{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.999030067895247,
  "eval_steps": 500,
  "global_step": 12885,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 4.99e-05,
      "loss": 0.0599,
      "step": 500
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.97999958968678e-05,
      "loss": 0.0763,
      "step": 1000
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.920159465099463e-05,
      "loss": 0.0765,
      "step": 1500
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.8214408436601485e-05,
      "loss": 0.0868,
      "step": 2000
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.685737469208415e-05,
      "loss": 0.0843,
      "step": 2500
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.514686169369878e-05,
      "loss": 0.0716,
      "step": 3000
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.311270072490833e-05,
      "loss": 0.0691,
      "step": 3500
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.0787569434422325e-05,
      "loss": 0.0677,
      "step": 4000
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.82142034348649e-05,
      "loss": 0.0695,
      "step": 4500
    },
    {
      "epoch": 1.94,
      "learning_rate": 3.5423642164834494e-05,
      "loss": 0.0666,
      "step": 5000
    },
    {
      "epoch": 2.13,
      "learning_rate": 3.24656309622951e-05,
      "loss": 0.0555,
      "step": 5500
    },
    {
      "epoch": 2.33,
      "learning_rate": 2.9387688608915686e-05,
      "loss": 0.0526,
      "step": 6000
    },
    {
      "epoch": 2.52,
      "learning_rate": 2.6245594204007562e-05,
      "loss": 0.0478,
      "step": 6500
    },
    {
      "epoch": 2.72,
      "learning_rate": 2.30772470772302e-05,
      "loss": 0.0545,
      "step": 7000
    },
    {
      "epoch": 2.91,
      "learning_rate": 1.9939787891736486e-05,
      "loss": 0.0511,
      "step": 7500
    },
    {
      "epoch": 3.1,
      "learning_rate": 1.6883618159833997e-05,
      "loss": 0.0414,
      "step": 8000
    },
    {
      "epoch": 3.3,
      "learning_rate": 1.3963523303957105e-05,
      "loss": 0.0355,
      "step": 8500
    },
    {
      "epoch": 3.49,
      "learning_rate": 1.1214724938519077e-05,
      "loss": 0.0387,
      "step": 9000
    },
    {
      "epoch": 3.69,
      "learning_rate": 8.692185278441231e-06,
      "loss": 0.0376,
      "step": 9500
    },
    {
      "epoch": 3.88,
      "learning_rate": 6.426330704931902e-06,
      "loss": 0.0387,
      "step": 10000
    },
    {
      "epoch": 4.07,
      "learning_rate": 4.458851653214341e-06,
      "loss": 0.0339,
      "step": 10500
    },
    {
      "epoch": 4.27,
      "learning_rate": 2.821354564608486e-06,
      "loss": 0.0337,
      "step": 11000
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.542337081476908e-06,
      "loss": 0.0363,
      "step": 11500
    },
    {
      "epoch": 4.66,
      "learning_rate": 6.372264631526293e-07,
      "loss": 0.0355,
      "step": 12000
    },
    {
      "epoch": 4.85,
      "learning_rate": 1.2349006124565966e-07,
      "loss": 0.0398,
      "step": 12500
    }
  ],
  "logging_steps": 500,
  "max_steps": 12885,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.0922943771416986e+17,
  "trial_name": null,
  "trial_params": null
}