{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.998453448809156,
  "eval_steps": 500,
  "global_step": 8080,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 0.02,
      "step": 500
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.9469375006178444e-05,
      "loss": 0.0364,
      "step": 1000
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.789170365674227e-05,
      "loss": 0.0359,
      "step": 1500
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.533448658971904e-05,
      "loss": 0.0306,
      "step": 2000
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.1914779409602436e-05,
      "loss": 0.0274,
      "step": 2500
    },
    {
      "epoch": 1.86,
      "learning_rate": 3.776525578007916e-05,
      "loss": 0.0264,
      "step": 3000
    },
    {
      "epoch": 2.17,
      "learning_rate": 3.3069501436547976e-05,
      "loss": 0.024,
      "step": 3500
    },
    {
      "epoch": 2.47,
      "learning_rate": 2.802844970083667e-05,
      "loss": 0.0175,
      "step": 4000
    },
    {
      "epoch": 2.78,
      "learning_rate": 2.2868132844916794e-05,
      "loss": 0.0185,
      "step": 4500
    },
    {
      "epoch": 3.09,
      "learning_rate": 1.77887546017395e-05,
      "loss": 0.0148,
      "step": 5000
    },
    {
      "epoch": 3.4,
      "learning_rate": 1.3017948610512293e-05,
      "loss": 0.01,
      "step": 5500
    },
    {
      "epoch": 3.71,
      "learning_rate": 8.76773859580714e-06,
      "loss": 0.0088,
      "step": 6000
    },
    {
      "epoch": 4.02,
      "learning_rate": 5.203019065951417e-06,
      "loss": 0.009,
      "step": 6500
    },
    {
      "epoch": 4.33,
      "learning_rate": 2.4854207545895515e-06,
      "loss": 0.0063,
      "step": 7000
    },
    {
      "epoch": 4.64,
      "learning_rate": 7.312308471548624e-07,
      "loss": 0.0078,
      "step": 7500
    },
    {
      "epoch": 4.95,
      "learning_rate": 1.587896786990062e-08,
      "loss": 0.0073,
      "step": 8000
    }
  ],
  "logging_steps": 500,
  "max_steps": 8080,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6.849571262744986e+16,
  "trial_name": null,
  "trial_params": null
}