{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 78.67820613690007,
  "eval_steps": 500,
  "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.79,
      "learning_rate": 4.000000000000001e-06,
      "loss": 7.6372,
      "step": 1000
    },
    {
      "epoch": 1.57,
      "learning_rate": 8.000000000000001e-06,
      "loss": 6.7047,
      "step": 2000
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.2e-05,
      "loss": 6.5606,
      "step": 3000
    },
    {
      "epoch": 3.15,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 6.5006,
      "step": 4000
    },
    {
      "epoch": 3.93,
      "learning_rate": 2e-05,
      "loss": 6.4672,
      "step": 5000
    },
    {
      "epoch": 4.72,
      "learning_rate": 2.4e-05,
      "loss": 6.4504,
      "step": 6000
    },
    {
      "epoch": 5.51,
      "learning_rate": 2.8e-05,
      "loss": 6.4387,
      "step": 7000
    },
    {
      "epoch": 6.29,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 6.4264,
      "step": 8000
    },
    {
      "epoch": 7.08,
      "learning_rate": 3.6e-05,
      "loss": 6.4217,
      "step": 9000
    },
    {
      "epoch": 7.87,
      "learning_rate": 4e-05,
      "loss": 6.4154,
      "step": 10000
    },
    {
      "epoch": 8.65,
      "learning_rate": 3.955555555555556e-05,
      "loss": 6.4112,
      "step": 11000
    },
    {
      "epoch": 9.44,
      "learning_rate": 3.9111111111111115e-05,
      "loss": 6.408,
      "step": 12000
    },
    {
      "epoch": 10.23,
      "learning_rate": 3.866666666666667e-05,
      "loss": 6.4051,
      "step": 13000
    },
    {
      "epoch": 11.01,
      "learning_rate": 3.8222222222222226e-05,
      "loss": 6.4045,
      "step": 14000
    },
    {
      "epoch": 11.8,
      "learning_rate": 3.777777777777778e-05,
      "loss": 6.3991,
      "step": 15000
    },
    {
      "epoch": 12.59,
      "learning_rate": 3.733333333333334e-05,
      "loss": 6.3983,
      "step": 16000
    },
    {
      "epoch": 13.38,
      "learning_rate": 3.6888888888888896e-05,
      "loss": 6.3853,
      "step": 17000
    },
    {
      "epoch": 14.16,
      "learning_rate": 3.644444444444445e-05,
      "loss": 6.2985,
      "step": 18000
    },
    {
      "epoch": 14.95,
      "learning_rate": 3.6e-05,
      "loss": 6.2514,
      "step": 19000
    },
    {
      "epoch": 15.74,
      "learning_rate": 3.555555555555555e-05,
      "loss": 6.2058,
      "step": 20000
    },
    {
      "epoch": 16.52,
      "learning_rate": 3.511111111111111e-05,
      "loss": 6.1647,
      "step": 21000
    },
    {
      "epoch": 17.31,
      "learning_rate": 3.466666666666667e-05,
      "loss": 6.1212,
      "step": 22000
    },
    {
      "epoch": 18.1,
      "learning_rate": 3.4222222222222224e-05,
      "loss": 6.0786,
      "step": 23000
    },
    {
      "epoch": 18.88,
      "learning_rate": 3.377777777777778e-05,
      "loss": 6.033,
      "step": 24000
    },
    {
      "epoch": 19.67,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.9848,
      "step": 25000
    },
    {
      "epoch": 20.46,
      "learning_rate": 3.288888888888889e-05,
      "loss": 5.9115,
      "step": 26000
    },
    {
      "epoch": 21.24,
      "learning_rate": 3.2444444444444446e-05,
      "loss": 5.8206,
      "step": 27000
    },
    {
      "epoch": 22.03,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 5.7035,
      "step": 28000
    },
    {
      "epoch": 22.82,
      "learning_rate": 3.155555555555556e-05,
      "loss": 5.5902,
      "step": 29000
    },
    {
      "epoch": 23.6,
      "learning_rate": 3.111111111111112e-05,
      "loss": 5.5141,
      "step": 30000
    },
    {
      "epoch": 24.39,
      "learning_rate": 3.066666666666667e-05,
      "loss": 5.4631,
      "step": 31000
    },
    {
      "epoch": 25.18,
      "learning_rate": 3.0222222222222225e-05,
      "loss": 5.42,
      "step": 32000
    },
    {
      "epoch": 25.96,
      "learning_rate": 2.977777777777778e-05,
      "loss": 5.3857,
      "step": 33000
    },
    {
      "epoch": 26.75,
      "learning_rate": 2.9333333333333333e-05,
      "loss": 5.3598,
      "step": 34000
    },
    {
      "epoch": 27.54,
