{
  "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": 1.6892813444137573,
      "learning_rate": 0.0008,
      "loss": 3.1746,
      "step": 894
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 2.195862054824829,
      "eval_rouge1": 0.7078,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7098,
      "eval_rougeLsum": 0.7123,
      "eval_runtime": 53.0138,
      "eval_samples_per_second": 14.091,
      "eval_steps_per_second": 0.453,
      "step": 894
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.710464358329773,
      "learning_rate": 0.0006,
      "loss": 2.6338,
      "step": 1788
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.8010061979293823,
      "eval_rouge1": 0.6756,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6754,
      "eval_rougeLsum": 0.6777,
      "eval_runtime": 51.5674,
      "eval_samples_per_second": 14.486,
      "eval_steps_per_second": 0.465,
      "step": 1788
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.0555338859558105,
      "learning_rate": 0.0004,
      "loss": 2.3554,
      "step": 2682
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.635724425315857,
      "eval_rouge1": 0.6666,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6694,
      "eval_rougeLsum": 0.6707,
      "eval_runtime": 55.5539,
      "eval_samples_per_second": 13.446,
      "eval_steps_per_second": 0.432,
      "step": 2682
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.1167752742767334,
      "learning_rate": 0.0002,
      "loss": 2.1588,
      "step": 3576
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.5056090354919434,
      "eval_rouge1": 0.6936,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6944,
      "eval_rougeLsum": 0.6927,
      "eval_runtime": 54.4935,
      "eval_samples_per_second": 13.708,
      "eval_steps_per_second": 0.44,
      "step": 3576
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.513161301612854,
      "learning_rate": 0.0,
      "loss": 2.009,
      "step": 4470
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.4051402807235718,
      "eval_rouge1": 0.6787,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6817,
      "eval_rougeLsum": 0.6796,
      "eval_runtime": 53.7051,
      "eval_samples_per_second": 13.909,
      "eval_steps_per_second": 0.447,
      "step": 4470
    },
    {
      "epoch": 5.0,
      "step": 4470,
      "total_flos": 5.54115403874304e+16,
      "train_loss": 2.466313236245106,
      "train_runtime": 5712.4317,
      "train_samples_per_second": 12.508,
      "train_steps_per_second": 0.783
    }
  ],
  "logging_steps": 500,
  "max_steps": 4470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 5.54115403874304e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}