{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02603918028660458,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002603918028660458,
      "grad_norm": 0.4500846266746521,
      "learning_rate": 5.194805194805195e-06,
      "loss": 1.0381,
      "step": 10
    },
    {
      "epoch": 0.0005207836057320916,
      "grad_norm": 0.35188010334968567,
      "learning_rate": 1.038961038961039e-05,
      "loss": 1.0108,
      "step": 20
    },
    {
      "epoch": 0.0007811754085981374,
      "grad_norm": 0.2300374060869217,
      "learning_rate": 1.5584415584415583e-05,
      "loss": 0.9668,
      "step": 30
    },
    {
      "epoch": 0.0010415672114641832,
      "grad_norm": 0.16189467906951904,
      "learning_rate": 2.077922077922078e-05,
      "loss": 0.918,
      "step": 40
    },
    {
      "epoch": 0.001301959014330229,
      "grad_norm": 0.18843211233615875,
      "learning_rate": 2.5974025974025972e-05,
      "loss": 0.9265,
      "step": 50
    },
    {
      "epoch": 0.0015623508171962747,
      "grad_norm": 0.20334510505199432,
      "learning_rate": 3.1168831168831166e-05,
      "loss": 0.9234,
      "step": 60
    },
    {
      "epoch": 0.0018227426200623205,
      "grad_norm": 0.1745327115058899,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.881,
      "step": 70
    },
    {
      "epoch": 0.0020831344229283663,
      "grad_norm": 0.18667331337928772,
      "learning_rate": 4.155844155844156e-05,
      "loss": 0.8592,
      "step": 80
    },
    {
      "epoch": 0.002343526225794412,
      "grad_norm": 0.1848158985376358,
      "learning_rate": 4.675324675324675e-05,
      "loss": 0.8537,
      "step": 90
    },
    {
      "epoch": 0.002603918028660458,
      "grad_norm": 0.17589879035949707,
      "learning_rate": 5.1948051948051944e-05,
      "loss": 0.8518,
      "step": 100
    },
    {
      "epoch": 0.0028643098315265037,
      "grad_norm": 0.2132624089717865,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.8511,
      "step": 110
    },
    {
      "epoch": 0.0031247016343925495,
      "grad_norm": 0.23070092499256134,
      "learning_rate": 6.233766233766233e-05,
      "loss": 0.7975,
      "step": 120
    },
    {
      "epoch": 0.0033850934372585953,
      "grad_norm": 0.25368157029151917,
      "learning_rate": 6.753246753246754e-05,
      "loss": 0.8134,
      "step": 130
    },
    {
      "epoch": 0.003645485240124641,
      "grad_norm": 0.22897231578826904,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.8322,
      "step": 140
    },
    {
      "epoch": 0.003905877042990687,
      "grad_norm": 0.19932536780834198,
      "learning_rate": 7.792207792207793e-05,
      "loss": 0.7959,
      "step": 150
    },
    {
      "epoch": 0.004166268845856733,
      "grad_norm": 0.21011792123317719,
      "learning_rate": 8.311688311688312e-05,
      "loss": 0.8102,
      "step": 160
    },
    {
      "epoch": 0.004426660648722778,
      "grad_norm": 0.20594824850559235,
      "learning_rate": 8.831168831168831e-05,
      "loss": 0.8128,
      "step": 170
    },
    {
      "epoch": 0.004687052451588824,
      "grad_norm": 0.20465536415576935,
      "learning_rate": 9.35064935064935e-05,
      "loss": 0.7989,
      "step": 180
    },
    {
      "epoch": 0.00494744425445487,
      "grad_norm": 0.4109392762184143,
      "learning_rate": 9.870129870129871e-05,
      "loss": 0.8108,
      "step": 190
    },
    {
      "epoch": 0.005207836057320916,
      "grad_norm": 0.4293076694011688,
      "learning_rate": 0.00010389610389610389,
      "loss": 0.8101,
