{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9992646286374619,
  "eval_steps": 500,
  "global_step": 1189,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008404244143292362,
      "grad_norm": 0.7383340001106262,
      "learning_rate": 2e-05,
      "loss": 2.4066,
      "step": 10
    },
    {
      "epoch": 0.016808488286584725,
      "grad_norm": 0.46394309401512146,
      "learning_rate": 4e-05,
      "loss": 2.0375,
      "step": 20
    },
    {
      "epoch": 0.025212732429877087,
      "grad_norm": 0.4739478528499603,
      "learning_rate": 6e-05,
      "loss": 1.5044,
      "step": 30
    },
    {
      "epoch": 0.03361697657316945,
      "grad_norm": 0.20930196344852448,
      "learning_rate": 8e-05,
      "loss": 0.8704,
      "step": 40
    },
    {
      "epoch": 0.04202122071646181,
      "grad_norm": 0.15288038551807404,
      "learning_rate": 0.0001,
      "loss": 0.6533,
      "step": 50
    },
    {
      "epoch": 0.050425464859754174,
      "grad_norm": 0.13073962926864624,
      "learning_rate": 0.00012,
      "loss": 0.586,
      "step": 60
    },
    {
      "epoch": 0.058829709003046536,
      "grad_norm": 0.14555367827415466,
      "learning_rate": 0.00014,
      "loss": 0.5793,
      "step": 70
    },
    {
      "epoch": 0.0672339531463389,
      "grad_norm": 0.12397414445877075,
      "learning_rate": 0.00016,
      "loss": 0.581,
      "step": 80
    },
    {
      "epoch": 0.07563819728963127,
      "grad_norm": 0.13021130859851837,
      "learning_rate": 0.00018,
      "loss": 0.5512,
      "step": 90
    },
    {
      "epoch": 0.08404244143292362,
      "grad_norm": 0.13012883067131042,
      "learning_rate": 0.0002,
      "loss": 0.5403,
      "step": 100
    },
    {
      "epoch": 0.09244668557621599,
      "grad_norm": 0.11942347884178162,
      "learning_rate": 0.00019942313239111625,
      "loss": 0.5247,
      "step": 110
    },
    {
      "epoch": 0.10085092971950835,
      "grad_norm": 0.11690942198038101,
      "learning_rate": 0.0001988462647822325,
      "loss": 0.5417,
      "step": 120
    },
    {
      "epoch": 0.10925517386280072,
      "grad_norm": 0.1355101615190506,
      "learning_rate": 0.00019826939717334873,
      "loss": 0.5273,
      "step": 130
    },
    {
      "epoch": 0.11765941800609307,
      "grad_norm": 0.1345665603876114,
      "learning_rate": 0.00019769252956446497,
      "loss": 0.5243,
      "step": 140
    },
    {
      "epoch": 0.12606366214938544,
      "grad_norm": 0.12515193223953247,
      "learning_rate": 0.0001971156619555812,
      "loss": 0.5344,
      "step": 150
    },
    {
      "epoch": 0.1344679062926778,
      "grad_norm": 0.15686553716659546,
      "learning_rate": 0.00019653879434669745,
      "loss": 0.5118,
      "step": 160
    },
    {
      "epoch": 0.14287215043597015,
      "grad_norm": 0.12068944424390793,
      "learning_rate": 0.0001959619267378137,
      "loss": 0.4979,
      "step": 170
    },
    {
      "epoch": 0.15127639457926254,
      "grad_norm": 0.13319459557533264,
      "learning_rate": 0.00019538505912892993,
      "loss": 0.503,
      "step": 180
    },
    {
      "epoch": 0.1596806387225549,
      "grad_norm": 0.11806949228048325,
      "learning_rate": 0.00019480819152004617,
      "loss": 0.49,
      "step": 190
    },
    {
      "epoch": 0.16808488286584725,
      "grad_norm": 0.12932075560092926,
      "learning_rate": 0.00019423132391116238,
      "loss": 0.514,
