{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5003996802557954,
  "eval_steps": 313,
  "global_step": 626,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007993605115907274,
      "grad_norm": 0.9691409468650818,
      "learning_rate": 2e-05,
      "loss": 1.579,
      "step": 1
    },
    {
      "epoch": 0.0015987210231814548,
      "grad_norm": 1.4015984535217285,
      "learning_rate": 4e-05,
      "loss": 1.6108,
      "step": 2
    },
    {
      "epoch": 0.002398081534772182,
      "grad_norm": 1.4863674640655518,
      "learning_rate": 6e-05,
      "loss": 1.5698,
      "step": 3
    },
    {
      "epoch": 0.0031974420463629096,
      "grad_norm": 1.6171231269836426,
      "learning_rate": 8e-05,
      "loss": 1.7706,
      "step": 4
    },
    {
      "epoch": 0.003996802557953637,
      "grad_norm": 3.1889543533325195,
      "learning_rate": 0.0001,
      "loss": 1.7264,
      "step": 5
    },
    {
      "epoch": 0.004796163069544364,
      "grad_norm": 1.7145410776138306,
      "learning_rate": 0.00012,
      "loss": 1.7818,
      "step": 6
    },
    {
      "epoch": 0.005595523581135092,
      "grad_norm": 0.9461150169372559,
      "learning_rate": 0.00014,
      "loss": 1.5379,
      "step": 7
    },
    {
      "epoch": 0.006394884092725819,
      "grad_norm": 1.3639153242111206,
      "learning_rate": 0.00016,
      "loss": 1.4683,
      "step": 8
    },
    {
      "epoch": 0.007194244604316547,
      "grad_norm": 1.1742007732391357,
      "learning_rate": 0.00018,
      "loss": 1.5821,
      "step": 9
    },
    {
      "epoch": 0.007993605115907274,
      "grad_norm": 0.6428038477897644,
      "learning_rate": 0.0002,
      "loss": 1.4243,
      "step": 10
    },
    {
      "epoch": 0.008792965627498001,
      "grad_norm": 0.5557376146316528,
      "learning_rate": 0.0001999996795753233,
      "loss": 1.3842,
      "step": 11
    },
    {
      "epoch": 0.009592326139088728,
      "grad_norm": 0.35388731956481934,
      "learning_rate": 0.00019999871830334666,
      "loss": 1.4213,
      "step": 12
    },
    {
      "epoch": 0.010391686650679457,
      "grad_norm": 0.3517228662967682,
      "learning_rate": 0.00019999711619023033,
      "loss": 1.3737,
      "step": 13
    },
    {
      "epoch": 0.011191047162270184,
      "grad_norm": 0.37514588236808777,
      "learning_rate": 0.0001999948732462415,
      "loss": 1.6331,
      "step": 14
    },
    {
      "epoch": 0.011990407673860911,
      "grad_norm": 0.4272635579109192,
      "learning_rate": 0.00019999198948575405,
      "loss": 1.4726,
      "step": 15
    },
    {
      "epoch": 0.012789768185451638,
      "grad_norm": 0.4880916476249695,
      "learning_rate": 0.00019998846492724848,
      "loss": 1.4294,
      "step": 16
    },
    {
      "epoch": 0.013589128697042365,
      "grad_norm": 0.38794147968292236,
      "learning_rate": 0.00019998429959331202,
      "loss": 1.4384,
      "step": 17
    },
    {
      "epoch": 0.014388489208633094,
      "grad_norm": 0.31120356917381287,
      "learning_rate": 0.00019997949351063807,
      "loss": 1.3983,
      "step": 18
    },
    {
      "epoch": 0.015187849720223821,
      "grad_norm": 0.4935799539089203,
      "learning_rate": 0.00019997404671002645,
      "loss": 1.263,
      "step": 19
    },
    {
      "epoch": 0.01598721023181455,
      "grad_norm": 0.329028844833374,
      "learning_rate": 0.00019996795922638293,
      "loss": 1.2443,
      "step": 20
    },
    {
      "epoch": 0.016786570743405275,
      "grad_norm": 0.2973022758960724,
      "learning_rate": 0.00019996123109871906,
      "loss": 1.2702,
      "step": 21
    },
    {
      "epoch": 0.017585931254996003,
      "grad_norm": 0.32669177651405334,
      "learning_rate": 0.00019995386237015207,
      "loss": 1.3152,
      "step": 22
    },
    {
      "epoch": 0.01838529176658673,
      "grad_norm": 0.3220458924770355,
      "learning_rate": 0.00019994585308790437,
      "loss": 1.4059,
      "step": 23
    },
    {
      "epoch": 0.019184652278177457,
      "grad_norm": 0.38787347078323364,
      "learning_rate": 0.00019993720330330344,
      "loss": 1.1777,
      "step": 24
    },
    {
      "epoch": 0.019984012789768184,
      "grad_norm": 0.695192277431488,
      "learning_rate": 0.00019992791307178132,
      "loss": 1.4574,
      "step": 25
    },
    {
      "epoch": 0.020783373301358914,
      "grad_norm": 0.6521245837211609,
      "learning_rate": 0.00019991798245287437,
      "loss": 1.1948,
      "step": 26
    },
    {
      "epoch": 0.02158273381294964,
      "grad_norm": 0.5856667757034302,
      "learning_rate": 0.00019990741151022301,
      "loss": 1.2414,
      "step": 27
    },
    {
      "epoch": 0.02238209432454037,
      "grad_norm": 0.5117306709289551,
      "learning_rate": 0.00019989620031157096,
      "loss": 1.273,
      "step": 28
    },
    {
      "epoch": 0.023181454836131096,
      "grad_norm": 0.4806709587574005,
      "learning_rate": 0.00019988434892876514,
      "loss": 1.2461,
      "step": 29
    },
    {
      "epoch": 0.023980815347721823,
      "grad_norm": 0.4751984179019928,
      "learning_rate": 0.00019987185743775506,
      "loss": 1.3404,
      "step": 30
    },
    {
      "epoch": 0.02478017585931255,
      "grad_norm": 0.5241938233375549,
      "learning_rate": 0.0001998587259185924,
      "loss": 1.2368,
      "step": 31
    },
    {
      "epoch": 0.025579536370903277,
      "grad_norm": 0.4881473779678345,
      "learning_rate": 0.00019984495445543035,
      "loss": 1.1433,
      "step": 32
    },
    {
      "epoch": 0.026378896882494004,
      "grad_norm": 0.5861169695854187,
      "learning_rate": 0.00019983054313652327,
      "loss": 1.3639,
      "step": 33
    },
    {
      "epoch": 0.02717825739408473,
      "grad_norm": 0.5575733780860901,
      "learning_rate": 0.000199815492054226,
      "loss": 1.2566,
      "step": 34
    },
    {
      "epoch": 0.027977617905675458,
      "grad_norm": 0.5485345721244812,
      "learning_rate": 0.00019979980130499332,
      "loss": 1.2673,
      "step": 35
    },
    {
      "epoch": 0.02877697841726619,
      "grad_norm": 0.678505003452301,
      "learning_rate": 0.0001997834709893793,
      "loss": 1.2663,
      "step": 36
    },
    {
      "epoch": 0.029576338928856916,
      "grad_norm": 0.7110869884490967,
      "learning_rate": 0.00019976650121203662,
      "loss": 1.3822,
      "step": 37
    },
    {
      "epoch": 0.030375699440447643,
      "grad_norm": 0.8161877989768982,
      "learning_rate": 0.000199748892081716,
      "loss": 1.1504,
      "step": 38
    },
    {
      "epoch": 0.03117505995203837,
      "grad_norm": 0.7314615845680237,
      "learning_rate": 0.00019973064371126548,
      "loss": 1.3762,
      "step": 39
    },
    {
      "epoch": 0.0319744204636291,
      "grad_norm": 0.7901433706283569,
      "learning_rate": 0.0001997117562176296,
      "loss": 1.2416,
      "step": 40
    },
    {
      "epoch": 0.032773780975219824,
      "grad_norm": 0.7982814908027649,
      "learning_rate": 0.00019969222972184873,
      "loss": 1.3356,
      "step": 41
    },
    {
      "epoch": 0.03357314148681055,
      "grad_norm": 1.3451604843139648,
      "learning_rate": 0.0001996720643490583,
      "loss": 1.3487,
      "step": 42
    },
    {
      "epoch": 0.03437250199840128,
      "grad_norm": 0.8946935534477234,
      "learning_rate": 0.00019965126022848795,
      "loss": 1.3564,
      "step": 43
    },
    {
      "epoch": 0.035171862509992005,
      "grad_norm": 1.7600996494293213,
      "learning_rate": 0.00019962981749346078,
      "loss": 1.2413,
      "step": 44
    },
    {
      "epoch": 0.03597122302158273,
      "grad_norm": 1.187146544456482,
      "learning_rate": 0.0001996077362813924,
      "loss": 1.4331,
      "step": 45
    },
    {
      "epoch": 0.03677058353317346,
      "grad_norm": 1.0808261632919312,
      "learning_rate": 0.00019958501673379017,
      "loss": 1.3436,
      "step": 46
    },
    {
      "epoch": 0.037569944044764186,
      "grad_norm": 1.1636722087860107,
      "learning_rate": 0.0001995616589962521,
      "loss": 1.3923,
      "step": 47
    },
    {
      "epoch": 0.03836930455635491,
      "grad_norm": 1.2179851531982422,
      "learning_rate": 0.0001995376632184661,
      "loss": 1.4711,
      "step": 48
    },
    {
      "epoch": 0.03916866506794564,
      "grad_norm": 1.260860800743103,
      "learning_rate": 0.000199513029554209,
      "loss": 1.5432,
      "step": 49
    },
    {
      "epoch": 0.03996802557953637,
      "grad_norm": 1.9464174509048462,
      "learning_rate": 0.00019948775816134545,
      "loss": 1.511,
      "step": 50
    },
    {
      "epoch": 0.0407673860911271,
      "grad_norm": 0.4390850067138672,
      "learning_rate": 0.00019946184920182703,
      "loss": 0.9991,
      "step": 51
    },
    {
      "epoch": 0.04156674660271783,
      "grad_norm": 0.42749834060668945,
      "learning_rate": 0.00019943530284169107,
      "loss": 1.1283,
      "step": 52
    },
    {
      "epoch": 0.042366107114308556,
      "grad_norm": 0.4460582435131073,
      "learning_rate": 0.00019940811925105983,
      "loss": 1.2345,
      "step": 53
    },
    {
      "epoch": 0.04316546762589928,
      "grad_norm": 0.45763692259788513,
      "learning_rate": 0.00019938029860413914,
      "loss": 1.2941,
      "step": 54
    },
    {
      "epoch": 0.04396482813749001,
      "grad_norm": 0.46411487460136414,
      "learning_rate": 0.00019935184107921746,
      "loss": 1.3687,
      "step": 55
    },
    {
      "epoch": 0.04476418864908074,
      "grad_norm": 0.388842910528183,
      "learning_rate": 0.0001993227468586646,
      "loss": 1.1788,
      "step": 56
    },
    {
      "epoch": 0.045563549160671464,
      "grad_norm": 0.3251805007457733,
      "learning_rate": 0.00019929301612893076,
      "loss": 1.3171,
      "step": 57
    },
    {
      "epoch": 0.04636290967226219,
      "grad_norm": 0.3713827431201935,
      "learning_rate": 0.00019926264908054505,
      "loss": 1.2828,
      "step": 58
    },
    {
      "epoch": 0.04716227018385292,
      "grad_norm": 0.29696419835090637,
      "learning_rate": 0.00019923164590811453,
      "loss": 1.2708,
      "step": 59
    },
    {
      "epoch": 0.047961630695443645,
      "grad_norm": 0.3488282263278961,
      "learning_rate": 0.00019920000681032288,
      "loss": 1.2673,
      "step": 60
    },
    {
      "epoch": 0.04876099120703437,
      "grad_norm": 0.3075105547904968,
      "learning_rate": 0.000199167731989929,
      "loss": 1.3265,
      "step": 61
    },
    {
      "epoch": 0.0495603517186251,
      "grad_norm": 0.3479640781879425,
      "learning_rate": 0.0001991348216537659,
      "loss": 1.3545,
      "step": 62
    },
    {
      "epoch": 0.050359712230215826,
      "grad_norm": 0.3479630947113037,
      "learning_rate": 0.00019910127601273922,
      "loss": 1.2322,
      "step": 63
    },
    {
      "epoch": 0.051159072741806554,
      "grad_norm": 0.32833385467529297,
      "learning_rate": 0.000199067095281826,
      "loss": 1.3306,
      "step": 64
    },
    {
      "epoch": 0.05195843325339728,
      "grad_norm": 0.45465975999832153,
      "learning_rate": 0.00019903227968007326,
      "loss": 1.1733,
      "step": 65
    },
    {
      "epoch": 0.05275779376498801,
      "grad_norm": 0.31810107827186584,
      "learning_rate": 0.0001989968294305965,
      "loss": 1.1675,
      "step": 66
    },
    {
      "epoch": 0.053557154276578735,
      "grad_norm": 0.3302905857563019,
      "learning_rate": 0.00019896074476057846,
      "loss": 1.1695,
      "step": 67
    },
    {
      "epoch": 0.05435651478816946,
      "grad_norm": 0.34600090980529785,
      "learning_rate": 0.0001989240259012675,
      "loss": 1.1706,
      "step": 68
    },
    {
      "epoch": 0.05515587529976019,
      "grad_norm": 0.3320174217224121,
      "learning_rate": 0.0001988866730879762,
      "loss": 1.2779,
      "step": 69
    },
    {
      "epoch": 0.055955235811350916,
      "grad_norm": 0.4127947688102722,
      "learning_rate": 0.00019884868656007982,
      "loss": 1.1394,
      "step": 70
    },
    {
      "epoch": 0.05675459632294165,
      "grad_norm": 0.4041900038719177,
      "learning_rate": 0.00019881006656101479,
      "loss": 1.3192,
      "step": 71
    },
    {
      "epoch": 0.05755395683453238,
      "grad_norm": 0.390407919883728,
      "learning_rate": 0.00019877081333827712,
      "loss": 1.261,
      "step": 72
    },
    {
      "epoch": 0.058353317346123104,
      "grad_norm": 0.3832196295261383,
      "learning_rate": 0.00019873092714342078,
      "loss": 1.1741,
      "step": 73
    },
    {
      "epoch": 0.05915267785771383,
      "grad_norm": 0.3609188199043274,
      "learning_rate": 0.0001986904082320563,
      "loss": 1.279,
      "step": 74
    },
    {
      "epoch": 0.05995203836930456,
      "grad_norm": 0.3944198191165924,
      "learning_rate": 0.00019864925686384873,
      "loss": 1.1863,
      "step": 75
    },
    {
      "epoch": 0.060751398880895285,
      "grad_norm": 0.4218379855155945,
      "learning_rate": 0.00019860747330251646,
      "loss": 1.1365,
      "step": 76
    },
    {
      "epoch": 0.06155075939248601,
      "grad_norm": 0.4537956416606903,
      "learning_rate": 0.0001985650578158291,
      "loss": 1.131,
      "step": 77
    },
    {
      "epoch": 0.06235011990407674,
      "grad_norm": 0.3956335186958313,
      "learning_rate": 0.00019852201067560606,
      "loss": 1.2713,
      "step": 78
    },
    {
      "epoch": 0.06314948041566747,
      "grad_norm": 0.5430086255073547,
      "learning_rate": 0.00019847833215771467,
