{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.9852,
      "step": 50
    },
    {
      "epoch": 0.33,
      "eval_gen_len": 19.0,
      "eval_loss": 0.10978420078754425,
      "eval_rouge1": 55.1421,
      "eval_rouge2": 49.8248,
      "eval_rougeL": 54.4294,
      "eval_rougeLsum": 54.7377,
      "eval_runtime": 39.7186,
      "eval_samples_per_second": 5.035,
      "eval_steps_per_second": 1.259,
      "step": 50
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.1186,
      "step": 100
    },
    {
      "epoch": 0.67,
      "eval_gen_len": 19.0,
      "eval_loss": 0.017564596608281136,
      "eval_rouge1": 58.0994,
      "eval_rouge2": 54.8973,
      "eval_rougeL": 57.7383,
      "eval_rougeLsum": 57.9538,
      "eval_runtime": 41.75,
      "eval_samples_per_second": 4.79,
      "eval_steps_per_second": 1.198,
      "step": 100
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0417,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 19.0,
      "eval_loss": 0.0056667388416826725,
      "eval_rouge1": 58.3685,
      "eval_rouge2": 55.7353,
      "eval_rougeL": 58.279,
      "eval_rougeLsum": 58.2729,
      "eval_runtime": 39.0626,
      "eval_samples_per_second": 5.12,
      "eval_steps_per_second": 1.28,
      "step": 150
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0225,
      "step": 200
    },
    {
      "epoch": 1.33,
      "eval_gen_len": 19.0,
      "eval_loss": 0.0028974052984267473,
      "eval_rouge1": 58.8981,
      "eval_rouge2": 56.2457,
      "eval_rougeL": 58.8202,
      "eval_rougeLsum": 58.7906,
      "eval_runtime": 37.062,
      "eval_samples_per_second": 5.396,
      "eval_steps_per_second": 1.349,
      "step": 200
    },
    {
      "epoch": 1.67,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0131,
      "step": 250
    },
    {
      "epoch": 1.67,
      "eval_gen_len": 19.0,
      "eval_loss": 0.002385010477155447,
      "eval_rouge1": 58.8439,
      "eval_rouge2": 56.2535,
      "eval_rougeL": 58.7557,
      "eval_rougeLsum": 58.7218,
      "eval_runtime": 35.1064,
      "eval_samples_per_second": 5.697,
      "eval_steps_per_second": 1.424,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0112,
      "step": 300
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 19.0,
      "eval_loss": 0.0012605164665728807,
      "eval_rouge1": 58.9538,
      "eval_rouge2": 56.4749,
      "eval_rougeL": 58.9322,
      "eval_rougeLsum": 58.8817,
      "eval_runtime": 34.7769,
      "eval_samples_per_second": 5.751,
      "eval_steps_per_second": 1.438,
      "step": 300
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0077,
      "step": 350
    },
    {
      "epoch": 2.33,
      "eval_gen_len": 19.0,
      "eval_loss": 0.0012833760119974613,
      "eval_rouge1": 58.9538,
      "eval_rouge2": 56.4749,
      "eval_rougeL": 58.9322,
      "eval_rougeLsum": 58.8817,
      "eval_runtime": 36.7902,
      "eval_samples_per_second": 5.436,
      "eval_steps_per_second": 1.359,
      "step": 350
    },
    {
      "epoch": 2.67,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0043,
      "step": 400
    },
    {
      "epoch": 2.67,
      "eval_gen_len": 19.0,
      "eval_loss": 0.0010497889015823603,
      "eval_rouge1": 59.0124,
      "eval_rouge2": 56.5806,
      "eval_rougeL": 58.9867,
      "eval_rougeLsum": 58.9342,
      "eval_runtime": 38.5671,
      "eval_samples_per_second": 5.186,
      "eval_steps_per_second": 1.296,
      "step": 400
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.0052,
      "step": 450
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 19.0,
      "eval_loss": 0.0010262294672429562,
      "eval_rouge1": 59.0402,
      "eval_rouge2": 56.6982,
      "eval_rougeL": 59.0385,
      "eval_rougeLsum": 58.986,
      "eval_runtime": 40.6407,
      "eval_samples_per_second": 4.921,
      "eval_steps_per_second": 1.23,
      "step": 450
    },
    {
      "epoch": 3.0,
      "step": 450,
      "total_flos": 2085075861504000.0,
      "train_loss": 0.13440267986721463,
      "train_runtime": 578.2653,
      "train_samples_per_second": 3.113,
      "train_steps_per_second": 0.778
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 3,
  "total_flos": 2085075861504000.0,
  "trial_name": null,
  "trial_params": null
}