{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 8433,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 4.7035455946875374e-05,
      "loss": 2.3765,
      "step": 500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.4070911893750746e-05,
      "loss": 2.0326,
      "step": 1000
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.110636784062611e-05,
      "loss": 1.9006,
      "step": 1500
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.8141823787501484e-05,
      "loss": 1.8182,
      "step": 2000
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.5177279734376856e-05,
      "loss": 1.763,
      "step": 2500
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.221273568125223e-05,
      "loss": 1.7162,
      "step": 3000
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.9248191628127597e-05,
      "loss": 1.6754,
      "step": 3500
    },
    {
      "epoch": 1.42,
      "learning_rate": 2.628364757500297e-05,
      "loss": 1.6466,
      "step": 4000
    },
    {
      "epoch": 1.6,
      "learning_rate": 2.3319103521878334e-05,
      "loss": 1.6309,
      "step": 4500
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.0354559468753706e-05,
      "loss": 1.5998,
      "step": 5000
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.7390015415629078e-05,
      "loss": 1.5846,
      "step": 5500
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.4425471362504448e-05,
      "loss": 1.5677,
      "step": 6000
    },
    {
      "epoch": 2.31,
      "learning_rate": 1.1460927309379819e-05,
      "loss": 1.5562,
      "step": 6500
    },
    {
      "epoch": 2.49,
      "learning_rate": 8.496383256255189e-06,
      "loss": 1.5459,
      "step": 7000
    },
    {
      "epoch": 2.67,
      "learning_rate": 5.531839203130558e-06,
      "loss": 1.5372,
      "step": 7500
    },
    {
      "epoch": 2.85,
      "learning_rate": 2.567295150005929e-06,
      "loss": 1.5282,
      "step": 8000
    },
    {
      "epoch": 3.0,
      "step": 8433,
      "total_flos": 1.7760941215801344e+16,
      "train_loss": 1.7074700184427065,
      "train_runtime": 2192.338,
      "train_samples_per_second": 246.133,
      "train_steps_per_second": 3.847
    }
  ],
  "max_steps": 8433,
  "num_train_epochs": 3,
  "total_flos": 1.7760941215801344e+16,
  "trial_name": null,
  "trial_params": null
}