{
  "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": 1.9132194519042969,
      "learning_rate": 1.7699115044247788e-06,
      "loss": 2.8127,
      "step": 1
    },
    {
      "epoch": 0.022172949002217297,
      "grad_norm": 2.0755808353424072,
      "learning_rate": 8.849557522123894e-06,
      "loss": 2.8248,
      "step": 5
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 1.6995130777359009,
      "learning_rate": 1.7699115044247787e-05,
      "loss": 2.7381,
      "step": 10
    },
    {
      "epoch": 0.06651884700665188,
      "grad_norm": 1.6350675821304321,
      "learning_rate": 2.6548672566371686e-05,
      "loss": 2.6572,
      "step": 15
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 1.2029041051864624,
      "learning_rate": 3.5398230088495574e-05,
      "loss": 2.4881,
      "step": 20
    },
    {
      "epoch": 0.11086474501108648,
      "grad_norm": 0.7936518788337708,
      "learning_rate": 4.4247787610619477e-05,
      "loss": 2.3403,
      "step": 25
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 0.8098437190055847,
      "learning_rate": 5.309734513274337e-05,
      "loss": 2.2186,
      "step": 30
    },
    {
      "epoch": 0.15521064301552107,
      "grad_norm": 0.6613564491271973,
      "learning_rate": 6.194690265486725e-05,
      "loss": 2.1041,
      "step": 35
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 0.6659165620803833,
      "learning_rate": 7.079646017699115e-05,
      "loss": 1.9928,
      "step": 40
    },
    {
      "epoch": 0.19955654101995565,
      "grad_norm": 0.559091329574585,
      "learning_rate": 7.964601769911504e-05,
      "loss": 1.9216,
      "step": 45
    },
    {
      "epoch": 0.22172949002217296,
      "grad_norm": 0.4300543963909149,
      "learning_rate": 8.849557522123895e-05,
      "loss": 1.8657,
      "step": 50
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.34058740735054016,
      "learning_rate": 9.734513274336283e-05,
      "loss": 1.7914,
      "step": 55
    },
    {
      "epoch": 0.2660753880266075,
      "grad_norm": 0.34278205037117004,
      "learning_rate": 0.00010619469026548674,
      "loss": 1.7762,
      "step": 60
    },
    {
      "epoch": 0.28824833702882485,
      "grad_norm": 0.31179192662239075,
      "learning_rate": 0.00011504424778761063,
      "loss": 1.7351,
      "step": 65
    },
    {
      "epoch": 0.31042128603104213,
      "grad_norm": 0.3422749936580658,
      "learning_rate": 0.0001238938053097345,
      "loss": 1.6966,
      "step": 70
    },
    {
      "epoch": 0.3325942350332594,
      "grad_norm": 0.4129348397254944,
      "learning_rate": 0.00013274336283185842,
      "loss": 1.6817,
      "step": 75
    },
    {
      "epoch": 0.35476718403547675,
      "grad_norm": 0.48307937383651733,
      "learning_rate": 0.0001415929203539823,
      "loss": 1.6672,
      "step": 80
    },
    {
      "epoch": 0.376940133037694,
      "grad_norm": 0.5420916676521301,
      "learning_rate": 0.00015044247787610618,
      "loss": 1.6174,
      "step": 85
    },
    {
      "epoch": 0.3991130820399113,
      "grad_norm": 0.41327813267707825,
      "learning_rate": 0.0001592920353982301,
      "loss": 1.5966,
      "step": 90
    },
    {
      "epoch": 0.4212860310421286,
      "grad_norm": 0.4299337565898895,
      "learning_rate": 0.000168141592920354,
      "loss": 1.569,
      "step": 95
    },
    {
      "epoch": 0.4434589800443459,
      "grad_norm": 0.3761642575263977,
      "learning_rate": 0.0001769911504424779,
      "loss": 1.5668,
      "step": 100
    },
    {
      "epoch": 0.4656319290465632,
      "grad_norm": 0.41222497820854187,
      "learning_rate": 0.0001858407079646018,
      "loss": 1.5515,
      "step": 105
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.4026060402393341,
      "learning_rate": 0.00019469026548672567,
      "loss": 1.5341,
      "step": 110
    },
    {
      "epoch": 0.5099778270509978,
      "grad_norm": 0.36704277992248535,
      "learning_rate": 0.00019999807262012045,
      "loss": 1.536,
      "step": 115
    },
    {
      "epoch": 0.532150776053215,
      "grad_norm": 0.33943068981170654,
      "learning_rate": 0.00019997639044970784,
      "loss": 1.5084,
      "step": 120
    },
    {
      "epoch": 0.5543237250554324,
      "grad_norm": 0.42166343331336975,
      "learning_rate": 0.00019993062212508053,
      "loss": 1.5056,
      "step": 125
    },
    {
      "epoch": 0.5764966740576497,
      "grad_norm": 0.3949909806251526,
      "learning_rate": 0.00019986077867267113,
      "loss": 1.4979,
      "step": 130
    },
    {
      "epoch": 0.5986696230598669,
      "grad_norm": 0.47220396995544434,
      "learning_rate": 0.00019976687691905393,
      "loss": 1.4935,
      "step": 135
    },
    {
      "epoch": 0.6208425720620843,
      "grad_norm": 0.4970516860485077,
      "learning_rate": 0.00019964893948689122,
      "loss": 1.5058,
      "step": 140
    },
    {
      "epoch": 0.6430155210643016,
      "grad_norm": 0.40719351172447205,
