Downloads · 30 days
7
28% of all-time downloads
vit5-base-v3-masked-paraphase_data
nguyen10001/vit5-base-v3-masked-paraphase_data
vit5-base-v3-masked-paraphase_data is a machine learning model from nguyen10001. 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
25
Public
Repo size
282 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors281 MB · 98%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Oct 11, 2025
- Updated
- Oct 12, 2025
- SHA
- d5062864
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. -->
vit5-base-v3-masked-paraphase_data
This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4413
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_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7432 | 0.4250 | 3500 | 1.6474 |
| 1.633 | 0.8501 | 7000 | 1.5411 |
| 1.5891 | 1.2751 | 10500 | 1.5058 |
| 1.5597 | 1.7001 | 14000 | 1.4846 |
| 1.5248 | 2.1251 | 17500 | 1.4725 |
| 1.5172 | 2.5501 | 21000 | 1.4589 |
| 1.5439 | 2.9752 | 24500 | 1.4521 |
| 1.5156 | 3.4001 | 28000 | 1.4472 |
| 1.5025 | 3.8252 | 31500 | 1.4435 |
| 1.5018 | 4.2502 | 35000 | 1.4416 |
| 1.4935 | 4.6752 | 38500 | 1.4413 |
Framework versions
- PEFT 0.10.0
- Transformers 4.49.0
- Pytorch 2.4.1+cu118
- Datasets 4.1.1
- Tokenizers 0.21.0
- Library
- peft
- License
- mit
- Created
- Oct 11, 2025
- Updated
- Oct 12, 2025