{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.988913525498892,
  "eval_steps": 500,
  "global_step": 1125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004434589800443459,
      "grad_norm": 1.9136914014816284,
      "learning_rate": 1.7699115044247788e-06,
      "loss": 2.8127,
      "step": 1
    },
    {
      "epoch": 0.022172949002217297,
      "grad_norm": 2.073108434677124,
      "learning_rate": 8.849557522123894e-06,
      "loss": 2.8249,
      "step": 5
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 1.7010493278503418,
      "learning_rate": 1.7699115044247787e-05,
      "loss": 2.7382,
      "step": 10
    },
    {
      "epoch": 0.06651884700665188,
      "grad_norm": 1.6392902135849,
      "learning_rate": 2.6548672566371686e-05,
      "loss": 2.6574,
      "step": 15
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 1.1917133331298828,
      "learning_rate": 3.5398230088495574e-05,
      "loss": 2.4883,
      "step": 20
    },
    {
      "epoch": 0.11086474501108648,
      "grad_norm": 0.7972588539123535,
      "learning_rate": 4.4247787610619477e-05,
      "loss": 2.3405,
      "step": 25
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 0.8086889982223511,
      "learning_rate": 5.309734513274337e-05,
      "loss": 2.2187,
      "step": 30
    },
    {
      "epoch": 0.15521064301552107,
      "grad_norm": 0.6612704396247864,
      "learning_rate": 6.194690265486725e-05,
      "loss": 2.1042,
      "step": 35
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 0.6673336029052734,
      "learning_rate": 7.079646017699115e-05,
      "loss": 1.9928,
      "step": 40
    },
    {
      "epoch": 0.19955654101995565,
      "grad_norm": 0.5582772493362427,
      "learning_rate": 7.964601769911504e-05,
      "loss": 1.9215,
      "step": 45
    },
    {
      "epoch": 0.22172949002217296,
      "grad_norm": 0.43071338534355164,
      "learning_rate": 8.849557522123895e-05,
      "loss": 1.8657,
      "step": 50
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.34688612818717957,
      "learning_rate": 9.734513274336283e-05,
      "loss": 1.7914,
      "step": 55
    },
    {
      "epoch": 0.2660753880266075,
      "grad_norm": 0.3413448631763458,
      "learning_rate": 0.00010619469026548674,
      "loss": 1.7762,
      "step": 60
    },
    {
      "epoch": 0.28824833702882485,
      "grad_norm": 0.313379168510437,
      "learning_rate": 0.00011504424778761063,
      "loss": 1.7352,
      "step": 65
    },
    {
      "epoch": 0.31042128603104213,
      "grad_norm": 0.36069634556770325,
      "learning_rate": 0.0001238938053097345,
      "loss": 1.6967,
      "step": 70
    },
    {
      "epoch": 0.3325942350332594,
      "grad_norm": 0.40712735056877136,
      "learning_rate": 0.00013274336283185842,
      "loss": 1.6816,
      "step": 75
    },
    {
      "epoch": 0.35476718403547675,
      "grad_norm": 0.48003074526786804,
      "learning_rate": 0.0001415929203539823,
      "loss": 1.667,
      "step": 80
    },
    {
      "epoch": 0.376940133037694,
      "grad_norm": 0.556786835193634,
      "learning_rate": 0.00015044247787610618,
      "loss": 1.6168,
      "step": 85
    },
    {
      "epoch": 0.3991130820399113,
      "grad_norm": 0.41180524230003357,
      "learning_rate": 0.0001592920353982301,
      "loss": 1.596,
      "step": 90
    },
    {
      "epoch": 0.4212860310421286,
      "grad_norm": 0.4306657910346985,
      "learning_rate": 0.000168141592920354,
      "loss": 1.569,
      "step": 95
    },
    {
      "epoch": 0.4434589800443459,
      "grad_norm": 0.3725152313709259,
      "learning_rate": 0.0001769911504424779,
      "loss": 1.5671,
      "step": 100
    },
    {
      "epoch": 0.4656319290465632,
      "grad_norm": 0.402552992105484,
      "learning_rate": 0.0001858407079646018,
      "loss": 1.5516,
      "step": 105
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.3868615925312042,
      "learning_rate": 0.00019469026548672567,
      "loss": 1.534,
      "step": 110
    },
    {
      "epoch": 0.5099778270509978,
      "grad_norm": 0.37014004588127136,
      "learning_rate": 0.00019999807262012045,
      "loss": 1.5358,
      "step": 115
    },
    {
      "epoch": 0.532150776053215,
      "grad_norm": 0.3409845530986786,
      "learning_rate": 0.00019997639044970784,
      "loss": 1.5083,
      "step": 120
    },
    {
      "epoch": 0.5543237250554324,
      "grad_norm": 0.42291566729545593,
      "learning_rate": 0.00019993062212508053,
      "loss": 1.5057,
      "step": 125
    },
    {
      "epoch": 0.5764966740576497,
      "grad_norm": 0.3941720426082611,
      "learning_rate": 0.00019986077867267113,
      "loss": 1.4975,
      "step": 130
    },
    {
      "epoch": 0.5986696230598669,
      "grad_norm": 0.47755852341651917,
      "learning_rate": 0.00019976687691905393,
      "loss": 1.4933,
      "step": 135
    },
    {
      "epoch": 0.6208425720620843,
      "grad_norm": 0.5203377604484558,
      "learning_rate": 0.00019964893948689122,
      "loss": 1.5053,
