t2ance/mat-01-lr-versus-learning-signal download history

t2ance/mat-01-lr-versus-learning-signal is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 436 times (54 in the last 7 days), and 436 times in total. It ranks #36,874 among datasets by monthly downloads.

01 Learning rate versus the learning signal When the round-best score on a CPU-only Kaggle task stops rising during GRPO training, is the binding constraint the learning rate (too small to move the policy, or too large to keep it stable), or the learning signal itself (what the search

Open t2ance/mat-01-lr-versus-learning-signal on Hugging Face