DALPA_new_GER_3domains
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: 1.0282
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 48
- 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 |
|---|---|---|---|
| 9.6354 | 1.0 | 103 | 1.7235 |
| 7.6734 | 2.0 | 206 | 1.4384 |
| 5.9733 | 3.0 | 309 | 1.2603 |
| 5.4526 | 4.0 | 412 | 1.1576 |
| 4.895 | 5.0 | 515 | 1.0935 |
| 4.8102 | 6.0 | 618 | 1.0553 |
| 4.6399 | 7.0 | 721 | 1.0355 |
| 4.5897 | 8.0 | 824 | 1.0294 |
| 4.698 | 9.0 | 927 | 1.0284 |
| 4.2359 | 10.0 | 1030 | 1.0293 |
| 4.5866 | 11.0 | 1133 | 1.0291 |
| 4.4889 | 12.0 | 1236 | 1.0288 |
| 4.5006 | 13.0 | 1339 | 1.0285 |
| 4.5055 | 14.0 | 1442 | 1.0282 |
| 4.7412 | 14.8613 | 1530 | 1.0282 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 4.1.1
- Tokenizers 0.21.0
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for bustamiyusoef/DALPA_new_GER_3domains
Base model
facebook/nougat-base