{
  "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": 0.12182320654392242,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.6409461498260498,
      "step": 10
    },
    {
      "epoch": 0.010650336151234773,
      "grad_norm": 0.1363009512424469,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.6779457092285156,
      "step": 20
    },
    {
      "epoch": 0.01597550422685216,
      "grad_norm": 0.16375352442264557,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.5765519142150879,
      "step": 30
    },
    {
      "epoch": 0.021300672302469546,
      "grad_norm": 0.1207907497882843,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.6171613216400147,
      "step": 40
    },
    {
      "epoch": 0.026625840378086935,
      "grad_norm": 0.17915089428424835,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.6188801288604736,
      "step": 50
    },
    {
      "epoch": 0.03195100845370432,
      "grad_norm": 0.2441256046295166,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.6470537662506104,
      "step": 60
    },
    {
      "epoch": 0.037276176529321706,
      "grad_norm": 0.2620764672756195,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.5195772647857666,
      "step": 70
    },
    {
      "epoch": 0.04260134460493909,
      "grad_norm": 0.2821812033653259,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 0.6430625438690185,
      "step": 80
    },
    {
      "epoch": 0.04792651268055648,
      "grad_norm": 0.36121875047683716,
      "learning_rate": 4.734042553191489e-05,
      "loss": 0.525498342514038,
      "step": 90
    },
    {
      "epoch": 0.05325168075617387,
      "grad_norm": 0.2926883399486542,
      "learning_rate": 4.985986547085202e-05,
      "loss": 0.5632081985473633,
      "step": 100
    },
    {
      "epoch": 0.058576848831791255,
      "grad_norm": 0.3214546740055084,
      "learning_rate": 4.9579596412556055e-05,
      "loss": 0.5223509311676026,
      "step": 110
    },
    {
      "epoch": 0.06390201690740864,
      "grad_norm": 0.24347242712974548,
      "learning_rate": 4.9299327354260097e-05,
      "loss": 0.5506986618041992,
      "step": 120
    },
    {
      "epoch": 0.06922718498302603,
      "grad_norm": 0.39196303486824036,
      "learning_rate": 4.9019058295964125e-05,
      "loss": 0.5343639373779296,
      "step": 130
    },
    {
      "epoch": 0.07455235305864341,
      "grad_norm": 0.2370986044406891,
      "learning_rate": 4.8738789237668166e-05,
      "loss": 0.634202241897583,
      "step": 140
    },
    {
      "epoch": 0.0798775211342608,
      "grad_norm": 0.5534964799880981,
      "learning_rate": 4.84585201793722e-05,
      "loss": 0.5778422355651855,
      "step": 150
    },
    {
      "epoch": 0.08520268920987818,
      "grad_norm": 0.30655860900878906,
      "learning_rate": 4.8178251121076236e-05,
      "loss": 0.5519596576690674,
      "step": 160
    },
    {
      "epoch": 0.09052785728549557,
      "grad_norm": 0.4148649573326111,
      "learning_rate": 4.789798206278027e-05,
      "loss": 0.5354521751403809,
      "step": 170
    },
    {
      "epoch": 0.09585302536111295,
      "grad_norm": 0.46059107780456543,
      "learning_rate": 4.7617713004484306e-05,
      "loss": 0.5110114574432373,
      "step": 180
    },
    {
      "epoch": 0.10117819343673035,
      "grad_norm": 0.29660817980766296,
      "learning_rate": 4.733744394618834e-05,
      "loss": 0.5167609214782715,
      "step": 190
    },
    {
      "epoch": 0.10650336151234774,
      "grad_norm": 0.3021899461746216,
      "learning_rate": 4.705717488789238e-05,
      "loss": 0.46111321449279785,
      "step": 200
    },
    {
      "epoch": 0.11182852958796512,
      "grad_norm": 0.47710350155830383,
      "learning_rate": 4.677690582959641e-05,
      "loss": 0.5681551456451416,
      "step": 210
    },
    {
      "epoch": 0.11715369766358251,
      "grad_norm": 0.5306881666183472,
      "learning_rate": 4.649663677130045e-05,
      "loss": 0.46531901359558103,
      "step": 220
    },
    {
      "epoch": 0.12247886573919989,
      "grad_norm": 0.513879120349884,
      "learning_rate": 4.621636771300449e-05,
      "loss": 0.4722289085388184,
      "step": 230
    },
    {
      "epoch": 0.12780403381481728,
      "grad_norm": 0.3301677405834198,
      "learning_rate": 4.593609865470852e-05,
      "loss": 0.5384090900421142,
      "step": 240
    },
    {
      "epoch": 0.13312920189043467,
      "grad_norm": 0.45560935139656067,
      "learning_rate": 4.565582959641256e-05,
      "loss": 0.4672722339630127,
      "step": 250
    },
    {
      "epoch": 0.13845436996605207,
      "grad_norm": 0.31638070940971375,
