{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 200,
  "global_step": 3094,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032323232323232323,
      "grad_norm": 0.03605492040514946,
      "learning_rate": 5.806451612903226e-06,
      "loss": 0.4773341178894043,
      "step": 10
    },
    {
      "epoch": 0.006464646464646465,
      "grad_norm": 0.019345857203006744,
      "learning_rate": 1.2258064516129032e-05,
      "loss": 0.45131635665893555,
      "step": 20
    },
    {
      "epoch": 0.009696969696969697,
      "grad_norm": 0.013088575564324856,
      "learning_rate": 1.870967741935484e-05,
      "loss": 0.4297126293182373,
      "step": 30
    },
    {
      "epoch": 0.01292929292929293,
      "grad_norm": 0.011059993878006935,
      "learning_rate": 2.5161290322580645e-05,
      "loss": 0.41430253982543946,
      "step": 40
    },
    {
      "epoch": 0.01616161616161616,
      "grad_norm": 0.010876496322453022,
      "learning_rate": 3.161290322580645e-05,
      "loss": 0.399013614654541,
      "step": 50
    },
    {
      "epoch": 0.019393939393939394,
      "grad_norm": 0.00941646471619606,
      "learning_rate": 3.8064516129032254e-05,
      "loss": 0.394245982170105,
      "step": 60
    },
    {
      "epoch": 0.022626262626262626,
      "grad_norm": 0.011145997792482376,
      "learning_rate": 4.451612903225807e-05,
      "loss": 0.4129539966583252,
      "step": 70
    },
    {
      "epoch": 0.02585858585858586,
      "grad_norm": 0.009536129422485828,
      "learning_rate": 5.096774193548387e-05,
      "loss": 0.40581393241882324,
      "step": 80
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 0.008861752226948738,
      "learning_rate": 5.7419354838709685e-05,
      "loss": 0.381392502784729,
      "step": 90
    },
    {
      "epoch": 0.03232323232323232,
      "grad_norm": 0.010512659326195717,
      "learning_rate": 6.387096774193548e-05,
      "loss": 0.39757261276245115,
      "step": 100
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 0.010718696750700474,
      "learning_rate": 7.03225806451613e-05,
      "loss": 0.38897051811218264,
      "step": 110
    },
    {
      "epoch": 0.03878787878787879,
      "grad_norm": 0.010814059525728226,
      "learning_rate": 7.67741935483871e-05,
      "loss": 0.38843908309936526,
      "step": 120
    },
    {
      "epoch": 0.04202020202020202,
      "grad_norm": 0.010136906057596207,
      "learning_rate": 8.32258064516129e-05,
      "loss": 0.3926044225692749,
      "step": 130
    },
    {
      "epoch": 0.04525252525252525,
      "grad_norm": 0.009705257602036,
      "learning_rate": 8.967741935483871e-05,
      "loss": 0.3880144596099854,
      "step": 140
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 0.009561076760292053,
      "learning_rate": 9.612903225806452e-05,
      "loss": 0.3880956172943115,
      "step": 150
    },
    {
      "epoch": 0.05171717171717172,
      "grad_norm": 0.009765783324837685,
      "learning_rate": 9.999954295400999e-05,
      "loss": 0.39316844940185547,
      "step": 160
    },
    {
      "epoch": 0.05494949494949495,
      "grad_norm": 0.010105657391250134,
      "learning_rate": 9.999440128258112e-05,
      "loss": 0.38610661029815674,
      "step": 170
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 0.008919674903154373,
      "learning_rate": 9.998354722168459e-05,
      "loss": 0.3945873975753784,
      "step": 180
    },
    {
      "epoch": 0.061414141414141414,
      "grad_norm": 0.009847168810665607,
      "learning_rate": 9.996698201151175e-05,
      "loss": 0.4054004669189453,
      "step": 190
    },
    {
      "epoch": 0.06464646464646465,
      "grad_norm": 0.008714244700968266,
      "learning_rate": 9.994470754481315e-05,
      "loss": 0.3861499786376953,
      "step": 200
    },
    {
      "epoch": 0.06787878787878789,
      "grad_norm": 0.009142388589680195,
      "learning_rate": 9.991672636668239e-05,
      "loss": 0.39889438152313234,
      "step": 210
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.008630151860415936,
      "learning_rate": 9.988304167426519e-05,
      "loss": 0.37990422248840333,
      "step": 220
    },
    {
      "epoch": 0.07434343434343435,
      "grad_norm": 0.008543030358850956,
      "learning_rate": 9.984365731639419e-05,
      "loss": 0.3961310386657715,
      "step": 230
    },
    {
      "epoch": 0.07757575757575758,
      "grad_norm": 0.009128885343670845,
      "learning_rate": 9.979857779314906e-05,
      "loss": 0.38288607597351076,
      "step": 240
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 0.007948827929794788,
      "learning_rate": 9.974780825534246e-05,
      "loss": 0.39522628784179686,
      "step": 250
    },
    {
      "epoch": 0.08404040404040404,
      "grad_norm": 0.009197822771966457,
      "learning_rate": 9.969135450393141e-05,
      "loss": 0.38869237899780273,
      "step": 260
    },
    {
      "epoch": 0.08727272727272728,
      "grad_norm": 0.00922387931495905,
      "learning_rate": 9.96292229893545e-05,
      "loss": 0.38947885036468505,
      "step": 270
    },
    {
      "epoch": 0.0905050505050505,
      "grad_norm": 0.008089344948530197,
      "learning_rate": 9.956142081079484e-05,
      "loss": 0.3940277576446533,
      "step": 280
    },
    {
      "epoch": 0.09373737373737374,
      "grad_norm": 0.008494450710713863,
      "learning_rate": 9.948795571536891e-05,
      "loss": 0.3915890693664551,
      "step": 290
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 0.008135691285133362,
      "learning_rate": 9.94088360972414e-05,
      "loss": 0.37494850158691406,
      "step": 300
    },
    {
      "epoch": 0.10020202020202021,
      "grad_norm": 0.008869413286447525,
      "learning_rate": 9.932407099666608e-05,
      "loss": 0.4039336681365967,
      "step": 310
    },
    {
      "epoch": 0.10343434343434343,
      "grad_norm": 0.00836237333714962,
      "learning_rate": 9.923367009895274e-05,
      "loss": 0.3808545351028442,
      "step": 320
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.008709998801350594,
      "learning_rate": 9.913764373336079e-05,
      "loss": 0.3846753597259521,
      "step": 330
    },
    {
      "epoch": 0.1098989898989899,
      "grad_norm": 0.008051419630646706,
      "learning_rate": 9.903600287191875e-05,
      "loss": 0.3809442281723022,
      "step": 340
    },
    {
      "epoch": 0.11313131313131314,
      "grad_norm": 0.008488772436976433,
      "learning_rate": 9.892875912817079e-05,
      "loss": 0.39042062759399415,
      "step": 350
    },
    {
      "epoch": 0.11636363636363636,
      "grad_norm": 0.007915249094367027,
      "learning_rate": 9.881592475584964e-05,
      "loss": 0.37756659984588625,
      "step": 360
    },
    {
      "epoch": 0.1195959595959596,
      "grad_norm": 0.008581338450312614,
      "learning_rate": 9.869751264747656e-05,
      "loss": 0.3929391145706177,
      "step": 370
    },
    {
      "epoch": 0.12282828282828283,
      "grad_norm": 0.008737748488783836,
      "learning_rate": 9.857353633288814e-05,
      "loss": 0.3863339424133301,
      "step": 380
    },
    {
      "epoch": 0.12606060606060607,
      "grad_norm": 0.008519729599356651,
