MRR-NER-08-09-Layoutlmv3

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

• Loss: 0.0175
• Precision: 0.8367
• Recall: 0.9111
• F1: 0.8723
• Accuracy: 0.9960

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	8.33	100	0.2585	0.1667	0.0222	0.0392	0.9607
No log	16.67	200	0.1281	0.4783	0.2444	0.3235	0.9727
No log	25.0	300	0.0821	0.3696	0.3778	0.3736	0.9767
No log	33.33	400	0.0493	0.5111	0.5111	0.5111	0.9813
0.2244	41.67	500	0.0330	0.625	0.7778	0.6931	0.9913
0.2244	50.0	600	0.0272	0.6909	0.8444	0.7600	0.9927
0.2244	58.33	700	0.0218	0.7843	0.8889	0.8333	0.9953
0.2244	66.67	800	0.0190	0.7547	0.8889	0.8163	0.9947
0.2244	75.0	900	0.0158	0.8936	0.9333	0.9130	0.9973
0.038	83.33	1000	0.0175	0.8367	0.9111	0.8723	0.9960

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3