QA-DeBERTa-v3-large-binary-2

<!-- 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. -->

QA-DeBERTa-v3-large-binary-2

This model is a fine-tuned version of microsoft/deberta-v3-large on the saiteki-kai/Beavertails-it dataset. It achieves the following results on the evaluation set:

• Loss: 0.3122
• Accuracy: 0.8623
• Unsafe Precision: 0.8712
• Unsafe Recall: 0.8831
• Unsafe F1: 0.8771
• Unsafe Fpr: 0.1638
• Unsafe Aucpr: 0.9560
• Safe Precision: 0.8508
• Safe Recall: 0.8362
• Safe F1: 0.8435
• Safe Fpr: 0.1169
• Safe Aucpr: 0.9221

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: 5e-06
• train_batch_size: 64
• eval_batch_size: 128
• 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
• lr_scheduler_warmup_steps: 1000
• num_epochs: 10

Training results

Framework versions

• Transformers 4.57.1
• Pytorch 2.7.1+cu118
• Datasets 4.4.1
• Tokenizers 0.22.1