lmv2ubiai-pan8doc-06-11

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9633
• Dob Precision: 1.0
• Dob Recall: 1.0
• Dob F1: 1.0
• Dob Number: 2
• Fname Precision: 0.6667
• Fname Recall: 1.0
• Fname F1: 0.8
• Fname Number: 2
• Name Precision: 1.0
• Name Recall: 1.0
• Name F1: 1.0
• Name Number: 2
• Pan Precision: 1.0
• Pan Recall: 1.0
• Pan F1: 1.0
• Pan Number: 2
• Overall Precision: 0.8889
• Overall Recall: 1.0
• Overall F1: 0.9412
• Overall Accuracy: 0.9821

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: 4e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Dob Precision	Dob Recall	Dob F1	Dob Number	Fname Precision	Fname Recall	Fname F1	Fname Number	Name Precision	Name Recall	Name F1	Name Number	Pan Precision	Pan Recall	Pan F1	Pan Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
2.1195	1.0	6	1.7519	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	0.7857
1.6994	2.0	12	1.5117	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	0.7857
1.5521	3.0	18	1.4130	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	0.7857
1.4726	4.0	24	1.3410	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	0.7857
1.395	5.0	30	1.2693	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.0	0.0	0.0	0.7857
1.3131	6.0	36	1.2079	1.0	1.0	1.0	2	0.1667	0.5	0.25	2	0.0	0.0	0.0	2	0.0	0.0	0.0	2	0.3	0.375	0.3333	0.8929
1.2474	7.0	42	1.1495	1.0	1.0	1.0	2	0.2	0.5	0.2857	2	0.0	0.0	0.0	2	1.0	1.0	1.0	2	0.4167	0.625	0.5	0.9286
1.1869	8.0	48	1.0942	1.0	1.0	1.0	2	0.2	0.5	0.2857	2	0.0	0.0	0.0	2	1.0	1.0	1.0	2	0.4167	0.625	0.5	0.9286
1.1369	9.0	54	1.0453	1.0	1.0	1.0	2	0.4	1.0	0.5714	2	0.0	0.0	0.0	2	1.0	1.0	1.0	2	0.5455	0.75	0.6316	0.9464
1.0882	10.0	60	1.0054	1.0	1.0	1.0	2	0.5	1.0	0.6667	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.7	0.875	0.7778	0.9643
1.0482	11.0	66	0.9633	1.0	1.0	1.0	2	0.6667	1.0	0.8	2	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.8889	1.0	0.9412	0.9821
1.017	12.0	72	0.9368	1.0	1.0	1.0	2	0.6667	1.0	0.8	2	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.8889	1.0	0.9412	0.9643
0.9825	13.0	78	0.9139	1.0	1.0	1.0	2	0.6667	1.0	0.8	2	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.8889	1.0	0.9412	0.9821
0.9459	14.0	84	0.8837	1.0	1.0	1.0	2	0.6667	1.0	0.8	2	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.8889	1.0	0.9412	0.9643
0.9155	15.0	90	0.8472	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.8819	16.0	96	0.8231	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.8523	17.0	102	0.7957	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.6667	1.0	0.8	2	1.0	1.0	1.0	2	0.8889	1.0	0.9412	0.9821
0.8251	18.0	108	0.7681	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.7982	19.0	114	0.7533	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.7762	20.0	120	0.7283	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.7558	21.0	126	0.7114	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.7346	22.0	132	0.6889	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.7116	23.0	138	0.6697	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.6898	24.0	144	0.6593	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.6748	25.0	150	0.6356	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.6487	26.0	156	0.6142	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.6312	27.0	162	0.6008	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.6156	28.0	168	0.5855	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.5961	29.0	174	0.5625	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643
0.5781	30.0	180	0.5553	1.0	1.0	1.0	2	1.0	1.0	1.0	2	0.5	0.5	0.5	2	1.0	1.0	1.0	2	0.875	0.875	0.875	0.9643

Framework versions

• Transformers 4.20.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1