donut_checkpoints

konstantis/donut_checkpoints

donut_checkpoints is a image-text-to-text model from konstantis. 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

0% of all-time downloads

All-time downloads

Public

Parameters

202M

809 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors809 MB · 100%

Parameter types

How the weights are stored.

F32202M · 100%

Try a prompt

Base models

naver-clova-ix/donut-base

Model card

From the Hugging Face model README

donut_checkpoints

This model is a fine-tuned version of naver-clova-ix/donut-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7296

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.0573	1.0	250	1.4718
0.6312	2.0	500	0.7169
0.2924	3.0	750	0.6494
0.1544	4.0	1000	0.6331
0.0682	5.0	1250	0.7624
0.0562	6.0	1500	0.7330
0.027	7.0	1750	0.7246
0.0076	8.0	2000	0.6950
0.0069	9.0	2250	0.7208
0.008	10.0	2500	0.7296

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.1

Task: Image-Text-to-Text
Library: transformers
Type: vision-encoder-decoder
License: mit
Created: Jun 21, 2025
Updated: Jun 21, 2025