{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 78.125,
  "eval_steps": 500,
  "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.78,
      "learning_rate": 4.000000000000001e-06,
      "loss": 7.5832,
      "step": 1000
    },
    {
      "epoch": 1.56,
      "learning_rate": 8.000000000000001e-06,
      "loss": 6.9724,
      "step": 2000
    },
    {
      "epoch": 2.34,
      "learning_rate": 1.2e-05,
      "loss": 6.7695,
      "step": 3000
    },
    {
      "epoch": 3.12,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 6.7002,
      "step": 4000
    },
    {
      "epoch": 3.91,
      "learning_rate": 2e-05,
      "loss": 6.666,
      "step": 5000
    },
    {
      "epoch": 4.69,
      "learning_rate": 2.4e-05,
      "loss": 6.6503,
      "step": 6000
    },
    {
      "epoch": 5.47,
      "learning_rate": 2.8e-05,
      "loss": 6.6407,
      "step": 7000
    },
    {
      "epoch": 6.25,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 6.6277,
      "step": 8000
    },
    {
      "epoch": 7.03,
      "learning_rate": 3.6e-05,
      "loss": 6.6209,
      "step": 9000
    },
    {
      "epoch": 7.81,
      "learning_rate": 4e-05,
      "loss": 6.6135,
      "step": 10000
    },
    {
      "epoch": 8.59,
      "learning_rate": 3.955555555555556e-05,
      "loss": 6.6084,
      "step": 11000
    },
    {
      "epoch": 9.38,
      "learning_rate": 3.9111111111111115e-05,
      "loss": 6.6041,
      "step": 12000
    },
    {
      "epoch": 10.16,
      "learning_rate": 3.866666666666667e-05,
      "loss": 6.6013,
      "step": 13000
    },
    {
      "epoch": 10.94,
      "learning_rate": 3.8222222222222226e-05,
      "loss": 6.5994,
      "step": 14000
    },
    {
      "epoch": 11.72,
      "learning_rate": 3.777777777777778e-05,
      "loss": 6.594,
      "step": 15000
    },
    {
      "epoch": 12.5,
      "learning_rate": 3.733333333333334e-05,
      "loss": 6.5925,
      "step": 16000
    },
    {
      "epoch": 13.28,
      "learning_rate": 3.6888888888888896e-05,
      "loss": 6.5893,
      "step": 17000
    },
    {
      "epoch": 14.06,
      "learning_rate": 3.644444444444445e-05,
      "loss": 6.5875,
      "step": 18000
    },
    {
      "epoch": 14.84,
      "learning_rate": 3.6e-05,
      "loss": 6.5232,
      "step": 19000
    },
    {
      "epoch": 15.62,
      "learning_rate": 3.555555555555555e-05,
      "loss": 6.4358,
      "step": 20000
    },
    {
      "epoch": 16.41,
      "learning_rate": 3.511111111111111e-05,
      "loss": 6.3712,
      "step": 21000
    },
    {
      "epoch": 17.19,
      "learning_rate": 3.466666666666667e-05,
      "loss": 6.311,
      "step": 22000
    },
    {
      "epoch": 17.97,
      "learning_rate": 3.4222222222222224e-05,
      "loss": 6.2493,
      "step": 23000
    },
    {
      "epoch": 18.75,
      "learning_rate": 3.377777777777778e-05,
      "loss": 6.1597,
      "step": 24000
    },
    {
      "epoch": 19.53,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 6.0276,
      "step": 25000
    },
    {
      "epoch": 20.31,
      "learning_rate": 3.288888888888889e-05,
      "loss": 5.8317,
      "step": 26000
    },
    {
      "epoch": 21.09,
      "learning_rate": 3.2444444444444446e-05,
      "loss": 5.6782,
      "step": 27000
    },
    {
      "epoch": 21.88,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 5.5975,
      "step": 28000
    },
    {
      "epoch": 22.66,
      "learning_rate": 3.155555555555556e-05,
      "loss": 5.5369,
      "step": 29000
    },
    {
      "epoch": 23.44,
      "learning_rate": 3.111111111111112e-05,
      "loss": 5.4921,
      "step": 30000
    },
    {
      "epoch": 24.22,
      "learning_rate": 3.066666666666667e-05,
      "loss": 5.4554,
      "step": 31000
    },
    {
      "epoch": 25.0,
      "learning_rate": 3.0222222222222225e-05,
      "loss": 5.4237,
      "step": 32000
    },
    {
      "epoch": 25.78,
      "learning_rate": 2.977777777777778e-05,
      "loss": 5.3938,
      "step": 33000
    },
    {
      "epoch": 26.56,
      "learning_rate": 2.9333333333333333e-05,
      "loss": 5.3701,
      "step": 34000
    },
    {
      "epoch": 27.34,
