{
  "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": 0.013463530214833642,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.1803,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.011845217828748904,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.1673,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.013646502520523648,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1838,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.014002482209160422,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1774,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.013493377482137435,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1721,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.01434869045360832,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1785,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.011503842491506279,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.1656,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.016135923176932326,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.1761,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.019847658400393,
      "learning_rate": 4.8e-05,
      "loss": 0.173,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.02042397838702541,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1683,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.022637379868866818,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 0.1702,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.020638377817722386,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1528,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.01890100078032332,
      "learning_rate": 6.933333333333334e-05,
      "loss": 0.1489,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.018569125953115682,
      "learning_rate": 7.466666666666667e-05,
      "loss": 0.1539,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.025771688878431002,
      "learning_rate": 8e-05,
      "loss": 0.1418,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.027067413534118196,
      "learning_rate": 7.998916964717848e-05,
      "loss": 0.1404,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.020871459090136057,
      "learning_rate": 7.9956684453541e-05,
      "loss": 0.1331,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.017802957206296485,
      "learning_rate": 7.990256201039297e-05,
      "loss": 0.1259,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.019554541216538004,
      "learning_rate": 7.982683162599218e-05,
      "loss": 0.135,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.018795829495754864,
      "learning_rate": 7.972953430967773e-05,
      "loss": 0.1276,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.016358050768319886,
      "learning_rate": 7.961072274966282e-05,
      "loss": 0.1301,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.017193768621726464,
      "learning_rate": 7.947046128450319e-05,
      "loss": 0.1179,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.016232475621048778,
      "learning_rate": 7.930882586825653e-05,
      "loss": 0.1101,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.015515973448351462,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.1101,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.013813527108607953,
      "learning_rate": 7.892179482319297e-05,
      "loss": 0.1086,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.012759212459466058,
      "learning_rate": 7.869660877851456e-05,
      "loss": 0.0932,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.012972809924559184,
      "learning_rate": 7.845046783753276e-05,
      "loss": 0.1057,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.013083491921314276,
      "learning_rate": 7.818350528990929e-05,
      "loss": 0.0925,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.013250837145141768,
      "learning_rate": 7.789586570057317e-05,
      "loss": 0.0874,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.013047674013749193,
      "learning_rate": 7.758770483143634e-05,
      "loss": 0.0865,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.012395830787301542,
      "learning_rate": 7.72591895570457e-05,
      "loss": 0.0862,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.013268199918811964,
      "learning_rate": 7.69104977742177e-05,
      "loss": 0.0706,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.012543231011455089,
      "learning_rate": 7.654181830570404e-05,
      "loss": 0.0715,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.012325415518618531,
      "learning_rate": 7.615335079794083e-05,
      "loss": 0.0652,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.012013156626822034,
      "learning_rate": 7.57453056129365e-05,
      "loss": 0.0677,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.011578223937699257,
      "learning_rate": 7.531790371435709e-05,
      "loss": 0.0718,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.020973770213598072,
      "learning_rate": 7.48713765478705e-05,
      "loss": 0.0606,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.012398007715503166,
      "learning_rate": 7.440596591581463e-05,
      "loss": 0.0611,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.012585309232981508,
      "learning_rate": 7.392192384625704e-05,
      "loss": 0.0672,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.013661818877092995,
      "learning_rate": 7.341951245651747e-05,
      "loss": 0.0734,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.011323057898998325,
