lilt-en-funsd2

eroy4u/lilt-en-funsd2

lilt-en-funsd2 is a token classification model from eroy4u. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

12% of all-time downloads

All-time downloads

Public

Parameters

130M

7.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors521 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: lilt
Access: Public
Created: Nov 8, 2025
Updated: Nov 8, 2025
SHA: 68cfc9a1

Try a prompt

Base models

SCUT-DLVCLab/lilt-roberta-en-base

Model card

From the Hugging Face model README

lilt-en-funsd2

This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0440
Totalamt: {'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}
Overall Precision: 1.0
Overall Recall: 0.6667
Overall F1: 0.8
Overall Accuracy: 0.9947

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: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
training_steps: 2500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Totalamt	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.0134	50.0	200	0.0440	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	100.0	400	0.0472	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	150.0	600	0.0490	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	200.0	800	0.0504	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	250.0	1000	0.0513	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	300.0	1200	0.0519	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	350.0	1400	0.0525	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	400.0	1600	0.0529	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	450.0	1800	0.0533	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	500.0	2000	0.0536	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	550.0	2200	0.0537	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947
0.0	600.0	2400	0.0538	{'precision': 1.0, 'recall': 0.6666666666666666, 'f1': 0.8, 'number': 3}	1.0	0.6667	0.8	0.9947

Framework versions

Transformers 4.57.1
Pytorch 2.9.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

Task: Token Classification
Library: transformers
Type: lilt
License: mit
Created: Nov 8, 2025
Updated: Nov 8, 2025