{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4813186813186814,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.0287306308746338,
      "learning_rate": 0.0,
      "loss": 1.084,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.948112428188324,
      "learning_rate": 9.56e-05,
      "loss": 1.0638,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.0350998640060425,
      "learning_rate": 0.0001912,
      "loss": 1.143,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.1360750198364258,
      "learning_rate": 0.0002868,
      "loss": 1.0394,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.7310333251953125,
      "learning_rate": 0.0003824,
      "loss": 0.8949,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.6246419548988342,
      "learning_rate": 0.000478,
      "loss": 0.9157,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5591331720352173,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9064,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.411284863948822,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8349,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.30876654386520386,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8626,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.39697328209877014,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.8347,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.3990109860897064,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8383,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.3827734589576721,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.7593,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5764995217323303,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.7725,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5014582276344299,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7577,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4466342628002167,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7279,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.3709656894207001,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7577,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5953618288040161,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.8038,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.43582218885421753,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7836,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.35281723737716675,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.7541,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4125503897666931,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7476,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3566338121891022,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.6958,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3785325884819031,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7827,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3147861659526825,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7631,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.4547198712825775,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7453,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3506404459476471,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.7397,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.35579541325569153,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.8032,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.35984915494918823,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.6869,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3912736177444458,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7423,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3313451111316681,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.826,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3460421860218048,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7155,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.42073190212249756,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.7308,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3369511067867279,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7529,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3326997756958008,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.7098,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3323321044445038,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.7104,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.365688294172287,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.6777,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.4034178853034973,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7655,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.4079640209674835,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.6348,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.35669246315956116,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7146,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.4017118513584137,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.8002,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.37425458431243896,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.6953,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3201092779636383,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.6991,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3773852288722992,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.7467,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2974673807621002,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7288,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.30199432373046875,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.7304,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.3696371018886566,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.7752,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3928535282611847,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.6959,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3518235683441162,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.7344,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3202143907546997,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7144,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.39293670654296875,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.7044,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.42684948444366455,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7236,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4143947958946228,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.687,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.46073058247566223,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.7201,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.38219717144966125,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.7589,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.27848541736602783,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.7208,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.2882401943206787,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.7121,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3918374180793762,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.6783,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3108501732349396,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7249,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.31900638341903687,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.725,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.4268058240413666,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.7717