Update README.md

README.md

@@ -1,40 +1,68 @@
----
-base_model: Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1
-tags:
-- alignment-handbook
-- trl
-- dpo
-- generated_from_trainer
-datasets:
-- princeton-nlp/llama3-ultrafeedback-armorm
-model-index:
-- name: Llama-3.1-8B-Magpie-Align-v0.1
-  results: []
----
+---
+base_model: Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1
+tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- princeton-nlp/llama3-ultrafeedback-armorm
+model-index:
+- name: Llama-3.1-8B-Magpie-Align-v0.1
+  results: []
+license: llama3.1
+language:
+- en
+---
+
+![Magpie](https://cdn-uploads.huggingface.co/production/uploads/653df1323479e9ebbe3eb6cc/FWWILXrAGNwWr52aghV0S.png)
+## 🔥 Chat with Magpie [Here](https://huggingface.co/spaces/flydust/Chat-with-Magpie)!
+
+# 🐦 Llama-3.1-8B-Magpie-Align-v0.1
+
+Project Web: [https://magpie-align.github.io/](https://magpie-align.github.io/)
+
+Online Model Demo: [https://huggingface.co/spaces/flydust/Chat-with-Magpie](https://huggingface.co/spaces/flydust/Chat-with-Magpie)
+
+Arxiv Technical Report: [https://arxiv.org/abs/2406.08464](https://arxiv.org/abs/2406.08464)
+
+Codes: [https://github.com/magpie-align/magpie](https://github.com/magpie-align/magpie)
+
+## 🧐 About This Model
 
-This model is a fine-tuned version of [Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1) on the princeton-nlp/llama3-ultrafeedback-armorm dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3290
-- Rewards/chosen: -4.8185
-- Rewards/rejected: -6.6901
-- Rewards/accuracies: 0.8952
-- Rewards/margins: 1.8716
-- Logps/rejected: -867.8638
-- Logps/chosen: -686.8736
-- Logits/rejected: -0.5907
-- Logits/chosen: -0.5749
+This model is an aligned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B). We apply the following pipeline:
 
-## Model description
+We first perform SFT using:
+* [Magpie-Align/Magpie-Pro-MT-300K-v0.1](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-MT-300K-v0.1), and
+* [Magpie-Align/Magpie-Reasoning-150K](https://huggingface.co/datasets/Magpie-Align/Magpie-Reasoning-150K)
+* **SFT Model Checkpoint:** [Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1)
 
-More details will be added soon. 
+We then perform DPO on the [princeton-nlp/llama3-ultrafeedback-armorm](https://huggingface.co/datasets/princeton-nlp/llama3-ultrafeedback-armorm) dataset.
 
-## Benchmark
+The overall performance is much better than the official Llama-3.1-8B-Instruct Model! 
 
 - **MT-Bench: 8.375 (1st Turn), 7.650 (Second Turn), 8.013 (Average)**
 - **Alpaca Eval 2 (GPT-4-Turbo-1106): 45.73 (LC), 52.79 (WR)**
 - **Arena Hard: 42.4**
 
-## Training procedure
+## 👀 Other Information
+
+**License**: Please follow [Meta Llama 3 Community License](https://llama.meta.com/llama3/license) (Data) and [Meta Llama 3.1 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE) (Model).
+
+**Conversation Template**: Please use Llama 3 **official chat template** for the best performance.
+
+**How to use it?** Please check the official [Llama 3.1 repository](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct#how-to-use) for detailed instructions. Simply replace the original `model_id` with this model id.
+
+---
+# Alignment Pipeline
+
+The detailed alignment pipeline is as follows.
+
+## Stage 1: Supervised Fine-tuning
+
+We use [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) for SFT. Please refer to the model card of [SFT checkpoint](https://huggingface.co/Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1) for detailed configurations.
+
+## Stage 2: Direct Preference Optimization
 