      "learning_rate": 0.00019950699478948309,
      "loss": 1.4937,
      "step": 145
    },
    {
      "epoch": 0.6651884700665188,
      "grad_norm": 0.3738563358783722,
      "learning_rate": 0.000199341077023922,
      "loss": 1.4998,
      "step": 150
    },
    {
      "epoch": 0.6873614190687362,
      "grad_norm": 0.3738692104816437,
      "learning_rate": 0.00019915122616285418,
      "loss": 1.4868,
      "step": 155
    },
    {
      "epoch": 0.7095343680709535,
      "grad_norm": 0.3409136235713959,
      "learning_rate": 0.00019893748794484948,
      "loss": 1.4755,
      "step": 160
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 0.36116743087768555,
      "learning_rate": 0.0001986999138633821,
      "loss": 1.4555,
      "step": 165
    },
    {
      "epoch": 0.753880266075388,
      "grad_norm": 0.38903379440307617,
      "learning_rate": 0.00019843856115442482,
      "loss": 1.4628,
      "step": 170
    },
    {
      "epoch": 0.7760532150776053,
      "grad_norm": 0.42216047644615173,
      "learning_rate": 0.00019815349278265988,
      "loss": 1.4725,
      "step": 175
    },
    {
      "epoch": 0.7982261640798226,
      "grad_norm": 0.3521736264228821,
      "learning_rate": 0.00019784477742630952,
      "loss": 1.4695,
      "step": 180
    },
    {
      "epoch": 0.8203991130820399,
      "grad_norm": 0.3384956419467926,
      "learning_rate": 0.00019751248946059014,
      "loss": 1.4512,
      "step": 185
    },
    {
      "epoch": 0.8425720620842572,
      "grad_norm": 0.35126349329948425,
      "learning_rate": 0.00019715670893979414,
      "loss": 1.4509,
      "step": 190
    },
    {
      "epoch": 0.8647450110864745,
      "grad_norm": 0.37433576583862305,
      "learning_rate": 0.00019677752157800312,
      "loss": 1.4386,
      "step": 195
    },
    {
      "epoch": 0.8869179600886918,
      "grad_norm": 0.39587318897247314,
      "learning_rate": 0.0001963750187284379,
      "loss": 1.4529,
      "step": 200
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.403945654630661,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.4368,
      "step": 205
    },
    {
      "epoch": 0.9312638580931264,
      "grad_norm": 0.3656717538833618,
      "learning_rate": 0.0001955004600411586,
      "loss": 1.4208,
      "step": 210
    },
    {
      "epoch": 0.9534368070953437,
      "grad_norm": 0.409030556678772,
      "learning_rate": 0.0001950286149007434,
      "loss": 1.4151,
      "step": 215
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.4138728678226471,
      "learning_rate": 0.0001945338756163907,
      "loss": 1.4441,
      "step": 220
    },
    {
      "epoch": 0.9977827050997783,
      "grad_norm": 0.4125191271305084,
      "learning_rate": 0.00019401636137990816,
      "loss": 1.4429,
      "step": 225
    },
    {
      "epoch": 0.9977827050997783,
      "eval_loss": 1.7484289407730103,
      "eval_runtime": 0.374,
      "eval_samples_per_second": 2.674,
      "eval_steps_per_second": 2.674,
      "step": 225
    },
    {
      "epoch": 1.0199556541019956,
      "grad_norm": 0.498823344707489,
      "learning_rate": 0.00019347619687000892,
      "loss": 1.4079,
      "step": 230
    },
    {
      "epoch": 1.042128603104213,
      "grad_norm": 0.3439851999282837,
      "learning_rate": 0.00019291351222227432,
      "loss": 1.4058,
      "step": 235
    },
    {
      "epoch": 1.06430155210643,
      "grad_norm": 0.38840946555137634,
      "learning_rate": 0.0001923284429978017,
      "loss": 1.4204,
      "step": 240
    },
    {
      "epoch": 1.0864745011086474,
      "grad_norm": 0.34416335821151733,
      "learning_rate": 0.00019172113015054532,
      "loss": 1.4056,
      "step": 245
    },
    {
      "epoch": 1.1086474501108647,
      "grad_norm": 0.3941856324672699,
      "learning_rate": 0.00019109171999335793,
      "loss": 1.4249,
      "step": 250
    },
    {
      "epoch": 1.130820399113082,
      "grad_norm": 0.36946943402290344,
      "learning_rate": 0.00019044036416274133,
      "loss": 1.4083,
      "step": 255
    },
    {
      "epoch": 1.1529933481152994,
      "grad_norm": 0.3524357080459595,
      "learning_rate": 0.00018976721958231438,
      "loss": 1.3953,
      "step": 260
    },
    {
      "epoch": 1.1751662971175167,
      "grad_norm": 0.39715054631233215,
      "learning_rate": 0.00018907244842500704,
      "loss": 1.4021,
      "step": 265
    },
    {
      "epoch": 1.1973392461197339,
      "grad_norm": 0.43194007873535156,
      "learning_rate": 0.00018835621807399016,
      "loss": 1.4057,
      "step": 270
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 0.38655465841293335,
      "learning_rate": 0.0001876187010823496,
      "loss": 1.3816,
      "step": 275
    },
    {
      "epoch": 1.2416851441241685,
      "grad_norm": 0.330555260181427,
      "learning_rate": 0.00018686007513151514,
      "loss": 1.3913,
      "step": 280
    },
    {
      "epoch": 1.2638580931263859,
      "grad_norm": 0.34880608320236206,
