{
  "best_metric": 1.2089511156082153,
  "best_model_checkpoint": "miner_id_24/checkpoint-600",
  "epoch": 0.03813912836200389,
  "eval_steps": 100,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.356521393667315e-05,
      "grad_norm": 0.9428938031196594,
      "learning_rate": 2e-05,
      "loss": 1.7738,
      "step": 1
    },
    {
      "epoch": 6.356521393667315e-05,
      "eval_loss": 1.7346340417861938,
      "eval_runtime": 1229.3502,
      "eval_samples_per_second": 4.067,
      "eval_steps_per_second": 1.017,
      "step": 1
    },
    {
      "epoch": 0.0001271304278733463,
      "grad_norm": 0.9990512728691101,
      "learning_rate": 4e-05,
      "loss": 1.7963,
      "step": 2
    },
    {
      "epoch": 0.00019069564181001947,
      "grad_norm": 0.9891267418861389,
      "learning_rate": 6e-05,
      "loss": 1.7598,
      "step": 3
    },
    {
      "epoch": 0.0002542608557466926,
      "grad_norm": 0.9866920709609985,
      "learning_rate": 8e-05,
      "loss": 1.7408,
      "step": 4
    },
    {
      "epoch": 0.0003178260696833658,
      "grad_norm": 1.0441697835922241,
      "learning_rate": 0.0001,
      "loss": 1.7145,
      "step": 5
    },
    {
      "epoch": 0.00038139128362003893,
      "grad_norm": 0.6852884888648987,
      "learning_rate": 0.00012,
      "loss": 1.5726,
      "step": 6
    },
    {
      "epoch": 0.00044495649755671207,
      "grad_norm": 0.3806685507297516,
      "learning_rate": 0.00014,
      "loss": 1.4647,
      "step": 7
    },
    {
      "epoch": 0.0005085217114933852,
      "grad_norm": 1.17180597782135,
      "learning_rate": 0.00016,
      "loss": 1.6533,
      "step": 8
    },
    {
      "epoch": 0.0005720869254300584,
      "grad_norm": 1.060241937637329,
      "learning_rate": 0.00018,
      "loss": 1.6696,
      "step": 9
    },
    {
      "epoch": 0.0006356521393667316,
      "grad_norm": 0.5335236191749573,
      "learning_rate": 0.0002,
      "loss": 1.5761,
      "step": 10
    },
    {
      "epoch": 0.0006992173533034047,
      "grad_norm": 0.2798483967781067,
      "learning_rate": 0.00019999928367015404,
      "loss": 1.5146,
      "step": 11
    },
    {
      "epoch": 0.0007627825672400779,
      "grad_norm": 0.3353223502635956,
      "learning_rate": 0.00019999713469087867,
      "loss": 1.6184,
      "step": 12
    },
    {
      "epoch": 0.0008263477811767511,
      "grad_norm": 0.3838560879230499,
      "learning_rate": 0.00019999355309296144,
      "loss": 1.4522,
      "step": 13
    },
    {
      "epoch": 0.0008899129951134241,
      "grad_norm": 0.39443036913871765,
      "learning_rate": 0.00019998853892771453,
      "loss": 1.517,
      "step": 14
    },
    {
      "epoch": 0.0009534782090500973,
      "grad_norm": 0.2620809078216553,
      "learning_rate": 0.00019998209226697376,
      "loss": 1.3812,
      "step": 15
    },
    {
      "epoch": 0.0010170434229867704,
      "grad_norm": 0.23137860000133514,
      "learning_rate": 0.00019997421320309795,
      "loss": 1.3922,
      "step": 16
    },
    {
      "epoch": 0.0010806086369234437,
      "grad_norm": 0.2614266276359558,
      "learning_rate": 0.00019996490184896723,
      "loss": 1.508,
      "step": 17
    },
    {
      "epoch": 0.0011441738508601168,
      "grad_norm": 0.325157105922699,
      "learning_rate": 0.00019995415833798158,
      "loss": 1.4778,
      "step": 18
    },
    {
      "epoch": 0.0012077390647967899,
      "grad_norm": 0.3683066666126251,
      "learning_rate": 0.000199941982824059,
      "loss": 1.5108,
      "step": 19
    },
    {
      "epoch": 0.0012713042787334632,
      "grad_norm": 0.24171724915504456,
      "learning_rate": 0.00019992837548163316,
      "loss": 1.4124,
      "step": 20
    },
    {
      "epoch": 0.0013348694926701363,
      "grad_norm": 0.2298036813735962,
      "learning_rate": 0.00019991333650565095,
      "loss": 1.4449,
      "step": 21
    },
    {
      "epoch": 0.0013984347066068094,
      "grad_norm": 0.26465296745300293,
      "learning_rate": 0.00019989686611156972,
      "loss": 1.4632,
      "step": 22
    },
    {
      "epoch": 0.0014619999205434827,
      "grad_norm": 0.26514774560928345,
      "learning_rate": 0.0001998789645353542,
      "loss": 1.3014,
      "step": 23
    },
    {
      "epoch": 0.0015255651344801557,
      "grad_norm": 0.21595242619514465,
      "learning_rate": 0.000199859632033473,
      "loss": 1.3242,
      "step": 24
    },
    {
      "epoch": 0.0015891303484168288,
      "grad_norm": 0.21354669332504272,
      "learning_rate": 0.00019983886888289514,
      "loss": 1.234,
      "step": 25
    },
    {
      "epoch": 0.0016526955623535021,
      "grad_norm": 0.2628548741340637,
      "learning_rate": 0.00019981667538108587,
      "loss": 1.4919,
      "step": 26
    },
    {
      "epoch": 0.0017162607762901752,
      "grad_norm": 0.26308178901672363,
      "learning_rate": 0.00019979305184600256,
      "loss": 1.462,
      "step": 27
    },
    {
      "epoch": 0.0017798259902268483,
      "grad_norm": 0.2193090170621872,
      "learning_rate": 0.00019976799861609008,
      "loss": 1.4595,
      "step": 28
    },
    {
      "epoch": 0.0018433912041635216,
      "grad_norm": 0.22884628176689148,
      "learning_rate": 0.00019974151605027594,
      "loss": 1.4373,
      "step": 29
    },
    {
      "epoch": 0.0019069564181001947,
      "grad_norm": 0.23094788193702698,
      "learning_rate": 0.00019971360452796522,
      "loss": 1.4242,
      "step": 30
    },
    {
      "epoch": 0.001970521632036868,
      "grad_norm": 0.2305305153131485,
      "learning_rate": 0.000199684264449035,
      "loss": 1.4417,
      "step": 31
    },
    {
      "epoch": 0.002034086845973541,
      "grad_norm": 0.23320302367210388,
      "learning_rate": 0.0001996534962338288,
      "loss": 1.4594,
      "step": 32
    },
    {
      "epoch": 0.002097652059910214,
      "grad_norm": 0.2571035623550415,
      "learning_rate": 0.00019962130032315044,
      "loss": 1.4992,
      "step": 33
    },
    {
      "epoch": 0.0021612172738468874,
      "grad_norm": 0.23477134108543396,
      "learning_rate": 0.0001995876771782577,
      "loss": 1.4658,
      "step": 34
    },
    {
      "epoch": 0.0022247824877835603,
      "grad_norm": 0.2341969609260559,
      "learning_rate": 0.0001995526272808559,
      "loss": 1.4237,
      "step": 35
    },
    {
      "epoch": 0.0022883477017202336,
      "grad_norm": 0.22168391942977905,
      "learning_rate": 0.00019951615113309075,
      "loss": 1.4189,
      "step": 36
    },
    {
      "epoch": 0.002351912915656907,
      "grad_norm": 0.21319416165351868,
      "learning_rate": 0.00019947824925754131,
      "loss": 1.3227,
      "step": 37
    },
    {
      "epoch": 0.0024154781295935798,
      "grad_norm": 0.21283291280269623,
      "learning_rate": 0.00019943892219721253,
      "loss": 1.2823,
      "step": 38
    },
    {
      "epoch": 0.002479043343530253,
      "grad_norm": 0.2249862402677536,
      "learning_rate": 0.00019939817051552728,
      "loss": 1.4165,
      "step": 39
    },
    {
      "epoch": 0.0025426085574669264,
      "grad_norm": 0.23104599118232727,
      "learning_rate": 0.0001993559947963185,
      "loss": 1.345,
      "step": 40
    },
    {
      "epoch": 0.0026061737714035992,
      "grad_norm": 0.21223703026771545,
      "learning_rate": 0.00019931239564382073,
      "loss": 1.3816,
      "step": 41
    },
    {
      "epoch": 0.0026697389853402725,
      "grad_norm": 0.22133688628673553,
      "learning_rate": 0.00019926737368266144,
      "loss": 1.4486,
      "step": 42
    },
    {
      "epoch": 0.002733304199276946,
      "grad_norm": 0.2195105105638504,
      "learning_rate": 0.00019922092955785217,
      "loss": 1.4167,
      "step": 43
    },
    {
      "epoch": 0.0027968694132136187,
      "grad_norm": 0.21872290968894958,
      "learning_rate": 0.00019917306393477907,
      "loss": 1.2899,
      "step": 44
    },
    {
      "epoch": 0.002860434627150292,
      "grad_norm": 0.22723184525966644,
      "learning_rate": 0.00019912377749919374,
      "loss": 1.3379,
      "step": 45
    },
    {
      "epoch": 0.0029239998410869653,
      "grad_norm": 0.20976956188678741,
      "learning_rate": 0.00019907307095720303,
      "loss": 1.4117,
      "step": 46
    },
    {
      "epoch": 0.002987565055023638,
      "grad_norm": 0.23163513839244843,
      "learning_rate": 0.0001990209450352591,
      "loss": 1.1854,
      "step": 47
    },
    {
      "epoch": 0.0030511302689603115,
      "grad_norm": 0.24127621948719025,
      "learning_rate": 0.00019896740048014908,
      "loss": 1.3795,
      "step": 48
    },
    {
      "epoch": 0.0031146954828969848,
      "grad_norm": 0.2310689091682434,
      "learning_rate": 0.0001989124380589842,
      "loss": 1.386,
      "step": 49
    },
    {
      "epoch": 0.0031782606968336576,
      "grad_norm": 0.21882858872413635,
      "learning_rate": 0.00019885605855918885,
      "loss": 1.3369,
      "step": 50
    },
    {
      "epoch": 0.003241825910770331,
      "grad_norm": 0.2317679077386856,
      "learning_rate": 0.0001987982627884895,
      "loss": 1.3222,
      "step": 51
    },
    {
      "epoch": 0.0033053911247070042,
      "grad_norm": 0.22262057662010193,
      "learning_rate": 0.00019873905157490285,
      "loss": 1.2872,
      "step": 52
    },
    {
      "epoch": 0.003368956338643677,
      "grad_norm": 0.2331005483865738,
      "learning_rate": 0.00019867842576672403,
      "loss": 1.3113,
      "step": 53
    },
    {
      "epoch": 0.0034325215525803504,
      "grad_norm": 0.22421784698963165,
      "learning_rate": 0.0001986163862325146,
      "loss": 1.3245,
      "step": 54
    },
    {
      "epoch": 0.0034960867665170237,
      "grad_norm": 0.23669274151325226,
      "learning_rate": 0.00019855293386108992,
      "loss": 1.2904,
      "step": 55
    },
    {
      "epoch": 0.0035596519804536966,
      "grad_norm": 0.2372964769601822,
      "learning_rate": 0.0001984880695615066,
      "loss": 1.4022,
      "step": 56
    },
    {
      "epoch": 0.00362321719439037,
      "grad_norm": 0.2388596534729004,
      "learning_rate": 0.00019842179426304924,
      "loss": 1.3641,
      "step": 57
    },
    {
      "epoch": 0.003686782408327043,
      "grad_norm": 0.2330758273601532,
      "learning_rate": 0.0001983541089152174,
      "loss": 1.3179,
      "step": 58
    },
    {
      "epoch": 0.003750347622263716,
      "grad_norm": 0.236953005194664,
      "learning_rate": 0.00019828501448771176,
      "loss": 1.4528,
      "step": 59
    },
    {
      "epoch": 0.0038139128362003893,
      "grad_norm": 0.22548601031303406,
      "learning_rate": 0.00019821451197042026,
      "loss": 1.4551,
      "step": 60
    },
    {
      "epoch": 0.0038774780501370626,
      "grad_norm": 0.2316240519285202,
      "learning_rate": 0.00019814260237340414,
      "loss": 1.3653,
      "step": 61
    },
    {
      "epoch": 0.003941043264073736,
      "grad_norm": 0.2395096868276596,
      "learning_rate": 0.0001980692867268832,
      "loss": 1.2773,
      "step": 62
    },
    {
      "epoch": 0.004004608478010409,
      "grad_norm": 0.23329375684261322,
      "learning_rate": 0.00019799456608122107,
      "loss": 1.3483,
      "step": 63
    },
    {
      "epoch": 0.004068173691947082,
      "grad_norm": 0.22131139039993286,
      "learning_rate": 0.0001979184415069104,
      "loss": 1.2442,
      "step": 64
    },
    {
      "epoch": 0.004131738905883755,
      "grad_norm": 0.22645598649978638,
      "learning_rate": 0.00019784091409455728,
      "loss": 1.3506,
      "step": 65
    },
    {
      "epoch": 0.004195304119820428,
      "grad_norm": 0.2391359955072403,
      "learning_rate": 0.00019776198495486565,
      "loss": 1.3665,
      "step": 66
    },
    {
      "epoch": 0.004258869333757101,
      "grad_norm": 0.2379651963710785,
      "learning_rate": 0.00019768165521862155,
      "loss": 1.3642,
      "step": 67
    },
    {
      "epoch": 0.004322434547693775,
      "grad_norm": 0.2432878315448761,
      "learning_rate": 0.00019759992603667667,
      "loss": 1.3705,
      "step": 68
    },
    {
      "epoch": 0.004385999761630448,
      "grad_norm": 0.22903011739253998,
      "learning_rate": 0.0001975167985799321,
      "loss": 1.4265,
      "step": 69
    },
    {
      "epoch": 0.004449564975567121,
      "grad_norm": 0.2231925129890442,
      "learning_rate": 0.00019743227403932134,
      "loss": 1.2986,
      "step": 70
    },
    {
      "epoch": 0.004513130189503794,
      "grad_norm": 0.21844634413719177,
      "learning_rate": 0.0001973463536257935,
      "loss": 1.3026,
      "step": 71
    },
    {
      "epoch": 0.004576695403440467,
      "grad_norm": 0.22515372931957245,
      "learning_rate": 0.00019725903857029564,
      "loss": 1.4038,
      "step": 72
    },
    {
      "epoch": 0.00464026061737714,
      "grad_norm": 0.22920459508895874,
      "learning_rate": 0.00019717033012375538,
      "loss": 1.3418,
      "step": 73
    },
    {
      "epoch": 0.004703825831313814,
      "grad_norm": 0.23658373951911926,
      "learning_rate": 0.00019708022955706292,
      "loss": 1.3967,
      "step": 74
    },
    {
      "epoch": 0.004767391045250487,
      "grad_norm": 0.2569814622402191,
      "learning_rate": 0.00019698873816105273,
