HF RL Explorer

When using the ~~--debug option~~ DEBUG environment variable in the sample command, the debug value is not…

When using the ~~--debug option~~ DEBUG environment variable in the sample command, the debug value is not…: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). When using the ~~--debug option~~ DEBUG environment variable in the sample command, the debug value is not correctly…

The task

When using the ~~--debug option~~ DEBUG environment variable in the sample command, the debug value is not correctly set (flag_value). It is expected to be either logging.DEBUG or None, but it seems to be getting the integer value directly from the environment variable. Sample…

Part of XiaomiMiMo/MiMo-V2.6-RL-oss.