      "step": 200
    },
    {
      "epoch": 0.005468227860186962,
      "grad_norm": 0.31628963351249695,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.7989,
      "step": 210
    },
    {
      "epoch": 0.005728619663053007,
      "grad_norm": 0.24642810225486755,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.7751,
      "step": 220
    },
    {
      "epoch": 0.005989011465919053,
      "grad_norm": 0.3599106967449188,
      "learning_rate": 0.00011948051948051949,
      "loss": 0.8063,
      "step": 230
    },
    {
      "epoch": 0.006249403268785099,
      "grad_norm": 0.17053447663784027,
      "learning_rate": 0.00012467532467532467,
      "loss": 0.7751,
      "step": 240
    },
    {
      "epoch": 0.006509795071651145,
      "grad_norm": 0.17303769290447235,
      "learning_rate": 0.00012987012987012987,
      "loss": 0.7883,
      "step": 250
    },
    {
      "epoch": 0.0067701868745171905,
      "grad_norm": 0.1815861016511917,
      "learning_rate": 0.00013506493506493507,
      "loss": 0.788,
      "step": 260
    },
    {
      "epoch": 0.007030578677383236,
      "grad_norm": 0.24125365912914276,
      "learning_rate": 0.00014025974025974028,
      "loss": 0.8018,
      "step": 270
    },
    {
      "epoch": 0.007290970480249282,
      "grad_norm": 0.19443446397781372,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.7908,
      "step": 280
    },
    {
      "epoch": 0.007551362283115328,
      "grad_norm": 0.17829768359661102,
      "learning_rate": 0.00015064935064935066,
      "loss": 0.8033,
      "step": 290
    },
    {
      "epoch": 0.007811754085981374,
      "grad_norm": 0.19535653293132782,
      "learning_rate": 0.00015584415584415587,
      "loss": 0.7997,
      "step": 300
    },
    {
      "epoch": 0.008072145888847419,
      "grad_norm": 0.19930541515350342,
      "learning_rate": 0.00016103896103896104,
      "loss": 0.7945,
      "step": 310
    },
    {
      "epoch": 0.008332537691713465,
      "grad_norm": 0.2156297266483307,
      "learning_rate": 0.00016623376623376625,
      "loss": 0.8018,
      "step": 320
    },
    {
      "epoch": 0.00859292949457951,
      "grad_norm": 0.1924206018447876,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.7746,
      "step": 330
    },
    {
      "epoch": 0.008853321297445557,
      "grad_norm": 0.2294880747795105,
      "learning_rate": 0.00017662337662337663,
      "loss": 0.8152,
      "step": 340
    },
    {
      "epoch": 0.009113713100311602,
      "grad_norm": 0.16817067563533783,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7972,
      "step": 350
    },
    {
      "epoch": 0.009374104903177648,
      "grad_norm": 0.18544812500476837,
      "learning_rate": 0.000187012987012987,
      "loss": 0.7801,
      "step": 360
    },
    {
      "epoch": 0.009634496706043693,
      "grad_norm": 0.19597066938877106,
      "learning_rate": 0.00019220779220779222,
      "loss": 0.7706,
      "step": 370
    },
    {
      "epoch": 0.00989488850890974,
      "grad_norm": 0.40291881561279297,
      "learning_rate": 0.00019740259740259742,
      "loss": 0.7911,
      "step": 380
    },
    {
      "epoch": 0.010155280311775785,
      "grad_norm": 0.23841074109077454,
      "learning_rate": 0.00019999996515752773,
      "loss": 0.7861,
      "step": 390
    },
    {
      "epoch": 0.010415672114641832,
      "grad_norm": 0.1675388514995575,
      "learning_rate": 0.00019999968641789507,
      "loss": 0.788,
      "step": 400
    },
    {
      "epoch": 0.010676063917507876,
