{
  "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": 2e-06,
      "loss": 4.7722,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-06,
      "loss": 4.8471,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-06,
      "loss": 4.8901,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-06,
      "loss": 4.7936,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 1e-05,
      "loss": 4.6226,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 1e-05,
      "loss": 4.6818,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2e-05,
      "loss": 4.6542,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4e-05,
      "loss": 4.6833,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6e-05,
      "loss": 4.5591,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.8e-05,
      "loss": 4.3732,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 4.4692,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.2e-05,
      "loss": 4.4868,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.4e-05,
      "loss": 4.3669,
      "step": 13
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.6e-05,
      "loss": 4.3111,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.8e-05,
      "loss": 4.3386,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 3e-05,
      "loss": 4.2529,
      "step": 16
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.2e-05,
      "loss": 4.3119,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 4.345,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.6e-05,
      "loss": 4.3061,
      "step": 19
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.8e-05,
      "loss": 4.3575,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 4e-05,
      "loss": 4.3639,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 4.332,
      "step": 22
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.4e-05,
      "loss": 4.2139,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.6e-05,
      "loss": 4.342,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.8e-05,
      "loss": 4.1966,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 4.4635,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.2e-05,
      "loss": 4.2323,
      "step": 27
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.4e-05,
      "loss": 4.2192,
      "step": 28
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.6e-05,
      "loss": 4.124,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.800000000000001e-05,
      "loss": 4.3273,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 6e-05,
      "loss": 4.3173,
      "step": 31
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.2e-05,
      "loss": 4.2152,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.4e-05,
      "loss": 4.2741,
      "step": 33
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.6e-05,
      "loss": 4.2259,
      "step": 34
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.800000000000001e-05,
      "loss": 4.2298,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 7.000000000000001e-05,
      "loss": 4.2443,
      "step": 36
    },
    {
      "epoch": 0.12,
      "learning_rate": 7.2e-05,
      "loss": 4.3289,
      "step": 37
    },
    {
      "epoch": 0.13,
      "learning_rate": 7.4e-05,
      "loss": 4.2854,
      "step": 38
    },
    {
      "epoch": 0.13,
      "learning_rate": 7.6e-05,
      "loss": 4.3371,
      "step": 39
    },
    {
      "epoch": 0.13,
      "learning_rate": 7.8e-05,
      "loss": 4.2088,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 8e-05,
      "loss": 4.2763,
      "step": 41
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.2e-05,
      "loss": 4.3167,
      "step": 42
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.400000000000001e-05,
      "loss": 4.1436,
      "step": 43
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.599999999999999e-05,
      "loss": 4.4299,
      "step": 44
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.8e-05,
      "loss": 4.3716,
      "step": 45
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.4052,
      "step": 46
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.2e-05,
      "loss": 4.3802,
      "step": 47
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.400000000000001e-05,
      "loss": 4.4711,
      "step": 48
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.6e-05,
      "loss": 4.5475,
      "step": 49
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.800000000000001e-05,
      "loss": 4.3163,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 4.2876,
      "step": 51
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000102,
      "loss": 4.1673,
      "step": 52
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000104,
      "loss": 4.1641,
      "step": 53
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000106,
      "loss": 4.1324,
      "step": 54
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000108,
      "loss": 4.1149,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00011,
      "loss": 4.1346,
      "step": 56
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000112,
      "loss": 4.2194,
      "step": 57
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000114,
      "loss": 4.2206,
      "step": 58
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00011600000000000001,
      "loss": 4.2098,
      "step": 59
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000118,
      "loss": 4.1653,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00012,
      "loss": 4.2034,
      "step": 61
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000122,
      "loss": 4.1436,
      "step": 62
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000124,
      "loss": 4.2173,
      "step": 63
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000126,
      "loss": 4.1701,
      "step": 64
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000128,
      "loss": 4.2817,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00013000000000000002,
      "loss": 4.2719,
      "step": 66
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000132,
      "loss": 4.2492,
      "step": 67
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000134,
      "loss": 4.2513,
      "step": 68
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00013600000000000003,
      "loss": 4.1976,
      "step": 69
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00013800000000000002,
      "loss": 4.2182,
      "step": 70
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00014000000000000001,
      "loss": 4.1483,
      "step": 71
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00014199999999999998,
      "loss": 4.2812,
      "step": 72
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000144,
      "loss": 4.224,
      "step": 73
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000146,
      "loss": 4.2017,
      "step": 74
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000148,
      "loss": 4.2882,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00015,
      "loss": 4.204,
      "step": 76
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000152,
      "loss": 4.1371,
      "step": 77
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000154,
      "loss": 4.2038,
      "step": 78
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000156,
      "loss": 4.0844,
      "step": 79
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.000158,
      "loss": 4.3707,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016,
      "loss": 4.2139,
      "step": 81
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000162,
