{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.997420464316423,
  "eval_steps": 500,
  "global_step": 1743,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017196904557179708,
      "grad_norm": 1.236184773002013,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 1.185,
      "step": 10
    },
    {
      "epoch": 0.034393809114359415,
      "grad_norm": 0.5456076333168367,
      "learning_rate": 2.2857142857142858e-05,
      "loss": 1.0131,
      "step": 20
    },
    {
      "epoch": 0.051590713671539126,
      "grad_norm": 0.35549053304697176,
      "learning_rate": 3.428571428571429e-05,
      "loss": 0.8296,
      "step": 30
    },
    {
      "epoch": 0.06878761822871883,
      "grad_norm": 0.254673976618386,
      "learning_rate": 4.5714285714285716e-05,
      "loss": 0.7454,
      "step": 40
    },
    {
      "epoch": 0.08598452278589853,
      "grad_norm": 0.23070603652224944,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.6662,
      "step": 50
    },
    {
      "epoch": 0.10318142734307825,
      "grad_norm": 0.17478929504818824,
      "learning_rate": 6.857142857142858e-05,
      "loss": 0.596,
      "step": 60
    },
    {
      "epoch": 0.12037833190025796,
      "grad_norm": 0.1561819886139925,
      "learning_rate": 8e-05,
      "loss": 0.578,
      "step": 70
    },
    {
      "epoch": 0.13757523645743766,
      "grad_norm": 0.20767032014128362,
      "learning_rate": 9.142857142857143e-05,
      "loss": 0.56,
      "step": 80
    },
    {
      "epoch": 0.15477214101461736,
      "grad_norm": 0.1783753453274605,
      "learning_rate": 0.00010285714285714286,
      "loss": 0.5486,
      "step": 90
    },
    {
      "epoch": 0.17196904557179707,
      "grad_norm": 0.21780447055549776,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.5442,
      "step": 100
    },
    {
      "epoch": 0.18916595012897677,
      "grad_norm": 0.17636411695201717,
      "learning_rate": 0.00012571428571428572,
      "loss": 0.5336,
      "step": 110
    },
    {
      "epoch": 0.2063628546861565,
      "grad_norm": 0.17514613701190404,
      "learning_rate": 0.00013714285714285716,
      "loss": 0.5267,
      "step": 120
    },
    {
      "epoch": 0.2235597592433362,
      "grad_norm": 0.19025963821244604,
      "learning_rate": 0.00014857142857142857,
      "loss": 0.5274,
      "step": 130
    },
    {
      "epoch": 0.2407566638005159,
      "grad_norm": 0.18019488365092756,
      "learning_rate": 0.00016,
      "loss": 0.5166,
      "step": 140
    },
    {
      "epoch": 0.2579535683576956,
      "grad_norm": 0.17880762343061918,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.5203,
      "step": 150
    },
    {
      "epoch": 0.2751504729148753,
      "grad_norm": 0.18388862726424096,
      "learning_rate": 0.00018285714285714286,
      "loss": 0.5224,
      "step": 160
    },
    {
      "epoch": 0.292347377472055,
      "grad_norm": 0.16430698379785788,
      "learning_rate": 0.0001942857142857143,
      "loss": 0.5188,
      "step": 170
    },
    {
      "epoch": 0.30954428202923473,
      "grad_norm": 0.15725107599349494,
      "learning_rate": 0.00019999498219234568,
      "loss": 0.516,
      "step": 180
    },
    {
      "epoch": 0.32674118658641443,
      "grad_norm": 0.15173489549988936,
      "learning_rate": 0.0001999548427524678,
      "loss": 0.5058,
      "step": 190
    },
    {
      "epoch": 0.34393809114359414,
      "grad_norm": 0.16657669365074929,
      "learning_rate": 0.0001998745799852668,
      "loss": 0.5072,
      "step": 200
    },
    {
      "epoch": 0.36113499570077384,
      "grad_norm": 0.14245522126193838,
      "learning_rate": 0.00019975422610938462,
      "loss": 0.5092,
      "step": 210
    },
    {
      "epoch": 0.37833190025795355,
      "grad_norm": 0.14204763106782423,
      "learning_rate": 0.00019959382943661704,