      "learning_rate": 0.0001860805229884536,
      "loss": 1.407,
      "step": 285
    },
    {
      "epoch": 1.2860310421286032,
      "grad_norm": 0.38133811950683594,
      "learning_rate": 0.00018528023246163717,
      "loss": 1.3834,
      "step": 290
    },
    {
      "epoch": 1.3082039911308203,
      "grad_norm": 0.36675792932510376,
      "learning_rate": 0.00018445939635579656,
      "loss": 1.377,
      "step": 295
    },
    {
      "epoch": 1.3303769401330376,
      "grad_norm": 0.383324533700943,
      "learning_rate": 0.0001836182124254711,
      "loss": 1.3904,
      "step": 300
    },
    {
      "epoch": 1.352549889135255,
      "grad_norm": 0.47266829013824463,
      "learning_rate": 0.00018275688332736577,
      "loss": 1.3839,
      "step": 305
    },
    {
      "epoch": 1.3747228381374723,
      "grad_norm": 0.36780834197998047,
      "learning_rate": 0.00018187561657152757,
      "loss": 1.3729,
      "step": 310
    },
    {
      "epoch": 1.3968957871396896,
      "grad_norm": 0.35294458270072937,
      "learning_rate": 0.00018097462447135273,
      "loss": 1.386,
      "step": 315
    },
    {
      "epoch": 1.4190687361419068,
      "grad_norm": 0.36432820558547974,
      "learning_rate": 0.00018005412409243606,
      "loss": 1.3678,
      "step": 320
    },
    {
      "epoch": 1.441241685144124,
      "grad_norm": 0.38247236609458923,
      "learning_rate": 0.00017911433720027624,
      "loss": 1.3612,
      "step": 325
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 0.4539274275302887,
      "learning_rate": 0.00017815549020684825,
      "loss": 1.3778,
      "step": 330
    },
    {
      "epoch": 1.4855875831485588,
      "grad_norm": 0.39669978618621826,
      "learning_rate": 0.0001771778141160566,
      "loss": 1.38,
      "step": 335
    },
    {
      "epoch": 1.507760532150776,
      "grad_norm": 0.3531462550163269,
      "learning_rate": 0.0001761815444680822,
      "loss": 1.3805,
      "step": 340
    },
    {
      "epoch": 1.5299334811529932,
      "grad_norm": 0.3824242055416107,
      "learning_rate": 0.00017516692128263648,
      "loss": 1.3764,
      "step": 345
    },
    {
      "epoch": 1.5521064301552108,
      "grad_norm": 0.3946467936038971,
      "learning_rate": 0.00017413418900113605,
      "loss": 1.3678,
      "step": 350
    },
    {
      "epoch": 1.5742793791574279,
      "grad_norm": 0.38375967741012573,
      "learning_rate": 0.00017308359642781242,
      "loss": 1.3767,
      "step": 355
    },
    {
      "epoch": 1.5964523281596452,
      "grad_norm": 0.418390154838562,
      "learning_rate": 0.00017201539666977043,
      "loss": 1.3734,
      "step": 360
    },
    {
      "epoch": 1.6186252771618626,
      "grad_norm": 0.35475605726242065,
      "learning_rate": 0.0001709298470760101,
      "loss": 1.3733,
      "step": 365
    },
    {
      "epoch": 1.6407982261640797,
      "grad_norm": 0.35535967350006104,
      "learning_rate": 0.0001698272091754264,
      "loss": 1.3879,
      "step": 370
    },
    {
      "epoch": 1.6629711751662972,
      "grad_norm": 0.38182777166366577,
      "learning_rate": 0.00016870774861380228,
      "loss": 1.3673,
      "step": 375
    },
    {
      "epoch": 1.6851441241685143,
      "grad_norm": 0.4077872037887573,
      "learning_rate": 0.00016757173508980965,
      "loss": 1.3711,
      "step": 380
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 0.42192327976226807,
      "learning_rate": 0.00016641944229003395,
      "loss": 1.376,
      "step": 385
    },
    {
      "epoch": 1.729490022172949,
      "grad_norm": 0.36239758133888245,
      "learning_rate": 0.00016525114782303807,
      "loss": 1.3643,
      "step": 390
    },
    {
      "epoch": 1.7516629711751663,
      "grad_norm": 0.37795644998550415,
      "learning_rate": 0.00016406713315248136,
      "loss": 1.3608,
      "step": 395
    },
    {
      "epoch": 1.7738359201773837,
      "grad_norm": 0.33361098170280457,
      "learning_rate": 0.00016286768352930973,
      "loss": 1.3693,
      "step": 400
    },
    {
      "epoch": 1.7960088691796008,
      "grad_norm": 0.36207035183906555,
      "learning_rate": 0.0001616530879230335,
      "loss": 1.3709,
      "step": 405
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.34705451130867004,
      "learning_rate": 0.00016042363895210946,
      "loss": 1.3502,
      "step": 410
    },
    {
      "epoch": 1.8403547671840355,
      "grad_norm": 0.339901864528656,
      "learning_rate": 0.00015917963281344345,
      "loss": 1.3591,
      "step": 415
    },
    {
      "epoch": 1.8625277161862528,
      "grad_norm": 0.3383360505104065,
      "learning_rate": 0.00015792136921103124,
      "loss": 1.3473,
      "step": 420
    },
    {
      "epoch": 1.8847006651884701,
      "grad_norm": 0.3463388979434967,
      "learning_rate": 0.0001566491512837543,
      "loss": 1.3723,
      "step": 425
    },
    {
      "epoch": 1.9068736141906872,
      "grad_norm": 0.36131027340888977,
      "learning_rate": 0.00015536328553234792,
