deberta-v3-base-uner-down200

izziehe/deberta-v3-base-uner-down200

deberta-v3-base-uner-down200 is a token classification model from izziehe. 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

19% of all-time downloads

All-time downloads

Public

Parameters

184M

738 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors735 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: deberta-v2
Access: Public
Created: Nov 27, 2025
Updated: Nov 27, 2025
SHA: 47e13a1c

Try a prompt

Base models

microsoft/deberta-v3-base

Model card

From the Hugging Face model README

deberta-v3-base-uner-down200

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1055
F1: 0.6677
Precision: 0.6249
Recall: 0.7168
Accuracy: 0.9765

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: 2.5e-05
train_batch_size: 16
eval_batch_size: 32
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
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall	Accuracy
0.0587	1.5385	20	0.2010	0.0	0.0	0.0	0.9422
0.0916	3.0769	40	0.1425	0.2535	0.3108	0.2141	0.9535
0.0571	4.6154	60	0.1251	0.3194	0.3126	0.3265	0.9594
0.0289	6.1538	80	0.1168	0.4129	0.3915	0.4368	0.9651
0.0144	7.6923	100	0.1160	0.4527	0.4473	0.4584	0.9671
0.0041	9.2308	120	0.1040	0.5464	0.4822	0.6303	0.9713
0.0036	10.7692	140	0.1011	0.5780	0.5410	0.6205	0.9728
0.0026	12.3077	160	0.1000	0.6219	0.5760	0.6757	0.9743
0.0025	13.8462	180	0.1004	0.6285	0.5867	0.6768	0.9749
0.003	15.3846	200	0.1018	0.6373	0.5989	0.6811	0.9753
0.0032	16.9231	220	0.1034	0.6484	0.6117	0.6897	0.9758
0.0022	18.4615	240	0.1035	0.6529	0.6105	0.7016	0.9760
0.0002	20.0	260	0.1044	0.6552	0.6154	0.7005	0.9763
0.0021	21.5385	280	0.1046	0.6629	0.6240	0.7070	0.9767
0.0029	23.0769	300	0.1041	0.6643	0.6215	0.7135	0.9764
0.0043	24.6154	320	0.1046	0.6663	0.6234	0.7157	0.9765
0.0012	26.1538	340	0.1052	0.6673	0.6251	0.7157	0.9765
0.0014	27.6923	360	0.1054	0.6680	0.6255	0.7168	0.9765
0.0009	29.2308	380	0.1055	0.6677	0.6249	0.7168	0.9765

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

Task: Token Classification
Library: transformers
Type: deberta-v2
License: mit
Created: Nov 27, 2025
Updated: Nov 27, 2025