{
  "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": 0.011809559675579825,
      "learning_rate": 5.333333333333334e-06,
      "loss": 0.183,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.01267923451031558,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 0.1875,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.012884530847067054,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1753,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.012803948042993374,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 0.1794,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.013497806292970425,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1817,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.012326804290005348,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1856,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.01631171328018395,
      "learning_rate": 3.733333333333334e-05,
      "loss": 0.1813,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.01789821165815095,
      "learning_rate": 4.266666666666667e-05,
      "loss": 0.182,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.01838453301953062,
      "learning_rate": 4.8e-05,
      "loss": 0.1792,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.02063925201456158,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.1653,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.016274389707900083,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 0.1625,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.01867902302469775,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1626,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.020161768038892157,
      "learning_rate": 6.933333333333334e-05,
      "loss": 0.152,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0217786468405877,
      "learning_rate": 7.466666666666667e-05,
      "loss": 0.1554,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.02309963188281866,
      "learning_rate": 8e-05,
      "loss": 0.1492,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.02145747731872863,
      "learning_rate": 7.998916964717848e-05,
      "loss": 0.1412,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.01805077288150445,
      "learning_rate": 7.9956684453541e-05,
      "loss": 0.1319,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.016369512181041046,
      "learning_rate": 7.990256201039297e-05,
      "loss": 0.1314,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.018291405722426157,
      "learning_rate": 7.982683162599218e-05,
      "loss": 0.1336,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.018135729510617763,
      "learning_rate": 7.972953430967773e-05,
      "loss": 0.1239,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.01893853563313568,
      "learning_rate": 7.961072274966282e-05,
      "loss": 0.1191,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.014097083600550668,
      "learning_rate": 7.947046128450319e-05,
      "loss": 0.1126,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.013691458170511199,
      "learning_rate": 7.930882586825653e-05,
      "loss": 0.1049,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.014132061716520952,
      "learning_rate": 7.912590402935223e-05,
      "loss": 0.1066,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.01639725724939301,
      "learning_rate": 7.892179482319297e-05,
      "loss": 0.1121,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.013559749513144124,
      "learning_rate": 7.869660877851456e-05,
      "loss": 0.1023,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.011940544081254969,
      "learning_rate": 7.845046783753276e-05,
      "loss": 0.0918,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.012231077121265607,
      "learning_rate": 7.818350528990929e-05,
      "loss": 0.0912,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.013023783265728752,
      "learning_rate": 7.789586570057317e-05,
      "loss": 0.0777,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.012634770311997728,
      "learning_rate": 7.758770483143634e-05,
      "loss": 0.0933,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.01379614406998224,
      "learning_rate": 7.72591895570457e-05,
      "loss": 0.084,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.012745395373850553,
      "learning_rate": 7.69104977742177e-05,
      "loss": 0.0694,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.012302518748909046,
      "learning_rate": 7.654181830570404e-05,
      "loss": 0.07,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.01056797537930334,
      "learning_rate": 7.615335079794083e-05,
      "loss": 0.0757,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.010860443879296976,
      "learning_rate": 7.57453056129365e-05,
      "loss": 0.067,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.009858239467399854,
      "learning_rate": 7.531790371435709e-05,
      "loss": 0.0698,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.012202971220293223,
      "learning_rate": 7.48713765478705e-05,
      "loss": 0.0676,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.009766332299900725,
      "learning_rate": 7.440596591581463e-05,
      "loss": 0.0617,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.010035953464377951,
      "learning_rate": 7.392192384625704e-05,
      "loss": 0.0586,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.008795367906736502,
      "learning_rate": 7.341951245651747e-05,
      "loss": 0.0641,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.010113806571957165,
