---
base_model: meta-llama/Meta-Llama-3-8B-Instruct
library_name: peft
license: llama3
tags:
- trl
- kto
- generated_from_trainer
model-index:
- name: kto-aligned-model-lora
  results: []
---

<!-- 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/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pauld/huggingface/runs/y7di7l44)
# kto-aligned-model-lora

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4990
- Eval/rewards/chosen: 0.1561
- Eval/logps/chosen: -0.6624
- Eval/rewards/rejected: 0.1281
- Eval/logps/rejected: -1.9415
- Eval/rewards/margins: 0.0281
- Eval/kl: 1.5643

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |        |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.4994        | 0.9057 | 8    | 0.4997          | 0.8856 |
| 0.5           | 1.9245 | 17   | 0.4994          | 1.5546 |
| 0.501         | 2.9434 | 26   | 0.4992          | 1.5634 |
| 0.5004        | 3.9623 | 35   | 0.4991          | 1.5675 |
| 0.4999        | 4.5283 | 40   | 0.4990          | 1.5643 |


### Framework versions

- PEFT 0.11.1
- Transformers 4.42.2
- Pytorch 2.2.0
- Datasets 2.20.0
- Tokenizers 0.19.1