bert-base-multilingual-uncased-finetuned-ner-harem
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1695
- Precision: 0.7849
- Recall: 0.7924
- F1: 0.7886
- Accuracy: 0.9673
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 | 0.2095 | 0.5957 | 0.5943 | 0.5950 | 0.9446 |
0.2657 | 2.0 | 564 | 0.1734 | 0.6925 | 0.6396 | 0.6650 | 0.9559 |
0.2657 | 3.0 | 846 | 0.1317 | 0.7370 | 0.7422 | 0.7396 | 0.9649 |
0.0834 | 4.0 | 1128 | 0.1444 | 0.7786 | 0.7637 | 0.7711 | 0.9658 |
0.0834 | 5.0 | 1410 | 0.1455 | 0.7743 | 0.7613 | 0.7677 | 0.9670 |
0.0384 | 6.0 | 1692 | 0.1487 | 0.7477 | 0.7780 | 0.7626 | 0.9641 |
0.0384 | 7.0 | 1974 | 0.1815 | 0.7817 | 0.7351 | 0.7577 | 0.9627 |
0.0187 | 8.0 | 2256 | 0.1594 | 0.7791 | 0.7995 | 0.7892 | 0.9678 |
0.0104 | 9.0 | 2538 | 0.1725 | 0.7941 | 0.7733 | 0.7836 | 0.9656 |
0.0104 | 10.0 | 2820 | 0.1695 | 0.7849 | 0.7924 | 0.7886 | 0.9673 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 8
Inference API (serverless) is not available, repository is disabled.
Model tree for GuiTap/bert-base-multilingual-uncased-finetuned-ner-harem
Base model
google-bert/bert-base-multilingual-uncased
Finetuned
this model