{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9923224568138194,
  "eval_steps": 500,
  "global_step": 1560,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1": 0.9034,
      "eval_gen_len": 26.296727272727274,
      "eval_loss": 1.8257849216461182,
      "eval_precision": 0.9049,
      "eval_recall": 0.9023,
      "eval_rouge1": 0.4338,
      "eval_rouge2": 0.1906,
      "eval_rougeL": 0.3496,
      "eval_rougeLsum": 0.3498,
      "eval_runtime": 513.5292,
      "eval_samples_per_second": 5.355,
      "eval_steps_per_second": 0.335,
      "step": 390
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.3589743589743592e-05,
      "loss": 2.1621,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.9054,
      "eval_gen_len": 26.272727272727273,
      "eval_loss": 1.7537195682525635,
      "eval_precision": 0.9068,
      "eval_recall": 0.9044,
      "eval_rouge1": 0.4449,
      "eval_rouge2": 0.2005,
      "eval_rougeL": 0.3633,
      "eval_rougeLsum": 0.3633,
      "eval_runtime": 505.2109,
      "eval_samples_per_second": 5.443,
      "eval_steps_per_second": 0.34,
      "step": 781
    },
    {
      "epoch": 2.56,
      "learning_rate": 7.17948717948718e-06,
      "loss": 1.8794,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.9066,
      "eval_gen_len": 26.434545454545454,
      "eval_loss": 1.726783275604248,
      "eval_precision": 0.9078,
      "eval_recall": 0.9058,
      "eval_rouge1": 0.4518,
      "eval_rouge2": 0.2061,
      "eval_rougeL": 0.3696,
      "eval_rougeLsum": 0.3695,
      "eval_runtime": 507.6007,
      "eval_samples_per_second": 5.418,
      "eval_steps_per_second": 0.339,
      "step": 1172
    },
    {
      "epoch": 3.84,
      "learning_rate": 7.692307692307694e-07,
      "loss": 1.8271,
      "step": 1500
    },
    {
      "epoch": 3.99,
      "eval_f1": 0.907,
      "eval_gen_len": 26.45309090909091,
      "eval_loss": 1.7193447351455688,
      "eval_precision": 0.9082,
      "eval_recall": 0.9061,
      "eval_rouge1": 0.4541,
      "eval_rouge2": 0.2071,
      "eval_rougeL": 0.3708,
      "eval_rougeLsum": 0.3708,
      "eval_runtime": 503.2966,
      "eval_samples_per_second": 5.464,
      "eval_steps_per_second": 0.342,
      "step": 1560
    },
    {
      "epoch": 3.99,
      "step": 1560,
      "total_flos": 2.884147799685857e+17,
      "train_loss": 1.950797971089681,
      "train_runtime": 8703.8597,
      "train_samples_per_second": 22.978,
      "train_steps_per_second": 0.179
    }
  ],
  "logging_steps": 500,
  "max_steps": 1560,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 2.884147799685857e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}