      "loss": 1.2474,
      "step": 75
    },
    {
      "epoch": 0.0048309562591871595,
      "grad_norm": 0.24887211620807648,
      "learning_rate": 0.00019689585724648516,
      "loss": 1.3784,
      "step": 76
    },
    {
      "epoch": 0.004894521473123833,
      "grad_norm": 0.24335400760173798,
      "learning_rate": 0.00019680158814402762,
      "loss": 1.2964,
      "step": 77
    },
    {
      "epoch": 0.004958086687060506,
      "grad_norm": 0.233675017952919,
      "learning_rate": 0.00019670593220423558,
      "loss": 1.2317,
      "step": 78
    },
    {
      "epoch": 0.005021651900997179,
      "grad_norm": 0.24147622287273407,
      "learning_rate": 0.0001966088907975331,
      "loss": 1.1799,
      "step": 79
    },
    {
      "epoch": 0.005085217114933853,
      "grad_norm": 0.24836859107017517,
      "learning_rate": 0.00019651046531419332,
      "loss": 1.2793,
      "step": 80
    },
    {
      "epoch": 0.005148782328870526,
      "grad_norm": 0.24832896888256073,
      "learning_rate": 0.00019641065716431849,
      "loss": 1.2897,
      "step": 81
    },
    {
      "epoch": 0.0052123475428071985,
      "grad_norm": 0.22504734992980957,
      "learning_rate": 0.00019630946777781966,
      "loss": 1.2926,
      "step": 82
    },
    {
      "epoch": 0.005275912756743872,
      "grad_norm": 0.23750871419906616,
      "learning_rate": 0.00019620689860439647,
      "loss": 1.3263,
      "step": 83
    },
    {
      "epoch": 0.005339477970680545,
      "grad_norm": 0.2326141744852066,
      "learning_rate": 0.0001961029511135161,
      "loss": 1.3168,
      "step": 84
    },
    {
      "epoch": 0.005403043184617218,
      "grad_norm": 0.24577590823173523,
      "learning_rate": 0.0001959976267943923,
      "loss": 1.3602,
      "step": 85
    },
    {
      "epoch": 0.005466608398553892,
      "grad_norm": 0.24200314283370972,
      "learning_rate": 0.00019589092715596417,
      "loss": 1.3106,
      "step": 86
    },
    {
      "epoch": 0.0055301736124905645,
      "grad_norm": 0.24798905849456787,
      "learning_rate": 0.00019578285372687446,
      "loss": 1.3652,
      "step": 87
    },
    {
      "epoch": 0.005593738826427237,
      "grad_norm": 0.24428631365299225,
      "learning_rate": 0.00019567340805544758,
      "loss": 1.3525,
      "step": 88
    },
    {
      "epoch": 0.005657304040363911,
      "grad_norm": 0.22070927917957306,
      "learning_rate": 0.00019556259170966755,
      "loss": 1.2287,
      "step": 89
    },
    {
      "epoch": 0.005720869254300584,
      "grad_norm": 0.22392472624778748,
      "learning_rate": 0.0001954504062771555,
      "loss": 1.2536,
      "step": 90
    },
    {
      "epoch": 0.005784434468237257,
      "grad_norm": 0.23670928180217743,
      "learning_rate": 0.00019533685336514697,
      "loss": 1.2817,
      "step": 91
    },
    {
      "epoch": 0.005847999682173931,
      "grad_norm": 0.24242345988750458,
      "learning_rate": 0.00019522193460046864,
      "loss": 1.4427,
      "step": 92
    },
    {
      "epoch": 0.0059115648961106035,
      "grad_norm": 0.23915454745292664,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3832,
      "step": 93
    },
    {
      "epoch": 0.005975130110047276,
      "grad_norm": 0.2182474136352539,
      "learning_rate": 0.00019498800611822645,
      "loss": 1.2558,
      "step": 94
    },
    {
      "epoch": 0.00603869532398395,
      "grad_norm": 0.2170976847410202,
      "learning_rate": 0.00019486899975206166,
      "loss": 1.2063,
      "step": 95
    },
    {
      "epoch": 0.006102260537920623,
      "grad_norm": 0.23279117047786713,
      "learning_rate": 0.00019474863423597728,
      "loss": 1.2725,
      "step": 96
    },
    {
      "epoch": 0.006165825751857296,
      "grad_norm": 0.2265056073665619,
      "learning_rate": 0.00019462691129440147,
      "loss": 1.3748,
      "step": 97
    },
    {
      "epoch": 0.0062293909657939696,
      "grad_norm": 0.24922017753124237,
      "learning_rate": 0.00019450383267120982,
      "loss": 1.2609,
      "step": 98
    },
    {
      "epoch": 0.006292956179730642,
      "grad_norm": 0.2250678539276123,
      "learning_rate": 0.00019437940012970013,
      "loss": 1.318,
      "step": 99
    },
    {
      "epoch": 0.006356521393667315,
      "grad_norm": 0.2318231761455536,
      "learning_rate": 0.00019425361545256727,
      "loss": 1.3742,
      "step": 100
    },
    {
      "epoch": 0.006356521393667315,
      "eval_loss": 1.2972837686538696,
      "eval_runtime": 1239.6451,
      "eval_samples_per_second": 4.033,
      "eval_steps_per_second": 1.008,
      "step": 100
    },
    {
      "epoch": 0.006420086607603989,
      "grad_norm": 0.2393624186515808,
      "learning_rate": 0.0001941264804418776,
      "loss": 1.3151,
      "step": 101
    },
    {
      "epoch": 0.006483651821540662,
      "grad_norm": 0.22296006977558136,
      "learning_rate": 0.0001939979969190432,
      "loss": 1.3039,
      "step": 102
    },
    {
      "epoch": 0.006547217035477335,
      "grad_norm": 0.23289115726947784,
      "learning_rate": 0.00019386816672479565,
      "loss": 1.2941,
      "step": 103
    },
    {
      "epoch": 0.0066107822494140085,
      "grad_norm": 0.23189423978328705,
      "learning_rate": 0.00019373699171915988,
      "loss": 1.383,
      "step": 104
    },
    {
      "epoch": 0.006674347463350681,
      "grad_norm": 0.23659420013427734,
      "learning_rate": 0.00019360447378142728,
      "loss": 1.3502,
      "step": 105
    },
    {
      "epoch": 0.006737912677287354,
      "grad_norm": 0.2206616997718811,
      "learning_rate": 0.00019347061481012894,
      "loss": 1.2325,
      "step": 106
    },
    {
      "epoch": 0.006801477891224028,
      "grad_norm": 0.23390865325927734,
      "learning_rate": 0.00019333541672300841,
      "loss": 1.3818,
      "step": 107
    },
    {
      "epoch": 0.006865043105160701,
      "grad_norm": 0.22923798859119415,
      "learning_rate": 0.00019319888145699415,
      "loss": 1.3863,
      "step": 108
    },
    {
      "epoch": 0.006928608319097374,
      "grad_norm": 0.2286650538444519,
      "learning_rate": 0.00019306101096817186,
      "loss": 1.3434,
      "step": 109
    },
    {
      "epoch": 0.006992173533034047,
      "grad_norm": 0.22913207113742828,
      "learning_rate": 0.00019292180723175654,
      "loss": 1.3104,
      "step": 110
    },
    {
      "epoch": 0.00705573874697072,
      "grad_norm": 0.22382238507270813,
      "learning_rate": 0.00019278127224206396,
      "loss": 1.3462,
      "step": 111
    },
    {
      "epoch": 0.007119303960907393,
      "grad_norm": 0.23973888158798218,
      "learning_rate": 0.00019263940801248226,
      "loss": 1.2197,
      "step": 112
    },
    {
      "epoch": 0.007182869174844067,
      "grad_norm": 0.22928211092948914,
      "learning_rate": 0.0001924962165754431,
      "loss": 1.2881,
      "step": 113
    },
    {
      "epoch": 0.00724643438878074,
      "grad_norm": 0.23706093430519104,
      "learning_rate": 0.0001923516999823925,
      "loss": 1.3918,
      "step": 114
    },
    {
      "epoch": 0.007309999602717413,
      "grad_norm": 0.23154719173908234,
      "learning_rate": 0.00019220586030376134,
      "loss": 1.2693,
      "step": 115
    },
    {
      "epoch": 0.007373564816654086,
      "grad_norm": 0.22728873789310455,
      "learning_rate": 0.00019205869962893605,
      "loss": 1.3066,
      "step": 116
    },
    {
      "epoch": 0.007437130030590759,
      "grad_norm": 0.23983193933963776,
      "learning_rate": 0.0001919102200662282,
      "loss": 1.2305,
      "step": 117
    },
    {
      "epoch": 0.007500695244527432,
      "grad_norm": 0.2278611958026886,
      "learning_rate": 0.0001917604237428447,
      "loss": 1.3355,
      "step": 118
    },
    {
      "epoch": 0.007564260458464106,
      "grad_norm": 0.22559694945812225,
      "learning_rate": 0.00019160931280485702,
      "loss": 1.2477,
      "step": 119
    },
    {
      "epoch": 0.007627825672400779,
      "grad_norm": 0.22317031025886536,
      "learning_rate": 0.00019145688941717075,
      "loss": 1.2892,
      "step": 120
    },
    {
      "epoch": 0.0076913908863374516,
      "grad_norm": 0.24438677728176117,
      "learning_rate": 0.00019130315576349423,
      "loss": 1.3355,
      "step": 121
    },
    {
      "epoch": 0.007754956100274125,
      "grad_norm": 0.22496148943901062,
      "learning_rate": 0.00019114811404630762,
      "loss": 1.2373,
      "step": 122
    },
    {
      "epoch": 0.007818521314210798,
      "grad_norm": 0.23284892737865448,
      "learning_rate": 0.0001909917664868311,
      "loss": 1.2912,
      "step": 123
    },
    {
      "epoch": 0.007882086528147472,
      "grad_norm": 0.23059885203838348,
      "learning_rate": 0.0001908341153249931,
      "loss": 1.2765,
      "step": 124
    },
    {
      "epoch": 0.007945651742084144,
      "grad_norm": 0.23237423598766327,
      "learning_rate": 0.00019067516281939825,
      "loss": 1.2671,
      "step": 125
    },
    {
      "epoch": 0.008009216956020818,
      "grad_norm": 0.24287502467632294,
      "learning_rate": 0.00019051491124729512,
      "loss": 1.3046,
      "step": 126
    },
    {
      "epoch": 0.008072782169957491,
      "grad_norm": 0.23740199208259583,
      "learning_rate": 0.00019035336290454334,
      "loss": 1.3117,
      "step": 127
    },
    {
      "epoch": 0.008136347383894163,
      "grad_norm": 0.2472347617149353,
      "learning_rate": 0.00019019052010558088,
      "loss": 1.213,
      "step": 128
    },
    {
      "epoch": 0.008199912597830837,
      "grad_norm": 0.23237191140651703,
      "learning_rate": 0.00019002638518339087,
      "loss": 1.3313,
      "step": 129
    },
    {
      "epoch": 0.00826347781176751,
      "grad_norm": 0.23392349481582642,
      "learning_rate": 0.00018986096048946824,
      "loss": 1.2891,
      "step": 130
    },
    {
      "epoch": 0.008327043025704183,
      "grad_norm": 0.23264287412166595,
      "learning_rate": 0.00018969424839378584,
      "loss": 1.2695,
      "step": 131
    },
    {
      "epoch": 0.008390608239640857,
      "grad_norm": 0.24009764194488525,
      "learning_rate": 0.0001895262512847607,
      "loss": 1.3448,
      "step": 132
    },
    {
      "epoch": 0.00845417345357753,
      "grad_norm": 0.2373800426721573,
      "learning_rate": 0.0001893569715692197,
      "loss": 1.2892,
      "step": 133
    },
    {
      "epoch": 0.008517738667514202,
      "grad_norm": 0.24795696139335632,
      "learning_rate": 0.00018918641167236505,
      "loss": 1.2628,
      "step": 134
    },
    {
      "epoch": 0.008581303881450876,
      "grad_norm": 0.2304483950138092,
      "learning_rate": 0.00018901457403773967,
      "loss": 1.3338,
      "step": 135
    },
    {
      "epoch": 0.00864486909538755,
      "grad_norm": 0.2331048846244812,
      "learning_rate": 0.00018884146112719207,
      "loss": 1.4057,
      "step": 136
    },
    {
      "epoch": 0.008708434309324222,
      "grad_norm": 0.23537760972976685,
      "learning_rate": 0.00018866707542084118,
      "loss": 1.211,
      "step": 137
    },
    {
      "epoch": 0.008771999523260895,
      "grad_norm": 0.24523571133613586,
      "learning_rate": 0.00018849141941704067,
      "loss": 1.3498,
      "step": 138
    },
    {
      "epoch": 0.00883556473719757,
      "grad_norm": 0.23081225156784058,
      "learning_rate": 0.0001883144956323433,
      "loss": 1.289,
      "step": 139
    },
    {
      "epoch": 0.008899129951134241,
      "grad_norm": 0.24642105400562286,
      "learning_rate": 0.00018813630660146488,
      "loss": 1.2903,
      "step": 140
    },
    {
      "epoch": 0.008962695165070915,
      "grad_norm": 0.24798071384429932,
      "learning_rate": 0.00018795685487724782,
      "loss": 1.2623,
      "step": 141
    },
    {
      "epoch": 0.009026260379007589,
      "grad_norm": 0.23816098272800446,
      "learning_rate": 0.00018777614303062457,
      "loss": 1.247,
      "step": 142
    },
    {
      "epoch": 0.00908982559294426,
      "grad_norm": 0.25761744379997253,
      "learning_rate": 0.000187594173650581,
      "loss": 1.2847,
      "step": 143
    },
    {
      "epoch": 0.009153390806880934,
      "grad_norm": 0.2335919439792633,
      "learning_rate": 0.000187410949344119,
      "loss": 1.3036,
      "step": 144
    },
    {
      "epoch": 0.009216956020817608,
      "grad_norm": 0.23194169998168945,
      "learning_rate": 0.0001872264727362194,
      "loss": 1.1859,
      "step": 145
    },
    {
      "epoch": 0.00928052123475428,
      "grad_norm": 0.23245130479335785,
      "learning_rate": 0.00018704074646980415,
      "loss": 1.271,
      "step": 146
    },
    {
      "epoch": 0.009344086448690954,
      "grad_norm": 0.2260020226240158,
      "learning_rate": 0.0001868537732056987,
      "loss": 1.3987,
      "step": 147
    },
    {
      "epoch": 0.009407651662627628,
      "grad_norm": 0.2418159693479538,
      "learning_rate": 0.00018666555562259356,
      "loss": 1.3091,
      "step": 148
    },
    {
      "epoch": 0.0094712168765643,
      "grad_norm": 0.24677526950836182,
      "learning_rate": 0.0001864760964170062,
      "loss": 1.296,
      "step": 149
    },
    {
      "epoch": 0.009534782090500973,
      "grad_norm": 0.25532832741737366,
