hongyi-zhang

Your dataloaders are taking up the bulk of the running time. It's likely that you are not assigning enough CPUs for the workers. Try e.g. at least 32 CPUs for...

Let's say you want to shuffle [1, 2, 3, 4, 5, 6] into [1, 4, 2, 5, 3, 6], just do: torch.Tensor([1, 2, 3, 4, 5, 6]).view(2, 3).permute(1, 0).contiguous().view(6) To...

@PeterSH6 @UbeCc @zhaochenyang20 I'm interested in multi-turn RL as well. We have a real-world use case and I was going to start my own implementation before seeing this thread. Would...