      "loss": 1.3747,
      "step": 430
    },
    {
      "epoch": 1.9290465631929048,
      "grad_norm": 0.3317002058029175,
      "learning_rate": 0.00015406408174555976,
      "loss": 1.3497,
      "step": 435
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.39210090041160583,
      "learning_rate": 0.00015275185292551585,
      "loss": 1.3622,
      "step": 440
    },
    {
      "epoch": 1.9733924611973392,
      "grad_norm": 0.3842204213142395,
      "learning_rate": 0.00015142691521231267,
      "loss": 1.3575,
      "step": 445
    },
    {
      "epoch": 1.9955654101995566,
      "grad_norm": 0.3843972980976105,
      "learning_rate": 0.0001500895878078532,
      "loss": 1.3594,
      "step": 450
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.77187979221344,
      "eval_runtime": 0.3372,
      "eval_samples_per_second": 2.966,
      "eval_steps_per_second": 2.966,
      "step": 451
    },
    {
      "epoch": 2.0177383592017737,
      "grad_norm": 0.3560327887535095,
      "learning_rate": 0.00014874019289894537,
      "loss": 1.3498,
      "step": 455
    },
    {
      "epoch": 2.0399113082039912,
      "grad_norm": 0.3512759804725647,
      "learning_rate": 0.00014737905557968105,
      "loss": 1.3208,
      "step": 460
    },
    {
      "epoch": 2.0620842572062084,
      "grad_norm": 0.35677239298820496,
      "learning_rate": 0.00014600650377311522,
      "loss": 1.3367,
      "step": 465
    },
    {
      "epoch": 2.084257206208426,
      "grad_norm": 0.3483263850212097,
      "learning_rate": 0.00014462286815226314,
      "loss": 1.3235,
      "step": 470
    },
    {
      "epoch": 2.106430155210643,
      "grad_norm": 0.3995297849178314,
      "learning_rate": 0.00014322848206043505,
      "loss": 1.3278,
      "step": 475
    },
    {
      "epoch": 2.12860310421286,
      "grad_norm": 0.34428730607032776,
      "learning_rate": 0.00014182368143092768,
      "loss": 1.3253,
      "step": 480
    },
    {
      "epoch": 2.1507760532150777,
      "grad_norm": 0.3784777820110321,
      "learning_rate": 0.00014040880470609187,
      "loss": 1.3062,
      "step": 485
    },
    {
      "epoch": 2.172949002217295,
      "grad_norm": 0.35997453331947327,
      "learning_rate": 0.00013898419275579522,
      "loss": 1.3055,
      "step": 490
    },
    {
      "epoch": 2.1951219512195124,
      "grad_norm": 0.37477272748947144,
      "learning_rate": 0.00013755018879530075,
      "loss": 1.3283,
      "step": 495
    },
    {
      "epoch": 2.2172949002217295,
      "grad_norm": 0.42467719316482544,
      "learning_rate": 0.00013610713830257954,
      "loss": 1.3244,
      "step": 500
    },
    {
      "epoch": 2.2394678492239466,
      "grad_norm": 0.37103238701820374,
      "learning_rate": 0.00013465538893507907,
      "loss": 1.3338,
      "step": 505
    },
    {
      "epoch": 2.261640798226164,
      "grad_norm": 0.3519739806652069,
      "learning_rate": 0.00013319529044596593,
      "loss": 1.3243,
      "step": 510
    },
    {
      "epoch": 2.2838137472283813,
      "grad_norm": 0.366401731967926,
      "learning_rate": 0.00013172719459986397,
      "loss": 1.3188,
      "step": 515
    },
    {
      "epoch": 2.305986696230599,
      "grad_norm": 0.39243802428245544,
      "learning_rate": 0.0001302514550881076,
      "loss": 1.3119,
      "step": 520
    },
    {
      "epoch": 2.328159645232816,
      "grad_norm": 0.3964441418647766,
      "learning_rate": 0.00012876842744353112,
      "loss": 1.3176,
      "step": 525
    },
    {
      "epoch": 2.3503325942350335,
      "grad_norm": 0.3520803153514862,
      "learning_rate": 0.00012727846895481434,
      "loss": 1.3171,
      "step": 530
    },
    {
      "epoch": 2.3725055432372506,
      "grad_norm": 0.35095489025115967,
      "learning_rate": 0.00012578193858040507,
      "loss": 1.3239,
      "step": 535
    },
    {
      "epoch": 2.3946784922394677,
      "grad_norm": 0.3672475516796112,
      "learning_rate": 0.0001242791968620394,
      "loss": 1.3295,
      "step": 540
    },
    {
      "epoch": 2.4168514412416853,
      "grad_norm": 0.3635219633579254,
      "learning_rate": 0.00012277060583788064,
      "loss": 1.3299,
      "step": 545
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 0.3647380471229553,
      "learning_rate": 0.00012125652895529766,
      "loss": 1.3255,
      "step": 550
    },
    {
      "epoch": 2.4611973392461195,
      "grad_norm": 0.40251094102859497,
      "learning_rate": 0.00011973733098330368,
      "loss": 1.324,
      "step": 555
    },
    {
      "epoch": 2.483370288248337,
      "grad_norm": 0.36837145686149597,
      "learning_rate": 0.0001182133779246766,
      "loss": 1.3061,
      "step": 560
    },
    {
      "epoch": 2.505543237250554,
      "grad_norm": 0.3746941387653351,
      "learning_rate": 0.00011668503692778239,
      "loss": 1.3239,
      "step": 565
    },
    {
      "epoch": 2.5277161862527717,
      "grad_norm": 0.3703044652938843,
      "learning_rate": 0.00011515267619812214,
