{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2835164835164834,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.092259407043457,
      "learning_rate": 0.0,
      "loss": 1.0581,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0709208250045776,
      "learning_rate": 9.56e-05,
      "loss": 1.1072,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.958633303642273,
      "learning_rate": 0.0001912,
      "loss": 0.9974,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.1406344175338745,
      "learning_rate": 0.0002868,
      "loss": 1.0239,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6300336122512817,
      "learning_rate": 0.0003824,
      "loss": 0.864,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.6665506958961487,
      "learning_rate": 0.000478,
      "loss": 0.9466,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5092409253120422,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9307,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.4416404068470001,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8977,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.2995733320713043,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8339,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.3041072487831116,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.8087,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.37241628766059875,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.771,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.39393821358680725,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8849,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.3837544918060303,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.8491,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.49497556686401367,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.8303,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5117122530937195,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.8409,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.49063509702682495,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7597,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.45528849959373474,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7641,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.6419070959091187,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7994,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4234957695007324,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.8006,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3917295038700104,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.672,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.42700546979904175,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.79,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.31304818391799927,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.8003,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5040671229362488,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7685,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3319059908390045,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.6304,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3119790554046631,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.6764,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.5550832748413086,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7242,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.34620189666748047,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7264,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.37555280327796936,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7266,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.37990307807922363,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.7272,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.41835644841194153,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.6954,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.4351997673511505,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.796,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.408133864402771,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7393,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3200816512107849,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.7437,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2987661063671112,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.724,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3201579451560974,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7287,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.30183011293411255,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7698,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3419806659221649,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.6937,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3351280391216278,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.6422,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3343323767185211,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.7491,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.31155410408973694,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.754,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.30340951681137085,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7478,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.32625922560691833,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.6869,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3275451958179474,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7391,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3605313003063202,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6923,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.25487375259399414,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.6635,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.34798017144203186,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.6847,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.38547784090042114,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.6828,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.43565401434898376,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7274,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.31378173828125,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.7155,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.28434091806411743,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.7387,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4276268780231476,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.6849,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