hate_speech_recognition_model_lvd

This model is a fine-tuned version of distilbert/distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3397
• Accuracy: {'accuracy': 0.8557281553398058}
• F1: {'f1': 0.72015065913371}
• Precision: {'precision': 0.750392464678179}
• Recall: {'recall': 0.6922519913106444}

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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.3451	1.0	10139	0.3402	{'accuracy': 0.8516782246879334}	{'f1': 0.7062894809118374}	{'precision': 0.7529866479269149}	{'recall': 0.6650460328954174}
0.2948	2.0	20278	0.3397	{'accuracy': 0.8557281553398058}	{'f1': 0.72015065913371}	{'precision': 0.750392464678179}	{'recall': 0.6922519913106444}

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1