      "learning_rate": 2.888888888888889e-05,
      "loss": 5.3325,
      "step": 35000
    },
    {
      "epoch": 28.32,
      "learning_rate": 2.8444444444444447e-05,
      "loss": 5.3111,
      "step": 36000
    },
    {
      "epoch": 29.11,
      "learning_rate": 2.8e-05,
      "loss": 5.2939,
      "step": 37000
    },
    {
      "epoch": 29.9,
      "learning_rate": 2.755555555555556e-05,
      "loss": 5.2756,
      "step": 38000
    },
    {
      "epoch": 30.68,
      "learning_rate": 2.7111111111111114e-05,
      "loss": 5.2598,
      "step": 39000
    },
    {
      "epoch": 31.47,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 5.2473,
      "step": 40000
    },
    {
      "epoch": 32.26,
      "learning_rate": 2.6222222222222226e-05,
      "loss": 5.2321,
      "step": 41000
    },
    {
      "epoch": 33.04,
      "learning_rate": 2.577777777777778e-05,
      "loss": 5.2204,
      "step": 42000
    },
    {
      "epoch": 33.83,
      "learning_rate": 2.5333333333333334e-05,
      "loss": 5.2083,
      "step": 43000
    },
    {
      "epoch": 34.62,
      "learning_rate": 2.4888888888888893e-05,
      "loss": 5.1969,
      "step": 44000
    },
    {
      "epoch": 35.41,
      "learning_rate": 2.444444444444445e-05,
      "loss": 5.1874,
      "step": 45000
    },
    {
      "epoch": 36.19,
      "learning_rate": 2.4e-05,
      "loss": 5.1779,
      "step": 46000
    },
    {
      "epoch": 36.98,
      "learning_rate": 2.355555555555556e-05,
      "loss": 5.169,
      "step": 47000
    },
    {
      "epoch": 37.77,
      "learning_rate": 2.3111111111111112e-05,
      "loss": 5.1576,
      "step": 48000
    },
    {
      "epoch": 38.55,
      "learning_rate": 2.2666666666666668e-05,
      "loss": 5.1496,
      "step": 49000
    },
    {
      "epoch": 39.34,
      "learning_rate": 2.2222222222222227e-05,
      "loss": 5.1417,
      "step": 50000
    },
    {
      "epoch": 40.13,
      "learning_rate": 2.177777777777778e-05,
      "loss": 5.1343,
      "step": 51000
    },
    {
      "epoch": 40.91,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 5.126,
      "step": 52000
    },
    {
      "epoch": 41.7,
      "learning_rate": 2.088888888888889e-05,
      "loss": 5.1197,
      "step": 53000
    },
    {
      "epoch": 42.49,
      "learning_rate": 2.0444444444444446e-05,
      "loss": 5.1117,
      "step": 54000
    },
    {
      "epoch": 43.27,
      "learning_rate": 2e-05,
      "loss": 5.1062,
      "step": 55000
    },
    {
      "epoch": 44.06,
      "learning_rate": 1.9555555555555557e-05,
      "loss": 5.1002,
      "step": 56000
    },
    {
      "epoch": 44.85,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 5.0936,
      "step": 57000
    },
    {
      "epoch": 45.63,
      "learning_rate": 1.866666666666667e-05,
      "loss": 5.0886,
      "step": 58000
    },
    {
      "epoch": 46.42,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 5.0812,
      "step": 59000
    },
    {
      "epoch": 47.21,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 5.076,
      "step": 60000
    },
    {
      "epoch": 47.99,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 5.0713,
      "step": 61000
    },
    {
      "epoch": 48.78,
      "learning_rate": 1.688888888888889e-05,
      "loss": 5.0654,
      "step": 62000
    },
    {
      "epoch": 49.57,
      "learning_rate": 1.6444444444444444e-05,
      "loss": 5.0619,
      "step": 63000
    },
    {
      "epoch": 50.35,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 5.0582,
      "step": 64000
    },
    {
      "epoch": 51.14,
      "learning_rate": 1.555555555555556e-05,
      "loss": 5.0543,
      "step": 65000
    },
    {
      "epoch": 51.93,
      "learning_rate": 1.5111111111111112e-05,
      "loss": 5.0475,
      "step": 66000
    },
    {
      "epoch": 52.71,
      "learning_rate": 1.4666666666666666e-05,
      "loss": 5.0462,
      "step": 67000
    },
    {
      "epoch": 53.5,
      "learning_rate": 1.4222222222222224e-05,
      "loss": 5.0407,
      "step": 68000
    },
    {
      "epoch": 54.29,
      "learning_rate": 1.377777777777778e-05,
      "loss": 5.0375,
      "step": 69000
    },