      "loss": 1.2556,
      "step": 79
    },
    {
      "epoch": 0.0639488409272582,
      "grad_norm": 0.40932217240333557,
      "learning_rate": 0.0001984340225420684,
      "loss": 0.9753,
      "step": 80
    },
    {
      "epoch": 0.06474820143884892,
      "grad_norm": 0.5276725888252258,
      "learning_rate": 0.00019838908211262512,
      "loss": 1.1394,
      "step": 81
    },
    {
      "epoch": 0.06554756195043965,
      "grad_norm": 0.6045296788215637,
      "learning_rate": 0.00019834351115738535,
      "loss": 1.128,
      "step": 82
    },
    {
      "epoch": 0.06634692246203037,
      "grad_norm": 0.6298900842666626,
      "learning_rate": 0.0001982973099683902,
      "loss": 1.2829,
      "step": 83
    },
    {
      "epoch": 0.0671462829736211,
      "grad_norm": 0.6042550206184387,
      "learning_rate": 0.0001982504788417197,
      "loss": 1.1628,
      "step": 84
    },
    {
      "epoch": 0.06794564348521183,
      "grad_norm": 0.6109876036643982,
      "learning_rate": 0.00019820301807749085,
      "loss": 1.0785,
      "step": 85
    },
    {
      "epoch": 0.06874500399680256,
      "grad_norm": 0.6248145699501038,
      "learning_rate": 0.0001981549279798556,
      "loss": 1.1856,
      "step": 86
    },
    {
      "epoch": 0.06954436450839328,
      "grad_norm": 0.74518883228302,
      "learning_rate": 0.00019810620885699905,
      "loss": 1.1553,
      "step": 87
    },
    {
      "epoch": 0.07034372501998401,
      "grad_norm": 0.7344063520431519,
      "learning_rate": 0.00019805686102113747,
      "loss": 1.2014,
      "step": 88
    },
    {
      "epoch": 0.07114308553157474,
      "grad_norm": 0.7360933423042297,
      "learning_rate": 0.000198006884788516,
      "loss": 1.1937,
      "step": 89
    },
    {
      "epoch": 0.07194244604316546,
      "grad_norm": 0.7342174649238586,
      "learning_rate": 0.00019795628047940714,
      "loss": 1.2054,
      "step": 90
    },
    {
      "epoch": 0.07274180655475619,
      "grad_norm": 0.7293947339057922,
      "learning_rate": 0.00019790504841810818,
      "loss": 1.2446,
      "step": 91
    },
    {
      "epoch": 0.07354116706634692,
      "grad_norm": 0.7864716053009033,
      "learning_rate": 0.0001978531889329395,
      "loss": 1.182,
      "step": 92
    },
    {
      "epoch": 0.07434052757793765,
      "grad_norm": 0.8126608729362488,
      "learning_rate": 0.00019780070235624221,
      "loss": 1.3634,
      "step": 93
    },
    {
      "epoch": 0.07513988808952837,
      "grad_norm": 0.797795295715332,
      "learning_rate": 0.00019774758902437633,
      "loss": 1.0883,
      "step": 94
    },
    {
      "epoch": 0.0759392486011191,
      "grad_norm": 0.8480005860328674,
      "learning_rate": 0.0001976938492777182,
      "loss": 1.3654,
      "step": 95
    },
    {
      "epoch": 0.07673860911270983,
      "grad_norm": 1.0392693281173706,
      "learning_rate": 0.00019763948346065863,
      "loss": 1.3555,
      "step": 96
    },
    {
      "epoch": 0.07753796962430055,
      "grad_norm": 1.147118330001831,
      "learning_rate": 0.00019758449192160067,
      "loss": 1.3023,
      "step": 97
    },
    {
      "epoch": 0.07833733013589128,
      "grad_norm": 1.447702169418335,
      "learning_rate": 0.0001975288750129572,
      "loss": 1.4948,
      "step": 98
    },
    {
      "epoch": 0.07913669064748201,
      "grad_norm": 1.1526646614074707,
      "learning_rate": 0.00019747263309114886,
      "loss": 1.2744,
      "step": 99
    },
    {
      "epoch": 0.07993605115907274,
      "grad_norm": 1.8174890279769897,
      "learning_rate": 0.00019741576651660157,
      "loss": 1.5239,
      "step": 100
    },
    {
      "epoch": 0.08073541167066348,
      "grad_norm": 0.33395928144454956,
      "learning_rate": 0.00019735827565374448,
      "loss": 0.8391,
      "step": 101
    },
    {
      "epoch": 0.0815347721822542,
      "grad_norm": 0.48688215017318726,
      "learning_rate": 0.00019730016087100738,
      "loss": 1.0899,
      "step": 102
    },
    {
      "epoch": 0.08233413269384493,
      "grad_norm": 0.3916321098804474,
      "learning_rate": 0.0001972414225408185,
      "loss": 1.2562,
      "step": 103
    },
    {
      "epoch": 0.08313349320543566,
      "grad_norm": 0.38845309615135193,
      "learning_rate": 0.00019718206103960199,
      "loss": 1.2981,
      "step": 104
    },
    {
      "epoch": 0.08393285371702638,
      "grad_norm": 0.35215434432029724,
      "learning_rate": 0.0001971220767477757,
      "loss": 0.9815,
      "step": 105
    },
    {
      "epoch": 0.08473221422861711,
      "grad_norm": 0.32380643486976624,
      "learning_rate": 0.00019706147004974858,
      "loss": 1.0154,
      "step": 106
    },
    {
      "epoch": 0.08553157474020784,
      "grad_norm": 0.35980847477912903,
      "learning_rate": 0.00019700024133391825,
      "loss": 1.2426,
      "step": 107
    },
    {
      "epoch": 0.08633093525179857,
      "grad_norm": 0.3244008421897888,
      "learning_rate": 0.00019693839099266854,
      "loss": 1.3621,
      "step": 108
    },
    {
      "epoch": 0.08713029576338929,
      "grad_norm": 0.4032576382160187,
      "learning_rate": 0.00019687591942236694,
      "loss": 1.2899,
      "step": 109
    },
    {
      "epoch": 0.08792965627498002,
      "grad_norm": 0.36872512102127075,
      "learning_rate": 0.00019681282702336213,
      "loss": 1.1612,
      "step": 110
    },
    {
      "epoch": 0.08872901678657075,
      "grad_norm": 0.3233664929866791,
      "learning_rate": 0.0001967491141999813,
      "loss": 1.2213,
      "step": 111
    },
    {
      "epoch": 0.08952837729816147,
      "grad_norm": 0.3443772792816162,
      "learning_rate": 0.00019668478136052774,
      "loss": 1.1822,
      "step": 112
    },
    {
      "epoch": 0.0903277378097522,
      "grad_norm": 0.3623986840248108,
      "learning_rate": 0.000196619828917278,
      "loss": 1.2398,
      "step": 113
    },
    {
      "epoch": 0.09112709832134293,
      "grad_norm": 0.2766810357570648,
      "learning_rate": 0.0001965542572864794,
      "loss": 1.2032,
      "step": 114
    },
    {
      "epoch": 0.09192645883293366,
      "grad_norm": 0.3393819332122803,
      "learning_rate": 0.00019648806688834727,
      "loss": 1.3039,
      "step": 115
    },
    {
      "epoch": 0.09272581934452438,
      "grad_norm": 0.33124133944511414,
      "learning_rate": 0.0001964212581470624,
      "loss": 1.137,
      "step": 116
    },
    {
      "epoch": 0.09352517985611511,
      "grad_norm": 0.3681512773036957,
      "learning_rate": 0.00019635383149076816,
      "loss": 1.1675,
      "step": 117
    },
    {
      "epoch": 0.09432454036770584,
      "grad_norm": 0.4348418116569519,
      "learning_rate": 0.00019628578735156782,
      "loss": 1.1787,
      "step": 118
    },
    {
      "epoch": 0.09512390087929656,
      "grad_norm": 0.37171006202697754,
      "learning_rate": 0.00019621712616552182,
      "loss": 1.137,
      "step": 119
    },
    {
      "epoch": 0.09592326139088729,
      "grad_norm": 0.42151620984077454,
      "learning_rate": 0.00019614784837264493,
      "loss": 1.2804,
      "step": 120
    },
    {
      "epoch": 0.09672262190247802,
      "grad_norm": 0.47245654463768005,
      "learning_rate": 0.00019607795441690343,
      "loss": 1.1102,
      "step": 121
    },
    {
      "epoch": 0.09752198241406874,
      "grad_norm": 0.42258185148239136,
      "learning_rate": 0.00019600744474621232,
      "loss": 1.2432,
      "step": 122
    },
    {
      "epoch": 0.09832134292565947,
      "grad_norm": 0.3666921555995941,
      "learning_rate": 0.0001959363198124323,
      "loss": 0.9307,
      "step": 123
    },
    {
      "epoch": 0.0991207034372502,
      "grad_norm": 0.4099723696708679,
      "learning_rate": 0.00019586458007136713,
      "loss": 1.0751,
      "step": 124
    },
    {
      "epoch": 0.09992006394884093,
      "grad_norm": 0.4759383201599121,
      "learning_rate": 0.00019579222598276042,
      "loss": 1.021,
      "step": 125
    },
    {
      "epoch": 0.10071942446043165,
      "grad_norm": 0.3923790156841278,
      "learning_rate": 0.0001957192580102929,
      "loss": 1.0722,
      "step": 126
    },
    {
      "epoch": 0.10151878497202238,
      "grad_norm": 0.47697147727012634,
      "learning_rate": 0.0001956456766215793,
      "loss": 1.1207,
      "step": 127
    },
    {
      "epoch": 0.10231814548361311,
      "grad_norm": 0.4863724410533905,
      "learning_rate": 0.00019557148228816558,
      "loss": 1.0626,
      "step": 128
    },
    {
      "epoch": 0.10311750599520383,
      "grad_norm": 0.576336681842804,
      "learning_rate": 0.00019549667548552556,
      "loss": 1.0729,
      "step": 129
    },
    {
      "epoch": 0.10391686650679456,
      "grad_norm": 0.7830796241760254,
      "learning_rate": 0.00019542125669305812,
      "loss": 1.3441,
      "step": 130
    },
    {
      "epoch": 0.10471622701838529,
      "grad_norm": 0.5463136434555054,
      "learning_rate": 0.0001953452263940842,
      "loss": 1.1252,
      "step": 131
    },
    {
      "epoch": 0.10551558752997602,
      "grad_norm": 0.7431773543357849,
      "learning_rate": 0.00019526858507584347,
      "loss": 1.3767,
      "step": 132
    },
    {
      "epoch": 0.10631494804156674,
      "grad_norm": 0.6066572666168213,
      "learning_rate": 0.00019519133322949122,
      "loss": 1.1088,
      "step": 133
    },
    {
      "epoch": 0.10711430855315747,
      "grad_norm": 0.5295929312705994,
      "learning_rate": 0.00019511347135009555,
      "loss": 1.1324,
      "step": 134
    },
    {
      "epoch": 0.1079136690647482,
      "grad_norm": 0.6992323994636536,
      "learning_rate": 0.0001950349999366337,
      "loss": 1.2556,
      "step": 135
    },
    {
      "epoch": 0.10871302957633892,
      "grad_norm": 0.6171619296073914,
      "learning_rate": 0.00019495591949198927,
      "loss": 1.1685,
      "step": 136
    },
    {
      "epoch": 0.10951239008792965,
      "grad_norm": 0.6525933146476746,
      "learning_rate": 0.00019487623052294873,
      "loss": 1.3022,
      "step": 137
    },
    {
      "epoch": 0.11031175059952038,
      "grad_norm": 0.8878188729286194,
      "learning_rate": 0.0001947959335401984,
      "loss": 1.2187,
      "step": 138
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.6956382393836975,
      "learning_rate": 0.0001947150290583209,
      "loss": 1.3016,
      "step": 139
    },
    {
      "epoch": 0.11191047162270183,
      "grad_norm": 0.7935355305671692,
      "learning_rate": 0.00019463351759579212,
      "loss": 1.2124,
      "step": 140
    },
    {
      "epoch": 0.11270983213429256,
      "grad_norm": 0.8994975686073303,
      "learning_rate": 0.0001945513996749777,
      "loss": 1.2633,
      "step": 141
    },
    {
      "epoch": 0.1135091926458833,
      "grad_norm": 0.7103203535079956,
      "learning_rate": 0.00019446867582212986,
      "loss": 1.1257,
      "step": 142
    },
    {
      "epoch": 0.11430855315747403,
      "grad_norm": 1.077649712562561,
      "learning_rate": 0.00019438534656738386,
      "loss": 1.2635,
      "step": 143
    },
    {
      "epoch": 0.11510791366906475,
      "grad_norm": 0.9161784648895264,
      "learning_rate": 0.0001943014124447547,
      "loss": 1.3306,
      "step": 144
    },
    {
      "epoch": 0.11590727418065548,
      "grad_norm": 1.036491870880127,
      "learning_rate": 0.0001942168739921336,
      "loss": 1.5151,
      "step": 145
    },
    {
      "epoch": 0.11670663469224621,
      "grad_norm": 0.8974622488021851,
      "learning_rate": 0.00019413173175128473,
      "loss": 1.4381,
      "step": 146
    },
    {
      "epoch": 0.11750599520383694,
      "grad_norm": 1.1696873903274536,
      "learning_rate": 0.0001940459862678416,
      "loss": 1.4909,
      "step": 147
    },
    {
      "epoch": 0.11830535571542766,
      "grad_norm": 1.1506264209747314,
      "learning_rate": 0.00019395963809130354,
      "loss": 1.3273,
      "step": 148
    },
    {
      "epoch": 0.11910471622701839,
      "grad_norm": 1.7458105087280273,
      "learning_rate": 0.00019387268777503236,
      "loss": 1.2036,
      "step": 149
    },
    {
      "epoch": 0.11990407673860912,
      "grad_norm": 1.8019418716430664,
      "learning_rate": 0.00019378513587624854,
      "loss": 1.3185,
      "step": 150
    },
    {
      "epoch": 0.12070343725019984,
      "grad_norm": 0.37937843799591064,
      "learning_rate": 0.00019369698295602786,
      "loss": 0.9703,
      "step": 151
    },
    {
      "epoch": 0.12150279776179057,
      "grad_norm": 0.4317457675933838,
      "learning_rate": 0.0001936082295792978,
      "loss": 1.1408,
      "step": 152
    },
    {
      "epoch": 0.1223021582733813,
      "grad_norm": 0.3610316216945648,
      "learning_rate": 0.0001935188763148337,
      "loss": 1.0476,
      "step": 153
    },
    {
      "epoch": 0.12310151878497202,
      "grad_norm": 0.4185445010662079,
      "learning_rate": 0.00019342892373525546,
      "loss": 1.1442,
      "step": 154
    },
    {
      "epoch": 0.12390087929656275,
      "grad_norm": 0.5041868686676025,
      "learning_rate": 0.00019333837241702358,
      "loss": 1.2064,
      "step": 155
    },
    {
      "epoch": 0.12470023980815348,
      "grad_norm": 0.36838433146476746,
      "learning_rate": 0.00019324722294043558,
      "loss": 1.1642,
      "step": 156
    },
    {
      "epoch": 0.1254996003197442,
      "grad_norm": 0.3606477379798889,
      "learning_rate": 0.0001931554758896223,
      "loss": 1.1654,
      "step": 157
    },
    {
      "epoch": 0.12629896083133493,
      "grad_norm": 0.3449469804763794,
