{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 4460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.6735097169876099,
      "learning_rate": 0.0008,
      "loss": 2.4406,
      "step": 892
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.2753673791885376,
      "eval_rouge1": 0.2408,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.2406,
      "eval_rougeLsum": 0.2405,
      "eval_runtime": 62.1479,
      "eval_samples_per_second": 12.052,
      "eval_steps_per_second": 0.386,
      "step": 892
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8161916732788086,
      "learning_rate": 0.0006,
      "loss": 1.5056,
      "step": 1784
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.9573599696159363,
      "eval_rouge1": 0.6755,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6719,
      "eval_rougeLsum": 0.6802,
      "eval_runtime": 60.0925,
      "eval_samples_per_second": 12.464,
      "eval_steps_per_second": 0.399,
      "step": 1784
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.8118889331817627,
      "learning_rate": 0.0004,
      "loss": 1.2114,
      "step": 2676
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.8394922614097595,
      "eval_rouge1": 0.6067,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6104,
      "eval_rougeLsum": 0.6102,
      "eval_runtime": 62.8412,
      "eval_samples_per_second": 11.919,
      "eval_steps_per_second": 0.382,
      "step": 2676
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.8188594579696655,
      "learning_rate": 0.0002,
      "loss": 1.0429,
      "step": 3568
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.7446844577789307,
      "eval_rouge1": 0.5115,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.5127,
      "eval_rougeLsum": 0.5115,
      "eval_runtime": 61.2936,
      "eval_samples_per_second": 12.22,
      "eval_steps_per_second": 0.392,
      "step": 3568
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.214055299758911,
      "learning_rate": 0.0,
      "loss": 0.9364,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.7108550071716309,
      "eval_rouge1": 0.5511,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.5526,
      "eval_rougeLsum": 0.548,
      "eval_runtime": 59.8075,
      "eval_samples_per_second": 12.524,
      "eval_steps_per_second": 0.401,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "step": 4460,
      "total_flos": 5.591485582092288e+16,
      "train_loss": 1.4273549580253293,
      "train_runtime": 6393.8404,
      "train_samples_per_second": 11.154,
      "train_steps_per_second": 0.698
    }
  ],
  "logging_steps": 500,
  "max_steps": 4460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 5.591485582092288e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}