      "learning_rate": 7.28990038112265e-05,
      "loss": 0.0639,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.010014275847274275,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.0528,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.012200574339085477,
      "learning_rate": 7.180483185979392e-05,
      "loss": 0.0581,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.010530095743640198,
      "learning_rate": 7.123176106706638e-05,
      "loss": 0.0562,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.01041122862239149,
      "learning_rate": 7.064177772475912e-05,
      "loss": 0.0539,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.012056859668374468,
      "learning_rate": 7.003520131925997e-05,
      "loss": 0.0525,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.012368863462043233,
      "learning_rate": 6.941236032239316e-05,
      "loss": 0.047,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.012258976022025418,
      "learning_rate": 6.877359201354606e-05,
      "loss": 0.0543,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.013622226660241423,
      "learning_rate": 6.811924229702648e-05,
      "loss": 0.0455,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.012980042960891657,
      "learning_rate": 6.744966551474936e-05,
      "loss": 0.0486,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.012378374004629487,
      "learning_rate": 6.676522425435433e-05,
      "loss": 0.0466,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.015317059878290412,
      "learning_rate": 6.606628915285822e-05,
      "loss": 0.0454,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.01600568768364644,
      "learning_rate": 6.53532386959484e-05,
      "loss": 0.0427,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.012535557156911917,
      "learning_rate": 6.462645901302633e-05,
      "loss": 0.036,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.015269150088188032,
      "learning_rate": 6.388634366811146e-05,
      "loss": 0.0443,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.01348708641657591,
      "learning_rate": 6.313329344671946e-05,
      "loss": 0.0395,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.013483163929589068,
      "learning_rate": 6.236771613882987e-05,
      "loss": 0.0428,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.010513312487965653,
      "learning_rate": 6.159002631806052e-05,
      "loss": 0.0452,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.01292538144043714,
      "learning_rate": 6.0800645117168616e-05,
      "loss": 0.0447,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.016066913284850035,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.0482,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.016125066803796075,
      "learning_rate": 5.918852453000986e-05,
      "loss": 0.0496,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.011577767340579134,
      "learning_rate": 5.836665813548047e-05,
      "loss": 0.0422,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.012800240962412258,
      "learning_rate": 5.75348458715631e-05,
      "loss": 0.0343,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.01898272032141443,
      "learning_rate": 5.669353817927272e-05,
      "loss": 0.0398,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.011918027065913203,
      "learning_rate": 5.584319064156628e-05,
      "loss": 0.0349,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.011300405564112754,
      "learning_rate": 5.4984263736636494e-05,
      "loss": 0.035,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.010055653277537008,
      "learning_rate": 5.4117222588554756e-05,
      "loss": 0.0328,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.013818601707812529,
      "learning_rate": 5.324253671539833e-05,
      "loss": 0.0357,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.009627679629392703,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.0351,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.009541748304422826,
      "learning_rate": 5.1472129308443616e-05,
      "loss": 0.0392,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.014531407344237414,
      "learning_rate": 5.05773664814881e-05,
      "loss": 0.0407,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.00842116734879857,
      "learning_rate": 4.967687582398671e-05,
      "loss": 0.0366,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.009059256192181722,
      "learning_rate": 4.877114496751613e-05,
      "loss": 0.0331,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.009603436922417382,
      "learning_rate": 4.786066438131321e-05,
      "loss": 0.0347,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.008947077858267722,
      "learning_rate": 4.694592710667723e-05,
      "loss": 0.0391,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.00904238841461903,
      "learning_rate": 4.602742848997933e-05,
      "loss": 0.0307,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.008716241203836152,
      "learning_rate": 4.51056659144238e-05,
      "loss": 0.0317,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.009352849352121143,
      "learning_rate": 4.418113853070614e-05,
      "loss": 0.0308,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.009089055965574848,
      "learning_rate": 4.3254346986714334e-05,
      "loss": 0.0329,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.010017892458095128,
      "learning_rate": 4.2325793156419035e-05,
