trainer_state.json

{
  "best_metric": 0.007663697935640812,
  "best_model_checkpoint": "codebert-base-Password_Strength_Classifier/checkpoint-25113",
  "epoch": 3.0,
  "global_step": 25113,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9999203599729225e-05,
      "loss": 1.1098,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0438,
      "step": 8371
    },
    {
      "epoch": 1.0,
      "eval_Macro F1": 0.9935141612116123,
      "eval_Macro Precision": 0.9907572834685863,
      "eval_Macro Recall": 0.9963461893460771,
      "eval_Micro F1": 0.9955795164349397,
      "eval_Micro Precision": 0.9955795164349397,
      "eval_Micro Recall": 0.9955795164349397,
      "eval_Weighted F1": 0.9955981682214771,
      "eval_Weighted Precision": 0.9956511554693804,
      "eval_Weighted Recall": 0.9955795164349397,
      "eval_accuracy": 0.9955795164349397,
      "eval_loss": 0.011203642003238201,
      "eval_runtime": 4218.6885,
      "eval_samples_per_second": 31.745,
      "eval_steps_per_second": 0.496,
      "step": 8371
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0133,
      "step": 16742
    },
    {
      "epoch": 2.0,
      "eval_Macro F1": 0.9950606828761922,
      "eval_Macro Precision": 0.9935094748560319,
      "eval_Macro Recall": 0.9966331855184408,
      "eval_Micro F1": 0.9966473021609593,
      "eval_Micro Precision": 0.9966473021609593,
      "eval_Micro Recall": 0.9966473021609593,
      "eval_Weighted F1": 0.9966547367208318,
      "eval_Weighted Precision": 0.9966719846981876,
      "eval_Weighted Recall": 0.9966473021609593,
      "eval_accuracy": 0.9966473021609593,
      "eval_loss": 0.009153525345027447,
      "eval_runtime": 4146.8808,
      "eval_samples_per_second": 32.295,
      "eval_steps_per_second": 0.505,
      "step": 16742
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.0067,
      "step": 25113
    },
    {
      "epoch": 3.0,
      "eval_Macro F1": 0.9962698425655323,
      "eval_Macro Precision": 0.9947514976785458,
      "eval_Macro Recall": 0.9978107425679793,
      "eval_Micro F1": 0.9974686757963591,
      "eval_Micro Precision": 0.9974686757963591,
      "eval_Micro Recall": 0.9974686757963591,
      "eval_Weighted F1": 0.9974744654630983,
      "eval_Weighted Precision": 0.9974905219201232,
      "eval_Weighted Recall": 0.9974686757963591,
      "eval_accuracy": 0.9974686757963591,
      "eval_loss": 0.007663697935640812,
      "eval_runtime": 4612.4931,
      "eval_samples_per_second": 29.035,
      "eval_steps_per_second": 0.454,
      "step": 25113
    },
    {
      "epoch": 3.0,
      "step": 25113,
      "total_flos": 2.394979350054543e+16,
      "train_loss": 0.021318447113758642,
      "train_runtime": 180269.7266,
      "train_samples_per_second": 8.915,
      "train_steps_per_second": 0.139
    }
  ],
  "max_steps": 25113,
  "num_train_epochs": 3,
  "total_flos": 2.394979350054543e+16,
  "trial_name": null,
  "trial_params": null
}