{
  "best_metric": 0.9185258471432105,
  "best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-56855",
  "epoch": 5.0,
  "global_step": 56855,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.777760406488177e-05,
      "loss": 0.3022,
      "step": 11371
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9000742023250062,
      "eval_combined_score": 0.8842561971635452,
      "eval_f1": 0.8684381920020842,
      "eval_loss": 0.23946747183799744,
      "eval_runtime": 101.9205,
      "eval_samples_per_second": 396.682,
      "eval_steps_per_second": 49.588,
      "step": 11371
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.3333203048661326e-05,
      "loss": 0.1938,
      "step": 22742
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9094978976007915,
      "eval_combined_score": 0.8954708488101162,
      "eval_f1": 0.8814438000194408,
      "eval_loss": 0.22696459293365479,
      "eval_runtime": 102.26,
      "eval_samples_per_second": 395.365,
      "eval_steps_per_second": 49.423,
      "step": 22742
    },
    {
      "epoch": 3.0,
      "learning_rate": 8.888802032440885e-06,
      "loss": 0.1328,
      "step": 34113
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9166460549097205,
      "eval_combined_score": 0.9021301374395198,
      "eval_f1": 0.887614219969319,
      "eval_loss": 0.2414465695619583,
      "eval_runtime": 101.5618,
      "eval_samples_per_second": 398.083,
      "eval_steps_per_second": 49.763,
      "step": 34113
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.4444010162204425e-06,
      "loss": 0.092,
      "step": 45484
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9181795696265149,
      "eval_combined_score": 0.9044410040031075,
      "eval_f1": 0.8907024383797,
      "eval_loss": 0.2913267910480499,
      "eval_runtime": 101.8301,
      "eval_samples_per_second": 397.034,
      "eval_steps_per_second": 49.632,
      "step": 45484
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.0656,
      "step": 56855
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9185258471432105,
      "eval_combined_score": 0.9047986378573195,
      "eval_f1": 0.8910714285714285,
      "eval_loss": 0.3511233627796173,
      "eval_runtime": 101.787,
      "eval_samples_per_second": 397.202,
      "eval_steps_per_second": 49.653,
      "step": 56855
    },
    {
      "epoch": 5.0,
      "step": 56855,
      "total_flos": 7.648365060516096e+16,
      "train_loss": 0.15726310307951696,
      "train_runtime": 12296.1085,
      "train_samples_per_second": 147.952,
      "train_steps_per_second": 4.624
    }
  ],
  "max_steps": 56855,
  "num_train_epochs": 5,
  "total_flos": 7.648365060516096e+16,
  "trial_name": null,
  "trial_params": null
}