      "learning_rate": 9.844400997769043e-05,
      "loss": 0.38788180351257323,
      "step": 390
    },
    {
      "epoch": 0.1292929292929293,
      "grad_norm": 0.008482911624014378,
      "learning_rate": 9.83089483816404e-05,
      "loss": 0.3903486967086792,
      "step": 400
    },
    {
      "epoch": 0.13252525252525252,
      "grad_norm": 0.008296508342027664,
      "learning_rate": 9.816836697695482e-05,
      "loss": 0.39067506790161133,
      "step": 410
    },
    {
      "epoch": 0.13575757575757577,
      "grad_norm": 0.009947331622242928,
      "learning_rate": 9.802228182654702e-05,
      "loss": 0.3869569540023804,
      "step": 420
    },
    {
      "epoch": 0.138989898989899,
      "grad_norm": 0.008398473262786865,
      "learning_rate": 9.787070962219156e-05,
      "loss": 0.3667590618133545,
      "step": 430
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.00859450176358223,
      "learning_rate": 9.771366768261696e-05,
      "loss": 0.38375401496887207,
      "step": 440
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.008234560489654541,
      "learning_rate": 9.755117395152689e-05,
      "loss": 0.3801938533782959,
      "step": 450
    },
    {
      "epoch": 0.1486868686868687,
      "grad_norm": 0.008372402749955654,
      "learning_rate": 9.73832469955499e-05,
      "loss": 0.3815694570541382,
      "step": 460
    },
    {
      "epoch": 0.15191919191919193,
      "grad_norm": 0.008638300001621246,
      "learning_rate": 9.720990600211797e-05,
      "loss": 0.38620219230651853,
      "step": 470
    },
    {
      "epoch": 0.15515151515151515,
      "grad_norm": 0.008054033853113651,
      "learning_rate": 9.703117077727419e-05,
      "loss": 0.36687431335449217,
      "step": 480
    },
    {
      "epoch": 0.15838383838383838,
      "grad_norm": 0.008317321538925171,
      "learning_rate": 9.684706174340965e-05,
      "loss": 0.3756044626235962,
      "step": 490
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.008002839982509613,
      "learning_rate": 9.665759993693e-05,
      "loss": 0.3840150833129883,
      "step": 500
    },
    {
      "epoch": 0.16484848484848486,
      "grad_norm": 0.008865526877343655,
      "learning_rate": 9.646280700585185e-05,
      "loss": 0.38756704330444336,
      "step": 510
    },
    {
      "epoch": 0.16808080808080808,
      "grad_norm": 0.009027686901390553,
      "learning_rate": 9.626270520732916e-05,
      "loss": 0.3690171241760254,
      "step": 520
    },
    {
      "epoch": 0.1713131313131313,
      "grad_norm": 0.009051651693880558,
      "learning_rate": 9.605731740511022e-05,
      "loss": 0.38026604652404783,
      "step": 530
    },
    {
      "epoch": 0.17454545454545456,
      "grad_norm": 0.008543914183974266,
      "learning_rate": 9.584666706692517e-05,
      "loss": 0.3790082216262817,
      "step": 540
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.008143576793372631,
      "learning_rate": 9.56307782618046e-05,
      "loss": 0.36831059455871584,
      "step": 550
    },
    {
      "epoch": 0.181010101010101,
      "grad_norm": 0.008094793185591698,
      "learning_rate": 9.540967565732937e-05,
      "loss": 0.39109277725219727,
      "step": 560
    },
    {
      "epoch": 0.18424242424242424,
      "grad_norm": 0.007765405345708132,
      "learning_rate": 9.51833845168121e-05,
      "loss": 0.38657331466674805,
      "step": 570
    },
    {
      "epoch": 0.1874747474747475,
      "grad_norm": 0.008732021786272526,
      "learning_rate": 9.495193069641057e-05,
      "loss": 0.375126314163208,
      "step": 580
    },
    {
      "epoch": 0.1907070707070707,
      "grad_norm": 0.008094674907624722,
      "learning_rate": 9.47153406421734e-05,
      "loss": 0.3850594997406006,
      "step": 590
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": 0.00792758259922266,
      "learning_rate": 9.447364138701823e-05,
      "loss": 0.3871599674224854,
      "step": 600
    },
    {
      "epoch": 0.19717171717171716,
      "grad_norm": 0.007575330324470997,
      "learning_rate": 9.422686054764302e-05,
      "loss": 0.37601659297943113,
      "step": 610
    },
    {
      "epoch": 0.20040404040404042,
      "grad_norm": 0.008024236187338829,
      "learning_rate": 9.397502632137055e-05,
      "loss": 0.3801377773284912,
      "step": 620
    },
    {
      "epoch": 0.20363636363636364,
      "grad_norm": 0.00865199789404869,
      "learning_rate": 9.371816748292641e-05,
      "loss": 0.37289042472839357,
      "step": 630
    },
    {
      "epoch": 0.20686868686868687,
      "grad_norm": 0.008158660493791103,
      "learning_rate": 9.345631338115141e-05,
      "loss": 0.3836984395980835,
      "step": 640
    },
    {
      "epoch": 0.2101010101010101,
      "grad_norm": 0.009124912321567535,
      "learning_rate": 9.318949393564807e-05,
      "loss": 0.3835611820220947,
      "step": 650
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.008734654635190964,
      "learning_rate": 9.291773963336193e-05,
      "loss": 0.3856090545654297,
      "step": 660
    },
    {
      "epoch": 0.21656565656565657,
      "grad_norm": 0.0075140586122870445,
      "learning_rate": 9.264108152509816e-05,
      "loss": 0.3813042163848877,
      "step": 670
    },
    {
      "epoch": 0.2197979797979798,
      "grad_norm": 0.008879176340997219,
      "learning_rate": 9.235955122197368e-05,
      "loss": 0.3917116165161133,
      "step": 680
    },
    {
      "epoch": 0.22303030303030302,
      "grad_norm": 0.008145987056195736,
      "learning_rate": 9.207318089180524e-05,
      "loss": 0.38028013706207275,
      "step": 690
    },
    {
      "epoch": 0.22626262626262628,
      "grad_norm": 0.007830113172531128,
      "learning_rate": 9.178200325543384e-05,
      "loss": 0.37664792537689207,
      "step": 700
    },
    {
      "epoch": 0.2294949494949495,
      "grad_norm": 0.008120265789330006,
      "learning_rate": 9.148605158298621e-05,
      "loss": 0.36904723644256593,
      "step": 710
    },
    {
      "epoch": 0.23272727272727273,
      "grad_norm": 0.00862862542271614,
      "learning_rate": 9.118535969007314e-05,
      "loss": 0.3809346675872803,
      "step": 720
    },
    {
      "epoch": 0.23595959595959595,
      "grad_norm": 0.00880429707467556,
      "learning_rate": 9.087996193392578e-05,
      "loss": 0.38595972061157224,
      "step": 730
    },
    {
      "epoch": 0.2391919191919192,
      "grad_norm": 0.008185146376490593,
      "learning_rate": 9.056989320947e-05,
      "loss": 0.3923794269561768,
      "step": 740
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.0071869189850986,
      "learning_rate": 9.025518894533921e-05,
      "loss": 0.38382692337036134,
      "step": 750
    },
    {
      "epoch": 0.24565656565656566,
      "grad_norm": 0.008295041508972645,
      "learning_rate": 8.99358850998263e-05,
      "loss": 0.3738658666610718,
      "step": 760
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 0.007510303985327482,
      "learning_rate": 8.9612018156775e-05,
      "loss": 0.3734901905059814,
      "step": 770
    },
    {
      "epoch": 0.25212121212121213,
      "grad_norm": 0.007918701507151127,
      "learning_rate": 8.928362512141124e-05,
