Downloads · 30 days
5
1% of all-time downloads
clip-wikiart-augmented-v1-10ep
turing552/clip-wikiart-augmented-v1-10ep
clip-wikiart-augmented-v1-10ep is a zero-shot image classification model from turing552. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
340
Public
Repo size
19.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin605 MB · 99%
At a glance
- Task
- Zero-Shot Image Classification
- Library
- transformers
- Model type
- clip
- Access
- Public
- Created
- Nov 12, 2025
- Updated
- Nov 12, 2025
- SHA
- dc5ecfc9
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. -->
clip-wikiart-augmented-v1-10ep
This model is a fine-tuned version of openai/clip-vit-base-patch32 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3020
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: 5e-06
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5061 | 0.3262 | 500 | 0.5061 |
| 0.4328 | 0.6523 | 1000 | 0.4704 |
| 0.426 | 0.9785 | 1500 | 0.4230 |
| 0.2924 | 1.3046 | 2000 | 0.4253 |
| 0.2673 | 1.6308 | 2500 | 0.3584 |
| 0.2739 | 1.9569 | 3000 | 0.3481 |
| 0.1496 | 2.2831 | 3500 | 0.3819 |
| 0.1652 | 2.6093 | 4000 | 0.3499 |
| 0.1281 | 2.9354 | 4500 | 0.3433 |
| 0.0967 | 3.2616 | 5000 | 0.3596 |
| 0.1006 | 3.5877 | 5500 | 0.3644 |
| 0.0897 | 3.9139 | 6000 | 0.3385 |
| 0.0738 | 4.2401 | 6500 | 0.3473 |
| 0.0707 | 4.5662 | 7000 | 0.3352 |
| 0.0704 | 4.8924 | 7500 | 0.3227 |
| 0.0522 | 5.2185 | 8000 | 0.3284 |
| 0.0622 | 5.5447 | 8500 | 0.3358 |
| 0.0568 | 5.8708 | 9000 | 0.3162 |
| 0.0456 | 6.1970 | 9500 | 0.3204 |
| 0.0333 | 6.5232 | 10000 | 0.3424 |
| 0.0466 | 6.8493 | 10500 | 0.3366 |
| 0.0306 | 7.1755 | 11000 | 0.3299 |
| 0.0331 | 7.5016 | 11500 | 0.3377 |
| 0.0268 | 7.8278 | 12000 | 0.3267 |
| 0.0244 | 8.1539 | 12500 | 0.3212 |
| 0.0274 | 8.4801 | 13000 | 0.3177 |
| 0.0298 | 8.8063 | 13500 | 0.3156 |
| 0.0245 | 9.1324 | 14000 | 0.3108 |
| 0.0259 | 9.4586 | 14500 | 0.3062 |
| 0.0194 | 9.7847 | 15000 | 0.3020 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.1+cu124
- Datasets 4.4.1
- Tokenizers 0.19.1
- Task
- Zero-Shot Image Classification
- Library
- transformers
- Type
- clip
- Created
- Nov 12, 2025
- Updated
- Nov 12, 2025