{
  "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": 0.253393292427063,
      "learning_rate": 0.0,
      "loss": 1.19514799118042,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.2720104455947876,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.2398133277893066,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.22159169614315033,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.9782462120056152,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.17487271130084991,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8072947263717651,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.08528934419155121,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.5301008224487305,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.08074624091386795,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.6367583274841309,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.05584918335080147,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.6089775562286377,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.032228983938694,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.5260579586029053,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.026230908930301666,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5446298122406006,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.019648801535367966,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.5338459610939026,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.014007463119924068,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.45045405626296997,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.013295263983309269,
      "learning_rate": 5e-06,
      "loss": 0.49363279342651367,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.01435786858201027,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.48757249116897583,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.015238163061439991,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.5002430081367493,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.014418123289942741,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.4964277148246765,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.014306087978184223,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.4818333387374878,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.009899069555103779,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.4609573483467102,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.010643995366990566,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.47600606083869934,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.012857547029852867,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.4962907135486603,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.01670556701719761,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5028363466262817,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.010331347584724426,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.44582226872444153,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.010525904595851898,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.4757377505302429,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.009544270113110542,
      "learning_rate": 1e-05,
      "loss": 0.4707476496696472,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.009730499237775803,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.49240708351135254,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.008985932916402817,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.450992614030838,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.01072725746780634,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.4514142870903015,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.01058228686451912,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.44021710753440857,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.009333685040473938,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.4491778016090393,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.009250632487237453,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.4285920560359955,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.010210932232439518,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5484102368354797,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.008848125115036964,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.4242202043533325,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.00905672088265419,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.4533390402793884,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.008254914544522762,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.4243648052215576,