{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0012771392081736,
  "eval_steps": 500,
  "global_step": 196,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005108556832694764,
      "grad_norm": 0.06296706199645996,
      "learning_rate": 0.00019998715457999314,
      "loss": 10.3788,
      "step": 1
    },
    {
      "epoch": 0.010217113665389528,
      "grad_norm": 0.06155822426080704,
      "learning_rate": 0.0001999486216200688,
      "loss": 10.3876,
      "step": 2
    },
    {
      "epoch": 0.01532567049808429,
      "grad_norm": 0.04243969917297363,
      "learning_rate": 0.0001998844110196681,
      "loss": 10.383,
      "step": 3
    },
    {
      "epoch": 0.020434227330779056,
      "grad_norm": 0.08324499428272247,
      "learning_rate": 0.00019979453927503364,
      "loss": 10.3854,
      "step": 4
    },
    {
      "epoch": 0.02554278416347382,
      "grad_norm": 0.06429007649421692,
      "learning_rate": 0.00019967902947497156,
      "loss": 10.3783,
      "step": 5
    },
    {
      "epoch": 0.03065134099616858,
      "grad_norm": 0.06722702831029892,
      "learning_rate": 0.00019953791129491983,
      "loss": 10.3771,
      "step": 6
    },
    {
      "epoch": 0.035759897828863345,
      "grad_norm": 0.04376779869198799,
      "learning_rate": 0.00019937122098932428,
      "loss": 10.3768,
      "step": 7
    },
    {
      "epoch": 0.04086845466155811,
      "grad_norm": 0.057710230350494385,
      "learning_rate": 0.0001991790013823246,
      "loss": 10.3731,
      "step": 8
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 0.06998121738433838,
      "learning_rate": 0.00019896130185675261,
      "loss": 10.3783,
      "step": 9
    },
    {
      "epoch": 0.05108556832694764,
      "grad_norm": 0.06011413037776947,
      "learning_rate": 0.00019871817834144504,
      "loss": 10.3773,
      "step": 10
    },
    {
      "epoch": 0.0561941251596424,
      "grad_norm": 0.05903960019350052,
      "learning_rate": 0.00019844969329687527,
      "loss": 10.379,
      "step": 11
    },
    {
      "epoch": 0.06130268199233716,
      "grad_norm": 0.06023373827338219,
      "learning_rate": 0.00019815591569910654,
      "loss": 10.3718,
      "step": 12
    },
    {
      "epoch": 0.06641123882503193,
      "grad_norm": 0.07594680041074753,
      "learning_rate": 0.00019783692102207155,
      "loss": 10.3802,
      "step": 13
    },
    {
      "epoch": 0.07151979565772669,
      "grad_norm": 0.07722143083810806,
      "learning_rate": 0.00019749279121818235,
      "loss": 10.3835,
      "step": 14
    },
    {
      "epoch": 0.07662835249042145,
      "grad_norm": 0.06465964019298553,
      "learning_rate": 0.0001971236146972764,
      "loss": 10.3811,
      "step": 15
    },
    {
      "epoch": 0.08173690932311622,
      "grad_norm": 0.08145278692245483,
      "learning_rate": 0.00019672948630390294,
      "loss": 10.3771,
      "step": 16
    },
    {
      "epoch": 0.08684546615581099,
      "grad_norm": 0.06017107516527176,
      "learning_rate": 0.00019631050729295707,
      "loss": 10.3816,
      "step": 17
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 0.07251092046499252,
      "learning_rate": 0.00019586678530366606,
      "loss": 10.3833,
      "step": 18
    },
    {
      "epoch": 0.0970625798212005,
      "grad_norm": 0.04419001191854477,
      "learning_rate": 0.00019539843433193639,
      "loss": 10.3781,
      "step": 19
    },
    {
      "epoch": 0.10217113665389528,
      "grad_norm": 0.0600612536072731,
      "learning_rate": 0.00019490557470106686,
      "loss": 10.3828,
      "step": 20
    },
    {
      "epoch": 0.10727969348659004,
      "grad_norm": 0.07362791895866394,
      "learning_rate": 0.00019438833303083678,
      "loss": 10.3844,
      "step": 21
    },
    {
      "epoch": 0.1123882503192848,
      "grad_norm": 0.06240883469581604,
      "learning_rate": 0.00019384684220497605,
      "loss": 10.3754,
      "step": 22
    },
    {
      "epoch": 0.11749680715197956,
      "grad_norm": 0.06827075779438019,
      "learning_rate": 0.0001932812413370265,
      "loss": 10.3727,
      "step": 23
    },
    {
      "epoch": 0.12260536398467432,
      "grad_norm": 0.06609390676021576,
      "learning_rate": 0.0001926916757346022,
      "loss": 10.3814,
      "step": 24
    },
    {
