{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9987389659520807,
  "global_step": 297,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 4.7416,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 4.822,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.000000000000001e-07,
      "loss": 4.8917,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.000000000000001e-07,
      "loss": 4.833,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 4.7162,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 4.8449,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 4.8237,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 4.8885,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 4.7995,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.8e-06,
      "loss": 4.6334,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 4.765,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.2e-06,
      "loss": 4.7846,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 4.6955,
      "step": 13
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.6e-06,
      "loss": 4.6238,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 4.6308,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 3e-06,
      "loss": 4.5522,
      "step": 16
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 4.6306,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 4.6244,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.6e-06,
      "loss": 4.5672,
      "step": 19
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.8e-06,
      "loss": 4.6278,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.6397,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 4.5934,
      "step": 22
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.4e-06,
      "loss": 4.4719,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.6e-06,
      "loss": 4.6009,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.800000000000001e-06,
      "loss": 4.4169,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-06,
      "loss": 4.7091,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.2e-06,
      "loss": 4.4467,
      "step": 27
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.4e-06,
      "loss": 4.4314,
      "step": 28
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.600000000000001e-06,
      "loss": 4.3324,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.8e-06,
      "loss": 4.4922,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 6e-06,
      "loss": 4.4856,
      "step": 31
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.2e-06,
      "loss": 4.3944,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 4.4152,
      "step": 33
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.6e-06,
      "loss": 4.3853,
      "step": 34
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.800000000000001e-06,
      "loss": 4.3918,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 7.000000000000001e-06,
      "loss": 4.3543,
      "step": 36
    },
    {
      "epoch": 0.12,
      "learning_rate": 7.2e-06,
      "loss": 4.4801,
      "step": 37
    },
    {
      "epoch": 0.13,
      "learning_rate": 7.4e-06,
      "loss": 4.4362,
      "step": 38
    },
    {
      "epoch": 0.13,
      "learning_rate": 7.6e-06,
      "loss": 4.4816,
      "step": 39
    },
    {
      "epoch": 0.13,
      "learning_rate": 7.8e-06,
      "loss": 4.347,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.000000000000001e-06,
      "loss": 4.4076,
      "step": 41
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.200000000000001e-06,
      "loss": 4.4635,
      "step": 42
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.400000000000001e-06,
      "loss": 4.2502,
      "step": 43
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.599999999999999e-06,
      "loss": 4.5461,
      "step": 44
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.8e-06,
      "loss": 4.4963,
      "step": 45
    },
    {
      "epoch": 0.15,
      "learning_rate": 9e-06,
      "loss": 4.5238,
      "step": 46
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.2e-06,
      "loss": 4.5026,
      "step": 47
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.4e-06,
      "loss": 4.5945,
      "step": 48
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.600000000000001e-06,
      "loss": 4.7031,
      "step": 49
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.800000000000001e-06,
      "loss": 4.415,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 1e-05,
      "loss": 4.3481,
      "step": 51
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.02e-05,
      "loss": 4.2441,
      "step": 52
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.04e-05,
      "loss": 4.2067,
      "step": 53
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.06e-05,
      "loss": 4.206,
      "step": 54
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.08e-05,
      "loss": 4.1688,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 4.1921,
      "step": 56
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 4.3179,
      "step": 57
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 4.3096,
      "step": 58
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.16e-05,
      "loss": 4.2819,
      "step": 59
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.18e-05,
      "loss": 4.2195,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.2e-05,
      "loss": 4.2763,
      "step": 61
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.22e-05,
      "loss": 4.1643,
      "step": 62
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.24e-05,
      "loss": 4.2968,
      "step": 63
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 4.2292,
      "step": 64
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 4.2935,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 4.3136,
      "step": 66
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.32e-05,
