{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.982758620689655,
  "eval_steps": 500,
  "global_step": 1159,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 4.288447380065918,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 1.24,
      "step": 10
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 3.9249799251556396,
      "learning_rate": 6.896551724137931e-05,
      "loss": 0.5159,
      "step": 20
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 1.7602132558822632,
      "learning_rate": 0.00010344827586206898,
      "loss": 0.3011,
      "step": 30
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.8162740468978882,
      "learning_rate": 0.00013793103448275863,
      "loss": 0.1873,
      "step": 40
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.7871344685554504,
      "learning_rate": 0.00017241379310344826,
      "loss": 0.1371,
      "step": 50
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 1.0209136009216309,
      "learning_rate": 0.00019999837162688113,
      "loss": 0.1282,
      "step": 60
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 0.5767734050750732,
      "learning_rate": 0.00019994138413588491,
      "loss": 0.117,
      "step": 70
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 0.9807557463645935,
      "learning_rate": 0.00019980303101316228,
      "loss": 0.1053,
      "step": 80
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 0.8148991465568542,
      "learning_rate": 0.00019958342489662917,
      "loss": 0.095,
      "step": 90
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 0.7483856678009033,
      "learning_rate": 0.00019928274457498818,
      "loss": 0.0823,
      "step": 100
    },
    {
      "epoch": 1.896551724137931,
      "grad_norm": 0.38755494356155396,
      "learning_rate": 0.00019890123484217056,
      "loss": 0.0852,
      "step": 110
    },
    {
      "epoch": 2.0689655172413794,
      "grad_norm": 0.40888020396232605,
      "learning_rate": 0.0001984392062980413,
      "loss": 0.0776,
      "step": 120
    },
    {
      "epoch": 2.2413793103448274,
      "grad_norm": 0.4752354919910431,
      "learning_rate": 0.00019789703509552945,
      "loss": 0.065,
      "step": 130
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 0.2943930923938751,
      "learning_rate": 0.00019727516263438918,
      "loss": 0.0703,
      "step": 140
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 0.3636096119880676,
      "learning_rate": 0.0001965740952018417,
      "loss": 0.0734,
      "step": 150
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 0.49514421820640564,
      "learning_rate": 0.00019579440356038967,
      "loss": 0.0685,
      "step": 160
    },
    {
      "epoch": 2.9310344827586206,
      "grad_norm": 0.7530002593994141,
      "learning_rate": 0.00019493672248314044,
      "loss": 0.0653,
      "step": 170
    },
    {
      "epoch": 3.103448275862069,
      "grad_norm": 0.4943099021911621,
      "learning_rate": 0.00019400175023701586,
      "loss": 0.0569,
      "step": 180
    },
    {
      "epoch": 3.2758620689655173,
      "grad_norm": 0.5510227084159851,
      "learning_rate": 0.00019299024801426994,
      "loss": 0.0612,
      "step": 190
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 0.4278947114944458,
      "learning_rate": 0.0001919030393127765,
      "loss": 0.0554,
      "step": 200
    },
    {
      "epoch": 3.6206896551724137,
      "grad_norm": 0.3584755063056946,
      "learning_rate": 0.0001907410092655921,
      "loss": 0.0599,
      "step": 210
    },
    {
      "epoch": 3.793103448275862,
      "grad_norm": 0.5437096953392029,
      "learning_rate": 0.00018950510392033945,
      "loss": 0.0597,
      "step": 220
    },
    {
      "epoch": 3.9655172413793105,
      "grad_norm": 0.3559582531452179,
      "learning_rate": 0.0001881963294689984,
      "loss": 0.0569,
      "step": 230
    },
    {
      "epoch": 4.137931034482759,
      "grad_norm": 0.4884796440601349,
      "learning_rate": 0.00018681575142873126,
      "loss": 0.0578,
