MNIST CNN from scratch — SGD lr=0.03
Trained for 60s wall clock (batch 128, SGD momentum 0.9, seed 0), reaching step 10484 with final train loss 1.6587353456998244e-05 and test accuracy 0.9909.
Part of a 10-learning-rate sweep. Live curves: https://huggingface.co/spaces/abidlabs/mnist-lr-sweep-trackio
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support