{
  "best_metric": 0.5194681286811829,
  "best_model_checkpoint": "distilbert_final_config_dropout/checkpoint-5154",
  "epoch": 5.0,
  "global_step": 8590,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29,
      "learning_rate": 1.970896391152503e-05,
      "loss": 0.7068,
      "step": 500
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.941792782305006e-05,
      "loss": 0.5844,
      "step": 1000
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.9126891734575087e-05,
      "loss": 0.5631,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7849462365591398,
      "eval_f1": 0.7884996645660559,
      "eval_loss": 0.5497974753379822,
      "eval_runtime": 8.1439,
      "eval_samples_per_second": 433.946,
      "eval_steps_per_second": 27.137,
      "step": 1718
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.8835855646100117e-05,
      "loss": 0.4957,
      "step": 2000
    },
    {
      "epoch": 1.46,
      "learning_rate": 1.8544819557625148e-05,
      "loss": 0.4703,
      "step": 2500
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.825378346915018e-05,
      "loss": 0.4683,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7920203735144312,
      "eval_f1": 0.7952858811810856,
      "eval_loss": 0.5246105790138245,
      "eval_runtime": 8.0847,
      "eval_samples_per_second": 437.12,
      "eval_steps_per_second": 27.335,
      "step": 3436
    },
    {
      "epoch": 2.04,
      "learning_rate": 1.7962747380675206e-05,
      "loss": 0.4785,
      "step": 3500
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.7671711292200233e-05,
      "loss": 0.3916,
      "step": 4000
    },
    {
      "epoch": 2.62,
      "learning_rate": 1.7380675203725264e-05,
      "loss": 0.3933,
      "step": 4500
    },
    {
      "epoch": 2.91,
      "learning_rate": 1.708963911525029e-05,
      "loss": 0.4015,
      "step": 5000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7934352009054896,
      "eval_f1": 0.7969035613432119,
      "eval_loss": 0.5194681286811829,
      "eval_runtime": 8.124,
      "eval_samples_per_second": 435.009,
      "eval_steps_per_second": 27.203,
      "step": 5154
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.679860302677532e-05,
      "loss": 0.3422,
      "step": 5500
    },
    {
      "epoch": 3.49,
      "learning_rate": 1.650756693830035e-05,
      "loss": 0.3195,
      "step": 6000
    },
    {
      "epoch": 3.78,
      "learning_rate": 1.621653084982538e-05,
      "loss": 0.3382,
      "step": 6500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7832484436898698,
      "eval_f1": 0.7869745047177638,
      "eval_loss": 0.6190190315246582,
      "eval_runtime": 8.0892,
      "eval_samples_per_second": 436.876,
      "eval_steps_per_second": 27.32,
      "step": 6872
    },
    {
      "epoch": 4.07,
      "learning_rate": 1.592549476135041e-05,
      "loss": 0.3111,
      "step": 7000
    },
    {
      "epoch": 4.37,
      "learning_rate": 1.5634458672875437e-05,
      "loss": 0.2659,
      "step": 7500
    },
    {
      "epoch": 4.66,
      "learning_rate": 1.5343422584400468e-05,
      "loss": 0.2618,
      "step": 8000
    },
    {
      "epoch": 4.95,
      "learning_rate": 1.5052386495925495e-05,
      "loss": 0.2774,
      "step": 8500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7911714770797963,
      "eval_f1": 0.7951684998615031,
      "eval_loss": 0.6736249923706055,
      "eval_runtime": 8.1656,
      "eval_samples_per_second": 432.793,
      "eval_steps_per_second": 27.065,
      "step": 8590
    }
  ],
  "max_steps": 34360,
  "num_train_epochs": 20,
  "total_flos": 3910587551729100.0,
  "trial_name": null,
  "trial_params": null
}