Downloads · 30 days
3
6% of all-time downloads
unlearn_nlvr2_vilt_salun_4_42
jialicheng/unlearn_nlvr2_vilt_salun_4_42
unlearn_nlvr2_vilt_salun_4_42 is a machine learning model from jialicheng. 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
48
Public
Parameters
114M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt912 MB · 67%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- vilt
- Access
- Public
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025
- SHA
- f4aa0d75
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. -->
42
This model is a fine-tuned version of dandelin/vilt-b32-finetuned-nlvr2 on the nlvr2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0296
- Accuracy: 0.7355
- Dt Accuracy: 0.7355
- Df Accuracy: 0.4951
- Unlearn Overall Accuracy: 0.8995
- Unlearn Time: None
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| 0.2549 | 1.0 | 2700 | 0.6269 | 0.8422 | 0.6552 | 0.6552 | None |
| 0.1933 | 2.0 | 5400 | 0.7083 | 0.6995 | 0.7709 | 0.7709 | None |
| 0.1468 | 3.0 | 8100 | 0.8717 | 0.5835 | 0.8484 | 0.8484 | None |
| 0.1163 | 4.0 | 10800 | 0.9751 | 0.5226 | 0.8842 | 0.8842 | None |
| 0.0946 | 5.0 | 13500 | 1.0296 | 0.4951 | 0.8995 | 0.8995 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.21.0
- Library
- transformers
- Type
- vilt
- License
- apache-2.0
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025