Downloads · 30 days
10
23% of all-time downloads
finetuned_byT5base_per_translit
lowresource-igt/finetuned_byT5base_per_translit
finetuned_byT5base_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
44
Public
Parameters
582M
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026
- SHA
- 895bcdf4
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_byT5base_per_translit
This model is a fine-tuned version of google/byt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3234
- Chrf++: 14.7213
- Gen Len: 81.7721
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 |
|---|---|---|---|---|---|
| 30.6052 | 1.9 | 38 | 2.7215 | 5.5988 | 188.3897 |
| 30.6052 | 3.8 | 76 | 2.5044 | 9.1409 | 188.2206 |
| 26.2374 | 5.7 | 114 | 2.2479 | 11.1783 | 186.1691 |
| 26.2374 | 7.6 | 152 | 2.1132 | 11.0574 | 143.3529 |
| 26.2374 | 9.5 | 190 | 2.0706 | 11.5096 | 67.4485 |
| 13.8560 | 11.4 | 228 | 2.1101 | 12.1579 | 56.6838 |
| 13.8560 | 13.3 | 266 | 2.0116 | 12.7105 | 58.8382 |
| 8.1494 | 15.2 | 304 | 2.0147 | 12.9359 | 63.7941 |
| 8.1494 | 17.1 | 342 | 1.9953 | 13.5755 | 83.0294 |
| 8.1494 | 19.0 | 380 | 1.9592 | 14.3697 | 75.3309 |
| 5.2876 | 20.9 | 418 | 2.0457 | 14.5881 | 76.1324 |
| 5.2876 | 22.8 | 456 | 2.0887 | 14.4596 | 79.6544 |
| 5.2876 | 24.7 | 494 | 2.0152 | 15.788 | 72.9044 |
| 3.3345 | 26.6 | 532 | 2.1208 | 14.6692 | 86.0368 |
| 3.3345 | 28.5 | 570 | 2.0688 | 14.6077 | 78.75 |
| 1.9113 | 30.4 | 608 | 2.3234 | 14.7213 | 81.7721 |
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 10, 2026
- Updated
- Jul 10, 2026