{
  "best_metric": 0.5880547761917114,
  "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34B-hf_codellama_blob_1/checkpoint-400",
  "epoch": 0.5616005616005616,
  "global_step": 400,
  "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
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.8622,
      "step": 201
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.7277,
      "step": 202
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7358,
      "step": 203
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.6171,
      "step": 204
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7573,
      "step": 205
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7947,
      "step": 206
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.438,
      "step": 207
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.4314,
      "step": 208
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7751,
      "step": 209
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.7193,
      "step": 210
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.5671,
      "step": 211
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.6712,
      "step": 212
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.5761,
      "step": 213
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.6589,
      "step": 214
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4178,
      "step": 215
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.4622,
      "step": 216
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.5189,
      "step": 217
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.8789,
      "step": 218
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.2529,
      "step": 219
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.5861,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6578,
      "step": 221
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.5289,
      "step": 222
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.5529,
      "step": 223
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.6496,
      "step": 224
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.7043,
      "step": 225
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.5955,
      "step": 226
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.6942,
      "step": 227
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.3691,
      "step": 228
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.6348,
      "step": 229
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.5973,
      "step": 230
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.2706,
      "step": 231
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.6844,
      "step": 232
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.2182,
      "step": 233
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.6845,
      "step": 234
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.6271,
      "step": 235
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.7151,
      "step": 236
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.5568,
      "step": 237
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.9098,
      "step": 238
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.0819,
      "step": 239
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.5894,
      "step": 240
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.833,
      "step": 241
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.4099,
      "step": 242
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.8302,
      "step": 243
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.4284,
      "step": 244
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.5485,
      "step": 245
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.5654,
      "step": 246
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.5599,
      "step": 247
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.5756,
      "step": 248
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.4219,
      "step": 249
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.7499,
      "step": 250
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.6233,
      "step": 251
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.6872,
      "step": 252
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.8836,
      "step": 253
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.8242,
      "step": 254
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.9424,
      "step": 255
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.6088,
      "step": 256
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.6363,
      "step": 257
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.6582,
      "step": 258
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.0579,
      "step": 259
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.5946,
      "step": 260
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.9046,
      "step": 261
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.6693,
      "step": 262
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.6784,
      "step": 263
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.4804,
      "step": 264
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.5627,
      "step": 265
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.4451,
      "step": 266
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.3804,
      "step": 267
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.4614,
      "step": 268
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.4386,
      "step": 269
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.5054,
      "step": 270
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.3299,
      "step": 271
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.3767,
      "step": 272
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.6474,
      "step": 273
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.5278,
      "step": 274
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.6876,
      "step": 275
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.6743,
      "step": 276
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.6905,
      "step": 277
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.5167,
      "step": 278
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.8943,
      "step": 279
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.5534,
      "step": 280
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.6501,
      "step": 281
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.4966,
      "step": 282