      "loss": 0.3856965065002441,
      "step": 780
    },
    {
      "epoch": 0.25535353535353533,
      "grad_norm": 0.008347084745764732,
      "learning_rate": 8.895074351611488e-05,
      "loss": 0.3775136470794678,
      "step": 790
    },
    {
      "epoch": 0.2585858585858586,
      "grad_norm": 0.007822258397936821,
      "learning_rate": 8.861341137613242e-05,
      "loss": 0.3710262060165405,
      "step": 800
    },
    {
      "epoch": 0.26181818181818184,
      "grad_norm": 0.008437932468950748,
      "learning_rate": 8.827166724523105e-05,
      "loss": 0.38133988380432127,
      "step": 810
    },
    {
      "epoch": 0.26505050505050504,
      "grad_norm": 0.008143547922372818,
      "learning_rate": 8.792555017129461e-05,
      "loss": 0.38831157684326173,
      "step": 820
    },
    {
      "epoch": 0.2682828282828283,
      "grad_norm": 0.008261593990027905,
      "learning_rate": 8.757509970186196e-05,
      "loss": 0.3812253475189209,
      "step": 830
    },
    {
      "epoch": 0.27151515151515154,
      "grad_norm": 0.007986029610037804,
      "learning_rate": 8.722035587960826e-05,
      "loss": 0.3840745449066162,
      "step": 840
    },
    {
      "epoch": 0.27474747474747474,
      "grad_norm": 0.008006410673260689,
      "learning_rate": 8.686135923776969e-05,
      "loss": 0.389667272567749,
      "step": 850
    },
    {
      "epoch": 0.277979797979798,
      "grad_norm": 0.008182629942893982,
      "learning_rate": 8.649815079551205e-05,
      "loss": 0.3824803113937378,
      "step": 860
    },
    {
      "epoch": 0.2812121212121212,
      "grad_norm": 0.0076688132248818874,
      "learning_rate": 8.613077205324389e-05,
      "loss": 0.36859698295593263,
      "step": 870
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.0075200945138931274,
      "learning_rate": 8.575926498787476e-05,
      "loss": 0.37808995246887206,
      "step": 880
    },
    {
      "epoch": 0.2876767676767677,
      "grad_norm": 0.00802092906087637,
      "learning_rate": 8.538367204801872e-05,
      "loss": 0.3732459545135498,
      "step": 890
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.008313149213790894,
      "learning_rate": 8.500403614914432e-05,
      "loss": 0.36839566230773924,
      "step": 900
    },
    {
      "epoch": 0.29414141414141415,
      "grad_norm": 0.0081673264503479,
      "learning_rate": 8.462040066867089e-05,
      "loss": 0.3731460332870483,
      "step": 910
    },
    {
      "epoch": 0.2973737373737374,
      "grad_norm": 0.007819955237209797,
      "learning_rate": 8.423280944101233e-05,
      "loss": 0.3801119804382324,
      "step": 920
    },
    {
      "epoch": 0.3006060606060606,
      "grad_norm": 0.008252877742052078,
      "learning_rate": 8.384130675256852e-05,
      "loss": 0.36914944648742676,
      "step": 930
    },
    {
      "epoch": 0.30383838383838385,
      "grad_norm": 0.008051907643675804,
      "learning_rate": 8.34459373366651e-05,
      "loss": 0.37649900913238527,
      "step": 940
    },
    {
      "epoch": 0.30707070707070705,
      "grad_norm": 0.007895972579717636,
      "learning_rate": 8.304674636844231e-05,
      "loss": 0.3798959255218506,
      "step": 950
    },
    {
      "epoch": 0.3103030303030303,
      "grad_norm": 0.0086957523599267,
      "learning_rate": 8.264377945969312e-05,
      "loss": 0.393034553527832,
      "step": 960
    },
    {
      "epoch": 0.31353535353535356,
      "grad_norm": 0.008488897234201431,
      "learning_rate": 8.223708265365174e-05,
      "loss": 0.3909647226333618,
      "step": 970
    },
    {
      "epoch": 0.31676767676767675,
      "grad_norm": 0.008450930006802082,
      "learning_rate": 8.182670241973253e-05,
      "loss": 0.37601802349090574,
      "step": 980
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.008603021502494812,
      "learning_rate": 8.141268564822053e-05,
      "loss": 0.39119911193847656,
      "step": 990
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.008219755254685879,
      "learning_rate": 8.099507964491369e-05,
      "loss": 0.36634268760681155,
      "step": 1000
    },
    {
      "epoch": 0.32646464646464646,
      "grad_norm": 0.008747057989239693,
      "learning_rate": 8.057393212571767e-05,
      "loss": 0.390001916885376,
      "step": 1010
    },
    {
      "epoch": 0.3296969696969697,
      "grad_norm": 0.009628907777369022,
      "learning_rate": 8.014929121119378e-05,
      "loss": 0.3795316696166992,
      "step": 1020
    },
    {
      "epoch": 0.3329292929292929,
      "grad_norm": 0.007869881577789783,
      "learning_rate": 7.972120542106077e-05,
      "loss": 0.37975897789001467,
      "step": 1030
    },
    {
      "epoch": 0.33616161616161616,
      "grad_norm": 0.00830437894910574,
      "learning_rate": 7.92897236686508e-05,
      "loss": 0.3775317192077637,
      "step": 1040
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": 0.008555877953767776,
      "learning_rate": 7.885489525532075e-05,
      "loss": 0.3789222240447998,
      "step": 1050
    },
    {
      "epoch": 0.3426262626262626,
      "grad_norm": 0.01898166537284851,
      "learning_rate": 7.84167698648189e-05,
      "loss": 0.3830681085586548,
      "step": 1060
    },
    {
      "epoch": 0.34585858585858587,
      "grad_norm": 0.008047427050769329,
      "learning_rate": 7.797539755760805e-05,
      "loss": 0.3770411968231201,
      "step": 1070
    },
    {
      "epoch": 0.3490909090909091,
      "grad_norm": 0.0074907769449055195,
      "learning_rate": 7.753082876514562e-05,
      "loss": 0.3806899547576904,
      "step": 1080
    },
    {
      "epoch": 0.3523232323232323,
      "grad_norm": 0.00827647466212511,
      "learning_rate": 7.708311428412129e-05,
      "loss": 0.37074985504150393,
      "step": 1090
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.008136745542287827,
      "learning_rate": 7.663230527065293e-05,
      "loss": 0.37122316360473634,
      "step": 1100
    },
    {
      "epoch": 0.35878787878787877,
      "grad_norm": 0.008221322670578957,
      "learning_rate": 7.617845323444156e-05,
      "loss": 0.38070154190063477,
      "step": 1110
    },
    {
      "epoch": 0.362020202020202,
      "grad_norm": 0.008503571152687073,
      "learning_rate": 7.572161003288565e-05,
      "loss": 0.3785174608230591,
      "step": 1120
    },
    {
      "epoch": 0.3652525252525253,
      "grad_norm": 0.009484554640948772,
      "learning_rate": 7.526182786515609e-05,
      "loss": 0.37593255043029783,
      "step": 1130
    },
    {
      "epoch": 0.36848484848484847,
      "grad_norm": 0.008690858259797096,
      "learning_rate": 7.479915926623165e-05,
      "loss": 0.3795978307723999,
      "step": 1140
    },
    {
      "epoch": 0.3717171717171717,
      "grad_norm": 0.008204210549592972,
      "learning_rate": 7.433365710089646e-05,
      "loss": 0.3610103130340576,
      "step": 1150
    },
    {
      "epoch": 0.374949494949495,
      "grad_norm": 0.008487153798341751,
      "learning_rate": 7.386537455769963e-05,
      "loss": 0.380059027671814,
      "step": 1160
    },
    {
      "epoch": 0.3781818181818182,
      "grad_norm": 0.008578482083976269,
      "learning_rate": 7.339436514287783e-05,
      "loss": 0.377803635597229,
