balanced-augmented-ft-roberta-gest-pred-seqeval-partialmatch

Jsevisal/balanced-augmented-ft-roberta-gest-pred-seqeval-partialmatch

balanced-augmented-ft-roberta-gest-pred-seqeval-partialmatch is a token classification model from Jsevisal. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as other.

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

Downloads · 30 days

5% of all-time downloads

All-time downloads

264

Public

Parameters

559M

11.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin2.2 GB · 50%

Parameter types

How the weights are stored.

F32559M · 100%

Try a prompt

Datasets

Jsevisal/balanced_augmented_dataset

Model card

From the Hugging Face model README

balanced-augmented-mlroberta-gest-pred-seqeval-partialmatch

This model is a fine-tuned version of xlm-roberta-large-finetuned-conll03-english on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9051
Precision: 0.8395
Recall: 0.8114
F1: 0.8189
Accuracy: 0.7987

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
3.1888	1.0	32	2.4935	0.2783	0.1689	0.1470	0.3131
2.25	2.0	64	1.6646	0.6169	0.5430	0.5416	0.5888
1.4955	3.0	96	1.2759	0.7516	0.6600	0.6688	0.6586
0.9512	4.0	128	1.0307	0.8052	0.7394	0.7513	0.7147
0.6053	5.0	160	0.9993	0.7975	0.7757	0.7724	0.7398
0.4064	6.0	192	0.9347	0.8335	0.7939	0.7988	0.7732
0.2802	7.0	224	0.9249	0.8285	0.7970	0.8013	0.7818
0.2062	8.0	256	0.9051	0.8395	0.8114	0.8189	0.7987
0.1372	9.0	288	0.9771	0.8447	0.7922	0.8079	0.7910
0.1	10.0	320	1.0232	0.8246	0.8086	0.8042	0.7974
0.0815	11.0	352	1.0103	0.8391	0.8173	0.8209	0.8024
0.0586	12.0	384	1.0424	0.8366	0.7980	0.8085	0.7932
0.0534	13.0	416	1.1246	0.8318	0.8070	0.8126	0.7969
0.0412	14.0	448	1.0816	0.8338	0.8186	0.8167	0.8028
0.0346	15.0	480	1.1178	0.8277	0.8222	0.8182	0.8037
0.0312	16.0	512	1.1570	0.8387	0.8237	0.8219	0.8037
0.0268	17.0	544	1.1548	0.8375	0.8279	0.8240	0.8028
0.0221	18.0	576	1.1514	0.8316	0.8149	0.8169	0.8005
0.0215	19.0	608	1.1698	0.8351	0.8221	0.8204	0.8037
0.0213	20.0	640	1.1691	0.8311	0.8196	0.8166	0.8015

Framework versions

Transformers 4.27.3
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2

LICENSE

Copyright (c) 2014, Universidad Carlos III de Madrid. Todos los derechos reservados. Este software es propiedad de la Universidad Carlos III de Madrid, grupo de investigación Robots Sociales. La Universidad Carlos III de Madrid es titular en exclusiva de los derechos de propiedad intelectual de este software. Queda prohibido cualquier uso indebido o no autorizado, entre estos, a título enunciativo pero no limitativo, la reproducción, fijación, distribución, comunicación pública, ingeniería inversa y/o transformación sobre dicho software, ya sea total o parcialmente, siendo el responsable del uso indebido o no autorizado también responsable de las consecuencias legales que pudieran derivarse de sus actos.

Task: Token Classification
Library: transformers
Type: xlm-roberta
License: other
Created: Mar 27, 2023
Updated: Jun 23, 2025