{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 4685,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 2.67982924226254e-05,
      "loss": 2.2761,
      "step": 500
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.35965848452508e-05,
      "loss": 1.6473,
      "step": 1000
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.0394877267876203e-05,
      "loss": 1.5402,
      "step": 1500
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.7193169690501603e-05,
      "loss": 1.4675,
      "step": 2000
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.3991462113127e-05,
      "loss": 1.4086,
      "step": 2500
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.0789754535752402e-05,
      "loss": 1.3708,
      "step": 3000
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.588046958377802e-06,
      "loss": 1.3538,
      "step": 3500
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.386339381003202e-06,
      "loss": 1.2966,
      "step": 4000
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1846318036286021e-06,
      "loss": 1.2822,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "step": 4685,
      "total_flos": 1.1016793857503232e+16,
      "train_loss": 1.5054649426308615,
      "train_runtime": 2424.9282,
      "train_samples_per_second": 23.183,
      "train_steps_per_second": 1.932
    }
  ],
  "max_steps": 4685,
  "num_train_epochs": 1,
  "total_flos": 1.1016793857503232e+16,
  "trial_name": null,
  "trial_params": null
}