{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.959866220735786,
  "eval_steps": 500,
  "global_step": 296,
  "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": 3.3735,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018927892607143717,
      "loss": 3.4333,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 3.4033,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 3.2866,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 3.1956,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 3.2327,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 3.2285,
      "step": 7
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 3.1553,
      "step": 8
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 3.1208,
      "step": 9
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 3.1433,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 3.2463,
      "step": 11
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 3.2375,
      "step": 12
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 3.1509,
      "step": 13
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 3.1587,
      "step": 14
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 3.1511,
      "step": 15
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 3.1155,
      "step": 16
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 3.2439,
      "step": 17
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 3.124,
      "step": 18
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 3.1448,
      "step": 19
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 3.1562,
      "step": 20
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 3.1211,
      "step": 21
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 3.1689,
      "step": 22
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 3.032,
      "step": 23
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 3.0703,
      "step": 24
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 3.0483,
      "step": 25
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 3.0603,
      "step": 26
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 3.0596,
      "step": 27
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 3.0471,
      "step": 28
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 3.0806,
      "step": 29
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 3.1157,
      "step": 30
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 2.957,
      "step": 31
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 3.0391,
      "step": 32
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 3.0684,
      "step": 33
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 3.0413,
      "step": 34
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 2.9812,
      "step": 35
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 2.9978,
      "step": 36
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 2.9976,
      "step": 37
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 2.9836,
      "step": 38
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 3.002,
      "step": 39
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 3.0127,
      "step": 40
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 2.9312,
      "step": 41
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 2.9155,
      "step": 42
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 3.0063,
      "step": 43
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 2.9919,
      "step": 44
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 2.9868,
      "step": 45
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 3.0422,
      "step": 46
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 2.9829,
      "step": 47
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 2.9717,
      "step": 48
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 3.0137,
      "step": 49
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 2.9841,
      "step": 50
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 2.9727,
      "step": 51
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 2.9177,
      "step": 52
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 2.928,
      "step": 53
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 2.9106,
      "step": 54
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 2.9189,
      "step": 55
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 2.9849,
      "step": 56
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 2.9912,
      "step": 57
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 2.9336,
      "step": 58
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 3.0144,
      "step": 59
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 2.938,
      "step": 60
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 2.9417,
      "step": 61
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 3.0129,
      "step": 62
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 2.9568,
      "step": 63
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 2.9773,
      "step": 64
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 2.8545,
      "step": 65
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 2.9648,
      "step": 66
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 2.9768,
      "step": 67
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 2.9709,
      "step": 68
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 2.8271,
      "step": 69
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 2.8428,
      "step": 70
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 2.8523,
      "step": 71
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 2.9082,
      "step": 72
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 2.9089,
      "step": 73
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 2.845,
      "step": 74
    },
    {
      "epoch": 0.99,
      "eval_loss": 2.943359375,
      "eval_runtime": 93.5805,
      "eval_samples_per_second": 2.511,
      "eval_steps_per_second": 1.261,
      "step": 74
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 2.8491,
      "step": 75
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0003,
      "loss": 2.7544,
      "step": 76
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0003,
      "loss": 2.7939,
      "step": 77
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0003,
      "loss": 2.834,
      "step": 78
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0003,
      "loss": 2.8313,
      "step": 79
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0003,
      "loss": 2.8206,
      "step": 80
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0003,
      "loss": 2.8225,
      "step": 81
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0003,
      "loss": 2.8218,
      "step": 82
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0003,
      "loss": 2.7241,
      "step": 83
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0003,
      "loss": 2.7415,
      "step": 84
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0003,
      "loss": 2.8203,
      "step": 85
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0003,
      "loss": 2.7729,
      "step": 86
