{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2501998401278977,
  "eval_steps": 313,
  "global_step": 313,
  "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
    }
  ],
  "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": 1.3892953531062682e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}