{
  "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": 0.6636476516723633,
      "learning_rate": 0.0008,
      "loss": 3.0315,
      "step": 892
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.9886474609375,
      "eval_rouge1": 0.6709,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6725,
      "eval_rougeLsum": 0.6735,
      "eval_runtime": 52.6707,
      "eval_samples_per_second": 14.239,
      "eval_steps_per_second": 0.456,
      "step": 892
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7732788324356079,
      "learning_rate": 0.0006,
      "loss": 2.3884,
      "step": 1784
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.7005009651184082,
      "eval_rouge1": 0.6607,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6602,
      "eval_rougeLsum": 0.6605,
      "eval_runtime": 53.2179,
      "eval_samples_per_second": 14.093,
      "eval_steps_per_second": 0.451,
      "step": 1784
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6329182386398315,
      "learning_rate": 0.0004,
      "loss": 2.1281,
      "step": 2676
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.5320008993148804,
      "eval_rouge1": 0.6654,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6668,
      "eval_rougeLsum": 0.6641,
      "eval_runtime": 50.9101,
      "eval_samples_per_second": 14.732,
      "eval_steps_per_second": 0.471,
      "step": 2676
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6751648187637329,
      "learning_rate": 0.0002,
      "loss": 1.9407,
      "step": 3568
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.3940863609313965,
      "eval_rouge1": 0.6373,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6357,
      "eval_rougeLsum": 0.6361,
      "eval_runtime": 51.9967,
      "eval_samples_per_second": 14.424,
      "eval_steps_per_second": 0.462,
      "step": 3568
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7165943384170532,
      "learning_rate": 0.0,
      "loss": 1.7957,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.3072751760482788,
      "eval_rouge1": 0.6591,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6548,
      "eval_rougeLsum": 0.6576,
      "eval_runtime": 53.0918,
      "eval_samples_per_second": 14.126,
      "eval_steps_per_second": 0.452,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "step": 4460,
      "total_flos": 5.534174278582272e+16,
      "train_loss": 2.25687800522877,
      "train_runtime": 5700.4224,
      "train_samples_per_second": 12.518,
      "train_steps_per_second": 0.782
    }
  ],
  "logging_steps": 500,
  "max_steps": 4460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 5.534174278582272e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}