      "grad_norm": 1.8860758543014526,
      "learning_rate": 0.0001999991289394067,
      "loss": 0.7632,
      "step": 410
    },
    {
      "epoch": 0.010936455720373923,
      "grad_norm": 0.17022117972373962,
      "learning_rate": 0.00019999829272361654,
      "loss": 0.784,
      "step": 420
    },
    {
      "epoch": 0.011196847523239968,
      "grad_norm": 0.21460269391536713,
      "learning_rate": 0.00019999717777285545,
      "loss": 0.761,
      "step": 430
    },
    {
      "epoch": 0.011457239326106015,
      "grad_norm": 0.19413785636425018,
      "learning_rate": 0.00019999578409023126,
      "loss": 0.7772,
      "step": 440
    },
    {
      "epoch": 0.01171763112897206,
      "grad_norm": 0.20223405957221985,
      "learning_rate": 0.00019999411167962868,
      "loss": 0.7811,
      "step": 450
    },
    {
      "epoch": 0.011978022931838106,
      "grad_norm": 0.15166303515434265,
      "learning_rate": 0.00019999216054570942,
      "loss": 0.7709,
      "step": 460
    },
    {
      "epoch": 0.012238414734704151,
      "grad_norm": 0.16307081282138824,
      "learning_rate": 0.00019998993069391205,
      "loss": 0.7811,
      "step": 470
    },
    {
      "epoch": 0.012498806537570198,
      "grad_norm": 0.15996049344539642,
      "learning_rate": 0.00019998742213045206,
      "loss": 0.7599,
      "step": 480
    },
    {
      "epoch": 0.012759198340436243,
      "grad_norm": 0.17560279369354248,
      "learning_rate": 0.00019998463486232179,
      "loss": 0.7572,
      "step": 490
    },
    {
      "epoch": 0.01301959014330229,
      "grad_norm": 0.17571642994880676,
      "learning_rate": 0.0001999815688972905,
      "loss": 0.7643,
      "step": 500
    },
    {
      "epoch": 0.013279981946168334,
      "grad_norm": 0.17719799280166626,
      "learning_rate": 0.00019997822424390422,
      "loss": 0.7923,
      "step": 510
    },
    {
      "epoch": 0.013540373749034381,
      "grad_norm": 0.19846616685390472,
      "learning_rate": 0.00019997460091148586,
      "loss": 0.7674,
      "step": 520
    },
    {
      "epoch": 0.013800765551900426,
      "grad_norm": 0.2715558111667633,
      "learning_rate": 0.00019997069891013503,
      "loss": 0.7421,
      "step": 530
    },
    {
      "epoch": 0.014061157354766473,
      "grad_norm": 0.1725197583436966,
      "learning_rate": 0.00019996651825072826,
      "loss": 0.7663,
      "step": 540
    },
    {
      "epoch": 0.014321549157632518,
      "grad_norm": 0.15060502290725708,
      "learning_rate": 0.00019996205894491856,
      "loss": 0.7794,
      "step": 550
    },
    {
      "epoch": 0.014581940960498564,
      "grad_norm": 0.16645808517932892,
      "learning_rate": 0.00019995732100513592,
      "loss": 0.752,
      "step": 560
    },
    {
      "epoch": 0.014842332763364609,
      "grad_norm": 0.1736789345741272,
      "learning_rate": 0.00019995230444458682,
      "loss": 0.7788,
      "step": 570
    },
    {
      "epoch": 0.015102724566230656,
      "grad_norm": 0.15416319668293,
      "learning_rate": 0.0001999470092772544,
      "loss": 0.7656,
      "step": 580
    },
    {
      "epoch": 0.0153631163690967,
      "grad_norm": 0.16610187292099,
      "learning_rate": 0.00019994143551789839,
      "loss": 0.7676,
      "step": 590
    },
    {
      "epoch": 0.015623508171962747,
      "grad_norm": 0.15843011438846588,
      "learning_rate": 0.00019993558318205507,
      "loss": 0.7746,
      "step": 600
    },
    {
      "epoch": 0.015883899974828794,
      "grad_norm": 0.26837801933288574,
