ROBerta-distortion-fold-4-v3

Kudod/ROBerta-distortion-fold-4-v3

ROBerta-distortion-fold-4-v3 is a text classification model from Kudod. 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

560M

15.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.2 GB · 99%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: xlm-roberta
Access: Public
Created: Jan 21, 2026
Updated: Jan 21, 2026
SHA: 6c79ad16

Try a prompt

Base models

FacebookAI/xlm-roberta-large

Model card

From the Hugging Face model README

ROBerta-distortion-fold-4-v3

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.9090
Accuracy: 0.4201
Precision Macro: 0.4228
Recall Macro: 0.4203
F1 Macro: 0.4176
Precision Weighted: 0.4302
Recall Weighted: 0.4201
F1 Weighted: 0.4206

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: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Macro	Recall Macro	F1 Macro	Precision Weighted	Recall Weighted	F1 Weighted
2.3155	1.0	60	2.2644	0.1505	0.0151	0.1	0.0263	0.0228	0.1505	0.0396
2.2698	2.0	120	2.2487	0.2132	0.0447	0.1417	0.0674	0.0673	0.2132	0.1014
2.2482	3.0	180	1.9317	0.3009	0.1920	0.2275	0.1810	0.2242	0.3009	0.2276
1.9519	4.0	240	1.8661	0.3574	0.3011	0.2997	0.2688	0.3441	0.3574	0.3094
1.3719	5.0	300	1.8582	0.3856	0.4047	0.3377	0.3172	0.4271	0.3856	0.3585
1.0288	6.0	360	1.8333	0.4013	0.4178	0.3902	0.3798	0.4476	0.4013	0.4053
0.7487	7.0	420	1.9662	0.4169	0.4289	0.4045	0.4052	0.4390	0.4169	0.4175
0.4954	8.0	480	2.1659	0.4169	0.4712	0.4161	0.4184	0.4829	0.4169	0.4251
0.3224	9.0	540	2.5581	0.3918	0.4488	0.4019	0.3846	0.4689	0.3918	0.3909
0.1312	10.0	600	2.6168	0.4107	0.4359	0.4076	0.4091	0.4463	0.4107	0.4151
0.0738	11.0	660	2.9090	0.4201	0.4228	0.4203	0.4176	0.4302	0.4201	0.4206

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.2

Task: Text Classification
Library: transformers
Type: xlm-roberta
License: mit
Created: Jan 21, 2026
Updated: Jan 21, 2026