      "loss": 1.3197,
      "step": 570
    },
    {
      "epoch": 2.549889135254989,
      "grad_norm": 0.3508300185203552,
      "learning_rate": 0.00011361666490962468,
      "loss": 1.3231,
      "step": 575
    },
    {
      "epoch": 2.5720620842572064,
      "grad_norm": 0.36951854825019836,
      "learning_rate": 0.00011207737311570559,
      "loss": 1.3205,
      "step": 580
    },
    {
      "epoch": 2.5942350332594235,
      "grad_norm": 0.3559792637825012,
      "learning_rate": 0.00011053517166011471,
      "loss": 1.312,
      "step": 585
    },
    {
      "epoch": 2.6164079822616406,
      "grad_norm": 0.37214240431785583,
      "learning_rate": 0.00010899043208759305,
      "loss": 1.3354,
      "step": 590
    },
    {
      "epoch": 2.638580931263858,
      "grad_norm": 0.35989540815353394,
      "learning_rate": 0.00010744352655436059,
      "loss": 1.3408,
      "step": 595
    },
    {
      "epoch": 2.6607538802660753,
      "grad_norm": 0.35892507433891296,
      "learning_rate": 0.00010589482773845727,
      "loss": 1.3268,
      "step": 600
    },
    {
      "epoch": 2.682926829268293,
      "grad_norm": 0.3559330105781555,
      "learning_rate": 0.00010434470874995781,
      "loss": 1.3102,
      "step": 605
    },
    {
      "epoch": 2.70509977827051,
      "grad_norm": 0.3716677725315094,
      "learning_rate": 0.00010279354304108271,
      "loss": 1.3015,
      "step": 610
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.3538273572921753,
      "learning_rate": 0.0001012417043162266,
      "loss": 1.3046,
      "step": 615
    },
    {
      "epoch": 2.7494456762749446,
      "grad_norm": 0.38784587383270264,
      "learning_rate": 9.968956644192617e-05,
      "loss": 1.3245,
      "step": 620
    },
    {
      "epoch": 2.7716186252771617,
      "grad_norm": 0.3511577248573303,
      "learning_rate": 9.813750335678866e-05,
      "loss": 1.3181,
      "step": 625
    },
    {
      "epoch": 2.7937915742793793,
      "grad_norm": 0.37702956795692444,
      "learning_rate": 9.658588898140322e-05,
      "loss": 1.3147,
      "step": 630
    },
    {
      "epoch": 2.8159645232815964,
      "grad_norm": 0.3686079680919647,
      "learning_rate": 9.503509712825658e-05,
      "loss": 1.311,
      "step": 635
    },
    {
      "epoch": 2.8381374722838135,
      "grad_norm": 0.3567045331001282,
      "learning_rate": 9.348550141167472e-05,
      "loss": 1.2965,
      "step": 640
    },
    {
      "epoch": 2.860310421286031,
      "grad_norm": 0.3552383780479431,
      "learning_rate": 9.193747515781224e-05,
      "loss": 1.3121,
      "step": 645
    },
    {
      "epoch": 2.882483370288248,
      "grad_norm": 0.3610834777355194,
      "learning_rate": 9.039139131471128e-05,
      "loss": 1.3136,
      "step": 650
    },
    {
      "epoch": 2.9046563192904657,
      "grad_norm": 0.36015474796295166,
      "learning_rate": 8.884762236245145e-05,
      "loss": 1.3131,
      "step": 655
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 0.3582945764064789,
      "learning_rate": 8.730654022341256e-05,
      "loss": 1.3237,
      "step": 660
    },
    {
      "epoch": 2.9490022172949004,
      "grad_norm": 0.34879669547080994,
      "learning_rate": 8.57685161726715e-05,
      "loss": 1.3295,
      "step": 665
    },
    {
      "epoch": 2.9711751662971175,
      "grad_norm": 0.3675631582736969,
      "learning_rate": 8.423392074855545e-05,
      "loss": 1.3066,
      "step": 670
    },
    {
      "epoch": 2.9933481152993346,
      "grad_norm": 0.34397903084754944,
      "learning_rate": 8.270312366337226e-05,
      "loss": 1.3154,
      "step": 675
    },
    {
      "epoch": 2.9977827050997785,
      "eval_loss": 1.7679176330566406,
      "eval_runtime": 0.3532,
      "eval_samples_per_second": 2.831,
      "eval_steps_per_second": 2.831,
      "step": 676
    },
    {
      "epoch": 3.015521064301552,
      "grad_norm": 0.38900941610336304,
      "learning_rate": 8.117649371433994e-05,
      "loss": 1.2977,
      "step": 680
    },
    {
      "epoch": 3.0376940133037693,
      "grad_norm": 0.3746815025806427,
      "learning_rate": 7.965439869473664e-05,
      "loss": 1.2848,
      "step": 685
    },
    {
      "epoch": 3.059866962305987,
      "grad_norm": 0.3739188313484192,
      "learning_rate": 7.813720530529243e-05,
      "loss": 1.29,
      "step": 690
    },
    {
      "epoch": 3.082039911308204,
      "grad_norm": 0.3820560574531555,
      "learning_rate": 7.66252790658445e-05,
      "loss": 1.2729,
      "step": 695
    },
    {
      "epoch": 3.104212860310421,
      "grad_norm": 0.41729655861854553,
      "learning_rate": 7.511898422727642e-05,
      "loss": 1.2701,
      "step": 700
    },
    {
      "epoch": 3.1263858093126387,
      "grad_norm": 0.3661589026451111,
      "learning_rate": 7.361868368376364e-05,
      "loss": 1.279,
      "step": 705
    },
    {
      "epoch": 3.1485587583148558,
      "grad_norm": 0.3968789875507355,
      "learning_rate": 7.212473888534546e-05,
