Downloads · 30 days
13
24% of all-time downloads
mobilevit-small_alpha0.5_temp5.0_t3
c14kevincardenas/mobilevit-small_alpha0.5_temp5.0_t3
mobilevit-small_alpha0.5_temp5.0_t3 is a image classification model from c14kevincardenas. Use it when you need a label for an image. 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
54
Public
Parameters
7.3M
585 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29.3 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- mobilevit
- Access
- Public
- Created
- Feb 26, 2025
- Updated
- Mar 18, 2025
- SHA
- 7b14248f
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. -->
mobilevit-small_alpha0.5_temp5.0_t3
This model is a fine-tuned version of c14kevincardenas/ClimBEiT-t3 on the c14kevincardenas/beta_caller_284_person_crop_seq_withlimb dataset. It achieves the following results on the evaluation set:
- Loss: 0.8560
- Accuracy: 0.7104
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: 32
- eval_batch_size: 32
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8038 | 1.0 | 164 | 1.3827 | 0.2842 |
| 0.7616 | 2.0 | 328 | 1.3392 | 0.2928 |
| 0.6901 | 3.0 | 492 | 1.1423 | 0.5228 |
| 0.6066 | 4.0 | 656 | 1.0579 | 0.5651 |
| 0.5802 | 5.0 | 820 | 1.0286 | 0.5792 |
| 0.5439 | 6.0 | 984 | 0.9586 | 0.6215 |
| 0.5157 | 7.0 | 1148 | 0.9451 | 0.6508 |
| 0.4997 | 8.0 | 1312 | 0.9125 | 0.6779 |
| 0.4715 | 9.0 | 1476 | 0.9168 | 0.6594 |
| 0.4488 | 10.0 | 1640 | 0.9279 | 0.6453 |
| 0.4554 | 11.0 | 1804 | 0.9372 | 0.6497 |
| 0.4412 | 12.0 | 1968 | 0.8724 | 0.6649 |
| 0.4232 | 13.0 | 2132 | 0.8759 | 0.7007 |
| 0.4189 | 14.0 | 2296 | 0.8838 | 0.6866 |
| 0.4072 | 15.0 | 2460 | 0.8874 | 0.6909 |
| 0.4033 | 16.0 | 2624 | 0.8691 | 0.7017 |
| 0.4054 | 17.0 | 2788 | 0.8560 | 0.7104 |
| 0.3878 | 18.0 | 2952 | 0.8586 | 0.7093 |
| 0.3956 | 19.0 | 3116 | 0.8643 | 0.6996 |
| 0.3806 | 20.0 | 3280 | 0.8676 | 0.7017 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Task
- Image Classification
- Library
- transformers
- Type
- mobilevit
- License
- apache-2.0
- Created
- Feb 26, 2025
- Updated
- Mar 18, 2025