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.009192033670842648,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5120309591293335,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.009636987932026386,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.4871100187301636,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.008572430349886417,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.46277713775634766,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.008587818592786789,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.45996755361557007,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.010775095783174038,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.47378021478652954,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.00995537731796503,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.4684975743293762,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.009079818613827229,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.5784010887145996,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.008139098063111305,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.46650874614715576,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.007847482338547707,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.42804157733917236,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.008446140214800835,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.48224180936813354,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.008632696233689785,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.4561079144477844,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.008637293241918087,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.4007866382598877,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.008761093020439148,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.4587845802307129,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.008726399391889572,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.4571158289909363,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.008282204158604145,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.4724605679512024,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.008231760933995247,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.4600468575954437,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.00751511100679636,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.4377005994319916,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.4685295820236206,
      "eval_runtime": 5.4716,
      "eval_samples_per_second": 36.553,
      "eval_steps_per_second": 18.276,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.008261662907898426,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.4415626525878906,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.007395230233669281,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.42561036348342896,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.008451394736766815,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4630648195743561,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.007475187536329031,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.43418699502944946,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.00859637837857008,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.47063255310058594,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.007597765419632196,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.41920918226242065,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.018636908382177353,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.4757845401763916,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.008423218503594398,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.5198032855987549,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.008149159140884876,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.46035224199295044,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.00819750688970089,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.4945712983608246,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.00855066254734993,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.4513372778892517,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.008660132065415382,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.49865084886550903,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.007741494104266167,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.4319220185279846,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.007900395430624485,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.43760013580322266,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.007346940692514181,