{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 0.013867295956530036,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.1853,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.012901889546321085,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.1805,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.013669492621805477,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1858,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.01609097220107385,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1856,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.013183056098176767,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1817,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.016629664832822726,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1875,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.016998420819100087,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.185,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.017966540716787605,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.1813,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.021100449295056813,
      "learning_rate": 4.8e-05,
      "loss": 0.1855,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.02028394373397695,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1759,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.019646850688602367,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 0.1843,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.018519973807038036,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1638,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.0203039692195391,
      "learning_rate": 6.933333333333334e-05,
      "loss": 0.1546,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.025108108775827247,
      "learning_rate": 7.466666666666667e-05,
      "loss": 0.1513,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.022696936502719103,
      "learning_rate": 8e-05,
      "loss": 0.1544,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.021421072611534506,
      "learning_rate": 7.998916964717848e-05,
      "loss": 0.1451,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.018970644045108453,
      "learning_rate": 7.9956684453541e-05,
      "loss": 0.1442,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.017627303884716828,
      "learning_rate": 7.990256201039297e-05,
      "loss": 0.143,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.016307247867171012,
      "learning_rate": 7.982683162599218e-05,
      "loss": 0.1354,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.016933210499937162,
      "learning_rate": 7.972953430967773e-05,
      "loss": 0.1517,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.019437681875879565,
      "learning_rate": 7.961072274966282e-05,
      "loss": 0.1351,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.018097608435632177,
      "learning_rate": 7.947046128450319e-05,
      "loss": 0.1153,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.01703746896355508,
      "learning_rate": 7.930882586825653e-05,
      "loss": 0.1158,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.014184499761851526,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.1119,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.013589141702250947,
      "learning_rate": 7.892179482319297e-05,
      "loss": 0.1111,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.01265431785304965,
      "learning_rate": 7.869660877851456e-05,
      "loss": 0.1008,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.012310001938534938,
      "learning_rate": 7.845046783753276e-05,
      "loss": 0.1024,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.013194587442213667,
      "learning_rate": 7.818350528990929e-05,
      "loss": 0.0965,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.012929467665690617,
      "learning_rate": 7.789586570057317e-05,
      "loss": 0.0901,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.013562172966171772,
      "learning_rate": 7.758770483143634e-05,
      "loss": 0.0816,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.012972005424762293,
      "learning_rate": 7.72591895570457e-05,
      "loss": 0.082,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.011946656736015486,
      "learning_rate": 7.69104977742177e-05,
      "loss": 0.0783,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.010983076348566467,
      "learning_rate": 7.654181830570404e-05,
      "loss": 0.0693,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.011860687476178211,
      "learning_rate": 7.615335079794083e-05,
      "loss": 0.0773,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.010295048268203811,
      "learning_rate": 7.57453056129365e-05,
      "loss": 0.0699,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.011008899849976786,
      "learning_rate": 7.531790371435709e-05,
      "loss": 0.0676,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.01099262827191461,
      "learning_rate": 7.48713765478705e-05,
      "loss": 0.068,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.01144075928969889,
      "learning_rate": 7.440596591581463e-05,
      "loss": 0.0675,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.011559738504793212,
      "learning_rate": 7.392192384625704e-05,
      "loss": 0.0724,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.010685951937090162,
      "learning_rate": 7.341951245651747e-05,
      "loss": 0.0659,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.010730412703463154,
