LayoutLMv3_5_entities_7

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

• Loss: 0.2592
• Precision: 0.8130
• Recall: 0.8850
• F1: 0.8475
• Accuracy: 0.9690

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: 6e-06
• 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: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	2.56	100	0.1332	0.7154	0.8230	0.7654	0.9566
No log	5.13	200	0.1432	0.7698	0.8584	0.8117	0.9646
No log	7.69	300	0.1612	0.7805	0.8496	0.8136	0.9619
No log	10.26	400	0.1885	0.8333	0.8407	0.8370	0.9655
0.0796	12.82	500	0.2244	0.7724	0.8407	0.8051	0.9611
0.0796	15.38	600	0.2407	0.8017	0.8584	0.8291	0.9655
0.0796	17.95	700	0.2231	0.8167	0.8673	0.8412	0.9699
0.0796	20.51	800	0.2435	0.7967	0.8673	0.8305	0.9655
0.0796	23.08	900	0.2429	0.8167	0.8673	0.8412	0.9690
0.0043	25.64	1000	0.2304	0.8684	0.8761	0.8722	0.9735
0.0043	28.21	1100	0.2704	0.7823	0.8584	0.8186	0.9655
0.0043	30.77	1200	0.2647	0.8033	0.8673	0.8340	0.9673
0.0043	33.33	1300	0.2509	0.8115	0.8761	0.8426	0.9681
0.0043	35.9	1400	0.2561	0.7967	0.8673	0.8305	0.9664
0.0014	38.46	1500	0.2774	0.7823	0.8584	0.8186	0.9664
0.0014	41.03	1600	0.2580	0.7951	0.8584	0.8255	0.9673
0.0014	43.59	1700	0.2688	0.7937	0.8850	0.8368	0.9673
0.0014	46.15	1800	0.2706	0.8	0.8850	0.8403	0.9681
0.0014	48.72	1900	0.2608	0.8130	0.8850	0.8475	0.9690
0.0008	51.28	2000	0.2592	0.8130	0.8850	0.8475	0.9690

Framework versions

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