{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.769062385990514,
  "global_step": 35000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18,
      "learning_rate": 3.9428571428571435e-05,
      "loss": 0.7626,
      "step": 500
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.885714285714286e-05,
      "loss": 0.3395,
      "step": 1000
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.828571428571429e-05,
      "loss": 0.1906,
      "step": 1500
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.771428571428572e-05,
      "loss": 0.1287,
      "step": 2000
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.714285714285715e-05,
      "loss": 0.1061,
      "step": 2500
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.6571428571428576e-05,
      "loss": 0.0865,
      "step": 3000
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.6e-05,
      "loss": 0.0646,
      "step": 3500
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.542857142857143e-05,
      "loss": 0.0562,
      "step": 4000
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.485714285714286e-05,
      "loss": 0.0685,
      "step": 4500
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.4285714285714284e-05,
      "loss": 0.0481,
      "step": 5000
    },
    {
      "epoch": 2.01,
      "learning_rate": 3.3714285714285716e-05,
      "loss": 0.0445,
      "step": 5500
    },
    {
      "epoch": 2.19,
      "learning_rate": 3.314285714285715e-05,
      "loss": 0.0345,
      "step": 6000
    },
    {
      "epoch": 2.37,
      "learning_rate": 3.257142857142857e-05,
      "loss": 0.0353,
      "step": 6500
    },
    {
      "epoch": 2.55,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0436,
      "step": 7000
    },
    {
      "epoch": 2.74,
      "learning_rate": 3.142857142857143e-05,
      "loss": 0.0337,
      "step": 7500
    },
    {
      "epoch": 2.92,
      "learning_rate": 3.085714285714286e-05,
      "loss": 0.0325,
      "step": 8000
    },
    {
      "epoch": 3.1,
      "learning_rate": 3.0285714285714288e-05,
      "loss": 0.0325,
      "step": 8500
    },
    {
      "epoch": 3.28,
      "learning_rate": 2.9714285714285717e-05,
      "loss": 0.0303,
      "step": 9000
    },
    {
      "epoch": 3.47,
      "learning_rate": 2.9142857142857146e-05,
      "loss": 0.0243,
      "step": 9500
    },
    {
      "epoch": 3.65,
      "learning_rate": 2.8571428571428574e-05,
      "loss": 0.0269,
      "step": 10000
    },
    {
      "epoch": 3.83,
      "learning_rate": 2.8e-05,
      "loss": 0.0252,
      "step": 10500
    },
    {
      "epoch": 4.01,
      "learning_rate": 2.742857142857143e-05,
      "loss": 0.0285,
      "step": 11000
    },
    {
      "epoch": 4.2,
      "learning_rate": 2.6857142857142857e-05,
      "loss": 0.0265,
      "step": 11500
    },
    {
      "epoch": 4.38,
      "learning_rate": 2.628571428571429e-05,
      "loss": 0.0197,
      "step": 12000
    },
    {
      "epoch": 4.56,
      "learning_rate": 2.5714285714285718e-05,
      "loss": 0.0253,
      "step": 12500
    },
    {
      "epoch": 4.74,
      "learning_rate": 2.5142857142857143e-05,
      "loss": 0.025,
      "step": 13000
    },
    {
      "epoch": 4.93,
      "learning_rate": 2.4571428571428575e-05,
      "loss": 0.0254,
      "step": 13500
    },
    {
      "epoch": 5.11,
      "learning_rate": 2.4e-05,
      "loss": 0.0235,
      "step": 14000
    },
    {
      "epoch": 5.29,
      "learning_rate": 2.3428571428571433e-05,
      "loss": 0.025,
      "step": 14500
    },
    {
      "epoch": 5.47,
      "learning_rate": 2.2857142857142858e-05,
      "loss": 0.0191,
      "step": 15000
    },
    {
      "epoch": 5.65,
      "learning_rate": 2.2285714285714287e-05,
      "loss": 0.0225,
      "step": 15500
    },
    {
      "epoch": 5.84,
      "learning_rate": 2.1714285714285715e-05,
      "loss": 0.0195,
      "step": 16000
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.1142857142857144e-05,
      "loss": 0.017,
      "step": 16500
    },
    {
      "epoch": 6.2,
      "learning_rate": 2.057142857142857e-05,
      "loss": 0.0196,
      "step": 17000
    },
    {
      "epoch": 6.38,
      "learning_rate": 2e-05,
      "loss": 0.0174,
      "step": 17500
    },
    {
      "epoch": 6.57,
      "learning_rate": 1.942857142857143e-05,
      "loss": 0.0205,
