mdeberta-semeval25_narratives09_maxf1_fold2

g-assismoraes/mdeberta-semeval25_narratives09_maxf1_fold2

mdeberta-semeval25_narratives09_maxf1_fold2 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

2% of all-time downloads

All-time downloads

319

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: b23dbe73

Try a prompt

Base models

microsoft/mdeberta-v3-base

Model card

From the Hugging Face model README

mdeberta-semeval25_narratives09_maxf1_fold2

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: 4.2924
Precision Samples: 0.3835
Recall Samples: 0.7260
F1 Samples: 0.4634
Precision Macro: 0.7151
Recall Macro: 0.4542
F1 Macro: 0.2876
Precision Micro: 0.3288
Recall Micro: 0.6993
F1 Micro: 0.4473
Precision Weighted: 0.4996
Recall Weighted: 0.6993
F1 Weighted: 0.3945

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
5.4789	1.0	19	5.4032	1.0	0.0	0.0	1.0	0.0476	0.0476	1.0	0.0	0.0	1.0	0.0	0.0
5.2625	2.0	38	5.1900	0.2862	0.3454	0.2875	0.9023	0.1688	0.1126	0.2993	0.2971	0.2982	0.7626	0.2971	0.1551
4.6987	3.0	57	4.9994	0.3075	0.4170	0.3242	0.8697	0.2013	0.1334	0.3152	0.3768	0.3432	0.6836	0.3768	0.2102
4.5529	4.0	76	4.7748	0.3609	0.5142	0.3956	0.8025	0.2616	0.1706	0.3299	0.4601	0.3843	0.5944	0.4601	0.2532
4.2214	5.0	95	4.5893	0.3386	0.6308	0.4087	0.7724	0.3379	0.2022	0.3141	0.5725	0.4056	0.5535	0.5725	0.3059
4.0347	6.0	114	4.4605	0.3553	0.6856	0.4302	0.7133	0.3972	0.2396	0.3092	0.6486	0.4187	0.4927	0.6486	0.3504
4.0031	7.0	133	4.3696	0.3480	0.6976	0.4299	0.7169	0.4262	0.2524	0.3090	0.6739	0.4237	0.4939	0.6739	0.3596
3.8849	8.0	152	4.3297	0.3646	0.7105	0.4444	0.7205	0.4312	0.2570	0.3170	0.6812	0.4327	0.5006	0.6812	0.3678
3.8207	9.0	171	4.3091	0.3659	0.7131	0.4474	0.7203	0.4422	0.2781	0.3183	0.6884	0.4353	0.4987	0.6884	0.3819
4.3441	10.0	190	4.2924	0.3835	0.7260	0.4634	0.7151	0.4542	0.2876	0.3288	0.6993	0.4473	0.4996	0.6993	0.3945

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