{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 10020,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 0.0373,
      "step": 500
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.9663165247662615e-05,
      "loss": 0.0614,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.865640637350898e-05,
      "loss": 0.0588,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.700706468751901e-05,
      "loss": 0.0661,
      "step": 2000
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.475994152602118e-05,
      "loss": 0.0515,
      "step": 2500
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.197607586073667e-05,
      "loss": 0.0518,
      "step": 3000
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.8731086287268264e-05,
      "loss": 0.052,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.511311698489561e-05,
      "loss": 0.0506,
      "step": 4000
    },
    {
      "epoch": 2.25,
      "learning_rate": 3.1228433624560175e-05,
      "loss": 0.0383,
      "step": 4500
    },
    {
      "epoch": 2.5,
      "learning_rate": 2.7175240839918063e-05,
      "loss": 0.0409,
      "step": 5000
    },
    {
      "epoch": 2.74,
      "learning_rate": 2.3054972130358894e-05,
      "loss": 0.0372,
      "step": 5500
    },
    {
      "epoch": 2.99,
      "learning_rate": 1.8987536529000545e-05,
      "loss": 0.0349,
      "step": 6000
    },
    {
      "epoch": 3.24,
      "learning_rate": 1.5083418450272521e-05,
      "loss": 0.0246,
      "step": 6500
    },
    {
      "epoch": 3.49,
      "learning_rate": 1.1455599648308674e-05,
      "loss": 0.0232,
      "step": 7000
    },
    {
      "epoch": 3.74,
      "learning_rate": 8.188115868146839e-06,
      "loss": 0.0255,
      "step": 7500
    },
    {
      "epoch": 3.99,
      "learning_rate": 5.377296029546741e-06,
      "loss": 0.0236,
      "step": 8000
    },
    {
      "epoch": 4.24,
      "learning_rate": 3.1034708332441433e-06,
      "loss": 0.0154,
      "step": 8500
    },
    {
      "epoch": 4.49,
      "learning_rate": 1.4193117617159691e-06,
      "loss": 0.0195,
      "step": 9000
    },
    {
      "epoch": 4.74,
      "learning_rate": 3.756787580085019e-07,
      "loss": 0.0224,
      "step": 9500
    },
    {
      "epoch": 4.99,
      "learning_rate": 9.201950512210955e-10,
      "loss": 0.0249,
      "step": 10000
    }
  ],
  "logging_steps": 500,
  "max_steps": 10020,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 8.494405705116672e+16,
  "trial_name": null,
  "trial_params": null
}