      "learning_rate": 0.00019306313185254417,
      "loss": 1.1154,
      "step": 158
    },
    {
      "epoch": 0.12709832134292565,
      "grad_norm": 0.33281880617141724,
      "learning_rate": 0.00019297019142098723,
      "loss": 1.3186,
      "step": 159
    },
    {
      "epoch": 0.1278976818545164,
      "grad_norm": 0.34775304794311523,
      "learning_rate": 0.00019287665519055977,
      "loss": 1.1772,
      "step": 160
    },
    {
      "epoch": 0.1286970423661071,
      "grad_norm": 0.32196998596191406,
      "learning_rate": 0.00019278252376068807,
      "loss": 1.1682,
      "step": 161
    },
    {
      "epoch": 0.12949640287769784,
      "grad_norm": 0.3235302269458771,
      "learning_rate": 0.00019268779773461275,
      "loss": 1.2322,
      "step": 162
    },
    {
      "epoch": 0.13029576338928858,
      "grad_norm": 0.31604263186454773,
      "learning_rate": 0.000192592477719385,
      "loss": 1.1779,
      "step": 163
    },
    {
      "epoch": 0.1310951239008793,
      "grad_norm": 0.29469355940818787,
      "learning_rate": 0.00019249656432586247,
      "loss": 1.1083,
      "step": 164
    },
    {
      "epoch": 0.13189448441247004,
      "grad_norm": 0.3672734797000885,
      "learning_rate": 0.00019240005816870554,
      "loss": 1.1481,
      "step": 165
    },
    {
      "epoch": 0.13269384492406075,
      "grad_norm": 0.35141581296920776,
      "learning_rate": 0.0001923029598663733,
      "loss": 1.0356,
      "step": 166
    },
    {
      "epoch": 0.1334932054356515,
      "grad_norm": 0.38158297538757324,
      "learning_rate": 0.0001922052700411196,
      "loss": 1.1449,
      "step": 167
    },
    {
      "epoch": 0.1342925659472422,
      "grad_norm": 0.33295100927352905,
      "learning_rate": 0.00019210698931898903,
      "loss": 1.1372,
      "step": 168
    },
    {
      "epoch": 0.13509192645883294,
      "grad_norm": 0.4519907236099243,
      "learning_rate": 0.00019200811832981298,
      "loss": 1.1314,
      "step": 169
    },
    {
      "epoch": 0.13589128697042366,
      "grad_norm": 0.3855970501899719,
      "learning_rate": 0.00019190865770720553,
      "loss": 1.0639,
      "step": 170
    },
    {
      "epoch": 0.1366906474820144,
      "grad_norm": 0.405184268951416,
      "learning_rate": 0.00019180860808855945,
      "loss": 1.2448,
      "step": 171
    },
    {
      "epoch": 0.1374900079936051,
      "grad_norm": 0.41066446900367737,
      "learning_rate": 0.00019170797011504206,
      "loss": 1.0956,
      "step": 172
    },
    {
      "epoch": 0.13828936850519585,
      "grad_norm": 0.3971129059791565,
      "learning_rate": 0.00019160674443159122,
      "loss": 1.0819,
      "step": 173
    },
    {
      "epoch": 0.13908872901678657,
      "grad_norm": 0.43992650508880615,
      "learning_rate": 0.00019150493168691094,
      "loss": 1.248,
      "step": 174
    },
    {
      "epoch": 0.1398880895283773,
      "grad_norm": 0.41885894536972046,
      "learning_rate": 0.00019140253253346768,
      "loss": 1.1889,
      "step": 175
    },
    {
      "epoch": 0.14068745003996802,
      "grad_norm": 0.47921714186668396,
      "learning_rate": 0.00019129954762748568,
      "loss": 1.093,
      "step": 176
    },
    {
      "epoch": 0.14148681055155876,
      "grad_norm": 0.4085664451122284,
      "learning_rate": 0.00019119597762894304,
      "loss": 1.2167,
      "step": 177
    },
    {
      "epoch": 0.14228617106314947,
      "grad_norm": 0.6234189867973328,
      "learning_rate": 0.00019109182320156744,
      "loss": 1.1884,
      "step": 178
    },
    {
      "epoch": 0.14308553157474022,
      "grad_norm": 0.45891621708869934,
      "learning_rate": 0.00019098708501283186,
      "loss": 1.1723,
      "step": 179
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 0.46962589025497437,
      "learning_rate": 0.0001908817637339503,
      "loss": 1.0018,
      "step": 180
    },
    {
      "epoch": 0.14468425259792167,
      "grad_norm": 0.5809106230735779,
      "learning_rate": 0.0001907758600398735,
      "loss": 1.099,
      "step": 181
    },
    {
      "epoch": 0.14548361310951238,
      "grad_norm": 0.48514389991760254,
      "learning_rate": 0.0001906693746092846,
      "loss": 1.0701,
      "step": 182
    },
    {
      "epoch": 0.14628297362110312,
      "grad_norm": 0.5460750460624695,
      "learning_rate": 0.00019056230812459474,
      "loss": 1.2026,
      "step": 183
    },
    {
      "epoch": 0.14708233413269384,
      "grad_norm": 0.5718762874603271,
      "learning_rate": 0.0001904546612719389,
      "loss": 1.1434,
      "step": 184
    },
    {
      "epoch": 0.14788169464428458,
      "grad_norm": 0.5084953904151917,
      "learning_rate": 0.00019034643474117113,
      "loss": 1.0963,
      "step": 185
    },
    {
      "epoch": 0.1486810551558753,
      "grad_norm": 0.7148297429084778,
      "learning_rate": 0.00019023762922586052,
      "loss": 1.3716,
      "step": 186
    },
    {
      "epoch": 0.14948041566746603,
      "grad_norm": 0.6428340673446655,
      "learning_rate": 0.00019012824542328648,
      "loss": 1.028,
      "step": 187
    },
    {
      "epoch": 0.15027977617905675,
      "grad_norm": 0.7076712846755981,
      "learning_rate": 0.00019001828403443445,
      "loss": 1.1724,
      "step": 188
    },
    {
      "epoch": 0.1510791366906475,
      "grad_norm": 0.7304551601409912,
      "learning_rate": 0.00018990774576399123,
      "loss": 1.2831,
      "step": 189
    },
    {
      "epoch": 0.1518784972022382,
      "grad_norm": 0.673502504825592,
      "learning_rate": 0.00018979663132034062,
      "loss": 1.2381,
      "step": 190
    },
    {
      "epoch": 0.15267785771382894,
      "grad_norm": 0.7513559460639954,
      "learning_rate": 0.0001896849414155588,
      "loss": 1.1118,
      "step": 191
    },
    {
      "epoch": 0.15347721822541965,
      "grad_norm": 0.7825088500976562,
      "learning_rate": 0.00018957267676540987,
      "loss": 1.2032,
      "step": 192
    },
    {
      "epoch": 0.1542765787370104,
      "grad_norm": 0.8123567700386047,
      "learning_rate": 0.00018945983808934104,
      "loss": 1.2227,
      "step": 193
    },
    {
      "epoch": 0.1550759392486011,
      "grad_norm": 0.8477492332458496,
      "learning_rate": 0.00018934642611047827,
      "loss": 1.3514,
      "step": 194
    },
    {
      "epoch": 0.15587529976019185,
      "grad_norm": 0.8480494618415833,
      "learning_rate": 0.00018923244155562147,
      "loss": 1.1612,
      "step": 195
    },
    {
      "epoch": 0.15667466027178256,
      "grad_norm": 1.06630539894104,
      "learning_rate": 0.00018911788515523997,
      "loss": 1.4464,
      "step": 196
    },
    {
      "epoch": 0.1574740207833733,
      "grad_norm": 1.0468109846115112,
      "learning_rate": 0.00018900275764346768,
      "loss": 1.4918,
      "step": 197
    },
    {
      "epoch": 0.15827338129496402,
      "grad_norm": 1.234046459197998,
      "learning_rate": 0.0001888870597580985,
      "loss": 1.3812,
      "step": 198
    },
    {
      "epoch": 0.15907274180655476,
      "grad_norm": 1.3013675212860107,
      "learning_rate": 0.00018877079224058165,
      "loss": 1.1392,
      "step": 199
    },
    {
      "epoch": 0.15987210231814547,
      "grad_norm": 1.3213999271392822,
      "learning_rate": 0.00018865395583601667,
      "loss": 1.0561,
      "step": 200
    },
    {
      "epoch": 0.1606714628297362,
      "grad_norm": 0.33066526055336,
      "learning_rate": 0.000188536551293149,
      "loss": 1.0385,
      "step": 201
    },
    {
      "epoch": 0.16147082334132695,
      "grad_norm": 0.41339030861854553,
      "learning_rate": 0.0001884185793643648,
      "loss": 1.4136,
      "step": 202
    },
    {
      "epoch": 0.16227018385291767,
      "grad_norm": 0.37679141759872437,
      "learning_rate": 0.0001883000408056865,
      "loss": 1.2518,
      "step": 203
    },
    {
      "epoch": 0.1630695443645084,
      "grad_norm": 0.4325602352619171,
      "learning_rate": 0.0001881809363767676,
      "loss": 1.2739,
      "step": 204
    },
    {
      "epoch": 0.16386890487609912,
      "grad_norm": 0.3498510718345642,
      "learning_rate": 0.00018806126684088815,
      "loss": 1.1294,
      "step": 205
    },
    {
      "epoch": 0.16466826538768986,
      "grad_norm": 0.4043656885623932,
      "learning_rate": 0.00018794103296494955,
      "loss": 1.0051,
      "step": 206
    },
    {
      "epoch": 0.16546762589928057,
      "grad_norm": 0.3355083465576172,
      "learning_rate": 0.0001878202355194698,
      "loss": 1.132,
      "step": 207
    },
    {
      "epoch": 0.16626698641087131,
      "grad_norm": 0.35696941614151,
      "learning_rate": 0.0001876988752785786,
      "loss": 1.0992,
      "step": 208
    },
    {
      "epoch": 0.16706634692246203,
      "grad_norm": 0.3169572949409485,
      "learning_rate": 0.00018757695302001223,
      "loss": 1.2305,
      "step": 209
    },
    {
      "epoch": 0.16786570743405277,
      "grad_norm": 0.38945549726486206,
      "learning_rate": 0.0001874544695251087,
      "loss": 1.1978,
      "step": 210
    },
    {
      "epoch": 0.16866506794564348,
      "grad_norm": 0.35129424929618835,
      "learning_rate": 0.00018733142557880267,
      "loss": 1.1808,
      "step": 211
    },
    {
      "epoch": 0.16946442845723422,
      "grad_norm": 0.3321034014225006,
      "learning_rate": 0.00018720782196962054,
      "loss": 1.1648,
      "step": 212
    },
    {
      "epoch": 0.17026378896882494,
      "grad_norm": 0.3599945604801178,
      "learning_rate": 0.00018708365948967522,
      "loss": 1.2779,
      "step": 213
    },
    {
      "epoch": 0.17106314948041568,
      "grad_norm": 0.3521081209182739,
      "learning_rate": 0.0001869589389346611,
      "loss": 1.1971,
      "step": 214
    },
    {
      "epoch": 0.1718625099920064,
      "grad_norm": 0.3376477062702179,
      "learning_rate": 0.00018683366110384912,
      "loss": 1.3075,
      "step": 215
    },
    {
      "epoch": 0.17266187050359713,
      "grad_norm": 0.36610740423202515,
      "learning_rate": 0.00018670782680008143,
      "loss": 1.2168,
      "step": 216
    },
    {
      "epoch": 0.17346123101518784,
      "grad_norm": 0.31685808300971985,
      "learning_rate": 0.00018658143682976635,
      "loss": 1.0374,
      "step": 217
    },
    {
      "epoch": 0.17426059152677859,
      "grad_norm": 0.3511636257171631,
      "learning_rate": 0.00018645449200287314,
      "loss": 0.9931,
      "step": 218
    },
    {
      "epoch": 0.1750599520383693,
      "grad_norm": 0.4250391125679016,
      "learning_rate": 0.000186326993132927,
      "loss": 1.1782,
      "step": 219
    },
    {
      "epoch": 0.17585931254996004,
      "grad_norm": 0.3989580571651459,
      "learning_rate": 0.00018619894103700352,
      "loss": 1.1014,
      "step": 220
    },
    {
      "epoch": 0.17665867306155075,
      "grad_norm": 0.409648060798645,
      "learning_rate": 0.00018607033653572378,
      "loss": 1.0888,
      "step": 221
    },
    {
      "epoch": 0.1774580335731415,
      "grad_norm": 0.38411882519721985,
      "learning_rate": 0.00018594118045324887,
      "loss": 1.0785,
      "step": 222
    },
    {
      "epoch": 0.1782573940847322,
      "grad_norm": 0.45235031843185425,
      "learning_rate": 0.00018581147361727477,
      "loss": 1.2181,
      "step": 223
    },
    {
      "epoch": 0.17905675459632295,
      "grad_norm": 0.47184649109840393,
      "learning_rate": 0.00018568121685902682,
      "loss": 1.0918,
      "step": 224
    },
    {
      "epoch": 0.17985611510791366,
      "grad_norm": 0.4382520616054535,
      "learning_rate": 0.00018555041101325466,
      "loss": 1.1234,
      "step": 225
    },
    {
      "epoch": 0.1806554756195044,
      "grad_norm": 0.4980821907520294,
      "learning_rate": 0.00018541905691822668,
      "loss": 1.2183,
      "step": 226
    },
    {
      "epoch": 0.18145483613109512,
      "grad_norm": 0.6325019001960754,
      "learning_rate": 0.00018528715541572474,
      "loss": 0.9963,
      "step": 227
    },
    {
      "epoch": 0.18225419664268586,
      "grad_norm": 0.48259237408638,
      "learning_rate": 0.0001851547073510388,
      "loss": 1.1,
      "step": 228
    },
    {
      "epoch": 0.18305355715427657,
      "grad_norm": 0.5209122896194458,
      "learning_rate": 0.00018502171357296144,
      "loss": 1.0281,
      "step": 229
    },
    {
      "epoch": 0.1838529176658673,
      "grad_norm": 0.5251787900924683,
      "learning_rate": 0.00018488817493378235,
      "loss": 1.1696,
      "step": 230
    },
    {
      "epoch": 0.18465227817745802,
      "grad_norm": 0.522381067276001,
      "learning_rate": 0.00018475409228928312,
      "loss": 1.0588,
      "step": 231
    },
    {
      "epoch": 0.18545163868904876,
      "grad_norm": 0.5586369037628174,
      "learning_rate": 0.00018461946649873148,
      "loss": 1.0162,
      "step": 232
    },
    {
      "epoch": 0.18625099920063948,
      "grad_norm": 0.6529503464698792,
      "learning_rate": 0.0001844842984248759,
      "loss": 1.1062,
      "step": 233
    },
    {
      "epoch": 0.18705035971223022,
      "grad_norm": 0.6378787159919739,
      "learning_rate": 0.00018434858893394017,
      "loss": 1.1263,
      "step": 234
    },
    {
      "epoch": 0.18784972022382093,
      "grad_norm": 0.6238505840301514,
      "learning_rate": 0.00018421233889561765,
      "loss": 1.1797,
      "step": 235
    },
    {
      "epoch": 0.18864908073541167,
      "grad_norm": 0.7397989630699158,
      "learning_rate": 0.00018407554918306582,
      "loss": 1.1618,
      "step": 236
    },
    {
