{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 50,
  "global_step": 213,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 0.10009177774190903,
      "learning_rate": 0.0,
      "loss": 0.704937219619751,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.10451912879943848,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.7318670749664307,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.07928935438394547,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.6017104387283325,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.048069290816783905,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.6029032468795776,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.02866927720606327,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.5051919221878052,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.022201435640454292,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.5942293405532837,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.018263086676597595,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.5781338214874268,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.01827927492558956,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.5180214047431946,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.014687157236039639,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5420116186141968,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.012042663060128689,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.5345908403396606,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.012934447266161442,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.46689414978027344,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.012295619584619999,
      "learning_rate": 5e-06,
      "loss": 0.5062131881713867,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.011856353841722012,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.5063096880912781,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.009451798163354397,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.5130602121353149,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.01111016795039177,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.5016045570373535,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.010735263116657734,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.49827253818511963,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.010710126720368862,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.479993999004364,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.009600787423551083,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.4925128221511841,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.010486789979040623,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.5188871622085571,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.013396799564361572,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5192517042160034,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.009299715980887413,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.4580157399177551,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.009691477753221989,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.49455106258392334,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.008896945044398308,
      "learning_rate": 1e-05,
      "loss": 0.48672014474868774,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.009234798140823841,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.5052967071533203,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.009167873300611973,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.4740435779094696,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.009001555852591991,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.47315946221351624,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.00915393978357315,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.4557237923145294,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.008505849167704582,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.46317678689956665,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.008668503724038601,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.4533114433288574,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.009284070692956448,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5624005794525146,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.00935022346675396,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.4420597553253174,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.008682326413691044,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.4745720624923706,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.007816251367