NougatArabic_CL_selfsupervised_DANN_GER_1
This model is a fine-tuned version of facebook/nougat-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 55.0182
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: 0.0001
- train_batch_size: 10
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 60
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.8753 | 1.0 | 82 | 1.2500 |
| 5.5042 | 2.0 | 164 | 1.0180 |
| 5.2724 | 3.0 | 246 | 1.0744 |
| 4.7891 | 4.0 | 328 | 1.0056 |
| 4.3945 | 5.0 | 410 | 0.9734 |
| 4.5137 | 6.0 | 492 | 0.9604 |
| 4.6212 | 7.0 | 574 | 0.9745 |
| 9.2208 | 8.0 | 656 | 1.4678 |
| 9.3394 | 9.0 | 738 | 1.3357 |
| 7.497 | 10.0 | 820 | 1.3624 |
| 507.5631 | 11.0 | 902 | 55.0182 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 4.0.0
- Tokenizers 0.21.0
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for bustamiyusoef/NougatArabic_CL_selfsupervised_DANN_GER_1
Base model
facebook/nougat-base