{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 0,
  "global_step": 123,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008130081300813009,
      "grad_norm": 0.47265625,
      "learning_rate": 9.91869918699187e-06,
      "loss": 1.7914,
      "step": 1
    },
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 0.482421875,
      "learning_rate": 9.837398373983741e-06,
      "loss": 1.8308,
      "step": 2
    },
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 0.451171875,
      "learning_rate": 9.756097560975611e-06,
      "loss": 1.8346,
      "step": 3
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.4609375,
      "learning_rate": 9.67479674796748e-06,
      "loss": 1.8078,
      "step": 4
    },
    {
      "epoch": 0.04065040650406504,
      "grad_norm": 0.4765625,
      "learning_rate": 9.59349593495935e-06,
      "loss": 1.83,
      "step": 5
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.60546875,
      "learning_rate": 9.51219512195122e-06,
      "loss": 1.9395,
      "step": 6
    },
    {
      "epoch": 0.056910569105691054,
      "grad_norm": 0.431640625,
      "learning_rate": 9.43089430894309e-06,
      "loss": 1.8757,
      "step": 7
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.36328125,
      "learning_rate": 9.34959349593496e-06,
      "loss": 1.8858,
      "step": 8
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 0.408203125,
      "learning_rate": 9.268292682926831e-06,
      "loss": 1.6752,
      "step": 9
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 0.30859375,
      "learning_rate": 9.1869918699187e-06,
      "loss": 1.7763,
      "step": 10
    },
    {
      "epoch": 0.08943089430894309,
      "grad_norm": 0.27734375,
      "learning_rate": 9.10569105691057e-06,
      "loss": 1.7691,
      "step": 11
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.2734375,
      "learning_rate": 9.02439024390244e-06,
      "loss": 1.6506,
      "step": 12
    },
    {
      "epoch": 0.10569105691056911,
      "grad_norm": 0.310546875,
      "learning_rate": 8.94308943089431e-06,
      "loss": 1.733,
      "step": 13
    },
    {
      "epoch": 0.11382113821138211,
      "grad_norm": 0.26171875,
      "learning_rate": 8.86178861788618e-06,
      "loss": 1.7344,
      "step": 14
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 0.32421875,
      "learning_rate": 8.78048780487805e-06,
      "loss": 1.7125,
      "step": 15
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 0.3515625,
      "learning_rate": 8.69918699186992e-06,
      "loss": 1.7315,
      "step": 16
    },
    {
      "epoch": 0.13821138211382114,
      "grad_norm": 0.2470703125,
      "learning_rate": 8.617886178861789e-06,
      "loss": 1.6819,
      "step": 17
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.2333984375,
      "learning_rate": 8.536585365853658e-06,
      "loss": 1.6793,
      "step": 18
    },
    {
      "epoch": 0.15447154471544716,
      "grad_norm": 0.263671875,
      "learning_rate": 8.45528455284553e-06,
      "loss": 1.6847,
      "step": 19
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.2333984375,
      "learning_rate": 8.373983739837399e-06,
      "loss": 1.6838,
      "step": 20
    },
    {
      "epoch": 0.17073170731707318,
      "grad_norm": 0.2099609375,
      "learning_rate": 8.292682926829268e-06,
      "loss": 1.63,
      "step": 21
    },
    {
      "epoch": 0.17886178861788618,
      "grad_norm": 0.2392578125,
      "learning_rate": 8.21138211382114e-06,
      "loss": 1.6067,
      "step": 22
    },
    {
      "epoch": 0.18699186991869918,
      "grad_norm": 0.1962890625,
      "learning_rate": 8.130081300813009e-06,
      "loss": 1.638,
      "step": 23
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.1982421875,
      "learning_rate": 8.048780487804879e-06,
      "loss": 1.6493,
      "step": 24
    },
    {
      "epoch": 0.2032520325203252,
      "grad_norm": 0.19140625,
      "learning_rate": 7.967479674796748e-06,
      "loss": 1.6309,