      "step": 140
    },
    {
      "epoch": 0.6430155210643016,
      "grad_norm": 0.3959715664386749,
      "learning_rate": 0.00019950699478948309,
      "loss": 1.4937,
      "step": 145
    },
    {
      "epoch": 0.6651884700665188,
      "grad_norm": 0.3711565136909485,
      "learning_rate": 0.000199341077023922,
      "loss": 1.4995,
      "step": 150
    },
    {
      "epoch": 0.6873614190687362,
      "grad_norm": 0.37361645698547363,
      "learning_rate": 0.00019915122616285418,
      "loss": 1.4863,
      "step": 155
    },
    {
      "epoch": 0.7095343680709535,
      "grad_norm": 0.34434613585472107,
      "learning_rate": 0.00019893748794484948,
      "loss": 1.4752,
      "step": 160
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 0.36264362931251526,
      "learning_rate": 0.0001986999138633821,
      "loss": 1.455,
      "step": 165
    },
    {
      "epoch": 0.753880266075388,
      "grad_norm": 0.3910064995288849,
      "learning_rate": 0.00019843856115442482,
      "loss": 1.4627,
      "step": 170
    },
    {
      "epoch": 0.7760532150776053,
      "grad_norm": 0.41227295994758606,
      "learning_rate": 0.00019815349278265988,
      "loss": 1.4723,
      "step": 175
    },
    {
      "epoch": 0.7982261640798226,
      "grad_norm": 0.34940609335899353,
      "learning_rate": 0.00019784477742630952,
      "loss": 1.4692,
      "step": 180
    },
    {
      "epoch": 0.8203991130820399,
      "grad_norm": 0.33894529938697815,
      "learning_rate": 0.00019751248946059014,
      "loss": 1.4513,
      "step": 185
    },
    {
      "epoch": 0.8425720620842572,
      "grad_norm": 0.3944953978061676,
      "learning_rate": 0.00019715670893979414,
      "loss": 1.4504,
      "step": 190
    },
    {
      "epoch": 0.8647450110864745,
      "grad_norm": 0.37704771757125854,
      "learning_rate": 0.00019677752157800312,
      "loss": 1.4383,
      "step": 195
    },
    {
      "epoch": 0.8869179600886918,
      "grad_norm": 0.39401814341545105,
      "learning_rate": 0.0001963750187284379,
      "loss": 1.4524,
      "step": 200
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.39860641956329346,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.4363,
      "step": 205
    },
    {
      "epoch": 0.9312638580931264,
      "grad_norm": 0.36418575048446655,
      "learning_rate": 0.0001955004600411586,
      "loss": 1.4199,
      "step": 210
    },
    {
      "epoch": 0.9534368070953437,
      "grad_norm": 0.40804576873779297,
      "learning_rate": 0.0001950286149007434,
      "loss": 1.4151,
      "step": 215
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.4127281606197357,
      "learning_rate": 0.0001945338756163907,
      "loss": 1.4438,
      "step": 220
    },
    {
      "epoch": 0.9977827050997783,
      "grad_norm": 0.4101060628890991,
      "learning_rate": 0.00019401636137990816,
      "loss": 1.4428,
      "step": 225
    },
    {
      "epoch": 0.9977827050997783,
      "eval_loss": 1.748767375946045,
      "eval_runtime": 0.3757,
      "eval_samples_per_second": 2.662,
      "eval_steps_per_second": 2.662,
      "step": 225
    },
    {
      "epoch": 1.0199556541019956,
      "grad_norm": 0.5033897757530212,
      "learning_rate": 0.00019347619687000892,
      "loss": 1.4076,
      "step": 230
    },
    {
      "epoch": 1.042128603104213,
      "grad_norm": 0.34217771887779236,
      "learning_rate": 0.00019291351222227432,
      "loss": 1.4057,
      "step": 235
    },
    {
      "epoch": 1.06430155210643,
      "grad_norm": 0.3883781135082245,
      "learning_rate": 0.0001923284429978017,
      "loss": 1.4198,
      "step": 240
    },
    {
      "epoch": 1.0864745011086474,
      "grad_norm": 0.34347742795944214,
      "learning_rate": 0.00019172113015054532,
      "loss": 1.4052,
      "step": 245
    },
    {
      "epoch": 1.1086474501108647,
      "grad_norm": 0.4281429648399353,
      "learning_rate": 0.00019109171999335793,
      "loss": 1.4255,
      "step": 250
    },
    {
      "epoch": 1.130820399113082,
      "grad_norm": 0.377329558134079,
      "learning_rate": 0.00019044036416274133,
      "loss": 1.4081,
      "step": 255
    },
    {
      "epoch": 1.1529933481152994,
      "grad_norm": 0.3482955992221832,
      "learning_rate": 0.00018976721958231438,
      "loss": 1.3953,
      "step": 260
    },
    {
      "epoch": 1.1751662971175167,
      "grad_norm": 0.40098318457603455,
      "learning_rate": 0.00018907244842500704,
      "loss": 1.4021,
      "step": 265
    },
    {
      "epoch": 1.1973392461197339,
      "grad_norm": 0.43027186393737793,
      "learning_rate": 0.00018835621807399016,
      "loss": 1.4056,
      "step": 270
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 0.38251981139183044,
      "learning_rate": 0.0001876187010823496,
      "loss": 1.3814,
      "step": 275
    },
    {
      "epoch": 1.2416851441241685,
      "grad_norm": 0.330834299325943,
      "learning_rate": 0.00018686007513151514,
      "loss": 1.391,
      "step": 280
    },
    {
      "epoch": 1.2638580931263859,
