AraBERT_token_classification__AraEval24_trun_concat
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: 1.3885
- Precision: 0.0303
- Recall: 0.0554
- F1: 0.0392
- Accuracy: 0.6335
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 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 268 | 0.9800 | 0.0034 | 0.0002 | 0.0005 | 0.8620 |
1.5757 | 2.0 | 536 | 0.9902 | 0.0222 | 0.0176 | 0.0196 | 0.8193 |
1.5757 | 3.0 | 804 | 1.0814 | 0.0194 | 0.0282 | 0.0230 | 0.7296 |
1.1715 | 4.0 | 1072 | 1.2076 | 0.0216 | 0.0386 | 0.0277 | 0.6544 |
1.1715 | 5.0 | 1340 | 1.2372 | 0.0313 | 0.0645 | 0.0422 | 0.6457 |
0.9092 | 6.0 | 1608 | 1.2709 | 0.0303 | 0.0579 | 0.0397 | 0.6474 |
0.9092 | 7.0 | 1876 | 1.3102 | 0.0303 | 0.0575 | 0.0397 | 0.6427 |
0.7262 | 8.0 | 2144 | 1.3638 | 0.0290 | 0.0537 | 0.0376 | 0.6311 |
0.7262 | 9.0 | 2412 | 1.4512 | 0.0290 | 0.0561 | 0.0383 | 0.6109 |
0.635 | 10.0 | 2680 | 1.3885 | 0.0303 | 0.0554 | 0.0392 | 0.6335 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.2
- Tokenizers 0.13.3
- Downloads last month
- 5
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.