Downloads · 30 days
26
67% of all-time downloads
finetuned_byT5large_per_joint
Tsedeniya/finetuned_byT5large_per_joint
finetuned_byT5large_per_joint is a machine learning model from Tsedeniya. 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
39
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
- Oct 11, 2026
- Updated
- Oct 11, 2026
- SHA
- c0d1938f
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_joint
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: 2.6964
- Chrf++: 15.9326
- Gen Len: 105.2059
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: 4
- seed: 9030
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 |
|---|---|---|---|---|---|
| 46.1494 | 1.95 | 78 | 2.4310 | 4.1149 | 189.5882 |
| 41.9528 | 3.9 | 156 | 2.1949 | 6.2695 | 187.6176 |
| 25.3338 | 5.85 | 234 | 1.8638 | 12.9422 | 90.7941 |
| 13.6044 | 7.8 | 312 | 1.5267 | 19.5627 | 116.5294 |
| 13.6044 | 9.75 | 390 | 1.4227 | 19.462 | 131.4118 |
| 7.4640 | 11.7 | 468 | 1.5455 | 20.6241 | 127.3529 |
| 3.8894 | 13.65 | 546 | 1.7138 | 21.9822 | 133.3824 |
| 2.5303 | 15.6 | 624 | 1.7222 | 20.7415 | 127.3824 |
| 1.8806 | 17.55 | 702 | 1.8453 | 19.9191 | 124.8824 |
| 1.8806 | 19.5 | 780 | 1.9262 | 19.5932 | 123.1176 |
| 1.4053 | 21.45 | 858 | 1.9117 | 20.0532 | 114.5588 |
| 0.6436 | 23.4 | 936 | 2.3013 | 18.2787 | 116.9412 |
| 0.4878 | 25.35 | 1014 | 2.3362 | 18.3594 | 123.1765 |
| 0.4878 | 27.3 | 1092 | 2.1512 | 19.7506 | 125.2647 |
| 0.3544 | 29.25 | 1170 | 2.3554 | 18.4894 | 125.2647 |
| 0.3294 | 31.2 | 1248 | 2.4870 | 19.0701 | 115.6471 |
| 0.2741 | 33.15 | 1326 | 2.1730 | 19.9554 | 121.4706 |
| 0.2418 | 35.1 | 1404 | 2.4314 | 16.9357 | 109.5 |
| 0.2418 | 37.05 | 1482 | 2.4573 | 17.0153 | 105.2647 |
| 0.2145 | 39.0 | 1560 | 2.5105 | 19.3985 | 114.1765 |
| 0.2023 | 40.95 | 1638 | 2.3884 | 18.2469 | 114.2647 |
| 0.2146 | 42.9 | 1716 | 2.6964 | 15.9326 | 105.2059 |
Framework versions
- Transformers 5.5.0
- Pytorch 2.12.1+cu130
- Datasets 4.3.0
- Tokenizers 0.22.2
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Oct 11, 2026
- Updated
- Oct 11, 2026