AraBERT_token_classification__AraEval24_merged_rassd_fixed
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: 0.8835
- Precision: 0.0974
- Recall: 0.0209
- F1: 0.0344
- Accuracy: 0.8600
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 |
---|---|---|---|---|---|---|---|
0.6721 | 1.0 | 2878 | 0.7894 | 0.05 | 0.0002 | 0.0005 | 0.8632 |
0.6093 | 2.0 | 5756 | 0.7914 | 0.0841 | 0.0033 | 0.0064 | 0.8636 |
0.5514 | 3.0 | 8634 | 0.7789 | 0.1141 | 0.0042 | 0.0081 | 0.8633 |
0.5117 | 4.0 | 11512 | 0.7879 | 0.1026 | 0.0129 | 0.0229 | 0.8623 |
0.4447 | 5.0 | 14390 | 0.8013 | 0.0881 | 0.0053 | 0.0100 | 0.8628 |
0.4371 | 6.0 | 17268 | 0.8165 | 0.1255 | 0.0151 | 0.0270 | 0.8630 |
0.415 | 7.0 | 20146 | 0.8406 | 0.0984 | 0.0116 | 0.0208 | 0.8623 |
0.3919 | 8.0 | 23024 | 0.8537 | 0.0999 | 0.0173 | 0.0295 | 0.8616 |
0.3611 | 9.0 | 25902 | 0.8645 | 0.1039 | 0.0183 | 0.0311 | 0.8614 |
0.3518 | 10.0 | 28780 | 0.8835 | 0.0974 | 0.0209 | 0.0344 | 0.8600 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.2
- Tokenizers 0.13.3
- Downloads last month
- 2