      "loss": 1.2863,
      "step": 710
    },
    {
      "epoch": 3.1707317073170733,
      "grad_norm": 0.3675246238708496,
      "learning_rate": 7.063750975084518e-05,
      "loss": 1.2811,
      "step": 715
    },
    {
      "epoch": 3.1929046563192904,
      "grad_norm": 0.39409342408180237,
      "learning_rate": 6.915735458115884e-05,
      "loss": 1.2765,
      "step": 720
    },
    {
      "epoch": 3.2150776053215075,
      "grad_norm": 0.3648887574672699,
      "learning_rate": 6.768462997293413e-05,
      "loss": 1.2882,
      "step": 725
    },
    {
      "epoch": 3.237250554323725,
      "grad_norm": 0.3808637857437134,
      "learning_rate": 6.62196907326595e-05,
      "loss": 1.2973,
      "step": 730
    },
    {
      "epoch": 3.259423503325942,
      "grad_norm": 0.388408362865448,
      "learning_rate": 6.476288979118496e-05,
      "loss": 1.3099,
      "step": 735
    },
    {
      "epoch": 3.2815964523281598,
      "grad_norm": 0.3849842846393585,
      "learning_rate": 6.331457811869437e-05,
      "loss": 1.2919,
      "step": 740
    },
    {
      "epoch": 3.303769401330377,
      "grad_norm": 0.3851810693740845,
      "learning_rate": 6.187510464015022e-05,
      "loss": 1.2793,
      "step": 745
    },
    {
      "epoch": 3.3259423503325944,
      "grad_norm": 0.3811032474040985,
      "learning_rate": 6.0444816151231375e-05,
      "loss": 1.2803,
      "step": 750
    },
    {
      "epoch": 3.3481152993348116,
      "grad_norm": 0.36981481313705444,
      "learning_rate": 5.902405723478346e-05,
      "loss": 1.2612,
      "step": 755
    },
    {
      "epoch": 3.3702882483370287,
      "grad_norm": 0.37967202067375183,
      "learning_rate": 5.76131701778025e-05,
      "loss": 1.2924,
      "step": 760
    },
    {
      "epoch": 3.3924611973392462,
      "grad_norm": 0.39395394921302795,
      "learning_rate": 5.621249488897176e-05,
      "loss": 1.2714,
      "step": 765
    },
    {
      "epoch": 3.4146341463414633,
      "grad_norm": 0.38406023383140564,
      "learning_rate": 5.4822368816771406e-05,
      "loss": 1.2885,
      "step": 770
    },
    {
      "epoch": 3.436807095343681,
      "grad_norm": 0.372646301984787,
      "learning_rate": 5.344312686818106e-05,
      "loss": 1.2791,
      "step": 775
    },
    {
      "epoch": 3.458980044345898,
      "grad_norm": 0.3789440393447876,
      "learning_rate": 5.207510132799436e-05,
      "loss": 1.2918,
      "step": 780
    },
    {
      "epoch": 3.481152993348115,
      "grad_norm": 0.3723030388355255,
      "learning_rate": 5.0718621778765476e-05,
      "loss": 1.2772,
      "step": 785
    },
    {
      "epoch": 3.5033259423503327,
      "grad_norm": 0.373038649559021,
      "learning_rate": 4.9374015021406914e-05,
      "loss": 1.2677,
      "step": 790
    },
    {
      "epoch": 3.52549889135255,
      "grad_norm": 0.3948681354522705,
      "learning_rate": 4.804160499645667e-05,
      "loss": 1.2791,
      "step": 795
    },
    {
      "epoch": 3.5476718403547673,
      "grad_norm": 0.3771447241306305,
      "learning_rate": 4.6721712706035236e-05,
      "loss": 1.2895,
      "step": 800
    },
    {
      "epoch": 3.5698447893569845,
      "grad_norm": 0.37859615683555603,
      "learning_rate": 4.5414656136510334e-05,
      "loss": 1.2841,
      "step": 805
    },
    {
      "epoch": 3.5920177383592016,
      "grad_norm": 0.3813944160938263,
      "learning_rate": 4.412075018188805e-05,
      "loss": 1.2785,
      "step": 810
    },
    {
      "epoch": 3.614190687361419,
      "grad_norm": 0.37438470125198364,
      "learning_rate": 4.2840306567949076e-05,
      "loss": 1.2803,
      "step": 815
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.36801373958587646,
      "learning_rate": 4.157363377714819e-05,
      "loss": 1.3009,
      "step": 820
    },
    {
      "epoch": 3.658536585365854,
      "grad_norm": 0.37997427582740784,
      "learning_rate": 4.0321036974295156e-05,
      "loss": 1.2833,
      "step": 825
    },
    {
      "epoch": 3.680709534368071,
      "grad_norm": 0.36499011516571045,
      "learning_rate": 3.9082817933035134e-05,
      "loss": 1.2836,
      "step": 830
    },
    {
      "epoch": 3.7028824833702885,
      "grad_norm": 0.3749338984489441,
      "learning_rate": 3.785927496314543e-05,
      "loss": 1.2869,
      "step": 835
    },
    {
      "epoch": 3.7250554323725056,
      "grad_norm": 0.3751271665096283,
      "learning_rate": 3.6650702838667464e-05,
      "loss": 1.2732,
      "step": 840
    },
    {
      "epoch": 3.7472283813747227,
      "grad_norm": 0.3683511018753052,
      "learning_rate": 3.5457392726890236e-05,
      "loss": 1.2787,
      "step": 845
    },
    {
      "epoch": 3.7694013303769403,
      "grad_norm": 0.38828131556510925,
      "learning_rate": 3.427963211820274e-05,
      "loss": 1.2811,
      "step": 850
    },
    {
      "epoch": 3.7915742793791574,
      "grad_norm": 0.37317919731140137,
      "learning_rate": 3.3117704756832226e-05,
