{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 75.9301442672741,
  "eval_steps": 500,
  "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.76,
      "learning_rate": 4.000000000000001e-06,
      "loss": 7.3387,
      "step": 1000
    },
    {
      "epoch": 1.52,
      "learning_rate": 8.000000000000001e-06,
      "loss": 6.4662,
      "step": 2000
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.2e-05,
      "loss": 6.3379,
      "step": 3000
    },
    {
      "epoch": 3.04,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 6.287,
      "step": 4000
    },
    {
      "epoch": 3.8,
      "learning_rate": 2e-05,
      "loss": 6.2594,
      "step": 5000
    },
    {
      "epoch": 4.56,
      "learning_rate": 2.4e-05,
      "loss": 6.2451,
      "step": 6000
    },
    {
      "epoch": 5.32,
      "learning_rate": 2.8e-05,
      "loss": 6.2351,
      "step": 7000
    },
    {
      "epoch": 6.07,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 6.2254,
      "step": 8000
    },
    {
      "epoch": 6.83,
      "learning_rate": 3.6e-05,
      "loss": 6.2211,
      "step": 9000
    },
    {
      "epoch": 7.59,
      "learning_rate": 4e-05,
      "loss": 6.215,
      "step": 10000
    },
    {
      "epoch": 8.35,
      "learning_rate": 3.955555555555556e-05,
      "loss": 6.2115,
      "step": 11000
    },
    {
      "epoch": 9.11,
      "learning_rate": 3.9111111111111115e-05,
      "loss": 6.2086,
      "step": 12000
    },
    {
      "epoch": 9.87,
      "learning_rate": 3.866666666666667e-05,
      "loss": 6.2057,
      "step": 13000
    },
    {
      "epoch": 10.63,
      "learning_rate": 3.8222222222222226e-05,
      "loss": 6.2055,
      "step": 14000
    },
    {
      "epoch": 11.39,
      "learning_rate": 3.777777777777778e-05,
      "loss": 6.2001,
      "step": 15000
    },
    {
      "epoch": 12.15,
      "learning_rate": 3.733333333333334e-05,
      "loss": 6.1979,
      "step": 16000
    },
    {
      "epoch": 12.91,
      "learning_rate": 3.6888888888888896e-05,
      "loss": 6.1258,
      "step": 17000
    },
    {
      "epoch": 13.67,
      "learning_rate": 3.644444444444445e-05,
      "loss": 6.0685,
      "step": 18000
    },
    {
      "epoch": 14.43,
      "learning_rate": 3.6e-05,
      "loss": 6.0221,
      "step": 19000
    },
    {
      "epoch": 15.19,
      "learning_rate": 3.555555555555555e-05,
      "loss": 5.9751,
      "step": 20000
    },
    {
      "epoch": 15.95,
      "learning_rate": 3.511111111111111e-05,
      "loss": 5.9314,
      "step": 21000
    },
    {
      "epoch": 16.7,
      "learning_rate": 3.466666666666667e-05,
      "loss": 5.8882,
      "step": 22000
    },
    {
      "epoch": 17.46,
      "learning_rate": 3.4222222222222224e-05,
      "loss": 5.8426,
      "step": 23000
    },
    {
      "epoch": 18.22,
      "learning_rate": 3.377777777777778e-05,
      "loss": 5.7933,
      "step": 24000
    },
    {
      "epoch": 18.98,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.7178,
      "step": 25000
    },
    {
      "epoch": 19.74,
      "learning_rate": 3.288888888888889e-05,
      "loss": 5.6193,
      "step": 26000
    },
    {
      "epoch": 20.5,
      "learning_rate": 3.2444444444444446e-05,
      "loss": 5.5022,
      "step": 27000
    },
    {
      "epoch": 21.26,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 5.3896,
      "step": 28000
    },
    {
      "epoch": 22.02,
      "learning_rate": 3.155555555555556e-05,
      "loss": 5.313,
      "step": 29000
    },
    {
      "epoch": 22.78,
      "learning_rate": 3.111111111111112e-05,
      "loss": 5.2619,
      "step": 30000
    },
    {
      "epoch": 23.54,
      "learning_rate": 3.066666666666667e-05,
      "loss": 5.2206,
      "step": 31000
    },
    {
      "epoch": 24.3,
      "learning_rate": 3.0222222222222225e-05,
      "loss": 5.1893,
      "step": 32000
    },
    {
      "epoch": 25.06,
      "learning_rate": 2.977777777777778e-05,
      "loss": 5.1596,
      "step": 33000
    },
    {
      "epoch": 25.82,
      "learning_rate": 2.9333333333333333e-05,
      "loss": 5.1372,
      "step": 34000
    },
    {
      "epoch": 26.58,
