mdeberta-semeval25_narratives09_maxf1_fold4

g-assismoraes/mdeberta-semeval25_narratives09_maxf1_fold4

mdeberta-semeval25_narratives09_maxf1_fold4 is a text classification model from g-assismoraes. Use it when you need a label for a piece of text. 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

8% of all-time downloads

All-time downloads

Public

Parameters

279M

5.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.1 GB · 100%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: deberta-v2
Access: Public
Created: Oct 27, 2024
Updated: Oct 27, 2024
SHA: 0731daf2

Try a prompt

Base models

microsoft/mdeberta-v3-base

Model card

From the Hugging Face model README

mdeberta-semeval25_narratives09_maxf1_fold4

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.7723
Precision Samples: 0.3728
Recall Samples: 0.7825
F1 Samples: 0.4666
Precision Macro: 0.6810
Recall Macro: 0.4981
F1 Macro: 0.2753
Precision Micro: 0.3085
Recall Micro: 0.7647
F1 Micro: 0.4397
Precision Weighted: 0.4751
Recall Weighted: 0.7647
F1 Weighted: 0.3999

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: 32
eval_batch_size: 32
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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision Samples	Recall Samples	F1 Samples	Precision Macro	Recall Macro	F1 Macro	Precision Micro	Recall Micro	F1 Micro	Precision Weighted	Recall Weighted	F1 Weighted
5.7927	1.0	19	4.9875	1.0	0.0	0.0	1.0	0.0476	0.0476	1.0	0.0	0.0	1.0	0.0	0.0
5.0899	2.0	38	4.7740	0.3023	0.3386	0.2905	0.8797	0.1700	0.1306	0.316	0.3098	0.3129	0.7069	0.3098	0.2068
5.1834	3.0	57	4.4517	0.3345	0.4776	0.3732	0.8493	0.2311	0.1457	0.3314	0.4471	0.3806	0.6524	0.4471	0.2368
4.8195	4.0	76	4.2678	0.3568	0.6033	0.4120	0.7813	0.3360	0.2022	0.2962	0.5843	0.3931	0.5651	0.5843	0.3175
4.6183	5.0	95	4.0323	0.3872	0.6493	0.4394	0.7313	0.3521	0.2083	0.3204	0.6157	0.4215	0.5136	0.6157	0.3340
4.4332	6.0	114	3.9321	0.3921	0.7197	0.4615	0.7159	0.4256	0.2492	0.3092	0.7020	0.4293	0.4982	0.7020	0.3797
4.0992	7.0	133	3.8524	0.3728	0.7641	0.4640	0.6877	0.4789	0.2773	0.3147	0.7490	0.4432	0.4802	0.7490	0.4020
4.1885	8.0	152	3.7985	0.3751	0.7932	0.4751	0.6821	0.4933	0.2773	0.3176	0.7647	0.4488	0.4788	0.7647	0.4065
4.3678	9.0	171	3.7859	0.3739	0.7825	0.4678	0.6821	0.4981	0.2766	0.3105	0.7647	0.4417	0.4760	0.7647	0.4010
3.9512	10.0	190	3.7723	0.3728	0.7825	0.4666	0.6810	0.4981	0.2753	0.3085	0.7647	0.4397	0.4751	0.7647	0.3999

Framework versions

Transformers 4.46.0
Pytorch 2.3.1
Datasets 2.21.0
Tokenizers 0.20.1

Task: Text Classification
Library: transformers
Type: deberta-v2
License: mit
Created: Oct 27, 2024
Updated: Oct 27, 2024