      "step": 240
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 0.4382438659667969,
      "learning_rate": 0.0001853644937744095,
      "loss": 0.051,
      "step": 250
    },
    {
      "epoch": 4.482758620689655,
      "grad_norm": 0.34379124641418457,
      "learning_rate": 0.0001838437380235483,
      "loss": 0.0529,
      "step": 260
    },
    {
      "epoch": 4.655172413793103,
      "grad_norm": 0.5280494093894958,
      "learning_rate": 0.0001822547222743933,
      "loss": 0.0503,
      "step": 270
    },
    {
      "epoch": 4.827586206896552,
      "grad_norm": 0.3714671730995178,
      "learning_rate": 0.00018059874019794351,
      "loss": 0.0474,
      "step": 280
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.2870706617832184,
      "learning_rate": 0.00017887713998473022,
      "loss": 0.0473,
      "step": 290
    },
    {
      "epoch": 5.172413793103448,
      "grad_norm": 0.35148724913597107,
      "learning_rate": 0.00017709132324720997,
      "loss": 0.0492,
      "step": 300
    },
    {
      "epoch": 5.344827586206897,
      "grad_norm": 0.2515222728252411,
      "learning_rate": 0.00017524274387866484,
      "loss": 0.0462,
      "step": 310
    },
    {
      "epoch": 5.517241379310345,
      "grad_norm": 0.22452038526535034,
      "learning_rate": 0.00017333290686953915,
      "loss": 0.0414,
      "step": 320
    },
    {
      "epoch": 5.689655172413794,
      "grad_norm": 0.3675800561904907,
      "learning_rate": 0.00017136336708217632,
      "loss": 0.0483,
      "step": 330
    },
    {
      "epoch": 5.862068965517241,
      "grad_norm": 0.3029170334339142,
      "learning_rate": 0.00016933572798495328,
      "loss": 0.0553,
      "step": 340
    },
    {
      "epoch": 6.0344827586206895,
      "grad_norm": 0.2198949158191681,
      "learning_rate": 0.00016725164034684317,
      "loss": 0.0466,
      "step": 350
    },
    {
      "epoch": 6.206896551724138,
      "grad_norm": 0.1851377636194229,
      "learning_rate": 0.00016511280089346876,
      "loss": 0.0462,
      "step": 360
    },
    {
      "epoch": 6.379310344827586,
      "grad_norm": 0.3081173300743103,
      "learning_rate": 0.00016292095092574154,
      "loss": 0.0433,
      "step": 370
    },
    {
      "epoch": 6.551724137931035,
      "grad_norm": 0.2842998206615448,
      "learning_rate": 0.00016067787490221008,
      "loss": 0.0389,
      "step": 380
    },
    {
      "epoch": 6.724137931034483,
      "grad_norm": 0.31966182589530945,
      "learning_rate": 0.00015838539898627242,
      "loss": 0.04,
      "step": 390
    },
    {
      "epoch": 6.896551724137931,
      "grad_norm": 0.23094028234481812,
      "learning_rate": 0.0001560453895594354,
      "loss": 0.0395,
      "step": 400
    },
    {
      "epoch": 7.068965517241379,
      "grad_norm": 0.35125771164894104,
      "learning_rate": 0.00015365975170183085,
      "loss": 0.0445,
      "step": 410
    },
    {
      "epoch": 7.241379310344827,
      "grad_norm": 0.18835288286209106,
      "learning_rate": 0.00015123042764122584,
      "loss": 0.0391,
      "step": 420
    },
    {
      "epoch": 7.413793103448276,
      "grad_norm": 0.26209092140197754,
      "learning_rate": 0.00014875939517179016,
      "loss": 0.0433,
      "step": 430
    },
    {
      "epoch": 7.586206896551724,
      "grad_norm": 0.23597943782806396,
      "learning_rate": 0.00014624866604390758,
      "loss": 0.0383,
      "step": 440
    },
    {
      "epoch": 7.758620689655173,
      "grad_norm": 0.32963162660598755,
      "learning_rate": 0.00014370028432634252,
      "loss": 0.0438,
      "step": 450
    },
    {
      "epoch": 7.931034482758621,
      "grad_norm": 0.2865336537361145,
      "learning_rate": 0.00014111632474209505,
      "loss": 0.0367,
      "step": 460
    },
    {
      "epoch": 8.10344827586207,
      "grad_norm": 0.22742541134357452,
      "learning_rate": 0.0001384988909792995,
      "loss": 0.0366,
      "step": 470
    },
    {
      "epoch": 8.275862068965518,
