--- base_model: meta-llama/Llama-3.2-1B-Instruct library_name: peft license: other tags: - lora - generated_from_trainer model-index: - name: sft_241015_1600_1 results: [] --- # sft_241015_1600_1 This model is a fine-tuned version of [/media/enssel/DataDisk/Models/Llama-3.2-3B-Instruct](https://huggingface.co//media/enssel/DataDisk/Models/Llama-3.2-3B-Instruct) on the app_logs_modified_1 and the NIST_SP_800_53 datasets. It achieves the following results on the evaluation set: - Loss: 1.8549 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data Application_logs and NIST_SP_800_53 datasets ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 1 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 8 - total_train_batch_size: 256 - total_eval_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10.0 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 1.9548 | 8.6957 | 50 | 1.8549 | ### Framework versions - PEFT 0.12.0 - Transformers 4.43.3 - Pytorch 2.4.0+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1