      "step": 200
    },
    {
      "epoch": 0.17648912700913963,
      "grad_norm": 0.11743929982185364,
      "learning_rate": 0.00019365445630227862,
      "loss": 0.4788,
      "step": 210
    },
    {
      "epoch": 0.18489337115243198,
      "grad_norm": 0.11788313835859299,
      "learning_rate": 0.00019307758869339486,
      "loss": 0.4891,
      "step": 220
    },
    {
      "epoch": 0.19329761529572434,
      "grad_norm": 0.11414741724729538,
      "learning_rate": 0.0001925007210845111,
      "loss": 0.5033,
      "step": 230
    },
    {
      "epoch": 0.2017018594390167,
      "grad_norm": 0.11419043689966202,
      "learning_rate": 0.00019192385347562737,
      "loss": 0.4844,
      "step": 240
    },
    {
      "epoch": 0.21010610358230908,
      "grad_norm": 0.12788020074367523,
      "learning_rate": 0.0001913469858667436,
      "loss": 0.4697,
      "step": 250
    },
    {
      "epoch": 0.21851034772560143,
      "grad_norm": 0.13661302626132965,
      "learning_rate": 0.00019077011825785982,
      "loss": 0.4627,
      "step": 260
    },
    {
      "epoch": 0.2269145918688938,
      "grad_norm": 0.12041325867176056,
      "learning_rate": 0.00019019325064897606,
      "loss": 0.4964,
      "step": 270
    },
    {
      "epoch": 0.23531883601218614,
      "grad_norm": 0.133742094039917,
      "learning_rate": 0.0001896163830400923,
      "loss": 0.4658,
      "step": 280
    },
    {
      "epoch": 0.24372308015547853,
      "grad_norm": 0.1261977106332779,
      "learning_rate": 0.00018903951543120854,
      "loss": 0.4781,
      "step": 290
    },
    {
      "epoch": 0.2521273242987709,
      "grad_norm": 0.130150705575943,
      "learning_rate": 0.00018846264782232478,
      "loss": 0.4922,
      "step": 300
    },
    {
      "epoch": 0.26053156844206327,
      "grad_norm": 0.13174410164356232,
      "learning_rate": 0.00018788578021344102,
      "loss": 0.4559,
      "step": 310
    },
    {
      "epoch": 0.2689358125853556,
      "grad_norm": 0.1186077669262886,
      "learning_rate": 0.00018730891260455726,
      "loss": 0.4722,
      "step": 320
    },
    {
      "epoch": 0.277340056728648,
      "grad_norm": 0.116569384932518,
      "learning_rate": 0.0001867320449956735,
      "loss": 0.4457,
      "step": 330
    },
    {
      "epoch": 0.2857443008719403,
      "grad_norm": 0.12219471484422684,
      "learning_rate": 0.00018615517738678974,
      "loss": 0.4849,
      "step": 340
    },
    {
      "epoch": 0.2941485450152327,
      "grad_norm": 0.12746909260749817,
      "learning_rate": 0.00018557830977790598,
      "loss": 0.4821,
      "step": 350
    },
    {
      "epoch": 0.30255278915852507,
      "grad_norm": 0.14125944674015045,
      "learning_rate": 0.00018500144216902222,
      "loss": 0.4605,
      "step": 360
    },
    {
      "epoch": 0.3109570333018174,
      "grad_norm": 0.19157269597053528,
      "learning_rate": 0.00018442457456013846,
      "loss": 0.4541,
      "step": 370
    },
    {
      "epoch": 0.3193612774451098,
      "grad_norm": 0.12603330612182617,
      "learning_rate": 0.0001838477069512547,
      "loss": 0.4536,
      "step": 380
    },
    {
      "epoch": 0.32776552158840216,
      "grad_norm": 0.12653909623622894,
      "learning_rate": 0.00018327083934237091,
      "loss": 0.4468,
      "step": 390
    },
    {
      "epoch": 0.3361697657316945,
      "grad_norm": 0.15930472314357758,
      "learning_rate": 0.00018269397173348718,
