{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 10715,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23,
      "learning_rate": 4.7666822211852545e-05,
      "loss": 1.8978,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.5333644423705094e-05,
      "loss": 1.6943,
      "step": 1000
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.300046663555763e-05,
      "loss": 1.6273,
      "step": 1500
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.066728884741017e-05,
      "loss": 1.59,
      "step": 2000
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.8334111059262714e-05,
      "loss": 1.5531,
      "step": 2500
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.600093327111526e-05,
      "loss": 1.5196,
      "step": 3000
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.3667755482967805e-05,
      "loss": 1.4976,
      "step": 3500
    },
    {
      "epoch": 1.87,
      "learning_rate": 3.133457769482035e-05,
      "loss": 1.4651,
      "step": 4000
    },
    {
      "epoch": 2.1,
      "learning_rate": 2.9001399906672887e-05,
      "loss": 1.4498,
      "step": 4500
    },
    {
      "epoch": 2.33,
      "learning_rate": 2.6668222118525432e-05,
      "loss": 1.4301,
      "step": 5000
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.4335044330377978e-05,
      "loss": 1.4194,
      "step": 5500
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.200186654223052e-05,
      "loss": 1.4035,
      "step": 6000
    },
    {
      "epoch": 3.03,
      "learning_rate": 1.9668688754083062e-05,
      "loss": 1.3985,
      "step": 6500
    },
    {
      "epoch": 3.27,
      "learning_rate": 1.7335510965935605e-05,
      "loss": 1.3829,
      "step": 7000
    },
    {
      "epoch": 3.5,
      "learning_rate": 1.5002333177788147e-05,
      "loss": 1.3729,
      "step": 7500
    },
    {
      "epoch": 3.73,
      "learning_rate": 1.2669155389640691e-05,
      "loss": 1.3654,
      "step": 8000
    },
    {
      "epoch": 3.97,
      "learning_rate": 1.0335977601493233e-05,
      "loss": 1.3587,
      "step": 8500
    },
    {
      "epoch": 4.2,
      "learning_rate": 8.002799813345777e-06,
      "loss": 1.3466,
      "step": 9000
    },
    {
      "epoch": 4.43,
      "learning_rate": 5.6696220251983205e-06,
      "loss": 1.3435,
      "step": 9500
    },
    {
      "epoch": 4.67,
      "learning_rate": 3.3364442370508633e-06,
      "loss": 1.3398,
      "step": 10000
    },
    {
      "epoch": 4.9,
      "learning_rate": 1.0032664489034066e-06,
      "loss": 1.3377,
      "step": 10500
    },
    {
      "epoch": 5.0,
      "step": 10715,
      "total_flos": 1.357077205905408e+17,
      "train_loss": 1.4635986100275606,
      "train_runtime": 50086.6399,
      "train_samples_per_second": 10.268,
      "train_steps_per_second": 0.214
    }
  ],
  "max_steps": 10715,
  "num_train_epochs": 5,
  "total_flos": 1.357077205905408e+17,
  "trial_name": null,
  "trial_params": null
}