 ### Training hyperparameters
 
@@ -67,3 +95,109 @@ The following hyperparameters were used during training:
 - Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1
+
+<details><summary>See alignment handbook config</summary>
+
+```yaml
+# Customized Configs
+model_name_or_path: Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1
+hub_model_id: Magpie-Align/Llama-3.1-8B-Magpie-Align-v0.1
+output_dir: /data/zhangchen_xu/alignment_handbook_out/Llama-3.1-8B-Magpie-Align-v0.1
+run_name: Llama-3.1-8B-Magpie-Align-v0.1
+
+dataset_mixer:
+  princeton-nlp/llama3-ultrafeedback-armorm: 1.0
+dataset_splits:
+- train
+- test
+preprocessing_num_workers: 64
+
+# DPOTrainer arguments
+bf16: true
+beta: 0.01
+learning_rate: 1.0e-6
+gradient_accumulation_steps: 16
+per_device_train_batch_size: 2
+per_device_eval_batch_size: 4
+num_train_epochs: 1
+max_length: 2048
+max_prompt_length: 1800
+warmup_ratio: 0.1
+logging_steps: 1
+lr_scheduler_type: cosine
+optim: adamw_torch
+
+torch_dtype: null
+use_flash_attention_2: true
+do_eval: true
+evaluation_strategy: steps
+eval_steps: 100
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: False
+log_level: info
+push_to_hub: true
+save_strategy: "steps"
+save_steps: 100
+save_total_limit: 1
+seed: 42
+report_to:
+- wandb
+```
+</details><be>
+
+---
+
+## Paper Abstract
+
+<details><summary>Click Here</summary>
+High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain private, which hinders the democratization of AI. High human labor costs and a limited, predefined scope for prompting prevent existing open-source data creation methods from scaling effectively, potentially limiting the diversity and quality of public alignment datasets. Is it possible to synthesize high-quality instruction data at scale by extracting it directly from an aligned LLM? We present a self-synthesis method for generating large-scale alignment data named Magpie. Our key observation is that aligned LLMs like Llama-3-Instruct can generate a user query when we input only the left-side templates up to the position reserved for user messages, thanks to their auto-regressive nature. We use this method to prompt Llama-3-Instruct and generate 4 million instructions along with their corresponding responses. We perform a comprehensive analysis of the extracted data and select 300K high-quality instances. To compare Magpie data with other public instruction datasets, we fine-tune Llama-3-8B-Base with each dataset and evaluate the performance of the fine-tuned models. Our results indicate that in some tasks, models fine-tuned with Magpie perform comparably to the official Llama-3-8B-Instruct, despite the latter being enhanced with 10 million data points through supervised fine-tuning (SFT) and subsequent feedback learning. We also show that using Magpie solely for SFT can surpass the performance of previous public datasets utilized for both SFT and preference optimization, such as direct preference optimization with UltraFeedback. This advantage is evident on alignment benchmarks such as AlpacaEval, ArenaHard, and WildBench.
+</details><be>
+
+## 📚 Citation
+
+If you find the model, data, or code useful, please cite our paper:
+```
+@article{xu2024magpie,
+	title={Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing}, 
+	author={Zhangchen Xu and Fengqing Jiang and Luyao Niu and Yuntian Deng and Radha Poovendran and Yejin Choi and Bill Yuchen Lin},
+	year={2024},
+	eprint={2406.08464},
+	archivePrefix={arXiv},
+	primaryClass={cs.CL}
+}
+```
+
+Please also cite the creators of preference datasets:
+
+SimPO paper:
+```
+@article{meng2024simpo,
+  title={{SimPO}: Simple preference optimization with a reference-free reward},
+  author={Meng, Yu and Xia, Mengzhou and Chen, Danqi},
+  journal={arXiv preprint arXiv:2405.14734},
+  year={2024}
+}
+```
+
+UltraFeedback paper:
+```
+@article{cui2023ultrafeedback,
+  title={{UltraFeedback}: Boosting language models with high-quality feedback},
+  author={Cui, Ganqu and Yuan, Lifan and Ding, Ning and Yao, Guanming and Zhu, Wei and Ni, Yuan and Xie, Guotong and Liu, Zhiyuan and Sun, Maosong},
+  journal={arXiv preprint arXiv:2310.01377},
+  year={2023}
+}
+```
+
+ArmoRM paper:
+```
+@article{wang2024interpretable,
+  title={Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts},
+  author={Wang, Haoxiang and Xiong, Wei and Xie, Tengyang and Zhao, Han and Zhang, Tong},
+  journal={arXiv preprint arXiv:2406.12845},
+  year={2024}
+}
+```
+
+**Questions?** Please contact [Zhangchen](https://zhangchenxu.com/) by email.