laaj_5k_3epochs_all

This model is a fine-tuned version of meta-llama/Llama-Guard-3-8B on the laaj_5k_allbatch dataset.

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: 0.0001
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 3.0

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.45.2
• Pytorch 2.5.0
• Datasets 3.0.1
• Tokenizers 0.20.1