Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
donut_finetuning_macif – AI Model by come-st | AlphaNeural AI
You can deploy this model and start earning money today!
come-st
/
donut_finetuning_macif
like
0
transformers
pytorch
tensorboard
vision-encoder-decoder
image-to-text
generated_from_trainer
imagefolder
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
donut_finetuning_macif
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: 0.0392
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: 3
Training results
Training Loss
Epoch
Step
Validation Loss
0.0537
1.0
2552
0.0519
0.0267
2.0
5104
0.0400
0.0096
3.0
7656
0.0392
Framework versions
Transformers 4.30.2
Pytorch 1.13.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3
