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.

翻译：DARWIN是一种进化型GPT模型，采用类似遗传算法的优化结构，通过独特的训练代码对多个独立的GPT代理进行分别训练。在每次迭代中，GPT模型会以类似突变的方式相互修改训练代码以提升性能，随后通过遗传算法对最佳GPT代理进行基准测试并选择进入下一轮迭代。出于演示目的及预算与时间限制，本研究采用OpenAI API驱动训练代码改进，并以nanoGPT框架作为训练代码基础。DARWIN还利用基于JSON的持久化记忆文件追踪先前的推理过程与代码变更，以关联模型性能的改进；同时构建双向人机交互接口，允许模型请求升级（如额外数据集、训练脚本及文件层级重构）。实验表明，经过5轮训练迭代，DARWIN相较于基线配置实现了1.26%的模型浮点运算利用率（MFU）提升与2.07%的困惑度改善，展现了其作为进化式GPT训练扩展基础框架的潜力。