bert-finetuned-steel-english-news
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1012
- F1: 0.9039
- Roc Auc: 0.9426
- Accuracy: 0.6095
- Precision: 0.9016
- Recall: 0.9062
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|---|
| 0.1261 | 1.0 | 1052 | 0.1128 | 0.8874 | 0.9312 | 0.5499 | 0.8889 | 0.8859 |
| 0.096 | 2.0 | 2104 | 0.1012 | 0.9039 | 0.9426 | 0.6095 | 0.9016 | 0.9062 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1