      "step": 1170
    },
    {
      "epoch": 0.3814141414141414,
      "grad_norm": 0.007899395190179348,
      "learning_rate": 7.292068267424165e-05,
      "loss": 0.3671201229095459,
      "step": 1180
    },
    {
      "epoch": 0.3846464646464646,
      "grad_norm": 0.009204370900988579,
      "learning_rate": 7.244438127502647e-05,
      "loss": 0.3741163969039917,
      "step": 1190
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": 0.008694990538060665,
      "learning_rate": 7.196551536770807e-05,
      "loss": 0.3826310396194458,
      "step": 1200
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 0.008572017773985863,
      "learning_rate": 7.148413966778451e-05,
      "loss": 0.381903338432312,
      "step": 1210
    },
    {
      "epoch": 0.39434343434343433,
      "grad_norm": 0.008069795556366444,
      "learning_rate": 7.100030917752423e-05,
      "loss": 0.38312816619873047,
      "step": 1220
    },
    {
      "epoch": 0.3975757575757576,
      "grad_norm": 0.007709018420428038,
      "learning_rate": 7.051407917968138e-05,
      "loss": 0.3835233211517334,
      "step": 1230
    },
    {
      "epoch": 0.40080808080808084,
      "grad_norm": 0.007809523958712816,
      "learning_rate": 7.002550523117926e-05,
      "loss": 0.37577004432678224,
      "step": 1240
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.008419531397521496,
      "learning_rate": 6.953464315676241e-05,
      "loss": 0.37052106857299805,
      "step": 1250
    },
    {
      "epoch": 0.4072727272727273,
      "grad_norm": 0.009041344746947289,
      "learning_rate": 6.904154904261792e-05,
      "loss": 0.3696247339248657,
      "step": 1260
    },
    {
      "epoch": 0.4105050505050505,
      "grad_norm": 0.00816253386437893,
      "learning_rate": 6.8546279229967e-05,
      "loss": 0.38099074363708496,
      "step": 1270
    },
    {
      "epoch": 0.41373737373737374,
      "grad_norm": 0.008244721218943596,
      "learning_rate": 6.804889030862753e-05,
      "loss": 0.37920713424682617,
      "step": 1280
    },
    {
      "epoch": 0.416969696969697,
      "grad_norm": 0.007987082935869694,
      "learning_rate": 6.754943911054793e-05,
      "loss": 0.3793349742889404,
      "step": 1290
    },
    {
      "epoch": 0.4202020202020202,
      "grad_norm": 0.008034025318920612,
      "learning_rate": 6.704798270331358e-05,
      "loss": 0.37303624153137205,
      "step": 1300
    },
    {
      "epoch": 0.42343434343434344,
      "grad_norm": 0.008346694521605968,
      "learning_rate": 6.654457838362621e-05,
      "loss": 0.3781913757324219,
      "step": 1310
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.008833488449454308,
      "learning_rate": 6.603928367075718e-05,
      "loss": 0.3740977764129639,
      "step": 1320
    },
    {
      "epoch": 0.4298989898989899,
      "grad_norm": 0.00850659143179655,
      "learning_rate": 6.553215629997529e-05,
      "loss": 0.37595219612121583,
      "step": 1330
    },
    {
      "epoch": 0.43313131313131314,
      "grad_norm": 0.008206614293158054,
      "learning_rate": 6.502325421594988e-05,
      "loss": 0.3707082271575928,
      "step": 1340
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.008460193872451782,
      "learning_rate": 6.451263556613007e-05,
      "loss": 0.37059659957885743,
      "step": 1350
    },
    {
      "epoch": 0.4395959595959596,
      "grad_norm": 0.007676625624299049,
      "learning_rate": 6.40003586941008e-05,
      "loss": 0.37028162479400634,
      "step": 1360
    },
    {
      "epoch": 0.44282828282828285,
      "grad_norm": 0.00827883929014206,
      "learning_rate": 6.348648213291642e-05,
      "loss": 0.38210372924804686,
      "step": 1370
    },
    {
      "epoch": 0.44606060606060605,
      "grad_norm": 0.008517625741660595,
      "learning_rate": 6.297106459841272e-05,
      "loss": 0.37311854362487795,
      "step": 1380
    },
    {
      "epoch": 0.4492929292929293,
      "grad_norm": 0.007962854579091072,
      "learning_rate": 6.245416498249801e-05,
      "loss": 0.3756999969482422,
      "step": 1390
    },
    {
      "epoch": 0.45252525252525255,
      "grad_norm": 0.008170384913682938,
      "learning_rate": 6.193584234642403e-05,
      "loss": 0.36833963394165037,
      "step": 1400
    },
    {
      "epoch": 0.45575757575757575,
      "grad_norm": 0.008493859320878983,
      "learning_rate": 6.141615591403771e-05,
      "loss": 0.3753085136413574,
      "step": 1410
    },
    {
      "epoch": 0.458989898989899,
      "grad_norm": 0.008191689848899841,
      "learning_rate": 6.0895165065014106e-05,
      "loss": 0.3819756269454956,
      "step": 1420
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.008063061162829399,
      "learning_rate": 6.037292932807167e-05,
      "loss": 0.38694086074829104,
      "step": 1430
    },
    {
      "epoch": 0.46545454545454545,
      "grad_norm": 0.009821748360991478,
      "learning_rate": 5.984950837417048e-05,
      "loss": 0.36938455104827883,
      "step": 1440
    },
    {
      "epoch": 0.4686868686868687,
      "grad_norm": 0.008381606079638004,
      "learning_rate": 5.932496200969422e-05,
      "loss": 0.37668848037719727,
      "step": 1450
    },
    {
      "epoch": 0.4719191919191919,
      "grad_norm": 0.008244876749813557,
      "learning_rate": 5.879935016961661e-05,
      "loss": 0.38069169521331786,
      "step": 1460
    },
    {
      "epoch": 0.47515151515151516,
      "grad_norm": 0.008627382107079029,
      "learning_rate": 5.827273291065326e-05,
      "loss": 0.37565131187438966,
      "step": 1470
    },
    {
      "epoch": 0.4783838383838384,
      "grad_norm": 0.008732340298593044,
      "learning_rate": 5.7745170404399484e-05,
      "loss": 0.379933762550354,
      "step": 1480
    },
    {
      "epoch": 0.4816161616161616,
      "grad_norm": 0.008591915480792522,
      "learning_rate": 5.721672293045518e-05,
      "loss": 0.3786482810974121,
      "step": 1490
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.008559978567063808,
      "learning_rate": 5.668745086953712e-05,
      "loss": 0.37692484855651853,
      "step": 1500
    },
    {
      "epoch": 0.48808080808080806,
      "grad_norm": 0.008458509109914303,
      "learning_rate": 5.615741469657985e-05,
      "loss": 0.3862480878829956,
      "step": 1510
    },
    {
      "epoch": 0.4913131313131313,
      "grad_norm": 0.00866667926311493,
      "learning_rate": 5.562667497382582e-05,
      "loss": 0.3674156188964844,
      "step": 1520
    },
    {
      "epoch": 0.49454545454545457,
      "grad_norm": 0.00853388849645853,
      "learning_rate": 5.509529234390553e-05,
      "loss": 0.38260979652404786,
      "step": 1530
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.008287868462502956,
      "learning_rate": 5.456332752290837e-05,
      "loss": 0.36568374633789064,
      "step": 1540
    },
    {
      "epoch": 0.501010101010101,
      "grad_norm": 0.008751815184950829,
      "learning_rate": 5.4030841293445244e-05,
      "loss": 0.37983543872833253,
      "step": 1550
    },
    {
      "epoch": 0.5042424242424243,
      "grad_norm": 0.007895979098975658,
      "learning_rate": 5.349789449770351e-05,