      "learning_rate": 0.00018628539830324229,
      "loss": 1.4065,
      "step": 150
    },
    {
      "epoch": 0.009598347304437647,
      "grad_norm": 0.2427254617214203,
      "learning_rate": 0.00018609346401335684,
      "loss": 1.3204,
      "step": 151
    },
    {
      "epoch": 0.009661912518374319,
      "grad_norm": 0.24365244805812836,
      "learning_rate": 0.00018590029629711506,
      "loss": 1.3882,
      "step": 152
    },
    {
      "epoch": 0.009725477732310993,
      "grad_norm": 0.22638386487960815,
      "learning_rate": 0.00018570589792195298,
      "loss": 1.2492,
      "step": 153
    },
    {
      "epoch": 0.009789042946247667,
      "grad_norm": 0.2262774556875229,
      "learning_rate": 0.00018551027167293768,
      "loss": 1.2209,
      "step": 154
    },
    {
      "epoch": 0.009852608160184339,
      "grad_norm": 0.21981820464134216,
      "learning_rate": 0.00018531342035272766,
      "loss": 1.1872,
      "step": 155
    },
    {
      "epoch": 0.009916173374121012,
      "grad_norm": 0.23878952860832214,
      "learning_rate": 0.00018511534678153244,
      "loss": 1.3344,
      "step": 156
    },
    {
      "epoch": 0.009979738588057686,
      "grad_norm": 0.2407320737838745,
      "learning_rate": 0.0001849160537970722,
      "loss": 1.259,
      "step": 157
    },
    {
      "epoch": 0.010043303801994358,
      "grad_norm": 0.23277470469474792,
      "learning_rate": 0.0001847155442545372,
      "loss": 1.2743,
      "step": 158
    },
    {
      "epoch": 0.010106869015931032,
      "grad_norm": 0.23986446857452393,
      "learning_rate": 0.00018451382102654683,
      "loss": 1.2853,
      "step": 159
    },
    {
      "epoch": 0.010170434229867705,
      "grad_norm": 0.23248420655727386,
      "learning_rate": 0.00018431088700310844,
      "loss": 1.2478,
      "step": 160
    },
    {
      "epoch": 0.010233999443804377,
      "grad_norm": 0.2354133576154709,
      "learning_rate": 0.00018410674509157607,
      "loss": 1.2036,
      "step": 161
    },
    {
      "epoch": 0.010297564657741051,
      "grad_norm": 0.2392132580280304,
      "learning_rate": 0.00018390139821660855,
      "loss": 1.2546,
      "step": 162
    },
    {
      "epoch": 0.010361129871677725,
      "grad_norm": 0.2282291203737259,
      "learning_rate": 0.00018369484932012777,
      "loss": 1.2038,
      "step": 163
    },
    {
      "epoch": 0.010424695085614397,
      "grad_norm": 0.24312043190002441,
      "learning_rate": 0.00018348710136127655,
      "loss": 1.3012,
      "step": 164
    },
    {
      "epoch": 0.01048826029955107,
      "grad_norm": 0.2509647309780121,
      "learning_rate": 0.00018327815731637612,
      "loss": 1.2312,
      "step": 165
    },
    {
      "epoch": 0.010551825513487744,
      "grad_norm": 0.2409852147102356,
      "learning_rate": 0.0001830680201788836,
      "loss": 1.2188,
      "step": 166
    },
    {
      "epoch": 0.010615390727424416,
      "grad_norm": 0.23334528505802155,
      "learning_rate": 0.0001828566929593491,
      "loss": 1.3472,
      "step": 167
    },
    {
      "epoch": 0.01067895594136109,
      "grad_norm": 0.23858241736888885,
      "learning_rate": 0.00018264417868537244,
      "loss": 1.3308,
      "step": 168
    },
    {
      "epoch": 0.010742521155297764,
      "grad_norm": 0.22705812752246857,
      "learning_rate": 0.00018243048040156003,
      "loss": 1.2548,
      "step": 169
    },
    {
      "epoch": 0.010806086369234436,
      "grad_norm": 0.24830320477485657,
      "learning_rate": 0.00018221560116948103,
      "loss": 1.308,
      "step": 170
    },
    {
      "epoch": 0.01086965158317111,
      "grad_norm": 0.23871473968029022,
      "learning_rate": 0.00018199954406762352,
      "loss": 1.2678,
      "step": 171
    },
    {
      "epoch": 0.010933216797107783,
      "grad_norm": 0.23958680033683777,
      "learning_rate": 0.0001817823121913506,
      "loss": 1.2768,
      "step": 172
    },
    {
      "epoch": 0.010996782011044455,
      "grad_norm": 0.2274036854505539,
      "learning_rate": 0.00018156390865285574,
      "loss": 1.239,
      "step": 173
    },
    {
      "epoch": 0.011060347224981129,
      "grad_norm": 0.24076679348945618,
      "learning_rate": 0.00018134433658111845,
      "loss": 1.3382,
      "step": 174
    },
    {
      "epoch": 0.011123912438917803,
      "grad_norm": 0.23195293545722961,
      "learning_rate": 0.00018112359912185924,
      "loss": 1.2813,
      "step": 175
    },
    {
      "epoch": 0.011187477652854475,
      "grad_norm": 0.24076253175735474,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.2844,
      "step": 176
    },
    {
      "epoch": 0.011251042866791149,
      "grad_norm": 0.228972926735878,
      "learning_rate": 0.00018067864070709231,
      "loss": 1.3109,
      "step": 177
    },
    {
      "epoch": 0.011314608080727822,
      "grad_norm": 0.23846612870693207,
      "learning_rate": 0.00018045442612632444,
      "loss": 1.2099,
      "step": 178
    },
    {
      "epoch": 0.011378173294664494,
      "grad_norm": 0.22861884534358978,
      "learning_rate": 0.00018022905890742306,
      "loss": 1.3219,
      "step": 179
    },
    {
      "epoch": 0.011441738508601168,
      "grad_norm": 0.23232094943523407,
      "learning_rate": 0.00018000254227913348,
      "loss": 1.1867,
      "step": 180
    },
    {
      "epoch": 0.011505303722537842,
      "grad_norm": 0.24195295572280884,
      "learning_rate": 0.0001797748794866681,
      "loss": 1.3789,
      "step": 181
    },
    {
      "epoch": 0.011568868936474514,
      "grad_norm": 0.23893454670906067,
      "learning_rate": 0.00017954607379166,
      "loss": 1.2436,
      "step": 182
    },
    {
      "epoch": 0.011632434150411188,
      "grad_norm": 0.23289944231510162,
      "learning_rate": 0.00017931612847211614,
      "loss": 1.2716,
      "step": 183
    },
    {
      "epoch": 0.011695999364347861,
      "grad_norm": 0.23664525151252747,
      "learning_rate": 0.00017908504682237047,
      "loss": 1.2751,
      "step": 184
    },
    {
      "epoch": 0.011759564578284533,
      "grad_norm": 0.22646844387054443,
      "learning_rate": 0.0001788528321530366,
      "loss": 1.2692,
      "step": 185
    },
    {
      "epoch": 0.011823129792221207,
      "grad_norm": 0.23897014558315277,
      "learning_rate": 0.00017861948779096046,
      "loss": 1.2104,
      "step": 186
    },
    {
      "epoch": 0.01188669500615788,
      "grad_norm": 0.2374998778104782,
      "learning_rate": 0.00017838501707917277,
      "loss": 1.3326,
      "step": 187
    },
    {
      "epoch": 0.011950260220094553,
      "grad_norm": 0.23287327587604523,
      "learning_rate": 0.0001781494233768408,
      "loss": 1.2739,
      "step": 188
    },
    {
      "epoch": 0.012013825434031226,
      "grad_norm": 0.25094935297966003,
      "learning_rate": 0.00017791271005922066,
      "loss": 1.3138,
      "step": 189
    },
    {
      "epoch": 0.0120773906479679,
      "grad_norm": 0.24589940905570984,
      "learning_rate": 0.00017767488051760857,
      "loss": 1.2747,
      "step": 190
    },
    {
      "epoch": 0.012140955861904572,
      "grad_norm": 0.22110210359096527,
      "learning_rate": 0.0001774359381592925,
      "loss": 1.2751,
      "step": 191
    },
    {
      "epoch": 0.012204521075841246,
      "grad_norm": 0.25095194578170776,
      "learning_rate": 0.00017719588640750336,
      "loss": 1.25,
      "step": 192
    },
    {
      "epoch": 0.01226808628977792,
      "grad_norm": 0.2439023107290268,
      "learning_rate": 0.00017695472870136577,
      "loss": 1.1904,
      "step": 193
    },
    {
      "epoch": 0.012331651503714592,
      "grad_norm": 0.2421332150697708,
      "learning_rate": 0.00017671246849584903,
      "loss": 1.2793,
      "step": 194
    },
    {
      "epoch": 0.012395216717651265,
      "grad_norm": 0.23399034142494202,
      "learning_rate": 0.00017646910926171747,
      "loss": 1.2824,
      "step": 195
    },
    {
      "epoch": 0.012458781931587939,
      "grad_norm": 0.22972531616687775,
      "learning_rate": 0.0001762246544854807,
      "loss": 1.1848,
      "step": 196
    },
    {
      "epoch": 0.012522347145524611,
      "grad_norm": 0.22563257813453674,
      "learning_rate": 0.00017597910766934378,
      "loss": 1.2338,
      "step": 197
    },
    {
      "epoch": 0.012585912359461285,
      "grad_norm": 0.24203820526599884,
      "learning_rate": 0.00017573247233115694,
      "loss": 1.2555,
      "step": 198
    },
    {
      "epoch": 0.012649477573397959,
      "grad_norm": 0.2555934488773346,
      "learning_rate": 0.00017548475200436533,
      "loss": 1.3626,
      "step": 199
    },
    {
      "epoch": 0.01271304278733463,
      "grad_norm": 0.2504107356071472,
      "learning_rate": 0.00017523595023795813,
      "loss": 1.3926,
      "step": 200
    },
    {
      "epoch": 0.01271304278733463,
      "eval_loss": 1.2624019384384155,
      "eval_runtime": 1240.3941,
      "eval_samples_per_second": 4.031,
      "eval_steps_per_second": 1.008,
      "step": 200
    },
    {
      "epoch": 0.012776608001271304,
      "grad_norm": 0.24385319650173187,
      "learning_rate": 0.00017498607059641806,
      "loss": 1.3571,
      "step": 201
    },
    {
      "epoch": 0.012840173215207978,
      "grad_norm": 0.22875139117240906,
      "learning_rate": 0.00017473511665966993,
      "loss": 1.1978,
      "step": 202
    },
    {
      "epoch": 0.01290373842914465,
      "grad_norm": 0.23931051790714264,
      "learning_rate": 0.00017448309202302968,
      "loss": 1.2109,
      "step": 203
    },
    {
      "epoch": 0.012967303643081324,
      "grad_norm": 0.24745705723762512,
      "learning_rate": 0.00017423000029715267,
      "loss": 1.2498,
      "step": 204
    },
    {
      "epoch": 0.013030868857017998,
      "grad_norm": 0.2564117908477783,
      "learning_rate": 0.0001739758451079821,
      "loss": 1.3109,
      "step": 205
    },
    {
      "epoch": 0.01309443407095467,
      "grad_norm": 0.23329947888851166,
      "learning_rate": 0.00017372063009669686,
      "loss": 1.2075,
      "step": 206
    },
    {
      "epoch": 0.013157999284891343,
      "grad_norm": 0.25186190009117126,
      "learning_rate": 0.00017346435891965956,
      "loss": 1.3316,
      "step": 207
    },
    {
      "epoch": 0.013221564498828017,
      "grad_norm": 0.24167706072330475,
      "learning_rate": 0.00017320703524836405,
      "loss": 1.2435,
      "step": 208
    },
    {
      "epoch": 0.013285129712764689,
      "grad_norm": 0.24145130813121796,
      "learning_rate": 0.00017294866276938288,
      "loss": 1.2089,
      "step": 209
    },
    {
      "epoch": 0.013348694926701363,
      "grad_norm": 0.23003919422626495,
      "learning_rate": 0.00017268924518431438,
      "loss": 1.2861,
      "step": 210
    },
    {
      "epoch": 0.013412260140638036,
      "grad_norm": 0.2578867971897125,
      "learning_rate": 0.00017242878620972972,
      "loss": 1.2853,
      "step": 211
    },
    {
      "epoch": 0.013475825354574708,
      "grad_norm": 0.2372393161058426,
      "learning_rate": 0.00017216728957711967,
      "loss": 1.2119,
      "step": 212
    },
    {
      "epoch": 0.013539390568511382,
      "grad_norm": 0.2317056953907013,
      "learning_rate": 0.0001719047590328411,
      "loss": 1.2229,
      "step": 213
    },
    {
      "epoch": 0.013602955782448056,
      "grad_norm": 0.24721965193748474,
      "learning_rate": 0.0001716411983380632,
      "loss": 1.3942,
      "step": 214
    },
    {
      "epoch": 0.013666520996384728,
      "grad_norm": 0.2334171086549759,
      "learning_rate": 0.0001713766112687139,
      "loss": 1.2808,
      "step": 215
    },
    {
      "epoch": 0.013730086210321402,
      "grad_norm": 0.23908108472824097,
      "learning_rate": 0.00017111100161542545,
      "loss": 1.2997,
      "step": 216
    },
    {
      "epoch": 0.013793651424258075,
      "grad_norm": 0.23297281563282013,
      "learning_rate": 0.00017084437318348034,
      "loss": 1.2322,
      "step": 217
    },
    {
      "epoch": 0.013857216638194747,
      "grad_norm": 0.23927763104438782,
      "learning_rate": 0.00017057672979275656,
      "loss": 1.2686,
      "step": 218
    },
    {
      "epoch": 0.013920781852131421,
      "grad_norm": 0.24085508286952972,
      "learning_rate": 0.00017030807527767318,
      "loss": 1.279,
      "step": 219
    },
    {
      "epoch": 0.013984347066068095,
      "grad_norm": 0.24235960841178894,
      "learning_rate": 0.0001700384134871351,
      "loss": 1.2663,
      "step": 220
    },
    {
      "epoch": 0.014047912280004767,
      "grad_norm": 0.23297156393527985,
      "learning_rate": 0.00016976774828447808,
      "loss": 1.3186,
      "step": 221
    },
    {
      "epoch": 0.01411147749394144,
      "grad_norm": 0.23962871730327606,
      "learning_rate": 0.0001694960835474134,
      "loss": 1.3278,
      "step": 222
    },
    {
      "epoch": 0.014175042707878114,
      "grad_norm": 0.23609745502471924,
      "learning_rate": 0.00016922342316797224,
      "loss": 1.2402,
      "step": 223
    },
    {
      "epoch": 0.014238607921814786,
      "grad_norm": 0.23808908462524414,
      "learning_rate": 0.00016894977105244997,
      "loss": 1.179,
      "step": 224
    },
    {
      "epoch": 0.01430217313575146,
