bert-base-cased-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: 0.1896
- Precision: 0.8500
- Recall: 0.8593
- F1: 0.8546
- Accuracy: 0.9505
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1881 | 1.0 | 1105 | 0.1666 | 0.8345 | 0.8367 | 0.8356 | 0.9451 |
0.1376 | 2.0 | 2210 | 0.1675 | 0.8473 | 0.8406 | 0.8439 | 0.9477 |
0.0959 | 3.0 | 3315 | 0.1670 | 0.8416 | 0.8593 | 0.8504 | 0.9492 |
0.0704 | 4.0 | 4420 | 0.1787 | 0.8492 | 0.8575 | 0.8533 | 0.9499 |
0.0542 | 5.0 | 5525 | 0.1896 | 0.8500 | 0.8593 | 0.8546 | 0.9505 |
Framework versions
- Transformers 4.41.2
- Pytorch 1.13.1
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 8