{
  "best_metric": 0.6144051551818848,
  "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34B-hf_Open_Platypus_standardized/checkpoint-600",
  "epoch": 0.20082001506150113,
  "global_step": 600,
  "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": 0.9974,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.874,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.1093,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.2226,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.9258,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.1969,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.0644,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.7431,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.7242,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.0492,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.819,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.7201,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.8492,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.8507,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.8835,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7159,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.5291,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.8011,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7135,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7048,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.9917,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.8041,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.5732,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.5196,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.6906,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.6765,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.8674,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.5437,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.6465,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.597,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.9258,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.6476,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.5101,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.8301,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7371,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.5574,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.4116,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.796,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7157,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.5822,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.4536,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.992,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.6346,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.3916,
      "step": 44
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.9415,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.708,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.9521,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0144,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.5007,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.5162,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.769,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.5958,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.1788,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.6173,
      "step": 54
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.727,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.5947,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.6464,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7074,
      "step": 58
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.5933,
      "step": 59
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.6751,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.5407,
      "step": 61
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8309,
      "step": 62
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7815,
      "step": 63
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7673,
      "step": 64
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.6196,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8225,
      "step": 66
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7859,
      "step": 67
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7924,
      "step": 68
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.785,
      "step": 69
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.678,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.6123,
      "step": 71
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0889,
      "step": 72
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8391,
      "step": 73
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.5602,
      "step": 74
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8796,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7054,
      "step": 76
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6829,
      "step": 77
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8272,
      "step": 78
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7807,
      "step": 79
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5505,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6452,
      "step": 81
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.4883,
      "step": 82
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7258,
      "step": 83
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5574,
      "step": 84
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8778,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8697,
      "step": 86
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.875,
      "step": 87
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8997,
      "step": 88
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.3743,
      "step": 89
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6712,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8667,
      "step": 91
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6988,
      "step": 92
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5897,
      "step": 93
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.8508,
      "step": 94
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5095,
      "step": 95
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.9916,
      "step": 96
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5758,
      "step": 97
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7502,
      "step": 98
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7904,
      "step": 99
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6974,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.766,
      "step": 101
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6698,
      "step": 102
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5184,
      "step": 103
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.6732,
      "step": 104
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6211,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6675,