      "grad_norm": 0.35464873909950256,
      "learning_rate": 0.0001860805229884536,
      "loss": 1.4068,
      "step": 285
    },
    {
      "epoch": 1.2860310421286032,
      "grad_norm": 0.365756094455719,
      "learning_rate": 0.00018528023246163717,
      "loss": 1.3833,
      "step": 290
    },
    {
      "epoch": 1.3082039911308203,
      "grad_norm": 0.36964625120162964,
      "learning_rate": 0.00018445939635579656,
      "loss": 1.3772,
      "step": 295
    },
    {
      "epoch": 1.3303769401330376,
      "grad_norm": 0.3860366642475128,
      "learning_rate": 0.0001836182124254711,
      "loss": 1.3901,
      "step": 300
    },
    {
      "epoch": 1.352549889135255,
      "grad_norm": 0.4819258153438568,
      "learning_rate": 0.00018275688332736577,
      "loss": 1.384,
      "step": 305
    },
    {
      "epoch": 1.3747228381374723,
      "grad_norm": 0.3682605028152466,
      "learning_rate": 0.00018187561657152757,
      "loss": 1.3729,
      "step": 310
    },
    {
      "epoch": 1.3968957871396896,
      "grad_norm": 0.35252609848976135,
      "learning_rate": 0.00018097462447135273,
      "loss": 1.3859,
      "step": 315
    },
    {
      "epoch": 1.4190687361419068,
      "grad_norm": 0.3672533631324768,
      "learning_rate": 0.00018005412409243606,
      "loss": 1.3677,
      "step": 320
    },
    {
      "epoch": 1.441241685144124,
      "grad_norm": 0.37152794003486633,
      "learning_rate": 0.00017911433720027624,
      "loss": 1.3611,
      "step": 325
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 0.4452725648880005,
      "learning_rate": 0.00017815549020684825,
      "loss": 1.3775,
      "step": 330
    },
    {
      "epoch": 1.4855875831485588,
      "grad_norm": 0.38919898867607117,
      "learning_rate": 0.0001771778141160566,
      "loss": 1.3799,
      "step": 335
    },
    {
      "epoch": 1.507760532150776,
      "grad_norm": 0.3549223244190216,
      "learning_rate": 0.0001761815444680822,
      "loss": 1.3807,
      "step": 340
    },
    {
      "epoch": 1.5299334811529932,
      "grad_norm": 0.3846336901187897,
      "learning_rate": 0.00017516692128263648,
      "loss": 1.3763,
      "step": 345
    },
    {
      "epoch": 1.5521064301552108,
      "grad_norm": 0.37670284509658813,
      "learning_rate": 0.00017413418900113605,
      "loss": 1.3678,
      "step": 350
    },
    {
      "epoch": 1.5742793791574279,
      "grad_norm": 0.37929922342300415,
      "learning_rate": 0.00017308359642781242,
      "loss": 1.377,
      "step": 355
    },
    {
      "epoch": 1.5964523281596452,
      "grad_norm": 0.41200995445251465,
      "learning_rate": 0.00017201539666977043,
      "loss": 1.3732,
      "step": 360
    },
    {
      "epoch": 1.6186252771618626,
      "grad_norm": 0.3412715196609497,
      "learning_rate": 0.0001709298470760101,
      "loss": 1.3726,
      "step": 365
    },
    {
      "epoch": 1.6407982261640797,
      "grad_norm": 0.3528231680393219,
      "learning_rate": 0.0001698272091754264,
      "loss": 1.3873,
      "step": 370
    },
    {
      "epoch": 1.6629711751662972,
      "grad_norm": 0.3747865855693817,
      "learning_rate": 0.00016870774861380228,
      "loss": 1.3665,
      "step": 375
    },
    {
      "epoch": 1.6851441241685143,
      "grad_norm": 0.40505874156951904,
      "learning_rate": 0.00016757173508980965,
      "loss": 1.3696,
      "step": 380
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 0.5333726406097412,
      "learning_rate": 0.00016641944229003395,
      "loss": 1.3748,
      "step": 385
    },
    {
      "epoch": 1.729490022172949,
      "grad_norm": 0.3569813370704651,
      "learning_rate": 0.00016525114782303807,
      "loss": 1.3631,
      "step": 390
    },
    {
      "epoch": 1.7516629711751663,
      "grad_norm": 0.3798842430114746,
      "learning_rate": 0.00016406713315248136,
      "loss": 1.3604,
      "step": 395
    },
    {
      "epoch": 1.7738359201773837,
      "grad_norm": 0.33182796835899353,
      "learning_rate": 0.00016286768352930973,
      "loss": 1.3692,
      "step": 400
    },
    {
      "epoch": 1.7960088691796008,
      "grad_norm": 0.3485672175884247,
      "learning_rate": 0.0001616530879230335,
      "loss": 1.3709,
      "step": 405
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.34393855929374695,
      "learning_rate": 0.00016042363895210946,
      "loss": 1.3494,
      "step": 410
    },
    {
      "epoch": 1.8403547671840355,
      "grad_norm": 0.34030023217201233,
      "learning_rate": 0.00015917963281344345,
      "loss": 1.3587,
      "step": 415
    },
    {
      "epoch": 1.8625277161862528,
      "grad_norm": 0.34356924891471863,
      "learning_rate": 0.00015792136921103124,
      "loss": 1.3473,
      "step": 420
    },
    {
      "epoch": 1.8847006651884701,
      "grad_norm": 0.3498888909816742,
      "learning_rate": 0.0001566491512837543,
      "loss": 1.3722,
      "step": 425
    },
    {
      "epoch": 1.9068736141906872,
      "grad_norm": 0.36746105551719666,
