{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.26625840378086935,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005325168075617386,
      "grad_norm": 1.179490566253662,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.7552515983581543,
      "step": 10
    },
    {
      "epoch": 0.010650336151234773,
      "grad_norm": 0.7021263837814331,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.7758663654327392,
      "step": 20
    },
    {
      "epoch": 0.01597550422685216,
      "grad_norm": 0.6242384314537048,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.620504903793335,
      "step": 30
    },
    {
      "epoch": 0.021300672302469546,
      "grad_norm": 0.4310513138771057,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.6261196613311768,
      "step": 40
    },
    {
      "epoch": 0.026625840378086935,
      "grad_norm": 0.5022103786468506,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.6593732833862305,
      "step": 50
    },
    {
      "epoch": 0.03195100845370432,
      "grad_norm": 0.6999115943908691,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.687755012512207,
      "step": 60
    },
    {
      "epoch": 0.037276176529321706,
      "grad_norm": 0.4458341598510742,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.6062395572662354,
      "step": 70
    },
    {
      "epoch": 0.04260134460493909,
      "grad_norm": 0.5636934638023376,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 0.6789586544036865,
      "step": 80
    },
    {
      "epoch": 0.04792651268055648,
      "grad_norm": 0.47693607211112976,
      "learning_rate": 4.734042553191489e-05,
      "loss": 0.5777320384979248,
      "step": 90
    },
    {
      "epoch": 0.05325168075617387,
      "grad_norm": 0.5000275373458862,
      "learning_rate": 4.985986547085202e-05,
      "loss": 0.5979567527770996,
      "step": 100
    },
    {
      "epoch": 0.058576848831791255,
      "grad_norm": 0.7978994250297546,
      "learning_rate": 4.9579596412556055e-05,
      "loss": 0.5918041229248047,
      "step": 110
    },
    {
      "epoch": 0.06390201690740864,
      "grad_norm": 0.6180557012557983,
      "learning_rate": 4.9299327354260097e-05,
      "loss": 0.6245941162109375,
      "step": 120
    },
    {
      "epoch": 0.06922718498302603,
      "grad_norm": 0.8771600723266602,
      "learning_rate": 4.9019058295964125e-05,
      "loss": 0.5516412258148193,
      "step": 130
    },
    {
      "epoch": 0.07455235305864341,
      "grad_norm": 0.570806622505188,
      "learning_rate": 4.8738789237668166e-05,
      "loss": 0.6044556140899658,
      "step": 140
    },
    {
      "epoch": 0.0798775211342608,
      "grad_norm": 0.5548396110534668,
      "learning_rate": 4.84585201793722e-05,
      "loss": 0.5861228466033935,
      "step": 150
    },
    {
      "epoch": 0.08520268920987818,
      "grad_norm": 0.3578498661518097,
      "learning_rate": 4.8178251121076236e-05,
      "loss": 0.5874335289001464,
      "step": 160
    },
    {
      "epoch": 0.09052785728549557,
      "grad_norm": 0.6209887266159058,
      "learning_rate": 4.789798206278027e-05,
      "loss": 0.5836649894714355,
      "step": 170
    },
    {
      "epoch": 0.09585302536111295,
      "grad_norm": 0.5073224902153015,
      "learning_rate": 4.7617713004484306e-05,
      "loss": 0.5651541233062745,
      "step": 180
    },
    {
      "epoch": 0.10117819343673035,
      "grad_norm": 0.5013888478279114,
      "learning_rate": 4.733744394618834e-05,
      "loss": 0.5798611164093017,
      "step": 190
    },
    {
      "epoch": 0.10650336151234774,
      "grad_norm": 0.2958514094352722,
      "learning_rate": 4.705717488789238e-05,
      "loss": 0.5263164520263672,
      "step": 200
    },
    {
      "epoch": 0.11182852958796512,
      "grad_norm": 0.5098234415054321,
      "learning_rate": 4.677690582959641e-05,
      "loss": 0.6066572189331054,
      "step": 210
    },
    {
      "epoch": 0.11715369766358251,
      "grad_norm": 0.68392413854599,
      "learning_rate": 4.649663677130045e-05,
      "loss": 0.501525592803955,
      "step": 220
    },
    {
      "epoch": 0.12247886573919989,
      "grad_norm": 0.5342642068862915,
      "learning_rate": 4.621636771300449e-05,
      "loss": 0.5538065910339356,
      "step": 230
    },
    {
      "epoch": 0.12780403381481728,
      "grad_norm": 0.46322742104530334,
      "learning_rate": 4.593609865470852e-05,
      "loss": 0.6028264999389649,
      "step": 240
    },
    {
      "epoch": 0.13312920189043467,
      "grad_norm": 0.5507689714431763,
      "learning_rate": 4.565582959641256e-05,
      "loss": 0.524617338180542,
      "step": 250
    },
    {
      "epoch": 0.13845436996605207,
      "grad_norm": 0.5451244711875916,