      "learning_rate": 7.28990038112265e-05,
      "loss": 0.0551,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.011241566797803007,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.0542,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.011103767406157096,
      "learning_rate": 7.180483185979392e-05,
      "loss": 0.0602,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.011347178520779239,
      "learning_rate": 7.123176106706638e-05,
      "loss": 0.0611,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.011980306071512138,
      "learning_rate": 7.064177772475912e-05,
      "loss": 0.0573,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.011035889224176854,
      "learning_rate": 7.003520131925997e-05,
      "loss": 0.0553,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.010942557638351245,
      "learning_rate": 6.941236032239316e-05,
      "loss": 0.0622,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.012905158128320694,
      "learning_rate": 6.877359201354606e-05,
      "loss": 0.0475,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.01358723299782615,
      "learning_rate": 6.811924229702648e-05,
      "loss": 0.0459,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.01292356578526783,
      "learning_rate": 6.744966551474936e-05,
      "loss": 0.0521,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.013156927655164944,
      "learning_rate": 6.676522425435433e-05,
      "loss": 0.0502,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.011465261334396565,
      "learning_rate": 6.606628915285822e-05,
      "loss": 0.0405,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.012888288443593814,
      "learning_rate": 6.53532386959484e-05,
      "loss": 0.0469,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.012458682146321785,
      "learning_rate": 6.462645901302633e-05,
      "loss": 0.0364,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.014741809217870798,
      "learning_rate": 6.388634366811146e-05,
      "loss": 0.0415,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.014743076600017132,
      "learning_rate": 6.313329344671946e-05,
      "loss": 0.0412,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.013816566888530099,
      "learning_rate": 6.236771613882987e-05,
      "loss": 0.0375,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.014281781714434769,
      "learning_rate": 6.159002631806052e-05,
      "loss": 0.0421,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.015036264776782982,
      "learning_rate": 6.0800645117168616e-05,
      "loss": 0.0367,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.014732313770867037,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0367,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.015746580273173185,
      "learning_rate": 5.918852453000986e-05,
      "loss": 0.0388,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.011505609018297528,
      "learning_rate": 5.836665813548047e-05,
      "loss": 0.0309,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.013523394573497018,
      "learning_rate": 5.75348458715631e-05,
      "loss": 0.0384,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.013660396327252718,
      "learning_rate": 5.669353817927272e-05,
      "loss": 0.0335,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.010900153907423698,
      "learning_rate": 5.584319064156628e-05,
      "loss": 0.0337,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.014787643855909591,
      "learning_rate": 5.4984263736636494e-05,
      "loss": 0.0346,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.014137328869655562,
      "learning_rate": 5.4117222588554756e-05,
      "loss": 0.0401,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.012825556687611392,
      "learning_rate": 5.324253671539833e-05,
      "loss": 0.0357,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.013666727771354612,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.0298,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.01058709054426832,
      "learning_rate": 5.1472129308443616e-05,
      "loss": 0.0386,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.011417947544411736,
      "learning_rate": 5.05773664814881e-05,
      "loss": 0.0332,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.010048152485653236,
      "learning_rate": 4.967687582398671e-05,
      "loss": 0.0462,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.013064267935706567,
      "learning_rate": 4.877114496751613e-05,
      "loss": 0.0407,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.010501256312642386,
      "learning_rate": 4.786066438131321e-05,
      "loss": 0.028,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.012824580455937696,
      "learning_rate": 4.694592710667723e-05,
      "loss": 0.039,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.010045770448064024,
      "learning_rate": 4.602742848997933e-05,
      "loss": 0.0337,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.009304104508508925,
      "learning_rate": 4.51056659144238e-05,
      "loss": 0.0271,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.008511667940565851,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.0295,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.010313717993682218,
      "learning_rate": 4.3254346986714334e-05,
      "loss": 0.0387,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.011276099426769961,
      "learning_rate": 4.2325793156419035e-05,
      "loss": 0.0341,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.00870269848965714,
