layoutlm-funsd

barryjdevereux/layoutlm-funsd

layoutlm-funsd is a token classification model from barryjdevereux. Use it when you need labels on individual words, such as names. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

14% of all-time downloads

All-time downloads

Public

Parameters

113M

3.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors451 MB · 100%

At a glance

Task: Token Classification
Library: transformers
Model type: layoutlm
Access: Public
Created: Nov 7, 2023
Updated: Nov 7, 2023
SHA: d28f9b8f

Try a prompt

Base models

microsoft/layoutlm-base-uncased

Datasets

funsd

Model card

From the Hugging Face model README

layoutlm-funsd

This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the funsd dataset. It achieves the following results on the evaluation set:

Loss: 0.6559
Answer: {'precision': 0.7160220994475138, 'recall': 0.8009888751545118, 'f1': 0.7561260210035006, 'number': 809}
Header: {'precision': 0.31932773109243695, 'recall': 0.31932773109243695, 'f1': 0.31932773109243695, 'number': 119}
Question: {'precision': 0.7674216027874564, 'recall': 0.8272300469483568, 'f1': 0.7962042476276546, 'number': 1065}
Overall Precision: 0.7215
Overall Recall: 0.7863
Overall F1: 0.7525
Overall Accuracy: 0.8165

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: 3e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Answer	Header	Question	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
1.8319	1.0	10	1.6114	{'precision': 0.02668213457076566, 'recall': 0.02843016069221261, 'f1': 0.02752842609216038, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.21885521885521886, 'recall': 0.18309859154929578, 'f1': 0.19938650306748468, 'number': 1065}	0.1244	0.1094	0.1164	0.3478
1.4535	2.0	20	1.2624	{'precision': 0.2141119221411192, 'recall': 0.21755253399258342, 'f1': 0.2158185162477008, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.45236250968241676, 'recall': 0.5483568075117371, 'f1': 0.4957555178268252, 'number': 1065}	0.3597	0.3813	0.3702	0.5768
1.099	3.0	30	0.9496	{'precision': 0.46866840731070497, 'recall': 0.4437577255871446, 'f1': 0.4558730158730159, 'number': 809}	{'precision': 0.05405405405405406, 'recall': 0.01680672268907563, 'f1': 0.02564102564102564, 'number': 119}	{'precision': 0.6174957118353345, 'recall': 0.676056338028169, 'f1': 0.6454504706409682, 'number': 1065}	0.5490	0.5424	0.5457	0.7045
0.8218	4.0	40	0.7695	{'precision': 0.5814606741573034, 'recall': 0.7676143386897404, 'f1': 0.6616941928609482, 'number': 809}	{'precision': 0.1935483870967742, 'recall': 0.10084033613445378, 'f1': 0.13259668508287292, 'number': 119}	{'precision': 0.6691983122362869, 'recall': 0.7446009389671362, 'f1': 0.7048888888888889, 'number': 1065}	0.6160	0.7155	0.6620	0.7620
0.6633	5.0	50	0.7008	{'precision': 0.6237006237006237, 'recall': 0.7416563658838071, 'f1': 0.6775832862789385, 'number': 809}	{'precision': 0.2571428571428571, 'recall': 0.15126050420168066, 'f1': 0.19047619047619044, 'number': 119}	{'precision': 0.7088055797733217, 'recall': 0.7633802816901408, 'f1': 0.7350813743218807, 'number': 1065}	0.6567	0.7180	0.6860	0.7819
0.5651	6.0	60	0.6659	{'precision': 0.6533192834562698, 'recall': 0.7663782447466008, 'f1': 0.7053469852104665, 'number': 809}	{'precision': 0.2564102564102564, 'recall': 0.25210084033613445, 'f1': 0.2542372881355932, 'number': 119}	{'precision': 0.7251655629139073, 'recall': 0.8225352112676056, 'f1': 0.7707875054993402, 'number': 1065}	0.6711	0.7657	0.7153	0.7976
