{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 91,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.8496,
      "step": 2
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.9673,
      "step": 4
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.8491,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.9002,
      "step": 8
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.873,
      "step": 10
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.9039,
      "step": 12
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.8956,
      "step": 14
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001966942148760331,
      "loss": 1.8618,
      "step": 16
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001933884297520661,
      "loss": 1.7929,
      "step": 18
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001900826446280992,
      "loss": 1.852,
      "step": 20
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00018677685950413224,
      "loss": 1.8218,
      "step": 22
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018347107438016532,
      "loss": 1.8421,
      "step": 24
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018016528925619835,
      "loss": 1.7531,
      "step": 26
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00017685950413223143,
      "loss": 1.7133,
      "step": 28
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00017520661157024794,
      "loss": 2.2706,
      "step": 30
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017190082644628102,
      "loss": 1.7739,
      "step": 32
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00016859504132231404,
      "loss": 1.7082,
      "step": 34
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00016528925619834712,
      "loss": 1.7831,
      "step": 36
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016198347107438017,
      "loss": 1.778,
      "step": 38
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00015867768595041322,
      "loss": 1.7482,
      "step": 40
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00015537190082644627,
      "loss": 1.8466,
      "step": 42
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015206611570247935,
      "loss": 1.7918,
      "step": 44
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001487603305785124,
      "loss": 1.7058,
      "step": 46
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.7294,
      "step": 48
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001421487603305785,
      "loss": 1.7285,
      "step": 50
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001388429752066116,
      "loss": 1.6392,
      "step": 52
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013553719008264464,
      "loss": 1.712,
      "step": 54
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001322314049586777,
      "loss": 1.6992,
      "step": 56
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012892561983471074,
      "loss": 1.7677,
      "step": 58
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012561983471074382,
      "loss": 1.7096,
      "step": 60
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00012231404958677685,
      "loss": 1.7602,
      "step": 62
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011900826446280992,
      "loss": 1.7128,
      "step": 64
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00011570247933884298,
      "loss": 1.6605,
      "step": 66
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00011239669421487604,
      "loss": 1.6559,
      "step": 68
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00010909090909090909,
      "loss": 1.6775,
      "step": 70
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00010578512396694216,
      "loss": 1.8318,
      "step": 72
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00010247933884297521,
      "loss": 1.7568,
      "step": 74
    },
    {
      "epoch": 1.67,
      "learning_rate": 9.917355371900827e-05,
      "loss": 1.7349,
      "step": 76
    },
    {
      "epoch": 1.71,
      "learning_rate": 9.586776859504133e-05,
      "loss": 1.7956,
      "step": 78
    },
    {
      "epoch": 1.76,
      "learning_rate": 9.256198347107439e-05,
      "loss": 1.684,
      "step": 80
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.925619834710744e-05,
      "loss": 1.6579,
      "step": 82
    },
    {
      "epoch": 1.85,
      "learning_rate": 8.595041322314051e-05,
      "loss": 1.7188,
      "step": 84
    },
    {
      "epoch": 1.89,
      "learning_rate": 8.264462809917356e-05,
      "loss": 1.6533,
      "step": 86
    },
    {
      "epoch": 1.93,
      "learning_rate": 8.099173553719009e-05,
      "loss": 1.9246,
      "step": 88
    },
    {
      "epoch": 1.98,
      "learning_rate": 7.768595041322314e-05,
      "loss": 1.7969,
      "step": 90
    }
  ],
  "logging_steps": 2,
  "max_steps": 135,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 5.946469637318246e+16,
  "trial_name": null,
  "trial_params": null
}