330551,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.439736545085907,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.009315130300819874,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5357447862625122,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.009141312912106514,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.519463062286377,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.008826862089335918,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.48377716541290283,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.008700878359377384,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.48436683416366577,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.011412105523049831,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.4949312210083008,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.009214675053954124,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.4901079535484314,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.01163570862263441,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.6070311665534973,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.009325762279331684,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.48412975668907166,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.008266489021480083,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.4440661072731018,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.00843313243240118,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.502442479133606,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.00934070535004139,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.47924768924713135,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.010360248386859894,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.4161364436149597,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.0094041982665658,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.48306071758270264,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.009070150554180145,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.4774249792098999,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.009771023876965046,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.4948921203613281,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.008749130181968212,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.4825429916381836,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.007630312815308571,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.46055319905281067,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.48781517148017883,
      "eval_runtime": 4.5903,
      "eval_samples_per_second": 43.57,
      "eval_steps_per_second": 21.785,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.008408056572079659,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.4626312255859375,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.007699670735746622,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.4499070644378662,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.009070169180631638,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4825657606124878,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.007915646769106388,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.4534468650817871,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.011336776427924633,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.4988631010055542,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.00761911366134882,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.4371437728404999,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.009316994808614254,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.4956932067871094,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.009821794927120209,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.5392974615097046,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.008422416634857655,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.47983357310295105,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.00837004091590643,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.5183510780334473,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.008596297353506088,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.47292786836624146,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.009059637784957886,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.5188573598861694,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.007816917262971401,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.45641395449638367,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.007985202595591545,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.4586361050605774,