      "loss": 0.5124,
      "step": 220
    },
    {
      "epoch": 0.39552880481513325,
      "grad_norm": 0.14674244927319882,
      "learning_rate": 0.00019939345435252088,
      "loss": 0.515,
      "step": 230
    },
    {
      "epoch": 0.412725709372313,
      "grad_norm": 0.13843089052767493,
      "learning_rate": 0.00019915318129056853,
      "loss": 0.4994,
      "step": 240
    },
    {
      "epoch": 0.4299226139294927,
      "grad_norm": 0.146900895726969,
      "learning_rate": 0.00019887310669986085,
      "loss": 0.5052,
      "step": 250
    },
    {
      "epoch": 0.4471195184866724,
      "grad_norm": 0.14008859218618483,
      "learning_rate": 0.00019855334300641114,
      "loss": 0.5041,
      "step": 260
    },
    {
      "epoch": 0.4643164230438521,
      "grad_norm": 0.18809570469767778,
      "learning_rate": 0.0001981940185680156,
      "loss": 0.4978,
      "step": 270
    },
    {
      "epoch": 0.4815133276010318,
      "grad_norm": 0.14104099043343712,
      "learning_rate": 0.00019779527762272877,
      "loss": 0.5001,
      "step": 280
    },
    {
      "epoch": 0.49871023215821153,
      "grad_norm": 0.13804026353342516,
      "learning_rate": 0.0001973572802309642,
      "loss": 0.4885,
      "step": 290
    },
    {
      "epoch": 0.5159071367153912,
      "grad_norm": 0.14300868500069924,
      "learning_rate": 0.00019688020221124376,
      "loss": 0.495,
      "step": 300
    },
    {
      "epoch": 0.5331040412725709,
      "grad_norm": 0.14885187886758067,
      "learning_rate": 0.00019636423506962181,
      "loss": 0.4963,
      "step": 310
    },
    {
      "epoch": 0.5503009458297506,
      "grad_norm": 0.13442343336925347,
      "learning_rate": 0.00019580958592281167,
      "loss": 0.4924,
      "step": 320
    },
    {
      "epoch": 0.5674978503869303,
      "grad_norm": 0.13673211813600614,
      "learning_rate": 0.00019521647741504604,
      "loss": 0.5004,
      "step": 330
    },
    {
      "epoch": 0.58469475494411,
      "grad_norm": 0.13956825916960136,
      "learning_rate": 0.00019458514762870426,
      "loss": 0.485,
      "step": 340
    },
    {
      "epoch": 0.6018916595012898,
      "grad_norm": 0.14073396199862337,
      "learning_rate": 0.0001939158499887428,
      "loss": 0.4933,
      "step": 350
    },
    {
      "epoch": 0.6190885640584695,
      "grad_norm": 0.13603301551856595,
      "learning_rate": 0.00019320885316096654,
      "loss": 0.4938,
      "step": 360
    },
    {
      "epoch": 0.6362854686156492,
      "grad_norm": 0.1420552122294903,
      "learning_rate": 0.00019246444094418255,
      "loss": 0.4786,
      "step": 370
    },
    {
      "epoch": 0.6534823731728289,
      "grad_norm": 0.1414519600117056,
      "learning_rate": 0.00019168291215627926,
      "loss": 0.4926,
      "step": 380
    },
    {
      "epoch": 0.6706792777300086,
      "grad_norm": 0.13984821923297133,
      "learning_rate": 0.00019086458051427622,
      "loss": 0.4911,
      "step": 390
    },
    {
      "epoch": 0.6878761822871883,
      "grad_norm": 0.13752756195301288,
      "learning_rate": 0.00019000977450839393,
      "loss": 0.4827,
      "step": 400
    },
    {
      "epoch": 0.705073086844368,
      "grad_norm": 0.13335244333926366,
      "learning_rate": 0.00018911883727019285,
      "loss": 0.4898,
      "step": 410
    },
    {
      "epoch": 0.7222699914015477,
      "grad_norm": 0.13230952803690713,
      "learning_rate": 0.0001881921264348355,
      "loss": 0.4854,
      "step": 420
    },
    {
      "epoch": 0.7394668959587274,
      "grad_norm": 0.13478694398925248,
      "learning_rate": 0.00018723001399752653,
      "loss": 0.4897,
      "step": 430
    },
    {
      "epoch": 0.7566638005159071,
      "grad_norm": 0.1442034436213339,
      "learning_rate": 0.0001862328861641883,