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0003,
      "loss": 2.7581,
      "step": 87
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0003,
      "loss": 2.75,
      "step": 88
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0003,
      "loss": 2.7783,
      "step": 89
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003,
      "loss": 2.7671,
      "step": 90
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0003,
      "loss": 2.7773,
      "step": 91
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0003,
      "loss": 2.7808,
      "step": 92
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0003,
      "loss": 2.6885,
      "step": 93
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0003,
      "loss": 2.7766,
      "step": 94
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0003,
      "loss": 2.8889,
      "step": 95
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0003,
      "loss": 2.7654,
      "step": 96
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0003,
      "loss": 2.7915,
      "step": 97
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0003,
      "loss": 2.7454,
      "step": 98
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0003,
      "loss": 2.7744,
      "step": 99
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0003,
      "loss": 2.7595,
      "step": 100
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0003,
      "loss": 2.7566,
      "step": 101
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0003,
      "loss": 2.6567,
      "step": 102
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0003,
      "loss": 2.7207,
      "step": 103
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0003,
      "loss": 2.7051,
      "step": 104
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0003,
      "loss": 2.6968,
      "step": 105
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0003,
      "loss": 2.7419,
      "step": 106
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0003,
      "loss": 2.7764,
      "step": 107
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0003,
      "loss": 2.6992,
      "step": 108
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0003,
      "loss": 2.7251,
      "step": 109
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0003,
      "loss": 2.7183,
      "step": 110
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0003,
      "loss": 2.7048,
      "step": 111
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0003,
      "loss": 2.6912,
      "step": 112
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0003,
      "loss": 2.7107,
      "step": 113
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0003,
      "loss": 2.7776,
      "step": 114
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0003,
      "loss": 2.7649,
      "step": 115
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0003,
      "loss": 2.7378,
      "step": 116
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0003,
      "loss": 2.7139,
      "step": 117
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0003,
      "loss": 2.7139,
      "step": 118
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0003,
      "loss": 2.7632,
      "step": 119
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0003,
      "loss": 2.7268,
      "step": 120
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0003,
      "loss": 2.7534,
      "step": 121
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0003,
      "loss": 2.7964,
      "step": 122
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0003,
      "loss": 2.729,
      "step": 123
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0003,
      "loss": 2.748,
      "step": 124
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0003,
      "loss": 2.7483,
      "step": 125
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0003,
      "loss": 2.7832,
      "step": 126
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0003,
      "loss": 2.6958,
      "step": 127
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0003,
      "loss": 2.7148,
      "step": 128
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0003,
      "loss": 2.6577,
      "step": 129
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0003,
      "loss": 2.7297,
      "step": 130
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0003,
      "loss": 2.7915,
      "step": 131
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0003,
      "loss": 2.7109,
      "step": 132
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0003,
      "loss": 2.7217,
      "step": 133
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0003,
      "loss": 2.7512,
      "step": 134
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0003,
      "loss": 2.8252,
      "step": 135
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0003,
      "loss": 2.7615,
      "step": 136
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0003,
      "loss": 2.7061,
      "step": 137
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0003,
      "loss": 2.7461,
      "step": 138
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0003,
      "loss": 2.6477,
      "step": 139
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0003,
      "loss": 2.7061,
      "step": 140
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0003,
      "loss": 2.7549,
      "step": 141
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0003,
      "loss": 2.7356,
      "step": 142
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0003,
      "loss": 2.6492,
      "step": 143
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0003,
      "loss": 2.6611,
      "step": 144
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0003,
      "loss": 2.7107,
      "step": 145
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0003,
      "loss": 2.7417,
      "step": 146
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0003,
      "loss": 2.6902,
      "step": 147
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0003,
      "loss": 2.6724,
      "step": 148
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0003,
      "loss": 2.7014,
      "step": 149
    },
    {
      "epoch": 1.99,
      "eval_loss": 2.880859375,
      "eval_runtime": 92.4687,
      "eval_samples_per_second": 2.541,
      "eval_steps_per_second": 1.276,
      "step": 149
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0003,
      "loss": 2.584,
      "step": 150
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0003,
      "loss": 2.552,
      "step": 151
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0003,
      "loss": 2.5398,
      "step": 152
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0003,
      "loss": 2.5303,
      "step": 153
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0003,
      "loss": 2.6184,
      "step": 154
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0003,
      "loss": 2.5503,
      "step": 155
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0003,
      "loss": 2.5076,
      "step": 156
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0003,
      "loss": 2.541,
      "step": 157
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0003,
