
    {
      "epoch": 0.6162246489859594,
      "grad_norm": 2.532404661178589,
      "learning_rate": 0.0009120793403164698,
      "loss": 0.3423,
      "step": 790
    },
    {
      "epoch": 0.62402496099844,
      "grad_norm": 3.6324350833892822,
      "learning_rate": 0.0009109650100289726,
      "loss": 0.4205,
      "step": 800
    },
    {
      "epoch": 0.6318252730109204,
      "grad_norm": 1.4804415702819824,
      "learning_rate": 0.0009098506797414754,
      "loss": 0.4042,
      "step": 810
    },
    {
      "epoch": 0.6396255850234009,
      "grad_norm": 1.5140562057495117,
      "learning_rate": 0.0009087363494539782,
      "loss": 0.3056,
      "step": 820
    },
    {
      "epoch": 0.6474258970358814,
      "grad_norm": 2.470576047897339,
      "learning_rate": 0.000907622019166481,
      "loss": 0.391,
      "step": 830
    },
    {
      "epoch": 0.6552262090483619,
      "grad_norm": 3.4496209621429443,
      "learning_rate": 0.0009065076888789837,
      "loss": 0.4163,
      "step": 840
    },
    {
      "epoch": 0.6630265210608425,
      "grad_norm": 1.8823250532150269,
      "learning_rate": 0.0009053933585914866,
      "loss": 0.3877,
      "step": 850
    },
    {
      "epoch": 0.6708268330733229,
      "grad_norm": 2.492297410964966,
      "learning_rate": 0.0009042790283039894,
      "loss": 0.3542,
      "step": 860
    },
    {
      "epoch": 0.6786271450858035,
      "grad_norm": 3.977569341659546,
      "learning_rate": 0.0009031646980164922,
      "loss": 0.4168,
      "step": 870
    },
    {
      "epoch": 0.6864274570982839,
      "grad_norm": 3.938462495803833,
      "learning_rate": 0.0009020503677289949,
      "loss": 0.4894,
      "step": 880
    },
    {
      "epoch": 0.6942277691107644,
      "grad_norm": 1.3457701206207275,
      "learning_rate": 0.0009009360374414977,
      "loss": 0.4903,
      "step": 890
    },
    {
      "epoch": 0.7020280811232449,
      "grad_norm": 6.3473124504089355,
      "learning_rate": 0.0008998217071540005,
      "loss": 0.4766,
      "step": 900
    },
    {
      "epoch": 0.7098283931357254,
      "grad_norm": 3.145792245864868,
      "learning_rate": 0.0008987073768665033,
      "loss": 0.4119,
      "step": 910
    },
    {
      "epoch": 0.717628705148206,
      "grad_norm": 1.809446930885315,
      "learning_rate": 0.0008975930465790061,
      "loss": 0.3991,
      "step": 920
    },
    {
      "epoch": 0.7254290171606864,
      "grad_norm": 1.7960044145584106,
      "learning_rate": 0.0008964787162915088,
      "loss": 0.3095,
      "step": 930
    },
    {
      "epoch": 0.733229329173167,
      "grad_norm": 2.9710285663604736,
      "learning_rate": 0.0008953643860040116,
      "loss": 0.5104,
      "step": 940
    },
    {
      "epoch": 0.7410296411856474,
      "grad_norm": 2.460524797439575,
      "learning_rate": 0.0008942500557165144,
      "loss": 0.4332,
      "step": 950
    },
    {
      "epoch": 0.748829953198128,
      "grad_norm": 1.6166704893112183,
      "learning_rate": 0.0008931357254290172,
      "loss": 0.3856,
      "step": 960
    },
    {
      "epoch": 0.7566302652106084,
      "grad_norm": 1.747750163078308,
      "learning_rate": 0.0008920213951415199,
      "loss": 0.3973,
      "step": 970
    },
    {
      "epoch": 0.7644305772230889,
      "grad_norm": 1.4469414949417114,
      "learning_rate": 0.0008909070648540227,
      "loss": 0.3344,
      "step": 980
    },
    {
      "epoch": 0.7722308892355694,
      "grad_norm": 4.661273956298828,
      "learning_rate": 0.0008897927345665256,
      "loss": 0.6003,
      "step": 990
    },
    {
      "epoch": 0.7800312012480499,
      "grad_norm": 3.6588950157165527,
      "learning_rate": 0.0008886784042790284,
      "loss": 0.473,
      "step": 1000
    },
    {
      "epoch": 0.7878315132605305,
      "grad_norm": 2.208383798599243,
      "learning_rate": 0.0008876755070202809,
      "loss": 0.3899,
      "step": 1010
    },
    {
      "epoch": 0.7956318252730109,
      "grad_norm": 2.3569576740264893,
      "learning_rate": 0.0008865611767327836,
      "loss": 0.3871,
      "step": 1020
    },
    {
      "epoch": 0.8034321372854915,
      "grad_norm": 2.7071454524993896,
      "learning_rate": 0.0008854468464452864,
      "loss": 0.3149,
      "step": 1030
    },
    {
      "epoch": 0.8112324492979719,
      "grad_norm": 2.8024532794952393,
      "learning_rate": 0.0008843325161577892,
      "loss": 0.3328,
      "step": 1040
    },
    {
      "epoch": 0.8190327613104524,