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.007170964498072863,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.4394378066062927,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.00909162126481533,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.509820818901062,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.00786044355481863,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.43584880232810974,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.00832363311201334,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.4317135214805603,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.008376957848668098,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.49933016300201416,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.00835558120161295,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.46570393443107605,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.013256405480206013,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.45107918977737427,
      "step": 71
    },
    {
      "epoch": 1.0142222222222221,
      "grad_norm": 0.008708071894943714,
      "learning_rate": 8.462100635075097e-06,
      "loss": 0.47125527262687683,
      "step": 72
    },
    {
      "epoch": 1.0284444444444445,
      "grad_norm": 0.008086243644356728,
      "learning_rate": 8.40229882467003e-06,
      "loss": 0.4322492480278015,
      "step": 73
    },
    {
      "epoch": 1.0426666666666666,
      "grad_norm": 0.0073950947262346745,
      "learning_rate": 8.341576573860049e-06,
      "loss": 0.38362830877304077,
      "step": 74
    },
    {
      "epoch": 1.056888888888889,
      "grad_norm": 0.0076777078211307526,
      "learning_rate": 8.279950310130218e-06,
      "loss": 0.3878062665462494,
      "step": 75
    },
    {
      "epoch": 1.0711111111111111,
      "grad_norm": 0.007898081094026566,
      "learning_rate": 8.2174367055326e-06,
      "loss": 0.3833811283111572,
      "step": 76
    },
    {
      "epoch": 1.0853333333333333,
      "grad_norm": 0.007348628249019384,
      "learning_rate": 8.154052672175888e-06,
      "loss": 0.3845909833908081,
      "step": 77
    },
    {
      "epoch": 1.0995555555555556,
      "grad_norm": 0.008542248979210854,
      "learning_rate": 8.08981535765009e-06,
      "loss": 0.44259265065193176,
      "step": 78
    },
    {
      "epoch": 1.1137777777777778,
      "grad_norm": 0.007998447865247726,
      "learning_rate": 8.024742140387506e-06,
      "loss": 0.38503497838974,
      "step": 79
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.008362009190022945,
      "learning_rate": 7.95885062496126e-06,
      "loss": 0.42608046531677246,
      "step": 80
    },
    {
      "epoch": 1.1422222222222222,
      "grad_norm": 0.007770548574626446,
      "learning_rate": 7.892158637322647e-06,
      "loss": 0.38991105556488037,
      "step": 81
    },
    {
      "epoch": 1.1564444444444444,
      "grad_norm": 0.007649772334843874,
      "learning_rate": 7.824684219978591e-06,
      "loss": 0.36854323744773865,
      "step": 82
    },
    {
      "epoch": 1.1706666666666667,
      "grad_norm": 0.008056909777224064,
      "learning_rate": 7.756445627110523e-06,
      "loss": 0.4200327396392822,
      "step": 83
    },
    {
      "epoch": 1.1848888888888889,
      "grad_norm": 0.0089965695515275,
      "learning_rate": 7.68746131963598e-06,
      "loss": 0.4378758668899536,
      "step": 84
    },
    {
      "epoch": 1.199111111111111,
      "grad_norm": 0.007884320802986622,
      "learning_rate": 7.6177499602143e-06,
      "loss": 0.3808164894580841,
      "step": 85
    },
    {
      "epoch": 1.2133333333333334,
      "grad_norm": 0.009615465067327023,
      "learning_rate": 7.547330408197695e-06,
      "loss": 0.4453170895576477,
      "step": 86
    },
    {
      "epoch": 1.2275555555555555,
      "grad_norm": 0.00891174841672182,
      "learning_rate": 7.476221714529167e-06,
      "loss": 0.4456181526184082,
      "step": 87
    },
    {
      "epoch": 1.2417777777777779,
      "grad_norm": 0.008833018131554127,
      "learning_rate": 7.404443116588548e-06,
      "loss": 0.43805548548698425,
      "step": 88
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.008171891793608665,
      "learning_rate": 7.332014032988123e-06,
      "loss": 0.4144285321235657,
      "step": 89
    },
    {
      "epoch": 1.2702222222222221,
      "grad_norm": 0.009090668521821499,
      "learning_rate": 7.2589540583192165e-06,
      "loss": 0.38928651809692383,
      "step": 90
    },
    {
      "epoch": 1.2844444444444445,
      "grad_norm": 0.008077106438577175,
      "learning_rate": 7.185282957851175e-06,
      "loss": 0.387723445892334,
      "step": 91
    },
    {
