---
license: other
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: Qwen2/Qwen2-7B-Instruct
model-index:
- name: dpo_06221544_policy2
  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_06221544_policy2

This model is a fine-tuned version of [/root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-sft-06221544-iter1-policy2](https://huggingface.co//root/LLM_Data_Engineer/LLaMA-Factory/models/Qwen2-7B-Instruct-sft-06221544-iter1-policy2) on the dpo_data_5370_0621 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0678
- Rewards/chosen: 0.9462
- Rewards/rejected: -3.0599
- Rewards/accuracies: 0.9778
- Rewards/margins: 4.0060
- Logps/rejected: -203.4532
- Logps/chosen: -274.8549
- Logits/rejected: -1.4117
- Logits/chosen: -0.2185

## 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: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0

### Training results



### Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1