trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.042549796558785206,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 3.1705,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9777399852193505e-05,
      "loss": 2.5041,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.955479970438701e-05,
      "loss": 2.3883,
      "step": 1500
    }
  ],
  "max_steps": 112809,
  "num_train_epochs": 3,
  "total_flos": 1672299203788800.0,
  "trial_name": null,
  "trial_params": null
}