{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.665934065934066,
  "eval_steps": 500,
  "global_step": 405,
  "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
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.35167747735977173,
      "learning_rate": 0.00024482926829268295,
      "loss": 0.5827,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.37536776065826416,
      "learning_rate": 0.00024376940133037696,
      "loss": 0.5965,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.3983894884586334,
      "learning_rate": 0.00024270953436807097,
      "loss": 0.6679,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.37814024090766907,
      "learning_rate": 0.00024164966740576496,
      "loss": 0.7044,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.3688487708568573,
      "learning_rate": 0.00024058980044345897,
      "loss": 0.6515,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.3644563555717468,
      "learning_rate": 0.000239529933481153,
      "loss": 0.6822,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.36729520559310913,
      "learning_rate": 0.00023847006651884703,
      "loss": 0.5966,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.3619236350059509,
      "learning_rate": 0.00023741019955654104,
      "loss": 0.7006,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.4138461947441101,
      "learning_rate": 0.00023635033259423503,
      "loss": 0.6851,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.36005640029907227,
      "learning_rate": 0.00023529046563192907,
      "loss": 0.7015,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.36355483531951904,
      "learning_rate": 0.00023423059866962308,
      "loss": 0.6797,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.34447717666625977,
      "learning_rate": 0.00023317073170731707,
      "loss": 0.6873,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.3675404191017151,
      "learning_rate": 0.0002321108647450111,
      "loss": 0.6605,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.3445720970630646,
      "learning_rate": 0.00023105099778270512,
      "loss": 0.6958,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.3916369676589966,
      "learning_rate": 0.0002299911308203991,
      "loss": 0.6927,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.42796406149864197,
      "learning_rate": 0.00022893126385809315,
      "loss": 0.614,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.38712581992149353,
      "learning_rate": 0.00022787139689578716,
      "loss": 0.6569,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4039648473262787,
      "learning_rate": 0.00022681152993348115,
      "loss": 0.6383,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.3667120933532715,
      "learning_rate": 0.00022575166297117516,
      "loss": 0.6243,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.42547807097435,
      "learning_rate": 0.0002246917960088692,
      "loss": 0.6042,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.36566227674484253,
      "learning_rate": 0.0002236319290465632,
      "loss": 0.7497,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.32676053047180176,
      "learning_rate": 0.0002225720620842572,
      "loss": 0.6627,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.36180517077445984,
      "learning_rate": 0.00022151219512195125,
      "loss": 0.6555,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.3728333115577698,
      "learning_rate": 0.00022045232815964523,
      "loss": 0.6367,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.3665814697742462,
      "learning_rate": 0.00021939246119733925,
      "loss": 0.6436,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.3807748556137085,
      "learning_rate": 0.0002183325942350333,
      "loss": 0.6126,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.34011518955230713,
      "learning_rate": 0.00021727272727272727,
      "loss": 0.5731,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.3884364068508148,
      "learning_rate": 0.0002162128603104213,
      "loss": 0.6086,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.3920266330242157,
      "learning_rate": 0.00021515299334811533,
      "loss": 0.6263,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.41247713565826416,
      "learning_rate": 0.00021409312638580931,
      "loss": 0.7076,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.3659220337867737,
      "learning_rate": 0.00021303325942350333,
      "loss": 0.6928,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.42150160670280457,
      "learning_rate": 0.00021197339246119737,
      "loss": 0.685,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.41313761472702026,
      "learning_rate": 0.00021091352549889135,
      "loss": 0.7083,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.3637872338294983,
      "learning_rate": 0.00020985365853658537,
      "loss": 0.6875,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.3552550673484802,
      "learning_rate": 0.0002087937915742794,
      "loss": 0.5811,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.33103230595588684,
      "learning_rate": 0.0002077339246119734,
      "loss": 0.6322,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.3987133800983429,
      "learning_rate": 0.0002066740576496674,
      "loss": 0.6923,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.37328866124153137,
      "learning_rate": 0.00020561419068736142,
      "loss": 0.5956,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.35645592212677,
      "learning_rate": 0.00020455432372505544,
      "loss": 0.623,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.45821356773376465,
      "learning_rate": 0.00020349445676274945,
      "loss": 0.6963,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.4325563311576843,
      "learning_rate": 0.00020243458980044346,
      "loss": 0.6437,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.3883129358291626,
      "learning_rate": 0.00020137472283813748,
      "loss": 0.6564,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.37192174792289734,
      "learning_rate": 0.0002003148558758315,
      "loss": 0.7297,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.41306498646736145,
      "learning_rate": 0.0001992549889135255,
      "loss": 0.6091,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.3892672657966614,