      "learning_rate": 2.888888888888889e-05,
      "loss": 5.1142,
      "step": 35000
    },
    {
      "epoch": 27.33,
      "learning_rate": 2.8444444444444447e-05,
      "loss": 5.0947,
      "step": 36000
    },
    {
      "epoch": 28.09,
      "learning_rate": 2.8e-05,
      "loss": 5.0789,
      "step": 37000
    },
    {
      "epoch": 28.85,
      "learning_rate": 2.755555555555556e-05,
      "loss": 5.0641,
      "step": 38000
    },
    {
      "epoch": 29.61,
      "learning_rate": 2.7111111111111114e-05,
      "loss": 5.0514,
      "step": 39000
    },
    {
      "epoch": 30.37,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 5.0385,
      "step": 40000
    },
    {
      "epoch": 31.13,
      "learning_rate": 2.6222222222222226e-05,
      "loss": 5.0261,
      "step": 41000
    },
    {
      "epoch": 31.89,
      "learning_rate": 2.577777777777778e-05,
      "loss": 5.016,
      "step": 42000
    },
    {
      "epoch": 32.65,
      "learning_rate": 2.5333333333333334e-05,
      "loss": 5.0028,
      "step": 43000
    },
    {
      "epoch": 33.41,
      "learning_rate": 2.4888888888888893e-05,
      "loss": 4.9953,
      "step": 44000
    },
    {
      "epoch": 34.17,
      "learning_rate": 2.444444444444445e-05,
      "loss": 4.9852,
      "step": 45000
    },
    {
      "epoch": 34.93,
      "learning_rate": 2.4e-05,
      "loss": 4.9763,
      "step": 46000
    },
    {
      "epoch": 35.69,
      "learning_rate": 2.355555555555556e-05,
      "loss": 4.9663,
      "step": 47000
    },
    {
      "epoch": 36.45,
      "learning_rate": 2.3111111111111112e-05,
      "loss": 4.96,
      "step": 48000
    },
    {
      "epoch": 37.21,
      "learning_rate": 2.2666666666666668e-05,
      "loss": 4.9497,
      "step": 49000
    },
    {
      "epoch": 37.97,
      "learning_rate": 2.2222222222222227e-05,
      "loss": 4.9442,
      "step": 50000
    },
    {
      "epoch": 38.72,
      "learning_rate": 2.177777777777778e-05,
      "loss": 4.9354,
      "step": 51000
    },
    {
      "epoch": 39.48,
      "learning_rate": 2.1333333333333335e-05,
      "loss": 4.9297,
      "step": 52000
    },
    {
      "epoch": 40.24,
      "learning_rate": 2.088888888888889e-05,
      "loss": 4.9221,
      "step": 53000
    },
    {
      "epoch": 41.0,
      "learning_rate": 2.0444444444444446e-05,
      "loss": 4.9182,
      "step": 54000
    },
    {
      "epoch": 41.76,
      "learning_rate": 2e-05,
      "loss": 4.9111,
      "step": 55000
    },
    {
      "epoch": 42.52,
      "learning_rate": 1.9555555555555557e-05,
      "loss": 4.9058,
      "step": 56000
    },
    {
      "epoch": 43.28,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 4.8997,
      "step": 57000
    },
    {
      "epoch": 44.04,
      "learning_rate": 1.866666666666667e-05,
      "loss": 4.8967,
      "step": 58000
    },
    {
      "epoch": 44.8,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 4.89,
      "step": 59000
    },
    {
      "epoch": 45.56,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 4.8834,
      "step": 60000
    },
    {
      "epoch": 46.32,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 4.8809,
      "step": 61000
    },
    {
      "epoch": 47.08,
      "learning_rate": 1.688888888888889e-05,
      "loss": 4.8751,
      "step": 62000
    },
    {
      "epoch": 47.84,
      "learning_rate": 1.6444444444444444e-05,
      "loss": 4.8716,
      "step": 63000
    },
    {
      "epoch": 48.6,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 4.8688,
      "step": 64000
    },
    {
      "epoch": 49.35,
      "learning_rate": 1.555555555555556e-05,
      "loss": 4.8625,
      "step": 65000
    },
    {
      "epoch": 50.11,
      "learning_rate": 1.5111111111111112e-05,
      "loss": 4.8591,
      "step": 66000
    },
    {
      "epoch": 50.87,
      "learning_rate": 1.4666666666666666e-05,
      "loss": 4.8554,
      "step": 67000
    },
    {
      "epoch": 51.63,
      "learning_rate": 1.4222222222222224e-05,
      "loss": 4.8528,
      "step": 68000
    },
    {
      "epoch": 52.39,
      "learning_rate": 1.377777777777778e-05,
      "loss": 4.8506,
      "step": 69000
    },