      "grad_norm": 0.23098573088645935,
      "learning_rate": 0.00013585011397854117,
      "loss": 0.0418,
      "step": 480
    },
    {
      "epoch": 8.448275862068966,
      "grad_norm": 0.3277537524700165,
      "learning_rate": 0.00013317215019798638,
      "loss": 0.0391,
      "step": 490
    },
    {
      "epoch": 8.620689655172415,
      "grad_norm": 0.33878064155578613,
      "learning_rate": 0.00013046717985773745,
      "loss": 0.0401,
      "step": 500
    },
    {
      "epoch": 8.793103448275861,
      "grad_norm": 0.4036126434803009,
      "learning_rate": 0.00012773740516484235,
      "loss": 0.0369,
      "step": 510
    },
    {
      "epoch": 8.96551724137931,
      "grad_norm": 0.2406553477048874,
      "learning_rate": 0.00012498504852040434,
      "loss": 0.0357,
      "step": 520
    },
    {
      "epoch": 9.137931034482758,
      "grad_norm": 0.33557119965553284,
      "learning_rate": 0.00012221235071025046,
      "loss": 0.0366,
      "step": 530
    },
    {
      "epoch": 9.310344827586206,
      "grad_norm": 0.2251608818769455,
      "learning_rate": 0.00011942156908063284,
      "loss": 0.0387,
      "step": 540
    },
    {
      "epoch": 9.482758620689655,
      "grad_norm": 0.331117182970047,
      "learning_rate": 0.00011661497570044738,
      "loss": 0.0306,
      "step": 550
    },
    {
      "epoch": 9.655172413793103,
      "grad_norm": 0.1580682098865509,
      "learning_rate": 0.00011379485551146621,
      "loss": 0.0332,
      "step": 560
    },
    {
      "epoch": 9.827586206896552,
      "grad_norm": 0.21949926018714905,
      "learning_rate": 0.00011096350446808998,
      "loss": 0.0378,
      "step": 570
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.300108402967453,
      "learning_rate": 0.00010812322766813461,
      "loss": 0.0354,
      "step": 580
    },
    {
      "epoch": 10.172413793103448,
      "grad_norm": 0.2582547664642334,
      "learning_rate": 0.00010527633747617362,
      "loss": 0.0348,
      "step": 590
    },
    {
      "epoch": 10.344827586206897,
      "grad_norm": 0.3702482283115387,
      "learning_rate": 0.00010242515164096471,
      "loss": 0.0334,
      "step": 600
    },
    {
      "epoch": 10.517241379310345,
      "grad_norm": 0.2247171700000763,
      "learning_rate": 9.957199140849278e-05,
      "loss": 0.0313,
      "step": 610
    },
    {
      "epoch": 10.689655172413794,
      "grad_norm": 0.26956915855407715,
      "learning_rate": 9.671917963216574e-05,
      "loss": 0.0336,
      "step": 620
    },
    {
      "epoch": 10.862068965517242,
      "grad_norm": 0.19159068167209625,
      "learning_rate": 9.386903888170172e-05,
      "loss": 0.0311,
      "step": 630
    },
    {
      "epoch": 11.03448275862069,
      "grad_norm": 0.244057759642601,
      "learning_rate": 9.102388955224703e-05,
      "loss": 0.033,
      "step": 640
    },
    {
      "epoch": 11.206896551724139,
      "grad_norm": 0.24532181024551392,
      "learning_rate": 8.818604797526493e-05,
      "loss": 0.0365,
      "step": 650
    },
    {
      "epoch": 11.379310344827585,
      "grad_norm": 0.3451012670993805,
      "learning_rate": 8.535782453273217e-05,
      "loss": 0.0297,
      "step": 660
    },
    {
      "epoch": 11.551724137931034,
      "grad_norm": 0.28239578008651733,
      "learning_rate": 8.254152177618e-05,
      "loss": 0.0285,
      "step": 670
    },
    {
      "epoch": 11.724137931034482,
      "grad_norm": 0.2965984046459198,
      "learning_rate": 7.97394325521093e-05,
      "loss": 0.0303,
      "step": 680
    },
    {
      "epoch": 11.89655172413793,
      "grad_norm": 0.25484567880630493,
      "learning_rate": 7.695383813530776e-05,
      "loss": 0.0283,
      "step": 690
    },
    {
      "epoch": 12.068965517241379,
      "grad_norm": 0.15973417460918427,
      "learning_rate": 7.418700637158742e-05,
      "loss": 0.0324,
      "step": 700
    },
    {
      "epoch": 12.241379310344827,
      "grad_norm": 0.16871625185012817,
      "learning_rate": 7.144118983145521e-05,
      "loss": 0.029,
