{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9801615306202462,
  "eval_steps": 500,
  "global_step": 12500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1500
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2000
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2500
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 3000
    },
    {
      "epoch": 0.27,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 3500
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4000
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4500
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 5000
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 5500
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 6000
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 6500
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 7000
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 7500
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 8000
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 8500
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 9000
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 9500
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 10000
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 10500
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 11000
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 11500
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 12000
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 12500
    }
  ],
  "logging_steps": 500,
  "max_steps": 12753,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 8830343986003968.0,
  "trial_name": null,
  "trial_params": null
}