{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.2703296703296703,
  "eval_steps": 500,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.9970224499702454,
      "learning_rate": 0.0,
      "loss": 1.0991,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.144827127456665,
      "learning_rate": 9.56e-05,
      "loss": 1.1545,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1169440746307373,
      "learning_rate": 0.0001912,
      "loss": 1.123,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0855385065078735,
      "learning_rate": 0.0002868,
      "loss": 0.9259,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.8469429016113281,
      "learning_rate": 0.0003824,
      "loss": 0.8556,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.7604000568389893,
      "learning_rate": 0.000478,
      "loss": 0.9009,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5317047834396362,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9281,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.47205209732055664,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8713,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.2961072027683258,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8788,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.38304176926612854,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.816,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.5212758779525757,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8274,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.543552577495575,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8489,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.4572776257991791,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.8166,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.44755756855010986,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.7803,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5597015023231506,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.801,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.39118215441703796,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7196,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4890790581703186,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7744,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.5199437737464905,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7521,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4048418402671814,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.7232,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4759422242641449,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.7887,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.373710572719574,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7673,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3180016577243805,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.7553,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.43041887879371643,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7573,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.4632937014102936,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.7318,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3658117651939392,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.7129,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.39879968762397766,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7212,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4226565659046173,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7441,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3761254549026489,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7351,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3735473155975342,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.7274,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3605045676231384,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7511,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.49938589334487915,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.733,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3388383090496063,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7086,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.6535608768463135,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.7686,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.36676231026649475,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.6831,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3847268521785736,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7375,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.37475308775901794,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7084,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3576759696006775,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.7693,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.33207494020462036,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7844,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.4797557592391968,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.6863,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3291913866996765,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.6941,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3354625701904297,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7254,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3200039267539978,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.6928,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.377468079328537,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7907,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.35265693068504333,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6916,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.4030437171459198,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.721,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3848680853843689,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.7261,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3052960932254791,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.7063,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3832049071788788,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7652,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3644565939903259,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.8106,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3032757639884949,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7162,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3071494996547699,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.7907,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.32176244258880615,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.7865,