      "loss": 2.5581,
      "step": 158
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0003,
      "loss": 2.5159,
      "step": 159
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0003,
      "loss": 2.5339,
      "step": 160
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0003,
      "loss": 2.5261,
      "step": 161
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0003,
      "loss": 2.4651,
      "step": 162
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0003,
      "loss": 2.5435,
      "step": 163
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0003,
      "loss": 2.5171,
      "step": 164
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0003,
      "loss": 2.4304,
      "step": 165
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0003,
      "loss": 2.5093,
      "step": 166
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0003,
      "loss": 2.4856,
      "step": 167
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0003,
      "loss": 2.4858,
      "step": 168
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0003,
      "loss": 2.5056,
      "step": 169
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0003,
      "loss": 2.5198,
      "step": 170
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0003,
      "loss": 2.4861,
      "step": 171
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0003,
      "loss": 2.4849,
      "step": 172
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0003,
      "loss": 2.5073,
      "step": 173
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0003,
      "loss": 2.49,
      "step": 174
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0003,
      "loss": 2.5383,
      "step": 175
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0003,
      "loss": 2.48,
      "step": 176
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0003,
      "loss": 2.4902,
      "step": 177
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0003,
      "loss": 2.5698,
      "step": 178
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0003,
      "loss": 2.4888,
      "step": 179
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0003,
      "loss": 2.5122,
      "step": 180
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0003,
      "loss": 2.5344,
      "step": 181
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0003,
      "loss": 2.5466,
      "step": 182
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0003,
      "loss": 2.5459,
      "step": 183
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0003,
      "loss": 2.5022,
      "step": 184
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0003,
      "loss": 2.5464,
      "step": 185
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0003,
      "loss": 2.5015,
      "step": 186
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0003,
      "loss": 2.5337,
      "step": 187
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0003,
      "loss": 2.5454,
      "step": 188
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0003,
      "loss": 2.6106,
      "step": 189
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0003,
      "loss": 2.5547,
      "step": 190
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0003,
      "loss": 2.4438,
      "step": 191
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0003,
      "loss": 2.5503,
      "step": 192
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0003,
      "loss": 2.512,
      "step": 193
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0003,
      "loss": 2.571,
      "step": 194
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0003,
      "loss": 2.5137,
      "step": 195
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0003,
      "loss": 2.5757,
      "step": 196
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0003,
      "loss": 2.5974,
      "step": 197
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0003,
      "loss": 2.491,
      "step": 198
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0003,
      "loss": 2.5105,
      "step": 199
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0003,
      "loss": 2.533,
      "step": 200
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0003,
      "loss": 2.3655,
      "step": 201
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0003,
      "loss": 2.4854,
      "step": 202
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0003,
      "loss": 2.4832,
      "step": 203
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0003,
      "loss": 2.4731,
      "step": 204
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0003,
      "loss": 2.5583,
      "step": 205
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0003,
      "loss": 2.5283,
      "step": 206
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0003,
      "loss": 2.4526,
      "step": 207
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0003,
      "loss": 2.5413,
      "step": 208
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0003,
      "loss": 2.512,
      "step": 209
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0003,
      "loss": 2.4771,
      "step": 210
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0003,
      "loss": 2.3931,
      "step": 211
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0003,
      "loss": 2.5083,
      "step": 212
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0003,
      "loss": 2.5298,
      "step": 213
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0003,
      "loss": 2.4907,
      "step": 214
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0003,
      "loss": 2.5344,
      "step": 215
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0003,
      "loss": 2.5618,
      "step": 216
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0003,
      "loss": 2.5276,
      "step": 217
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0003,
      "loss": 2.5593,
      "step": 218
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0003,
      "loss": 2.4836,
      "step": 219
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0003,
      "loss": 2.553,
      "step": 220
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0003,
      "loss": 2.4614,
      "step": 221
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0003,
      "loss": 2.5391,
      "step": 222
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0003,
      "loss": 2.5266,
      "step": 223
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0003,
      "loss": 2.4602,
      "step": 224
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.8984375,
      "eval_runtime": 92.6223,
      "eval_samples_per_second": 2.537,
      "eval_steps_per_second": 1.274,
      "step": 224
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0003,
      "loss": 2.3523,
      "step": 225
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0003,
      "loss": 2.2725,
      "step": 226
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0003,
      "loss": 2.3198,
      "step": 227
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0003,
      "loss": 2.3079,
      "step": 228
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0003,
      "loss": 2.1519,
      "step": 229
