layoutlmv2_output

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3471
• Precision: 0.8712
• Recall: 0.8742
• F1: 0.8727
• Accuracy: 0.9288

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3415	0.8772	500	0.4834	0.8227	0.8343	0.8285	0.8966
0.228	1.7544	1000	0.3607	0.8591	0.8528	0.8559	0.9170
0.1769	2.6316	1500	0.3408	0.8571	0.8556	0.8563	0.9208
0.1183	3.5088	2000	0.3570	0.8661	0.8579	0.8620	0.9208
0.0915	4.3860	2500	0.3603	0.8644	0.8702	0.8673	0.9256

Framework versions

• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1