Output_LayoutLMv3

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

• Loss: 0.2507
• Precision: 0.8319
• Recall: 0.8319
• F1: 0.8319
• Accuracy: 0.9771

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: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	2.27	100	0.1116	0.7705	0.8319	0.8	0.9676
No log	4.55	200	0.1130	0.8319	0.8540	0.8428	0.9762
No log	6.82	300	0.1707	0.7931	0.8142	0.8035	0.9686
No log	9.09	400	0.1998	0.7521	0.7920	0.7716	0.9648
0.0744	11.36	500	0.1633	0.8210	0.8319	0.8264	0.9752
0.0744	13.64	600	0.1784	0.8182	0.8363	0.8271	0.9752
0.0744	15.91	700	0.1909	0.8095	0.8274	0.8184	0.9724
0.0744	18.18	800	0.1962	0.7974	0.8186	0.8079	0.9724
0.0744	20.45	900	0.1723	0.8412	0.8673	0.8540	0.9781
0.0081	22.73	1000	0.2109	0.8210	0.8319	0.8264	0.9733
0.0081	25.0	1100	0.2194	0.8087	0.8230	0.8158	0.9743
0.0081	27.27	1200	0.2076	0.8465	0.8540	0.8502	0.9771
0.0081	29.55	1300	0.1883	0.8688	0.8496	0.8591	0.9819
0.0081	31.82	1400	0.2042	0.8170	0.8496	0.8330	0.9771
0.0034	34.09	1500	0.2144	0.8261	0.8407	0.8333	0.9771
0.0034	36.36	1600	0.1953	0.8205	0.8496	0.8348	0.9771
0.0034	38.64	1700	0.2259	0.8267	0.8230	0.8248	0.9762
0.0034	40.91	1800	0.2553	0.7974	0.8186	0.8079	0.9714
0.0034	43.18	1900	0.2238	0.8377	0.8451	0.8414	0.9781
0.0006	45.45	2000	0.2245	0.8451	0.8451	0.8451	0.9790
0.0006	47.73	2100	0.2389	0.8326	0.8142	0.8233	0.9762
0.0006	50.0	2200	0.2500	0.8251	0.8142	0.8196	0.9752
0.0006	52.27	2300	0.2537	0.8304	0.8451	0.8377	0.9762
0.0006	54.55	2400	0.2410	0.8319	0.8319	0.8319	0.9771
0.0001	56.82	2500	0.2484	0.8319	0.8319	0.8319	0.9771
0.0001	59.09	2600	0.2517	0.8319	0.8319	0.8319	0.9771
0.0001	61.36	2700	0.2524	0.8319	0.8319	0.8319	0.9771
0.0001	63.64	2800	0.2531	0.8319	0.8319	0.8319	0.9771
0.0001	65.91	2900	0.2528	0.8319	0.8319	0.8319	0.9771
0.0	68.18	3000	0.2507	0.8319	0.8319	0.8319	0.9771

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2