      "loss": 0.3738078594207764,
      "step": 1560
    },
    {
      "epoch": 0.5074747474747475,
      "grad_norm": 0.008043098263442516,
      "learning_rate": 5.2964548030495065e-05,
      "loss": 0.3763037919998169,
      "step": 1570
    },
    {
      "epoch": 0.5107070707070707,
      "grad_norm": 0.00858687050640583,
      "learning_rate": 5.243086283229852e-05,
      "loss": 0.3780511856079102,
      "step": 1580
    },
    {
      "epoch": 0.5139393939393939,
      "grad_norm": 0.00860162265598774,
      "learning_rate": 5.18968998822961e-05,
      "loss": 0.37319676876068114,
      "step": 1590
    },
    {
      "epoch": 0.5171717171717172,
      "grad_norm": 0.009063811041414738,
      "learning_rate": 5.1362720191406065e-05,
      "loss": 0.3769842624664307,
      "step": 1600
    },
    {
      "epoch": 0.5204040404040404,
      "grad_norm": 0.009149775840342045,
      "learning_rate": 5.082838479531169e-05,
      "loss": 0.3767851829528809,
      "step": 1610
    },
    {
      "epoch": 0.5236363636363637,
      "grad_norm": 0.007992517203092575,
      "learning_rate": 5.029395474748714e-05,
      "loss": 0.3868858814239502,
      "step": 1620
    },
    {
      "epoch": 0.5268686868686868,
      "grad_norm": 0.008455543778836727,
      "learning_rate": 4.975949111222158e-05,
      "loss": 0.37787058353424074,
      "step": 1630
    },
    {
      "epoch": 0.5301010101010101,
      "grad_norm": 0.008353844285011292,
      "learning_rate": 4.9225054957641916e-05,
      "loss": 0.366853141784668,
      "step": 1640
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.008381880819797516,
      "learning_rate": 4.8690707348735035e-05,
      "loss": 0.3768073558807373,
      "step": 1650
    },
    {
      "epoch": 0.5365656565656566,
      "grad_norm": 0.00869447086006403,
      "learning_rate": 4.8156509340370605e-05,
      "loss": 0.3740663766860962,
      "step": 1660
    },
    {
      "epoch": 0.5397979797979798,
      "grad_norm": 0.00835113599896431,
      "learning_rate": 4.762252197032482e-05,
      "loss": 0.3748412847518921,
      "step": 1670
    },
    {
      "epoch": 0.5430303030303031,
      "grad_norm": 0.008712276816368103,
      "learning_rate": 4.7088806252306224e-05,
      "loss": 0.3652827262878418,
      "step": 1680
    },
    {
      "epoch": 0.5462626262626262,
      "grad_norm": 0.008263722993433475,
      "learning_rate": 4.655542316898423e-05,
      "loss": 0.35825161933898925,
      "step": 1690
    },
    {
      "epoch": 0.5494949494949495,
      "grad_norm": 0.008255276829004288,
      "learning_rate": 4.6022433665021246e-05,
      "loss": 0.3670318603515625,
      "step": 1700
    },
    {
      "epoch": 0.5527272727272727,
      "grad_norm": 0.008898588828742504,
      "learning_rate": 4.548989864010902e-05,
      "loss": 0.37490177154541016,
      "step": 1710
    },
    {
      "epoch": 0.555959595959596,
      "grad_norm": 0.00867844931781292,
      "learning_rate": 4.495787894201031e-05,
      "loss": 0.3661633014678955,
      "step": 1720
    },
    {
      "epoch": 0.5591919191919192,
      "grad_norm": 0.00891869980841875,
      "learning_rate": 4.442643535960631e-05,
      "loss": 0.38137781620025635,
      "step": 1730
    },
    {
      "epoch": 0.5624242424242424,
      "grad_norm": 0.008473970927298069,
      "learning_rate": 4.3895628615950864e-05,
      "loss": 0.37122745513916017,
      "step": 1740
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.00889658834785223,
      "learning_rate": 4.3365519361332345e-05,
      "loss": 0.3819819211959839,
      "step": 1750
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.008457816205918789,
      "learning_rate": 4.283616816634353e-05,
      "loss": 0.3663030624389648,
      "step": 1760
    },
    {
      "epoch": 0.5721212121212121,
      "grad_norm": 0.008427497930824757,
      "learning_rate": 4.230763551496089e-05,
      "loss": 0.38602652549743655,
      "step": 1770
    },
    {
      "epoch": 0.5753535353535354,
      "grad_norm": 0.008894660510122776,
      "learning_rate": 4.1779981797633645e-05,
      "loss": 0.3838383674621582,
      "step": 1780
    },
    {
      "epoch": 0.5785858585858585,
      "grad_norm": 0.008388307876884937,
      "learning_rate": 4.1253267304383455e-05,
      "loss": 0.3710144281387329,
      "step": 1790
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.008177547715604305,
      "learning_rate": 4.072755221791572e-05,
      "loss": 0.36981887817382814,
      "step": 1800
    },
    {
      "epoch": 0.585050505050505,
      "grad_norm": 0.008034786209464073,
      "learning_rate": 4.020289660674306e-05,
      "loss": 0.3789166212081909,
      "step": 1810
    },
    {
      "epoch": 0.5882828282828283,
      "grad_norm": 0.008227713406085968,
      "learning_rate": 3.967936041832173e-05,
      "loss": 0.3742852210998535,
      "step": 1820
    },
    {
      "epoch": 0.5915151515151515,
      "grad_norm": 0.008400660008192062,
      "learning_rate": 3.9157003472202246e-05,
      "loss": 0.3705322504043579,
      "step": 1830
    },
    {
      "epoch": 0.5947474747474748,
      "grad_norm": 0.008642120286822319,
      "learning_rate": 3.863588545319407e-05,
      "loss": 0.3812143087387085,
      "step": 1840
    },
    {
      "epoch": 0.597979797979798,
      "grad_norm": 0.008550690487027168,
      "learning_rate": 3.8116065904546196e-05,
      "loss": 0.36846873760223386,
      "step": 1850
    },
    {
      "epoch": 0.6012121212121212,
      "grad_norm": 0.009093121625483036,
      "learning_rate": 3.759760422114362e-05,
      "loss": 0.36917288303375245,
      "step": 1860
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 0.011531802825629711,
      "learning_rate": 3.708055964272088e-05,
      "loss": 0.37623181343078616,
      "step": 1870
    },
    {
      "epoch": 0.6076767676767677,
      "grad_norm": 0.008886284194886684,
      "learning_rate": 3.6564991247093234e-05,
      "loss": 0.368613076210022,
      "step": 1880
    },
    {
      "epoch": 0.610909090909091,
      "grad_norm": 0.008327574469149113,
      "learning_rate": 3.6050957943406465e-05,
      "loss": 0.3828991413116455,
      "step": 1890
    },
    {
      "epoch": 0.6141414141414141,
      "grad_norm": 0.008432856760919094,
      "learning_rate": 3.553851846540584e-05,
      "loss": 0.36706550121307374,
      "step": 1900
    },
    {
      "epoch": 0.6173737373737374,
      "grad_norm": 0.008847289718687534,
      "learning_rate": 3.50277313647252e-05,
      "loss": 0.3688380718231201,
      "step": 1910
    },
    {
      "epoch": 0.6206060606060606,
      "grad_norm": 0.008496418595314026,
      "learning_rate": 3.451865500419676e-05,
      "loss": 0.37277908325195314,
      "step": 1920
    },
    {
      "epoch": 0.6238383838383839,
      "grad_norm": 0.008594812825322151,
      "learning_rate": 3.401134755118256e-05,
      "loss": 0.3851970911026001,
      "step": 1930
    },
    {
      "epoch": 0.6270707070707071,
      "grad_norm": 0.00816626101732254,
      "learning_rate": 3.350586697092826e-05,
      "loss": 0.3817636251449585,
      "step": 1940
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": 0.008723457343876362,
      "learning_rate": 3.300227101993998e-05,