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.41593095660209656,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.00902250874787569,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.48464590311050415,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.007672084029763937,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.41884416341781616,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.008009645156562328,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.40650737285614014,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.008077424019575119,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.4726918637752533,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.007576521951705217,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.4404842257499695,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.012638773769140244,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.42633137106895447,
      "step": 71
    },
    {
      "epoch": 1.0142222222222221,
      "grad_norm": 0.008662556298077106,
      "learning_rate": 8.462100635075097e-06,
      "loss": 0.46000930666923523,
      "step": 72
    },
    {
      "epoch": 1.0284444444444445,
      "grad_norm": 0.008270082995295525,
      "learning_rate": 8.40229882467003e-06,
      "loss": 0.42150819301605225,
      "step": 73
    },
    {
      "epoch": 1.0426666666666666,
      "grad_norm": 0.007625850848853588,
      "learning_rate": 8.341576573860049e-06,
      "loss": 0.37313175201416016,
      "step": 74
    },
    {
      "epoch": 1.056888888888889,
      "grad_norm": 0.00790152233093977,
      "learning_rate": 8.279950310130218e-06,
      "loss": 0.382789671421051,
      "step": 75
    },
    {
      "epoch": 1.0711111111111111,
      "grad_norm": 0.007986027747392654,
      "learning_rate": 8.2174367055326e-06,
      "loss": 0.3734534978866577,
      "step": 76
    },
    {
      "epoch": 1.0853333333333333,
      "grad_norm": 0.007174879312515259,
      "learning_rate": 8.154052672175888e-06,
      "loss": 0.37693876028060913,
      "step": 77
    },
    {
      "epoch": 1.0995555555555556,
      "grad_norm": 0.008486706763505936,
      "learning_rate": 8.08981535765009e-06,
      "loss": 0.4265296459197998,
      "step": 78
    },
    {
      "epoch": 1.1137777777777778,
      "grad_norm": 0.007609546184539795,
      "learning_rate": 8.024742140387506e-06,
      "loss": 0.3812956213951111,
      "step": 79
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.007912754081189632,
      "learning_rate": 7.95885062496126e-06,
      "loss": 0.4131423234939575,
      "step": 80
    },
    {
      "epoch": 1.1422222222222222,
      "grad_norm": 0.007641648408025503,
      "learning_rate": 7.892158637322647e-06,
      "loss": 0.37861311435699463,
      "step": 81
    },
    {
      "epoch": 1.1564444444444444,
      "grad_norm": 0.007570190355181694,
      "learning_rate": 7.824684219978591e-06,
      "loss": 0.3589654564857483,
      "step": 82
    },
    {
      "epoch": 1.1706666666666667,
      "grad_norm": 0.007670491933822632,
      "learning_rate": 7.756445627110523e-06,
      "loss": 0.40794360637664795,
      "step": 83
    },
    {
      "epoch": 1.1848888888888889,
      "grad_norm": 0.009116973727941513,
      "learning_rate": 7.68746131963598e-06,
      "loss": 0.4278006851673126,
      "step": 84
    },
    {
      "epoch": 1.199111111111111,
      "grad_norm": 0.007852817885577679,
      "learning_rate": 7.6177499602143e-06,
      "loss": 0.371395081281662,
      "step": 85
    },
    {
      "epoch": 1.2133333333333334,
      "grad_norm": 0.00870604906231165,
      "learning_rate": 7.547330408197695e-06,
      "loss": 0.4305034279823303,
      "step": 86
    },
    {
      "epoch": 1.2275555555555555,
      "grad_norm": 0.008404702879488468,
      "learning_rate": 7.476221714529167e-06,
      "loss": 0.4348181188106537,
      "step": 87
    },
    {
      "epoch": 1.2417777777777779,
      "grad_norm": 0.008913768455386162,
      "learning_rate": 7.404443116588548e-06,
      "loss": 0.4309384822845459,
      "step": 88
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.007682010997086763,
      "learning_rate": 7.332014032988123e-06,
      "loss": 0.4107038676738739,
      "step": 89
    },
    {
      "epoch": 1.2702222222222221,
      "grad_norm": 0.00787457637488842,
      "learning_rate": 7.2589540583192165e-06,
      "loss": 0.37457963824272156,
      "step": 90
    },
    {
      "epoch": 1.2844444444444445,
      "grad_norm": 0.007768277078866959,
      "learning_rate": 7.185282957851175e-06,
      "loss": 0.37697723507881165,
      "step": 91
    },
    {
      "epoch": 1.2986666666666666,
      "grad_norm": 0.008521760813891888,