      "learning_rate": 4.537556053811659e-05,
      "loss": 0.4908642292022705,
      "step": 260
    },
    {
      "epoch": 0.14377953804166943,
      "grad_norm": 0.32199767231941223,
      "learning_rate": 4.509529147982063e-05,
      "loss": 0.5462312221527099,
      "step": 270
    },
    {
      "epoch": 0.14910470611728682,
      "grad_norm": 0.2937774062156677,
      "learning_rate": 4.481502242152467e-05,
      "loss": 0.47396349906921387,
      "step": 280
    },
    {
      "epoch": 0.15442987419290422,
      "grad_norm": 0.2907174229621887,
      "learning_rate": 4.4534753363228704e-05,
      "loss": 0.46338305473327634,
      "step": 290
    },
    {
      "epoch": 0.1597550422685216,
      "grad_norm": 0.4924933910369873,
      "learning_rate": 4.425448430493274e-05,
      "loss": 0.542780065536499,
      "step": 300
    },
    {
      "epoch": 0.165080210344139,
      "grad_norm": 0.6004148125648499,
      "learning_rate": 4.3974215246636774e-05,
      "loss": 0.5385100841522217,
      "step": 310
    },
    {
      "epoch": 0.17040537841975636,
      "grad_norm": 0.48270919919013977,
      "learning_rate": 4.369394618834081e-05,
      "loss": 0.4900692939758301,
      "step": 320
    },
    {
      "epoch": 0.17573054649537376,
      "grad_norm": 0.7385998368263245,
      "learning_rate": 4.3413677130044844e-05,
      "loss": 0.5876289367675781,
      "step": 330
    },
    {
      "epoch": 0.18105571457099115,
      "grad_norm": 0.3292222321033478,
      "learning_rate": 4.313340807174888e-05,
      "loss": 0.5060083866119385,
      "step": 340
    },
    {
      "epoch": 0.18638088264660854,
      "grad_norm": 0.2551015019416809,
      "learning_rate": 4.2853139013452914e-05,
      "loss": 0.4813774585723877,
      "step": 350
    },
    {
      "epoch": 0.1917060507222259,
      "grad_norm": 0.3968099355697632,
      "learning_rate": 4.257286995515695e-05,
      "loss": 0.477051830291748,
      "step": 360
    },
    {
      "epoch": 0.1970312187978433,
      "grad_norm": 0.5009409189224243,
      "learning_rate": 4.229260089686099e-05,
      "loss": 0.5575748920440674,
      "step": 370
    },
    {
      "epoch": 0.2023563868734607,
      "grad_norm": 0.32792729139328003,
      "learning_rate": 4.201233183856502e-05,
      "loss": 0.4213892459869385,
      "step": 380
    },
    {
      "epoch": 0.20768155494907808,
      "grad_norm": 0.3064369559288025,
      "learning_rate": 4.173206278026906e-05,
      "loss": 0.4275490760803223,
      "step": 390
    },
    {
      "epoch": 0.21300672302469548,
      "grad_norm": 0.3220454752445221,
      "learning_rate": 4.1451793721973096e-05,
      "loss": 0.48259787559509276,
      "step": 400
    },
    {
      "epoch": 0.21833189110031284,
      "grad_norm": 0.5888713002204895,
      "learning_rate": 4.117152466367713e-05,
      "loss": 0.578326940536499,
      "step": 410
    },
    {
      "epoch": 0.22365705917593023,
      "grad_norm": 0.6319938898086548,
      "learning_rate": 4.0891255605381166e-05,
      "loss": 0.4845900535583496,
      "step": 420
    },
    {
      "epoch": 0.22898222725154763,
      "grad_norm": 0.29064664244651794,
      "learning_rate": 4.061098654708521e-05,
      "loss": 0.46815996170043944,
      "step": 430
    },
    {
      "epoch": 0.23430739532716502,
      "grad_norm": 0.3988511562347412,
      "learning_rate": 4.0330717488789236e-05,
      "loss": 0.46213793754577637,
      "step": 440
    },
    {
      "epoch": 0.2396325634027824,
      "grad_norm": 0.3999287188053131,
      "learning_rate": 4.005044843049328e-05,
      "loss": 0.47902555465698243,
      "step": 450
    },
    {
      "epoch": 0.24495773147839978,
      "grad_norm": 0.4859839081764221,
      "learning_rate": 3.977017937219731e-05,
      "loss": 0.515401554107666,
      "step": 460
    },
    {
      "epoch": 0.25028289955401717,
      "grad_norm": 0.3084466755390167,
      "learning_rate": 3.948991031390135e-05,
      "loss": 0.4710197448730469,
      "step": 470
    },
    {
      "epoch": 0.25560806762963456,
      "grad_norm": 0.28355690836906433,
      "learning_rate": 3.920964125560538e-05,
      "loss": 0.4545428276062012,
      "step": 480
    },
    {
      "epoch": 0.26093323570525195,
      "grad_norm": 0.3173733651638031,
      "learning_rate": 3.8929372197309424e-05,
      "loss": 0.5014235019683838,
      "step": 490
    },
    {
      "epoch": 0.26625840378086935,
      "grad_norm": 0.5729868412017822,
      "learning_rate": 3.864910313901345e-05,
      "loss": 0.508852195739746,
      "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": 2.9641622724399514e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}