{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 5155,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 4.8383446492078885e-05,
      "loss": 1.1648,
      "step": 500
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.6766892984157775e-05,
      "loss": 0.9035,
      "step": 1000
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5150339476236665e-05,
      "loss": 0.8586,
      "step": 1500
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.3533785968315555e-05,
      "loss": 0.7936,
      "step": 2000
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.191723246039444e-05,
      "loss": 0.6652,
      "step": 2500
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.030067895247333e-05,
      "loss": 0.709,
      "step": 3000
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.868412544455222e-05,
      "loss": 0.6842,
      "step": 3500
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.706757193663111e-05,
      "loss": 0.6578,
      "step": 4000
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.545101842870999e-05,
      "loss": 0.5872,
      "step": 4500
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.383446492078888e-05,
      "loss": 0.6085,
      "step": 5000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.014681339263916,
      "eval_runtime": 2.9407,
      "eval_samples_per_second": 702.22,
      "eval_steps_per_second": 88.075,
      "step": 5155
    }
  ],
  "max_steps": 15465,
  "num_train_epochs": 3,
  "total_flos": 396590020549200.0,
  "trial_name": null,
  "trial_params": null
}