      "loss": 1.289,
      "step": 855
    },
    {
      "epoch": 3.8137472283813745,
      "grad_norm": 0.3718849718570709,
      "learning_rate": 3.197189057248491e-05,
      "loss": 1.2764,
      "step": 860
    },
    {
      "epoch": 3.835920177383592,
      "grad_norm": 0.3691292107105255,
      "learning_rate": 3.0842465612905837e-05,
      "loss": 1.2862,
      "step": 865
    },
    {
      "epoch": 3.858093126385809,
      "grad_norm": 0.3802024722099304,
      "learning_rate": 2.9729701977374035e-05,
      "loss": 1.2838,
      "step": 870
    },
    {
      "epoch": 3.8802660753880267,
      "grad_norm": 0.38017788529396057,
      "learning_rate": 2.863386775114848e-05,
      "loss": 1.2934,
      "step": 875
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 0.38141724467277527,
      "learning_rate": 2.7555226940881583e-05,
      "loss": 1.2829,
      "step": 880
    },
    {
      "epoch": 3.9246119733924614,
      "grad_norm": 0.38505685329437256,
      "learning_rate": 2.6494039411015193e-05,
      "loss": 1.3002,
      "step": 885
    },
    {
      "epoch": 3.9467849223946785,
      "grad_norm": 0.3752408027648926,
      "learning_rate": 2.545056082117433e-05,
      "loss": 1.2971,
      "step": 890
    },
    {
      "epoch": 3.9689578713968956,
      "grad_norm": 0.3711921274662018,
      "learning_rate": 2.4425042564574184e-05,
      "loss": 1.282,
      "step": 895
    },
    {
      "epoch": 3.991130820399113,
      "grad_norm": 0.37682175636291504,
      "learning_rate": 2.3417731707454737e-05,
      "loss": 1.268,
      "step": 900
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.796044945716858,
      "eval_runtime": 0.3372,
      "eval_samples_per_second": 2.965,
      "eval_steps_per_second": 2.965,
      "step": 902
    },
    {
      "epoch": 4.013303769401331,
      "grad_norm": 0.37139764428138733,
      "learning_rate": 2.242887092955801e-05,
      "loss": 1.2666,
      "step": 905
    },
    {
      "epoch": 4.035476718403547,
      "grad_norm": 0.3784310221672058,
      "learning_rate": 2.1458698465662187e-05,
      "loss": 1.2518,
      "step": 910
    },
    {
      "epoch": 4.057649667405765,
      "grad_norm": 0.3832833766937256,
      "learning_rate": 2.0507448048186208e-05,
      "loss": 1.2522,
      "step": 915
    },
    {
      "epoch": 4.0798226164079825,
      "grad_norm": 0.38216501474380493,
      "learning_rate": 1.957534885087944e-05,
      "loss": 1.2616,
      "step": 920
    },
    {
      "epoch": 4.101995565410199,
      "grad_norm": 0.37775281071662903,
      "learning_rate": 1.866262543360958e-05,
      "loss": 1.2696,
      "step": 925
    },
    {
      "epoch": 4.124168514412417,
      "grad_norm": 0.3922324478626251,
      "learning_rate": 1.7769497688261973e-05,
      "loss": 1.2572,
      "step": 930
    },
    {
      "epoch": 4.146341463414634,
      "grad_norm": 0.39753395318984985,
      "learning_rate": 1.6896180785763593e-05,
      "loss": 1.2574,
      "step": 935
    },
    {
      "epoch": 4.168514412416852,
      "grad_norm": 0.39192479848861694,
      "learning_rate": 1.604288512424439e-05,
      "loss": 1.2624,
      "step": 940
    },
    {
      "epoch": 4.1906873614190685,
      "grad_norm": 0.3945992588996887,
      "learning_rate": 1.520981627834851e-05,
      "loss": 1.2756,
      "step": 945
    },
    {
      "epoch": 4.212860310421286,
      "grad_norm": 0.37924352288246155,
      "learning_rate": 1.4397174949707725e-05,
      "loss": 1.257,
      "step": 950
    },
    {
      "epoch": 4.235033259423504,
      "grad_norm": 0.373811274766922,
      "learning_rate": 1.3605156918588469e-05,
      "loss": 1.2703,
      "step": 955
    },
    {
      "epoch": 4.25720620842572,
      "grad_norm": 0.3824734389781952,
      "learning_rate": 1.2833952996724863e-05,
      "loss": 1.2635,
      "step": 960
    },
    {
      "epoch": 4.279379157427938,
      "grad_norm": 0.3803390562534332,
      "learning_rate": 1.208374898134883e-05,
      "loss": 1.2715,
      "step": 965
    },
    {
      "epoch": 4.301552106430155,
      "grad_norm": 0.38187548518180847,
      "learning_rate": 1.1354725610427807e-05,
      "loss": 1.2775,
      "step": 970
    },
    {
      "epoch": 4.323725055432373,
      "grad_norm": 0.3768659234046936,
      "learning_rate": 1.0647058519121821e-05,
      "loss": 1.2394,
      "step": 975
    },
    {
      "epoch": 4.34589800443459,
      "grad_norm": 0.3807064890861511,
      "learning_rate": 9.960918197469771e-06,
      "loss": 1.2673,
      "step": 980
    },
    {
      "epoch": 4.368070953436807,
      "grad_norm": 0.38065963983535767,
      "learning_rate": 9.296469949315156e-06,
      "loss": 1.2713,
      "step": 985
    },
    {
      "epoch": 4.390243902439025,
      "grad_norm": 0.3850005865097046,
      "learning_rate": 8.653873852481364e-06,
      "loss": 1.2468,
      "step": 990
    },
    {
      "epoch": 4.412416851441241,
      "grad_norm": 0.3868677020072937,
      "learning_rate": 8.033284720205946e-06,
