{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 218,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 15.4681,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 15.9568,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 1e-06,
      "loss": 16.5144,
      "step": 3
    },
    {
      "epoch": 0.04,
      "learning_rate": 2e-06,
      "loss": 15.6766,
      "step": 4
    },
    {
      "epoch": 0.05,
      "learning_rate": 3e-06,
      "loss": 14.7129,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 4e-06,
      "loss": 16.0718,
      "step": 6
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-06,
      "loss": 14.91,
      "step": 7
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-06,
      "loss": 14.6946,
      "step": 8
    },
    {
      "epoch": 0.08,
      "learning_rate": 7e-06,
      "loss": 14.2719,
      "step": 9
    },
    {
      "epoch": 0.09,
      "learning_rate": 8e-06,
      "loss": 15.1354,
      "step": 10
    },
    {
      "epoch": 0.1,
      "learning_rate": 9e-06,
      "loss": 14.5036,
      "step": 11
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-05,
      "loss": 14.337,
      "step": 12
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.1e-05,
      "loss": 14.2807,
      "step": 13
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.2e-05,
      "loss": 14.556,
      "step": 14
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.3e-05,
      "loss": 13.5745,
      "step": 15
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.4e-05,
      "loss": 14.0562,
      "step": 16
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.5e-05,
      "loss": 12.5592,
      "step": 17
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.6e-05,
      "loss": 13.5733,
      "step": 18
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 13.0924,
      "step": 19
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8e-05,
      "loss": 12.5755,
      "step": 20
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9e-05,
      "loss": 12.2455,
      "step": 21
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 11.8012,
      "step": 22
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.1000000000000002e-05,
      "loss": 12.3153,
      "step": 23
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.2e-05,
      "loss": 12.5406,
      "step": 24
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.3e-05,
      "loss": 12.94,
      "step": 25
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.4e-05,
      "loss": 11.7376,
      "step": 26
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5e-05,
      "loss": 11.8349,
      "step": 27
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.6e-05,
      "loss": 11.66,
      "step": 28
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.7e-05,
      "loss": 11.7223,
      "step": 29
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.8e-05,
      "loss": 10.8818,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.9000000000000004e-05,
      "loss": 10.7231,
      "step": 31
    },
    {
      "epoch": 0.29,
      "learning_rate": 3e-05,
      "loss": 10.0117,
      "step": 32
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.1e-05,
      "loss": 9.636,
      "step": 33
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.2e-05,
      "loss": 8.3897,
      "step": 34
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.3e-05,
      "loss": 8.0832,
      "step": 35
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 8.0655,
      "step": 36
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 7.5712,
      "step": 37
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.6e-05,
      "loss": 6.8451,
      "step": 38
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.7e-05,
      "loss": 6.3271,
      "step": 39
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.8e-05,
      "loss": 6.5283,
      "step": 40
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.9e-05,
      "loss": 6.5524,
      "step": 41
    },
    {
      "epoch": 0.39,
      "learning_rate": 4e-05,
      "loss": 5.632,
      "step": 42
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.1e-05,
      "loss": 5.7602,
      "step": 43
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 5.7941,
      "step": 44
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.2999999999999995e-05,
      "loss": 5.44,
      "step": 45
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.4e-05,
      "loss": 5.2118,
      "step": 46
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 5.3243,
      "step": 47
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.6e-05,
      "loss": 5.1308,
      "step": 48
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.7000000000000004e-05,
      "loss": 5.0647,
      "step": 49
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.8e-05,
      "loss": 5.3896,
      "step": 50
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.9000000000000005e-05,
      "loss": 4.8733,
      "step": 51
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 4.9111,
      "step": 52
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.1e-05,
      "loss": 4.9757,
      "step": 53
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.2e-05,
      "loss": 5.2087,
      "step": 54
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.3e-05,
      "loss": 5.0727,
      "step": 55
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.4e-05,
      "loss": 4.7675,
      "step": 56
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.5e-05,
      "loss": 4.8481,
      "step": 57
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.6e-05,
      "loss": 4.6186,
      "step": 58
