ricecake/Orca-2-13B-Pygmalion-LoRA

++ This model's response was too short, so I re-trained it, check this out: https://huggingface.co/ricecake/Orca-2-13B-Pyg-and-Bluemoon

<!-- 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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Orca-2-13B-Pygmalion-LoRA

This LoRA adapter is a fine-tuned version of microsoft/Orca-2-13b on the PygmalionAI/PIPPA dataset. It achieves the following results on the evaluation set:

• —Loss: 1.9190

Model description

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 0.0002
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 2
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 10
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.35.1
• —Pytorch 2.1.0+cu121
• —Datasets 2.14.7
• —Tokenizers 0.14.1