      "epoch": 1.2986666666666666,
      "grad_norm": 0.008803839795291424,
      "learning_rate": 7.111020662184174e-06,
      "loss": 0.4158015549182892,
      "step": 92
    },
    {
      "epoch": 1.3128888888888888,
      "grad_norm": 0.008249706588685513,
      "learning_rate": 7.036187261857289e-06,
      "loss": 0.39764612913131714,
      "step": 93
    },
    {
      "epoch": 1.3271111111111111,
      "grad_norm": 0.008549178950488567,
      "learning_rate": 6.960803001913315e-06,
      "loss": 0.38216379284858704,
      "step": 94
    },
    {
      "epoch": 1.3413333333333333,
      "grad_norm": 0.007755788508802652,
      "learning_rate": 6.884888276421766e-06,
      "loss": 0.413602352142334,
      "step": 95
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 0.008742124773561954,
      "learning_rate": 6.8084636229615786e-06,
      "loss": 0.41756486892700195,
      "step": 96
    },
    {
      "epoch": 1.3697777777777778,
      "grad_norm": 0.008473540656268597,
      "learning_rate": 6.731549717064975e-06,
      "loss": 0.4028819799423218,
      "step": 97
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.008585155010223389,
      "learning_rate": 6.654167366624009e-06,
      "loss": 0.37123921513557434,
      "step": 98
    },
    {
      "epoch": 1.3982222222222223,
      "grad_norm": 0.00882649328559637,
      "learning_rate": 6.576337506261314e-06,
      "loss": 0.39443182945251465,
      "step": 99
    },
    {
      "epoch": 1.4124444444444444,
      "grad_norm": 0.008174613118171692,
      "learning_rate": 6.498081191666549e-06,
      "loss": 0.42232874035835266,
      "step": 100
    },
    {
      "epoch": 1.4124444444444444,
      "eval_loss": 0.4897068440914154,
      "eval_runtime": 5.0728,
      "eval_samples_per_second": 39.426,
      "eval_steps_per_second": 19.713,
      "step": 100
    },
    {
      "epoch": 1.4266666666666667,
      "grad_norm": 0.00753920478746295,
      "learning_rate": 6.419419593900109e-06,
      "loss": 0.38927626609802246,
      "step": 101
    },
    {
      "epoch": 1.4408888888888889,
      "grad_norm": 0.007967391051352024,
      "learning_rate": 6.340373993665607e-06,
      "loss": 0.36544570326805115,
      "step": 102
    },
    {
      "epoch": 1.455111111111111,
      "grad_norm": 0.008992813527584076,
      "learning_rate": 6.2609657755527135e-06,
      "loss": 0.4033282995223999,
      "step": 103
    },
    {
      "epoch": 1.4693333333333334,
      "grad_norm": 0.007906445302069187,
      "learning_rate": 6.1812164222518626e-06,
      "loss": 0.40876060724258423,
      "step": 104
    },
    {
      "epoch": 1.4835555555555555,
      "grad_norm": 0.00823493767529726,
      "learning_rate": 6.101147508742456e-06,
      "loss": 0.3994408845901489,
      "step": 105
    },
    {
      "epoch": 1.4977777777777779,
      "grad_norm": 0.009032925590872765,
      "learning_rate": 6.020780696456059e-06,
      "loss": 0.4667425751686096,
      "step": 106
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.007943308912217617,
      "learning_rate": 5.940137727416247e-06,
      "loss": 0.4092869460582733,
      "step": 107
    },
    {
      "epoch": 1.5262222222222221,
      "grad_norm": 0.008353099226951599,
      "learning_rate": 5.859240418356614e-06,
      "loss": 0.39832064509391785,
      "step": 108
    },
    {
      "epoch": 1.5404444444444443,
      "grad_norm": 0.008241581730544567,
      "learning_rate": 5.778110654818602e-06,
      "loss": 0.4114166498184204,
      "step": 109
    },
    {
      "epoch": 1.5546666666666666,
      "grad_norm": 0.007937194779515266,
      "learning_rate": 5.696770385230679e-06,
      "loss": 0.4360125660896301,
      "step": 110
    },
    {
      "epoch": 1.568888888888889,
      "grad_norm": 0.008319812826812267,
      "learning_rate": 5.615241614970546e-06,
      "loss": 0.4153256118297577,
      "step": 111
    },
    {
      "epoch": 1.5831111111111111,
      "grad_norm": 0.008011740632355213,
      "learning_rate": 5.533546400411899e-06,
      "loss": 0.3954656720161438,
      "step": 112
    },
    {
      "epoch": 1.5973333333333333,
      "grad_norm": 0.008084246888756752,
      "learning_rate": 5.4517068429574215e-06,
      "loss": 0.4052407741546631,
      "step": 113
    },
    {
      "epoch": 1.6115555555555554,
      "grad_norm": 0.007481739390641451,
      "learning_rate": 5.3697450830595775e-06,
      "loss": 0.4017290472984314,
      "step": 114
    },
    {
      "epoch": 1.6257777777777778,
      "grad_norm": 0.008050751872360706,
      "learning_rate": 5.287683294230855e-06,
      "loss": 0.38467150926589966,
      "step": 115
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.0077187251299619675,
