{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 3.6346,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 3.602,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 3e-05,
      "loss": 3.5741,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 3.4904,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 5e-05,
      "loss": 3.4215,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 3.4568,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.000000000000001e-05,
      "loss": 3.3978,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 3.4991,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999999999999999e-05,
      "loss": 3.5852,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 3.3132,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00011,
      "loss": 3.2737,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 3.1399,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00013000000000000002,
      "loss": 3.1828,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00014000000000000001,
      "loss": 3.0638,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00015,
      "loss": 3.185,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 3.0669,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017,
      "loss": 2.9026,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.9591,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019,
      "loss": 2.8483,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.7707,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00021,
      "loss": 2.8564,
      "step": 21
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00022,
      "loss": 2.6997,
      "step": 22
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00023,
      "loss": 2.8052,
      "step": 23
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00024,
      "loss": 2.5826,
      "step": 24
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00025,
      "loss": 2.6266,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00026000000000000003,
      "loss": 2.6477,
      "step": 26
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00027,
      "loss": 2.6133,
      "step": 27
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00028000000000000003,
      "loss": 2.5395,
      "step": 28
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00029,
      "loss": 2.664,
      "step": 29
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 2.5568,
      "step": 30
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00031,
      "loss": 2.4346,
      "step": 31
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00032,
      "loss": 2.5765,
      "step": 32
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00033,
      "loss": 2.4884,
      "step": 33
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00034,
      "loss": 2.4257,
      "step": 34
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00035,
      "loss": 2.4281,
      "step": 35
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00035999999999999997,
      "loss": 2.4858,
      "step": 36
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00037,
      "loss": 2.383,
      "step": 37
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00038,
      "loss": 2.4865,
      "step": 38
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00039000000000000005,
      "loss": 2.3564,
      "step": 39
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 2.4276,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00041,
      "loss": 2.4225,
      "step": 41
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00042,
      "loss": 2.2718,
      "step": 42
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00043,
      "loss": 2.3566,
      "step": 43
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00044,
      "loss": 2.3911,
      "step": 44
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00045000000000000004,
      "loss": 2.3999,
      "step": 45
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00046,
      "loss": 2.2776,
      "step": 46
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00047,
      "loss": 2.3891,
      "step": 47
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00048,
      "loss": 2.3132,
      "step": 48
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00049,
      "loss": 2.3353,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005,
      "loss": 2.3691,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00051,
      "loss": 2.3271,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005200000000000001,
      "loss": 2.2881,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005300000000000001,
      "loss": 2.2731,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00054,
      "loss": 2.3186,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00055,
      "loss": 2.3216,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005600000000000001,
      "loss": 2.3204,
      "step": 56
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00057,
      "loss": 2.1832,
      "step": 57
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00058,
      "loss": 2.4125,
      "step": 58
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00059,
      "loss": 2.2649,
      "step": 59
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006,
      "loss": 2.1589,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00061,
      "loss": 2.1431,
      "step": 61
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00062,
      "loss": 2.3738,
      "step": 62
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00063,
      "loss": 2.2525,
      "step": 63
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00064,
      "loss": 2.2778,
      "step": 64
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006500000000000001,
      "loss": 2.2739,
      "step": 65
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00066,
      "loss": 2.2878,
      "step": 66
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00067,
      "loss": 2.196,
      "step": 67
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00068,
      "loss": 2.2384,
      "step": 68
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00069,
      "loss": 2.1638,
      "step": 69
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007,
      "loss": 2.1578,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00071,
      "loss": 2.1781,
      "step": 71
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007199999999999999,
      "loss": 2.2486,
      "step": 72
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00073,
      "loss": 2.2475,
      "step": 73
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00074,
      "loss": 2.0713,
      "step": 74
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00075,
      "loss": 2.1261,
      "step": 75
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00076,
      "loss": 2.156,
      "step": 76
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007700000000000001,
      "loss": 2.2273,
      "step": 77
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007800000000000001,
      "loss": 2.2245,
      "step": 78
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00079,
      "loss": 2.1527,
      "step": 79
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0008,
      "loss": 2.0454,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0008100000000000001,
      "loss": 2.2643,
      "step": 81
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00082,
      "loss": 2.2447,
      "step": 82
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00083,
      "loss": 2.1656,
      "step": 83
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00084,
      "loss": 2.099,
      "step": 84
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00085,
      "loss": 2.2078,
      "step": 85
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00086,
      "loss": 2.1537,
      "step": 86
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00087,
      "loss": 2.1013,
      "step": 87
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00088,
      "loss": 2.0553,
      "step": 88
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0008900000000000001,
      "loss": 2.1702,
      "step": 89
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0009000000000000001,
      "loss": 2.0685,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00091,
      "loss": 2.149,
      "step": 91
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00092,
      "loss": 2.1102,
      "step": 92
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00093,
      "loss": 2.2527,
      "step": 93
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00094,
      "loss": 2.0719,
      "step": 94
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00095,
      "loss": 2.1293,
      "step": 95
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00096,
      "loss": 2.1333,
      "step": 96
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0009699999999999999,
      "loss": 2.1497,
      "step": 97
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00098,
      "loss": 2.0996,
      "step": 98
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00099,
      "loss": 2.1576,
      "step": 99
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.001,
      "loss": 2.1483,
      "step": 100
    }
  ],
  "max_steps": 10000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 9.635560229376e+16,
  "trial_name": null,
  "trial_params": null
}