{
  "best_metric": 0.5060370564460754,
  "best_model_checkpoint": "t5_results/checkpoint-46875",
  "epoch": 5.0,
  "global_step": 46875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.978752e-05,
      "loss": 0.7612,
      "step": 500
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9574613333333336e-05,
      "loss": 0.67,
      "step": 1000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9361280000000002e-05,
      "loss": 0.6474,
      "step": 1500
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.914794666666667e-05,
      "loss": 0.6322,
      "step": 2000
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8934613333333335e-05,
      "loss": 0.6293,
      "step": 2500
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.8721706666666667e-05,
      "loss": 0.6208,
      "step": 3000
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.8508373333333333e-05,
      "loss": 0.6115,
      "step": 3500
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8295040000000003e-05,
      "loss": 0.6073,
      "step": 4000
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8081706666666666e-05,
      "loss": 0.6049,
      "step": 4500
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7868373333333336e-05,
      "loss": 0.6014,
      "step": 5000
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7655040000000002e-05,
      "loss": 0.5932,
      "step": 5500
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.744170666666667e-05,
      "loss": 0.5947,
      "step": 6000
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.7228373333333335e-05,
      "loss": 0.5972,
      "step": 6500
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.701504e-05,
      "loss": 0.5875,
      "step": 7000
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.6801706666666668e-05,
      "loss": 0.5896,
      "step": 7500
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.6588373333333335e-05,
      "loss": 0.5832,
      "step": 8000
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.637546666666667e-05,
      "loss": 0.5866,
      "step": 8500
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.616256e-05,
      "loss": 0.5815,
      "step": 9000
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 17.2391,
      "eval_loss": 0.5298414826393127,
      "eval_rouge1": 72.5682,
      "eval_rouge2": 63.0274,
      "eval_rougeL": 71.9035,
      "eval_rougeLsum": 71.9355,
      "eval_runtime": 1951.2025,
      "eval_samples_per_second": 51.25,
      "eval_steps_per_second": 3.203,
      "step": 9375
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.5949226666666667e-05,
      "loss": 0.5847,
      "step": 9500
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.5735893333333334e-05,
      "loss": 0.5753,
      "step": 10000
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.5522560000000003e-05,
      "loss": 0.5704,
      "step": 10500
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.5309226666666666e-05,
      "loss": 0.5757,
      "step": 11000
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.5095893333333333e-05,
      "loss": 0.571,
      "step": 11500
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.4882560000000001e-05,
      "loss": 0.5684,
      "step": 12000
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.4669226666666667e-05,
      "loss": 0.5713,
      "step": 12500
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.4455893333333336e-05,
      "loss": 0.5652,
      "step": 13000
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.4242986666666667e-05,
      "loss": 0.5671,
      "step": 13500
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.4029653333333335e-05,
      "loss": 0.5646,
      "step": 14000
    },
    {
      "epoch": 1.55,
      "learning_rate": 1.3817173333333333e-05,
      "loss": 0.564,
      "step": 14500
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.3603840000000001e-05,
      "loss": 0.5628,
      "step": 15000
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3390506666666668e-05,
      "loss": 0.5638,
      "step": 15500
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.3177173333333336e-05,
      "loss": 0.5631,
      "step": 16000
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.296384e-05,
      "loss": 0.5641,
      "step": 16500
