Downloads · 30 days
5
16% of all-time downloads
finetuned_byT5large_per_translit
lowresource-igt/finetuned_byT5large_per_translit
finetuned_byT5large_per_translit is a machine learning model from lowresource-igt. Use it for the machine learning 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
31
Public
Parameters
1.2B
4.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.9 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026
- SHA
- b9909cdd
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. -->
finetuned_byT5large_per_translit
This model is a fine-tuned version of google/byt5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0475
- Chrf++: 13.2966
- Gen Len: 70.3382
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Chrf++ | Gen Len |
|---|---|---|---|---|---|
| 52.7988 | 1.95 | 78 | 2.5268 | 7.122 | 183.3971 |
| 44.4803 | 3.9 | 156 | 2.2769 | 7.3584 | 158.6471 |
| 26.0012 | 5.85 | 234 | 1.9600 | 11.6324 | 57.9632 |
| 15.4409 | 7.8 | 312 | 1.8427 | 11.7175 | 53.8897 |
| 15.4409 | 9.75 | 390 | 1.6761 | 14.3345 | 70.9191 |
| 9.2887 | 11.7 | 468 | 1.6699 | 15.1494 | 74.7206 |
| 5.2223 | 13.65 | 546 | 1.7266 | 14.9425 | 75.1029 |
| 3.2055 | 15.6 | 624 | 1.9094 | 15.1792 | 70.9559 |
| 2.1860 | 17.55 | 702 | 2.1180 | 14.3851 | 75.2794 |
| 2.1860 | 19.5 | 780 | 1.9884 | 15.1437 | 75.3603 |
| 1.6991 | 21.45 | 858 | 2.3153 | 15.5552 | 77.6691 |
| 1.1873 | 23.4 | 936 | 2.3674 | 14.7176 | 74.2721 |
| 0.6295 | 25.35 | 1014 | 2.3239 | 13.9219 | 69.4779 |
| 0.6295 | 27.3 | 1092 | 2.4456 | 13.5737 | 71.3971 |
| 0.4863 | 29.25 | 1170 | 2.5873 | 14.146 | 67.5 |
| 0.3892 | 31.2 | 1248 | 2.6454 | 15.3789 | 79.1544 |
| 0.3635 | 33.15 | 1326 | 2.9488 | 15.6994 | 81.0221 |
| 0.2951 | 35.1 | 1404 | 2.7358 | 14.8269 | 84.0368 |
| 0.2951 | 37.05 | 1482 | 2.8879 | 13.8636 | 69.8676 |
| 0.2771 | 39.0 | 1560 | 2.6495 | 13.2987 | 64.0368 |
| 0.2789 | 40.95 | 1638 | 2.6585 | 15.1878 | 73.8897 |
| 0.2388 | 42.9 | 1716 | 2.6201 | 15.0134 | 74.2794 |
| 0.2388 | 44.85 | 1794 | 2.6878 | 15.1479 | 71.6618 |
| 0.2463 | 46.8 | 1872 | 2.7575 | 14.2387 | 69.5882 |
| 0.2238 | 48.75 | 1950 | 2.2271 | 13.5865 | 65.3309 |
| 0.2214 | 50.7 | 2028 | 2.5883 | 13.7973 | 73.2794 |
| 0.2054 | 52.65 | 2106 | 2.6957 | 13.2994 | 59.6985 |
| 0.2054 | 54.6 | 2184 | 2.5756 | 13.5321 | 72.1985 |
| 0.2178 | 56.55 | 2262 | 2.6257 | 13.7851 | 65.8676 |
| 0.2135 | 58.5 | 2340 | 2.6285 | 14.4508 | 62.1985 |
| 0.1976 | 60.45 | 2418 | 2.5815 | 14.2807 | 80.6029 |
| 0.1976 | 62.4 | 2496 | 3.0475 | 13.2966 | 70.3382 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.6.0+cu124
- Datasets 5.0.0
- Tokenizers 0.22.2
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Jul 11, 2026
- Updated
- Jul 11, 2026