{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.4461,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.428,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.2611,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0726,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8897,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7397,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.699,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7029,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.63,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7011,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5865,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6309,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5263,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5052,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5682,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5076,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5277,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4567,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4831,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4565,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4851,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4713,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4407,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.486,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4523,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.3908,
      "step": 26
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.3896,
      "step": 27
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.461,
      "step": 28
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.3669,
      "step": 29
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.3972,
      "step": 30
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.4331,
      "step": 31
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4026,
      "step": 32
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.3947,
      "step": 33
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.3655,
      "step": 34
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.38,
      "step": 35
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.3827,
      "step": 36
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.3392,
      "step": 37
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.3551,
      "step": 38
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.3289,
      "step": 39
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4063,
      "step": 40
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.3476,
      "step": 41
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.3281,
      "step": 42
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.3472,
      "step": 43
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4055,
      "step": 44
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3521,
      "step": 45
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3066,
      "step": 46
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3168,
      "step": 47
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.2874,
      "step": 48
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.3128,
      "step": 49
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.3771,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.6121,
      "step": 51
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.6522,
      "step": 52
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.5899,
      "step": 53
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.553,
      "step": 54
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.5083,
      "step": 55
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.521,
      "step": 56
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.5096,
      "step": 57
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.505,
      "step": 58
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.5147,
      "step": 59
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.4574,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.4849,
      "step": 61
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.468,
      "step": 62
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.4689,
      "step": 63
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.4742,
      "step": 64
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.5248,
      "step": 65
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.4175,
      "step": 66
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.4392,
      "step": 67
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.432,
      "step": 68
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.4469,
      "step": 69
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.4488,
      "step": 70
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.4216,
      "step": 71
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.4339,
      "step": 72
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.4061,
      "step": 73
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4094,
      "step": 74
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.3995,
      "step": 75
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4378,
      "step": 76
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.3806,
      "step": 77
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.4527,
      "step": 78
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.4134,
      "step": 79
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.4041,
      "step": 80
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.4204,
      "step": 81
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.3897,
      "step": 82
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.3705,
      "step": 83
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.3859,
      "step": 84
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.4114,
      "step": 85
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.3563,
      "step": 86
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.3701,
      "step": 87
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.405,
      "step": 88
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3582,
      "step": 89
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3699,
      "step": 90
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.3795,
      "step": 91
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.3353,
      "step": 92
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.3374,
      "step": 93
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.3016,
      "step": 94
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.296,
      "step": 95
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.3053,
      "step": 96
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.2697,
      "step": 97
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.3006,
      "step": 98
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.2873,
      "step": 99
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.3578,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.5302,
      "step": 101
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5466,
      "step": 102
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.475,
      "step": 103
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5258,
      "step": 104
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.4626,
      "step": 105
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.4305,
      "step": 106
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.4337,
      "step": 107
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.4489,
      "step": 108
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.5187,
      "step": 109
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.3916,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.4749,
      "step": 111
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.513,
      "step": 112
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.4148,
      "step": 113
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4179,
      "step": 114
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4243,
      "step": 115
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.468,
      "step": 116
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.4043,
      "step": 117
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.4281,
      "step": 118
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4485,
      "step": 119
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4543,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4417,
      "step": 121
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.4127,
      "step": 122
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.3809,
      "step": 123
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.3857,
      "step": 124
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.3803,
      "step": 125
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.3578,
      "step": 126
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.384,
      "step": 127
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.3869,
      "step": 128
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.3881,
      "step": 129
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.3808,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.3545,
      "step": 131
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.4008,
      "step": 132
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.3862,
      "step": 133
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.387,
      "step": 134
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.3681,
      "step": 135
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.3414,
      "step": 136
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.3895,
      "step": 137
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.4336,
      "step": 138
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.3338,
      "step": 139
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.3223,
      "step": 140
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.337,
      "step": 141
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.3579,
      "step": 142
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.283,
      "step": 143
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.3138,
      "step": 144
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.3492,
      "step": 145
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.2995,
      "step": 146
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.3199,
      "step": 147
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.2826,
      "step": 148
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.2774,
      "step": 149
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.2919,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 2.259012175896576e+16,
  "trial_name": null,
  "trial_params": null
}