---
tags:
- generated_from_trainer
model-index:
- name: out
  results: []
language:
- en
license: llama2
---

Hesperus-v1 - A trained 8-bit LoRA for RP & General Purposes.
<br>Trained on the base 13B Llama 2 model.

fp16 repo: https://huggingface.co/Sao10K/Hesperus-v1-13B-L2-fp16
<br>GGUF Quants: https://huggingface.co/Sao10K/Hesperus-v1-13B-L2-GGUF

Dataset Entry Rows:
<br>RP: 8.95K
<br>MED: 10.5K
<br>General: 8.7K
<br>Total: 28.15K

This is after heavy filtering of ~500K Rows and Entries from randomly selected scraped sites and datasets.

v1 is simply an experimental release. V2 will be the main product?
<br>Goals:
<br>--- Reduce 28.15K to <10K Entries. 
<br>--- Adjust RP / Med / General Ratios again.
<br>--- Fix Formatting, Markdown in Each Entry.
<br>--- Further Filter and Remove Low Quality entries ***again***, with a much harsher pass this time around.
<br>--- Do a spellcheck & fix for entries.
<br>--- Commit to one prompt format for dataset. Either ShareGPT or Alpaca. Not Both.

I recommend keeping Repetition Penalty below 1.1, preferably at 1 as Hesperus begins breaking down at 1.2 Rep Pen and might output nonsense outputs.

![Format](https://i.gyazo.com/b22ba269e509c8a62276cbd5bde5acef.png)

Prompt Format:
```
- sharegpt (recommended!)
User:
GPT: 
```
```
- alpaca (less recommended)
###Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
###Response:
```

V1 is trained on 50/50 for these two formats. 
<br>I am working on converting to either for v2.

Once V2 is Completed, I will also train a 70B variant of this.

EXAMPLE OUTPUTS:
![Alexandra](https://i.gyazo.com/a93a1a9d1a134f1f0d6163b54645cc20.png)
![LewdTV](https://i.gyazo.com/7016a1928d449c4fdff24f83a0707dcb.png)
![Beryl](https://i.gyazo.com/74e6c52f182e0934190ad5249df39534.png)

***

<!-- 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"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
# out

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5134

## 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
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5513        | 0.05  | 1    | 1.6200          |
| 1.5555        | 0.11  | 2    | 1.6200          |
| 1.5558        | 0.22  | 4    | 1.6180          |
| 1.5195        | 0.33  | 6    | 1.6109          |
| 1.5358        | 0.44  | 8    | 1.5929          |
| 1.5124        | 0.55  | 10   | 1.5740          |
| 1.4938        | 0.66  | 12   | 1.5591          |
| 1.4881        | 0.77  | 14   | 1.5495          |
| 1.4639        | 0.88  | 16   | 1.5427          |
| 1.4824        | 0.99  | 18   | 1.5373          |
| 1.4752        | 1.1   | 20   | 1.5318          |
| 1.4768        | 1.21  | 22   | 1.5278          |
| 1.4482        | 1.32  | 24   | 1.5236          |
| 1.4444        | 1.42  | 26   | 1.5209          |
| 1.4381        | 1.53  | 28   | 1.5192          |
| 1.4415        | 1.64  | 30   | 1.5166          |
| 1.4412        | 1.75  | 32   | 1.5150          |
| 1.4263        | 1.86  | 34   | 1.5146          |
| 1.4608        | 1.97  | 36   | 1.5134          |


### Framework versions

- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1