{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 72.09805335255948,
  "eval_steps": 500,
  "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.72,
      "learning_rate": 4.000000000000001e-06,
      "loss": 6.9233,
      "step": 1000
    },
    {
      "epoch": 1.44,
      "learning_rate": 8.000000000000001e-06,
      "loss": 6.1457,
      "step": 2000
    },
    {
      "epoch": 2.16,
      "learning_rate": 1.2e-05,
      "loss": 6.0352,
      "step": 3000
    },
    {
      "epoch": 2.88,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 5.9933,
      "step": 4000
    },
    {
      "epoch": 3.6,
      "learning_rate": 2e-05,
      "loss": 5.973,
      "step": 5000
    },
    {
      "epoch": 4.33,
      "learning_rate": 2.4e-05,
      "loss": 5.9614,
      "step": 6000
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.8e-05,
      "loss": 5.9541,
      "step": 7000
    },
    {
      "epoch": 5.77,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 5.9456,
      "step": 8000
    },
    {
      "epoch": 6.49,
      "learning_rate": 3.6e-05,
      "loss": 5.9431,
      "step": 9000
    },
    {
      "epoch": 7.21,
      "learning_rate": 4e-05,
      "loss": 5.9381,
      "step": 10000
    },
    {
      "epoch": 7.93,
      "learning_rate": 3.955555555555556e-05,
      "loss": 5.9346,
      "step": 11000
    },
    {
      "epoch": 8.65,
      "learning_rate": 3.9111111111111115e-05,
      "loss": 5.9317,
      "step": 12000
    },
    {
      "epoch": 9.37,
      "learning_rate": 3.866666666666667e-05,
      "loss": 5.9301,
      "step": 13000
    },
    {
      "epoch": 10.09,
      "learning_rate": 3.8222222222222226e-05,
      "loss": 5.929,
      "step": 14000
    },
    {
      "epoch": 10.81,
      "learning_rate": 3.777777777777778e-05,
      "loss": 5.8828,
      "step": 15000
    },
    {
      "epoch": 11.54,
      "learning_rate": 3.733333333333334e-05,
      "loss": 5.8159,
      "step": 16000
    },
    {
      "epoch": 12.26,
      "learning_rate": 3.6888888888888896e-05,
      "loss": 5.7662,
      "step": 17000
    },
    {
      "epoch": 12.98,
      "learning_rate": 3.644444444444445e-05,
      "loss": 5.7179,
      "step": 18000
    },
    {
      "epoch": 13.7,
      "learning_rate": 3.6e-05,
      "loss": 5.6688,
      "step": 19000
    },
    {
      "epoch": 14.42,
      "learning_rate": 3.555555555555555e-05,
      "loss": 5.6191,
      "step": 20000
    },
    {
      "epoch": 15.14,
      "learning_rate": 3.511111111111111e-05,
      "loss": 5.5682,
      "step": 21000
    },
    {
      "epoch": 15.86,
      "learning_rate": 3.466666666666667e-05,
      "loss": 5.499,
      "step": 22000
    },
    {
      "epoch": 16.58,
      "learning_rate": 3.4222222222222224e-05,
      "loss": 5.3804,
      "step": 23000
    },
    {
      "epoch": 17.3,
      "learning_rate": 3.377777777777778e-05,
      "loss": 5.2307,
      "step": 24000
    },
    {
      "epoch": 18.02,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.114,
      "step": 25000
    },
    {
      "epoch": 18.75,
      "learning_rate": 3.288888888888889e-05,
      "loss": 5.0386,
      "step": 26000
    },
    {
      "epoch": 19.47,
      "learning_rate": 3.2444444444444446e-05,
      "loss": 4.9856,
      "step": 27000
    },
    {
      "epoch": 20.19,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 4.9475,
      "step": 28000
    },
    {
      "epoch": 20.91,
      "learning_rate": 3.155555555555556e-05,
      "loss": 4.9154,
      "step": 29000
    },
    {
      "epoch": 21.63,
      "learning_rate": 3.111111111111112e-05,
      "loss": 4.8895,
      "step": 30000
    },
    {
      "epoch": 22.35,
      "learning_rate": 3.066666666666667e-05,
      "loss": 4.8653,
      "step": 31000
    },
    {
      "epoch": 23.07,
      "learning_rate": 3.0222222222222225e-05,
      "loss": 4.8486,
      "step": 32000
    },
    {
      "epoch": 23.79,
      "learning_rate": 2.977777777777778e-05,
      "loss": 4.829,
      "step": 33000
    },
    {
      "epoch": 24.51,
      "learning_rate": 2.9333333333333333e-05,
      "loss": 4.8145,
      "step": 34000
    },
    {
      "epoch": 25.23,
