aoi_clip_clean

sharkMeow/aoi_clip_clean

aoi_clip_clean is a machine learning model from sharkMeow. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

0% of all-time downloads

All-time downloads

Public

Parameters

291M

407 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

Model type: chinese_clip
Access: Public
Created: Aug 30, 2024
Updated: Aug 31, 2024
SHA: 350ba356

Base models

OFA-Sys/chinese-clip-vit-base-patch16

Model card

From the Hugging Face model README

aoi_clip_clean

This model is a fine-tuned version of OFA-Sys/chinese-clip-vit-base-patch16 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 5.6248

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: 1e-05
train_batch_size: 40
eval_batch_size: 44
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 120.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.2626	12.0	17748	6.2362
0.057	24.0	35496	6.3541
0.0428	36.0	53244	6.0895
0.0359	48.0	70992	6.1071
0.0312	60.0	88740	5.9994
0.0287	72.0	106488	5.8543
0.0262	84.0	124236	5.7595
0.0246	96.0	141984	5.7167
0.0227	108.0	159732	5.6840
0.0215	120.0	177480	5.6248

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Type: chinese_clip
Created: Aug 30, 2024
Updated: Aug 31, 2024