CNEC2_0_extended_xlm-roberta-large

stulcrad/CNEC2_0_extended_xlm-roberta-large

CNEC2_0_extended_xlm-roberta-large is a token classification model from stulcrad. 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

13% of all-time downloads

All-time downloads

101

Public

Parameters

559M

159 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.2 GB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: xlm-roberta
Access: Public
Created: May 2, 2024
Updated: Jun 5, 2025
SHA: 6d8eefbf

Base models

FacebookAI/xlm-roberta-large

Datasets

stulcrad/CNEC2_0_CONLL_ext

Model card

From the Hugging Face model README

CNEC2_0_extended_xlm-roberta-large

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the cnec dataset. It achieves the following results on the evaluation set:

Loss: 0.1919
Precision: 0.8861
Recall: 0.9072
F1: 0.8965
Accuracy: 0.9773

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: 2e-05
train_batch_size: 8
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

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1664	1.12	1000	0.1312	0.8299	0.8521	0.8408	0.9695
0.1153	2.24	2000	0.1121	0.8283	0.8640	0.8458	0.9722
0.0815	3.36	3000	0.1159	0.8523	0.8531	0.8527	0.9735
0.0633	4.48	4000	0.1166	0.8515	0.8819	0.8664	0.9750
0.0472	5.6	5000	0.1624	0.8635	0.8918	0.8774	0.9735
0.0369	6.72	6000	0.1476	0.8710	0.8983	0.8844	0.9770
0.0325	7.84	7000	0.1590	0.8710	0.8943	0.8825	0.9752
0.0268	8.96	8000	0.1698	0.8709	0.9037	0.8870	0.9761
0.0236	10.08	9000	0.1721	0.8807	0.9087	0.8945	0.9763
0.0125	11.2	10000	0.1843	0.8781	0.9047	0.8912	0.9768
0.009	12.32	11000	0.1971	0.8789	0.9077	0.8931	0.9766
0.0097	13.44	12000	0.1823	0.8857	0.9077	0.8966	0.9775
0.0077	14.56	13000	0.1919	0.8861	0.9072	0.8965	0.9773

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0

Task: Token Classification
Library: transformers
Type: xlm-roberta
License: mit
Languages: cs
Created: May 2, 2024
Updated: Jun 5, 2025