invoice_extraction_donut_fromv0_f21_ep3_0724_adaptive_custom_loss – AI Model by VVVVL | AlphaNeural AI

You can deploy this model and start earning money today!

VVVVL/
invoice_extraction_donut_fromv0_f21_ep3_0724_adaptive_custom_loss

like

0

vision-encoder-decoder

generated_from_trainer

naver-clova-ix/donut-base

endpoints_compatible

Views

No views yet

invoice_extraction_donut_fromv0_f21_ep3_0724_adaptive_custom_loss

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: 8.2553
Char Accuracy: 0.9997
Avg Pred Length: 6.9980
Avg Label Length: 7.0
Length Ratio: 0.9997

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: 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	Avg Pred Length	Avg Label Length	Length Ratio
1.6365	1.0	1496	7.2490	0.9997	6.9980	7.0	0.9997
1.4961	2.0	2992	8.0436	0.9997	6.9980	7.0	0.9997
1.4653	3.0	4488	8.2553	0.9997	6.9980	7.0	0.9997

Framework versions

Transformers 4.53.2
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1