4526767432689667,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.6946,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.420036643743515,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.6688,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.4806784391403198,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.7359,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.41160258650779724,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.6726,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.31491726636886597,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.684,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.4807892441749573,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7384,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3902229964733124,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.7077,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2929512858390808,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.6925,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3077262043952942,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.6587,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.44585803151130676,
      "learning_rate": 0.00041970731707317074,
      "loss": 0.6851,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.33904632925987244,
      "learning_rate": 0.0004186474501108648,
      "loss": 0.6596,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2696736454963684,
      "learning_rate": 0.0004175875831485588,
      "loss": 0.7057,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.26604217290878296,
      "learning_rate": 0.00041652771618625275,
      "loss": 0.6929,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.32026171684265137,
      "learning_rate": 0.0004154678492239468,
      "loss": 0.6836,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.2880091071128845,
      "learning_rate": 0.00041440798226164083,
      "loss": 0.7041,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.31481364369392395,
      "learning_rate": 0.0004133481152993348,
      "loss": 0.7478,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2715815603733063,
      "learning_rate": 0.00041228824833702886,
      "loss": 0.7109,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.31372612714767456,
      "learning_rate": 0.00041122838137472285,
      "loss": 0.7366,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.38761797547340393,
      "learning_rate": 0.00041016851441241683,
      "loss": 0.6759,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.37390732765197754,
      "learning_rate": 0.00040910864745011087,
      "loss": 0.6955,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.33533158898353577,
      "learning_rate": 0.00040804878048780486,
      "loss": 0.7363,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3151540160179138,
      "learning_rate": 0.0004069889135254989,
      "loss": 0.6806,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3429710268974304,
      "learning_rate": 0.00040592904656319294,
      "loss": 0.7545,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3716053366661072,
      "learning_rate": 0.0004048691796008869,
      "loss": 0.7218,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3623422384262085,
      "learning_rate": 0.00040380931263858097,
      "loss": 0.6841,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.30717232823371887,
      "learning_rate": 0.00040274944567627495,
      "loss": 0.7246,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3356327414512634,
      "learning_rate": 0.00040168957871396894,
      "loss": 0.6963,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3588886857032776,
      "learning_rate": 0.000400629711751663,
      "loss": 0.7186,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3841427266597748,
      "learning_rate": 0.000399569844789357,
      "loss": 0.7589,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.28263726830482483,
      "learning_rate": 0.000398509977827051,
      "loss": 0.7125,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.32447806000709534,
      "learning_rate": 0.00039745011086474505,
      "loss": 0.6923,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4162701964378357,
      "learning_rate": 0.00039639024390243904,
      "loss": 0.6787,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.35858726501464844,
      "learning_rate": 0.000395330376940133,
      "loss": 0.7394,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.37772467732429504,
      "learning_rate": 0.00039427050997782706,
      "loss": 0.7884,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.35319265723228455,
      "learning_rate": 0.0003932106430155211,
      "loss": 0.7014,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3901425004005432,
      "learning_rate": 0.0003921507760532151,
      "loss": 0.783,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3614656329154968,
      "learning_rate": 0.00039109090909090913,
      "loss": 0.7162,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3332541584968567,
      "learning_rate": 0.0003900310421286031,
      "loss": 0.7087,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3593405783176422,
      "learning_rate": 0.0003889711751662971,
      "loss": 0.6434,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28303709626197815,
      "learning_rate": 0.00038791130820399114,
      "loss": 0.6528,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3028731346130371,
      "learning_rate": 0.0003868514412416852,
      "loss": 0.6534,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.2780463397502899,
      "learning_rate": 0.00038579157427937917,
      "loss": 0.6735,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3711230158805847,
      "learning_rate": 0.0003847317073170732,
      "loss": 0.6829,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.34687119722366333,
      "learning_rate": 0.0003836718403547672,
      "loss": 0.7141,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.345458984375,
      "learning_rate": 0.0003826119733924612,
      "loss": 0.6959,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3982362151145935,
      "learning_rate": 0.0003815521064301552,
      "loss": 0.7386,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.3474859893321991,
      "learning_rate": 0.00038049223946784927,
      "loss": 0.773,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.29728448390960693,
      "learning_rate": 0.00037943237250554325,
      "loss": 0.7317,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.37078380584716797,
      "learning_rate": 0.0003783725055432373,
