distilbert-base-multilingual-cased-finetuned-ner-harem
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1777
- Precision: 0.7455
- Recall: 0.7780
- F1: 0.7614
- Accuracy: 0.9616
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 282 | 0.2251 | 0.5886 | 0.6203 | 0.6040 | 0.9414 |
| 0.2833 | 2.0 | 564 | 0.1686 | 0.6566 | 0.6784 | 0.6673 | 0.9505 |
| 0.2833 | 3.0 | 846 | 0.1603 | 0.6795 | 0.7303 | 0.7040 | 0.9565 |
| 0.0914 | 4.0 | 1128 | 0.1642 | 0.7310 | 0.7386 | 0.7348 | 0.9582 |
| 0.0914 | 5.0 | 1410 | 0.1545 | 0.7385 | 0.7676 | 0.7528 | 0.9595 |
| 0.0408 | 6.0 | 1692 | 0.1782 | 0.7179 | 0.7552 | 0.7361 | 0.9565 |
| 0.0408 | 7.0 | 1974 | 0.1840 | 0.7324 | 0.7552 | 0.7436 | 0.9599 |
| 0.0193 | 8.0 | 2256 | 0.1839 | 0.7324 | 0.7552 | 0.7436 | 0.9590 |
| 0.0107 | 9.0 | 2538 | 0.1788 | 0.7571 | 0.7697 | 0.7634 | 0.9624 |
| 0.0107 | 10.0 | 2820 | 0.1777 | 0.7455 | 0.7780 | 0.7614 | 0.9616 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 22