{
  "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": 1.5868409872055054,
      "learning_rate": 0.0008,
      "loss": 0.7823,
      "step": 894
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5091907978057861,
      "eval_rouge1": 0.6551,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6537,
      "eval_rougeLsum": 0.6535,
      "eval_runtime": 38.6735,
      "eval_samples_per_second": 19.316,
      "eval_steps_per_second": 0.621,
      "step": 894
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5867279171943665,
      "learning_rate": 0.0006,
      "loss": 0.6005,
      "step": 1788
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.47693932056427,
      "eval_rouge1": 0.6706,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6693,
      "eval_rougeLsum": 0.6688,
      "eval_runtime": 38.2912,
      "eval_samples_per_second": 19.508,
      "eval_steps_per_second": 0.627,
      "step": 1788
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6152400970458984,
      "learning_rate": 0.0004,
      "loss": 0.5564,
      "step": 2682
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.4768148362636566,
      "eval_rouge1": 0.6725,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6709,
      "eval_rougeLsum": 0.6731,
      "eval_runtime": 38.223,
      "eval_samples_per_second": 19.543,
      "eval_steps_per_second": 0.628,
      "step": 2682
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3360026776790619,
      "learning_rate": 0.0002,
      "loss": 0.5269,
      "step": 3576
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.4666813910007477,
      "eval_rouge1": 0.6722,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6726,
      "eval_rougeLsum": 0.6742,
      "eval_runtime": 37.865,
      "eval_samples_per_second": 19.728,
      "eval_steps_per_second": 0.634,
      "step": 3576
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6582946181297302,
      "learning_rate": 0.0,
      "loss": 0.5061,
      "step": 4470
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.4682966470718384,
      "eval_rouge1": 0.6725,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6711,
      "eval_rougeLsum": 0.6719,
      "eval_runtime": 38.3475,
      "eval_samples_per_second": 19.48,
      "eval_steps_per_second": 0.626,
      "step": 4470
    },
    {
      "epoch": 5.0,
      "step": 4470,
      "total_flos": 4.93143020273664e+16,
      "train_loss": 0.5944349318809424,
      "train_runtime": 3932.2853,
      "train_samples_per_second": 18.17,
      "train_steps_per_second": 1.137
    }
  ],
  "logging_steps": 500,
  "max_steps": 4470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4.93143020273664e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}