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3945949375629425,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.8038,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2989363968372345,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.7172,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.317256361246109,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.7325,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.27640077471733093,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.765,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.3094281256198883,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7391,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.30334004759788513,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.7486,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3377019166946411,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.7444,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.34436339139938354,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.7041,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.27596402168273926,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.6926,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3022932708263397,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.7138,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2816564738750458,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7261,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3032025992870331,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.6791,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.26954764127731323,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.7032,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3011576235294342,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.7512,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.33316031098365784,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.7345,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3042667508125305,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.7834,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.28509846329689026,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7127,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3400508761405945,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.7382,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3198228180408478,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.7625,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.32544252276420593,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.7485,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.345786988735199,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.7448,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2966018319129944,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.6449,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.27237051725387573,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.6467,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.332011342048645,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.7323,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.32000380754470825,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.7653,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.34098610281944275,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.7202,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2874126732349396,
      "learning_rate": 0.000400629711751663,
      "loss": 0.7367,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.322229266166687,
      "learning_rate": 0.000399569844789357,
      "loss": 0.6588,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3342168927192688,
      "learning_rate": 0.000398509977827051,
      "loss": 0.7579,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3295648396015167,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.7388,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2803487479686737,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.7614,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.32823750376701355,
      "learning_rate": 0.000395330376940133,
      "loss": 0.7479,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.32557007670402527,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.7527,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.33845341205596924,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.7203,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.39683398604393005,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.7576,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3514403998851776,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.7556,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3493777811527252,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.6633,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.28230881690979004,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.7153,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.31960365176200867,
      "learning_rate": 0.00038791130820399114,
      "loss": 0.7101,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3226240575313568,
      "learning_rate": 0.0003868514412416852,
      "loss": 0.6795,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.37568366527557373,
      "learning_rate": 0.00038579157427937917,
      "loss": 0.6586,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3764398992061615,
      "learning_rate": 0.0003847317073170732,
      "loss": 0.8014,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.32533973455429077,
      "learning_rate": 0.0003836718403547672,
      "loss": 0.7237,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.28496646881103516,
      "learning_rate": 0.0003826119733924612,
      "loss": 0.7134,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.29689112305641174,
      "learning_rate": 0.0003815521064301552,
      "loss": 0.7035,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.31590795516967773,
      "learning_rate": 0.00038049223946784927,
      "loss": 0.7087,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2947428822517395,
      "learning_rate": 0.00037943237250554325,
      "loss": 0.6697,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.27264344692230225,
      "learning_rate": 0.0003783725055432373,
      "loss": 0.6232,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.38913288712501526,
      "learning_rate": 0.0003773126385809313,
      "loss": 0.6705,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3600233793258667,
      "learning_rate": 0.00037625277161862527,
      "loss": 0.69,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.36744818091392517,
      "learning_rate": 0.0003751929046563193,
