Allenda/ScaleSeek-GRPOv3-fsdp-state

ScaleSeek-GRPOv3-fsdp-state: ScaleSeek GRPOv3 FSDP training state: RL dataset on Hugging Face. verl FSDP shards for the v3.1 GRPO run, steps 160 and 300, carrying the AdamW moments and dataloader position that merged HF weights do not. Shards are written per world size, so they load only on 4…