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.5887,
      "step": 283
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.5823,
      "step": 284
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.4327,
      "step": 285
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.6986,
      "step": 286
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.3851,
      "step": 287
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.9356,
      "step": 288
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.4721,
      "step": 289
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5978,
      "step": 290
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5783,
      "step": 291
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5125,
      "step": 292
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5305,
      "step": 293
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.5606,
      "step": 294
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.4431,
      "step": 295
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.7331,
      "step": 296
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.6763,
      "step": 297
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.4489,
      "step": 298
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5757,
      "step": 299
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.6899,
      "step": 300
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.5681,
      "step": 301
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.8638,
      "step": 302
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.5007,
      "step": 303
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.4922,
      "step": 304
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.6042,
      "step": 305
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.6398,
      "step": 306
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.6903,
      "step": 307
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.8877,
      "step": 308
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.7088,
      "step": 309
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.6013,
      "step": 310
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.8319,
      "step": 311
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.4064,
      "step": 312
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.6466,
      "step": 313
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.6873,
      "step": 314
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.9556,
      "step": 315
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.4119,
      "step": 316
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.5019,
      "step": 317
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6108,
      "step": 318
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.5208,
      "step": 319
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6555,
      "step": 320
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.3786,
      "step": 321
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.7625,
      "step": 322
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6542,
      "step": 323
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.7737,
      "step": 324
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.6379,
      "step": 325
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5464,
      "step": 326
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.6817,
      "step": 327
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.4032,
      "step": 328
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.1049,
      "step": 329
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.5744,
      "step": 330
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.3844,
      "step": 331
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6441,
      "step": 332
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.3441,
      "step": 333
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6981,
      "step": 334
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.437,
      "step": 335
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.9664,
      "step": 336
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.5144,
      "step": 337
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6048,
      "step": 338
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4976,
      "step": 339
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5221,
      "step": 340
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4715,
      "step": 341
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.7036,
      "step": 342
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5815,
      "step": 343
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.4843,
      "step": 344
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.5816,
      "step": 345
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.2778,
      "step": 346
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.5073,
      "step": 347
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.3484,
      "step": 348
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.4671,
      "step": 349
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.5155,
      "step": 350
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.5333,
      "step": 351
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.7035,
      "step": 352
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.6029,
      "step": 353
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.9084,
      "step": 354
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.6098,
      "step": 355
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.3604,
      "step": 356
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.5221,
      "step": 357
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.4751,
      "step": 358
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.9367,
      "step": 359
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.418,
      "step": 360
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.3642,
      "step": 361
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.5618,
      "step": 362
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.5638,
      "step": 363
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.9389,
      "step": 364
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.8087,
      "step": 365
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.5299,
      "step": 366
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.8063,
      "step": 367
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.4529,