      "grad_norm": 0.253446102142334,
      "learning_rate": 0.00016867513112135013,
      "loss": 1.1718,
      "step": 225
    },
    {
      "epoch": 0.014365738349688134,
      "grad_norm": 0.2394704669713974,
      "learning_rate": 0.0001683995073093283,
      "loss": 1.3013,
      "step": 226
    },
    {
      "epoch": 0.014429303563624806,
      "grad_norm": 0.2568953335285187,
      "learning_rate": 0.00016812290356513576,
      "loss": 1.3447,
      "step": 227
    },
    {
      "epoch": 0.01449286877756148,
      "grad_norm": 0.24280501902103424,
      "learning_rate": 0.00016784532385156285,
      "loss": 1.1629,
      "step": 228
    },
    {
      "epoch": 0.014556433991498153,
      "grad_norm": 0.24458537995815277,
      "learning_rate": 0.0001675667721453822,
      "loss": 1.3059,
      "step": 229
    },
    {
      "epoch": 0.014619999205434825,
      "grad_norm": 0.2558242082595825,
      "learning_rate": 0.0001672872524372919,
      "loss": 1.2409,
      "step": 230
    },
    {
      "epoch": 0.014683564419371499,
      "grad_norm": 0.2413797229528427,
      "learning_rate": 0.0001670067687318581,
      "loss": 1.1722,
      "step": 231
    },
    {
      "epoch": 0.014747129633308173,
      "grad_norm": 0.23881018161773682,
      "learning_rate": 0.00016672532504745778,
      "loss": 1.2605,
      "step": 232
    },
    {
      "epoch": 0.014810694847244845,
      "grad_norm": 0.2394268959760666,
      "learning_rate": 0.00016644292541622118,
      "loss": 1.3001,
      "step": 233
    },
    {
      "epoch": 0.014874260061181518,
      "grad_norm": 0.2380480170249939,
      "learning_rate": 0.00016615957388397399,
      "loss": 1.2341,
      "step": 234
    },
    {
      "epoch": 0.014937825275118192,
      "grad_norm": 0.25071921944618225,
      "learning_rate": 0.00016587527451017938,
      "loss": 1.2613,
      "step": 235
    },
    {
      "epoch": 0.015001390489054864,
      "grad_norm": 0.24680428206920624,
      "learning_rate": 0.00016559003136787988,
      "loss": 1.1784,
      "step": 236
    },
    {
      "epoch": 0.015064955702991538,
      "grad_norm": 0.23283323645591736,
      "learning_rate": 0.00016530384854363908,
      "loss": 1.2108,
      "step": 237
    },
    {
      "epoch": 0.015128520916928212,
      "grad_norm": 0.25436681509017944,
      "learning_rate": 0.00016501673013748284,
      "loss": 1.2712,
      "step": 238
    },
    {
      "epoch": 0.015192086130864884,
      "grad_norm": 0.24940147995948792,
      "learning_rate": 0.0001647286802628409,
      "loss": 1.3073,
      "step": 239
    },
    {
      "epoch": 0.015255651344801557,
      "grad_norm": 0.24033071100711823,
      "learning_rate": 0.0001644397030464877,
      "loss": 1.2888,
      "step": 240
    },
    {
      "epoch": 0.015319216558738231,
      "grad_norm": 0.2522200047969818,
      "learning_rate": 0.00016414980262848333,
      "loss": 1.3287,
      "step": 241
    },
    {
      "epoch": 0.015382781772674903,
      "grad_norm": 0.24863417446613312,
      "learning_rate": 0.00016385898316211426,
      "loss": 1.3074,
      "step": 242
    },
    {
      "epoch": 0.015446346986611577,
      "grad_norm": 0.2419770359992981,
      "learning_rate": 0.0001635672488138337,
      "loss": 1.22,
      "step": 243
    },
    {
      "epoch": 0.01550991220054825,
      "grad_norm": 0.24712932109832764,
      "learning_rate": 0.0001632746037632021,
      "loss": 1.1722,
      "step": 244
    },
    {
      "epoch": 0.015573477414484923,
      "grad_norm": 0.2783099412918091,
      "learning_rate": 0.00016298105220282713,
      "loss": 1.2831,
      "step": 245
    },
    {
      "epoch": 0.015637042628421596,
      "grad_norm": 0.24741223454475403,
      "learning_rate": 0.00016268659833830367,
      "loss": 1.2515,
      "step": 246
    },
    {
      "epoch": 0.01570060784235827,
      "grad_norm": 0.23735453188419342,
      "learning_rate": 0.00016239124638815357,
      "loss": 1.3524,
      "step": 247
    },
    {
      "epoch": 0.015764173056294944,
      "grad_norm": 0.24380360543727875,
      "learning_rate": 0.00016209500058376515,
      "loss": 1.3111,
      "step": 248
    },
    {
      "epoch": 0.015827738270231616,
      "grad_norm": 0.2466178685426712,
      "learning_rate": 0.00016179786516933264,
      "loss": 1.212,
      "step": 249
    },
    {
      "epoch": 0.015891303484168288,
      "grad_norm": 0.2434193640947342,
      "learning_rate": 0.00016149984440179537,
      "loss": 1.271,
      "step": 250
    },
    {
      "epoch": 0.015954868698104963,
      "grad_norm": 0.23572176694869995,
      "learning_rate": 0.0001612009425507767,
      "loss": 1.2519,
      "step": 251
    },
    {
      "epoch": 0.016018433912041635,
      "grad_norm": 0.25842970609664917,
      "learning_rate": 0.00016090116389852306,
      "loss": 1.2756,
      "step": 252
    },
    {
      "epoch": 0.016081999125978307,
      "grad_norm": 0.24664999544620514,
      "learning_rate": 0.00016060051273984226,
      "loss": 1.3055,
      "step": 253
    },
    {
      "epoch": 0.016145564339914983,
      "grad_norm": 0.2308342307806015,
      "learning_rate": 0.00016029899338204233,
      "loss": 1.2021,
      "step": 254
    },
    {
      "epoch": 0.016209129553851655,
      "grad_norm": 0.2438189834356308,
      "learning_rate": 0.00015999661014486956,
      "loss": 1.2889,
      "step": 255
    },
    {
      "epoch": 0.016272694767788327,
      "grad_norm": 0.25176259875297546,
      "learning_rate": 0.0001596933673604467,
      "loss": 1.2601,
      "step": 256
    },
    {
      "epoch": 0.016336259981725002,
      "grad_norm": 0.2458602339029312,
      "learning_rate": 0.0001593892693732109,
      "loss": 1.2662,
      "step": 257
    },
    {
      "epoch": 0.016399825195661674,
      "grad_norm": 0.2469761073589325,
      "learning_rate": 0.00015908432053985143,
      "loss": 1.2756,
      "step": 258
    },
    {
      "epoch": 0.016463390409598346,
      "grad_norm": 0.24446940422058105,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.2768,
      "step": 259
    },
    {
      "epoch": 0.01652695562353502,
      "grad_norm": 0.23439179360866547,
      "learning_rate": 0.0001584718878224047,
      "loss": 1.2613,
      "step": 260
    },
    {
      "epoch": 0.016590520837471694,
      "grad_norm": 0.2435050904750824,
      "learning_rate": 0.00015816441271239415,
      "loss": 1.1588,
      "step": 261
    },
    {
      "epoch": 0.016654086051408366,
      "grad_norm": 0.24683699011802673,
      "learning_rate": 0.00015785610430428762,
      "loss": 1.2775,
      "step": 262
    },
    {
      "epoch": 0.01671765126534504,
      "grad_norm": 0.24520638585090637,
      "learning_rate": 0.00015754696701509533,
      "loss": 1.2367,
      "step": 263
    },
    {
      "epoch": 0.016781216479281713,
      "grad_norm": 0.24515977501869202,
      "learning_rate": 0.00015723700527370268,
      "loss": 1.3044,
      "step": 264
    },
    {
      "epoch": 0.016844781693218385,
      "grad_norm": 0.23757795989513397,
      "learning_rate": 0.00015692622352080662,
      "loss": 1.2438,
      "step": 265
    },
    {
      "epoch": 0.01690834690715506,
      "grad_norm": 0.23741991817951202,
      "learning_rate": 0.00015661462620885199,
      "loss": 1.2141,
      "step": 266
    },
    {
      "epoch": 0.016971912121091733,
      "grad_norm": 0.2564014494419098,
      "learning_rate": 0.00015630221780196793,
      "loss": 1.2862,
      "step": 267
    },
    {
      "epoch": 0.017035477335028405,
      "grad_norm": 0.24640651047229767,
      "learning_rate": 0.0001559890027759037,
      "loss": 1.3254,
      "step": 268
    },
    {
      "epoch": 0.01709904254896508,
      "grad_norm": 0.24048472940921783,
      "learning_rate": 0.0001556749856179648,
      "loss": 1.2562,
      "step": 269
    },
    {
      "epoch": 0.017162607762901752,
      "grad_norm": 0.24159260094165802,
      "learning_rate": 0.00015536017082694846,
      "loss": 1.1149,
      "step": 270
    },
    {
      "epoch": 0.017226172976838424,
      "grad_norm": 0.2385244071483612,
      "learning_rate": 0.00015504456291307928,
      "loss": 1.1802,
      "step": 271
    },
    {
      "epoch": 0.0172897381907751,
      "grad_norm": 0.2397131323814392,
      "learning_rate": 0.0001547281663979446,
      "loss": 1.1722,
      "step": 272
    },
    {
      "epoch": 0.01735330340471177,
      "grad_norm": 0.24814891815185547,
      "learning_rate": 0.0001544109858144298,
      "loss": 1.2578,
      "step": 273
    },
    {
      "epoch": 0.017416868618648444,
      "grad_norm": 0.2575724124908447,
      "learning_rate": 0.00015409302570665325,
      "loss": 1.2823,
      "step": 274
    },
    {
      "epoch": 0.01748043383258512,
      "grad_norm": 0.2540719211101532,
      "learning_rate": 0.00015377429062990122,
      "loss": 1.2979,
      "step": 275
    },
    {
      "epoch": 0.01754399904652179,
      "grad_norm": 0.24557684361934662,
      "learning_rate": 0.00015345478515056267,
      "loss": 1.3124,
      "step": 276
    },
    {
      "epoch": 0.017607564260458463,
      "grad_norm": 0.24520032107830048,
      "learning_rate": 0.0001531345138460639,
      "loss": 1.2435,
      "step": 277
    },
    {
      "epoch": 0.01767112947439514,
      "grad_norm": 0.24698208272457123,
      "learning_rate": 0.00015281348130480272,
      "loss": 1.1623,
      "step": 278
    },
    {
      "epoch": 0.01773469468833181,
      "grad_norm": 0.2547725439071655,
      "learning_rate": 0.00015249169212608294,
      "loss": 1.2966,
      "step": 279
    },
    {
      "epoch": 0.017798259902268482,
      "grad_norm": 0.24341244995594025,
      "learning_rate": 0.00015216915092004847,
      "loss": 1.3736,
      "step": 280
    },
    {
      "epoch": 0.017861825116205158,
      "grad_norm": 0.2434585839509964,
      "learning_rate": 0.0001518458623076171,
      "loss": 1.285,
      "step": 281
    },
    {
      "epoch": 0.01792539033014183,
      "grad_norm": 0.2521164119243622,
      "learning_rate": 0.0001515218309204145,
      "loss": 1.2666,
      "step": 282
    },
    {
      "epoch": 0.017988955544078502,
      "grad_norm": 0.23752371966838837,
      "learning_rate": 0.00015119706140070778,
      "loss": 1.1804,
      "step": 283
    },
    {
      "epoch": 0.018052520758015177,
      "grad_norm": 0.2338380366563797,
      "learning_rate": 0.00015087155840133888,
      "loss": 1.2849,
      "step": 284
    },
    {
      "epoch": 0.01811608597195185,
      "grad_norm": 0.24568547308444977,
      "learning_rate": 0.0001505453265856581,
      "loss": 1.3278,
      "step": 285
    },
    {
      "epoch": 0.01817965118588852,
      "grad_norm": 0.24116171896457672,
      "learning_rate": 0.00015021837062745714,
      "loss": 1.1844,
      "step": 286
    },
    {
      "epoch": 0.018243216399825197,
      "grad_norm": 0.23728054761886597,
      "learning_rate": 0.00014989069521090226,
      "loss": 1.1546,
      "step": 287
    },
    {
      "epoch": 0.01830678161376187,
      "grad_norm": 0.24119961261749268,
      "learning_rate": 0.00014956230503046703,
      "loss": 1.1987,
      "step": 288
    },
    {
      "epoch": 0.01837034682769854,
      "grad_norm": 0.24379144608974457,
      "learning_rate": 0.00014923320479086523,
      "loss": 1.2073,
      "step": 289
    },
    {
      "epoch": 0.018433912041635216,
      "grad_norm": 0.2407054901123047,
      "learning_rate": 0.00014890339920698334,
      "loss": 1.2317,
      "step": 290
    },
    {
      "epoch": 0.01849747725557189,
      "grad_norm": 0.22647134959697723,
      "learning_rate": 0.000148572893003813,
      "loss": 1.1869,
      "step": 291
    },
    {
      "epoch": 0.01856104246950856,
      "grad_norm": 0.24462617933750153,
      "learning_rate": 0.00014824169091638337,
      "loss": 1.1895,
      "step": 292
    },
    {
      "epoch": 0.018624607683445236,
      "grad_norm": 0.24606405198574066,
      "learning_rate": 0.0001479097976896933,
      "loss": 1.3085,
      "step": 293
    },
    {
      "epoch": 0.018688172897381908,
      "grad_norm": 0.24407516419887543,
      "learning_rate": 0.00014757721807864317,
      "loss": 1.2148,
      "step": 294
    },
    {
      "epoch": 0.01875173811131858,
      "grad_norm": 0.24692152440547943,
      "learning_rate": 0.0001472439568479671,
      "loss": 1.2923,
      "step": 295
    },
    {
      "epoch": 0.018815303325255255,
      "grad_norm": 0.2552792429924011,
      "learning_rate": 0.0001469100187721644,
      "loss": 1.3185,
      "step": 296
    },
    {
      "epoch": 0.018878868539191927,
      "grad_norm": 0.24867340922355652,
      "learning_rate": 0.0001465754086354312,
      "loss": 1.2277,
      "step": 297
    },
    {
      "epoch": 0.0189424337531286,
      "grad_norm": 0.2612234354019165,
      "learning_rate": 0.0001462401312315922,
      "loss": 1.1123,
      "step": 298
    },
    {
      "epoch": 0.019005998967065275,
      "grad_norm": 0.24172838032245636,
      "learning_rate": 0.00014590419136403148,
      "loss": 1.384,
      "step": 299
    },
    {
      "epoch": 0.019069564181001947,
      "grad_norm": 0.25088098645210266,
      "learning_rate": 0.00014556759384562416,
      "loss": 1.2406,
      "step": 300
    },
    {
      "epoch": 0.019069564181001947,
      "eval_loss": 1.2426228523254395,