      "loss": 0.7739,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.33523765206336975,
      "learning_rate": 0.00037413303769401335,
      "loss": 0.7414,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.33133506774902344,
      "learning_rate": 0.00037307317073170733,
      "loss": 0.7447,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.38341405987739563,
      "learning_rate": 0.0003720133037694014,
      "loss": 0.7693,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3323330283164978,
      "learning_rate": 0.00037095343680709536,
      "loss": 0.7502,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3311186730861664,
      "learning_rate": 0.00036989356984478935,
      "loss": 0.6478,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.32154369354248047,
      "learning_rate": 0.0003688337028824834,
      "loss": 0.689,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.33734986186027527,
      "learning_rate": 0.0003677738359201774,
      "loss": 0.7497,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.29922378063201904,
      "learning_rate": 0.0003667139689578714,
      "loss": 0.6458,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.35878702998161316,
      "learning_rate": 0.00036565410199556546,
      "loss": 0.6826,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.4202096462249756,
      "learning_rate": 0.0003645942350332594,
      "loss": 0.7508,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.34974202513694763,
      "learning_rate": 0.00036353436807095343,
      "loss": 0.6995,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3248356878757477,
      "learning_rate": 0.00036247450110864747,
      "loss": 0.7133,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3106825649738312,
      "learning_rate": 0.00036141463414634146,
      "loss": 0.7873,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3386942148208618,
      "learning_rate": 0.0003603547671840355,
      "loss": 0.674,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.31210097670555115,
      "learning_rate": 0.00035929490022172954,
      "loss": 0.761,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3049944043159485,
      "learning_rate": 0.00035823503325942347,
      "loss": 0.6974,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.2945634722709656,
      "learning_rate": 0.0003571751662971175,
      "loss": 0.7786,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.334928423166275,
      "learning_rate": 0.00035611529933481155,
      "loss": 0.7759,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.33794817328453064,
      "learning_rate": 0.00035505543237250554,
      "loss": 0.7268,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.34872716665267944,
      "learning_rate": 0.0003539955654101996,
      "loss": 0.6964,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.27211689949035645,
      "learning_rate": 0.0003529356984478936,
      "loss": 0.7026,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.303218811750412,
      "learning_rate": 0.00035187583148558755,
      "loss": 0.7113,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.28027018904685974,
      "learning_rate": 0.0003508159645232816,
      "loss": 0.7727,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.2782959043979645,
      "learning_rate": 0.00034975609756097563,
      "loss": 0.7235,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.27962350845336914,
      "learning_rate": 0.0003486962305986696,
      "loss": 0.7115,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.28686633706092834,
      "learning_rate": 0.00034763636363636366,
      "loss": 0.7398,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3914222717285156,
      "learning_rate": 0.0003465764966740577,
      "loss": 0.7521,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.30597811937332153,
      "learning_rate": 0.00034551662971175163,
      "loss": 0.718,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.2956196069717407,
      "learning_rate": 0.00034445676274944567,
      "loss": 0.6925,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3160248398780823,
      "learning_rate": 0.0003433968957871397,
      "loss": 0.7046,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.2987951338291168,
      "learning_rate": 0.0003423370288248337,
      "loss": 0.6252,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3024667501449585,
      "learning_rate": 0.00034127716186252774,
      "loss": 0.778,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.2868024408817291,
      "learning_rate": 0.0003402172949002218,
      "loss": 0.6807,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.29994046688079834,
      "learning_rate": 0.00033915742793791577,
      "loss": 0.711,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3246282935142517,
      "learning_rate": 0.00033809756097560975,
      "loss": 0.7606,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.3361048698425293,
      "learning_rate": 0.0003370376940133038,
      "loss": 0.6995,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.3376304507255554,
      "learning_rate": 0.0003359778270509978,
      "loss": 0.71,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.29205799102783203,
      "learning_rate": 0.0003349179600886918,
      "loss": 0.6685,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.30635398626327515,
      "learning_rate": 0.00033385809312638586,
      "loss": 0.7522,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3423284590244293,
      "learning_rate": 0.00033279822616407985,
      "loss": 0.6769,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.30614131689071655,
      "learning_rate": 0.00033173835920177384,
      "loss": 0.6788,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3104928433895111,
      "learning_rate": 0.0003306784922394679,
      "loss": 0.6591,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.33305084705352783,
      "learning_rate": 0.00032961862527716186,
      "loss": 0.6966,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3775268495082855,
      "learning_rate": 0.0003285587583148559,
      "loss": 0.7447,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3366539776325226,
      "learning_rate": 0.00032749889135254994,
      "loss": 0.7501,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.38443613052368164,
      "learning_rate": 0.00032643902439024393,
      "loss": 0.645,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.3002435863018036,
      "learning_rate": 0.0003253791574279379,
      "loss": 0.7398,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.34713083505630493,
      "learning_rate": 0.0003243192904656319,
      "loss": 0.7262,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.35023507475852966,
      "learning_rate": 0.00032325942350332594,
