deberta-semeval25_justEN08_fold1

g-assismoraes/deberta-semeval25_justEN08_fold1

deberta-semeval25_justEN08_fold1 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

17% of all-time downloads

All-time downloads

Public

Parameters

184M

1.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors738 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: deberta-v2
Access: Public
Created: Oct 28, 2024
Updated: Oct 28, 2024
SHA: 581f885e

Try a prompt

Base models

microsoft/deberta-v3-base

Model card

From the Hugging Face model README

deberta-semeval25_justEN08_fold1

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

Loss: 5.7535
Precision Samples: 0.2667
Recall Samples: 0.5854
F1 Samples: 0.3465
Precision Macro: 0.9672
Recall Macro: 0.6
F1 Macro: 0.5719
Precision Micro: 0.2455
Recall Micro: 0.4030
F1 Micro: 0.3051
Precision Weighted: 0.7571
Recall Weighted: 0.4030
F1 Weighted: 0.2186

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
No log	1.0	5	6.8903	1.0	0.0	0.0	1.0	0.5571	0.5571	1.0	0.0	0.0	1.0	0.0	0.0
8.918	2.0	10	6.5025	0.5	0.475	0.475	0.9927	0.5707	0.5663	0.4872	0.2836	0.3585	0.8469	0.2836	0.1923
8.918	3.0	15	6.2307	0.5	0.5	0.5	0.9929	0.5714	0.5667	0.5	0.2985	0.3738	0.8507	0.2985	0.1990
8.3797	4.0	20	6.0425	0.5	0.5	0.5	0.9929	0.5714	0.5667	0.5	0.2985	0.3738	0.8507	0.2985	0.1990
8.3797	5.0	25	5.9342	0.3458	0.55	0.4113	0.9703	0.5893	0.5730	0.3077	0.3582	0.3310	0.7700	0.3582	0.2231
8.125	6.0	30	5.8713	0.3083	0.5542	0.3794	0.9676	0.5929	0.5721	0.2747	0.3731	0.3165	0.7590	0.3731	0.2196
8.125	7.0	35	5.8266	0.2875	0.5854	0.3687	0.9676	0.6	0.5725	0.2571	0.4030	0.3140	0.7589	0.4030	0.2213
7.9905	8.0	40	5.7884	0.2583	0.5854	0.3412	0.9671	0.6	0.5717	0.2389	0.4030	0.3	0.7567	0.4030	0.2180
7.9905	9.0	45	5.7639	0.2625	0.5854	0.3453	0.9671	0.6	0.5718	0.2432	0.4030	0.3034	0.7570	0.4030	0.2185
7.8886	10.0	50	5.7535	0.2667	0.5854	0.3465	0.9672	0.6	0.5719	0.2455	0.4030	0.3051	0.7571	0.4030	0.2186

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 28, 2024
Updated: Oct 28, 2024