{
  "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": 0.20683516561985016,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.7822918891906738,
      "step": 10
    },
    {
      "epoch": 0.010650336151234773,
      "grad_norm": 0.3277234733104706,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.7612236499786377,
      "step": 20
    },
    {
      "epoch": 0.01597550422685216,
      "grad_norm": 0.36984074115753174,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.6511845111846923,
      "step": 30
    },
    {
      "epoch": 0.021300672302469546,
      "grad_norm": 0.20985147356987,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.6681060314178466,
      "step": 40
    },
    {
      "epoch": 0.026625840378086935,
      "grad_norm": 0.7140442728996277,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.659309196472168,
      "step": 50
    },
    {
      "epoch": 0.03195100845370432,
      "grad_norm": 0.42718973755836487,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.6909014225006104,
      "step": 60
    },
    {
      "epoch": 0.037276176529321706,
      "grad_norm": 0.3533357083797455,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.5650594711303711,
      "step": 70
    },
    {
      "epoch": 0.04260134460493909,
      "grad_norm": 0.417624831199646,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 0.6802642345428467,
      "step": 80
    },
    {
      "epoch": 0.04792651268055648,
      "grad_norm": 0.35949471592903137,
      "learning_rate": 4.734042553191489e-05,
      "loss": 0.5739238739013672,
      "step": 90
    },
    {
      "epoch": 0.05325168075617387,
      "grad_norm": 0.3818545937538147,
      "learning_rate": 4.985986547085202e-05,
      "loss": 0.5993009090423584,
      "step": 100
    },
    {
      "epoch": 0.058576848831791255,
      "grad_norm": 0.4698786437511444,
      "learning_rate": 4.9579596412556055e-05,
      "loss": 0.557436180114746,
      "step": 110
    },
    {
      "epoch": 0.06390201690740864,
      "grad_norm": 0.35443201661109924,
      "learning_rate": 4.9299327354260097e-05,
      "loss": 0.581347131729126,
      "step": 120
    },
    {
      "epoch": 0.06922718498302603,
      "grad_norm": 0.7349355220794678,
      "learning_rate": 4.9019058295964125e-05,
      "loss": 0.5600838661193848,
      "step": 130
    },
    {
      "epoch": 0.07455235305864341,
      "grad_norm": 0.5207298398017883,
      "learning_rate": 4.8738789237668166e-05,
      "loss": 0.6590728282928466,
      "step": 140
    },
    {
      "epoch": 0.0798775211342608,
      "grad_norm": 0.6123145222663879,
      "learning_rate": 4.84585201793722e-05,
      "loss": 0.5984565734863281,
      "step": 150
    },
    {
      "epoch": 0.08520268920987818,
      "grad_norm": 0.37944698333740234,
      "learning_rate": 4.8178251121076236e-05,
      "loss": 0.5809710502624512,
      "step": 160
    },
    {
      "epoch": 0.09052785728549557,
      "grad_norm": 0.48942145705223083,
      "learning_rate": 4.789798206278027e-05,
      "loss": 0.5642497062683105,
      "step": 170
    },
    {
      "epoch": 0.09585302536111295,
      "grad_norm": 0.42988479137420654,
      "learning_rate": 4.7617713004484306e-05,
      "loss": 0.5531106472015381,
      "step": 180
    },
    {
      "epoch": 0.10117819343673035,
      "grad_norm": 0.4417687654495239,
      "learning_rate": 4.733744394618834e-05,
      "loss": 0.5732029438018799,
      "step": 190
    },
    {
      "epoch": 0.10650336151234774,
      "grad_norm": 0.2549873888492584,
      "learning_rate": 4.705717488789238e-05,
      "loss": 0.5021458625793457,
      "step": 200
    },
    {
      "epoch": 0.11182852958796512,
      "grad_norm": 0.4950169622898102,
      "learning_rate": 4.677690582959641e-05,
      "loss": 0.641213846206665,
      "step": 210
    },
    {
      "epoch": 0.11715369766358251,
      "grad_norm": 0.456673264503479,
      "learning_rate": 4.649663677130045e-05,
      "loss": 0.5225620746612549,
      "step": 220
    },
    {
      "epoch": 0.12247886573919989,
      "grad_norm": 0.6995387077331543,
      "learning_rate": 4.621636771300449e-05,
      "loss": 0.5139231204986572,
      "step": 230
    },
    {
      "epoch": 0.12780403381481728,
      "grad_norm": 0.26585784554481506,
      "learning_rate": 4.593609865470852e-05,
      "loss": 0.5961785793304444,
      "step": 240
    },
    {
      "epoch": 0.13312920189043467,
      "grad_norm": 0.5705807209014893,
      "learning_rate": 4.565582959641256e-05,
      "loss": 0.5149649143218994,
      "step": 250
    },
    {
      "epoch": 0.13845436996605207,
      "grad_norm": 0.39890748262405396,