      "loss": 0.4822,
      "step": 440
    },
    {
      "epoch": 0.7738607050730868,
      "grad_norm": 0.13449084966209246,
      "learning_rate": 0.00018520114319643235,
      "loss": 0.4886,
      "step": 450
    },
    {
      "epoch": 0.7910576096302665,
      "grad_norm": 0.1312938599246684,
      "learning_rate": 0.0001841351992508885,
      "loss": 0.4786,
      "step": 460
    },
    {
      "epoch": 0.8082545141874462,
      "grad_norm": 0.12664552711595364,
      "learning_rate": 0.0001830354822129564,
      "loss": 0.4882,
      "step": 470
    },
    {
      "epoch": 0.825451418744626,
      "grad_norm": 0.134819817437524,
      "learning_rate": 0.00018190243352504597,
      "loss": 0.48,
      "step": 480
    },
    {
      "epoch": 0.8426483233018057,
      "grad_norm": 0.14466404063388616,
      "learning_rate": 0.00018073650800937624,
      "loss": 0.4809,
      "step": 490
    },
    {
      "epoch": 0.8598452278589854,
      "grad_norm": 0.13311350418133092,
      "learning_rate": 0.00017953817368540292,
      "loss": 0.4834,
      "step": 500
    },
    {
      "epoch": 0.8770421324161651,
      "grad_norm": 0.13856027344204028,
      "learning_rate": 0.0001783079115819486,
      "loss": 0.4913,
      "step": 510
    },
    {
      "epoch": 0.8942390369733448,
      "grad_norm": 0.12870004634007948,
      "learning_rate": 0.00017704621554411084,
      "loss": 0.4827,
      "step": 520
    },
    {
      "epoch": 0.9114359415305245,
      "grad_norm": 0.12894303718503525,
      "learning_rate": 0.0001757535920350255,
      "loss": 0.4768,
      "step": 530
    },
    {
      "epoch": 0.9286328460877042,
      "grad_norm": 0.13086927730335407,
      "learning_rate": 0.0001744305599325652,
      "loss": 0.4857,
      "step": 540
    },
    {
      "epoch": 0.945829750644884,
      "grad_norm": 0.12929634161460313,
      "learning_rate": 0.00017307765032105406,
      "loss": 0.4883,
      "step": 550
    },
    {
      "epoch": 0.9630266552020637,
      "grad_norm": 0.13721669025539573,
      "learning_rate": 0.00017169540627808274,
      "loss": 0.4875,
      "step": 560
    },
    {
      "epoch": 0.9802235597592434,
      "grad_norm": 0.1285154415557853,
      "learning_rate": 0.00017028438265650933,
      "loss": 0.4821,
      "step": 570
    },
    {
      "epoch": 0.9974204643164231,
      "grad_norm": 0.13060285124046392,
      "learning_rate": 0.0001688451458617332,
      "loss": 0.4796,
      "step": 580
    },
    {
      "epoch": 1.0146173688736027,
      "grad_norm": 0.136066972815243,
      "learning_rate": 0.00016737827362433164,
      "loss": 0.4527,
      "step": 590
    },
    {
      "epoch": 1.0318142734307825,
      "grad_norm": 0.1366031218446295,
      "learning_rate": 0.0001658843547681506,
      "loss": 0.4484,
      "step": 600
    },
    {
      "epoch": 1.049011177987962,
      "grad_norm": 0.1378157386033563,
      "learning_rate": 0.000164363988973942,
      "loss": 0.4465,
      "step": 610
    },
    {
      "epoch": 1.0662080825451419,
      "grad_norm": 0.1435554531245416,
      "learning_rate": 0.00016281778653864316,
      "loss": 0.4415,
      "step": 620
    },
    {
      "epoch": 1.0834049871023215,
      "grad_norm": 0.14661925606567783,
      "learning_rate": 0.00016124636813039502,
      "loss": 0.441,
      "step": 630
    },
    {
      "epoch": 1.1006018916595013,
      "grad_norm": 0.13987832152903712,
      "learning_rate": 0.0001596503645393966,
      "loss": 0.4359,
      "step": 640
    },
    {
      "epoch": 1.117798796216681,
      "grad_norm": 0.14735126394013195,
      "learning_rate": 0.0001580304164246968,
      "loss": 0.4473,
      "step": 650
    },
    {
      "epoch": 1.1349957007738607,
      "grad_norm": 0.1429953902523938,
      "learning_rate": 0.0001563871740570245,
      "loss": 0.4451,
      "step": 660
