{
  "best_metric": 0.6557291150093079,
  "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34B-hf_Open_Platypus_standardized/checkpoint-200",
  "epoch": 0.06694000502050038,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 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
    }
  ],
  "max_steps": 5000,
  "num_train_epochs": 2,
  "total_flos": 9.032114560106496e+16,
  "trial_name": null,
  "trial_params": null
}