LayoutLM_1

This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4204
• Precision: 0.6552
• Recall: 0.7480
• F1: 0.6985
• Accuracy: 0.9071

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	3.7	100	0.6185	0.0	0.0	0.0	0.8310
No log	7.41	200	0.4585	0.6146	0.4646	0.5291	0.8839
No log	11.11	300	0.4020	0.5870	0.6378	0.6113	0.8929
No log	14.81	400	0.3775	0.6496	0.7008	0.6742	0.9006
0.4776	18.52	500	0.3826	0.6268	0.7008	0.6617	0.9019
0.4776	22.22	600	0.3864	0.6224	0.7008	0.6593	0.8981
0.4776	25.93	700	0.4307	0.5759	0.7165	0.6386	0.8916
0.4776	29.63	800	0.4205	0.6738	0.7480	0.7090	0.9123
0.4776	33.33	900	0.4176	0.6552	0.7480	0.6985	0.9084
0.0536	37.04	1000	0.4204	0.6552	0.7480	0.6985	0.9071

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3