      "epoch": 0.1277139208173691,
      "grad_norm": 0.06842462718486786,
      "learning_rate": 0.00019207829686205882,
      "loss": 10.3716,
      "step": 25
    },
    {
      "epoch": 0.13282247765006386,
      "grad_norm": 0.06660367548465729,
      "learning_rate": 0.00019144126230158127,
      "loss": 10.3826,
      "step": 26
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 0.08344798535108566,
      "learning_rate": 0.00019078073571269922,
      "loss": 10.3783,
      "step": 27
    },
    {
      "epoch": 0.14303959131545338,
      "grad_norm": 0.08380083739757538,
      "learning_rate": 0.0001900968867902419,
      "loss": 10.3732,
      "step": 28
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.0946107804775238,
      "learning_rate": 0.00018938989122074197,
      "loss": 10.37,
      "step": 29
    },
    {
      "epoch": 0.1532567049808429,
      "grad_norm": 0.06197074055671692,
      "learning_rate": 0.00018865993063730004,
      "loss": 10.3761,
      "step": 30
    },
    {
      "epoch": 0.1583652618135377,
      "grad_norm": 0.0819283053278923,
      "learning_rate": 0.00018790719257292174,
      "loss": 10.371,
      "step": 31
    },
    {
      "epoch": 0.16347381864623245,
      "grad_norm": 0.09213186800479889,
      "learning_rate": 0.00018713187041233896,
      "loss": 10.3725,
      "step": 32
    },
    {
      "epoch": 0.1685823754789272,
      "grad_norm": 0.08193743228912354,
      "learning_rate": 0.00018633416334232753,
      "loss": 10.3725,
      "step": 33
    },
    {
      "epoch": 0.17369093231162197,
      "grad_norm": 0.07233049720525742,
      "learning_rate": 0.00018551427630053463,
      "loss": 10.374,
      "step": 34
    },
    {
      "epoch": 0.17879948914431673,
      "grad_norm": 0.09028832614421844,
      "learning_rate": 0.00018467241992282843,
      "loss": 10.3732,
      "step": 35
    },
    {
      "epoch": 0.1839080459770115,
      "grad_norm": 0.10519926995038986,
      "learning_rate": 0.00018380881048918405,
      "loss": 10.3769,
      "step": 36
    },
    {
      "epoch": 0.18901660280970625,
      "grad_norm": 0.06255685538053513,
      "learning_rate": 0.0001829236698681195,
      "loss": 10.378,
      "step": 37
    },
    {
      "epoch": 0.194125159642401,
      "grad_norm": 0.08233755081892014,
      "learning_rate": 0.0001820172254596956,
      "loss": 10.3704,
      "step": 38
    },
    {
      "epoch": 0.19923371647509577,
      "grad_norm": 0.05263242870569229,
      "learning_rate": 0.0001810897101370951,
      "loss": 10.3834,
      "step": 39
    },
    {
      "epoch": 0.20434227330779056,
      "grad_norm": 0.1387779265642166,
      "learning_rate": 0.00018014136218679567,
      "loss": 10.3707,
      "step": 40
    },
    {
      "epoch": 0.20945083014048532,
      "grad_norm": 0.08574540168046951,
      "learning_rate": 0.000179172425247352,
      "loss": 10.377,
      "step": 41
    },
    {
      "epoch": 0.21455938697318008,
      "grad_norm": 0.06211940944194794,
      "learning_rate": 0.000178183148246803,
      "loss": 10.3647,
      "step": 42
    },
    {
      "epoch": 0.21966794380587484,
      "grad_norm": 0.09258867800235748,
      "learning_rate": 0.00017717378533872017,
      "loss": 10.3722,
      "step": 43
    },
    {
      "epoch": 0.2247765006385696,
      "grad_norm": 0.08623415976762772,
      "learning_rate": 0.00017614459583691346,
      "loss": 10.3754,
      "step": 44
    },
    {
      "epoch": 0.22988505747126436,
      "grad_norm": 0.1082397997379303,
      "learning_rate": 0.00017509584414881113,
      "loss": 10.3736,
      "step": 45
    },
    {
      "epoch": 0.23499361430395913,
      "grad_norm": 0.0896887555718422,
      "learning_rate": 0.00017402779970753155,
      "loss": 10.3732,
      "step": 46
    },
    {
      "epoch": 0.24010217113665389,
      "grad_norm": 0.09336112439632416,
      "learning_rate": 0.00017294073690266344,
      "loss": 10.373,
      "step": 47
    },
    {
      "epoch": 0.24521072796934865,
      "grad_norm": 0.08002498000860214,
      "learning_rate": 0.00017183493500977278,
      "loss": 10.3689,
      "step": 48
    },
    {
      "epoch": 0.2503192848020434,
      "grad_norm": 0.07161203771829605,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.3702,
      "step": 49
    },
    {
      "epoch": 0.2554278416347382,
