{
  "best_metric": 0.662463366985321,
  "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34b-Python-hf_codellama_blob_1/checkpoint-200",
  "epoch": 0.1404001404001404,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 1.5667,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 0.9201,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 0.6019,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 0.861,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 1.064,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 1.0007,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 1.0533,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.8498,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.9189,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.9369,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 1.1375,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.8369,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.689,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.8885,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.9666,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.744,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.8998,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.8371,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.7615,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.6963,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 0.5974,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 1.4922,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 1.1272,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.4373,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 1.0598,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 1.191,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.6499,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.7526,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.7252,
      "step": 29
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.8555,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.479,
      "step": 31
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.5273,
      "step": 32
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.3907,
      "step": 33
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.5284,
      "step": 34
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 0.8696,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.9264,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.6812,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.4482,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 1.9031,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 1.3295,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.7498,
      "step": 41
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 1.4452,
      "step": 42
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 1.224,
      "step": 43
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.3272,
      "step": 44
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.7366,
      "step": 45
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 1.0331,
      "step": 46
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.8471,
      "step": 47
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.8171,
      "step": 48
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004,
      "loss": 0.418,
      "step": 49
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.6942,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.1712,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.5041,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.4619,
      "step": 53
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.5011,
      "step": 54
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.5,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.917,
      "step": 56
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.8142,
      "step": 57
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.8708,
      "step": 58
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.7987,
      "step": 59
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.9699,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 1.0015,
      "step": 61
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.8052,
      "step": 62
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 0.8645,
      "step": 63
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004,
      "loss": 1.1444,
      "step": 64
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 1.0087,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.5679,
      "step": 66
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.5507,
      "step": 67
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 1.1764,
      "step": 68
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.6332,
      "step": 69
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.8759,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.8385,
      "step": 71
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.7869,
      "step": 72
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 1.4457,
      "step": 73
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.9331,
      "step": 74
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.8943,
      "step": 75
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.5783,
      "step": 76
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.6433,
      "step": 77
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0004,
      "loss": 0.7517,
      "step": 78
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.5061,
      "step": 79
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.7332,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 1.6546,
      "step": 81
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.4723,
      "step": 82
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.2814,
      "step": 83
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.4068,
      "step": 84
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 1.1729,
      "step": 85
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.698,
      "step": 86
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.7746,
      "step": 87
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.5065,
      "step": 88
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.4654,
      "step": 89
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.5724,
      "step": 90
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 1.1535,
      "step": 91
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004,
      "loss": 0.3854,
      "step": 92
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 1.6848,
      "step": 93
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.6667,
      "step": 94
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.4526,
      "step": 95
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.7112,
      "step": 96
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.6816,
      "step": 97
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.7496,
      "step": 98
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 1.189,
      "step": 99
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 1.4239,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.4378,
      "step": 101
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 2.3054,
      "step": 102
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.1593,
      "step": 103
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.2481,
      "step": 104
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.6469,
      "step": 105
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004,
      "loss": 0.7417,
      "step": 106
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.7767,
      "step": 107
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.831,
      "step": 108
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.7954,
      "step": 109
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.6376,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.6208,
      "step": 111
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.9038,
      "step": 112
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.9994,
      "step": 113
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 1.0233,
      "step": 114
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.7573,
      "step": 115
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.5333,
      "step": 116
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.4886,
      "step": 117
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.75,
      "step": 118
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.6377,