      "learning_rate": 4.537556053811659e-05,
      "loss": 0.5184399604797363,
      "step": 260
    },
    {
      "epoch": 0.14377953804166943,
      "grad_norm": 0.4679802656173706,
      "learning_rate": 4.509529147982063e-05,
      "loss": 0.5906213760375977,
      "step": 270
    },
    {
      "epoch": 0.14910470611728682,
      "grad_norm": 0.4486578702926636,
      "learning_rate": 4.481502242152467e-05,
      "loss": 0.5088740348815918,
      "step": 280
    },
    {
      "epoch": 0.15442987419290422,
      "grad_norm": 0.3085339665412903,
      "learning_rate": 4.4534753363228704e-05,
      "loss": 0.5231688499450684,
      "step": 290
    },
    {
      "epoch": 0.1597550422685216,
      "grad_norm": 0.8423092365264893,
      "learning_rate": 4.425448430493274e-05,
      "loss": 0.5785892963409424,
      "step": 300
    },
    {
      "epoch": 0.165080210344139,
      "grad_norm": 0.8173497319221497,
      "learning_rate": 4.3974215246636774e-05,
      "loss": 0.5546716690063477,
      "step": 310
    },
    {
      "epoch": 0.17040537841975636,
      "grad_norm": 0.4842700958251953,
      "learning_rate": 4.369394618834081e-05,
      "loss": 0.5258895874023437,
      "step": 320
    },
    {
      "epoch": 0.17573054649537376,
      "grad_norm": 0.645687460899353,
      "learning_rate": 4.3413677130044844e-05,
      "loss": 0.5903552532196045,
      "step": 330
    },
    {
      "epoch": 0.18105571457099115,
      "grad_norm": 0.5248221755027771,
      "learning_rate": 4.313340807174888e-05,
      "loss": 0.5313117027282714,
      "step": 340
    },
    {
      "epoch": 0.18638088264660854,
      "grad_norm": 0.4039202928543091,
      "learning_rate": 4.2853139013452914e-05,
      "loss": 0.5434175491333008,
      "step": 350
    },
    {
      "epoch": 0.1917060507222259,
      "grad_norm": 0.6575778126716614,
      "learning_rate": 4.257286995515695e-05,
      "loss": 0.5336236476898193,
      "step": 360
    },
    {
      "epoch": 0.1970312187978433,
      "grad_norm": 0.6030762791633606,
      "learning_rate": 4.229260089686099e-05,
      "loss": 0.5873087406158447,
      "step": 370
    },
    {
      "epoch": 0.2023563868734607,
      "grad_norm": 0.36645743250846863,
      "learning_rate": 4.201233183856502e-05,
      "loss": 0.44643635749816896,
      "step": 380
    },
    {
      "epoch": 0.20768155494907808,
      "grad_norm": 0.38583752512931824,
      "learning_rate": 4.173206278026906e-05,
      "loss": 0.48238911628723147,
      "step": 390
    },
    {
      "epoch": 0.21300672302469548,
      "grad_norm": 0.3569328486919403,
      "learning_rate": 4.1451793721973096e-05,
      "loss": 0.5249658107757569,
      "step": 400
    },
    {
      "epoch": 0.21833189110031284,
      "grad_norm": 0.5705183744430542,
      "learning_rate": 4.117152466367713e-05,
      "loss": 0.5840038299560547,
      "step": 410
    },
    {
      "epoch": 0.22365705917593023,
      "grad_norm": 0.5844929218292236,
      "learning_rate": 4.0891255605381166e-05,
      "loss": 0.49370269775390624,
      "step": 420
    },
    {
      "epoch": 0.22898222725154763,
      "grad_norm": 0.4003148376941681,
      "learning_rate": 4.061098654708521e-05,
      "loss": 0.5035266876220703,
      "step": 430
    },
    {
      "epoch": 0.23430739532716502,
      "grad_norm": 0.4637913405895233,
      "learning_rate": 4.0330717488789236e-05,
      "loss": 0.4923057556152344,
      "step": 440
    },
    {
      "epoch": 0.2396325634027824,
      "grad_norm": 0.41266828775405884,
      "learning_rate": 4.005044843049328e-05,
      "loss": 0.48969035148620604,
      "step": 450
    },
    {
      "epoch": 0.24495773147839978,
      "grad_norm": 0.6229465007781982,
      "learning_rate": 3.977017937219731e-05,
      "loss": 0.5537493228912354,
      "step": 460
    },
    {
      "epoch": 0.25028289955401717,
      "grad_norm": 0.3518058657646179,
      "learning_rate": 3.948991031390135e-05,
      "loss": 0.5104994297027587,
      "step": 470
    },
    {
      "epoch": 0.25560806762963456,
      "grad_norm": 0.3331281840801239,
      "learning_rate": 3.920964125560538e-05,
      "loss": 0.48421249389648435,
      "step": 480
    },
    {
      "epoch": 0.26093323570525195,
      "grad_norm": 0.6162995100021362,
      "learning_rate": 3.8929372197309424e-05,
      "loss": 0.5097816944122314,
      "step": 490
    },
    {
      "epoch": 0.26625840378086935,
      "grad_norm": 0.7575991153717041,
      "learning_rate": 3.864910313901345e-05,
      "loss": 0.538728666305542,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1878,
  "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": 2.087945270656128e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}