      "step": 106
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5814,
      "step": 107
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6639,
      "step": 108
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8929,
      "step": 109
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6263,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.4944,
      "step": 111
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6063,
      "step": 112
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7328,
      "step": 113
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7439,
      "step": 114
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.675,
      "step": 115
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.55,
      "step": 116
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5713,
      "step": 117
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7216,
      "step": 118
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5499,
      "step": 119
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6456,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7837,
      "step": 121
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5507,
      "step": 122
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7078,
      "step": 123
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7494,
      "step": 124
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.461,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.4941,
      "step": 126
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.42,
      "step": 127
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.403,
      "step": 128
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.0497,
      "step": 129
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8345,
      "step": 130
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5247,
      "step": 131
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6948,
      "step": 132
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6085,
      "step": 133
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.668,
      "step": 134
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5969,
      "step": 135
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.8655,
      "step": 136
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6922,
      "step": 137
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6899,
      "step": 138
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5439,
      "step": 139
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5807,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6863,
      "step": 141
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.9302,
      "step": 142
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.702,
      "step": 143
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.4566,
      "step": 144
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.8384,
      "step": 145
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5952,
      "step": 146
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.4924,
      "step": 147
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6212,
      "step": 148
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.1828,
      "step": 149
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7859,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.0486,
      "step": 151
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6263,
      "step": 152
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.625,
      "step": 153
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6996,
      "step": 154
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5317,
      "step": 155
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7068,
      "step": 156
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6604,
      "step": 157
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6499,
      "step": 158
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5961,
      "step": 159
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.4959,
      "step": 160
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.7063,
      "step": 161
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5933,
      "step": 162
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6614,
      "step": 163
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5275,
      "step": 164
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5575,
      "step": 165
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7251,
      "step": 166
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7238,
      "step": 167
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.8683,
      "step": 168
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.565,
      "step": 169
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5126,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.0359,
      "step": 171
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5299,
      "step": 172
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6603,
      "step": 173
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6035,
      "step": 174
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.4791,
      "step": 175
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5295,
      "step": 176
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.4359,
      "step": 177
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9803,
      "step": 178
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5275,
      "step": 179
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6536,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6357,
      "step": 181
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.49,
      "step": 182
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6875,
      "step": 183
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.4978,
      "step": 184
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5567,
      "step": 185
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5616,
      "step": 186
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.6833,
      "step": 187
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5819,
      "step": 188
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9065,
      "step": 189
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.508,
      "step": 190
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7259,
      "step": 191
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.434,
      "step": 192
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.4405,
      "step": 193
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5654,
      "step": 194
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4657,
      "step": 195
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6703,
      "step": 196
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.0718,
      "step": 197
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6018,
      "step": 198
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5977,
