DARWIN让GPT模型自我改写代码，逐步提升训练效率和性能。
DARWIN: Dynamic Agentically Rewriting Self-Improving Network
- 多GPT代理互改训练代码，模拟进化优化过程。
- 5轮迭代后，模型算力利用率提升1.26%，困惑度降低2.07%。
- 支持人工干预升级，适合研究自进化AI系统者阅读。
DARWIN是一种演化式GPT模型，采用类遗传算法的优化结构，多个独立GPT代理使用各自独特的训练代码进行训练。每轮迭代中，GPT模型被提示修改彼此的训练代码，以类似突变的方式提升性能，随后通过遗传算法评估并选出表现最优的代理进入下一轮。由于预算与时间限制，实验中使用OpenAI API生成代码改进，以nanoGPT框架作为训练代码基础。DARWIN还利用基于JSON的持久化内存文件，记录推理历史与代码变更，以关联性能提升。同时提供双向人机协同接口（HITL），支持模型请求数据集扩展、脚本重构或文件结构调整。在实验中，经过5轮训练，模型的每秒浮点运算利用率（MFU）提升1.26%，困惑度下降2.07%，展现出作为规模化演化GPT训练基础的潜力。
原文摘要 · Abstract (English)
DARWIN is an evolutionary GPT model, utilizing a genetic-algorithm like optimization structure with several independent GPT agents being trained individually using unique training code. Each iteration, the GPT models are prompted to modify the training code of one another in an attempt to improve their performance in a mutation-like manner, and the best GPT agents are then benchmarked and selected for the next iteration by genetic algorithm. For demonstration purposes and due to budget and time constraints, OpenAI API is used to prompt training code improvements and the nanoGPT framework is used as the training code. DARWIN also utilizes persistent JSON-based memory files to track previous reasoning and changes to code to correlate with improvement to model performance. and a bidirectional interface for HITL intervention allowing the model to request upgrades such as additional datasets, training scripts, and restructuring of file hierarchies. In experiments, DARWIN achieved a 1.26 percent improvement in model FLOPS utilization (MFU) and a 2.07 percent improvement to perplexity in 5 iterations of training over baseline configurations, demonstrating promising capabilities as a foundation for scaling evolutionary GPT training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。