Downloads · 30 days
5
26% of all-time downloads
new-vit5-fast
lamdoanh2468/new-vit5-fast
new-vit5-fast is a machine learning model from lamdoanh2468. 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 peft. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
19
Public
Repo size
7.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.1 MB · 58%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Dec 18, 2025
- Updated
- Dec 18, 2025
- SHA
- a3310d1b
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. -->
new-vit5-fast
This model is a fine-tuned version of VietAI/vit5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6629
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9423 | 0.0703 | 500 | 1.7860 |
| 1.8964 | 0.1405 | 1000 | 1.7491 |
| 1.8636 | 0.2108 | 1500 | 1.7210 |
| 1.8715 | 0.2811 | 2000 | 1.7103 |
| 1.8336 | 0.3513 | 2500 | 1.7005 |
| 1.8521 | 0.4216 | 3000 | 1.6903 |
| 1.7806 | 0.4919 | 3500 | 1.6823 |
| 1.8209 | 0.5622 | 4000 | 1.6788 |
| 1.8205 | 0.6324 | 4500 | 1.6714 |
| 1.8183 | 0.7027 | 5000 | 1.6670 |
| 1.8176 | 0.7730 | 5500 | 1.6664 |
| 1.8072 | 0.8432 | 6000 | 1.6653 |
| 1.785 | 0.9135 | 6500 | 1.6637 |
| 1.8074 | 0.9838 | 7000 | 1.6629 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.21.2
- Library
- peft
- License
- mit
- Created
- Dec 18, 2025
- Updated
- Dec 18, 2025