      "learning_rate": 4.139597986810005e-05,
      "loss": 0.0326,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.010591385025088149,
      "learning_rate": 4.046541063205589e-05,
      "loss": 0.0518,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.009452490537278252,
      "learning_rate": 3.953458936794413e-05,
      "loss": 0.0337,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.00889622545014073,
      "learning_rate": 3.860402013189998e-05,
      "loss": 0.0289,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.01156256403355826,
      "learning_rate": 3.767420684358097e-05,
      "loss": 0.0329,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.007910664671176211,
      "learning_rate": 3.674565301328568e-05,
      "loss": 0.0307,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.009140969774923473,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.045,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.009262810966615475,
      "learning_rate": 3.4894334085576215e-05,
      "loss": 0.0377,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.009055616276602717,
      "learning_rate": 3.397257151002068e-05,
      "loss": 0.0409,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.008247336369336772,
      "learning_rate": 3.305407289332279e-05,
      "loss": 0.0446,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.010286279460512431,
      "learning_rate": 3.213933561868679e-05,
      "loss": 0.03,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.0073312361855879,
      "learning_rate": 3.122885503248386e-05,
      "loss": 0.0371,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.0074827711870533095,
      "learning_rate": 3.0323124176013297e-05,
      "loss": 0.0392,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.008407060682817082,
      "learning_rate": 2.9422633518511926e-05,
      "loss": 0.0294,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.008772905240145457,
      "learning_rate": 2.8527870691556404e-05,
      "loss": 0.0327,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.008609224359112093,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.0337,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.008482097974687538,
      "learning_rate": 2.6757463284601682e-05,
      "loss": 0.031,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.009597395228757034,
      "learning_rate": 2.5882777411445254e-05,
      "loss": 0.0279,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.0073871413378571085,
      "learning_rate": 2.501573626336352e-05,
      "loss": 0.0303,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.008542949207081041,
      "learning_rate": 2.4156809358433728e-05,
      "loss": 0.0268,
      "step": 100
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.008039767714515119,
      "learning_rate": 2.330646182072729e-05,
      "loss": 0.0298,
      "step": 101
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.00832818099174294,
      "learning_rate": 2.24651541284369e-05,
      "loss": 0.0251,
      "step": 102
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.008127682884428188,
      "learning_rate": 2.1633341864519526e-05,
      "loss": 0.0392,
      "step": 103
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.0074397378477801665,
      "learning_rate": 2.0811475469990167e-05,
      "loss": 0.0284,
      "step": 104
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.007968936979464427,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.037,
      "step": 105
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.008772241820162636,
      "learning_rate": 1.9199354882831387e-05,
      "loss": 0.0318,
      "step": 106
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.0073878820839398986,
      "learning_rate": 1.8409973681939498e-05,
      "loss": 0.0308,
      "step": 107
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.008201258713403508,
      "learning_rate": 1.7632283861170135e-05,
      "loss": 0.0347,
      "step": 108
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.006487757000052526,
      "learning_rate": 1.686670655328054e-05,
      "loss": 0.036,
      "step": 109
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.007558536768715412,
      "learning_rate": 1.6113656331888563e-05,
      "loss": 0.0375,
      "step": 110
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.0074063390205446325,
      "learning_rate": 1.537354098697367e-05,
      "loss": 0.0275,
      "step": 111
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.007766444884188422,
      "learning_rate": 1.4646761304051587e-05,
      "loss": 0.0406,
      "step": 112
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.009026775212328466,
      "learning_rate": 1.3933710847141795e-05,
      "loss": 0.0318,
      "step": 113
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.007561907922265738,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.0256,
      "step": 114
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.008310659450912314,
      "learning_rate": 1.2550334485250661e-05,
      "loss": 0.0277,
      "step": 115
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.00741197498663112,
      "learning_rate": 1.1880757702973531e-05,
      "loss": 0.0251,
      "step": 116
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.01001103856600107,
      "learning_rate": 1.1226407986453963e-05,
      "loss": 0.0408,
      "step": 117
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.007100472348024105,