      "learning_rate": 0.00019819512195121952,
      "loss": 0.7049,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.3587683439254761,
      "learning_rate": 0.00019713525498891353,
      "loss": 0.6431,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.3469403088092804,
      "learning_rate": 0.00019607538802660754,
      "loss": 0.7194,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.4051947295665741,
      "learning_rate": 0.00019501552106430156,
      "loss": 0.7144,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.37906739115715027,
      "learning_rate": 0.00019395565410199557,
      "loss": 0.6582,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.40413400530815125,
      "learning_rate": 0.00019289578713968959,
      "loss": 0.6423,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.3686625063419342,
      "learning_rate": 0.0001918359201773836,
      "loss": 0.6472,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.3732779324054718,
      "learning_rate": 0.0001907760532150776,
      "loss": 0.6646,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.34917259216308594,
      "learning_rate": 0.00018971618625277163,
      "loss": 0.7183,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.3639671206474304,
      "learning_rate": 0.00018865631929046564,
      "loss": 0.6548,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.34556910395622253,
      "learning_rate": 0.00018759645232815965,
      "loss": 0.6565,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.35177111625671387,
      "learning_rate": 0.00018653658536585367,
      "loss": 0.6833,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4248157739639282,
      "learning_rate": 0.00018547671840354768,
      "loss": 0.6806,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.3665319085121155,
      "learning_rate": 0.0001844168514412417,
      "loss": 0.6643,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.3526496887207031,
      "learning_rate": 0.0001833569844789357,
      "loss": 0.6291,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.3764701783657074,
      "learning_rate": 0.0001822971175166297,
      "loss": 0.6496,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.3442821204662323,
      "learning_rate": 0.00018123725055432373,
      "loss": 0.5689,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.37878355383872986,
      "learning_rate": 0.00018017738359201775,
      "loss": 0.727,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.3501584827899933,
      "learning_rate": 0.00017911751662971173,
      "loss": 0.6277,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.3762091100215912,
      "learning_rate": 0.00017805764966740578,
      "loss": 0.6569,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.37765055894851685,
      "learning_rate": 0.0001769977827050998,
      "loss": 0.694,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.39236217737197876,
      "learning_rate": 0.00017593791574279378,
      "loss": 0.6392,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.3917315900325775,
      "learning_rate": 0.00017487804878048782,
      "loss": 0.6466,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.3855416774749756,
      "learning_rate": 0.00017381818181818183,
      "loss": 0.6126,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.40920308232307434,
      "learning_rate": 0.00017275831485587582,
      "loss": 0.6965,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.4434974789619446,
      "learning_rate": 0.00017169844789356986,
      "loss": 0.6146,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.34732627868652344,
      "learning_rate": 0.00017063858093126387,
      "loss": 0.6199,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.3674536347389221,
      "learning_rate": 0.00016957871396895788,
      "loss": 0.6012,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.36995163559913635,
      "learning_rate": 0.0001685188470066519,
      "loss": 0.6334,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.3592709004878998,
      "learning_rate": 0.0001674589800443459,
      "loss": 0.6883,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.37183427810668945,
      "learning_rate": 0.00016639911308203992,
      "loss": 0.6888,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.40252208709716797,
      "learning_rate": 0.00016533924611973394,
      "loss": 0.5818,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.3765590488910675,
      "learning_rate": 0.00016427937915742795,
      "loss": 0.6904,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.4293619990348816,
      "learning_rate": 0.00016321951219512197,
      "loss": 0.6777,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5116645097732544,
      "learning_rate": 0.00016215964523281595,
      "loss": 0.6377,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.37566491961479187,
      "learning_rate": 0.00016109977827051,
      "loss": 0.5819,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.3537121117115021,
      "learning_rate": 0.000160039911308204,
      "loss": 0.5909,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.39034998416900635,
      "learning_rate": 0.000158980044345898,
      "loss": 0.5391,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.37659239768981934,
      "learning_rate": 0.00015792017738359203,
      "loss": 0.5118,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.38732704520225525,
      "learning_rate": 0.00015686031042128605,
      "loss": 0.5745,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.4092656970024109,
      "learning_rate": 0.00015580044345898003,
      "loss": 0.5925,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.40416091680526733,
      "learning_rate": 0.00015474057649667407,
      "loss": 0.5532,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.4108326733112335,
      "learning_rate": 0.0001536807095343681,
      "loss": 0.5338,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.4379502236843109,
      "learning_rate": 0.00015262084257206207,
      "loss": 0.5819,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.4083239734172821,
      "learning_rate": 0.00015156097560975611,
      "loss": 0.5132,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.4189518988132477,
      "learning_rate": 0.00015050110864745013,