    {
      "epoch": 53.15,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 4.846,
      "step": 70000
    },
    {
      "epoch": 53.91,
      "learning_rate": 1.288888888888889e-05,
      "loss": 4.8416,
      "step": 71000
    },
    {
      "epoch": 54.67,
      "learning_rate": 1.2444444444444446e-05,
      "loss": 4.8408,
      "step": 72000
    },
    {
      "epoch": 55.43,
      "learning_rate": 1.2e-05,
      "loss": 4.8356,
      "step": 73000
    },
    {
      "epoch": 56.19,
      "learning_rate": 1.1555555555555556e-05,
      "loss": 4.837,
      "step": 74000
    },
    {
      "epoch": 56.95,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 4.8319,
      "step": 75000
    },
    {
      "epoch": 57.71,
      "learning_rate": 1.0666666666666667e-05,
      "loss": 4.8291,
      "step": 76000
    },
    {
      "epoch": 58.47,
      "learning_rate": 1.0222222222222223e-05,
      "loss": 4.8284,
      "step": 77000
    },
    {
      "epoch": 59.23,
      "learning_rate": 9.777777777777779e-06,
      "loss": 4.827,
      "step": 78000
    },
    {
      "epoch": 59.98,
      "learning_rate": 9.333333333333334e-06,
      "loss": 4.8233,
      "step": 79000
    },
    {
      "epoch": 60.74,
      "learning_rate": 8.888888888888888e-06,
      "loss": 4.8212,
      "step": 80000
    },
    {
      "epoch": 61.5,
      "learning_rate": 8.444444444444446e-06,
      "loss": 4.8208,
      "step": 81000
    },
    {
      "epoch": 62.26,
      "learning_rate": 8.000000000000001e-06,
      "loss": 4.8191,
      "step": 82000
    },
    {
      "epoch": 63.02,
      "learning_rate": 7.555555555555556e-06,
      "loss": 4.8163,
      "step": 83000
    },
    {
      "epoch": 63.78,
      "learning_rate": 7.111111111111112e-06,
      "loss": 4.8122,
      "step": 84000
    },
    {
      "epoch": 64.54,
      "learning_rate": 6.666666666666667e-06,
      "loss": 4.8144,
      "step": 85000
    },
    {
      "epoch": 65.3,
      "learning_rate": 6.222222222222223e-06,
      "loss": 4.8124,
      "step": 86000
    },
    {
      "epoch": 66.06,
      "learning_rate": 5.777777777777778e-06,
      "loss": 4.8091,
      "step": 87000
    },
    {
      "epoch": 66.82,
      "learning_rate": 5.333333333333334e-06,
      "loss": 4.8075,
      "step": 88000
    },
    {
      "epoch": 67.58,
      "learning_rate": 4.888888888888889e-06,
      "loss": 4.8066,
      "step": 89000
    },
    {
      "epoch": 68.34,
      "learning_rate": 4.444444444444444e-06,
      "loss": 4.804,
      "step": 90000
    },
    {
      "epoch": 69.1,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.8072,
      "step": 91000
    },
    {
      "epoch": 69.86,
      "learning_rate": 3.555555555555556e-06,
      "loss": 4.8032,
      "step": 92000
    },
    {
      "epoch": 70.62,
      "learning_rate": 3.1111111111111116e-06,
      "loss": 4.805,
      "step": 93000
    },
    {
      "epoch": 71.37,
      "learning_rate": 2.666666666666667e-06,
      "loss": 4.802,
      "step": 94000
    },
    {
      "epoch": 72.13,
      "learning_rate": 2.222222222222222e-06,
      "loss": 4.8026,
      "step": 95000
    },
    {
      "epoch": 72.89,
      "learning_rate": 1.777777777777778e-06,
      "loss": 4.8016,
      "step": 96000
    },
    {
      "epoch": 73.65,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 4.8009,
      "step": 97000
    },
    {
      "epoch": 74.41,
      "learning_rate": 8.88888888888889e-07,
      "loss": 4.799,
      "step": 98000
    },
    {
      "epoch": 75.17,
      "learning_rate": 4.444444444444445e-07,
      "loss": 4.8006,
      "step": 99000
    },
    {
      "epoch": 75.93,
      "learning_rate": 0.0,
      "loss": 4.7991,
      "step": 100000
    },
    {
      "epoch": 75.93,
      "step": 100000,
      "total_flos": 2.0207652764961997e+19,
      "train_loss": 5.246563823242187,
      "train_runtime": 82973.744,
      "train_samples_per_second": 925.594,
      "train_steps_per_second": 1.205
    }
  ],
  "logging_steps": 1000,
  "max_steps": 100000,
  "num_train_epochs": 76,
  "save_steps": 1000,
  "total_flos": 2.0207652764961997e+19,
  "trial_name": null,
  "trial_params": null
}