trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "learning_rate": 1.6686666666666667e-05,
      "loss": 0.4204,
      "step": 500
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3353333333333333e-05,
      "loss": 0.3196,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.89025,
      "eval_classification_report": "              precision    recall  f1-score     support\n0              0.908031  0.951485  0.929251  3030.00000\n1              0.821818  0.698969  0.755432   970.00000\naccuracy       0.890250  0.890250  0.890250     0.89025\nmacro avg      0.864925  0.825227  0.842341  4000.00000\nweighted avg   0.887125  0.890250  0.887100  4000.00000",
      "eval_confusion_matrix": "[[2883  147]\n [ 292  678]]",
      "eval_confusion_matrix_norm": "[[0.95148515 0.04851485]\n [0.30103093 0.69896907]]",
      "eval_f1": 0.7554317548746518,
      "eval_f1_macro": 0.8423411796129907,
      "eval_f1_weighted": 0.8870995333532351,
      "eval_loss": 0.2972576320171356,
      "eval_runtime": 9.6365,
      "eval_samples_per_second": 415.089,
      "eval_steps_per_second": 25.943,
      "step": 1000
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.002e-05,
      "loss": 0.2671,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.6866666666666665e-06,
      "loss": 0.2447,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8885,
      "eval_classification_report": "              precision    recall  f1-score    support\n0              0.917582  0.936964  0.927172  3030.0000\n1              0.789183  0.737113  0.762260   970.0000\naccuracy       0.888500  0.888500  0.888500     0.8885\nmacro avg      0.853383  0.837039  0.844716  4000.0000\nweighted avg   0.886446  0.888500  0.887181  4000.0000",
      "eval_confusion_matrix": "[[2839  191]\n [ 255  715]]",
      "eval_confusion_matrix_norm": "[[0.9369637 0.0630363]\n [0.2628866 0.7371134]]",
      "eval_f1": 0.7622601279317698,
      "eval_f1_macro": 0.8447159555400194,
      "eval_f1_weighted": 0.887180706758268,
      "eval_loss": 0.3277442157268524,
      "eval_runtime": 9.6604,
      "eval_samples_per_second": 414.059,
      "eval_steps_per_second": 25.879,
      "step": 2000
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.3600000000000004e-06,
      "loss": 0.2056,
      "step": 2500
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.6666666666666667e-08,
      "loss": 0.2037,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.88675,
      "eval_classification_report": "              precision    recall  f1-score     support\n0              0.925950  0.924422  0.925186  3030.00000\n1              0.765128  0.769072  0.767095   970.00000\naccuracy       0.886750  0.886750  0.886750     0.88675\nmacro avg      0.845539  0.846747  0.846140  4000.00000\nweighted avg   0.886951  0.886750  0.886849  4000.00000",
      "eval_confusion_matrix": "[[2801  229]\n [ 224  746]]",
      "eval_confusion_matrix_norm": "[[0.92442244 0.07557756]\n [0.23092784 0.76907216]]",
      "eval_f1": 0.7670951156812339,
      "eval_f1_macro": 0.8461404562716657,
      "eval_f1_weighted": 0.886848806675738,
      "eval_loss": 0.33370330929756165,
      "eval_runtime": 9.6495,
      "eval_samples_per_second": 414.529,
      "eval_steps_per_second": 25.908,
      "step": 3000
    },
    {
      "epoch": 3.0,
      "step": 3000,
      "total_flos": 1.262933065728e+16,
      "train_loss": 0.276834108988444,
      "train_runtime": 431.6054,
      "train_samples_per_second": 111.213,
      "train_steps_per_second": 6.951
    }
  ],
  "max_steps": 3000,
  "num_train_epochs": 3,
  "total_flos": 1.262933065728e+16,
  "trial_name": null,
  "trial_params": null
}