{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.824392126592049,
  "global_step": 50000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 7.142857142857143e-06,
      "loss": 5.3189,
      "step": 1000
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 5.3266,
      "step": 2000
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 5.3215,
      "step": 3000
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.857142857142857e-05,
      "loss": 5.3156,
      "step": 4000
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.571428571428572e-05,
      "loss": 5.3094,
      "step": 5000
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 5.294,
      "step": 6000
    },
    {
      "epoch": 0.68,
      "learning_rate": 5e-05,
      "loss": 5.2852,
      "step": 7000
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.883720930232558e-05,
      "loss": 5.2715,
      "step": 8000
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.7674418604651164e-05,
      "loss": 5.2477,
      "step": 9000
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.651162790697675e-05,
      "loss": 5.2361,
      "step": 10000
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.5348837209302326e-05,
      "loss": 5.2234,
      "step": 11000
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.418604651162791e-05,
      "loss": 5.2037,
      "step": 12000
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.302325581395349e-05,
      "loss": 5.1853,
      "step": 13000
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.186046511627907e-05,
      "loss": 5.1751,
      "step": 14000
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.0697674418604655e-05,
      "loss": 5.1663,
      "step": 15000
    },
    {
      "epoch": 1.54,
      "learning_rate": 3.953488372093023e-05,
      "loss": 5.1615,
      "step": 16000
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.837209302325582e-05,
      "loss": 5.1547,
      "step": 17000
    },
    {
      "epoch": 1.74,
      "learning_rate": 3.7209302325581394e-05,
      "loss": 5.1431,
      "step": 18000
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.604651162790698e-05,
      "loss": 5.1293,
      "step": 19000
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.488372093023256e-05,
      "loss": 5.1278,
      "step": 20000
    },
    {
      "epoch": 2.03,
      "learning_rate": 3.372093023255814e-05,
      "loss": 5.1174,
      "step": 21000
    },
    {
      "epoch": 2.12,
      "learning_rate": 3.2558139534883724e-05,
      "loss": 5.1033,
      "step": 22000
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.13953488372093e-05,
      "loss": 5.1019,
      "step": 23000
    },
    {
      "epoch": 2.32,
      "learning_rate": 3.0232558139534883e-05,
      "loss": 5.096,
      "step": 24000
    },
    {
      "epoch": 2.41,
      "learning_rate": 2.9069767441860467e-05,
      "loss": 5.0878,
      "step": 25000
    },
    {
      "epoch": 2.51,
      "learning_rate": 2.7906976744186048e-05,
      "loss": 5.0847,
      "step": 26000
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.674418604651163e-05,
      "loss": 5.0731,
      "step": 27000
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.5581395348837212e-05,
      "loss": 5.0672,
      "step": 28000
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.441860465116279e-05,
      "loss": 5.0717,
      "step": 29000
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.3255813953488374e-05,
      "loss": 5.0631,
      "step": 30000
    },
    {
      "epoch": 2.99,
      "learning_rate": 2.2093023255813955e-05,
      "loss": 5.0626,
      "step": 31000
    },
    {
      "epoch": 3.09,
      "learning_rate": 2.0930232558139536e-05,
      "loss": 5.06,
      "step": 32000
    },
    {
      "epoch": 3.18,
      "learning_rate": 1.9767441860465116e-05,
      "loss": 5.0461,
      "step": 33000
    },
    {
      "epoch": 3.28,
      "learning_rate": 1.8604651162790697e-05,
      "loss": 5.039,
      "step": 34000
    },
    {
      "epoch": 3.38,
      "learning_rate": 1.744186046511628e-05,
      "loss": 5.0416,
      "step": 35000
    },
    {
      "epoch": 3.47,
      "learning_rate": 1.6279069767441862e-05,
      "loss": 5.0437,
      "step": 36000
    },
    {
      "epoch": 3.57,
      "learning_rate": 1.5116279069767441e-05,
      "loss": 5.03,
      "step": 37000
    },
    {
      "epoch": 3.67,
      "learning_rate": 1.3953488372093024e-05,
      "loss": 5.027,
      "step": 38000
    },
    {
      "epoch": 3.76,
      "learning_rate": 1.2790697674418606e-05,
      "loss": 5.0289,
      "step": 39000
    },
    {
      "epoch": 3.86,
      "learning_rate": 1.1627906976744187e-05,
      "loss": 5.0246,
      "step": 40000
    },
    {
      "epoch": 3.96,
      "learning_rate": 1.0465116279069768e-05,
      "loss": 5.0209,
      "step": 41000
    },
    {
      "epoch": 4.05,
      "learning_rate": 9.302325581395349e-06,
      "loss": 5.0167,
      "step": 42000
    },
    {
      "epoch": 4.15,
      "learning_rate": 8.139534883720931e-06,
      "loss": 5.0108,
      "step": 43000
    },
    {
      "epoch": 4.25,
      "learning_rate": 6.976744186046512e-06,
      "loss": 5.0121,
      "step": 44000
    },
    {
      "epoch": 4.34,
      "learning_rate": 5.8139534883720935e-06,
      "loss": 5.0122,
      "step": 45000
    },
    {
      "epoch": 4.44,
      "learning_rate": 4.651162790697674e-06,
      "loss": 5.0222,
      "step": 46000
    },
    {
      "epoch": 4.53,
      "learning_rate": 3.488372093023256e-06,
      "loss": 5.0162,
      "step": 47000
    },
    {
      "epoch": 4.63,
      "learning_rate": 2.325581395348837e-06,
      "loss": 5.0045,
      "step": 48000
    },
    {
      "epoch": 4.73,
      "learning_rate": 1.1627906976744186e-06,
      "loss": 5.0047,
      "step": 49000
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.0,
      "loss": 5.005,
      "step": 50000
    }
  ],
  "max_steps": 50000,
  "num_train_epochs": 5,
  "total_flos": 1.2629229170809897e+18,
  "trial_name": null,
  "trial_params": null
}