Resuming training is broken, and the default dtype won't even let me construct a config
Resuming training is broken, and the default dtype won't even let me construct a config: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). Resuming training is broken, and the default dtype won't even let me construct a config I'm trying to spin up an SAE training run with…
The task
Resuming training is broken, and the default dtype won't even let me construct a config I'm trying to spin up an SAE training run with SAELens for the first time and ran into two issues that look like bugs. 1. Default LanguageModelSAERunnerConfig() doesn't construct Minimal…
Part of XiaomiMiMo/MiMo-V2.6-RL-oss.