      "loss": 0.6768,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.38305485248565674,
      "learning_rate": 0.00032219955654102,
      "loss": 0.6883,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3572325110435486,
      "learning_rate": 0.00032113968957871397,
      "loss": 0.6868,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.31668391823768616,
      "learning_rate": 0.000320079822616408,
      "loss": 0.6352,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3431554436683655,
      "learning_rate": 0.000319019955654102,
      "loss": 0.6212,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3789862394332886,
      "learning_rate": 0.000317960088691796,
      "loss": 0.6692,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.304165780544281,
      "learning_rate": 0.00031690022172949,
      "loss": 0.6753,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.3196735382080078,
      "learning_rate": 0.00031584035476718407,
      "loss": 0.6402,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3539210259914398,
      "learning_rate": 0.00031478048780487805,
      "loss": 0.637,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.41358649730682373,
      "learning_rate": 0.0003137206208425721,
      "loss": 0.7002,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3271334767341614,
      "learning_rate": 0.0003126607538802661,
      "loss": 0.6182,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.4126374423503876,
      "learning_rate": 0.00031160088691796007,
      "loss": 0.6383,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.3880680799484253,
      "learning_rate": 0.0003105410199556541,
      "loss": 0.6802,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.32755038142204285,
      "learning_rate": 0.00030948115299334815,
      "loss": 0.6573,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3592837154865265,
      "learning_rate": 0.00030842128603104213,
      "loss": 0.6518,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.42520859837532043,
      "learning_rate": 0.0003073614190687362,
      "loss": 0.5939,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3364773988723755,
      "learning_rate": 0.00030630155210643016,
      "loss": 0.6153,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3265248239040375,
      "learning_rate": 0.00030524168514412415,
      "loss": 0.6962,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.34393543004989624,
      "learning_rate": 0.0003041818181818182,
      "loss": 0.6184,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3520282506942749,
      "learning_rate": 0.00030312195121951223,
      "loss": 0.6726,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.4375007450580597,
      "learning_rate": 0.0003020620842572062,
      "loss": 0.6876,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.35851043462753296,
      "learning_rate": 0.00030100221729490026,
      "loss": 0.6282,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3228410482406616,
      "learning_rate": 0.00029994235033259424,
      "loss": 0.7026,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.36233118176460266,
      "learning_rate": 0.00029888248337028823,
      "loss": 0.6905,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3298339247703552,
      "learning_rate": 0.00029782261640798227,
      "loss": 0.6957,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.3960157334804535,
      "learning_rate": 0.0002967627494456763,
      "loss": 0.643,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.4046969711780548,
      "learning_rate": 0.0002957028824833703,
      "loss": 0.6738,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3787284791469574,
      "learning_rate": 0.00029464301552106434,
      "loss": 0.6648,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.4840444028377533,
      "learning_rate": 0.0002935831485587583,
      "loss": 0.6528,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.35219264030456543,
      "learning_rate": 0.0002925232815964523,
      "loss": 0.7295,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.33763912320137024,
      "learning_rate": 0.00029146341463414635,
      "loss": 0.5904,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.4614327847957611,
      "learning_rate": 0.0002904035476718404,
      "loss": 0.6324,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.410922110080719,
      "learning_rate": 0.0002893436807095344,
      "loss": 0.6963,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.33478567004203796,
      "learning_rate": 0.0002882838137472284,
      "loss": 0.6746,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.38460463285446167,
      "learning_rate": 0.0002872239467849224,
      "loss": 0.7287,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.41470155119895935,
      "learning_rate": 0.0002861640798226164,
      "loss": 0.7065,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.40113189816474915,
      "learning_rate": 0.00028510421286031043,
      "loss": 0.635,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.35355815291404724,
      "learning_rate": 0.0002840443458980045,
      "loss": 0.7256,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.3277815580368042,
      "learning_rate": 0.00028298447893569846,
      "loss": 0.6529,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.37198781967163086,
      "learning_rate": 0.0002819246119733925,
      "loss": 0.6507,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.33678582310676575,
      "learning_rate": 0.00028086474501108643,
      "loss": 0.6389,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.34777119755744934,
      "learning_rate": 0.0002798048780487805,
      "loss": 0.6804,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.3285517692565918,
      "learning_rate": 0.0002787450110864745,
      "loss": 0.648,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.33483248949050903,
      "learning_rate": 0.0002776851441241685,
      "loss": 0.6687,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.37951233983039856,
      "learning_rate": 0.00027662527716186254,
      "loss": 0.6466,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.35914433002471924,
      "learning_rate": 0.0002755654101995566,
      "loss": 0.6814,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.3615425229072571,
      "learning_rate": 0.0002745055432372505,
      "loss": 0.7048,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.37614500522613525,
      "learning_rate": 0.00027344567627494455,
      "loss": 0.631,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.3917557895183563,
      "learning_rate": 0.0002723858093126386,
      "loss": 0.6921,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.3767569661140442,