      "learning_rate": 7.111020662184174e-06,
      "loss": 0.40353477001190186,
      "step": 92
    },
    {
      "epoch": 1.3128888888888888,
      "grad_norm": 0.0077499281615018845,
      "learning_rate": 7.036187261857289e-06,
      "loss": 0.37755411863327026,
      "step": 93
    },
    {
      "epoch": 1.3271111111111111,
      "grad_norm": 0.00870734266936779,
      "learning_rate": 6.960803001913315e-06,
      "loss": 0.3729894757270813,
      "step": 94
    },
    {
      "epoch": 1.3413333333333333,
      "grad_norm": 0.007563227321952581,
      "learning_rate": 6.884888276421766e-06,
      "loss": 0.4091319441795349,
      "step": 95
    },
    {
      "epoch": 1.3555555555555556,
      "grad_norm": 0.00803642813116312,
      "learning_rate": 6.8084636229615786e-06,
      "loss": 0.4048840403556824,
      "step": 96
    },
    {
      "epoch": 1.3697777777777778,
      "grad_norm": 0.00779891200363636,
      "learning_rate": 6.731549717064975e-06,
      "loss": 0.39409685134887695,
      "step": 97
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.008260682225227356,
      "learning_rate": 6.654167366624009e-06,
      "loss": 0.36237582564353943,
      "step": 98
    },
    {
      "epoch": 1.3982222222222223,
      "grad_norm": 0.008373094722628593,
      "learning_rate": 6.576337506261314e-06,
      "loss": 0.38763654232025146,
      "step": 99
    },
    {
      "epoch": 1.4124444444444444,
      "grad_norm": 0.007797387894243002,
      "learning_rate": 6.498081191666549e-06,
      "loss": 0.41751331090927124,
      "step": 100
    },
    {
      "epoch": 1.4124444444444444,
      "eval_loss": 0.4669477939605713,
      "eval_runtime": 5.2715,
      "eval_samples_per_second": 37.94,
      "eval_steps_per_second": 18.97,
      "step": 100
    },
    {
      "epoch": 1.4266666666666667,
      "grad_norm": 0.007338334806263447,
      "learning_rate": 6.419419593900109e-06,
      "loss": 0.38504236936569214,
      "step": 101
    },
    {
      "epoch": 1.4408888888888889,
      "grad_norm": 0.007528901565819979,
      "learning_rate": 6.340373993665607e-06,
      "loss": 0.36031031608581543,
      "step": 102
    },
    {
      "epoch": 1.455111111111111,
      "grad_norm": 0.007573080714792013,
      "learning_rate": 6.2609657755527135e-06,
      "loss": 0.3863949179649353,
      "step": 103
    },
    {
      "epoch": 1.4693333333333334,
      "grad_norm": 0.008099780417978764,
      "learning_rate": 6.1812164222518626e-06,
      "loss": 0.3955462574958801,
      "step": 104
    },
    {
      "epoch": 1.4835555555555555,
      "grad_norm": 0.008717137388885021,
      "learning_rate": 6.101147508742456e-06,
      "loss": 0.39310169219970703,
      "step": 105
    },
    {
      "epoch": 1.4977777777777779,
      "grad_norm": 0.008383029140532017,
      "learning_rate": 6.020780696456059e-06,
      "loss": 0.4533539414405823,
      "step": 106
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.007702656090259552,
      "learning_rate": 5.940137727416247e-06,
      "loss": 0.3985057473182678,
      "step": 107
    },
    {
      "epoch": 1.5262222222222221,
      "grad_norm": 0.00808175653219223,
      "learning_rate": 5.859240418356614e-06,
      "loss": 0.3878968358039856,
      "step": 108
    },
    {
      "epoch": 1.5404444444444443,
      "grad_norm": 0.008781371638178825,
      "learning_rate": 5.778110654818602e-06,
      "loss": 0.39648741483688354,
      "step": 109
    },
    {
      "epoch": 1.5546666666666666,
      "grad_norm": 0.008896375074982643,
      "learning_rate": 5.696770385230679e-06,
      "loss": 0.4319821000099182,
      "step": 110
    },
    {
      "epoch": 1.568888888888889,
      "grad_norm": 0.008202116936445236,
      "learning_rate": 5.615241614970546e-06,
      "loss": 0.4078192710876465,
      "step": 111
    },
    {
      "epoch": 1.5831111111111111,
      "grad_norm": 0.007843846455216408,
      "learning_rate": 5.533546400411899e-06,
      "loss": 0.38504159450531006,
      "step": 112
    },
    {
      "epoch": 1.5973333333333333,
      "grad_norm": 0.00823921337723732,
      "learning_rate": 5.4517068429574215e-06,
      "loss": 0.3971819579601288,
      "step": 113
    },
    {
      "epoch": 1.6115555555555554,
      "grad_norm": 0.007411513011902571,
      "learning_rate": 5.3697450830595775e-06,
      "loss": 0.3886791169643402,
      "step": 114
    },
    {
      "epoch": 1.6257777777777778,
      "grad_norm": 0.007902945391833782,
      "learning_rate": 5.287683294230855e-06,
      "loss": 0.37610527873039246,
      "step": 115
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.007778776343911886,
      "learning_rate": 5.20554367704505e-06,
