{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4013761467889908,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005733944954128441,
      "grad_norm": 2424.536243313375,
      "learning_rate": 8.240909090909092e-06,
      "loss": 0.9108621597290039,
      "step": 10
    },
    {
      "epoch": 0.011467889908256881,
      "grad_norm": 37.78530410203578,
      "learning_rate": 1.728636363636364e-05,
      "loss": 0.5426582336425781,
      "step": 20
    },
    {
      "epoch": 0.017201834862385322,
      "grad_norm": 83.550623391138,
      "learning_rate": 2e-05,
      "loss": 0.5049797058105469,
      "step": 30
    },
    {
      "epoch": 0.022935779816513763,
      "grad_norm": 99.63848149025779,
      "learning_rate": 2e-05,
      "loss": 0.49935340881347656,
      "step": 40
    },
    {
      "epoch": 0.028669724770642203,
      "grad_norm": 10.501930137714238,
      "learning_rate": 2e-05,
      "loss": 0.5058582782745361,
      "step": 50
    },
    {
      "epoch": 0.034403669724770644,
      "grad_norm": 160.4335548270735,
      "learning_rate": 2e-05,
      "loss": 0.5008002689906529,
      "step": 60
    },
    {
      "epoch": 0.040137614678899085,
      "grad_norm": 32.60866846365697,
      "learning_rate": 2e-05,
      "loss": 0.4980472087860107,
      "step": 70
    },
    {
      "epoch": 0.045871559633027525,
      "grad_norm": 383.78137504784166,
      "learning_rate": 2e-05,
      "loss": 0.4923880577087402,
      "step": 80
    },
    {
      "epoch": 0.051605504587155966,
      "grad_norm": 12.258337543101845,
      "learning_rate": 2e-05,
      "loss": 0.5059388160705567,
      "step": 90
    },
    {
      "epoch": 0.05733944954128441,
      "grad_norm": 70.75213422531445,
      "learning_rate": 2e-05,
      "loss": 0.5172739505767823,
      "step": 100
    },
    {
      "epoch": 0.06307339449541284,
      "grad_norm": 9.118480423969425,
      "learning_rate": 2e-05,
      "loss": 0.5014046430587769,
      "step": 110
    },
    {
      "epoch": 0.06880733944954129,
      "grad_norm": 20.996365288395644,
      "learning_rate": 2e-05,
      "loss": 0.5090189456939698,
      "step": 120
    },
    {
      "epoch": 0.07454128440366972,
      "grad_norm": 56.02604349780112,
      "learning_rate": 2e-05,
      "loss": 0.49025602340698243,
      "step": 130
    },
    {
      "epoch": 0.08027522935779817,
      "grad_norm": 19.3505911449923,
      "learning_rate": 2e-05,
      "loss": 0.48434019088745117,
      "step": 140
    },
    {
      "epoch": 0.0860091743119266,
      "grad_norm": 27.917775261227472,
      "learning_rate": 2e-05,
      "loss": 0.4863023281097412,
      "step": 150
    },
    {
      "epoch": 0.09174311926605505,
      "grad_norm": 48.26473957311906,
      "learning_rate": 2e-05,
      "loss": 0.504635214805603,
      "step": 160
    },
    {
      "epoch": 0.09747706422018348,
      "grad_norm": 4.6254297649556,
      "learning_rate": 2e-05,
      "loss": 0.5211471080780029,
      "step": 170
    },
    {
      "epoch": 0.10321100917431193,
      "grad_norm": 3.745779387451582,
      "learning_rate": 2e-05,
      "loss": 0.5565423488616943,
      "step": 180
    },
    {
      "epoch": 0.10894495412844037,
      "grad_norm": 28.466723404670876,
      "learning_rate": 2e-05,
      "loss": 0.5750695705413819,
      "step": 190
    },
    {
      "epoch": 0.11467889908256881,
      "grad_norm": 5.120695170176135,
      "learning_rate": 2e-05,
      "loss": 0.5925271034240722,
      "step": 200
    },
    {
      "epoch": 0.12041284403669725,
      "grad_norm": 63.306431857802934,
      "learning_rate": 2e-05,
      "loss": 0.5285980224609375,
      "step": 210
    },
    {
      "epoch": 0.12614678899082568,
      "grad_norm": 16.28311672665213,
      "learning_rate": 2e-05,
      "loss": 0.5151910185813904,
      "step": 220
    },
    {
      "epoch": 0.13188073394495411,
      "grad_norm": 52.40327201579259,
      "learning_rate": 2e-05,
      "loss": 0.5116393566131592,
      "step": 230
    },
    {
      "epoch": 0.13761467889908258,
      "grad_norm": 4.205827062828148,
      "learning_rate": 2e-05,
      "loss": 0.5311302185058594,
      "step": 240
