trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "global_step": 54,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8819742202758789,
      "eval_f1": 0.905982905982906,
      "eval_loss": 0.31945469975471497,
      "eval_runtime": 9.1195,
      "eval_samples_per_second": 51.099,
      "step": 9
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9098712205886841,
      "eval_f1": 0.9285714285714286,
      "eval_loss": 0.307280570268631,
      "eval_runtime": 9.1577,
      "eval_samples_per_second": 50.886,
      "step": 18
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9291845560073853,
      "eval_f1": 0.9417989417989417,
      "eval_loss": 0.2344941943883896,
      "eval_runtime": 9.2002,
      "eval_samples_per_second": 50.651,
      "step": 27
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9442059993743896,
      "eval_f1": 0.9553264604810997,
      "eval_loss": 0.21704576909542084,
      "eval_runtime": 9.3218,
      "eval_samples_per_second": 49.991,
      "step": 36
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9613733887672424,
      "eval_f1": 0.9681978798586572,
      "eval_loss": 0.16624483466148376,
      "eval_runtime": 9.2765,
      "eval_samples_per_second": 50.234,
      "step": 45
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9635193347930908,
      "eval_f1": 0.9699115044247788,
      "eval_loss": 0.1768765151500702,
      "eval_runtime": 9.2004,
      "eval_samples_per_second": 50.65,
      "step": 54
    }
  ],
  "max_steps": 81,
  "num_train_epochs": 9,
  "total_flos": 25406631484416.0,
  "trial_name": null,
  "trial_params": null
}