AraBERT_token_classification__AraEval24_truncated_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: 2.0021
- Precision: 0.1263
- Recall: 0.1171
- F1: 0.1215
- Accuracy: 0.5544
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 | 479 | 1.7309 | 0.0864 | 0.0189 | 0.0310 | 0.5847 |
1.6653 | 2.0 | 958 | 1.6503 | 0.0855 | 0.0393 | 0.0539 | 0.5793 |
1.3608 | 3.0 | 1437 | 1.6761 | 0.1075 | 0.0579 | 0.0753 | 0.5869 |
1.1267 | 4.0 | 1916 | 1.7633 | 0.1003 | 0.0786 | 0.0882 | 0.5442 |
0.9119 | 5.0 | 2395 | 1.7995 | 0.1050 | 0.0877 | 0.0956 | 0.5442 |
0.783 | 6.0 | 2874 | 1.8613 | 0.1151 | 0.0937 | 0.1033 | 0.5607 |
0.6667 | 7.0 | 3353 | 1.9148 | 0.1155 | 0.1061 | 0.1106 | 0.5472 |
0.5967 | 8.0 | 3832 | 1.9480 | 0.1267 | 0.1175 | 0.1219 | 0.5511 |
0.5397 | 9.0 | 4311 | 1.9909 | 0.1235 | 0.1126 | 0.1178 | 0.5487 |
0.4948 | 10.0 | 4790 | 2.0021 | 0.1263 | 0.1171 | 0.1215 | 0.5544 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.2
- Tokenizers 0.13.3
- Downloads last month
- 3