Downloads · 30 days
43
6% of all-time downloads
clip-finetuned-csu-p14-336-e3l55-l
kevinoli/clip-finetuned-csu-p14-336-e3l55-l
clip-finetuned-csu-p14-336-e3l55-l is a zero-shot image classification model from kevinoli. 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
694
Public
Parameters
428M
361 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt113 GB · 66%
At a glance
- Task
- Zero-Shot Image Classification
- Library
- transformers
- Model type
- clip
- Access
- Public
- Created
- Aug 21, 2024
- Updated
- Aug 23, 2024
- SHA
- 9fcb04ea
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-finetuned-csu-p14-336-e3l55-l
This model is a fine-tuned version of openai/clip-vit-large-patch14-336 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9574
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-05
- train_batch_size: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7076 | 0.0921 | 500 | 2.0787 |
| 0.7045 | 0.1842 | 1000 | 2.0783 |
| 0.7106 | 0.2763 | 1500 | 2.0474 |
| 0.704 | 0.3685 | 2000 | 2.2816 |
| 0.6996 | 0.4606 | 2500 | 2.0450 |
| 0.6739 | 0.5527 | 3000 | 2.0969 |
| 0.6687 | 0.6448 | 3500 | 2.0315 |
| 0.8387 | 0.7369 | 4000 | 2.3810 |
| 0.6988 | 0.8290 | 4500 | 2.0409 |
| 0.6808 | 0.9211 | 5000 | 1.9745 |
| 0.6584 | 1.0133 | 5500 | 1.9649 |
| 0.6567 | 1.1054 | 6000 | 2.0569 |
| 0.6542 | 1.1975 | 6500 | 1.9789 |
| 0.6536 | 1.2896 | 7000 | 1.9676 |
| 0.637 | 1.3817 | 7500 | 2.0040 |
| 0.6409 | 1.4738 | 8000 | 1.9905 |
| 0.6127 | 1.5660 | 8500 | 2.2639 |
| 0.6564 | 1.6581 | 9000 | 1.9574 |
| 0.6813 | 1.7502 | 9500 | 2.0365 |
| 0.6421 | 1.8423 | 10000 | 2.2432 |
| 0.6531 | 1.9344 | 10500 | 1.9985 |
| 0.6388 | 2.0265 | 11000 | 1.9725 |
| 0.6394 | 2.1186 | 11500 | 2.0171 |
| 0.6151 | 2.2108 | 12000 | 1.9587 |
| 0.5947 | 2.3029 | 12500 | 2.0684 |
| 0.6166 | 2.3950 | 13000 | 2.0580 |
| 0.6382 | 2.4871 | 13500 | 2.0209 |
| 0.5949 | 2.5792 | 14000 | 2.0776 |
| 0.6282 | 2.6713 | 14500 | 2.0721 |
| 0.6057 | 2.7634 | 15000 | 2.0813 |
| 0.6229 | 2.8556 | 15500 | 2.0468 |
| 0.612 | 2.9477 | 16000 | 2.0670 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 1.12.1
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Zero-Shot Image Classification
- Library
- transformers
- Type
- clip
- Created
- Aug 21, 2024
- Updated
- Aug 23, 2024