      "epoch": 0.18944844124700239,
      "grad_norm": 0.6958909034729004,
      "learning_rate": 0.0001839382206729007,
      "loss": 1.1088,
      "step": 237
    },
    {
      "epoch": 0.19024780175859313,
      "grad_norm": 0.8362878561019897,
      "learning_rate": 0.00018380035424519115,
      "loss": 1.1162,
      "step": 238
    },
    {
      "epoch": 0.19104716227018384,
      "grad_norm": 0.6862859725952148,
      "learning_rate": 0.00018366195078345327,
      "loss": 1.1711,
      "step": 239
    },
    {
      "epoch": 0.19184652278177458,
      "grad_norm": 0.6498910188674927,
      "learning_rate": 0.00018352301117464473,
      "loss": 1.1287,
      "step": 240
    },
    {
      "epoch": 0.1926458832933653,
      "grad_norm": 0.8801695108413696,
      "learning_rate": 0.00018338353630915915,
      "loss": 1.3638,
      "step": 241
    },
    {
      "epoch": 0.19344524380495604,
      "grad_norm": 0.8688244223594666,
      "learning_rate": 0.00018324352708082032,
      "loss": 1.1142,
      "step": 242
    },
    {
      "epoch": 0.19424460431654678,
      "grad_norm": 1.11106276512146,
      "learning_rate": 0.00018310298438687644,
      "loss": 1.0854,
      "step": 243
    },
    {
      "epoch": 0.1950439648281375,
      "grad_norm": 1.1534092426300049,
      "learning_rate": 0.00018296190912799442,
      "loss": 1.2603,
      "step": 244
    },
    {
      "epoch": 0.19584332533972823,
      "grad_norm": 1.00962233543396,
      "learning_rate": 0.00018282030220825423,
      "loss": 1.118,
      "step": 245
    },
    {
      "epoch": 0.19664268585131894,
      "grad_norm": 1.2045316696166992,
      "learning_rate": 0.00018267816453514284,
      "loss": 1.3775,
      "step": 246
    },
    {
      "epoch": 0.19744204636290968,
      "grad_norm": 0.9561203718185425,
      "learning_rate": 0.00018253549701954862,
      "loss": 1.114,
      "step": 247
    },
    {
      "epoch": 0.1982414068745004,
      "grad_norm": 1.6712232828140259,
      "learning_rate": 0.00018239230057575542,
      "loss": 1.3807,
      "step": 248
    },
    {
      "epoch": 0.19904076738609114,
      "grad_norm": 1.390113115310669,
      "learning_rate": 0.00018224857612143675,
      "loss": 1.2788,
      "step": 249
    },
    {
      "epoch": 0.19984012789768185,
      "grad_norm": 2.1578612327575684,
      "learning_rate": 0.00018210432457764982,
      "loss": 1.2059,
      "step": 250
    },
    {
      "epoch": 0.2006394884092726,
      "grad_norm": 0.40902066230773926,
      "learning_rate": 0.00018195954686882972,
      "loss": 1.147,
      "step": 251
    },
    {
      "epoch": 0.2014388489208633,
      "grad_norm": 0.41376692056655884,
      "learning_rate": 0.00018181424392278345,
      "loss": 1.1842,
      "step": 252
    },
    {
      "epoch": 0.20223820943245405,
      "grad_norm": 0.4128184914588928,
      "learning_rate": 0.00018166841667068405,
      "loss": 1.0763,
      "step": 253
    },
    {
      "epoch": 0.20303756994404476,
      "grad_norm": 0.4061759114265442,
      "learning_rate": 0.00018152206604706445,
      "loss": 1.2217,
      "step": 254
    },
    {
      "epoch": 0.2038369304556355,
      "grad_norm": 0.42886969447135925,
      "learning_rate": 0.00018137519298981172,
      "loss": 1.2359,
      "step": 255
    },
    {
      "epoch": 0.20463629096722621,
      "grad_norm": 0.32949739694595337,
      "learning_rate": 0.00018122779844016086,
      "loss": 0.9807,
      "step": 256
    },
    {
      "epoch": 0.20543565147881696,
      "grad_norm": 0.39663881063461304,
      "learning_rate": 0.00018107988334268896,
      "loss": 1.144,
      "step": 257
    },
    {
      "epoch": 0.20623501199040767,
      "grad_norm": 0.41834643483161926,
      "learning_rate": 0.0001809314486453089,
      "loss": 1.0347,
      "step": 258
    },
    {
      "epoch": 0.2070343725019984,
      "grad_norm": 0.34301498532295227,
      "learning_rate": 0.0001807824952992635,
      "loss": 1.1805,
      "step": 259
    },
    {
      "epoch": 0.20783373301358912,
      "grad_norm": 0.3798671364784241,
      "learning_rate": 0.00018063302425911935,
      "loss": 1.2937,
      "step": 260
    },
    {
      "epoch": 0.20863309352517986,
      "grad_norm": 0.3300327658653259,
      "learning_rate": 0.00018048303648276058,
      "loss": 1.2345,
      "step": 261
    },
    {
      "epoch": 0.20943245403677058,
      "grad_norm": 0.30229341983795166,
      "learning_rate": 0.0001803325329313829,
      "loss": 1.1839,
      "step": 262
    },
    {
      "epoch": 0.21023181454836132,
      "grad_norm": 0.33945149183273315,
      "learning_rate": 0.00018018151456948738,
      "loss": 1.0572,
      "step": 263
    },
    {
      "epoch": 0.21103117505995203,
      "grad_norm": 0.3481135666370392,
      "learning_rate": 0.00018002998236487421,
      "loss": 1.1325,
      "step": 264
    },
    {
      "epoch": 0.21183053557154277,
      "grad_norm": 0.33425942063331604,
      "learning_rate": 0.00017987793728863651,
      "loss": 1.1208,
      "step": 265
    },
    {
      "epoch": 0.21262989608313348,
      "grad_norm": 0.36472010612487793,
      "learning_rate": 0.00017972538031515417,
      "loss": 1.1532,
      "step": 266
    },
    {
      "epoch": 0.21342925659472423,
      "grad_norm": 0.5549772381782532,
      "learning_rate": 0.0001795723124220876,
      "loss": 1.2021,
      "step": 267
    },
    {
      "epoch": 0.21422861710631494,
      "grad_norm": 0.37048134207725525,
      "learning_rate": 0.00017941873459037142,
      "loss": 1.1668,
      "step": 268
    },
    {
      "epoch": 0.21502797761790568,
      "grad_norm": 0.41433608531951904,
      "learning_rate": 0.0001792646478042081,
      "loss": 1.1087,
      "step": 269
    },
    {
      "epoch": 0.2158273381294964,
      "grad_norm": 0.4452265202999115,
      "learning_rate": 0.00017911005305106187,
      "loss": 1.1752,
      "step": 270
    },
    {
      "epoch": 0.21662669864108713,
      "grad_norm": 0.3953174948692322,
      "learning_rate": 0.0001789549513216522,
      "loss": 1.0982,
      "step": 271
    },
    {
      "epoch": 0.21742605915267785,
      "grad_norm": 0.39090120792388916,
      "learning_rate": 0.0001787993436099475,
      "loss": 1.0464,
      "step": 272
    },
    {
      "epoch": 0.2182254196642686,
      "grad_norm": 0.4702832102775574,
      "learning_rate": 0.0001786432309131588,
      "loss": 1.1884,
      "step": 273
    },
    {
      "epoch": 0.2190247801758593,
      "grad_norm": 0.377530574798584,
      "learning_rate": 0.00017848661423173326,
      "loss": 1.2785,
      "step": 274
    },
    {
      "epoch": 0.21982414068745004,
      "grad_norm": 0.39601218700408936,
      "learning_rate": 0.00017832949456934798,
      "loss": 1.145,
      "step": 275
    },
    {
      "epoch": 0.22062350119904076,
      "grad_norm": 0.4364507794380188,
      "learning_rate": 0.00017817187293290318,
      "loss": 1.2276,
      "step": 276
    },
    {
      "epoch": 0.2214228617106315,
      "grad_norm": 0.6152124404907227,
      "learning_rate": 0.00017801375033251618,
      "loss": 1.2185,
      "step": 277
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.42372921109199524,
      "learning_rate": 0.00017785512778151457,
      "loss": 0.8677,
      "step": 278
    },
    {
      "epoch": 0.22302158273381295,
      "grad_norm": 0.5250888466835022,
      "learning_rate": 0.00017769600629643004,
      "loss": 1.0941,
      "step": 279
    },
    {
      "epoch": 0.22382094324540366,
      "grad_norm": 0.48516589403152466,
      "learning_rate": 0.0001775363868969915,
      "loss": 1.0313,
      "step": 280
    },
    {
      "epoch": 0.2246203037569944,
      "grad_norm": 0.4571071267127991,
      "learning_rate": 0.0001773762706061189,
      "loss": 1.111,
      "step": 281
    },
    {
      "epoch": 0.22541966426858512,
      "grad_norm": 0.595092236995697,
      "learning_rate": 0.00017721565844991643,
      "loss": 1.1941,
      "step": 282
    },
    {
      "epoch": 0.22621902478017586,
      "grad_norm": 0.5247442126274109,
      "learning_rate": 0.00017705455145766607,
      "loss": 1.2034,
      "step": 283
    },
    {
      "epoch": 0.2270183852917666,
      "grad_norm": 0.5719393491744995,
      "learning_rate": 0.0001768929506618209,
      "loss": 0.9624,
      "step": 284
    },
    {
      "epoch": 0.2278177458033573,
      "grad_norm": 0.6198736429214478,
      "learning_rate": 0.00017673085709799866,
      "loss": 1.1507,
      "step": 285
    },
    {
      "epoch": 0.22861710631494805,
      "grad_norm": 0.5668182969093323,
      "learning_rate": 0.00017656827180497482,
      "loss": 1.0515,
      "step": 286
    },
    {
      "epoch": 0.22941646682653877,
      "grad_norm": 0.5910491347312927,
      "learning_rate": 0.0001764051958246762,
      "loss": 1.0355,
      "step": 287
    },
    {
      "epoch": 0.2302158273381295,
      "grad_norm": 0.6988612413406372,
      "learning_rate": 0.0001762416302021742,
      "loss": 1.1333,
      "step": 288
    },
    {
      "epoch": 0.23101518784972022,
      "grad_norm": 0.6751168370246887,
      "learning_rate": 0.000176077575985678,
      "loss": 1.2745,
      "step": 289
    },
    {
      "epoch": 0.23181454836131096,
      "grad_norm": 0.6833542585372925,
      "learning_rate": 0.00017591303422652803,
      "loss": 1.3063,
      "step": 290
    },
    {
      "epoch": 0.23261390887290168,
      "grad_norm": 0.7865142226219177,
      "learning_rate": 0.00017574800597918908,
      "loss": 1.2927,
      "step": 291
    },
    {
      "epoch": 0.23341326938449242,
      "grad_norm": 0.8319119215011597,
      "learning_rate": 0.0001755824923012436,
      "loss": 1.0652,
      "step": 292
    },
    {
      "epoch": 0.23421262989608313,
      "grad_norm": 0.801260769367218,
      "learning_rate": 0.0001754164942533849,
      "loss": 1.3349,
      "step": 293
    },
    {
      "epoch": 0.23501199040767387,
      "grad_norm": 0.9116886854171753,
      "learning_rate": 0.00017525001289941044,
      "loss": 1.373,
      "step": 294
    },
    {
      "epoch": 0.23581135091926458,
      "grad_norm": 0.9009039998054504,
      "learning_rate": 0.00017508304930621488,
      "loss": 1.1461,
      "step": 295
    },
    {
      "epoch": 0.23661071143085532,
      "grad_norm": 0.9449632167816162,
      "learning_rate": 0.00017491560454378332,
      "loss": 1.0613,
      "step": 296
    },
    {
      "epoch": 0.23741007194244604,
      "grad_norm": 0.9248090982437134,
      "learning_rate": 0.00017474767968518446,
      "loss": 1.3297,
      "step": 297
    },
    {
      "epoch": 0.23820943245403678,
      "grad_norm": 1.0803725719451904,
      "learning_rate": 0.00017457927580656366,
      "loss": 1.278,
      "step": 298
    },
    {
      "epoch": 0.2390087929656275,
      "grad_norm": 1.1624330282211304,
      "learning_rate": 0.00017441039398713608,
      "loss": 1.3367,
      "step": 299
    },
    {
      "epoch": 0.23980815347721823,
      "grad_norm": 1.5282617807388306,
      "learning_rate": 0.00017424103530917976,
      "loss": 1.433,
      "step": 300
    },
    {
      "epoch": 0.24060751398880895,
      "grad_norm": 0.3481718897819519,
      "learning_rate": 0.00017407120085802873,
      "loss": 1.0721,
      "step": 301
    },
    {
      "epoch": 0.2414068745003997,
      "grad_norm": 0.3966723084449768,
      "learning_rate": 0.00017390089172206592,
      "loss": 1.0614,
      "step": 302
    },
    {
      "epoch": 0.2422062350119904,
      "grad_norm": 0.3270397484302521,
      "learning_rate": 0.00017373010899271636,
      "loss": 1.1234,
      "step": 303
    },
    {
      "epoch": 0.24300559552358114,
      "grad_norm": 0.3478359580039978,
      "learning_rate": 0.00017355885376444007,
      "loss": 1.0732,
      "step": 304
    },
    {
      "epoch": 0.24380495603517185,
      "grad_norm": 0.38680601119995117,
      "learning_rate": 0.00017338712713472508,
      "loss": 1.0783,
      "step": 305
    },
    {
      "epoch": 0.2446043165467626,
      "grad_norm": 0.35394465923309326,
      "learning_rate": 0.00017321493020408033,
      "loss": 1.2562,
      "step": 306
    },
    {
      "epoch": 0.2454036770583533,
      "grad_norm": 0.36669933795928955,
      "learning_rate": 0.0001730422640760288,
      "loss": 1.2158,
      "step": 307
    },
    {
      "epoch": 0.24620303756994405,
      "grad_norm": 0.37237656116485596,
      "learning_rate": 0.00017286912985710023,
      "loss": 1.1921,
      "step": 308
    },
    {
      "epoch": 0.24700239808153476,
      "grad_norm": 0.35484257340431213,
      "learning_rate": 0.00017269552865682413,
      "loss": 1.1135,
      "step": 309
    },
    {
      "epoch": 0.2478017585931255,
      "grad_norm": 0.3214118480682373,
      "learning_rate": 0.00017252146158772269,
      "loss": 1.1479,
      "step": 310
    },
    {
      "epoch": 0.24860111910471622,
      "grad_norm": 0.3264860212802887,
      "learning_rate": 0.00017234692976530357,
      "loss": 1.2161,
      "step": 311
    },
    {
      "epoch": 0.24940047961630696,
      "grad_norm": 0.33951637148857117,
      "learning_rate": 0.00017217193430805287,
      "loss": 1.1978,
      "step": 312
    },
    {
      "epoch": 0.2501998401278977,
      "grad_norm": 0.30299174785614014,
      "learning_rate": 0.00017199647633742783,
      "loss": 1.1297,
      "step": 313
    },
    {
      "epoch": 0.2501998401278977,
      "eval_loss": 1.1418739557266235,
      "eval_runtime": 39.9979,
      "eval_samples_per_second": 13.176,
      "eval_steps_per_second": 6.6,
      "step": 313
    },
    {
      "epoch": 0.2509992006394884,
      "grad_norm": 0.3521738052368164,