      "learning_rate": 0.00015536328553234792,
      "loss": 1.3743,
      "step": 430
    },
    {
      "epoch": 1.9290465631929048,
      "grad_norm": 0.33155015110969543,
      "learning_rate": 0.00015406408174555976,
      "loss": 1.3496,
      "step": 435
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.3875883221626282,
      "learning_rate": 0.00015275185292551585,
      "loss": 1.3618,
      "step": 440
    },
    {
      "epoch": 1.9733924611973392,
      "grad_norm": 0.38502293825149536,
      "learning_rate": 0.00015142691521231267,
      "loss": 1.3572,
      "step": 445
    },
    {
      "epoch": 1.9955654101995566,
      "grad_norm": 0.382053405046463,
      "learning_rate": 0.0001500895878078532,
      "loss": 1.3593,
      "step": 450
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.7692114114761353,
      "eval_runtime": 0.3373,
      "eval_samples_per_second": 2.965,
      "eval_steps_per_second": 2.965,
      "step": 451
    },
    {
      "epoch": 2.0177383592017737,
      "grad_norm": 0.35466691851615906,
      "learning_rate": 0.00014874019289894537,
      "loss": 1.3497,
      "step": 455
    },
    {
      "epoch": 2.0399113082039912,
      "grad_norm": 0.35485056042671204,
      "learning_rate": 0.00014737905557968105,
      "loss": 1.3208,
      "step": 460
    },
    {
      "epoch": 2.0620842572062084,
      "grad_norm": 0.3566678464412689,
      "learning_rate": 0.00014600650377311522,
      "loss": 1.3366,
      "step": 465
    },
    {
      "epoch": 2.084257206208426,
      "grad_norm": 0.34695708751678467,
      "learning_rate": 0.00014462286815226314,
      "loss": 1.3231,
      "step": 470
    },
    {
      "epoch": 2.106430155210643,
      "grad_norm": 0.4017435610294342,
      "learning_rate": 0.00014322848206043505,
      "loss": 1.3277,
      "step": 475
    },
    {
      "epoch": 2.12860310421286,
      "grad_norm": 0.3486361801624298,
      "learning_rate": 0.00014182368143092768,
      "loss": 1.325,
      "step": 480
    },
    {
      "epoch": 2.1507760532150777,
      "grad_norm": 0.37655895948410034,
      "learning_rate": 0.00014040880470609187,
      "loss": 1.3062,
      "step": 485
    },
    {
      "epoch": 2.172949002217295,
      "grad_norm": 0.36101478338241577,
      "learning_rate": 0.00013898419275579522,
      "loss": 1.3053,
      "step": 490
    },
    {
      "epoch": 2.1951219512195124,
      "grad_norm": 0.37982380390167236,
      "learning_rate": 0.00013755018879530075,
      "loss": 1.328,
      "step": 495
    },
    {
      "epoch": 2.2172949002217295,
      "grad_norm": 0.42325547337532043,
      "learning_rate": 0.00013610713830257954,
      "loss": 1.324,
      "step": 500
    },
    {
      "epoch": 2.2394678492239466,
      "grad_norm": 0.3722022473812103,
      "learning_rate": 0.00013465538893507907,
      "loss": 1.3335,
      "step": 505
    },
    {
      "epoch": 2.261640798226164,
      "grad_norm": 0.347001314163208,
      "learning_rate": 0.00013319529044596593,
      "loss": 1.3243,
      "step": 510
    },
    {
      "epoch": 2.2838137472283813,
      "grad_norm": 0.3675149381160736,
      "learning_rate": 0.00013172719459986397,
      "loss": 1.3185,
      "step": 515
    },
    {
      "epoch": 2.305986696230599,
      "grad_norm": 0.39877083897590637,
      "learning_rate": 0.0001302514550881076,
      "loss": 1.3114,
      "step": 520
    },
    {
      "epoch": 2.328159645232816,
      "grad_norm": 1.4218645095825195,
      "learning_rate": 0.00012876842744353112,
      "loss": 1.3175,
      "step": 525
    },
    {
      "epoch": 2.3503325942350335,
      "grad_norm": 0.3768659234046936,
      "learning_rate": 0.00012727846895481434,
      "loss": 1.3201,
      "step": 530
    },
    {
      "epoch": 2.3725055432372506,
      "grad_norm": 0.35776379704475403,
      "learning_rate": 0.00012578193858040507,
      "loss": 1.3274,
      "step": 535
    },
    {
      "epoch": 2.3946784922394677,
      "grad_norm": 0.3721405267715454,
      "learning_rate": 0.0001242791968620394,
      "loss": 1.3307,
      "step": 540
    },
    {
      "epoch": 2.4168514412416853,
      "grad_norm": 0.37725499272346497,
      "learning_rate": 0.00012277060583788064,
      "loss": 1.3324,
      "step": 545
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 0.3748611807823181,
      "learning_rate": 0.00012125652895529766,
      "loss": 1.3269,
      "step": 550
    },
    {
      "epoch": 2.4611973392461195,
      "grad_norm": 0.3902246952056885,
      "learning_rate": 0.00011973733098330368,
      "loss": 1.3257,
      "step": 555
    },
    {
      "epoch": 2.483370288248337,
      "grad_norm": 0.37103980779647827,
      "learning_rate": 0.0001182133779246766,
      "loss": 1.3073,
      "step": 560
    },
    {
      "epoch": 2.505543237250554,
      "grad_norm": 0.38661038875579834,
      "learning_rate": 0.00011668503692778239,
      "loss": 1.3261,
      "step": 565
    },
    {
      "epoch": 2.5277161862527717,
      "grad_norm": 0.3725627362728119,
      "learning_rate": 0.00011515267619812214,
