BERT_msda_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: 0.3990
- Accuracy: 0.8603
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 |
|---|---|---|---|---|
| No log | 1.0 | 2952 | 0.3707 | 0.8542 |
| 0.3898 | 2.0 | 5904 | 0.3692 | 0.8641 |
| 0.3898 | 3.0 | 8856 | 0.3990 | 0.8603 |
Framework versions
- Transformers 4.32.0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1