{
  "best_metric": 0.6127411127090454,
  "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34B-hf_codellama_blob_1/checkpoint-200",
  "epoch": 0.2808002808002808,
  "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": 0.0002,
      "loss": 1.5798,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.6599,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.6807,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.4016,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.2944,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.5477,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.1555,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.8678,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.1943,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.8046,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0481,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7954,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.3301,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.9544,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8664,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.1004,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.6603,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5278,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5971,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6106,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.9927,
      "step": 21
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7429,
      "step": 22
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5403,
      "step": 23
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8739,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7539,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7598,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.9449,
      "step": 27
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7586,
      "step": 28
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5068,
      "step": 29
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6072,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6695,
      "step": 31
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.9185,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6406,
      "step": 33
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.2219,
      "step": 34
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.8394,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6016,
      "step": 36
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.3244,
      "step": 37
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5451,
      "step": 38
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7036,
      "step": 39
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6548,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9478,
      "step": 41
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9163,
      "step": 42
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9001,
      "step": 43
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7748,
      "step": 44
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7414,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.4948,
      "step": 46
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7041,
      "step": 47
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6931,
      "step": 48
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7196,
      "step": 49
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6884,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5539,
      "step": 51
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6652,
      "step": 52
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.9422,
      "step": 53
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.447,
      "step": 54
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7642,
      "step": 55
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4434,
      "step": 56
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7617,
      "step": 57
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5312,
      "step": 58
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7388,
      "step": 59
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.9614,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.2599,
      "step": 61
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.595,
      "step": 62
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7218,
      "step": 63
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5194,
      "step": 64
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5519,
      "step": 65
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5712,
      "step": 66
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6011,
      "step": 67
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6643,
      "step": 68
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7581,
      "step": 69
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.2109,
      "step": 70
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8814,
      "step": 71
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.507,
      "step": 72
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7569,
      "step": 73
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7431,
      "step": 74
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7837,
      "step": 75
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5242,
      "step": 76
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.3062,
      "step": 77
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5109,
      "step": 78
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.8998,
      "step": 79
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.875,
      "step": 80
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7363,
      "step": 81
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6465,
      "step": 82
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.8307,
      "step": 83
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6284,
      "step": 84
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5862,
      "step": 85
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7502,
      "step": 86
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6251,
      "step": 87
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7613,
      "step": 88
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6527,
      "step": 89
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5793,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.459,
      "step": 91
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7156,
      "step": 92
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.6078,
      "step": 93
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.2572,
      "step": 94
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5447,
      "step": 95
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.6109,
      "step": 96
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.0691,
      "step": 97
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.3149,
      "step": 98
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5433,
      "step": 99
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7371,
      "step": 100
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.8157,
      "step": 101
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5899,
      "step": 102
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6743,
      "step": 103
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.9741,
      "step": 104
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5697,
      "step": 105
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6596,
      "step": 106
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7502,
      "step": 107
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6138,
      "step": 108
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6065,
      "step": 109
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6661,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.987,
      "step": 111
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.773,
      "step": 112
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4769,
      "step": 113
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8634,
      "step": 114
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.9495,
      "step": 115
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6708,
      "step": 116
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.7206,
      "step": 117
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.628,
      "step": 118
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7703,
      "step": 119
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.6506,
      "step": 120
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.8484,
      "step": 121
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.8516,
      "step": 122
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4612,
      "step": 123
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5995,
      "step": 124
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6679,
      "step": 125
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.8091,
      "step": 126
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6702,
      "step": 127
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7588,
      "step": 128
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5301,
      "step": 129
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4867,
