{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.9220672682526665,
  "global_step": 6000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.41,
      "learning_rate": 1.8372436423297786e-05,
      "loss": 0.4396,
      "step": 500
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.673502871205907e-05,
      "loss": 0.3623,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7705605028810896,
      "eval_f1": 0.7981601731601731,
      "eval_loss": 0.3199549615383148,
      "eval_roc_auc": 0.8454688318491356,
      "eval_runtime": 4.9345,
      "eval_samples_per_second": 386.871,
      "eval_steps_per_second": 48.435,
      "step": 1219
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.5097621000820346e-05,
      "loss": 0.3118,
      "step": 1500
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.345693191140279e-05,
      "loss": 0.3084,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.787323205866946,
      "eval_f1": 0.8144357662267707,
      "eval_loss": 0.3036384880542755,
      "eval_roc_auc": 0.857778941854374,
      "eval_runtime": 5.4523,
      "eval_samples_per_second": 350.13,
      "eval_steps_per_second": 43.835,
      "step": 2438
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.1816242821985235e-05,
      "loss": 0.2862,
      "step": 2500
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.017555373256768e-05,
      "loss": 0.2544,
      "step": 3000
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.534864643150123e-06,
      "loss": 0.2555,
      "step": 3500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7946568884232582,
      "eval_f1": 0.8135683760683762,
      "eval_loss": 0.34248924255371094,
      "eval_roc_auc": 0.858040859088528,
      "eval_runtime": 4.9485,
      "eval_samples_per_second": 385.776,
      "eval_steps_per_second": 48.298,
      "step": 3657
    },
    {
      "epoch": 3.28,
      "learning_rate": 6.894175553732568e-06,
      "loss": 0.2306,
      "step": 4000
    },
    {
      "epoch": 3.69,
      "learning_rate": 5.253486464315013e-06,
      "loss": 0.2173,
      "step": 4500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8114195914091147,
      "eval_f1": 0.8226875165650676,
      "eval_loss": 0.35695233941078186,
      "eval_roc_auc": 0.8656364588789941,
      "eval_runtime": 4.8414,
      "eval_samples_per_second": 394.309,
      "eval_steps_per_second": 49.366,
      "step": 4876
    },
    {
      "epoch": 4.1,
      "learning_rate": 3.612797374897457e-06,
      "loss": 0.2049,
      "step": 5000
    },
    {
      "epoch": 4.51,
      "learning_rate": 1.9753896636587367e-06,
      "loss": 0.1896,
      "step": 5500
    },
    {
      "epoch": 4.92,
      "learning_rate": 3.347005742411813e-07,
      "loss": 0.1873,
      "step": 6000
    }
  ],
  "max_steps": 6095,
  "num_train_epochs": 5,
  "total_flos": 3156308559065088.0,
  "trial_name": null,
  "trial_params": null
}