    {
      "epoch": 55.07,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 5.0358,
      "step": 70000
    },
    {
      "epoch": 55.86,
      "learning_rate": 1.288888888888889e-05,
      "loss": 5.0314,
      "step": 71000
    },
    {
      "epoch": 56.65,
      "learning_rate": 1.2444444444444446e-05,
      "loss": 5.0289,
      "step": 72000
    },
    {
      "epoch": 57.44,
      "learning_rate": 1.2e-05,
      "loss": 5.0233,
      "step": 73000
    },
    {
      "epoch": 58.22,
      "learning_rate": 1.1555555555555556e-05,
      "loss": 5.0236,
      "step": 74000
    },
    {
      "epoch": 59.01,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 5.0205,
      "step": 75000
    },
    {
      "epoch": 59.8,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 5.0158,
      "step": 76000
    },
    {
      "epoch": 60.58,
      "learning_rate": 1.0222222222222223e-05,
      "loss": 5.0162,
      "step": 77000
    },
    {
      "epoch": 61.37,
      "learning_rate": 9.777777777777779e-06,
      "loss": 5.0151,
      "step": 78000
    },
    {
      "epoch": 62.16,
      "learning_rate": 9.333333333333334e-06,
      "loss": 5.0086,
      "step": 79000
    },
    {
      "epoch": 62.94,
      "learning_rate": 8.888888888888888e-06,
      "loss": 5.0071,
      "step": 80000
    },
    {
      "epoch": 63.73,
      "learning_rate": 8.444444444444446e-06,
      "loss": 5.0072,
      "step": 81000
    },
    {
      "epoch": 64.52,
      "learning_rate": 8.000000000000001e-06,
      "loss": 5.0045,
      "step": 82000
    },
    {
      "epoch": 65.3,
      "learning_rate": 7.555555555555556e-06,
      "loss": 5.0023,
      "step": 83000
    },
    {
      "epoch": 66.09,
      "learning_rate": 7.111111111111112e-06,
      "loss": 4.9999,
      "step": 84000
    },
    {
      "epoch": 66.88,
      "learning_rate": 6.666666666666667e-06,
      "loss": 4.9992,
      "step": 85000
    },
    {
      "epoch": 67.66,
      "learning_rate": 6.222222222222223e-06,
      "loss": 4.9952,
      "step": 86000
    },
    {
      "epoch": 68.45,
      "learning_rate": 5.777777777777778e-06,
      "loss": 4.9966,
      "step": 87000
    },
    {
      "epoch": 69.24,
      "learning_rate": 5.333333333333334e-06,
      "loss": 4.9933,
      "step": 88000
    },
    {
      "epoch": 70.02,
      "learning_rate": 4.888888888888889e-06,
      "loss": 4.9929,
      "step": 89000
    },
    {
      "epoch": 70.81,
      "learning_rate": 4.444444444444444e-06,
      "loss": 4.9919,
      "step": 90000
    },
    {
      "epoch": 71.6,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.9906,
      "step": 91000
    },
    {
      "epoch": 72.38,
      "learning_rate": 3.555555555555556e-06,
      "loss": 4.9906,
      "step": 92000
    },
    {
      "epoch": 73.17,
      "learning_rate": 3.1111111111111116e-06,
      "loss": 4.989,
      "step": 93000
    },
    {
      "epoch": 73.96,
      "learning_rate": 2.666666666666667e-06,
      "loss": 4.9887,
      "step": 94000
    },
    {
      "epoch": 74.74,
      "learning_rate": 2.222222222222222e-06,
      "loss": 4.9874,
      "step": 95000
    },
    {
      "epoch": 75.53,
      "learning_rate": 1.777777777777778e-06,
      "loss": 4.9883,
      "step": 96000
    },
    {
      "epoch": 76.32,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 4.984,
      "step": 97000
    },
    {
      "epoch": 77.1,
      "learning_rate": 8.88888888888889e-07,
      "loss": 4.9851,
      "step": 98000
    },
    {
      "epoch": 77.89,
      "learning_rate": 4.444444444444445e-07,
      "loss": 4.9855,
      "step": 99000
    },
    {
      "epoch": 78.68,
      "learning_rate": 0.0,
      "loss": 4.9836,
      "step": 100000
    },
    {
      "epoch": 78.68,
      "step": 100000,
      "total_flos": 2.020789500111749e+19,
      "train_loss": 5.453042978515625,
      "train_runtime": 84100.8462,
      "train_samples_per_second": 913.189,
      "train_steps_per_second": 1.189
    }
  ],
  "logging_steps": 1000,
  "max_steps": 100000,
  "num_train_epochs": 79,
  "save_steps": 1000,
  "total_flos": 2.020789500111749e+19,
  "trial_name": null,
  "trial_params": null
}