xlm-roberta-mushroom-qa

This model was fine-tuned to tackle SemEval 2025 Task3: Mu-SHROOM. Its task is to extract hallucination spans from large language model output.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Fine-tuning hyperparameters

The following hyperparameters were used during fine-tuning:

• learning_rate: 5e-02
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 4.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0