      "step": 199
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.8486,
      "step": 200
    },
    {
      "epoch": 0.07,
      "eval_loss": 0.6557291150093079,
      "eval_runtime": 759.3262,
      "eval_samples_per_second": 1.317,
      "eval_steps_per_second": 0.658,
      "step": 200
    },
    {
      "epoch": 0.07,
      "mmlu_eval_accuracy": 0.45540898434673277,
      "mmlu_eval_accuracy_abstract_algebra": 0.2727272727272727,
      "mmlu_eval_accuracy_anatomy": 0.35714285714285715,
      "mmlu_eval_accuracy_astronomy": 0.4375,
      "mmlu_eval_accuracy_business_ethics": 0.5454545454545454,
      "mmlu_eval_accuracy_clinical_knowledge": 0.41379310344827586,
      "mmlu_eval_accuracy_college_biology": 0.1875,
      "mmlu_eval_accuracy_college_chemistry": 0.125,
      "mmlu_eval_accuracy_college_computer_science": 0.45454545454545453,
      "mmlu_eval_accuracy_college_mathematics": 0.36363636363636365,
      "mmlu_eval_accuracy_college_medicine": 0.4090909090909091,
      "mmlu_eval_accuracy_college_physics": 0.18181818181818182,
      "mmlu_eval_accuracy_computer_security": 0.5454545454545454,
      "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": 0.36585365853658536,
      "mmlu_eval_accuracy_formal_logic": 0.2857142857142857,
      "mmlu_eval_accuracy_global_facts": 0.3,
      "mmlu_eval_accuracy_high_school_biology": 0.21875,
      "mmlu_eval_accuracy_high_school_chemistry": 0.3181818181818182,
      "mmlu_eval_accuracy_high_school_computer_science": 0.7777777777777778,
      "mmlu_eval_accuracy_high_school_european_history": 0.6111111111111112,
      "mmlu_eval_accuracy_high_school_geography": 0.6363636363636364,
      "mmlu_eval_accuracy_high_school_government_and_politics": 0.7142857142857143,
      "mmlu_eval_accuracy_high_school_macroeconomics": 0.3023255813953488,
      "mmlu_eval_accuracy_high_school_mathematics": 0.41379310344827586,
      "mmlu_eval_accuracy_high_school_microeconomics": 0.4230769230769231,
      "mmlu_eval_accuracy_high_school_physics": 0.23529411764705882,
      "mmlu_eval_accuracy_high_school_psychology": 0.6333333333333333,
      "mmlu_eval_accuracy_high_school_statistics": 0.391304347826087,
      "mmlu_eval_accuracy_high_school_us_history": 0.5,
      "mmlu_eval_accuracy_high_school_world_history": 0.5384615384615384,
      "mmlu_eval_accuracy_human_aging": 0.5652173913043478,
      "mmlu_eval_accuracy_human_sexuality": 0.5,
      "mmlu_eval_accuracy_international_law": 0.46153846153846156,
      "mmlu_eval_accuracy_jurisprudence": 0.2727272727272727,
      "mmlu_eval_accuracy_logical_fallacies": 0.5555555555555556,
      "mmlu_eval_accuracy_machine_learning": 0.2727272727272727,
      "mmlu_eval_accuracy_management": 0.8181818181818182,
      "mmlu_eval_accuracy_marketing": 0.76,
      "mmlu_eval_accuracy_medical_genetics": 0.8181818181818182,
      "mmlu_eval_accuracy_miscellaneous": 0.5930232558139535,
      "mmlu_eval_accuracy_moral_disputes": 0.3684210526315789,
      "mmlu_eval_accuracy_moral_scenarios": 0.25,
      "mmlu_eval_accuracy_nutrition": 0.48484848484848486,
      "mmlu_eval_accuracy_philosophy": 0.5588235294117647,
      "mmlu_eval_accuracy_prehistory": 0.4,
      "mmlu_eval_accuracy_professional_accounting": 0.3870967741935484,
      "mmlu_eval_accuracy_professional_law": 0.2647058823529412,
      "mmlu_eval_accuracy_professional_medicine": 0.25806451612903225,
      "mmlu_eval_accuracy_professional_psychology": 0.463768115942029,
      "mmlu_eval_accuracy_public_relations": 0.5,
      "mmlu_eval_accuracy_security_studies": 0.48148148148148145,
      "mmlu_eval_accuracy_sociology": 0.7727272727272727,
      "mmlu_eval_accuracy_us_foreign_policy": 0.7272727272727273,
      "mmlu_eval_accuracy_virology": 0.5,
      "mmlu_eval_accuracy_world_religions": 0.6842105263157895,
      "mmlu_loss": 1.404012922207307,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7539,
      "step": 201
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5673,
      "step": 202
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5025,
      "step": 203
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4752,
      "step": 204
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.736,
      "step": 205
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4773,
      "step": 206
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4508,
      "step": 207
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.8819,
      "step": 208
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6631,
      "step": 209
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6067,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4271,
      "step": 211
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4825,
      "step": 212
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.8182,
      "step": 213
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6511,
      "step": 214
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5887,
      "step": 215
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5328,
      "step": 216
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6688,
      "step": 217
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.0067,
      "step": 218
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5932,
      "step": 219
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6998,
      "step": 220
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6783,
      "step": 221
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7357,
      "step": 222
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6226,
      "step": 223
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6971,
      "step": 224
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6065,
      "step": 225
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5975,
      "step": 226
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6704,
      "step": 227
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5387,
      "step": 228
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.655,
      "step": 229
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5337,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5077,
      "step": 231
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7793,
      "step": 232
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6353,
      "step": 233
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.8184,
      "step": 234
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5164,
      "step": 235
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5517,
      "step": 236
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4584,
      "step": 237
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6679,
      "step": 238
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4366,
      "step": 239
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6073,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4587,
      "step": 241
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6445,
      "step": 242
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4099,
      "step": 243
