{
  "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": 0.011533741361846905,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.1857,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0114181703283135,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.1793,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.012232295928906524,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1793,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.012992567769436872,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1747,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.012595327195600031,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1841,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.013669666154973984,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1803,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.013972374110734738,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.1901,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.01418999963797349,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.1728,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.01936720255377307,
      "learning_rate": 4.8e-05,
      "loss": 0.1762,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.01855569766003145,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1799,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.020325316446671397,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 0.1719,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.020803977740626166,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1563,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.020736338212486213,
      "learning_rate": 6.933333333333334e-05,
      "loss": 0.1566,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.02227564860198617,
      "learning_rate": 7.466666666666667e-05,
      "loss": 0.1515,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.02510885508767834,
      "learning_rate": 8e-05,
      "loss": 0.1487,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.019145676213348374,
      "learning_rate": 7.998916964717848e-05,
      "loss": 0.1426,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.018679668912230402,
      "learning_rate": 7.9956684453541e-05,
      "loss": 0.1315,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.016965873926298062,
      "learning_rate": 7.990256201039297e-05,
      "loss": 0.1285,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.016579062555963274,
      "learning_rate": 7.982683162599218e-05,
      "loss": 0.1336,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.018736249918837544,
      "learning_rate": 7.972953430967773e-05,
      "loss": 0.1245,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.015048168902431712,
      "learning_rate": 7.961072274966282e-05,
      "loss": 0.1206,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.017546746240757985,
      "learning_rate": 7.947046128450319e-05,
      "loss": 0.1133,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.015503186692115945,
      "learning_rate": 7.930882586825653e-05,
      "loss": 0.1177,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.01575043314086665,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.1147,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.01218180386501791,
      "learning_rate": 7.892179482319297e-05,
      "loss": 0.0922,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.013652361184786282,
      "learning_rate": 7.869660877851456e-05,
      "loss": 0.102,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.01133295954944864,
      "learning_rate": 7.845046783753276e-05,
      "loss": 0.0936,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.011912475150506833,
      "learning_rate": 7.818350528990929e-05,
      "loss": 0.0856,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.01224997482285458,
      "learning_rate": 7.789586570057317e-05,
      "loss": 0.082,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.013380055651404507,
      "learning_rate": 7.758770483143634e-05,
      "loss": 0.0879,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.011637633768961587,
      "learning_rate": 7.72591895570457e-05,
      "loss": 0.0828,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.011536947969068246,
      "learning_rate": 7.69104977742177e-05,
      "loss": 0.0705,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.011485755354257596,
      "learning_rate": 7.654181830570404e-05,
      "loss": 0.0673,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.010901050868582049,
      "learning_rate": 7.615335079794083e-05,
      "loss": 0.0718,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.012649307399297607,
      "learning_rate": 7.57453056129365e-05,
      "loss": 0.0772,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.010662280190118183,
      "learning_rate": 7.531790371435709e-05,
      "loss": 0.0722,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.015839532507818232,
      "learning_rate": 7.48713765478705e-05,
      "loss": 0.0625,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.0100449567851637,
      "learning_rate": 7.440596591581463e-05,
      "loss": 0.0687,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.01276870213202684,
      "learning_rate": 7.392192384625704e-05,
      "loss": 0.0689,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.009648332325354576,
      "learning_rate": 7.341951245651747e-05,
      "loss": 0.0578,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.011582952096664528,
