{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 17840,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 3.6087698936462402,
      "learning_rate": 4e-05,
      "loss": 0.6296,
      "step": 3568
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5221142172813416,
      "eval_rouge1": 0.3678,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.3666,
      "eval_rougeLsum": 0.3673,
      "eval_runtime": 336.4559,
      "eval_samples_per_second": 2.229,
      "eval_steps_per_second": 0.279,
      "step": 3568
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.6926398277282715,
      "learning_rate": 3e-05,
      "loss": 0.4308,
      "step": 7136
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.49270936846733093,
      "eval_rouge1": 0.4034,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.3999,
      "eval_rougeLsum": 0.4032,
      "eval_runtime": 331.5676,
      "eval_samples_per_second": 2.262,
      "eval_steps_per_second": 0.284,
      "step": 7136
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.8685302734375,
      "learning_rate": 2e-05,
      "loss": 0.3347,
      "step": 10704
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5028479099273682,
      "eval_rouge1": 0.4081,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.407,
      "eval_rougeLsum": 0.4083,
      "eval_runtime": 334.0023,
      "eval_samples_per_second": 2.245,
      "eval_steps_per_second": 0.281,
      "step": 10704
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.236206293106079,
      "learning_rate": 1e-05,
      "loss": 0.2655,
      "step": 14272
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5220881700515747,
      "eval_rouge1": 0.4264,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.4239,
      "eval_rougeLsum": 0.4268,
      "eval_runtime": 328.7023,
      "eval_samples_per_second": 2.282,
      "eval_steps_per_second": 0.286,
      "step": 14272
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.0813827514648438,
      "learning_rate": 0.0,
      "loss": 0.2179,
      "step": 17840
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5374429821968079,
      "eval_rouge1": 0.4096,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.4081,
      "eval_rougeLsum": 0.4102,
      "eval_runtime": 330.0064,
      "eval_samples_per_second": 2.273,
      "eval_steps_per_second": 0.285,
      "step": 17840
    },
    {
      "epoch": 5.0,
      "step": 17840,
      "total_flos": 6.555985119973786e+16,
      "train_loss": 0.37568705947944403,
      "train_runtime": 9312.7957,
      "train_samples_per_second": 7.663,
      "train_steps_per_second": 1.916
    }
  ],
  "logging_steps": 500,
  "max_steps": 17840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6.555985119973786e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}