      "eval_runtime": 1240.5903,
      "eval_samples_per_second": 4.03,
      "eval_steps_per_second": 1.008,
      "step": 300
    },
    {
      "epoch": 0.01913312939493862,
      "grad_norm": 0.24052245914936066,
      "learning_rate": 0.00014523034349866724,
      "loss": 1.1181,
      "step": 301
    },
    {
      "epoch": 0.019196694608875294,
      "grad_norm": 0.24944396317005157,
      "learning_rate": 0.00014489244515481046,
      "loss": 1.2483,
      "step": 302
    },
    {
      "epoch": 0.019260259822811966,
      "grad_norm": 0.24091075360774994,
      "learning_rate": 0.00014455390365498722,
      "loss": 1.3159,
      "step": 303
    },
    {
      "epoch": 0.019323825036748638,
      "grad_norm": 0.23631052672863007,
      "learning_rate": 0.0001442147238493451,
      "loss": 1.2644,
      "step": 304
    },
    {
      "epoch": 0.019387390250685314,
      "grad_norm": 0.25283417105674744,
      "learning_rate": 0.00014387491059717652,
      "loss": 1.1845,
      "step": 305
    },
    {
      "epoch": 0.019450955464621986,
      "grad_norm": 0.24758540093898773,
      "learning_rate": 0.00014353446876684892,
      "loss": 1.1757,
      "step": 306
    },
    {
      "epoch": 0.019514520678558658,
      "grad_norm": 0.2573185861110687,
      "learning_rate": 0.00014319340323573518,
      "loss": 1.2536,
      "step": 307
    },
    {
      "epoch": 0.019578085892495333,
      "grad_norm": 0.25676408410072327,
      "learning_rate": 0.0001428517188901437,
      "loss": 1.2669,
      "step": 308
    },
    {
      "epoch": 0.019641651106432005,
      "grad_norm": 0.2364342361688614,
      "learning_rate": 0.00014250942062524834,
      "loss": 1.2699,
      "step": 309
    },
    {
      "epoch": 0.019705216320368677,
      "grad_norm": 0.24659450352191925,
      "learning_rate": 0.0001421665133450184,
      "loss": 1.2379,
      "step": 310
    },
    {
      "epoch": 0.019768781534305353,
      "grad_norm": 0.24497289955615997,
      "learning_rate": 0.00014182300196214829,
      "loss": 1.2435,
      "step": 311
    },
    {
      "epoch": 0.019832346748242025,
      "grad_norm": 0.2553839683532715,
      "learning_rate": 0.00014147889139798708,
      "loss": 1.264,
      "step": 312
    },
    {
      "epoch": 0.019895911962178697,
      "grad_norm": 0.2326495200395584,
      "learning_rate": 0.00014113418658246815,
      "loss": 1.2118,
      "step": 313
    },
    {
      "epoch": 0.019959477176115372,
      "grad_norm": 0.2362123280763626,
      "learning_rate": 0.00014078889245403844,
      "loss": 1.2604,
      "step": 314
    },
    {
      "epoch": 0.020023042390052044,
      "grad_norm": 0.24172857403755188,
      "learning_rate": 0.0001404430139595877,
      "loss": 1.2177,
      "step": 315
    },
    {
      "epoch": 0.020086607603988716,
      "grad_norm": 0.2595900595188141,
      "learning_rate": 0.0001400965560543778,
      "loss": 1.1845,
      "step": 316
    },
    {
      "epoch": 0.02015017281792539,
      "grad_norm": 0.2511995732784271,
      "learning_rate": 0.0001397495237019714,
      "loss": 1.2778,
      "step": 317
    },
    {
      "epoch": 0.020213738031862064,
      "grad_norm": 0.256143182516098,
      "learning_rate": 0.0001394019218741612,
      "loss": 1.1939,
      "step": 318
    },
    {
      "epoch": 0.020277303245798736,
      "grad_norm": 0.2604413330554962,
      "learning_rate": 0.00013905375555089844,
      "loss": 1.2582,
      "step": 319
    },
    {
      "epoch": 0.02034086845973541,
      "grad_norm": 0.24835054576396942,
      "learning_rate": 0.00013870502972022173,
      "loss": 1.2737,
      "step": 320
    },
    {
      "epoch": 0.020404433673672083,
      "grad_norm": 0.24885138869285583,
      "learning_rate": 0.00013835574937818543,
      "loss": 1.1771,
      "step": 321
    },
    {
      "epoch": 0.020467998887608755,
      "grad_norm": 0.24037449061870575,
      "learning_rate": 0.00013800591952878825,
      "loss": 1.11,
      "step": 322
    },
    {
      "epoch": 0.02053156410154543,
      "grad_norm": 0.24274124205112457,
      "learning_rate": 0.00013765554518390142,
      "loss": 1.2627,
      "step": 323
    },
    {
      "epoch": 0.020595129315482102,
      "grad_norm": 0.23798492550849915,
      "learning_rate": 0.00013730463136319692,
      "loss": 1.2339,
      "step": 324
    },
    {
      "epoch": 0.020658694529418774,
      "grad_norm": 0.24593910574913025,
      "learning_rate": 0.0001369531830940757,
      "loss": 1.2493,
      "step": 325
    },
    {
      "epoch": 0.02072225974335545,
      "grad_norm": 0.25841817259788513,
      "learning_rate": 0.00013660120541159537,
      "loss": 1.234,
      "step": 326
    },
    {
      "epoch": 0.020785824957292122,
      "grad_norm": 0.24712218344211578,
      "learning_rate": 0.00013624870335839835,
      "loss": 1.3844,
      "step": 327
    },
    {
      "epoch": 0.020849390171228794,
      "grad_norm": 0.25257477164268494,
      "learning_rate": 0.00013589568198463944,
      "loss": 1.2407,
      "step": 328
    },
    {
      "epoch": 0.02091295538516547,
      "grad_norm": 0.24789343774318695,
      "learning_rate": 0.00013554214634791358,
      "loss": 1.2008,
      "step": 329
    },
    {
      "epoch": 0.02097652059910214,
      "grad_norm": 0.2543022930622101,
      "learning_rate": 0.0001351881015131833,
      "loss": 1.2352,
      "step": 330
    },
    {
      "epoch": 0.021040085813038813,
      "grad_norm": 0.2460203766822815,
      "learning_rate": 0.00013483355255270634,
      "loss": 1.2062,
      "step": 331
    },
    {
      "epoch": 0.02110365102697549,
      "grad_norm": 0.25283366441726685,
      "learning_rate": 0.00013447850454596265,
      "loss": 1.2771,
      "step": 332
    },
    {
      "epoch": 0.02116721624091216,
      "grad_norm": 0.24133743345737457,
      "learning_rate": 0.0001341229625795819,
      "loss": 1.1678,
      "step": 333
    },
    {
      "epoch": 0.021230781454848833,
      "grad_norm": 0.2596588432788849,
      "learning_rate": 0.00013376693174727065,
      "loss": 1.293,
      "step": 334
    },
    {
      "epoch": 0.02129434666878551,
      "grad_norm": 0.23952282965183258,
      "learning_rate": 0.000133410417149739,
      "loss": 1.235,
      "step": 335
    },
    {
      "epoch": 0.02135791188272218,
      "grad_norm": 0.24762655794620514,
      "learning_rate": 0.00013305342389462792,
      "loss": 1.2907,
      "step": 336
    },
    {
      "epoch": 0.021421477096658852,
      "grad_norm": 0.2540108859539032,
      "learning_rate": 0.0001326959570964359,
      "loss": 1.2545,
      "step": 337
    },
    {
      "epoch": 0.021485042310595528,
      "grad_norm": 0.24914731085300446,
      "learning_rate": 0.00013233802187644566,
      "loss": 1.2428,
      "step": 338
    },
    {
      "epoch": 0.0215486075245322,
      "grad_norm": 0.24028116464614868,
      "learning_rate": 0.00013197962336265078,
      "loss": 1.2802,
      "step": 339
    },
    {
      "epoch": 0.021612172738468872,
      "grad_norm": 0.2514800727367401,
      "learning_rate": 0.0001316207666896824,
      "loss": 1.2193,
      "step": 340
    },
    {
      "epoch": 0.021675737952405547,
      "grad_norm": 0.24528062343597412,
      "learning_rate": 0.00013126145699873532,
      "loss": 1.3053,
      "step": 341
    },
    {
      "epoch": 0.02173930316634222,
      "grad_norm": 0.2537722587585449,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.0966,
      "step": 342
    },
    {
      "epoch": 0.02180286838027889,
      "grad_norm": 0.25322455167770386,
      "learning_rate": 0.00013054149916006218,
      "loss": 1.1693,
      "step": 343
    },
    {
      "epoch": 0.021866433594215567,
      "grad_norm": 0.2454894334077835,
      "learning_rate": 0.00013018086132688184,
      "loss": 1.1239,
      "step": 344
    },
    {
      "epoch": 0.02192999880815224,
      "grad_norm": 0.25263822078704834,
      "learning_rate": 0.00012981979110466654,
      "loss": 1.3322,
      "step": 345
    },
    {
      "epoch": 0.02199356402208891,
      "grad_norm": 0.2569487988948822,
      "learning_rate": 0.0001294582936663239,
      "loss": 1.2597,
      "step": 346
    },
    {
      "epoch": 0.022057129236025586,
      "grad_norm": 0.26036956906318665,
      "learning_rate": 0.00012909637419088193,
      "loss": 1.2215,
      "step": 347
    },
    {
      "epoch": 0.022120694449962258,
      "grad_norm": 0.24927780032157898,
      "learning_rate": 0.00012873403786341513,
      "loss": 1.2706,
      "step": 348
    },
    {
      "epoch": 0.02218425966389893,
      "grad_norm": 0.2510969340801239,
      "learning_rate": 0.00012837128987497,
      "loss": 1.2803,
      "step": 349
    },
    {
      "epoch": 0.022247824877835606,
      "grad_norm": 0.25289925932884216,
      "learning_rate": 0.00012800813542249072,
      "loss": 1.279,
      "step": 350
    },
    {
      "epoch": 0.022311390091772278,
      "grad_norm": 0.27076616883277893,
      "learning_rate": 0.00012764457970874474,
      "loss": 1.2417,
      "step": 351
    },
    {
      "epoch": 0.02237495530570895,
      "grad_norm": 0.25417760014533997,
      "learning_rate": 0.00012728062794224832,
      "loss": 1.2225,
      "step": 352
    },
    {
      "epoch": 0.022438520519645625,
      "grad_norm": 0.2544157803058624,
      "learning_rate": 0.00012691628533719162,
      "loss": 1.2485,
      "step": 353
    },
    {
      "epoch": 0.022502085733582297,
      "grad_norm": 0.24504055082798004,
      "learning_rate": 0.0001265515571133643,
      "loss": 1.213,
      "step": 354
    },
    {
      "epoch": 0.02256565094751897,
      "grad_norm": 0.24301055073738098,
      "learning_rate": 0.0001261864484960807,
      "loss": 1.3125,
      "step": 355
    },
    {
      "epoch": 0.022629216161455645,
      "grad_norm": 0.25097525119781494,
      "learning_rate": 0.00012582096471610467,
      "loss": 1.1494,
      "step": 356
    },
    {
      "epoch": 0.022692781375392317,
      "grad_norm": 0.24074026942253113,
      "learning_rate": 0.00012545511100957513,
      "loss": 1.2536,
      "step": 357
    },
    {
      "epoch": 0.02275634658932899,
      "grad_norm": 0.26268255710601807,
      "learning_rate": 0.00012508889261793059,
      "loss": 1.276,
      "step": 358
    },
    {
      "epoch": 0.022819911803265664,
      "grad_norm": 0.2453855574131012,
      "learning_rate": 0.00012472231478783432,
      "loss": 1.1745,
      "step": 359
    },
    {
      "epoch": 0.022883477017202336,
      "grad_norm": 0.25187695026397705,
      "learning_rate": 0.0001243553827710992,
      "loss": 1.2707,
      "step": 360
    },
    {
      "epoch": 0.022947042231139008,
      "grad_norm": 0.2632068991661072,
      "learning_rate": 0.00012398810182461228,
      "loss": 1.3185,
      "step": 361
    },
    {
      "epoch": 0.023010607445075684,
      "grad_norm": 0.24560274183750153,
      "learning_rate": 0.00012362047721025968,
      "loss": 1.1637,
      "step": 362
    },
    {
      "epoch": 0.023074172659012356,
      "grad_norm": 0.2577439546585083,
      "learning_rate": 0.00012325251419485102,
      "loss": 1.2254,
      "step": 363
    },
    {
      "epoch": 0.023137737872949028,
      "grad_norm": 0.24503523111343384,
      "learning_rate": 0.00012288421805004414,
      "loss": 1.2327,
      "step": 364
    },
    {
      "epoch": 0.023201303086885703,
      "grad_norm": 0.24148108065128326,
      "learning_rate": 0.00012251559405226941,
      "loss": 1.2588,
      "step": 365
    },
    {
      "epoch": 0.023264868300822375,
      "grad_norm": 0.24820099771022797,
      "learning_rate": 0.0001221466474826543,
      "loss": 1.1931,
      "step": 366
    },
    {
      "epoch": 0.023328433514759047,
      "grad_norm": 0.24834313988685608,
      "learning_rate": 0.00012177738362694757,
      "loss": 1.2426,
      "step": 367
    },
    {
      "epoch": 0.023391998728695722,
      "grad_norm": 0.24435977637767792,
      "learning_rate": 0.00012140780777544367,
      "loss": 1.3185,
      "step": 368
    },
    {
      "epoch": 0.023455563942632394,
      "grad_norm": 0.2529852092266083,
      "learning_rate": 0.00012103792522290682,
      "loss": 1.2934,
      "step": 369
    },
    {
      "epoch": 0.023519129156569066,
      "grad_norm": 0.2517044246196747,
      "learning_rate": 0.00012066774126849529,
      "loss": 1.1421,
      "step": 370
    },
    {
      "epoch": 0.023582694370505742,
      "grad_norm": 0.24829211831092834,
      "learning_rate": 0.00012029726121568541,
      "loss": 1.2096,
      "step": 371
    },
    {
      "epoch": 0.023646259584442414,
      "grad_norm": 0.25763294100761414,
      "learning_rate": 0.00011992649037219545,
      "loss": 1.253,
      "step": 372
    },
    {
      "epoch": 0.023709824798379086,
      "grad_norm": 0.2500714659690857,
      "learning_rate": 0.00011955543404990994,
      "loss": 1.2382,
      "step": 373
    },
    {
      "epoch": 0.02377339001231576,
      "grad_norm": 0.2516911029815674,
      "learning_rate": 0.0001191840975648032,
      "loss": 1.2695,
      "step": 374
    },
    {
      "epoch": 0.023836955226252433,
      "grad_norm": 0.2422354817390442,
      "learning_rate": 0.00011881248623686338,
      "loss": 1.1835,
      "step": 375
    },
    {
      "epoch": 0.023900520440189105,