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7e-05,
      "loss": 4.4946,
      "step": 59
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.800000000000001e-05,
      "loss": 4.4504,
      "step": 60
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.9e-05,
      "loss": 4.298,
      "step": 61
    },
    {
      "epoch": 0.57,
      "learning_rate": 6e-05,
      "loss": 4.396,
      "step": 62
    },
    {
      "epoch": 0.58,
      "learning_rate": 6.1e-05,
      "loss": 4.3293,
      "step": 63
    },
    {
      "epoch": 0.59,
      "learning_rate": 6.2e-05,
      "loss": 4.2654,
      "step": 64
    },
    {
      "epoch": 0.6,
      "learning_rate": 6.3e-05,
      "loss": 4.23,
      "step": 65
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.4e-05,
      "loss": 4.2528,
      "step": 66
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.500000000000001e-05,
      "loss": 4.2186,
      "step": 67
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.6e-05,
      "loss": 4.0544,
      "step": 68
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.7e-05,
      "loss": 4.0677,
      "step": 69
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.800000000000001e-05,
      "loss": 4.0365,
      "step": 70
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.900000000000001e-05,
      "loss": 4.0395,
      "step": 71
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.000000000000001e-05,
      "loss": 3.9003,
      "step": 72
    },
    {
      "epoch": 0.67,
      "learning_rate": 7.099999999999999e-05,
      "loss": 3.9501,
      "step": 73
    },
    {
      "epoch": 0.68,
      "learning_rate": 7.2e-05,
      "loss": 3.8808,
      "step": 74
    },
    {
      "epoch": 0.69,
      "learning_rate": 7.3e-05,
      "loss": 3.9191,
      "step": 75
    },
    {
      "epoch": 0.7,
      "learning_rate": 7.4e-05,
      "loss": 3.8672,
      "step": 76
    },
    {
      "epoch": 0.71,
      "learning_rate": 7.5e-05,
      "loss": 3.859,
      "step": 77
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.6e-05,
      "loss": 3.9086,
      "step": 78
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.7e-05,
      "loss": 3.858,
      "step": 79
    },
    {
      "epoch": 0.73,
      "learning_rate": 7.8e-05,
      "loss": 3.7822,
      "step": 80
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.9e-05,
      "loss": 4.0317,
      "step": 81
    },
    {
      "epoch": 0.75,
      "learning_rate": 8e-05,
      "loss": 3.9539,
      "step": 82
    },
    {
      "epoch": 0.76,
      "learning_rate": 8.1e-05,
      "loss": 3.7545,
      "step": 83
    },
    {
      "epoch": 0.77,
      "learning_rate": 8.2e-05,
      "loss": 3.7628,
      "step": 84
    },
    {
      "epoch": 0.78,
      "learning_rate": 8.300000000000001e-05,
      "loss": 3.7037,
      "step": 85
    },
    {
      "epoch": 0.79,
      "learning_rate": 8.400000000000001e-05,
      "loss": 3.6012,
      "step": 86
    },
    {
      "epoch": 0.8,
      "learning_rate": 8.5e-05,
      "loss": 3.6133,
      "step": 87
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.599999999999999e-05,
      "loss": 3.6023,
      "step": 88
    },
    {
      "epoch": 0.82,
      "learning_rate": 8.7e-05,
      "loss": 3.6009,
      "step": 89
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.8e-05,
      "loss": 3.6065,
      "step": 90
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.9e-05,
      "loss": 3.4981,
      "step": 91
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.999999999999999e-05,
      "loss": 3.4965,
      "step": 92
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.1e-05,
      "loss": 3.4709,
      "step": 93
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.2e-05,
      "loss": 3.4635,
      "step": 94
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.3e-05,
      "loss": 3.4336,
      "step": 95
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.400000000000001e-05,
      "loss": 3.4499,
      "step": 96
    },
    {
      "epoch": 0.89,
      "learning_rate": 9.5e-05,
      "loss": 3.4041,
      "step": 97
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.6e-05,
      "loss": 3.4108,
      "step": 98
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.7e-05,
      "loss": 3.3855,
      "step": 99
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.800000000000001e-05,
      "loss": 3.3555,
      "step": 100
    },
    {
      "epoch": 0.93,
      "learning_rate": 9.900000000000001e-05,
      "loss": 3.339,
      "step": 101
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 3.36,
      "step": 102
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000101,
      "loss": 3.3049,
      "step": 103
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000102,
      "loss": 3.3477,
      "step": 104
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000103,
      "loss": 3.3347,
      "step": 105
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000104,
      "loss": 3.2893,
      "step": 106
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000105,
      "loss": 3.3464,
      "step": 107
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000106,
      "loss": 3.5181,
      "step": 108
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000107,
      "loss": 3.3032,
      "step": 109
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000108,
      "loss": 3.3675,
      "step": 110
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.000109,
      "loss": 3.2402,
      "step": 111
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00011,
      "loss": 3.2579,
      "step": 112
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.000111,
      "loss": 3.2438,