      "learning_rate": 7.28990038112265e-05,
      "loss": 0.0683,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.01040497731721257,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.0601,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.010953737230862133,
      "learning_rate": 7.180483185979392e-05,
      "loss": 0.0587,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.01134266700054216,
      "learning_rate": 7.123176106706638e-05,
      "loss": 0.0608,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.012169930759150384,
      "learning_rate": 7.064177772475912e-05,
      "loss": 0.0537,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.012117372368886294,
      "learning_rate": 7.003520131925997e-05,
      "loss": 0.0596,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.011493362945805581,
      "learning_rate": 6.941236032239316e-05,
      "loss": 0.0518,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.012667427357429215,
      "learning_rate": 6.877359201354606e-05,
      "loss": 0.0492,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.012672963185370456,
      "learning_rate": 6.811924229702648e-05,
      "loss": 0.0469,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.012027503712436114,
      "learning_rate": 6.744966551474936e-05,
      "loss": 0.0611,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.01241776037947528,
      "learning_rate": 6.676522425435433e-05,
      "loss": 0.0463,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.012550964101096419,
      "learning_rate": 6.606628915285822e-05,
      "loss": 0.049,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.014305464340895819,
      "learning_rate": 6.53532386959484e-05,
      "loss": 0.0482,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.010918877625514677,
      "learning_rate": 6.462645901302633e-05,
      "loss": 0.0438,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.014242177154232986,
      "learning_rate": 6.388634366811146e-05,
      "loss": 0.0444,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.011055707412927284,
      "learning_rate": 6.313329344671946e-05,
      "loss": 0.0382,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.016969969910699472,
      "learning_rate": 6.236771613882987e-05,
      "loss": 0.0449,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.011366698723515563,
      "learning_rate": 6.159002631806052e-05,
      "loss": 0.0373,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.017151650453359896,
      "learning_rate": 6.0800645117168616e-05,
      "loss": 0.0418,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.01335726262467511,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0354,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.013348054069578074,
      "learning_rate": 5.918852453000986e-05,
      "loss": 0.0355,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.012168463945846324,
      "learning_rate": 5.836665813548047e-05,
      "loss": 0.0349,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.014773974937959917,
      "learning_rate": 5.75348458715631e-05,
      "loss": 0.0393,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.010961505030213247,
      "learning_rate": 5.669353817927272e-05,
      "loss": 0.062,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.013766619916071124,
      "learning_rate": 5.584319064156628e-05,
      "loss": 0.0452,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.00999943882409506,
      "learning_rate": 5.4984263736636494e-05,
      "loss": 0.0388,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.010021848155109956,
      "learning_rate": 5.4117222588554756e-05,
      "loss": 0.0333,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.012287842734195144,
      "learning_rate": 5.324253671539833e-05,
      "loss": 0.0415,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.00876898598348026,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.0375,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.012502278229612526,
      "learning_rate": 5.1472129308443616e-05,
      "loss": 0.0349,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.011494621448608858,
      "learning_rate": 5.05773664814881e-05,
      "loss": 0.0424,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.009875540218914533,
      "learning_rate": 4.967687582398671e-05,
      "loss": 0.0358,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.019131879357786475,
      "learning_rate": 4.877114496751613e-05,
      "loss": 0.0369,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.008749158641001491,
      "learning_rate": 4.786066438131321e-05,
      "loss": 0.0384,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.012382628493667357,
      "learning_rate": 4.694592710667723e-05,
      "loss": 0.0347,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.010700936803413682,
      "learning_rate": 4.602742848997933e-05,
      "loss": 0.0467,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.013556948614811628,
      "learning_rate": 4.51056659144238e-05,
      "loss": 0.041,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.009812072194877406,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.0337,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.012041745316935911,
      "learning_rate": 4.3254346986714334e-05,
      "loss": 0.0376,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.008376785046737107,
      "learning_rate": 4.2325793156419035e-05,
      "loss": 0.0375,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.00925525997823723,
