lschimmelpfe/Llama-3-8B_civic_discussion_qlora

<!-- 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. -->

Llama-3-8Bcivicdiscussion_qlora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 1.9642
• —Model Preparation Time: 0.0063
• —Rouge1: 64.1464
• —Rouge2: 24.9084
• —Rougel: 45.772
• —Rougelsum: 62.0758

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
• —trainbatchsize: 2
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 3

Training results

Framework versions

• —PEFT 0.12.0
• —Transformers 4.45.2
• —Pytorch 2.5.0+cu124
• —Datasets 3.0.2
• —Tokenizers 0.20.1