{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 4470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.405137300491333,
      "learning_rate": 0.0008,
      "loss": 1.21,
      "step": 894
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.757002055644989,
      "eval_rouge1": 0.6899,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6953,
      "eval_rougeLsum": 0.6878,
      "eval_runtime": 34.9973,
      "eval_samples_per_second": 21.345,
      "eval_steps_per_second": 0.686,
      "step": 894
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.47069525718688965,
      "learning_rate": 0.0006,
      "loss": 0.6826,
      "step": 1788
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6250166893005371,
      "eval_rouge1": 0.6779,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6777,
      "eval_rougeLsum": 0.6768,
      "eval_runtime": 36.3214,
      "eval_samples_per_second": 20.566,
      "eval_steps_per_second": 0.661,
      "step": 1788
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9726473093032837,
      "learning_rate": 0.0004,
      "loss": 0.4899,
      "step": 2682
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5914681553840637,
      "eval_rouge1": 0.6825,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.681,
      "eval_rougeLsum": 0.6837,
      "eval_runtime": 35.4381,
      "eval_samples_per_second": 21.079,
      "eval_steps_per_second": 0.677,
      "step": 2682
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.1989498138427734,
      "learning_rate": 0.0002,
      "loss": 0.3413,
      "step": 3576
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6194024085998535,
      "eval_rouge1": 0.7341,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7341,
      "eval_rougeLsum": 0.7373,
      "eval_runtime": 34.5389,
      "eval_samples_per_second": 21.628,
      "eval_steps_per_second": 0.695,
      "step": 3576
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5519212484359741,
      "learning_rate": 0.0,
      "loss": 0.2044,
      "step": 4470
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6972991824150085,
      "eval_rouge1": 0.6972,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6971,
      "eval_rougeLsum": 0.6984,
      "eval_runtime": 34.9342,
      "eval_samples_per_second": 21.383,
      "eval_steps_per_second": 0.687,
      "step": 4470
    },
    {
      "epoch": 5.0,
      "step": 4470,
      "total_flos": 4.89259128324096e+16,
      "train_loss": 0.5856431316742694,
      "train_runtime": 4335.6884,
      "train_samples_per_second": 16.48,
      "train_steps_per_second": 1.031
    }
  ],
  "logging_steps": 500,
  "max_steps": 4470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4.89259128324096e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}