      "learning_rate": 4.139597986810005e-05,
      "loss": 0.0384,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.018369237026328845,
      "learning_rate": 4.046541063205589e-05,
      "loss": 0.0482,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.008740006444976746,
      "learning_rate": 3.953458936794413e-05,
      "loss": 0.0332,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.007559314078760183,
      "learning_rate": 3.860402013189998e-05,
      "loss": 0.0419,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.010854569957394396,
      "learning_rate": 3.767420684358097e-05,
      "loss": 0.0379,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.009275365287194633,
      "learning_rate": 3.674565301328568e-05,
      "loss": 0.0313,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.008028945791512946,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.0332,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.008974697132271283,
      "learning_rate": 3.4894334085576215e-05,
      "loss": 0.0343,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.00985570950739205,
      "learning_rate": 3.397257151002068e-05,
      "loss": 0.0392,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.008425361117132067,
      "learning_rate": 3.305407289332279e-05,
      "loss": 0.0349,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.007643998944950762,
      "learning_rate": 3.213933561868679e-05,
      "loss": 0.0431,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.008881123825479958,
      "learning_rate": 3.122885503248386e-05,
      "loss": 0.0424,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.009636421141184922,
      "learning_rate": 3.0323124176013297e-05,
      "loss": 0.0339,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.008933402659247844,
      "learning_rate": 2.9422633518511926e-05,
      "loss": 0.0428,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.007694133732800659,
      "learning_rate": 2.8527870691556404e-05,
      "loss": 0.0368,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.007268939651737201,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.0406,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.00837794106214224,
      "learning_rate": 2.6757463284601682e-05,
      "loss": 0.0394,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.009508454036638019,
      "learning_rate": 2.5882777411445254e-05,
      "loss": 0.0346,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.009459391901877601,
      "learning_rate": 2.501573626336352e-05,
      "loss": 0.043,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.009173818493717014,
      "learning_rate": 2.4156809358433728e-05,
      "loss": 0.0312,
      "step": 100
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.00941229203811891,
      "learning_rate": 2.330646182072729e-05,
      "loss": 0.0331,
      "step": 101
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.007365083346589343,
      "learning_rate": 2.24651541284369e-05,
      "loss": 0.0426,
      "step": 102
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.00706600493815007,
      "learning_rate": 2.1633341864519526e-05,
      "loss": 0.0357,
      "step": 103
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.007445002617722714,
      "learning_rate": 2.0811475469990167e-05,
      "loss": 0.0357,
      "step": 104
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.007327592692598984,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.0305,
      "step": 105
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.007639736696607274,
      "learning_rate": 1.9199354882831387e-05,
      "loss": 0.0303,
      "step": 106
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.007244135568708305,
      "learning_rate": 1.8409973681939498e-05,
      "loss": 0.0297,
      "step": 107
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.006870044325088533,
      "learning_rate": 1.7632283861170135e-05,
      "loss": 0.0287,
      "step": 108
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.008426028969484384,
      "learning_rate": 1.686670655328054e-05,
      "loss": 0.0463,
      "step": 109
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.009480489929774313,
      "learning_rate": 1.6113656331888563e-05,
      "loss": 0.0295,
      "step": 110
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.007768591886098681,
      "learning_rate": 1.537354098697367e-05,
      "loss": 0.0323,
      "step": 111
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.007364492529780269,
      "learning_rate": 1.4646761304051587e-05,
      "loss": 0.0424,
      "step": 112
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.007906362382640043,
      "learning_rate": 1.3933710847141795e-05,
      "loss": 0.0324,
      "step": 113
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.008184116431354182,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.0355,
      "step": 114
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.007477261999052342,
      "learning_rate": 1.2550334485250661e-05,
      "loss": 0.0407,
      "step": 115
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.008644638902187399,
      "learning_rate": 1.1880757702973531e-05,
      "loss": 0.0434,
      "step": 116
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.007180693442126002,
      "learning_rate": 1.1226407986453963e-05,
      "loss": 0.0312,
      "step": 117
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.008740598780625835,