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.2750933333333335e-05,
      "loss": 0.5659,
      "step": 17000
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.25376e-05,
      "loss": 0.5625,
      "step": 17500
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.2324266666666666e-05,
      "loss": 0.5637,
      "step": 18000
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.2110933333333335e-05,
      "loss": 0.5626,
      "step": 18500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 17.2327,
      "eval_loss": 0.5176606774330139,
      "eval_rouge1": 72.7237,
      "eval_rouge2": 63.3082,
      "eval_rougeL": 72.0632,
      "eval_rougeLsum": 72.0935,
      "eval_runtime": 1949.9946,
      "eval_samples_per_second": 51.282,
      "eval_steps_per_second": 3.205,
      "step": 18750
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.1897600000000001e-05,
      "loss": 0.5541,
      "step": 19000
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.1684266666666668e-05,
      "loss": 0.557,
      "step": 19500
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.1470933333333334e-05,
      "loss": 0.5559,
      "step": 20000
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.1257600000000002e-05,
      "loss": 0.5577,
      "step": 20500
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.1044266666666667e-05,
      "loss": 0.5506,
      "step": 21000
    },
    {
      "epoch": 2.29,
      "learning_rate": 1.0830933333333333e-05,
      "loss": 0.5517,
      "step": 21500
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.0617600000000001e-05,
      "loss": 0.551,
      "step": 22000
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.0404266666666666e-05,
      "loss": 0.5507,
      "step": 22500
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.0191360000000001e-05,
      "loss": 0.5501,
      "step": 23000
    },
    {
      "epoch": 2.51,
      "learning_rate": 9.978026666666667e-06,
      "loss": 0.552,
      "step": 23500
    },
    {
      "epoch": 2.56,
      "learning_rate": 9.764693333333334e-06,
      "loss": 0.5511,
      "step": 24000
    },
    {
      "epoch": 2.61,
      "learning_rate": 9.55136e-06,
      "loss": 0.5479,
      "step": 24500
    },
    {
      "epoch": 2.67,
      "learning_rate": 9.338453333333333e-06,
      "loss": 0.5522,
      "step": 25000
    },
    {
      "epoch": 2.72,
      "learning_rate": 9.12512e-06,
      "loss": 0.5511,
      "step": 25500
    },
    {
      "epoch": 2.77,
      "learning_rate": 8.912213333333335e-06,
      "loss": 0.5502,
      "step": 26000
    },
    {
      "epoch": 2.83,
      "learning_rate": 8.698880000000001e-06,
      "loss": 0.548,
      "step": 26500
    },
    {
      "epoch": 2.88,
      "learning_rate": 8.485546666666667e-06,
      "loss": 0.5513,
      "step": 27000
    },
    {
      "epoch": 2.93,
      "learning_rate": 8.272213333333334e-06,
      "loss": 0.5484,
      "step": 27500
    },
    {
      "epoch": 2.99,
      "learning_rate": 8.05888e-06,
      "loss": 0.547,
      "step": 28000
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 17.2248,
      "eval_loss": 0.5098650455474854,
      "eval_rouge1": 72.8028,
      "eval_rouge2": 63.4587,
      "eval_rougeL": 72.1437,
      "eval_rougeLsum": 72.1738,
      "eval_runtime": 1955.4373,
      "eval_samples_per_second": 51.139,
      "eval_steps_per_second": 3.196,
      "step": 28125
    },
    {
      "epoch": 3.04,
      "learning_rate": 7.845546666666667e-06,
      "loss": 0.5466,
      "step": 28500
    },
    {
      "epoch": 3.09,
      "learning_rate": 7.632640000000002e-06,
      "loss": 0.5464,
      "step": 29000
    },
    {
      "epoch": 3.15,
      "learning_rate": 7.419306666666667e-06,
      "loss": 0.5484,
      "step": 29500
    },
    {
      "epoch": 3.2,
      "learning_rate": 7.2059733333333336e-06,
      "loss": 0.5421,
      "step": 30000
    },
    {
      "epoch": 3.25,
      "learning_rate": 6.992640000000001e-06,
      "loss": 0.5425,
      "step": 30500
    },
    {
      "epoch": 3.31,
      "learning_rate": 6.779306666666667e-06,
      "loss": 0.5446,
      "step": 31000
    },
    {
      "epoch": 3.36,
      "learning_rate": 6.565973333333335e-06,
      "loss": 0.5407,
      "step": 31500
    },
    {
      "epoch": 3.41,
      "learning_rate": 6.352640000000001e-06,
      "loss": 0.546,
