{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.244167962674961,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.00099375,
      "loss": 2.9311,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0009875,
      "loss": 2.9309,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00098125,
      "loss": 2.8566,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000975,
      "loss": 2.773,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00096875,
      "loss": 2.7367,
      "step": 5
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009625,
      "loss": 2.7924,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009562500000000001,
      "loss": 2.7099,
      "step": 7
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00095,
      "loss": 2.7658,
      "step": 8
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00094375,
      "loss": 2.7514,
      "step": 9
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0009375,
      "loss": 2.6899,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00093125,
      "loss": 2.7072,
      "step": 11
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000925,
      "loss": 2.7687,
      "step": 12
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00091875,
      "loss": 2.652,
      "step": 13
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009125,
      "loss": 2.6991,
      "step": 14
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00090625,
      "loss": 2.6259,
      "step": 15
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0009000000000000001,
      "loss": 2.5914,
      "step": 16
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00089375,
      "loss": 2.7453,
      "step": 17
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0008874999999999999,
      "loss": 2.6502,
      "step": 18
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00088125,
      "loss": 2.6558,
      "step": 19
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000875,
      "loss": 2.6839,
      "step": 20
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0008687500000000001,
      "loss": 2.5649,
      "step": 21
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0008625000000000001,
      "loss": 2.724,
      "step": 22
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00085625,
      "loss": 2.6601,
      "step": 23
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00085,
      "loss": 2.573,
      "step": 24
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00084375,
      "loss": 2.5586,
      "step": 25
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0008375,
      "loss": 2.6952,
      "step": 26
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0008312500000000001,
      "loss": 2.6349,
      "step": 27
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000825,
      "loss": 2.7674,
      "step": 28
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00081875,
      "loss": 2.6728,
      "step": 29
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0008125000000000001,
      "loss": 2.7608,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00080625,
      "loss": 2.5593,
      "step": 31
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0008,
      "loss": 2.6426,
      "step": 32
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00079375,
      "loss": 2.7065,
      "step": 33
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0007875,
      "loss": 2.7022,
      "step": 34
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00078125,
      "loss": 2.6398,
      "step": 35
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0007750000000000001,
      "loss": 2.5589,
      "step": 36
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00076875,
      "loss": 2.7217,
      "step": 37
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0007624999999999999,
      "loss": 2.7152,
      "step": 38
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00075625,
      "loss": 2.6679,
      "step": 39
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00075,
      "loss": 2.5681,
      "step": 40
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00074375,
      "loss": 2.6518,
      "step": 41
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0007375000000000001,
      "loss": 2.6684,
      "step": 42
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00073125,
      "loss": 2.6757,
      "step": 43
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000725,
      "loss": 2.6836,
      "step": 44
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00071875,
      "loss": 2.685,
      "step": 45
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007125,
      "loss": 2.6512,
      "step": 46
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007062500000000001,
      "loss": 2.6766,
      "step": 47
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0007,
      "loss": 2.5773,
      "step": 48
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00069375,
      "loss": 2.7344,
      "step": 49
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006875,
      "loss": 2.6468,
      "step": 50
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00068125,
      "loss": 2.6663,
      "step": 51
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000675,
      "loss": 2.6363,
      "step": 52
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00066875,
      "loss": 2.7287,
      "step": 53
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0006625,
      "loss": 2.7259,
      "step": 54
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00065625,
      "loss": 2.6912,
      "step": 55
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0006500000000000001,
      "loss": 2.5956,
      "step": 56
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00064375,
      "loss": 2.7398,
      "step": 57
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0006374999999999999,
      "loss": 2.7265,
      "step": 58
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00063125,
      "loss": 2.6031,
      "step": 59
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000625,
      "loss": 2.6263,
      "step": 60
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00061875,
      "loss": 2.6544,
      "step": 61
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0006125000000000001,
      "loss": 2.7403,
      "step": 62
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00060625,
      "loss": 2.6565,
      "step": 63
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0006,
      "loss": 2.7286,
      "step": 64
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00059375,
      "loss": 2.7061,
      "step": 65
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0005875,
      "loss": 2.5849,
      "step": 66
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0005812500000000001,
      "loss": 2.6668,
      "step": 67
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000575,
      "loss": 2.6454,
      "step": 68
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00056875,
      "loss": 2.635,
      "step": 69
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0005625000000000001,
      "loss": 2.6358,
      "step": 70
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00055625,
      "loss": 2.6379,
      "step": 71
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00055,
      "loss": 2.6447,
      "step": 72
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00054375,
      "loss": 2.6083,
      "step": 73
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0005375,
      "loss": 2.6816,
      "step": 74
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00053125,
      "loss": 2.6415,
      "step": 75
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0005250000000000001,
      "loss": 2.6407,
      "step": 76
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00051875,
      "loss": 2.6056,
      "step": 77
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0005124999999999999,
      "loss": 2.5552,
      "step": 78
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00050625,
      "loss": 2.6193,
      "step": 79
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0005,
      "loss": 2.5949,
      "step": 80
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00049375,
      "loss": 2.5104,
      "step": 81
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0004875,
      "loss": 2.4372,
      "step": 82
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00048125,
      "loss": 2.3689,
      "step": 83
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000475,
      "loss": 2.5339,
      "step": 84
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00046875,
      "loss": 2.5443,
      "step": 85
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0004625,
      "loss": 2.4477,
      "step": 86
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00045625,
      "loss": 2.4904,
      "step": 87
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00045000000000000004,
      "loss": 2.43,
      "step": 88
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00044374999999999997,
      "loss": 2.476,
      "step": 89
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0004375,
      "loss": 2.5321,
      "step": 90
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00043125000000000005,
      "loss": 2.4374,
      "step": 91
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.000425,
      "loss": 2.4265,
      "step": 92
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00041875,
      "loss": 2.4505,
      "step": 93
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0004125,
      "loss": 2.4275,
      "step": 94
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00040625000000000004,
      "loss": 2.4458,
      "step": 95
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0004,
      "loss": 2.5226,
      "step": 96
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00039375,
      "loss": 2.4048,
      "step": 97
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00038750000000000004,
      "loss": 2.5091,
      "step": 98
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00038124999999999997,
      "loss": 2.4583,
      "step": 99
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.000375,
      "loss": 2.4678,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 160,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 2.588289853513728e+16,
  "trial_name": null,
  "trial_params": null
}