      "learning_rate": 0.0001718205569778497,
      "loss": 1.189,
      "step": 314
    },
    {
      "epoch": 0.2517985611510791,
      "grad_norm": 0.40434741973876953,
      "learning_rate": 0.0001716441773566966,
      "loss": 1.1654,
      "step": 315
    },
    {
      "epoch": 0.25259792166266987,
      "grad_norm": 0.3887425661087036,
      "learning_rate": 0.00017146733860429612,
      "loss": 1.1563,
      "step": 316
    },
    {
      "epoch": 0.2533972821742606,
      "grad_norm": 0.36217692494392395,
      "learning_rate": 0.0001712900418539183,
      "loss": 1.1309,
      "step": 317
    },
    {
      "epoch": 0.2541966426858513,
      "grad_norm": 0.3586144745349884,
      "learning_rate": 0.00017111228824176825,
      "loss": 1.1123,
      "step": 318
    },
    {
      "epoch": 0.25499600319744203,
      "grad_norm": 0.3718055784702301,
      "learning_rate": 0.0001709340789069788,
      "loss": 1.1042,
      "step": 319
    },
    {
      "epoch": 0.2557953637090328,
      "grad_norm": 0.4410824179649353,
      "learning_rate": 0.00017075541499160334,
      "loss": 1.1729,
      "step": 320
    },
    {
      "epoch": 0.2565947242206235,
      "grad_norm": 0.42812585830688477,
      "learning_rate": 0.0001705762976406084,
      "loss": 1.1608,
      "step": 321
    },
    {
      "epoch": 0.2573940847322142,
      "grad_norm": 0.46935486793518066,
      "learning_rate": 0.00017039672800186638,
      "loss": 1.0939,
      "step": 322
    },
    {
      "epoch": 0.25819344524380494,
      "grad_norm": 0.4472469091415405,
      "learning_rate": 0.00017021670722614817,
      "loss": 1.0144,
      "step": 323
    },
    {
      "epoch": 0.2589928057553957,
      "grad_norm": 0.4422782361507416,
      "learning_rate": 0.0001700362364671157,
      "loss": 1.2359,
      "step": 324
    },
    {
      "epoch": 0.2597921662669864,
      "grad_norm": 0.4598246216773987,
      "learning_rate": 0.0001698553168813147,
      "loss": 1.3228,
      "step": 325
    },
    {
      "epoch": 0.26059152677857716,
      "grad_norm": 0.5052394866943359,
      "learning_rate": 0.00016967394962816713,
      "loss": 1.2048,
      "step": 326
    },
    {
      "epoch": 0.26139088729016785,
      "grad_norm": 0.43572553992271423,
      "learning_rate": 0.0001694921358699639,
      "loss": 0.8828,
      "step": 327
    },
    {
      "epoch": 0.2621902478017586,
      "grad_norm": 0.558404803276062,
      "learning_rate": 0.00016930987677185727,
      "loss": 1.2108,
      "step": 328
    },
    {
      "epoch": 0.26298960831334933,
      "grad_norm": 0.4867321848869324,
      "learning_rate": 0.00016912717350185355,
      "loss": 1.1716,
      "step": 329
    },
    {
      "epoch": 0.2637889688249401,
      "grad_norm": 0.5654073357582092,
      "learning_rate": 0.00016894402723080537,
      "loss": 1.2348,
      "step": 330
    },
    {
      "epoch": 0.26458832933653076,
      "grad_norm": 0.524683952331543,
      "learning_rate": 0.00016876043913240452,
      "loss": 1.1331,
      "step": 331
    },
    {
      "epoch": 0.2653876898481215,
      "grad_norm": 0.5388863682746887,
      "learning_rate": 0.00016857641038317404,
      "loss": 1.1401,
      "step": 332
    },
    {
      "epoch": 0.26618705035971224,
      "grad_norm": 0.52965247631073,
      "learning_rate": 0.00016839194216246108,
      "loss": 1.0995,
      "step": 333
    },
    {
      "epoch": 0.266986410871303,
      "grad_norm": 0.5100024342536926,
      "learning_rate": 0.00016820703565242898,
      "loss": 1.0813,
      "step": 334
    },
    {
      "epoch": 0.26778577138289367,
      "grad_norm": 0.6176280379295349,
      "learning_rate": 0.0001680216920380499,
      "loss": 0.8405,
      "step": 335
    },
    {
      "epoch": 0.2685851318944844,
      "grad_norm": 0.661065399646759,
      "learning_rate": 0.00016783591250709728,
      "loss": 1.0367,
      "step": 336
    },
    {
      "epoch": 0.26938449240607515,
      "grad_norm": 0.6393107175827026,
      "learning_rate": 0.00016764969825013793,
      "loss": 0.8476,
      "step": 337
    },
    {
      "epoch": 0.2701838529176659,
      "grad_norm": 0.8756284713745117,
      "learning_rate": 0.0001674630504605248,
      "loss": 1.1601,
      "step": 338
    },
    {
      "epoch": 0.2709832134292566,
      "grad_norm": 0.6742208003997803,
      "learning_rate": 0.00016727597033438902,
      "loss": 1.0125,
      "step": 339
    },
    {
      "epoch": 0.2717825739408473,
      "grad_norm": 0.8255277276039124,
      "learning_rate": 0.00016708845907063236,
      "loss": 1.1828,
      "step": 340
    },
    {
      "epoch": 0.27258193445243806,
      "grad_norm": 0.8534565567970276,
      "learning_rate": 0.0001669005178709195,
      "loss": 1.1659,
      "step": 341
    },
    {
      "epoch": 0.2733812949640288,
      "grad_norm": 0.9478426575660706,
      "learning_rate": 0.00016671214793967048,
      "loss": 1.133,
      "step": 342
    },
    {
      "epoch": 0.2741806554756195,
      "grad_norm": 1.1164189577102661,
      "learning_rate": 0.00016652335048405274,
      "loss": 1.125,
      "step": 343
    },
    {
      "epoch": 0.2749800159872102,
      "grad_norm": 0.866569459438324,
      "learning_rate": 0.00016633412671397357,
      "loss": 0.9521,
      "step": 344
    },
    {
      "epoch": 0.27577937649880097,
      "grad_norm": 0.9649004340171814,
      "learning_rate": 0.00016614447784207227,
      "loss": 1.264,
      "step": 345
    },
    {
      "epoch": 0.2765787370103917,
      "grad_norm": 1.1662349700927734,
      "learning_rate": 0.00016595440508371237,
      "loss": 1.4375,
      "step": 346
    },
    {
      "epoch": 0.2773780975219824,
      "grad_norm": 1.5530859231948853,
      "learning_rate": 0.00016576390965697405,
      "loss": 0.9643,
      "step": 347
    },
    {
      "epoch": 0.27817745803357313,
      "grad_norm": 1.300599455833435,
      "learning_rate": 0.00016557299278264584,
      "loss": 1.6229,
      "step": 348
    },
    {
      "epoch": 0.2789768185451639,
      "grad_norm": 1.559091567993164,
      "learning_rate": 0.0001653816556842174,
      "loss": 1.3086,
      "step": 349
    },
    {
      "epoch": 0.2797761790567546,
      "grad_norm": 2.289126396179199,
      "learning_rate": 0.00016518989958787126,
      "loss": 0.8696,
      "step": 350
    },
    {
      "epoch": 0.2805755395683453,
      "grad_norm": 0.3264933228492737,
      "learning_rate": 0.00016499772572247515,
      "loss": 0.8783,
      "step": 351
    },
    {
      "epoch": 0.28137490007993604,
      "grad_norm": 0.37487271428108215,
      "learning_rate": 0.000164805135319574,
      "loss": 1.0175,
      "step": 352
    },
    {
      "epoch": 0.2821742605915268,
      "grad_norm": 0.43567776679992676,
      "learning_rate": 0.0001646121296133822,
      "loss": 1.1585,
      "step": 353
    },
    {
      "epoch": 0.2829736211031175,
      "grad_norm": 0.3546614646911621,
      "learning_rate": 0.00016441870984077554,
      "loss": 1.095,
      "step": 354
    },
    {
      "epoch": 0.2837729816147082,
      "grad_norm": 0.39957696199417114,
      "learning_rate": 0.00016422487724128342,
      "loss": 1.0681,
      "step": 355
    },
    {
      "epoch": 0.28457234212629895,
      "grad_norm": 0.6007651686668396,
      "learning_rate": 0.00016403063305708078,
      "loss": 1.023,
      "step": 356
    },
    {
      "epoch": 0.2853717026378897,
      "grad_norm": 0.4657421112060547,
      "learning_rate": 0.0001638359785329802,
      "loss": 1.1031,
      "step": 357
    },
    {
      "epoch": 0.28617106314948043,
      "grad_norm": 0.3539028465747833,
      "learning_rate": 0.00016364091491642398,
      "loss": 1.2028,
      "step": 358
    },
    {
      "epoch": 0.2869704236610711,
      "grad_norm": 0.3230942189693451,
      "learning_rate": 0.000163445443457476,
      "loss": 1.07,
      "step": 359
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.3208749294281006,
      "learning_rate": 0.00016324956540881384,
      "loss": 1.0636,
      "step": 360
    },
    {
      "epoch": 0.2885691446842526,
      "grad_norm": 0.2991190254688263,
      "learning_rate": 0.00016305328202572076,
      "loss": 1.0855,
      "step": 361
    },
    {
      "epoch": 0.28936850519584334,
      "grad_norm": 0.3368874490261078,
      "learning_rate": 0.0001628565945660775,
      "loss": 1.0894,
      "step": 362
    },
    {
      "epoch": 0.290167865707434,
      "grad_norm": 0.34719499945640564,
      "learning_rate": 0.00016265950429035443,
      "loss": 1.0933,
      "step": 363
    },
    {
      "epoch": 0.29096722621902477,
      "grad_norm": 0.34301942586898804,
      "learning_rate": 0.00016246201246160327,
      "loss": 1.1828,
      "step": 364
    },
    {
      "epoch": 0.2917665867306155,
      "grad_norm": 0.46968960762023926,
      "learning_rate": 0.00016226412034544912,
      "loss": 1.1122,
      "step": 365
    },
    {
      "epoch": 0.29256594724220625,
      "grad_norm": 0.3344099521636963,
      "learning_rate": 0.00016206582921008233,
      "loss": 1.0661,
      "step": 366
    },
    {
      "epoch": 0.293365307753797,
      "grad_norm": 0.3538711965084076,
      "learning_rate": 0.00016186714032625035,
      "loss": 1.0411,
      "step": 367
    },
    {
      "epoch": 0.2941646682653877,
      "grad_norm": 0.4503370523452759,
      "learning_rate": 0.00016166805496724965,
      "loss": 1.1247,
      "step": 368
    },
    {
      "epoch": 0.2949640287769784,
      "grad_norm": 0.43027833104133606,
      "learning_rate": 0.00016146857440891744,
      "loss": 1.1507,
      "step": 369
    },
    {
      "epoch": 0.29576338928856916,
      "grad_norm": 0.5363488793373108,
      "learning_rate": 0.00016126869992962357,
      "loss": 1.0835,
      "step": 370
    },
    {
      "epoch": 0.2965627498001599,
      "grad_norm": 0.3750304877758026,
      "learning_rate": 0.00016106843281026237,
      "loss": 1.2127,
      "step": 371
    },
    {
      "epoch": 0.2973621103117506,
      "grad_norm": 0.4115138053894043,
      "learning_rate": 0.00016086777433424435,
      "loss": 1.081,
      "step": 372
    },
    {
      "epoch": 0.2981614708233413,
      "grad_norm": 0.4057779610157013,
      "learning_rate": 0.00016066672578748814,
      "loss": 1.0342,
      "step": 373
    },
    {
      "epoch": 0.29896083133493206,
      "grad_norm": 0.3976861238479614,
      "learning_rate": 0.00016046528845841196,
      "loss": 0.9994,
      "step": 374
    },
    {
      "epoch": 0.2997601918465228,
      "grad_norm": 0.4205765426158905,
      "learning_rate": 0.00016026346363792567,
      "loss": 0.885,
      "step": 375
    },
    {
      "epoch": 0.3005595523581135,
      "grad_norm": 0.44076278805732727,
      "learning_rate": 0.00016006125261942229,
      "loss": 1.0035,
      "step": 376
    },
    {
      "epoch": 0.30135891286970423,
      "grad_norm": 0.44243985414505005,
      "learning_rate": 0.00015985865669876988,
      "loss": 0.9194,
      "step": 377
    },
    {
      "epoch": 0.302158273381295,
      "grad_norm": 0.5455163717269897,
      "learning_rate": 0.00015965567717430304,
      "loss": 1.0047,
      "step": 378
    },
    {
      "epoch": 0.3029576338928857,
      "grad_norm": 0.47469913959503174,
      "learning_rate": 0.00015945231534681483,
      "loss": 1.0338,
      "step": 379
    },
    {
      "epoch": 0.3037569944044764,
      "grad_norm": 0.5423705577850342,
      "learning_rate": 0.00015924857251954806,
      "loss": 1.059,
      "step": 380
    },
    {
      "epoch": 0.30455635491606714,
      "grad_norm": 0.5439475178718567,
      "learning_rate": 0.00015904444999818745,
      "loss": 1.0005,
      "step": 381
    },
    {
      "epoch": 0.3053557154276579,
      "grad_norm": 0.6124017834663391,
      "learning_rate": 0.0001588399490908508,
      "loss": 0.8819,
      "step": 382
    },
    {
      "epoch": 0.3061550759392486,
      "grad_norm": 0.7043859958648682,
      "learning_rate": 0.00015863507110808086,
      "loss": 1.4554,
      "step": 383
    },
    {
      "epoch": 0.3069544364508393,
      "grad_norm": 0.5058495998382568,
      "learning_rate": 0.00015842981736283686,
      "loss": 0.8867,
      "step": 384
    },
    {
      "epoch": 0.30775379696243005,
      "grad_norm": 0.6541773080825806,
      "learning_rate": 0.0001582241891704861,
      "loss": 1.2015,
      "step": 385
    },
    {
      "epoch": 0.3085531574740208,
      "grad_norm": 0.6508180499076843,
      "learning_rate": 0.0001580181878487955,
      "loss": 1.0498,
      "step": 386
    },
    {
      "epoch": 0.30935251798561153,
      "grad_norm": 0.6798310875892639,
      "learning_rate": 0.00015781181471792322,
      "loss": 1.1951,
      "step": 387
    },
    {
      "epoch": 0.3101518784972022,
      "grad_norm": 0.6557720303535461,
      "learning_rate": 0.00015760507110041015,
      "loss": 1.0498,
      "step": 388
    },
    {
      "epoch": 0.31095123900879296,
      "grad_norm": 0.8685877323150635,
      "learning_rate": 0.00015739795832117143,
      "loss": 1.1951,
      "step": 389
    },
    {
      "epoch": 0.3117505995203837,
      "grad_norm": 0.8445819020271301,
      "learning_rate": 0.00015719047770748788,
      "loss": 0.8783,
      "step": 390
    },
    {
      "epoch": 0.31254996003197444,
      "grad_norm": 1.0820878744125366,
      "learning_rate": 0.00015698263058899778,
      "loss": 1.1618,
      "step": 391
    },
    {
      "epoch": 0.3133493205435651,
      "grad_norm": 0.8614665269851685,
      "learning_rate": 0.000156774418297688,
      "loss": 1.2297,
      "step": 392
    },
    {
      "epoch": 0.31414868105515587,
