yuchiahung/donut_f21_v3_ep3_edit_distance_loss

invoice_extraction_donut_fromv0_f21_ep3_0724_edit_distance_edit_dist_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: 25.3603
• Char Accuracy: 0.9997
• Exact Match Accuracy: 0.9980
• Avg Pred Length: 6.9980
• Avg Label Length: 7.0
• Length Ratio: 0.9997
• Avg Edit Distance: 0.0020

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	Exact Match Accuracy	Avg Pred Length	Avg Label Length	Length Ratio	Avg Edit Distance
16.9872	1.0	1496	12.4943	0.9977	0.9960	6.9839	7.0	0.9977	0.0161
10.2946	2.0	2992	21.1310	0.9977	0.9960	6.9839	7.0	0.9977	0.0161
4.1933	3.0	4488	25.3603	0.9997	0.9980	6.9980	7.0	0.9997	0.0020

Framework versions

• Transformers 4.53.2
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1