{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 3909,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.38,
      "learning_rate": 4.360450243028908e-05,
      "loss": 2.6273,
      "step": 500
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.7209004860578156e-05,
      "loss": 2.3755,
      "step": 1000
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.0813507290867236e-05,
      "loss": 2.1927,
      "step": 1500
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4418009721156306e-05,
      "loss": 1.9905,
      "step": 2000
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.8022512151445383e-05,
      "loss": 1.9672,
      "step": 2500
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.162701458173446e-05,
      "loss": 1.841,
      "step": 3000
    },
    {
      "epoch": 2.69,
      "learning_rate": 5.231517012023536e-06,
      "loss": 1.8011,
      "step": 3500
    },
    {
      "epoch": 3.0,
      "step": 3909,
      "total_flos": 2119732555677696.0,
      "train_loss": 2.077282390072389,
      "train_runtime": 3363.6598,
      "train_samples_per_second": 4.648,
      "train_steps_per_second": 1.162
    }
  ],
  "max_steps": 3909,
  "num_train_epochs": 3,
  "total_flos": 2119732555677696.0,
  "trial_name": null,
  "trial_params": null
}