{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 202,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 0.27145588397979736,
      "learning_rate": 0.00019876883405951377,
      "loss": 1.4266,
      "step": 50
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.269089013338089,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.8104,
      "step": 100
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.296158105134964,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.7768,
      "step": 150
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.3121841847896576,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7581,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4220501926677504.0,
  "train_batch_size": 7,
  "trial_name": null,
  "trial_params": null
}