      "learning_rate": 5.20554367704505e-06,
      "loss": 0.395123690366745,
      "step": 116
    },
    {
      "epoch": 1.6542222222222223,
      "grad_norm": 0.008423185907304287,
      "learning_rate": 5.123348453131242e-06,
      "loss": 0.39796996116638184,
      "step": 117
    },
    {
      "epoch": 1.6684444444444444,
      "grad_norm": 0.009052549488842487,
      "learning_rate": 5.041119859162068e-06,
      "loss": 0.4162113070487976,
      "step": 118
    },
    {
      "epoch": 1.6826666666666665,
      "grad_norm": 0.008246202953159809,
      "learning_rate": 4.958880140837934e-06,
      "loss": 0.42128854990005493,
      "step": 119
    },
    {
      "epoch": 1.696888888888889,
      "grad_norm": 0.00833312701433897,
      "learning_rate": 4.876651546868759e-06,
      "loss": 0.4024372696876526,
      "step": 120
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 0.008461604826152325,
      "learning_rate": 4.794456322954953e-06,
      "loss": 0.46918508410453796,
      "step": 121
    },
    {
      "epoch": 1.7253333333333334,
      "grad_norm": 0.00825911108404398,
      "learning_rate": 4.7123167057691446e-06,
      "loss": 0.41863948106765747,
      "step": 122
    },
    {
      "epoch": 1.7395555555555555,
      "grad_norm": 0.009252563118934631,
      "learning_rate": 4.630254916940424e-06,
      "loss": 0.44644808769226074,
      "step": 123
    },
    {
      "epoch": 1.7537777777777777,
      "grad_norm": 0.007843364961445332,
      "learning_rate": 4.548293157042581e-06,
      "loss": 0.42086148262023926,
      "step": 124
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.007915403693914413,
      "learning_rate": 4.466453599588103e-06,
      "loss": 0.4266040027141571,
      "step": 125
    },
    {
      "epoch": 1.7822222222222224,
      "grad_norm": 0.007302967831492424,
      "learning_rate": 4.384758385029457e-06,
      "loss": 0.3592030704021454,
      "step": 126
    },
    {
      "epoch": 1.7964444444444445,
      "grad_norm": 0.00869770348072052,
      "learning_rate": 4.3032296147693225e-06,
      "loss": 0.42212432622909546,
      "step": 127
    },
    {
      "epoch": 1.8106666666666666,
      "grad_norm": 0.008091778494417667,
      "learning_rate": 4.2218893451814005e-06,
      "loss": 0.37964335083961487,
      "step": 128
    },
    {
      "epoch": 1.8248888888888888,
      "grad_norm": 0.0076453504152596,
      "learning_rate": 4.140759581643386e-06,
      "loss": 0.37467944622039795,
      "step": 129
    },
    {
      "epoch": 1.8391111111111111,
      "grad_norm": 0.007656064350157976,
      "learning_rate": 4.059862272583755e-06,
      "loss": 0.393369197845459,
      "step": 130
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 0.008399168029427528,
      "learning_rate": 3.979219303543942e-06,
      "loss": 0.394899845123291,
      "step": 131
    },
    {
      "epoch": 1.8675555555555556,
      "grad_norm": 0.008833736181259155,
      "learning_rate": 3.898852491257547e-06,
      "loss": 0.3997966945171356,
      "step": 132
    },
    {
      "epoch": 1.8817777777777778,
      "grad_norm": 0.008364683948457241,
      "learning_rate": 3.818783577748138e-06,
      "loss": 0.44034862518310547,
      "step": 133
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.008851971477270126,
      "learning_rate": 3.7390342244472886e-06,
      "loss": 0.4251548647880554,
      "step": 134
    },
    {
      "epoch": 1.9102222222222223,
      "grad_norm": 0.007921694777905941,
      "learning_rate": 3.659626006334395e-06,
      "loss": 0.3972621560096741,
      "step": 135
    },
    {
      "epoch": 1.9244444444444444,
      "grad_norm": 0.008714950643479824,
      "learning_rate": 3.5805804060998926e-06,
      "loss": 0.4237692356109619,
      "step": 136
    },
    {
      "epoch": 1.9386666666666668,
      "grad_norm": 0.008546526543796062,
      "learning_rate": 3.501918808333453e-06,
      "loss": 0.5015424489974976,
      "step": 137
    },
    {
      "epoch": 1.952888888888889,
      "grad_norm": 0.008581602945923805,
      "learning_rate": 3.4236624937386874e-06,
      "loss": 0.4541424512863159,
      "step": 138
    },
    {
      "epoch": 1.967111111111111,
      "grad_norm": 0.008913579396903515,
      "learning_rate": 3.3458326333759927e-06,
      "loss": 0.42448267340660095,
      "step": 139
    },
    {
      "epoch": 1.9813333333333332,
      "grad_norm": 0.008540489710867405,
      "learning_rate": 3.268450282935026e-06,
      "loss": 0.4514390528202057,
      "step": 140
    },
    {
      "epoch": 1.9955555555555555,
      "grad_norm": 0.007863311097025871,
      "learning_rate": 3.1915363770384223e-06,
      "loss": 0.38879817724227905,
      "step": 141