      "loss": 1.3207,
      "step": 570
    },
    {
      "epoch": 2.549889135254989,
      "grad_norm": 0.3544328212738037,
      "learning_rate": 0.00011361666490962468,
      "loss": 1.3254,
      "step": 575
    },
    {
      "epoch": 2.5720620842572064,
      "grad_norm": 0.37323811650276184,
      "learning_rate": 0.00011207737311570559,
      "loss": 1.3216,
      "step": 580
    },
    {
      "epoch": 2.5942350332594235,
      "grad_norm": 0.42373356223106384,
      "learning_rate": 0.00011053517166011471,
      "loss": 1.3131,
      "step": 585
    },
    {
      "epoch": 2.6164079822616406,
      "grad_norm": 0.37566041946411133,
      "learning_rate": 0.00010899043208759305,
      "loss": 1.3357,
      "step": 590
    },
    {
      "epoch": 2.638580931263858,
      "grad_norm": 0.36090078949928284,
      "learning_rate": 0.00010744352655436059,
      "loss": 1.3416,
      "step": 595
    },
    {
      "epoch": 2.6607538802660753,
      "grad_norm": 0.3593694567680359,
      "learning_rate": 0.00010589482773845727,
      "loss": 1.3277,
      "step": 600
    },
    {
      "epoch": 2.682926829268293,
      "grad_norm": 0.356411337852478,
      "learning_rate": 0.00010434470874995781,
      "loss": 1.3114,
      "step": 605
    },
    {
      "epoch": 2.70509977827051,
      "grad_norm": 0.376769095659256,
      "learning_rate": 0.00010279354304108271,
      "loss": 1.3027,
      "step": 610
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.3567696213722229,
      "learning_rate": 0.0001012417043162266,
      "loss": 1.3058,
      "step": 615
    },
    {
      "epoch": 2.7494456762749446,
      "grad_norm": 0.3865494728088379,
      "learning_rate": 9.968956644192617e-05,
      "loss": 1.3247,
      "step": 620
    },
    {
      "epoch": 2.7716186252771617,
      "grad_norm": 0.3545072674751282,
      "learning_rate": 9.813750335678866e-05,
      "loss": 1.319,
      "step": 625
    },
    {
      "epoch": 2.7937915742793793,
      "grad_norm": 0.3772957921028137,
      "learning_rate": 9.658588898140322e-05,
      "loss": 1.3151,
      "step": 630
    },
    {
      "epoch": 2.8159645232815964,
      "grad_norm": 0.3590118885040283,
      "learning_rate": 9.503509712825658e-05,
      "loss": 1.3115,
      "step": 635
    },
    {
      "epoch": 2.8381374722838135,
      "grad_norm": 0.3592722713947296,
      "learning_rate": 9.348550141167472e-05,
      "loss": 1.2971,
      "step": 640
    },
    {
      "epoch": 2.860310421286031,
      "grad_norm": 0.35377687215805054,
      "learning_rate": 9.193747515781224e-05,
      "loss": 1.3128,
      "step": 645
    },
    {
      "epoch": 2.882483370288248,
      "grad_norm": 0.36321666836738586,
      "learning_rate": 9.039139131471128e-05,
      "loss": 1.3141,
      "step": 650
    },
    {
      "epoch": 2.9046563192904657,
      "grad_norm": 0.36464789509773254,
      "learning_rate": 8.884762236245145e-05,
      "loss": 1.3136,
      "step": 655
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 0.36149683594703674,
      "learning_rate": 8.730654022341256e-05,
      "loss": 1.3242,
      "step": 660
    },
    {
      "epoch": 2.9490022172949004,
      "grad_norm": 0.3480617105960846,
      "learning_rate": 8.57685161726715e-05,
      "loss": 1.3297,
      "step": 665
    },
    {
      "epoch": 2.9711751662971175,
      "grad_norm": 0.3669663965702057,
      "learning_rate": 8.423392074855545e-05,
      "loss": 1.3073,
      "step": 670
    },
    {
      "epoch": 2.9933481152993346,
      "grad_norm": 0.34812483191490173,
      "learning_rate": 8.270312366337226e-05,
      "loss": 1.3157,
      "step": 675
    },
    {
      "epoch": 2.9977827050997785,
      "eval_loss": 1.7700002193450928,
      "eval_runtime": 0.3583,
      "eval_samples_per_second": 2.791,
      "eval_steps_per_second": 2.791,
      "step": 676
    },
    {
      "epoch": 3.015521064301552,
      "grad_norm": 0.3915573060512543,
      "learning_rate": 8.117649371433994e-05,
      "loss": 1.298,
      "step": 680
    },
    {
      "epoch": 3.0376940133037693,
      "grad_norm": 0.37077027559280396,
      "learning_rate": 7.965439869473664e-05,
      "loss": 1.2853,
      "step": 685
    },
    {
      "epoch": 3.059866962305987,
      "grad_norm": 0.3731926381587982,
      "learning_rate": 7.813720530529243e-05,
      "loss": 1.2908,
      "step": 690
    },
    {
      "epoch": 3.082039911308204,
      "grad_norm": 0.37934252619743347,
      "learning_rate": 7.66252790658445e-05,
      "loss": 1.2732,
      "step": 695
    },
    {
      "epoch": 3.104212860310421,
      "grad_norm": 0.4166705310344696,
      "learning_rate": 7.511898422727642e-05,
      "loss": 1.2702,
      "step": 700
    },
    {
      "epoch": 3.1263858093126387,
      "grad_norm": 0.3665112257003784,
      "learning_rate": 7.361868368376364e-05,
      "loss": 1.2801,
      "step": 705
    },
    {
      "epoch": 3.1485587583148558,
      "grad_norm": 0.393635094165802,
      "learning_rate": 7.212473888534546e-05,
      "loss": 1.2873,