    },
    {
      "epoch": 1.1521926053310405,
      "grad_norm": 0.1459735378688384,
      "learning_rate": 0.00015472129705776047,
      "loss": 0.4422,
      "step": 670
    },
    {
      "epoch": 1.16938950988822,
      "grad_norm": 0.14561658254102702,
      "learning_rate": 0.00015303345413415564,
      "loss": 0.4409,
      "step": 680
    },
    {
      "epoch": 1.1865864144454,
      "grad_norm": 0.14737248104484174,
      "learning_rate": 0.00015132432281090256,
      "loss": 0.4419,
      "step": 690
    },
    {
      "epoch": 1.2037833190025795,
      "grad_norm": 0.15311335569967213,
      "learning_rate": 0.0001495945891581668,
      "loss": 0.4419,
      "step": 700
    },
    {
      "epoch": 1.2209802235597593,
      "grad_norm": 0.14524361407042563,
      "learning_rate": 0.00014784494751618853,
      "loss": 0.4411,
      "step": 710
    },
    {
      "epoch": 1.238177128116939,
      "grad_norm": 0.14910830182050996,
      "learning_rate": 0.0001460761002165645,
      "loss": 0.4471,
      "step": 720
    },
    {
      "epoch": 1.2553740326741187,
      "grad_norm": 0.15226336213789984,
      "learning_rate": 0.00014428875730032145,
      "loss": 0.4423,
      "step": 730
    },
    {
      "epoch": 1.2725709372312983,
      "grad_norm": 0.15781539164450759,
      "learning_rate": 0.00014248363623289574,
      "loss": 0.4359,
      "step": 740
    },
    {
      "epoch": 1.2897678417884781,
      "grad_norm": 0.14138385096885275,
      "learning_rate": 0.00014066146161613208,
      "loss": 0.4414,
      "step": 750
    },
    {
      "epoch": 1.3069647463456577,
      "grad_norm": 0.14745231010770607,
      "learning_rate": 0.00013882296489741783,
      "loss": 0.4457,
      "step": 760
    },
    {
      "epoch": 1.3241616509028376,
      "grad_norm": 0.155323506204182,
      "learning_rate": 0.00013696888407606952,
      "loss": 0.4468,
      "step": 770
    },
    {
      "epoch": 1.3413585554600171,
      "grad_norm": 0.14906188336013929,
      "learning_rate": 0.0001350999634070889,
      "loss": 0.4561,
      "step": 780
    },
    {
      "epoch": 1.358555460017197,
      "grad_norm": 0.1509482546916061,
      "learning_rate": 0.0001332169531024085,
      "loss": 0.4488,
      "step": 790
    },
    {
      "epoch": 1.3757523645743766,
      "grad_norm": 0.1577110542147225,
      "learning_rate": 0.00013132060902974554,
      "loss": 0.4481,
      "step": 800
    },
    {
      "epoch": 1.3929492691315564,
      "grad_norm": 0.1519302579308639,
      "learning_rate": 0.00012941169240918534,
      "loss": 0.4434,
      "step": 810
    },
    {
      "epoch": 1.410146173688736,
      "grad_norm": 0.16574786040919845,
      "learning_rate": 0.00012749096950761702,
      "loss": 0.4422,
      "step": 820
    },
    {
      "epoch": 1.4273430782459158,
      "grad_norm": 0.14939058136631353,
      "learning_rate": 0.00012555921133114247,
      "loss": 0.4439,
      "step": 830
    },
    {
      "epoch": 1.4445399828030954,
      "grad_norm": 0.14433259289852834,
      "learning_rate": 0.00012361719331558345,
      "loss": 0.4412,
      "step": 840
    },
    {
      "epoch": 1.4617368873602752,
      "grad_norm": 0.14779220063991433,
      "learning_rate": 0.00012166569501521017,
      "loss": 0.444,
      "step": 850
    },
    {
      "epoch": 1.4789337919174548,
      "grad_norm": 0.15109790098843823,
      "learning_rate": 0.00011970549978981715,
      "loss": 0.4489,
      "step": 860
    },
    {
      "epoch": 1.4961306964746346,
      "grad_norm": 0.14824981470720835,
      "learning_rate": 0.00011773739449027108,
      "loss": 0.4377,
      "step": 870
    },
    {
      "epoch": 1.5133276010318144,
      "grad_norm": 0.14490199589122096,
      "learning_rate": 0.00011576216914265734,
      "loss": 0.4454,
      "step": 880
    },
    {
