
Loading weights:   0%|          | 0/311 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 311/311 [00:00<00:00, 4881.95it/s]
mlp2 0.0001 step 0 loss 1.2652 exact 32/128 train_s 0
mlp2 0.0001 step 16 loss 0.2687 exact 103/128 train_s 1.86
Saved artifacts/qwen3-06b/2026-09-08-efficiency-replication/mlp2-seed101
