{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2742857142857143,
  "global_step": 480,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.7468,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.4221,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 3.2415,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 3.087,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 3.0862,
      "step": 150
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.8754,
      "step": 180
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.8564,
      "step": 210
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.7123,
      "step": 240
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.605,
      "step": 270
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.6557,
      "step": 300
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 2.5594,
      "step": 330
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 2.4986,
      "step": 360
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.4444,
      "step": 390
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.356,
      "step": 420
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.4237,
      "step": 450
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.2358,
      "step": 480
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 1,
  "total_flos": 8.124998979944448e+16,
  "trial_name": null,
  "trial_params": null
}