      "step": 119
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.6518,
      "step": 120
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0004,
      "loss": 0.6409,
      "step": 121
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.5996,
      "step": 122
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.7964,
      "step": 123
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.5898,
      "step": 124
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.8753,
      "step": 125
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.6304,
      "step": 126
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.5428,
      "step": 127
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.8571,
      "step": 128
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.8339,
      "step": 129
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.6087,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.3547,
      "step": 131
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.3494,
      "step": 132
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.5394,
      "step": 133
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.4315,
      "step": 134
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004,
      "loss": 0.3575,
      "step": 135
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.4983,
      "step": 136
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.4292,
      "step": 137
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.6315,
      "step": 138
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.9827,
      "step": 139
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 1.4456,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.5151,
      "step": 141
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.4651,
      "step": 142
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.8682,
      "step": 143
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 1.1543,
      "step": 144
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.3378,
      "step": 145
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.5381,
      "step": 146
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.5189,
      "step": 147
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.3988,
      "step": 148
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004,
      "loss": 0.9694,
      "step": 149
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 1.2404,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.3767,
      "step": 151
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.5564,
      "step": 152
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.2665,
      "step": 153
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.172,
      "step": 154
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.6584,
      "step": 155
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.7588,
      "step": 156
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.9431,
      "step": 157
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.9456,
      "step": 158
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.7471,
      "step": 159
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.8477,
      "step": 160
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.7679,
      "step": 161
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 0.8937,
      "step": 162
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0004,
      "loss": 1.2858,
      "step": 163
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.7806,
      "step": 164
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.8034,
      "step": 165
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.6372,
      "step": 166
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.8217,
      "step": 167
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.3706,
      "step": 168
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 1.0851,
      "step": 169
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.6719,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 1.0366,
      "step": 171
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.5603,
      "step": 172
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.5651,
      "step": 173
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.3804,
      "step": 174
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.5946,
      "step": 175
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.7649,
      "step": 176
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.5035,
      "step": 177
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004,
      "loss": 0.8066,
      "step": 178
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.8046,
      "step": 179
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.4233,
      "step": 180
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.7945,
      "step": 181
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.5722,
      "step": 182
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.6088,
      "step": 183
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.4229,
      "step": 184
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.8723,
      "step": 185
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.9287,
      "step": 186
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.8082,
      "step": 187
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.4144,
      "step": 188
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.372,
      "step": 189
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.5725,
      "step": 190
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.3837,
      "step": 191
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0004,
      "loss": 0.5155,
      "step": 192
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 0.5472,
      "step": 193
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 0.6488,
      "step": 194
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 1.4385,
      "step": 195
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 0.3418,
      "step": 196
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 0.8811,
      "step": 197
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 0.8176,
      "step": 198
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 0.5379,
      "step": 199
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 1.0277,
      "step": 200
    },
    {
      "epoch": 0.14,
      "eval_loss": 0.662463366985321,
      "eval_runtime": 262.5709,
      "eval_samples_per_second": 1.904,
      "eval_steps_per_second": 0.952,
      "step": 200
    },
    {
      "epoch": 0.14,
      "mmlu_eval_accuracy": 0.41276444254447825,
      "mmlu_eval_accuracy_abstract_algebra": 0.09090909090909091,
      "mmlu_eval_accuracy_anatomy": 0.42857142857142855,
      "mmlu_eval_accuracy_astronomy": 0.5,
      "mmlu_eval_accuracy_business_ethics": 0.2727272727272727,
      "mmlu_eval_accuracy_clinical_knowledge": 0.4482758620689655,
      "mmlu_eval_accuracy_college_biology": 0.3125,
      "mmlu_eval_accuracy_college_chemistry": 0.375,
      "mmlu_eval_accuracy_college_computer_science": 0.5454545454545454,
      "mmlu_eval_accuracy_college_mathematics": 0.2727272727272727,
      "mmlu_eval_accuracy_college_medicine": 0.6363636363636364,
      "mmlu_eval_accuracy_college_physics": 0.2727272727272727,
      "mmlu_eval_accuracy_computer_security": 0.36363636363636365,
      "mmlu_eval_accuracy_conceptual_physics": 0.3076923076923077,
      "mmlu_eval_accuracy_econometrics": 0.4166666666666667,
      "mmlu_eval_accuracy_electrical_engineering": 0.5,
      "mmlu_eval_accuracy_elementary_mathematics": 0.4146341463414634,
      "mmlu_eval_accuracy_formal_logic": 0.5714285714285714,
      "mmlu_eval_accuracy_global_facts": 0.2,
      "mmlu_eval_accuracy_high_school_biology": 0.1875,
      "mmlu_eval_accuracy_high_school_chemistry": 0.4090909090909091,
      "mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
      "mmlu_eval_accuracy_high_school_european_history": 0.4444444444444444,
      "mmlu_eval_accuracy_high_school_geography": 0.5909090909090909,
      "mmlu_eval_accuracy_high_school_government_and_politics": 0.5714285714285714,
      "mmlu_eval_accuracy_high_school_macroeconomics": 0.32558139534883723,
      "mmlu_eval_accuracy_high_school_mathematics": 0.4482758620689655,
      "mmlu_eval_accuracy_high_school_microeconomics": 0.5714285714285714,
      "mmlu_loss": 0.7435930466353893,
      "step": 200
    }
  ],
  "max_steps": 30000,
  "num_train_epochs": 22,
  "total_flos": 3.977831564987597e+16,
  "trial_name": null,
  "trial_params": null
}