      "learning_rate": 1.0587639677606857e-05,
      "loss": 0.0412,
      "step": 118
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.008303347734857159,
      "learning_rate": 9.964798680740033e-06,
      "loss": 0.0353,
      "step": 119
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.008547809317742008,
      "learning_rate": 9.358222275240884e-06,
      "loss": 0.0345,
      "step": 120
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.006851367080441287,
      "learning_rate": 8.768238932933632e-06,
      "loss": 0.0313,
      "step": 121
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.007948765791971566,
      "learning_rate": 8.195168140206084e-06,
      "loss": 0.0295,
      "step": 122
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.008138182678200167,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.0326,
      "step": 123
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.007968130024952405,
      "learning_rate": 7.1009961887735075e-06,
      "loss": 0.0336,
      "step": 124
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.0080475361878583,
      "learning_rate": 6.58048754348255e-06,
      "loss": 0.0289,
      "step": 125
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.007633389581276618,
      "learning_rate": 6.078076153742962e-06,
      "loss": 0.0463,
      "step": 126
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.008076944442631259,
      "learning_rate": 5.5940340841853915e-06,
      "loss": 0.0323,
      "step": 127
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.007194254866761241,
      "learning_rate": 5.128623452129508e-06,
      "loss": 0.0254,
      "step": 128
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.0068710943490134235,
      "learning_rate": 4.6820962856429205e-06,
      "loss": 0.0283,
      "step": 129
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.008178870082825866,
      "learning_rate": 4.254694387063514e-06,
      "loss": 0.0278,
      "step": 130
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.007802411933325013,
      "learning_rate": 3.846649202059181e-06,
      "loss": 0.0271,
      "step": 131
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.007733784569674351,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.0277,
      "step": 132
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.008249599570486847,
      "learning_rate": 3.0895022257823083e-06,
      "loss": 0.0334,
      "step": 133
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.007037780289802248,
      "learning_rate": 2.7408104429543025e-06,
      "loss": 0.0291,
      "step": 134
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.007218087412974466,
      "learning_rate": 2.4122951685636674e-06,
      "loss": 0.0324,
      "step": 135
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.009278466022756032,
      "learning_rate": 2.104134299426832e-06,
      "loss": 0.0322,
      "step": 136
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.007466935833621002,
      "learning_rate": 1.8164947100907238e-06,
      "loss": 0.0295,
      "step": 137
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.008458165307798018,
      "learning_rate": 1.5495321624672443e-06,
      "loss": 0.0319,
      "step": 138
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.008781989160313657,
      "learning_rate": 1.3033912214854482e-06,
      "loss": 0.0287,
      "step": 139
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.0073835182207144774,
      "learning_rate": 1.0782051768070477e-06,
      "loss": 0.0335,
      "step": 140
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.007888637863693208,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.0248,
      "step": 141
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.007319858976691647,
      "learning_rate": 6.911741317434706e-07,
      "loss": 0.0293,
      "step": 142
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.0095518491440252,
      "learning_rate": 5.295387154968312e-07,
      "loss": 0.0407,
      "step": 143
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.008031499783669351,
      "learning_rate": 3.8927725033718553e-07,
      "loss": 0.031,
      "step": 144
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.007008219025894124,
      "learning_rate": 2.704656903222791e-07,
      "loss": 0.0312,
      "step": 145
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.007930280010856581,
      "learning_rate": 1.7316837400782604e-07,
      "loss": 0.0267,
      "step": 146
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.00767187871829823,
      "learning_rate": 9.74379896070321e-08,
      "loss": 0.0259,
      "step": 147
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.00763909496317218,
      "learning_rate": 4.331554645901737e-08,
      "loss": 0.0288,
      "step": 148
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.00762650301509748,
      "learning_rate": 1.0830352821531442e-08,
      "loss": 0.028,
      "step": 149
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.007473447242621107,
      "learning_rate": 0.0,
      "loss": 0.0312,
      "step": 150
    },
    {
      "epoch": 3.0,
      "step": 150,
      "total_flos": 115820849201152.0,
      "train_loss": 0.058999945012231665,
      "train_runtime": 1390.7598,
      "train_samples_per_second": 0.863,
      "train_steps_per_second": 0.108
    }
  ],
  "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": 115820849201152.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}