      "step": 710
    },
    {
      "epoch": 3.1707317073170733,
      "grad_norm": 0.37354576587677,
      "learning_rate": 7.063750975084518e-05,
      "loss": 1.2823,
      "step": 715
    },
    {
      "epoch": 3.1929046563192904,
      "grad_norm": 0.3939523994922638,
      "learning_rate": 6.915735458115884e-05,
      "loss": 1.2766,
      "step": 720
    },
    {
      "epoch": 3.2150776053215075,
      "grad_norm": 0.3616690933704376,
      "learning_rate": 6.768462997293413e-05,
      "loss": 1.2892,
      "step": 725
    },
    {
      "epoch": 3.237250554323725,
      "grad_norm": 0.3850267231464386,
      "learning_rate": 6.62196907326595e-05,
      "loss": 1.2981,
      "step": 730
    },
    {
      "epoch": 3.259423503325942,
      "grad_norm": 0.39054858684539795,
      "learning_rate": 6.476288979118496e-05,
      "loss": 1.3101,
      "step": 735
    },
    {
      "epoch": 3.2815964523281598,
      "grad_norm": 0.38400739431381226,
      "learning_rate": 6.331457811869437e-05,
      "loss": 1.2923,
      "step": 740
    },
    {
      "epoch": 3.303769401330377,
      "grad_norm": 0.3852229714393616,
      "learning_rate": 6.187510464015022e-05,
      "loss": 1.2801,
      "step": 745
    },
    {
      "epoch": 3.3259423503325944,
      "grad_norm": 0.3806511461734772,
      "learning_rate": 6.0444816151231375e-05,
      "loss": 1.2816,
      "step": 750
    },
    {
      "epoch": 3.3481152993348116,
      "grad_norm": 0.3717353045940399,
      "learning_rate": 5.902405723478346e-05,
      "loss": 1.2615,
      "step": 755
    },
    {
      "epoch": 3.3702882483370287,
      "grad_norm": 0.3781892657279968,
      "learning_rate": 5.76131701778025e-05,
      "loss": 1.2936,
      "step": 760
    },
    {
      "epoch": 3.3924611973392462,
      "grad_norm": 0.38951125741004944,
      "learning_rate": 5.621249488897176e-05,
      "loss": 1.2719,
      "step": 765
    },
    {
      "epoch": 3.4146341463414633,
      "grad_norm": 0.6626437306404114,
      "learning_rate": 5.4822368816771406e-05,
      "loss": 1.2889,
      "step": 770
    },
    {
      "epoch": 3.436807095343681,
      "grad_norm": 0.3741094172000885,
      "learning_rate": 5.344312686818106e-05,
      "loss": 1.2795,
      "step": 775
    },
    {
      "epoch": 3.458980044345898,
      "grad_norm": 0.38097867369651794,
      "learning_rate": 5.207510132799436e-05,
      "loss": 1.2923,
      "step": 780
    },
    {
      "epoch": 3.481152993348115,
      "grad_norm": 0.3767342269420624,
      "learning_rate": 5.0718621778765476e-05,
      "loss": 1.278,
      "step": 785
    },
    {
      "epoch": 3.5033259423503327,
      "grad_norm": 0.37775152921676636,
      "learning_rate": 4.9374015021406914e-05,
      "loss": 1.2681,
      "step": 790
    },
    {
      "epoch": 3.52549889135255,
      "grad_norm": 0.3940396010875702,
      "learning_rate": 4.804160499645667e-05,
      "loss": 1.2799,
      "step": 795
    },
    {
      "epoch": 3.5476718403547673,
      "grad_norm": 0.3780502378940582,
      "learning_rate": 4.6721712706035236e-05,
      "loss": 1.2897,
      "step": 800
    },
    {
      "epoch": 3.5698447893569845,
      "grad_norm": 0.3779968321323395,
      "learning_rate": 4.5414656136510334e-05,
      "loss": 1.2842,
      "step": 805
    },
    {
      "epoch": 3.5920177383592016,
      "grad_norm": 0.38577476143836975,
      "learning_rate": 4.412075018188805e-05,
      "loss": 1.2793,
      "step": 810
    },
    {
      "epoch": 3.614190687361419,
      "grad_norm": 0.3731294274330139,
      "learning_rate": 4.2840306567949076e-05,
      "loss": 1.2809,
      "step": 815
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.37152302265167236,
      "learning_rate": 4.157363377714819e-05,
      "loss": 1.3013,
      "step": 820
    },
    {
      "epoch": 3.658536585365854,
      "grad_norm": 0.38100916147232056,
      "learning_rate": 4.0321036974295156e-05,
      "loss": 1.2836,
      "step": 825
    },
    {
      "epoch": 3.680709534368071,
      "grad_norm": 0.3642306625843048,
      "learning_rate": 3.9082817933035134e-05,
      "loss": 1.2839,
      "step": 830
    },
    {
      "epoch": 3.7028824833702885,
      "grad_norm": 0.3758902847766876,
      "learning_rate": 3.785927496314543e-05,
      "loss": 1.2876,
      "step": 835
    },
    {
      "epoch": 3.7250554323725056,
      "grad_norm": 0.3736809194087982,
      "learning_rate": 3.6650702838667464e-05,
      "loss": 1.2741,
      "step": 840
    },
    {
      "epoch": 3.7472283813747227,
      "grad_norm": 0.36693236231803894,
      "learning_rate": 3.5457392726890236e-05,
      "loss": 1.2791,
      "step": 845
    },
    {
      "epoch": 3.7694013303769403,
      "grad_norm": 0.38247162103652954,
      "learning_rate": 3.427963211820274e-05,
      "loss": 1.2813,
      "step": 850
    },
    {
      "epoch": 3.7915742793791574,
      "grad_norm": 0.37350913882255554,
      "learning_rate": 3.3117704756832226e-05,
      "loss": 1.29,
      "step": 855
    },
    {
      "epoch": 3.8137472283813745,