      "loss": 0.3650315284729004,
      "step": 1950
    },
    {
      "epoch": 0.6335353535353535,
      "grad_norm": 0.0087728351354599,
      "learning_rate": 3.2500617239384947e-05,
      "loss": 0.37312395572662355,
      "step": 1960
    },
    {
      "epoch": 0.6367676767676768,
      "grad_norm": 0.008724791929125786,
      "learning_rate": 3.200096294851691e-05,
      "loss": 0.3921516418457031,
      "step": 1970
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.008351181633770466,
      "learning_rate": 3.150336523812674e-05,
      "loss": 0.3623528957366943,
      "step": 1980
    },
    {
      "epoch": 0.6432323232323233,
      "grad_norm": 0.008469253778457642,
      "learning_rate": 3.100788096401925e-05,
      "loss": 0.36600675582885744,
      "step": 1990
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.008192651905119419,
      "learning_rate": 3.051456674051677e-05,
      "loss": 0.3711225986480713,
      "step": 2000
    },
    {
      "epoch": 0.6496969696969697,
      "grad_norm": 0.007976829074323177,
      "learning_rate": 3.0023478933990347e-05,
      "loss": 0.37237536907196045,
      "step": 2010
    },
    {
      "epoch": 0.6529292929292929,
      "grad_norm": 0.009051225148141384,
      "learning_rate": 2.9534673656419377e-05,
      "loss": 0.37553870677948,
      "step": 2020
    },
    {
      "epoch": 0.6561616161616162,
      "grad_norm": 0.008214341476559639,
      "learning_rate": 2.9048206758980136e-05,
      "loss": 0.36155047416687014,
      "step": 2030
    },
    {
      "epoch": 0.6593939393939394,
      "grad_norm": 0.008441639132797718,
      "learning_rate": 2.856413382566425e-05,
      "loss": 0.3772094488143921,
      "step": 2040
    },
    {
      "epoch": 0.6626262626262627,
      "grad_norm": 0.008770185522735119,
      "learning_rate": 2.8082510166927583e-05,
      "loss": 0.37615342140197755,
      "step": 2050
    },
    {
      "epoch": 0.6658585858585858,
      "grad_norm": 0.008841089904308319,
      "learning_rate": 2.760339081337041e-05,
      "loss": 0.37926411628723145,
      "step": 2060
    },
    {
      "epoch": 0.6690909090909091,
      "grad_norm": 0.008792232722043991,
      "learning_rate": 2.7126830509449773e-05,
      "loss": 0.36652073860168455,
      "step": 2070
    },
    {
      "epoch": 0.6723232323232323,
      "grad_norm": 0.008509263396263123,
      "learning_rate": 2.6652883707224075e-05,
      "loss": 0.3772120952606201,
      "step": 2080
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 0.0077481819316744804,
      "learning_rate": 2.618160456013153e-05,
      "loss": 0.3723082304000854,
      "step": 2090
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": 0.008416908793151379,
      "learning_rate": 2.571304691680255e-05,
      "loss": 0.3793506145477295,
      "step": 2100
    },
    {
      "epoch": 0.682020202020202,
      "grad_norm": 0.008886829949915409,
      "learning_rate": 2.5247264314906917e-05,
      "loss": 0.3736711025238037,
      "step": 2110
    },
    {
      "epoch": 0.6852525252525252,
      "grad_norm": 0.008566746488213539,
      "learning_rate": 2.4784309975036513e-05,
      "loss": 0.37454140186309814,
      "step": 2120
    },
    {
      "epoch": 0.6884848484848485,
      "grad_norm": 0.008895625360310078,
      "learning_rate": 2.4324236794624456e-05,
      "loss": 0.3789727210998535,
      "step": 2130
    },
    {
      "epoch": 0.6917171717171717,
      "grad_norm": 0.008392645977437496,
      "learning_rate": 2.386709734190079e-05,
      "loss": 0.35956587791442873,
      "step": 2140
    },
    {
      "epoch": 0.694949494949495,
      "grad_norm": 0.008756759576499462,
      "learning_rate": 2.34129438498862e-05,
      "loss": 0.3661501884460449,
      "step": 2150
    },
    {
      "epoch": 0.6981818181818182,
      "grad_norm": 0.008462606929242611,
      "learning_rate": 2.296182821042374e-05,
      "loss": 0.37202165126800535,
      "step": 2160
    },
    {
      "epoch": 0.7014141414141414,
      "grad_norm": 0.008555078878998756,
      "learning_rate": 2.2513801968249644e-05,
      "loss": 0.37806949615478513,
      "step": 2170
    },
    {
      "epoch": 0.7046464646464646,
      "grad_norm": 0.008424860425293446,
      "learning_rate": 2.2068916315103783e-05,
      "loss": 0.36311826705932615,
      "step": 2180
    },
    {
      "epoch": 0.7078787878787879,
      "grad_norm": 0.008660963736474514,
      "learning_rate": 2.162722208388057e-05,
      "loss": 0.3788281440734863,
      "step": 2190
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.008829527534544468,
      "learning_rate": 2.1188769742820625e-05,
      "loss": 0.363692045211792,
      "step": 2200
    },
    {
      "epoch": 0.7143434343434344,
      "grad_norm": 0.008732212707400322,
      "learning_rate": 2.075360938974429e-05,
      "loss": 0.377083945274353,
      "step": 2210
    },
    {
      "epoch": 0.7175757575757575,
      "grad_norm": 0.008612161502242088,
      "learning_rate": 2.03217907463275e-05,
      "loss": 0.37938365936279295,
      "step": 2220
    },
    {
      "epoch": 0.7208080808080808,
      "grad_norm": 0.008470796048641205,
      "learning_rate": 1.989336315242048e-05,
      "loss": 0.36910898685455323,
      "step": 2230
    },
    {
      "epoch": 0.724040404040404,
      "grad_norm": 0.008112024515867233,
      "learning_rate": 1.9468375560410117e-05,
      "loss": 0.37638006210327146,
      "step": 2240
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.008808580227196217,
      "learning_rate": 1.90468765296267e-05,
      "loss": 0.3817383050918579,
      "step": 2250
    },
    {
      "epoch": 0.7305050505050505,
      "grad_norm": 0.00813962984830141,
      "learning_rate": 1.8628914220795494e-05,
      "loss": 0.37254207134246825,
      "step": 2260
    },
    {
      "epoch": 0.7337373737373737,
      "grad_norm": 0.00881427712738514,
      "learning_rate": 1.8214536390533822e-05,
      "loss": 0.3720477819442749,
      "step": 2270
    },
    {
      "epoch": 0.7369696969696969,
      "grad_norm": 0.00897192768752575,
      "learning_rate": 1.7803790385894387e-05,
      "loss": 0.3803945302963257,
      "step": 2280
    },
    {
      "epoch": 0.7402020202020202,
      "grad_norm": 0.008690549992024899,
      "learning_rate": 1.7396723138955428e-05,
      "loss": 0.36781790256500246,
      "step": 2290
    },
    {
      "epoch": 0.7434343434343434,
      "grad_norm": 0.008678211830556393,
      "learning_rate": 1.699338116145811e-05,
      "loss": 0.3670048236846924,
      "step": 2300
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.008816958405077457,
      "learning_rate": 1.6593810539492195e-05,
      "loss": 0.373481011390686,
      "step": 2310
    },
    {
      "epoch": 0.74989898989899,
      "grad_norm": 0.008747234009206295,
      "learning_rate": 1.619805692823016e-05,
      "loss": 0.37540497779846194,
      "step": 2320
    },
    {
      "epoch": 0.7531313131313131,
      "grad_norm": 0.00825244840234518,
      "learning_rate": 1.580616554671057e-05,
      "loss": 0.36757464408874513,
      "step": 2330
    },
    {
      "epoch": 0.7563636363636363,
      "grad_norm": 0.008477483876049519,
      "learning_rate": 1.5418181172671382e-05,