      "loss": 1.2654,
      "step": 995
    },
    {
      "epoch": 4.434589800443459,
      "grad_norm": 0.37283623218536377,
      "learning_rate": 7.434852063843278e-06,
      "loss": 1.2616,
      "step": 1000
    },
    {
      "epoch": 4.4567627494456765,
      "grad_norm": 0.3784988522529602,
      "learning_rate": 6.858720056844614e-06,
      "loss": 1.2602,
      "step": 1005
    },
    {
      "epoch": 4.478935698447893,
      "grad_norm": 0.389172226190567,
      "learning_rate": 6.3050275000238414e-06,
      "loss": 1.2671,
      "step": 1010
    },
    {
      "epoch": 4.501108647450111,
      "grad_norm": 0.37874796986579895,
      "learning_rate": 5.77390778811796e-06,
      "loss": 1.2743,
      "step": 1015
    },
    {
      "epoch": 4.523281596452328,
      "grad_norm": 0.39037781953811646,
      "learning_rate": 5.265488877649816e-06,
      "loss": 1.2684,
      "step": 1020
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.3832471966743469,
      "learning_rate": 4.7798932561009865e-06,
      "loss": 1.2674,
      "step": 1025
    },
    {
      "epoch": 4.5676274944567625,
      "grad_norm": 0.3740783631801605,
      "learning_rate": 4.317237912402316e-06,
      "loss": 1.2686,
      "step": 1030
    },
    {
      "epoch": 4.58980044345898,
      "grad_norm": 0.38245856761932373,
      "learning_rate": 3.877634308749078e-06,
      "loss": 1.2457,
      "step": 1035
    },
    {
      "epoch": 4.611973392461198,
      "grad_norm": 0.38514626026153564,
      "learning_rate": 3.461188353747702e-06,
      "loss": 1.2631,
      "step": 1040
    },
    {
      "epoch": 4.634146341463414,
      "grad_norm": 0.38133639097213745,
      "learning_rate": 3.068000376900515e-06,
      "loss": 1.2775,
      "step": 1045
    },
    {
      "epoch": 4.656319290465632,
      "grad_norm": 0.3845633268356323,
      "learning_rate": 2.6981651044344024e-06,
      "loss": 1.2642,
      "step": 1050
    },
    {
      "epoch": 4.678492239467849,
      "grad_norm": 0.38162142038345337,
      "learning_rate": 2.3517716364795385e-06,
      "loss": 1.2692,
      "step": 1055
    },
    {
      "epoch": 4.700665188470067,
      "grad_norm": 0.392133504152298,
      "learning_rate": 2.028903425603612e-06,
      "loss": 1.2628,
      "step": 1060
    },
    {
      "epoch": 4.722838137472284,
      "grad_norm": 0.374054878950119,
      "learning_rate": 1.7296382567064672e-06,
      "loss": 1.2611,
      "step": 1065
    },
    {
      "epoch": 4.745011086474501,
      "grad_norm": 0.38326382637023926,
      "learning_rate": 1.4540482282803137e-06,
      "loss": 1.2453,
      "step": 1070
    },
    {
      "epoch": 4.767184035476719,
      "grad_norm": 0.39525189995765686,
      "learning_rate": 1.2021997350399106e-06,
      "loss": 1.2849,
      "step": 1075
    },
    {
      "epoch": 4.789356984478935,
      "grad_norm": 0.38262608647346497,
      "learning_rate": 9.741534519267736e-07,
      "loss": 1.2696,
      "step": 1080
    },
    {
      "epoch": 4.811529933481153,
      "grad_norm": 0.38532087206840515,
      "learning_rate": 7.699643194915784e-07,
      "loss": 1.26,
      "step": 1085
    },
    {
      "epoch": 4.8337028824833705,
      "grad_norm": 0.3865302503108978,
      "learning_rate": 5.896815306578818e-07,
      "loss": 1.2568,
      "step": 1090
    },
    {
      "epoch": 4.855875831485587,
      "grad_norm": 0.3837885856628418,
      "learning_rate": 4.333485188706576e-07,
      "loss": 1.2644,
      "step": 1095
    },
    {
      "epoch": 4.878048780487805,
      "grad_norm": 0.37372496724128723,
      "learning_rate": 3.0100294763238946e-07,
      "loss": 1.2764,
      "step": 1100
    },
    {
      "epoch": 4.900221729490022,
      "grad_norm": 0.38477322459220886,
      "learning_rate": 1.9267670142926187e-07,
      "loss": 1.2529,
      "step": 1105
    },
    {
      "epoch": 4.922394678492239,
      "grad_norm": 0.3782412111759186,
      "learning_rate": 1.0839587804954975e-07,
      "loss": 1.2552,
      "step": 1110
    },
    {
      "epoch": 4.9445676274944566,
      "grad_norm": 0.3779396116733551,
      "learning_rate": 4.818078229622547e-08,
      "loss": 1.2773,
      "step": 1115
    },
    {
      "epoch": 4.966740576496674,
      "grad_norm": 0.38919439911842346,
      "learning_rate": 1.2045921095127366e-08,
      "loss": 1.2647,
      "step": 1120
    },
    {
      "epoch": 4.988913525498892,
      "grad_norm": 0.38752755522727966,
      "learning_rate": 0.0,
      "loss": 1.2695,
      "step": 1125
    },
    {
      "epoch": 4.988913525498892,
      "eval_loss": 1.8087279796600342,
      "eval_runtime": 0.3391,
      "eval_samples_per_second": 2.949,
      "eval_steps_per_second": 2.949,
      "step": 1125
    },
    {
      "epoch": 4.988913525498892,
      "step": 1125,
      "total_flos": 1.6629843858229821e+18,
      "train_loss": 1.390608725865682,
      "train_runtime": 3610.9267,
      "train_samples_per_second": 9.977,
      "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
}