Compared to v0.1, we enhance its reasoning ability by incorporating a reasoning dataset (150K math, code, and reasoning data). It achieves performance comparable with the official Llama-3-8B-Instruct Model with SFT only! The detailed benchmark performance is as follows:

MT-Bench: 8.350 (1st Turn), 7.700 (Second Turn), 8.025 (Average)
Alpaca Eval 2 (GPT-4-Turbo-1106): 24.89 (LC), 24.63 (WR)
Alpaca Eval 2 (Llama-3-8B-Instruct): 54.70 (LC), 54.73 (WR)
Arena Hard: 19.1

Other Information

License: Please follow Meta Llama 3 Community License.

Conversation Template: Please use Llama 3 official chat template for the best performance.

How to use it? Please check the official Llama 3 repository for detailed instructions. Simply replace the original model_id with Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.2.

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}
}

Questions? Please contact Zhangchen by email.

Paper Abstract

Click Here

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.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 128
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 79
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.8241	0.0024	1	0.8068
0.5623	0.2007	85	0.5087
0.4704	0.4014	170	0.4326
0.4478	0.6020	255	0.4079
0.4256	0.8027	340	0.3948
0.4261	1.0034	425	0.3867
0.3662	1.1844	510	0.3850
0.363	1.3851	595	0.3823
0.357	1.5858	680	0.3813
0.3677	1.7865	765	0.3813

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Internal name for identification: Llama-3-8B-Magpie-Mix-300KMT-150KR. Please change the model name in the below Axolotl config.

See axolotl config

axolotl version: 0.4.1

yaml

base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Magpie-Align/Magpie-Reasoning-150K
    type: sharegpt
    conversation: llama3
  - path: Magpie-Align/Magpie-Pro-MT-300K-v0.1
    type: sharegpt
    conversation: llama3
dataset_prepared_path: last_run_prepared
val_set_size: 0.001
output_dir: axolotl_out/Llama-3-8B-Magpie-Mix-300KMT-150KR

sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project: SynDa
wandb_entity:
wandb_watch:
wandb_name: Llama-3-8B-Magpie-Mix-300KMT-150KR
wandb_log_model:
hub_model_id: Magpie-Align/Llama-3-8B-Magpie-Mix-300KMT-150KR

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 5
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>