deberta-large-semeval25_EN08_fold3

g-assismoraes/deberta-large-semeval25_EN08_fold3

deberta-large-semeval25_EN08_fold3 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

13% of all-time downloads

All-time downloads

Public

Parameters

435M

15.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.7 GB · 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: a8d10771

Try a prompt

Base models

microsoft/deberta-v3-large

Model card

From the Hugging Face model README

deberta-large-semeval25_EN08_fold3

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

Loss: 8.2442
Precision Samples: 0.1144
Recall Samples: 0.7997
F1 Samples: 0.1930
Precision Macro: 0.3896
Recall Macro: 0.6167
F1 Macro: 0.2236
Precision Micro: 0.1104
Recall Micro: 0.7507
F1 Micro: 0.1924
Precision Weighted: 0.2237
Recall Weighted: 0.7507
F1 Weighted: 0.2130

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: 8
eval_batch_size: 8
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
8.2513	1.0	73	9.8237	0.1093	0.4542	0.1631	0.8860	0.2559	0.1808	0.1110	0.3399	0.1674	0.6512	0.3399	0.0922
6.8883	2.0	146	9.3725	0.1082	0.6445	0.1710	0.7810	0.3726	0.1997	0.0995	0.5637	0.1692	0.4732	0.5637	0.1274
8.4363	3.0	219	8.8450	0.1195	0.7090	0.1933	0.6684	0.4525	0.2167	0.1073	0.6374	0.1837	0.3811	0.6374	0.1603
8.6787	4.0	292	8.5427	0.1068	0.7465	0.1790	0.5303	0.5162	0.1950	0.0967	0.6941	0.1697	0.2823	0.6941	0.1599
6.8889	5.0	365	8.5407	0.1100	0.7823	0.1854	0.4867	0.5780	0.2249	0.1022	0.7337	0.1794	0.2365	0.7337	0.1842
7.9121	6.0	438	8.4019	0.1096	0.7957	0.1858	0.4441	0.5804	0.2166	0.1041	0.7365	0.1825	0.2387	0.7365	0.1936
7.1827	7.0	511	8.3315	0.1085	0.8046	0.1846	0.4158	0.6204	0.2251	0.1042	0.7507	0.1831	0.2210	0.7507	0.2018
5.9674	8.0	584	8.1923	0.1100	0.8047	0.1857	0.3929	0.6172	0.2292	0.1046	0.7620	0.1839	0.2236	0.7620	0.2136
6.397	9.0	657	8.2536	0.1113	0.8023	0.1884	0.3999	0.6139	0.2328	0.1077	0.7507	0.1883	0.2269	0.7507	0.2148
6.4848	10.0	730	8.2442	0.1144	0.7997	0.1930	0.3896	0.6167	0.2236	0.1104	0.7507	0.1924	0.2237	0.7507	0.2130

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