      "loss": 0.6527,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.2784273028373718,
      "learning_rate": 0.0003773126385809313,
      "loss": 0.7453,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3079737722873688,
      "learning_rate": 0.00037625277161862527,
      "loss": 0.7709,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.37596800923347473,
      "learning_rate": 0.0003751929046563193,
      "loss": 0.6839,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3462836444377899,
      "learning_rate": 0.00037413303769401335,
      "loss": 0.6834,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3802523612976074,
      "learning_rate": 0.00037307317073170733,
      "loss": 0.7861,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.35195550322532654,
      "learning_rate": 0.0003720133037694014,
      "loss": 0.6706,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.2925601005554199,
      "learning_rate": 0.00037095343680709536,
      "loss": 0.7173,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.3123745322227478,
      "learning_rate": 0.00036989356984478935,
      "loss": 0.6999,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.33011817932128906,
      "learning_rate": 0.0003688337028824834,
      "loss": 0.7333,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.2912536859512329,
      "learning_rate": 0.0003677738359201774,
      "loss": 0.6387,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3130698502063751,
      "learning_rate": 0.0003667139689578714,
      "loss": 0.7611,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.36619213223457336,
      "learning_rate": 0.00036565410199556546,
      "loss": 0.6892,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.3015907108783722,
      "learning_rate": 0.0003645942350332594,
      "loss": 0.706,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.35781264305114746,
      "learning_rate": 0.00036353436807095343,
      "loss": 0.7279,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3180965483188629,
      "learning_rate": 0.00036247450110864747,
      "loss": 0.7057,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3428914546966553,
      "learning_rate": 0.00036141463414634146,
      "loss": 0.7257,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.29366132616996765,
      "learning_rate": 0.0003603547671840355,
      "loss": 0.7501,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.28782641887664795,
      "learning_rate": 0.00035929490022172954,
      "loss": 0.6641,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.2645438611507416,
      "learning_rate": 0.00035823503325942347,
      "loss": 0.6863,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.32708922028541565,
      "learning_rate": 0.0003571751662971175,
      "loss": 0.7197,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.31933650374412537,
      "learning_rate": 0.00035611529933481155,
      "loss": 0.6765,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3052234351634979,
      "learning_rate": 0.00035505543237250554,
      "loss": 0.6017,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.33753010630607605,
      "learning_rate": 0.0003539955654101996,
      "loss": 0.7471,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.31018975377082825,
      "learning_rate": 0.0003529356984478936,
      "loss": 0.6847,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3185444474220276,
      "learning_rate": 0.00035187583148558755,
      "loss": 0.7374,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3511684834957123,
      "learning_rate": 0.0003508159645232816,
      "loss": 0.7206,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.2725747227668762,
      "learning_rate": 0.00034975609756097563,
      "loss": 0.7114,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.2914865016937256,
      "learning_rate": 0.0003486962305986696,
      "loss": 0.6888,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.33189496397972107,
      "learning_rate": 0.00034763636363636366,
      "loss": 0.7039,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.32994407415390015,
      "learning_rate": 0.0003465764966740577,
      "loss": 0.7042,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.2937301695346832,
      "learning_rate": 0.00034551662971175163,
      "loss": 0.7361,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.347198486328125,
      "learning_rate": 0.00034445676274944567,
      "loss": 0.6354,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.326761931180954,
      "learning_rate": 0.0003433968957871397,
      "loss": 0.7419,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3521762192249298,
      "learning_rate": 0.0003423370288248337,
      "loss": 0.6564,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.29606369137763977,
      "learning_rate": 0.00034127716186252774,
      "loss": 0.7516,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.32473766803741455,
      "learning_rate": 0.0003402172949002218,
      "loss": 0.6393,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3140825629234314,
      "learning_rate": 0.00033915742793791577,
      "loss": 0.7199,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.3303295373916626,
      "learning_rate": 0.00033809756097560975,
      "loss": 0.6445,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.2945369780063629,
      "learning_rate": 0.0003370376940133038,
      "loss": 0.6484,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.30725225806236267,
      "learning_rate": 0.0003359778270509978,
      "loss": 0.6868,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.31323936581611633,
      "learning_rate": 0.0003349179600886918,
      "loss": 0.7059,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.34050843119621277,
      "learning_rate": 0.00033385809312638586,
      "loss": 0.6837,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.28915706276893616,
      "learning_rate": 0.00033279822616407985,
      "loss": 0.6548,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.29176533222198486,
      "learning_rate": 0.00033173835920177384,
      "loss": 0.675,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.32223474979400635,
      "learning_rate": 0.0003306784922394679,
      "loss": 0.7157,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.29556649923324585,
      "learning_rate": 0.00032961862527716186,
      "loss": 0.6877,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.28119975328445435,
      "learning_rate": 0.0003285587583148559,
      "loss": 0.6399,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.26829302310943604,
      "learning_rate": 0.00032749889135254994,
