{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15242392141022612,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.9951222486433756e-05,
      "loss": 0.0754,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.990244497286751e-05,
      "loss": 0.0747,
      "step": 400
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9853667459301263e-05,
      "loss": 0.0737,
      "step": 600
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9804889945735017e-05,
      "loss": 0.073,
      "step": 800
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.975611243216877e-05,
      "loss": 0.0723,
      "step": 1000
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9707334918602525e-05,
      "loss": 0.072,
      "step": 1200
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.965855740503628e-05,
      "loss": 0.0709,
      "step": 1400
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9609779891470033e-05,
      "loss": 0.0703,
      "step": 1600
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9561002377903787e-05,
      "loss": 0.0708,
      "step": 1800
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.951222486433754e-05,
      "loss": 0.0711,
      "step": 2000
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9463447350771295e-05,
      "loss": 0.0699,
      "step": 2200
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.941466983720505e-05,
      "loss": 0.0701,
      "step": 2400
    },
    {
      "epoch": 0.15,
      "eval_loss": 0.055753033608198166,
      "eval_runtime": 1008.1775,
      "eval_samples_per_second": 82.199,
      "eval_steps_per_second": 13.7,
      "step": 2500
    }
  ],
  "max_steps": 82005,
  "num_train_epochs": 5,
  "total_flos": 1.268999258112e+17,
  "trial_name": null,
  "trial_params": null
}