      "step": 25
    },
    {
      "epoch": 0.21138211382113822,
      "grad_norm": 0.212890625,
      "learning_rate": 7.886178861788618e-06,
      "loss": 1.653,
      "step": 26
    },
    {
      "epoch": 0.21951219512195122,
      "grad_norm": 0.2236328125,
      "learning_rate": 7.804878048780489e-06,
      "loss": 1.5796,
      "step": 27
    },
    {
      "epoch": 0.22764227642276422,
      "grad_norm": 0.1787109375,
      "learning_rate": 7.723577235772358e-06,
      "loss": 1.6617,
      "step": 28
    },
    {
      "epoch": 0.23577235772357724,
      "grad_norm": 0.1923828125,
      "learning_rate": 7.64227642276423e-06,
      "loss": 1.6065,
      "step": 29
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.17578125,
      "learning_rate": 7.560975609756098e-06,
      "loss": 1.635,
      "step": 30
    },
    {
      "epoch": 0.25203252032520324,
      "grad_norm": 0.1787109375,
      "learning_rate": 7.4796747967479676e-06,
      "loss": 1.593,
      "step": 31
    },
    {
      "epoch": 0.2601626016260163,
      "grad_norm": 0.201171875,
      "learning_rate": 7.398373983739838e-06,
      "loss": 1.6044,
      "step": 32
    },
    {
      "epoch": 0.2682926829268293,
      "grad_norm": 0.1806640625,
      "learning_rate": 7.317073170731707e-06,
      "loss": 1.6211,
      "step": 33
    },
    {
      "epoch": 0.2764227642276423,
      "grad_norm": 0.1689453125,
      "learning_rate": 7.2357723577235786e-06,
      "loss": 1.6082,
      "step": 34
    },
    {
      "epoch": 0.2845528455284553,
      "grad_norm": 0.1875,
      "learning_rate": 7.154471544715448e-06,
      "loss": 1.5812,
      "step": 35
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.166015625,
      "learning_rate": 7.0731707317073175e-06,
      "loss": 1.6133,
      "step": 36
    },
    {
      "epoch": 0.3008130081300813,
      "grad_norm": 0.1923828125,
      "learning_rate": 6.991869918699188e-06,
      "loss": 1.5672,
      "step": 37
    },
    {
      "epoch": 0.3089430894308943,
      "grad_norm": 0.166015625,
      "learning_rate": 6.910569105691057e-06,
      "loss": 1.6293,
      "step": 38
    },
    {
      "epoch": 0.3170731707317073,
      "grad_norm": 0.197265625,
      "learning_rate": 6.829268292682928e-06,
      "loss": 1.6276,
      "step": 39
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 0.1572265625,
      "learning_rate": 6.747967479674797e-06,
      "loss": 1.5441,
      "step": 40
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.1787109375,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.564,
      "step": 41
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 0.1962890625,
      "learning_rate": 6.585365853658538e-06,
      "loss": 1.5339,
      "step": 42
    },
    {
      "epoch": 0.34959349593495936,
      "grad_norm": 0.1923828125,
      "learning_rate": 6.504065040650407e-06,
      "loss": 1.5444,
      "step": 43
    },
    {
      "epoch": 0.35772357723577236,
      "grad_norm": 0.201171875,
      "learning_rate": 6.422764227642278e-06,
      "loss": 1.5525,
      "step": 44
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 0.169921875,
      "learning_rate": 6.341463414634147e-06,
      "loss": 1.5702,
      "step": 45
    },
    {
      "epoch": 0.37398373983739835,
      "grad_norm": 0.27734375,
      "learning_rate": 6.260162601626017e-06,
      "loss": 1.6304,
      "step": 46
    },
    {
      "epoch": 0.3821138211382114,
      "grad_norm": 0.1962890625,
      "learning_rate": 6.178861788617887e-06,
      "loss": 1.5507,
      "step": 47
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.166015625,
      "learning_rate": 6.0975609756097564e-06,
      "loss": 1.4688,
      "step": 48
    },
    {
      "epoch": 0.3983739837398374,
      "grad_norm": 0.19140625,
      "learning_rate": 6.016260162601627e-06,
      "loss": 1.5426,
      "step": 49
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 0.1767578125,
      "learning_rate": 5.934959349593496e-06,
      "loss": 1.575,