      "learning_rate": 2.888888888888889e-05,
      "loss": 4.8005,
      "step": 35000
    },
    {
      "epoch": 25.96,
      "learning_rate": 2.8444444444444447e-05,
      "loss": 4.7862,
      "step": 36000
    },
    {
      "epoch": 26.68,
      "learning_rate": 2.8e-05,
      "loss": 4.7725,
      "step": 37000
    },
    {
      "epoch": 27.4,
      "learning_rate": 2.755555555555556e-05,
      "loss": 4.7609,
      "step": 38000
    },
    {
      "epoch": 28.12,
      "learning_rate": 2.7111111111111114e-05,
      "loss": 4.7488,
      "step": 39000
    },
    {
      "epoch": 28.84,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 4.7398,
      "step": 40000
    },
    {
      "epoch": 29.56,
      "learning_rate": 2.6222222222222226e-05,
      "loss": 4.7291,
      "step": 41000
    },
    {
      "epoch": 30.28,
      "learning_rate": 2.577777777777778e-05,
      "loss": 4.7198,
      "step": 42000
    },
    {
      "epoch": 31.0,
      "learning_rate": 2.5333333333333334e-05,
      "loss": 4.7099,
      "step": 43000
    },
    {
      "epoch": 31.72,
      "learning_rate": 2.4888888888888893e-05,
      "loss": 4.7025,
      "step": 44000
    },
    {
      "epoch": 32.44,
      "learning_rate": 2.444444444444445e-05,
      "loss": 4.6943,
      "step": 45000
    },
    {
      "epoch": 33.17,
      "learning_rate": 2.4e-05,
      "loss": 4.687,
      "step": 46000
    },
    {
      "epoch": 33.89,
      "learning_rate": 2.355555555555556e-05,
      "loss": 4.6807,
      "step": 47000
    },
    {
      "epoch": 34.61,
      "learning_rate": 2.3111111111111112e-05,
      "loss": 4.6732,
      "step": 48000
    },
    {
      "epoch": 35.33,
      "learning_rate": 2.2666666666666668e-05,
      "loss": 4.6672,
      "step": 49000
    },
    {
      "epoch": 36.05,
      "learning_rate": 2.2222222222222227e-05,
      "loss": 4.6603,
      "step": 50000
    },
    {
      "epoch": 36.77,
      "learning_rate": 2.177777777777778e-05,
      "loss": 4.6536,
      "step": 51000
    },
    {
      "epoch": 37.49,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 4.6498,
      "step": 52000
    },
    {
      "epoch": 38.21,
      "learning_rate": 2.088888888888889e-05,
      "loss": 4.6425,
      "step": 53000
    },
    {
      "epoch": 38.93,
      "learning_rate": 2.0444444444444446e-05,
      "loss": 4.6388,
      "step": 54000
    },
    {
      "epoch": 39.65,
      "learning_rate": 2e-05,
      "loss": 4.6321,
      "step": 55000
    },
    {
      "epoch": 40.37,
      "learning_rate": 1.9555555555555557e-05,
      "loss": 4.6309,
      "step": 56000
    },
    {
      "epoch": 41.1,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 4.624,
      "step": 57000
    },
    {
      "epoch": 41.82,
      "learning_rate": 1.866666666666667e-05,
      "loss": 4.6209,
      "step": 58000
    },
    {
      "epoch": 42.54,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 4.6145,
      "step": 59000
    },
    {
      "epoch": 43.26,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 4.6126,
      "step": 60000
    },
    {
      "epoch": 43.98,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 4.6061,
      "step": 61000
    },
    {
      "epoch": 44.7,
      "learning_rate": 1.688888888888889e-05,
      "loss": 4.6019,
      "step": 62000
    },
    {
      "epoch": 45.42,
      "learning_rate": 1.6444444444444444e-05,
      "loss": 4.6019,
      "step": 63000
    },
    {
      "epoch": 46.14,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 4.5961,
      "step": 64000
    },
    {
      "epoch": 46.86,
      "learning_rate": 1.555555555555556e-05,
      "loss": 4.5941,
      "step": 65000
    },
    {
      "epoch": 47.58,
      "learning_rate": 1.5111111111111112e-05,
      "loss": 4.589,
      "step": 66000
    },
    {
      "epoch": 48.31,
      "learning_rate": 1.4666666666666666e-05,
      "loss": 4.5869,
      "step": 67000
    },
    {
      "epoch": 49.03,
      "learning_rate": 1.4222222222222224e-05,
      "loss": 4.5842,
      "step": 68000
    },
    {
      "epoch": 49.75,
      "learning_rate": 1.377777777777778e-05,
      "loss": 4.5802,
      "step": 69000
