layoutlmv3-finetuned-Algo_427Images

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: 0.0013
• Precision: 0.9937
• Recall: 0.9964
• F1: 0.9950
• Accuracy: 0.9999

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: 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	1.25	100	0.0082	0.9505	0.9367	0.9435	0.9983
No log	2.5	200	0.0024	0.9883	0.9901	0.9892	0.9997
No log	3.75	300	0.0020	0.9883	0.9919	0.9901	0.9997
No log	5.0	400	0.0016	0.9910	0.9928	0.9919	0.9998
0.0301	6.25	500	0.0015	0.9910	0.9928	0.9919	0.9998
0.0301	7.5	600	0.0014	0.9928	0.9946	0.9937	0.9998
0.0301	8.75	700	0.0013	0.9928	0.9946	0.9937	0.9998
0.0301	10.0	800	0.0013	0.9937	0.9964	0.9950	0.9999
0.0301	11.25	900	0.0013	0.9928	0.9946	0.9937	0.9998
0.002	12.5	1000	0.0013	0.9937	0.9964	0.9950	0.9999

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3