---
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: Meta-Llama-3-8B-Instruct
model-index:
- name: dpo
  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

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6736
- Rewards/chosen: 0.5769
- Rewards/rejected: 0.5039
- Rewards/accuracies: 0.6000
- Rewards/margins: 0.0730
- Logps/rejected: -171.1358
- Logps/chosen: -181.4562
- Logits/rejected: -0.0987
- Logits/chosen: -0.0683

## 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-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 0
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 250

### Training results



### Framework versions

- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1