      "learning_rate": 7.28990038112265e-05,
      "loss": 0.057,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.010535028551847814,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.057,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.009718478254773557,
      "learning_rate": 7.180483185979392e-05,
      "loss": 0.0533,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.012510968388985811,
      "learning_rate": 7.123176106706638e-05,
      "loss": 0.0564,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.01114765668240734,
      "learning_rate": 7.064177772475912e-05,
      "loss": 0.0507,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.010909502872751635,
      "learning_rate": 7.003520131925997e-05,
      "loss": 0.0589,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.012115530660611922,
      "learning_rate": 6.941236032239316e-05,
      "loss": 0.046,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.011414296301503956,
      "learning_rate": 6.877359201354606e-05,
      "loss": 0.0451,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.01285129260244732,
      "learning_rate": 6.811924229702648e-05,
      "loss": 0.0483,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.012324914929085131,
      "learning_rate": 6.744966551474936e-05,
      "loss": 0.0436,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.01629049539908866,
      "learning_rate": 6.676522425435433e-05,
      "loss": 0.0433,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.013116582612548255,
      "learning_rate": 6.606628915285822e-05,
      "loss": 0.0558,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.014600738063885068,
      "learning_rate": 6.53532386959484e-05,
      "loss": 0.0513,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.012852790380831,
      "learning_rate": 6.462645901302633e-05,
      "loss": 0.0453,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.01584367605347062,
      "learning_rate": 6.388634366811146e-05,
      "loss": 0.0396,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.014522563917463234,
      "learning_rate": 6.313329344671946e-05,
      "loss": 0.0403,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.014443281478973153,
      "learning_rate": 6.236771613882987e-05,
      "loss": 0.0385,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.011588774487606621,
      "learning_rate": 6.159002631806052e-05,
      "loss": 0.0354,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.012241602480609928,
      "learning_rate": 6.0800645117168616e-05,
      "loss": 0.0373,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.01228135092720813,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0329,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.011231289974429223,
      "learning_rate": 5.918852453000986e-05,
      "loss": 0.0388,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.011906787090568222,
      "learning_rate": 5.836665813548047e-05,
      "loss": 0.0362,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.012315968856944505,
      "learning_rate": 5.75348458715631e-05,
      "loss": 0.0314,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.010818970252895205,
      "learning_rate": 5.669353817927272e-05,
      "loss": 0.0436,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.010397671994602394,
      "learning_rate": 5.584319064156628e-05,
      "loss": 0.0416,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.012351723415005475,
      "learning_rate": 5.4984263736636494e-05,
      "loss": 0.0327,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.010850490842364906,
      "learning_rate": 5.4117222588554756e-05,
      "loss": 0.042,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.01272608356602084,
      "learning_rate": 5.324253671539833e-05,
      "loss": 0.03,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.010843531988012862,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.0323,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.012270177581520495,
      "learning_rate": 5.1472129308443616e-05,
      "loss": 0.036,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.008738236617786657,
      "learning_rate": 5.05773664814881e-05,
      "loss": 0.0271,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.016472417401249266,
      "learning_rate": 4.967687582398671e-05,
      "loss": 0.0291,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.010002929580376142,
      "learning_rate": 4.877114496751613e-05,
      "loss": 0.0318,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.009574196449977125,
      "learning_rate": 4.786066438131321e-05,
      "loss": 0.0383,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.010156777456598404,
      "learning_rate": 4.694592710667723e-05,
      "loss": 0.0336,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.013422684448294446,
      "learning_rate": 4.602742848997933e-05,
      "loss": 0.0372,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.0103409630201648,
      "learning_rate": 4.51056659144238e-05,
      "loss": 0.0366,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.012684325490123525,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.0443,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.012935759747544968,
      "learning_rate": 4.3254346986714334e-05,
      "loss": 0.0355,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.009751733385978515,
      "learning_rate": 4.2325793156419035e-05,
      "loss": 0.0347,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.009679502063496069,
