metadata
tags:
- finetuned
meta-llama/Llama-3.2-3B-Instruct-finetuned with Atomic
Model Description
This model was fine-tuned from meta-llama/Llama-3.2-3B-Instruct on carseng/titleix_explainer_reformat data using NOLA AI's Atomic system.
Training Data
- Dataset name: carseng/titleix_explainer_reformat
Training Arguments
- Batch size: 32
- Learning rate: 0.0001
- Used ATOMIC Speed: True
Final Metrics
- Training loss: 0.8799177351043664
- Training Runtime: 0:11:12