      "epoch": 1.530524505588994,
      "grad_norm": 0.14668336107167357,
      "learning_rate": 0.00011378061663115222,
      "loss": 0.4374,
      "step": 890
    },
    {
      "epoch": 1.5477214101461736,
      "grad_norm": 0.15306161877683747,
      "learning_rate": 0.00011179353237974756,
      "loss": 0.441,
      "step": 900
    },
    {
      "epoch": 1.5649183147033534,
      "grad_norm": 0.14629253984953647,
      "learning_rate": 0.0001098017140329561,
      "loss": 0.4402,
      "step": 910
    },
    {
      "epoch": 1.5821152192605332,
      "grad_norm": 0.15181211231388803,
      "learning_rate": 0.00010780596113562514,
      "loss": 0.4441,
      "step": 920
    },
    {
      "epoch": 1.5993121238177128,
      "grad_norm": 0.14895949287614227,
      "learning_rate": 0.00010580707481198796,
      "loss": 0.4415,
      "step": 930
    },
    {
      "epoch": 1.6165090283748924,
      "grad_norm": 0.14919588155250404,
      "learning_rate": 0.00010380585744408065,
      "loss": 0.4428,
      "step": 940
    },
    {
      "epoch": 1.6337059329320722,
      "grad_norm": 0.15195396903926595,
      "learning_rate": 0.00010180311234965433,
      "loss": 0.4338,
      "step": 950
    },
    {
      "epoch": 1.650902837489252,
      "grad_norm": 0.15192117531451788,
      "learning_rate": 9.979964345971188e-05,
      "loss": 0.445,
      "step": 960
    },
    {
      "epoch": 1.6680997420464316,
      "grad_norm": 0.14674515514268918,
      "learning_rate": 9.779625499579805e-05,
      "loss": 0.4416,
      "step": 970
    },
    {
      "epoch": 1.6852966466036112,
      "grad_norm": 0.14766438549971136,
      "learning_rate": 9.579375114717351e-05,
      "loss": 0.434,
      "step": 980
    },
    {
      "epoch": 1.702493551160791,
      "grad_norm": 0.14681911182175214,
      "learning_rate": 9.379293574800154e-05,
      "loss": 0.4363,
      "step": 990
    },
    {
      "epoch": 1.7196904557179709,
      "grad_norm": 0.1464492709373849,
      "learning_rate": 9.179461195467714e-05,
      "loss": 0.4353,
      "step": 1000
    },
    {
      "epoch": 1.7368873602751504,
      "grad_norm": 0.15011221390319449,
      "learning_rate": 8.979958192342862e-05,
      "loss": 0.4445,
      "step": 1010
    },
    {
      "epoch": 1.75408426483233,
      "grad_norm": 0.152429302734013,
      "learning_rate": 8.780864648832022e-05,
      "loss": 0.4404,
      "step": 1020
    },
    {
      "epoch": 1.7712811693895099,
      "grad_norm": 0.14681226342261067,
      "learning_rate": 8.58226048397857e-05,
      "loss": 0.4435,
      "step": 1030
    },
    {
      "epoch": 1.7884780739466897,
      "grad_norm": 0.15354804740449426,
      "learning_rate": 8.384225420382185e-05,
      "loss": 0.4377,
      "step": 1040
    },
    {
      "epoch": 1.8056749785038693,
      "grad_norm": 0.15108728472484245,
      "learning_rate": 8.186838952197018e-05,
      "loss": 0.4344,
      "step": 1050
    },
    {
      "epoch": 1.8228718830610489,
      "grad_norm": 0.14903695640608858,
      "learning_rate": 7.990180313221596e-05,
      "loss": 0.4381,
      "step": 1060
    },
    {
      "epoch": 1.8400687876182287,
      "grad_norm": 0.14676064171835554,
      "learning_rate": 7.794328445093208e-05,
      "loss": 0.4379,
      "step": 1070
    },
    {
      "epoch": 1.8572656921754085,
      "grad_norm": 0.15258822928003124,
      "learning_rate": 7.599361965599606e-05,
      "loss": 0.4426,
      "step": 1080
    },
    {
      "epoch": 1.874462596732588,
      "grad_norm": 0.26094072520435535,
      "learning_rate": 7.405359137120662e-05,
      "loss": 0.4368,
      "step": 1090
    },
    {
      "epoch": 1.8916595012897677,
      "grad_norm": 0.15223526485978567,
      "learning_rate": 7.212397835212722e-05,
      "loss": 0.4426,
      "step": 1100
    },
    {
      "epoch": 1.9088564058469477,
