{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.023631723225257587,
  "eval_steps": 1000,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 13.5045,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 13.2514,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 14.3156,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 13.0763,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 12.9353,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 12.8562,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 12.6139,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 12.8862,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 12.0442,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001995967741935484,
      "loss": 11.959,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001991935483870968,
      "loss": 11.7023,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019879032258064515,
      "loss": 10.7218,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019838709677419357,
      "loss": 10.9581,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019798387096774193,
      "loss": 11.3065,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019758064516129035,
      "loss": 10.2943,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001971774193548387,
      "loss": 10.1651,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001967741935483871,
      "loss": 9.8951,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001963709677419355,
      "loss": 9.6734,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019596774193548388,
      "loss": 9.4096,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019556451612903227,
      "loss": 9.0653,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019516129032258066,
      "loss": 8.9835,
      "step": 21
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019475806451612905,
      "loss": 9.399,
      "step": 22
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019435483870967744,
      "loss": 9.1367,
      "step": 23
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001939516129032258,
      "loss": 8.4746,
      "step": 24
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019354838709677422,
      "loss": 8.4179,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019314516129032258,
      "loss": 8.6536,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000192741935483871,
      "loss": 8.2193,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019233870967741936,
      "loss": 8.3287,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019193548387096775,
      "loss": 8.1268,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019153225806451614,
      "loss": 8.2402,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019112903225806453,
      "loss": 7.9379,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019072580645161291,
      "loss": 8.2621,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001903225806451613,
      "loss": 8.0542,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001899193548387097,
      "loss": 7.9747,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018951612903225808,
      "loss": 7.9519,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018911290322580645,
      "loss": 7.7444,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018870967741935486,
      "loss": 7.9391,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018830645161290322,
      "loss": 7.9026,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018790322580645164,
      "loss": 7.8992,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001875,
      "loss": 7.7428,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001870967741935484,
      "loss": 7.7166,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018669354838709678,
      "loss": 7.7254,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018629032258064517,
      "loss": 7.5929,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018588709677419356,
      "loss": 7.4957,
      "step": 44
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018548387096774192,
      "loss": 7.805,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018508064516129034,
      "loss": 7.91,
      "step": 46
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001846774193548387,
      "loss": 7.6839,
      "step": 47
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018427419354838712,
      "loss": 7.7526,
      "step": 48
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018387096774193548,
      "loss": 7.9365,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018346774193548387,
      "loss": 7.455,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018306451612903226,
      "loss": 7.5666,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018266129032258065,
      "loss": 7.5442,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018225806451612904,
      "loss": 7.7723,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018185483870967743,
      "loss": 7.5818,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018145161290322582,
      "loss": 7.5512,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001810483870967742,
      "loss": 7.7454,
      "step": 56
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018064516129032257,
      "loss": 7.5012,
      "step": 57
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000180241935483871,
      "loss": 7.6233,
      "step": 58
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017983870967741935,
      "loss": 7.6972,
      "step": 59
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017943548387096777,
      "loss": 7.6155,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017903225806451613,
      "loss": 7.4599,
      "step": 61
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017862903225806452,
      "loss": 7.7154,
      "step": 62
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001782258064516129,
      "loss": 7.598,
      "step": 63
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001778225806451613,
      "loss": 7.4523,
      "step": 64
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001774193548387097,
      "loss": 7.5589,
      "step": 65
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017701612903225808,
      "loss": 7.4396,
      "step": 66
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017661290322580647,
      "loss": 7.6101,
      "step": 67
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017620967741935486,
      "loss": 7.5708,
      "step": 68
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017580645161290325,
      "loss": 7.3261,
      "step": 69
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017540322580645164,
      "loss": 7.4395,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000175,
      "loss": 7.2618,
      "step": 71
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001745967741935484,
      "loss": 7.1965,
      "step": 72
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017419354838709678,
      "loss": 7.1342,
      "step": 73
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017379032258064517,
      "loss": 7.1008,
      "step": 74
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017338709677419356,
      "loss": 7.0397,
      "step": 75
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017298387096774195,
      "loss": 7.0406,
      "step": 76
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017258064516129034,
      "loss": 6.9318,
      "step": 77
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001721774193548387,
      "loss": 6.9892,
      "step": 78
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017177419354838711,
      "loss": 6.5501,
      "step": 79
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017137096774193548,
      "loss": 6.8337,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001709677419354839,
      "loss": 6.4362,
      "step": 81
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017056451612903226,
      "loss": 6.1646,
      "step": 82
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017016129032258065,
      "loss": 6.3416,
      "step": 83
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016975806451612904,
      "loss": 6.3828,
      "step": 84
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016935483870967742,
      "loss": 6.4853,
      "step": 85
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016895161290322581,
      "loss": 5.7598,
      "step": 86
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001685483870967742,
      "loss": 6.3524,
      "step": 87
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001681451612903226,
      "loss": 5.8323,
      "step": 88
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016774193548387098,
      "loss": 6.16,
      "step": 89
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016733870967741935,
      "loss": 5.9581,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016693548387096776,
      "loss": 5.741,
      "step": 91
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016653225806451612,
      "loss": 6.0302,
      "step": 92
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016612903225806454,
      "loss": 5.6973,
      "step": 93
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001657258064516129,
      "loss": 6.1547,
      "step": 94
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016532258064516132,
      "loss": 5.5362,
      "step": 95
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016491935483870968,
      "loss": 5.8757,
      "step": 96
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016451612903225807,
      "loss": 5.1669,
      "step": 97
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016411290322580646,
      "loss": 5.6761,
      "step": 98
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016370967741935485,
      "loss": 5.3759,
      "step": 99
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016330645161290324,
      "loss": 5.6455,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016290322580645163,
      "loss": 5.5912,
      "step": 101
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016250000000000002,
      "loss": 5.3943,
      "step": 102
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016209677419354838,
      "loss": 5.5953,
      "step": 103
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016169354838709677,
      "loss": 5.4715,
      "step": 104
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016129032258064516,
      "loss": 5.2222,
      "step": 105
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016088709677419355,
      "loss": 5.3243,
      "step": 106
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016048387096774194,
      "loss": 4.9239,
      "step": 107
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016008064516129033,
      "loss": 5.232,
      "step": 108
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015967741935483872,
      "loss": 5.3394,
      "step": 109
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001592741935483871,
      "loss": 4.5978,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015887096774193547,
      "loss": 5.0104,
      "step": 111
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001584677419354839,
      "loss": 5.2945,
      "step": 112
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015806451612903225,
      "loss": 4.9366,
      "step": 113
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015766129032258067,
      "loss": 4.8425,
      "step": 114
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015725806451612903,
      "loss": 5.0086,
      "step": 115
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015685483870967742,
      "loss": 4.7297,
      "step": 116
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001564516129032258,
      "loss": 4.834,
      "step": 117
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001560483870967742,
      "loss": 4.9643,
      "step": 118
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001556451612903226,
      "loss": 4.7391,
      "step": 119
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015524193548387098,
      "loss": 4.8393,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015483870967741937,
      "loss": 4.9257,
      "step": 121
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015443548387096776,
      "loss": 5.0117,
      "step": 122
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015403225806451615,
      "loss": 4.643,
      "step": 123
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015362903225806454,
      "loss": 5.0408,
      "step": 124
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001532258064516129,
      "loss": 4.9834,
      "step": 125
    }
  ],
  "logging_steps": 1,
  "max_steps": 501,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 184698227957760.0,
  "trial_name": null,
  "trial_params": null
}