      "learning_rate": 2.888888888888889e-05,
      "loss": 5.3452,
      "step": 35000
    },
    {
      "epoch": 28.12,
      "learning_rate": 2.8444444444444447e-05,
      "loss": 5.327,
      "step": 36000
    },
    {
      "epoch": 28.91,
      "learning_rate": 2.8e-05,
      "loss": 5.3063,
      "step": 37000
    },
    {
      "epoch": 29.69,
      "learning_rate": 2.755555555555556e-05,
      "loss": 5.2905,
      "step": 38000
    },
    {
      "epoch": 30.47,
      "learning_rate": 2.7111111111111114e-05,
      "loss": 5.2747,
      "step": 39000
    },
    {
      "epoch": 31.25,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 5.2596,
      "step": 40000
    },
    {
      "epoch": 32.03,
      "learning_rate": 2.6222222222222226e-05,
      "loss": 5.2483,
      "step": 41000
    },
    {
      "epoch": 32.81,
      "learning_rate": 2.577777777777778e-05,
      "loss": 5.2336,
      "step": 42000
    },
    {
      "epoch": 33.59,
      "learning_rate": 2.5333333333333334e-05,
      "loss": 5.2214,
      "step": 43000
    },
    {
      "epoch": 34.38,
      "learning_rate": 2.4888888888888893e-05,
      "loss": 5.2103,
      "step": 44000
    },
    {
      "epoch": 35.16,
      "learning_rate": 2.444444444444445e-05,
      "loss": 5.2015,
      "step": 45000
    },
    {
      "epoch": 35.94,
      "learning_rate": 2.4e-05,
      "loss": 5.1907,
      "step": 46000
    },
    {
      "epoch": 36.72,
      "learning_rate": 2.355555555555556e-05,
      "loss": 5.1801,
      "step": 47000
    },
    {
      "epoch": 37.5,
      "learning_rate": 2.3111111111111112e-05,
      "loss": 5.1713,
      "step": 48000
    },
    {
      "epoch": 38.28,
      "learning_rate": 2.2666666666666668e-05,
      "loss": 5.1645,
      "step": 49000
    },
    {
      "epoch": 39.06,
      "learning_rate": 2.2222222222222227e-05,
      "loss": 5.1548,
      "step": 50000
    },
    {
      "epoch": 39.84,
      "learning_rate": 2.177777777777778e-05,
      "loss": 5.1462,
      "step": 51000
    },
    {
      "epoch": 40.62,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 5.1417,
      "step": 52000
    },
    {
      "epoch": 41.41,
      "learning_rate": 2.088888888888889e-05,
      "loss": 5.1305,
      "step": 53000
    },
    {
      "epoch": 42.19,
      "learning_rate": 2.0444444444444446e-05,
      "loss": 5.1287,
      "step": 54000
    },
    {
      "epoch": 42.97,
      "learning_rate": 2e-05,
      "loss": 5.1202,
      "step": 55000
    },
    {
      "epoch": 43.75,
      "learning_rate": 1.9555555555555557e-05,
      "loss": 5.1139,
      "step": 56000
    },
    {
      "epoch": 44.53,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 5.1081,
      "step": 57000
    },
    {
      "epoch": 45.31,
      "learning_rate": 1.866666666666667e-05,
      "loss": 5.1032,
      "step": 58000
    },
    {
      "epoch": 46.09,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 5.0968,
      "step": 59000
    },
    {
      "epoch": 46.88,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 5.0914,
      "step": 60000
    },
    {
      "epoch": 47.66,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 5.085,
      "step": 61000
    },
    {
      "epoch": 48.44,
      "learning_rate": 1.688888888888889e-05,
      "loss": 5.0806,
      "step": 62000
    },
    {
      "epoch": 49.22,
      "learning_rate": 1.6444444444444444e-05,
      "loss": 5.0769,
      "step": 63000
    },
    {
      "epoch": 50.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 5.0728,
      "step": 64000
    },
    {
      "epoch": 50.78,
      "learning_rate": 1.555555555555556e-05,
      "loss": 5.0692,
      "step": 65000
    },
    {
      "epoch": 51.56,
      "learning_rate": 1.5111111111111112e-05,
      "loss": 5.065,
      "step": 66000
    },
    {
      "epoch": 52.34,
      "learning_rate": 1.4666666666666666e-05,
      "loss": 5.0594,
      "step": 67000
    },
    {
      "epoch": 53.12,
      "learning_rate": 1.4222222222222224e-05,
      "loss": 5.0549,
      "step": 68000
    },
    {
      "epoch": 53.91,
      "learning_rate": 1.377777777777778e-05,
      "loss": 5.0538,
      "step": 69000
    },
    {