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.013070300221443176,
      "learning_rate": 3.1151117235782346e-06,
      "loss": 0.3734951913356781,
      "step": 142
    },
    {
      "epoch": 2.014222222222222,
      "grad_norm": 0.00914511177688837,
      "learning_rate": 3.0391969980866874e-06,
      "loss": 0.3868422210216522,
      "step": 143
    },
    {
      "epoch": 2.0284444444444443,
      "grad_norm": 0.008015231229364872,
      "learning_rate": 2.963812738142713e-06,
      "loss": 0.3441769480705261,
      "step": 144
    },
    {
      "epoch": 2.042666666666667,
      "grad_norm": 0.008334742859005928,
      "learning_rate": 2.8889793378158284e-06,
      "loss": 0.3698546290397644,
      "step": 145
    },
    {
      "epoch": 2.056888888888889,
      "grad_norm": 0.0077324071899056435,
      "learning_rate": 2.814717042148827e-06,
      "loss": 0.3752461075782776,
      "step": 146
    },
    {
      "epoch": 2.071111111111111,
      "grad_norm": 0.007629899773746729,
      "learning_rate": 2.7410459416807856e-06,
      "loss": 0.3570592999458313,
      "step": 147
    },
    {
      "epoch": 2.0853333333333333,
      "grad_norm": 0.008662652224302292,
      "learning_rate": 2.6679859670118785e-06,
      "loss": 0.3812662363052368,
      "step": 148
    },
    {
      "epoch": 2.0995555555555554,
      "grad_norm": 0.007828332483768463,
      "learning_rate": 2.5955568834114523e-06,
      "loss": 0.3505663275718689,
      "step": 149
    },
    {
      "epoch": 2.113777777777778,
      "grad_norm": 0.0074827345088124275,
      "learning_rate": 2.523778285470835e-06,
      "loss": 0.35809028148651123,
      "step": 150
    },
    {
      "epoch": 2.113777777777778,
      "eval_loss": 0.49233150482177734,
      "eval_runtime": 4.1869,
      "eval_samples_per_second": 47.768,
      "eval_steps_per_second": 23.884,
      "step": 150
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.007365878205746412,
      "learning_rate": 2.452669591802307e-06,
      "loss": 0.32126089930534363,
      "step": 151
    },
    {
      "epoch": 2.1422222222222222,
      "grad_norm": 0.007244541309773922,
      "learning_rate": 2.3822500397857016e-06,
      "loss": 0.3627392649650574,
      "step": 152
    },
    {
      "epoch": 2.1564444444444444,
      "grad_norm": 0.00791338924318552,
      "learning_rate": 2.3125386803640188e-06,
      "loss": 0.36303800344467163,
      "step": 153
    },
    {
      "epoch": 2.1706666666666665,
      "grad_norm": 0.007537501864135265,
      "learning_rate": 2.243554372889479e-06,
      "loss": 0.3294636011123657,
      "step": 154
    },
    {
      "epoch": 2.1848888888888887,
      "grad_norm": 0.008005894720554352,
      "learning_rate": 2.1753157800214107e-06,
      "loss": 0.35944664478302,
      "step": 155
    },
    {
      "epoch": 2.1991111111111112,
      "grad_norm": 0.008430157788097858,
      "learning_rate": 2.1078413626773547e-06,
      "loss": 0.35921794176101685,
      "step": 156
    },
    {
      "epoch": 2.2133333333333334,
      "grad_norm": 0.00803217850625515,
      "learning_rate": 2.0411493750387423e-06,
      "loss": 0.3335600197315216,
      "step": 157
    },
    {
      "epoch": 2.2275555555555555,
      "grad_norm": 0.007777590304613113,
      "learning_rate": 1.9752578596124955e-06,
      "loss": 0.3621842861175537,
      "step": 158
    },
    {
      "epoch": 2.2417777777777776,
      "grad_norm": 0.007962247356772423,
      "learning_rate": 1.9101846423499113e-06,
      "loss": 0.34454649686813354,
      "step": 159
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.007974164560437202,
      "learning_rate": 1.8459473278241125e-06,
      "loss": 0.3537226915359497,
      "step": 160
    },
    {
      "epoch": 2.2702222222222224,
      "grad_norm": 0.007959051057696342,
      "learning_rate": 1.7825632944674016e-06,
      "loss": 0.3517017662525177,
      "step": 161
    },
    {
      "epoch": 2.2844444444444445,
      "grad_norm": 0.008884078823029995,
      "learning_rate": 1.7200496898697832e-06,
      "loss": 0.34244149923324585,
      "step": 162
    },
    {
      "epoch": 2.2986666666666666,
      "grad_norm": 0.008463534526526928,
      "learning_rate": 1.6584234261399535e-06,
      "loss": 0.35110828280448914,
      "step": 163
    },
    {
      "epoch": 2.3128888888888888,
      "grad_norm": 0.008407258428633213,
      "learning_rate": 1.5977011753299726e-06,
      "loss": 0.34295642375946045,
      "step": 164
    },
    {
      "epoch": 2.327111111111111,
      "grad_norm": 0.008790143765509129,
      "learning_rate": 1.5378993649249053e-06,
      "loss": 0.4045950770378113,
      "step": 165
    },
    {
      "epoch": 2.3413333333333335,
