{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.1,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 4e-05,
      "loss": 1.6708,
      "step": 1
    },
    {
      "epoch": 1.1,
      "learning_rate": 8e-05,
      "loss": 1.6708,
      "step": 2
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00012,
      "loss": 1.638,
      "step": 3
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.00016,
      "loss": 1.571,
      "step": 4
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.0002,
      "loss": 1.4647,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1093244289024000.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}