layoutlmv3-finetuned-sroie

This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0742
• Precision: 0.9472
• Recall: 0.9668
• F1: 0.9569
• Accuracy: 0.9872

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: 1e-05
• train_batch_size: 5
• eval_batch_size: 5
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.9841	250	0.0544	0.9319	0.9592	0.9453	0.9836
0.0813	3.9683	500	0.0607	0.9280	0.9683	0.9477	0.9844
0.0813	5.9524	750	0.0530	0.9451	0.9589	0.9519	0.9854
0.023	7.9365	1000	0.0562	0.9434	0.9643	0.9537	0.9863
0.023	9.9206	1250	0.0613	0.9486	0.9614	0.9549	0.9867
0.0128	11.9048	1500	0.0632	0.9510	0.9650	0.9579	0.9875
0.0128	13.8889	1750	0.0705	0.9403	0.9670	0.9535	0.9862
0.0073	15.8730	2000	0.0723	0.9485	0.9643	0.9563	0.9871
0.0073	17.8571	2250	0.0728	0.9505	0.9653	0.9579	0.9875
0.0054	19.8413	2500	0.0742	0.9472	0.9668	0.9569	0.9872

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1