{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8219074598677998,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0004,
      "loss": 2.8174,
      "step": 2
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0008,
      "loss": 2.8801,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009999575185316995,
      "loss": 2.8676,
      "step": 6
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009996177100962712,
      "loss": 2.8733,
      "step": 8
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000998938324184584,
      "loss": 2.9105,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009979198225579969,
      "loss": 2.9035,
      "step": 12
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009965628974662145,
      "loss": 2.8884,
      "step": 14
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00099486847117678,
      "loss": 2.879,
      "step": 16
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0009928376953482344,
      "loss": 2.9521,
      "step": 18
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0009904719502473634,
      "loss": 2.9526,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009877728438110645,
      "loss": 2.9211,
      "step": 22
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009847422105534738,
      "loss": 2.8804,
      "step": 24
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000981382110319093,
      "loss": 2.9045,
      "step": 26
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0009776948268827657,
      "loss": 2.9369,
      "step": 28
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0009736828663974526,
      "loss": 2.9049,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009693489556908641,
      "loss": 2.9069,
      "step": 32
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0009646960404121041,
      "loss": 2.9257,
      "step": 34
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009597272830295876,
      "loss": 2.8909,
      "step": 36
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00095444606068159,
      "loss": 2.9512,
      "step": 38
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009488559628808938,
      "loss": 3.0004,
      "step": 40
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009429607890750862,
      "loss": 3.1118,
      "step": 42
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009367645460641715,
      "loss": 3.082,
      "step": 44
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0009302714452772515,
      "loss": 3.0348,
      "step": 46
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009234858999101231,
      "loss": 3.0918,
      "step": 48
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009164125219257418,
      "loss": 3.0042,
      "step": 50
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.000909056118919587,
      "loss": 2.971,
      "step": 52
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0009014216908520619,
      "loss": 2.9717,
      "step": 54
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0008935144266501469,
      "loss": 3.0012,
      "step": 56
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0008853397006806182,
      "loss": 2.9478,
      "step": 58
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0008769030690972262,
      "loss": 2.9312,
      "step": 60
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0008682102660643197,
      "loss": 2.898,
      "step": 62
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0008592671998594795,
      "loss": 2.8673,
      "step": 64
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0008500799488578119,
      "loss": 2.8984,
      "step": 66
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0008406547574006325,
      "loss": 2.8778,
      "step": 68
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0008309980315513443,
      "loss": 2.8978,
      "step": 70
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0008211163347414004,
      "loss": 2.8657,
      "step": 72
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0008110163833093049,
      "loss": 2.881,
      "step": 74
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0008007050419356898,
      "loss": 2.8425,
      "step": 76
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0007901893189775639,
      "loss": 2.899,
      "step": 78
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0007794763617049123,
      "loss": 2.8116,
      "step": 80
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0007685734514428766,
      "loss": 2.8995,
      "step": 82
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0007574879986228245,
      "loss": 3.874,
      "step": 84
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.000746227537745667,
      "loss": 2.7812,
      "step": 86
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0007347997222608493,
      "loss": 2.7706,
      "step": 88
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0007232123193644956,
      "loss": 2.727,
      "step": 90
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0007114732047202433,
      "loss": 2.7466,
      "step": 92
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.000699590357106354,
      "loss": 2.7615,
      "step": 94
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0006875718529927403,
      "loss": 2.7312,
      "step": 96
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0006754258610515948,
      "loss": 2.7192,
      "step": 98
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0006631606366053507,
      "loss": 2.7178,
      "step": 100
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0006507845160157477,
      "loss": 2.7426,
      "step": 102
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0006383059110178205,
      "loss": 2.78,
      "step": 104
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0006257333030026537,
      "loss": 2.801,
      "step": 106
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0006130752372527982,
      "loss": 2.8101,
      "step": 108
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0006003403171342563,
      "loss": 2.8212,
      "step": 110
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0005875371982489958,
      "loss": 2.8073,
      "step": 112
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0005746745825519538,
      "loss": 2.7252,
      "step": 114
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0005617612124365409,
      "loss": 2.783,
      "step": 116
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0005488058647926577,
      "loss": 2.7034,
      "step": 118
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0005358173450412649,
      "loss": 2.7864,
      "step": 120
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0005228044811495631,
      "loss": 2.7136,
      "step": 122
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0005097761176308471,
      "loss": 2.762,
      "step": 124
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0004967411095331149,
      "loss": 2.7633,
      "step": 126
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0004837083164205159,
      "loss": 2.7863,
      "step": 128
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00047068659635173026,
      "loss": 2.7523,
      "step": 130
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00045768479985937196,
      "loss": 2.6834,
      "step": 132
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0004447117639345052,
      "loss": 2.7107,
      "step": 134
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0004317763060203664,
      "loss": 2.7554,
      "step": 136
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0004188872180193723,
      "loss": 2.7709,
      "step": 138
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00040605326031748645,
      "loss": 2.7199,
      "step": 140
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0003932831558300074,
      "loss": 2.702,
      "step": 142
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0003805855840728246,
      "loss": 2.7447,
      "step": 144
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00036796917526317154,
      "loss": 2.7329,
      "step": 146
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0003554425044538868,
      "loss": 2.7188,
      "step": 148
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00034301408570516746,
      "loss": 2.7646,
      "step": 150
    }
  ],
  "max_steps": 246,
  "num_train_epochs": 3,
  "total_flos": 1.4229744023408476e+18,
  "trial_name": null,
  "trial_params": null
}