mdeberta-semeval25_maxf1_fold5

g-assismoraes/mdeberta-semeval25_maxf1_fold5

mdeberta-semeval25_maxf1_fold5 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

19% of all-time downloads

All-time downloads

Public

Parameters

279M

4.5 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: ec25d9cf

Try a prompt

Base models

microsoft/mdeberta-v3-base

Model card

From the Hugging Face model README

mdeberta-semeval25_maxf1_fold5

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: 8.7990
Precision Samples: 0.1660
Recall Samples: 0.4739
F1 Samples: 0.2271
Precision Macro: 0.8737
Recall Macro: 0.3063
F1 Macro: 0.2305
Precision Micro: 0.1452
Recall Micro: 0.3694
F1 Micro: 0.2085
Precision Weighted: 0.6156
Recall Weighted: 0.3694
F1 Weighted: 0.1150

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
10.6336	1.0	19	9.9912	1.0	0.0	0.0	1.0	0.2	0.2	1.0	0.0	0.0	1.0	0.0	0.0
9.4458	2.0	38	9.6839	0.1655	0.2456	0.1864	0.9814	0.2222	0.2062	0.1655	0.1381	0.1506	0.8858	0.1381	0.0406
9.4682	3.0	57	9.4970	0.1563	0.2984	0.1882	0.9642	0.2349	0.2108	0.1536	0.1772	0.1646	0.8400	0.1772	0.0523
9.0448	4.0	76	9.3362	0.1425	0.3520	0.1881	0.9422	0.2569	0.2152	0.1377	0.2312	0.1726	0.7853	0.2312	0.0641
9.0807	5.0	95	9.1579	0.1457	0.3938	0.1992	0.9336	0.2692	0.2188	0.1407	0.2763	0.1864	0.7446	0.2763	0.0831
8.6731	6.0	114	9.0240	0.1615	0.4392	0.2203	0.8931	0.2830	0.2251	0.1454	0.3153	0.1991	0.6493	0.3153	0.0996
8.9953	7.0	133	8.9087	0.1693	0.4769	0.2311	0.8866	0.3012	0.2322	0.1509	0.3634	0.2132	0.6350	0.3634	0.1190
9.1116	8.0	152	8.8515	0.1689	0.4669	0.2294	0.8861	0.3010	0.2315	0.1482	0.3544	0.2090	0.6334	0.3544	0.1167
8.5738	9.0	171	8.8080	0.1672	0.4879	0.2303	0.8754	0.3143	0.2330	0.1471	0.3904	0.2136	0.6191	0.3904	0.1203
9.1037	10.0	190	8.7990	0.1660	0.4739	0.2271	0.8737	0.3063	0.2305	0.1452	0.3694	0.2085	0.6156	0.3694	0.1150

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