      "step": 18000
    },
    {
      "epoch": 6.75,
      "learning_rate": 1.885714285714286e-05,
      "loss": 0.0223,
      "step": 18500
    },
    {
      "epoch": 6.93,
      "learning_rate": 1.8285714285714288e-05,
      "loss": 0.0181,
      "step": 19000
    },
    {
      "epoch": 7.11,
      "learning_rate": 1.7714285714285717e-05,
      "loss": 0.026,
      "step": 19500
    },
    {
      "epoch": 7.3,
      "learning_rate": 1.7142857142857142e-05,
      "loss": 0.0191,
      "step": 20000
    },
    {
      "epoch": 7.48,
      "learning_rate": 1.6571428571428574e-05,
      "loss": 0.0194,
      "step": 20500
    },
    {
      "epoch": 7.66,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.021,
      "step": 21000
    },
    {
      "epoch": 7.84,
      "learning_rate": 1.542857142857143e-05,
      "loss": 0.0166,
      "step": 21500
    },
    {
      "epoch": 8.03,
      "learning_rate": 1.4857142857142858e-05,
      "loss": 0.017,
      "step": 22000
    },
    {
      "epoch": 8.21,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.0185,
      "step": 22500
    },
    {
      "epoch": 8.39,
      "learning_rate": 1.3714285714285716e-05,
      "loss": 0.0179,
      "step": 23000
    },
    {
      "epoch": 8.57,
      "learning_rate": 1.3142857142857145e-05,
      "loss": 0.0179,
      "step": 23500
    },
    {
      "epoch": 8.76,
      "learning_rate": 1.2571428571428572e-05,
      "loss": 0.0175,
      "step": 24000
    },
    {
      "epoch": 8.94,
      "learning_rate": 1.2e-05,
      "loss": 0.0146,
      "step": 24500
    },
    {
      "epoch": 9.12,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.0223,
      "step": 25000
    },
    {
      "epoch": 9.3,
      "learning_rate": 1.0857142857142858e-05,
      "loss": 0.0173,
      "step": 25500
    },
    {
      "epoch": 9.49,
      "learning_rate": 1.0285714285714285e-05,
      "loss": 0.0214,
      "step": 26000
    },
    {
      "epoch": 9.67,
      "learning_rate": 9.714285714285715e-06,
      "loss": 0.0185,
      "step": 26500
    },
    {
      "epoch": 9.85,
      "learning_rate": 9.142857142857144e-06,
      "loss": 0.021,
      "step": 27000
    },
    {
      "epoch": 10.03,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.0191,
      "step": 27500
    },
    {
      "epoch": 10.22,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0145,
      "step": 28000
    },
    {
      "epoch": 10.4,
      "learning_rate": 7.428571428571429e-06,
      "loss": 0.0187,
      "step": 28500
    },
    {
      "epoch": 10.58,
      "learning_rate": 6.857142857142858e-06,
      "loss": 0.0184,
      "step": 29000
    },
    {
      "epoch": 10.76,
      "learning_rate": 6.285714285714286e-06,
      "loss": 0.0171,
      "step": 29500
    },
    {
      "epoch": 10.94,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.0167,
      "step": 30000
    },
    {
      "epoch": 11.13,
      "learning_rate": 5.142857142857142e-06,
      "loss": 0.0193,
      "step": 30500
    },
    {
      "epoch": 11.31,
      "learning_rate": 4.571428571428572e-06,
      "loss": 0.0151,
      "step": 31000
    },
    {
      "epoch": 11.49,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0148,
      "step": 31500
    },
    {
      "epoch": 11.67,
      "learning_rate": 3.428571428571429e-06,
      "loss": 0.0202,
      "step": 32000
    },
    {
      "epoch": 11.86,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.0155,
      "step": 32500
    },
    {
      "epoch": 12.04,
      "learning_rate": 2.285714285714286e-06,
      "loss": 0.017,
      "step": 33000
    },
    {
      "epoch": 12.22,
      "learning_rate": 1.7142857142857145e-06,
      "loss": 0.022,
      "step": 33500
    },
    {
      "epoch": 12.4,
      "learning_rate": 1.142857142857143e-06,
      "loss": 0.0176,
      "step": 34000
    },
    {
      "epoch": 12.59,
      "learning_rate": 5.714285714285715e-07,
      "loss": 0.0158,
      "step": 34500
    },
    {
      "epoch": 12.77,
      "learning_rate": 0.0,
      "loss": 0.0116,
      "step": 35000
    },
    {
      "epoch": 12.77,
      "step": 35000,
      "train_runtime": 11218.2271,
      "train_samples_per_second": 3.12
    }
  ],
  "max_steps": 35000,
  "num_train_epochs": 13,
  "total_flos": 72522034090868736,
  "trial_name": null,
  "trial_params": null
}