    },
    {
      "epoch": 0.143348623853211,
      "grad_norm": 3.0535480180134824,
      "learning_rate": 2e-05,
      "loss": 0.5316281795501709,
      "step": 250
    },
    {
      "epoch": 0.14908256880733944,
      "grad_norm": 5.134980500059291,
      "learning_rate": 2e-05,
      "loss": 0.5198026657104492,
      "step": 260
    },
    {
      "epoch": 0.15481651376146788,
      "grad_norm": 1.2525820840387116,
      "learning_rate": 2e-05,
      "loss": 0.49965686798095704,
      "step": 270
    },
    {
      "epoch": 0.16055045871559634,
      "grad_norm": 2.1419127532403173,
      "learning_rate": 2e-05,
      "loss": 0.48150157928466797,
      "step": 280
    },
    {
      "epoch": 0.16628440366972477,
      "grad_norm": 3.9523548653584237,
      "learning_rate": 2e-05,
      "loss": 0.4833134651184082,
      "step": 290
    },
    {
      "epoch": 0.1720183486238532,
      "grad_norm": 2.798154446195494,
      "learning_rate": 2e-05,
      "loss": 0.4786534309387207,
      "step": 300
    },
    {
      "epoch": 0.17775229357798164,
      "grad_norm": 71.17928601308672,
      "learning_rate": 2e-05,
      "loss": 0.48014464378356936,
      "step": 310
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 2.3051106579724965,
      "learning_rate": 2e-05,
      "loss": 0.4746496081352234,
      "step": 320
    },
    {
      "epoch": 0.18922018348623854,
      "grad_norm": 3.8149048144361224,
      "learning_rate": 2e-05,
      "loss": 0.5038511753082275,
      "step": 330
    },
    {
      "epoch": 0.19495412844036697,
      "grad_norm": 10.72772920756461,
      "learning_rate": 2e-05,
      "loss": 0.4958949565887451,
      "step": 340
    },
    {
      "epoch": 0.2006880733944954,
      "grad_norm": 30.638376309802364,
      "learning_rate": 2e-05,
      "loss": 0.4817504405975342,
      "step": 350
    },
    {
      "epoch": 0.20642201834862386,
      "grad_norm": 5.18088410327949,
      "learning_rate": 2e-05,
      "loss": 0.477231502532959,
      "step": 360
    },
    {
      "epoch": 0.2121559633027523,
      "grad_norm": 2.199175054305401,
      "learning_rate": 2e-05,
      "loss": 0.48193044662475587,
      "step": 370
    },
    {
      "epoch": 0.21788990825688073,
      "grad_norm": 2.2644100360083517,
      "learning_rate": 2e-05,
      "loss": 0.47909344567192924,
      "step": 380
    },
    {
      "epoch": 0.22362385321100917,
      "grad_norm": 1.2245398894826636,
      "learning_rate": 2e-05,
      "loss": 0.47615752220153806,
      "step": 390
    },
    {
      "epoch": 0.22935779816513763,
      "grad_norm": 1.2865994631920663,
      "learning_rate": 2e-05,
      "loss": 0.4700117588043213,
      "step": 400
    },
    {
      "epoch": 0.23509174311926606,
      "grad_norm": 0.955868053787797,
      "learning_rate": 2e-05,
      "loss": 0.4637158870697021,
      "step": 410
    },
    {
      "epoch": 0.2408256880733945,
      "grad_norm": 3.6901104312101154,
      "learning_rate": 2e-05,
      "loss": 0.4664497375488281,
      "step": 420
    },
    {
      "epoch": 0.24655963302752293,
      "grad_norm": 1.2071690896641283,
      "learning_rate": 2e-05,
      "loss": 0.4575640360514323,
      "step": 430
    },
    {
      "epoch": 0.25229357798165136,
      "grad_norm": 1.889040231933846,
      "learning_rate": 2e-05,
      "loss": 0.45377335548400877,
      "step": 440
    },
    {
      "epoch": 0.2580275229357798,
      "grad_norm": 9.81935003269608,
      "learning_rate": 2e-05,
      "loss": 0.46431803703308105,
      "step": 450
    },
    {
      "epoch": 0.26376146788990823,
      "grad_norm": 21.975238628800835,
      "learning_rate": 2e-05,
      "loss": 0.4612529754638672,
      "step": 460
    },
    {
      "epoch": 0.2694954128440367,
      "grad_norm": 0.46631993192313115,
      "learning_rate": 2e-05,
      "loss": 0.46733980178833007,
      "step": 470
    },
    {
      "epoch": 0.27522935779816515,
      "grad_norm": 1.469658429645411,
      "learning_rate": 2e-05,
      "loss": 0.4814738432566325,
      "step": 480
    },
    {
      "epoch": 0.2809633027522936,
      "grad_norm": 0.9590987257268475,
      "learning_rate": 2e-05,
