---
base_model: Llama-Mamba-3.1-8B-teacher-Llama-3.1-70B-Instruct-kl1.0-ce0.0
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
- HuggingFaceH4/orca_dpo_pairs
- JunxiongWang/llama3-ultrafeedback-armorm
model-index:
- name: Llama-Mamba-3.1-8B-teacher-Llama-3.1-70B-Instruct-kl1.0-ce0.0-dpo-short
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/osieosie/huggingface/runs/va8s5gk4)
# Llama-Mamba-3.1-8B-teacher-Llama-3.1-70B-Instruct-kl1.0-ce0.0-dpo-short

This model is a fine-tuned version of [Llama-Mamba-3.1-8B-teacher-Llama-3.1-70B-Instruct-kl1.0-ce0.0](https://huggingface.co/Llama-Mamba-3.1-8B-teacher-Llama-3.1-70B-Instruct-kl1.0-ce0.0) on the HuggingFaceH4/ultrafeedback_binarized, the HuggingFaceH4/orca_dpo_pairs and the JunxiongWang/llama3-ultrafeedback-armorm datasets.

## 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: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 32
- total_eval_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: 1

### Training results



### Framework versions

- Transformers 4.43.1
- Pytorch 2.1.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1