{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.488335925349922,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.00099375,
      "loss": 2.9857,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009875,
      "loss": 2.8497,
      "step": 2
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00098125,
      "loss": 2.8853,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000975,
      "loss": 2.7689,
      "step": 4
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00096875,
      "loss": 2.7474,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009625,
      "loss": 2.7695,
      "step": 6
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009562500000000001,
      "loss": 2.6897,
      "step": 7
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00095,
      "loss": 2.6285,
      "step": 8
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00094375,
      "loss": 2.7107,
      "step": 9
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0009375,
      "loss": 2.6897,
      "step": 10
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00093125,
      "loss": 2.6634,
      "step": 11
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000925,
      "loss": 2.635,
      "step": 12
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00091875,
      "loss": 2.643,
      "step": 13
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0009125,
      "loss": 2.7166,
      "step": 14
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00090625,
      "loss": 2.7354,
      "step": 15
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009000000000000001,
      "loss": 2.615,
      "step": 16
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00089375,
      "loss": 2.7225,
      "step": 17
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0008874999999999999,
      "loss": 2.6189,
      "step": 18
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00088125,
      "loss": 2.7269,
      "step": 19
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000875,
      "loss": 2.6312,
      "step": 20
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0008687500000000001,
      "loss": 2.6758,
      "step": 21
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0008625000000000001,
      "loss": 2.6997,
      "step": 22
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00085625,
      "loss": 2.6878,
      "step": 23
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00085,
      "loss": 2.6433,
      "step": 24
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00084375,
      "loss": 2.7053,
      "step": 25
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008375,
      "loss": 2.6745,
      "step": 26
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0008312500000000001,
      "loss": 2.7376,
      "step": 27
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000825,
      "loss": 2.6577,
      "step": 28
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00081875,
      "loss": 2.7428,
      "step": 29
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0008125000000000001,
      "loss": 2.6231,
      "step": 30
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00080625,
      "loss": 2.7078,
      "step": 31
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0008,
      "loss": 2.7057,
      "step": 32
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00079375,
      "loss": 2.6594,
      "step": 33
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0007875,
      "loss": 2.6718,
      "step": 34
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00078125,
      "loss": 2.6459,
      "step": 35
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0007750000000000001,
      "loss": 2.6558,
      "step": 36
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00076875,
      "loss": 2.6559,
      "step": 37
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0007624999999999999,
      "loss": 2.6488,
      "step": 38
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00075625,
      "loss": 2.5902,
      "step": 39
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00075,
      "loss": 2.6244,
      "step": 40
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00074375,
      "loss": 2.5278,
      "step": 41
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0007375000000000001,
      "loss": 2.5213,
      "step": 42
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00073125,
      "loss": 2.5515,
      "step": 43
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000725,
      "loss": 2.5196,
      "step": 44
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00071875,
      "loss": 2.5725,
      "step": 45
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0007125,
      "loss": 2.4971,
      "step": 46
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0007062500000000001,
      "loss": 2.4976,
      "step": 47
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0007,
      "loss": 2.5467,
      "step": 48
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00069375,
      "loss": 2.5302,
      "step": 49
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0006875,
      "loss": 2.5224,
      "step": 50
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00068125,
      "loss": 2.5451,
      "step": 51
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.000675,
      "loss": 2.4609,
      "step": 52
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00066875,
      "loss": 2.4897,
      "step": 53
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0006625,
      "loss": 2.5583,
      "step": 54
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00065625,
      "loss": 2.5675,
      "step": 55
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0006500000000000001,
      "loss": 2.5598,
      "step": 56
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00064375,
      "loss": 2.48,
      "step": 57
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0006374999999999999,
      "loss": 2.4761,
      "step": 58
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00063125,
      "loss": 2.5599,
      "step": 59
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.000625,
      "loss": 2.5199,
      "step": 60
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00061875,
      "loss": 2.5161,
      "step": 61
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0006125000000000001,
      "loss": 2.5797,
      "step": 62
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00060625,
      "loss": 2.5345,
      "step": 63
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0006,
      "loss": 2.4726,
      "step": 64
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00059375,
      "loss": 2.448,
      "step": 65
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0005875,
      "loss": 2.4939,
      "step": 66
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0005812500000000001,
      "loss": 2.4881,
      "step": 67
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.000575,
      "loss": 2.5731,
      "step": 68
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00056875,
      "loss": 2.5114,
      "step": 69
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0005625000000000001,
      "loss": 2.5049,
      "step": 70
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00055625,
      "loss": 2.4856,
      "step": 71
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00055,
      "loss": 2.5077,
      "step": 72
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00054375,
      "loss": 2.4801,
      "step": 73
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0005375,
      "loss": 2.5599,
      "step": 74
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00053125,
      "loss": 2.5269,
      "step": 75
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0005250000000000001,
      "loss": 2.4963,
      "step": 76
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00051875,
      "loss": 2.4595,
      "step": 77
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0005124999999999999,
      "loss": 2.4801,
      "step": 78
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00050625,
      "loss": 2.5154,
      "step": 79
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0005,
      "loss": 2.5179,
      "step": 80
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00049375,
      "loss": 2.4121,
      "step": 81
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0004875,
      "loss": 2.354,
      "step": 82
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00048125,
      "loss": 2.3033,
      "step": 83
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.000475,
      "loss": 2.4023,
      "step": 84
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00046875,
      "loss": 2.3755,
      "step": 85
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0004625,
      "loss": 2.3892,
      "step": 86
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00045625,
      "loss": 2.3534,
      "step": 87
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00045000000000000004,
      "loss": 2.3634,
      "step": 88
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00044374999999999997,
      "loss": 2.3336,
      "step": 89
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0004375,
      "loss": 2.3646,
      "step": 90
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00043125000000000005,
      "loss": 2.3333,
      "step": 91
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.000425,
      "loss": 2.3344,
      "step": 92
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00041875,
      "loss": 2.3308,
      "step": 93
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0004125,
      "loss": 2.3677,
      "step": 94
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00040625000000000004,
      "loss": 2.3755,
      "step": 95
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0004,
      "loss": 2.3721,
      "step": 96
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00039375,
      "loss": 2.3463,
      "step": 97
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00038750000000000004,
      "loss": 2.3536,
      "step": 98
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00038124999999999997,
      "loss": 2.3895,
      "step": 99
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.000375,
      "loss": 2.3767,
      "step": 100
    }
  ],
  "max_steps": 160,
  "num_train_epochs": 4,
  "total_flos": 5.95613039443968e+16,
  "trial_name": null,
  "trial_params": null
}