layoutlmv3-funsd

apriliantono/layoutlmv3-funsd

layoutlmv3-funsd is a token classification model from apriliantono. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as cc-by-nc-sa-4.0.

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

Downloads · 30 days

6% of all-time downloads

All-time downloads

105

Public

Parameters

128M

3.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors511 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: cc-by-nc-sa-4.0
Model type: layoutlm
Access: Public
Created: Feb 13, 2025
Updated: Feb 13, 2025
SHA: 903d3127

Try a prompt

Base models

microsoft/layoutlmv3-base

Datasets

funsd

Model card

From the Hugging Face model README

layoutlmv3-funsd

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

Loss: 1.5869
Answer: {'precision': 0.06117908787541713, 'recall': 0.13597033374536466, 'f1': 0.08438818565400844, 'number': 809}
Header: {'precision': 0.015789473684210527, 'recall': 0.025210084033613446, 'f1': 0.01941747572815534, 'number': 119}
Question: {'precision': 0.1918819188191882, 'recall': 0.39061032863849765, 'f1': 0.257346118156511, 'number': 1065}
Overall Precision: 0.1273
Overall Recall: 0.2654
Overall F1: 0.1721
Overall Accuracy: 0.4198

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
1.9534	1.0	10	1.7563	{'precision': 0.021798365122615803, 'recall': 0.009888751545117428, 'f1': 0.013605442176870746, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.029567053854276663, 'recall': 0.05258215962441314, 'f1': 0.037850625211220006, 'number': 1065}	0.0283	0.0321	0.0301	0.2212
1.7529	2.0	20	1.6621	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.28431372549019607, 'recall': 0.027230046948356807, 'f1': 0.049700085689802914, 'number': 1065}	0.0769	0.0146	0.0245	0.3060
1.6557	3.0	30	1.6846	{'precision': 0.025611175785797437, 'recall': 0.054388133498145856, 'f1': 0.034823901859912944, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.12563044475011462, 'recall': 0.25727699530516435, 'f1': 0.16882316697473815, 'number': 1065}	0.0816	0.1596	0.1079	0.3209
1.5482	4.0	40	1.6706	{'precision': 0.03781297904956566, 'recall': 0.09147095179233622, 'f1': 0.05350686912509039, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.1303972366148532, 'recall': 0.28356807511737087, 'f1': 0.17864537119195506, 'number': 1065}	0.0880	0.1887	0.1200	0.3287
1.4535	5.0	50	1.6188	{'precision': 0.035333707234997194, 'recall': 0.07787391841779975, 'f1': 0.04861111111111111, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.16204690831556504, 'recall': 0.28544600938967135, 'f1': 0.20673240394423667, 'number': 1065}	0.0988	0.1841	0.1286	0.3580
1.3517	6.0	60	1.5478	{'precision': 0.04584221748400853, 'recall': 0.10630407911001236, 'f1': 0.06405959031657356, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.22127329192546583, 'recall': 0.2676056338028169, 'f1': 0.24224394390140241, 'number': 1065}	0.1147	0.1862	0.1420	0.4143
1.2494	7.0	70	1.5328	{'precision': 0.049443757725587144, 'recall': 0.09888751545117429, 'f1': 0.06592501030078285, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.16467780429594273, 'recall': 0.323943661971831, 'f1': 0.21835443037974686, 'number': 1065}	0.1114	0.2132	0.1463	0.4101
1.1759	8.0	80	1.5335	{'precision': 0.051237766263673, 'recall': 0.1100123609394314, 'f1': 0.06991358994501179, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.1746031746031746, 'recall': 0.3408450704225352, 'f1': 0.2309160305343511, 'number': 1065}	0.1157	0.2268	0.1532	0.4102
1.1089	9.0	90	1.5206	{'precision': 0.055843408175014396, 'recall': 0.11990111248454882, 'f1': 0.07619795758051845, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.18374558303886926, 'recall': 0.34178403755868547, 'f1': 0.23900196979645438, 'number': 1065}	0.1181	0.2313	0.1563	0.4231
1.0817	10.0	100	1.5927	{'precision': 0.05695830886670581, 'recall': 0.11990111248454882, 'f1': 0.07722929936305732, 'number': 809}	{'precision': 0.006993006993006993, 'recall': 0.008403361344537815, 'f1': 0.007633587786259542, 'number': 119}	{'precision': 0.19786396852164137, 'recall': 0.3305164319248826, 'f1': 0.24753867791842474, 'number': 1065}	0.1241	0.2258	0.1602	0.4152
1.025	11.0	110	1.5822	{'precision': 0.058394160583941604, 'recall': 0.12855377008652658, 'f1': 0.08030888030888031, 'number': 809}	{'precision': 0.005952380952380952, 'recall': 0.008403361344537815, 'f1': 0.006968641114982578, 'number': 119}	{'precision': 0.20356943669827104, 'recall': 0.3427230046948357, 'f1': 0.2554233729881036, 'number': 1065}	0.1256	0.2358	0.1639	0.4192
1.0025	12.0	120	1.5577	{'precision': 0.056910569105691054, 'recall': 0.1211372064276885, 'f1': 0.07743974713551956, 'number': 809}	{'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}	{'precision': 0.19216589861751152, 'recall': 0.39154929577464787, 'f1': 0.2578052550231839, 'number': 1065}	0.1269	0.2584	0.1702	0.4225
0.9791	13.0	130	1.5920	{'precision': 0.0602655771195097, 'recall': 0.14585908529048208, 'f1': 0.08529092880375859, 'number': 809}	{'precision': 0.015306122448979591, 'recall': 0.025210084033613446, 'f1': 0.01904761904761905, 'number': 119}	{'precision': 0.19343945972021226, 'recall': 0.37652582159624415, 'f1': 0.2555768005098789, 'number': 1065}	0.1235	0.2619	0.1678	0.4155
0.9566	14.0	140	1.5777	{'precision': 0.06111111111111111, 'recall': 0.13597033374536466, 'f1': 0.0843234955921809, 'number': 809}	{'precision': 0.016483516483516484, 'recall': 0.025210084033613446, 'f1': 0.019933554817275746, 'number': 119}	{'precision': 0.19855072463768117, 'recall': 0.38591549295774646, 'f1': 0.26220095693779905, 'number': 1065}	0.1293	0.2629	0.1734	0.4223
0.9369	15.0	150	1.5869	{'precision': 0.06117908787541713, 'recall': 0.13597033374536466, 'f1': 0.08438818565400844, 'number': 809}	{'precision': 0.015789473684210527, 'recall': 0.025210084033613446, 'f1': 0.01941747572815534, 'number': 119}	{'precision': 0.1918819188191882, 'recall': 0.39061032863849765, 'f1': 0.257346118156511, 'number': 1065}	0.1273	0.2654	0.1721	0.4198

Framework versions

Transformers 4.48.2
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Task: Token Classification
Library: transformers
Type: layoutlm
License: cc-by-nc-sa-4.0
Created: Feb 13, 2025
Updated: Feb 13, 2025