{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 9820,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 4.9693251533742335e-05,
      "loss": 20966.374,
      "step": 500
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.918200408997955e-05,
      "loss": 2277.2115,
      "step": 1000
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.867075664621677e-05,
      "loss": 549.5879,
      "step": 1500
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.815950920245399e-05,
      "loss": 283.1544,
      "step": 2000
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.764826175869121e-05,
      "loss": 184.1967,
      "step": 2500
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.7137014314928426e-05,
      "loss": 137.0529,
      "step": 3000
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.6625766871165645e-05,
      "loss": 114.6247,
      "step": 3500
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.611451942740286e-05,
      "loss": 102.8662,
      "step": 4000
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.560327198364008e-05,
      "loss": 97.2861,
      "step": 4500
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.5092024539877307e-05,
      "loss": 87.1393,
      "step": 5000
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.4580777096114525e-05,
      "loss": 73.0929,
      "step": 5500
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.4069529652351736e-05,
      "loss": 70.3143,
      "step": 6000
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.3558282208588955e-05,
      "loss": 67.2985,
      "step": 6500
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.304703476482618e-05,
      "loss": 69.378,
      "step": 7000
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.25357873210634e-05,
      "loss": 64.2011,
      "step": 7500
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.2024539877300617e-05,
      "loss": 63.1896,
      "step": 8000
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.1513292433537835e-05,
      "loss": 63.1367,
      "step": 8500
    },
    {
      "epoch": 1.83,
      "learning_rate": 4.100204498977505e-05,
      "loss": 60.7672,
      "step": 9000
    },
    {
      "epoch": 1.93,
      "learning_rate": 4.049079754601227e-05,
      "loss": 61.0841,
      "step": 9500
    }
  ],
  "max_steps": 49100,
  "num_train_epochs": 10,
  "total_flos": 9.13949176598519e+16,
  "trial_name": null,
  "trial_params": null
}