mdeberta-semeval25_thresh05_fold1

g-assismoraes/mdeberta-semeval25_thresh05_fold1

mdeberta-semeval25_thresh05_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

15% 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: 567e3ce6

Try a prompt

Base models

microsoft/mdeberta-v3-base

Model card

From the Hugging Face model README

mdeberta-semeval25_thresh05_fold1

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: 8.3426
Precision Samples: 0.0847
Recall Samples: 0.6765
F1 Samples: 0.1429
Precision Macro: 0.6975
Recall Macro: 0.4876
F1 Macro: 0.2607
Precision Micro: 0.0834
Recall Micro: 0.6327
F1 Micro: 0.1474
Precision Weighted: 0.4030
Recall Weighted: 0.6327
F1 Weighted: 0.1331

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
10.7546	1.0	19	9.5932	0.1128	0.3025	0.1528	0.9525	0.2692	0.2334	0.1107	0.2006	0.1427	0.8087	0.2006	0.0589
10.2899	2.0	38	9.2634	0.0827	0.4297	0.1304	0.8750	0.3222	0.2372	0.0827	0.3364	0.1328	0.6341	0.3364	0.0675
9.7416	3.0	57	9.0902	0.0707	0.5288	0.1185	0.8338	0.3889	0.2434	0.0704	0.4506	0.1217	0.5824	0.4506	0.0806
10.0751	4.0	76	8.9610	0.0702	0.5700	0.1195	0.8020	0.4042	0.2462	0.0709	0.5	0.1241	0.5009	0.5	0.0894
9.6663	5.0	95	8.7696	0.0704	0.6170	0.1212	0.7620	0.4396	0.2425	0.0725	0.5648	0.1285	0.4550	0.5648	0.1053
9.575	6.0	114	8.6391	0.0767	0.6493	0.1308	0.7593	0.4571	0.2634	0.0777	0.5988	0.1375	0.4346	0.5988	0.1221
9.1185	7.0	133	8.4813	0.0807	0.6714	0.1365	0.7286	0.4721	0.2551	0.0810	0.6265	0.1435	0.4204	0.6265	0.1275
9.2126	8.0	152	8.4100	0.0846	0.6765	0.1423	0.7116	0.4876	0.2620	0.0831	0.6327	0.1468	0.4082	0.6327	0.1329
9.104	9.0	171	8.3677	0.0838	0.6834	0.1414	0.7006	0.4987	0.2623	0.0827	0.6358	0.1464	0.3923	0.6358	0.1322
8.8092	10.0	190	8.3426	0.0847	0.6765	0.1429	0.6975	0.4876	0.2607	0.0834	0.6327	0.1474	0.4030	0.6327	0.1331

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