{
  "best_metric": 2.732292890548706,
  "best_model_checkpoint": "flan-t5-base-tldr-100k/checkpoint-45000",
  "epoch": 5.0,
  "global_step": 56250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 4.955555555555556e-05,
      "loss": 3.2897,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9111111111111114e-05,
      "loss": 3.2632,
      "step": 1000
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.866666666666667e-05,
      "loss": 3.2601,
      "step": 1500
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.8222222222222225e-05,
      "loss": 3.2293,
      "step": 2000
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.7777777777777784e-05,
      "loss": 3.2164,
      "step": 2500
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.7333333333333336e-05,
      "loss": 3.1959,
      "step": 3000
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.6888888888888895e-05,
      "loss": 3.1905,
      "step": 3500
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.644444444444445e-05,
      "loss": 3.233,
      "step": 4000
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.600000000000001e-05,
      "loss": 3.1792,
      "step": 4500
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.555555555555556e-05,
      "loss": 3.2026,
      "step": 5000
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.511111111111112e-05,
      "loss": 3.1937,
      "step": 5500
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.466666666666667e-05,
      "loss": 3.1751,
      "step": 6000
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.422222222222222e-05,
      "loss": 3.173,
      "step": 6500
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.377777777777778e-05,
      "loss": 3.1968,
      "step": 7000
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 3.1666,
      "step": 7500
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.2888888888888886e-05,
      "loss": 3.1855,
      "step": 8000
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.2444444444444445e-05,
      "loss": 3.1626,
      "step": 8500
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.2e-05,
      "loss": 3.1699,
      "step": 9000
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.155555555555556e-05,
      "loss": 3.1657,
      "step": 9500
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.111111111111111e-05,
      "loss": 3.1547,
      "step": 10000
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.066666666666667e-05,
      "loss": 3.1496,
      "step": 10500
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.022222222222222e-05,
      "loss": 3.1467,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 16.4911,
      "eval_loss": 2.953094482421875,
      "eval_rouge1": 15.909,
      "eval_rouge2": 3.8156,
      "eval_rougeL": 13.4884,
      "eval_rougeLsum": 13.9568,
      "eval_runtime": 1704.954,
      "eval_samples_per_second": 5.865,
      "eval_steps_per_second": 0.733,
      "step": 11250
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.977777777777778e-05,
      "loss": 3.0983,
      "step": 11500
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.933333333333333e-05,
      "loss": 3.0641,
      "step": 12000
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.888888888888889e-05,
      "loss": 3.0471,
      "step": 12500
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.844444444444444e-05,
      "loss": 3.0583,
      "step": 13000
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.8e-05,
      "loss": 3.069,
      "step": 13500
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.7555555555555554e-05,
      "loss": 3.0642,
      "step": 14000
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.7111111111111113e-05,
      "loss": 3.0729,
      "step": 14500
    },
    {
      "epoch": 1.33,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 3.0753,
      "step": 15000
    },
    {
      "epoch": 1.38,
      "learning_rate": 3.6222222222222225e-05,
      "loss": 3.0415,
      "step": 15500
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.577777777777778e-05,
      "loss": 3.0632,
      "step": 16000
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.5333333333333336e-05,
      "loss": 3.0757,
      "step": 16500
    },
    {
      "epoch": 1.51,
      "learning_rate": 3.4888888888888895e-05,
      "loss": 3.0589,
      "step": 17000
    },
    {
      "epoch": 1.56,
      "learning_rate": 3.444444444444445e-05,
      "loss": 3.0586,
      "step": 17500
    },
    {
      "epoch": 1.6,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 3.0582,
      "step": 18000
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.355555555555556e-05,
      "loss": 3.0657,
      "step": 18500
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.311111111111112e-05,
      "loss": 3.0653,
      "step": 19000
    },
    {
      "epoch": 1.73,
      "learning_rate": 3.266666666666667e-05,
      "loss": 3.0513,
      "step": 19500
    },
    {
      "epoch": 1.78,
      "learning_rate": 3.222222222222223e-05,
