{
  "best_metric": 2.6812784671783447,
  "best_model_checkpoint": "./models/final_bart/checkpoint-2000",
  "epoch": 5.0,
  "global_step": 3340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 8.982035928143711e-06,
      "loss": 5.6146,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7964071856287423e-05,
      "loss": 2.8024,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.6946107784431136e-05,
      "loss": 2.5446,
      "step": 300
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.934131736526946e-05,
      "loss": 2.4198,
      "step": 400
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.8343313373253494e-05,
      "loss": 2.3636,
      "step": 500
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.7345309381237524e-05,
      "loss": 2.3251,
      "step": 600
    },
    {
      "epoch": 1.05,
      "learning_rate": 2.6347305389221558e-05,
      "loss": 2.2522,
      "step": 700
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.534930139720559e-05,
      "loss": 2.1959,
      "step": 800
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.4351297405189622e-05,
      "loss": 2.1588,
      "step": 900
    },
    {
      "epoch": 1.5,
      "learning_rate": 2.3353293413173656e-05,
      "loss": 2.1542,
      "step": 1000
    },
    {
      "epoch": 1.5,
      "eval_bleu1": 27.9938,
      "eval_bleu2": 15.5354,
      "eval_bleu3": 8.2494,
      "eval_bleu4": 4.42,
      "eval_gen_len": 50.08,
      "eval_loss": 2.749131202697754,
      "eval_rdass": 0.6093000173568726,
      "eval_rouge1": 33.5554,
      "eval_rouge2": 11.2371,
      "eval_rougeL": 22.006,
      "eval_runtime": 24.7242,
      "eval_samples_per_second": 4.045,
      "eval_steps_per_second": 0.04,
      "step": 1000
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.2355289421157686e-05,
      "loss": 2.1473,
      "step": 1100
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.135728542914172e-05,
      "loss": 2.1459,
      "step": 1200
    },
    {
      "epoch": 1.95,
      "learning_rate": 2.0359281437125747e-05,
      "loss": 2.1324,
      "step": 1300
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.936127744510978e-05,
      "loss": 2.0676,
      "step": 1400
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.836327345309381e-05,
      "loss": 2.0206,
      "step": 1500
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.7365269461077845e-05,
      "loss": 2.0198,
      "step": 1600
    },
    {
      "epoch": 2.54,
      "learning_rate": 1.6367265469061875e-05,
      "loss": 2.0177,
      "step": 1700
    },
    {
      "epoch": 2.69,
      "learning_rate": 1.536926147704591e-05,
      "loss": 2.0143,
      "step": 1800
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.437125748502994e-05,
      "loss": 2.0075,
      "step": 1900
    },
    {
      "epoch": 2.99,
      "learning_rate": 1.3373253493013973e-05,
      "loss": 2.0071,
      "step": 2000
    },
    {
      "epoch": 2.99,
      "eval_bleu1": 29.6866,
      "eval_bleu2": 17.1396,
      "eval_bleu3": 9.7016,
      "eval_bleu4": 5.3559,
      "eval_gen_len": 54.04,
      "eval_loss": 2.6812784671783447,
      "eval_rdass": 0.6154999732971191,
      "eval_rouge1": 35.0501,
      "eval_rouge2": 12.2759,
      "eval_rougeL": 22.6669,
      "eval_runtime": 20.0572,
      "eval_samples_per_second": 4.986,
      "eval_steps_per_second": 0.05,
      "step": 2000
    },
    {
      "epoch": 3.14,
      "learning_rate": 1.2375249500998005e-05,
      "loss": 1.9318,
      "step": 2100
    },
    {
      "epoch": 3.29,
      "learning_rate": 1.1377245508982035e-05,
      "loss": 1.9389,
      "step": 2200
    },
    {
      "epoch": 3.44,
      "learning_rate": 1.0379241516966067e-05,
      "loss": 1.9214,
      "step": 2300
    },
    {
      "epoch": 3.59,
      "learning_rate": 9.3812375249501e-06,
      "loss": 1.9144,
      "step": 2400
    },
    {
      "epoch": 3.74,
      "learning_rate": 8.383233532934131e-06,
      "loss": 1.9404,
      "step": 2500
    },
    {
      "epoch": 3.89,
      "learning_rate": 7.385229540918164e-06,
      "loss": 1.9189,
      "step": 2600
    },
    {
      "epoch": 4.04,
      "learning_rate": 6.3872255489021955e-06,
      "loss": 1.9155,
      "step": 2700
    },
    {
      "epoch": 4.19,
      "learning_rate": 5.3892215568862275e-06,
      "loss": 1.874,
      "step": 2800
    },
    {
      "epoch": 4.34,
      "learning_rate": 4.39121756487026e-06,
      "loss": 1.8951,
      "step": 2900
    },
    {
      "epoch": 4.49,
      "learning_rate": 3.3932135728542917e-06,
      "loss": 1.8694,
      "step": 3000
    },
    {
      "epoch": 4.49,
      "eval_bleu1": 30.5261,
      "eval_bleu2": 17.6264,
      "eval_bleu3": 10.3974,
      "eval_bleu4": 5.4348,
      "eval_gen_len": 53.47,
      "eval_loss": 2.684814453125,
      "eval_rdass": 0.6248000264167786,
      "eval_rouge1": 35.7722,
      "eval_rouge2": 12.5127,
      "eval_rougeL": 23.3002,
      "eval_runtime": 17.6216,
      "eval_samples_per_second": 5.675,
      "eval_steps_per_second": 0.057,
      "step": 3000
    },
    {
      "epoch": 4.64,
      "learning_rate": 2.3952095808383233e-06,
      "loss": 1.8708,
      "step": 3100
    },
    {
      "epoch": 4.79,
      "learning_rate": 1.3972055888223554e-06,
      "loss": 1.8628,
      "step": 3200
    },
    {
      "epoch": 4.94,
      "learning_rate": 3.992015968063872e-07,
      "loss": 1.8613,
      "step": 3300
    },
    {
      "epoch": 5.0,
      "step": 3340,
      "total_flos": 5.5473275160576e+16,
      "train_loss": 2.181800748630912,
      "train_runtime": 3900.3613,
      "train_samples_per_second": 54.733,
      "train_steps_per_second": 0.856
    }
  ],
  "max_steps": 3340,
  "num_train_epochs": 5,
  "total_flos": 5.5473275160576e+16,
  "trial_name": null,
  "trial_params": null
}