      "grad_norm": 0.24256454408168793,
      "learning_rate": 0.00011844060539001618,
      "loss": 1.1847,
      "step": 376
    },
    {
      "epoch": 0.02396408565412578,
      "grad_norm": 0.24635834991931915,
      "learning_rate": 0.00011806846035204863,
      "loss": 1.1659,
      "step": 377
    },
    {
      "epoch": 0.024027650868062453,
      "grad_norm": 0.24487607181072235,
      "learning_rate": 0.00011769605645453265,
      "loss": 1.1742,
      "step": 378
    },
    {
      "epoch": 0.024091216081999125,
      "grad_norm": 0.24941600859165192,
      "learning_rate": 0.00011732339903274878,
      "loss": 1.272,
      "step": 379
    },
    {
      "epoch": 0.0241547812959358,
      "grad_norm": 0.251520037651062,
      "learning_rate": 0.00011695049342560968,
      "loss": 1.2567,
      "step": 380
    },
    {
      "epoch": 0.024218346509872472,
      "grad_norm": 0.24927428364753723,
      "learning_rate": 0.00011657734497558371,
      "loss": 1.2295,
      "step": 381
    },
    {
      "epoch": 0.024281911723809144,
      "grad_norm": 0.266940712928772,
      "learning_rate": 0.00011620395902861822,
      "loss": 1.2919,
      "step": 382
    },
    {
      "epoch": 0.02434547693774582,
      "grad_norm": 0.2506616711616516,
      "learning_rate": 0.00011583034093406327,
      "loss": 1.2859,
      "step": 383
    },
    {
      "epoch": 0.024409042151682492,
      "grad_norm": 0.24484044313430786,
      "learning_rate": 0.00011545649604459466,
      "loss": 1.2118,
      "step": 384
    },
    {
      "epoch": 0.024472607365619164,
      "grad_norm": 0.2639765441417694,
      "learning_rate": 0.00011508242971613741,
      "loss": 1.3253,
      "step": 385
    },
    {
      "epoch": 0.02453617257955584,
      "grad_norm": 0.257828950881958,
      "learning_rate": 0.00011470814730778905,
      "loss": 1.2582,
      "step": 386
    },
    {
      "epoch": 0.02459973779349251,
      "grad_norm": 0.26992151141166687,
      "learning_rate": 0.00011433365418174278,
      "loss": 1.3236,
      "step": 387
    },
    {
      "epoch": 0.024663303007429183,
      "grad_norm": 0.2564980387687683,
      "learning_rate": 0.00011395895570321064,
      "loss": 1.2659,
      "step": 388
    },
    {
      "epoch": 0.02472686822136586,
      "grad_norm": 0.2378605455160141,
      "learning_rate": 0.00011358405724034676,
      "loss": 1.2018,
      "step": 389
    },
    {
      "epoch": 0.02479043343530253,
      "grad_norm": 0.2514176070690155,
      "learning_rate": 0.00011320896416417026,
      "loss": 1.1897,
      "step": 390
    },
    {
      "epoch": 0.024853998649239203,
      "grad_norm": 0.24492673575878143,
      "learning_rate": 0.00011283368184848842,
      "loss": 1.2224,
      "step": 391
    },
    {
      "epoch": 0.024917563863175878,
      "grad_norm": 0.23529104888439178,
      "learning_rate": 0.00011245821566981976,
      "loss": 1.0588,
      "step": 392
    },
    {
      "epoch": 0.02498112907711255,
      "grad_norm": 0.25407955050468445,
      "learning_rate": 0.0001120825710073169,
      "loss": 1.3508,
      "step": 393
    },
    {
      "epoch": 0.025044694291049222,
      "grad_norm": 0.25098952651023865,
      "learning_rate": 0.00011170675324268942,
      "loss": 1.3079,
      "step": 394
    },
    {
      "epoch": 0.025108259504985898,
      "grad_norm": 0.2655404806137085,
      "learning_rate": 0.000111330767760127,
      "loss": 1.2383,
      "step": 395
    },
    {
      "epoch": 0.02517182471892257,
      "grad_norm": 0.2586209774017334,
      "learning_rate": 0.00011095461994622209,
      "loss": 1.2128,
      "step": 396
    },
    {
      "epoch": 0.02523538993285924,
      "grad_norm": 0.24864241480827332,
      "learning_rate": 0.0001105783151898928,
      "loss": 1.3113,
      "step": 397
    },
    {
      "epoch": 0.025298955146795917,
      "grad_norm": 0.24880805611610413,
      "learning_rate": 0.00011020185888230571,
      "loss": 1.263,
      "step": 398
    },
    {
      "epoch": 0.02536252036073259,
      "grad_norm": 0.2573794424533844,
      "learning_rate": 0.00010982525641679859,
      "loss": 1.2119,
      "step": 399
    },
    {
      "epoch": 0.02542608557466926,
      "grad_norm": 0.24325676262378693,
      "learning_rate": 0.00010944851318880314,
      "loss": 1.3042,
      "step": 400
    },
    {
      "epoch": 0.02542608557466926,
      "eval_loss": 1.2277675867080688,
      "eval_runtime": 1239.5038,
      "eval_samples_per_second": 4.034,
      "eval_steps_per_second": 1.008,
      "step": 400
    },
    {
      "epoch": 0.025489650788605937,
      "grad_norm": 0.2504250407218933,
      "learning_rate": 0.00010907163459576775,
      "loss": 1.1943,
      "step": 401
    },
    {
      "epoch": 0.02555321600254261,
      "grad_norm": 0.23995766043663025,
      "learning_rate": 0.00010869462603708011,
      "loss": 1.1737,
      "step": 402
    },
    {
      "epoch": 0.02561678121647928,
      "grad_norm": 0.2422688603401184,
      "learning_rate": 0.00010831749291398984,
      "loss": 1.1162,
      "step": 403
    },
    {
      "epoch": 0.025680346430415956,
      "grad_norm": 0.2618953287601471,
      "learning_rate": 0.00010794024062953123,
      "loss": 1.2612,
      "step": 404
    },
    {
      "epoch": 0.025743911644352628,
      "grad_norm": 0.2553127110004425,
      "learning_rate": 0.00010756287458844569,
      "loss": 1.2236,
      "step": 405
    },
    {
      "epoch": 0.0258074768582893,
      "grad_norm": 0.24291488528251648,
      "learning_rate": 0.00010718540019710432,
      "loss": 1.1694,
      "step": 406
    },
    {
      "epoch": 0.025871042072225976,
      "grad_norm": 0.25561729073524475,
      "learning_rate": 0.0001068078228634307,
      "loss": 1.224,
      "step": 407
    },
    {
      "epoch": 0.025934607286162648,
      "grad_norm": 0.25068506598472595,
      "learning_rate": 0.00010643014799682296,
      "loss": 1.2409,
      "step": 408
    },
    {
      "epoch": 0.02599817250009932,
      "grad_norm": 0.2648126482963562,
      "learning_rate": 0.00010605238100807673,
      "loss": 1.1836,
      "step": 409
    },
    {
      "epoch": 0.026061737714035995,
      "grad_norm": 0.2548812925815582,
      "learning_rate": 0.00010567452730930743,
      "loss": 1.2615,
      "step": 410
    },
    {
      "epoch": 0.026125302927972667,
      "grad_norm": 0.24808640778064728,
      "learning_rate": 0.00010529659231387263,
      "loss": 1.2308,
      "step": 411
    },
    {
      "epoch": 0.02618886814190934,
      "grad_norm": 0.25301888585090637,
      "learning_rate": 0.00010491858143629469,
      "loss": 1.2277,
      "step": 412
    },
    {
      "epoch": 0.026252433355846014,
      "grad_norm": 0.2523147761821747,
      "learning_rate": 0.00010454050009218313,
      "loss": 1.2519,
      "step": 413
    },
    {
      "epoch": 0.026315998569782686,
      "grad_norm": 0.2423991709947586,
      "learning_rate": 0.00010416235369815693,
      "loss": 1.211,
      "step": 414
    },
    {
      "epoch": 0.02637956378371936,
      "grad_norm": 0.24331238865852356,
      "learning_rate": 0.00010378414767176705,
      "loss": 1.1111,
      "step": 415
    },
    {
      "epoch": 0.026443128997656034,
      "grad_norm": 0.2526540756225586,
      "learning_rate": 0.00010340588743141879,
      "loss": 1.2619,
      "step": 416
    },
    {
      "epoch": 0.026506694211592706,
      "grad_norm": 0.23379378020763397,
      "learning_rate": 0.00010302757839629416,
      "loss": 1.2193,
      "step": 417
    },
    {
      "epoch": 0.026570259425529378,
      "grad_norm": 0.2350548952817917,
      "learning_rate": 0.00010264922598627418,
      "loss": 1.266,
      "step": 418
    },
    {
      "epoch": 0.026633824639466053,
      "grad_norm": 0.25372815132141113,
      "learning_rate": 0.00010227083562186135,
      "loss": 1.1881,
      "step": 419
    },
    {
      "epoch": 0.026697389853402725,
      "grad_norm": 0.26083245873451233,
      "learning_rate": 0.0001018924127241019,
      "loss": 1.1722,
      "step": 420
    },
    {
      "epoch": 0.026760955067339397,
      "grad_norm": 0.2449260652065277,
      "learning_rate": 0.00010151396271450817,
      "loss": 1.2495,
      "step": 421
    },
    {
      "epoch": 0.026824520281276073,
      "grad_norm": 0.2520759105682373,
      "learning_rate": 0.00010113549101498086,
      "loss": 1.0433,
      "step": 422
    },
    {
      "epoch": 0.026888085495212745,
      "grad_norm": 0.2503208518028259,
      "learning_rate": 0.00010075700304773148,
      "loss": 1.2593,
      "step": 423
    },
    {
      "epoch": 0.026951650709149417,
      "grad_norm": 0.25252294540405273,
      "learning_rate": 0.00010037850423520454,
      "loss": 1.2165,
      "step": 424
    },
    {
      "epoch": 0.027015215923086092,
      "grad_norm": 0.25652945041656494,
      "learning_rate": 0.0001,
      "loss": 1.3014,
      "step": 425
    },
    {
      "epoch": 0.027078781137022764,
      "grad_norm": 0.2584279775619507,
      "learning_rate": 9.962149576479545e-05,
      "loss": 1.2832,
      "step": 426
    },
    {
      "epoch": 0.027142346350959436,
      "grad_norm": 0.2617090344429016,
      "learning_rate": 9.924299695226857e-05,
      "loss": 1.2049,
      "step": 427
    },
    {
      "epoch": 0.027205911564896112,
      "grad_norm": 0.2533385157585144,
      "learning_rate": 9.886450898501917e-05,
      "loss": 1.2449,
      "step": 428
    },
    {
      "epoch": 0.027269476778832784,
      "grad_norm": 0.251128226518631,
      "learning_rate": 9.848603728549185e-05,
      "loss": 1.1209,
      "step": 429
    },
    {
      "epoch": 0.027333041992769456,
      "grad_norm": 0.256508469581604,
      "learning_rate": 9.810758727589813e-05,
      "loss": 1.2408,
      "step": 430
    },
    {
      "epoch": 0.02739660720670613,
      "grad_norm": 0.24774308502674103,
      "learning_rate": 9.772916437813868e-05,
      "loss": 1.2901,
      "step": 431
    },
    {
      "epoch": 0.027460172420642803,
      "grad_norm": 0.24494284391403198,
      "learning_rate": 9.735077401372583e-05,
      "loss": 1.2019,
      "step": 432
    },
    {
      "epoch": 0.027523737634579475,
      "grad_norm": 0.24128341674804688,
      "learning_rate": 9.697242160370589e-05,
      "loss": 1.196,
      "step": 433
    },
    {
      "epoch": 0.02758730284851615,
      "grad_norm": 0.24446694552898407,
      "learning_rate": 9.659411256858122e-05,
      "loss": 1.3256,
      "step": 434
    },
    {
      "epoch": 0.027650868062452823,
      "grad_norm": 0.22289952635765076,
      "learning_rate": 9.621585232823298e-05,
      "loss": 1.0862,
      "step": 435
    },
    {
      "epoch": 0.027714433276389495,
      "grad_norm": 0.25129738450050354,
      "learning_rate": 9.583764630184311e-05,
      "loss": 1.2579,
      "step": 436
    },
    {
      "epoch": 0.02777799849032617,
      "grad_norm": 0.25697946548461914,
      "learning_rate": 9.54594999078169e-05,
      "loss": 1.2646,
      "step": 437
    },
    {
      "epoch": 0.027841563704262842,
      "grad_norm": 0.2540769577026367,
      "learning_rate": 9.508141856370532e-05,
      "loss": 1.3544,
      "step": 438
    },
    {
      "epoch": 0.027905128918199514,
      "grad_norm": 0.24931739270687103,
      "learning_rate": 9.470340768612742e-05,
      "loss": 1.2314,
      "step": 439
    },
    {
      "epoch": 0.02796869413213619,
      "grad_norm": 0.25047457218170166,
      "learning_rate": 9.432547269069261e-05,
      "loss": 1.2619,
      "step": 440
    },
    {
      "epoch": 0.02803225934607286,
      "grad_norm": 0.24546508491039276,
      "learning_rate": 9.394761899192327e-05,
      "loss": 1.1973,
      "step": 441
    },
    {
      "epoch": 0.028095824560009534,
      "grad_norm": 0.25607752799987793,
      "learning_rate": 9.356985200317709e-05,
      "loss": 1.2323,
      "step": 442
    },
    {
      "epoch": 0.02815938977394621,
      "grad_norm": 0.2613637149333954,
      "learning_rate": 9.319217713656934e-05,
      "loss": 1.1984,
      "step": 443
    },
    {
      "epoch": 0.02822295498788288,
      "grad_norm": 0.24950894713401794,
      "learning_rate": 9.281459980289567e-05,
      "loss": 1.1618,
      "step": 444
    },
    {
      "epoch": 0.028286520201819553,
      "grad_norm": 0.24787862598896027,
      "learning_rate": 9.243712541155436e-05,
      "loss": 1.2381,
      "step": 445
    },
    {
      "epoch": 0.02835008541575623,
      "grad_norm": 0.2636643946170807,
      "learning_rate": 9.205975937046879e-05,
      "loss": 1.1979,
      "step": 446
    },
    {
      "epoch": 0.0284136506296929,
      "grad_norm": 0.25856512784957886,
      "learning_rate": 9.168250708601017e-05,
      "loss": 1.2338,
      "step": 447
    },
    {
      "epoch": 0.028477215843629573,
      "grad_norm": 0.2551221251487732,
      "learning_rate": 9.130537396291994e-05,
      "loss": 1.2167,
      "step": 448
    },
    {
      "epoch": 0.028540781057566248,
      "grad_norm": 0.26933833956718445,
      "learning_rate": 9.092836540423227e-05,
      "loss": 1.0898,
      "step": 449
    },
    {
      "epoch": 0.02860434627150292,
      "grad_norm": 0.2525901198387146,
      "learning_rate": 9.055148681119688e-05,
      "loss": 1.2945,
      "step": 450
    },
    {
      "epoch": 0.028667911485439592,
