Downloads · 30 days
3
9% of all-time downloads
finetuned_glosslm_pnb_translit
lowresource-igt/finetuned_glosslm_pnb_translit
finetuned_glosslm_pnb_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
33
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 11, 2026
- Updated
- Jul 11, 2026
- SHA
- c21da98f
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_glosslm_pnb_translit
This model is a fine-tuned version of lecslab/glosslm on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5675
- Chrf++: 59.9107
- Gen Len: 68.9412
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 |
|---|---|---|---|---|---|
| 9.3545 | 1.4706 | 4 | 0.9640 | 32.7256 | 79.7059 |
| 9.3545 | 2.9412 | 8 | 0.9560 | 33.2561 | 78.5882 |
| 9.3545 | 4.0 | 12 | 0.9434 | 33.1629 | 78.0588 |
| 9.3545 | 5.4706 | 16 | 0.9256 | 33.1745 | 78.2353 |
| 9.3545 | 6.9412 | 20 | 0.9059 | 32.9811 | 79.2941 |
| 9.3545 | 8.0 | 24 | 0.8850 | 33.1525 | 78.9412 |
| 9.3545 | 9.4706 | 28 | 0.8581 | 35.531 | 76.5882 |
| 9.3545 | 10.9412 | 32 | 0.8295 | 35.5757 | 77.0 |
| 9.3545 | 12.0 | 36 | 0.8074 | 36.0071 | 76.3529 |
| 9.3545 | 13.4706 | 40 | 0.7806 | 35.7797 | 75.7647 |
| 9.3545 | 14.9412 | 44 | 0.7511 | 36.8661 | 73.0588 |
| 9.3545 | 16.0 | 48 | 0.7278 | 38.5238 | 72.6471 |
| 9.3545 | 17.4706 | 52 | 0.6999 | 41.078 | 69.7647 |
| 9.3545 | 18.9412 | 56 | 0.6732 | 41.0391 | 70.1176 |
| 9.3545 | 20.0 | 60 | 0.6489 | 42.7095 | 69.1176 |
| 9.3545 | 21.4706 | 64 | 0.6225 | 44.0069 | 66.7647 |
| 9.3545 | 22.9412 | 68 | 0.5993 | 43.6155 | 66.9412 |
| 9.3545 | 24.0 | 72 | 0.5824 | 46.4268 | 65.5882 |
| 9.3545 | 25.4706 | 76 | 0.5616 | 46.7914 | 66.7647 |
| 9.3545 | 26.9412 | 80 | 0.5417 | 46.5362 | 66.5294 |
| 9.3545 | 28.0 | 84 | 0.5286 | 50.1703 | 66.5882 |
| 9.3545 | 29.4706 | 88 | 0.5146 | 50.1734 | 66.9412 |
| 9.3545 | 30.9412 | 92 | 0.5038 | 51.1723 | 67.6471 |
| 9.3545 | 32.0 | 96 | 0.4946 | 51.8295 | 67.0 |
| 4.5494 | 33.4706 | 100 | 0.4858 | 52.3169 | 67.9412 |
| 4.5494 | 34.9412 | 104 | 0.4771 | 53.8233 | 67.8824 |
| 4.5494 | 36.0 | 108 | 0.4753 | 54.2808 | 68.2941 |
| 4.5494 | 37.4706 | 112 | 0.4735 | 56.4086 | 67.5294 |
| 4.5494 | 38.9412 | 116 | 0.4694 | 55.7997 | 67.2353 |
| 4.5494 | 40.0 | 120 | 0.4651 | 56.3586 | 67.3529 |
| 4.5494 | 41.4706 | 124 | 0.4622 | 56.9888 | 68.2353 |
| 4.5494 | 42.9412 | 128 | 0.4621 | 55.8518 | 68.5294 |
| 4.5494 | 44.0 | 132 | 0.4605 | 57.0898 | 68.6471 |
| 4.5494 | 45.4706 | 136 | 0.4630 | 58.1613 | 67.5294 |
| 4.5494 | 46.9412 | 140 | 0.4573 | 57.7822 | 68.0588 |
| 4.5494 | 48.0 | 144 | 0.4585 | 58.2382 | 68.4706 |
| 4.5494 | 49.4706 | 148 | 0.4616 | 59.2086 | 69.1765 |
| 4.5494 | 50.9412 | 152 | 0.4634 | 58.3231 | 68.8824 |
| 4.5494 | 52.0 | 156 | 0.4669 | 60.1604 | 68.4706 |
| 4.5494 | 53.4706 | 160 | 0.4701 | 61.5682 | 68.5882 |
| 4.5494 | 54.9412 | 164 | 0.4798 | 61.4659 | 68.6471 |
| 4.5494 | 56.0 | 168 | 0.4776 | 61.0306 | 68.8824 |
| 4.5494 | 57.4706 | 172 | 0.4797 | 59.9299 | 68.6471 |
| 4.5494 | 58.9412 | 176 | 0.4812 | 60.8477 | 69.1176 |
| 4.5494 | 60.0 | 180 | 0.4892 | 61.9511 | 68.3529 |
| 4.5494 | 61.4706 | 184 | 0.5022 | 61.6379 | 68.5882 |
| 4.5494 | 62.9412 | 188 | 0.5063 | 62.8867 | 68.5882 |
| 4.5494 | 64.0 | 192 | 0.5091 | 61.6728 | 68.2941 |
| 4.5494 | 65.4706 | 196 | 0.5156 | 60.7661 | 68.2941 |
| 0.9052 | 66.9412 | 200 | 0.5175 | 61.1588 | 68.3529 |
| 0.9052 | 68.0 | 204 | 0.5209 | 61.219 | 68.4118 |
| 0.9052 | 69.4706 | 208 | 0.5335 | 61.8711 | 68.3529 |
| 0.9052 | 70.9412 | 212 | 0.5233 | 61.1431 | 68.3529 |
| 0.9052 | 72.0 | 216 | 0.5299 | 60.7019 | 69.0588 |
| 0.9052 | 73.4706 | 220 | 0.5375 | 61.2184 | 68.3529 |
| 0.9052 | 74.9412 | 224 | 0.5407 | 60.2466 | 68.6471 |
| 0.9052 | 76.0 | 228 | 0.5502 | 61.3105 | 68.6471 |
| 0.9052 | 77.4706 | 232 | 0.5518 | 62.0079 | 68.7059 |
| 0.9052 | 78.9412 | 236 | 0.5583 | 61.8194 | 68.5294 |
| 0.9052 | 80.0 | 240 | 0.5651 | 61.4379 | 67.8235 |
| 0.9052 | 81.4706 | 244 | 0.5685 | 59.4843 | 67.8824 |
| 0.9052 | 82.9412 | 248 | 0.5675 | 59.9107 | 68.9412 |
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