      "step": 130
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.0696,
      "step": 131
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3769,
      "step": 132
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.558,
      "step": 133
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.7511,
      "step": 134
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3991,
      "step": 135
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.6713,
      "step": 136
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.4538,
      "step": 137
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5503,
      "step": 138
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.6534,
      "step": 139
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4622,
      "step": 140
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5731,
      "step": 141
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7238,
      "step": 142
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.8143,
      "step": 143
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.539,
      "step": 144
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.447,
      "step": 145
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4711,
      "step": 146
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.5584,
      "step": 147
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.5887,
      "step": 148
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.3808,
      "step": 149
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.5771,
      "step": 150
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.5276,
      "step": 151
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.4132,
      "step": 152
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.9056,
      "step": 153
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.5737,
      "step": 154
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6992,
      "step": 155
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.4023,
      "step": 156
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6238,
      "step": 157
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.5521,
      "step": 158
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.6641,
      "step": 159
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.4478,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.865,
      "step": 161
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.4332,
      "step": 162
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.8205,
      "step": 163
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.6539,
      "step": 164
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.6957,
      "step": 165
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.6279,
      "step": 166
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.6073,
      "step": 167
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.5831,
      "step": 168
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.5383,
      "step": 169
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.0065,
      "step": 170
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.5239,
      "step": 171
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.4246,
      "step": 172
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.633,
      "step": 173
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.4318,
      "step": 174
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.5228,
      "step": 175
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.791,
      "step": 176
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.6141,
      "step": 177
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.4894,
      "step": 178
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.0344,
      "step": 179
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7332,
      "step": 180
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.6845,
      "step": 181
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.8027,
      "step": 182
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6537,
      "step": 183
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.7333,
      "step": 184
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6149,
      "step": 185
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.0586,
      "step": 186
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.6911,
      "step": 187
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.75,
      "step": 188
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.4598,
      "step": 189
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.5292,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.6164,
      "step": 191
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.3216,
      "step": 192
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.6229,
      "step": 193
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.6054,
      "step": 194
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.4821,
      "step": 195
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.8481,
      "step": 196
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.633,
      "step": 197
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.4537,
      "step": 198
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.6689,
      "step": 199
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.8891,
      "step": 200
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.6127411127090454,
      "eval_runtime": 397.1016,
      "eval_samples_per_second": 2.518,
      "eval_steps_per_second": 1.259,
      "step": 200
    },
    {
      "epoch": 0.28,
      "mmlu_eval_accuracy": 0.49968036766977914,
      "mmlu_eval_accuracy_abstract_algebra": 0.36363636363636365,
      "mmlu_eval_accuracy_anatomy": 0.5,
      "mmlu_eval_accuracy_astronomy": 0.375,
      "mmlu_eval_accuracy_business_ethics": 0.2727272727272727,
      "mmlu_eval_accuracy_clinical_knowledge": 0.4482758620689655,
      "mmlu_eval_accuracy_college_biology": 0.5,
      "mmlu_eval_accuracy_college_chemistry": 0.25,
      "mmlu_eval_accuracy_college_computer_science": 0.5454545454545454,
      "mmlu_eval_accuracy_college_mathematics": 0.45454545454545453,
      "mmlu_eval_accuracy_college_medicine": 0.5454545454545454,
      "mmlu_eval_accuracy_college_physics": 0.5454545454545454,
      "mmlu_eval_accuracy_computer_security": 0.45454545454545453,
      "mmlu_eval_accuracy_conceptual_physics": 0.2692307692307692,
      "mmlu_eval_accuracy_econometrics": 0.3333333333333333,
      "mmlu_eval_accuracy_electrical_engineering": 0.25,
      "mmlu_eval_accuracy_elementary_mathematics": 0.3902439024390244,
      "mmlu_eval_accuracy_formal_logic": 0.2857142857142857,
      "mmlu_eval_accuracy_global_facts": 0.3,
      "mmlu_eval_accuracy_high_school_biology": 0.46875,
      "mmlu_eval_accuracy_high_school_chemistry": 0.2727272727272727,
      "mmlu_eval_accuracy_high_school_computer_science": 0.5555555555555556,
      "mmlu_eval_accuracy_high_school_european_history": 0.6666666666666666,
      "mmlu_eval_accuracy_high_school_geography": 0.8181818181818182,
      "mmlu_eval_accuracy_high_school_government_and_politics": 0.7619047619047619,
      "mmlu_eval_accuracy_high_school_macroeconomics": 0.3488372093023256,
      "mmlu_eval_accuracy_high_school_mathematics": 0.1724137931034483,
      "mmlu_eval_accuracy_high_school_microeconomics": 0.5384615384615384,
      "mmlu_eval_accuracy_high_school_physics": 0.35294117647058826,
      "mmlu_eval_accuracy_high_school_psychology": 0.8333333333333334,
      "mmlu_eval_accuracy_high_school_statistics": 0.34782608695652173,
      "mmlu_eval_accuracy_high_school_us_history": 0.8181818181818182,
      "mmlu_eval_accuracy_high_school_world_history": 0.6153846153846154,
      "mmlu_eval_accuracy_human_aging": 0.4782608695652174,
      "mmlu_eval_accuracy_human_sexuality": 0.5,
      "mmlu_eval_accuracy_international_law": 0.8461538461538461,
      "mmlu_eval_accuracy_jurisprudence": 0.5454545454545454,
      "mmlu_eval_accuracy_logical_fallacies": 0.6666666666666666,
      "mmlu_eval_accuracy_machine_learning": 0.6363636363636364,
      "mmlu_eval_accuracy_management": 0.7272727272727273,
      "mmlu_eval_accuracy_marketing": 0.68,
      "mmlu_eval_accuracy_medical_genetics": 0.7272727272727273,
      "mmlu_eval_accuracy_miscellaneous": 0.6511627906976745,
      "mmlu_eval_accuracy_moral_disputes": 0.5,
      "mmlu_eval_accuracy_moral_scenarios": 0.21,
      "mmlu_eval_accuracy_nutrition": 0.696969696969697,
      "mmlu_eval_accuracy_philosophy": 0.5882352941176471,
      "mmlu_eval_accuracy_prehistory": 0.5428571428571428,
      "mmlu_eval_accuracy_professional_accounting": 0.3225806451612903,
      "mmlu_eval_accuracy_professional_law": 0.37058823529411766,
      "mmlu_eval_accuracy_professional_medicine": 0.4838709677419355,
      "mmlu_eval_accuracy_professional_psychology": 0.4492753623188406,
      "mmlu_eval_accuracy_public_relations": 0.4166666666666667,
      "mmlu_eval_accuracy_security_studies": 0.3333333333333333,
      "mmlu_eval_accuracy_sociology": 0.7272727272727273,
      "mmlu_eval_accuracy_us_foreign_policy": 0.5454545454545454,
      "mmlu_eval_accuracy_virology": 0.4444444444444444,
      "mmlu_eval_accuracy_world_religions": 0.7368421052631579,
      "mmlu_loss": 0.9665496518188607,
      "step": 200
    }
  ],
  "max_steps": 5000,
  "num_train_epochs": 8,
  "total_flos": 1.0947640647293338e+17,
  "trial_name": null,
  "trial_params": null
}