Downloads · 30 days
17
5% of all-time downloads
phobert-base-vinli-ph
dtran612/phobert-base-vinli-ph
phobert-base-vinli-ph is a text classification model from dtran612. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
343
Public
Parameters
135M
10.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors540 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- May 2, 2026
- Updated
- May 6, 2026
- SHA
- 4d8d67b9
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. -->
phobert-base-vinli-ph
This model is a fine-tuned version of vinai/phobert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3984
- Accuracy: 0.8595
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1012 | 1.0 | 142 | 1.0750 | 0.4594 |
| 1.0143 | 2.0 | 284 | 0.9419 | 0.5782 |
| 0.8990 | 3.0 | 426 | 0.8025 | 0.6758 |
| 0.8533 | 4.0 | 568 | 0.6941 | 0.7288 |
| 0.7260 | 5.0 | 710 | 0.6040 | 0.7650 |
| 0.6594 | 6.0 | 852 | 0.5203 | 0.8145 |
| 0.6001 | 7.0 | 994 | 0.5053 | 0.8087 |
| 0.5556 | 8.0 | 1136 | 0.4411 | 0.8436 |
| 0.4895 | 9.0 | 1278 | 0.4059 | 0.8640 |
| 0.5975 | 10.0 | 1420 | 0.3984 | 0.8595 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- May 2, 2026
- Updated
- May 6, 2026