Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
invoice_extraction_donut_fromv0_f21_ep3_0724_length_penalty – AI Model by VVVVL | AlphaNeural AI
You can deploy this model and start earning money today!
VVVVL
/
invoice_extraction_donut_fromv0_f21_ep3_0724_length_penalty
like
0
transformers
tensorboard
safetensors
vision-encoder-decoder
image-to-text
generated_from_trainer
naver-clova-ix/donut-base
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
invoice_extraction_donut_fromv0_f21_ep3_0724_length_penalty
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: 0.0730
Char Accuracy: -0.9885
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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 2
total_eval_batch_size: 2
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Char Accuracy
0.2649
1.0
1496
0.1212
0.6823
0.078
2.0
2992
0.0745
-0.4810
0.025
3.0
4488
0.0730
-0.9885
Framework versions
Transformers 4.53.2
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1