      "learning_rate": 0.0002713259423503326,
      "loss": 0.6566,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.3442741930484772,
      "learning_rate": 0.0002702660753880266,
      "loss": 0.6354,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.31562164425849915,
      "learning_rate": 0.00026920620842572066,
      "loss": 0.6291,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.3532516658306122,
      "learning_rate": 0.00026814634146341465,
      "loss": 0.6796,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.3777218759059906,
      "learning_rate": 0.00026708647450110864,
      "loss": 0.6734,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.35049760341644287,
      "learning_rate": 0.0002660266075388027,
      "loss": 0.6792,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.37494373321533203,
      "learning_rate": 0.00026496674057649666,
      "loss": 0.757,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.37660735845565796,
      "learning_rate": 0.0002639068736141907,
      "loss": 0.7308,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4234360158443451,
      "learning_rate": 0.00026284700665188474,
      "loss": 0.6798,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.3924785852432251,
      "learning_rate": 0.00026178713968957873,
      "loss": 0.6312,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.35264280438423157,
      "learning_rate": 0.0002607272727272727,
      "loss": 0.6692,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.3955014646053314,
      "learning_rate": 0.00025966740576496676,
      "loss": 0.6219,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.36072415113449097,
      "learning_rate": 0.00025860753880266074,
      "loss": 0.6306,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.3578793704509735,
      "learning_rate": 0.0002575476718403548,
      "loss": 0.6307,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.38820844888687134,
      "learning_rate": 0.0002564878048780488,
      "loss": 0.6426,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.3640262186527252,
      "learning_rate": 0.0002554279379157428,
      "loss": 0.6798,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.355820894241333,
      "learning_rate": 0.0002543680709534368,
      "loss": 0.6732,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.358778715133667,
      "learning_rate": 0.00025330820399113084,
      "loss": 0.6162,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.40246081352233887,
      "learning_rate": 0.0002522483370288248,
      "loss": 0.6655,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.37145930528640747,
      "learning_rate": 0.00025118847006651887,
      "loss": 0.627,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.3811812400817871,
      "learning_rate": 0.0002501286031042129,
      "loss": 0.6546,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.3838576376438141,
      "learning_rate": 0.0002490687361419069,
      "loss": 0.6268,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.3758513033390045,
      "learning_rate": 0.0002480088691796009,
      "loss": 0.6633,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.3423100411891937,
      "learning_rate": 0.0002469490022172949,
      "loss": 0.5918,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.38100165128707886,
      "learning_rate": 0.0002458891352549889,
      "loss": 0.6865,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.4081498384475708,
      "learning_rate": 0.00024482926829268295,
      "loss": 0.7151,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.3668079376220703,
      "learning_rate": 0.00024376940133037696,
      "loss": 0.5827,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.40372422337532043,
      "learning_rate": 0.00024270953436807097,
      "loss": 0.6658,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.3988126218318939,
      "learning_rate": 0.00024164966740576496,
      "loss": 0.5753,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.398112028837204,
      "learning_rate": 0.00024058980044345897,
      "loss": 0.687,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.4017437994480133,
      "learning_rate": 0.000239529933481153,
      "loss": 0.6603,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.40356186032295227,
      "learning_rate": 0.00023847006651884703,
      "loss": 0.6526,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.40809166431427,
      "learning_rate": 0.00023741019955654104,
      "loss": 0.6537,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.3994799852371216,
      "learning_rate": 0.00023635033259423503,
      "loss": 0.6892,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.3911482095718384,
      "learning_rate": 0.00023529046563192907,
      "loss": 0.6855,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.40330222249031067,
      "learning_rate": 0.00023423059866962308,
      "loss": 0.5921,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.37935584783554077,
      "learning_rate": 0.00023317073170731707,
      "loss": 0.6465,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.3929573893547058,
      "learning_rate": 0.0002321108647450111,
      "loss": 0.6346,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.38034695386886597,
      "learning_rate": 0.00023105099778270512,
      "loss": 0.6796,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.32818010449409485,
      "learning_rate": 0.0002299911308203991,
      "loss": 0.6635,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.35218796133995056,
      "learning_rate": 0.00022893126385809315,
      "loss": 0.7231,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.36161521077156067,
      "learning_rate": 0.00022787139689578716,
      "loss": 0.6457,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.35236117243766785,
      "learning_rate": 0.00022681152993348115,
      "loss": 0.6446,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.41815316677093506,
      "learning_rate": 0.00022575166297117516,
      "loss": 0.6849,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.36881476640701294,
      "learning_rate": 0.0002246917960088692,
      "loss": 0.6419,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.36567461490631104,
      "learning_rate": 0.0002236319290465632,
      "loss": 0.6977,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.374749094247818,
      "learning_rate": 0.0002225720620842572,
      "loss": 0.6615,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.3468921482563019,
      "learning_rate": 0.00022151219512195125,
      "loss": 0.7002,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.41083279252052307,
      "learning_rate": 0.00022045232815964523,