      "grad_norm": 0.008037876337766647,
      "learning_rate": 1.4790341733986085e-06,
      "loss": 0.3649445176124573,
      "step": 166
    },
    {
      "epoch": 2.3555555555555556,
      "grad_norm": 0.007316106464713812,
      "learning_rate": 1.4211215258368866e-06,
      "loss": 0.3201165795326233,
      "step": 167
    },
    {
      "epoch": 2.3697777777777778,
      "grad_norm": 0.00920423399657011,
      "learning_rate": 1.3641770896292083e-06,
      "loss": 0.345939040184021,
      "step": 168
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.008216304704546928,
      "learning_rate": 1.3082162702301276e-06,
      "loss": 0.35247528553009033,
      "step": 169
    },
    {
      "epoch": 2.398222222222222,
      "grad_norm": 0.008257976733148098,
      "learning_rate": 1.2532542069915722e-06,
      "loss": 0.40231946110725403,
      "step": 170
    },
    {
      "epoch": 2.4124444444444446,
      "grad_norm": 0.008689168840646744,
      "learning_rate": 1.1993057690671174e-06,
      "loss": 0.3605418801307678,
      "step": 171
    },
    {
      "epoch": 2.4266666666666667,
      "grad_norm": 0.008199715055525303,
      "learning_rate": 1.1463855513893695e-06,
      "loss": 0.382945716381073,
      "step": 172
    },
    {
      "epoch": 2.440888888888889,
      "grad_norm": 0.00789699237793684,
      "learning_rate": 1.0945078707215224e-06,
      "loss": 0.36510083079338074,
      "step": 173
    },
    {
      "epoch": 2.455111111111111,
      "grad_norm": 0.008184579201042652,
      "learning_rate": 1.0436867617841768e-06,
      "loss": 0.38933348655700684,
      "step": 174
    },
    {
      "epoch": 2.469333333333333,
      "grad_norm": 0.007531109265983105,
      "learning_rate": 9.939359734584552e-07,
      "loss": 0.3710438013076782,
      "step": 175
    },
    {
      "epoch": 2.4835555555555557,
      "grad_norm": 0.008019962348043919,
      "learning_rate": 9.452689650664515e-07,
      "loss": 0.36227256059646606,
      "step": 176
    },
    {
      "epoch": 2.497777777777778,
      "grad_norm": 0.007935193367302418,
      "learning_rate": 8.976989027300265e-07,
      "loss": 0.36987176537513733,
      "step": 177
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.007968267425894737,
      "learning_rate": 8.512386558088919e-07,
      "loss": 0.35104453563690186,
      "step": 178
    },
    {
      "epoch": 2.526222222222222,
      "grad_norm": 0.008082241751253605,
      "learning_rate": 8.059007934190194e-07,
      "loss": 0.3681498169898987,
      "step": 179
    },
    {
      "epoch": 2.5404444444444443,
      "grad_norm": 0.00833115540444851,
      "learning_rate": 7.61697581032243e-07,
      "loss": 0.353618860244751,
      "step": 180
    },
    {
      "epoch": 2.554666666666667,
      "grad_norm": 0.008011356927454472,
      "learning_rate": 7.186409771580355e-07,
      "loss": 0.35408419370651245,
      "step": 181
    },
    {
      "epoch": 2.568888888888889,
      "grad_norm": 0.00763704115524888,
      "learning_rate": 6.76742630108298e-07,
      "loss": 0.3726443648338318,
      "step": 182
    },
    {
      "epoch": 2.583111111111111,
      "grad_norm": 0.007385968696326017,
      "learning_rate": 6.360138748461015e-07,
      "loss": 0.3561905026435852,
      "step": 183
    },
    {
      "epoch": 2.5973333333333333,
      "grad_norm": 0.00736213056370616,
      "learning_rate": 5.964657299191712e-07,
      "loss": 0.3148964047431946,
      "step": 184
    },
    {
      "epoch": 2.6115555555555554,
      "grad_norm": 0.008179187774658203,
      "learning_rate": 5.581088944789953e-07,
      "loss": 0.3561857342720032,
      "step": 185
    },
    {
      "epoch": 2.6257777777777775,
      "grad_norm": 0.008100884966552258,
      "learning_rate": 5.20953745386329e-07,
      "loss": 0.3500719964504242,
      "step": 186
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.007978768087923527,
      "learning_rate": 4.850103344038853e-07,
      "loss": 0.3637757897377014,
      "step": 187
    },
    {
      "epoch": 2.6542222222222223,
      "grad_norm": 0.007483206689357758,
      "learning_rate": 4.502883854769935e-07,
      "loss": 0.32206273078918457,
      "step": 188
    },
    {
      "epoch": 2.6684444444444444,
      "grad_norm": 0.007899755612015724,
      "learning_rate": 4.167972921029262e-07,
      "loss": 0.33746200799942017,
      "step": 189
    },
    {
      "epoch": 2.6826666666666665,
      "grad_norm": 0.008544563315808773,
      "learning_rate": 3.8454611478963235e-07,
      "loss": 0.38060814142227173,
      "step": 190
    },
    {
      "epoch": 2.696888888888889,
      "grad_norm": 0.00889600533992052,
      "learning_rate": 3.535435786045538e-07,
