deberta-semeval25_noHINDI08_fold2

g-assismoraes/deberta-semeval25_noHINDI08_fold2

deberta-semeval25_noHINDI08_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

10% of all-time downloads

All-time downloads

Public

Parameters

184M

3 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: 9dcefe98

Try a prompt

Base models

microsoft/deberta-v3-base

Model card

From the Hugging Face model README

deberta-semeval25_noHINDI08_fold2

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: 8.8517
Precision Samples: 0.1527
Recall Samples: 0.5474
F1 Samples: 0.2243
Precision Macro: 0.7907
Recall Macro: 0.3516
F1 Macro: 0.2296
Precision Micro: 0.1381
Recall Micro: 0.4690
F1 Micro: 0.2133
Precision Weighted: 0.5289
Recall Weighted: 0.4690
F1 Weighted: 0.1485

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
10.5058	1.0	16	10.2942	1.0	0.0	0.0	1.0	0.1818	0.1818	1.0	0.0	0.0	1.0	0.0	0.0
9.4489	2.0	32	9.9428	0.1940	0.2988	0.2165	0.9662	0.2242	0.1978	0.1906	0.1966	0.1935	0.8457	0.1966	0.0763
10.0907	3.0	48	9.6744	0.1541	0.3731	0.2047	0.9300	0.2477	0.1983	0.1491	0.2690	0.1919	0.7249	0.2690	0.0775
9.248	4.0	64	9.4563	0.1541	0.4441	0.2153	0.9010	0.2716	0.2064	0.1481	0.3345	0.2053	0.6702	0.3345	0.1007
9.019	5.0	80	9.2882	0.1564	0.4842	0.2207	0.8711	0.2977	0.2181	0.1491	0.3897	0.2156	0.6126	0.3897	0.1272
8.712	6.0	96	9.1284	0.1652	0.5359	0.2355	0.8646	0.3226	0.2216	0.1511	0.4414	0.2252	0.5993	0.4414	0.1369
8.2497	7.0	112	8.9849	0.1629	0.5686	0.2357	0.8226	0.3406	0.2263	0.1453	0.4759	0.2226	0.5563	0.4759	0.1450
8.2378	8.0	128	8.9047	0.1556	0.5406	0.2275	0.8014	0.3457	0.2283	0.1424	0.4690	0.2185	0.5376	0.4690	0.1466
8.6465	9.0	144	8.8786	0.1525	0.5406	0.2237	0.7903	0.3478	0.2290	0.1391	0.4690	0.2145	0.5282	0.4690	0.1479
8.7721	10.0	160	8.8517	0.1527	0.5474	0.2243	0.7907	0.3516	0.2296	0.1381	0.4690	0.2133	0.5289	0.4690	0.1485

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