nepali_citiznship_model_final

bashyaldhiraj2067/nepali_citiznship_model_final

nepali_citiznship_model_final is a token classification model from bashyaldhiraj2067. 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

27% of all-time downloads

All-time downloads

Public

Parameters

284M

8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.1 GB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: lilt
Access: Public
Created: Apr 5, 2025
Updated: Apr 5, 2025
SHA: 94e9bb3a

Try a prompt

Base models

nielsr/lilt-xlm-roberta-base

Model card

From the Hugging Face model README

nepali_citiznship_model_final

This model is a fine-tuned version of nielsr/lilt-xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1655
Precision: 0.9135
Recall: 0.9075
F1: 0.9105
Accuracy: 0.9720

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: 8
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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.5625	50	0.3123	0.7434	0.7810	0.7617	0.9123
No log	3.125	100	0.1550	0.8621	0.8880	0.8749	0.9605
No log	4.6875	150	0.1411	0.8959	0.8989	0.8974	0.9665
No log	6.25	200	0.1282	0.8969	0.9194	0.9080	0.9701
No log	7.8125	250	0.1171	0.9143	0.9204	0.9174	0.9739
No log	9.375	300	0.1213	0.9117	0.9214	0.9165	0.9734
No log	10.9375	350	0.1270	0.9210	0.9092	0.9150	0.9729
No log	12.5	400	0.1269	0.9014	0.9184	0.9098	0.9712
No log	14.0625	450	0.1300	0.9192	0.9171	0.9181	0.9732
0.18	15.625	500	0.1377	0.9138	0.9002	0.9070	0.9707
0.18	17.1875	550	0.1378	0.9164	0.9052	0.9108	0.9719
0.18	18.75	600	0.1471	0.917	0.9088	0.9129	0.9727
0.18	20.3125	650	0.1453	0.9144	0.9065	0.9104	0.9721
0.18	21.875	700	0.1586	0.9086	0.9035	0.9061	0.9704
0.18	23.4375	750	0.1546	0.9149	0.9055	0.9102	0.9721
0.18	25.0	800	0.1595	0.9129	0.9108	0.9119	0.9722
0.18	26.5625	850	0.1569	0.9054	0.9039	0.9046	0.9704
0.18	28.125	900	0.1687	0.9153	0.9072	0.9112	0.9720
0.18	29.6875	950	0.1655	0.9135	0.9075	0.9105	0.9720

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

Task: Token Classification
Library: transformers
Type: lilt
License: mit
Created: Apr 5, 2025
Updated: Apr 5, 2025