Downloads · 30 days
1
4% of all-time downloads
unlearn_nlvr2_vilt_salun_8_87
jialicheng/unlearn_nlvr2_vilt_salun_8_87
unlearn_nlvr2_vilt_salun_8_87 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. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
25
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
- License
- apache-2.0
- Model type
- vilt
- Access
- Public
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025
- SHA
- 140aa0f6
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. -->
87
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: 0.9840
- Accuracy: 0.7293
- Dt Accuracy: 0.7293
- Df Accuracy: 0.4353
- Unlearn Overall Accuracy: 0.4649
- 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: 87
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| 0.3521 | 1.0 | 2700 | 0.5534 | 0.8614 | 0.3189 | 0.3189 | None |
| 0.2902 | 2.0 | 5400 | 0.5890 | 0.7066 | 0.3826 | 0.3826 | None |
| 0.2232 | 3.0 | 8100 | 0.7256 | 0.5758 | 0.4258 | 0.4258 | None |
| 0.1873 | 4.0 | 10800 | 0.8449 | 0.4980 | 0.4486 | 0.4486 | None |
| 0.142 | 5.0 | 13500 | 0.9510 | 0.4542 | 0.4604 | 0.4604 | None |
| 0.1206 | 6.0 | 16200 | 0.9840 | 0.4353 | 0.4649 | 0.4649 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Type
- vilt
- License
- apache-2.0
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025