---
license: other
base_model: Qwen/Qwen1.5-0.5B-Chat
tags:
- trl
- orpo
- generated_from_trainer
model-index:
- name: Qwen-Orpo-v1
  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. -->

# Qwen-Orpo-v1

This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8005
- Rewards/chosen: -0.1607
- Rewards/rejected: -0.2097
- Rewards/accuracies: 0.8936
- Rewards/margins: 0.0490
- Logps/rejected: -2.0968
- Logps/chosen: -1.6067
- Logits/rejected: -1.4714
- Logits/chosen: -1.5480
- Nll Loss: 1.7529
- Log Odds Ratio: -0.4757
- Log Odds Chosen: 0.5760

## 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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
| 1.9413        | 0.5001 | 1744 | 1.8005          | -0.1607        | -0.2097          | 0.8936             | 0.0490          | -2.0968        | -1.6067      | -1.4714         | -1.5480       | 1.7529   | -0.4757        | 0.5760          |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1