Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
PDFDonut1-5Epochs-LargeTrain1 – AI Model by tedad09 | AlphaNeural AI
You can deploy this model and start earning money today!
tedad09
/
PDFDonut1-5Epochs-LargeTrain1
like
0
tensorboard
safetensors
vision-encoder-decoder
generated_from_trainer
imagefolder
naver-clova-ix/donut-base
finetune
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
PDFDonut1-5Epochs-LargeTrain1
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: 0.6373
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: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
3.3804
1.0
225
1.4858
1.417
2.0
450
0.8949
1.0463
3.0
675
0.8247
0.8522
4.0
900
0.6329
0.7658
5.0
1125
0.6373
Framework versions
Transformers 4.38.2
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.15.2