      "loss": 0.4542,
      "step": 400
    },
    {
      "epoch": 0.3445740098749869,
      "grad_norm": 0.13266988098621368,
      "learning_rate": 0.00018211710412460342,
      "loss": 0.4335,
      "step": 410
    },
    {
      "epoch": 0.35297825401827926,
      "grad_norm": 0.12103667855262756,
      "learning_rate": 0.00018154023651571966,
      "loss": 0.4575,
      "step": 420
    },
    {
      "epoch": 0.3613824981615716,
      "grad_norm": 0.14439740777015686,
      "learning_rate": 0.0001809633689068359,
      "loss": 0.4377,
      "step": 430
    },
    {
      "epoch": 0.36978674230486397,
      "grad_norm": 0.12652407586574554,
      "learning_rate": 0.00018038650129795214,
      "loss": 0.4363,
      "step": 440
    },
    {
      "epoch": 0.3781909864481563,
      "grad_norm": 0.14594405889511108,
      "learning_rate": 0.00017980963368906835,
      "loss": 0.4306,
      "step": 450
    },
    {
      "epoch": 0.3865952305914487,
      "grad_norm": 0.12562687695026398,
      "learning_rate": 0.0001792327660801846,
      "loss": 0.4501,
      "step": 460
    },
    {
      "epoch": 0.39499947473474106,
      "grad_norm": 0.14584492146968842,
      "learning_rate": 0.00017865589847130083,
      "loss": 0.4509,
      "step": 470
    },
    {
      "epoch": 0.4034037188780334,
      "grad_norm": 0.13192500174045563,
      "learning_rate": 0.00017807903086241707,
      "loss": 0.4505,
      "step": 480
    },
    {
      "epoch": 0.4118079630213258,
      "grad_norm": 0.14266645908355713,
      "learning_rate": 0.00017750216325353331,
      "loss": 0.4585,
      "step": 490
    },
    {
      "epoch": 0.42021220716461816,
      "grad_norm": 0.1400412619113922,
      "learning_rate": 0.00017692529564464958,
      "loss": 0.4365,
      "step": 500
    },
    {
      "epoch": 0.4286164513079105,
      "grad_norm": 0.14728468656539917,
      "learning_rate": 0.0001763484280357658,
      "loss": 0.4303,
      "step": 510
    },
    {
      "epoch": 0.43702069545120287,
      "grad_norm": 0.15791365504264832,
      "learning_rate": 0.00017577156042688203,
      "loss": 0.4407,
      "step": 520
    },
    {
      "epoch": 0.4454249395944952,
      "grad_norm": 0.15447258949279785,
      "learning_rate": 0.00017519469281799827,
      "loss": 0.4365,
      "step": 530
    },
    {
      "epoch": 0.4538291837377876,
      "grad_norm": 0.1518252044916153,
      "learning_rate": 0.00017461782520911451,
      "loss": 0.4305,
      "step": 540
    },
    {
      "epoch": 0.46223342788107996,
      "grad_norm": 0.1154065877199173,
      "learning_rate": 0.00017404095760023075,
      "loss": 0.4212,
      "step": 550
    },
    {
      "epoch": 0.4706376720243723,
      "grad_norm": 0.12900012731552124,
      "learning_rate": 0.000173464089991347,
      "loss": 0.4277,
      "step": 560
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 0.1349458247423172,
      "learning_rate": 0.00017288722238246323,
      "loss": 0.4051,
      "step": 570
    },
    {
      "epoch": 0.48744616031095706,
      "grad_norm": 0.16337165236473083,
      "learning_rate": 0.00017231035477357947,
      "loss": 0.407,
      "step": 580
    },
    {
      "epoch": 0.4958504044542494,
      "grad_norm": 0.13420593738555908,
      "learning_rate": 0.0001717334871646957,
      "loss": 0.4138,
      "step": 590
    },
    {
      "epoch": 0.5042546485975418,
      "grad_norm": 0.13840581476688385,
