metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: AraBERT_token_classification_AraEval24_back_translation_mlm1k_augmented
results: []
AraBERT_token_classification_AraEval24_back_translation_mlm1k_augmented
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: 0.9905
- Precision: 0.0511
- Recall: 0.0181
- F1: 0.0267
- Accuracy: 0.8621
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 |
---|---|---|---|---|---|---|---|
0.4984 | 1.0 | 7951 | 0.7412 | 0.0194 | 0.0011 | 0.0020 | 0.8715 |
0.4115 | 2.0 | 15902 | 0.7585 | 0.0571 | 0.0035 | 0.0066 | 0.8721 |
0.3718 | 3.0 | 23853 | 0.7859 | 0.0720 | 0.0049 | 0.0092 | 0.8724 |
0.3331 | 4.0 | 31804 | 0.8117 | 0.0431 | 0.0062 | 0.0108 | 0.8679 |
0.3017 | 5.0 | 39755 | 0.8332 | 0.0477 | 0.0097 | 0.0161 | 0.8658 |
0.2682 | 6.0 | 47706 | 0.8462 | 0.0540 | 0.0123 | 0.0200 | 0.8628 |
0.2627 | 7.0 | 55657 | 0.8597 | 0.0553 | 0.0125 | 0.0204 | 0.8636 |
0.2372 | 8.0 | 63608 | 0.9231 | 0.0556 | 0.0149 | 0.0236 | 0.8646 |
0.2208 | 9.0 | 71559 | 0.9553 | 0.0567 | 0.0160 | 0.0250 | 0.8657 |
0.2206 | 10.0 | 79510 | 0.9905 | 0.0511 | 0.0181 | 0.0267 | 0.8621 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.2
- Tokenizers 0.13.3