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0003,
      "loss": 2.167,
      "step": 230
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0003,
      "loss": 2.2751,
      "step": 231
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0003,
      "loss": 2.2551,
      "step": 232
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0003,
      "loss": 2.2458,
      "step": 233
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0003,
      "loss": 2.231,
      "step": 234
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0003,
      "loss": 2.196,
      "step": 235
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0003,
      "loss": 2.252,
      "step": 236
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0003,
      "loss": 2.2136,
      "step": 237
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.0003,
      "loss": 2.2168,
      "step": 238
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0003,
      "loss": 2.1956,
      "step": 239
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.0003,
      "loss": 2.2034,
      "step": 240
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0003,
      "loss": 2.2258,
      "step": 241
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0003,
      "loss": 2.2449,
      "step": 242
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0003,
      "loss": 2.2307,
      "step": 243
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0003,
      "loss": 2.1936,
      "step": 244
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0003,
      "loss": 2.2822,
      "step": 245
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0003,
      "loss": 2.2852,
      "step": 246
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.0003,
      "loss": 2.3364,
      "step": 247
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0003,
      "loss": 2.2305,
      "step": 248
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0003,
      "loss": 2.2444,
      "step": 249
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0003,
      "loss": 2.3188,
      "step": 250
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0003,
      "loss": 2.1794,
      "step": 251
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0003,
      "loss": 2.3245,
      "step": 252
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0003,
      "loss": 2.2239,
      "step": 253
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0003,
      "loss": 2.2244,
      "step": 254
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0003,
      "loss": 2.2092,
      "step": 255
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0003,
      "loss": 2.2544,
      "step": 256
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0003,
      "loss": 2.2385,
      "step": 257
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0003,
      "loss": 2.2588,
      "step": 258
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0003,
      "loss": 2.3193,
      "step": 259
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0003,
      "loss": 2.2844,
      "step": 260
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0003,
      "loss": 2.2725,
      "step": 261
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0003,
      "loss": 2.241,
      "step": 262
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0003,
      "loss": 2.272,
      "step": 263
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0003,
      "loss": 2.292,
      "step": 264
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0003,
      "loss": 2.2366,
      "step": 265
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0003,
      "loss": 2.2412,
      "step": 266
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0003,
      "loss": 2.2478,
      "step": 267
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0003,
      "loss": 2.2139,
      "step": 268
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0003,
      "loss": 2.2808,
      "step": 269
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0003,
      "loss": 2.3083,
      "step": 270
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0003,
      "loss": 2.2112,
      "step": 271
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0003,
      "loss": 2.2676,
      "step": 272
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0003,
      "loss": 2.2532,
      "step": 273
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0003,
      "loss": 2.3318,
      "step": 274
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0003,
      "loss": 2.2227,
      "step": 275
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0003,
      "loss": 2.3018,
      "step": 276
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0003,
      "loss": 2.2874,
      "step": 277
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.0003,
      "loss": 2.282,
      "step": 278
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0003,
      "loss": 2.2705,
      "step": 279
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.0003,
      "loss": 2.2534,
      "step": 280
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0003,
      "loss": 2.2744,
      "step": 281
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0003,
      "loss": 2.2212,
      "step": 282
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0003,
      "loss": 2.2507,
      "step": 283
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0003,
      "loss": 2.3235,
      "step": 284
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.0003,
      "loss": 2.2859,
      "step": 285
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0003,
      "loss": 2.2629,
      "step": 286
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.0003,
      "loss": 2.27,
      "step": 287
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0003,
      "loss": 2.2432,
      "step": 288
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0003,
      "loss": 2.2455,
      "step": 289
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.0003,
      "loss": 2.3276,
      "step": 290
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0003,
      "loss": 2.2976,
      "step": 291
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0003,
      "loss": 2.2205,
      "step": 292
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0003,
      "loss": 2.2708,
      "step": 293
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0003,
      "loss": 2.218,
      "step": 294
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0003,
      "loss": 2.2646,
      "step": 295
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0003,
      "loss": 2.2998,
      "step": 296
    },
    {
      "epoch": 3.96,
      "eval_loss": 2.978515625,
      "eval_runtime": 92.5066,
      "eval_samples_per_second": 2.54,
      "eval_steps_per_second": 1.276,
      "step": 296
    },
    {
      "epoch": 3.96,
      "step": 296,
      "total_flos": 1.523122330182615e+17,
      "train_loss": 2.6439707988017314,
      "train_runtime": 11454.487,
      "train_samples_per_second": 0.835,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 296,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 1000,
  "total_flos": 1.523122330182615e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}