layoutlmv3-finetuned-ex

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: 0.1199
• Precision: 0.8362
• Recall: 0.8351
• F1: 0.8332
• Accuracy: 0.9807

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0894	2.2321	500	0.0853	0.8742	0.7571	0.7733	0.9788
0.0296	4.4643	1000	0.0978	0.8005	0.8277	0.8134	0.9782
0.0154	6.6964	1500	0.1022	0.8286	0.8330	0.8289	0.9805
0.0089	8.9286	2000	0.1055	0.8101	0.8344	0.8212	0.9797
0.0051	11.1607	2500	0.1190	0.8346	0.8442	0.8375	0.9813
0.0028	13.3929	3000	0.1199	0.8362	0.8351	0.8332	0.9807

Framework versions

• Transformers 5.13.1
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2