Downloads · 30 days
3
7% of all-time downloads
mt5-small-sinhala-bias-aware-v2
anupa41222/mt5-small-sinhala-bias-aware-v2
mt5-small-sinhala-bias-aware-v2 is a machine learning model from anupa41222. 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
42
Public
Parameters
556M
33.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 99%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- mt5
- Access
- Public
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026
- SHA
- 3277a7f6
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. -->
mt5-small-bias-aware-v2
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7843
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: 0.00056
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2859 | 1.0 | 511 | 0.9038 |
| 1.7052 | 2.0 | 1022 | 0.7732 |
| 1.4456 | 3.0 | 1533 | 0.7316 |
| 1.2653 | 4.0 | 2044 | 0.7125 |
| 1.1238 | 5.0 | 2555 | 0.7132 |
| 1.0196 | 6.0 | 3066 | 0.7161 |
| 0.9413 | 7.0 | 3577 | 0.7233 |
| 0.8494 | 8.0 | 4088 | 0.7360 |
| 0.7938 | 9.0 | 4599 | 0.7518 |
| 0.7294 | 10.0 | 5110 | 0.7607 |
| 0.6992 | 11.0 | 5621 | 0.7672 |
| 0.6743 | 12.0 | 6132 | 0.7735 |
| 0.6551 | 13.0 | 6643 | 0.7798 |
| 0.6518 | 14.0 | 7154 | 0.7833 |
| 0.6403 | 15.0 | 7665 | 0.7843 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Library
- transformers
- Type
- mt5
- License
- apache-2.0
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026