BERT_NER_Ep5-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: 0.3553
- Precision: 0.6526
- Recall: 0.7248
- F1: 0.6868
- Accuracy: 0.9004
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 288 | 0.3675 | 0.5906 | 0.5854 | 0.5880 | 0.8802 |
| 0.4803 | 2.0 | 576 | 0.3456 | 0.5863 | 0.7371 | 0.6531 | 0.8864 |
| 0.4803 | 3.0 | 864 | 0.3273 | 0.6478 | 0.7091 | 0.6771 | 0.8987 |
| 0.2233 | 4.0 | 1152 | 0.3441 | 0.6539 | 0.7226 | 0.6865 | 0.9001 |
| 0.2233 | 5.0 | 1440 | 0.3553 | 0.6526 | 0.7248 | 0.6868 | 0.9004 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.9.0+cu111
- Datasets 1.12.1
- Tokenizers 0.10.3