      "loss": 0.5928,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.37868770956993103,
      "learning_rate": 0.00021939246119733925,
      "loss": 0.7236,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.3629273474216461,
      "learning_rate": 0.0002183325942350333,
      "loss": 0.633,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.35424259305000305,
      "learning_rate": 0.00021727272727272727,
      "loss": 0.6305,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.439231276512146,
      "learning_rate": 0.0002162128603104213,
      "loss": 0.7461,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.4257543385028839,
      "learning_rate": 0.00021515299334811533,
      "loss": 0.6634,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.3998747766017914,
      "learning_rate": 0.00021409312638580931,
      "loss": 0.6854,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.3800191879272461,
      "learning_rate": 0.00021303325942350333,
      "loss": 0.6449,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.4337719976902008,
      "learning_rate": 0.00021197339246119737,
      "loss": 0.671,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.44184720516204834,
      "learning_rate": 0.00021091352549889135,
      "loss": 0.527,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.33520013093948364,
      "learning_rate": 0.00020985365853658537,
      "loss": 0.7268,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.3855791985988617,
      "learning_rate": 0.0002087937915742794,
      "loss": 0.5909,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.3870508074760437,
      "learning_rate": 0.0002077339246119734,
      "loss": 0.6634,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.4269031882286072,
      "learning_rate": 0.0002066740576496674,
      "loss": 0.6776,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.37803956866264343,
      "learning_rate": 0.00020561419068736142,
      "loss": 0.6311,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.39058563113212585,
      "learning_rate": 0.00020455432372505544,
      "loss": 0.599,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.4414854943752289,
      "learning_rate": 0.00020349445676274945,
      "loss": 0.6691,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.4004284143447876,
      "learning_rate": 0.00020243458980044346,
      "loss": 0.6383,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.3992699086666107,
      "learning_rate": 0.00020137472283813748,
      "loss": 0.6672,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.358350545167923,
      "learning_rate": 0.0002003148558758315,
      "loss": 0.6446,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.4032428562641144,
      "learning_rate": 0.0001992549889135255,
      "loss": 0.6778,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.3804583251476288,
      "learning_rate": 0.00019819512195121952,
      "loss": 0.6544,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.3812550902366638,
      "learning_rate": 0.00019713525498891353,
      "loss": 0.6647,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.3965335786342621,
      "learning_rate": 0.00019607538802660754,
      "loss": 0.6015,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.3880223333835602,
      "learning_rate": 0.00019501552106430156,
      "loss": 0.661,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.3955674171447754,
      "learning_rate": 0.00019395565410199557,
      "loss": 0.5993,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.427304208278656,
      "learning_rate": 0.00019289578713968959,
      "loss": 0.6222,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.43342676758766174,
      "learning_rate": 0.0001918359201773836,
      "loss": 0.6385,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.38551008701324463,
      "learning_rate": 0.0001907760532150776,
      "loss": 0.6297,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.34939613938331604,
      "learning_rate": 0.00018971618625277163,
      "loss": 0.6703,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.3339291214942932,
      "learning_rate": 0.00018865631929046564,
      "loss": 0.6689,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.32809391617774963,
      "learning_rate": 0.00018759645232815965,
      "loss": 0.6801,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.3705151081085205,
      "learning_rate": 0.00018653658536585367,
      "loss": 0.6401,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.3831600546836853,
      "learning_rate": 0.00018547671840354768,
      "loss": 0.6629,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.3629395663738251,
      "learning_rate": 0.0001844168514412417,
      "loss": 0.7061,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.40745213627815247,
      "learning_rate": 0.0001833569844789357,
      "loss": 0.675,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.4040345251560211,
      "learning_rate": 0.0001822971175166297,
      "loss": 0.6418,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.38781166076660156,
      "learning_rate": 0.00018123725055432373,
      "loss": 0.6584,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.4350965917110443,
      "learning_rate": 0.00018017738359201775,
      "loss": 0.6696,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.3712170124053955,
      "learning_rate": 0.00017911751662971173,
      "loss": 0.6406,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.3749583959579468,
      "learning_rate": 0.00017805764966740578,
      "loss": 0.6281,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.39066019654273987,
      "learning_rate": 0.0001769977827050998,
      "loss": 0.5958,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.32838478684425354,
      "learning_rate": 0.00017593791574279378,
      "loss": 0.6969,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.34712207317352295,
      "learning_rate": 0.00017487804878048782,
      "loss": 0.6894,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.41427138447761536,
      "learning_rate": 0.00017381818181818183,
      "loss": 0.6919,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.36579301953315735,
      "learning_rate": 0.00017275831485587582,
      "loss": 0.7193,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.4437645971775055,
      "learning_rate": 0.00017169844789356986,
      "loss": 0.7467,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.367373526096344,
      "learning_rate": 0.00017063858093126387,
      "loss": 0.6547,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.3570501208305359,
      "learning_rate": 0.00016957871396895788,
      "loss": 0.6587,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.3444426953792572,