      "grad_norm": 0.121755450963974,
      "learning_rate": 0.00016956825506034867,
      "loss": 10.3821,
      "step": 50
    },
    {
      "epoch": 0.26053639846743293,
      "grad_norm": 0.08657146245241165,
      "learning_rate": 0.00016840795933293463,
      "loss": 10.3803,
      "step": 51
    },
    {
      "epoch": 0.2656449553001277,
      "grad_norm": 0.07844258099794388,
      "learning_rate": 0.0001672300890261317,
      "loss": 10.3719,
      "step": 52
    },
    {
      "epoch": 0.2707535121328225,
      "grad_norm": 0.08680905401706696,
      "learning_rate": 0.00016603494674471593,
      "loss": 10.3649,
      "step": 53
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.10259506851434708,
      "learning_rate": 0.00016482283953077887,
      "loss": 10.3725,
      "step": 54
    },
    {
      "epoch": 0.280970625798212,
      "grad_norm": 0.08116184920072556,
      "learning_rate": 0.00016359407878484552,
      "loss": 10.3681,
      "step": 55
    },
    {
      "epoch": 0.28607918263090676,
      "grad_norm": 0.06668803840875626,
      "learning_rate": 0.00016234898018587337,
      "loss": 10.3731,
      "step": 56
    },
    {
      "epoch": 0.29118773946360155,
      "grad_norm": 0.08566579967737198,
      "learning_rate": 0.00016108786361015143,
      "loss": 10.37,
      "step": 57
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.11228417605161667,
      "learning_rate": 0.00015981105304912162,
      "loss": 10.3716,
      "step": 58
    },
    {
      "epoch": 0.30140485312899107,
      "grad_norm": 0.07987914979457855,
      "learning_rate": 0.00015851887652614237,
      "loss": 10.3712,
      "step": 59
    },
    {
      "epoch": 0.3065134099616858,
      "grad_norm": 0.1201016902923584,
      "learning_rate": 0.00015721166601221698,
      "loss": 10.3647,
      "step": 60
    },
    {
      "epoch": 0.3116219667943806,
      "grad_norm": 0.08329416066408157,
      "learning_rate": 0.00015588975734070717,
      "loss": 10.3792,
      "step": 61
    },
    {
      "epoch": 0.3167305236270754,
      "grad_norm": 0.10588457435369492,
      "learning_rate": 0.00015455349012105486,
      "loss": 10.3688,
      "step": 62
    },
    {
      "epoch": 0.3218390804597701,
      "grad_norm": 0.12081307172775269,
      "learning_rate": 0.00015320320765153367,
      "loss": 10.3642,
      "step": 63
    },
    {
      "epoch": 0.3269476372924649,
      "grad_norm": 0.08195498585700989,
      "learning_rate": 0.00015183925683105254,
      "loss": 10.3682,
      "step": 64
    },
    {
      "epoch": 0.33205619412515963,
      "grad_norm": 0.06908663362264633,
      "learning_rate": 0.0001504619880700346,
      "loss": 10.367,
      "step": 65
    },
    {
      "epoch": 0.3371647509578544,
      "grad_norm": 0.09832872450351715,
      "learning_rate": 0.0001490717552003938,
      "loss": 10.377,
      "step": 66
    },
    {
      "epoch": 0.34227330779054915,
      "grad_norm": 0.0903470367193222,
      "learning_rate": 0.00014766891538463254,
      "loss": 10.3772,
      "step": 67
    },
    {
      "epoch": 0.34738186462324394,
      "grad_norm": 0.09079986065626144,
      "learning_rate": 0.00014625382902408356,
      "loss": 10.366,
      "step": 68
    },
    {
      "epoch": 0.3524904214559387,
      "grad_norm": 0.05147509649395943,
      "learning_rate": 0.0001448268596663197,
      "loss": 10.3652,
      "step": 69
    },
    {
      "epoch": 0.35759897828863346,
      "grad_norm": 0.14060315489768982,
      "learning_rate": 0.00014338837391175582,
      "loss": 10.3629,
      "step": 70
    },
    {
      "epoch": 0.36270753512132825,
      "grad_norm": 0.11259511113166809,
      "learning_rate": 0.0001419387413194657,
      "loss": 10.3691,
      "step": 71
    },
    {
      "epoch": 0.367816091954023,
      "grad_norm": 0.09399597346782684,
      "learning_rate": 0.00014047833431223938,
      "loss": 10.3617,
      "step": 72
    },
    {
      "epoch": 0.37292464878671777,
      "grad_norm": 0.11537044495344162,
      "learning_rate": 0.00013900752808090468,
      "loss": 10.366,
      "step": 73
    },
    {
      "epoch": 0.3780332056194125,
      "grad_norm": 0.11738992482423782,
      "learning_rate": 0.00013752670048793744,
      "loss": 10.3471,
      "step": 74
    },
    {
      "epoch": 0.3831417624521073,