      "learning_rate": 4.537556053811659e-05,
      "loss": 0.5415900230407715,
      "step": 260
    },
    {
      "epoch": 0.14377953804166943,
      "grad_norm": 0.32965633273124695,
      "learning_rate": 4.509529147982063e-05,
      "loss": 0.5950401782989502,
      "step": 270
    },
    {
      "epoch": 0.14910470611728682,
      "grad_norm": 0.6010472178459167,
      "learning_rate": 4.481502242152467e-05,
      "loss": 0.5145067691802978,
      "step": 280
    },
    {
      "epoch": 0.15442987419290422,
      "grad_norm": 0.3178304135799408,
      "learning_rate": 4.4534753363228704e-05,
      "loss": 0.505909013748169,
      "step": 290
    },
    {
      "epoch": 0.1597550422685216,
      "grad_norm": 0.48335757851600647,
      "learning_rate": 4.425448430493274e-05,
      "loss": 0.6062196254730224,
      "step": 300
    },
    {
      "epoch": 0.165080210344139,
      "grad_norm": 0.6835651993751526,
      "learning_rate": 4.3974215246636774e-05,
      "loss": 0.6059549808502197,
      "step": 310
    },
    {
      "epoch": 0.17040537841975636,
      "grad_norm": 0.3845309019088745,
      "learning_rate": 4.369394618834081e-05,
      "loss": 0.5377228736877442,
      "step": 320
    },
    {
      "epoch": 0.17573054649537376,
      "grad_norm": 0.7088361382484436,
      "learning_rate": 4.3413677130044844e-05,
      "loss": 0.6384317398071289,
      "step": 330
    },
    {
      "epoch": 0.18105571457099115,
      "grad_norm": 0.33346283435821533,
      "learning_rate": 4.313340807174888e-05,
      "loss": 0.5557454586029053,
      "step": 340
    },
    {
      "epoch": 0.18638088264660854,
      "grad_norm": 0.3019021153450012,
      "learning_rate": 4.2853139013452914e-05,
      "loss": 0.518170690536499,
      "step": 350
    },
    {
      "epoch": 0.1917060507222259,
      "grad_norm": 0.5704140067100525,
      "learning_rate": 4.257286995515695e-05,
      "loss": 0.524034070968628,
      "step": 360
    },
    {
      "epoch": 0.1970312187978433,
      "grad_norm": 0.6912387013435364,
      "learning_rate": 4.229260089686099e-05,
      "loss": 0.6240747451782227,
      "step": 370
    },
    {
      "epoch": 0.2023563868734607,
      "grad_norm": 0.35987111926078796,
      "learning_rate": 4.201233183856502e-05,
      "loss": 0.45235018730163573,
      "step": 380
    },
    {
      "epoch": 0.20768155494907808,
      "grad_norm": 0.3558119535446167,
      "learning_rate": 4.173206278026906e-05,
      "loss": 0.4568950176239014,
      "step": 390
    },
    {
      "epoch": 0.21300672302469548,
      "grad_norm": 0.44445547461509705,
      "learning_rate": 4.1451793721973096e-05,
      "loss": 0.5185273647308349,
      "step": 400
    },
    {
      "epoch": 0.21833189110031284,
      "grad_norm": 0.6698095798492432,
      "learning_rate": 4.117152466367713e-05,
      "loss": 0.6193028450012207,
      "step": 410
    },
    {
      "epoch": 0.22365705917593023,
      "grad_norm": 0.7176916599273682,
      "learning_rate": 4.0891255605381166e-05,
      "loss": 0.5141634464263916,
      "step": 420
    },
    {
      "epoch": 0.22898222725154763,
      "grad_norm": 0.3718442916870117,
      "learning_rate": 4.061098654708521e-05,
      "loss": 0.49727892875671387,
      "step": 430
    },
    {
      "epoch": 0.23430739532716502,
      "grad_norm": 0.47129976749420166,
      "learning_rate": 4.0330717488789236e-05,
      "loss": 0.4925837993621826,
      "step": 440
    },
    {
      "epoch": 0.2396325634027824,
      "grad_norm": 0.5557712912559509,
      "learning_rate": 4.005044843049328e-05,
      "loss": 0.5097068786621094,
      "step": 450
    },
    {
      "epoch": 0.24495773147839978,
      "grad_norm": 0.5537528395652771,
      "learning_rate": 3.977017937219731e-05,
      "loss": 0.5421949863433838,
      "step": 460
    },
    {
      "epoch": 0.25028289955401717,
      "grad_norm": 0.32208332419395447,
      "learning_rate": 3.948991031390135e-05,
      "loss": 0.4985233783721924,
      "step": 470
    },
    {
      "epoch": 0.25560806762963456,
      "grad_norm": 0.381181538105011,
      "learning_rate": 3.920964125560538e-05,
      "loss": 0.4739542007446289,
      "step": 480
    },
    {
      "epoch": 0.26093323570525195,
      "grad_norm": 0.39554715156555176,
      "learning_rate": 3.8929372197309424e-05,
      "loss": 0.5237335681915283,
      "step": 490
    },
    {
      "epoch": 0.26625840378086935,
      "grad_norm": 0.710545539855957,
      "learning_rate": 3.864910313901345e-05,
      "loss": 0.5354659080505371,
      "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": 1.1165404548635136e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}