      "step": 50
    },
    {
      "epoch": 0.4146341463414634,
      "grad_norm": 0.162109375,
      "learning_rate": 5.853658536585366e-06,
      "loss": 1.572,
      "step": 51
    },
    {
      "epoch": 0.42276422764227645,
      "grad_norm": 0.197265625,
      "learning_rate": 5.772357723577237e-06,
      "loss": 1.5698,
      "step": 52
    },
    {
      "epoch": 0.43089430894308944,
      "grad_norm": 0.287109375,
      "learning_rate": 5.691056910569106e-06,
      "loss": 1.5296,
      "step": 53
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 0.1708984375,
      "learning_rate": 5.609756097560977e-06,
      "loss": 1.5567,
      "step": 54
    },
    {
      "epoch": 0.44715447154471544,
      "grad_norm": 0.1708984375,
      "learning_rate": 5.528455284552846e-06,
      "loss": 1.5867,
      "step": 55
    },
    {
      "epoch": 0.45528455284552843,
      "grad_norm": 0.173828125,
      "learning_rate": 5.447154471544716e-06,
      "loss": 1.522,
      "step": 56
    },
    {
      "epoch": 0.4634146341463415,
      "grad_norm": 0.16015625,
      "learning_rate": 5.365853658536586e-06,
      "loss": 1.5443,
      "step": 57
    },
    {
      "epoch": 0.4715447154471545,
      "grad_norm": 0.2099609375,
      "learning_rate": 5.2845528455284555e-06,
      "loss": 1.5125,
      "step": 58
    },
    {
      "epoch": 0.4796747967479675,
      "grad_norm": 0.212890625,
      "learning_rate": 5.203252032520326e-06,
      "loss": 1.6069,
      "step": 59
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.15625,
      "learning_rate": 5.121951219512195e-06,
      "loss": 1.5464,
      "step": 60
    },
    {
      "epoch": 0.4959349593495935,
      "grad_norm": 0.2109375,
      "learning_rate": 5.040650406504065e-06,
      "loss": 1.5834,
      "step": 61
    },
    {
      "epoch": 0.5040650406504065,
      "grad_norm": 0.1796875,
      "learning_rate": 4.959349593495935e-06,
      "loss": 1.5126,
      "step": 62
    },
    {
      "epoch": 0.5121951219512195,
      "grad_norm": 0.177734375,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 1.5238,
      "step": 63
    },
    {
      "epoch": 0.5203252032520326,
      "grad_norm": 0.1455078125,
      "learning_rate": 4.796747967479675e-06,
      "loss": 1.5456,
      "step": 64
    },
    {
      "epoch": 0.5284552845528455,
      "grad_norm": 0.1513671875,
      "learning_rate": 4.715447154471545e-06,
      "loss": 1.5332,
      "step": 65
    },
    {
      "epoch": 0.5365853658536586,
      "grad_norm": 0.1484375,
      "learning_rate": 4.634146341463416e-06,
      "loss": 1.5083,
      "step": 66
    },
    {
      "epoch": 0.5447154471544715,
      "grad_norm": 0.150390625,
      "learning_rate": 4.552845528455285e-06,
      "loss": 1.5709,
      "step": 67
    },
    {
      "epoch": 0.5528455284552846,
      "grad_norm": 0.138671875,
      "learning_rate": 4.471544715447155e-06,
      "loss": 1.5517,
      "step": 68
    },
    {
      "epoch": 0.5609756097560976,
      "grad_norm": 0.14453125,
      "learning_rate": 4.390243902439025e-06,
      "loss": 1.4947,
      "step": 69
    },
    {
      "epoch": 0.5691056910569106,
      "grad_norm": 0.244140625,
      "learning_rate": 4.308943089430894e-06,
      "loss": 1.4829,
      "step": 70
    },
    {
      "epoch": 0.5772357723577236,
      "grad_norm": 0.1630859375,
      "learning_rate": 4.227642276422765e-06,
      "loss": 1.5183,
      "step": 71
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.171875,
      "learning_rate": 4.146341463414634e-06,
      "loss": 1.5429,
      "step": 72
    },
    {
      "epoch": 0.5934959349593496,
      "grad_norm": 0.13671875,
      "learning_rate": 4.0650406504065046e-06,
      "loss": 1.5305,
      "step": 73
    },
    {
      "epoch": 0.6016260162601627,
      "grad_norm": 0.1533203125,
      "learning_rate": 3.983739837398374e-06,
      "loss": 1.4979,
      "step": 74
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 0.1640625,
      "learning_rate": 3.902439024390244e-06,