      "grad_norm": 0.11229626834392548,
      "learning_rate": 0.00013603623197038536,
      "loss": 10.3645,
      "step": 75
    },
    {
      "epoch": 0.388250319284802,
      "grad_norm": 0.14596045017242432,
      "learning_rate": 0.00013453650544213076,
      "loss": 10.3751,
      "step": 76
    },
    {
      "epoch": 0.3933588761174968,
      "grad_norm": 0.06448373198509216,
      "learning_rate": 0.00013302790619551674,
      "loss": 10.3572,
      "step": 77
    },
    {
      "epoch": 0.39846743295019155,
      "grad_norm": 0.11809150874614716,
      "learning_rate": 0.0001315108218023621,
      "loss": 10.3695,
      "step": 78
    },
    {
      "epoch": 0.40357598978288634,
      "grad_norm": 0.08517828583717346,
      "learning_rate": 0.00012998564201439116,
      "loss": 10.3629,
      "step": 79
    },
    {
      "epoch": 0.4086845466155811,
      "grad_norm": 0.12408934533596039,
      "learning_rate": 0.00012845275866310324,
      "loss": 10.3607,
      "step": 80
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.12312637269496918,
      "learning_rate": 0.00012691256555910768,
      "loss": 10.3654,
      "step": 81
    },
    {
      "epoch": 0.41890166028097064,
      "grad_norm": 0.12126640975475311,
      "learning_rate": 0.00012536545839095074,
      "loss": 10.3617,
      "step": 82
    },
    {
      "epoch": 0.4240102171136654,
      "grad_norm": 0.15894931554794312,
      "learning_rate": 0.00012381183462345982,
      "loss": 10.3564,
      "step": 83
    },
    {
      "epoch": 0.42911877394636017,
      "grad_norm": 0.07874782383441925,
      "learning_rate": 0.00012225209339563145,
      "loss": 10.3653,
      "step": 84
    },
    {
      "epoch": 0.4342273307790549,
      "grad_norm": 0.12640683352947235,
      "learning_rate": 0.00012068663541808909,
      "loss": 10.3631,
      "step": 85
    },
    {
      "epoch": 0.4393358876117497,
      "grad_norm": 0.10024367272853851,
      "learning_rate": 0.00011911586287013725,
      "loss": 10.3672,
      "step": 86
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.12512411177158356,
      "learning_rate": 0.00011754017929643817,
      "loss": 10.3611,
      "step": 87
    },
    {
      "epoch": 0.4495530012771392,
      "grad_norm": 0.1329926997423172,
      "learning_rate": 0.00011595998950333793,
      "loss": 10.3591,
      "step": 88
    },
    {
      "epoch": 0.454661558109834,
      "grad_norm": 0.11963527649641037,
      "learning_rate": 0.00011437569945486819,
      "loss": 10.365,
      "step": 89
    },
    {
      "epoch": 0.45977011494252873,
      "grad_norm": 0.11451319605112076,
      "learning_rate": 0.00011278771616845061,
      "loss": 10.3549,
      "step": 90
    },
    {
      "epoch": 0.4648786717752235,
      "grad_norm": 0.09816919267177582,
      "learning_rate": 0.00011119644761033078,
      "loss": 10.3577,
      "step": 91
    },
    {
      "epoch": 0.46998722860791825,
      "grad_norm": 0.15458016097545624,
      "learning_rate": 0.00010960230259076818,
      "loss": 10.3668,
      "step": 92
    },
    {
      "epoch": 0.47509578544061304,
      "grad_norm": 0.1010480597615242,
      "learning_rate": 0.00010800569065900933,
      "loss": 10.3592,
      "step": 93
    },
    {
      "epoch": 0.48020434227330777,
      "grad_norm": 0.11193486303091049,
      "learning_rate": 0.0001064070219980713,
      "loss": 10.3568,
      "step": 94
    },
    {
      "epoch": 0.48531289910600256,
      "grad_norm": 0.10354366153478622,
      "learning_rate": 0.00010480670731936208,
      "loss": 10.3509,
      "step": 95
    },
    {
      "epoch": 0.4904214559386973,
      "grad_norm": 0.15040072798728943,
      "learning_rate": 0.00010320515775716555,
      "loss": 10.3566,
      "step": 96
    },
    {
      "epoch": 0.4955300127713921,
      "grad_norm": 0.10507191717624664,
      "learning_rate": 0.0001016027847630174,
      "loss": 10.3547,
      "step": 97
    },
    {
      "epoch": 0.5006385696040868,
      "grad_norm": 0.11989340931177139,
      "learning_rate": 0.0001,
      "loss": 10.3656,
      "step": 98
    },
    {
      "epoch": 0.5057471264367817,
      "grad_norm": 0.12597250938415527,
      "learning_rate": 9.839721523698264e-05,
      "loss": 10.3657,
      "step": 99
    },
    {
      "epoch": 0.5108556832694764,