      "loss": 0.3551645278930664,
      "step": 191
    },
    {
      "epoch": 2.7111111111111112,
      "grad_norm": 0.007875156588852406,
      "learning_rate": 3.237980708141919e-07,
      "loss": 0.35464680194854736,
      "step": 192
    },
    {
      "epoch": 2.7253333333333334,
      "grad_norm": 0.008730563335120678,
      "learning_rate": 2.9531763861505967e-07,
      "loss": 0.3980952501296997,
      "step": 193
    },
    {
      "epoch": 2.7395555555555555,
      "grad_norm": 0.008214394561946392,
      "learning_rate": 2.681099869566328e-07,
      "loss": 0.33311402797698975,
      "step": 194
    },
    {
      "epoch": 2.7537777777777777,
      "grad_norm": 0.007815193384885788,
      "learning_rate": 2.4218247645689306e-07,
      "loss": 0.36939185857772827,
      "step": 195
    },
    {
      "epoch": 2.768,
      "grad_norm": 0.008210226893424988,
      "learning_rate": 2.175421214110235e-07,
      "loss": 0.3736470937728882,
      "step": 196
    },
    {
      "epoch": 2.7822222222222224,
      "grad_norm": 0.007955148816108704,
      "learning_rate": 1.941955878938029e-07,
      "loss": 0.35068604350090027,
      "step": 197
    },
    {
      "epoch": 2.7964444444444445,
      "grad_norm": 0.008125124499201775,
      "learning_rate": 1.721491919561913e-07,
      "loss": 0.3597073554992676,
      "step": 198
    },
    {
      "epoch": 2.8106666666666666,
      "grad_norm": 0.007504038512706757,
      "learning_rate": 1.514088979166256e-07,
      "loss": 0.3420804440975189,
      "step": 199
    },
    {
      "epoch": 2.824888888888889,
      "grad_norm": 0.007838167250156403,
      "learning_rate": 1.3198031674745814e-07,
      "loss": 0.3697103261947632,
      "step": 200
    },
    {
      "epoch": 2.824888888888889,
      "eval_loss": 0.49903449416160583,
      "eval_runtime": 4.213,
      "eval_samples_per_second": 47.473,
      "eval_steps_per_second": 23.736,
      "step": 200
    },
    {
      "epoch": 2.8391111111111114,
      "grad_norm": 0.008086729794740677,
      "learning_rate": 1.138687045569975e-07,
      "loss": 0.35418957471847534,
      "step": 201
    },
    {
      "epoch": 2.8533333333333335,
      "grad_norm": 0.007895248010754585,
      "learning_rate": 9.70789611675449e-08,
      "loss": 0.3809206783771515,
      "step": 202
    },
    {
      "epoch": 2.8675555555555556,
      "grad_norm": 0.007653921376913786,
      "learning_rate": 8.161562878982399e-08,
      "loss": 0.33729785680770874,
      "step": 203
    },
    {
      "epoch": 2.8817777777777778,
      "grad_norm": 0.00890001654624939,
      "learning_rate": 6.74828907941516e-08,
      "loss": 0.3682692050933838,
      "step": 204
    },
    {
      "epoch": 2.896,
      "grad_norm": 0.008669495582580566,
      "learning_rate": 5.468457057869358e-08,
      "loss": 0.40091854333877563,
      "step": 205
    },
    {
      "epoch": 2.910222222222222,
      "grad_norm": 0.00770574901252985,
      "learning_rate": 4.322413053509944e-08,
      "loss": 0.338018000125885,
      "step": 206
    },
    {
      "epoch": 2.924444444444444,
      "grad_norm": 0.008314141072332859,
      "learning_rate": 3.31046711118066e-08,
      "loss": 0.3696953058242798,
      "step": 207
    },
    {
      "epoch": 2.9386666666666668,
      "grad_norm": 0.007442758418619633,
      "learning_rate": 2.4328929975260262e-08,
      "loss": 0.3460949659347534,
      "step": 208
    },
    {
      "epoch": 2.952888888888889,
      "grad_norm": 0.008314011618494987,
      "learning_rate": 1.6899281269279756e-08,
      "loss": 0.35688620805740356,
      "step": 209
    },
    {
      "epoch": 2.967111111111111,
      "grad_norm": 0.007803616113960743,
      "learning_rate": 1.0817734972768946e-08,
      "loss": 0.39211517572402954,
      "step": 210
    },
    {
      "epoch": 2.981333333333333,
      "grad_norm": 0.008699736557900906,
      "learning_rate": 6.085936355947897e-09,
      "loss": 0.38052815198898315,
      "step": 211
    },
    {
      "epoch": 2.9955555555555557,
      "grad_norm": 0.007957417517900467,
      "learning_rate": 2.7051655352494654e-09,
      "loss": 0.3612944185733795,
      "step": 212
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.014429433271288872,
      "learning_rate": 6.763371270035457e-10,
      "loss": 0.5174569487571716,
      "step": 213
    },
    {
      "epoch": 3.0,
      "step": 213,
      "total_flos": 4.868007593928294e+16,
      "train_loss": 0.0,
      "train_runtime": 3.3055,
      "train_samples_per_second": 16336.51,
      "train_steps_per_second": 32.673
    }
  ],
  "logging_steps": 1,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.868007593928294e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}