Downloads · 30 days
10
4% of all-time downloads
clip-mixer-300k
bilbo991/clip-mixer-300k
clip-mixer-300k is a feature extraction model from bilbo991. 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
252
Public
Repo size
3.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin892 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- vision-text-dual-encoder
- Access
- Public
- Created
- Aug 16, 2023
- Updated
- Aug 17, 2023
- SHA
- d541de1c
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-mixer-300k
This model is a fine-tuned version of clip-mixer-300k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4179
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
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2811 | 1.0 | 9375 | 2.5993 |
| 0.8159 | 2.0 | 18750 | 2.4179 |
| 0.374 | 3.0 | 28125 | 2.4597 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.1
- Tokenizers 0.13.3
- Task
- Feature Extraction
- Library
- transformers
- Type
- vision-text-dual-encoder
- Created
- Aug 16, 2023
- Updated
- Aug 17, 2023