layoutlmv3-finetuned-cne_100

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

• Loss: 0.0008
• Precision: 0.9951
• Recall: 0.9951
• F1: 0.9951
• Accuracy: 0.9993

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: 3
• eval_batch_size: 3
• 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	7.81	250	0.0028	0.9951	0.9951	0.9951	0.9993
0.0229	15.62	500	0.0015	0.9951	0.9951	0.9951	0.9993
0.0229	23.44	750	0.0011	0.9951	0.9951	0.9951	0.9993
0.0031	31.25	1000	0.0009	0.9951	0.9951	0.9951	0.9993
0.0031	39.06	1250	0.0009	0.9951	0.9951	0.9951	0.9993
0.0019	46.88	1500	0.0008	0.9951	0.9951	0.9951	0.9993
0.0019	54.69	1750	0.0008	0.9951	0.9951	0.9951	0.9993
0.0014	62.5	2000	0.0008	0.9951	0.9951	0.9951	0.9993
0.0014	70.31	2250	0.0008	0.9951	0.9951	0.9951	0.9993
0.001	78.12	2500	0.0008	0.9951	0.9951	0.9951	0.9993

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1
• Datasets 2.13.1
• Tokenizers 0.13.3