trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 19.0,
      "eval_loss": 2.3647923469543457,
      "eval_rouge1": 0.1656,
      "eval_rouge2": 0.0725,
      "eval_rougeL": 0.1381,
      "eval_rougeLsum": 0.1379,
      "eval_runtime": 7.2312,
      "eval_samples_per_second": 34.296,
      "eval_steps_per_second": 2.213,
      "step": 62
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 19.0,
      "eval_loss": 2.3301684856414795,
      "eval_rouge1": 0.1892,
      "eval_rouge2": 0.0914,
      "eval_rougeL": 0.159,
      "eval_rougeLsum": 0.159,
      "eval_runtime": 7.2363,
      "eval_samples_per_second": 34.272,
      "eval_steps_per_second": 2.211,
      "step": 124
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 19.0,
      "eval_loss": 2.3109350204467773,
      "eval_rouge1": 0.1948,
      "eval_rouge2": 0.099,
      "eval_rougeL": 0.1645,
      "eval_rougeLsum": 0.1647,
      "eval_runtime": 7.2534,
      "eval_samples_per_second": 34.191,
      "eval_steps_per_second": 2.206,
      "step": 186
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 19.0,
      "eval_loss": 2.304762125015259,
      "eval_rouge1": 0.1948,
      "eval_rouge2": 0.099,
      "eval_rougeL": 0.165,
      "eval_rougeLsum": 0.1652,
      "eval_runtime": 7.2516,
      "eval_samples_per_second": 34.199,
      "eval_steps_per_second": 2.206,
      "step": 248
    }
  ],
  "max_steps": 248,
  "num_train_epochs": 4,
  "total_flos": 1070824333246464.0,
  "trial_name": null,
  "trial_params": null
}