---
license: cc-by-nc-4.0
base_model: athirdpath/Harmonia-20B
tags:
- generated_from_trainer
model-index:
- name: lora
  results: []
---

[<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)
# lora

This model is a fine-tuned version of [athirdpath/Harmonia-20B](https://huggingface.co/athirdpath/Harmonia-20B) on the same dataset as Eileithyia-13b.
It achieves the following results on the evaluation set:
- Loss: 1.6941

## 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: 8e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.0833        | 1.41  | 10   | 1.9357          |
| 1.8053        | 2.81  | 20   | 1.7229          |
| 1.7493        | 4.15  | 30   | 1.6941          |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0