capitaletech/Language-levels-LayoutLMv3-v5

layoutlmv3-finetuned-language-levels-v5-4000

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: 0.0913
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Accuracy: 0.9824

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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.2618	100	0.8184	0.9647	0.9630	0.9639	0.6971
No log	0.5236	200	0.6254	0.9743	0.9815	0.9779	0.7404
No log	0.7853	300	0.4760	0.9926	0.9944	0.9935	0.7981
No log	1.0471	400	0.3675	0.9798	0.9889	0.9843	0.8910
0.6763	1.3089	500	0.0913	1.0	1.0	1.0	0.9824
0.6763	1.5707	600	0.0375	1.0	1.0	1.0	0.9904
0.6763	1.8325	700	0.0149	1.0	1.0	1.0	1.0
0.6763	2.0942	800	0.0078	1.0	1.0	1.0	1.0
0.6763	2.3560	900	0.0047	1.0	1.0	1.0	1.0
0.037	2.6178	1000	0.0037	1.0	1.0	1.0	1.0
0.037	2.8796	1100	0.0030	1.0	1.0	1.0	1.0
0.037	3.1414	1200	0.0026	1.0	1.0	1.0	1.0
0.037	3.4031	1300	0.0022	1.0	1.0	1.0	1.0
0.037	3.6649	1400	0.0019	1.0	1.0	1.0	1.0
0.0046	3.9267	1500	0.0017	1.0	1.0	1.0	1.0
0.0046	4.1885	1600	0.0016	1.0	1.0	1.0	1.0
0.0046	4.4503	1700	0.0014	1.0	1.0	1.0	1.0
0.0046	4.7120	1800	0.0013	1.0	1.0	1.0	1.0
0.0046	4.9738	1900	0.0012	1.0	1.0	1.0	1.0
0.0025	5.2356	2000	0.0011	1.0	1.0	1.0	1.0
0.0025	5.4974	2100	0.0010	1.0	1.0	1.0	1.0
0.0025	5.7592	2200	0.0010	1.0	1.0	1.0	1.0
0.0025	6.0209	2300	0.0009	1.0	1.0	1.0	1.0
0.0025	6.2827	2400	0.0009	1.0	1.0	1.0	1.0
0.0017	6.5445	2500	0.0008	1.0	1.0	1.0	1.0
0.0017	6.8063	2600	0.0008	1.0	1.0	1.0	1.0
0.0017	7.0681	2700	0.0007	1.0	1.0	1.0	1.0
0.0017	7.3298	2800	0.0007	1.0	1.0	1.0	1.0
0.0017	7.5916	2900	0.0007	1.0	1.0	1.0	1.0
0.0013	7.8534	3000	0.0007	1.0	1.0	1.0	1.0
0.0013	8.1152	3100	0.0006	1.0	1.0	1.0	1.0
0.0013	8.3770	3200	0.0006	1.0	1.0	1.0	1.0
0.0013	8.6387	3300	0.0006	1.0	1.0	1.0	1.0
0.0013	8.9005	3400	0.0006	1.0	1.0	1.0	1.0
0.0011	9.1623	3500	0.0006	1.0	1.0	1.0	1.0
0.0011	9.4241	3600	0.0006	1.0	1.0	1.0	1.0
0.0011	9.6859	3700	0.0006	1.0	1.0	1.0	1.0
0.0011	9.9476	3800	0.0005	1.0	1.0	1.0	1.0
0.0011	10.2094	3900	0.0005	1.0	1.0	1.0	1.0
0.001	10.4712	4000	0.0005	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.43.3
• Pytorch 2.1.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1