aoi_clip_clean_new_sampler_fomula_clean

sharkMeow/aoi_clip_clean_new_sampler_fomula_clean

aoi_clip_clean_new_sampler_fomula_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

345

50% of all-time downloads

All-time downloads

687

Public

Parameters

291M

410 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: Sep 1, 2024
Updated: Sep 3, 2024
SHA: 0cbf4fca

Base models

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

Model card

From the Hugging Face model README

aoi_clip_clean_new_sampler_fomula_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: 4.9099

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: 60.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.4122	6.0	8874	3.9394
2.2167	12.0	17748	4.1647
2.0965	18.0	26622	4.4300
2.0238	24.0	35496	4.5740
1.9938	30.0	44370	4.6265
1.973	36.0	53244	4.6714
1.9583	42.0	62118	4.7931
1.9466	48.0	70992	4.7913
1.9415	54.0	79866	4.8448
1.9369	60.0	88740	4.8862

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Type: chinese_clip
Created: Sep 1, 2024
Updated: Sep 3, 2024