      "loss": 4.2581,
      "step": 67
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.3400000000000002e-05,
      "loss": 4.2987,
      "step": 68
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 4.2362,
      "step": 69
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 4.1762,
      "step": 70
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 4.1934,
      "step": 71
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.42e-05,
      "loss": 4.309,
      "step": 72
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.44e-05,
      "loss": 4.2195,
      "step": 73
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.4599999999999999e-05,
      "loss": 4.2148,
      "step": 74
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.48e-05,
      "loss": 4.3228,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.5e-05,
      "loss": 4.1966,
      "step": 76
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.52e-05,
      "loss": 4.1663,
      "step": 77
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.54e-05,
      "loss": 4.2249,
      "step": 78
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.56e-05,
      "loss": 4.1044,
      "step": 79
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.58e-05,
      "loss": 4.2918,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 4.215,
      "step": 81
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.62e-05,
      "loss": 4.2246,
      "step": 82
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.6400000000000002e-05,
      "loss": 4.1984,
      "step": 83
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.66e-05,
      "loss": 4.2291,
      "step": 84
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 4.337,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 4.2152,
      "step": 86
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7199999999999998e-05,
      "loss": 4.2546,
      "step": 87
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.74e-05,
      "loss": 4.2966,
      "step": 88
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.76e-05,
      "loss": 4.3031,
      "step": 89
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.78e-05,
      "loss": 4.3245,
      "step": 90
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.8e-05,
      "loss": 4.3341,
      "step": 91
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 4.4108,
      "step": 92
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.84e-05,
      "loss": 4.3563,
      "step": 93
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.86e-05,
      "loss": 4.294,
      "step": 94
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.88e-05,
      "loss": 4.2507,
      "step": 95
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9e-05,
      "loss": 4.4097,
      "step": 96
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 4.6024,
      "step": 97
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.94e-05,
      "loss": 4.5406,
      "step": 98
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 4.5267,
      "step": 99
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9800000000000004e-05,
      "loss": 4.5753,
      "step": 100
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 4.1584,
      "step": 101
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 4.2193,
      "step": 102
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.04e-05,
      "loss": 4.2235,
      "step": 103
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.06e-05,
      "loss": 4.1147,
      "step": 104
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.08e-05,
      "loss": 4.2271,
      "step": 105
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.1e-05,
      "loss": 4.14,
      "step": 106
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.12e-05,
      "loss": 4.1039,
      "step": 107
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.1400000000000002e-05,
      "loss": 4.2112,
      "step": 108
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.16e-05,
      "loss": 4.2219,
      "step": 109
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.18e-05,
      "loss": 4.2005,
      "step": 110
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 4.2685,
      "step": 111
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.22e-05,
      "loss": 4.1964,
      "step": 112
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 4.1327,
      "step": 113
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.26e-05,
      "loss": 4.1996,
      "step": 114
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 4.1549,
      "step": 115
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 4.1736,
      "step": 116
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.32e-05,
      "loss": 4.1134,
      "step": 117
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.3400000000000003e-05,
      "loss": 4.1522,
      "step": 118
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.36e-05,
      "loss": 4.2019,
      "step": 119
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.38e-05,
      "loss": 4.208,
      "step": 120
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.4e-05,
      "loss": 4.2208,
      "step": 121
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.4200000000000002e-05,
      "loss": 4.2966,
      "step": 122
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.44e-05,
      "loss": 4.1012,
      "step": 123
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.46e-05,
      "loss": 4.2317,
      "step": 124
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.48e-05,
      "loss": 4.2931,
      "step": 125
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.5e-05,
      "loss": 4.1984,
      "step": 126
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.5200000000000003e-05,
      "loss": 4.2407,
      "step": 127
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.54e-05,