      "learning_rate": 4.139597986810005e-05,
      "loss": 0.0407,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.009315628237803105,
      "learning_rate": 4.046541063205589e-05,
      "loss": 0.0419,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.012376733675580788,
      "learning_rate": 3.953458936794413e-05,
      "loss": 0.0397,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.009048606105935083,
      "learning_rate": 3.860402013189998e-05,
      "loss": 0.0336,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.010459005932045835,
      "learning_rate": 3.767420684358097e-05,
      "loss": 0.0439,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.00939796821381542,
      "learning_rate": 3.674565301328568e-05,
      "loss": 0.0294,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.007450503716989558,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.0314,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.008717740828032632,
      "learning_rate": 3.4894334085576215e-05,
      "loss": 0.0306,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.008399533970760277,
      "learning_rate": 3.397257151002068e-05,
      "loss": 0.0274,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.008896524163598086,
      "learning_rate": 3.305407289332279e-05,
      "loss": 0.0391,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.009099185193762573,
      "learning_rate": 3.213933561868679e-05,
      "loss": 0.0321,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.008607893818886068,
      "learning_rate": 3.122885503248386e-05,
      "loss": 0.0435,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.007364222555601681,
      "learning_rate": 3.0323124176013297e-05,
      "loss": 0.0296,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.008734773537874671,
      "learning_rate": 2.9422633518511926e-05,
      "loss": 0.0402,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.007673332796185802,
      "learning_rate": 2.8527870691556404e-05,
      "loss": 0.0389,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.008053171286819484,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.0403,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.007865099649005447,
      "learning_rate": 2.6757463284601682e-05,
      "loss": 0.031,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.009481180555552289,
      "learning_rate": 2.5882777411445254e-05,
      "loss": 0.0451,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.010741824998934916,
      "learning_rate": 2.501573626336352e-05,
      "loss": 0.0406,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.00861389827638987,
      "learning_rate": 2.4156809358433728e-05,
      "loss": 0.0295,
      "step": 100
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.006973113664073819,
      "learning_rate": 2.330646182072729e-05,
      "loss": 0.0331,
      "step": 101
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.00822179737634369,
      "learning_rate": 2.24651541284369e-05,
      "loss": 0.0302,
      "step": 102
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.008412187696895144,
      "learning_rate": 2.1633341864519526e-05,
      "loss": 0.0337,
      "step": 103
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.008981077383626104,
      "learning_rate": 2.0811475469990167e-05,
      "loss": 0.0271,
      "step": 104
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.007653365789329876,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.0413,
      "step": 105
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.01110449253917593,
      "learning_rate": 1.9199354882831387e-05,
      "loss": 0.0397,
      "step": 106
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.007448483618991412,
      "learning_rate": 1.8409973681939498e-05,
      "loss": 0.0388,
      "step": 107
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.007353338535951924,
      "learning_rate": 1.7632283861170135e-05,
      "loss": 0.0274,
      "step": 108
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.006960770135705052,
      "learning_rate": 1.686670655328054e-05,
      "loss": 0.0256,
      "step": 109
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.007433477889945605,
      "learning_rate": 1.6113656331888563e-05,
      "loss": 0.0351,
      "step": 110
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.007975252443829088,
      "learning_rate": 1.537354098697367e-05,
      "loss": 0.0299,
      "step": 111
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.008083334211776455,
      "learning_rate": 1.4646761304051587e-05,
      "loss": 0.0383,
      "step": 112
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.007692897110307389,
      "learning_rate": 1.3933710847141795e-05,
      "loss": 0.0393,
      "step": 113
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.007591360096631125,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.0288,
      "step": 114
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.008000230520159067,
      "learning_rate": 1.2550334485250661e-05,
      "loss": 0.0358,
      "step": 115
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.008597608419669833,
      "learning_rate": 1.1880757702973531e-05,
      "loss": 0.0312,
      "step": 116
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.007877285473112366,
      "learning_rate": 1.1226407986453963e-05,
      "loss": 0.0269,
      "step": 117
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.008367556326829725,
