{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0812248710555172,
  "eval_steps": 500,
  "global_step": 1000,
  "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
    },
    {
      "epoch": 0.041424684238313775,
      "grad_norm": 0.11565863341093063,
      "learning_rate": 0.00016662207357859532,
      "loss": 0.5864393234252929,
      "step": 510
    },
    {
      "epoch": 0.04223693294886895,
      "grad_norm": 0.14647597074508667,
      "learning_rate": 0.00016595317725752508,
      "loss": 0.565390157699585,
      "step": 520
    },
    {
      "epoch": 0.04304918165942412,
      "grad_norm": 0.11932296305894852,
      "learning_rate": 0.00016528428093645484,
      "loss": 0.6000445365905762,
      "step": 530
    },
    {
      "epoch": 0.04386143036997929,
      "grad_norm": 0.14222687482833862,
      "learning_rate": 0.0001646153846153846,
      "loss": 0.6550194263458252,
      "step": 540
    },
    {
      "epoch": 0.04467367908053446,
      "grad_norm": 0.12822918593883514,
      "learning_rate": 0.00016394648829431437,
      "loss": 0.6483684062957764,
      "step": 550
    },
    {
      "epoch": 0.045485927791089634,
      "grad_norm": 0.13619735836982727,
      "learning_rate": 0.00016327759197324413,
      "loss": 0.6203540802001953,
      "step": 560
    },
    {
      "epoch": 0.046298176501644805,
      "grad_norm": 0.13233502209186554,
      "learning_rate": 0.00016260869565217393,
      "loss": 0.6185849189758301,
      "step": 570
    },
    {
      "epoch": 0.04711042521219998,
      "grad_norm": 0.12952451407909393,
      "learning_rate": 0.0001619397993311037,
      "loss": 0.5921258449554443,
      "step": 580
    },
    {
      "epoch": 0.04792267392275515,
      "grad_norm": 0.12617622315883636,
      "learning_rate": 0.00016127090301003345,
      "loss": 0.6221595287322998,
      "step": 590
    },
    {
      "epoch": 0.04873492263331032,
      "grad_norm": 0.10956388711929321,
      "learning_rate": 0.00016060200668896322,
      "loss": 0.599628210067749,
      "step": 600
    },
    {
      "epoch": 0.04954717134386549,
      "grad_norm": 0.11363332718610764,
      "learning_rate": 0.00015993311036789298,
      "loss": 0.5865818977355957,
      "step": 610
    },
    {
      "epoch": 0.050359420054420664,
      "grad_norm": 0.1252753585577011,
      "learning_rate": 0.00015926421404682275,
      "loss": 0.5941249847412109,
      "step": 620
    },
    {
      "epoch": 0.051171668764975836,
      "grad_norm": 0.12859514355659485,
      "learning_rate": 0.0001585953177257525,
      "loss": 0.598096513748169,
      "step": 630
    },
    {
      "epoch": 0.05198391747553101,
      "grad_norm": 0.11355341970920563,
      "learning_rate": 0.00015792642140468227,
      "loss": 0.6211743354797363,
      "step": 640
    },
    {
      "epoch": 0.05279616618608618,
      "grad_norm": 0.12344721704721451,
      "learning_rate": 0.00015725752508361204,
      "loss": 0.5909175395965576,
      "step": 650
    },
    {
      "epoch": 0.05360841489664135,
      "grad_norm": 0.1423984318971634,
      "learning_rate": 0.0001565886287625418,
      "loss": 0.5645668029785156,
      "step": 660
    },
    {
      "epoch": 0.05442066360719652,
      "grad_norm": 0.11847086995840073,
      "learning_rate": 0.00015591973244147156,
      "loss": 0.6111773014068603,
      "step": 670
    },
    {
      "epoch": 0.055232912317751695,
      "grad_norm": 0.10838636755943298,
      "learning_rate": 0.00015525083612040136,
      "loss": 0.598857069015503,
      "step": 680
    },
    {
      "epoch": 0.05604516102830687,
      "grad_norm": 0.12422847002744675,
      "learning_rate": 0.00015458193979933112,
      "loss": 0.6086232185363769,
      "step": 690
    },
    {
      "epoch": 0.05685740973886204,
      "grad_norm": 0.11844707280397415,
      "learning_rate": 0.00015391304347826088,
      "loss": 0.6083204269409179,
      "step": 700
    },
    {
      "epoch": 0.05766965844941721,
      "grad_norm": 0.12434474378824234,
      "learning_rate": 0.00015324414715719065,
      "loss": 0.5938045024871826,
      "step": 710
    },
    {
      "epoch": 0.05848190715997238,
      "grad_norm": 0.1373196393251419,
      "learning_rate": 0.0001525752508361204,
      "loss": 0.5924835205078125,
      "step": 720
    },
    {
      "epoch": 0.059294155870527554,
      "grad_norm": 0.1279742270708084,
      "learning_rate": 0.00015190635451505017,
      "loss": 0.5970086574554443,
      "step": 730
    },
    {
      "epoch": 0.060106404581082726,
      "grad_norm": 0.1276446133852005,
      "learning_rate": 0.00015123745819397994,
      "loss": 0.6073202610015869,
      "step": 740
    },
    {
      "epoch": 0.0609186532916379,
      "grad_norm": 0.15001341700553894,
      "learning_rate": 0.0001505685618729097,
      "loss": 0.5822910785675048,
