balanced-augmented-distilbert-base-gest-pred-seqeval-partialmatch

Jsevisal/balanced-augmented-distilbert-base-gest-pred-seqeval-partialmatch

balanced-augmented-distilbert-base-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

26% of all-time downloads

All-time downloads

Public

Parameters

65.2M

2.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin261 MB · 50%

At a glance

Task: Token Classification
Library: transformers
License: other
Model type: distilbert
Access: Public
Created: Mar 27, 2023
Updated: Jan 21, 2025
SHA: f6f0b19d

Try a prompt

Datasets

Jsevisal/balanced_augmented_dataset

Model card

From the Hugging Face model README

balanced-augmented-distilbert-base-gest-pred-seqeval-partialmatch

This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.945763
Precision: 0.8278
Recall: 0.756
F1: 0.7773
Accuracy: 0.7808

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
2.675	1.0	32	2.2896	0.2866	0.1994	0.2017	0.3764
2.0426	2.0	64	1.7819	0.5176	0.4342	0.4249	0.5357
1.5284	3.0	96	1.4798	0.7435	0.5285	0.5441	0.6210
1.1542	4.0	128	1.3020	0.7677	0.6013	0.6319	0.6737
0.8963	5.0	160	1.1608	0.7886	0.6494	0.6814	0.7053
0.6926	6.0	192	1.1128	0.7891	0.6968	0.7238	0.7316
0.5249	7.0	224	1.0319	0.8019	0.7179	0.7406	0.7487
0.4063	8.0	256	1.0163	0.8117	0.7091	0.7399	0.7570
0.3238	9.0	288	1.0071	0.8052	0.7201	0.7447	0.7642
0.2578	10.0	320	0.9579	0.8070	0.7469	0.7655	0.7740
0.2097	11.0	352	0.9458	0.8278	0.7560	0.7773	0.7808
0.1729	12.0	384	0.9760	0.8184	0.7471	0.7670	0.7756
0.1473	13.0	416	0.9598	0.8175	0.7503	0.7702	0.7823
0.1235	14.0	448	0.9671	0.8244	0.7548	0.7734	0.7802
0.1082	15.0	480	0.9788	0.8169	0.7508	0.7709	0.7746
0.0966	16.0	512	1.0090	0.8098	0.7489	0.7669	0.7715
0.0871	17.0	544	0.9926	0.8111	0.7545	0.7690	0.7694
0.0825	18.0	576	1.0070	0.8144	0.7524	0.7688	0.7704
0.0768	19.0	608	1.0137	0.8191	0.7557	0.7743	0.7746
0.0744	20.0	640	1.0130	0.8209	0.7559	0.7750	0.7746

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: distilbert
License: other
Created: Mar 27, 2023
Updated: Jan 21, 2025