      "learning_rate": 1.0587639677606857e-05,
      "loss": 0.0351,
      "step": 118
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.007508895547219534,
      "learning_rate": 9.964798680740033e-06,
      "loss": 0.0306,
      "step": 119
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.008133070034097752,
      "learning_rate": 9.358222275240884e-06,
      "loss": 0.0356,
      "step": 120
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.007135959793304952,
      "learning_rate": 8.768238932933632e-06,
      "loss": 0.0272,
      "step": 121
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.007134556369850943,
      "learning_rate": 8.195168140206084e-06,
      "loss": 0.0282,
      "step": 122
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.007759211656623642,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.0335,
      "step": 123
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.007674309381219113,
      "learning_rate": 7.1009961887735075e-06,
      "loss": 0.0314,
      "step": 124
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.008557565051198937,
      "learning_rate": 6.58048754348255e-06,
      "loss": 0.0312,
      "step": 125
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.007491352596206436,
      "learning_rate": 6.078076153742962e-06,
      "loss": 0.0277,
      "step": 126
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.008083255502928773,
      "learning_rate": 5.5940340841853915e-06,
      "loss": 0.0271,
      "step": 127
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.008297165616106128,
      "learning_rate": 5.128623452129508e-06,
      "loss": 0.0372,
      "step": 128
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.008064649617761387,
      "learning_rate": 4.6820962856429205e-06,
      "loss": 0.0388,
      "step": 129
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.008022713368147645,
      "learning_rate": 4.254694387063514e-06,
      "loss": 0.0315,
      "step": 130
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.007709624406751448,
      "learning_rate": 3.846649202059181e-06,
      "loss": 0.0283,
      "step": 131
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.009672264763332019,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.0314,
      "step": 132
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.00696854468669425,
      "learning_rate": 3.0895022257823083e-06,
      "loss": 0.0284,
      "step": 133
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.007871556555448436,
      "learning_rate": 2.7408104429543025e-06,
      "loss": 0.0333,
      "step": 134
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.0076044221014191175,
      "learning_rate": 2.4122951685636674e-06,
      "loss": 0.0389,
      "step": 135
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.007451859948643417,
      "learning_rate": 2.104134299426832e-06,
      "loss": 0.0335,
      "step": 136
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.012507088600657865,
      "learning_rate": 1.8164947100907238e-06,
      "loss": 0.0284,
      "step": 137
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.007201632592383295,
      "learning_rate": 1.5495321624672443e-06,
      "loss": 0.0288,
      "step": 138
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.007847731269820179,
      "learning_rate": 1.3033912214854482e-06,
      "loss": 0.0267,
      "step": 139
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.007940572391287577,
      "learning_rate": 1.0782051768070477e-06,
      "loss": 0.0331,
      "step": 140
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.008502034909848136,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.0383,
      "step": 141
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.008192145290128986,
      "learning_rate": 6.911741317434706e-07,
      "loss": 0.0265,
      "step": 142
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.007533648765277636,
      "learning_rate": 5.295387154968312e-07,
      "loss": 0.0346,
      "step": 143
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.008223813151374541,
      "learning_rate": 3.8927725033718553e-07,
      "loss": 0.0361,
      "step": 144
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.007880492517689467,
      "learning_rate": 2.704656903222791e-07,
      "loss": 0.0312,
      "step": 145
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.007503647532193668,
      "learning_rate": 1.7316837400782604e-07,
      "loss": 0.0403,
      "step": 146
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.007802606745675773,
      "learning_rate": 9.74379896070321e-08,
      "loss": 0.0337,
      "step": 147
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.0076012146035336296,
      "learning_rate": 4.331554645901737e-08,
      "loss": 0.0336,
      "step": 148
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.007696021207709515,
      "learning_rate": 1.0830352821531442e-08,
      "loss": 0.0277,
      "step": 149
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.007693970406450271,
      "learning_rate": 0.0,
      "loss": 0.0417,
      "step": 150
    },
    {
      "epoch": 3.0,
      "step": 150,
      "total_flos": 113529887391744.0,
      "train_loss": 0.059777319145699344,
      "train_runtime": 1362.8606,
      "train_samples_per_second": 0.881,
      "train_steps_per_second": 0.11
    }
  ],
  "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": 113529887391744.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}