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.8068,
      "step": 244
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5481,
      "step": 245
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.6068,
      "step": 246
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.444,
      "step": 247
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.8129,
      "step": 248
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5736,
      "step": 249
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5598,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.7505,
      "step": 251
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5679,
      "step": 252
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.5698,
      "step": 253
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5696,
      "step": 254
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6921,
      "step": 255
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6299,
      "step": 256
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5304,
      "step": 257
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5249,
      "step": 258
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5026,
      "step": 259
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.9686,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7332,
      "step": 261
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.818,
      "step": 262
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7532,
      "step": 263
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5057,
      "step": 264
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7765,
      "step": 265
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6023,
      "step": 266
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6898,
      "step": 267
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.9004,
      "step": 268
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6033,
      "step": 269
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4235,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.601,
      "step": 271
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5113,
      "step": 272
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.264,
      "step": 273
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6642,
      "step": 274
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6201,
      "step": 275
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6221,
      "step": 276
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5185,
      "step": 277
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.8359,
      "step": 278
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4591,
      "step": 279
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.5939,
      "step": 280
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4488,
      "step": 281
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.9399,
      "step": 282
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.7421,
      "step": 283
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.311,
      "step": 284
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6534,
      "step": 285
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6236,
      "step": 286
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7579,
      "step": 287
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6619,
      "step": 288
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8431,
      "step": 289
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6214,
      "step": 290
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7332,
      "step": 291
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4542,
      "step": 292
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4751,
      "step": 293
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5033,
      "step": 294
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.1173,
      "step": 295
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.653,
      "step": 296
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5135,
      "step": 297
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6351,
      "step": 298
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5678,
      "step": 299
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4033,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5198,
      "step": 301
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.658,
      "step": 302
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5737,
      "step": 303
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4471,
      "step": 304
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4014,
      "step": 305
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6887,
      "step": 306
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8763,
      "step": 307
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4083,
      "step": 308
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6262,
      "step": 309
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4291,
      "step": 310
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6374,
      "step": 311
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8255,
      "step": 312
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5868,
      "step": 313
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.4965,
      "step": 314
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6123,
      "step": 315
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7349,
      "step": 316
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7083,
      "step": 317
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6545,
      "step": 318
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6046,
      "step": 319
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5912,
      "step": 320
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.4861,
      "step": 321
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6726,
      "step": 322
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.9282,
      "step": 323
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5542,
      "step": 324
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.572,
      "step": 325
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7893,
      "step": 326
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5002,
      "step": 327
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.671,
      "step": 328
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7084,
      "step": 329
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6358,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5766,
      "step": 331
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5403,
      "step": 332
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6217,
      "step": 333
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.4736,
      "step": 334
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.58,
      "step": 335
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5939,
      "step": 336