      "grad_norm": 0.44421860575675964,
      "learning_rate": 3.197189057248491e-05,
      "loss": 1.2773,
      "step": 860
    },
    {
      "epoch": 3.835920177383592,
      "grad_norm": 0.3692834973335266,
      "learning_rate": 3.0842465612905837e-05,
      "loss": 1.2869,
      "step": 865
    },
    {
      "epoch": 3.858093126385809,
      "grad_norm": 0.375489205121994,
      "learning_rate": 2.9729701977374035e-05,
      "loss": 1.2846,
      "step": 870
    },
    {
      "epoch": 3.8802660753880267,
      "grad_norm": 0.3838193714618683,
      "learning_rate": 2.863386775114848e-05,
      "loss": 1.294,
      "step": 875
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 0.38194307684898376,
      "learning_rate": 2.7555226940881583e-05,
      "loss": 1.2838,
      "step": 880
    },
    {
      "epoch": 3.9246119733924614,
      "grad_norm": 0.3884502947330475,
      "learning_rate": 2.6494039411015193e-05,
      "loss": 1.301,
      "step": 885
    },
    {
      "epoch": 3.9467849223946785,
      "grad_norm": 0.38043659925460815,
      "learning_rate": 2.545056082117433e-05,
      "loss": 1.2984,
      "step": 890
    },
    {
      "epoch": 3.9689578713968956,
      "grad_norm": 0.37292882800102234,
      "learning_rate": 2.4425042564574184e-05,
      "loss": 1.2826,
      "step": 895
    },
    {
      "epoch": 3.991130820399113,
      "grad_norm": 0.37573322653770447,
      "learning_rate": 2.3417731707454737e-05,
      "loss": 1.2688,
      "step": 900
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.7925071716308594,
      "eval_runtime": 0.3371,
      "eval_samples_per_second": 2.967,
      "eval_steps_per_second": 2.967,
      "step": 902
    },
    {
      "epoch": 4.013303769401331,
      "grad_norm": 0.37189018726348877,
      "learning_rate": 2.242887092955801e-05,
      "loss": 1.2666,
      "step": 905
    },
    {
      "epoch": 4.035476718403547,
      "grad_norm": 0.37796613574028015,
      "learning_rate": 2.1458698465662187e-05,
      "loss": 1.2526,
      "step": 910
    },
    {
      "epoch": 4.057649667405765,
      "grad_norm": 0.3842335343360901,
      "learning_rate": 2.0507448048186208e-05,
      "loss": 1.2523,
      "step": 915
    },
    {
      "epoch": 4.0798226164079825,
      "grad_norm": 0.38330337405204773,
      "learning_rate": 1.957534885087944e-05,
      "loss": 1.2627,
      "step": 920
    },
    {
      "epoch": 4.101995565410199,
      "grad_norm": 0.37810632586479187,
      "learning_rate": 1.866262543360958e-05,
      "loss": 1.2702,
      "step": 925
    },
    {
      "epoch": 4.124168514412417,
      "grad_norm": 0.39427462220191956,
      "learning_rate": 1.7769497688261973e-05,
      "loss": 1.2574,
      "step": 930
    },
    {
      "epoch": 4.146341463414634,
      "grad_norm": 0.39581403136253357,
      "learning_rate": 1.6896180785763593e-05,
      "loss": 1.2577,
      "step": 935
    },
    {
      "epoch": 4.168514412416852,
      "grad_norm": 0.3902391195297241,
      "learning_rate": 1.604288512424439e-05,
      "loss": 1.2624,
      "step": 940
    },
    {
      "epoch": 4.1906873614190685,
      "grad_norm": 0.3963169753551483,
      "learning_rate": 1.520981627834851e-05,
      "loss": 1.2757,
      "step": 945
    },
    {
      "epoch": 4.212860310421286,
      "grad_norm": 0.379292756319046,
      "learning_rate": 1.4397174949707725e-05,
      "loss": 1.2572,
      "step": 950
    },
    {
      "epoch": 4.235033259423504,
      "grad_norm": 0.3748960494995117,
      "learning_rate": 1.3605156918588469e-05,
      "loss": 1.2713,
      "step": 955
    },
    {
      "epoch": 4.25720620842572,
      "grad_norm": 0.3822687268257141,
      "learning_rate": 1.2833952996724863e-05,
      "loss": 1.2634,
      "step": 960
    },
    {
      "epoch": 4.279379157427938,
      "grad_norm": 0.3805009126663208,
      "learning_rate": 1.208374898134883e-05,
      "loss": 1.2715,
      "step": 965
    },
    {
      "epoch": 4.301552106430155,
      "grad_norm": 0.38446545600891113,
      "learning_rate": 1.1354725610427807e-05,
      "loss": 1.2776,
      "step": 970
    },
    {
      "epoch": 4.323725055432373,
      "grad_norm": 0.37589287757873535,
      "learning_rate": 1.0647058519121821e-05,
      "loss": 1.2405,
      "step": 975
    },
    {
      "epoch": 4.34589800443459,
      "grad_norm": 0.38052481412887573,
      "learning_rate": 9.960918197469771e-06,
      "loss": 1.2674,
      "step": 980
    },
    {
      "epoch": 4.368070953436807,
      "grad_norm": 0.3807436227798462,
      "learning_rate": 9.296469949315156e-06,
      "loss": 1.2721,
      "step": 985
    },
    {
      "epoch": 4.390243902439025,
      "grad_norm": 0.38531798124313354,
      "learning_rate": 8.653873852481364e-06,
      "loss": 1.2474,
      "step": 990
    },
    {
      "epoch": 4.412416851441241,
      "grad_norm": 0.3917078673839569,
      "learning_rate": 8.033284720205946e-06,
      "loss": 1.2672,
      "step": 995
    },
    {
      "epoch": 4.434589800443459,
      "grad_norm": 0.372130423784256,
