trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1143,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.44,
      "learning_rate": 0.0005625546806649168,
      "loss": 1.8855,
      "step": 500
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00012510936132983377,
      "loss": 1.7649,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "step": 1143,
      "total_flos": 4.649509810297897e+17,
      "train_loss": 1.8161194168050772,
      "train_runtime": 6916.1714,
      "train_samples_per_second": 10.577,
      "train_steps_per_second": 0.165
    }
  ],
  "logging_steps": 500,
  "max_steps": 1143,
  "num_train_epochs": 1,
  "save_steps": -1143,
  "total_flos": 4.649509810297897e+17,
  "trial_name": null,
  "trial_params": null
}