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6423,
      "step": 337
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5506,
      "step": 338
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.703,
      "step": 339
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5611,
      "step": 340
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.6143,
      "step": 341
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.5727,
      "step": 342
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.4942,
      "step": 343
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6503,
      "step": 344
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5855,
      "step": 345
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5166,
      "step": 346
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6751,
      "step": 347
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7308,
      "step": 348
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7075,
      "step": 349
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5562,
      "step": 350
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.4143,
      "step": 351
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6813,
      "step": 352
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7541,
      "step": 353
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5106,
      "step": 354
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6815,
      "step": 355
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6109,
      "step": 356
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5636,
      "step": 357
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7069,
      "step": 358
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7022,
      "step": 359
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.8022,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6228,
      "step": 361
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6192,
      "step": 362
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.9364,
      "step": 363
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.0686,
      "step": 364
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6621,
      "step": 365
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.4185,
      "step": 366
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.434,
      "step": 367
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.8,
      "step": 368
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.8418,
      "step": 369
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.7371,
      "step": 370
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6699,
      "step": 371
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.4759,
      "step": 372
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.3463,
      "step": 373
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4955,
      "step": 374
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7571,
      "step": 375
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7566,
      "step": 376
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.6771,
      "step": 377
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7395,
      "step": 378
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4656,
      "step": 379
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.9277,
      "step": 380
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5906,
      "step": 381
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5234,
      "step": 382
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.6513,
      "step": 383
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5257,
      "step": 384
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4017,
      "step": 385
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.644,
      "step": 386
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5911,
      "step": 387
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.8831,
      "step": 388
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7084,
      "step": 389
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4315,
      "step": 390
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.8026,
      "step": 391
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.8424,
      "step": 392
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4967,
      "step": 393
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.4148,
      "step": 394
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5364,
      "step": 395
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5742,
      "step": 396
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.7375,
      "step": 397
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5502,
      "step": 398
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5673,
      "step": 399
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.479,
      "step": 400
    },
    {
      "epoch": 0.13,
      "eval_loss": 0.6432567238807678,
      "eval_runtime": 756.6903,
      "eval_samples_per_second": 1.322,
      "eval_steps_per_second": 0.661,
      "step": 400
    },
    {
      "epoch": 0.13,
      "mmlu_eval_accuracy": 0.4410329246091114,
      "mmlu_eval_accuracy_abstract_algebra": 0.2727272727272727,
      "mmlu_eval_accuracy_anatomy": 0.6428571428571429,
      "mmlu_eval_accuracy_astronomy": 0.3125,
      "mmlu_eval_accuracy_business_ethics": 0.36363636363636365,
      "mmlu_eval_accuracy_clinical_knowledge": 0.4827586206896552,
      "mmlu_eval_accuracy_college_biology": 0.3125,
      "mmlu_eval_accuracy_college_chemistry": 0.125,
      "mmlu_eval_accuracy_college_computer_science": 0.09090909090909091,
      "mmlu_eval_accuracy_college_mathematics": 0.18181818181818182,
      "mmlu_eval_accuracy_college_medicine": 0.3181818181818182,
      "mmlu_eval_accuracy_college_physics": 0.45454545454545453,
      "mmlu_eval_accuracy_computer_security": 0.7272727272727273,
      "mmlu_eval_accuracy_conceptual_physics": 0.38461538461538464,
      "mmlu_eval_accuracy_econometrics": 0.3333333333333333,
      "mmlu_eval_accuracy_electrical_engineering": 0.25,
      "mmlu_eval_accuracy_elementary_mathematics": 0.2682926829268293,
      "mmlu_eval_accuracy_formal_logic": 0.07142857142857142,
      "mmlu_eval_accuracy_global_facts": 0.5,
      "mmlu_eval_accuracy_high_school_biology": 0.53125,
      "mmlu_eval_accuracy_high_school_chemistry": 0.22727272727272727,
      "mmlu_eval_accuracy_high_school_computer_science": 0.5555555555555556,
      "mmlu_eval_accuracy_high_school_european_history": 0.3888888888888889,
      "mmlu_eval_accuracy_high_school_geography": 0.6818181818181818,
      "mmlu_eval_accuracy_high_school_government_and_politics": 0.7142857142857143,
      "mmlu_eval_accuracy_high_school_macroeconomics": 0.3023255813953488,
      "mmlu_eval_accuracy_high_school_mathematics": 0.10344827586206896,
      "mmlu_eval_accuracy_high_school_microeconomics": 0.5384615384615384,
      "mmlu_eval_accuracy_high_school_physics": 0.4117647058823529,
      "mmlu_eval_accuracy_high_school_psychology": 0.6833333333333333,
