---
base_model: meta-llama/Meta-Llama-3.1-8B
library_name: peft
license: llama3.1
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: dpo-llama3-8b-grammar-rules
  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. -->

# dpo-llama3-8b-grammar-rules

This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1500
- Rewards/chosen: -0.7612
- Rewards/rejected: -2.8814
- Rewards/accuracies: 1.0
- Rewards/margins: 2.1202
- Logps/rejected: -647.7891
- Logps/chosen: -291.9149
- Logits/rejected: -1.1894
- Logits/chosen: -1.1810

## 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: 5e-06
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.388         | 0.4444 | 50   | 0.3531          | -0.2310        | -1.1328          | 1.0                | 0.9018          | -472.9276      | -238.8918    | -1.2924         | -1.2917       |
| 0.1309        | 0.8889 | 100  | 0.1500          | -0.7612        | -2.8814          | 1.0                | 2.1202          | -647.7891      | -291.9149    | -1.1894         | -1.1810       |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1