trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.13422818791946,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.36,
      "eval_accuracy": 0.9206798866855525,
      "eval_f1": 0.9303482587064678,
      "eval_loss": 0.2345595508813858,
      "eval_precision": 0.919672131147541,
      "eval_recall": 0.9412751677852349,
      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.92      0.89      0.91       463\n           1       0.92      0.94      0.93       596\n\n    accuracy                           0.92      1059\n   macro avg       0.92      0.92      0.92      1059\nweighted avg       0.92      0.92      0.92      1059\n",
      "eval_runtime": 8.0364,
      "eval_samples_per_second": 131.775,
      "eval_steps_per_second": 8.337,
      "step": 500
    },
    {
      "epoch": 6.71,
      "learning_rate": 4e-05,
      "loss": 0.2212,
      "step": 1000
    },
    {
      "epoch": 6.71,
      "eval_accuracy": 0.9046270066100094,
      "eval_f1": 0.9141886151231945,
      "eval_loss": 0.31608325242996216,
      "eval_precision": 0.9259896729776248,
      "eval_recall": 0.9026845637583892,
      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.88      0.91      0.89       463\n           1       0.93      0.90      0.91       596\n\n    accuracy                           0.90      1059\n   macro avg       0.90      0.90      0.90      1059\nweighted avg       0.91      0.90      0.90      1059\n",
      "eval_runtime": 8.0054,
      "eval_samples_per_second": 132.285,
      "eval_steps_per_second": 8.369,
      "step": 1000
    },
    {
      "epoch": 10.07,
      "eval_accuracy": 0.9065155807365439,
      "eval_f1": 0.9167367535744324,
      "eval_loss": 0.43374723196029663,
      "eval_precision": 0.9190556492411467,
      "eval_recall": 0.9144295302013423,
      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.89      0.90      0.89       463\n           1       0.92      0.91      0.92       596\n\n    accuracy                           0.91      1059\n   macro avg       0.90      0.91      0.91      1059\nweighted avg       0.91      0.91      0.91      1059\n",
      "eval_runtime": 8.0154,
      "eval_samples_per_second": 132.12,
      "eval_steps_per_second": 8.359,
      "step": 1500
    },
    {
      "epoch": 13.42,
      "learning_rate": 2e-05,
      "loss": 0.0651,
      "step": 2000
    },
    {
      "epoch": 13.42,
      "eval_accuracy": 0.9178470254957507,
      "eval_f1": 0.9271966527196652,
      "eval_loss": 0.47431105375289917,
      "eval_precision": 0.9248747913188647,
      "eval_recall": 0.9295302013422819,
      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.91      0.90      0.91       463\n           1       0.92      0.93      0.93       596\n\n    accuracy                           0.92      1059\n   macro avg       0.92      0.92      0.92      1059\nweighted avg       0.92      0.92      0.92      1059\n",
      "eval_runtime": 8.0135,
      "eval_samples_per_second": 132.152,
      "eval_steps_per_second": 8.361,
      "step": 2000
    },
    {
      "epoch": 16.78,
      "eval_accuracy": 0.9102927289896129,
      "eval_f1": 0.9203688181056161,
      "eval_loss": 0.5537705421447754,
      "eval_precision": 0.9195979899497487,
      "eval_recall": 0.9211409395973155,
      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.90      0.90      0.90       463\n           1       0.92      0.92      0.92       596\n\n    accuracy                           0.91      1059\n   macro avg       0.91      0.91      0.91      1059\nweighted avg       0.91      0.91      0.91      1059\n",
      "eval_runtime": 8.0263,
      "eval_samples_per_second": 131.941,
      "eval_steps_per_second": 8.348,
      "step": 2500
    },
    {
      "epoch": 20.13,
      "learning_rate": 0.0,
      "loss": 0.0296,
      "step": 3000
    },
    {
      "epoch": 20.13,
      "eval_accuracy": 0.9102927289896129,
      "eval_f1": 0.9199663016006739,
      "eval_loss": 0.6190621256828308,
      "eval_precision": 0.9238578680203046,
      "eval_recall": 0.9161073825503355,
      "eval_report": "              precision    recall  f1-score   support\n\n           0       0.89      0.90      0.90       463\n           1       0.92      0.92      0.92       596\n\n    accuracy                           0.91      1059\n   macro avg       0.91      0.91      0.91      1059\nweighted avg       0.91      0.91      0.91      1059\n",
      "eval_runtime": 8.0249,
      "eval_samples_per_second": 131.965,
      "eval_steps_per_second": 8.349,
      "step": 3000
    },
    {
      "epoch": 20.13,
      "step": 3000,
      "total_flos": 5.04436515336192e+16,
      "train_loss": 0.10527635129292806,
      "train_runtime": 3964.4436,
      "train_samples_per_second": 48.431,
      "train_steps_per_second": 0.757
    }
  ],
  "max_steps": 3000,
  "num_train_epochs": 21,
  "total_flos": 5.04436515336192e+16,
  "trial_name": null,
  "trial_params": null
}