      "loss": 4.2325,
      "step": 82
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000164,
      "loss": 4.1949,
      "step": 83
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016600000000000002,
      "loss": 4.2897,
      "step": 84
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016800000000000002,
      "loss": 4.3493,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017,
      "loss": 4.2138,
      "step": 86
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017199999999999998,
      "loss": 4.2173,
      "step": 87
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000174,
      "loss": 4.3482,
      "step": 88
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000176,
      "loss": 4.2918,
      "step": 89
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000178,
      "loss": 4.318,
      "step": 90
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.3096,
      "step": 91
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000182,
      "loss": 4.4027,
      "step": 92
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000184,
      "loss": 4.5431,
      "step": 93
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000186,
      "loss": 4.4248,
      "step": 94
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018800000000000002,
      "loss": 4.341,
      "step": 95
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019,
      "loss": 4.4704,
      "step": 96
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000192,
      "loss": 4.6444,
      "step": 97
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000194,
      "loss": 4.6959,
      "step": 98
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019600000000000002,
      "loss": 4.5906,
      "step": 99
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019800000000000002,
      "loss": 4.5786,
      "step": 100
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 4.2771,
      "step": 101
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000202,
      "loss": 4.3638,
      "step": 102
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000204,
      "loss": 4.3463,
      "step": 103
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000206,
      "loss": 4.2307,
      "step": 104
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000208,
      "loss": 4.3191,
      "step": 105
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00021,
      "loss": 4.2077,
      "step": 106
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000212,
      "loss": 4.171,
      "step": 107
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000214,
      "loss": 4.28,
      "step": 108
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000216,
      "loss": 4.3413,
      "step": 109
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000218,
      "loss": 4.3297,
      "step": 110
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00022,
      "loss": 4.3912,
      "step": 111
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000222,
      "loss": 4.2747,
      "step": 112
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000224,
      "loss": 4.2566,
      "step": 113
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00022600000000000002,
      "loss": 4.2711,
      "step": 114
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000228,
      "loss": 4.2383,
      "step": 115
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00023,
      "loss": 4.2432,
      "step": 116
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00023200000000000003,
      "loss": 4.1736,
      "step": 117
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00023400000000000002,
      "loss": 4.1851,
      "step": 118
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000236,
      "loss": 4.2587,
      "step": 119
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00023799999999999998,
      "loss": 4.2478,
      "step": 120
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00024,
      "loss": 4.2483,
      "step": 121
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000242,
      "loss": 4.3501,
      "step": 122
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000244,
      "loss": 4.3387,
      "step": 123
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000246,
      "loss": 4.4114,
      "step": 124
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000248,
      "loss": 4.3815,
      "step": 125
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00025,
      "loss": 4.318,
      "step": 126
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000252,
      "loss": 4.336,
      "step": 127
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000254,
      "loss": 4.2494,
      "step": 128
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000256,
      "loss": 4.3796,
      "step": 129
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00025800000000000004,
      "loss": 4.4553,
      "step": 130
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00026000000000000003,
      "loss": 4.3515,
      "step": 131
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000262,
      "loss": 4.1923,
      "step": 132
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000264,
      "loss": 4.5483,
      "step": 133
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000266,
      "loss": 4.3097,
      "step": 134
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000268,
      "loss": 4.411,
      "step": 135
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00027,
      "loss": 4.3845,
      "step": 136
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00027200000000000005,
      "loss": 4.261,
      "step": 137
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00027400000000000005,
      "loss": 4.2935,
      "step": 138
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00027600000000000004,
      "loss": 4.3502,
      "step": 139
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00027800000000000004,
      "loss": 4.2937,
      "step": 140
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00028000000000000003,
      "loss": 4.5061,
      "step": 141
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00028199999999999997,
      "loss": 4.5488,
      "step": 142
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00028399999999999996,
      "loss": 4.3519,
      "step": 143
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00028599999999999996,
      "loss": 4.4849,
      "step": 144
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000288,
      "loss": 4.6754,
      "step": 145
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00029,
      "loss": 4.3389,
      "step": 146
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000292,
      "loss": 5.3417,
      "step": 147
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000294,
      "loss": 4.739,
      "step": 148
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000296,
      "loss": 4.8816,
      "step": 149
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.000298,
      "loss": 5.0976,
      "step": 150
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 4.6187,
      "step": 151
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000302,
      "loss": 4.5796,
      "step": 152
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000304,
      "loss": 4.4965,
      "step": 153
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000306,
      "loss": 4.4367,
      "step": 154
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000308,
      "loss": 4.3843,
      "step": 155
