---
license: other
library_name: peft
tags:
- llama-factory
- lora
- trl
- dpo
- generated_from_trainer
base_model: google/gemma-7b-it
model-index:
- name: orpo
  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. -->

# orpo

This model is a fine-tuned version of [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) on the dpo_mix_en dataset.
It achieves the following results on the evaluation set:
- Loss: 4.4269
- Rewards/chosen: -0.4347
- Rewards/rejected: -0.4158
- Rewards/accuracies: 0.0
- Rewards/margins: -0.0190
- Logps/rejected: -4.1575
- Logps/chosen: -4.3475
- Logits/rejected: 198.3044
- Logits/chosen: 195.7259
- Sft Loss: 4.3475
- Odds Ratio Loss: 0.7941

## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 1.0

### Training results



### Framework versions

- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1