      "step": 710
    },
    {
      "epoch": 12.413793103448276,
      "grad_norm": 0.19246120750904083,
      "learning_rate": 6.871862397622005e-05,
      "loss": 0.0309,
      "step": 720
    },
    {
      "epoch": 12.586206896551724,
      "grad_norm": 0.28560781478881836,
      "learning_rate": 6.60215253380287e-05,
      "loss": 0.03,
      "step": 730
    },
    {
      "epoch": 12.758620689655173,
      "grad_norm": 0.2544420659542084,
      "learning_rate": 6.335208971531265e-05,
      "loss": 0.0338,
      "step": 740
    },
    {
      "epoch": 12.931034482758621,
      "grad_norm": 0.16777703166007996,
      "learning_rate": 6.071249038511497e-05,
      "loss": 0.03,
      "step": 750
    },
    {
      "epoch": 13.10344827586207,
      "grad_norm": 0.13849933445453644,
      "learning_rate": 5.810487633375261e-05,
      "loss": 0.03,
      "step": 760
    },
    {
      "epoch": 13.275862068965518,
      "grad_norm": 0.2304876148700714,
      "learning_rate": 5.553137050725459e-05,
      "loss": 0.032,
      "step": 770
    },
    {
      "epoch": 13.448275862068966,
      "grad_norm": 0.17199701070785522,
      "learning_rate": 5.2994068083000495e-05,
      "loss": 0.0324,
      "step": 780
    },
    {
      "epoch": 13.620689655172415,
      "grad_norm": 0.15231479704380035,
      "learning_rate": 5.049503476396627e-05,
      "loss": 0.0269,
      "step": 790
    },
    {
      "epoch": 13.793103448275861,
      "grad_norm": 0.20847296714782715,
      "learning_rate": 4.803630509696627e-05,
      "loss": 0.0276,
      "step": 800
    },
    {
      "epoch": 13.96551724137931,
      "grad_norm": 0.2147344946861267,
      "learning_rate": 4.561988081626023e-05,
      "loss": 0.0252,
      "step": 810
    },
    {
      "epoch": 14.137931034482758,
      "grad_norm": 0.1602960079908371,
      "learning_rate": 4.32477292138746e-05,
      "loss": 0.025,
      "step": 820
    },
    {
      "epoch": 14.310344827586206,
      "grad_norm": 0.19987209141254425,
      "learning_rate": 4.092178153796401e-05,
      "loss": 0.0268,
      "step": 830
    },
    {
      "epoch": 14.482758620689655,
      "grad_norm": 0.18080690503120422,
      "learning_rate": 3.8643931420517255e-05,
      "loss": 0.0279,
      "step": 840
    },
    {
      "epoch": 14.655172413793103,
      "grad_norm": 0.1728052943944931,
      "learning_rate": 3.641603333568831e-05,
      "loss": 0.0226,
      "step": 850
    },
    {
      "epoch": 14.827586206896552,
      "grad_norm": 0.19159851968288422,
      "learning_rate": 3.423990109000641e-05,
      "loss": 0.0281,
      "step": 860
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.17135493457317352,
      "learning_rate": 3.211730634569563e-05,
      "loss": 0.0291,
      "step": 870
    },
    {
      "epoch": 15.172413793103448,
      "grad_norm": 0.24832935631275177,
      "learning_rate": 3.0049977178305076e-05,
      "loss": 0.0277,
      "step": 880
    },
    {
      "epoch": 15.344827586206897,
      "grad_norm": 0.22584789991378784,
      "learning_rate": 2.803959666982474e-05,
      "loss": 0.025,
      "step": 890
    },
    {
      "epoch": 15.517241379310345,
      "grad_norm": 0.17386794090270996,
      "learning_rate": 2.60878015384319e-05,
      "loss": 0.0289,
      "step": 900
    },
    {
      "epoch": 15.689655172413794,
      "grad_norm": 0.16346997022628784,
      "learning_rate": 2.419618080598417e-05,
      "loss": 0.0207,
      "step": 910
    },
    {
      "epoch": 15.862068965517242,
      "grad_norm": 0.11085375398397446,
      "learning_rate": 2.23662745043433e-05,
      "loss": 0.0227,
      "step": 920
    },
    {
      "epoch": 16.03448275862069,
      "grad_norm": 0.1747630387544632,
      "learning_rate": 2.05995724215838e-05,
      "loss": 0.0257,
      "step": 930
    },
    {
      "epoch": 16.20689655172414,
      "grad_norm": 0.15860582888126373,
      "learning_rate": 1.889751288910645e-05,
      "loss": 0.0254,
      "step": 940
    },
    {
      "epoch": 16.379310344827587,
