mawiie/llama31-8b-sft-nigeria-wvs-lora

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Llama-3.1-8B-Instruct Fine-tuned

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct using LoRA adapters on a custom instruction-following dataset. It achieves the following results on the evaluation set:

• —Loss: 0.8017
• —Memory/max Mem Active(gib): 30.13
• —Memory/max Mem Allocated(gib): 30.13
• —Memory/device Mem Reserved(gib): 38.36

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
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —optimizer: Use adamwtorchfused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 6
• —training_steps: 139

Training results

Framework versions

• —PEFT 0.17.0
• —Transformers 4.55.2
• —Pytorch 2.6.0+cu124
• —Datasets 4.0.0
• —Tokenizers 0.21.4