donut_marriage_RT_001

vishnu027/donut_marriage_RT_001

donut_marriage_RT_001 is a image-text-to-text model from vishnu027. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

268

Public

Parameters

202M

8.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors809 MB · 99%

Parameter types

How the weights are stored.

F32202M · 100%

Try a prompt

Base models

naver-clova-ix/donut-base

Datasets

imagefolder

Model card

From the Hugging Face model README

donut_marriage_RT_001

This model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3953

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: 2e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0315	1.0	163	0.9688
0.5694	2.0	326	0.5084
0.5065	3.0	489	0.4196
0.1008	4.0	652	0.3998
0.1531	5.0	815	0.3687
0.1606	6.0	978	0.3642
0.1383	7.0	1141	0.3745
0.0956	8.0	1304	0.3856
0.0331	9.0	1467	0.3850
0.0032	10.0	1630	0.3920
0.0164	11.0	1793	0.3953

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Task: Image-Text-to-Text
Library: transformers
Type: vision-encoder-decoder
License: mit
Created: Nov 27, 2023
Updated: Nov 27, 2023