      "grad_norm": 0.16077381372451782,
      "learning_rate": 9.679484224283449e-05,
      "loss": 10.3527,
      "step": 100
    },
    {
      "epoch": 0.5159642401021711,
      "grad_norm": 0.12048140168190002,
      "learning_rate": 9.519329268063795e-05,
      "loss": 10.3627,
      "step": 101
    },
    {
      "epoch": 0.5210727969348659,
      "grad_norm": 0.10793527215719223,
      "learning_rate": 9.359297800192872e-05,
      "loss": 10.3508,
      "step": 102
    },
    {
      "epoch": 0.5261813537675607,
      "grad_norm": 0.070986308157444,
      "learning_rate": 9.199430934099068e-05,
      "loss": 10.3545,
      "step": 103
    },
    {
      "epoch": 0.5312899106002554,
      "grad_norm": 0.08290573209524155,
      "learning_rate": 9.039769740923183e-05,
      "loss": 10.3568,
      "step": 104
    },
    {
      "epoch": 0.5363984674329502,
      "grad_norm": 0.09891117364168167,
      "learning_rate": 8.880355238966923e-05,
      "loss": 10.3572,
      "step": 105
    },
    {
      "epoch": 0.541507024265645,
      "grad_norm": 0.10156704485416412,
      "learning_rate": 8.721228383154939e-05,
      "loss": 10.3588,
      "step": 106
    },
    {
      "epoch": 0.5466155810983397,
      "grad_norm": 0.10102825611829758,
      "learning_rate": 8.562430054513184e-05,
      "loss": 10.3583,
      "step": 107
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.10080267488956451,
      "learning_rate": 8.404001049666211e-05,
      "loss": 10.365,
      "step": 108
    },
    {
      "epoch": 0.5568326947637292,
      "grad_norm": 0.08475471287965775,
      "learning_rate": 8.245982070356185e-05,
      "loss": 10.3606,
      "step": 109
    },
    {
      "epoch": 0.561941251596424,
      "grad_norm": 0.13166114687919617,
      "learning_rate": 8.08841371298628e-05,
      "loss": 10.3538,
      "step": 110
    },
    {
      "epoch": 0.5670498084291188,
      "grad_norm": 0.1031697690486908,
      "learning_rate": 7.931336458191092e-05,
      "loss": 10.3672,
      "step": 111
    },
    {
      "epoch": 0.5721583652618135,
      "grad_norm": 0.08675719797611237,
      "learning_rate": 7.774790660436858e-05,
      "loss": 10.3575,
      "step": 112
    },
    {
      "epoch": 0.5772669220945083,
      "grad_norm": 0.10204310715198517,
      "learning_rate": 7.618816537654018e-05,
      "loss": 10.3607,
      "step": 113
    },
    {
      "epoch": 0.5823754789272031,
      "grad_norm": 0.12430866807699203,
      "learning_rate": 7.463454160904928e-05,
      "loss": 10.3586,
      "step": 114
    },
    {
      "epoch": 0.5874840357598978,
      "grad_norm": 0.09749015420675278,
      "learning_rate": 7.308743444089232e-05,
      "loss": 10.3493,
      "step": 115
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.11196263879537582,
      "learning_rate": 7.154724133689677e-05,
      "loss": 10.3479,
      "step": 116
    },
    {
      "epoch": 0.5977011494252874,
      "grad_norm": 0.1198868602514267,
      "learning_rate": 7.001435798560883e-05,
      "loss": 10.349,
      "step": 117
    },
    {
      "epoch": 0.6028097062579821,
      "grad_norm": 0.10104350000619888,
      "learning_rate": 6.848917819763793e-05,
      "loss": 10.353,
      "step": 118
    },
    {
      "epoch": 0.6079182630906769,
      "grad_norm": 0.09838002175092697,
      "learning_rate": 6.697209380448333e-05,
      "loss": 10.3552,
      "step": 119
    },
    {
      "epoch": 0.6130268199233716,
      "grad_norm": 0.12079446762800217,
      "learning_rate": 6.546349455786926e-05,
      "loss": 10.3541,
      "step": 120
    },
    {
      "epoch": 0.6181353767560664,
      "grad_norm": 0.07775072753429413,
      "learning_rate": 6.396376802961468e-05,
      "loss": 10.3623,
      "step": 121
    },
    {
      "epoch": 0.6232439335887612,
      "grad_norm": 0.10357434302568436,
      "learning_rate": 6.24732995120626e-05,
      "loss": 10.3578,
      "step": 122
    },
    {
      "epoch": 0.6283524904214559,
      "grad_norm": 0.11605259031057358,
      "learning_rate": 6.0992471919095315e-05,
      "loss": 10.3513,
      "step": 123
    },
    {
      "epoch": 0.6334610472541508,
      "grad_norm": 0.0947057381272316,
      "learning_rate": 5.952166568776062e-05,
      "loss": 10.3484,
      "step": 124
    },
    {
      "epoch": 0.6385696040868455,