,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3654431700706482,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.7369,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.3035155236721039,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.6962,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3147648870944977,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.7239,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.30889788269996643,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7697,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.29330822825431824,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.7438,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3334480822086334,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.6889,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.29151853919029236,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.6632,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.38440635800361633,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.7305,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.32712990045547485,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.8122,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.37737423181533813,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.6368,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3335571885108948,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.6586,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3446078598499298,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.7299,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.30252110958099365,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.7084,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.23997364938259125,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.7479,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3268393576145172,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.7417,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.2819831371307373,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.7691,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3438951075077057,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.7447,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.34539034962654114,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.7299,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.39309996366500854,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.7103,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.4111672341823578,
      "learning_rate": 0.000400629711751663,
      "loss": 0.7175,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.35200831294059753,
      "learning_rate": 0.000399569844789357,
      "loss": 0.7914,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3106718063354492,
      "learning_rate": 0.000398509977827051,
      "loss": 0.7064,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.40410006046295166,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7015,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3284229338169098,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7696,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2930781841278076,
      "learning_rate": 0.000395330376940133,
      "loss": 0.6839,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.4067613184452057,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.7693,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.39632725715637207,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.776,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3314855992794037,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.7207,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3370056748390198,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.7828,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3866356313228607,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.7538,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3172929883003235,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.7807,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.32534992694854736,
      "learning_rate": 0.00038791130820399114,
      "loss": 0.7072,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.26510292291641235,
      "learning_rate": 0.0003868514412416852,
      "loss": 0.6967,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.29210713505744934,
      "learning_rate": 0.00038579157427937917,
      "loss": 0.6601,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3541831374168396,
      "learning_rate": 0.0003847317073170732,
      "loss": 0.7131,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3541385531425476,
      "learning_rate": 0.0003836718403547672,
      "loss": 0.7248,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3337606191635132,
      "learning_rate": 0.0003826119733924612,
      "loss": 0.7652,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.33775588870048523,
      "learning_rate": 0.0003815521064301552,
      "loss": 0.7818,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.3222000300884247,
      "learning_rate": 0.00038049223946784927,
      "loss": 0.733,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.3088921904563904,
      "learning_rate": 0.00037943237250554325,
      "loss": 0.6638,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.2936277687549591,
      "learning_rate": 0.0003783725055432373,
      "loss": 0.7121,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.26708656549453735,
      "learning_rate": 0.0003773126385809313,
      "loss": 0.7353,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.29909640550613403,
      "learning_rate": 0.00037625277161862527,
      "loss": 0.7214,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.30008482933044434,
      "learning_rate": 0.0003751929046563193,
      "loss": 0.7365,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.38386833667755127,
      "learning_rate": 0.00037413303769401335,
      "loss": 0.7514,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3135545253753662,
      "learning_rate": 0.00037307317073170733,
      "loss": 0.6882,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.31808924674987793,
      "learning_rate": 0.0003720133037694014,
      "loss": 0.744,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.30010560154914856,
      "learning_rate": 0.00037095343680709536,
      "loss": 0.6816,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.31569167971611023,
      "learning_rate": 0.00036989356984478935,
      "loss": 0.7064,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.30984246730804443,
      "learning_rate": 0.0003688337028824834,
      "loss": 0.7154,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.286091685295105,
      "learning_rate": 0.0003677738359201774,
      "loss": 0.701,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3322799503803253,
      "learning_rate": 0.0003667139689578714,
      "loss": 0.6629,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.32251879572868347,
      "learning_rate": 0.00036565410199556546,
      "loss": 0.7101,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.3163260221481323,
      "learning_rate": 0.0003645942350332594,
      "loss": 0.7318,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.35563021898269653,
      "learning_rate": 0.00036353436807095343,
      "loss": 0.6708,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3295123875141144,
      "learning_rate": 0.00036247450110864747,
      "loss": 0.7531,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3174284100532532,
      "learning_rate": 0.00036141463414634146,