      "learning_rate": 0.00017115661955581195,
      "loss": 0.4099,
      "step": 600
    },
    {
      "epoch": 0.5126588927408341,
      "grad_norm": 0.1378021389245987,
      "learning_rate": 0.0001705797519469282,
      "loss": 0.4254,
      "step": 610
    },
    {
      "epoch": 0.5210631368841265,
      "grad_norm": 0.1607150137424469,
      "learning_rate": 0.00017000288433804443,
      "loss": 0.4353,
      "step": 620
    },
    {
      "epoch": 0.5294673810274189,
      "grad_norm": 0.13462169468402863,
      "learning_rate": 0.00016942601672916067,
      "loss": 0.4267,
      "step": 630
    },
    {
      "epoch": 0.5378716251707112,
      "grad_norm": 0.14311543107032776,
      "learning_rate": 0.00016884914912027689,
      "loss": 0.4301,
      "step": 640
    },
    {
      "epoch": 0.5462758693140036,
      "grad_norm": 0.15559442341327667,
      "learning_rate": 0.00016827228151139313,
      "loss": 0.4102,
      "step": 650
    },
    {
      "epoch": 0.554680113457296,
      "grad_norm": 0.15557149052619934,
      "learning_rate": 0.00016769541390250937,
      "loss": 0.4136,
      "step": 660
    },
    {
      "epoch": 0.5630843576005883,
      "grad_norm": 0.135511115193367,
      "learning_rate": 0.00016711854629362563,
      "loss": 0.4153,
      "step": 670
    },
    {
      "epoch": 0.5714886017438806,
      "grad_norm": 0.13760776817798615,
      "learning_rate": 0.00016654167868474187,
      "loss": 0.4145,
      "step": 680
    },
    {
      "epoch": 0.579892845887173,
      "grad_norm": 0.14971590042114258,
      "learning_rate": 0.0001659648110758581,
      "loss": 0.3875,
      "step": 690
    },
    {
      "epoch": 0.5882970900304654,
      "grad_norm": 0.16005663573741913,
      "learning_rate": 0.00016538794346697433,
      "loss": 0.3938,
      "step": 700
    },
    {
      "epoch": 0.5967013341737577,
      "grad_norm": 0.1625218689441681,
      "learning_rate": 0.00016481107585809057,
      "loss": 0.3871,
      "step": 710
    },
    {
      "epoch": 0.6051055783170501,
      "grad_norm": 0.17047689855098724,
      "learning_rate": 0.0001642342082492068,
      "loss": 0.412,
      "step": 720
    },
    {
      "epoch": 0.6135098224603425,
      "grad_norm": 0.13825903832912445,
      "learning_rate": 0.00016365734064032305,
      "loss": 0.3948,
      "step": 730
    },
    {
      "epoch": 0.6219140666036348,
      "grad_norm": 0.14830929040908813,
      "learning_rate": 0.00016308047303143929,
      "loss": 0.3927,
      "step": 740
    },
    {
      "epoch": 0.6303183107469272,
      "grad_norm": 0.13950933516025543,
      "learning_rate": 0.00016250360542255553,
      "loss": 0.4051,
      "step": 750
    },
    {
      "epoch": 0.6387225548902196,
      "grad_norm": 0.15511371195316315,
      "learning_rate": 0.0001619267378136718,
      "loss": 0.4041,
      "step": 760
    },
    {
      "epoch": 0.6471267990335119,
      "grad_norm": 0.14828190207481384,
      "learning_rate": 0.000161349870204788,
      "loss": 0.3824,
      "step": 770
    },
    {
      "epoch": 0.6555310431768043,
      "grad_norm": 0.144051194190979,
      "learning_rate": 0.00016077300259590425,
      "loss": 0.3829,
      "step": 780
    },
    {
      "epoch": 0.6639352873200967,
      "grad_norm": 0.14780694246292114,
      "learning_rate": 0.00016019613498702049,
      "loss": 0.3814,
      "step": 790
    },
    {
      "epoch": 0.672339531463389,
      "grad_norm": 0.15042325854301453,
