apollo-research/rl-dynamics-gradient-sketches-toy-adam5e5 download history

apollo-research/rl-dynamics-gradient-sketches-toy-adam5e5 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 7,029 times (6,621 in the last 7 days), and 7,029 times in total. It ranks #4,243 among datasets by monthly downloads.

Gradient sketches of a toy RL run (Adam, lr 5e-5, rep 3) Random-projection sketches of per-rollout policy gradients from a small GRPO run in Apollo Research's RL-dynamics project (base model Qwen/Qwen3.5-4B with LoRA adapters, 129,859,584 trainable parameters, 20 training steps, 1,024

Spaces using rl-dynamics-gradient-sketches-toy-adam5e5

Open apollo-research/rl-dynamics-gradient-sketches-toy-adam5e5 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.