    },
    {
      "epoch": 50.47,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 4.5787,
      "step": 70000
    },
    {
      "epoch": 51.19,
      "learning_rate": 1.288888888888889e-05,
      "loss": 4.575,
      "step": 71000
    },
    {
      "epoch": 51.91,
      "learning_rate": 1.2444444444444446e-05,
      "loss": 4.5723,
      "step": 72000
    },
    {
      "epoch": 52.63,
      "learning_rate": 1.2e-05,
      "loss": 4.5706,
      "step": 73000
    },
    {
      "epoch": 53.35,
      "learning_rate": 1.1555555555555556e-05,
      "loss": 4.569,
      "step": 74000
    },
    {
      "epoch": 54.07,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 4.5666,
      "step": 75000
    },
    {
      "epoch": 54.79,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 4.5636,
      "step": 76000
    },
    {
      "epoch": 55.52,
      "learning_rate": 1.0222222222222223e-05,
      "loss": 4.5621,
      "step": 77000
    },
    {
      "epoch": 56.24,
      "learning_rate": 9.777777777777779e-06,
      "loss": 4.5621,
      "step": 78000
    },
    {
      "epoch": 56.96,
      "learning_rate": 9.333333333333334e-06,
      "loss": 4.5574,
      "step": 79000
    },
    {
      "epoch": 57.68,
      "learning_rate": 8.888888888888888e-06,
      "loss": 4.556,
      "step": 80000
    },
    {
      "epoch": 58.4,
      "learning_rate": 8.444444444444446e-06,
      "loss": 4.5554,
      "step": 81000
    },
    {
      "epoch": 59.12,
      "learning_rate": 8.000000000000001e-06,
      "loss": 4.5527,
      "step": 82000
    },
    {
      "epoch": 59.84,
      "learning_rate": 7.555555555555556e-06,
      "loss": 4.5526,
      "step": 83000
    },
    {
      "epoch": 60.56,
      "learning_rate": 7.111111111111112e-06,
      "loss": 4.5497,
      "step": 84000
    },
    {
      "epoch": 61.28,
      "learning_rate": 6.666666666666667e-06,
      "loss": 4.5482,
      "step": 85000
    },
    {
      "epoch": 62.0,
      "learning_rate": 6.222222222222223e-06,
      "loss": 4.5468,
      "step": 86000
    },
    {
      "epoch": 62.73,
      "learning_rate": 5.777777777777778e-06,
      "loss": 4.5456,
      "step": 87000
    },
    {
      "epoch": 63.45,
      "learning_rate": 5.333333333333334e-06,
      "loss": 4.5456,
      "step": 88000
    },
    {
      "epoch": 64.17,
      "learning_rate": 4.888888888888889e-06,
      "loss": 4.5435,
      "step": 89000
    },
    {
      "epoch": 64.89,
      "learning_rate": 4.444444444444444e-06,
      "loss": 4.5432,
      "step": 90000
    },
    {
      "epoch": 65.61,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.5416,
      "step": 91000
    },
    {
      "epoch": 66.33,
      "learning_rate": 3.555555555555556e-06,
      "loss": 4.5417,
      "step": 92000
    },
    {
      "epoch": 67.05,
      "learning_rate": 3.1111111111111116e-06,
      "loss": 4.5401,
      "step": 93000
    },
    {
      "epoch": 67.77,
      "learning_rate": 2.666666666666667e-06,
      "loss": 4.541,
      "step": 94000
    },
    {
      "epoch": 68.49,
      "learning_rate": 2.222222222222222e-06,
      "loss": 4.5386,
      "step": 95000
    },
    {
      "epoch": 69.21,
      "learning_rate": 1.777777777777778e-06,
      "loss": 4.5391,
      "step": 96000
    },
    {
      "epoch": 69.94,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 4.5365,
      "step": 97000
    },
    {
      "epoch": 70.66,
      "learning_rate": 8.88888888888889e-07,
      "loss": 4.5364,
      "step": 98000
    },
    {
      "epoch": 71.38,
      "learning_rate": 4.444444444444445e-07,
      "loss": 4.5384,
      "step": 99000
    },
    {
      "epoch": 72.1,
      "learning_rate": 0.0,
      "loss": 4.5359,
      "step": 100000
    },
    {
      "epoch": 72.1,
      "step": 100000,
      "total_flos": 2.020741224679342e+19,
      "train_loss": 2.8993955859375,
      "train_runtime": 51887.7803,
      "train_samples_per_second": 1480.117,
      "train_steps_per_second": 1.927
    }
  ],
  "logging_steps": 1000,
  "max_steps": 100000,
  "num_train_epochs": 73,
  "save_steps": 1000,
  "total_flos": 2.020741224679342e+19,
  "trial_name": null,
  "trial_params": null
}