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00031,
      "loss": 4.4425,
      "step": 156
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000312,
      "loss": 4.3224,
      "step": 157
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000314,
      "loss": 4.3704,
      "step": 158
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000316,
      "loss": 4.3799,
      "step": 159
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00031800000000000003,
      "loss": 4.4944,
      "step": 160
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00032,
      "loss": 4.4363,
      "step": 161
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.000322,
      "loss": 4.2812,
      "step": 162
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000324,
      "loss": 4.4024,
      "step": 163
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000326,
      "loss": 4.2637,
      "step": 164
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000328,
      "loss": 4.3806,
      "step": 165
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00033,
      "loss": 4.3163,
      "step": 166
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00033200000000000005,
      "loss": 4.2933,
      "step": 167
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00033400000000000004,
      "loss": 4.4188,
      "step": 168
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00033600000000000004,
      "loss": 4.4134,
      "step": 169
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00033800000000000003,
      "loss": 4.4127,
      "step": 170
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00034,
      "loss": 4.2583,
      "step": 171
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000342,
      "loss": 4.3188,
      "step": 172
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00034399999999999996,
      "loss": 4.3439,
      "step": 173
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000346,
      "loss": 4.4033,
      "step": 174
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000348,
      "loss": 4.5878,
      "step": 175
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00035,
      "loss": 4.4151,
      "step": 176
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000352,
      "loss": 4.4215,
      "step": 177
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000354,
      "loss": 4.305,
      "step": 178
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000356,
      "loss": 4.2926,
      "step": 179
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000358,
      "loss": 4.4736,
      "step": 180
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00035999999999999997,
      "loss": 4.4711,
      "step": 181
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000362,
      "loss": 4.4852,
      "step": 182
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000364,
      "loss": 4.4917,
      "step": 183
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000366,
      "loss": 4.4806,
      "step": 184
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000368,
      "loss": 4.4324,
      "step": 185
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00037,
      "loss": 4.3491,
      "step": 186
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000372,
      "loss": 4.4705,
      "step": 187
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000374,
      "loss": 4.3801,
      "step": 188
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00037600000000000003,
      "loss": 4.3337,
      "step": 189
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000378,
      "loss": 4.4856,
      "step": 190
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00038,
      "loss": 4.5416,
      "step": 191
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000382,
      "loss": 4.6047,
      "step": 192
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000384,
      "loss": 4.5076,
      "step": 193
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000386,
      "loss": 4.6097,
      "step": 194
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000388,
      "loss": 4.4656,
      "step": 195
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00039000000000000005,
      "loss": 4.5988,
      "step": 196
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00039200000000000004,
      "loss": 4.4527,
      "step": 197
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00039400000000000004,
      "loss": 5.1282,
      "step": 198
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00039600000000000003,
      "loss": 4.5988,
      "step": 199
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000398,
      "loss": 5.5887,
      "step": 200
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004,
      "loss": 6.4326,
      "step": 201
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000402,
      "loss": 4.8245,
      "step": 202
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000404,
      "loss": 4.625,
      "step": 203
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00040600000000000006,
      "loss": 4.7209,
      "step": 204
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000408,
      "loss": 4.6639,
      "step": 205
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00041,
      "loss": 4.709,
      "step": 206
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000412,
      "loss": 5.1396,
      "step": 207
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000414,
      "loss": 4.5794,
      "step": 208
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000416,
      "loss": 4.7483,
      "step": 209
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00041799999999999997,
      "loss": 4.6424,
      "step": 210
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00042,
      "loss": 4.4329,
      "step": 211
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000422,
      "loss": 4.5834,
      "step": 212
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000424,
      "loss": 4.893,
      "step": 213
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000426,
      "loss": 4.552,
      "step": 214
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000428,
      "loss": 4.6231,
      "step": 215
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00043,
      "loss": 4.4696,
      "step": 216
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000432,
      "loss": 4.5927,
      "step": 217
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00043400000000000003,
      "loss": 4.3821,
      "step": 218
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000436,
      "loss": 4.3723,
      "step": 219
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.000438,
      "loss": 4.5752,
      "step": 220
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00044,
      "loss": 4.4816,
      "step": 221
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000442,
      "loss": 4.4694,
      "step": 222
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000444,
      "loss": 4.4168,
      "step": 223
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.000446,
      "loss": 4.5059,
      "step": 224
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000448,
      "loss": 4.4529,
      "step": 225
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00045000000000000004,
      "loss": 4.6363,
      "step": 226
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00045200000000000004,
      "loss": 4.6407,
      "step": 227
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00045400000000000003,
      "loss": 4.3059,
      "step": 228