      "grad_norm": 0.14158786202820334,
      "learning_rate": 7.02055551734822e-05,
      "loss": 0.4304,
      "step": 1110
    },
    {
      "epoch": 1.9260533104041273,
      "grad_norm": 0.15562496727433017,
      "learning_rate": 6.829909191823121e-05,
      "loss": 0.4426,
      "step": 1120
    },
    {
      "epoch": 1.943250214961307,
      "grad_norm": 0.14930981803960258,
      "learning_rate": 6.640535386844679e-05,
      "loss": 0.4418,
      "step": 1130
    },
    {
      "epoch": 1.9604471195184867,
      "grad_norm": 0.1552156563224316,
      "learning_rate": 6.452510119811895e-05,
      "loss": 0.4367,
      "step": 1140
    },
    {
      "epoch": 1.9776440240756665,
      "grad_norm": 0.19090518551388455,
      "learning_rate": 6.26590886680103e-05,
      "loss": 0.4303,
      "step": 1150
    },
    {
      "epoch": 1.9948409286328461,
      "grad_norm": 0.1496699651502689,
      "learning_rate": 6.0808065322683993e-05,
      "loss": 0.4307,
      "step": 1160
    },
    {
      "epoch": 2.0120378331900257,
      "grad_norm": 0.16615207318616432,
      "learning_rate": 5.897277418982672e-05,
      "loss": 0.3983,
      "step": 1170
    },
    {
      "epoch": 2.0292347377472053,
      "grad_norm": 0.1652827612761684,
      "learning_rate": 5.715395198198603e-05,
      "loss": 0.3812,
      "step": 1180
    },
    {
      "epoch": 2.0464316423043853,
      "grad_norm": 0.16911724923353538,
      "learning_rate": 5.5352328800843724e-05,
      "loss": 0.3766,
      "step": 1190
    },
    {
      "epoch": 2.063628546861565,
      "grad_norm": 0.16951539871441879,
      "learning_rate": 5.356862784414199e-05,
      "loss": 0.3789,
      "step": 1200
    },
    {
      "epoch": 2.0808254514187445,
      "grad_norm": 0.17010125437035936,
      "learning_rate": 5.1803565115381694e-05,
      "loss": 0.3783,
      "step": 1210
    },
    {
      "epoch": 2.098022355975924,
      "grad_norm": 0.16860757374113347,
      "learning_rate": 5.0057849136407874e-05,
      "loss": 0.3815,
      "step": 1220
    },
    {
      "epoch": 2.115219260533104,
      "grad_norm": 0.17279827710775011,
      "learning_rate": 4.833218066299896e-05,
      "loss": 0.3775,
      "step": 1230
    },
    {
      "epoch": 2.1324161650902838,
      "grad_norm": 0.16772946452531912,
      "learning_rate": 4.6627252403573085e-05,
      "loss": 0.3719,
      "step": 1240
    },
    {
      "epoch": 2.1496130696474633,
      "grad_norm": 0.17982428185526986,
      "learning_rate": 4.4943748741124934e-05,
      "loss": 0.3779,
      "step": 1250
    },
    {
      "epoch": 2.166809974204643,
      "grad_norm": 0.18313593415470272,
      "learning_rate": 4.328234545850442e-05,
      "loss": 0.3836,
      "step": 1260
    },
    {
      "epoch": 2.184006878761823,
      "grad_norm": 0.1725383341952266,
      "learning_rate": 4.1643709467147615e-05,
      "loss": 0.369,
      "step": 1270
    },
    {
      "epoch": 2.2012037833190026,
      "grad_norm": 0.1971081873293993,
      "learning_rate": 4.002849853936891e-05,
      "loss": 0.3728,
      "step": 1280
    },
    {
      "epoch": 2.218400687876182,
      "grad_norm": 0.17991148711708474,
      "learning_rate": 3.843736104432137e-05,
      "loss": 0.3804,
      "step": 1290
    },
    {
      "epoch": 2.235597592433362,
      "grad_norm": 0.17934271418386846,
      "learning_rate": 3.687093568773229e-05,
      "loss": 0.3844,
      "step": 1300
    },
    {
      "epoch": 2.252794496990542,
      "grad_norm": 0.17862554374418718,
      "learning_rate": 3.532985125551715e-05,
      "loss": 0.385,
      "step": 1310
    },
    {
      "epoch": 2.2699914015477214,
      "grad_norm": 0.17397364598815349,
      "learning_rate": 3.381472636137591e-05,
      "loss": 0.3755,
      "step": 1320
    },
    {
      "epoch": 2.287188306104901,