      "loss": 1.5252,
      "step": 75
    },
    {
      "epoch": 0.6178861788617886,
      "grad_norm": 0.1591796875,
      "learning_rate": 3.821138211382115e-06,
      "loss": 1.4131,
      "step": 76
    },
    {
      "epoch": 0.6260162601626016,
      "grad_norm": 0.1484375,
      "learning_rate": 3.7398373983739838e-06,
      "loss": 1.4648,
      "step": 77
    },
    {
      "epoch": 0.6341463414634146,
      "grad_norm": 0.298828125,
      "learning_rate": 3.6585365853658537e-06,
      "loss": 1.5375,
      "step": 78
    },
    {
      "epoch": 0.6422764227642277,
      "grad_norm": 0.2119140625,
      "learning_rate": 3.577235772357724e-06,
      "loss": 1.4335,
      "step": 79
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 0.142578125,
      "learning_rate": 3.495934959349594e-06,
      "loss": 1.5052,
      "step": 80
    },
    {
      "epoch": 0.6585365853658537,
      "grad_norm": 0.1474609375,
      "learning_rate": 3.414634146341464e-06,
      "loss": 1.5025,
      "step": 81
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.248046875,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.4299,
      "step": 82
    },
    {
      "epoch": 0.6747967479674797,
      "grad_norm": 0.1689453125,
      "learning_rate": 3.2520325203252037e-06,
      "loss": 1.4853,
      "step": 83
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.138671875,
      "learning_rate": 3.1707317073170736e-06,
      "loss": 1.5545,
      "step": 84
    },
    {
      "epoch": 0.6910569105691057,
      "grad_norm": 0.158203125,
      "learning_rate": 3.0894308943089435e-06,
      "loss": 1.4281,
      "step": 85
    },
    {
      "epoch": 0.6991869918699187,
      "grad_norm": 0.1396484375,
      "learning_rate": 3.0081300813008134e-06,
      "loss": 1.4572,
      "step": 86
    },
    {
      "epoch": 0.7073170731707317,
      "grad_norm": 0.1357421875,
      "learning_rate": 2.926829268292683e-06,
      "loss": 1.4792,
      "step": 87
    },
    {
      "epoch": 0.7154471544715447,
      "grad_norm": 0.15625,
      "learning_rate": 2.845528455284553e-06,
      "loss": 1.4081,
      "step": 88
    },
    {
      "epoch": 0.7235772357723578,
      "grad_norm": 0.13671875,
      "learning_rate": 2.764227642276423e-06,
      "loss": 1.4979,
      "step": 89
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 0.1298828125,
      "learning_rate": 2.682926829268293e-06,
      "loss": 1.4775,
      "step": 90
    },
    {
      "epoch": 0.7398373983739838,
      "grad_norm": 0.140625,
      "learning_rate": 2.601626016260163e-06,
      "loss": 1.4734,
      "step": 91
    },
    {
      "epoch": 0.7479674796747967,
      "grad_norm": 0.1455078125,
      "learning_rate": 2.5203252032520324e-06,
      "loss": 1.3895,
      "step": 92
    },
    {
      "epoch": 0.7560975609756098,
      "grad_norm": 0.1611328125,
      "learning_rate": 2.4390243902439027e-06,
      "loss": 1.4338,
      "step": 93
    },
    {
      "epoch": 0.7642276422764228,
      "grad_norm": 0.150390625,
      "learning_rate": 2.3577235772357727e-06,
      "loss": 1.4483,
      "step": 94
    },
    {
      "epoch": 0.7723577235772358,
      "grad_norm": 0.1396484375,
      "learning_rate": 2.2764227642276426e-06,
      "loss": 1.4468,
      "step": 95
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.16796875,
      "learning_rate": 2.1951219512195125e-06,
      "loss": 1.4327,
      "step": 96
    },
    {
      "epoch": 0.7886178861788617,
      "grad_norm": 0.1796875,
      "learning_rate": 2.1138211382113824e-06,
      "loss": 1.5092,
      "step": 97
    },
    {
      "epoch": 0.7967479674796748,
      "grad_norm": 0.1630859375,
      "learning_rate": 2.0325203252032523e-06,
      "loss": 1.499,
      "step": 98
    },
    {
      "epoch": 0.8048780487804879,
      "grad_norm": 0.1474609375,
      "learning_rate": 1.951219512195122e-06,
      "loss": 1.4513,
      "step": 99
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 0.2099609375,
