trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 193,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.999867521457224e-05,
      "loss": 1.1405,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9541811347007751,
      "eval_runtime": 86.189,
      "eval_samples_per_second": 179.037,
      "eval_steps_per_second": 0.36,
      "step": 193
    },
    {
      "epoch": 1.0,
      "step": 193,
      "total_flos": 323282188369920.0,
      "train_loss": 1.006550097712581,
      "train_runtime": 2174.1063,
      "train_samples_per_second": 45.285,
      "train_steps_per_second": 0.089
    }
  ],
  "logging_steps": 500,
  "max_steps": 193,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 323282188369920.0,
  "trial_name": null,
  "trial_params": null
}