LimaRP-UtopiaXL-13B-v3-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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

UtopiaXL-LimaRP

This lora was trained from the LimaRP dataset Version 2023-10-19 (2003 samples) on the UtopiaXL-13B model I cooked (before applying it obviously).

It achieves the following results on the evaluation set:

• Loss: 1.7890

Intended uses & limitations

This LoRA was created to be used on my own model, but since it's done, I share it.

Should work on any Llama2-13B model, but I can't tell you if the result will be good.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.00065
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 10
• num_epochs: 2

Training results

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.6
• Tokenizers 0.14.1

If you want to support me, you can here.