      "mmlu_eval_accuracy_high_school_statistics": 0.2608695652173913,
      "mmlu_eval_accuracy_high_school_us_history": 0.6363636363636364,
      "mmlu_eval_accuracy_high_school_world_history": 0.46153846153846156,
      "mmlu_eval_accuracy_human_aging": 0.6086956521739131,
      "mmlu_eval_accuracy_human_sexuality": 0.4166666666666667,
      "mmlu_eval_accuracy_international_law": 0.8461538461538461,
      "mmlu_eval_accuracy_jurisprudence": 0.5454545454545454,
      "mmlu_eval_accuracy_logical_fallacies": 0.5555555555555556,
      "mmlu_eval_accuracy_machine_learning": 0.2727272727272727,
      "mmlu_eval_accuracy_management": 0.7272727272727273,
      "mmlu_eval_accuracy_marketing": 0.64,
      "mmlu_eval_accuracy_medical_genetics": 0.6363636363636364,
      "mmlu_eval_accuracy_miscellaneous": 0.627906976744186,
      "mmlu_eval_accuracy_moral_disputes": 0.42105263157894735,
      "mmlu_eval_accuracy_moral_scenarios": 0.22,
      "mmlu_eval_accuracy_nutrition": 0.48484848484848486,
      "mmlu_eval_accuracy_philosophy": 0.47058823529411764,
      "mmlu_eval_accuracy_prehistory": 0.6,
      "mmlu_eval_accuracy_professional_accounting": 0.3870967741935484,
      "mmlu_eval_accuracy_professional_law": 0.31176470588235294,
      "mmlu_eval_accuracy_professional_medicine": 0.3225806451612903,
      "mmlu_eval_accuracy_professional_psychology": 0.34782608695652173,
      "mmlu_eval_accuracy_public_relations": 0.3333333333333333,
      "mmlu_eval_accuracy_security_studies": 0.4074074074074074,
      "mmlu_eval_accuracy_sociology": 0.5454545454545454,
      "mmlu_eval_accuracy_us_foreign_policy": 0.6363636363636364,
      "mmlu_eval_accuracy_virology": 0.5,
      "mmlu_eval_accuracy_world_religions": 0.6842105263157895,
      "mmlu_loss": 1.5850642004461264,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5791,
      "step": 401
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.6984,
      "step": 402
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.6577,
      "step": 403
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7056,
      "step": 404
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6149,
      "step": 405
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6986,
      "step": 406
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5791,
      "step": 407
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7074,
      "step": 408
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6128,
      "step": 409
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6618,
      "step": 410
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5853,
      "step": 411
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7372,
      "step": 412
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6915,
      "step": 413
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5494,
      "step": 414
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5576,
      "step": 415
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.801,
      "step": 416
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7341,
      "step": 417
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6024,
      "step": 418
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5558,
      "step": 419
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.4463,
      "step": 420
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.531,
      "step": 421
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.376,
      "step": 422
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7166,
      "step": 423
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5849,
      "step": 424
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5586,
      "step": 425
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.8412,
      "step": 426
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5248,
      "step": 427
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6914,
      "step": 428
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7158,
      "step": 429
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5397,
      "step": 430
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.6427,
      "step": 431
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.8908,
      "step": 432
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.5162,
      "step": 433
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7492,
      "step": 434
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6496,
      "step": 435
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5557,
      "step": 436
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5541,
      "step": 437
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6776,
      "step": 438
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7697,
      "step": 439
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5601,
      "step": 440
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5604,
      "step": 441
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7305,
      "step": 442
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5166,
      "step": 443
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.4873,
      "step": 444
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6354,
      "step": 445
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6325,
      "step": 446
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.727,
      "step": 447
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7134,
      "step": 448
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.4263,
      "step": 449
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.9492,
      "step": 450
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5065,
      "step": 451
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5735,
      "step": 452
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7795,
      "step": 453
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.4623,
      "step": 454
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.4858,
      "step": 455
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.716,
      "step": 456
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.8737,
      "step": 457
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.4898,
      "step": 458
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.7951,
      "step": 459
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6631,
      "step": 460
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5274,
      "step": 461
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5595,
      "step": 462
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6568,
      "step": 463
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4264,
      "step": 464
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4296,
      "step": 465
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6789,
      "step": 466
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5369,
      "step": 467
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5055,
      "step": 468
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8553,
