Spaces:

agentDebugger
/

AgentDebugger-training-v3

Running

App Files Files Community

AgentDebugger-training-v3 / training

Ctrl+K

Ctrl+K

5 contributors

History: 5 commits

shank

Optimize for A100 80GB: 8 generations, batch 4, lr 2e-5, dense logging

2b1fbf3 13 days ago

train_grpo.py

18.2 kB
Optimize for A100 80GB: 8 generations, batch 4, lr 2e-5, dense logging 13 days ago