AraBERT_token_classification__AraEval24_merged_rassd_aratweets_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: 0.8307
- Precision: 0.1139
- Recall: 0.0381
- F1: 0.0571
- Accuracy: 0.8586
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 |
---|---|---|---|---|---|---|---|
0.6962 | 1.0 | 3105 | 0.8159 | 0.3333 | 0.0001 | 0.0002 | 0.8633 |
0.6349 | 2.0 | 6210 | 0.7622 | 0.2091 | 0.0028 | 0.0056 | 0.8633 |
0.5356 | 3.0 | 9315 | 0.7444 | 0.1391 | 0.0113 | 0.0208 | 0.8632 |
0.5163 | 4.0 | 12420 | 0.7396 | 0.1024 | 0.0114 | 0.0205 | 0.8631 |
0.4782 | 5.0 | 15525 | 0.7700 | 0.1520 | 0.0218 | 0.0381 | 0.8635 |
0.4585 | 6.0 | 18630 | 0.7833 | 0.1281 | 0.0236 | 0.0399 | 0.8623 |
0.3992 | 7.0 | 21735 | 0.7816 | 0.1164 | 0.0358 | 0.0547 | 0.8595 |
0.4135 | 8.0 | 24840 | 0.8094 | 0.1163 | 0.0307 | 0.0486 | 0.8608 |
0.3836 | 9.0 | 27945 | 0.8221 | 0.1060 | 0.0328 | 0.0501 | 0.8593 |
0.3594 | 10.0 | 31050 | 0.8307 | 0.1139 | 0.0381 | 0.0571 | 0.8586 |
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.