      "grad_norm": 0.25787627696990967,
      "learning_rate": 9.017474358320144e-05,
      "loss": 1.2626,
      "step": 451
    },
    {
      "epoch": 0.028731476699376268,
      "grad_norm": 0.25059428811073303,
      "learning_rate": 8.979814111769431e-05,
      "loss": 1.1074,
      "step": 452
    },
    {
      "epoch": 0.02879504191331294,
      "grad_norm": 0.2509251832962036,
      "learning_rate": 8.94216848101072e-05,
      "loss": 1.2628,
      "step": 453
    },
    {
      "epoch": 0.02885860712724961,
      "grad_norm": 0.26459380984306335,
      "learning_rate": 8.904538005377794e-05,
      "loss": 1.2641,
      "step": 454
    },
    {
      "epoch": 0.028922172341186287,
      "grad_norm": 0.2545078694820404,
      "learning_rate": 8.866923223987302e-05,
      "loss": 1.2532,
      "step": 455
    },
    {
      "epoch": 0.02898573755512296,
      "grad_norm": 0.269462525844574,
      "learning_rate": 8.829324675731059e-05,
      "loss": 1.1667,
      "step": 456
    },
    {
      "epoch": 0.02904930276905963,
      "grad_norm": 0.2679223418235779,
      "learning_rate": 8.791742899268315e-05,
      "loss": 1.3168,
      "step": 457
    },
    {
      "epoch": 0.029112867982996306,
      "grad_norm": 0.25728389620780945,
      "learning_rate": 8.754178433018025e-05,
      "loss": 1.1545,
      "step": 458
    },
    {
      "epoch": 0.02917643319693298,
      "grad_norm": 0.2632697820663452,
      "learning_rate": 8.716631815151158e-05,
      "loss": 1.2874,
      "step": 459
    },
    {
      "epoch": 0.02923999841086965,
      "grad_norm": 0.24366050958633423,
      "learning_rate": 8.679103583582979e-05,
      "loss": 1.2196,
      "step": 460
    },
    {
      "epoch": 0.029303563624806326,
      "grad_norm": 0.24694758653640747,
      "learning_rate": 8.641594275965327e-05,
      "loss": 1.1856,
      "step": 461
    },
    {
      "epoch": 0.029367128838742998,
      "grad_norm": 0.26368018984794617,
      "learning_rate": 8.604104429678935e-05,
      "loss": 1.2568,
      "step": 462
    },
    {
      "epoch": 0.02943069405267967,
      "grad_norm": 0.2524515390396118,
      "learning_rate": 8.566634581825727e-05,
      "loss": 1.2232,
      "step": 463
    },
    {
      "epoch": 0.029494259266616345,
      "grad_norm": 0.26754358410835266,
      "learning_rate": 8.529185269221097e-05,
      "loss": 1.1847,
      "step": 464
    },
    {
      "epoch": 0.029557824480553017,
      "grad_norm": 0.2522285282611847,
      "learning_rate": 8.491757028386263e-05,
      "loss": 1.1285,
      "step": 465
    },
    {
      "epoch": 0.02962138969448969,
      "grad_norm": 0.25777748227119446,
      "learning_rate": 8.45435039554054e-05,
      "loss": 1.2401,
      "step": 466
    },
    {
      "epoch": 0.029684954908426365,
      "grad_norm": 0.23897330462932587,
      "learning_rate": 8.416965906593675e-05,
      "loss": 1.1599,
      "step": 467
    },
    {
      "epoch": 0.029748520122363037,
      "grad_norm": 0.25694599747657776,
      "learning_rate": 8.379604097138179e-05,
      "loss": 1.1386,
      "step": 468
    },
    {
      "epoch": 0.02981208533629971,
      "grad_norm": 0.2588801980018616,
      "learning_rate": 8.342265502441636e-05,
      "loss": 1.2106,
      "step": 469
    },
    {
      "epoch": 0.029875650550236384,
      "grad_norm": 0.2556898593902588,
      "learning_rate": 8.304950657439033e-05,
      "loss": 1.2324,
      "step": 470
    },
    {
      "epoch": 0.029939215764173056,
      "grad_norm": 0.2549362778663635,
      "learning_rate": 8.267660096725123e-05,
      "loss": 1.253,
      "step": 471
    },
    {
      "epoch": 0.03000278097810973,
      "grad_norm": 0.24882453680038452,
      "learning_rate": 8.230394354546737e-05,
      "loss": 1.1547,
      "step": 472
    },
    {
      "epoch": 0.030066346192046404,
      "grad_norm": 0.25553610920906067,
      "learning_rate": 8.193153964795139e-05,
      "loss": 1.1983,
      "step": 473
    },
    {
      "epoch": 0.030129911405983076,
      "grad_norm": 0.2545006275177002,
      "learning_rate": 8.15593946099838e-05,
      "loss": 1.211,
      "step": 474
    },
    {
      "epoch": 0.030193476619919748,
      "grad_norm": 0.261358380317688,
      "learning_rate": 8.118751376313664e-05,
      "loss": 1.2255,
      "step": 475
    },
    {
      "epoch": 0.030257041833856423,
      "grad_norm": 0.24736320972442627,
      "learning_rate": 8.08159024351968e-05,
      "loss": 1.1618,
      "step": 476
    },
    {
      "epoch": 0.030320607047793095,
      "grad_norm": 0.2506306767463684,
      "learning_rate": 8.044456595009006e-05,
      "loss": 1.2803,
      "step": 477
    },
    {
      "epoch": 0.030384172261729767,
      "grad_norm": 0.25885093212127686,
      "learning_rate": 8.007350962780456e-05,
      "loss": 1.2624,
      "step": 478
    },
    {
      "epoch": 0.030447737475666443,
      "grad_norm": 0.26026806235313416,
      "learning_rate": 7.970273878431463e-05,
      "loss": 1.1407,
      "step": 479
    },
    {
      "epoch": 0.030511302689603115,
      "grad_norm": 0.24689649045467377,
      "learning_rate": 7.93322587315047e-05,
      "loss": 1.2858,
      "step": 480
    },
    {
      "epoch": 0.030574867903539787,
      "grad_norm": 0.24269208312034607,
      "learning_rate": 7.89620747770932e-05,
      "loss": 1.2273,
      "step": 481
    },
    {
      "epoch": 0.030638433117476462,
      "grad_norm": 0.2571215331554413,
      "learning_rate": 7.859219222455634e-05,
      "loss": 1.1898,
      "step": 482
    },
    {
      "epoch": 0.030701998331413134,
      "grad_norm": 0.24754567444324493,
      "learning_rate": 7.822261637305242e-05,
      "loss": 1.2594,
      "step": 483
    },
    {
      "epoch": 0.030765563545349806,
      "grad_norm": 0.2660878300666809,
      "learning_rate": 7.785335251734573e-05,
      "loss": 1.314,
      "step": 484
    },
    {
      "epoch": 0.03082912875928648,
      "grad_norm": 0.2501409351825714,
      "learning_rate": 7.74844059477306e-05,
      "loss": 1.1022,
      "step": 485
    },
    {
      "epoch": 0.030892693973223154,
      "grad_norm": 0.2525741755962372,
      "learning_rate": 7.711578194995589e-05,
      "loss": 1.27,
      "step": 486
    },
    {
      "epoch": 0.030956259187159826,
      "grad_norm": 0.25781622529029846,
      "learning_rate": 7.674748580514899e-05,
      "loss": 1.1116,
      "step": 487
    },
    {
      "epoch": 0.0310198244010965,
      "grad_norm": 0.2542114555835724,
      "learning_rate": 7.637952278974034e-05,
      "loss": 1.2904,
      "step": 488
    },
    {
      "epoch": 0.031083389615033173,
      "grad_norm": 0.25267302989959717,
      "learning_rate": 7.60118981753877e-05,
      "loss": 1.3022,
      "step": 489
    },
    {
      "epoch": 0.031146954828969845,
      "grad_norm": 0.27163398265838623,
      "learning_rate": 7.564461722890081e-05,
      "loss": 1.2724,
      "step": 490
    },
    {
      "epoch": 0.03121052004290652,
      "grad_norm": 0.25189656019210815,
      "learning_rate": 7.527768521216568e-05,
      "loss": 1.1929,
      "step": 491
    },
    {
      "epoch": 0.03127408525684319,
      "grad_norm": 0.24594004452228546,
      "learning_rate": 7.491110738206942e-05,
      "loss": 1.063,
      "step": 492
    },
    {
      "epoch": 0.03133765047077987,
      "grad_norm": 0.25397610664367676,
      "learning_rate": 7.45448889904249e-05,
      "loss": 1.2254,
      "step": 493
    },
    {
      "epoch": 0.03140121568471654,
      "grad_norm": 0.2588002383708954,
      "learning_rate": 7.417903528389534e-05,
      "loss": 1.187,
      "step": 494
    },
    {
      "epoch": 0.03146478089865321,
      "grad_norm": 0.2593894898891449,
      "learning_rate": 7.381355150391933e-05,
      "loss": 1.2026,
      "step": 495
    },
    {
      "epoch": 0.03152834611258989,
      "grad_norm": 0.2586647868156433,
      "learning_rate": 7.344844288663571e-05,
      "loss": 1.2351,
      "step": 496
    },
    {
      "epoch": 0.031591911326526556,
      "grad_norm": 0.25638607144355774,
      "learning_rate": 7.30837146628084e-05,
      "loss": 1.2891,
      "step": 497
    },
    {
      "epoch": 0.03165547654046323,
      "grad_norm": 0.26439526677131653,
      "learning_rate": 7.27193720577517e-05,
      "loss": 1.2405,
      "step": 498
    },
    {
      "epoch": 0.03171904175439991,
      "grad_norm": 0.26030415296554565,
      "learning_rate": 7.235542029125527e-05,
      "loss": 1.3782,
      "step": 499
    },
    {
      "epoch": 0.031782606968336576,
      "grad_norm": 0.26349353790283203,
      "learning_rate": 7.19918645775093e-05,
      "loss": 1.1462,
      "step": 500
    },
    {
      "epoch": 0.031782606968336576,
      "eval_loss": 1.2162970304489136,
      "eval_runtime": 1239.1136,
      "eval_samples_per_second": 4.035,
      "eval_steps_per_second": 1.009,
      "step": 500
    },
    {
      "epoch": 0.03184617218227325,
      "grad_norm": 0.26652681827545166,
      "learning_rate": 7.162871012503003e-05,
      "loss": 1.2841,
      "step": 501
    },
    {
      "epoch": 0.031909737396209926,
      "grad_norm": 0.258722722530365,
      "learning_rate": 7.126596213658488e-05,
      "loss": 1.3076,
      "step": 502
    },
    {
      "epoch": 0.031973302610146595,
      "grad_norm": 0.2519145607948303,
      "learning_rate": 7.090362580911808e-05,
      "loss": 1.3191,
      "step": 503
    },
    {
      "epoch": 0.03203686782408327,
      "grad_norm": 0.24408216774463654,
      "learning_rate": 7.05417063336761e-05,
      "loss": 1.2056,
      "step": 504
    },
    {
      "epoch": 0.032100433038019946,
      "grad_norm": 0.25859251618385315,
      "learning_rate": 7.018020889533348e-05,
      "loss": 1.2509,
      "step": 505
    },
    {
      "epoch": 0.032163998251956614,
      "grad_norm": 0.274295836687088,
      "learning_rate": 6.981913867311819e-05,
      "loss": 1.1457,
      "step": 506
    },
    {
      "epoch": 0.03222756346589329,
      "grad_norm": 0.25392991304397583,
      "learning_rate": 6.945850083993781e-05,
      "loss": 1.1389,
      "step": 507
    },
    {
      "epoch": 0.032291128679829965,
      "grad_norm": 0.2518613338470459,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.1288,
      "step": 508
    },
    {
      "epoch": 0.032354693893766634,
      "grad_norm": 0.25153687596321106,
      "learning_rate": 6.873854300126467e-05,
      "loss": 1.1106,
      "step": 509
    },
    {
      "epoch": 0.03241825910770331,
      "grad_norm": 0.2594717741012573,
      "learning_rate": 6.83792333103176e-05,
      "loss": 1.2556,
      "step": 510
    },
    {
      "epoch": 0.032481824321639985,
      "grad_norm": 0.2567812204360962,
      "learning_rate": 6.802037663734923e-05,
      "loss": 1.1773,
      "step": 511
    },
    {
      "epoch": 0.03254538953557665,
      "grad_norm": 0.2533416748046875,
      "learning_rate": 6.766197812355438e-05,
      "loss": 1.2053,
      "step": 512
    },
    {
      "epoch": 0.03260895474951333,
      "grad_norm": 0.2625131607055664,
      "learning_rate": 6.73040429035641e-05,
      "loss": 1.2467,
      "step": 513
    },
    {
      "epoch": 0.032672519963450004,
      "grad_norm": 0.2665756344795227,
      "learning_rate": 6.69465761053721e-05,
      "loss": 1.2737,
      "step": 514
    },
    {
      "epoch": 0.03273608517738667,
      "grad_norm": 0.2558302581310272,
      "learning_rate": 6.658958285026102e-05,
      "loss": 1.2684,
      "step": 515
    },
    {
      "epoch": 0.03279965039132335,
      "grad_norm": 0.24979649484157562,
      "learning_rate": 6.623306825272937e-05,
      "loss": 1.2144,
      "step": 516
    },
    {
      "epoch": 0.032863215605260024,
      "grad_norm": 0.25010988116264343,
      "learning_rate": 6.58770374204181e-05,
      "loss": 1.2679,
      "step": 517
    },
    {
      "epoch": 0.03292678081919669,
      "grad_norm": 0.2494756430387497,
      "learning_rate": 6.552149545403739e-05,
      "loss": 1.2291,
      "step": 518
    },
    {
      "epoch": 0.03299034603313337,
      "grad_norm": 0.2528434097766876,
      "learning_rate": 6.516644744729367e-05,
      "loss": 1.2519,
      "step": 519
    },
    {
      "epoch": 0.03305391124707004,
      "grad_norm": 0.2631024718284607,
      "learning_rate": 6.48118984868167e-05,
      "loss": 1.2086,
      "step": 520
    },
    {
      "epoch": 0.03311747646100671,
      "grad_norm": 0.2514025866985321,
      "learning_rate": 6.445785365208645e-05,
      "loss": 1.2098,
      "step": 521
    },
    {
      "epoch": 0.03318104167494339,
      "grad_norm": 0.25096845626831055,
      "learning_rate": 6.410431801536058e-05,
      "loss": 1.2062,
      "step": 522
    },
    {
      "epoch": 0.03324460688888006,
      "grad_norm": 0.24552412331104279,
      "learning_rate": 6.375129664160168e-05,
      "loss": 1.139,
      "step": 523
    },
    {
      "epoch": 0.03330817210281673,
      "grad_norm": 0.257235586643219,
      "learning_rate": 6.339879458840465e-05,
      "loss": 1.3102,
      "step": 524
    },
    {
      "epoch": 0.03337173731675341,
      "grad_norm": 0.24831882119178772,
      "learning_rate": 6.304681690592431e-05,
      "loss": 1.1848,
      "step": 525
    },
    {
      "epoch": 0.03343530253069008,
      "grad_norm": 0.2522595524787903,
