iiiiwis/DEMO_Agent

Training procedure

• —totalbatchsize: 32
• —epoch: 3
• —lr: 1.0e-4
• —warm-up rate: 0.1
• —type: Lora

Framework versions

• —LLaMA-Factory: v0.9.0

Paper

• —link: arxiv.org/abs/2412.04905

Data

• —link: https://github.com/MozerWang/DEMO