      "grad_norm": 0.8265265822410583,
      "learning_rate": 0.00015656584216788567,
      "loss": 1.2369,
      "step": 393
    },
    {
      "epoch": 0.3149480415667466,
      "grad_norm": 1.281562328338623,
      "learning_rate": 0.00015635690353624955,
      "loss": 1.1882,
      "step": 394
    },
    {
      "epoch": 0.31574740207833735,
      "grad_norm": 1.058127999305725,
      "learning_rate": 0.0001561476037417615,
      "loss": 1.3153,
      "step": 395
    },
    {
      "epoch": 0.31654676258992803,
      "grad_norm": 1.0368887186050415,
      "learning_rate": 0.00015593794412571796,
      "loss": 1.3065,
      "step": 396
    },
    {
      "epoch": 0.3173461231015188,
      "grad_norm": 1.2579238414764404,
      "learning_rate": 0.00015572792603172115,
      "loss": 1.1121,
      "step": 397
    },
    {
      "epoch": 0.3181454836131095,
      "grad_norm": 1.089697003364563,
      "learning_rate": 0.00015551755080567075,
      "loss": 1.2048,
      "step": 398
    },
    {
      "epoch": 0.31894484412470026,
      "grad_norm": 1.2540833950042725,
      "learning_rate": 0.00015530681979575496,
      "loss": 1.2861,
      "step": 399
    },
    {
      "epoch": 0.31974420463629094,
      "grad_norm": 1.39395010471344,
      "learning_rate": 0.00015509573435244214,
      "loss": 1.1636,
      "step": 400
    },
    {
      "epoch": 0.3205435651478817,
      "grad_norm": 0.3763245940208435,
      "learning_rate": 0.00015488429582847192,
      "loss": 0.8533,
      "step": 401
    },
    {
      "epoch": 0.3213429256594724,
      "grad_norm": 0.4181549847126007,
      "learning_rate": 0.00015467250557884684,
      "loss": 1.0928,
      "step": 402
    },
    {
      "epoch": 0.32214228617106316,
      "grad_norm": 0.38936108350753784,
      "learning_rate": 0.0001544603649608232,
      "loss": 1.1645,
      "step": 403
    },
    {
      "epoch": 0.3229416466826539,
      "grad_norm": 0.4016236364841461,
      "learning_rate": 0.0001542478753339029,
      "loss": 1.0839,
      "step": 404
    },
    {
      "epoch": 0.3237410071942446,
      "grad_norm": 0.43020734190940857,
      "learning_rate": 0.0001540350380598243,
      "loss": 0.968,
      "step": 405
    },
    {
      "epoch": 0.32454036770583533,
      "grad_norm": 0.38603150844573975,
      "learning_rate": 0.00015382185450255365,
      "loss": 1.1274,
      "step": 406
    },
    {
      "epoch": 0.32533972821742607,
      "grad_norm": 0.44878101348876953,
      "learning_rate": 0.00015360832602827644,
      "loss": 1.1192,
      "step": 407
    },
    {
      "epoch": 0.3261390887290168,
      "grad_norm": 0.35593459010124207,
      "learning_rate": 0.00015339445400538852,
      "loss": 1.0117,
      "step": 408
    },
    {
      "epoch": 0.3269384492406075,
      "grad_norm": 0.3497203588485718,
      "learning_rate": 0.00015318023980448735,
      "loss": 1.2231,
      "step": 409
    },
    {
      "epoch": 0.32773780975219824,
      "grad_norm": 0.40464532375335693,
      "learning_rate": 0.00015296568479836325,
      "loss": 1.2276,
      "step": 410
    },
    {
      "epoch": 0.328537170263789,
      "grad_norm": 0.3322058320045471,
      "learning_rate": 0.00015275079036199062,
      "loss": 1.1565,
      "step": 411
    },
    {
      "epoch": 0.3293365307753797,
      "grad_norm": 0.30930295586586,
      "learning_rate": 0.000152535557872519,
      "loss": 1.0212,
      "step": 412
    },
    {
      "epoch": 0.3301358912869704,
      "grad_norm": 0.3241097927093506,
      "learning_rate": 0.00015231998870926446,
      "loss": 1.1983,
      "step": 413
    },
    {
      "epoch": 0.33093525179856115,
      "grad_norm": 0.31953859329223633,
      "learning_rate": 0.0001521040842537006,
      "loss": 1.1207,
      "step": 414
    },
    {
      "epoch": 0.3317346123101519,
      "grad_norm": 0.35638073086738586,
      "learning_rate": 0.0001518878458894497,
      "loss": 1.1693,
      "step": 415
    },
    {
      "epoch": 0.33253397282174263,
      "grad_norm": 0.48129066824913025,
      "learning_rate": 0.00015167127500227397,
      "loss": 1.0441,
      "step": 416
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.3575907051563263,
      "learning_rate": 0.0001514543729800664,
      "loss": 0.885,
      "step": 417
    },
    {
      "epoch": 0.33413269384492406,
      "grad_norm": 0.35546669363975525,
      "learning_rate": 0.0001512371412128424,
      "loss": 0.9673,
      "step": 418
    },
    {
      "epoch": 0.3349320543565148,
      "grad_norm": 0.36895594000816345,
      "learning_rate": 0.00015101958109273015,
      "loss": 1.0111,
      "step": 419
    },
    {
      "epoch": 0.33573141486810554,
      "grad_norm": 0.39300018548965454,
      "learning_rate": 0.0001508016940139624,
      "loss": 1.1185,
      "step": 420
    },
    {
      "epoch": 0.3365307753796962,
      "grad_norm": 0.45900556445121765,
      "learning_rate": 0.00015058348137286703,
      "loss": 1.3187,
      "step": 421
    },
    {
      "epoch": 0.33733013589128696,
      "grad_norm": 0.3960709273815155,
      "learning_rate": 0.00015036494456785836,
      "loss": 1.1019,
      "step": 422
    },
    {
      "epoch": 0.3381294964028777,
      "grad_norm": 0.43770337104797363,
      "learning_rate": 0.00015014608499942808,
      "loss": 1.0425,
      "step": 423
    },
    {
      "epoch": 0.33892885691446845,
      "grad_norm": 0.39608171582221985,
      "learning_rate": 0.00014992690407013634,
      "loss": 0.9861,
      "step": 424
    },
    {
      "epoch": 0.33972821742605913,
      "grad_norm": 0.37925106287002563,
      "learning_rate": 0.0001497074031846027,
      "loss": 1.0193,
      "step": 425
    },
    {
      "epoch": 0.3405275779376499,
      "grad_norm": 0.40427684783935547,
      "learning_rate": 0.00014948758374949713,
      "loss": 1.1671,
      "step": 426
    },
    {
      "epoch": 0.3413269384492406,
      "grad_norm": 0.5301655530929565,
      "learning_rate": 0.0001492674471735311,
      "loss": 0.9758,
      "step": 427
    },
    {
      "epoch": 0.34212629896083135,
      "grad_norm": 0.5658469796180725,
      "learning_rate": 0.00014904699486744847,
      "loss": 1.2819,
      "step": 428
    },
    {
      "epoch": 0.34292565947242204,
      "grad_norm": 0.5009921789169312,
      "learning_rate": 0.0001488262282440163,
      "loss": 1.0126,
      "step": 429
    },
    {
      "epoch": 0.3437250199840128,
      "grad_norm": 0.49652495980262756,
      "learning_rate": 0.00014860514871801618,
      "loss": 1.1613,
      "step": 430
    },
    {
      "epoch": 0.3445243804956035,
      "grad_norm": 0.6930481195449829,
      "learning_rate": 0.0001483837577062348,
      "loss": 0.9825,
      "step": 431
    },
    {
      "epoch": 0.34532374100719426,
      "grad_norm": 0.4906662106513977,
      "learning_rate": 0.00014816205662745497,
      "loss": 1.1218,
      "step": 432
    },
    {
      "epoch": 0.34612310151878495,
      "grad_norm": 0.5959265828132629,
      "learning_rate": 0.00014794004690244669,
      "loss": 1.1655,
      "step": 433
    },
    {
      "epoch": 0.3469224620303757,
      "grad_norm": 0.6609960794448853,
      "learning_rate": 0.00014771772995395777,
      "loss": 1.1025,
      "step": 434
    },
    {
      "epoch": 0.34772182254196643,
      "grad_norm": 0.6050605177879333,
      "learning_rate": 0.00014749510720670506,
      "loss": 0.9879,
      "step": 435
    },
    {
      "epoch": 0.34852118305355717,
      "grad_norm": 0.7246385812759399,
      "learning_rate": 0.00014727218008736486,
      "loss": 1.1155,
      "step": 436
    },
    {
      "epoch": 0.34932054356514786,
      "grad_norm": 0.6366634368896484,
      "learning_rate": 0.00014704895002456424,
      "loss": 1.0055,
      "step": 437
    },
    {
      "epoch": 0.3501199040767386,
      "grad_norm": 0.7289115786552429,
      "learning_rate": 0.00014682541844887164,
      "loss": 1.2236,
      "step": 438
    },
    {
      "epoch": 0.35091926458832934,
      "grad_norm": 0.7496143579483032,
      "learning_rate": 0.00014660158679278765,
      "loss": 1.1094,
      "step": 439
    },
    {
      "epoch": 0.3517186250999201,
      "grad_norm": 0.7350897789001465,
      "learning_rate": 0.00014637745649073602,
      "loss": 1.2462,
      "step": 440
    },
    {
      "epoch": 0.35251798561151076,
      "grad_norm": 0.7020392417907715,
      "learning_rate": 0.00014615302897905434,
      "loss": 1.1669,
      "step": 441
    },
    {
      "epoch": 0.3533173461231015,
      "grad_norm": 0.7738919854164124,
      "learning_rate": 0.0001459283056959849,
      "loss": 0.989,
      "step": 442
    },
    {
      "epoch": 0.35411670663469225,
      "grad_norm": 0.8123486638069153,
      "learning_rate": 0.00014570328808166539,
      "loss": 1.0462,
      "step": 443
    },
    {
      "epoch": 0.354916067146283,
      "grad_norm": 0.8612303137779236,
      "learning_rate": 0.0001454779775781197,
      "loss": 1.3888,
      "step": 444
    },
    {
      "epoch": 0.35571542765787373,
      "grad_norm": 0.8494888544082642,
      "learning_rate": 0.00014525237562924877,
      "loss": 1.2268,
      "step": 445
    },
    {
      "epoch": 0.3565147881694644,
      "grad_norm": 1.2113531827926636,
      "learning_rate": 0.00014502648368082123,
      "loss": 1.3974,
      "step": 446
    },
    {
      "epoch": 0.35731414868105515,
      "grad_norm": 1.109397053718567,
      "learning_rate": 0.00014480030318046416,
      "loss": 1.3267,
      "step": 447
    },
    {
      "epoch": 0.3581135091926459,
      "grad_norm": 1.2456046342849731,
      "learning_rate": 0.00014457383557765386,
      "loss": 1.4305,
      "step": 448
    },
    {
      "epoch": 0.35891286970423664,
      "grad_norm": 1.5046449899673462,
      "learning_rate": 0.0001443470823237064,
      "loss": 0.9759,
      "step": 449
    },
    {
      "epoch": 0.3597122302158273,
      "grad_norm": 1.4025421142578125,
      "learning_rate": 0.0001441200448717687,
      "loss": 0.8929,
      "step": 450
    },
    {
      "epoch": 0.36051159072741806,
      "grad_norm": 0.30919286608695984,
      "learning_rate": 0.0001438927246768087,
      "loss": 0.8245,
      "step": 451
    },
    {
      "epoch": 0.3613109512390088,
      "grad_norm": 0.3811976909637451,
      "learning_rate": 0.0001436651231956064,
      "loss": 1.1732,
      "step": 452
    },
    {
      "epoch": 0.36211031175059955,
      "grad_norm": 0.3917795717716217,
      "learning_rate": 0.00014343724188674447,
      "loss": 1.1951,
      "step": 453
    },
    {
      "epoch": 0.36290967226219023,
      "grad_norm": 0.4045757055282593,
      "learning_rate": 0.00014320908221059875,
      "loss": 1.0743,
      "step": 454
    },
    {
      "epoch": 0.36370903277378097,
      "grad_norm": 0.3281409442424774,
      "learning_rate": 0.00014298064562932904,
      "loss": 1.0291,
      "step": 455
    },
    {
      "epoch": 0.3645083932853717,
      "grad_norm": 0.46397122740745544,
      "learning_rate": 0.0001427519336068698,
      "loss": 1.1945,
      "step": 456
    },
    {
      "epoch": 0.36530775379696245,
      "grad_norm": 0.35933932662010193,
      "learning_rate": 0.0001425229476089204,
      "loss": 1.1349,
      "step": 457
    },
    {
      "epoch": 0.36610711430855314,
      "grad_norm": 0.42518380284309387,
      "learning_rate": 0.00014229368910293627,
      "loss": 1.0901,
      "step": 458
    },
    {
      "epoch": 0.3669064748201439,
      "grad_norm": 0.3412696123123169,
      "learning_rate": 0.00014206415955811898,
      "loss": 1.0984,
      "step": 459
    },
    {
      "epoch": 0.3677058353317346,
      "grad_norm": 0.32191070914268494,
      "learning_rate": 0.00014183436044540713,
      "loss": 1.0522,
      "step": 460
    },
    {
      "epoch": 0.36850519584332536,
      "grad_norm": 0.34181419014930725,
      "learning_rate": 0.00014160429323746687,
      "loss": 1.0657,
      "step": 461
    },
    {
      "epoch": 0.36930455635491605,
      "grad_norm": 0.3284541368484497,
      "learning_rate": 0.00014137395940868244,
      "loss": 1.0296,
      "step": 462
    },
    {
      "epoch": 0.3701039168665068,
      "grad_norm": 0.31918108463287354,
      "learning_rate": 0.00014114336043514661,
      "loss": 1.1504,
      "step": 463
    },
    {
      "epoch": 0.37090327737809753,
      "grad_norm": 0.2991093397140503,
      "learning_rate": 0.0001409124977946515,
      "loss": 1.2299,
      "step": 464
    },
    {
      "epoch": 0.37170263788968827,
      "grad_norm": 0.3887624442577362,
      "learning_rate": 0.00014068137296667884,
      "loss": 1.3608,
      "step": 465
    },
    {
      "epoch": 0.37250199840127896,
      "grad_norm": 0.42528679966926575,
      "learning_rate": 0.0001404499874323905,
      "loss": 1.0458,
      "step": 466
    },
    {
      "epoch": 0.3733013589128697,
      "grad_norm": 0.32530438899993896,
      "learning_rate": 0.00014021834267461932,
      "loss": 1.2109,
      "step": 467
    },
    {
      "epoch": 0.37410071942446044,
      "grad_norm": 0.3990713953971863,
      "learning_rate": 0.00013998644017785913,
      "loss": 1.0526,
      "step": 468
    },
    {
      "epoch": 0.3749000799360512,
      "grad_norm": 0.3738067150115967,
      "learning_rate": 0.0001397542814282556,
      "loss": 1.2217,
      "step": 469
    },
    {
      "epoch": 0.37569944044764186,
      "grad_norm": 0.37012550234794617,
      "learning_rate": 0.0001395218679135966,
      "loss": 0.9932,
      "step": 470
    },
    {
      "epoch": 0.3764988009592326,
      "grad_norm": 0.3903065323829651,
      "learning_rate": 0.00013928920112330262,
      "loss": 1.122,
      "step": 471
    },
