{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.714285714285714,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.002998214285714286,
      "loss": 3.0944,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0029964285714285713,
      "loss": 2.8734,
      "step": 2
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.002994642857142857,
      "loss": 8.7265,
      "step": 3
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.002992857142857143,
      "loss": 4.7587,
      "step": 4
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.002991071428571429,
      "loss": 4.3637,
      "step": 5
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0029892857142857143,
      "loss": 3.315,
      "step": 6
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0029875,
      "loss": 3.1726,
      "step": 7
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.002985714285714286,
      "loss": 2.9938,
      "step": 8
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0029839285714285714,
      "loss": 3.0509,
      "step": 9
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0029821428571428573,
      "loss": 2.93,
      "step": 10
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.002980357142857143,
      "loss": 2.8436,
      "step": 11
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0029785714285714285,
      "loss": 2.8756,
      "step": 12
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0029767857142857144,
      "loss": 2.8528,
      "step": 13
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.002975,
      "loss": 2.8405,
      "step": 14
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.002973214285714286,
      "loss": 2.8022,
      "step": 15
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0029714285714285715,
      "loss": 2.8356,
      "step": 16
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0029696428571428573,
      "loss": 2.7915,
      "step": 17
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.002967857142857143,
      "loss": 2.7848,
      "step": 18
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0029660714285714286,
      "loss": 2.6604,
      "step": 19
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0029642857142857144,
      "loss": 2.736,
      "step": 20
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0029625000000000003,
      "loss": 2.7747,
      "step": 21
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0029607142857142857,
      "loss": 2.6958,
      "step": 22
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0029589285714285716,
      "loss": 2.7309,
      "step": 23
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0029571428571428574,
      "loss": 2.7294,
      "step": 24
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0029553571428571433,
      "loss": 2.7493,
      "step": 25
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0029535714285714287,
      "loss": 2.7351,
      "step": 26
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.002951785714285714,
      "loss": 2.6825,
      "step": 27
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00295,
      "loss": 2.6658,
      "step": 28
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0029482142857142858,
      "loss": 2.6127,
      "step": 29
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.002946428571428571,
      "loss": 2.6338,
      "step": 30
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.002944642857142857,
      "loss": 2.7094,
      "step": 31
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.002942857142857143,
      "loss": 2.6943,
      "step": 32
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0029410714285714283,
      "loss": 2.7222,
      "step": 33
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.002939285714285714,
      "loss": 2.6541,
      "step": 34
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0029375,
      "loss": 2.7111,
      "step": 35
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.002935714285714286,
      "loss": 2.5123,
      "step": 36
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0029339285714285713,
      "loss": 2.493,
      "step": 37
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.002932142857142857,
      "loss": 2.4434,
      "step": 38
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.002930357142857143,
      "loss": 2.4883,
      "step": 39
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0029285714285714284,
      "loss": 2.5004,
      "step": 40
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0029267857142857142,
      "loss": 2.4667,
      "step": 41
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.002925,
      "loss": 2.4461,
      "step": 42
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.002923214285714286,
      "loss": 2.5361,
      "step": 43
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0029214285714285713,
      "loss": 2.4597,
      "step": 44
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.002919642857142857,
      "loss": 2.4006,
      "step": 45
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.002917857142857143,
      "loss": 2.5019,
      "step": 46
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0029160714285714285,
      "loss": 2.5209,
      "step": 47
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0029142857142857143,
      "loss": 2.4753,
      "step": 48
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0029125,
      "loss": 2.4104,
      "step": 49
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0029107142857142856,
      "loss": 2.3938,
      "step": 50
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0029089285714285714,
      "loss": 2.4999,
      "step": 51
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0029071428571428573,
      "loss": 2.4292,
      "step": 52
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.002905357142857143,
      "loss": 2.4636,
      "step": 53
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0029035714285714285,
      "loss": 2.5163,
      "step": 54
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0029017857142857144,
      "loss": 2.5098,
      "step": 55
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0029000000000000002,
      "loss": 2.447,
      "step": 56
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0028982142857142856,
      "loss": 2.4262,
      "step": 57
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0028964285714285715,
      "loss": 2.5146,
      "step": 58
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0028946428571428573,
      "loss": 2.4225,
      "step": 59
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0028928571428571428,
      "loss": 2.452,
      "step": 60
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0028910714285714286,
      "loss": 2.4449,
      "step": 61
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0028892857142857145,
      "loss": 2.4984,
      "step": 62
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0028875000000000003,
      "loss": 2.4493,
      "step": 63
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0028857142857142857,
      "loss": 2.4187,
      "step": 64
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0028839285714285716,
      "loss": 2.5019,
      "step": 65
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0028821428571428574,
      "loss": 2.4274,
      "step": 66
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.002880357142857143,
      "loss": 2.4485,
      "step": 67
