Downloads · 30 days
3
3% of all-time downloads
nougatArbic_AHRXjawi
bustamiyusoef/nougatArbic_AHRXjawi
nougatArbic_AHRXjawi is a image-text-to-text model from bustamiyusoef. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
87
Public
Parameters
349M
698 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors698 MB · 99%
Parameter types
How the weights are stored.
BF16349M · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
_finetunned_nougat_AHR_jawi
This model is a fine-tuned version of bustamiyusoef/_base_nougat_AHR on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2215
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4421 | 0.996 | 83 | 1.3987 |
| 0.9271 | 1.992 | 166 | 0.7992 |
| 0.6591 | 3.0 | 250 | 0.5874 |
| 0.5797 | 3.996 | 333 | 0.4766 |
| 0.5308 | 4.992 | 416 | 0.4747 |
| 0.4441 | 6.0 | 500 | 0.3578 |
| 0.3555 | 6.996 | 583 | 0.3452 |
| 0.319 | 7.992 | 666 | 0.3231 |
| 0.2794 | 9.0 | 750 | 0.3032 |
| 0.2817 | 9.996 | 833 | 0.2769 |
| 0.2337 | 10.992 | 916 | 0.2796 |
| 0.2344 | 12.0 | 1000 | 0.2497 |
| 0.1966 | 12.996 | 1083 | 0.2579 |
| 0.2119 | 13.992 | 1166 | 0.2385 |
| 0.1604 | 15.0 | 1250 | 0.2364 |
| 0.1207 | 15.996 | 1333 | 0.2336 |
| 0.1452 | 16.992 | 1416 | 0.2250 |
| 0.1255 | 18.0 | 1500 | 0.2282 |
| 0.1294 | 18.996 | 1583 | 0.2304 |
| 0.1016 | 19.992 | 1666 | 0.2202 |
| 0.1195 | 21.0 | 1750 | 0.2245 |
| 0.1382 | 21.996 | 1833 | 0.2202 |
| 0.1201 | 22.992 | 1916 | 0.2178 |
| 0.1185 | 24.0 | 2000 | 0.2150 |
| 0.1149 | 24.996 | 2083 | 0.2264 |
| 0.1011 | 25.992 | 2166 | 0.2190 |
| 0.1046 | 27.0 | 2250 | 0.2215 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- cc-by-nc-4.0
- Created
- Jan 8, 2025
- Updated
- Jan 8, 2025