{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002828094288663584,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 3.198284149169922,
      "learning_rate": 0.0002,
      "loss": 5.5114,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.7400519847869873,
      "learning_rate": 0.00015000000000000001,
      "loss": 5.9469,
      "step": 2
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.8131814002990723,
      "learning_rate": 0.0001,
      "loss": 4.776,
      "step": 3
    },
    {
      "epoch": 0.0,
      "grad_norm": 4.289147853851318,
      "learning_rate": 5e-05,
      "loss": 4.4021,
      "step": 4
    },
    {
      "epoch": 0.0,
      "grad_norm": 4.208286762237549,
      "learning_rate": 0.0,
      "loss": 3.9358,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 22372723003392.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}