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000456,
      "loss": 4.4393,
      "step": 229
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.000458,
      "loss": 4.4847,
      "step": 230
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00046,
      "loss": 4.7014,
      "step": 231
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.000462,
      "loss": 4.6399,
      "step": 232
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00046400000000000006,
      "loss": 4.6032,
      "step": 233
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046600000000000005,
      "loss": 4.7998,
      "step": 234
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00046800000000000005,
      "loss": 4.6568,
      "step": 235
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00047,
      "loss": 4.5006,
      "step": 236
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000472,
      "loss": 4.5085,
      "step": 237
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.000474,
      "loss": 4.5638,
      "step": 238
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00047599999999999997,
      "loss": 4.5744,
      "step": 239
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00047799999999999996,
      "loss": 4.6586,
      "step": 240
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00048,
      "loss": 5.0386,
      "step": 241
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.000482,
      "loss": 4.9982,
      "step": 242
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000484,
      "loss": 4.6487,
      "step": 243
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000486,
      "loss": 4.4706,
      "step": 244
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000488,
      "loss": 4.581,
      "step": 245
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00049,
      "loss": 4.6588,
      "step": 246
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000492,
      "loss": 4.6926,
      "step": 247
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000494,
      "loss": 4.712,
      "step": 248
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000496,
      "loss": 5.1018,
      "step": 249
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000498,
      "loss": 4.5331,
      "step": 250
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0005,
      "loss": 4.8435,
      "step": 251
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0005020000000000001,
      "loss": 4.7466,
      "step": 252
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000504,
      "loss": 4.7877,
      "step": 253
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000506,
      "loss": 4.6377,
      "step": 254
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000508,
      "loss": 4.6048,
      "step": 255
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00051,
      "loss": 4.6086,
      "step": 256
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000512,
      "loss": 4.8381,
      "step": 257
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000514,
      "loss": 4.5629,
      "step": 258
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0005160000000000001,
      "loss": 4.6615,
      "step": 259
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000518,
      "loss": 4.5271,
      "step": 260
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0005200000000000001,
      "loss": 4.6963,
      "step": 261
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000522,
      "loss": 4.616,
      "step": 262
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.000524,
      "loss": 4.6217,
      "step": 263
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000526,
      "loss": 4.5987,
      "step": 264
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.000528,
      "loss": 4.6084,
      "step": 265
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0005300000000000001,
      "loss": 4.7973,
      "step": 266
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000532,
      "loss": 4.5744,
      "step": 267
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0005340000000000001,
      "loss": 4.7483,
      "step": 268
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000536,
      "loss": 4.4083,
      "step": 269
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0005380000000000001,
      "loss": 4.6659,
      "step": 270
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00054,
      "loss": 4.5806,
      "step": 271
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0005420000000000001,
      "loss": 4.4699,
      "step": 272
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0005440000000000001,
      "loss": 4.6826,
      "step": 273
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.000546,
      "loss": 4.5738,
      "step": 274
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0005480000000000001,
      "loss": 4.5848,
      "step": 275
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00055,
      "loss": 4.6156,
      "step": 276
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0005520000000000001,
      "loss": 4.6793,
      "step": 277
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000554,
      "loss": 4.6557,
      "step": 278
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0005560000000000001,
      "loss": 4.6794,
      "step": 279
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000558,
      "loss": 4.4396,
      "step": 280
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0005600000000000001,
      "loss": 4.7257,
      "step": 281
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0005620000000000001,
      "loss": 4.4927,
      "step": 282
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0005639999999999999,
      "loss": 4.6712,
      "step": 283
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.000566,
      "loss": 4.4852,
      "step": 284
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0005679999999999999,
      "loss": 4.7465,
      "step": 285
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00057,
      "loss": 4.7233,
      "step": 286
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0005719999999999999,
      "loss": 4.6061,
      "step": 287
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000574,
      "loss": 4.6499,
      "step": 288
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000576,
      "loss": 4.5556,
      "step": 289
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000578,
      "loss": 4.6277,
      "step": 290
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00058,
      "loss": 4.6354,
      "step": 291
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0005819999999999999,
      "loss": 4.7174,
      "step": 292
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000584,
      "loss": 4.5303,
      "step": 293
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0005859999999999999,
      "loss": 5.5856,
      "step": 294
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.000588,
      "loss": 4.7103,
      "step": 295
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00059,
      "loss": 5.2133,
      "step": 296
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000592,
      "loss": 4.7346,
      "step": 297
    },
    {
      "epoch": 1.0,
      "step": 297,
      "total_flos": 0.0,
      "train_loss": 4.473529295487837,
      "train_runtime": 4542.6558,
      "train_samples_per_second": 6.282,
      "train_steps_per_second": 0.065
    }
  ],
  "max_steps": 297,
  "num_train_epochs": 1,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}