      "loss": 0.6435,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3112541139125824,
      "learning_rate": 0.0003603547671840355,
      "loss": 0.7079,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.2765205204486847,
      "learning_rate": 0.00035929490022172954,
      "loss": 0.7399,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.4011540412902832,
      "learning_rate": 0.00035823503325942347,
      "loss": 0.7471,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3467070758342743,
      "learning_rate": 0.0003571751662971175,
      "loss": 0.749,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.322721391916275,
      "learning_rate": 0.00035611529933481155,
      "loss": 0.6992,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3257431089878082,
      "learning_rate": 0.00035505543237250554,
      "loss": 0.7448,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3538271188735962,
      "learning_rate": 0.0003539955654101996,
      "loss": 0.7202,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.33168667554855347,
      "learning_rate": 0.0003529356984478936,
      "loss": 0.7521,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3086656630039215,
      "learning_rate": 0.00035187583148558755,
      "loss": 0.6933,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.29101550579071045,
      "learning_rate": 0.0003508159645232816,
      "loss": 0.6807,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.31047967076301575,
      "learning_rate": 0.00034975609756097563,
      "loss": 0.7028,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.4100898206233978,
      "learning_rate": 0.0003486962305986696,
      "loss": 0.7063,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3553723096847534,
      "learning_rate": 0.00034763636363636366,
      "loss": 0.6585,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.34842953085899353,
      "learning_rate": 0.0003465764966740577,
      "loss": 0.6551,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.29668596386909485,
      "learning_rate": 0.00034551662971175163,
      "loss": 0.7625,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.32529106736183167,
      "learning_rate": 0.00034445676274944567,
      "loss": 0.6823,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3435796797275543,
      "learning_rate": 0.0003433968957871397,
      "loss": 0.7695,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.360817015171051,
      "learning_rate": 0.0003423370288248337,
      "loss": 0.718,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.37331467866897583,
      "learning_rate": 0.00034127716186252774,
      "loss": 0.7678,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.29934585094451904,
      "learning_rate": 0.0003402172949002218,
      "loss": 0.7433,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.29423919320106506,
      "learning_rate": 0.00033915742793791577,
      "loss": 0.7844,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.2784546911716461,
      "learning_rate": 0.00033809756097560975,
      "loss": 0.6756,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3294104039669037,
      "learning_rate": 0.0003370376940133038,
      "loss": 0.7055,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.32865482568740845,
      "learning_rate": 0.0003359778270509978,
      "loss": 0.6911,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.28258049488067627,
      "learning_rate": 0.0003349179600886918,
      "loss": 0.6967,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.34952202439308167,
      "learning_rate": 0.00033385809312638586,
      "loss": 0.7296,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.32775378227233887,
      "learning_rate": 0.00033279822616407985,
      "loss": 0.7261,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.34333598613739014,
      "learning_rate": 0.00033173835920177384,
      "loss": 0.6252,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3044952154159546,
      "learning_rate": 0.0003306784922394679,
      "loss": 0.7971,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3026304244995117,
      "learning_rate": 0.00032961862527716186,
      "loss": 0.7358,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.32202282547950745,
      "learning_rate": 0.0003285587583148559,
      "loss": 0.7518,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.28900209069252014,
      "learning_rate": 0.00032749889135254994,
      "loss": 0.7378,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.30475756525993347,
      "learning_rate": 0.00032643902439024393,
      "loss": 0.6967,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.27916035056114197,
      "learning_rate": 0.0003253791574279379,
      "loss": 0.7024,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.2913808226585388,
      "learning_rate": 0.0003243192904656319,
      "loss": 0.7749,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3602457344532013,
      "learning_rate": 0.00032325942350332594,
      "loss": 0.7215,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.2920915186405182,
      "learning_rate": 0.00032219955654102,
      "loss": 0.6784,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3847486674785614,
      "learning_rate": 0.00032113968957871397,
      "loss": 0.7006,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3039335608482361,
      "learning_rate": 0.000320079822616408,
      "loss": 0.7179,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.37524399161338806,
      "learning_rate": 0.000319019955654102,
      "loss": 0.6545,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.4635438024997711,
      "learning_rate": 0.000317960088691796,
      "loss": 0.6507,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3045228123664856,
      "learning_rate": 0.00031690022172949,
      "loss": 0.626,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.3595406413078308,
      "learning_rate": 0.00031584035476718407,
      "loss": 0.6734,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3613088130950928,
      "learning_rate": 0.00031478048780487805,
      "loss": 0.6549,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3239917457103729,
      "learning_rate": 0.0003137206208425721,
      "loss": 0.6908,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.29154351353645325,
      "learning_rate": 0.0003126607538802661,
      "loss": 0.6391,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.3466133177280426,
      "learning_rate": 0.00031160088691796007,
      "loss": 0.6487,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3646586537361145,
      "learning_rate": 0.0003105410199556541,
      "loss": 0.6962,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.33777064085006714,
      "learning_rate": 0.00030948115299334815,
      "loss": 0.6735,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3152996301651001,
      "learning_rate": 0.00030842128603104213,
      "loss": 0.654,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.36545827984809875,
      "learning_rate": 0.0003073614190687362,
      "loss": 0.6566,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3125882148742676,
      "learning_rate": 0.00030630155210643016,
      "loss": 0.624,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3677145540714264,
      "learning_rate": 0.00030524168514412415,
      "loss": 0.6399,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.37805038690567017,
      "learning_rate": 0.0003041818181818182,
      "loss": 0.6356,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.36514320969581604,
      "learning_rate": 0.00030312195121951223,