      "learning_rate": 0.00019992945228603724,
      "loss": 0.7617,
      "step": 610
    },
    {
      "epoch": 0.016144291777694837,
      "grad_norm": 0.15099173784255981,
      "learning_rate": 0.0001999230428469341,
      "loss": 0.7601,
      "step": 620
    },
    {
      "epoch": 0.016404683580560884,
      "grad_norm": 0.15511856973171234,
      "learning_rate": 0.00019991635488261138,
      "loss": 0.7647,
      "step": 630
    },
    {
      "epoch": 0.01666507538342693,
      "grad_norm": 0.14919579029083252,
      "learning_rate": 0.00019990938841171104,
      "loss": 0.7692,
      "step": 640
    },
    {
      "epoch": 0.016925467186292977,
      "grad_norm": 0.15838642418384552,
      "learning_rate": 0.0001999021434536514,
      "loss": 0.7763,
      "step": 650
    },
    {
      "epoch": 0.01718585898915902,
      "grad_norm": 0.15956635773181915,
      "learning_rate": 0.00019989462002862704,
      "loss": 0.7598,
      "step": 660
    },
    {
      "epoch": 0.017446250792025067,
      "grad_norm": 0.1499069333076477,
      "learning_rate": 0.0001998868181576088,
      "loss": 0.7626,
      "step": 670
    },
    {
      "epoch": 0.017706642594891114,
      "grad_norm": 0.2170073390007019,
      "learning_rate": 0.00019987873786234348,
      "loss": 0.7569,
      "step": 680
    },
    {
      "epoch": 0.01796703439775716,
      "grad_norm": 0.17841948568820953,
      "learning_rate": 0.00019987037916535417,
      "loss": 0.7494,
      "step": 690
    },
    {
      "epoch": 0.018227426200623204,
      "grad_norm": 0.2066909372806549,
      "learning_rate": 0.0001998617420899398,
      "loss": 0.7609,
      "step": 700
    },
    {
      "epoch": 0.01848781800348925,
      "grad_norm": 0.17015361785888672,
      "learning_rate": 0.0001998528266601754,
      "loss": 0.7761,
      "step": 710
    },
    {
      "epoch": 0.018748209806355297,
      "grad_norm": 0.22166290879249573,
      "learning_rate": 0.0001998436329009118,
      "loss": 0.7573,
      "step": 720
    },
    {
      "epoch": 0.01900860160922134,
      "grad_norm": 0.15084640681743622,
      "learning_rate": 0.00019983416083777563,
      "loss": 0.7775,
      "step": 730
    },
    {
      "epoch": 0.019268993412087387,
      "grad_norm": 0.17800921201705933,
      "learning_rate": 0.0001998244104971693,
      "loss": 0.7359,
      "step": 740
    },
    {
      "epoch": 0.019529385214953433,
      "grad_norm": 0.17354707419872284,
      "learning_rate": 0.0001998143819062709,
      "loss": 0.7415,
      "step": 750
    },
    {
      "epoch": 0.01978977701781948,
      "grad_norm": 0.16408118605613708,
      "learning_rate": 0.00019980407509303413,
      "loss": 0.7708,
      "step": 760
    },
    {
      "epoch": 0.020050168820685523,
      "grad_norm": 0.16820089519023895,
      "learning_rate": 0.00019979349008618808,
      "loss": 0.791,
      "step": 770
    },
    {
      "epoch": 0.02031056062355157,
      "grad_norm": 0.15958388149738312,
      "learning_rate": 0.00019978262691523743,
      "loss": 0.7412,
      "step": 780
    },
    {
      "epoch": 0.020570952426417616,
      "grad_norm": 0.1646542251110077,
      "learning_rate": 0.00019977148561046217,
      "loss": 0.7529,
      "step": 790
    },
    {
      "epoch": 0.020831344229283663,
      "grad_norm": 0.17032025754451752,
      "learning_rate": 0.0001997600662029175,
      "loss": 0.7656,
      "step": 800
    },
    {
      "epoch": 0.021091736032149706,
      "grad_norm": 0.17189227044582367,
      "learning_rate": 0.00019974836872443388,
