{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 90.9090909090909,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.27,
      "learning_rate": 3e-06,
      "loss": 7.7201,
      "step": 50
    },
    {
      "epoch": 4.55,
      "learning_rate": 6e-06,
      "loss": 4.0276,
      "step": 100
    },
    {
      "epoch": 6.82,
      "learning_rate": 9e-06,
      "loss": 2.3807,
      "step": 150
    },
    {
      "epoch": 9.09,
      "learning_rate": 1.2e-05,
      "loss": 2.0072,
      "step": 200
    },
    {
      "epoch": 11.36,
      "learning_rate": 1.5e-05,
      "loss": 1.8108,
      "step": 250
    },
    {
      "epoch": 13.64,
      "learning_rate": 1.8e-05,
      "loss": 1.7074,
      "step": 300
    },
    {
      "epoch": 15.91,
      "learning_rate": 2.1e-05,
      "loss": 1.6441,
      "step": 350
    },
    {
      "epoch": 18.18,
      "learning_rate": 2.4e-05,
      "loss": 1.5972,
      "step": 400
    },
    {
      "epoch": 20.45,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.5593,
      "step": 450
    },
    {
      "epoch": 22.73,
      "learning_rate": 3e-05,
      "loss": 1.5459,
      "step": 500
    },
    {
      "epoch": 25.0,
      "learning_rate": 2.911764705882353e-05,
      "loss": 1.5295,
      "step": 550
    },
    {
      "epoch": 27.27,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.5236,
      "step": 600
    },
    {
      "epoch": 29.55,
      "learning_rate": 2.735294117647059e-05,
      "loss": 1.4994,
      "step": 650
    },
    {
      "epoch": 31.82,
      "learning_rate": 2.647058823529412e-05,
      "loss": 1.4965,
      "step": 700
    },
    {
      "epoch": 34.09,
      "learning_rate": 2.5588235294117648e-05,
      "loss": 1.4875,
      "step": 750
    },
    {
      "epoch": 36.36,
      "learning_rate": 2.4705882352941174e-05,
      "loss": 1.4824,
      "step": 800
    },
    {
      "epoch": 38.64,
      "learning_rate": 2.3823529411764704e-05,
      "loss": 1.481,
      "step": 850
    },
    {
      "epoch": 40.91,
      "learning_rate": 2.2941176470588233e-05,
      "loss": 1.4717,
      "step": 900
    },
    {
      "epoch": 43.18,
      "learning_rate": 2.2058823529411766e-05,
      "loss": 1.4692,
      "step": 950
    },
    {
      "epoch": 45.45,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.4677,
      "step": 1000
    },
    {
      "epoch": 47.73,
      "learning_rate": 2.0294117647058825e-05,
      "loss": 1.4637,
      "step": 1050
    },
    {
      "epoch": 50.0,
      "learning_rate": 1.9411764705882355e-05,
      "loss": 1.4649,
      "step": 1100
    },
    {
      "epoch": 52.27,
      "learning_rate": 1.8529411764705884e-05,
      "loss": 1.4665,
      "step": 1150
    },
    {
      "epoch": 54.55,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.4584,
      "step": 1200
    },
    {
      "epoch": 56.82,
      "learning_rate": 1.6764705882352943e-05,
      "loss": 1.4576,
      "step": 1250
    },
    {
      "epoch": 59.09,
      "learning_rate": 1.5882352941176473e-05,
      "loss": 1.455,
      "step": 1300
    },
    {
      "epoch": 61.36,
      "learning_rate": 1.5e-05,
      "loss": 1.4541,
      "step": 1350
    },
    {
      "epoch": 63.64,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.4532,
      "step": 1400
    },
    {
      "epoch": 65.91,
      "learning_rate": 1.323529411764706e-05,
      "loss": 1.4557,
      "step": 1450
    },
    {
      "epoch": 68.18,
      "learning_rate": 1.2352941176470587e-05,
      "loss": 1.452,
      "step": 1500
    },
    {
      "epoch": 70.45,
      "learning_rate": 1.1470588235294117e-05,
      "loss": 1.4513,
      "step": 1550
    },
    {
      "epoch": 72.73,
      "learning_rate": 1.0588235294117648e-05,
      "loss": 1.4697,
      "step": 1600
    },
    {
      "epoch": 75.0,
      "learning_rate": 9.705882352941177e-06,
      "loss": 1.4492,
      "step": 1650
    },
    {
      "epoch": 77.27,
      "learning_rate": 8.823529411764707e-06,
      "loss": 1.447,
      "step": 1700
    },
    {
      "epoch": 79.55,
      "learning_rate": 7.941176470588236e-06,
      "loss": 1.4489,
      "step": 1750
    },
    {
      "epoch": 81.82,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.4475,
      "step": 1800
    },
    {
      "epoch": 84.09,
      "learning_rate": 6.176470588235294e-06,
      "loss": 1.447,
      "step": 1850
    },
    {
      "epoch": 86.36,
      "learning_rate": 5.294117647058824e-06,
      "loss": 1.4472,
      "step": 1900
    },
    {
      "epoch": 88.64,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.4602,
      "step": 1950
    },
    {
      "epoch": 90.91,
      "learning_rate": 3.5294117647058825e-06,
      "loss": 1.447,
      "step": 2000
    }
  ],
  "max_steps": 2200,
  "num_train_epochs": 100,
  "total_flos": 4713262822195200.0,
  "trial_name": null,
  "trial_params": null
}