      "grad_norm": 0.09507757425308228,
      "learning_rate": 5.806125868053433e-05,
      "loss": 10.3521,
      "step": 125
    },
    {
      "epoch": 0.6436781609195402,
      "grad_norm": 0.09619959443807602,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 10.3583,
      "step": 126
    },
    {
      "epoch": 0.648786717752235,
      "grad_norm": 0.0792725682258606,
      "learning_rate": 5.5173140333680306e-05,
      "loss": 10.354,
      "step": 127
    },
    {
      "epoch": 0.6538952745849298,
      "grad_norm": 0.105789415538311,
      "learning_rate": 5.37461709759165e-05,
      "loss": 10.3583,
      "step": 128
    },
    {
      "epoch": 0.6590038314176245,
      "grad_norm": 0.10440662503242493,
      "learning_rate": 5.2331084615367485e-05,
      "loss": 10.3523,
      "step": 129
    },
    {
      "epoch": 0.6641123882503193,
      "grad_norm": 0.10326969623565674,
      "learning_rate": 5.092824479960625e-05,
      "loss": 10.3574,
      "step": 130
    },
    {
      "epoch": 0.669220945083014,
      "grad_norm": 0.08976173400878906,
      "learning_rate": 4.953801192996543e-05,
      "loss": 10.3548,
      "step": 131
    },
    {
      "epoch": 0.6743295019157088,
      "grad_norm": 0.09830819070339203,
      "learning_rate": 4.8160743168947496e-05,
      "loss": 10.3497,
      "step": 132
    },
    {
      "epoch": 0.6794380587484036,
      "grad_norm": 0.12448275089263916,
      "learning_rate": 4.6796792348466356e-05,
      "loss": 10.3661,
      "step": 133
    },
    {
      "epoch": 0.6845466155810983,
      "grad_norm": 0.1166510358452797,
      "learning_rate": 4.544650987894514e-05,
      "loss": 10.3572,
      "step": 134
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.11028123646974564,
      "learning_rate": 4.4110242659292836e-05,
      "loss": 10.3607,
      "step": 135
    },
    {
      "epoch": 0.6947637292464879,
      "grad_norm": 0.14801649749279022,
      "learning_rate": 4.278833398778306e-05,
      "loss": 10.3544,
      "step": 136
    },
    {
      "epoch": 0.6998722860791826,
      "grad_norm": 0.10162738710641861,
      "learning_rate": 4.148112347385762e-05,
      "loss": 10.3514,
      "step": 137
    },
    {
      "epoch": 0.7049808429118773,
      "grad_norm": 0.08851826190948486,
      "learning_rate": 4.0188946950878404e-05,
      "loss": 10.3545,
      "step": 138
    },
    {
      "epoch": 0.7100893997445722,
      "grad_norm": 0.0674971416592598,
      "learning_rate": 3.8912136389848576e-05,
      "loss": 10.3527,
      "step": 139
    },
    {
      "epoch": 0.7151979565772669,
      "grad_norm": 0.07837618142366409,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 10.3495,
      "step": 140
    },
    {
      "epoch": 0.7203065134099617,
      "grad_norm": 0.13337913155555725,
      "learning_rate": 3.6405921215154494e-05,
      "loss": 10.3601,
      "step": 141
    },
    {
      "epoch": 0.7254150702426565,
      "grad_norm": 0.1068163514137268,
      "learning_rate": 3.517716046922118e-05,
      "loss": 10.3553,
      "step": 142
    },
    {
      "epoch": 0.7305236270753512,
      "grad_norm": 0.09636684507131577,
      "learning_rate": 3.3965053255284084e-05,
      "loss": 10.3609,
      "step": 143
    },
    {
      "epoch": 0.735632183908046,
      "grad_norm": 0.10259624570608139,
      "learning_rate": 3.276991097386831e-05,
      "loss": 10.3514,
      "step": 144
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.08181837946176529,
      "learning_rate": 3.159204066706539e-05,
      "loss": 10.3508,
      "step": 145
    },
    {
      "epoch": 0.7458492975734355,
      "grad_norm": 0.10370145738124847,
      "learning_rate": 3.0431744939651364e-05,
      "loss": 10.3518,
      "step": 146
    },
    {
      "epoch": 0.7509578544061303,
      "grad_norm": 0.11586267501115799,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 10.3494,
      "step": 147
    },
    {
      "epoch": 0.756066411238825,
      "grad_norm": 0.07326210290193558,
      "learning_rate": 2.8165064990227252e-05,
      "loss": 10.3618,
      "step": 148
    },
    {
      "epoch": 0.7611749680715197,
      "grad_norm": 0.07508935779333115,
      "learning_rate": 2.7059263097336597e-05,
      "loss": 10.354,
      "step": 149
    },
    {
      "epoch": 0.7662835249042146,
      "grad_norm": 0.09258796274662018,
