_Nougat_gerXehwt_01
This model is a fine-tuned version of facebook/nougat-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3299
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.4535 | 1.0 | 194 | 1.3974 |
| 6.7708 | 2.0 | 388 | 1.2762 |
| 6.261 | 3.0 | 582 | 1.2291 |
| 5.0723 | 4.0 | 776 | 1.2160 |
| 4.3433 | 5.0 | 970 | 1.2350 |
| 4.1106 | 6.0 | 1164 | 1.2587 |
| 4.1372 | 7.0 | 1358 | 1.2843 |
| 3.7315 | 8.0 | 1552 | 1.2992 |
| 3.3733 | 9.0 | 1746 | 1.3299 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.5.0
- Tokenizers 0.21.0
- Downloads last month
- 6
Model tree for bustamiyusoef/_Nougat_gerXehwt_01
Base model
facebook/nougat-base