cf-bert-finetuned2
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3719
- F1: 0.5684
- Roc Auc: 0.7143
- Accuracy: 0.2743
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4143 | 1.0 | 452 | 0.4147 | 0.3017 | 0.5861 | 0.1018 |
| 0.3625 | 2.0 | 904 | 0.3660 | 0.5140 | 0.6798 | 0.2677 |
| 0.3269 | 3.0 | 1356 | 0.3536 | 0.5357 | 0.6930 | 0.2942 |
| 0.2977 | 4.0 | 1808 | 0.3556 | 0.5574 | 0.7066 | 0.2931 |
| 0.263 | 5.0 | 2260 | 0.3588 | 0.5656 | 0.7131 | 0.2909 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1