      "learning_rate": 2.5972200292468464e-05,
      "loss": 10.3528,
      "step": 150
    },
    {
      "epoch": 0.7713920817369093,
      "grad_norm": 0.09141936898231506,
      "learning_rate": 2.4904155851188872e-05,
      "loss": 10.3475,
      "step": 151
    },
    {
      "epoch": 0.776500638569604,
      "grad_norm": 0.06457791477441788,
      "learning_rate": 2.3855404163086558e-05,
      "loss": 10.3594,
      "step": 152
    },
    {
      "epoch": 0.7816091954022989,
      "grad_norm": 0.0867636650800705,
      "learning_rate": 2.282621466127982e-05,
      "loss": 10.357,
      "step": 153
    },
    {
      "epoch": 0.7867177522349936,
      "grad_norm": 0.07386265695095062,
      "learning_rate": 2.181685175319702e-05,
      "loss": 10.3601,
      "step": 154
    },
    {
      "epoch": 0.7918263090676884,
      "grad_norm": 0.09301372617483139,
      "learning_rate": 2.0827574752648038e-05,
      "loss": 10.3521,
      "step": 155
    },
    {
      "epoch": 0.7969348659003831,
      "grad_norm": 0.09825734794139862,
      "learning_rate": 1.985863781320435e-05,
      "loss": 10.3518,
      "step": 156
    },
    {
      "epoch": 0.8020434227330779,
      "grad_norm": 0.09146848320960999,
      "learning_rate": 1.891028986290492e-05,
      "loss": 10.3543,
      "step": 157
    },
    {
      "epoch": 0.8071519795657727,
      "grad_norm": 0.10811572521924973,
      "learning_rate": 1.7982774540304403e-05,
      "loss": 10.3486,
      "step": 158
    },
    {
      "epoch": 0.8122605363984674,
      "grad_norm": 0.10702500492334366,
      "learning_rate": 1.7076330131880526e-05,
      "loss": 10.3506,
      "step": 159
    },
    {
      "epoch": 0.8173690932311622,
      "grad_norm": 0.09714721143245697,
      "learning_rate": 1.619118951081594e-05,
      "loss": 10.3542,
      "step": 160
    },
    {
      "epoch": 0.822477650063857,
      "grad_norm": 0.09883596003055573,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 10.355,
      "step": 161
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.07649561762809753,
      "learning_rate": 1.4485723699465392e-05,
      "loss": 10.3488,
      "step": 162
    },
    {
      "epoch": 0.8326947637292464,
      "grad_norm": 0.0714419037103653,
      "learning_rate": 1.3665836657672493e-05,
      "loss": 10.3463,
      "step": 163
    },
    {
      "epoch": 0.8378033205619413,
      "grad_norm": 0.09287029504776001,
      "learning_rate": 1.286812958766106e-05,
      "loss": 10.3506,
      "step": 164
    },
    {
      "epoch": 0.842911877394636,
      "grad_norm": 0.0882708728313446,
      "learning_rate": 1.2092807427078279e-05,
      "loss": 10.3538,
      "step": 165
    },
    {
      "epoch": 0.8480204342273308,
      "grad_norm": 0.0939875915646553,
      "learning_rate": 1.134006936269999e-05,
      "loss": 10.3498,
      "step": 166
    },
    {
      "epoch": 0.8531289910600255,
      "grad_norm": 0.10232677310705185,
      "learning_rate": 1.0610108779258044e-05,
      "loss": 10.3573,
      "step": 167
    },
    {
      "epoch": 0.8582375478927203,
      "grad_norm": 0.09528540074825287,
      "learning_rate": 9.903113209758096e-06,
      "loss": 10.3558,
      "step": 168
    },
    {
      "epoch": 0.8633461047254151,
      "grad_norm": 0.08980326354503632,
      "learning_rate": 9.219264287300799e-06,
      "loss": 10.3564,
      "step": 169
    },
    {
      "epoch": 0.8684546615581098,
      "grad_norm": 0.0988466814160347,
      "learning_rate": 8.558737698418761e-06,
      "loss": 10.3518,
      "step": 170
    },
    {
      "epoch": 0.8735632183908046,
      "grad_norm": 0.09410892426967621,
      "learning_rate": 7.921703137941173e-06,
      "loss": 10.3501,
      "step": 171
    },
    {
      "epoch": 0.8786717752234994,
      "grad_norm": 0.0989941656589508,
      "learning_rate": 7.308324265397836e-06,
      "loss": 10.3563,
      "step": 172
    },
    {
      "epoch": 0.8837803320561941,
      "grad_norm": 0.12267417460680008,
      "learning_rate": 6.718758662973523e-06,
      "loss": 10.3536,
      "step": 173
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.09049776196479797,
      "learning_rate": 6.153157795023956e-06,
      "loss": 10.3524,
      "step": 174
    },
    {
      "epoch": 0.8939974457215837,
      "grad_norm": 0.10820028930902481,
