trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.189944134078212,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_bleu": 0.1373172423659855,
      "eval_brevity_penalty": 0.863178178199581,
      "eval_length_ratio": 0.8717376288914105,
      "eval_loss": 1.3936889171600342,
      "eval_precisions": [
        0.4792318104428126,
        0.20573488994401803,
        0.10659255262806203,
        0.06094218676248915
      ],
      "eval_reference_length": 486456,
      "eval_rouge1": 0.44042550876447684,
      "eval_rouge2": 0.1938260053598076,
      "eval_rougeL": 0.34271151603512445,
      "eval_rougeLsum": 0.3426928685202588,
      "eval_runtime": 386.2238,
      "eval_samples_per_second": 25.892,
      "eval_steps_per_second": 0.117,
      "eval_translation_length": 424062,
      "step": 358
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.13664308592332633,
      "eval_brevity_penalty": 0.865916223478426,
      "eval_length_ratio": 0.874151002351703,
      "eval_loss": 1.3927369117736816,
      "eval_precisions": [
        0.477490146647979,
        0.2043055033763932,
        0.10560019346751029,
        0.06019188535457296
      ],
      "eval_reference_length": 486456,
      "eval_rouge1": 0.43955648572275374,
      "eval_rouge2": 0.1927397664063572,
      "eval_rougeL": 0.3418946993055956,
      "eval_rougeLsum": 0.3417954159461587,
      "eval_runtime": 386.3881,
      "eval_samples_per_second": 25.881,
      "eval_steps_per_second": 0.116,
      "eval_translation_length": 425236,
      "step": 716
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.13664308592332633,
      "eval_brevity_penalty": 0.865916223478426,
      "eval_length_ratio": 0.874151002351703,
      "eval_loss": 1.3927369117736816,
      "eval_precisions": [
        0.477490146647979,
        0.2043055033763932,
        0.10560019346751029,
        0.06019188535457296
      ],
      "eval_reference_length": 486456,
      "eval_rouge1": 0.43955648572275374,
      "eval_rouge2": 0.1927397664063572,
      "eval_rougeL": 0.3418946993055956,
      "eval_rougeLsum": 0.3417954159461587,
      "eval_runtime": 386.4105,
      "eval_samples_per_second": 25.879,
      "eval_steps_per_second": 0.116,
      "eval_translation_length": 425236,
      "step": 1074
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.13664308592332633,
      "eval_brevity_penalty": 0.865916223478426,
      "eval_length_ratio": 0.874151002351703,
      "eval_loss": 1.3927369117736816,
      "eval_precisions": [
        0.477490146647979,
        0.2043055033763932,
        0.10560019346751029,
        0.06019188535457296
      ],
      "eval_reference_length": 486456,
      "eval_rouge1": 0.43955648572275374,
      "eval_rouge2": 0.1927397664063572,
      "eval_rougeL": 0.3418946993055956,
      "eval_rougeLsum": 0.3417954159461587,
      "eval_runtime": 386.7983,
      "eval_samples_per_second": 25.853,
      "eval_steps_per_second": 0.116,
      "eval_translation_length": 425236,
      "step": 1432
    }
  ],
  "max_steps": 1790,
  "num_train_epochs": 5,
  "total_flos": 2.0414217156820992e+17,
  "trial_name": null,
  "trial_params": null
}