trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 235,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5727023482322693,
      "eval_runtime": 1.0164,
      "eval_samples_per_second": 106.257,
      "eval_steps_per_second": 6.887,
      "step": 47
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7962962962962963,
      "eval_loss": 0.5028897523880005,
      "eval_runtime": 1.0142,
      "eval_samples_per_second": 106.487,
      "eval_steps_per_second": 6.902,
      "step": 94
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8240740740740741,
      "eval_loss": 0.7567664980888367,
      "eval_runtime": 1.019,
      "eval_samples_per_second": 105.991,
      "eval_steps_per_second": 6.87,
      "step": 141
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8148148148148148,
      "eval_loss": 0.8691176176071167,
      "eval_runtime": 1.0115,
      "eval_samples_per_second": 106.777,
      "eval_steps_per_second": 6.921,
      "step": 188
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8148148148148148,
      "eval_loss": 0.9419552683830261,
      "eval_runtime": 1.0218,
      "eval_samples_per_second": 105.692,
      "eval_steps_per_second": 6.85,
      "step": 235
    }
  ],
  "max_steps": 235,
  "num_train_epochs": 5,
  "total_flos": 986666457600000.0,
  "trial_name": null,
  "trial_params": null
}