      "loss": 0.3846814036369324,
      "step": 116
    },
    {
      "epoch": 1.6542222222222223,
      "grad_norm": 0.008897176012396812,
      "learning_rate": 5.123348453131242e-06,
      "loss": 0.3917155861854553,
      "step": 117
    },
    {
      "epoch": 1.6684444444444444,
      "grad_norm": 0.008548559620976448,
      "learning_rate": 5.041119859162068e-06,
      "loss": 0.39533206820487976,
      "step": 118
    },
    {
      "epoch": 1.6826666666666665,
      "grad_norm": 0.008137239143252373,
      "learning_rate": 4.958880140837934e-06,
      "loss": 0.4113273620605469,
      "step": 119
    },
    {
      "epoch": 1.696888888888889,
      "grad_norm": 0.008478965610265732,
      "learning_rate": 4.876651546868759e-06,
      "loss": 0.39543214440345764,
      "step": 120
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 0.00835413858294487,
      "learning_rate": 4.794456322954953e-06,
      "loss": 0.4548013508319855,
      "step": 121
    },
    {
      "epoch": 1.7253333333333334,
      "grad_norm": 0.00832394976168871,
      "learning_rate": 4.7123167057691446e-06,
      "loss": 0.4111294150352478,
      "step": 122
    },
    {
      "epoch": 1.7395555555555555,
      "grad_norm": 0.008472571149468422,
      "learning_rate": 4.630254916940424e-06,
      "loss": 0.43050098419189453,
      "step": 123
    },
    {
      "epoch": 1.7537777777777777,
      "grad_norm": 0.00816201139241457,
      "learning_rate": 4.548293157042581e-06,
      "loss": 0.41356489062309265,
      "step": 124
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.008180899545550346,
      "learning_rate": 4.466453599588103e-06,
      "loss": 0.41799914836883545,
      "step": 125
    },
    {
      "epoch": 1.7822222222222224,
      "grad_norm": 0.007402091287076473,
      "learning_rate": 4.384758385029457e-06,
      "loss": 0.3510154187679291,
      "step": 126
    },
    {
      "epoch": 1.7964444444444445,
      "grad_norm": 0.008476709015667439,
      "learning_rate": 4.3032296147693225e-06,
      "loss": 0.4098949432373047,
      "step": 127
    },
    {
      "epoch": 1.8106666666666666,
      "grad_norm": 0.008135325275361538,
      "learning_rate": 4.2218893451814005e-06,
      "loss": 0.36957240104675293,
      "step": 128
    },
    {
      "epoch": 1.8248888888888888,
      "grad_norm": 0.007964376360177994,
      "learning_rate": 4.140759581643386e-06,
      "loss": 0.3535369038581848,
      "step": 129
    },
    {
      "epoch": 1.8391111111111111,
      "grad_norm": 0.00742813665419817,
      "learning_rate": 4.059862272583755e-06,
      "loss": 0.38296306133270264,
      "step": 130
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 0.007901367731392384,
      "learning_rate": 3.979219303543942e-06,
      "loss": 0.38752996921539307,
      "step": 131
    },
    {
      "epoch": 1.8675555555555556,
      "grad_norm": 0.008205283433198929,
      "learning_rate": 3.898852491257547e-06,
      "loss": 0.3867356479167938,
      "step": 132
    },
    {
      "epoch": 1.8817777777777778,
      "grad_norm": 0.008251599036157131,
      "learning_rate": 3.818783577748138e-06,
      "loss": 0.42934614419937134,
      "step": 133
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.008710331283509731,
      "learning_rate": 3.7390342244472886e-06,
      "loss": 0.4096015691757202,
      "step": 134
    },
    {
      "epoch": 1.9102222222222223,
      "grad_norm": 0.008127489127218723,
      "learning_rate": 3.659626006334395e-06,
      "loss": 0.3849722743034363,
      "step": 135
    },
    {
      "epoch": 1.9244444444444444,
      "grad_norm": 0.008900986984372139,
      "learning_rate": 3.5805804060998926e-06,
      "loss": 0.415260910987854,
      "step": 136
    },
    {
      "epoch": 1.9386666666666668,
      "grad_norm": 0.00907993782311678,
      "learning_rate": 3.501918808333453e-06,
      "loss": 0.48382842540740967,
      "step": 137
    },
    {
      "epoch": 1.952888888888889,
      "grad_norm": 0.008263039402663708,
      "learning_rate": 3.4236624937386874e-06,
      "loss": 0.4434107542037964,
      "step": 138
    },
    {
      "epoch": 1.967111111111111,
      "grad_norm": 0.008353665471076965,
      "learning_rate": 3.3458326333759927e-06,
      "loss": 0.41760051250457764,
      "step": 139
    },
    {
      "epoch": 1.9813333333333332,
      "grad_norm": 0.008556668646633625,
      "learning_rate": 3.268450282935026e-06,
      "loss": 0.43642479181289673,
      "step": 140
    },
    {
      "epoch": 1.9955555555555555,
      "grad_norm": 0.008040979504585266,
      "learning_rate": 3.1915363770384223e-06,
      "loss": 0.38327687978744507,
      "step": 141
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.012571632862091064,