      "learning_rate": 1.8699186991869919e-06,
      "loss": 1.473,
      "step": 100
    },
    {
      "epoch": 0.8211382113821138,
      "grad_norm": 0.185546875,
      "learning_rate": 1.788617886178862e-06,
      "loss": 1.4495,
      "step": 101
    },
    {
      "epoch": 0.8292682926829268,
      "grad_norm": 0.1416015625,
      "learning_rate": 1.707317073170732e-06,
      "loss": 1.504,
      "step": 102
    },
    {
      "epoch": 0.8373983739837398,
      "grad_norm": 0.20703125,
      "learning_rate": 1.6260162601626018e-06,
      "loss": 1.4803,
      "step": 103
    },
    {
      "epoch": 0.8455284552845529,
      "grad_norm": 0.1376953125,
      "learning_rate": 1.5447154471544717e-06,
      "loss": 1.4936,
      "step": 104
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 0.1552734375,
      "learning_rate": 1.4634146341463414e-06,
      "loss": 1.5159,
      "step": 105
    },
    {
      "epoch": 0.8617886178861789,
      "grad_norm": 0.140625,
      "learning_rate": 1.3821138211382116e-06,
      "loss": 1.5042,
      "step": 106
    },
    {
      "epoch": 0.8699186991869918,
      "grad_norm": 0.380859375,
      "learning_rate": 1.3008130081300815e-06,
      "loss": 1.3785,
      "step": 107
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.15625,
      "learning_rate": 1.2195121951219514e-06,
      "loss": 1.4519,
      "step": 108
    },
    {
      "epoch": 0.8861788617886179,
      "grad_norm": 0.2080078125,
      "learning_rate": 1.1382113821138213e-06,
      "loss": 1.4291,
      "step": 109
    },
    {
      "epoch": 0.8943089430894309,
      "grad_norm": 0.158203125,
      "learning_rate": 1.0569105691056912e-06,
      "loss": 1.3927,
      "step": 110
    },
    {
      "epoch": 0.9024390243902439,
      "grad_norm": 0.138671875,
      "learning_rate": 9.75609756097561e-07,
      "loss": 1.4396,
      "step": 111
    },
    {
      "epoch": 0.9105691056910569,
      "grad_norm": 0.1416015625,
      "learning_rate": 8.94308943089431e-07,
      "loss": 1.4591,
      "step": 112
    },
    {
      "epoch": 0.9186991869918699,
      "grad_norm": 0.1748046875,
      "learning_rate": 8.130081300813009e-07,
      "loss": 1.5032,
      "step": 113
    },
    {
      "epoch": 0.926829268292683,
      "grad_norm": 0.15234375,
      "learning_rate": 7.317073170731707e-07,
      "loss": 1.4562,
      "step": 114
    },
    {
      "epoch": 0.9349593495934959,
      "grad_norm": 0.169921875,
      "learning_rate": 6.504065040650407e-07,
      "loss": 1.4683,
      "step": 115
    },
    {
      "epoch": 0.943089430894309,
      "grad_norm": 0.1396484375,
      "learning_rate": 5.691056910569106e-07,
      "loss": 1.5243,
      "step": 116
    },
    {
      "epoch": 0.9512195121951219,
      "grad_norm": 0.1884765625,
      "learning_rate": 4.878048780487805e-07,
      "loss": 1.4146,
      "step": 117
    },
    {
      "epoch": 0.959349593495935,
      "grad_norm": 0.1552734375,
      "learning_rate": 4.0650406504065046e-07,
      "loss": 1.3936,
      "step": 118
    },
    {
      "epoch": 0.967479674796748,
      "grad_norm": 0.1552734375,
      "learning_rate": 3.2520325203252037e-07,
      "loss": 1.4421,
      "step": 119
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.251953125,
      "learning_rate": 2.439024390243903e-07,
      "loss": 1.3564,
      "step": 120
    },
    {
      "epoch": 0.983739837398374,
      "grad_norm": 0.1708984375,
      "learning_rate": 1.6260162601626018e-07,
      "loss": 1.5465,
      "step": 121
    },
    {
      "epoch": 0.991869918699187,
      "grad_norm": 0.19140625,
      "learning_rate": 8.130081300813009e-08,
      "loss": 1.4304,
      "step": 122
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1474609375,
      "learning_rate": 0.0,
      "loss": 1.4253,
      "step": 123
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 123,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.31844774623445e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}