<!-- 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. -->
BERT_hard_adversarial
This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4143
- Accuracy: 0.8336
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4479 | 1.0 | 5974 | 0.3903 | 0.8340 |
| 0.387 | 2.0 | 11948 | 0.3902 | 0.8379 |
| 0.3485 | 3.0 | 17922 | 0.4143 | 0.8336 |
Framework versions
- Transformers 4.32.0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1