      "grad_norm": 0.15299658477306366,
      "learning_rate": 1.726148161064437e-05,
      "loss": 0.0251,
      "step": 950
    },
    {
      "epoch": 16.551724137931036,
      "grad_norm": 0.1972336769104004,
      "learning_rate": 1.569281053411532e-05,
      "loss": 0.0256,
      "step": 960
    },
    {
      "epoch": 16.724137931034484,
      "grad_norm": 0.13377782702445984,
      "learning_rate": 1.4192776767238158e-05,
      "loss": 0.0249,
      "step": 970
    },
    {
      "epoch": 16.896551724137932,
      "grad_norm": 0.17352934181690216,
      "learning_rate": 1.276260153779667e-05,
      "loss": 0.0231,
      "step": 980
    },
    {
      "epoch": 17.06896551724138,
      "grad_norm": 0.21800649166107178,
      "learning_rate": 1.1403449199396966e-05,
      "loss": 0.0279,
      "step": 990
    },
    {
      "epoch": 17.24137931034483,
      "grad_norm": 0.18025921285152435,
      "learning_rate": 1.0116426283528302e-05,
      "loss": 0.0227,
      "step": 1000
    },
    {
      "epoch": 17.413793103448278,
      "grad_norm": 0.17031840980052948,
      "learning_rate": 8.902580598698663e-06,
      "loss": 0.0208,
      "step": 1010
    },
    {
      "epoch": 17.586206896551722,
      "grad_norm": 0.12430210411548615,
      "learning_rate": 7.7629003773787e-06,
      "loss": 0.0269,
      "step": 1020
    },
    {
      "epoch": 17.75862068965517,
      "grad_norm": 0.17070575058460236,
      "learning_rate": 6.698313471448547e-06,
      "loss": 0.0209,
      "step": 1030
    },
    {
      "epoch": 17.93103448275862,
      "grad_norm": 0.17201951146125793,
      "learning_rate": 5.709686596802521e-06,
      "loss": 0.0218,
      "step": 1040
    },
    {
      "epoch": 18.103448275862068,
      "grad_norm": 0.10487387329339981,
      "learning_rate": 4.797824627726577e-06,
      "loss": 0.0201,
      "step": 1050
    },
    {
      "epoch": 18.275862068965516,
      "grad_norm": 0.14748798310756683,
      "learning_rate": 3.963469941623288e-06,
      "loss": 0.0202,
      "step": 1060
    },
    {
      "epoch": 18.448275862068964,
      "grad_norm": 0.1550891101360321,
      "learning_rate": 3.2073018146173805e-06,
      "loss": 0.0202,
      "step": 1070
    },
    {
      "epoch": 18.620689655172413,
      "grad_norm": 0.14703543484210968,
      "learning_rate": 2.529935868534372e-06,
      "loss": 0.0243,
      "step": 1080
    },
    {
      "epoch": 18.79310344827586,
      "grad_norm": 0.1516178995370865,
      "learning_rate": 1.9319235697021763e-06,
      "loss": 0.0207,
      "step": 1090
    },
    {
      "epoch": 18.96551724137931,
      "grad_norm": 0.12201597541570663,
      "learning_rate": 1.4137517799837852e-06,
      "loss": 0.0225,
      "step": 1100
    },
    {
      "epoch": 19.137931034482758,
      "grad_norm": 0.15553522109985352,
      "learning_rate": 9.758423604068312e-07,
      "loss": 0.0188,
      "step": 1110
    },
    {
      "epoch": 19.310344827586206,
      "grad_norm": 0.13390740752220154,
      "learning_rate": 6.185518277123214e-07,
      "loss": 0.0214,
      "step": 1120
    },
    {
      "epoch": 19.482758620689655,
      "grad_norm": 0.17719490826129913,
      "learning_rate": 3.421710641023923e-07,
      "loss": 0.0245,
      "step": 1130
    },
    {
      "epoch": 19.655172413793103,
      "grad_norm": 0.206907719373703,
      "learning_rate": 1.4692508042337682e-07,
      "loss": 0.0216,
      "step": 1140
    },
    {
      "epoch": 19.82758620689655,
      "grad_norm": 0.08690398931503296,
      "learning_rate": 3.2972832976918554e-08,
      "loss": 0.0197,
      "step": 1150
    },
    {
      "epoch": 19.982758620689655,
      "step": 1159,
      "total_flos": 8.16714982017792e+16,
      "train_loss": 0.05862578803655708,
      "train_runtime": 806.3047,
      "train_samples_per_second": 91.995,
      "train_steps_per_second": 1.437
    }
  ],
  "logging_steps": 10,
  "max_steps": 1159,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.16714982017792e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}