--- base_model: meta-llama/Meta-Llama-3.1-8B-Instruct datasets: - barc0/induction_gpt-4_description_20000_with_gpt-4o-mini_codegen_messages_format_0.3 library_name: peft license: llama3.1 tags: - alignment-handbook - trl - sft - generated_from_trainer model-index: - name: barc-llama3.1-8b-instruct-lora64-induction-gpt4-desc-4omini20k_lr2e-4_epoch3 results: [] --- # barc-llama3.1-8b-instruct-lora64-induction-gpt4-desc-4omini20k_lr2e-4_epoch3 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/induction_gpt-4_description_20000_with_gpt-4o-mini_codegen_messages_format_0.3 dataset. It achieves the following results on the evaluation set: - Loss: 0.2928 ## 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: 0.0002 - train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 2 - total_train_batch_size: 128 - total_eval_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 0.3214 | 0.9966 | 145 | 0.3190 | | 0.2761 | 2.0 | 291 | 0.2950 | | 0.2592 | 2.9897 | 435 | 0.2928 | ### Framework versions - PEFT 0.13.0 - Transformers 4.45.0.dev0 - Pytorch 2.4.1+cu121 - Datasets 3.0.0 - Tokenizers 0.19.1