{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0406124355277586,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000812248710555172,
      "grad_norm": 0.3937675654888153,
      "learning_rate": 0.00018,
      "loss": 1.2718635559082032,
      "step": 10
    },
    {
      "epoch": 0.001624497421110344,
      "grad_norm": 0.15561772882938385,
      "learning_rate": 0.00019939799331103678,
      "loss": 0.79568510055542,
      "step": 20
    },
    {
      "epoch": 0.0024367461316655158,
      "grad_norm": 0.1349518895149231,
      "learning_rate": 0.00019872909698996657,
      "loss": 0.6877449035644532,
      "step": 30
    },
    {
      "epoch": 0.003248994842220688,
      "grad_norm": 0.1342487335205078,
      "learning_rate": 0.00019806020066889633,
      "loss": 0.7130545616149903,
      "step": 40
    },
    {
      "epoch": 0.00406124355277586,
      "grad_norm": 0.11474266648292542,
      "learning_rate": 0.0001973913043478261,
      "loss": 0.6835604190826416,
      "step": 50
    },
    {
      "epoch": 0.0048734922633310316,
      "grad_norm": 0.10755404084920883,
      "learning_rate": 0.00019672240802675586,
      "loss": 0.652743148803711,
      "step": 60
    },
    {
      "epoch": 0.005685740973886204,
      "grad_norm": 0.11963178217411041,
      "learning_rate": 0.00019605351170568562,
      "loss": 0.6648129940032959,
      "step": 70
    },
    {
      "epoch": 0.006497989684441376,
      "grad_norm": 0.0965123176574707,
      "learning_rate": 0.0001953846153846154,
      "loss": 0.6699862003326416,
      "step": 80
    },
    {
      "epoch": 0.007310238394996548,
      "grad_norm": 0.10343202203512192,
      "learning_rate": 0.00019471571906354515,
      "loss": 0.7039784908294677,
      "step": 90
    },
    {
      "epoch": 0.00812248710555172,
      "grad_norm": 0.12766548991203308,
      "learning_rate": 0.00019404682274247492,
      "loss": 0.6552480697631836,
      "step": 100
    },
    {
      "epoch": 0.008934735816106891,
      "grad_norm": 0.10638143867254257,
      "learning_rate": 0.00019337792642140468,
      "loss": 0.6422908782958985,
      "step": 110
    },
    {
      "epoch": 0.009746984526662063,
      "grad_norm": 0.13318222761154175,
      "learning_rate": 0.00019270903010033444,
      "loss": 0.6597362995147705,
      "step": 120
    },
    {
      "epoch": 0.010559233237217237,
      "grad_norm": 0.11342291533946991,
      "learning_rate": 0.0001920401337792642,
      "loss": 0.6484825611114502,
      "step": 130
    },
    {
      "epoch": 0.011371481947772408,
      "grad_norm": 0.10095760971307755,
      "learning_rate": 0.000191371237458194,
      "loss": 0.6201153755187988,
      "step": 140
    },
    {
      "epoch": 0.01218373065832758,
      "grad_norm": 0.12489528954029083,
      "learning_rate": 0.00019070234113712376,
      "loss": 0.6547854900360107,
      "step": 150
    },
    {
      "epoch": 0.012995979368882752,
      "grad_norm": 0.10871083289384842,
      "learning_rate": 0.00019003344481605353,
      "loss": 0.654566764831543,
      "step": 160
    },
    {
      "epoch": 0.013808228079437924,
      "grad_norm": 0.1039392426609993,
      "learning_rate": 0.0001893645484949833,
      "loss": 0.649402379989624,
      "step": 170
    },
    {
      "epoch": 0.014620476789993096,
      "grad_norm": 0.1328577846288681,
      "learning_rate": 0.00018869565217391305,
      "loss": 0.6331918716430665,
      "step": 180
    },
    {
      "epoch": 0.015432725500548267,
      "grad_norm": 0.1274302750825882,
      "learning_rate": 0.00018802675585284282,
      "loss": 0.6307297706604004,
      "step": 190
    },
    {
      "epoch": 0.01624497421110344,
      "grad_norm": 0.12753233313560486,
      "learning_rate": 0.00018735785953177258,
      "loss": 0.6115467071533203,
      "step": 200
    },
    {
      "epoch": 0.01705722292165861,
      "grad_norm": 0.10285915434360504,
      "learning_rate": 0.00018668896321070235,
      "loss": 0.6152299880981446,
      "step": 210
    },
    {
      "epoch": 0.017869471632213783,
      "grad_norm": 0.17819221317768097,
      "learning_rate": 0.0001860200668896321,
      "loss": 0.6279479026794433,
      "step": 220
    },
    {
      "epoch": 0.018681720342768954,
      "grad_norm": 0.11906374990940094,
      "learning_rate": 0.00018535117056856187,
      "loss": 0.642233943939209,
      "step": 230
    },
    {
      "epoch": 0.019493969053324126,
      "grad_norm": 0.13238145411014557,
      "learning_rate": 0.00018468227424749164,
      "loss": 0.6336838245391846,
      "step": 240
    },
    {
      "epoch": 0.0203062177638793,
      "grad_norm": 0.11965897679328918,
      "learning_rate": 0.00018401337792642143,
      "loss": 0.6414345264434814,
      "step": 250
    },
    {
      "epoch": 0.021118466474434473,
