layoutlmv3-finetuned-cne_nvidia_100

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

• Loss: 0.0064
• 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	0.0143	0.9951	0.9951	0.9951	0.9993
0.1596	15.62	500	0.0085	0.9951	0.9951	0.9951	0.9993
0.1596	23.44	750	0.0074	0.9951	0.9951	0.9951	0.9993
0.0195	31.25	1000	0.0068	0.9951	0.9951	0.9951	0.9993
0.0195	39.06	1250	0.0067	0.9951	0.9951	0.9951	0.9993
0.008	46.88	1500	0.0067	0.9951	0.9951	0.9951	0.9993
0.008	54.69	1750	0.0064	0.9951	0.9951	0.9951	0.9993
0.0034	62.5	2000	0.0063	0.9951	0.9951	0.9951	0.9993
0.0034	70.31	2250	0.0063	0.9951	0.9951	0.9951	0.9993
0.0023	78.12	2500	0.0064	0.9951	0.9951	0.9951	0.9993

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1
• Datasets 2.14.3
• Tokenizers 0.13.3