      "learning_rate": 0.00015961926737813673,
      "loss": 0.3962,
      "step": 800
    },
    {
      "epoch": 0.6807437756066814,
      "grad_norm": 0.16325107216835022,
      "learning_rate": 0.00015904239976925297,
      "loss": 0.3801,
      "step": 810
    },
    {
      "epoch": 0.6891480197499738,
      "grad_norm": 0.14843328297138214,
      "learning_rate": 0.0001584655321603692,
      "loss": 0.4082,
      "step": 820
    },
    {
      "epoch": 0.6975522638932661,
      "grad_norm": 0.16731064021587372,
      "learning_rate": 0.00015788866455148545,
      "loss": 0.4192,
      "step": 830
    },
    {
      "epoch": 0.7059565080365585,
      "grad_norm": 0.18703435361385345,
      "learning_rate": 0.00015731179694260169,
      "loss": 0.4009,
      "step": 840
    },
    {
      "epoch": 0.7143607521798508,
      "grad_norm": 0.13935630023479462,
      "learning_rate": 0.00015673492933371793,
      "loss": 0.3618,
      "step": 850
    },
    {
      "epoch": 0.7227649963231432,
      "grad_norm": 0.13263636827468872,
      "learning_rate": 0.00015615806172483417,
      "loss": 0.3963,
      "step": 860
    },
    {
      "epoch": 0.7311692404664355,
      "grad_norm": 0.14940643310546875,
      "learning_rate": 0.0001555811941159504,
      "loss": 0.3585,
      "step": 870
    },
    {
      "epoch": 0.7395734846097279,
      "grad_norm": 0.14807912707328796,
      "learning_rate": 0.00015500432650706665,
      "loss": 0.3748,
      "step": 880
    },
    {
      "epoch": 0.7479777287530203,
      "grad_norm": 0.15254080295562744,
      "learning_rate": 0.00015442745889818286,
      "loss": 0.3718,
      "step": 890
    },
    {
      "epoch": 0.7563819728963126,
      "grad_norm": 0.16590768098831177,
      "learning_rate": 0.0001538505912892991,
      "loss": 0.386,
      "step": 900
    },
    {
      "epoch": 0.764786217039605,
      "grad_norm": 0.15733902156352997,
      "learning_rate": 0.00015327372368041534,
      "loss": 0.3756,
      "step": 910
    },
    {
      "epoch": 0.7731904611828974,
      "grad_norm": 0.13757385313510895,
      "learning_rate": 0.00015269685607153158,
      "loss": 0.3843,
      "step": 920
    },
    {
      "epoch": 0.7815947053261897,
      "grad_norm": 0.14952607452869415,
      "learning_rate": 0.00015211998846264784,
      "loss": 0.3634,
      "step": 930
    },
    {
      "epoch": 0.7899989494694821,
      "grad_norm": 0.1516282558441162,
      "learning_rate": 0.00015154312085376408,
      "loss": 0.3798,
      "step": 940
    },
    {
      "epoch": 0.7984031936127745,
      "grad_norm": 0.17785628139972687,
      "learning_rate": 0.00015096625324488032,
      "loss": 0.3681,
      "step": 950
    },
    {
      "epoch": 0.8068074377560668,
      "grad_norm": 0.171351820230484,
      "learning_rate": 0.00015038938563599654,
      "loss": 0.3686,
      "step": 960
    },
    {
      "epoch": 0.8152116818993592,
      "grad_norm": 0.1742231398820877,
      "learning_rate": 0.00014981251802711278,
      "loss": 0.3792,
      "step": 970
    },
    {
      "epoch": 0.8236159260426515,
      "grad_norm": 0.16650599241256714,
      "learning_rate": 0.00014923565041822902,
      "loss": 0.3577,
      "step": 980
    },
    {
      "epoch": 0.8320201701859439,
      "grad_norm": 0.1497887670993805,
      "learning_rate": 0.00014865878280934526,
      "loss": 0.3553,
      "step": 990
    },
    {
      "epoch": 0.8404244143292363,