    {
      "epoch": 0.37729816147082335,
      "grad_norm": 0.4195614457130432,
      "learning_rate": 0.00013905628254841729,
      "loss": 1.193,
      "step": 472
    },
    {
      "epoch": 0.3780975219824141,
      "grad_norm": 0.35402435064315796,
      "learning_rate": 0.00013882311368159782,
      "loss": 0.9951,
      "step": 473
    },
    {
      "epoch": 0.37889688249400477,
      "grad_norm": 0.36403220891952515,
      "learning_rate": 0.00013858969601710533,
      "loss": 0.9178,
      "step": 474
    },
    {
      "epoch": 0.3796962430055955,
      "grad_norm": 0.40461957454681396,
      "learning_rate": 0.00013835603105079539,
      "loss": 0.9439,
      "step": 475
    },
    {
      "epoch": 0.38049560351718625,
      "grad_norm": 0.42805224657058716,
      "learning_rate": 0.00013812212028010854,
      "loss": 1.0269,
      "step": 476
    },
    {
      "epoch": 0.381294964028777,
      "grad_norm": 0.4904803931713104,
      "learning_rate": 0.00013788796520406034,
      "loss": 1.0917,
      "step": 477
    },
    {
      "epoch": 0.3820943245403677,
      "grad_norm": 0.4846837818622589,
      "learning_rate": 0.0001376535673232321,
      "loss": 1.0697,
      "step": 478
    },
    {
      "epoch": 0.3828936850519584,
      "grad_norm": 0.46769338846206665,
      "learning_rate": 0.00013741892813976116,
      "loss": 1.142,
      "step": 479
    },
    {
      "epoch": 0.38369304556354916,
      "grad_norm": 0.5554665327072144,
      "learning_rate": 0.0001371840491573312,
      "loss": 1.184,
      "step": 480
    },
    {
      "epoch": 0.3844924060751399,
      "grad_norm": 0.46426481008529663,
      "learning_rate": 0.0001369489318811626,
      "loss": 1.1334,
      "step": 481
    },
    {
      "epoch": 0.3852917665867306,
      "grad_norm": 0.5384045243263245,
      "learning_rate": 0.000136713577818003,
      "loss": 1.0772,
      "step": 482
    },
    {
      "epoch": 0.38609112709832133,
      "grad_norm": 0.5401681065559387,
      "learning_rate": 0.0001364779884761173,
      "loss": 1.1188,
      "step": 483
    },
    {
      "epoch": 0.38689048760991207,
      "grad_norm": 0.5268040299415588,
      "learning_rate": 0.0001362421653652784,
      "loss": 1.0124,
      "step": 484
    },
    {
      "epoch": 0.3876898481215028,
      "grad_norm": 0.6549224853515625,
      "learning_rate": 0.00013600610999675702,
      "loss": 1.1054,
      "step": 485
    },
    {
      "epoch": 0.38848920863309355,
      "grad_norm": 0.5715364217758179,
      "learning_rate": 0.0001357698238833126,
      "loss": 0.9463,
      "step": 486
    },
    {
      "epoch": 0.38928856914468424,
      "grad_norm": 0.5503459572792053,
      "learning_rate": 0.00013553330853918304,
      "loss": 1.1581,
      "step": 487
    },
    {
      "epoch": 0.390087929656275,
      "grad_norm": 0.6885532736778259,
      "learning_rate": 0.0001352965654800755,
      "loss": 1.0947,
      "step": 488
    },
    {
      "epoch": 0.3908872901678657,
      "grad_norm": 0.606448233127594,
      "learning_rate": 0.0001350595962231563,
      "loss": 1.1791,
      "step": 489
    },
    {
      "epoch": 0.39168665067945646,
      "grad_norm": 0.748115062713623,
      "learning_rate": 0.00013482240228704142,
      "loss": 1.191,
      "step": 490
    },
    {
      "epoch": 0.39248601119104715,
      "grad_norm": 0.7352818250656128,
      "learning_rate": 0.00013458498519178664,
      "loss": 1.1051,
      "step": 491
    },
    {
      "epoch": 0.3932853717026379,
      "grad_norm": 0.8258904814720154,
      "learning_rate": 0.00013434734645887788,
      "loss": 0.8982,
      "step": 492
    },
    {
      "epoch": 0.39408473221422863,
      "grad_norm": 0.8865075707435608,
      "learning_rate": 0.00013410948761122143,
      "loss": 1.0176,
      "step": 493
    },
    {
      "epoch": 0.39488409272581937,
      "grad_norm": 0.8664267063140869,
      "learning_rate": 0.00013387141017313418,
      "loss": 1.1245,
      "step": 494
    },
    {
      "epoch": 0.39568345323741005,
      "grad_norm": 0.8627355098724365,
      "learning_rate": 0.00013363311567033382,
      "loss": 1.1,
      "step": 495
    },
    {
      "epoch": 0.3964828137490008,
      "grad_norm": 0.766534149646759,
      "learning_rate": 0.0001333946056299292,
      "loss": 1.0663,
      "step": 496
    },
    {
      "epoch": 0.39728217426059154,
      "grad_norm": 0.9121149182319641,
      "learning_rate": 0.00013315588158041032,
      "loss": 1.1432,
      "step": 497
    },
    {
      "epoch": 0.3980815347721823,
      "grad_norm": 1.1074888706207275,
      "learning_rate": 0.0001329169450516387,
      "loss": 0.9393,
      "step": 498
    },
    {
      "epoch": 0.39888089528377296,
      "grad_norm": 1.1374878883361816,
      "learning_rate": 0.0001326777975748376,
      "loss": 1.1407,
      "step": 499
    },
    {
      "epoch": 0.3996802557953637,
      "grad_norm": 1.6384693384170532,
      "learning_rate": 0.000132438440682582,
      "loss": 1.2904,
      "step": 500
    },
    {
      "epoch": 0.40047961630695444,
      "grad_norm": 0.3537842929363251,
      "learning_rate": 0.00013219887590878903,
      "loss": 1.0584,
      "step": 501
    },
    {
      "epoch": 0.4012789768185452,
      "grad_norm": 0.3787943422794342,
      "learning_rate": 0.00013195910478870803,
      "loss": 1.0717,
      "step": 502
    },
    {
      "epoch": 0.40207833733013587,
      "grad_norm": 0.40689560770988464,
      "learning_rate": 0.00013171912885891063,
      "loss": 1.1355,
      "step": 503
    },
    {
      "epoch": 0.4028776978417266,
      "grad_norm": 0.40294623374938965,
      "learning_rate": 0.000131478949657281,
      "loss": 1.2585,
      "step": 504
    },
    {
      "epoch": 0.40367705835331735,
      "grad_norm": 0.33191537857055664,
      "learning_rate": 0.00013123856872300607,
      "loss": 0.8516,
      "step": 505
    },
    {
      "epoch": 0.4044764188649081,
      "grad_norm": 0.3889703154563904,
      "learning_rate": 0.00013099798759656545,
      "loss": 1.1512,
      "step": 506
    },
    {
      "epoch": 0.4052757793764988,
      "grad_norm": 0.36418843269348145,
      "learning_rate": 0.00013075720781972175,
      "loss": 1.2602,
      "step": 507
    },
    {
      "epoch": 0.4060751398880895,
      "grad_norm": 0.3365548551082611,
      "learning_rate": 0.00013051623093551063,
      "loss": 1.1464,
      "step": 508
    },
    {
      "epoch": 0.40687450039968026,
      "grad_norm": 0.38964754343032837,
      "learning_rate": 0.00013027505848823084,
      "loss": 1.09,
      "step": 509
    },
    {
      "epoch": 0.407673860911271,
      "grad_norm": 0.43493184447288513,
      "learning_rate": 0.00013003369202343453,
      "loss": 1.1176,
      "step": 510
    },
    {
      "epoch": 0.4084732214228617,
      "grad_norm": 0.3899182677268982,
      "learning_rate": 0.0001297921330879171,
      "loss": 1.2212,
      "step": 511
    },
    {
      "epoch": 0.40927258193445243,
      "grad_norm": 0.35002589225769043,
      "learning_rate": 0.00012955038322970736,
      "loss": 1.1259,
      "step": 512
    },
    {
      "epoch": 0.41007194244604317,
      "grad_norm": 0.3097720146179199,
      "learning_rate": 0.0001293084439980578,
      "loss": 1.1399,
      "step": 513
    },
    {
      "epoch": 0.4108713029576339,
      "grad_norm": 0.34566211700439453,
      "learning_rate": 0.00012906631694343436,
      "loss": 1.0455,
      "step": 514
    },
    {
      "epoch": 0.4116706634692246,
      "grad_norm": 0.3389396369457245,
      "learning_rate": 0.00012882400361750675,
      "loss": 1.2381,
      "step": 515
    },
    {
      "epoch": 0.41247002398081534,
      "grad_norm": 0.3703395128250122,
      "learning_rate": 0.0001285815055731383,
      "loss": 1.1114,
      "step": 516
    },
    {
      "epoch": 0.4132693844924061,
      "grad_norm": 0.36339160799980164,
      "learning_rate": 0.00012833882436437624,
      "loss": 1.0136,
      "step": 517
    },
    {
      "epoch": 0.4140687450039968,
      "grad_norm": 0.35047227144241333,
      "learning_rate": 0.00012809596154644148,
      "loss": 1.0354,
      "step": 518
    },
    {
      "epoch": 0.4148681055155875,
      "grad_norm": 0.3567598760128021,
      "learning_rate": 0.00012785291867571883,
      "loss": 1.1561,
      "step": 519
    },
    {
      "epoch": 0.41566746602717825,
      "grad_norm": 0.3623413145542145,
      "learning_rate": 0.00012760969730974694,
      "loss": 1.0828,
      "step": 520
    },
    {
      "epoch": 0.416466826538769,
      "grad_norm": 0.41852647066116333,
      "learning_rate": 0.0001273662990072083,
      "loss": 1.1553,
      "step": 521
    },
    {
      "epoch": 0.4172661870503597,
      "grad_norm": 0.41852867603302,
      "learning_rate": 0.00012712272532791946,
      "loss": 1.145,
      "step": 522
    },
    {
      "epoch": 0.4180655475619504,
      "grad_norm": 0.4308965802192688,
      "learning_rate": 0.0001268789778328207,
      "loss": 1.0496,
      "step": 523
    },
    {
      "epoch": 0.41886490807354115,
      "grad_norm": 0.4174908399581909,
      "learning_rate": 0.0001266350580839664,
      "loss": 0.9394,
      "step": 524
    },
    {
      "epoch": 0.4196642685851319,
      "grad_norm": 0.4295555353164673,
      "learning_rate": 0.0001263909676445145,
      "loss": 1.1062,
      "step": 525
    },
    {
      "epoch": 0.42046362909672264,
      "grad_norm": 0.43274104595184326,
      "learning_rate": 0.0001261467080787171,
      "loss": 1.0089,
      "step": 526
    },
    {
      "epoch": 0.4212629896083134,
      "grad_norm": 0.4415391683578491,
      "learning_rate": 0.0001259022809519101,
      "loss": 0.9486,
      "step": 527
    },
    {
      "epoch": 0.42206235011990406,
      "grad_norm": 0.4199742376804352,
      "learning_rate": 0.00012565768783050305,
      "loss": 1.1883,
      "step": 528
    },
    {
      "epoch": 0.4228617106314948,
      "grad_norm": 0.454895943403244,
      "learning_rate": 0.00012541293028196944,
      "loss": 1.1424,
      "step": 529
    },
    {
      "epoch": 0.42366107114308554,
      "grad_norm": 0.4642922878265381,
      "learning_rate": 0.0001251680098748365,
      "loss": 1.1524,
      "step": 530
    },
    {
      "epoch": 0.4244604316546763,
      "grad_norm": 0.499031126499176,
      "learning_rate": 0.00012492292817867497,
      "loss": 0.888,
      "step": 531
    },
    {
      "epoch": 0.42525979216626697,
      "grad_norm": 0.5840815305709839,
      "learning_rate": 0.00012467768676408935,
      "loss": 1.0772,
      "step": 532
    },
    {
      "epoch": 0.4260591526778577,
      "grad_norm": 0.5054577589035034,
      "learning_rate": 0.00012443228720270767,
      "loss": 0.9563,
      "step": 533
    },
    {
      "epoch": 0.42685851318944845,
      "grad_norm": 0.5701196193695068,
      "learning_rate": 0.00012418673106717143,
      "loss": 1.2029,
      "step": 534
    },
    {
      "epoch": 0.4276578737010392,
      "grad_norm": 0.5654375553131104,
      "learning_rate": 0.00012394101993112557,
      "loss": 1.2564,
      "step": 535
    },
    {
      "epoch": 0.4284572342126299,
      "grad_norm": 0.7642629742622375,
      "learning_rate": 0.00012369515536920825,
      "loss": 1.0069,
      "step": 536
    },
    {
      "epoch": 0.4292565947242206,
      "grad_norm": 0.583177387714386,
      "learning_rate": 0.00012344913895704097,
      "loss": 0.893,
      "step": 537
    },
    {
      "epoch": 0.43005595523581136,
      "grad_norm": 0.5912151336669922,
      "learning_rate": 0.00012320297227121833,
      "loss": 1.1477,
      "step": 538
    },
    {
      "epoch": 0.4308553157474021,
      "grad_norm": 0.6719471216201782,
      "learning_rate": 0.0001229566568892979,
      "loss": 1.1085,
      "step": 539
    },
    {
      "epoch": 0.4316546762589928,
      "grad_norm": 0.8098368644714355,
      "learning_rate": 0.00012271019438979023,
      "loss": 1.181,
      "step": 540
    },
    {
      "epoch": 0.4324540367705835,
      "grad_norm": 0.7867881655693054,
      "learning_rate": 0.00012246358635214868,
      "loss": 1.0798,
      "step": 541
    },
    {
      "epoch": 0.43325339728217427,
      "grad_norm": 0.6670185327529907,
      "learning_rate": 0.0001222168343567592,
      "loss": 1.0568,
      "step": 542
    },
    {
      "epoch": 0.434052757793765,
      "grad_norm": 0.7349308729171753,
      "learning_rate": 0.00012196993998493043,
      "loss": 1.1429,
      "step": 543
    },
    {
      "epoch": 0.4348521183053557,
      "grad_norm": 0.7176403999328613,
      "learning_rate": 0.00012172290481888331,
      "loss": 1.0956,
      "step": 544
    },
    {
      "epoch": 0.43565147881694644,
      "grad_norm": 0.8897795677185059,
      "learning_rate": 0.00012147573044174112,
      "loss": 1.2973,
      "step": 545
    },
    {
      "epoch": 0.4364508393285372,
      "grad_norm": 0.7887820601463318,
      "learning_rate": 0.00012122841843751924,
      "loss": 1.1597,
      "step": 546
    },
    {
      "epoch": 0.4372501998401279,
      "grad_norm": 0.8651790618896484,
      "learning_rate": 0.00012098097039111512,
      "loss": 1.0137,
      "step": 547
    },
    {
      "epoch": 0.4380495603517186,
      "grad_norm": 1.0698950290679932,
      "learning_rate": 0.00012073338788829787,
      "loss": 1.0543,
      "step": 548
    },
    {
      "epoch": 0.43884892086330934,
      "grad_norm": 1.1988959312438965,
      "learning_rate": 0.0001204856725156984,
      "loss": 1.1408,
      "step": 549
    },
    {
      "epoch": 0.4396482813749001,
      "grad_norm": 1.5389310121536255,
      "learning_rate": 0.00012023782586079908,
