trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.3033,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.518870234489441,
      "eval_runtime": 9.6429,
      "eval_samples_per_second": 10.474,
      "eval_steps_per_second": 1.348,
      "step": 1
    },
    {
      "epoch": 1.0,
      "step": 1,
      "total_flos": 2285025504337920.0,
      "train_loss": 0.30327314138412476,
      "train_runtime": 39.3282,
      "train_samples_per_second": 2.568,
      "train_steps_per_second": 0.025
    }
  ],
  "logging_steps": 5,
  "max_steps": 1,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 2285025504337920.0,
  "trial_name": null,
  "trial_params": null
}