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0028785714285714287,
      "loss": 2.5096,
      "step": 68
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0028767857142857145,
      "loss": 2.4862,
      "step": 69
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0028750000000000004,
      "loss": 2.469,
      "step": 70
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.002873214285714286,
      "loss": 2.1795,
      "step": 71
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0028714285714285716,
      "loss": 2.1106,
      "step": 72
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0028696428571428575,
      "loss": 2.0896,
      "step": 73
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.002867857142857143,
      "loss": 2.2018,
      "step": 74
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0028660714285714288,
      "loss": 2.0803,
      "step": 75
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0028642857142857146,
      "loss": 2.1395,
      "step": 76
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0028625,
      "loss": 2.1019,
      "step": 77
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.002860714285714286,
      "loss": 2.1383,
      "step": 78
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0028589285714285713,
      "loss": 2.1109,
      "step": 79
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.002857142857142857,
      "loss": 2.0854,
      "step": 80
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0028553571428571426,
      "loss": 2.1667,
      "step": 81
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0028535714285714284,
      "loss": 2.1111,
      "step": 82
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0028517857142857143,
      "loss": 2.1032,
      "step": 83
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00285,
      "loss": 2.1708,
      "step": 84
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0028482142857142855,
      "loss": 2.1118,
      "step": 85
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0028464285714285714,
      "loss": 2.1481,
      "step": 86
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.002844642857142857,
      "loss": 2.1538,
      "step": 87
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0028428571428571426,
      "loss": 2.1843,
      "step": 88
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0028410714285714285,
      "loss": 2.1828,
      "step": 89
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0028392857142857143,
      "loss": 2.2151,
      "step": 90
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0028375,
      "loss": 2.1969,
      "step": 91
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0028357142857142856,
      "loss": 2.1509,
      "step": 92
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0028339285714285714,
      "loss": 2.2636,
      "step": 93
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0028321428571428573,
      "loss": 2.2809,
      "step": 94
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0028303571428571427,
      "loss": 2.2044,
      "step": 95
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0028285714285714286,
      "loss": 2.2064,
      "step": 96
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0028267857142857144,
      "loss": 2.2408,
      "step": 97
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.002825,
      "loss": 2.2446,
      "step": 98
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0028232142857142857,
      "loss": 2.1965,
      "step": 99
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0028214285714285715,
      "loss": 2.3093,
      "step": 100
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0028196428571428574,
      "loss": 2.2188,
      "step": 101
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0028178571428571428,
      "loss": 2.3098,
      "step": 102
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0028160714285714286,
      "loss": 2.2268,
      "step": 103
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0028142857142857145,
      "loss": 2.2574,
      "step": 104
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0028125,
      "loss": 2.2982,
      "step": 105
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0028107142857142857,
      "loss": 1.879,
      "step": 106
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0028089285714285716,
      "loss": 1.8074,
      "step": 107
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.002807142857142857,
      "loss": 1.8174,
      "step": 108
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.002805357142857143,
      "loss": 1.784,
      "step": 109
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0028035714285714287,
      "loss": 1.8469,
      "step": 110
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0028017857142857146,
      "loss": 1.8614,
      "step": 111
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0028,
      "loss": 1.8648,
      "step": 112
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.002798214285714286,
      "loss": 1.8172,
      "step": 113
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0027964285714285717,
      "loss": 1.8579,
      "step": 114
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.002794642857142857,
      "loss": 1.8261,
      "step": 115
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.002792857142857143,
      "loss": 1.8993,
      "step": 116
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0027910714285714288,
      "loss": 1.8144,
      "step": 117
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0027892857142857146,
      "loss": 1.8583,
      "step": 118
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0027875,
      "loss": 1.8589,
      "step": 119
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.002785714285714286,
      "loss": 1.9069,
      "step": 120
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0027839285714285717,
      "loss": 1.9004,
      "step": 121
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.002782142857142857,
      "loss": 1.9378,
      "step": 122
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.002780357142857143,
      "loss": 1.9161,
      "step": 123
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.002778571428571429,
      "loss": 1.9886,
      "step": 124
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0027767857142857143,
      "loss": 1.8636,
      "step": 125
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.002775,
      "loss": 1.9642,
      "step": 126
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.002773214285714286,
      "loss": 1.959,
      "step": 127
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.002771428571428572,
      "loss": 1.9787,
      "step": 128
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0027696428571428572,
      "loss": 2.0272,
      "step": 129
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.002767857142857143,
      "loss": 2.0362,
      "step": 130
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.002766071428571429,
      "loss": 2.0369,
      "step": 131
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0027642857142857143,
      "loss": 2.0721,
      "step": 132
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0027624999999999998,
      "loss": 1.9939,
      "step": 133
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0027607142857142856,
      "loss": 2.0403,
      "step": 134
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0027589285714285715,