      "learning_rate": 3.1151117235782346e-06,
      "loss": 0.3751964867115021,
      "step": 142
    },
    {
      "epoch": 2.014222222222222,
      "grad_norm": 0.008403269574046135,
      "learning_rate": 3.0391969980866874e-06,
      "loss": 0.3831713795661926,
      "step": 143
    },
    {
      "epoch": 2.0284444444444443,
      "grad_norm": 0.008236616849899292,
      "learning_rate": 2.963812738142713e-06,
      "loss": 0.338630735874176,
      "step": 144
    },
    {
      "epoch": 2.042666666666667,
      "grad_norm": 0.008433214388787746,
      "learning_rate": 2.8889793378158284e-06,
      "loss": 0.3684050440788269,
      "step": 145
    },
    {
      "epoch": 2.056888888888889,
      "grad_norm": 0.008040281943976879,
      "learning_rate": 2.814717042148827e-06,
      "loss": 0.37092137336730957,
      "step": 146
    },
    {
      "epoch": 2.071111111111111,
      "grad_norm": 0.008197156712412834,
      "learning_rate": 2.7410459416807856e-06,
      "loss": 0.34995853900909424,
      "step": 147
    },
    {
      "epoch": 2.0853333333333333,
      "grad_norm": 0.009072407148778439,
      "learning_rate": 2.6679859670118785e-06,
      "loss": 0.37355348467826843,
      "step": 148
    },
    {
      "epoch": 2.0995555555555554,
      "grad_norm": 0.00807118322700262,
      "learning_rate": 2.5955568834114523e-06,
      "loss": 0.3448713421821594,
      "step": 149
    },
    {
      "epoch": 2.113777777777778,
      "grad_norm": 0.00770068122074008,
      "learning_rate": 2.523778285470835e-06,
      "loss": 0.3545028865337372,
      "step": 150
    },
    {
      "epoch": 2.113777777777778,
      "eval_loss": 0.4679063558578491,
      "eval_runtime": 5.4161,
      "eval_samples_per_second": 36.927,
      "eval_steps_per_second": 18.463,
      "step": 150
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.007919526658952236,
      "learning_rate": 2.452669591802307e-06,
      "loss": 0.32551515102386475,
      "step": 151
    },
    {
      "epoch": 2.1422222222222222,
      "grad_norm": 0.007321993354707956,
      "learning_rate": 2.3822500397857016e-06,
      "loss": 0.35764873027801514,
      "step": 152
    },
    {
      "epoch": 2.1564444444444444,
      "grad_norm": 0.0076365480199456215,
      "learning_rate": 2.3125386803640188e-06,
      "loss": 0.35795581340789795,
      "step": 153
    },
    {
      "epoch": 2.1706666666666665,
      "grad_norm": 0.007587647996842861,
      "learning_rate": 2.243554372889479e-06,
      "loss": 0.32651567459106445,
      "step": 154
    },
    {
      "epoch": 2.1848888888888887,
      "grad_norm": 0.007799312938004732,
      "learning_rate": 2.1753157800214107e-06,
      "loss": 0.3542096018791199,
      "step": 155
    },
    {
      "epoch": 2.1991111111111112,
      "grad_norm": 0.007910694926977158,
      "learning_rate": 2.1078413626773547e-06,
      "loss": 0.3560444116592407,
      "step": 156
    },
    {
      "epoch": 2.2133333333333334,
      "grad_norm": 0.008300457149744034,
      "learning_rate": 2.0411493750387423e-06,
      "loss": 0.3283962607383728,
      "step": 157
    },
    {
      "epoch": 2.2275555555555555,
      "grad_norm": 0.007787623442709446,
      "learning_rate": 1.9752578596124955e-06,
      "loss": 0.362970769405365,
      "step": 158
    },
    {
      "epoch": 2.2417777777777776,
      "grad_norm": 0.007931886240839958,
      "learning_rate": 1.9101846423499113e-06,
      "loss": 0.3372136354446411,
      "step": 159
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.008211000822484493,
      "learning_rate": 1.8459473278241125e-06,
      "loss": 0.343697726726532,
      "step": 160
    },
    {
      "epoch": 2.2702222222222224,
      "grad_norm": 0.008033247664570808,
      "learning_rate": 1.7825632944674016e-06,
      "loss": 0.3472204804420471,
      "step": 161
    },
    {
      "epoch": 2.2844444444444445,
      "grad_norm": 0.008930593729019165,
      "learning_rate": 1.7200496898697832e-06,
      "loss": 0.34057295322418213,
      "step": 162
    },
    {
      "epoch": 2.2986666666666666,
      "grad_norm": 0.007960367947816849,
      "learning_rate": 1.6584234261399535e-06,
      "loss": 0.3398140072822571,
      "step": 163
    },
    {
      "epoch": 2.3128888888888888,
      "grad_norm": 0.008388614282011986,
      "learning_rate": 1.5977011753299726e-06,
      "loss": 0.3423030376434326,
      "step": 164
    },
    {
      "epoch": 2.327111111111111,
      "grad_norm": 0.009143203496932983,
      "learning_rate": 1.5378993649249053e-06,
      "loss": 0.4059848189353943,
      "step": 165
    },
    {
      "epoch": 2.3413333333333335,
      "grad_norm": 0.008042566478252411,
