---
base_model: mamba_0_75_dpo_ep1
tags:
- mamba
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: mamba_0_75_dpo_ep1
  results: []
---

Please check [here](https://github.com/jxiw/MambaInLlama/tree/main) for details.

<!-- 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. -->

# mamba_0_75_dpo_ep1

This model is a fine-tuned version of [JunxiongWang/mamba_0_75_sft](https://huggingface.co/JunxiongWang/mamba_0_75_sft) on the HuggingFaceH4/ultrafeedback_binarized dataset.

## 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-07
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 32
- total_eval_batch_size: 64
- 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

### Training results



### Framework versions

- Transformers 4.41.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1


[MambaInLlama](arxiv.org/abs/2408.15237)

```
@article{junxiongdaniele2024mambainllama,
  title   = {The Mamba in the Llama: Distilling and Accelerating Hybrid Models},
  author  = {Junxiong Wang and Daniele Paliotta and Avner May and Alexander M. Rush and Tri Dao},
  journal = {arXiv preprint arXiv:2408.15237},
  year    = {2024}
}
```