{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 4182,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3586800573888092,
      "grad_norm": 8.820939064025879,
      "learning_rate": 1.760879961740794e-05,
      "loss": 2.101,
      "step": 500
    },
    {
      "epoch": 0.7173601147776184,
      "grad_norm": 7.0845489501953125,
      "learning_rate": 1.5217599234815878e-05,
      "loss": 1.8819,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.590270757675171,
      "eval_rouge1": 0.3916416859053997,
      "eval_rouge2": 0.19880729723807156,
      "eval_rougeL": 0.382750399398817,
      "eval_rougeLsum": 0.38311641208619757,
      "eval_runtime": 1067.7291,
      "eval_samples_per_second": 2.611,
      "eval_steps_per_second": 0.653,
      "step": 1394
    },
    {
      "epoch": 1.0760401721664274,
      "grad_norm": 7.022219181060791,
      "learning_rate": 1.2826398852223818e-05,
      "loss": 1.8208,
      "step": 1500
    },
    {
      "epoch": 1.4347202295552366,
      "grad_norm": 8.181060791015625,
      "learning_rate": 1.0435198469631755e-05,
      "loss": 1.718,
      "step": 2000
    },
    {
      "epoch": 1.793400286944046,
      "grad_norm": 8.304183959960938,
      "learning_rate": 8.043998087039695e-06,
      "loss": 1.7516,
      "step": 2500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5554497241973877,
      "eval_rouge1": 0.38234006744658555,
      "eval_rouge2": 0.19842659831002687,
      "eval_rougeL": 0.3723334371691044,
      "eval_rougeLsum": 0.3724996919585559,
      "eval_runtime": 1048.7275,
      "eval_samples_per_second": 2.658,
      "eval_steps_per_second": 0.665,
      "step": 2788
    },
    {
      "epoch": 2.152080344332855,
      "grad_norm": 5.35423469543457,
      "learning_rate": 5.652797704447634e-06,
      "loss": 1.6662,
      "step": 3000
    },
    {
      "epoch": 2.5107604017216643,
      "grad_norm": 5.020022392272949,
      "learning_rate": 3.261597321855572e-06,
      "loss": 1.6696,
      "step": 3500
    },
    {
      "epoch": 2.869440459110473,
      "grad_norm": 6.37124490737915,
      "learning_rate": 8.703969392635103e-07,
      "loss": 1.6634,
      "step": 4000
    }
  ],
  "logging_steps": 500,
  "max_steps": 4182,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2776798057512960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}