      "learning_rate": 1.0587639677606857e-05,
      "loss": 0.0308,
      "step": 118
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.0077033601849302935,
      "learning_rate": 9.964798680740033e-06,
      "loss": 0.0344,
      "step": 119
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.007494742448079472,
      "learning_rate": 9.358222275240884e-06,
      "loss": 0.0313,
      "step": 120
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.0074493192306603956,
      "learning_rate": 8.768238932933632e-06,
      "loss": 0.0341,
      "step": 121
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.008666851604836807,
      "learning_rate": 8.195168140206084e-06,
      "loss": 0.0336,
      "step": 122
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.007588236403981548,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.0412,
      "step": 123
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.008254442121937522,
      "learning_rate": 7.1009961887735075e-06,
      "loss": 0.0344,
      "step": 124
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.007344754829078734,
      "learning_rate": 6.58048754348255e-06,
      "loss": 0.0366,
      "step": 125
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.007962718164512191,
      "learning_rate": 6.078076153742962e-06,
      "loss": 0.0354,
      "step": 126
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.007798731192148417,
      "learning_rate": 5.5940340841853915e-06,
      "loss": 0.0371,
      "step": 127
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.0081025309925076,
      "learning_rate": 5.128623452129508e-06,
      "loss": 0.0359,
      "step": 128
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.007653987804455616,
      "learning_rate": 4.6820962856429205e-06,
      "loss": 0.0337,
      "step": 129
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.007823360851805461,
      "learning_rate": 4.254694387063514e-06,
      "loss": 0.0307,
      "step": 130
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.00961259182463439,
      "learning_rate": 3.846649202059181e-06,
      "loss": 0.0354,
      "step": 131
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.007668814768367928,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.031,
      "step": 132
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.007890538521979762,
      "learning_rate": 3.0895022257823083e-06,
      "loss": 0.0598,
      "step": 133
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.007716182957329839,
      "learning_rate": 2.7408104429543025e-06,
      "loss": 0.0354,
      "step": 134
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.007815882498435118,
      "learning_rate": 2.4122951685636674e-06,
      "loss": 0.0362,
      "step": 135
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.0072274425494613815,
      "learning_rate": 2.104134299426832e-06,
      "loss": 0.0302,
      "step": 136
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.007030434870460914,
      "learning_rate": 1.8164947100907238e-06,
      "loss": 0.0317,
      "step": 137
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.007809976006505835,
      "learning_rate": 1.5495321624672443e-06,
      "loss": 0.0296,
      "step": 138
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.008133699609415169,
      "learning_rate": 1.3033912214854482e-06,
      "loss": 0.0341,
      "step": 139
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.00946122317394682,
      "learning_rate": 1.0782051768070477e-06,
      "loss": 0.0394,
      "step": 140
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.008145042039505735,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.0302,
      "step": 141
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.007761856022764203,
      "learning_rate": 6.911741317434706e-07,
      "loss": 0.0361,
      "step": 142
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.008815265452742468,
      "learning_rate": 5.295387154968312e-07,
      "loss": 0.0376,
      "step": 143
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.009195174936095396,
      "learning_rate": 3.8927725033718553e-07,
      "loss": 0.0357,
      "step": 144
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.008037925444083516,
      "learning_rate": 2.704656903222791e-07,
      "loss": 0.0341,
      "step": 145
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.008201413798226587,
      "learning_rate": 1.7316837400782604e-07,
      "loss": 0.037,
      "step": 146
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.007419770149276821,
      "learning_rate": 9.74379896070321e-08,
      "loss": 0.0381,
      "step": 147
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.00814176994633773,
      "learning_rate": 4.331554645901737e-08,
      "loss": 0.0395,
      "step": 148
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.00751856569116023,
      "learning_rate": 1.0830352821531442e-08,
      "loss": 0.0308,
      "step": 149
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.007828428394699667,
      "learning_rate": 0.0,
      "loss": 0.0329,
      "step": 150
    },
    {
      "epoch": 3.0,
      "step": 150,
      "total_flos": 110976016449536.0,
      "train_loss": 0.06301471510281166,
      "train_runtime": 1253.4212,
      "train_samples_per_second": 0.957,
      "train_steps_per_second": 0.12
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 110976016449536.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}