      "grad_norm": 0.14781557023525238,
      "learning_rate": 0.0001480819152004615,
      "loss": 0.3538,
      "step": 1000
    },
    {
      "epoch": 0.8488286584725286,
      "grad_norm": 0.15724751353263855,
      "learning_rate": 0.00014750504759157774,
      "loss": 0.3597,
      "step": 1010
    },
    {
      "epoch": 0.857232902615821,
      "grad_norm": 0.18635571002960205,
      "learning_rate": 0.00014692817998269398,
      "loss": 0.3615,
      "step": 1020
    },
    {
      "epoch": 0.8656371467591134,
      "grad_norm": 0.17742526531219482,
      "learning_rate": 0.00014635131237381022,
      "loss": 0.348,
      "step": 1030
    },
    {
      "epoch": 0.8740413909024057,
      "grad_norm": 0.20535768568515778,
      "learning_rate": 0.00014577444476492646,
      "loss": 0.3343,
      "step": 1040
    },
    {
      "epoch": 0.8824456350456981,
      "grad_norm": 0.18968522548675537,
      "learning_rate": 0.0001451975771560427,
      "loss": 0.3615,
      "step": 1050
    },
    {
      "epoch": 0.8908498791889904,
      "grad_norm": 0.1528492122888565,
      "learning_rate": 0.00014462070954715894,
      "loss": 0.3786,
      "step": 1060
    },
    {
      "epoch": 0.8992541233322828,
      "grad_norm": 0.15841075778007507,
      "learning_rate": 0.00014404384193827518,
      "loss": 0.3761,
      "step": 1070
    },
    {
      "epoch": 0.9076583674755752,
      "grad_norm": 0.15167982876300812,
      "learning_rate": 0.0001434669743293914,
      "loss": 0.3528,
      "step": 1080
    },
    {
      "epoch": 0.9160626116188675,
      "grad_norm": 0.14096671342849731,
      "learning_rate": 0.00014289010672050766,
      "loss": 0.371,
      "step": 1090
    },
    {
      "epoch": 0.9244668557621599,
      "grad_norm": 0.1579194813966751,
      "learning_rate": 0.0001423132391116239,
      "loss": 0.3491,
      "step": 1100
    },
    {
      "epoch": 0.9328710999054523,
      "grad_norm": 0.16789057850837708,
      "learning_rate": 0.00014173637150274014,
      "loss": 0.3536,
      "step": 1110
    },
    {
      "epoch": 0.9412753440487446,
      "grad_norm": 0.13980717957019806,
      "learning_rate": 0.00014115950389385638,
      "loss": 0.3423,
      "step": 1120
    },
    {
      "epoch": 0.949679588192037,
      "grad_norm": 0.19879643619060516,
      "learning_rate": 0.00014058263628497262,
      "loss": 0.3285,
      "step": 1130
    },
    {
      "epoch": 0.9580838323353293,
      "grad_norm": 0.16574440896511078,
      "learning_rate": 0.00014000576867608886,
      "loss": 0.3568,
      "step": 1140
    },
    {
      "epoch": 0.9664880764786217,
      "grad_norm": 0.15376180410385132,
      "learning_rate": 0.00013942890106720507,
      "loss": 0.3558,
      "step": 1150
    },
    {
      "epoch": 0.9748923206219141,
      "grad_norm": 0.17232170701026917,
      "learning_rate": 0.0001388520334583213,
      "loss": 0.342,
      "step": 1160
    },
    {
      "epoch": 0.9832965647652064,
      "grad_norm": 0.1959993690252304,
      "learning_rate": 0.00013827516584943755,
      "loss": 0.3458,
      "step": 1170
    },
    {
      "epoch": 0.9917008089084988,
      "grad_norm": 0.14029347896575928,
      "learning_rate": 0.0001376982982405538,
      "loss": 0.3297,
      "step": 1180
    }
  ],
  "logging_steps": 10,
  "max_steps": 3567,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.069523410383258e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}