0.4862	7.0	70	0.6514	{'precision': 0.6496815286624203, 'recall': 0.7564894932014833, 'f1': 0.6990291262135921, 'number': 809}	{'precision': 0.30927835051546393, 'recall': 0.25210084033613445, 'f1': 0.2777777777777778, 'number': 119}	{'precision': 0.7352206494587843, 'recall': 0.8291079812206573, 'f1': 0.7793468667255075, 'number': 1065}	0.6808	0.7652	0.7205	0.8038
0.4421	8.0	80	0.6342	{'precision': 0.6720085470085471, 'recall': 0.7775030902348579, 'f1': 0.7209169054441262, 'number': 809}	{'precision': 0.3017241379310345, 'recall': 0.29411764705882354, 'f1': 0.29787234042553185, 'number': 119}	{'precision': 0.7461928934010152, 'recall': 0.828169014084507, 'f1': 0.7850467289719626, 'number': 1065}	0.6920	0.7757	0.7315	0.8087
0.3898	9.0	90	0.6485	{'precision': 0.7045203969128997, 'recall': 0.7898640296662547, 'f1': 0.7447552447552448, 'number': 809}	{'precision': 0.32038834951456313, 'recall': 0.2773109243697479, 'f1': 0.29729729729729737, 'number': 119}	{'precision': 0.7669902912621359, 'recall': 0.815962441314554, 'f1': 0.7907188353048227, 'number': 1065}	0.7191	0.7732	0.7452	0.8099
0.3531	10.0	100	0.6380	{'precision': 0.7058177826564215, 'recall': 0.7948084054388134, 'f1': 0.7476744186046511, 'number': 809}	{'precision': 0.33980582524271846, 'recall': 0.29411764705882354, 'f1': 0.31531531531531537, 'number': 119}	{'precision': 0.7579672695951766, 'recall': 0.8262910798122066, 'f1': 0.7906558849955077, 'number': 1065}	0.7163	0.7817	0.7476	0.8155
0.3226	11.0	110	0.6484	{'precision': 0.72, 'recall': 0.8009888751545118, 'f1': 0.7583382094792276, 'number': 809}	{'precision': 0.2962962962962963, 'recall': 0.2689075630252101, 'f1': 0.28193832599118945, 'number': 119}	{'precision': 0.7819481680071493, 'recall': 0.8215962441314554, 'f1': 0.8012820512820512, 'number': 1065}	0.7311	0.7802	0.7549	0.8171
0.3066	12.0	120	0.6399	{'precision': 0.7007616974972797, 'recall': 0.796044499381953, 'f1': 0.7453703703703702, 'number': 809}	{'precision': 0.3181818181818182, 'recall': 0.29411764705882354, 'f1': 0.3056768558951965, 'number': 119}	{'precision': 0.7610544217687075, 'recall': 0.8403755868544601, 'f1': 0.7987505577867025, 'number': 1065}	0.7138	0.7898	0.7499	0.8195
0.2932	13.0	130	0.6628	{'precision': 0.7155555555555555, 'recall': 0.796044499381953, 'f1': 0.7536571094207138, 'number': 809}	{'precision': 0.288, 'recall': 0.3025210084033613, 'f1': 0.2950819672131147, 'number': 119}	{'precision': 0.7783783783783784, 'recall': 0.8112676056338028, 'f1': 0.7944827586206896, 'number': 1065}	0.7232	0.7747	0.7481	0.8163
0.2739	14.0	140	0.6550	{'precision': 0.7190265486725663, 'recall': 0.8034610630407911, 'f1': 0.7589025102159953, 'number': 809}	{'precision': 0.3157894736842105, 'recall': 0.3025210084033613, 'f1': 0.30901287553648066, 'number': 119}	{'precision': 0.766695576756288, 'recall': 0.8300469483568075, 'f1': 0.7971145175834085, 'number': 1065}	0.7232	0.7878	0.7541	0.8173
0.2715	15.0	150	0.6559	{'precision': 0.7160220994475138, 'recall': 0.8009888751545118, 'f1': 0.7561260210035006, 'number': 809}	{'precision': 0.31932773109243695, 'recall': 0.31932773109243695, 'f1': 0.31932773109243695, 'number': 119}	{'precision': 0.7674216027874564, 'recall': 0.8272300469483568, 'f1': 0.7962042476276546, 'number': 1065}	0.7215	0.7863	0.7525	0.8165

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Task: Token Classification
Library: transformers
Type: layoutlm
Created: Nov 7, 2023
Updated: Nov 7, 2023