AraBERT_token_classification_AraEval24_18_labels_augmented_fixed2
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: 0.8169
- Precision: 0.0952
- Recall: 0.0280
- F1: 0.0432
- Accuracy: 0.8714
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 |
---|---|---|---|---|---|---|---|
0.684 | 1.0 | 3215 | 0.7004 | 0.0 | 0.0 | 0.0 | 0.8767 |
0.5935 | 2.0 | 6430 | 0.6946 | 0.0909 | 0.0005 | 0.0010 | 0.8765 |
0.5262 | 3.0 | 9645 | 0.7115 | 0.0952 | 0.0097 | 0.0176 | 0.8755 |
0.4585 | 4.0 | 12860 | 0.7140 | 0.0788 | 0.0204 | 0.0324 | 0.8718 |
0.4415 | 5.0 | 16075 | 0.7314 | 0.0982 | 0.0104 | 0.0188 | 0.8750 |
0.39 | 6.0 | 19290 | 0.7542 | 0.0942 | 0.0167 | 0.0284 | 0.8734 |
0.3668 | 7.0 | 22505 | 0.7570 | 0.0947 | 0.0230 | 0.0371 | 0.8721 |
0.3314 | 8.0 | 25720 | 0.8040 | 0.0887 | 0.0290 | 0.0437 | 0.8712 |
0.308 | 9.0 | 28935 | 0.7975 | 0.0977 | 0.0295 | 0.0454 | 0.8714 |
0.3007 | 10.0 | 32150 | 0.8169 | 0.0952 | 0.0280 | 0.0432 | 0.8714 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.2
- Tokenizers 0.13.3
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.