      "loss": 4.111,
      "step": 128
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.5600000000000002e-05,
      "loss": 4.2664,
      "step": 129
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.58e-05,
      "loss": 4.3569,
      "step": 130
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 4.2576,
      "step": 131
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.6200000000000003e-05,
      "loss": 4.1036,
      "step": 132
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.64e-05,
      "loss": 4.2504,
      "step": 133
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.6600000000000003e-05,
      "loss": 4.1388,
      "step": 134
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.6800000000000004e-05,
      "loss": 4.3289,
      "step": 135
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 4.2359,
      "step": 136
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7200000000000004e-05,
      "loss": 4.1676,
      "step": 137
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7400000000000002e-05,
      "loss": 4.1007,
      "step": 138
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.7600000000000003e-05,
      "loss": 4.1463,
      "step": 139
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.7800000000000005e-05,
      "loss": 4.1603,
      "step": 140
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 4.3578,
      "step": 141
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 4.1484,
      "step": 142
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.84e-05,
      "loss": 4.2449,
      "step": 143
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.86e-05,
      "loss": 4.2826,
      "step": 144
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.88e-05,
      "loss": 4.3742,
      "step": 145
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.9e-05,
      "loss": 4.1835,
      "step": 146
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.9199999999999998e-05,
      "loss": 4.3268,
      "step": 147
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.94e-05,
      "loss": 4.454,
      "step": 148
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.96e-05,
      "loss": 4.4426,
      "step": 149
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.98e-05,
      "loss": 4.5606,
      "step": 150
    },
    {
      "epoch": 0.51,
      "learning_rate": 3e-05,
      "loss": 4.2171,
      "step": 151
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.02e-05,
      "loss": 4.1916,
      "step": 152
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.04e-05,
      "loss": 4.2203,
      "step": 153
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.06e-05,
      "loss": 4.1566,
      "step": 154
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.08e-05,
      "loss": 4.1767,
      "step": 155
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.1e-05,
      "loss": 4.1967,
      "step": 156
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.12e-05,
      "loss": 4.1163,
      "step": 157
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.1400000000000004e-05,
      "loss": 4.1687,
      "step": 158
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.16e-05,
      "loss": 4.1796,
      "step": 159
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.18e-05,
      "loss": 4.1479,
      "step": 160
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 4.1677,
      "step": 161
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.2200000000000003e-05,
      "loss": 4.1325,
      "step": 162
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.24e-05,
      "loss": 4.203,
      "step": 163
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.26e-05,
      "loss": 4.1248,
      "step": 164
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.2800000000000004e-05,
      "loss": 4.1852,
      "step": 165
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.3e-05,
      "loss": 4.1591,
      "step": 166
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.32e-05,
      "loss": 4.1522,
      "step": 167
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.3400000000000005e-05,
      "loss": 4.1526,
      "step": 168
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 4.1457,
      "step": 169
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.38e-05,
      "loss": 4.0866,
      "step": 170
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 4.0714,
      "step": 171
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.4200000000000005e-05,
      "loss": 4.1798,
      "step": 172
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.4399999999999996e-05,
      "loss": 4.032,
      "step": 173
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.46e-05,
      "loss": 4.1041,
      "step": 174
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.48e-05,
      "loss": 4.2255,
      "step": 175
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.5e-05,
      "loss": 4.1027,
      "step": 176
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.52e-05,
      "loss": 4.2227,
      "step": 177
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.54e-05,
      "loss": 4.071,
      "step": 178
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.56e-05,
      "loss": 4.1006,
      "step": 179
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.58e-05,
      "loss": 4.2902,
      "step": 180
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.6e-05,
      "loss": 4.1315,
      "step": 181
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.62e-05,
      "loss": 4.0543,
      "step": 182
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.6400000000000004e-05,
      "loss": 4.0681,
      "step": 183
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.66e-05,
      "loss": 4.1713,
      "step": 184
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.68e-05,
      "loss": 4.2008,
      "step": 185
