Files
Qwen2.5-1.5B-GRPO-v5/trainer_state.json

4 lines
133 B
JSON
Raw Normal View History

version https://git-lfs.github.com/spec/v1
oid sha256:2ad828b69e700b6d477dab6db62b78170187cd29f0ee63aca098b3063471bb51
size 18036130