      "step": 750
    },
    {
      "epoch": 0.06173090200219307,
      "grad_norm": 0.13396278023719788,
      "learning_rate": 0.00014989966555183947,
      "loss": 0.5936754226684571,
      "step": 760
    },
    {
      "epoch": 0.06254315071274824,
      "grad_norm": 0.21268559992313385,
      "learning_rate": 0.00014923076923076923,
      "loss": 0.6138639926910401,
      "step": 770
    },
    {
      "epoch": 0.06335539942330341,
      "grad_norm": 0.1419883519411087,
      "learning_rate": 0.000148561872909699,
      "loss": 0.6192237854003906,
      "step": 780
    },
    {
      "epoch": 0.06416764813385858,
      "grad_norm": 0.12715154886245728,
      "learning_rate": 0.00014789297658862879,
      "loss": 0.6032827377319336,
      "step": 790
    },
    {
      "epoch": 0.06497989684441376,
      "grad_norm": 0.14222534000873566,
      "learning_rate": 0.00014722408026755855,
      "loss": 0.5837327480316162,
      "step": 800
    },
    {
      "epoch": 0.06579214555496893,
      "grad_norm": 0.12761105597019196,
      "learning_rate": 0.0001465551839464883,
      "loss": 0.5880168437957763,
      "step": 810
    },
    {
      "epoch": 0.0666043942655241,
      "grad_norm": 0.13514447212219238,
      "learning_rate": 0.00014588628762541808,
      "loss": 0.6178320407867431,
      "step": 820
    },
    {
      "epoch": 0.06741664297607927,
      "grad_norm": 0.1156405657529831,
      "learning_rate": 0.00014521739130434784,
      "loss": 0.5975133895874023,
      "step": 830
    },
    {
      "epoch": 0.06822889168663444,
      "grad_norm": 0.13029585778713226,
      "learning_rate": 0.0001445484949832776,
      "loss": 0.6032638549804688,
      "step": 840
    },
    {
      "epoch": 0.06904114039718962,
      "grad_norm": 0.12680095434188843,
      "learning_rate": 0.00014387959866220737,
      "loss": 0.5651222705841065,
      "step": 850
    },
    {
      "epoch": 0.06985338910774479,
      "grad_norm": 0.14011035859584808,
      "learning_rate": 0.00014321070234113713,
      "loss": 0.5644700050354003,
      "step": 860
    },
    {
      "epoch": 0.07066563781829996,
      "grad_norm": 0.12153138220310211,
      "learning_rate": 0.0001425418060200669,
      "loss": 0.5840569019317627,
      "step": 870
    },
    {
      "epoch": 0.07147788652885513,
      "grad_norm": 0.13272343575954437,
      "learning_rate": 0.00014187290969899666,
      "loss": 0.6429564476013183,
      "step": 880
    },
    {
      "epoch": 0.0722901352394103,
      "grad_norm": 0.14595189690589905,
      "learning_rate": 0.00014120401337792642,
      "loss": 0.5844541072845459,
      "step": 890
    },
    {
      "epoch": 0.07310238394996547,
      "grad_norm": 0.1272500455379486,
      "learning_rate": 0.00014053511705685621,
      "loss": 0.6260814189910888,
      "step": 900
    },
    {
      "epoch": 0.07391463266052065,
      "grad_norm": 0.1340891271829605,
      "learning_rate": 0.00013986622073578598,
      "loss": 0.5867656707763672,
      "step": 910
    },
    {
      "epoch": 0.07472688137107582,
      "grad_norm": 0.14307370781898499,
      "learning_rate": 0.00013919732441471574,
      "loss": 0.577037000656128,
      "step": 920
    },
    {
      "epoch": 0.07553913008163099,
      "grad_norm": 0.15650159120559692,
      "learning_rate": 0.0001385284280936455,
      "loss": 0.6175992488861084,
      "step": 930
    },
    {
      "epoch": 0.07635137879218616,
      "grad_norm": 0.15327556431293488,
      "learning_rate": 0.00013785953177257527,
      "loss": 0.5842644691467285,
      "step": 940
    },
    {
      "epoch": 0.07716362750274133,
      "grad_norm": 0.12911345064640045,
      "learning_rate": 0.00013719063545150503,
      "loss": 0.5888010025024414,
      "step": 950
    },
    {
      "epoch": 0.0779758762132965,
      "grad_norm": 0.16856183111667633,
      "learning_rate": 0.00013652173913043477,
      "loss": 0.6148488521575928,
      "step": 960
    },
    {
      "epoch": 0.07878812492385168,
      "grad_norm": 0.1216643676161766,
      "learning_rate": 0.00013585284280936453,
      "loss": 0.5580620765686035,
      "step": 970
    },
    {
      "epoch": 0.07960037363440685,
      "grad_norm": 0.12570665776729584,
      "learning_rate": 0.0001351839464882943,
      "loss": 0.5656413078308106,
      "step": 980
    },
    {
      "epoch": 0.08041262234496203,
      "grad_norm": 0.1392045021057129,
      "learning_rate": 0.0001345150501672241,
      "loss": 0.6019979000091553,
      "step": 990
    },
    {
      "epoch": 0.0812248710555172,
      "grad_norm": 0.13696540892124176,
      "learning_rate": 0.00013384615384615385,
      "loss": 0.5685174465179443,
      "step": 1000
    }
  ],
  "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": 6.684342531125576e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}