      "step": 469
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5986,
      "step": 470
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6609,
      "step": 471
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6719,
      "step": 472
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5331,
      "step": 473
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6491,
      "step": 474
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.7992,
      "step": 475
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.628,
      "step": 476
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8285,
      "step": 477
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4682,
      "step": 478
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6536,
      "step": 479
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8417,
      "step": 480
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4365,
      "step": 481
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6735,
      "step": 482
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.844,
      "step": 483
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6271,
      "step": 484
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5283,
      "step": 485
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.6396,
      "step": 486
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.4392,
      "step": 487
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.5326,
      "step": 488
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.3786,
      "step": 489
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8448,
      "step": 490
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.3758,
      "step": 491
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.9714,
      "step": 492
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.3945,
      "step": 493
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5928,
      "step": 494
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5628,
      "step": 495
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5287,
      "step": 496
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.6803,
      "step": 497
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5203,
      "step": 498
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4936,
      "step": 499
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.6099,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.0689,
      "step": 501
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5493,
      "step": 502
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.3357,
      "step": 503
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.743,
      "step": 504
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5006,
      "step": 505
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7855,
      "step": 506
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5236,
      "step": 507
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.6805,
      "step": 508
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.832,
      "step": 509
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7112,
      "step": 510
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4767,
      "step": 511
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.6167,
      "step": 512
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.4454,
      "step": 513
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.3774,
      "step": 514
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.0991,
      "step": 515
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5241,
      "step": 516
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5636,
      "step": 517
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5667,
      "step": 518
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.468,
      "step": 519
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5522,
      "step": 520
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.5915,
      "step": 521
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.7287,
      "step": 522
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3986,
      "step": 523
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6877,
      "step": 524
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.9186,
      "step": 525
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4384,
      "step": 526
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5418,
      "step": 527
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5993,
      "step": 528
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4271,
      "step": 529
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4797,
      "step": 530
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3676,
      "step": 531
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.678,
      "step": 532
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6784,
      "step": 533
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6061,
      "step": 534
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4749,
      "step": 535
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5826,
      "step": 536
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.687,
      "step": 537
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7116,
      "step": 538
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.8938,
      "step": 539
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4449,
      "step": 540
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.3321,
      "step": 541
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5173,
      "step": 542
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6881,
      "step": 543
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5084,
      "step": 544
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7647,
      "step": 545
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.437,
      "step": 546
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.6408,
      "step": 547
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.4488,
      "step": 548
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5057,
      "step": 549
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7203,
      "step": 550
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5925,
      "step": 551
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.5358,
      "step": 552
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.4949,
      "step": 553
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.4638,
      "step": 554
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5589,
      "step": 555
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.6149,
      "step": 556
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5596,
      "step": 557
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.4933,
      "step": 558
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5764,
      "step": 559
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5016,
      "step": 560
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.9582,
      "step": 561