      "step": 32000
    },
    {
      "epoch": 3.47,
      "learning_rate": 6.139306666666667e-06,
      "loss": 0.5415,
      "step": 32500
    },
    {
      "epoch": 3.52,
      "learning_rate": 5.925973333333334e-06,
      "loss": 0.5456,
      "step": 33000
    },
    {
      "epoch": 3.57,
      "learning_rate": 5.71264e-06,
      "loss": 0.5435,
      "step": 33500
    },
    {
      "epoch": 3.63,
      "learning_rate": 5.4997333333333335e-06,
      "loss": 0.5424,
      "step": 34000
    },
    {
      "epoch": 3.68,
      "learning_rate": 5.2868266666666665e-06,
      "loss": 0.5439,
      "step": 34500
    },
    {
      "epoch": 3.73,
      "learning_rate": 5.073493333333334e-06,
      "loss": 0.5402,
      "step": 35000
    },
    {
      "epoch": 3.79,
      "learning_rate": 4.86016e-06,
      "loss": 0.5396,
      "step": 35500
    },
    {
      "epoch": 3.84,
      "learning_rate": 4.6468266666666675e-06,
      "loss": 0.5362,
      "step": 36000
    },
    {
      "epoch": 3.89,
      "learning_rate": 4.4339200000000006e-06,
      "loss": 0.5459,
      "step": 36500
    },
    {
      "epoch": 3.95,
      "learning_rate": 4.220586666666667e-06,
      "loss": 0.5419,
      "step": 37000
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.0072533333333335e-06,
      "loss": 0.5432,
      "step": 37500
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 17.2265,
      "eval_loss": 0.5071600079536438,
      "eval_rouge1": 72.831,
      "eval_rouge2": 63.5122,
      "eval_rougeL": 72.1737,
      "eval_rougeLsum": 72.2038,
      "eval_runtime": 1947.9767,
      "eval_samples_per_second": 51.335,
      "eval_steps_per_second": 3.208,
      "step": 37500
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.7939200000000003e-06,
      "loss": 0.5406,
      "step": 38000
    },
    {
      "epoch": 4.11,
      "learning_rate": 3.5810133333333334e-06,
      "loss": 0.5414,
      "step": 38500
    },
    {
      "epoch": 4.16,
      "learning_rate": 3.368106666666667e-06,
      "loss": 0.539,
      "step": 39000
    },
    {
      "epoch": 4.21,
      "learning_rate": 3.1547733333333337e-06,
      "loss": 0.5391,
      "step": 39500
    },
    {
      "epoch": 4.27,
      "learning_rate": 2.9414400000000006e-06,
      "loss": 0.5385,
      "step": 40000
    },
    {
      "epoch": 4.32,
      "learning_rate": 2.7281066666666666e-06,
      "loss": 0.5391,
      "step": 40500
    },
    {
      "epoch": 4.37,
      "learning_rate": 2.5147733333333335e-06,
      "loss": 0.5372,
      "step": 41000
    },
    {
      "epoch": 4.43,
      "learning_rate": 2.30144e-06,
      "loss": 0.5375,
      "step": 41500
    },
    {
      "epoch": 4.48,
      "learning_rate": 2.0885333333333334e-06,
      "loss": 0.5364,
      "step": 42000
    },
    {
      "epoch": 4.53,
      "learning_rate": 1.8752e-06,
      "loss": 0.5343,
      "step": 42500
    },
    {
      "epoch": 4.59,
      "learning_rate": 1.661866666666667e-06,
      "loss": 0.5386,
      "step": 43000
    },
    {
      "epoch": 4.64,
      "learning_rate": 1.4485333333333334e-06,
      "loss": 0.5362,
      "step": 43500
    },
    {
      "epoch": 4.69,
      "learning_rate": 1.2352e-06,
      "loss": 0.5385,
      "step": 44000
    },
    {
      "epoch": 4.75,
      "learning_rate": 1.0218666666666667e-06,
      "loss": 0.5411,
      "step": 44500
    },
    {
      "epoch": 4.8,
      "learning_rate": 8.085333333333334e-07,
      "loss": 0.537,
      "step": 45000
    },
    {
      "epoch": 4.85,
      "learning_rate": 5.952e-07,
      "loss": 0.5378,
      "step": 45500
    },
    {
      "epoch": 4.91,
      "learning_rate": 3.818666666666667e-07,
      "loss": 0.5407,
      "step": 46000
    },
    {
      "epoch": 4.96,
      "learning_rate": 1.6896000000000003e-07,
      "loss": 0.54,
      "step": 46500
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 17.2227,
      "eval_loss": 0.5060370564460754,
      "eval_rouge1": 72.8556,
      "eval_rouge2": 63.5466,
      "eval_rougeL": 72.1975,
      "eval_rougeLsum": 72.228,
      "eval_runtime": 1951.1899,
      "eval_samples_per_second": 51.251,
      "eval_steps_per_second": 3.203,
      "step": 46875
    }
  ],
  "max_steps": 46875,
  "num_train_epochs": 5,
  "total_flos": 3.315684370415616e+17,
  "trial_name": null,
  "trial_params": null
}