      "grad_norm": 0.18500269890886714,
      "learning_rate": 3.2326169198472556e-05,
      "loss": 0.384,
      "step": 1330
    },
    {
      "epoch": 2.304385210662081,
      "grad_norm": 0.18186600816942164,
      "learning_rate": 3.0864777295297376e-05,
      "loss": 0.3726,
      "step": 1340
    },
    {
      "epoch": 2.3215821152192606,
      "grad_norm": 0.17773737221105249,
      "learning_rate": 2.9431137275810317e-05,
      "loss": 0.3704,
      "step": 1350
    },
    {
      "epoch": 2.33877901977644,
      "grad_norm": 0.18256211613697612,
      "learning_rate": 2.8025824623961773e-05,
      "loss": 0.3769,
      "step": 1360
    },
    {
      "epoch": 2.35597592433362,
      "grad_norm": 0.18129287061779392,
      "learning_rate": 2.664940345268483e-05,
      "loss": 0.3766,
      "step": 1370
    },
    {
      "epoch": 2.3731728288908,
      "grad_norm": 0.1785686917578723,
      "learning_rate": 2.5302426277452172e-05,
      "loss": 0.3701,
      "step": 1380
    },
    {
      "epoch": 2.3903697334479794,
      "grad_norm": 0.19834019533954172,
      "learning_rate": 2.398543379448832e-05,
      "loss": 0.3768,
      "step": 1390
    },
    {
      "epoch": 2.407566638005159,
      "grad_norm": 0.18177776105752433,
      "learning_rate": 2.26989546637263e-05,
      "loss": 0.3755,
      "step": 1400
    },
    {
      "epoch": 2.4247635425623386,
      "grad_norm": 0.18362730161587285,
      "learning_rate": 2.144350529659589e-05,
      "loss": 0.368,
      "step": 1410
    },
    {
      "epoch": 2.4419604471195187,
      "grad_norm": 0.18330397808911847,
      "learning_rate": 2.021958964872851e-05,
      "loss": 0.3794,
      "step": 1420
    },
    {
      "epoch": 2.4591573516766982,
      "grad_norm": 0.19205219312460517,
      "learning_rate": 1.9027699017662194e-05,
      "loss": 0.3703,
      "step": 1430
    },
    {
      "epoch": 2.476354256233878,
      "grad_norm": 0.18216660996651907,
      "learning_rate": 1.7868311845627472e-05,
      "loss": 0.3754,
      "step": 1440
    },
    {
      "epoch": 2.4935511607910574,
      "grad_norm": 0.18809064927597854,
      "learning_rate": 1.6741893527493858e-05,
      "loss": 0.3707,
      "step": 1450
    },
    {
      "epoch": 2.5107480653482375,
      "grad_norm": 0.18562863684234907,
      "learning_rate": 1.564889622395349e-05,
      "loss": 0.3698,
      "step": 1460
    },
    {
      "epoch": 2.527944969905417,
      "grad_norm": 0.18350802969723742,
      "learning_rate": 1.4589758680017263e-05,
      "loss": 0.3733,
      "step": 1470
    },
    {
      "epoch": 2.5451418744625967,
      "grad_norm": 0.18684066406776073,
      "learning_rate": 1.356490604889622e-05,
      "loss": 0.3787,
      "step": 1480
    },
    {
      "epoch": 2.5623387790197762,
      "grad_norm": 0.1811515744478759,
      "learning_rate": 1.2574749721338874e-05,
      "loss": 0.3769,
      "step": 1490
    },
    {
      "epoch": 2.5795356835769563,
      "grad_norm": 0.18069550077179752,
      "learning_rate": 1.1619687160492953e-05,
      "loss": 0.3701,
      "step": 1500
    },
    {
      "epoch": 2.596732588134136,
      "grad_norm": 0.18462589607546182,
      "learning_rate": 1.0700101742357926e-05,
      "loss": 0.3744,
      "step": 1510
    },
    {
      "epoch": 2.6139294926913155,
      "grad_norm": 0.18712041177077796,
      "learning_rate": 9.816362601892326e-06,
      "loss": 0.3677,
      "step": 1520
    },
    {
      "epoch": 2.6311263972484955,
      "grad_norm": 0.18908434345209518,
      "learning_rate": 8.968824484837578e-06,
      "loss": 0.3685,
      "step": 1530
    },
    {
      "epoch": 2.648323301805675,
      "grad_norm": 0.1847336144413599,
      "learning_rate": 8.157827605317892e-06,
      "loss": 0.3713,
      "step": 1540
    },
    {
      "epoch": 2.6655202063628547,
      "grad_norm": 0.18269892602018764,