      "loss": 0.5367,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.4176078140735626,
      "learning_rate": 0.00014944124168514411,
      "loss": 0.5611,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.40296265482902527,
      "learning_rate": 0.00014838137472283816,
      "loss": 0.5503,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.44326770305633545,
      "learning_rate": 0.00014732150776053217,
      "loss": 0.537,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.5095427632331848,
      "learning_rate": 0.00014626164079822616,
      "loss": 0.4934,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.42088446021080017,
      "learning_rate": 0.0001452017738359202,
      "loss": 0.5053,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.45307278633117676,
      "learning_rate": 0.0001441419068736142,
      "loss": 0.5966,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.514121949672699,
      "learning_rate": 0.0001430820399113082,
      "loss": 0.5255,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.48232635855674744,
      "learning_rate": 0.00014202217294900224,
      "loss": 0.5705,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.4331412613391876,
      "learning_rate": 0.00014096230598669625,
      "loss": 0.5803,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.42453521490097046,
      "learning_rate": 0.00013990243902439024,
      "loss": 0.5267,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.47767454385757446,
      "learning_rate": 0.00013884257206208425,
      "loss": 0.6002,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.44827523827552795,
      "learning_rate": 0.0001377827050997783,
      "loss": 0.5816,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.429264634847641,
      "learning_rate": 0.00013672283813747228,
      "loss": 0.6079,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.48142921924591064,
      "learning_rate": 0.0001356629711751663,
      "loss": 0.5402,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.47979727387428284,
      "learning_rate": 0.00013460310421286033,
      "loss": 0.5563,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.5298358798027039,
      "learning_rate": 0.00013354323725055432,
      "loss": 0.5641,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.5011658072471619,
      "learning_rate": 0.00013248337028824833,
      "loss": 0.5331,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.533147931098938,
      "learning_rate": 0.00013142350332594237,
      "loss": 0.6307,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.5181835889816284,
      "learning_rate": 0.00013036363636363636,
      "loss": 0.4885,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.4809086322784424,
      "learning_rate": 0.00012930376940133037,
      "loss": 0.5033,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.5145286321640015,
      "learning_rate": 0.0001282439024390244,
      "loss": 0.5702,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.4592391550540924,
      "learning_rate": 0.0001271840354767184,
      "loss": 0.5509,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.47879448533058167,
      "learning_rate": 0.0001261241685144124,
      "loss": 0.6233,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.48939841985702515,
      "learning_rate": 0.00012506430155210645,
      "loss": 0.5934,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.517932116985321,
      "learning_rate": 0.00012400443458980044,
      "loss": 0.5251,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.5007826089859009,
      "learning_rate": 0.00012294456762749445,
      "loss": 0.6142,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.4412643313407898,
      "learning_rate": 0.00012188470066518848,
      "loss": 0.5415,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.45227885246276855,
      "learning_rate": 0.00012082483370288248,
      "loss": 0.5462,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.45222949981689453,
      "learning_rate": 0.0001197649667405765,
      "loss": 0.5426,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.5486775636672974,
      "learning_rate": 0.00011870509977827052,
      "loss": 0.5819,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.47183334827423096,
      "learning_rate": 0.00011764523281596453,
      "loss": 0.541,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.4757823348045349,
      "learning_rate": 0.00011658536585365853,
      "loss": 0.552,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.5165002346038818,
      "learning_rate": 0.00011552549889135256,
      "loss": 0.5353,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.4850943684577942,
      "learning_rate": 0.00011446563192904658,
      "loss": 0.5771,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.4945162534713745,
      "learning_rate": 0.00011340576496674058,
      "loss": 0.5896,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.4818560779094696,
      "learning_rate": 0.0001123458980044346,
      "loss": 0.5205,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.4599496126174927,
      "learning_rate": 0.0001112860310421286,
      "loss": 0.5892,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.5347880721092224,
      "learning_rate": 0.00011022616407982262,
      "loss": 0.5411,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.44645607471466064,
      "learning_rate": 0.00010916629711751664,
      "loss": 0.5331,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.5465013980865479,
      "learning_rate": 0.00010810643015521064,
      "loss": 0.5334,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.4818529784679413,
      "learning_rate": 0.00010704656319290466,
      "loss": 0.57,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.5043441653251648,
      "learning_rate": 0.00010598669623059868,
      "loss": 0.5573,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.4900377094745636,
      "learning_rate": 0.00010492682926829268,
      "loss": 0.5604,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.5478551387786865,
      "learning_rate": 0.0001038669623059867,
      "loss": 0.6402,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.5178705453872681,
      "learning_rate": 0.00010280709534368071,
      "loss": 0.6082,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.5018958449363708,