      "loss": 2.1132,
      "step": 135
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.002757142857142857,
      "loss": 2.0741,
      "step": 136
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0027553571428571427,
      "loss": 2.0754,
      "step": 137
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0027535714285714286,
      "loss": 2.1321,
      "step": 138
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.0027517857142857144,
      "loss": 2.0665,
      "step": 139
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00275,
      "loss": 2.1085,
      "step": 140
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0027482142857142857,
      "loss": 1.653,
      "step": 141
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0027464285714285715,
      "loss": 1.5934,
      "step": 142
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.002744642857142857,
      "loss": 1.6795,
      "step": 143
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.002742857142857143,
      "loss": 1.6043,
      "step": 144
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0027410714285714287,
      "loss": 1.586,
      "step": 145
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.002739285714285714,
      "loss": 1.6061,
      "step": 146
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0027375,
      "loss": 1.6438,
      "step": 147
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0027357142857142858,
      "loss": 1.6097,
      "step": 148
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0027339285714285716,
      "loss": 1.7163,
      "step": 149
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.002732142857142857,
      "loss": 1.6485,
      "step": 150
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.002730357142857143,
      "loss": 1.6555,
      "step": 151
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0027285714285714287,
      "loss": 1.689,
      "step": 152
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.002726785714285714,
      "loss": 1.7174,
      "step": 153
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.002725,
      "loss": 1.7205,
      "step": 154
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.002723214285714286,
      "loss": 1.7064,
      "step": 155
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0027214285714285717,
      "loss": 1.7045,
      "step": 156
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.002719642857142857,
      "loss": 1.7749,
      "step": 157
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.002717857142857143,
      "loss": 1.7826,
      "step": 158
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.002716071428571429,
      "loss": 1.7882,
      "step": 159
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0027142857142857142,
      "loss": 1.8073,
      "step": 160
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0027125,
      "loss": 1.7931,
      "step": 161
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.002710714285714286,
      "loss": 1.8388,
      "step": 162
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0027089285714285713,
      "loss": 1.8267,
      "step": 163
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.002707142857142857,
      "loss": 1.8208,
      "step": 164
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.002705357142857143,
      "loss": 1.8404,
      "step": 165
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.002703571428571429,
      "loss": 1.8375,
      "step": 166
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.0027017857142857143,
      "loss": 1.9444,
      "step": 167
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0027,
      "loss": 1.8325,
      "step": 168
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.002698214285714286,
      "loss": 1.8705,
      "step": 169
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0026964285714285714,
      "loss": 1.9368,
      "step": 170
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0026946428571428573,
      "loss": 1.8758,
      "step": 171
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.002692857142857143,
      "loss": 1.999,
      "step": 172
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0026910714285714285,
      "loss": 1.9547,
      "step": 173
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0026892857142857144,
      "loss": 1.9332,
      "step": 174
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0026875000000000002,
      "loss": 1.9704,
      "step": 175
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.002685714285714286,
      "loss": 1.4766,
      "step": 176
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0026839285714285715,
      "loss": 1.4459,
      "step": 177
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.0026821428571428573,
      "loss": 1.4451,
      "step": 178
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.002680357142857143,
      "loss": 1.4761,
      "step": 179
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.0026785714285714286,
      "loss": 1.5092,
      "step": 180
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.0026767857142857144,
      "loss": 1.4439,
      "step": 181
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.0026750000000000003,
      "loss": 1.4539,
      "step": 182
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.002673214285714286,
      "loss": 1.4804,
      "step": 183
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.002671428571428571,
      "loss": 1.4958,
      "step": 184
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.002669642857142857,
      "loss": 1.5054,
      "step": 185
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.002667857142857143,
      "loss": 1.4673,
      "step": 186
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0026660714285714287,
      "loss": 1.5703,
      "step": 187
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.002664285714285714,
      "loss": 1.5504,
      "step": 188
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.0026625,
      "loss": 1.6126,
      "step": 189
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.002660714285714286,
      "loss": 1.5777,
      "step": 190
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.002658928571428571,
      "loss": 1.5994,
      "step": 191
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.002657142857142857,
      "loss": 1.5939,
      "step": 192
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.002655357142857143,
      "loss": 1.6297,
      "step": 193
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.0026535714285714283,
      "loss": 1.6749,
      "step": 194
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.002651785714285714,
      "loss": 1.6525,
      "step": 195
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.00265,
      "loss": 1.657,
      "step": 196
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.002648214285714286,
      "loss": 1.6818,
      "step": 197
    },
    {
      "epoch": 5.66,
      "learning_rate": 0.0026464285714285713,
      "loss": 1.6985,
      "step": 198
    },
    {
      "epoch": 5.69,
      "learning_rate": 0.002644642857142857,
      "loss": 1.7456,
      "step": 199
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.002642857142857143,
      "loss": 1.678,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 1680,
  "num_train_epochs": 48,
  "save_steps": 100,
  "total_flos": 1.1559978611371008e+17,
  "trial_name": null,
  "trial_params": null
}