berel_finetuned_on_HB_3_epochs
This model is a fine-tuned version of dicta-il/BEREL on the None dataset. It achieves the following results on the evaluation set:
- Loss: 8.5156
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.139 | 0.2153 | 500 | 8.6571 |
| 8.6879 | 0.4307 | 1000 | 8.6309 |
| 8.6526 | 0.6460 | 1500 | 8.6215 |
| 8.631 | 0.8613 | 2000 | 8.6143 |
| 8.7418 | 1.0767 | 2500 | 8.6499 |
| 8.6406 | 1.2920 | 3000 | 8.6562 |
| 8.577 | 1.5073 | 3500 | 8.5696 |
| 8.6103 | 1.7227 | 4000 | 8.6186 |
| 8.5473 | 1.9380 | 4500 | 8.5872 |
| 8.4976 | 2.1533 | 5000 | 8.5632 |
| 8.4777 | 2.3686 | 5500 | 8.6354 |
| 8.4708 | 2.5840 | 6000 | 8.5897 |
| 8.4545 | 2.7993 | 6500 | 8.5156 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 1
Model tree for martijn75/berel_finetuned_on_HB_3_epochs
Base model
dicta-il/BEREL