      "learning_rate": 6.269536863680307e-05,
      "loss": 1.228,
      "step": 526
    },
    {
      "epoch": 0.03349886774462675,
      "grad_norm": 0.25006258487701416,
      "learning_rate": 6.23444548160986e-05,
      "loss": 1.1059,
      "step": 527
    },
    {
      "epoch": 0.033562432958563426,
      "grad_norm": 0.2498662769794464,
      "learning_rate": 6.199408047121174e-05,
      "loss": 1.2354,
      "step": 528
    },
    {
      "epoch": 0.0336259981725001,
      "grad_norm": 0.25638020038604736,
      "learning_rate": 6.16442506218146e-05,
      "loss": 1.2332,
      "step": 529
    },
    {
      "epoch": 0.03368956338643677,
      "grad_norm": 0.26172903180122375,
      "learning_rate": 6.129497027977829e-05,
      "loss": 1.2062,
      "step": 530
    },
    {
      "epoch": 0.033753128600373446,
      "grad_norm": 0.2451334148645401,
      "learning_rate": 6.0946244449101574e-05,
      "loss": 1.2513,
      "step": 531
    },
    {
      "epoch": 0.03381669381431012,
      "grad_norm": 0.2550620436668396,
      "learning_rate": 6.059807812583883e-05,
      "loss": 1.08,
      "step": 532
    },
    {
      "epoch": 0.03388025902824679,
      "grad_norm": 0.2467305064201355,
      "learning_rate": 6.02504762980286e-05,
      "loss": 1.1822,
      "step": 533
    },
    {
      "epoch": 0.033943824242183465,
      "grad_norm": 0.2539975345134735,
      "learning_rate": 5.990344394562226e-05,
      "loss": 1.2334,
      "step": 534
    },
    {
      "epoch": 0.03400738945612014,
      "grad_norm": 0.26874592900276184,
      "learning_rate": 5.955698604041231e-05,
      "loss": 1.2736,
      "step": 535
    },
    {
      "epoch": 0.03407095467005681,
      "grad_norm": 0.25802844762802124,
      "learning_rate": 5.92111075459616e-05,
      "loss": 1.1959,
      "step": 536
    },
    {
      "epoch": 0.034134519883993485,
      "grad_norm": 0.2507290542125702,
      "learning_rate": 5.88658134175319e-05,
      "loss": 1.2045,
      "step": 537
    },
    {
      "epoch": 0.03419808509793016,
      "grad_norm": 0.25168654322624207,
      "learning_rate": 5.852110860201294e-05,
      "loss": 1.259,
      "step": 538
    },
    {
      "epoch": 0.03426165031186683,
      "grad_norm": 0.25015729665756226,
      "learning_rate": 5.817699803785174e-05,
      "loss": 1.0865,
      "step": 539
    },
    {
      "epoch": 0.034325215525803504,
      "grad_norm": 0.24665945768356323,
      "learning_rate": 5.7833486654981606e-05,
      "loss": 1.1366,
      "step": 540
    },
    {
      "epoch": 0.03438878073974018,
      "grad_norm": 0.2521713972091675,
      "learning_rate": 5.7490579374751686e-05,
      "loss": 1.2052,
      "step": 541
    },
    {
      "epoch": 0.03445234595367685,
      "grad_norm": 0.24369041621685028,
      "learning_rate": 5.714828110985635e-05,
      "loss": 1.1564,
      "step": 542
    },
    {
      "epoch": 0.034515911167613524,
      "grad_norm": 0.2600708603858948,
      "learning_rate": 5.6806596764264874e-05,
      "loss": 1.1852,
      "step": 543
    },
    {
      "epoch": 0.0345794763815502,
      "grad_norm": 0.25693967938423157,
      "learning_rate": 5.6465531233151126e-05,
      "loss": 1.1887,
      "step": 544
    },
    {
      "epoch": 0.03464304159548687,
      "grad_norm": 0.24953435361385345,
      "learning_rate": 5.6125089402823485e-05,
      "loss": 1.0897,
      "step": 545
    },
    {
      "epoch": 0.03470660680942354,
      "grad_norm": 0.2587718665599823,
      "learning_rate": 5.578527615065492e-05,
      "loss": 1.1345,
      "step": 546
    },
    {
      "epoch": 0.03477017202336022,
      "grad_norm": 0.2567615807056427,
      "learning_rate": 5.544609634501279e-05,
      "loss": 1.277,
      "step": 547
    },
    {
      "epoch": 0.03483373723729689,
      "grad_norm": 0.25938692688941956,
      "learning_rate": 5.510755484518955e-05,
      "loss": 1.2087,
      "step": 548
    },
    {
      "epoch": 0.03489730245123356,
      "grad_norm": 0.25982430577278137,
      "learning_rate": 5.476965650133279e-05,
      "loss": 1.2554,
      "step": 549
    },
    {
      "epoch": 0.03496086766517024,
      "grad_norm": 0.25441205501556396,
      "learning_rate": 5.443240615437586e-05,
      "loss": 1.1437,
      "step": 550
    },
    {
      "epoch": 0.035024432879106907,
      "grad_norm": 0.2553006410598755,
      "learning_rate": 5.4095808635968546e-05,
      "loss": 1.2544,
      "step": 551
    },
    {
      "epoch": 0.03508799809304358,
      "grad_norm": 0.2520417273044586,
      "learning_rate": 5.375986876840784e-05,
      "loss": 1.0661,
      "step": 552
    },
    {
      "epoch": 0.03515156330698026,
      "grad_norm": 0.2597469091415405,
      "learning_rate": 5.342459136456881e-05,
      "loss": 1.1732,
      "step": 553
    },
    {
      "epoch": 0.035215128520916926,
      "grad_norm": 0.2597144544124603,
      "learning_rate": 5.30899812278356e-05,
      "loss": 1.2128,
      "step": 554
    },
    {
      "epoch": 0.0352786937348536,
      "grad_norm": 0.2565470039844513,
      "learning_rate": 5.275604315203293e-05,
      "loss": 1.1585,
      "step": 555
    },
    {
      "epoch": 0.03534225894879028,
      "grad_norm": 0.24314232170581818,
      "learning_rate": 5.2422781921356826e-05,
      "loss": 1.0955,
      "step": 556
    },
    {
      "epoch": 0.035405824162726945,
      "grad_norm": 0.24443262815475464,
      "learning_rate": 5.209020231030672e-05,
      "loss": 1.1649,
      "step": 557
    },
    {
      "epoch": 0.03546938937666362,
      "grad_norm": 0.26083680987358093,
      "learning_rate": 5.1758309083616673e-05,
      "loss": 1.2195,
      "step": 558
    },
    {
      "epoch": 0.035532954590600296,
      "grad_norm": 0.25181084871292114,
      "learning_rate": 5.142710699618701e-05,
      "loss": 1.2411,
      "step": 559
    },
    {
      "epoch": 0.035596519804536965,
      "grad_norm": 0.24913780391216278,
      "learning_rate": 5.109660079301668e-05,
      "loss": 1.2251,
      "step": 560
    },
    {
      "epoch": 0.03566008501847364,
      "grad_norm": 0.2578226625919342,
      "learning_rate": 5.076679520913479e-05,
      "loss": 1.1685,
      "step": 561
    },
    {
      "epoch": 0.035723650232410316,
      "grad_norm": 0.25115758180618286,
      "learning_rate": 5.043769496953299e-05,
      "loss": 1.0909,
      "step": 562
    },
    {
      "epoch": 0.035787215446346984,
      "grad_norm": 0.24539780616760254,
      "learning_rate": 5.010930478909779e-05,
      "loss": 1.221,
      "step": 563
    },
    {
      "epoch": 0.03585078066028366,
      "grad_norm": 0.26085364818573,
      "learning_rate": 4.9781629372542895e-05,
      "loss": 1.2141,
      "step": 564
    },
    {
      "epoch": 0.035914345874220335,
      "grad_norm": 0.25367042422294617,
      "learning_rate": 4.945467341434195e-05,
      "loss": 1.2999,
      "step": 565
    },
    {
      "epoch": 0.035977911088157004,
      "grad_norm": 0.27679672837257385,
      "learning_rate": 4.912844159866112e-05,
      "loss": 1.2494,
      "step": 566
    },
    {
      "epoch": 0.03604147630209368,
      "grad_norm": 0.2423914223909378,
      "learning_rate": 4.880293859929227e-05,
      "loss": 1.1681,
      "step": 567
    },
    {
      "epoch": 0.036105041516030355,
      "grad_norm": 0.24873730540275574,
      "learning_rate": 4.847816907958549e-05,
      "loss": 1.2964,
      "step": 568
    },
    {
      "epoch": 0.03616860672996702,
      "grad_norm": 0.2618268132209778,
      "learning_rate": 4.8154137692382907e-05,
      "loss": 1.2184,
      "step": 569
    },
    {
      "epoch": 0.0362321719439037,
      "grad_norm": 0.2559436857700348,
      "learning_rate": 4.783084907995156e-05,
      "loss": 1.216,
      "step": 570
    },
    {
      "epoch": 0.036295737157840374,
      "grad_norm": 0.2557474970817566,
      "learning_rate": 4.750830787391708e-05,
      "loss": 1.2993,
      "step": 571
    },
    {
      "epoch": 0.03635930237177704,
      "grad_norm": 0.25075972080230713,
      "learning_rate": 4.718651869519731e-05,
      "loss": 1.1178,
      "step": 572
    },
    {
      "epoch": 0.03642286758571372,
      "grad_norm": 0.2534898817539215,
      "learning_rate": 4.686548615393613e-05,
      "loss": 1.1891,
      "step": 573
    },
    {
      "epoch": 0.036486432799650394,
      "grad_norm": 0.26913774013519287,
      "learning_rate": 4.654521484943735e-05,
      "loss": 1.2552,
      "step": 574
    },
    {
      "epoch": 0.03654999801358706,
      "grad_norm": 0.2566869556903839,
      "learning_rate": 4.622570937009879e-05,
      "loss": 1.3527,
      "step": 575
    },
    {
      "epoch": 0.03661356322752374,
      "grad_norm": 0.26296791434288025,
      "learning_rate": 4.59069742933468e-05,
      "loss": 1.2464,
      "step": 576
    },
    {
      "epoch": 0.03667712844146041,
      "grad_norm": 0.261929988861084,
      "learning_rate": 4.558901418557021e-05,
      "loss": 1.2744,
      "step": 577
    },
    {
      "epoch": 0.03674069365539708,
      "grad_norm": 0.252572238445282,
      "learning_rate": 4.527183360205541e-05,
      "loss": 1.112,
      "step": 578
    },
    {
      "epoch": 0.03680425886933376,
      "grad_norm": 0.27232858538627625,
      "learning_rate": 4.495543708692075e-05,
      "loss": 1.2743,
      "step": 579
    },
    {
      "epoch": 0.03686782408327043,
      "grad_norm": 0.2609007656574249,
      "learning_rate": 4.4639829173051554e-05,
      "loss": 1.3188,
      "step": 580
    },
    {
      "epoch": 0.0369313892972071,
      "grad_norm": 0.2632231116294861,
      "learning_rate": 4.43250143820352e-05,
      "loss": 1.1243,
      "step": 581
    },
    {
      "epoch": 0.03699495451114378,
      "grad_norm": 0.2551668882369995,
      "learning_rate": 4.401099722409631e-05,
      "loss": 1.1864,
      "step": 582
    },
    {
      "epoch": 0.03705851972508045,
      "grad_norm": 0.2566946744918823,
      "learning_rate": 4.369778219803211e-05,
      "loss": 1.2117,
      "step": 583
    },
    {
      "epoch": 0.03712208493901712,
      "grad_norm": 0.2648017704486847,
      "learning_rate": 4.338537379114801e-05,
      "loss": 1.2357,
      "step": 584
    },
    {
      "epoch": 0.037185650152953796,
      "grad_norm": 0.24553461372852325,
      "learning_rate": 4.307377647919343e-05,
      "loss": 1.1774,
      "step": 585
    },
    {
      "epoch": 0.03724921536689047,
      "grad_norm": 0.24831490218639374,
      "learning_rate": 4.2762994726297346e-05,
      "loss": 1.1336,
      "step": 586
    },
    {
      "epoch": 0.03731278058082714,
      "grad_norm": 0.2644321024417877,
      "learning_rate": 4.245303298490467e-05,
      "loss": 1.1865,
      "step": 587
    },
    {
      "epoch": 0.037376345794763816,
      "grad_norm": 0.2654249370098114,
      "learning_rate": 4.2143895695712444e-05,
      "loss": 1.1872,
      "step": 588
    },
    {
      "epoch": 0.03743991100870049,
      "grad_norm": 0.24722780287265778,
      "learning_rate": 4.183558728760586e-05,
      "loss": 1.1609,
      "step": 589
    },
    {
      "epoch": 0.03750347622263716,
      "grad_norm": 0.2560960054397583,
      "learning_rate": 4.152811217759529e-05,
      "loss": 1.1897,
      "step": 590
    },
    {
      "epoch": 0.037567041436573835,
      "grad_norm": 0.24647943675518036,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.1098,
      "step": 591
    },
    {
      "epoch": 0.03763060665051051,
      "grad_norm": 0.2763408422470093,
      "learning_rate": 4.091567946014858e-05,
      "loss": 1.2313,
      "step": 592
    },
    {
      "epoch": 0.03769417186444718,
      "grad_norm": 0.254727303981781,
      "learning_rate": 4.061073062678912e-05,
      "loss": 1.2363,
      "step": 593
    },
    {
      "epoch": 0.037757737078383855,
      "grad_norm": 0.2722640037536621,
      "learning_rate": 4.0306632639553323e-05,
      "loss": 1.1633,
      "step": 594
    },
    {
      "epoch": 0.03782130229232053,
      "grad_norm": 0.2594556212425232,
      "learning_rate": 4.000338985513046e-05,
      "loss": 1.224,
      "step": 595
    },
    {
      "epoch": 0.0378848675062572,
      "grad_norm": 0.25068074464797974,
      "learning_rate": 3.970100661795766e-05,
      "loss": 1.1809,
      "step": 596
    },
    {
      "epoch": 0.037948432720193874,
      "grad_norm": 0.2550009787082672,
      "learning_rate": 3.9399487260157766e-05,
      "loss": 1.2022,
      "step": 597
    },
    {
      "epoch": 0.03801199793413055,
      "grad_norm": 0.2593897879123688,
      "learning_rate": 3.909883610147696e-05,
      "loss": 1.3124,
      "step": 598
    },
    {
      "epoch": 0.03807556314806722,
      "grad_norm": 0.2558402717113495,
      "learning_rate": 3.879905744922329e-05,
      "loss": 1.1618,
      "step": 599
    },
    {
      "epoch": 0.03813912836200389,
      "grad_norm": 0.25934746861457825,
      "learning_rate": 3.8500155598204644e-05,
      "loss": 1.0083,
      "step": 600
    },
    {
      "epoch": 0.03813912836200389,
      "eval_loss": 1.2089511156082153,
      "eval_runtime": 1239.249,
      "eval_samples_per_second": 4.035,
      "eval_steps_per_second": 1.009,
      "step": 600
    }
  ],
  "logging_steps": 1,
  "max_steps": 840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.117735147995136e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}