Downloads · 30 days
7
17% of all-time downloads
AraBERT_token_classification__AraEval24_18_techs_translated_aug_trun_rand
MM2157/AraBERT_token_classification__AraEval24_18_techs_translated_aug_trun_rand
AraBERT_token_classification__AraEval24_18_techs_translated_aug_trun_rand is a token classification model from MM2157. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
42
Public
Repo size
5.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin539 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jul 18, 2024
- Updated
- Jul 18, 2024
- SHA
- 13c79268
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
AraBERT_token_classification__AraEval24_18_techs_translated_aug_trun_rand
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: 1.9138
- Precision: 0.0288
- Recall: 0.0563
- F1: 0.0381
- Accuracy: 0.6614
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 |
|---|---|---|---|---|---|---|---|
| 1.3417 | 1.0 | 2686 | 1.2701 | 0.0099 | 0.0178 | 0.0127 | 0.6866 |
| 1.0807 | 2.0 | 5372 | 1.1541 | 0.0232 | 0.0364 | 0.0284 | 0.7121 |
| 0.8547 | 3.0 | 8058 | 1.2004 | 0.0176 | 0.0262 | 0.0210 | 0.7066 |
| 0.6431 | 4.0 | 10744 | 1.1615 | 0.0202 | 0.0227 | 0.0214 | 0.7426 |
| 0.4806 | 5.0 | 13430 | 1.4048 | 0.0230 | 0.0318 | 0.0267 | 0.6994 |
| 0.3891 | 6.0 | 16116 | 1.6083 | 0.0237 | 0.0436 | 0.0307 | 0.6520 |
| 0.3045 | 7.0 | 18802 | 1.5851 | 0.0272 | 0.0480 | 0.0347 | 0.6685 |
| 0.2603 | 8.0 | 21488 | 1.8647 | 0.0266 | 0.0561 | 0.0361 | 0.6354 |
| 0.203 | 9.0 | 24174 | 1.8937 | 0.0249 | 0.0480 | 0.0328 | 0.6543 |
| 0.1767 | 10.0 | 26860 | 1.9138 | 0.0288 | 0.0563 | 0.0381 | 0.6614 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.2
- Tokenizers 0.13.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Jul 18, 2024
- Updated
- Jul 18, 2024