      "learning_rate": 7.434852063843278e-06,
      "loss": 1.2621,
      "step": 1000
    },
    {
      "epoch": 4.4567627494456765,
      "grad_norm": 0.37912076711654663,
      "learning_rate": 6.858720056844614e-06,
      "loss": 1.2607,
      "step": 1005
    },
    {
      "epoch": 4.478935698447893,
      "grad_norm": 0.39060723781585693,
      "learning_rate": 6.3050275000238414e-06,
      "loss": 1.2672,
      "step": 1010
    },
    {
      "epoch": 4.501108647450111,
      "grad_norm": 0.3805095851421356,
      "learning_rate": 5.77390778811796e-06,
      "loss": 1.2756,
      "step": 1015
    },
    {
      "epoch": 4.523281596452328,
      "grad_norm": 0.39004358649253845,
      "learning_rate": 5.265488877649816e-06,
      "loss": 1.2687,
      "step": 1020
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.3834868371486664,
      "learning_rate": 4.7798932561009865e-06,
      "loss": 1.2681,
      "step": 1025
    },
    {
      "epoch": 4.5676274944567625,
      "grad_norm": 0.3744969666004181,
      "learning_rate": 4.317237912402316e-06,
      "loss": 1.2697,
      "step": 1030
    },
    {
      "epoch": 4.58980044345898,
      "grad_norm": 0.3825860321521759,
      "learning_rate": 3.877634308749078e-06,
      "loss": 1.2459,
      "step": 1035
    },
    {
      "epoch": 4.611973392461198,
      "grad_norm": 0.38495102524757385,
      "learning_rate": 3.461188353747702e-06,
      "loss": 1.2642,
      "step": 1040
    },
    {
      "epoch": 4.634146341463414,
      "grad_norm": 0.3805482089519501,
      "learning_rate": 3.068000376900515e-06,
      "loss": 1.2781,
      "step": 1045
    },
    {
      "epoch": 4.656319290465632,
      "grad_norm": 0.3828931748867035,
      "learning_rate": 2.6981651044344024e-06,
      "loss": 1.2646,
      "step": 1050
    },
    {
      "epoch": 4.678492239467849,
      "grad_norm": 0.38155028223991394,
      "learning_rate": 2.3517716364795385e-06,
      "loss": 1.2696,
      "step": 1055
    },
    {
      "epoch": 4.700665188470067,
      "grad_norm": 0.3936275541782379,
      "learning_rate": 2.028903425603612e-06,
      "loss": 1.2635,
      "step": 1060
    },
    {
      "epoch": 4.722838137472284,
      "grad_norm": 0.37505555152893066,
      "learning_rate": 1.7296382567064672e-06,
      "loss": 1.2617,
      "step": 1065
    },
    {
      "epoch": 4.745011086474501,
      "grad_norm": 0.3843250572681427,
      "learning_rate": 1.4540482282803137e-06,
      "loss": 1.246,
      "step": 1070
    },
    {
      "epoch": 4.767184035476719,
      "grad_norm": 0.388374388217926,
      "learning_rate": 1.2021997350399106e-06,
      "loss": 1.2853,
      "step": 1075
    },
    {
      "epoch": 4.789356984478935,
      "grad_norm": 0.3848237991333008,
      "learning_rate": 9.741534519267736e-07,
      "loss": 1.2703,
      "step": 1080
    },
    {
      "epoch": 4.811529933481153,
      "grad_norm": 0.3839035928249359,
      "learning_rate": 7.699643194915784e-07,
      "loss": 1.2602,
      "step": 1085
    },
    {
      "epoch": 4.8337028824833705,
      "grad_norm": 0.3856402337551117,
      "learning_rate": 5.896815306578818e-07,
      "loss": 1.2569,
      "step": 1090
    },
    {
      "epoch": 4.855875831485587,
      "grad_norm": 0.38281336426734924,
      "learning_rate": 4.333485188706576e-07,
      "loss": 1.2648,
      "step": 1095
    },
    {
      "epoch": 4.878048780487805,
      "grad_norm": 0.37251806259155273,
      "learning_rate": 3.0100294763238946e-07,
      "loss": 1.2769,
      "step": 1100
    },
    {
      "epoch": 4.900221729490022,
      "grad_norm": 0.38437706232070923,
      "learning_rate": 1.9267670142926187e-07,
      "loss": 1.2534,
      "step": 1105
    },
    {
      "epoch": 4.922394678492239,
      "grad_norm": 0.3764530420303345,
      "learning_rate": 1.0839587804954975e-07,
      "loss": 1.2557,
      "step": 1110
    },
    {
      "epoch": 4.9445676274944566,
      "grad_norm": 0.3766900599002838,
      "learning_rate": 4.818078229622547e-08,
      "loss": 1.2779,
      "step": 1115
    },
    {
      "epoch": 4.966740576496674,
      "grad_norm": 0.3775485157966614,
      "learning_rate": 1.2045921095127366e-08,
      "loss": 1.265,
      "step": 1120
    },
    {
      "epoch": 4.988913525498892,
      "grad_norm": 0.38629209995269775,
      "learning_rate": 0.0,
      "loss": 1.2699,
      "step": 1125
    },
    {
      "epoch": 4.988913525498892,
      "eval_loss": 1.8047916889190674,
      "eval_runtime": 0.3388,
      "eval_samples_per_second": 2.951,
      "eval_steps_per_second": 2.951,
      "step": 1125
    },
    {
      "epoch": 4.988913525498892,
      "step": 1125,
      "total_flos": 1.6629843858229821e+18,
      "train_loss": 1.3908887059953479,
      "train_runtime": 3606.4613,
      "train_samples_per_second": 9.989,
      "train_steps_per_second": 0.312
    }
  ],
  "logging_steps": 5,
  "max_steps": 1125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6629843858229821e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}