bge-small-en-v1.5-prompt-screener

This model was trained to test English prompts and single-turn English conversations using the fine-grained data in the agentlans/prompt-screening-dataset

• Input format: <|user|>prompt<|assistant|>reply. For very long messages, use the special token <|...|>.
• Output: whether the prompt and answer meet minimal safety, quality, and refusal criteria.

This model is a fine-tuned version of BAAI/bge-small-en-v1.5. It achieves the following results on the evaluation set:

• Loss: 0.2614
• Accuracy: 0.9052
• Num Input Tokens Seen: 92144640

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-05
• train_batch_size: 8
• eval_batch_size: 8
• 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: 5.0

Training results

Framework versions

• Transformers 5.0.0.dev0
• Pytorch 2.9.1+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1