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.7e-05,
      "loss": 4.1546,
      "step": 186
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.72e-05,
      "loss": 4.1709,
      "step": 187
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.74e-05,
      "loss": 4.1473,
      "step": 188
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.76e-05,
      "loss": 4.1097,
      "step": 189
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.7800000000000004e-05,
      "loss": 4.2103,
      "step": 190
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.8e-05,
      "loss": 4.2618,
      "step": 191
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.82e-05,
      "loss": 4.2977,
      "step": 192
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 4.3615,
      "step": 193
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.86e-05,
      "loss": 4.2861,
      "step": 194
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.88e-05,
      "loss": 4.2774,
      "step": 195
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 4.231,
      "step": 196
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 4.0982,
      "step": 197
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.94e-05,
      "loss": 4.6038,
      "step": 198
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.960000000000001e-05,
      "loss": 4.3139,
      "step": 199
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.9800000000000005e-05,
      "loss": 4.5138,
      "step": 200
    },
    {
      "epoch": 0.68,
      "learning_rate": 4e-05,
      "loss": 4.2164,
      "step": 201
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.02e-05,
      "loss": 4.1559,
      "step": 202
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 4.1452,
      "step": 203
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 4.0741,
      "step": 204
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.08e-05,
      "loss": 4.1215,
      "step": 205
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.1e-05,
      "loss": 4.0996,
      "step": 206
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.12e-05,
      "loss": 4.164,
      "step": 207
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.14e-05,
      "loss": 4.1406,
      "step": 208
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.16e-05,
      "loss": 4.1043,
      "step": 209
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.18e-05,
      "loss": 4.2183,
      "step": 210
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.2e-05,
      "loss": 3.9963,
      "step": 211
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.22e-05,
      "loss": 4.1352,
      "step": 212
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.24e-05,
      "loss": 4.1756,
      "step": 213
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.26e-05,
      "loss": 4.1339,
      "step": 214
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 4.1696,
      "step": 215
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.3e-05,
      "loss": 4.1555,
      "step": 216
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.32e-05,
      "loss": 4.104,
      "step": 217
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.3400000000000005e-05,
      "loss": 4.0657,
      "step": 218
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.36e-05,
      "loss": 4.0738,
      "step": 219
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.38e-05,
      "loss": 4.1514,
      "step": 220
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 4.0798,
      "step": 221
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.4200000000000004e-05,
      "loss": 4.0354,
      "step": 222
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.44e-05,
      "loss": 4.0835,
      "step": 223
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.46e-05,
      "loss": 4.1241,
      "step": 224
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.4800000000000005e-05,
      "loss": 4.1139,
      "step": 225
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.5e-05,
      "loss": 4.1373,
      "step": 226
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.52e-05,
      "loss": 4.1314,
      "step": 227
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.5400000000000006e-05,
      "loss": 4.0515,
      "step": 228
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.5600000000000004e-05,
      "loss": 4.0908,
      "step": 229
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.58e-05,
      "loss": 4.1007,
      "step": 230
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.600000000000001e-05,
      "loss": 4.2356,
      "step": 231
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.6200000000000005e-05,
      "loss": 4.0633,
      "step": 232
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.64e-05,
      "loss": 4.1935,
      "step": 233
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.660000000000001e-05,
      "loss": 4.1731,
      "step": 234
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 4.2143,
      "step": 235
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.7e-05,
      "loss": 4.0391,
      "step": 236
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.72e-05,
      "loss": 4.1392,
      "step": 237
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.74e-05,
      "loss": 4.2716,
      "step": 238
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.76e-05,
      "loss": 4.0908,
      "step": 239
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.78e-05,
      "loss": 4.1365,
      "step": 240
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.8e-05,
      "loss": 4.2666,
      "step": 241
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.82e-05,
      "loss": 4.1715,
      "step": 242
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 4.1233,
      "step": 243
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.86e-05,
      "loss": 4.1594,
