{
  "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": 0.8082135319709778,
      "learning_rate": 0.0008,
      "loss": 0.7807,
      "step": 892
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5299099087715149,
      "eval_rouge1": 0.6861,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6833,
      "eval_rougeLsum": 0.6836,
      "eval_runtime": 37.7592,
      "eval_samples_per_second": 19.783,
      "eval_steps_per_second": 0.636,
      "step": 892
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7777946591377258,
      "learning_rate": 0.0006,
      "loss": 0.6079,
      "step": 1784
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.4988546669483185,
      "eval_rouge1": 0.7141,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7153,
      "eval_rougeLsum": 0.7147,
      "eval_runtime": 37.1649,
      "eval_samples_per_second": 20.1,
      "eval_steps_per_second": 0.646,
      "step": 1784
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8722276091575623,
      "learning_rate": 0.0004,
      "loss": 0.5583,
      "step": 2676
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.4761173725128174,
      "eval_rouge1": 0.7153,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7152,
      "eval_rougeLsum": 0.7139,
      "eval_runtime": 36.3686,
      "eval_samples_per_second": 20.54,
      "eval_steps_per_second": 0.66,
      "step": 2676
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7476885318756104,
      "learning_rate": 0.0002,
      "loss": 0.5208,
      "step": 3568
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.4718637764453888,
      "eval_rouge1": 0.7433,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.743,
      "eval_rougeLsum": 0.7395,
      "eval_runtime": 36.3604,
      "eval_samples_per_second": 20.544,
      "eval_steps_per_second": 0.66,
      "step": 3568
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.997207760810852,
      "learning_rate": 0.0,
      "loss": 0.4912,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.4652620851993561,
      "eval_rouge1": 0.7309,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7284,
      "eval_rougeLsum": 0.7264,
      "eval_runtime": 37.8929,
      "eval_samples_per_second": 19.713,
      "eval_steps_per_second": 0.633,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "step": 4460,
      "total_flos": 4.92357702057984e+16,
      "train_loss": 0.5918008025986197,
      "train_runtime": 3747.1994,
      "train_samples_per_second": 19.036,
      "train_steps_per_second": 1.19
    }
  ],
  "logging_steps": 500,
  "max_steps": 4460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4.92357702057984e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}