Model Card for Tulu V2.5 13B RM - HH-RLHF 60k

Tulu is a series of language models that are trained to act as helpful assistants. Tulu V2.5 is a series of models trained using DPO and PPO starting from the Tulu 2 suite. This is a reward model used for PPO training trained on the HH-RLHF 60k dataset. It was used to train this model.

For more details, read the paper: Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback.

.Model description

• Model type: One model belonging to a suite of RLHF tuned chat models on a mix of publicly available, synthetic and human-created datasets.
• Language(s) (NLP): English
• License: Apache 2.0.
• Finetuned from model: meta-llama/Llama-2-13b-hf

Model Sources

• Repository: https://github.com/allenai/open-instruct
• Dataset: Data used to train this model can be found here - specifically the hh_rlhf_60k split.
• Model Family: The collection of related models can be found here.

Input Format

The model is trained to use the following format (note the newlines):

<|user|>
Your message here!
<|assistant|>

For best results, format all inputs in this manner. Make sure to include a newline after <|assistant|>, this can affect generation quality quite a bit. We have included a chat template in the tokenizer implementing this template.

Intended uses & limitations

The model was initially fine-tuned on a filtered and preprocessed of the Tulu V2 mix dataset, which contains a diverse range of human created instructions and synthetic dialogues generated primarily by other LLMs. We then further trained the model with a Jax RM trainer built on EasyLM on the dataset mentioned above. This model is meant as a research artefact.

Training hyperparameters

The following hyperparameters were used during PPO training:

• learning_rate: 1e-06
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear cooldown to 1e-05.
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1.0

Citation

If you find Tulu 2.5 is useful in your work, please cite it with:

@misc{ivison2024unpacking,
      title={{Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback}}, 
      author={{Hamish Ivison and Yizhong Wang and Jiacheng Liu and Ellen Wu and Valentina Pyatkin and Nathan Lambert and Yejin Choi and Noah A. Smith and Hannaneh Hajishirzi}}
      year={2024},
      eprint={2406.09279},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}