AraBERT_token_classification_AraEval24_multi_span_n_duplicates
This model is a fine-tuned version of aubmindlab/bert-base-arabert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9263
- Precision: 0.1033
- Recall: 0.1042
- F1: 0.1037
- Accuracy: 0.6847
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: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|---|---|---|---|
1.2794 | 1.0 | 777 | 1.3310 | 0.0297 | 0.0020 | 0.0037 | 0.7241 |
1.0082 | 2.0 | 1554 | 1.2594 | 0.1001 | 0.0446 | 0.0617 | 0.7157 |
0.8023 | 3.0 | 2331 | 1.2844 | 0.0915 | 0.0608 | 0.0731 | 0.7048 |
0.5636 | 4.0 | 3108 | 1.4725 | 0.1060 | 0.1015 | 0.1037 | 0.6721 |
0.4528 | 5.0 | 3885 | 1.5490 | 0.1042 | 0.1042 | 0.1042 | 0.6820 |
0.317 | 6.0 | 4662 | 1.6573 | 0.1091 | 0.1075 | 0.1083 | 0.6858 |
0.2821 | 7.0 | 5439 | 1.7894 | 0.1089 | 0.1128 | 0.1108 | 0.6812 |
0.2045 | 8.0 | 6216 | 1.8657 | 0.1059 | 0.0995 | 0.1026 | 0.6892 |
0.1931 | 9.0 | 6993 | 1.8792 | 0.1015 | 0.1128 | 0.1068 | 0.6798 |
0.1587 | 10.0 | 7770 | 1.9263 | 0.1033 | 0.1042 | 0.1037 | 0.6847 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3
- Downloads last month
- 7