Downloads · 30 days
0
transformer_translation-en-ta
siddheswaran/transformer_translation-en-ta
transformer_translation-en-ta is a machine learning model from siddheswaran. 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.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Jul 26, 2026
Parameters
93.3M
373 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors373 MB · 99%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Jul 26, 2026
- SHA
- e605cea7
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. -->
checkpoints
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7222
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: 0.0003
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-09 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 4256
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.0510 | 1.0 | 3548 | 3.3034 |
| 2.4684 | 2.0 | 7096 | 2.9294 |
| 2.0990 | 3.0 | 10644 | 2.8268 |
| 1.9468 | 4.0 | 14192 | 2.7616 |
| 1.8410 | 5.0 | 17740 | 2.7173 |
| 1.7610 | 6.0 | 21288 | 2.7105 |
| 1.6875 | 7.0 | 24836 | 2.7027 |
| 1.6496 | 8.0 | 28384 | 2.6985 |
| 1.6112 | 9.0 | 31932 | 2.7161 |
| 1.5963 | 10.0 | 35480 | 2.7222 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2
- Library
- transformers
- Created
- Jul 4, 2026
- Updated
- Jul 26, 2026