      "grad_norm": 0.11781352013349533,
      "learning_rate": 0.0001833444816053512,
      "loss": 0.6286166191101075,
      "step": 260
    },
    {
      "epoch": 0.021930715184989645,
      "grad_norm": 0.13107237219810486,
      "learning_rate": 0.00018267558528428096,
      "loss": 0.6182798385620117,
      "step": 270
    },
    {
      "epoch": 0.022742963895544817,
      "grad_norm": 0.11255916953086853,
      "learning_rate": 0.00018200668896321072,
      "loss": 0.6299595832824707,
      "step": 280
    },
    {
      "epoch": 0.02355521260609999,
      "grad_norm": 0.11259932816028595,
      "learning_rate": 0.00018133779264214048,
      "loss": 0.6332510471343994,
      "step": 290
    },
    {
      "epoch": 0.02436746131665516,
      "grad_norm": 0.11110201478004456,
      "learning_rate": 0.00018066889632107025,
      "loss": 0.6277278900146485,
      "step": 300
    },
    {
      "epoch": 0.025179710027210332,
      "grad_norm": 0.11659885942935944,
      "learning_rate": 0.00018,
      "loss": 0.6012191772460938,
      "step": 310
    },
    {
      "epoch": 0.025991958737765504,
      "grad_norm": 0.11534283310174942,
      "learning_rate": 0.00017933110367892978,
      "loss": 0.6344992160797119,
      "step": 320
    },
    {
      "epoch": 0.026804207448320676,
      "grad_norm": 0.13291247189044952,
      "learning_rate": 0.00017866220735785954,
      "loss": 0.6238264560699462,
      "step": 330
    },
    {
      "epoch": 0.027616456158875848,
      "grad_norm": 0.12442389875650406,
      "learning_rate": 0.0001779933110367893,
      "loss": 0.6141870975494385,
      "step": 340
    },
    {
      "epoch": 0.02842870486943102,
      "grad_norm": 0.10461113601922989,
      "learning_rate": 0.00017732441471571907,
      "loss": 0.6277643203735351,
      "step": 350
    },
    {
      "epoch": 0.02924095357998619,
      "grad_norm": 0.11059945821762085,
      "learning_rate": 0.00017665551839464886,
      "loss": 0.650815773010254,
      "step": 360
    },
    {
      "epoch": 0.030053202290541363,
      "grad_norm": 0.1186944767832756,
      "learning_rate": 0.00017598662207357862,
      "loss": 0.6423202991485596,
      "step": 370
    },
    {
      "epoch": 0.030865451001096535,
      "grad_norm": 0.1306525617837906,
      "learning_rate": 0.00017531772575250839,
      "loss": 0.6001749038696289,
      "step": 380
    },
    {
      "epoch": 0.031677699711651706,
      "grad_norm": 0.12819500267505646,
      "learning_rate": 0.00017464882943143815,
      "loss": 0.6060415744781494,
      "step": 390
    },
    {
      "epoch": 0.03248994842220688,
      "grad_norm": 0.13138507306575775,
      "learning_rate": 0.0001739799331103679,
      "loss": 0.5925205707550049,
      "step": 400
    },
    {
      "epoch": 0.03330219713276205,
      "grad_norm": 0.14968585968017578,
      "learning_rate": 0.00017331103678929768,
      "loss": 0.6501868724822998,
      "step": 410
    },
    {
      "epoch": 0.03411444584331722,
      "grad_norm": 0.12787474691867828,
      "learning_rate": 0.00017264214046822744,
      "loss": 0.6108675956726074,
      "step": 420
    },
    {
      "epoch": 0.034926694553872394,
      "grad_norm": 0.13028663396835327,
      "learning_rate": 0.0001719732441471572,
      "loss": 0.6132050514221191,
      "step": 430
    },
    {
      "epoch": 0.035738943264427565,
      "grad_norm": 0.1314769834280014,
      "learning_rate": 0.00017130434782608697,
      "loss": 0.6264569759368896,
      "step": 440
    },
    {
      "epoch": 0.03655119197498274,
      "grad_norm": 0.11964884400367737,
      "learning_rate": 0.00017063545150501673,
      "loss": 0.6445899486541748,
      "step": 450
    },
    {
      "epoch": 0.03736344068553791,
      "grad_norm": 0.11594310402870178,
      "learning_rate": 0.0001699665551839465,
      "loss": 0.6022776603698731,
      "step": 460
    },
    {
      "epoch": 0.03817568939609308,
      "grad_norm": 0.11167627573013306,
      "learning_rate": 0.00016929765886287626,
      "loss": 0.6172833442687988,
      "step": 470
    },
    {
      "epoch": 0.03898793810664825,
      "grad_norm": 0.131842702627182,
      "learning_rate": 0.00016862876254180602,
      "loss": 0.6316081523895264,
      "step": 480
    },
    {
      "epoch": 0.039800186817203424,
      "grad_norm": 0.12949836254119873,
      "learning_rate": 0.0001679598662207358,
      "loss": 0.5979058742523193,
      "step": 490
    },
    {
      "epoch": 0.0406124355277586,
      "grad_norm": 0.1311161369085312,
      "learning_rate": 0.00016729096989966555,
      "loss": 0.6085984230041503,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 3000,
  "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": 3.351969772278866e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}