      "loss": 0.7095,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.29534584283828735,
      "learning_rate": 0.00032643902439024393,
      "loss": 0.6601,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.32757872343063354,
      "learning_rate": 0.0003253791574279379,
      "loss": 0.731,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3757317364215851,
      "learning_rate": 0.0003243192904656319,
      "loss": 0.7314,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5265413522720337,
      "learning_rate": 0.00032325942350332594,
      "loss": 0.7166,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.30276599526405334,
      "learning_rate": 0.00032219955654102,
      "loss": 0.6543,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.2979506552219391,
      "learning_rate": 0.00032113968957871397,
      "loss": 0.7316,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.3436979651451111,
      "learning_rate": 0.000320079822616408,
      "loss": 0.6541,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.32019904255867004,
      "learning_rate": 0.000319019955654102,
      "loss": 0.6461,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.35557907819747925,
      "learning_rate": 0.000317960088691796,
      "loss": 0.6096,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3053385317325592,
      "learning_rate": 0.00031690022172949,
      "loss": 0.6203,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.3197833299636841,
      "learning_rate": 0.00031584035476718407,
      "loss": 0.6792,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.35202038288116455,
      "learning_rate": 0.00031478048780487805,
      "loss": 0.6185,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3381637930870056,
      "learning_rate": 0.0003137206208425721,
      "loss": 0.6349,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.36586257815361023,
      "learning_rate": 0.0003126607538802661,
      "loss": 0.6532,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.36223551630973816,
      "learning_rate": 0.00031160088691796007,
      "loss": 0.6593,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.33133384585380554,
      "learning_rate": 0.0003105410199556541,
      "loss": 0.677,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3387676179409027,
      "learning_rate": 0.00030948115299334815,
      "loss": 0.632,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.34593525528907776,
      "learning_rate": 0.00030842128603104213,
      "loss": 0.6312,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.37897729873657227,
      "learning_rate": 0.0003073614190687362,
      "loss": 0.59,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.41148775815963745,
      "learning_rate": 0.00030630155210643016,
      "loss": 0.6855,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3731421232223511,
      "learning_rate": 0.00030524168514412415,
      "loss": 0.723,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3452712595462799,
      "learning_rate": 0.0003041818181818182,
      "loss": 0.6532,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.3143898546695709,
      "learning_rate": 0.00030312195121951223,
      "loss": 0.5611,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3600401282310486,
      "learning_rate": 0.0003020620842572062,
      "loss": 0.6577,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.2966977655887604,
      "learning_rate": 0.00030100221729490026,
      "loss": 0.68,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3393426239490509,
      "learning_rate": 0.00029994235033259424,
      "loss": 0.6616,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.3751320242881775,
      "learning_rate": 0.00029888248337028823,
      "loss": 0.6353,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.39001548290252686,
      "learning_rate": 0.00029782261640798227,
      "loss": 0.623,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.35858088731765747,
      "learning_rate": 0.0002967627494456763,
      "loss": 0.683,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.37301671504974365,
      "learning_rate": 0.0002957028824833703,
      "loss": 0.6458,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.4310253858566284,
      "learning_rate": 0.00029464301552106434,
      "loss": 0.6556,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3796077072620392,
      "learning_rate": 0.0002935831485587583,
      "loss": 0.6945,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.3386010229587555,
      "learning_rate": 0.0002925232815964523,
      "loss": 0.632,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.392260879278183,
      "learning_rate": 0.00029146341463414635,
      "loss": 0.6457,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.3873871862888336,
      "learning_rate": 0.0002904035476718404,
      "loss": 0.6515,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.4391847550868988,
      "learning_rate": 0.0002893436807095344,
      "loss": 0.6208,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.38512229919433594,
      "learning_rate": 0.0002882838137472284,
      "loss": 0.5948,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.32289543747901917,
      "learning_rate": 0.0002872239467849224,
      "loss": 0.6981,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.43988853693008423,
      "learning_rate": 0.0002861640798226164,
      "loss": 0.6575,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.3641416132450104,
      "learning_rate": 0.00028510421286031043,
      "loss": 0.6399,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.40127384662628174,
      "learning_rate": 0.0002840443458980045,
      "loss": 0.6185,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.42784059047698975,
      "learning_rate": 0.00028298447893569846,
      "loss": 0.6646,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.4455963969230652,
      "learning_rate": 0.0002819246119733925,
      "loss": 0.6248,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4095698595046997,
      "learning_rate": 0.00028086474501108643,
      "loss": 0.5531,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.43887901306152344,
      "learning_rate": 0.0002798048780487805,
      "loss": 0.6853,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.429691344499588,
      "learning_rate": 0.0002787450110864745,
      "loss": 0.6336,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.3567647337913513,
      "learning_rate": 0.0002776851441241685,
      "loss": 0.609,
      "step": 195
    }
  ],
  "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": 8.915029899813274e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}