      "loss": 3.082,
      "step": 20000
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.177777777777778e-05,
      "loss": 3.0785,
      "step": 20500
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.1333333333333334e-05,
      "loss": 3.0654,
      "step": 21000
    },
    {
      "epoch": 1.91,
      "learning_rate": 3.088888888888889e-05,
      "loss": 3.0531,
      "step": 21500
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.044444444444445e-05,
      "loss": 3.0518,
      "step": 22000
    },
    {
      "epoch": 2.0,
      "learning_rate": 3e-05,
      "loss": 3.0673,
      "step": 22500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 16.4639,
      "eval_loss": 2.93178129196167,
      "eval_rouge1": 16.4972,
      "eval_rouge2": 3.9757,
      "eval_rougeL": 13.9517,
      "eval_rougeLsum": 14.4336,
      "eval_runtime": 1398.1721,
      "eval_samples_per_second": 7.152,
      "eval_steps_per_second": 0.894,
      "step": 22500
    },
    {
      "epoch": 2.04,
      "learning_rate": 2.955555555555556e-05,
      "loss": 2.9751,
      "step": 23000
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.9111111111111112e-05,
      "loss": 2.9883,
      "step": 23500
    },
    {
      "epoch": 2.13,
      "learning_rate": 2.8666666666666668e-05,
      "loss": 2.9911,
      "step": 24000
    },
    {
      "epoch": 2.18,
      "learning_rate": 2.8222222222222223e-05,
      "loss": 2.9796,
      "step": 24500
    },
    {
      "epoch": 2.22,
      "learning_rate": 2.777777777777778e-05,
      "loss": 2.9767,
      "step": 25000
    },
    {
      "epoch": 2.27,
      "learning_rate": 2.733333333333333e-05,
      "loss": 2.9795,
      "step": 25500
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.688888888888889e-05,
      "loss": 2.9654,
      "step": 26000
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.6444444444444443e-05,
      "loss": 2.9904,
      "step": 26500
    },
    {
      "epoch": 2.4,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.9785,
      "step": 27000
    },
    {
      "epoch": 2.44,
      "learning_rate": 2.5555555555555554e-05,
      "loss": 2.9856,
      "step": 27500
    },
    {
      "epoch": 2.49,
      "learning_rate": 2.5111111111111113e-05,
      "loss": 3.007,
      "step": 28000
    },
    {
      "epoch": 2.53,
      "learning_rate": 2.466666666666667e-05,
      "loss": 2.9819,
      "step": 28500
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.4222222222222224e-05,
      "loss": 3.0003,
      "step": 29000
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.377777777777778e-05,
      "loss": 2.981,
      "step": 29500
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 2.9926,
      "step": 30000
    },
    {
      "epoch": 2.71,
      "learning_rate": 2.288888888888889e-05,
      "loss": 2.9901,
      "step": 30500
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.2444444444444447e-05,
      "loss": 2.9893,
      "step": 31000
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.9668,
      "step": 31500
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.1555555555555555e-05,
      "loss": 2.9903,
      "step": 32000
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.111111111111111e-05,
      "loss": 2.9687,
      "step": 32500
    },
    {
      "epoch": 2.93,
      "learning_rate": 2.0666666666666666e-05,
      "loss": 2.9839,
      "step": 33000
    },
    {
      "epoch": 2.98,
      "learning_rate": 2.0222222222222222e-05,
      "loss": 2.9952,
      "step": 33500
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 16.2585,
      "eval_loss": 2.924546003341675,
      "eval_rouge1": 16.5997,
      "eval_rouge2": 4.1068,
      "eval_rougeL": 14.0299,
      "eval_rougeLsum": 14.5147,
      "eval_runtime": 945.9838,
      "eval_samples_per_second": 10.571,
      "eval_steps_per_second": 1.321,
      "step": 33750
    },
    {
      "epoch": 3.02,
      "learning_rate": 1.9777777777777778e-05,
      "loss": 2.9548,
      "step": 34000
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 2.9566,
      "step": 34500
    },
    {
      "epoch": 3.11,
      "learning_rate": 1.888888888888889e-05,
      "loss": 2.953,
      "step": 35000
    },
    {
      "epoch": 3.16,
      "learning_rate": 1.8444444444444445e-05,
      "loss": 2.9514,
      "step": 35500
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.8e-05,
      "loss": 2.9362,
      "step": 36000
    },
    {
      "epoch": 3.24,
      "learning_rate": 1.7555555555555556e-05,
      "loss": 2.9482,
      "step": 36500
    },
    {
      "epoch": 3.29,
      "learning_rate": 1.7111111111111112e-05,
      "loss": 2.9441,
      "step": 37000
    },
    {
      "epoch": 3.33,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.9366,
      "step": 37500
    },
    {
      "epoch": 3.38,
      "learning_rate": 1.6222222222222223e-05,
      "loss": 2.9558,
      "step": 38000
    },
    {
      "epoch": 3.42,
      "learning_rate": 1.577777777777778e-05,
      "loss": 2.959,
      "step": 38500
    },
    {