      "step": 113
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000112,
      "loss": 3.1981,
      "step": 114
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00011300000000000001,
      "loss": 3.2296,
      "step": 115
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.000114,
      "loss": 3.2426,
      "step": 116
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.000115,
      "loss": 3.1625,
      "step": 117
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00011600000000000001,
      "loss": 3.1942,
      "step": 118
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00011700000000000001,
      "loss": 3.1669,
      "step": 119
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000118,
      "loss": 3.1891,
      "step": 120
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00011899999999999999,
      "loss": 3.1943,
      "step": 121
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012,
      "loss": 3.1586,
      "step": 122
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.000121,
      "loss": 3.2002,
      "step": 123
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.000122,
      "loss": 3.1995,
      "step": 124
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.000123,
      "loss": 3.1766,
      "step": 125
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.000124,
      "loss": 3.2021,
      "step": 126
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.000125,
      "loss": 3.1619,
      "step": 127
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.000126,
      "loss": 3.1791,
      "step": 128
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.000127,
      "loss": 3.1569,
      "step": 129
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.000128,
      "loss": 3.157,
      "step": 130
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012900000000000002,
      "loss": 3.1783,
      "step": 131
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013000000000000002,
      "loss": 3.2148,
      "step": 132
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.000131,
      "loss": 3.1511,
      "step": 133
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.000132,
      "loss": 3.1599,
      "step": 134
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.000133,
      "loss": 3.1501,
      "step": 135
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.000134,
      "loss": 3.3067,
      "step": 136
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.000135,
      "loss": 3.1363,
      "step": 137
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00013600000000000003,
      "loss": 3.1319,
      "step": 138
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00013700000000000002,
      "loss": 3.1119,
      "step": 139
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00013800000000000002,
      "loss": 3.1286,
      "step": 140
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00013900000000000002,
      "loss": 3.098,
      "step": 141
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00014000000000000001,
      "loss": 3.1234,
      "step": 142
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00014099999999999998,
      "loss": 3.0793,
      "step": 143
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00014199999999999998,
      "loss": 3.1221,
      "step": 144
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00014299999999999998,
      "loss": 3.108,
      "step": 145
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.000144,
      "loss": 3.0942,
      "step": 146
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.000145,
      "loss": 3.0935,
      "step": 147
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.000146,
      "loss": 3.1319,
      "step": 148
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.000147,
      "loss": 3.1109,
      "step": 149
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.000148,
      "loss": 3.0755,
      "step": 150
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.000149,
      "loss": 3.1479,
      "step": 151
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00015,
      "loss": 3.0523,
      "step": 152
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.000151,
      "loss": 3.0499,
      "step": 153
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.000152,
      "loss": 3.0934,
      "step": 154
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.000153,
      "loss": 3.058,
      "step": 155
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000154,
      "loss": 3.0411,
      "step": 156
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.000155,
      "loss": 3.1034,
      "step": 157
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.000156,
      "loss": 3.0418,
      "step": 158
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.000157,
      "loss": 3.0837,
      "step": 159
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.000158,
      "loss": 3.0592,
      "step": 160
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00015900000000000002,
      "loss": 3.1358,
      "step": 161
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00016,
      "loss": 3.0622,
      "step": 162
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.000161,
      "loss": 3.2177,
      "step": 163
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.000162,
      "loss": 3.0518,
      "step": 164
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.000163,
      "loss": 3.1122,
      "step": 165
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.000164,
      "loss": 3.1148,
      "step": 166
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.000165,
      "loss": 3.0676,
      "step": 167
