{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 10969,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.9699152156076217e-05,
      "loss": 2.2617,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.939526544504209e-05,
      "loss": 1.242,
      "step": 1000
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9091378734007962e-05,
      "loss": 1.1706,
      "step": 1500
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8787492022973838e-05,
      "loss": 1.123,
      "step": 2000
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8484820858783847e-05,
      "loss": 1.1132,
      "step": 2500
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.818093414774972e-05,
      "loss": 1.0418,
      "step": 3000
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.7877655210137663e-05,
      "loss": 1.0142,
      "step": 3500
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.7573768499103536e-05,
      "loss": 1.0665,
      "step": 4000
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.726988178806941e-05,
      "loss": 0.9765,
      "step": 4500
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.696599507703528e-05,
      "loss": 0.9874,
      "step": 5000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.6662108366001154e-05,
      "loss": 0.9705,
      "step": 5500
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.635822165496703e-05,
      "loss": 0.9824,
      "step": 6000
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.6054334943932903e-05,
      "loss": 0.939,
      "step": 6500
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.5750448232898775e-05,
      "loss": 0.9501,
      "step": 7000
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.5446561521864648e-05,
      "loss": 0.9427,
      "step": 7500
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.5142674810830524e-05,
      "loss": 0.9215,
      "step": 8000
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.4838788099796397e-05,
      "loss": 0.9106,
      "step": 8500
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.4534901388762271e-05,
      "loss": 0.9276,
      "step": 9000
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.4231014677728144e-05,
      "loss": 0.9249,
      "step": 9500
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.3927127966694018e-05,
      "loss": 0.9114,
      "step": 10000
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.3623849029081959e-05,
      "loss": 0.888,
      "step": 10500
    }
  ],
  "max_steps": 32907,
  "num_train_epochs": 3,
  "total_flos": 2.292748391980032e+16,
  "trial_name": null,
  "trial_params": null
}