      "loss": 0.0329,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.008742545120030757,
      "learning_rate": 4.139597986810005e-05,
      "loss": 0.0307,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.00860493976718958,
      "learning_rate": 4.046541063205589e-05,
      "loss": 0.0396,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.00931430174023112,
      "learning_rate": 3.953458936794413e-05,
      "loss": 0.0393,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.00888578979102054,
      "learning_rate": 3.860402013189998e-05,
      "loss": 0.0317,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.009611340729536759,
      "learning_rate": 3.767420684358097e-05,
      "loss": 0.0369,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.008556552177287602,
      "learning_rate": 3.674565301328568e-05,
      "loss": 0.0354,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.009278896365675238,
      "learning_rate": 3.581886146929387e-05,
      "loss": 0.0335,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.009611527536127002,
      "learning_rate": 3.4894334085576215e-05,
      "loss": 0.0343,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.008060710241196208,
      "learning_rate": 3.397257151002068e-05,
      "loss": 0.036,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.009094207109428477,
      "learning_rate": 3.305407289332279e-05,
      "loss": 0.0359,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.008559942809412288,
      "learning_rate": 3.213933561868679e-05,
      "loss": 0.0326,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.00791376826891888,
      "learning_rate": 3.122885503248386e-05,
      "loss": 0.034,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.00887567089399094,
      "learning_rate": 3.0323124176013297e-05,
      "loss": 0.0311,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.008302409801068842,
      "learning_rate": 2.9422633518511926e-05,
      "loss": 0.0399,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.009242477279704472,
      "learning_rate": 2.8527870691556404e-05,
      "loss": 0.0334,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.00787347304413256,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.0345,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.007978954411853345,
      "learning_rate": 2.6757463284601682e-05,
      "loss": 0.0309,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.00819842371278869,
      "learning_rate": 2.5882777411445254e-05,
      "loss": 0.0328,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.008144067409768785,
      "learning_rate": 2.501573626336352e-05,
      "loss": 0.027,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.00816755482732266,
      "learning_rate": 2.4156809358433728e-05,
      "loss": 0.0287,
      "step": 100
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.007936888539808744,
      "learning_rate": 2.330646182072729e-05,
      "loss": 0.034,
      "step": 101
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.00742323304457344,
      "learning_rate": 2.24651541284369e-05,
      "loss": 0.0334,
      "step": 102
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.007584329606622692,
      "learning_rate": 2.1633341864519526e-05,
      "loss": 0.0297,
      "step": 103
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.008233049907862973,
      "learning_rate": 2.0811475469990167e-05,
      "loss": 0.0328,
      "step": 104
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.007361573217890433,
      "learning_rate": 2.0000000000000012e-05,
      "loss": 0.0327,
      "step": 105
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.010313004335540993,
      "learning_rate": 1.9199354882831387e-05,
      "loss": 0.027,
      "step": 106
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.0068064012517587025,
      "learning_rate": 1.8409973681939498e-05,
      "loss": 0.031,
      "step": 107
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.007055978265710038,
      "learning_rate": 1.7632283861170135e-05,
      "loss": 0.0375,
      "step": 108
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.008696273154620453,
      "learning_rate": 1.686670655328054e-05,
      "loss": 0.0364,
      "step": 109
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.008281022340679688,
      "learning_rate": 1.6113656331888563e-05,
      "loss": 0.0305,
      "step": 110
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.008050166443650853,
      "learning_rate": 1.537354098697367e-05,
      "loss": 0.0344,
      "step": 111
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.006986213842700649,
      "learning_rate": 1.4646761304051587e-05,
      "loss": 0.0385,
      "step": 112
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.008152097169884078,
      "learning_rate": 1.3933710847141795e-05,
      "loss": 0.032,
      "step": 113
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.007816131769792903,
      "learning_rate": 1.3234775745645684e-05,
      "loss": 0.0323,
      "step": 114
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.00837883345884222,
      "learning_rate": 1.2550334485250661e-05,
      "loss": 0.0283,
      "step": 115
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.007573018116025318,
      "learning_rate": 1.1880757702973531e-05,
      "loss": 0.0315,
      "step": 116
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.008520888688355023,
      "learning_rate": 1.1226407986453963e-05,
      "loss": 0.0366,
      "step": 117
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.007666441826759139,