      "step": 244
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.88e-05,
      "loss": 4.1508,
      "step": 245
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.9e-05,
      "loss": 4.3186,
      "step": 246
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.92e-05,
      "loss": 4.2761,
      "step": 247
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.94e-05,
      "loss": 4.2375,
      "step": 248
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.96e-05,
      "loss": 4.3505,
      "step": 249
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 4.3046,
      "step": 250
    },
    {
      "epoch": 0.84,
      "learning_rate": 5e-05,
      "loss": 4.23,
      "step": 251
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.02e-05,
      "loss": 4.1051,
      "step": 252
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.0400000000000005e-05,
      "loss": 4.0697,
      "step": 253
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.0600000000000003e-05,
      "loss": 4.0968,
      "step": 254
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.08e-05,
      "loss": 4.1046,
      "step": 255
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 4.0778,
      "step": 256
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.1200000000000004e-05,
      "loss": 4.2512,
      "step": 257
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.14e-05,
      "loss": 4.0971,
      "step": 258
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.16e-05,
      "loss": 4.1317,
      "step": 259
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.1800000000000005e-05,
      "loss": 4.0438,
      "step": 260
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 4.1585,
      "step": 261
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.22e-05,
      "loss": 4.1922,
      "step": 262
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.2400000000000007e-05,
      "loss": 4.0355,
      "step": 263
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.2600000000000005e-05,
      "loss": 4.0942,
      "step": 264
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.28e-05,
      "loss": 4.0823,
      "step": 265
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.300000000000001e-05,
      "loss": 4.2057,
      "step": 266
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.3200000000000006e-05,
      "loss": 4.1053,
      "step": 267
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.3400000000000004e-05,
      "loss": 4.0612,
      "step": 268
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.360000000000001e-05,
      "loss": 4.0192,
      "step": 269
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.380000000000001e-05,
      "loss": 4.1746,
      "step": 270
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 4.0217,
      "step": 271
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.420000000000001e-05,
      "loss": 4.0175,
      "step": 272
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.440000000000001e-05,
      "loss": 4.0711,
      "step": 273
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.4600000000000006e-05,
      "loss": 4.0552,
      "step": 274
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.4800000000000004e-05,
      "loss": 4.1794,
      "step": 275
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.500000000000001e-05,
      "loss": 4.1307,
      "step": 276
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.520000000000001e-05,
      "loss": 4.1143,
      "step": 277
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.5400000000000005e-05,
      "loss": 4.0236,
      "step": 278
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.560000000000001e-05,
      "loss": 4.0805,
      "step": 279
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.580000000000001e-05,
      "loss": 4.0284,
      "step": 280
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 4.1211,
      "step": 281
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.620000000000001e-05,
      "loss": 4.0672,
      "step": 282
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.6399999999999995e-05,
      "loss": 4.2571,
      "step": 283
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.66e-05,
      "loss": 4.0389,
      "step": 284
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.68e-05,
      "loss": 4.1248,
      "step": 285
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 4.1542,
      "step": 286
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.72e-05,
      "loss": 4.0784,
      "step": 287
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.74e-05,
      "loss": 4.0661,
      "step": 288
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.76e-05,
      "loss": 4.0908,
      "step": 289
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.7799999999999995e-05,
      "loss": 4.179,
      "step": 290
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.8e-05,
      "loss": 4.17,
      "step": 291
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.82e-05,
      "loss": 4.2625,
      "step": 292
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.8399999999999997e-05,
      "loss": 4.1965,
      "step": 293
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.86e-05,
      "loss": 4.5008,
      "step": 294
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.88e-05,
      "loss": 4.1809,
      "step": 295
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.9e-05,
      "loss": 4.5448,
      "step": 296
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.92e-05,
      "loss": 4.4749,
      "step": 297
    },
    {
      "epoch": 1.0,
      "step": 297,
      "total_flos": 0.0,
      "train_loss": 4.260829443883414,
      "train_runtime": 4532.5114,
      "train_samples_per_second": 6.296,
      "train_steps_per_second": 0.066
    }
  ],
  "max_steps": 297,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}