bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0569
- Precision: 0.9337
- Recall: 0.9504
- F1: 0.9420
- Accuracy: 0.9862
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0 | 0 | 2.2721 | 0.0093 | 0.0820 | 0.0167 | 0.0508 |
| 0.2520 | 1.0 | 110 | 0.0747 | 0.8501 | 0.9054 | 0.8769 | 0.9740 |
| 0.0643 | 2.0 | 220 | 0.0744 | 0.8713 | 0.9162 | 0.8932 | 0.9758 |
| 0.0385 | 3.0 | 330 | 0.0615 | 0.9113 | 0.9337 | 0.9224 | 0.9825 |
| 0.0240 | 4.0 | 440 | 0.0581 | 0.9234 | 0.9433 | 0.9332 | 0.9840 |
| 0.0119 | 5.0 | 550 | 0.0573 | 0.9338 | 0.9488 | 0.9412 | 0.9853 |
| 0.0084 | 6.0 | 660 | 0.0569 | 0.9337 | 0.9504 | 0.9420 | 0.9862 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.23.1