layoutlmv3-finetuned-invoice

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: 0.0558
• Precision: 0.9435
• Recall: 0.9612
• F1: 0.9523
• Accuracy: 0.9858

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: 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: linear
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.3195	100	0.0961	0.9121	0.9134	0.9128	0.9752
No log	0.6390	200	0.0772	0.9120	0.9396	0.9256	0.9780
No log	0.9585	300	0.0707	0.9272	0.9509	0.9389	0.9822
No log	1.2780	400	0.0638	0.9202	0.9602	0.9398	0.9819
0.1131	1.5974	500	0.0631	0.9270	0.9582	0.9423	0.9829
0.1131	1.9169	600	0.0561	0.9331	0.9615	0.9471	0.9843
0.1131	2.2364	700	0.0651	0.9141	0.9720	0.9421	0.9824
0.1131	2.5559	800	0.0537	0.9515	0.9556	0.9535	0.9862
0.1131	2.8754	900	0.0556	0.9467	0.9582	0.9524	0.9860
0.0379	3.1949	1000	0.0558	0.9435	0.9612	0.9523	0.9858

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0