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

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

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
• —trainbatchsize: 32
• —evalbatchsize: 64
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.2
• —num_epochs: 6

Training results

Framework versions

• —Transformers 4.57.1
• —Pytorch 2.8.0+cu126
• —Datasets 4.4.2
• —Tokenizers 0.22.1