mothy-08/deberta-v3-xsmall-finetuned-content-moderator

deberta-v3-xsmall-finetuned-content-moderator

This model is a fine-tuned version of microsoft/deberta-v3-xsmall on the google/civil_comments and ucberkeley-dlab/measuring-hate-speech dataset.

It achieves the following results on the evaluation set:

• —Loss: 0.2450
• —Accuracy: 0.9086
• —F1: 0.9124
• —Precision: 0.8757
• —Recall: 0.9523

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: 32
• —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
• —num_epochs: 3
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.57.1
• —Pytorch 2.9.0+cu126
• —Datasets 4.0.0
• —Tokenizers 0.22.1