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00016600000000000002,
      "loss": 3.0519,
      "step": 168
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016700000000000002,
      "loss": 3.067,
      "step": 169
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00016800000000000002,
      "loss": 3.0615,
      "step": 170
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00016900000000000002,
      "loss": 3.057,
      "step": 171
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00017,
      "loss": 3.0626,
      "step": 172
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.000171,
      "loss": 3.0312,
      "step": 173
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00017199999999999998,
      "loss": 3.0662,
      "step": 174
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.000173,
      "loss": 3.0178,
      "step": 175
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.000174,
      "loss": 3.0241,
      "step": 176
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.000175,
      "loss": 3.0433,
      "step": 177
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.000176,
      "loss": 3.062,
      "step": 178
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.000177,
      "loss": 3.0332,
      "step": 179
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.000178,
      "loss": 3.0195,
      "step": 180
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.000179,
      "loss": 3.0231,
      "step": 181
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00017999999999999998,
      "loss": 3.036,
      "step": 182
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.000181,
      "loss": 3.0259,
      "step": 183
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.000182,
      "loss": 3.0137,
      "step": 184
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.000183,
      "loss": 3.0499,
      "step": 185
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.000184,
      "loss": 3.0125,
      "step": 186
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.000185,
      "loss": 3.0035,
      "step": 187
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.000186,
      "loss": 3.0726,
      "step": 188
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.000187,
      "loss": 3.0637,
      "step": 189
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00018800000000000002,
      "loss": 3.0634,
      "step": 190
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.000189,
      "loss": 3.0577,
      "step": 191
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00019,
      "loss": 3.0286,
      "step": 192
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.000191,
      "loss": 3.0609,
      "step": 193
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.000192,
      "loss": 3.0474,
      "step": 194
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.000193,
      "loss": 3.0479,
      "step": 195
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.000194,
      "loss": 3.0259,
      "step": 196
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00019500000000000002,
      "loss": 3.0908,
      "step": 197
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00019600000000000002,
      "loss": 3.0143,
      "step": 198
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00019700000000000002,
      "loss": 3.0447,
      "step": 199
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00019800000000000002,
      "loss": 3.046,
      "step": 200
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.000199,
      "loss": 3.0045,
      "step": 201
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 3.0116,
      "step": 202
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.000201,
      "loss": 3.0011,
      "step": 203
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.000202,
      "loss": 3.0235,
      "step": 204
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00020300000000000003,
      "loss": 3.0093,
      "step": 205
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.000204,
      "loss": 3.034,
      "step": 206
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.000205,
      "loss": 3.0111,
      "step": 207
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.000206,
      "loss": 2.9713,
      "step": 208
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.000207,
      "loss": 2.9926,
      "step": 209
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.000208,
      "loss": 2.9659,
      "step": 210
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00020899999999999998,
      "loss": 2.9718,
      "step": 211
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00021,
      "loss": 2.9629,
      "step": 212
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.000211,
      "loss": 2.9738,
      "step": 213
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.000212,
      "loss": 3.011,
      "step": 214
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.000213,
      "loss": 2.9922,
      "step": 215
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.000214,
      "loss": 2.9583,
      "step": 216
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.000215,
      "loss": 3.0016,
      "step": 217
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.000216,
      "loss": 2.9846,
      "step": 218
    },
    {
      "epoch": 2.0,
      "step": 218,
      "total_flos": 8.759583648689587e+17,
      "train_loss": 5.117166843983012,
      "train_runtime": 293.2898,
      "train_samples_per_second": 23.717,
      "train_steps_per_second": 0.743
    }
  ],
  "max_steps": 218,
  "num_train_epochs": 2,
  "total_flos": 8.759583648689587e+17,
  "trial_name": null,
  "trial_params": null
}