xlm-roberta-multi-label-uk-toxic-comments-v14

viathorr/xlm-roberta-multi-label-uk-toxic-comments-v14

xlm-roberta-multi-label-uk-toxic-comments-v14 is a text classification model from viathorr. 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

0% of all-time downloads

All-time downloads

246

Public

Parameters

278M

6.7 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: xlm-roberta
Access: Public
Created: Apr 24, 2026
Updated: Apr 24, 2026
SHA: c2f3e5c3

Try a prompt

Base models

FacebookAI/xlm-roberta-base

Model card

From the Hugging Face model README

xlm-roberta-multi-label-uk-toxic-comments-v14

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2277
Macro F1: 0.7638
Micro F1: 0.7964
Macro Precision: 0.7629
Macro Recall: 0.7655
Macro Auc: 0.9469
Subset Accuracy: 0.6524
Toxic F1: 0.8549
Severe Toxic F1: 0.6305
Obscene F1: 0.8174
Threat F1: 0.8369
Insult F1: 0.7481
Identity Hate F1: 0.6948

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: 64
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: 0.2
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Macro F1	Micro F1	Macro Precision	Macro Recall	Macro Auc	Subset Accuracy	Toxic F1	Severe Toxic F1	Obscene F1	Threat F1	Insult F1	Identity Hate F1
0.3138	1.0	1043	0.2655	0.7096	0.7524	0.6932	0.7353	0.9240	0.5652	0.8278	0.5906	0.7648	0.7249	0.7066	0.6428
0.2384	2.0	2086	0.2217	0.7476	0.7839	0.7563	0.7463	0.9443	0.6325	0.8470	0.6136	0.7983	0.7915	0.7510	0.6843
0.2063	3.0	3129	0.2130	0.7542	0.7942	0.7626	0.7471	0.9476	0.6415	0.8577	0.5887	0.8123	0.8320	0.7447	0.6901
0.1791	4.0	4172	0.2201	0.7482	0.7953	0.7474	0.7562	0.9489	0.6443	0.8563	0.5538	0.8268	0.8103	0.7579	0.6843
0.1559	5.0	5215	0.2206	0.7653	0.7988	0.7715	0.7601	0.9476	0.6593	0.8585	0.6355	0.8138	0.8311	0.7532	0.6996
0.1394	6.0	6258	0.2277	0.7638	0.7964	0.7629	0.7655	0.9469	0.6524	0.8549	0.6305	0.8174	0.8369	0.7481	0.6948

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu126
Datasets 4.4.2
Tokenizers 0.22.1

Task: Text Classification
Library: transformers
Type: xlm-roberta
License: mit
Created: Apr 24, 2026
Updated: Apr 24, 2026