Downloads · 30 days
44
8% of all-time downloads
clip-finetuned-csu-p14-336-e5l510-l
kevinoli/clip-finetuned-csu-p14-336-e5l510-l
clip-finetuned-csu-p14-336-e5l510-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
546
Public
Parameters
428M
277 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt185 GB · 66%
At a glance
- Task
- Zero-Shot Image Classification
- Library
- transformers
- Model type
- clip
- Access
- Public
- Created
- Aug 22, 2024
- Updated
- Aug 22, 2024
- SHA
- 3e423183
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-e5l510-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: 1.4969
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-10
- 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: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3974 | 0.0921 | 500 | 1.5029 |
| 0.462 | 0.1842 | 1000 | 1.5026 |
| 0.5249 | 0.2763 | 1500 | 1.5022 |
| 0.4642 | 0.3685 | 2000 | 1.5019 |
| 0.5056 | 0.4606 | 2500 | 1.5016 |
| 0.4604 | 0.5527 | 3000 | 1.5013 |
| 0.4508 | 0.6448 | 3500 | 1.5010 |
| 0.4674 | 0.7369 | 4000 | 1.5008 |
| 0.4435 | 0.8290 | 4500 | 1.5005 |
| 0.4573 | 0.9211 | 5000 | 1.5003 |
| 0.4681 | 1.0133 | 5500 | 1.5001 |
| 0.4862 | 1.1054 | 6000 | 1.4999 |
| 0.4231 | 1.1975 | 6500 | 1.4997 |
| 0.3734 | 1.2896 | 7000 | 1.4996 |
| 0.4606 | 1.3817 | 7500 | 1.4994 |
| 0.467 | 1.4738 | 8000 | 1.4992 |
| 0.4202 | 1.5660 | 8500 | 1.4990 |
| 0.4866 | 1.6581 | 9000 | 1.4988 |
| 0.4848 | 1.7502 | 9500 | 1.4987 |
| 0.4385 | 1.8423 | 10000 | 1.4985 |
| 0.4781 | 1.9344 | 10500 | 1.4984 |
| 0.4287 | 2.0265 | 11000 | 1.4983 |
| 0.4392 | 2.1186 | 11500 | 1.4982 |
| 0.4447 | 2.2108 | 12000 | 1.4980 |
| 0.4449 | 2.3029 | 12500 | 1.4980 |
| 0.4748 | 2.3950 | 13000 | 1.4978 |
| 0.4935 | 2.4871 | 13500 | 1.4978 |
| 0.4113 | 2.5792 | 14000 | 1.4977 |
| 0.3934 | 2.6713 | 14500 | 1.4976 |
| 0.4901 | 2.7634 | 15000 | 1.4975 |
| 0.4601 | 2.8556 | 15500 | 1.4974 |
| 0.4224 | 2.9477 | 16000 | 1.4974 |
| 0.4381 | 3.0398 | 16500 | 1.4973 |
| 0.4942 | 3.1319 | 17000 | 1.4973 |
| 0.3885 | 3.2240 | 17500 | 1.4972 |
| 0.4407 | 3.3161 | 18000 | 1.4972 |
| 0.4635 | 3.4083 | 18500 | 1.4971 |
| 0.4228 | 3.5004 | 19000 | 1.4971 |
| 0.464 | 3.5925 | 19500 | 1.4971 |
| 0.4746 | 3.6846 | 20000 | 1.4970 |
| 0.4447 | 3.7767 | 20500 | 1.4970 |
| 0.4663 | 3.8688 | 21000 | 1.4970 |
| 0.4246 | 3.9609 | 21500 | 1.4970 |
| 0.4592 | 4.0531 | 22000 | 1.4970 |
| 0.4181 | 4.1452 | 22500 | 1.4970 |
| 0.4913 | 4.2373 | 23000 | 1.4969 |
| 0.4491 | 4.3294 | 23500 | 1.4969 |
| 0.5054 | 4.4215 | 24000 | 1.4969 |
| 0.3931 | 4.5136 | 24500 | 1.4969 |
| 0.4574 | 4.6057 | 25000 | 1.4969 |
| 0.418 | 4.6979 | 25500 | 1.4969 |
| 0.5482 | 4.7900 | 26000 | 1.4969 |
| 0.4376 | 4.8821 | 26500 | 1.4969 |
| 0.3889 | 4.9742 | 27000 | 1.4969 |
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 22, 2024
- Updated
- Aug 22, 2024