72b全参微调还没有example，现有的在这，https://github.com/modelscope/swift/tree/main/examples/...
QwenLM / Qwen2.5 Public Notifications Fork 598 Star 9.7k Code Issues 53 Pull requests 8 Discussions Actions Projects Security Insights New issue 使用examples 里的sft 代码进行全参数微调,同样的参数、数据集,每次训练的loss不一样,是哪里有随机性吗? #334 Closed zsl2549 opened this ...
QwenLM / Qwen2.5 Public Notifications Fork 642 Star 10.4k Code Issues 57 Pull requests 6 Discussions Actions Projects Security Insights New issue 使用examples 里的sft 代码进行全参数微调,同样的参数、数据集,每次训练的loss不一样,是哪里有随机性吗? #334 Closed zsl2549 opened this ...