      "loss": 0.37665433883666993,
      "step": 2340
    },
    {
      "epoch": 0.7595959595959596,
      "grad_norm": 0.00875260028988123,
      "learning_rate": 1.5034148137433623e-05,
      "loss": 0.366714334487915,
      "step": 2350
    },
    {
      "epoch": 0.7628282828282829,
      "grad_norm": 0.008853024803102016,
      "learning_rate": 1.4654110320836017e-05,
      "loss": 0.37020263671875,
      "step": 2360
    },
    {
      "epoch": 0.7660606060606061,
      "grad_norm": 0.009046499617397785,
      "learning_rate": 1.4278111146221263e-05,
      "loss": 0.3723160982131958,
      "step": 2370
    },
    {
      "epoch": 0.7692929292929293,
      "grad_norm": 0.008310087956488132,
      "learning_rate": 1.3906193575474508e-05,
      "loss": 0.3688467264175415,
      "step": 2380
    },
    {
      "epoch": 0.7725252525252525,
      "grad_norm": 0.008621731773018837,
      "learning_rate": 1.3538400104114446e-05,
      "loss": 0.37307281494140626,
      "step": 2390
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": 0.008672415278851986,
      "learning_rate": 1.3174772756437742e-05,
      "loss": 0.36974148750305175,
      "step": 2400
    },
    {
      "epoch": 0.778989898989899,
      "grad_norm": 0.008731256239116192,
      "learning_rate": 1.2815353080717379e-05,
      "loss": 0.37264394760131836,
      "step": 2410
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.014323744922876358,
      "learning_rate": 1.246018214445525e-05,
      "loss": 0.3763184309005737,
      "step": 2420
    },
    {
      "epoch": 0.7854545454545454,
      "grad_norm": 0.008530031889677048,
      "learning_rate": 1.210930052968981e-05,
      "loss": 0.3757563591003418,
      "step": 2430
    },
    {
      "epoch": 0.7886868686868687,
      "grad_norm": 0.008401346392929554,
      "learning_rate": 1.1762748328359152e-05,
      "loss": 0.3683294773101807,
      "step": 2440
    },
    {
      "epoch": 0.7919191919191919,
      "grad_norm": 0.008516985923051834,
      "learning_rate": 1.1420565137720045e-05,
      "loss": 0.36771197319030763,
      "step": 2450
    },
    {
      "epoch": 0.7951515151515152,
      "grad_norm": 0.009087449871003628,
      "learning_rate": 1.1082790055823533e-05,
      "loss": 0.3740364074707031,
      "step": 2460
    },
    {
      "epoch": 0.7983838383838384,
      "grad_norm": 0.008735416457057,
      "learning_rate": 1.0749461677047624e-05,
      "loss": 0.3658547639846802,
      "step": 2470
    },
    {
      "epoch": 0.8016161616161617,
      "grad_norm": 0.008218985982239246,
      "learning_rate": 1.0420618087687418e-05,
      "loss": 0.36727066040039064,
      "step": 2480
    },
    {
      "epoch": 0.8048484848484848,
      "grad_norm": 0.008089488372206688,
      "learning_rate": 1.0096296861603321e-05,
      "loss": 0.3734628200531006,
      "step": 2490
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.009074541740119457,
      "learning_rate": 9.776535055927931e-06,
      "loss": 0.38172001838684083,
      "step": 2500
    },
    {
      "epoch": 0.8113131313131313,
      "grad_norm": 0.008856716565787792,
      "learning_rate": 9.461369206831772e-06,
      "loss": 0.3696982622146606,
      "step": 2510
    },
    {
      "epoch": 0.8145454545454546,
      "grad_norm": 0.008767404593527317,
      "learning_rate": 9.150835325348678e-06,
      "loss": 0.37330069541931155,
      "step": 2520
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 0.009410719387233257,
      "learning_rate": 8.844968893261197e-06,
      "loss": 0.3685540914535522,
      "step": 2530
    },
    {
      "epoch": 0.821010101010101,
      "grad_norm": 0.008310632780194283,
      "learning_rate": 8.543804859046345e-06,
      "loss": 0.37013726234436034,
      "step": 2540
    },
    {
      "epoch": 0.8242424242424242,
      "grad_norm": 0.008878393098711967,
      "learning_rate": 8.247377633882463e-06,
      "loss": 0.3597676753997803,
      "step": 2550
    },
    {
      "epoch": 0.8274747474747475,
      "grad_norm": 0.008639859966933727,
      "learning_rate": 7.95572108771726e-06,
      "loss": 0.3774217128753662,
      "step": 2560
    },
    {
      "epoch": 0.8307070707070707,
      "grad_norm": 0.009035849943757057,
      "learning_rate": 7.66886854539795e-06,
      "loss": 0.3716104984283447,
      "step": 2570
    },
    {
      "epoch": 0.833939393939394,
      "grad_norm": 0.008561176247894764,
      "learning_rate": 7.386852782863407e-06,
      "loss": 0.3702033042907715,
      "step": 2580
    },
    {
      "epoch": 0.8371717171717171,
      "grad_norm": 0.008522417396306992,
      "learning_rate": 7.109706023399232e-06,
      "loss": 0.3779261589050293,
      "step": 2590
    },
    {
      "epoch": 0.8404040404040404,
      "grad_norm": 0.00893703568726778,
      "learning_rate": 6.837459933955936e-06,
      "loss": 0.37835590839385985,
      "step": 2600
    },
    {
      "epoch": 0.8436363636363636,
      "grad_norm": 0.008540214039385319,
      "learning_rate": 6.5701456215305656e-06,
      "loss": 0.3780329704284668,
      "step": 2610
    },
    {
      "epoch": 0.8468686868686869,
      "grad_norm": 0.008812173269689083,
      "learning_rate": 6.307793629612452e-06,
      "loss": 0.3683763980865479,
      "step": 2620
    },
    {
      "epoch": 0.8501010101010101,
      "grad_norm": 0.009678703732788563,
      "learning_rate": 6.050433934693339e-06,
      "loss": 0.37782022953033445,
      "step": 2630
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.008860490284860134,
      "learning_rate": 5.798095942842141e-06,
      "loss": 0.3841053009033203,
      "step": 2640
    },
    {
      "epoch": 0.8565656565656565,
      "grad_norm": 0.009095641784369946,
      "learning_rate": 5.550808486345072e-06,
      "loss": 0.378291392326355,
      "step": 2650
    },
    {
      "epoch": 0.8597979797979798,
      "grad_norm": 0.008367888629436493,
      "learning_rate": 5.308599820411247e-06,
      "loss": 0.36860671043396,
      "step": 2660
    },
    {
      "epoch": 0.863030303030303,
      "grad_norm": 0.008273428305983543,
      "learning_rate": 5.071497619944171e-06,
      "loss": 0.37145724296569826,
      "step": 2670
    },
    {
      "epoch": 0.8662626262626263,
      "grad_norm": 0.00850183516740799,
      "learning_rate": 4.839528976379648e-06,
      "loss": 0.37532649040222166,
      "step": 2680
    },
    {
      "epoch": 0.8694949494949495,
      "grad_norm": 0.008846405893564224,
      "learning_rate": 4.612720394590286e-06,
      "loss": 0.3695547580718994,
      "step": 2690
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.008502434007823467,
      "learning_rate": 4.391097789856985e-06,
      "loss": 0.3720081806182861,
      "step": 2700
    },
    {
      "epoch": 0.8759595959595959,
      "grad_norm": 0.00865609385073185,
      "learning_rate": 4.174686484907908e-06,
      "loss": 0.366014289855957,
      "step": 2710
    },
    {
      "epoch": 0.8791919191919192,
      "grad_norm": 0.008588762022554874,
      "learning_rate": 3.963511207025078e-06,
      "loss": 0.3735676288604736,
      "step": 2720
    },
    {
      "epoch": 0.8824242424242424,
      "grad_norm": 0.008576790802180767,