      "loss": 0.6121,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3287840187549591,
      "learning_rate": 0.0003020620842572062,
      "loss": 0.6713,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3480997085571289,
      "learning_rate": 0.00030100221729490026,
      "loss": 0.674,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.364396333694458,
      "learning_rate": 0.00029994235033259424,
      "loss": 0.6572,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4812280833721161,
      "learning_rate": 0.00029888248337028823,
      "loss": 0.6594,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3395230174064636,
      "learning_rate": 0.00029782261640798227,
      "loss": 0.6338,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.41288211941719055,
      "learning_rate": 0.0002967627494456763,
      "loss": 0.6237,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.47372809052467346,
      "learning_rate": 0.0002957028824833703,
      "loss": 0.6469,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.41541212797164917,
      "learning_rate": 0.00029464301552106434,
      "loss": 0.6521,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.43474531173706055,
      "learning_rate": 0.0002935831485587583,
      "loss": 0.6616,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.41923409700393677,
      "learning_rate": 0.0002925232815964523,
      "loss": 0.6552,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3597162663936615,
      "learning_rate": 0.00029146341463414635,
      "loss": 0.6857,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.35165292024612427,
      "learning_rate": 0.0002904035476718404,
      "loss": 0.6487,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.4463621973991394,
      "learning_rate": 0.0002893436807095344,
      "loss": 0.638,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.3660702109336853,
      "learning_rate": 0.0002882838137472284,
      "loss": 0.6647,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.3571101725101471,
      "learning_rate": 0.0002872239467849224,
      "loss": 0.6036,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.4000444710254669,
      "learning_rate": 0.0002861640798226164,
      "loss": 0.6574,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.3966808617115021,
      "learning_rate": 0.00028510421286031043,
      "loss": 0.6383,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.35577499866485596,
      "learning_rate": 0.0002840443458980045,
      "loss": 0.6826,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.3344907760620117,
      "learning_rate": 0.00028298447893569846,
      "loss": 0.7203,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.3684915602207184,
      "learning_rate": 0.0002819246119733925,
      "loss": 0.6001,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.35198649764060974,
      "learning_rate": 0.00028086474501108643,
      "loss": 0.6132,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.3658265471458435,
      "learning_rate": 0.0002798048780487805,
      "loss": 0.649,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.3490952253341675,
      "learning_rate": 0.0002787450110864745,
      "loss": 0.6074,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.3784042000770569,
      "learning_rate": 0.0002776851441241685,
      "loss": 0.7177,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.3963486850261688,
      "learning_rate": 0.00027662527716186254,
      "loss": 0.6297,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.37558165192604065,
      "learning_rate": 0.0002755654101995566,
      "loss": 0.6504,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4022054672241211,
      "learning_rate": 0.0002745055432372505,
      "loss": 0.6671,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.3610709011554718,
      "learning_rate": 0.00027344567627494455,
      "loss": 0.6391,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.3770296573638916,
      "learning_rate": 0.0002723858093126386,
      "loss": 0.7025,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.36008888483047485,
      "learning_rate": 0.0002713259423503326,
      "loss": 0.7433,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.32775282859802246,
      "learning_rate": 0.0002702660753880266,
      "loss": 0.6594,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.3801479935646057,
      "learning_rate": 0.00026920620842572066,
      "loss": 0.7221,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.38986077904701233,
      "learning_rate": 0.00026814634146341465,
      "loss": 0.7284,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.37275534868240356,
      "learning_rate": 0.00026708647450110864,
      "loss": 0.7326,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.44164395332336426,
      "learning_rate": 0.0002660266075388027,
      "loss": 0.668,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4948090612888336,
      "learning_rate": 0.00026496674057649666,
      "loss": 0.6547,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.36464622616767883,
      "learning_rate": 0.0002639068736141907,
      "loss": 0.7022,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.3787488639354706,
      "learning_rate": 0.00026284700665188474,
      "loss": 0.671,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.40161359310150146,
      "learning_rate": 0.00026178713968957873,
      "loss": 0.6901,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.37211689352989197,
      "learning_rate": 0.0002607272727272727,
      "loss": 0.6828,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.35739865899086,
      "learning_rate": 0.00025966740576496676,
      "loss": 0.648,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.3805038630962372,
      "learning_rate": 0.00025860753880266074,
      "loss": 0.6389,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.44372430443763733,
      "learning_rate": 0.0002575476718403548,
      "loss": 0.6569,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.37554511427879333,
      "learning_rate": 0.0002564878048780488,
      "loss": 0.6734,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.38463807106018066,
      "learning_rate": 0.0002554279379157428,
      "loss": 0.6162,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.34643927216529846,
      "learning_rate": 0.0002543680709534368,
      "loss": 0.6412,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.3526350259780884,
      "learning_rate": 0.00025330820399113084,
      "loss": 0.6927,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.37397295236587524,
      "learning_rate": 0.0002522483370288248,
      "loss": 0.6804,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.362845242023468,
      "learning_rate": 0.00025118847006651887,
      "loss": 0.7316,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.35700854659080505,
      "learning_rate": 0.0002501286031042129,
      "loss": 0.659,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.3640636205673218,
      "learning_rate": 0.0002490687361419069,
      "loss": 0.6662,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.37967148423194885,
      "learning_rate": 0.0002480088691796009,
      "loss": 0.6993,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.38931983709335327,
      "learning_rate": 0.0002469490022172949,
      "loss": 0.6974,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.40344876050949097,
      "learning_rate": 0.0002458891352549889,
      "loss": 0.6886,
      "step": 225
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.027861707898368e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}