      "learning_rate": 1.0587639677606857e-05,
      "loss": 0.0294,
      "step": 118
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.008798579155204884,
      "learning_rate": 9.964798680740033e-06,
      "loss": 0.0368,
      "step": 119
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.007542500723751338,
      "learning_rate": 9.358222275240884e-06,
      "loss": 0.0325,
      "step": 120
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.00715761768853097,
      "learning_rate": 8.768238932933632e-06,
      "loss": 0.0267,
      "step": 121
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.007792710941565013,
      "learning_rate": 8.195168140206084e-06,
      "loss": 0.037,
      "step": 122
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.008283433622988591,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.0253,
      "step": 123
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.00800993069600466,
      "learning_rate": 7.1009961887735075e-06,
      "loss": 0.0315,
      "step": 124
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.007979597318034411,
      "learning_rate": 6.58048754348255e-06,
      "loss": 0.041,
      "step": 125
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.007982505635606253,
      "learning_rate": 6.078076153742962e-06,
      "loss": 0.0283,
      "step": 126
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.008455043548748454,
      "learning_rate": 5.5940340841853915e-06,
      "loss": 0.0329,
      "step": 127
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.007716234019586476,
      "learning_rate": 5.128623452129508e-06,
      "loss": 0.0342,
      "step": 128
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.008189631539331816,
      "learning_rate": 4.6820962856429205e-06,
      "loss": 0.0311,
      "step": 129
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.007087740454390236,
      "learning_rate": 4.254694387063514e-06,
      "loss": 0.034,
      "step": 130
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.007106776792416499,
      "learning_rate": 3.846649202059181e-06,
      "loss": 0.0316,
      "step": 131
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.008259208370442899,
      "learning_rate": 3.458181694295961e-06,
      "loss": 0.0332,
      "step": 132
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.007669543692492833,
      "learning_rate": 3.0895022257823083e-06,
      "loss": 0.0307,
      "step": 133
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.00846595852854611,
      "learning_rate": 2.7408104429543025e-06,
      "loss": 0.0304,
      "step": 134
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.008381316323924064,
      "learning_rate": 2.4122951685636674e-06,
      "loss": 0.0299,
      "step": 135
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.007411309551930072,
      "learning_rate": 2.104134299426832e-06,
      "loss": 0.0389,
      "step": 136
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.007590089038013297,
      "learning_rate": 1.8164947100907238e-06,
      "loss": 0.0303,
      "step": 137
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.007570178082154396,
      "learning_rate": 1.5495321624672443e-06,
      "loss": 0.0309,
      "step": 138
    },
    {
      "epoch": 2.7800000000000002,
      "grad_norm": 0.00801720138823183,
      "learning_rate": 1.3033912214854482e-06,
      "loss": 0.0363,
      "step": 139
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.009049945854210595,
      "learning_rate": 1.0782051768070477e-06,
      "loss": 0.0303,
      "step": 140
    },
    {
      "epoch": 2.82,
      "grad_norm": 0.007583454674338024,
      "learning_rate": 8.740959706477725e-07,
      "loss": 0.0295,
      "step": 141
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.008605324416906694,
      "learning_rate": 6.911741317434706e-07,
      "loss": 0.0303,
      "step": 142
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.007914830768797076,
      "learning_rate": 5.295387154968312e-07,
      "loss": 0.03,
      "step": 143
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.008779478273284052,
      "learning_rate": 3.8927725033718553e-07,
      "loss": 0.0356,
      "step": 144
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.0075567347706382276,
      "learning_rate": 2.704656903222791e-07,
      "loss": 0.0289,
      "step": 145
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.008313652283078732,
      "learning_rate": 1.7316837400782604e-07,
      "loss": 0.0247,
      "step": 146
    },
    {
      "epoch": 2.94,
      "grad_norm": 0.007447434135329211,
      "learning_rate": 9.74379896070321e-08,
      "loss": 0.0304,
      "step": 147
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.008196845998956443,
      "learning_rate": 4.331554645901737e-08,
      "loss": 0.0271,
      "step": 148
    },
    {
      "epoch": 2.98,
      "grad_norm": 0.007174897262990998,
      "learning_rate": 1.0830352821531442e-08,
      "loss": 0.0298,
      "step": 149
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.008356753401373162,
      "learning_rate": 0.0,
      "loss": 0.0334,
      "step": 150
    },
    {
      "epoch": 3.0,
      "step": 150,
      "total_flos": 114407272677376.0,
      "train_loss": 0.05942371876289447,
      "train_runtime": 1366.5375,
      "train_samples_per_second": 0.878,
      "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": 114407272677376.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}