      "learning_rate": 0.00010174722838137472,
      "loss": 0.5591,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.5049342513084412,
      "learning_rate": 0.00010068736141906874,
      "loss": 0.5164,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.4705263078212738,
      "learning_rate": 9.962749445676275e-05,
      "loss": 0.5648,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.5149775147438049,
      "learning_rate": 9.856762749445677e-05,
      "loss": 0.5087,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.5052133202552795,
      "learning_rate": 9.750776053215078e-05,
      "loss": 0.5328,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.5089244246482849,
      "learning_rate": 9.644789356984479e-05,
      "loss": 0.5118,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.5100271105766296,
      "learning_rate": 9.53880266075388e-05,
      "loss": 0.511,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.4884236454963684,
      "learning_rate": 9.432815964523282e-05,
      "loss": 0.5526,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.4753691852092743,
      "learning_rate": 9.326829268292683e-05,
      "loss": 0.571,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.47016677260398865,
      "learning_rate": 9.220842572062085e-05,
      "loss": 0.5186,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.499392569065094,
      "learning_rate": 9.114855875831485e-05,
      "loss": 0.5496,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.5158039927482605,
      "learning_rate": 9.008869179600887e-05,
      "loss": 0.5244,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.48002421855926514,
      "learning_rate": 8.902882483370289e-05,
      "loss": 0.5425,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.5249605774879456,
      "learning_rate": 8.796895787139689e-05,
      "loss": 0.4915,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.48905298113822937,
      "learning_rate": 8.690909090909091e-05,
      "loss": 0.5422,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.43776431679725647,
      "learning_rate": 8.584922394678493e-05,
      "loss": 0.5054,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.517510175704956,
      "learning_rate": 8.478935698447894e-05,
      "loss": 0.5633,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.521196722984314,
      "learning_rate": 8.372949002217296e-05,
      "loss": 0.5826,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.48704734444618225,
      "learning_rate": 8.266962305986697e-05,
      "loss": 0.4671,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.5737009644508362,
      "learning_rate": 8.160975609756098e-05,
      "loss": 0.5626,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.5464959740638733,
      "learning_rate": 8.0549889135255e-05,
      "loss": 0.4647,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.5190503001213074,
      "learning_rate": 7.9490022172949e-05,
      "loss": 0.5669,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.5061521530151367,
      "learning_rate": 7.843015521064302e-05,
      "loss": 0.5379,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.6107311844825745,
      "learning_rate": 7.737028824833704e-05,
      "loss": 0.5359,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.4706372320652008,
      "learning_rate": 7.631042128603104e-05,
      "loss": 0.5368,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.46517807245254517,
      "learning_rate": 7.525055432372506e-05,
      "loss": 0.5837,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.5661277174949646,
      "learning_rate": 7.419068736141908e-05,
      "loss": 0.5656,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.5041473507881165,
      "learning_rate": 7.313082039911308e-05,
      "loss": 0.472,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.4884931147098541,
      "learning_rate": 7.20709534368071e-05,
      "loss": 0.5468,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.5164287686347961,
      "learning_rate": 7.101108647450112e-05,
      "loss": 0.4995,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.5293363928794861,
      "learning_rate": 6.995121951219512e-05,
      "loss": 0.5679,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.5201839804649353,
      "learning_rate": 6.889135254988915e-05,
      "loss": 0.5538,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.5030112862586975,
      "learning_rate": 6.783148558758315e-05,
      "loss": 0.6007,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.4886395335197449,
      "learning_rate": 6.677161862527716e-05,
      "loss": 0.5224,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.5146926641464233,
      "learning_rate": 6.571175166297119e-05,
      "loss": 0.5367,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.5484263896942139,
      "learning_rate": 6.465188470066519e-05,
      "loss": 0.5644,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.5186261534690857,
      "learning_rate": 6.35920177383592e-05,
      "loss": 0.5221,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.4857414662837982,
      "learning_rate": 6.253215077605323e-05,
      "loss": 0.5977,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.5213504433631897,
      "learning_rate": 6.147228381374723e-05,
      "loss": 0.5534,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.46881458163261414,
      "learning_rate": 6.041241685144124e-05,
      "loss": 0.5856,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.5869070291519165,
      "learning_rate": 5.935254988913526e-05,
      "loss": 0.477,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.5170873999595642,
      "learning_rate": 5.829268292682927e-05,
      "loss": 0.5893,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.5336002707481384,
      "learning_rate": 5.723281596452329e-05,
      "loss": 0.506,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.4747842848300934,
      "learning_rate": 5.61729490022173e-05,
      "loss": 0.5146,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.6062822341918945,
      "learning_rate": 5.511308203991131e-05,
      "loss": 0.6198,
      "step": 405
    }
  ],
  "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": 1.848310585072681e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}