      "learning_rate": 0.0001685188470066519,
      "loss": 0.7691,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.3180396258831024,
      "learning_rate": 0.0001674589800443459,
      "loss": 0.6942,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.34924229979515076,
      "learning_rate": 0.00016639911308203992,
      "loss": 0.6569,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.36888396739959717,
      "learning_rate": 0.00016533924611973394,
      "loss": 0.6636,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.3853783905506134,
      "learning_rate": 0.00016427937915742795,
      "loss": 0.6572,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.3830152451992035,
      "learning_rate": 0.00016321951219512197,
      "loss": 0.6726,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4932275116443634,
      "learning_rate": 0.00016215964523281595,
      "loss": 0.6578,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.392809122800827,
      "learning_rate": 0.00016109977827051,
      "loss": 0.6292,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.38704097270965576,
      "learning_rate": 0.000160039911308204,
      "loss": 0.5903,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.37722790241241455,
      "learning_rate": 0.000158980044345898,
      "loss": 0.5874,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.3986051380634308,
      "learning_rate": 0.00015792017738359203,
      "loss": 0.5913,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.42364734411239624,
      "learning_rate": 0.00015686031042128605,
      "loss": 0.5503,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.5147843956947327,
      "learning_rate": 0.00015580044345898003,
      "loss": 0.6069,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.4635319113731384,
      "learning_rate": 0.00015474057649667407,
      "loss": 0.5821,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.4730147123336792,
      "learning_rate": 0.0001536807095343681,
      "loss": 0.5704,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.4122169017791748,
      "learning_rate": 0.00015262084257206207,
      "loss": 0.5875,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.4188688397407532,
      "learning_rate": 0.00015156097560975611,
      "loss": 0.591,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.40339216589927673,
      "learning_rate": 0.00015050110864745013,
      "loss": 0.5964,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.4176221191883087,
      "learning_rate": 0.00014944124168514411,
      "loss": 0.5653,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.46824681758880615,
      "learning_rate": 0.00014838137472283816,
      "loss": 0.5551,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.4593164026737213,
      "learning_rate": 0.00014732150776053217,
      "loss": 0.5832,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.4187844395637512,
      "learning_rate": 0.00014626164079822616,
      "loss": 0.5358,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.45083922147750854,
      "learning_rate": 0.0001452017738359202,
      "loss": 0.5912,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.39994415640830994,
      "learning_rate": 0.0001441419068736142,
      "loss": 0.5225,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.4392825961112976,
      "learning_rate": 0.0001430820399113082,
      "loss": 0.4883,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.4866951107978821,
      "learning_rate": 0.00014202217294900224,
      "loss": 0.5112,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.49154168367385864,
      "learning_rate": 0.00014096230598669625,
      "loss": 0.5608,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.48593759536743164,
      "learning_rate": 0.00013990243902439024,
      "loss": 0.6128,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.48297789692878723,
      "learning_rate": 0.00013884257206208425,
      "loss": 0.4796,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.4775952398777008,
      "learning_rate": 0.0001377827050997783,
      "loss": 0.5012,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.4983569085597992,
      "learning_rate": 0.00013672283813747228,
      "loss": 0.5573,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.4817213714122772,
      "learning_rate": 0.0001356629711751663,
      "loss": 0.5503,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.4505611062049866,
      "learning_rate": 0.00013460310421286033,
      "loss": 0.5458,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.4732796549797058,
      "learning_rate": 0.00013354323725055432,
      "loss": 0.5078,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.4510941803455353,
      "learning_rate": 0.00013248337028824833,
      "loss": 0.5108,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.5138033628463745,
      "learning_rate": 0.00013142350332594237,
      "loss": 0.5883,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.44492408633232117,
      "learning_rate": 0.00013036363636363636,
      "loss": 0.5029,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.48559048771858215,
      "learning_rate": 0.00012930376940133037,
      "loss": 0.6139,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.4987350404262543,
      "learning_rate": 0.0001282439024390244,
      "loss": 0.5149,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.4999798536300659,
      "learning_rate": 0.0001271840354767184,
      "loss": 0.5593,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.4927052855491638,
      "learning_rate": 0.0001261241685144124,
      "loss": 0.5782,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.4854503571987152,
      "learning_rate": 0.00012506430155210645,
      "loss": 0.5479,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.4964471757411957,
      "learning_rate": 0.00012400443458980044,
      "loss": 0.5526,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.5352777242660522,
      "learning_rate": 0.00012294456762749445,
      "loss": 0.5871,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.523512065410614,
      "learning_rate": 0.00012188470066518848,
      "loss": 0.5555,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.5086607336997986,
      "learning_rate": 0.00012082483370288248,
      "loss": 0.5613,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.4900534152984619,
      "learning_rate": 0.0001197649667405765,
      "loss": 0.5573,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.4950725734233856,
      "learning_rate": 0.00011870509977827052,
      "loss": 0.595,
      "step": 345
    }
  ],
  "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": 1.5728779384851456e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}