      "learning_rate": 1.4790341733986085e-06,
      "loss": 0.35659873485565186,
      "step": 166
    },
    {
      "epoch": 2.3555555555555556,
      "grad_norm": 0.007340035866945982,
      "learning_rate": 1.4211215258368866e-06,
      "loss": 0.320560097694397,
      "step": 167
    },
    {
      "epoch": 2.3697777777777778,
      "grad_norm": 0.008758354000747204,
      "learning_rate": 1.3641770896292083e-06,
      "loss": 0.3432486057281494,
      "step": 168
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.008217270486056805,
      "learning_rate": 1.3082162702301276e-06,
      "loss": 0.3448861241340637,
      "step": 169
    },
    {
      "epoch": 2.398222222222222,
      "grad_norm": 0.008302765898406506,
      "learning_rate": 1.2532542069915722e-06,
      "loss": 0.4012100100517273,
      "step": 170
    },
    {
      "epoch": 2.4124444444444446,
      "grad_norm": 0.0086008096113801,
      "learning_rate": 1.1993057690671174e-06,
      "loss": 0.35434189438819885,
      "step": 171
    },
    {
      "epoch": 2.4266666666666667,
      "grad_norm": 0.009528086520731449,
      "learning_rate": 1.1463855513893695e-06,
      "loss": 0.37489616870880127,
      "step": 172
    },
    {
      "epoch": 2.440888888888889,
      "grad_norm": 0.008264975622296333,
      "learning_rate": 1.0945078707215224e-06,
      "loss": 0.3599584698677063,
      "step": 173
    },
    {
      "epoch": 2.455111111111111,
      "grad_norm": 0.008293098770081997,
      "learning_rate": 1.0436867617841768e-06,
      "loss": 0.38492339849472046,
      "step": 174
    },
    {
      "epoch": 2.469333333333333,
      "grad_norm": 0.007827190682291985,
      "learning_rate": 9.939359734584552e-07,
      "loss": 0.36968979239463806,
      "step": 175
    },
    {
      "epoch": 2.4835555555555557,
      "grad_norm": 0.008390667848289013,
      "learning_rate": 9.452689650664515e-07,
      "loss": 0.3575425148010254,
      "step": 176
    },
    {
      "epoch": 2.497777777777778,
      "grad_norm": 0.007562275975942612,
      "learning_rate": 8.976989027300265e-07,
      "loss": 0.35382080078125,
      "step": 177
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.007893560454249382,
      "learning_rate": 8.512386558088919e-07,
      "loss": 0.35292625427246094,
      "step": 178
    },
    {
      "epoch": 2.526222222222222,
      "grad_norm": 0.007973878644406796,
      "learning_rate": 8.059007934190194e-07,
      "loss": 0.3658143877983093,
      "step": 179
    },
    {
      "epoch": 2.5404444444444443,
      "grad_norm": 0.008489987812936306,
      "learning_rate": 7.61697581032243e-07,
      "loss": 0.34945034980773926,
      "step": 180
    },
    {
      "epoch": 2.554666666666667,
      "grad_norm": 0.007993645034730434,
      "learning_rate": 7.186409771580355e-07,
      "loss": 0.3492674231529236,
      "step": 181
    },
    {
      "epoch": 2.568888888888889,
      "grad_norm": 0.007816205732524395,
      "learning_rate": 6.76742630108298e-07,
      "loss": 0.35949787497520447,
      "step": 182
    },
    {
      "epoch": 2.583111111111111,
      "grad_norm": 0.00765154417604208,
      "learning_rate": 6.360138748461015e-07,
      "loss": 0.35065189003944397,
      "step": 183
    },
    {
      "epoch": 2.5973333333333333,
      "grad_norm": 0.007598839234560728,
      "learning_rate": 5.964657299191712e-07,
      "loss": 0.31525540351867676,
      "step": 184
    },
    {
      "epoch": 2.6115555555555554,
      "grad_norm": 0.00796365924179554,
      "learning_rate": 5.581088944789953e-07,
      "loss": 0.34680360555648804,
      "step": 185
    },
    {
      "epoch": 2.6257777777777775,
      "grad_norm": 0.008079800754785538,
      "learning_rate": 5.20953745386329e-07,
      "loss": 0.3423649072647095,
      "step": 186
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.008171727880835533,
      "learning_rate": 4.850103344038853e-07,
      "loss": 0.3583834767341614,
      "step": 187
    },
    {
      "epoch": 2.6542222222222223,
      "grad_norm": 0.007568752858787775,
      "learning_rate": 4.502883854769935e-07,
      "loss": 0.3272634744644165,
      "step": 188
    },
    {
      "epoch": 2.6684444444444444,
      "grad_norm": 0.00814193394035101,
      "learning_rate": 4.167972921029262e-07,
      "loss": 0.3352956175804138,
      "step": 189
    },
    {
      "epoch": 2.6826666666666665,
      "grad_norm": 0.008751407265663147,
      "learning_rate": 3.8454611478963235e-07,
      "loss": 0.3704286515712738,
      "step": 190
    },
    {
      "epoch": 2.696888888888889,
      "grad_norm": 0.007807895075529814,
      "learning_rate": 3.535435786045538e-07,
      "loss": 0.34566229581832886,
      "step": 191
