category_cleaning

kpalczewski-displate/category_cleaning

category_cleaning is a zero-shot image classification model from kpalczewski-displate. 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. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

362

Public

Parameters

151M

4.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors605 MB · 99%

At a glance

Task: Zero-Shot Image Classification
Library: transformers
Model type: clip
Access: Public
Created: Mar 7, 2024
Updated: Mar 8, 2024
SHA: 4ff944b4

Datasets

Displate/category_cleaning

Model card

From the Hugging Face model README

category_cleaning

This model was trained from scratch on the Displate/category_cleaning dataset. It achieves the following results on the evaluation set:

Loss: 4.5536

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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
3.0173	0.26	100	4.2489
2.8146	0.51	200	4.2605
2.7177	0.77	300	4.2547
2.6338	1.02	400	4.3864
2.102	1.28	500	4.3538
2.1015	1.53	600	4.3395
2.0691	1.79	700	4.3363
1.9422	2.04	800	4.6331
1.4405	2.3	900	4.5653
1.3896	2.55	1000	4.5768
1.3735	2.81	1100	4.5610

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Task: Zero-Shot Image Classification
Library: transformers
Type: clip
Created: Mar 7, 2024
Updated: Mar 8, 2024