      "epoch": 54.69,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 5.0482,
      "step": 70000
    },
    {
      "epoch": 55.47,
      "learning_rate": 1.288888888888889e-05,
      "loss": 5.0475,
      "step": 71000
    },
    {
      "epoch": 56.25,
      "learning_rate": 1.2444444444444446e-05,
      "loss": 5.0399,
      "step": 72000
    },
    {
      "epoch": 57.03,
      "learning_rate": 1.2e-05,
      "loss": 5.0406,
      "step": 73000
    },
    {
      "epoch": 57.81,
      "learning_rate": 1.1555555555555556e-05,
      "loss": 5.037,
      "step": 74000
    },
    {
      "epoch": 58.59,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 5.0326,
      "step": 75000
    },
    {
      "epoch": 59.38,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 5.031,
      "step": 76000
    },
    {
      "epoch": 60.16,
      "learning_rate": 1.0222222222222223e-05,
      "loss": 5.0291,
      "step": 77000
    },
    {
      "epoch": 60.94,
      "learning_rate": 9.777777777777779e-06,
      "loss": 5.0266,
      "step": 78000
    },
    {
      "epoch": 61.72,
      "learning_rate": 9.333333333333334e-06,
      "loss": 5.0235,
      "step": 79000
    },
    {
      "epoch": 62.5,
      "learning_rate": 8.888888888888888e-06,
      "loss": 5.0211,
      "step": 80000
    },
    {
      "epoch": 63.28,
      "learning_rate": 8.444444444444446e-06,
      "loss": 5.0214,
      "step": 81000
    },
    {
      "epoch": 64.06,
      "learning_rate": 8.000000000000001e-06,
      "loss": 5.0176,
      "step": 82000
    },
    {
      "epoch": 64.84,
      "learning_rate": 7.555555555555556e-06,
      "loss": 5.0157,
      "step": 83000
    },
    {
      "epoch": 65.62,
      "learning_rate": 7.111111111111112e-06,
      "loss": 5.014,
      "step": 84000
    },
    {
      "epoch": 66.41,
      "learning_rate": 6.666666666666667e-06,
      "loss": 5.0115,
      "step": 85000
    },
    {
      "epoch": 67.19,
      "learning_rate": 6.222222222222223e-06,
      "loss": 5.0087,
      "step": 86000
    },
    {
      "epoch": 67.97,
      "learning_rate": 5.777777777777778e-06,
      "loss": 5.0105,
      "step": 87000
    },
    {
      "epoch": 68.75,
      "learning_rate": 5.333333333333334e-06,
      "loss": 5.0062,
      "step": 88000
    },
    {
      "epoch": 69.53,
      "learning_rate": 4.888888888888889e-06,
      "loss": 5.0028,
      "step": 89000
    },
    {
      "epoch": 70.31,
      "learning_rate": 4.444444444444444e-06,
      "loss": 5.0066,
      "step": 90000
    },
    {
      "epoch": 71.09,
      "learning_rate": 4.000000000000001e-06,
      "loss": 5.0032,
      "step": 91000
    },
    {
      "epoch": 71.88,
      "learning_rate": 3.555555555555556e-06,
      "loss": 5.0022,
      "step": 92000
    },
    {
      "epoch": 72.66,
      "learning_rate": 3.1111111111111116e-06,
      "loss": 5.0024,
      "step": 93000
    },
    {
      "epoch": 73.44,
      "learning_rate": 2.666666666666667e-06,
      "loss": 5.0007,
      "step": 94000
    },
    {
      "epoch": 74.22,
      "learning_rate": 2.222222222222222e-06,
      "loss": 5.0008,
      "step": 95000
    },
    {
      "epoch": 75.0,
      "learning_rate": 1.777777777777778e-06,
      "loss": 4.9978,
      "step": 96000
    },
    {
      "epoch": 75.78,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 4.9966,
      "step": 97000
    },
    {
      "epoch": 76.56,
      "learning_rate": 8.88888888888889e-07,
      "loss": 4.9994,
      "step": 98000
    },
    {
      "epoch": 77.34,
      "learning_rate": 4.444444444444445e-07,
      "loss": 4.9966,
      "step": 99000
    },
    {
      "epoch": 78.12,
      "learning_rate": 0.0,
      "loss": 4.9976,
      "step": 100000
    },
    {
      "epoch": 78.12,
      "step": 100000,
      "total_flos": 2.0208137237272986e+19,
      "train_loss": 5.5054574072265625,
      "train_runtime": 84130.9868,
      "train_samples_per_second": 912.862,
      "train_steps_per_second": 1.189
    }
  ],
  "logging_steps": 1000,
  "max_steps": 100000,
  "num_train_epochs": 79,
  "save_steps": 1000,
  "total_flos": 2.0208137237272986e+19,
  "trial_name": null,
  "trial_params": null
}