      "loss": 0.7433,
      "step": 810
    },
    {
      "epoch": 0.021352127835015753,
      "grad_norm": 0.16334249079227448,
      "learning_rate": 0.0001997363932076168,
      "loss": 0.7703,
      "step": 820
    },
    {
      "epoch": 0.0216125196378818,
      "grad_norm": 0.1676424890756607,
      "learning_rate": 0.00019972413968584682,
      "loss": 0.7603,
      "step": 830
    },
    {
      "epoch": 0.021872911440747846,
      "grad_norm": 0.16826209425926208,
      "learning_rate": 0.0001997116081932793,
      "loss": 0.7569,
      "step": 840
    },
    {
      "epoch": 0.02213330324361389,
      "grad_norm": 0.1876436173915863,
      "learning_rate": 0.0001996987987648446,
      "loss": 0.7553,
      "step": 850
    },
    {
      "epoch": 0.022393695046479936,
      "grad_norm": 0.17252250015735626,
      "learning_rate": 0.0001996857114362476,
      "loss": 0.7644,
      "step": 860
    },
    {
      "epoch": 0.022654086849345983,
      "grad_norm": 0.1632252335548401,
      "learning_rate": 0.00019967234624396793,
      "loss": 0.7568,
      "step": 870
    },
    {
      "epoch": 0.02291447865221203,
      "grad_norm": 0.1818259060382843,
      "learning_rate": 0.00019965870322525965,
      "loss": 0.7672,
      "step": 880
    },
    {
      "epoch": 0.023174870455078073,
      "grad_norm": 0.15418195724487305,
      "learning_rate": 0.0001996447824181513,
      "loss": 0.7642,
      "step": 890
    },
    {
      "epoch": 0.02343526225794412,
      "grad_norm": 0.17383505403995514,
      "learning_rate": 0.0001996305838614457,
      "loss": 0.7607,
      "step": 900
    },
    {
      "epoch": 0.023695654060810166,
      "grad_norm": 0.17794272303581238,
      "learning_rate": 0.00019961610759471984,
      "loss": 0.7588,
      "step": 910
    },
    {
      "epoch": 0.023956045863676213,
      "grad_norm": 0.1909121572971344,
      "learning_rate": 0.00019960135365832486,
      "loss": 0.7438,
      "step": 920
    },
    {
      "epoch": 0.024216437666542256,
      "grad_norm": 0.17758873105049133,
      "learning_rate": 0.00019958632209338587,
      "loss": 0.7323,
      "step": 930
    },
    {
      "epoch": 0.024476829469408302,
      "grad_norm": 0.15553662180900574,
      "learning_rate": 0.00019957101294180174,
      "loss": 0.7508,
      "step": 940
    },
    {
      "epoch": 0.02473722127227435,
      "grad_norm": 0.15310749411582947,
      "learning_rate": 0.00019955542624624522,
      "loss": 0.7563,
      "step": 950
    },
    {
      "epoch": 0.024997613075140396,
      "grad_norm": 0.1628728210926056,
      "learning_rate": 0.00019953956205016256,
      "loss": 0.7524,
      "step": 960
    },
    {
      "epoch": 0.02525800487800644,
      "grad_norm": 0.16211454570293427,
      "learning_rate": 0.00019952342039777362,
      "loss": 0.7564,
      "step": 970
    },
    {
      "epoch": 0.025518396680872486,
      "grad_norm": 0.15663012862205505,
      "learning_rate": 0.00019950700133407163,
      "loss": 0.7395,
      "step": 980
    },
    {
      "epoch": 0.025778788483738532,
      "grad_norm": 0.1684863567352295,
      "learning_rate": 0.00019949030490482296,
      "loss": 0.753,
      "step": 990
    },
    {
      "epoch": 0.02603918028660458,
      "grad_norm": 0.1561436653137207,
      "learning_rate": 0.0001994733311565673,
      "loss": 0.7409,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 19202,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 4.6916733763584e+17,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}