{
  "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": 0.6732619404792786,
      "learning_rate": 0.0008,
      "loss": 0.7757,
      "step": 892
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5546033978462219,
      "eval_rouge1": 0.6666,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6657,
      "eval_rougeLsum": 0.6687,
      "eval_runtime": 36.0614,
      "eval_samples_per_second": 20.798,
      "eval_steps_per_second": 0.666,
      "step": 892
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6083085536956787,
      "learning_rate": 0.0006,
      "loss": 0.6033,
      "step": 1784
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5361196398735046,
      "eval_rouge1": 0.6576,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6553,
      "eval_rougeLsum": 0.6594,
      "eval_runtime": 36.1132,
      "eval_samples_per_second": 20.768,
      "eval_steps_per_second": 0.665,
      "step": 1784
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7207215428352356,
      "learning_rate": 0.0004,
      "loss": 0.5534,
      "step": 2676
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5343378782272339,
      "eval_rouge1": 0.6895,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6885,
      "eval_rougeLsum": 0.6892,
      "eval_runtime": 36.2134,
      "eval_samples_per_second": 20.711,
      "eval_steps_per_second": 0.663,
      "step": 2676
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5183739066123962,
      "learning_rate": 0.0002,
      "loss": 0.5156,
      "step": 3568
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5145081281661987,
      "eval_rouge1": 0.6609,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6612,
      "eval_rougeLsum": 0.6631,
      "eval_runtime": 36.0417,
      "eval_samples_per_second": 20.809,
      "eval_steps_per_second": 0.666,
      "step": 3568
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5874832272529602,
      "learning_rate": 0.0,
      "loss": 0.4866,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5112622380256653,
      "eval_rouge1": 0.663,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6623,
      "eval_rougeLsum": 0.6589,
      "eval_runtime": 35.8754,
      "eval_samples_per_second": 20.906,
      "eval_steps_per_second": 0.669,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "step": 4460,
      "total_flos": 4.92564778057728e+16,
      "train_loss": 0.5869357532449901,
      "train_runtime": 3727.03,
      "train_samples_per_second": 19.147,
      "train_steps_per_second": 1.197
    }
  ],
  "logging_steps": 500,
  "max_steps": 4460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4.92564778057728e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}