      "loss": 1.1225,
      "step": 550
    },
    {
      "epoch": 0.4404476418864908,
      "grad_norm": 0.41004931926727295,
      "learning_rate": 0.00011998984951192361,
      "loss": 1.0031,
      "step": 551
    },
    {
      "epoch": 0.4412470023980815,
      "grad_norm": 0.4041696786880493,
      "learning_rate": 0.00011974174505822677,
      "loss": 0.9878,
      "step": 552
    },
    {
      "epoch": 0.44204636290967225,
      "grad_norm": 0.40297624468803406,
      "learning_rate": 0.00011949351408968439,
      "loss": 1.0132,
      "step": 553
    },
    {
      "epoch": 0.442845723421263,
      "grad_norm": 0.3916489779949188,
      "learning_rate": 0.000119245158197083,
      "loss": 1.0056,
      "step": 554
    },
    {
      "epoch": 0.44364508393285373,
      "grad_norm": 0.3816269636154175,
      "learning_rate": 0.00011899667897200977,
      "loss": 1.0741,
      "step": 555
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.36485084891319275,
      "learning_rate": 0.00011874807800684215,
      "loss": 1.0796,
      "step": 556
    },
    {
      "epoch": 0.44524380495603516,
      "grad_norm": 0.36104485392570496,
      "learning_rate": 0.00011849935689473786,
      "loss": 1.2108,
      "step": 557
    },
    {
      "epoch": 0.4460431654676259,
      "grad_norm": 0.6658501029014587,
      "learning_rate": 0.00011825051722962453,
      "loss": 1.2172,
      "step": 558
    },
    {
      "epoch": 0.44684252597921664,
      "grad_norm": 0.39362889528274536,
      "learning_rate": 0.00011800156060618955,
      "loss": 1.1477,
      "step": 559
    },
    {
      "epoch": 0.44764188649080733,
      "grad_norm": 0.361454039812088,
      "learning_rate": 0.00011775248861986978,
      "loss": 1.0736,
      "step": 560
    },
    {
      "epoch": 0.44844124700239807,
      "grad_norm": 0.3387874960899353,
      "learning_rate": 0.00011750330286684153,
      "loss": 1.1703,
      "step": 561
    },
    {
      "epoch": 0.4492406075139888,
      "grad_norm": 0.3527488112449646,
      "learning_rate": 0.00011725400494401,
      "loss": 1.1032,
      "step": 562
    },
    {
      "epoch": 0.45003996802557955,
      "grad_norm": 0.35559266805648804,
      "learning_rate": 0.00011700459644899937,
      "loss": 1.2311,
      "step": 563
    },
    {
      "epoch": 0.45083932853717024,
      "grad_norm": 0.36314061284065247,
      "learning_rate": 0.00011675507898014235,
      "loss": 1.1108,
      "step": 564
    },
    {
      "epoch": 0.451638689048761,
      "grad_norm": 0.3469599187374115,
      "learning_rate": 0.00011650545413647,
      "loss": 1.1626,
      "step": 565
    },
    {
      "epoch": 0.4524380495603517,
      "grad_norm": 0.3834267258644104,
      "learning_rate": 0.00011625572351770155,
      "loss": 1.1673,
      "step": 566
    },
    {
      "epoch": 0.45323741007194246,
      "grad_norm": 0.3510596752166748,
      "learning_rate": 0.00011600588872423405,
      "loss": 1.1076,
      "step": 567
    },
    {
      "epoch": 0.4540367705835332,
      "grad_norm": 0.3876965641975403,
      "learning_rate": 0.0001157559513571322,
      "loss": 1.1704,
      "step": 568
    },
    {
      "epoch": 0.4548361310951239,
      "grad_norm": 0.3952408730983734,
      "learning_rate": 0.00011550591301811788,
      "loss": 1.0154,
      "step": 569
    },
    {
      "epoch": 0.4556354916067146,
      "grad_norm": 0.38112473487854004,
      "learning_rate": 0.00011525577530956029,
      "loss": 1.0749,
      "step": 570
    },
    {
      "epoch": 0.45643485211830537,
      "grad_norm": 0.3879120945930481,
      "learning_rate": 0.00011500553983446527,
      "loss": 1.1225,
      "step": 571
    },
    {
      "epoch": 0.4572342126298961,
      "grad_norm": 0.4533351957798004,
      "learning_rate": 0.00011475520819646526,
      "loss": 1.046,
      "step": 572
    },
    {
      "epoch": 0.4580335731414868,
      "grad_norm": 0.5451374650001526,
      "learning_rate": 0.0001145047819998089,
      "loss": 0.9717,
      "step": 573
    },
    {
      "epoch": 0.45883293365307753,
      "grad_norm": 0.5647904276847839,
      "learning_rate": 0.00011425426284935091,
      "loss": 1.075,
      "step": 574
    },
    {
      "epoch": 0.4596322941646683,
      "grad_norm": 0.4953969717025757,
      "learning_rate": 0.0001140036523505416,
      "loss": 1.186,
      "step": 575
    },
    {
      "epoch": 0.460431654676259,
      "grad_norm": 0.3667427897453308,
      "learning_rate": 0.00011375295210941674,
      "loss": 1.0549,
      "step": 576
    },
    {
      "epoch": 0.4612310151878497,
      "grad_norm": 0.4673584997653961,
      "learning_rate": 0.00011350216373258722,
      "loss": 1.004,
      "step": 577
    },
    {
      "epoch": 0.46203037569944044,
      "grad_norm": 0.6425716876983643,
      "learning_rate": 0.00011325128882722875,
      "loss": 1.2121,
      "step": 578
    },
    {
      "epoch": 0.4628297362110312,
      "grad_norm": 0.4969245493412018,
      "learning_rate": 0.00011300032900107147,
      "loss": 0.9811,
      "step": 579
    },
    {
      "epoch": 0.4636290967226219,
      "grad_norm": 0.4420992136001587,
      "learning_rate": 0.00011274928586238986,
      "loss": 1.0611,
      "step": 580
    },
    {
      "epoch": 0.4644284572342126,
      "grad_norm": 0.5042086243629456,
      "learning_rate": 0.00011249816101999227,
      "loss": 0.9749,
      "step": 581
    },
    {
      "epoch": 0.46522781774580335,
      "grad_norm": 0.5414336919784546,
      "learning_rate": 0.00011224695608321056,
      "loss": 1.072,
      "step": 582
    },
    {
      "epoch": 0.4660271782573941,
      "grad_norm": 0.6206878423690796,
      "learning_rate": 0.00011199567266188999,
      "loss": 1.3321,
      "step": 583
    },
    {
      "epoch": 0.46682653876898483,
      "grad_norm": 0.6050058603286743,
      "learning_rate": 0.00011174431236637874,
      "loss": 1.0738,
      "step": 584
    },
    {
      "epoch": 0.4676258992805755,
      "grad_norm": 0.6047278642654419,
      "learning_rate": 0.00011149287680751763,
      "loss": 1.1115,
      "step": 585
    },
    {
      "epoch": 0.46842525979216626,
      "grad_norm": 0.648656964302063,
      "learning_rate": 0.0001112413675966298,
      "loss": 1.046,
      "step": 586
    },
    {
      "epoch": 0.469224620303757,
      "grad_norm": 0.6471766829490662,
      "learning_rate": 0.0001109897863455104,
      "loss": 1.1142,
      "step": 587
    },
    {
      "epoch": 0.47002398081534774,
      "grad_norm": 0.7656954526901245,
      "learning_rate": 0.00011073813466641632,
      "loss": 0.9949,
      "step": 588
    },
    {
      "epoch": 0.4708233413269384,
      "grad_norm": 0.7737781405448914,
      "learning_rate": 0.00011048641417205563,
      "loss": 1.1068,
      "step": 589
    },
    {
      "epoch": 0.47162270183852917,
      "grad_norm": 0.6723043322563171,
      "learning_rate": 0.00011023462647557751,
      "loss": 1.0541,
      "step": 590
    },
    {
      "epoch": 0.4724220623501199,
      "grad_norm": 0.8895704746246338,
      "learning_rate": 0.0001099827731905618,
      "loss": 1.0259,
      "step": 591
    },
    {
      "epoch": 0.47322142286171065,
      "grad_norm": 0.8586205840110779,
      "learning_rate": 0.0001097308559310087,
      "loss": 1.0622,
      "step": 592
    },
    {
      "epoch": 0.47402078337330134,
      "grad_norm": 0.9140827059745789,
      "learning_rate": 0.00010947887631132823,
      "loss": 1.0914,
      "step": 593
    },
    {
      "epoch": 0.4748201438848921,
      "grad_norm": 0.9299436211585999,
      "learning_rate": 0.00010922683594633021,
      "loss": 1.1697,
      "step": 594
    },
    {
      "epoch": 0.4756195043964828,
      "grad_norm": 1.0227932929992676,
      "learning_rate": 0.00010897473645121372,
      "loss": 1.1914,
      "step": 595
    },
    {
      "epoch": 0.47641886490807356,
      "grad_norm": 0.9583956003189087,
      "learning_rate": 0.00010872257944155669,
      "loss": 1.1075,
      "step": 596
    },
    {
      "epoch": 0.47721822541966424,
      "grad_norm": 0.8131706714630127,
      "learning_rate": 0.00010847036653330568,
      "loss": 0.9999,
      "step": 597
    },
    {
      "epoch": 0.478017585931255,
      "grad_norm": 1.167009711265564,
      "learning_rate": 0.00010821809934276554,
      "loss": 1.147,
      "step": 598
    },
    {
      "epoch": 0.4788169464428457,
      "grad_norm": 1.1924556493759155,
      "learning_rate": 0.00010796577948658892,
      "loss": 1.0572,
      "step": 599
    },
    {
      "epoch": 0.47961630695443647,
      "grad_norm": 1.5610358715057373,
      "learning_rate": 0.00010771340858176594,
      "loss": 1.3864,
      "step": 600
    },
    {
      "epoch": 0.48041566746602715,
      "grad_norm": 0.38183894753456116,
      "learning_rate": 0.00010746098824561397,
      "loss": 0.9494,
      "step": 601
    },
    {
      "epoch": 0.4812150279776179,
      "grad_norm": 0.404624879360199,
      "learning_rate": 0.00010720852009576705,
      "loss": 0.8817,
      "step": 602
    },
    {
      "epoch": 0.48201438848920863,
      "grad_norm": 0.4218512773513794,
      "learning_rate": 0.00010695600575016571,
      "loss": 0.9529,
      "step": 603
    },
    {
      "epoch": 0.4828137490007994,
      "grad_norm": 0.37252408266067505,
      "learning_rate": 0.0001067034468270465,
      "loss": 0.9314,
      "step": 604
    },
    {
      "epoch": 0.48361310951239006,
      "grad_norm": 0.36367425322532654,
      "learning_rate": 0.00010645084494493165,
      "loss": 1.1066,
      "step": 605
    },
    {
      "epoch": 0.4844124700239808,
      "grad_norm": 0.4049261510372162,
      "learning_rate": 0.00010619820172261867,
      "loss": 1.3076,
      "step": 606
    },
    {
      "epoch": 0.48521183053557154,
      "grad_norm": 0.4004517197608948,
      "learning_rate": 0.00010594551877917003,
      "loss": 0.9514,
      "step": 607
    },
    {
      "epoch": 0.4860111910471623,
      "grad_norm": 0.4588954746723175,
      "learning_rate": 0.00010569279773390273,
      "loss": 1.0399,
      "step": 608
    },
    {
      "epoch": 0.486810551558753,
      "grad_norm": 0.3579251766204834,
      "learning_rate": 0.00010544004020637799,
      "loss": 1.0246,
      "step": 609
    },
    {
      "epoch": 0.4876099120703437,
      "grad_norm": 0.3608669936656952,
      "learning_rate": 0.00010518724781639073,
      "loss": 1.2545,
      "step": 610
    },
    {
      "epoch": 0.48840927258193445,
      "grad_norm": 0.3573903441429138,
      "learning_rate": 0.00010493442218395936,
      "loss": 1.1229,
      "step": 611
    },
    {
      "epoch": 0.4892086330935252,
      "grad_norm": 0.35174012184143066,
      "learning_rate": 0.0001046815649293154,
      "loss": 1.0862,
      "step": 612
    },
    {
      "epoch": 0.49000799360511593,
      "grad_norm": 0.33587905764579773,
      "learning_rate": 0.00010442867767289281,
      "loss": 1.0393,
      "step": 613
    },
    {
      "epoch": 0.4908073541167066,
      "grad_norm": 0.363019198179245,
      "learning_rate": 0.000104175762035318,
      "loss": 1.1546,
      "step": 614
    },
    {
      "epoch": 0.49160671462829736,
      "grad_norm": 0.3578447997570038,
      "learning_rate": 0.00010392281963739918,
      "loss": 1.1706,
      "step": 615
    },
    {
      "epoch": 0.4924060751398881,
      "grad_norm": 0.41954872012138367,
      "learning_rate": 0.0001036698521001161,
      "loss": 1.0753,
      "step": 616
    },
    {
      "epoch": 0.49320543565147884,
      "grad_norm": 0.36402976512908936,
      "learning_rate": 0.00010341686104460954,
      "loss": 1.0745,
      "step": 617
    },
    {
      "epoch": 0.4940047961630695,
      "grad_norm": 0.38607266545295715,
      "learning_rate": 0.00010316384809217108,
      "loss": 1.0168,
      "step": 618
    },
    {
      "epoch": 0.49480415667466027,
      "grad_norm": 0.38932761549949646,
      "learning_rate": 0.0001029108148642326,
      "loss": 1.0627,
      "step": 619
    },
    {
      "epoch": 0.495603517186251,
      "grad_norm": 0.3459804058074951,
      "learning_rate": 0.00010265776298235586,
      "loss": 1.1029,
      "step": 620
    },
    {
      "epoch": 0.49640287769784175,
      "grad_norm": 0.3945534825325012,
      "learning_rate": 0.00010240469406822221,
      "loss": 0.9676,
      "step": 621
    },
    {
      "epoch": 0.49720223820943243,
      "grad_norm": 0.4144132733345032,
      "learning_rate": 0.00010215160974362223,
      "loss": 1.1176,
      "step": 622
    },
    {
      "epoch": 0.4980015987210232,
      "grad_norm": 0.4400719404220581,
      "learning_rate": 0.0001018985116304451,
      "loss": 0.968,
      "step": 623
    },
    {
      "epoch": 0.4988009592326139,
      "grad_norm": 0.4012643098831177,
      "learning_rate": 0.00010164540135066845,
      "loss": 1.0228,
      "step": 624
    },
    {
      "epoch": 0.49960031974420466,
      "grad_norm": 0.40959033370018005,
      "learning_rate": 0.00010139228052634789,
      "loss": 1.0099,
      "step": 625
    },
    {
      "epoch": 0.5003996802557954,
      "grad_norm": 0.3941745162010193,
      "learning_rate": 0.00010113915077960658,
      "loss": 1.1203,
      "step": 626
    },
    {
      "epoch": 0.5003996802557954,
      "eval_loss": 1.0932515859603882,
      "eval_runtime": 40.3343,
      "eval_samples_per_second": 13.066,
      "eval_steps_per_second": 6.545,
      "step": 626
    }
  ],
  "logging_steps": 1,
  "max_steps": 1251,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 313,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.738333182674862e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}