DANN_CL_new_selfsupervised_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: 9.7379
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 |
|---|---|---|---|
| 5.471 | 1.0 | 103 | 0.7024 |
| 5.3452 | 2.0 | 206 | 0.9035 |
| 5.3489 | 3.0 | 309 | 0.9306 |
| 79.1152 | 4.0 | 412 | 11.6010 |
| 64.1155 | 5.0 | 515 | 10.3075 |
| 119.3231 | 6.0 | 618 | 9.7379 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 4.1.1
- Tokenizers 0.21.0
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for bustamiyusoef/DANN_CL_new_selfsupervised_GER_3domains
Base model
facebook/nougat-base