trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 1150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.17,
      "learning_rate": 2e-05,
      "loss": 0.4803,
      "step": 500
    },
    {
      "epoch": 2.17,
      "eval_accuracy": 0.8872549019607843,
      "eval_combined_score": 0.9028473091364206,
      "eval_f1": 0.9184397163120569,
      "eval_loss": 0.34769126772880554,
      "eval_runtime": 2.2258,
      "eval_samples_per_second": 183.303,
      "eval_steps_per_second": 22.913,
      "step": 500
    },
    {
      "epoch": 4.35,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.164,
      "step": 1000
    },
    {
      "epoch": 4.35,
      "eval_accuracy": 0.8995098039215687,
      "eval_combined_score": 0.9138529755159507,
      "eval_f1": 0.9281961471103327,
      "eval_loss": 0.5612154006958008,
      "eval_runtime": 2.2216,
      "eval_samples_per_second": 183.653,
      "eval_steps_per_second": 22.957,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "step": 1150,
      "total_flos": 2412771647139840.0,
      "train_loss": 0.2895339061902917,
      "train_runtime": 312.3775,
      "train_samples_per_second": 58.711,
      "train_steps_per_second": 3.681
    }
  ],
  "max_steps": 1150,
  "num_train_epochs": 5,
  "total_flos": 2412771647139840.0,
  "trial_name": null,
  "trial_params": null
}