    },
    {
      "epoch": 2.7111111111111112,
      "grad_norm": 0.007984541356563568,
      "learning_rate": 3.237980708141919e-07,
      "loss": 0.35052379965782166,
      "step": 192
    },
    {
      "epoch": 2.7253333333333334,
      "grad_norm": 0.009312397800385952,
      "learning_rate": 2.9531763861505967e-07,
      "loss": 0.38708382844924927,
      "step": 193
    },
    {
      "epoch": 2.7395555555555555,
      "grad_norm": 0.008055887185037136,
      "learning_rate": 2.681099869566328e-07,
      "loss": 0.3316305875778198,
      "step": 194
    },
    {
      "epoch": 2.7537777777777777,
      "grad_norm": 0.008029562421143055,
      "learning_rate": 2.4218247645689306e-07,
      "loss": 0.3650358319282532,
      "step": 195
    },
    {
      "epoch": 2.768,
      "grad_norm": 0.00823246967047453,
      "learning_rate": 2.175421214110235e-07,
      "loss": 0.36560434103012085,
      "step": 196
    },
    {
      "epoch": 2.7822222222222224,
      "grad_norm": 0.008692881092429161,
      "learning_rate": 1.941955878938029e-07,
      "loss": 0.3463239371776581,
      "step": 197
    },
    {
      "epoch": 2.7964444444444445,
      "grad_norm": 0.008173434063792229,
      "learning_rate": 1.721491919561913e-07,
      "loss": 0.35629892349243164,
      "step": 198
    },
    {
      "epoch": 2.8106666666666666,
      "grad_norm": 0.00767622422426939,
      "learning_rate": 1.514088979166256e-07,
      "loss": 0.33887457847595215,
      "step": 199
    },
    {
      "epoch": 2.824888888888889,
      "grad_norm": 0.007811338175088167,
      "learning_rate": 1.3198031674745814e-07,
      "loss": 0.36586421728134155,
      "step": 200
    },
    {
      "epoch": 2.824888888888889,
      "eval_loss": 0.4734371602535248,
      "eval_runtime": 7.1506,
      "eval_samples_per_second": 27.97,
      "eval_steps_per_second": 13.985,
      "step": 200
    },
    {
      "epoch": 2.8391111111111114,
      "grad_norm": 0.008272381499409676,
      "learning_rate": 1.138687045569975e-07,
      "loss": 0.3514959216117859,
      "step": 201
    },
    {
      "epoch": 2.8533333333333335,
      "grad_norm": 0.008001282811164856,
      "learning_rate": 9.70789611675449e-08,
      "loss": 0.37950894236564636,
      "step": 202
    },
    {
      "epoch": 2.8675555555555556,
      "grad_norm": 0.007416888140141964,
      "learning_rate": 8.161562878982399e-08,
      "loss": 0.3352017402648926,
      "step": 203
    },
    {
      "epoch": 2.8817777777777778,
      "grad_norm": 0.008772965520620346,
      "learning_rate": 6.74828907941516e-08,
      "loss": 0.36504414677619934,
      "step": 204
    },
    {
      "epoch": 2.896,
      "grad_norm": 0.008397468365728855,
      "learning_rate": 5.468457057869358e-08,
      "loss": 0.3987666964530945,
      "step": 205
    },
    {
      "epoch": 2.910222222222222,
      "grad_norm": 0.00775982066988945,
      "learning_rate": 4.322413053509944e-08,
      "loss": 0.3345492482185364,
      "step": 206
    },
    {
      "epoch": 2.924444444444444,
      "grad_norm": 0.008166249841451645,
      "learning_rate": 3.31046711118066e-08,
      "loss": 0.367769718170166,
      "step": 207
    },
    {
      "epoch": 2.9386666666666668,
      "grad_norm": 0.007682916708290577,
      "learning_rate": 2.4328929975260262e-08,
      "loss": 0.34441590309143066,
      "step": 208
    },
    {
      "epoch": 2.952888888888889,
      "grad_norm": 0.008051120676100254,
      "learning_rate": 1.6899281269279756e-08,
      "loss": 0.3472161889076233,
      "step": 209
    },
    {
      "epoch": 2.967111111111111,
      "grad_norm": 0.0077741509303450584,
      "learning_rate": 1.0817734972768946e-08,
      "loss": 0.3906354308128357,
      "step": 210
    },
    {
      "epoch": 2.981333333333333,
      "grad_norm": 0.008870133198797703,
      "learning_rate": 6.085936355947897e-09,
      "loss": 0.37977275252342224,
      "step": 211
    },
    {
      "epoch": 2.9955555555555557,
      "grad_norm": 0.008871600031852722,
      "learning_rate": 2.7051655352494654e-09,
      "loss": 0.3533574342727661,
      "step": 212
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.014481575228273869,
      "learning_rate": 6.763371270035457e-10,
      "loss": 0.5198727250099182,
      "step": 213
    },
    {
      "epoch": 3.0,
      "step": 213,
      "total_flos": 1.0308479847759872e+17,
      "train_loss": 0.4208552807989255,
      "train_runtime": 5691.1072,
      "train_samples_per_second": 9.488,
      "train_steps_per_second": 0.037
    }
  ],
  "logging_steps": 1,
  "max_steps": 213,
  "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": 1.0308479847759872e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}