      "loss": 0.4802237510681152,
      "step": 490
    },
    {
      "epoch": 0.286697247706422,
      "grad_norm": 0.6517266300708695,
      "learning_rate": 2e-05,
      "loss": 0.4670071601867676,
      "step": 500
    },
    {
      "epoch": 0.29243119266055045,
      "grad_norm": 7.210821379507904,
      "learning_rate": 2e-05,
      "loss": 0.4768378257751465,
      "step": 510
    },
    {
      "epoch": 0.2981651376146789,
      "grad_norm": 1.7625345874290743,
      "learning_rate": 2e-05,
      "loss": 0.4566288948059082,
      "step": 520
    },
    {
      "epoch": 0.3038990825688073,
      "grad_norm": 3.5589258836037905,
      "learning_rate": 2e-05,
      "loss": 0.456721830368042,
      "step": 530
    },
    {
      "epoch": 0.30963302752293576,
      "grad_norm": 10.825201179065129,
      "learning_rate": 2e-05,
      "loss": 0.46009049415588377,
      "step": 540
    },
    {
      "epoch": 0.31536697247706424,
      "grad_norm": 1.2813118606393255,
      "learning_rate": 2e-05,
      "loss": 0.46355361938476564,
      "step": 550
    },
    {
      "epoch": 0.3211009174311927,
      "grad_norm": 17.81064852221345,
      "learning_rate": 2e-05,
      "loss": 0.45562305450439455,
      "step": 560
    },
    {
      "epoch": 0.3268348623853211,
      "grad_norm": 3.3686554961710415,
      "learning_rate": 2e-05,
      "loss": 0.45443029403686525,
      "step": 570
    },
    {
      "epoch": 0.33256880733944955,
      "grad_norm": 1.303864378484885,
      "learning_rate": 2e-05,
      "loss": 0.4673898220062256,
      "step": 580
    },
    {
      "epoch": 0.338302752293578,
      "grad_norm": 1.466693718684684,
      "learning_rate": 2e-05,
      "loss": 0.46768598556518554,
      "step": 590
    },
    {
      "epoch": 0.3440366972477064,
      "grad_norm": 9.975803950484181,
      "learning_rate": 2e-05,
      "loss": 0.45705389976501465,
      "step": 600
    },
    {
      "epoch": 0.34977064220183485,
      "grad_norm": 1.5366377915891616,
      "learning_rate": 2e-05,
      "loss": 0.4581932067871094,
      "step": 610
    },
    {
      "epoch": 0.3555045871559633,
      "grad_norm": 1.3165212090092135,
      "learning_rate": 2e-05,
      "loss": 0.4482154369354248,
      "step": 620
    },
    {
      "epoch": 0.36123853211009177,
      "grad_norm": 1.521798180272582,
      "learning_rate": 2e-05,
      "loss": 0.46234827041625975,
      "step": 630
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": 5.606209930844781,
      "learning_rate": 1.9892306274149575e-05,
      "loss": 0.4604673385620117,
      "step": 640
    },
    {
      "epoch": 0.37270642201834864,
      "grad_norm": 2.2281624985886768,
      "learning_rate": 1.8041914938232418e-05,
      "loss": 0.45578575134277344,
      "step": 650
    },
    {
      "epoch": 0.37844036697247707,
      "grad_norm": 74.71239734945986,
      "learning_rate": 1.430417317963131e-05,
      "loss": 0.4547560691833496,
      "step": 660
    },
    {
      "epoch": 0.3841743119266055,
      "grad_norm": 1.8617939112367834,
      "learning_rate": 9.561776640442192e-06,
      "loss": 0.45580496788024905,
      "step": 670
    },
    {
      "epoch": 0.38990825688073394,
      "grad_norm": 1.3820315331859674,
      "learning_rate": 4.934677695277445e-06,
      "loss": 0.44834179878234864,
      "step": 680
    },
    {
      "epoch": 0.3956422018348624,
      "grad_norm": 0.7473778752307001,
      "learning_rate": 1.5156003304972938e-06,
      "loss": 0.4534157276153564,
      "step": 690
    },
    {
      "epoch": 0.4013761467889908,
      "grad_norm": 1.17265697171241,
      "learning_rate": 1.1198521075853458e-07,
      "loss": 0.45271739959716795,
      "step": 700
    },
    {
      "epoch": 0.4013761467889908,
      "step": 700,
      "total_flos": 4821608300544000.0,
      "train_loss": 0.041500123568943566,
      "train_runtime": 2737.6719,
      "train_samples_per_second": 24.546,
      "train_steps_per_second": 0.256
    }
  ],
  "logging_steps": 10,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 53,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4821608300544000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}