Downloads · 30 days
13
8% of all-time downloads
visobert_model_UIT
levancuong17/visobert_model_UIT
visobert_model_UIT is a text classification model from levancuong17. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
169
Public
Parameters
97.6M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors390 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Mar 22, 2025
- Updated
- Mar 26, 2025
- SHA
- 8ec50432
Try a prompt
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. -->
visobert_model_UIT
This model is a fine-tuned version of uitnlp/visobert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9761
- Accuracy: 0.6551
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.93 | 1.0 | 526 | 1.0170 | 0.6341 |
| 0.533 | 2.0 | 1052 | 1.0406 | 0.6589 |
| 0.2317 | 3.0 | 1578 | 1.3728 | 0.6429 |
| 0.1081 | 4.0 | 2104 | 1.8683 | 0.6341 |
| 0.0647 | 5.0 | 2630 | 2.2965 | 0.6122 |
| 0.053 | 6.0 | 3156 | 2.3454 | 0.6385 |
| 0.0041 | 7.0 | 3682 | 2.5653 | 0.6399 |
| 0.0199 | 8.0 | 4208 | 2.7244 | 0.6414 |
| 0.0091 | 9.0 | 4734 | 2.7655 | 0.6312 |
| 0.0007 | 10.0 | 5260 | 2.8327 | 0.6370 |
| 0.0141 | 11.0 | 5786 | 2.9765 | 0.6283 |
| 0.0008 | 12.0 | 6312 | 2.9757 | 0.6283 |
| 0.0063 | 13.0 | 6838 | 2.9824 | 0.6370 |
| 0.0027 | 14.0 | 7364 | 2.8190 | 0.6341 |
| 0.0071 | 15.0 | 7890 | 3.0544 | 0.6254 |
| 0.0005 | 16.0 | 8416 | 2.9467 | 0.6385 |
| 0.006 | 17.0 | 8942 | 2.9506 | 0.6356 |
| 0.0035 | 18.0 | 9468 | 2.9577 | 0.6341 |
| 0.0097 | 19.0 | 9994 | 2.9790 | 0.6283 |
| 0.0004 | 19.9629 | 10500 | 2.9577 | 0.6327 |
Framework versions
- Transformers 4.50.1
- Pytorch 2.6.0+cu124
- Datasets 2.16.1
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- Created
- Mar 22, 2025
- Updated
- Mar 26, 2025