      "grad_norm": 3.0969290733337402,
      "learning_rate": 0.000883218185870292,
      "loss": 0.3948,
      "step": 1050
    },
    {
      "epoch": 0.8268330733229329,
      "grad_norm": 2.982484817504883,
      "learning_rate": 0.0008821038555827947,
      "loss": 0.4323,
      "step": 1060
    },
    {
      "epoch": 0.8346333853354134,
      "grad_norm": 3.133814573287964,
      "learning_rate": 0.0008809895252952975,
      "loss": 0.4393,
      "step": 1070
    },
    {
      "epoch": 0.8424336973478939,
      "grad_norm": 3.3123364448547363,
      "learning_rate": 0.0008798751950078003,
      "loss": 0.3244,
      "step": 1080
    },
    {
      "epoch": 0.8502340093603744,
      "grad_norm": 2.308555841445923,
      "learning_rate": 0.0008787608647203032,
      "loss": 0.424,
      "step": 1090
    },
    {
      "epoch": 0.858034321372855,
      "grad_norm": 3.654137134552002,
      "learning_rate": 0.000877646534432806,
      "loss": 0.3445,
      "step": 1100
    },
    {
      "epoch": 0.8658346333853354,
      "grad_norm": 2.149843692779541,
      "learning_rate": 0.0008765322041453087,
      "loss": 0.3398,
      "step": 1110
    },
    {
      "epoch": 0.8736349453978159,
      "grad_norm": 3.1334431171417236,
      "learning_rate": 0.0008754178738578115,
      "loss": 0.3333,
      "step": 1120
    },
    {
      "epoch": 0.8814352574102964,
      "grad_norm": 2.2942090034484863,
      "learning_rate": 0.0008743035435703143,
      "loss": 0.4188,
      "step": 1130
    },
    {
      "epoch": 0.8892355694227769,
      "grad_norm": 2.0195343494415283,
      "learning_rate": 0.0008731892132828171,
      "loss": 0.4047,
      "step": 1140
    },
    {
      "epoch": 0.8970358814352574,
      "grad_norm": 2.3850839138031006,
      "learning_rate": 0.0008720748829953198,
      "loss": 0.3931,
      "step": 1150
    },
    {
      "epoch": 0.9048361934477379,
      "grad_norm": 1.6200228929519653,
      "learning_rate": 0.0008709605527078226,
      "loss": 0.409,
      "step": 1160
    },
    {
      "epoch": 0.9126365054602185,
      "grad_norm": 2.9001989364624023,
      "learning_rate": 0.0008698462224203254,
      "loss": 0.4289,
      "step": 1170
    },
    {
      "epoch": 0.9204368174726989,
      "grad_norm": 1.52889883518219,
      "learning_rate": 0.0008687318921328282,
      "loss": 0.3575,
      "step": 1180
    },
    {
      "epoch": 0.9282371294851794,
      "grad_norm": 2.359733819961548,
      "learning_rate": 0.000867617561845331,
      "loss": 0.3837,
      "step": 1190
    },
    {
      "epoch": 0.9360374414976599,
      "grad_norm": 2.3807597160339355,
      "learning_rate": 0.0008665032315578337,
      "loss": 0.4206,
      "step": 1200
    },
    {
      "epoch": 0.9438377535101404,
      "grad_norm": 1.8366179466247559,
      "learning_rate": 0.0008653889012703365,
      "loss": 0.3101,
      "step": 1210
    },
    {
      "epoch": 0.9516380655226209,
      "grad_norm": 3.1048014163970947,
      "learning_rate": 0.0008642745709828393,
      "loss": 0.4104,
      "step": 1220
    },
    {
      "epoch": 0.9594383775351014,
      "grad_norm": 1.5314342975616455,
      "learning_rate": 0.0008631602406953422,
      "loss": 0.3539,
      "step": 1230
    },
    {
      "epoch": 0.9672386895475819,
      "grad_norm": 2.8501791954040527,
      "learning_rate": 0.0008620459104078449,
      "loss": 0.4104,
      "step": 1240
    },
    {
      "epoch": 0.9750390015600624,
      "grad_norm": 5.708191394805908,
      "learning_rate": 0.0008609315801203477,
      "loss": 0.4038,
      "step": 1250
    },
    {
      "epoch": 0.982839313572543,
      "grad_norm": 2.173867702484131,
      "learning_rate": 0.0008598172498328505,
      "loss": 0.338,
      "step": 1260
    },
    {
      "epoch": 0.9906396255850234,
      "grad_norm": 2.7057418823242188,
      "learning_rate": 0.0008587029195453533,
      "loss": 0.3941,
      "step": 1270
    },
    {
      "epoch": 0.9984399375975039,
      "grad_norm": 1.3492989540100098,
      "learning_rate": 0.0008575885892578561,
      "loss": 0.3696,
      "step": 1280
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4044143855571747,
      "eval_runtime": 635.8286,
      "eval_samples_per_second": 0.865,
      "eval_steps_per_second": 0.865,
      "eval_wer": 26.665379416875844,
      "step": 1282
    }
  ],
  "logging_steps": 10,
  "max_steps": 8974,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.12949897084928e+18,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}