{
  "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": 0.05487716570496559,
      "learning_rate": 4.787234042553191e-06,
      "loss": 0.5996371269226074,
      "step": 10
    },
    {
      "epoch": 0.010650336151234773,
      "grad_norm": 0.043438851833343506,
      "learning_rate": 1.0106382978723404e-05,
      "loss": 0.6392858028411865,
      "step": 20
    },
    {
      "epoch": 0.01597550422685216,
      "grad_norm": 0.04921114817261696,
      "learning_rate": 1.5425531914893617e-05,
      "loss": 0.5546797752380371,
      "step": 30
    },
    {
      "epoch": 0.021300672302469546,
      "grad_norm": 0.06968632340431213,
      "learning_rate": 2.074468085106383e-05,
      "loss": 0.598508071899414,
      "step": 40
    },
    {
      "epoch": 0.026625840378086935,
      "grad_norm": 0.07072321325540543,
      "learning_rate": 2.6063829787234046e-05,
      "loss": 0.5995429992675781,
      "step": 50
    },
    {
      "epoch": 0.03195100845370432,
      "grad_norm": 0.11021557450294495,
      "learning_rate": 3.1382978723404254e-05,
      "loss": 0.6088542938232422,
      "step": 60
    },
    {
      "epoch": 0.037276176529321706,
      "grad_norm": 0.10559481382369995,
      "learning_rate": 3.670212765957447e-05,
      "loss": 0.4991436004638672,
      "step": 70
    },
    {
      "epoch": 0.04260134460493909,
      "grad_norm": 0.13761867582798004,
      "learning_rate": 4.2021276595744684e-05,
      "loss": 0.601447582244873,
      "step": 80
    },
    {
      "epoch": 0.04792651268055648,
      "grad_norm": 0.14284180104732513,
      "learning_rate": 4.734042553191489e-05,
      "loss": 0.49308085441589355,
      "step": 90
    },
    {
      "epoch": 0.05325168075617387,
      "grad_norm": 0.13274621963500977,
      "learning_rate": 4.985986547085202e-05,
      "loss": 0.5244489669799804,
      "step": 100
    },
    {
      "epoch": 0.058576848831791255,
      "grad_norm": 0.14783857762813568,
      "learning_rate": 4.9579596412556055e-05,
      "loss": 0.48787918090820315,
      "step": 110
    },
    {
      "epoch": 0.06390201690740864,
      "grad_norm": 0.14742612838745117,
      "learning_rate": 4.9299327354260097e-05,
      "loss": 0.5078488349914551,
      "step": 120
    },
    {
      "epoch": 0.06922718498302603,
      "grad_norm": 0.26408520340919495,
      "learning_rate": 4.9019058295964125e-05,
      "loss": 0.48049073219299315,
      "step": 130
    },
    {
      "epoch": 0.07455235305864341,
      "grad_norm": 0.14286410808563232,
      "learning_rate": 4.8738789237668166e-05,
      "loss": 0.5604067325592041,
      "step": 140
    },
    {
      "epoch": 0.0798775211342608,
      "grad_norm": 0.1512993425130844,
      "learning_rate": 4.84585201793722e-05,
      "loss": 0.5293330669403076,
      "step": 150
    },
    {
      "epoch": 0.08520268920987818,
      "grad_norm": 0.14961321651935577,
      "learning_rate": 4.8178251121076236e-05,
      "loss": 0.5038127422332763,
      "step": 160
    },
    {
      "epoch": 0.09052785728549557,
      "grad_norm": 0.14800076186656952,
      "learning_rate": 4.789798206278027e-05,
      "loss": 0.4966014862060547,
      "step": 170
    },
    {
      "epoch": 0.09585302536111295,
      "grad_norm": 0.17610834538936615,
      "learning_rate": 4.7617713004484306e-05,
      "loss": 0.48385324478149416,
      "step": 180
    },
    {
      "epoch": 0.10117819343673035,
      "grad_norm": 0.1252691149711609,
      "learning_rate": 4.733744394618834e-05,
      "loss": 0.4838716983795166,
      "step": 190
    },
    {
      "epoch": 0.10650336151234774,
      "grad_norm": 0.14018668234348297,
      "learning_rate": 4.705717488789238e-05,
      "loss": 0.4520565032958984,
      "step": 200
    },
    {
      "epoch": 0.11182852958796512,
      "grad_norm": 0.1684730499982834,
      "learning_rate": 4.677690582959641e-05,
      "loss": 0.5429281711578369,
      "step": 210
    },
    {
      "epoch": 0.11715369766358251,
      "grad_norm": 0.22210614383220673,
      "learning_rate": 4.649663677130045e-05,
      "loss": 0.4519489288330078,
      "step": 220
    },
    {
      "epoch": 0.12247886573919989,
      "grad_norm": 0.178190216422081,
      "learning_rate": 4.621636771300449e-05,
      "loss": 0.45887036323547364,
      "step": 230
    },
    {
      "epoch": 0.12780403381481728,
      "grad_norm": 0.16266238689422607,
      "learning_rate": 4.593609865470852e-05,
      "loss": 0.52867112159729,
      "step": 240
    },
    {
      "epoch": 0.13312920189043467,
      "grad_norm": 0.16510607302188873,
      "learning_rate": 4.565582959641256e-05,
      "loss": 0.45111827850341796,
      "step": 250
    },
    {
      "epoch": 0.13845436996605207,