      "learning_rate": 7.383697509273424e-06,
      "loss": 0.367,
      "step": 1550
    },
    {
      "epoch": 2.6827171109200343,
      "grad_norm": 0.18647288570365314,
      "learning_rate": 6.646744943781325e-06,
      "loss": 0.3724,
      "step": 1560
    },
    {
      "epoch": 2.699914015477214,
      "grad_norm": 0.18698726008663819,
      "learning_rate": 5.947265732317408e-06,
      "loss": 0.3659,
      "step": 1570
    },
    {
      "epoch": 2.717110920034394,
      "grad_norm": 0.18309326292481923,
      "learning_rate": 5.285540656008303e-06,
      "loss": 0.3757,
      "step": 1580
    },
    {
      "epoch": 2.7343078245915735,
      "grad_norm": 0.18668212507421977,
      "learning_rate": 4.6618353409217386e-06,
      "loss": 0.3673,
      "step": 1590
    },
    {
      "epoch": 2.751504729148753,
      "grad_norm": 0.1840554864418513,
      "learning_rate": 4.076400151440485e-06,
      "loss": 0.367,
      "step": 1600
    },
    {
      "epoch": 2.768701633705933,
      "grad_norm": 0.1838274059601279,
      "learning_rate": 3.529470089762421e-06,
      "loss": 0.3676,
      "step": 1610
    },
    {
      "epoch": 2.7858985382631127,
      "grad_norm": 0.1905340116630113,
      "learning_rate": 3.021264701567206e-06,
      "loss": 0.3745,
      "step": 1620
    },
    {
      "epoch": 2.8030954428202923,
      "grad_norm": 0.1859751703399611,
      "learning_rate": 2.551987987887461e-06,
      "loss": 0.369,
      "step": 1630
    },
    {
      "epoch": 2.820292347377472,
      "grad_norm": 0.18905809126144052,
      "learning_rate": 2.1218283232198212e-06,
      "loss": 0.3774,
      "step": 1640
    },
    {
      "epoch": 2.8374892519346515,
      "grad_norm": 0.1853105742586414,
      "learning_rate": 1.7309583799086094e-06,
      "loss": 0.3726,
      "step": 1650
    },
    {
      "epoch": 2.8546861564918316,
      "grad_norm": 0.1840942740034349,
      "learning_rate": 1.3795350588327261e-06,
      "loss": 0.3779,
      "step": 1660
    },
    {
      "epoch": 2.871883061049011,
      "grad_norm": 0.18025938643579378,
      "learning_rate": 1.0676994264232854e-06,
      "loss": 0.3692,
      "step": 1670
    },
    {
      "epoch": 2.8890799656061907,
      "grad_norm": 0.18685969171459274,
      "learning_rate": 7.955766580375335e-07,
      "loss": 0.3688,
      "step": 1680
    },
    {
      "epoch": 2.9062768701633708,
      "grad_norm": 0.1830773378552538,
      "learning_rate": 5.632759877116422e-07,
      "loss": 0.3738,
      "step": 1690
    },
    {
      "epoch": 2.9234737747205504,
      "grad_norm": 0.18687096055320696,
      "learning_rate": 3.708906643125509e-07,
      "loss": 0.3754,
      "step": 1700
    },
    {
      "epoch": 2.94067067927773,
      "grad_norm": 0.18843515900821306,
      "learning_rate": 2.184979141065413e-07,
      "loss": 0.374,
      "step": 1710
    },
    {
      "epoch": 2.9578675838349096,
      "grad_norm": 0.1907738099777219,
      "learning_rate": 1.061589097595017e-07,
      "loss": 0.3719,
      "step": 1720
    },
    {
      "epoch": 2.9750644883920896,
      "grad_norm": 0.18629496289787387,
      "learning_rate": 3.3918745781291725e-08,
      "loss": 0.3734,
      "step": 1730
    },
    {
      "epoch": 2.992261392949269,
      "grad_norm": 0.1807736649886976,
      "learning_rate": 1.8064204241774462e-09,
      "loss": 0.3669,
      "step": 1740
    },
    {
      "epoch": 2.997420464316423,
      "step": 1743,
      "total_flos": 1.7624457120055296e+16,
      "train_loss": 0.4506890232783245,
      "train_runtime": 9589.9992,
      "train_samples_per_second": 5.818,
      "train_steps_per_second": 0.182
    }
  ],
  "logging_steps": 10,
  "max_steps": 1743,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.7624457120055296e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}