{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9305019305019306,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.58,
      "learning_rate": 7.239382239382239e-07,
      "loss": 2.3335,
      "step": 300
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.4478764478764478e-06,
      "loss": 2.322,
      "step": 600
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.171814671814672e-06,
      "loss": 2.268,
      "step": 900
    },
    {
      "epoch": 1.93,
      "eval_loss": 2.2363617420196533,
      "eval_runtime": 56.2328,
      "eval_samples_per_second": 51.98,
      "eval_steps_per_second": 3.254,
      "step": 1000
    }
  ],
  "logging_steps": 300,
  "max_steps": 8288,
  "num_train_epochs": 16,
  "save_steps": 1000,
  "total_flos": 8.662384740099686e+16,
  "trial_name": null,
  "trial_params": null
}