I want a ReporterList(reporters: list) class for training loops that keeps metric state across a sequence…
I want a ReporterList(reporters: list) class for training loops that keeps metric state across a sequence…: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). I want a ReporterList(reporters: list) class for training loops that keeps metric state across a sequence of calls. A…
The task
I want a ReporterList(reporters: list) class for training loops that keeps metric state across a sequence of calls. A typical session should look like r = ReporterList(backends), then for each batch call r.set_batch_size(batch_size) and r.add_value(key, value, is_averaged=True…
Part of XiaomiMiMo/MiMo-V2.6-RL-oss.