layoutlmv3-finetuned-language-levels-v2-4000

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: 0.0153
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Accuracy: 1.0

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: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.2618	100	0.8437	0.9605	0.9605	0.9605	0.6867
No log	0.5236	200	0.5414	0.9962	0.9981	0.9972	0.8052
No log	0.7853	300	0.1877	0.9944	0.9962	0.9953	0.9838
No log	1.0471	400	0.0502	1.0	1.0	1.0	0.9903
0.5339	1.3089	500	0.0153	1.0	1.0	1.0	1.0
0.5339	1.5707	600	0.0085	1.0	1.0	1.0	1.0
0.5339	1.8325	700	0.0062	1.0	1.0	1.0	1.0
0.5339	2.0942	800	0.0049	1.0	1.0	1.0	1.0
0.5339	2.3560	900	0.0041	1.0	1.0	1.0	1.0
0.0125	2.6178	1000	0.0035	1.0	1.0	1.0	1.0
0.0125	2.8796	1100	0.0031	1.0	1.0	1.0	1.0
0.0125	3.1414	1200	0.0028	1.0	1.0	1.0	1.0
0.0125	3.4031	1300	0.0026	1.0	1.0	1.0	1.0
0.0125	3.6649	1400	0.0024	1.0	1.0	1.0	1.0
0.0052	3.9267	1500	0.0022	1.0	1.0	1.0	1.0
0.0052	4.1885	1600	0.0021	1.0	1.0	1.0	1.0
0.0052	4.4503	1700	0.0020	1.0	1.0	1.0	1.0
0.0052	4.7120	1800	0.0020	1.0	1.0	1.0	1.0
0.0052	4.9738	1900	0.0019	1.0	1.0	1.0	1.0
0.004	5.2356	2000	0.0019	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.43.2
• Pytorch 2.1.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1