      "grad_norm": 0.14936929941177368,
      "learning_rate": 4.537556053811659e-05,
      "loss": 0.4746635913848877,
      "step": 260
    },
    {
      "epoch": 0.14377953804166943,
      "grad_norm": 0.1664894074201584,
      "learning_rate": 4.509529147982063e-05,
      "loss": 0.5356125354766845,
      "step": 270
    },
    {
      "epoch": 0.14910470611728682,
      "grad_norm": 0.13999034464359283,
      "learning_rate": 4.481502242152467e-05,
      "loss": 0.4625279426574707,
      "step": 280
    },
    {
      "epoch": 0.15442987419290422,
      "grad_norm": 0.14819900691509247,
      "learning_rate": 4.4534753363228704e-05,
      "loss": 0.45238590240478516,
      "step": 290
    },
    {
      "epoch": 0.1597550422685216,
      "grad_norm": 0.2902645468711853,
      "learning_rate": 4.425448430493274e-05,
      "loss": 0.523665189743042,
      "step": 300
    },
    {
      "epoch": 0.165080210344139,
      "grad_norm": 0.3842649757862091,
      "learning_rate": 4.3974215246636774e-05,
      "loss": 0.5117780208587647,
      "step": 310
    },
    {
      "epoch": 0.17040537841975636,
      "grad_norm": 0.3537648916244507,
      "learning_rate": 4.369394618834081e-05,
      "loss": 0.47908267974853513,
      "step": 320
    },
    {
      "epoch": 0.17573054649537376,
      "grad_norm": 0.24112680554389954,
      "learning_rate": 4.3413677130044844e-05,
      "loss": 0.5666882991790771,
      "step": 330
    },
    {
      "epoch": 0.18105571457099115,
      "grad_norm": 0.16881901025772095,
      "learning_rate": 4.313340807174888e-05,
      "loss": 0.49497289657592775,
      "step": 340
    },
    {
      "epoch": 0.18638088264660854,
      "grad_norm": 0.16978123784065247,
      "learning_rate": 4.2853139013452914e-05,
      "loss": 0.46808652877807616,
      "step": 350
    },
    {
      "epoch": 0.1917060507222259,
      "grad_norm": 0.24577109515666962,
      "learning_rate": 4.257286995515695e-05,
      "loss": 0.4676064491271973,
      "step": 360
    },
    {
      "epoch": 0.1970312187978433,
      "grad_norm": 0.2847534418106079,
      "learning_rate": 4.229260089686099e-05,
      "loss": 0.5394676685333252,
      "step": 370
    },
    {
      "epoch": 0.2023563868734607,
      "grad_norm": 0.14291039109230042,
      "learning_rate": 4.201233183856502e-05,
      "loss": 0.4125664234161377,
      "step": 380
    },
    {
      "epoch": 0.20768155494907808,
      "grad_norm": 0.31676554679870605,
      "learning_rate": 4.173206278026906e-05,
      "loss": 0.41750164031982423,
      "step": 390
    },
    {
      "epoch": 0.21300672302469548,
      "grad_norm": 0.2844577133655548,
      "learning_rate": 4.1451793721973096e-05,
      "loss": 0.4729475021362305,
      "step": 400
    },
    {
      "epoch": 0.21833189110031284,
      "grad_norm": 0.2866207957267761,
      "learning_rate": 4.117152466367713e-05,
      "loss": 0.5492980003356933,
      "step": 410
    },
    {
      "epoch": 0.22365705917593023,
      "grad_norm": 0.38996192812919617,
      "learning_rate": 4.0891255605381166e-05,
      "loss": 0.4734052181243896,
      "step": 420
    },
    {
      "epoch": 0.22898222725154763,
      "grad_norm": 0.1881261020898819,
      "learning_rate": 4.061098654708521e-05,
      "loss": 0.4500300407409668,
      "step": 430
    },
    {
      "epoch": 0.23430739532716502,
      "grad_norm": 0.20594148337841034,
      "learning_rate": 4.0330717488789236e-05,
      "loss": 0.4548191547393799,
      "step": 440
    },
    {
      "epoch": 0.2396325634027824,
      "grad_norm": 0.22915281355381012,
      "learning_rate": 4.005044843049328e-05,
      "loss": 0.465634822845459,
      "step": 450
    },
    {
      "epoch": 0.24495773147839978,
      "grad_norm": 0.3207595646381378,
      "learning_rate": 3.977017937219731e-05,
      "loss": 0.5047284603118897,
      "step": 460
    },
    {
      "epoch": 0.25028289955401717,
      "grad_norm": 0.17310434579849243,
      "learning_rate": 3.948991031390135e-05,
      "loss": 0.45878047943115235,
      "step": 470
    },
    {
      "epoch": 0.25560806762963456,
      "grad_norm": 0.1512192338705063,
      "learning_rate": 3.920964125560538e-05,
      "loss": 0.44451174736022947,
      "step": 480
    },
    {
      "epoch": 0.26093323570525195,
      "grad_norm": 0.17040136456489563,
      "learning_rate": 3.8929372197309424e-05,
      "loss": 0.485479736328125,
      "step": 490
    },
    {
      "epoch": 0.26625840378086935,
      "grad_norm": 0.3218516707420349,
      "learning_rate": 3.864910313901345e-05,
      "loss": 0.47697882652282714,
      "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": 5.78139605226409e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}