      "epoch": 3.47,
      "learning_rate": 1.5333333333333334e-05,
      "loss": 2.9634,
      "step": 39000
    },
    {
      "epoch": 3.51,
      "learning_rate": 1.4888888888888888e-05,
      "loss": 2.9464,
      "step": 39500
    },
    {
      "epoch": 3.56,
      "learning_rate": 1.4444444444444444e-05,
      "loss": 2.9669,
      "step": 40000
    },
    {
      "epoch": 3.6,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.9404,
      "step": 40500
    },
    {
      "epoch": 3.64,
      "learning_rate": 1.3555555555555557e-05,
      "loss": 2.9686,
      "step": 41000
    },
    {
      "epoch": 3.69,
      "learning_rate": 1.3111111111111113e-05,
      "loss": 2.9384,
      "step": 41500
    },
    {
      "epoch": 3.73,
      "learning_rate": 1.2666666666666668e-05,
      "loss": 2.9304,
      "step": 42000
    },
    {
      "epoch": 3.78,
      "learning_rate": 1.2222222222222222e-05,
      "loss": 2.9474,
      "step": 42500
    },
    {
      "epoch": 3.82,
      "learning_rate": 1.1777777777777778e-05,
      "loss": 2.9455,
      "step": 43000
    },
    {
      "epoch": 3.87,
      "learning_rate": 1.1333333333333334e-05,
      "loss": 2.9456,
      "step": 43500
    },
    {
      "epoch": 3.91,
      "learning_rate": 1.088888888888889e-05,
      "loss": 2.9359,
      "step": 44000
    },
    {
      "epoch": 3.96,
      "learning_rate": 1.0444444444444445e-05,
      "loss": 2.9445,
      "step": 44500
    },
    {
      "epoch": 4.0,
      "learning_rate": 1e-05,
      "loss": 2.9524,
      "step": 45000
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 16.0925,
      "eval_loss": 2.732292890548706,
      "eval_rouge1": 17.0772,
      "eval_rouge2": 4.4204,
      "eval_rougeL": 14.549,
      "eval_rougeLsum": 15.0148,
      "eval_runtime": 957.2679,
      "eval_samples_per_second": 10.446,
      "eval_steps_per_second": 1.306,
      "step": 45000
    },
    {
      "epoch": 4.04,
      "learning_rate": 9.555555555555556e-06,
      "loss": 2.8978,
      "step": 45500
    },
    {
      "epoch": 4.09,
      "learning_rate": 9.111111111111112e-06,
      "loss": 2.8935,
      "step": 46000
    },
    {
      "epoch": 4.13,
      "learning_rate": 8.666666666666668e-06,
      "loss": 2.9088,
      "step": 46500
    },
    {
      "epoch": 4.18,
      "learning_rate": 8.222222222222223e-06,
      "loss": 2.9148,
      "step": 47000
    },
    {
      "epoch": 4.22,
      "learning_rate": 7.777777777777777e-06,
      "loss": 2.9336,
      "step": 47500
    },
    {
      "epoch": 4.27,
      "learning_rate": 7.333333333333334e-06,
      "loss": 2.9111,
      "step": 48000
    },
    {
      "epoch": 4.31,
      "learning_rate": 6.888888888888889e-06,
      "loss": 2.934,
      "step": 48500
    },
    {
      "epoch": 4.36,
      "learning_rate": 6.4444444444444445e-06,
      "loss": 2.9219,
      "step": 49000
    },
    {
      "epoch": 4.4,
      "learning_rate": 6e-06,
      "loss": 2.914,
      "step": 49500
    },
    {
      "epoch": 4.44,
      "learning_rate": 5.555555555555556e-06,
      "loss": 2.9088,
      "step": 50000
    },
    {
      "epoch": 4.49,
      "learning_rate": 5.1111111111111115e-06,
      "loss": 2.93,
      "step": 50500
    },
    {
      "epoch": 4.53,
      "learning_rate": 4.666666666666667e-06,
      "loss": 2.9101,
      "step": 51000
    },
    {
      "epoch": 4.58,
      "learning_rate": 4.222222222222223e-06,
      "loss": 2.9189,
      "step": 51500
    },
    {
      "epoch": 4.62,
      "learning_rate": 3.777777777777778e-06,
      "loss": 2.9197,
      "step": 52000
    },
    {
      "epoch": 4.67,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.9263,
      "step": 52500
    },
    {
      "epoch": 4.71,
      "learning_rate": 2.888888888888889e-06,
      "loss": 2.925,
      "step": 53000
    },
    {
      "epoch": 4.76,
      "learning_rate": 2.4444444444444447e-06,
      "loss": 2.9124,
      "step": 53500
    },
    {
      "epoch": 4.8,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.8981,
      "step": 54000
    },
    {
      "epoch": 4.84,
      "learning_rate": 1.5555555555555556e-06,
      "loss": 2.9145,
      "step": 54500
    },
    {
      "epoch": 4.89,
      "learning_rate": 1.1111111111111112e-06,
      "loss": 2.9135,
      "step": 55000
    },
    {
      "epoch": 4.93,
      "learning_rate": 6.666666666666667e-07,
      "loss": 2.9066,
      "step": 55500
    },
    {
      "epoch": 4.98,
      "learning_rate": 2.2222222222222224e-07,
      "loss": 2.9223,
      "step": 56000
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 16.2163,
      "eval_loss": 2.732771158218384,
      "eval_rouge1": 17.1468,
      "eval_rouge2": 4.4384,
      "eval_rougeL": 14.5798,
      "eval_rougeLsum": 15.0572,
      "eval_runtime": 1011.7448,
      "eval_samples_per_second": 9.884,
      "eval_steps_per_second": 1.235,
      "step": 56250
    }
  ],
  "max_steps": 56250,
  "num_train_epochs": 5,
  "total_flos": 3.081408086016e+17,
  "trial_name": null,
  "trial_params": null
}