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.8449,
      "step": 562
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5227,
      "step": 563
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.7754,
      "step": 564
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.8791,
      "step": 565
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5431,
      "step": 566
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.553,
      "step": 567
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.7373,
      "step": 568
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.435,
      "step": 569
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.7225,
      "step": 570
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.6534,
      "step": 571
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.3981,
      "step": 572
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.6436,
      "step": 573
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.6845,
      "step": 574
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5722,
      "step": 575
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5973,
      "step": 576
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.8464,
      "step": 577
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.5197,
      "step": 578
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.56,
      "step": 579
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.4127,
      "step": 580
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.8647,
      "step": 581
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.762,
      "step": 582
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5749,
      "step": 583
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5817,
      "step": 584
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5008,
      "step": 585
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4107,
      "step": 586
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.6836,
      "step": 587
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5035,
      "step": 588
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.9804,
      "step": 589
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5511,
      "step": 590
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4449,
      "step": 591
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4869,
      "step": 592
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.3506,
      "step": 593
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5544,
      "step": 594
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.4992,
      "step": 595
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7314,
      "step": 596
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.6752,
      "step": 597
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.629,
      "step": 598
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5341,
      "step": 599
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.5053,
      "step": 600
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.6144051551818848,
      "eval_runtime": 757.5405,
      "eval_samples_per_second": 1.32,
      "eval_steps_per_second": 0.66,
      "step": 600
    },
    {
      "epoch": 0.2,
      "mmlu_eval_accuracy": 0.41703920264423217,
      "mmlu_eval_accuracy_abstract_algebra": 0.2727272727272727,
      "mmlu_eval_accuracy_anatomy": 0.6428571428571429,
      "mmlu_eval_accuracy_astronomy": 0.1875,
      "mmlu_eval_accuracy_business_ethics": 0.45454545454545453,
      "mmlu_eval_accuracy_clinical_knowledge": 0.41379310344827586,
      "mmlu_eval_accuracy_college_biology": 0.375,
      "mmlu_eval_accuracy_college_chemistry": 0.125,
      "mmlu_eval_accuracy_college_computer_science": 0.18181818181818182,
      "mmlu_eval_accuracy_college_mathematics": 0.18181818181818182,
      "mmlu_eval_accuracy_college_medicine": 0.4090909090909091,
      "mmlu_eval_accuracy_college_physics": 0.5454545454545454,
      "mmlu_eval_accuracy_computer_security": 0.5454545454545454,
      "mmlu_eval_accuracy_conceptual_physics": 0.34615384615384615,
      "mmlu_eval_accuracy_econometrics": 0.25,
      "mmlu_eval_accuracy_electrical_engineering": 0.25,
      "mmlu_eval_accuracy_elementary_mathematics": 0.2682926829268293,
      "mmlu_eval_accuracy_formal_logic": 0.14285714285714285,
      "mmlu_eval_accuracy_global_facts": 0.3,
      "mmlu_eval_accuracy_high_school_biology": 0.40625,
      "mmlu_eval_accuracy_high_school_chemistry": 0.22727272727272727,
      "mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
      "mmlu_eval_accuracy_high_school_european_history": 0.4444444444444444,
      "mmlu_eval_accuracy_high_school_geography": 0.6818181818181818,
      "mmlu_eval_accuracy_high_school_government_and_politics": 0.38095238095238093,
      "mmlu_eval_accuracy_high_school_macroeconomics": 0.46511627906976744,
      "mmlu_eval_accuracy_high_school_mathematics": 0.10344827586206896,
      "mmlu_eval_accuracy_high_school_microeconomics": 0.46153846153846156,
      "mmlu_eval_accuracy_high_school_physics": 0.47058823529411764,
      "mmlu_eval_accuracy_high_school_psychology": 0.6833333333333333,
      "mmlu_eval_accuracy_high_school_statistics": 0.30434782608695654,
      "mmlu_eval_accuracy_high_school_us_history": 0.5,
      "mmlu_eval_accuracy_high_school_world_history": 0.4230769230769231,
      "mmlu_eval_accuracy_human_aging": 0.5652173913043478,
      "mmlu_eval_accuracy_human_sexuality": 0.16666666666666666,
      "mmlu_eval_accuracy_international_law": 0.7692307692307693,
      "mmlu_eval_accuracy_jurisprudence": 0.36363636363636365,
      "mmlu_eval_accuracy_logical_fallacies": 0.5,
      "mmlu_eval_accuracy_machine_learning": 0.2727272727272727,
      "mmlu_eval_accuracy_management": 0.45454545454545453,
      "mmlu_eval_accuracy_marketing": 0.68,
      "mmlu_eval_accuracy_medical_genetics": 0.6363636363636364,
      "mmlu_eval_accuracy_miscellaneous": 0.686046511627907,
      "mmlu_eval_accuracy_moral_disputes": 0.5263157894736842,
      "mmlu_eval_accuracy_moral_scenarios": 0.21,
      "mmlu_eval_accuracy_nutrition": 0.42424242424242425,
      "mmlu_eval_accuracy_philosophy": 0.47058823529411764,
      "mmlu_eval_accuracy_prehistory": 0.5714285714285714,
      "mmlu_eval_accuracy_professional_accounting": 0.3225806451612903,
      "mmlu_eval_accuracy_professional_law": 0.3,
      "mmlu_eval_accuracy_professional_medicine": 0.3225806451612903,
      "mmlu_eval_accuracy_professional_psychology": 0.4057971014492754,
      "mmlu_eval_accuracy_public_relations": 0.5,
      "mmlu_eval_accuracy_security_studies": 0.48148148148148145,
      "mmlu_eval_accuracy_sociology": 0.4090909090909091,
      "mmlu_eval_accuracy_us_foreign_policy": 0.5454545454545454,
      "mmlu_eval_accuracy_virology": 0.4444444444444444,
      "mmlu_eval_accuracy_world_religions": 0.631578947368421,
      "mmlu_loss": 1.0211270551146165,
      "step": 600
    }
  ],
  "max_steps": 5000,
  "num_train_epochs": 2,
  "total_flos": 2.689442076599255e+17,
  "trial_name": null,
  "trial_params": null
}