{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.999774453048643,
  "eval_steps": 500,
  "global_step": 9975,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 9.49874686716792e-05,
      "loss": 2.1878,
      "step": 500
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.99749373433584e-05,
      "loss": 1.5576,
      "step": 1000
    },
    {
      "epoch": 0.45,
      "learning_rate": 8.49624060150376e-05,
      "loss": 1.4644,
      "step": 1500
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.994987468671679e-05,
      "loss": 1.4131,
      "step": 2000
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.4937343358396e-05,
      "loss": 1.3789,
      "step": 2500
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.99248120300752e-05,
      "loss": 1.3443,
      "step": 3000
    },
    {
      "epoch": 1.05,
      "learning_rate": 6.49122807017544e-05,
      "loss": 1.3263,
      "step": 3500
    },
    {
      "epoch": 1.2,
      "learning_rate": 5.989974937343359e-05,
      "loss": 1.2983,
      "step": 4000
    },
    {
      "epoch": 1.35,
      "learning_rate": 5.4887218045112786e-05,
      "loss": 1.2849,
      "step": 4500
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.987468671679198e-05,
      "loss": 1.2644,
      "step": 5000
    },
    {
      "epoch": 1.65,
      "learning_rate": 4.486215538847118e-05,
      "loss": 1.2527,
      "step": 5500
    },
    {
      "epoch": 1.8,
      "learning_rate": 3.9849624060150376e-05,
      "loss": 1.241,
      "step": 6000
    },
    {
      "epoch": 1.95,
      "learning_rate": 3.483709273182957e-05,
      "loss": 1.2278,
      "step": 6500
    },
    {
      "epoch": 2.11,
      "learning_rate": 2.9824561403508772e-05,
      "loss": 1.2116,
      "step": 7000
    },
    {
      "epoch": 2.26,
      "learning_rate": 2.4812030075187968e-05,
      "loss": 1.1994,
      "step": 7500
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.9799498746867168e-05,
      "loss": 1.1933,
      "step": 8000
    },
    {
      "epoch": 2.56,
      "learning_rate": 1.4786967418546366e-05,
      "loss": 1.1796,
      "step": 8500
    },
    {
      "epoch": 2.71,
      "learning_rate": 9.774436090225564e-06,
      "loss": 1.1787,
      "step": 9000
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 1.1672,
      "step": 9500
    },
    {
      "epoch": 3.0,
      "step": 9975,
      "total_flos": 1.6801282333309133e+17,
      "train_loss": 1.327384843945802,
      "train_runtime": 12602.7945,
      "train_samples_per_second": 50.659,
      "train_steps_per_second": 0.791
    }
  ],
  "logging_steps": 500,
  "max_steps": 9975,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.6801282333309133e+17,
  "trial_name": null,
  "trial_params": null
}