      "learning_rate": 3.7575960852189728e-06,
      "loss": 0.38012237548828126,
      "step": 2730
    },
    {
      "epoch": 0.8856565656565657,
      "grad_norm": 0.00867045484483242,
      "learning_rate": 3.5569646474715722e-06,
      "loss": 0.3639381885528564,
      "step": 2740
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.008396121673285961,
      "learning_rate": 3.361639818048068e-06,
      "loss": 0.3669224500656128,
      "step": 2750
    },
    {
      "epoch": 0.8921212121212121,
      "grad_norm": 0.008845800533890724,
      "learning_rate": 3.1716439148774534e-06,
      "loss": 0.37716219425201414,
      "step": 2760
    },
    {
      "epoch": 0.8953535353535353,
      "grad_norm": 0.008693251758813858,
      "learning_rate": 2.986998647002498e-06,
      "loss": 0.37473173141479493,
      "step": 2770
    },
    {
      "epoch": 0.8985858585858586,
      "grad_norm": 0.008422034792602062,
      "learning_rate": 2.8077251120992742e-06,
      "loss": 0.36577663421630857,
      "step": 2780
    },
    {
      "epoch": 0.9018181818181819,
      "grad_norm": 0.008648978546261787,
      "learning_rate": 2.633843794066515e-06,
      "loss": 0.367098331451416,
      "step": 2790
    },
    {
      "epoch": 0.9050505050505051,
      "grad_norm": 0.010963937267661095,
      "learning_rate": 2.465374560685091e-06,
      "loss": 0.3678403615951538,
      "step": 2800
    },
    {
      "epoch": 0.9082828282828282,
      "grad_norm": 0.009094985201954842,
      "learning_rate": 2.302336661347926e-06,
      "loss": 0.3675699234008789,
      "step": 2810
    },
    {
      "epoch": 0.9115151515151515,
      "grad_norm": 0.008743363432586193,
      "learning_rate": 2.1447487248605513e-06,
      "loss": 0.37444562911987306,
      "step": 2820
    },
    {
      "epoch": 0.9147474747474748,
      "grad_norm": 0.00941784493625164,
      "learning_rate": 1.9926287573125537e-06,
      "loss": 0.3681609630584717,
      "step": 2830
    },
    {
      "epoch": 0.917979797979798,
      "grad_norm": 0.00954042561352253,
      "learning_rate": 1.845994140020213e-06,
      "loss": 0.38029980659484863,
      "step": 2840
    },
    {
      "epoch": 0.9212121212121213,
      "grad_norm": 0.009196951985359192,
      "learning_rate": 1.7048616275404771e-06,
      "loss": 0.3789214134216309,
      "step": 2850
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.00853448174893856,
      "learning_rate": 1.5692473457565748e-06,
      "loss": 0.3718825340270996,
      "step": 2860
    },
    {
      "epoch": 0.9276767676767677,
      "grad_norm": 0.00839314702898264,
      "learning_rate": 1.439166790035501e-06,
      "loss": 0.3590099334716797,
      "step": 2870
    },
    {
      "epoch": 0.9309090909090909,
      "grad_norm": 0.008586350828409195,
      "learning_rate": 1.3146348234574724e-06,
      "loss": 0.3683621883392334,
      "step": 2880
    },
    {
      "epoch": 0.9341414141414142,
      "grad_norm": 0.008600099012255669,
      "learning_rate": 1.1956656751176577e-06,
      "loss": 0.37033562660217284,
      "step": 2890
    },
    {
      "epoch": 0.9373737373737374,
      "grad_norm": 0.008418564684689045,
      "learning_rate": 1.0822729385003727e-06,
      "loss": 0.3722561836242676,
      "step": 2900
    },
    {
      "epoch": 0.9406060606060606,
      "grad_norm": 0.009096021763980389,
      "learning_rate": 9.744695699258955e-07,
      "loss": 0.3705434799194336,
      "step": 2910
    },
    {
      "epoch": 0.9438383838383838,
      "grad_norm": 0.008366765454411507,
      "learning_rate": 8.722678870700274e-07,
      "loss": 0.3757180690765381,
      "step": 2920
    },
    {
      "epoch": 0.9470707070707071,
      "grad_norm": 0.00876353308558464,
      "learning_rate": 7.756795675566919e-07,
      "loss": 0.37983224391937254,
      "step": 2930
    },
    {
      "epoch": 0.9503030303030303,
      "grad_norm": 0.009546471759676933,
      "learning_rate": 6.847156476236516e-07,
      "loss": 0.3681799411773682,
      "step": 2940
    },
    {
      "epoch": 0.9535353535353536,
      "grad_norm": 0.009170792065560818,
      "learning_rate": 5.993865208614835e-07,
      "loss": 0.37668063640594485,
      "step": 2950
    },
    {
      "epoch": 0.9567676767676768,
      "grad_norm": 0.009117783978581429,
      "learning_rate": 5.197019370260125e-07,
      "loss": 0.37759225368499755,
      "step": 2960
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.008532952517271042,
      "learning_rate": 4.4567100092429704e-07,
      "loss": 0.37395672798156737,
      "step": 2970
    },
    {
      "epoch": 0.9632323232323232,
      "grad_norm": 0.009223098866641521,
      "learning_rate": 3.7730217137428857e-07,
      "loss": 0.37163801193237306,
      "step": 2980
    },
    {
      "epoch": 0.9664646464646465,
      "grad_norm": 0.008754228241741657,
      "learning_rate": 3.1460326023836083e-07,
      "loss": 0.36648709774017335,
      "step": 2990
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.008591044694185257,
      "learning_rate": 2.575814315306846e-07,
      "loss": 0.37227301597595214,
      "step": 3000
    },
    {
      "epoch": 0.972929292929293,
      "grad_norm": 0.008041838183999062,
      "learning_rate": 2.0624320059869918e-07,
      "loss": 0.3628725528717041,
      "step": 3010
    },
    {
      "epoch": 0.9761616161616161,
      "grad_norm": 0.008703021332621574,
      "learning_rate": 1.6059443337861912e-07,
      "loss": 0.37576377391815186,
      "step": 3020
    },
    {
      "epoch": 0.9793939393939394,
      "grad_norm": 0.008821804076433182,
      "learning_rate": 1.2064034572523142e-07,
      "loss": 0.3834287405014038,
      "step": 3030
    },
    {
      "epoch": 0.9826262626262626,
      "grad_norm": 0.008591694757342339,
      "learning_rate": 8.638550281591107e-08,
      "loss": 0.37302587032318113,
      "step": 3040
    },
    {
      "epoch": 0.9858585858585859,
      "grad_norm": 0.008161679841578007,
      "learning_rate": 5.7833818629005054e-08,
      "loss": 0.37163610458374025,
      "step": 3050
    },
    {
      "epoch": 0.9890909090909091,
      "grad_norm": 0.008312749676406384,
      "learning_rate": 3.498855549660118e-08,
      "loss": 0.36723101139068604,
      "step": 3060
    },
    {
      "epoch": 0.9923232323232323,
      "grad_norm": 0.00888834148645401,
      "learning_rate": 1.785232373180401e-08,
      "loss": 0.37539513111114503,
      "step": 3070
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.008697266690433025,
      "learning_rate": 6.427081330456774e-09,
      "loss": 0.36815404891967773,
      "step": 3080
    },
    {
      "epoch": 0.9987878787878788,
      "grad_norm": 0.008382439613342285,
      "learning_rate": 7.141337474148025e-10,
      "loss": 0.36412370204925537,
      "step": 3090
    },
    {
      "epoch": 1.0,
      "step": 3094,
      "total_flos": 4.707818479338652e+18,
      "train_loss": 0.3778848514375027,
      "train_runtime": 9023.6676,
      "train_samples_per_second": 21.942,
      "train_steps_per_second": 0.343
    }
  ],
  "logging_steps": 10,
  "max_steps": 3094,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.707818479338652e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}