      "learning_rate": 5.611666969163243e-06,
      "loss": 10.3631,
      "step": 175
    },
    {
      "epoch": 0.8991060025542784,
      "grad_norm": 0.08953528106212616,
      "learning_rate": 5.094425298933136e-06,
      "loss": 10.3467,
      "step": 176
    },
    {
      "epoch": 0.9042145593869731,
      "grad_norm": 0.12113954871892929,
      "learning_rate": 4.601565668063623e-06,
      "loss": 10.3563,
      "step": 177
    },
    {
      "epoch": 0.909323116219668,
      "grad_norm": 0.08720055967569351,
      "learning_rate": 4.133214696333942e-06,
      "loss": 10.356,
      "step": 178
    },
    {
      "epoch": 0.9144316730523627,
      "grad_norm": 0.09181863814592361,
      "learning_rate": 3.689492707042974e-06,
      "loss": 10.3552,
      "step": 179
    },
    {
      "epoch": 0.9195402298850575,
      "grad_norm": 0.09627222269773483,
      "learning_rate": 3.270513696097055e-06,
      "loss": 10.3541,
      "step": 180
    },
    {
      "epoch": 0.9246487867177522,
      "grad_norm": 0.11901070922613144,
      "learning_rate": 2.876385302723628e-06,
      "loss": 10.3597,
      "step": 181
    },
    {
      "epoch": 0.929757343550447,
      "grad_norm": 0.0824970006942749,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 10.3537,
      "step": 182
    },
    {
      "epoch": 0.9348659003831418,
      "grad_norm": 0.10875054448843002,
      "learning_rate": 2.1630789779284675e-06,
      "loss": 10.3465,
      "step": 183
    },
    {
      "epoch": 0.9399744572158365,
      "grad_norm": 0.08391505479812622,
      "learning_rate": 1.8440843008934561e-06,
      "loss": 10.3537,
      "step": 184
    },
    {
      "epoch": 0.9450830140485313,
      "grad_norm": 0.0997113361954689,
      "learning_rate": 1.5503067031247598e-06,
      "loss": 10.3528,
      "step": 185
    },
    {
      "epoch": 0.9501915708812261,
      "grad_norm": 0.1007162481546402,
      "learning_rate": 1.2818216585549825e-06,
      "loss": 10.3498,
      "step": 186
    },
    {
      "epoch": 0.9553001277139208,
      "grad_norm": 0.0825323835015297,
      "learning_rate": 1.0386981432474074e-06,
      "loss": 10.3464,
      "step": 187
    },
    {
      "epoch": 0.9604086845466155,
      "grad_norm": 0.07373323291540146,
      "learning_rate": 8.209986176753948e-07,
      "loss": 10.3546,
      "step": 188
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.10504812747240067,
      "learning_rate": 6.287790106757396e-07,
      "loss": 10.3522,
      "step": 189
    },
    {
      "epoch": 0.9706257982120051,
      "grad_norm": 0.07949844747781754,
      "learning_rate": 4.62088705080177e-07,
      "loss": 10.3554,
      "step": 190
    },
    {
      "epoch": 0.9757343550446999,
      "grad_norm": 0.09091745316982269,
      "learning_rate": 3.2097052502843007e-07,
      "loss": 10.3477,
      "step": 191
    },
    {
      "epoch": 0.9808429118773946,
      "grad_norm": 0.11523844301700592,
      "learning_rate": 2.054607249663665e-07,
      "loss": 10.3526,
      "step": 192
    },
    {
      "epoch": 0.9859514687100894,
      "grad_norm": 0.09753245860338211,
      "learning_rate": 1.1558898033191546e-07,
      "loss": 10.3566,
      "step": 193
    },
    {
      "epoch": 0.9910600255427842,
      "grad_norm": 0.08241667598485947,
      "learning_rate": 5.137837993121064e-08,
      "loss": 10.3576,
      "step": 194
    },
    {
      "epoch": 0.9961685823754789,
      "grad_norm": 0.08668815344572067,
      "learning_rate": 1.2845420006879494e-08,
      "loss": 10.3612,
      "step": 195
    },
    {
      "epoch": 0.9961685823754789,
      "eval_loss": 10.354520797729492,
      "eval_runtime": 0.2879,
      "eval_samples_per_second": 145.877,
      "eval_steps_per_second": 145.877,
      "step": 195
    },
    {
      "epoch": 1.0012771392081736,
      "grad_norm": 0.08981695771217346,
      "learning_rate": 0.0,
      "loss": 12.4365,
      "step": 196
    },
    {
      "epoch": 1.0012771392081736,
      "eval_loss": 10.354520797729492,
      "eval_runtime": 0.2791,
      "eval_samples_per_second": 150.484,
      "eval_steps_per_second": 150.484,
      "step": 196
    }
  ],
  "logging_steps": 1,
  "max_steps": 196,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2534457999360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}