Downloads · 30 days
8
13% of all-time downloads
finetuned_byT5large_jje_translit
lowresource-igt/finetuned_byT5large_jje_translit
finetuned_byT5large_jje_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
63
Public
Parameters
1.2B
9.8 GB on disk
Likes
1
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 6, 2026
- Updated
- Jul 13, 2026
- SHA
- 3a608ca3
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_jje
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: 0.8383
- Chrf++: 48.3125
- Gen Len: 79.3886
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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|---|
| 53.9502 | 2.0 | 44 | 3.5968 | 4.3636 | 187.8531 |
| 53.9502 | 4.0 | 88 | 3.3390 | 3.5972 | 182.0284 |
| 45.9349 | 6.0 | 132 | 3.0423 | 3.7864 | 186.7962 |
| 45.9349 | 8.0 | 176 | 2.5900 | 4.534 | 130.4692 |
| 27.4218 | 10.0 | 220 | 2.0768 | 7.4747 | 183.0 |
| 27.4218 | 12.0 | 264 | 1.6634 | 9.8867 | 184.8389 |
| 15.6772 | 14.0 | 308 | 1.3819 | 11.826 | 235.4123 |
| 15.6772 | 16.0 | 352 | 1.1647 | 16.806 | 102.4171 |
| 15.6772 | 18.0 | 396 | 0.9299 | 19.187 | 136.2796 |
| 9.8684 | 20.0 | 440 | 0.8869 | 18.816 | 142.6493 |
| 9.8684 | 22.0 | 484 | 0.8606 | 13.5508 | 409.5308 |
| 6.5886 | 24.0 | 528 | 0.8187 | 20.2269 | 105.2844 |
| 6.5886 | 26.0 | 572 | 0.8177 | 20.7708 | 230.7725 |
| 4.5775 | 28.0 | 616 | 0.8159 | 27.1465 | 110.763 |
| 4.5775 | 30.0 | 660 | 0.8324 | 24.8154 | 254.1185 |
| 3.3463 | 32.0 | 704 | 0.8108 | 30.2383 | 135.5308 |
| 3.3463 | 34.0 | 748 | 0.8084 | 33.5409 | 137.8294 |
| 3.3463 | 36.0 | 792 | 0.8288 | 31.1693 | 225.8626 |
| 2.3131 | 38.0 | 836 | 0.7869 | 40.0883 | 88.0569 |
| 2.3131 | 40.0 | 880 | 0.8891 | 40.0251 | 97.5403 |
| 1.6347 | 42.0 | 924 | 0.8600 | 42.8237 | 105.5687 |
| 1.6347 | 44.0 | 968 | 0.8726 | 42.9837 | 89.9242 |
| 1.1237 | 46.0 | 1012 | 0.9035 | 42.8499 | 90.5498 |
| 1.1237 | 48.0 | 1056 | 0.9364 | 45.9579 | 90.8483 |
| 0.8700 | 50.0 | 1100 | 0.8976 | 42.2744 | 82.3602 |
| 0.8700 | 52.0 | 1144 | 0.8949 | 46.6342 | 98.0379 |
| 0.8700 | 54.0 | 1188 | 0.9594 | 48.9761 | 89.3175 |
| 0.7185 | 56.0 | 1232 | 0.8942 | 48.8937 | 100.4028 |
| 0.7185 | 58.0 | 1276 | 0.9473 | 50.4423 | 97.0237 |
| 0.4533 | 60.0 | 1320 | 0.8314 | 51.7172 | 93.7915 |
| 0.4533 | 62.0 | 1364 | 0.9526 | 45.2679 | 160.4028 |
| 0.2788 | 64.0 | 1408 | 0.9636 | 50.2127 | 86.5687 |
| 0.2788 | 66.0 | 1452 | 0.8383 | 48.3125 | 79.3886 |
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 6, 2026
- Updated
- Jul 13, 2026