Downloads · 30 days
7
3% of all-time downloads
soda-clip
drAbreu/soda-clip
soda-clip is a feature extraction model from drAbreu. Use it when you need embeddings to search or compare text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
263
Public
Parameters
213M
6.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors852 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- vision-text-dual-encoder
- Access
- Public
- Created
- Jun 7, 2024
- Updated
- Jun 8, 2024
- SHA
- a9a06b9e
Datasets
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. -->
soda-clip
This model was trained from scratch on the soda-panelized-clip-loader dataset. It achieves the following results on the evaluation set:
- Loss: 1.9732
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 4.0258 | 0.13 | 100 | 3.7622 |
| 3.556 | 0.26 | 200 | 3.4317 |
| 3.3307 | 0.39 | 300 | 3.2219 |
| 3.2305 | 0.51 | 400 | 3.1044 |
| 3.1104 | 0.64 | 500 | 2.9733 |
| 2.9966 | 0.77 | 600 | 2.8562 |
| 2.8576 | 0.9 | 700 | 2.8080 |
| 2.7558 | 1.03 | 800 | 2.6612 |
| 2.5565 | 1.16 | 900 | 2.6441 |
| 2.4791 | 1.28 | 1000 | 2.5369 |
| 2.4483 | 1.41 | 1100 | 2.4951 |
| 2.3751 | 1.54 | 1200 | 2.3893 |
| 2.3408 | 1.67 | 1300 | 2.3960 |
| 2.2761 | 1.8 | 1400 | 2.2943 |
| 2.2426 | 1.93 | 1500 | 2.2422 |
| 2.0389 | 2.05 | 1600 | 2.2475 |
| 1.8415 | 2.18 | 1700 | 2.1555 |
| 1.8286 | 2.31 | 1800 | 2.1755 |
| 1.7927 | 2.44 | 1900 | 2.1267 |
| 1.7693 | 2.57 | 2000 | 2.0621 |
| 1.7448 | 2.7 | 2100 | 2.0653 |
| 1.7027 | 2.82 | 2200 | 2.0110 |
| 1.7184 | 2.95 | 2300 | 1.9699 |
| 1.4059 | 3.08 | 2400 | 1.9781 |
| 1.2499 | 3.21 | 2500 | 1.9837 |
| 1.2478 | 3.34 | 2600 | 1.9859 |
| 1.1903 | 3.47 | 2700 | 1.9470 |
| 1.1989 | 3.59 | 2800 | 1.9819 |
| 1.169 | 3.72 | 2900 | 1.9825 |
| 1.1538 | 3.85 | 3000 | 1.9429 |
| 1.1178 | 3.98 | 3100 | 1.9387 |
| 0.8271 | 4.11 | 3200 | 1.9931 |
| 0.748 | 4.24 | 3300 | 1.9974 |
| 0.7123 | 4.36 | 3400 | 1.9994 |
| 0.7012 | 4.49 | 3500 | 1.9967 |
| 0.7163 | 4.62 | 3600 | 1.9914 |
| 0.6899 | 4.75 | 3700 | 1.9836 |
| 0.6608 | 4.88 | 3800 | 1.9732 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Task
- Feature Extraction
- Library
- transformers
- Type
- vision-text-dual-encoder
- Created
- Jun 7, 2024
- Updated
- Jun 8, 2024