HF RL Explorer

DT enabled - Set new default span event limit

DT enabled - Set new default span event limit: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). Set the span event limit to the optimal default value determined by OATS testing. Based on testing, we should set the span event limit to 2000. (double check this value next week…

The task

Set the span event limit to the optimal default value determined by OATS testing. Based on testing, we should set the span event limit to 2000. (double check this value next week 9/7)

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