      "step": 368
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.6113,
      "step": 369
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.813,
      "step": 370
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.7885,
      "step": 371
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.4745,
      "step": 372
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.7722,
      "step": 373
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.7242,
      "step": 374
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.4531,
      "step": 375
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.9054,
      "step": 376
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.9152,
      "step": 377
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.4414,
      "step": 378
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.5136,
      "step": 379
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.3315,
      "step": 380
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.5251,
      "step": 381
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.7332,
      "step": 382
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5032,
      "step": 383
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5535,
      "step": 384
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5916,
      "step": 385
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.6259,
      "step": 386
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.6234,
      "step": 387
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.5661,
      "step": 388
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.3717,
      "step": 389
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.4362,
      "step": 390
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.6232,
      "step": 391
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.6514,
      "step": 392
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.2381,
      "step": 393
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.599,
      "step": 394
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.5788,
      "step": 395
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.4485,
      "step": 396
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.5755,
      "step": 397
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.7999,
      "step": 398
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.4548,
      "step": 399
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.5872,
      "step": 400
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.5880547761917114,
      "eval_runtime": 396.9467,
      "eval_samples_per_second": 2.519,
      "eval_steps_per_second": 1.26,
      "step": 400
    },
    {
      "epoch": 0.56,
      "mmlu_eval_accuracy": 0.4846205369111515,
      "mmlu_eval_accuracy_abstract_algebra": 0.2727272727272727,
      "mmlu_eval_accuracy_anatomy": 0.35714285714285715,
      "mmlu_eval_accuracy_astronomy": 0.4375,
      "mmlu_eval_accuracy_business_ethics": 0.6363636363636364,
      "mmlu_eval_accuracy_clinical_knowledge": 0.41379310344827586,
      "mmlu_eval_accuracy_college_biology": 0.4375,
      "mmlu_eval_accuracy_college_chemistry": 0.125,
      "mmlu_eval_accuracy_college_computer_science": 0.36363636363636365,
      "mmlu_eval_accuracy_college_mathematics": 0.36363636363636365,
      "mmlu_eval_accuracy_college_medicine": 0.36363636363636365,
      "mmlu_eval_accuracy_college_physics": 0.2727272727272727,
      "mmlu_eval_accuracy_computer_security": 0.45454545454545453,
      "mmlu_eval_accuracy_conceptual_physics": 0.38461538461538464,
      "mmlu_eval_accuracy_econometrics": 0.3333333333333333,
      "mmlu_eval_accuracy_electrical_engineering": 0.5625,
      "mmlu_eval_accuracy_elementary_mathematics": 0.3170731707317073,
      "mmlu_eval_accuracy_formal_logic": 0.35714285714285715,
      "mmlu_eval_accuracy_global_facts": 0.2,
      "mmlu_eval_accuracy_high_school_biology": 0.28125,
      "mmlu_eval_accuracy_high_school_chemistry": 0.2727272727272727,
      "mmlu_eval_accuracy_high_school_computer_science": 0.7777777777777778,
      "mmlu_eval_accuracy_high_school_european_history": 0.6111111111111112,
      "mmlu_eval_accuracy_high_school_geography": 0.7727272727272727,
      "mmlu_eval_accuracy_high_school_government_and_politics": 0.7142857142857143,
      "mmlu_eval_accuracy_high_school_macroeconomics": 0.32558139534883723,
      "mmlu_eval_accuracy_high_school_mathematics": 0.4482758620689655,
      "mmlu_eval_accuracy_high_school_microeconomics": 0.34615384615384615,
      "mmlu_eval_accuracy_high_school_physics": 0.23529411764705882,
      "mmlu_eval_accuracy_high_school_psychology": 0.75,
      "mmlu_eval_accuracy_high_school_statistics": 0.391304347826087,
      "mmlu_eval_accuracy_high_school_us_history": 0.6818181818181818,
      "mmlu_eval_accuracy_high_school_world_history": 0.5769230769230769,
      "mmlu_eval_accuracy_human_aging": 0.6956521739130435,
      "mmlu_eval_accuracy_human_sexuality": 0.4166666666666667,
      "mmlu_eval_accuracy_international_law": 0.6923076923076923,
      "mmlu_eval_accuracy_jurisprudence": 0.45454545454545453,
      "mmlu_eval_accuracy_logical_fallacies": 0.7222222222222222,
      "mmlu_eval_accuracy_machine_learning": 0.45454545454545453,
      "mmlu_eval_accuracy_management": 0.7272727272727273,
      "mmlu_eval_accuracy_marketing": 0.76,
      "mmlu_eval_accuracy_medical_genetics": 0.8181818181818182,
      "mmlu_eval_accuracy_miscellaneous": 0.6395348837209303,
      "mmlu_eval_accuracy_moral_disputes": 0.39473684210526316,
      "mmlu_eval_accuracy_moral_scenarios": 0.25,
      "mmlu_eval_accuracy_nutrition": 0.5454545454545454,
      "mmlu_eval_accuracy_philosophy": 0.6176470588235294,
      "mmlu_eval_accuracy_prehistory": 0.45714285714285713,
      "mmlu_eval_accuracy_professional_accounting": 0.41935483870967744,
      "mmlu_eval_accuracy_professional_law": 0.25882352941176473,
      "mmlu_eval_accuracy_professional_medicine": 0.45161290322580644,
      "mmlu_eval_accuracy_professional_psychology": 0.43478260869565216,
      "mmlu_eval_accuracy_public_relations": 0.5,
      "mmlu_eval_accuracy_security_studies": 0.48148148148148145,
      "mmlu_eval_accuracy_sociology": 0.6818181818181818,
      "mmlu_eval_accuracy_us_foreign_policy": 0.7272727272727273,
      "mmlu_eval_accuracy_virology": 0.5,
      "mmlu_eval_accuracy_world_religions": 0.6842105263157895,
      "mmlu_loss": 0.9576842238246305,
      "step": 400
    }
  ],
  "max_steps": 5000,
  "num_train_epochs": 8,
  "total_flos": 2.1344593766252544e+17,
  "trial_name": null,
  "trial_params": null
}